Original Ghostbuster Dan Aykroyd, who also co-wrote the 1984 Ghostbusters film, couldn’t be more pleased with the new all-female Ghostbusters cast, telling The Hollywood Reporter, “The Aykroyd family is delighted by this inheritance of the Ghostbusters torch by these most magnificent women in comedy.”
" f.write(message) f.seek(0) # Create an API instance api = API(user_key=key, service_url=altUrl) params = DocumentParameters() # Use an HTML file to load data instead of a string params.load_document_file(f.name) result = api.sentiment(params) # Clean up the file f.close() return result parser = argparse.ArgumentParser(formatter_class=argparse.ArgumentDefaultsHelpFormatter, description='Calls the ' + os.path.splitext(os.path.basename(__file__))[0] + ' endpoint') parser.add_argument('-k', '--key', help='Rosette API Key', required=True) parser.add_argument('-u', '--url', help="Alternative API URL", default='https://api.rosette.com/rest/v1/') if __name__ == '__main__': args = parser.parse_args() result = run(args.key, args.url) print(json.dumps(result, indent=2, ensure_ascii=False, sort_keys=True).encode("utf8")) python-0.7.4/examples/tokens.py 0000664 0000000 0000000 00000002002 12636317025 0016535 0 ustar 00root root 0000000 0000000 # -*- coding: utf-8 -*- """ Example code to call Rosette API to get the tokens (words) in a piece of text. """ import argparse import json import os from rosette.api import API, DocumentParameters def run(key, altUrl='https://api.rosette.com/rest/v1/'): # Create an API instance api = API(user_key=key, service_url=altUrl) params = DocumentParameters() params["content"] = u"北京大学生物系主任办公室内部会议" return api.tokens(params) parser = argparse.ArgumentParser(formatter_class=argparse.ArgumentDefaultsHelpFormatter, description='Calls the ' + os.path.splitext(os.path.basename(__file__))[0] + ' endpoint') parser.add_argument('-k', '--key', help='Rosette API Key', required=True) parser.add_argument('-u', '--url', help="Alternative API URL", default='https://api.rosette.com/rest/v1/') if __name__ == '__main__': args = parser.parse_args() result = run(args.key, args.url) print(json.dumps(result, indent=2, ensure_ascii=False, sort_keys=True).encode("utf8")) python-0.7.4/examples/translated-name.py 0000664 0000000 0000000 00000002143 12636317025 0020317 0 ustar 00root root 0000000 0000000 # -*- coding: utf-8 -*- """ Example code to call Rosette API to translate a name from one language to another. """ import argparse import json import os from rosette.api import API, NameTranslationParameters def run(key, altUrl='https://api.rosette.com/rest/v1/'): # Create an API instance api = API(user_key=key, service_url=altUrl) params = NameTranslationParameters() params["name"] = u"معمر محمد أبو منيار القذاف" params["entityType"] = "PERSON" params["targetLanguage"] = "eng" return api.translated_name(params) parser = argparse.ArgumentParser(formatter_class=argparse.ArgumentDefaultsHelpFormatter, description='Calls the ' + os.path.splitext(os.path.basename(__file__))[0] + ' endpoint') parser.add_argument('-k', '--key', help='Rosette API Key', required=True) parser.add_argument('-u', '--url', help="Alternative API URL", default='https://api.rosette.com/rest/v1/') if __name__ == '__main__': args = parser.parse_args() result = run(args.key, args.url) print(json.dumps(result, indent=2, ensure_ascii=False, sort_keys=True).encode("utf8")) python-0.7.4/pytest.ini 0000664 0000000 0000000 00000000076 12636317025 0015104 0 ustar 00root root 0000000 0000000 [pytest] pep8ignore = E501 norecursedirs = .tox target python-0.7.4/rosette/ 0000775 0000000 0000000 00000000000 12636317025 0014535 5 ustar 00root root 0000000 0000000 python-0.7.4/rosette/__init__.py 0000664 0000000 0000000 00000001202 12636317025 0016641 0 ustar 00root root 0000000 0000000 """ Python client for the Rosette API. Copyright (c) 2014-2015 Basis Technology Corporation. Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with the License. You may obtain a copy of the License at http://www.apache.org/licenses/LICENSE-2.0 Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions and limitations under the License. """ __version__ = '0.7.4' python-0.7.4/rosette/api.py 0000664 0000000 0000000 00000076671 12636317025 0015701 0 ustar 00root root 0000000 0000000 #!/usr/bin/env python """ Python client for the Rosette API. Copyright (c) 2014-2015 Basis Technology Corporation. Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with the License. You may obtain a copy of the License at http://www.apache.org/licenses/LICENSE-2.0 Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions and limitations under the License. """ from io import BytesIO import base64 import gzip import json import logging import sys import time import os from socket import gethostbyname, gaierror from datetime import datetime _BINDING_VERSION = "0.7" _GZIP_BYTEARRAY = bytearray([0x1F, 0x8b, 0x08]) N_RETRIES = 3 HTTP_CONNECTION = None REUSE_CONNECTION = True CONNECTION_TYPE = "" CONNECTION_START = datetime.now() CONNECTION_REFRESH_DURATION = 86400 N_RETRIES = 3 _IsPy3 = sys.version_info[0] == 3 try: import urlparse import urllib except ImportError: import urllib.parse as urlparse import urllib.parse as urllib try: import httplib except ImportError: import http.client as httplib if _IsPy3: _GZIP_SIGNATURE = _GZIP_BYTEARRAY else: _GZIP_SIGNATURE = str(_GZIP_BYTEARRAY) class _ReturnObject: def __init__(self, js, code): self._json = js self.status_code = code def json(self): return self._json def _my_loads(obj): if _IsPy3: return json.loads(obj.decode("utf-8")) # if py3, need chars. else: return json.loads(obj) def _retrying_request(op, url, data, headers): global HTTP_CONNECTION global REUSE_CONNECTION global CONNECTION_TYPE global CONNECTION_START global CONNECTION_REFRESH_DURATION headers['User-Agent'] = "RosetteAPIPython/" + _BINDING_VERSION timeDelta = datetime.now() - CONNECTION_START totalTime = timeDelta.days * 86400 + timeDelta.seconds parsed = urlparse.urlparse(url) if parsed.scheme != CONNECTION_TYPE: totalTime = CONNECTION_REFRESH_DURATION if not REUSE_CONNECTION or HTTP_CONNECTION is None or totalTime >= CONNECTION_REFRESH_DURATION: parsed = urlparse.urlparse(url) loc = parsed.netloc CONNECTION_TYPE = parsed.scheme CONNECTION_START = datetime.now() if parsed.scheme == "https": HTTP_CONNECTION = httplib.HTTPSConnection(loc) else: HTTP_CONNECTION = httplib.HTTPConnection(loc) message = None code = "unknownError" rdata = None for i in range(N_RETRIES + 1): # Try to connect with the Rosette API server # 500 errors will store a message and code try: HTTP_CONNECTION.request(op, url, data, headers) response = HTTP_CONNECTION.getresponse() status = response.status rdata = response.read() if status < 500: if not REUSE_CONNECTION: HTTP_CONNECTION.close() return rdata, status if rdata is not None: try: the_json = _my_loads(rdata) if "message" in the_json: message = the_json["message"] if "code" in the_json: code = the_json["code"] except: pass # If there are issues connecting to the API server, # try to regenerate the connection as long as there are # still retries left. # A short sleep delay occurs (similar to google reconnect) # if the problem was a temporal one. except (httplib.BadStatusLine, gaierror) as e: totalTime = CONNECTION_REFRESH_DURATION if i == N_RETRIES - 1: raise RosetteException("ConnectionError", "Unable to establish connection to the Rosette API server", url) else: if not REUSE_CONNECTION or HTTP_CONNECTION is None or totalTime >= CONNECTION_REFRESH_DURATION: time.sleep(min(5 * (i + 1) * (i + 1), 300)) parsed = urlparse.urlparse(url) loc = parsed.netloc CONNECTION_TYPE = parsed.scheme CONNECTION_START = datetime.now() if parsed.scheme == "https": HTTP_CONNECTION = httplib.HTTPSConnection(loc) else: HTTP_CONNECTION = httplib.HTTPConnection(loc) # Do not wait to retry -- the model is that a bunch of dynamically-routed # resources has failed -- Retry means some other set of servelets and their # underlings will be called up, and maybe they'll do better. # This will not help with a persistent or impassible delay situation, # but the former case is thought to be more likely. if not REUSE_CONNECTION: HTTP_CONNECTION.close() if message is None: message = "A retryable network operation has not succeeded after " + str(N_RETRIES) + " attempts" raise RosetteException(code, message, url) def _get_http(url, headers): (rdata, status) = _retrying_request("GET", url, None, headers) return _ReturnObject(_my_loads(rdata), status) def _post_http(url, data, headers): if data is None: json_data = "" else: json_data = json.dumps(data) (rdata, status) = _retrying_request("POST", url, json_data, headers) if len(rdata) > 3 and rdata[0:3] == _GZIP_SIGNATURE: buf = BytesIO(rdata) rdata = gzip.GzipFile(fileobj=buf).read() return _ReturnObject(_my_loads(rdata), status) def add_query(orig_url, key, value): parts = urlparse.urlsplit(orig_url) queries = urlparse.parse_qsl(parts[3]) queries.append((key, value)) qs = urllib.urlencode(queries) return urlparse.urlunsplit((parts[0], parts[1], parts[2], qs, parts[4])) class RosetteException(Exception): """Exception thrown by all Rosette API operations for errors local and remote. TBD. Right now, the only valid operation is conversion to __str__. """ def __init__(self, status, message, response_message): self.status = status self.message = message self.response_message = response_message def __str__(self): sst = self.status if not (isinstance(sst, str)): sst = repr(sst) return sst + ": " + self.message + ":\n " + self.response_message class _PseudoEnum: def __init__(self): pass @classmethod def validate(cls, value, name): values = [] for (k, v) in vars(cls).items(): if not k.startswith("__"): values += [v] # this is still needed to make sure that the parameter NAMES are known. # If python didn't allow setting unknown values, this would be a language error. if value not in values: raise RosetteException("unknownVariable", "The value supplied for " + name + " is not one of " + ", ".join(values) + ".", repr(value)) class DataFormat(_PseudoEnum): """Data Format, as much as it is known.""" SIMPLE = "text/plain" """The data is unstructured text, supplied as a possibly-unicode string.""" JSON = "application/json" """To be supplied. The API uses JSON internally, but that is not what this refers to.""" HTML = "text/html" """The data is a 'loose' HTML page; that is, it may not be HTML-compliant, or may even not really be HTML. The data must be a narrow (single-byte) string, not a python Unicode string, perhaps read from a file. (Of course, it can be UTF-8 encoded).""" XHTML = "application/xhtml+xml" """The data is a compliant XHTML page. The data must be a narrow (single-byte) string, not a python Unicode string, perhaps read from a file. (Of course, it can be UTF-8 encoded).""" UNSPECIFIED = "application/octet-stream" """The data is of unknown format, it may be a binary data type (the contents of a binary file), or may not. It will be sent as is and identified and analyzed by the server.""" class InputUnit(_PseudoEnum): """Elements are used in the L{DocumentParameters} class to specify whether textual data is to be treated as one sentence or possibly many.""" DOC = "doc" """The data is a whole document; it may or may not contain multiple sentences.""" SENTENCE = "sentence" """The data is a single sentence.""" class MorphologyOutput(_PseudoEnum): LEMMAS = "lemmas" PARTS_OF_SPEECH = "parts-of-speech" COMPOUND_COMPONENTS = "compound-components" HAN_READINGS = "han-readings" COMPLETE = "complete" class _DocumentParamSetBase(object): def __init__(self, repertoire): self.__params = {} for k in repertoire: self.__params[k] = None def __setitem__(self, key, val): if key not in self.__params: raise RosetteException("badKey", "Unknown Rosette parameter key", repr(key)) self.__params[key] = val def __getitem__(self, key): if key not in self.__params: raise RosetteException("badKey", "Unknown Rosette parameter key", repr(key)) return self.__params[key] def validate(self): pass def serialize(self): self.validate() v = {} for (key, val) in self.__params.items(): if val is None: pass else: v[key] = val return v def _byteify(s): # py 3 only l = len(s) b = bytearray(l) for ix in range(l): oc = ord(s[ix]) assert (oc < 256) b[ix] = oc return b class DocumentParameters(_DocumentParamSetBase): """Parameter object for all operations requiring input other than translated_name. Four fields, C{content}, C{contentType}, C{unit}, and C{inputUri}, are set via the subscript operator, e.g., C{params["content"]}, or the convenience instance methods L{DocumentParameters.load_document_file} and L{DocumentParameters.load_document_string}. The unit size and data format are defaulted to L{InputUnit.DOC} and L{DataFormat.SIMPLE}. Using subscripts instead of instance variables facilitates diagnosis. If the field C{contentUri} is set to the URL of a web page (only protocols C{http, https, ftp, ftps} are accepted), the server will fetch the content from that web page. In this case, neither C{content} nor C{contentType} may be set. """ def __init__(self): """Create a L{DocumentParameters} object. Default data format is L{DataFormat.SIMPLE}, unit is L{InputUnit.DOC}.""" _DocumentParamSetBase.__init__(self, ("content", "contentUri", "contentType", "unit", "language")) self["unit"] = InputUnit.DOC # default def validate(self): """Internal. Do not use.""" if self["content"] is None: if self["contentUri"] is None: raise RosetteException("badArgument", "Must supply one of Content or ContentUri", "bad arguments") else: # self["content"] not None if self["contentUri"] is not None: raise RosetteException("badArgument", "Cannot supply both Content and ContentUri", "bad arguments") def serialize(self): """Internal. Do not use.""" self.validate() slz = super(DocumentParameters, self).serialize() if self["contentType"] is None and self["contentUri"] is None: slz["contentType"] = DataFormat.SIMPLE elif self["contentType"] in (DataFormat.HTML, DataFormat.XHTML, DataFormat.UNSPECIFIED): content = slz["content"] if _IsPy3 and isinstance(content, str): content = _byteify(content) encoded = base64.b64encode(content) if _IsPy3: encoded = encoded.decode("utf-8") # if py3, need chars. slz["content"] = encoded return slz def load_document_file(self, path, data_type=DataFormat.UNSPECIFIED): """Loads a file into the object. The file will be read as bytes; the appropriate conversion will be determined by the server. The document unit size remains by default L{InputUnit.DOC}. @parameter path: Pathname of a file acceptable to the C{open} function. @parameter data_type: One of L{DataFormat.HTML}, L{DataFormat.XHTML}, or L{DataFormat.UNSPECIFIED}. No other types are acceptable at this time, although HTML is broad enough to include text strings without markup. If the data type is unknown, or describes a binary file, use the default (L{DataFormat.UNSPECIFIED}). @type data_type: L{DataFormat} """ if data_type not in (DataFormat.HTML, DataFormat.XHTML, DataFormat.UNSPECIFIED): raise RosetteException("badArgument", "Must supply one of HTML, XHTML, or UNSPECIFIED", data_type) self.load_document_string(open(path, "rb").read(), data_type) def load_document_string(self, s, data_type): """Loads a string into the object. The string will be taken as bytes or as Unicode dependent upon its native python type and the data type asked for; if the type is HTML or XHTML, bytes, not python Unicode, are expected, the encoding to be determined by the server. The document unit size remains (by default) L{InputUnit.DOC}. @parameter s: A string, possibly a unicode-string, to be loaded for subsequent analysis, as per the C{data_type}. @parameter data_type: The data type of the string, as per L{DataFormat}. @type data_type: L{DataFormat} """ self["content"] = s self["contentType"] = data_type self["unit"] = InputUnit.DOC class RelationshipsParameters(DocumentParameters): """Parameter object for relationships endpoint. Inherits from L(DocumentParameters), but allows the user to specify the relationships-unique options parameter.""" def __init__(self): """Create a L{RelationshipsParameters} object. Default data format is L{DataFormat.SIMPLE}, unit is L{InputUnit.DOC}.""" _DocumentParamSetBase.__init__(self, ("content", "contentUri", "contentType", "unit", "language", "options")) self["unit"] = InputUnit.DOC # default class NameTranslationParameters(_DocumentParamSetBase): """Parameter object for C{translated_name} endpoint. The following values may be set by the indexing (i.e.,C{ parms["name"]}) operator. The values are all strings (when not C{None}). All are optional except C{name} and C{targetLanguage}. Scripts are in ISO15924 codes, and languages in ISO639 (two- or three-letter) codes. See the Name Translation documentation for more description of these terms, as well as the content of the return result. C{name} The name to be translated. C{targetLangauge} The language into which the name is to be translated. C{entityType} The entity type (TBD) of the name. C{sourceLanguageOfOrigin} The language of origin of the name. C{sourceLanguageOfUse} The language of use of the name. C{sourceScript} The script in which the name is supplied. C{targetScript} The script into which the name should be translated. C{targetScheme} The transliteration scheme by which the translated name should be rendered. """ def __init__(self): _DocumentParamSetBase.__init__(self, ("name", "targetLanguage", "entityType", "sourceLanguageOfOrigin", "sourceLanguageOfUse", "sourceScript", "targetScript", "targetScheme")) def validate(self): """Internal. Do not use.""" for n in ("name", "targetLanguage"): # required if self[n] is None: raise RosetteException("missingParameter", "Required Name Translation parameter not supplied", repr(n)) class NameMatchingParameters(_DocumentParamSetBase): """Parameter object for C{matched_name} endpoint. All are required. C{name1} The name to be matched, a C{name} object. C{name2} The name to be matched, a C{name} object. The C{name} object contains these fields: C{text} Text of the name, required. C{language} Language of the name in ISO639 three-letter code, optional. C{script} The ISO15924 code of the name, optional. C{entityType} The entity type, can be "PERSON", "LOCATION" or "ORGANIZATION", optional. """ def __init__(self): _DocumentParamSetBase.__init__(self, ("name1", "name2")) def validate(self): """Internal. Do not use.""" for n in ("name1", "name2"): # required if self[n] is None: raise RosetteException("missingParameter", "Required Name Matching parameter not supplied", repr(n)) class EndpointCaller: """L{EndpointCaller} objects are invoked via their instance methods to obtain results from the Rosette server described by the L{API} object from which they are created. Each L{EndpointCaller} object communicates with a specific endpoint of the Rosette server, specified at its creation. Use the specific instance methods of the L{API} object to create L{EndpointCaller} objects bound to corresponding endpoints. Use L{EndpointCaller.ping} to ping, and L{EndpointCaller.info} to retrieve server info. For all other types of requests, use L{EndpointCaller.call}, which accepts an argument specifying the data to be processed and certain metadata. The results of all operations are returned as python dictionaries, whose keys and values correspond exactly to those of the corresponding JSON return value described in the Rosette web service documentation. """ def __init__(self, api, suburl): """This method should not be invoked by the user. Creation is reserved for internal use by API objects.""" self.service_url = api.service_url self.user_key = api.user_key self.logger = api.logger self.useMultipart = api.useMultipart self.checker = lambda: api.check_version() self.suburl = suburl self.debug = api.debug def __finish_result(self, r, ename): code = r.status_code the_json = r.json() if code == 200: return the_json else: if 'message' in the_json: msg = the_json['message'] else: msg = the_json['code'] # punt if can't get real message if self.suburl is None: complaint_url = "Top level info" else: complaint_url = ename + " " + self.suburl if "code" in the_json: server_code = the_json["code"] else: server_code = "unknownError" raise RosetteException(server_code, complaint_url + " : failed to communicate with Rosette", msg) def _set_use_multipart(self, value): self.useMultipart = value def info(self): """Issues an "info" request to the L{EndpointCaller}'s specific endpoint. @return: A dictionary telling server version and other identifying data.""" url = self.service_url + "info" if self.debug: url = add_query(url, "debug", "true") self.logger.info('info: ' + url) headers = {'Accept': 'application/json'} if self.user_key is not None: headers["user_key"] = self.user_key r = _get_http(url, headers=headers) return self.__finish_result(r, "info") def checkVersion(self): """Issues a special "info" request to the L{EndpointCaller}'s specific endpoint. @return: A dictionary containing server version as well as version check""" url = self.service_url + "info?clientVersion=" + _BINDING_VERSION if self.debug: url = add_query(url, "debug", "true") self.logger.info('info: ' + url) headers = {'Accept': 'application/json'} if self.user_key is not None: headers["user_key"] = self.user_key r = _post_http(url, None, headers=headers) return self.__finish_result(r, "info") def ping(self): """Issues a "ping" request to the L{EndpointCaller}'s (server-wide) endpoint. @return: A dictionary if OK. If the server cannot be reached, or is not the right server or some other error occurs, it will be signalled.""" url = self.service_url + 'ping' if self.debug: url = add_query(url, "debug", "true") self.logger.info('Ping: ' + url) headers = {'Accept': 'application/json'} if self.user_key is not None: headers["user_key"] = self.user_key r = _get_http(url, headers=headers) return self.__finish_result(r, "ping") def call(self, parameters): """Invokes the endpoint to which this L{EndpointCaller} is bound. Passes data and metadata specified by C{parameters} to the server endpoint to which this L{EndpointCaller} object is bound. For all endpoints except C{translated_name} and C{matched_name}, it must be a L{DocumentParameters} object or a string; for C{translated_name}, it must be an L{NameTranslationParameters} object; for C{matched_name}, it must be an L{NameMatchingParameters} object. For relationships, it may be an L(DocumentParameters) or an L(RelationshipsParameters). In all cases, the result is returned as a python dictionary conforming to the JSON object described in the endpoint's entry in the Rosette web service documentation. @param parameters: An object specifying the data, and possible metadata, to be processed by the endpoint. See the details for those object types. @type parameters: For C{translated_name}, L{NameTranslationParameters}, otherwise L{DocumentParameters} or L{str} @return: A python dictionary expressing the result of the invocation. """ if not isinstance(parameters, _DocumentParamSetBase): if self.suburl != "matched-name" and self.suburl != "translated-name": text = parameters parameters = DocumentParameters() parameters['content'] = text else: raise RosetteException("incompatible", "Text-only input only works for DocumentParameter endpoints", self.suburl) self.checker() if self.useMultipart and (parameters['contentType'] != DataFormat.SIMPLE): raise RosetteException("incompatible", "Multipart requires contentType SIMPLE", repr(parameters['contentType'])) url = self.service_url + self.suburl if self.debug: url = add_query(url, "debug", "true") self.logger.info('operate: ' + url) params_to_serialize = parameters.serialize() headers = {'Accept': "application/json", 'Accept-Encoding': "gzip"} if self.user_key is not None: headers["user_key"] = self.user_key headers['Content-Type'] = "application/json" r = _post_http(url, params_to_serialize, headers) # pprint.pprint(headers) # pprint.pprint(url) # pprint.pprint(params_to_serialize) return self.__finish_result(r, "operate") class API: """ Rosette Python Client Binding API; representation of a Rosette server. Call instance methods upon this object to obtain L{EndpointCaller} objects which can communicate with particular Rosette server endpoints. """ def __init__(self, user_key=None, service_url='https://api.rosette.com/rest/v1/', retries=3, reuse_connection=True, refresh_duration=86400, debug=False): """ Create an L{API} object. @param user_key: (Optional; required for servers requiring authentication.) An authentication string to be sent as user_key with all requests. The default Rosette server requires authentication. to the server. """ # logging.basicConfig(filename="binding.log", filemode="w", level=logging.DEBUG) self.user_key = user_key self.service_url = service_url if service_url.endswith('/') else service_url + '/' self.logger = logging.getLogger('rosette.api') self.logger.info('Initialized on ' + self.service_url) self.debug = debug self.useMultipart = False self.version_checked = False global N_RETRIES global REUSE_CONNECTION global CONNECTION_REFRESH_DURATION if (retries < 1): retries = 1 if (refresh_duration < 60): refresh_duration = 60 N_RETRIES = retries REUSE_CONNECTION = reuse_connection CONNECTION_REFRESH_DURATION = refresh_duration def check_version(self): if self.version_checked: return True op = EndpointCaller(self, None) result = op.checkVersion() version = ".".join(result["version"].split(".")[0:2]) if result['versionChecked'] is False: raise RosetteException("incompatibleVersion", "The server version is not compatible with binding version " + _BINDING_VERSION, version) self.version_checked = True return True def _set_use_multipart(self, value): self.useMultipart = value def ping(self): """ Create a ping L{EndpointCaller} for the server and ping it. @return: A python dictionary including the ping message of the L{API} """ return EndpointCaller(self, None).ping() def info(self): """ Create a ping L{EndpointCaller} for the server and ping it. @return: A python dictionary including the ping message of the L{API} """ return EndpointCaller(self, None).info() def language(self, parameters): """ Create an L{EndpointCaller} for language identification and call it. @param parameters: An object specifying the data, and possible metadata, to be processed by the language identifier. @type parameters: L{DocumentParameters} or L{str} @return: A python dictionary containing the results of language identification.""" return EndpointCaller(self, "language").call(parameters) def sentences(self, parameters): """ Create an L{EndpointCaller} to break a text into sentences and call it. @param parameters: An object specifying the data, and possible metadata, to be processed by the sentence identifier. @type parameters: L{DocumentParameters} or L{str} @return: A python dictionary containing the results of sentence identification.""" return EndpointCaller(self, "sentences").call(parameters) def tokens(self, parameters): """ Create an L{EndpointCaller} to break a text into tokens and call it. @param parameters: An object specifying the data, and possible metadata, to be processed by the tokens identifier. @type parameters: L{DocumentParameters} or L{str} @return: A python dictionary containing the results of tokenization.""" return EndpointCaller(self, "tokens").call(parameters) def morphology(self, parameters, facet=MorphologyOutput.COMPLETE): """ Create an L{EndpointCaller} to returns a specific facet of the morphological analyses of texts to which it is applied and call it. @param parameters: An object specifying the data, and possible metadata, to be processed by the morphology analyzer. @type parameters: L{DocumentParameters} or L{str} @param facet: The facet desired, to be returned by the created L{EndpointCaller}. @type facet: An element of L{MorphologyOutput}. @return: A python dictionary containing the results of morphological analysis.""" return EndpointCaller(self, "morphology/" + facet).call(parameters) def entities(self, parameters, linked=False): """ Create an L{EndpointCaller} to identify named entities found in the texts to which it is applied and call it. Linked entity information is optional, and its need must be specified at the time the operator is created. @param parameters: An object specifying the data, and possible metadata, to be processed by the entity identifier. @type parameters: L{DocumentParameters} or L{str} @param linked: Specifies whether or not linked entity information will be wanted. @type linked: Boolean @return: A python dictionary containing the results of entity extraction.""" if linked: return EndpointCaller(self, "entities/linked").call(parameters) else: return EndpointCaller(self, "entities").call(parameters) def categories(self, parameters): """ Create an L{EndpointCaller} to identify the category of the text to which it is applied and call it. @param parameters: An object specifying the data, and possible metadata, to be processed by the category identifier. @type parameters: L{DocumentParameters} or L{str} @return: A python dictionary containing the results of categorization.""" return EndpointCaller(self, "categories").call(parameters) def sentiment(self, parameters): """ Create an L{EndpointCaller} to identify the sentiment of the text to which it is applied and call it. @param parameters: An object specifying the data, and possible metadata, to be processed by the sentiment identifier. @type parameters: L{DocumentParameters} or L{str} @return: A python dictionary containing the results of sentiment identification.""" """Create an L{EndpointCaller} to identify sentiments of the texts to which is applied. @return: An L{EndpointCaller} object which can return sentiments of texts to which it is applied.""" return EndpointCaller(self, "sentiment").call(parameters) def relationships(self, parameters): """ Create an L{EndpointCaller} to identify the relationships between entities in the text to which it is applied and call it. @param parameters: An object specifying the data, and possible metadata, to be processed by the relationships identifier. @type parameters: L{DocumentParameters}, L(RelationshipsParameters), or L{str} @return: A python dictionary containing the results of relationship extraction.""" return EndpointCaller(self, "relationships").call(parameters) def translated_name(self, parameters): """ Create an L{EndpointCaller} to perform name analysis and translation upon the name to which it is applied and call it. @param parameters: An object specifying the data, and possible metadata, to be processed by the name translator. @type parameters: L{NameTranslationParameters} @return: A python dictionary containing the results of name translation.""" return EndpointCaller(self, "translated-name").call(parameters) def matched_name(self, parameters): """ Create an L{EndpointCaller} to perform name matching and call it. @param parameters: An object specifying the data, and possible metadata, to be processed by the name matcher. @type parameters: L{NameMatchingParameters} @return: A python dictionary containing the results of name matching.""" return EndpointCaller(self, "matched-name").call(parameters) python-0.7.4/setup.py 0000775 0000000 0000000 00000002547 12636317025 0014575 0 ustar 00root root 0000000 0000000 #!/usr/bin/env python from setuptools import setup import rosette import os import io NAME = "rosette_api" DESCRIPTION = "Rosette API Python client SDK" AUTHOR = "Basis Technology Corp." AUTHOR_EMAIL = "rosette_api@basistech.com" HOMEPAGE = "https://developer.rosette.com" VERSION = rosette.__version__ here = os.path.abspath(os.path.dirname(__file__)) def read(*filenames, **kwargs): encoding = kwargs.get('encoding', 'utf-8') sep = kwargs.get('sep', '\n') buf = [] for filename in filenames: with io.open(filename, encoding=encoding) as f: buf.append(f.read()) return sep.join(buf) long_description = read('README.md', 'CHANGES.txt') setup(name=NAME, author=AUTHOR, author_email=AUTHOR_EMAIL, description=DESCRIPTION, license='Apache License', long_description=long_description, packages=['rosette'], platforms='any', url=HOMEPAGE, version=VERSION, classifiers=[ 'Programming Language :: Python', 'Development Status :: 4 - Beta', 'Natural Language :: English', 'Environment :: Web Environment', 'Intended Audience :: Developers', 'License :: OSI Approved :: Apache Software License', 'Operating System :: OS Independent', 'Topic :: Software Development :: Libraries :: Python Modules'] ) python-0.7.4/tests/ 0000775 0000000 0000000 00000000000 12636317025 0014212 5 ustar 00root root 0000000 0000000 python-0.7.4/tests/__init__.py 0000664 0000000 0000000 00000001164 12636317025 0016325 0 ustar 00root root 0000000 0000000 # -*- coding: utf-8 -*- """ Copyright (c) 2014-2015 Basis Technology Corporation. Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with the License. You may obtain a copy of the License at http://www.apache.org/licenses/LICENSE-2.0 Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions and limitations under the License. """ # blank __init__.py python-0.7.4/tests/mock-data/ 0000775 0000000 0000000 00000000000 12636317025 0016052 5 ustar 00root root 0000000 0000000 python-0.7.4/tests/mock-data/request/ 0000775 0000000 0000000 00000000000 12636317025 0017542 5 ustar 00root root 0000000 0000000 python-0.7.4/tests/mock-data/request/ara-doc-categories.json 0000664 0000000 0000000 00000005076 12636317025 0024076 0 ustar 00root root 0000000 0000000 { "content": "الخميس 5/2/1431 هـ - الموافق 21/1/2010 م (آخر تحديث) الساعة 10:01 (مكة المكرمة)، 7:01 (غرينتش)\n\nناتو يفكر بمسؤول مدني لأفغانستان\n\nيخطط حلف شمال الأطلسي (ناتو) لتعيين مسؤول مدني كبير في أفغانستان، وسط دعوات لتحسين التنسيق السياسي والتنموي في البلاد وفق ما نقلته صحيفة وول ستريت. وقالت الصحيفة إن السفير البريطاني في كابل في مقدمة المرشحين لهذا المنصب والذي من المحتمل أن يعلن بالتزامن مع مؤتمر دولي عن مستقبل أفغانستان المقرر عقده في لندن في 28 يناير/كانون الثاني المقبل.\n وأضافت الصحيفة -في تقرير لها من كابل- أن المسؤول الجديد سيترأس دعامة مدنية للتحالف الذي تقوده الولايات المتحدة لإدارة التمويل والمساعدات للولايات الأفغانية لتحاشي المؤسسات الأفغانية الفاسدة\". وكان الأمين العام للأمم المتحدة بان كي مون دعا هذا الشهر لتعيين مسؤول مدني رفيع ضمن قوة المساعدة الدولية لإرساء الأمن في أفغانستان (إيساف) التي يقودها حلف الأطلسي للمساعدة في تنسيق الجهود السياسية والتنموية في الحرب التي دخلت عامها التاسع. وأضاف أن تعيين هذا المسؤول سيتيح تحسين التنسيق بين العمل السياسي والتنموي وخصوصا عبر فرق إعادة البناء في الولايات الأفغانية. وقالت جورنال ستريت إن المنصب الجديد سيكون نظيرا للأميركي ستانلي ماكريستال قائد القوات الأميركية وقوات حلف الأطلسي في أفغانستان. ويتوقع وصول أربعين ألف جندي آخرين لأفغانستان في الأشهر القليلة المقبلة في إطار إستراتيجية لمجابهة العمليات المسلحة لحركة طالبان. وأشارت الصحيفة إلى أن خطة تعيين السفير البريطاني مارك سيدويل وجدت تأييد الولايات المتحدة ومن المرجح أن يصادق عليها باقي الحلفاء.", "language": "ara", "unit": "doc" } python-0.7.4/tests/mock-data/request/ara-doc-entities.json 0000664 0000000 0000000 00000005076 12636317025 0023575 0 ustar 00root root 0000000 0000000 { "content": "الخميس 5/2/1431 هـ - الموافق 21/1/2010 م (آخر تحديث) الساعة 10:01 (مكة المكرمة)، 7:01 (غرينتش)\n\nناتو يفكر بمسؤول مدني لأفغانستان\n\nيخطط حلف شمال الأطلسي (ناتو) لتعيين مسؤول مدني كبير في أفغانستان، وسط دعوات لتحسين التنسيق السياسي والتنموي في البلاد وفق ما نقلته صحيفة وول ستريت. وقالت الصحيفة إن السفير البريطاني في كابل في مقدمة المرشحين لهذا المنصب والذي من المحتمل أن يعلن بالتزامن مع مؤتمر دولي عن مستقبل أفغانستان المقرر عقده في لندن في 28 يناير/كانون الثاني المقبل.\n وأضافت الصحيفة -في تقرير لها من كابل- أن المسؤول الجديد سيترأس دعامة مدنية للتحالف الذي تقوده الولايات المتحدة لإدارة التمويل والمساعدات للولايات الأفغانية لتحاشي المؤسسات الأفغانية الفاسدة\". وكان الأمين العام للأمم المتحدة بان كي مون دعا هذا الشهر لتعيين مسؤول مدني رفيع ضمن قوة المساعدة الدولية لإرساء الأمن في أفغانستان (إيساف) التي يقودها حلف الأطلسي للمساعدة في تنسيق الجهود السياسية والتنموية في الحرب التي دخلت عامها التاسع. وأضاف أن تعيين هذا المسؤول سيتيح تحسين التنسيق بين العمل السياسي والتنموي وخصوصا عبر فرق إعادة البناء في الولايات الأفغانية. وقالت جورنال ستريت إن المنصب الجديد سيكون نظيرا للأميركي ستانلي ماكريستال قائد القوات الأميركية وقوات حلف الأطلسي في أفغانستان. ويتوقع وصول أربعين ألف جندي آخرين لأفغانستان في الأشهر القليلة المقبلة في إطار إستراتيجية لمجابهة العمليات المسلحة لحركة طالبان. وأشارت الصحيفة إلى أن خطة تعيين السفير البريطاني مارك سيدويل وجدت تأييد الولايات المتحدة ومن المرجح أن يصادق عليها باقي الحلفاء.", "language": "ara", "unit": "doc" } python-0.7.4/tests/mock-data/request/ara-doc-entities_linked.json 0000664 0000000 0000000 00000005076 12636317025 0025123 0 ustar 00root root 0000000 0000000 { "content": "الخميس 5/2/1431 هـ - الموافق 21/1/2010 م (آخر تحديث) الساعة 10:01 (مكة المكرمة)، 7:01 (غرينتش)\n\nناتو يفكر بمسؤول مدني لأفغانستان\n\nيخطط حلف شمال الأطلسي (ناتو) لتعيين مسؤول مدني كبير في أفغانستان، وسط دعوات لتحسين التنسيق السياسي والتنموي في البلاد وفق ما نقلته صحيفة وول ستريت. وقالت الصحيفة إن السفير البريطاني في كابل في مقدمة المرشحين لهذا المنصب والذي من المحتمل أن يعلن بالتزامن مع مؤتمر دولي عن مستقبل أفغانستان المقرر عقده في لندن في 28 يناير/كانون الثاني المقبل.\n وأضافت الصحيفة -في تقرير لها من كابل- أن المسؤول الجديد سيترأس دعامة مدنية للتحالف الذي تقوده الولايات المتحدة لإدارة التمويل والمساعدات للولايات الأفغانية لتحاشي المؤسسات الأفغانية الفاسدة\". وكان الأمين العام للأمم المتحدة بان كي مون دعا هذا الشهر لتعيين مسؤول مدني رفيع ضمن قوة المساعدة الدولية لإرساء الأمن في أفغانستان (إيساف) التي يقودها حلف الأطلسي للمساعدة في تنسيق الجهود السياسية والتنموية في الحرب التي دخلت عامها التاسع. وأضاف أن تعيين هذا المسؤول سيتيح تحسين التنسيق بين العمل السياسي والتنموي وخصوصا عبر فرق إعادة البناء في الولايات الأفغانية. وقالت جورنال ستريت إن المنصب الجديد سيكون نظيرا للأميركي ستانلي ماكريستال قائد القوات الأميركية وقوات حلف الأطلسي في أفغانستان. ويتوقع وصول أربعين ألف جندي آخرين لأفغانستان في الأشهر القليلة المقبلة في إطار إستراتيجية لمجابهة العمليات المسلحة لحركة طالبان. وأشارت الصحيفة إلى أن خطة تعيين السفير البريطاني مارك سيدويل وجدت تأييد الولايات المتحدة ومن المرجح أن يصادق عليها باقي الحلفاء.", "language": "ara", "unit": "doc" } python-0.7.4/tests/mock-data/request/ara-doc-language.json 0000664 0000000 0000000 00000005076 12636317025 0023534 0 ustar 00root root 0000000 0000000 { "content": "الخميس 5/2/1431 هـ - الموافق 21/1/2010 م (آخر تحديث) الساعة 10:01 (مكة المكرمة)، 7:01 (غرينتش)\n\nناتو يفكر بمسؤول مدني لأفغانستان\n\nيخطط حلف شمال الأطلسي (ناتو) لتعيين مسؤول مدني كبير في أفغانستان، وسط دعوات لتحسين التنسيق السياسي والتنموي في البلاد وفق ما نقلته صحيفة وول ستريت. وقالت الصحيفة إن السفير البريطاني في كابل في مقدمة المرشحين لهذا المنصب والذي من المحتمل أن يعلن بالتزامن مع مؤتمر دولي عن مستقبل أفغانستان المقرر عقده في لندن في 28 يناير/كانون الثاني المقبل.\n وأضافت الصحيفة -في تقرير لها من كابل- أن المسؤول الجديد سيترأس دعامة مدنية للتحالف الذي تقوده الولايات المتحدة لإدارة التمويل والمساعدات للولايات الأفغانية لتحاشي المؤسسات الأفغانية الفاسدة\". وكان الأمين العام للأمم المتحدة بان كي مون دعا هذا الشهر لتعيين مسؤول مدني رفيع ضمن قوة المساعدة الدولية لإرساء الأمن في أفغانستان (إيساف) التي يقودها حلف الأطلسي للمساعدة في تنسيق الجهود السياسية والتنموية في الحرب التي دخلت عامها التاسع. وأضاف أن تعيين هذا المسؤول سيتيح تحسين التنسيق بين العمل السياسي والتنموي وخصوصا عبر فرق إعادة البناء في الولايات الأفغانية. وقالت جورنال ستريت إن المنصب الجديد سيكون نظيرا للأميركي ستانلي ماكريستال قائد القوات الأميركية وقوات حلف الأطلسي في أفغانستان. ويتوقع وصول أربعين ألف جندي آخرين لأفغانستان في الأشهر القليلة المقبلة في إطار إستراتيجية لمجابهة العمليات المسلحة لحركة طالبان. وأشارت الصحيفة إلى أن خطة تعيين السفير البريطاني مارك سيدويل وجدت تأييد الولايات المتحدة ومن المرجح أن يصادق عليها باقي الحلفاء.", "language": "ara", "unit": "doc" } python-0.7.4/tests/mock-data/request/ara-doc-morphology_complete.json 0000664 0000000 0000000 00000005076 12636317025 0026040 0 ustar 00root root 0000000 0000000 { "content": "الخميس 5/2/1431 هـ - الموافق 21/1/2010 م (آخر تحديث) الساعة 10:01 (مكة المكرمة)، 7:01 (غرينتش)\n\nناتو يفكر بمسؤول مدني لأفغانستان\n\nيخطط حلف شمال الأطلسي (ناتو) لتعيين مسؤول مدني كبير في أفغانستان، وسط دعوات لتحسين التنسيق السياسي والتنموي في البلاد وفق ما نقلته صحيفة وول ستريت. وقالت الصحيفة إن السفير البريطاني في كابل في مقدمة المرشحين لهذا المنصب والذي من المحتمل أن يعلن بالتزامن مع مؤتمر دولي عن مستقبل أفغانستان المقرر عقده في لندن في 28 يناير/كانون الثاني المقبل.\n وأضافت الصحيفة -في تقرير لها من كابل- أن المسؤول الجديد سيترأس دعامة مدنية للتحالف الذي تقوده الولايات المتحدة لإدارة التمويل والمساعدات للولايات الأفغانية لتحاشي المؤسسات الأفغانية الفاسدة\". وكان الأمين العام للأمم المتحدة بان كي مون دعا هذا الشهر لتعيين مسؤول مدني رفيع ضمن قوة المساعدة الدولية لإرساء الأمن في أفغانستان (إيساف) التي يقودها حلف الأطلسي للمساعدة في تنسيق الجهود السياسية والتنموية في الحرب التي دخلت عامها التاسع. وأضاف أن تعيين هذا المسؤول سيتيح تحسين التنسيق بين العمل السياسي والتنموي وخصوصا عبر فرق إعادة البناء في الولايات الأفغانية. وقالت جورنال ستريت إن المنصب الجديد سيكون نظيرا للأميركي ستانلي ماكريستال قائد القوات الأميركية وقوات حلف الأطلسي في أفغانستان. ويتوقع وصول أربعين ألف جندي آخرين لأفغانستان في الأشهر القليلة المقبلة في إطار إستراتيجية لمجابهة العمليات المسلحة لحركة طالبان. وأشارت الصحيفة إلى أن خطة تعيين السفير البريطاني مارك سيدويل وجدت تأييد الولايات المتحدة ومن المرجح أن يصادق عليها باقي الحلفاء.", "language": "ara", "unit": "doc" } python-0.7.4/tests/mock-data/request/ara-doc-sentiment.json 0000664 0000000 0000000 00000005076 12636317025 0023757 0 ustar 00root root 0000000 0000000 { "content": "الخميس 5/2/1431 هـ - الموافق 21/1/2010 م (آخر تحديث) الساعة 10:01 (مكة المكرمة)، 7:01 (غرينتش)\n\nناتو يفكر بمسؤول مدني لأفغانستان\n\nيخطط حلف شمال الأطلسي (ناتو) لتعيين مسؤول مدني كبير في أفغانستان، وسط دعوات لتحسين التنسيق السياسي والتنموي في البلاد وفق ما نقلته صحيفة وول ستريت. وقالت الصحيفة إن السفير البريطاني في كابل في مقدمة المرشحين لهذا المنصب والذي من المحتمل أن يعلن بالتزامن مع مؤتمر دولي عن مستقبل أفغانستان المقرر عقده في لندن في 28 يناير/كانون الثاني المقبل.\n وأضافت الصحيفة -في تقرير لها من كابل- أن المسؤول الجديد سيترأس دعامة مدنية للتحالف الذي تقوده الولايات المتحدة لإدارة التمويل والمساعدات للولايات الأفغانية لتحاشي المؤسسات الأفغانية الفاسدة\". وكان الأمين العام للأمم المتحدة بان كي مون دعا هذا الشهر لتعيين مسؤول مدني رفيع ضمن قوة المساعدة الدولية لإرساء الأمن في أفغانستان (إيساف) التي يقودها حلف الأطلسي للمساعدة في تنسيق الجهود السياسية والتنموية في الحرب التي دخلت عامها التاسع. وأضاف أن تعيين هذا المسؤول سيتيح تحسين التنسيق بين العمل السياسي والتنموي وخصوصا عبر فرق إعادة البناء في الولايات الأفغانية. وقالت جورنال ستريت إن المنصب الجديد سيكون نظيرا للأميركي ستانلي ماكريستال قائد القوات الأميركية وقوات حلف الأطلسي في أفغانستان. ويتوقع وصول أربعين ألف جندي آخرين لأفغانستان في الأشهر القليلة المقبلة في إطار إستراتيجية لمجابهة العمليات المسلحة لحركة طالبان. وأشارت الصحيفة إلى أن خطة تعيين السفير البريطاني مارك سيدويل وجدت تأييد الولايات المتحدة ومن المرجح أن يصادق عليها باقي الحلفاء.", "language": "ara", "unit": "doc" } python-0.7.4/tests/mock-data/request/ara-sentence-categories.json 0000664 0000000 0000000 00000003122 12636317025 0025123 0 ustar 00root root 0000000 0000000 { "content": "بدأ العمل في يناير 2004 الذي يتم بناءه في وسط دبي وبلغت تكلفته الإجمالية 1.5 مليار دولار أميركي[5]؛ وتم افتتاحه في 4 يناير 2010 بحضور الشيخ محمد بن راشد آل مكتوم حاكم دبي. ويبلغ طول البرج 828 مترا وستكون المساحة الإجمالية 4,000,000 متر مربع وسيضم 37 طابقاً كفندق ليضم 403 جناح فندقي، وسيضم 57 مصعد كهربائي وسيكون أسرعهم 10م/ثانية، وللوصول إلى 500 م تحتاج إلى 55 ثانية وتمتلكه شركة إعمار العقارية وتعد واحدة من أكبر الشركات العقارية في العالم.و قد تولت عملية البناء شركة Samsung C&T. وهذا البرج الذي يرتفع بسرعة طابق كل ثلاث أيام (تقريبا) شكل البناء الرئيسي في مشروع عمراني ضخم بقيمة 20 مليار دولار يتوقع أن يغير ملامح المدينة. وأوضح روبرت بوث المدير التنفيذي في الشركة الإماراتية التي تنفذ المشروع أنه سيتم استخدام المبنى لأغراض متعددة، وسيضم المبنى محلات تجارية وأماكن للترفيه وفندقاً ووحدات سكنية وأجنحة خاصة للمؤسسات وحديقة بانورامية. وتم افتتاحه في 4 يناير 2010 والمكون من 124 طابقا.", "language": "ara", "unit": "sentence" } python-0.7.4/tests/mock-data/request/ara-sentence-entities.json 0000664 0000000 0000000 00000003122 12636317025 0024622 0 ustar 00root root 0000000 0000000 { "content": "بدأ العمل في يناير 2004 الذي يتم بناءه في وسط دبي وبلغت تكلفته الإجمالية 1.5 مليار دولار أميركي[5]؛ وتم افتتاحه في 4 يناير 2010 بحضور الشيخ محمد بن راشد آل مكتوم حاكم دبي. ويبلغ طول البرج 828 مترا وستكون المساحة الإجمالية 4,000,000 متر مربع وسيضم 37 طابقاً كفندق ليضم 403 جناح فندقي، وسيضم 57 مصعد كهربائي وسيكون أسرعهم 10م/ثانية، وللوصول إلى 500 م تحتاج إلى 55 ثانية وتمتلكه شركة إعمار العقارية وتعد واحدة من أكبر الشركات العقارية في العالم.و قد تولت عملية البناء شركة Samsung C&T. وهذا البرج الذي يرتفع بسرعة طابق كل ثلاث أيام (تقريبا) شكل البناء الرئيسي في مشروع عمراني ضخم بقيمة 20 مليار دولار يتوقع أن يغير ملامح المدينة. وأوضح روبرت بوث المدير التنفيذي في الشركة الإماراتية التي تنفذ المشروع أنه سيتم استخدام المبنى لأغراض متعددة، وسيضم المبنى محلات تجارية وأماكن للترفيه وفندقاً ووحدات سكنية وأجنحة خاصة للمؤسسات وحديقة بانورامية. وتم افتتاحه في 4 يناير 2010 والمكون من 124 طابقا.", "language": "ara", "unit": "sentence" } python-0.7.4/tests/mock-data/request/ara-sentence-entities_linked.json 0000664 0000000 0000000 00000003122 12636317025 0026150 0 ustar 00root root 0000000 0000000 { "content": "بدأ العمل في يناير 2004 الذي يتم بناءه في وسط دبي وبلغت تكلفته الإجمالية 1.5 مليار دولار أميركي[5]؛ وتم افتتاحه في 4 يناير 2010 بحضور الشيخ محمد بن راشد آل مكتوم حاكم دبي. ويبلغ طول البرج 828 مترا وستكون المساحة الإجمالية 4,000,000 متر مربع وسيضم 37 طابقاً كفندق ليضم 403 جناح فندقي، وسيضم 57 مصعد كهربائي وسيكون أسرعهم 10م/ثانية، وللوصول إلى 500 م تحتاج إلى 55 ثانية وتمتلكه شركة إعمار العقارية وتعد واحدة من أكبر الشركات العقارية في العالم.و قد تولت عملية البناء شركة Samsung C&T. وهذا البرج الذي يرتفع بسرعة طابق كل ثلاث أيام (تقريبا) شكل البناء الرئيسي في مشروع عمراني ضخم بقيمة 20 مليار دولار يتوقع أن يغير ملامح المدينة. وأوضح روبرت بوث المدير التنفيذي في الشركة الإماراتية التي تنفذ المشروع أنه سيتم استخدام المبنى لأغراض متعددة، وسيضم المبنى محلات تجارية وأماكن للترفيه وفندقاً ووحدات سكنية وأجنحة خاصة للمؤسسات وحديقة بانورامية. وتم افتتاحه في 4 يناير 2010 والمكون من 124 طابقا.", "language": "ara", "unit": "sentence" } python-0.7.4/tests/mock-data/request/ara-sentence-language.json 0000664 0000000 0000000 00000003122 12636317025 0024561 0 ustar 00root root 0000000 0000000 { "content": "بدأ العمل في يناير 2004 الذي يتم بناءه في وسط دبي وبلغت تكلفته الإجمالية 1.5 مليار دولار أميركي[5]؛ وتم افتتاحه في 4 يناير 2010 بحضور الشيخ محمد بن راشد آل مكتوم حاكم دبي. ويبلغ طول البرج 828 مترا وستكون المساحة الإجمالية 4,000,000 متر مربع وسيضم 37 طابقاً كفندق ليضم 403 جناح فندقي، وسيضم 57 مصعد كهربائي وسيكون أسرعهم 10م/ثانية، وللوصول إلى 500 م تحتاج إلى 55 ثانية وتمتلكه شركة إعمار العقارية وتعد واحدة من أكبر الشركات العقارية في العالم.و قد تولت عملية البناء شركة Samsung C&T. وهذا البرج الذي يرتفع بسرعة طابق كل ثلاث أيام (تقريبا) شكل البناء الرئيسي في مشروع عمراني ضخم بقيمة 20 مليار دولار يتوقع أن يغير ملامح المدينة. وأوضح روبرت بوث المدير التنفيذي في الشركة الإماراتية التي تنفذ المشروع أنه سيتم استخدام المبنى لأغراض متعددة، وسيضم المبنى محلات تجارية وأماكن للترفيه وفندقاً ووحدات سكنية وأجنحة خاصة للمؤسسات وحديقة بانورامية. وتم افتتاحه في 4 يناير 2010 والمكون من 124 طابقا.", "language": "ara", "unit": "sentence" } python-0.7.4/tests/mock-data/request/ara-sentence-morphology_complete.json 0000664 0000000 0000000 00000003122 12636317025 0027065 0 ustar 00root root 0000000 0000000 { "content": "بدأ العمل في يناير 2004 الذي يتم بناءه في وسط دبي وبلغت تكلفته الإجمالية 1.5 مليار دولار أميركي[5]؛ وتم افتتاحه في 4 يناير 2010 بحضور الشيخ محمد بن راشد آل مكتوم حاكم دبي. ويبلغ طول البرج 828 مترا وستكون المساحة الإجمالية 4,000,000 متر مربع وسيضم 37 طابقاً كفندق ليضم 403 جناح فندقي، وسيضم 57 مصعد كهربائي وسيكون أسرعهم 10م/ثانية، وللوصول إلى 500 م تحتاج إلى 55 ثانية وتمتلكه شركة إعمار العقارية وتعد واحدة من أكبر الشركات العقارية في العالم.و قد تولت عملية البناء شركة Samsung C&T. وهذا البرج الذي يرتفع بسرعة طابق كل ثلاث أيام (تقريبا) شكل البناء الرئيسي في مشروع عمراني ضخم بقيمة 20 مليار دولار يتوقع أن يغير ملامح المدينة. وأوضح روبرت بوث المدير التنفيذي في الشركة الإماراتية التي تنفذ المشروع أنه سيتم استخدام المبنى لأغراض متعددة، وسيضم المبنى محلات تجارية وأماكن للترفيه وفندقاً ووحدات سكنية وأجنحة خاصة للمؤسسات وحديقة بانورامية. وتم افتتاحه في 4 يناير 2010 والمكون من 124 طابقا.", "language": "ara", "unit": "sentence" } python-0.7.4/tests/mock-data/request/ara-sentence-sentiment.json 0000664 0000000 0000000 00000003122 12636317025 0025004 0 ustar 00root root 0000000 0000000 { "content": "بدأ العمل في يناير 2004 الذي يتم بناءه في وسط دبي وبلغت تكلفته الإجمالية 1.5 مليار دولار أميركي[5]؛ وتم افتتاحه في 4 يناير 2010 بحضور الشيخ محمد بن راشد آل مكتوم حاكم دبي. ويبلغ طول البرج 828 مترا وستكون المساحة الإجمالية 4,000,000 متر مربع وسيضم 37 طابقاً كفندق ليضم 403 جناح فندقي، وسيضم 57 مصعد كهربائي وسيكون أسرعهم 10م/ثانية، وللوصول إلى 500 م تحتاج إلى 55 ثانية وتمتلكه شركة إعمار العقارية وتعد واحدة من أكبر الشركات العقارية في العالم.و قد تولت عملية البناء شركة Samsung C&T. وهذا البرج الذي يرتفع بسرعة طابق كل ثلاث أيام (تقريبا) شكل البناء الرئيسي في مشروع عمراني ضخم بقيمة 20 مليار دولار يتوقع أن يغير ملامح المدينة. وأوضح روبرت بوث المدير التنفيذي في الشركة الإماراتية التي تنفذ المشروع أنه سيتم استخدام المبنى لأغراض متعددة، وسيضم المبنى محلات تجارية وأماكن للترفيه وفندقاً ووحدات سكنية وأجنحة خاصة للمؤسسات وحديقة بانورامية. وتم افتتاحه في 4 يناير 2010 والمكون من 124 طابقا.", "language": "ara", "unit": "sentence" } python-0.7.4/tests/mock-data/request/ara-url-categories.json 0000664 0000000 0000000 00000001335 12636317025 0024125 0 ustar 00root root 0000000 0000000 { "contentUri": "http://news.google.com/news/url?sa=t&fd=R&ct2=ar_me&usg=AFQjCNHR6DD0ibhzUUYiL3dzGewRaj-3QQ&clid=c3a7d30bb8a4878e06b80cf16b898331&cid=52779450477067&ei=YwNNVf2qK5HT3AHmxYCQBQ&url=http://www.aljazeera.net/news/arabic/2015/5/8/%25D8%25A7%25D9%2584%25D8%25AA%25D8%25AD%25D8%25A7%25D9%2584%25D9%2581-%25D9%258A%25D9%2582%25D8%25B5%25D9%2581-%25D9%2585%25D9%2582%25D8%25B1%25D8%25A7%25D8%25AA-%25D9%2584%25D9%2584%25D8%25AD%25D9%2588%25D8%25AB%25D9%258A%25D9%258A%25D9%2586-%25D8%25A8%25D8%25B5%25D8%25B9%25D8%25AF%25D8%25A9-%25D9%2588%25D9%258A%25D8%25AF%25D8%25B9%25D9%2588-%25D8%25A7%25D9%2584%25D8%25B3%25D9%2583%25D8%25A7%25D9%2586-%25D9%2584%25D9%2584%25D9%2585%25D8%25BA%25D8%25A7%25D8%25AF%25D8%25B1%25D8%25A9" } python-0.7.4/tests/mock-data/request/ara-url-entities.json 0000664 0000000 0000000 00000001335 12636317025 0023624 0 ustar 00root root 0000000 0000000 { "contentUri": "http://news.google.com/news/url?sa=t&fd=R&ct2=ar_me&usg=AFQjCNHR6DD0ibhzUUYiL3dzGewRaj-3QQ&clid=c3a7d30bb8a4878e06b80cf16b898331&cid=52779450477067&ei=YwNNVf2qK5HT3AHmxYCQBQ&url=http://www.aljazeera.net/news/arabic/2015/5/8/%25D8%25A7%25D9%2584%25D8%25AA%25D8%25AD%25D8%25A7%25D9%2584%25D9%2581-%25D9%258A%25D9%2582%25D8%25B5%25D9%2581-%25D9%2585%25D9%2582%25D8%25B1%25D8%25A7%25D8%25AA-%25D9%2584%25D9%2584%25D8%25AD%25D9%2588%25D8%25AB%25D9%258A%25D9%258A%25D9%2586-%25D8%25A8%25D8%25B5%25D8%25B9%25D8%25AF%25D8%25A9-%25D9%2588%25D9%258A%25D8%25AF%25D8%25B9%25D9%2588-%25D8%25A7%25D9%2584%25D8%25B3%25D9%2583%25D8%25A7%25D9%2586-%25D9%2584%25D9%2584%25D9%2585%25D8%25BA%25D8%25A7%25D8%25AF%25D8%25B1%25D8%25A9" } python-0.7.4/tests/mock-data/request/ara-url-entities_linked.json 0000664 0000000 0000000 00000001335 12636317025 0025152 0 ustar 00root root 0000000 0000000 { "contentUri": "http://news.google.com/news/url?sa=t&fd=R&ct2=ar_me&usg=AFQjCNHR6DD0ibhzUUYiL3dzGewRaj-3QQ&clid=c3a7d30bb8a4878e06b80cf16b898331&cid=52779450477067&ei=YwNNVf2qK5HT3AHmxYCQBQ&url=http://www.aljazeera.net/news/arabic/2015/5/8/%25D8%25A7%25D9%2584%25D8%25AA%25D8%25AD%25D8%25A7%25D9%2584%25D9%2581-%25D9%258A%25D9%2582%25D8%25B5%25D9%2581-%25D9%2585%25D9%2582%25D8%25B1%25D8%25A7%25D8%25AA-%25D9%2584%25D9%2584%25D8%25AD%25D9%2588%25D8%25AB%25D9%258A%25D9%258A%25D9%2586-%25D8%25A8%25D8%25B5%25D8%25B9%25D8%25AF%25D8%25A9-%25D9%2588%25D9%258A%25D8%25AF%25D8%25B9%25D9%2588-%25D8%25A7%25D9%2584%25D8%25B3%25D9%2583%25D8%25A7%25D9%2586-%25D9%2584%25D9%2584%25D9%2585%25D8%25BA%25D8%25A7%25D8%25AF%25D8%25B1%25D8%25A9" } python-0.7.4/tests/mock-data/request/ara-url-language.json 0000664 0000000 0000000 00000001335 12636317025 0023563 0 ustar 00root root 0000000 0000000 { "contentUri": "http://news.google.com/news/url?sa=t&fd=R&ct2=ar_me&usg=AFQjCNHR6DD0ibhzUUYiL3dzGewRaj-3QQ&clid=c3a7d30bb8a4878e06b80cf16b898331&cid=52779450477067&ei=YwNNVf2qK5HT3AHmxYCQBQ&url=http://www.aljazeera.net/news/arabic/2015/5/8/%25D8%25A7%25D9%2584%25D8%25AA%25D8%25AD%25D8%25A7%25D9%2584%25D9%2581-%25D9%258A%25D9%2582%25D8%25B5%25D9%2581-%25D9%2585%25D9%2582%25D8%25B1%25D8%25A7%25D8%25AA-%25D9%2584%25D9%2584%25D8%25AD%25D9%2588%25D8%25AB%25D9%258A%25D9%258A%25D9%2586-%25D8%25A8%25D8%25B5%25D8%25B9%25D8%25AF%25D8%25A9-%25D9%2588%25D9%258A%25D8%25AF%25D8%25B9%25D9%2588-%25D8%25A7%25D9%2584%25D8%25B3%25D9%2583%25D8%25A7%25D9%2586-%25D9%2584%25D9%2584%25D9%2585%25D8%25BA%25D8%25A7%25D8%25AF%25D8%25B1%25D8%25A9" } python-0.7.4/tests/mock-data/request/ara-url-morphology_complete.json 0000664 0000000 0000000 00000001335 12636317025 0026067 0 ustar 00root root 0000000 0000000 { "contentUri": "http://news.google.com/news/url?sa=t&fd=R&ct2=ar_me&usg=AFQjCNHR6DD0ibhzUUYiL3dzGewRaj-3QQ&clid=c3a7d30bb8a4878e06b80cf16b898331&cid=52779450477067&ei=YwNNVf2qK5HT3AHmxYCQBQ&url=http://www.aljazeera.net/news/arabic/2015/5/8/%25D8%25A7%25D9%2584%25D8%25AA%25D8%25AD%25D8%25A7%25D9%2584%25D9%2581-%25D9%258A%25D9%2582%25D8%25B5%25D9%2581-%25D9%2585%25D9%2582%25D8%25B1%25D8%25A7%25D8%25AA-%25D9%2584%25D9%2584%25D8%25AD%25D9%2588%25D8%25AB%25D9%258A%25D9%258A%25D9%2586-%25D8%25A8%25D8%25B5%25D8%25B9%25D8%25AF%25D8%25A9-%25D9%2588%25D9%258A%25D8%25AF%25D8%25B9%25D9%2588-%25D8%25A7%25D9%2584%25D8%25B3%25D9%2583%25D8%25A7%25D9%2586-%25D9%2584%25D9%2584%25D9%2585%25D8%25BA%25D8%25A7%25D8%25AF%25D8%25B1%25D8%25A9" } python-0.7.4/tests/mock-data/request/ara-url-sentiment.json 0000664 0000000 0000000 00000001335 12636317025 0024006 0 ustar 00root root 0000000 0000000 { "contentUri": "http://news.google.com/news/url?sa=t&fd=R&ct2=ar_me&usg=AFQjCNHR6DD0ibhzUUYiL3dzGewRaj-3QQ&clid=c3a7d30bb8a4878e06b80cf16b898331&cid=52779450477067&ei=YwNNVf2qK5HT3AHmxYCQBQ&url=http://www.aljazeera.net/news/arabic/2015/5/8/%25D8%25A7%25D9%2584%25D8%25AA%25D8%25AD%25D8%25A7%25D9%2584%25D9%2581-%25D9%258A%25D9%2582%25D8%25B5%25D9%2581-%25D9%2585%25D9%2582%25D8%25B1%25D8%25A7%25D8%25AA-%25D9%2584%25D9%2584%25D8%25AD%25D9%2588%25D8%25AB%25D9%258A%25D9%258A%25D9%2586-%25D8%25A8%25D8%25B5%25D8%25B9%25D8%25AF%25D8%25A9-%25D9%2588%25D9%258A%25D8%25AF%25D8%25B9%25D9%2588-%25D8%25A7%25D9%2584%25D8%25B3%25D9%2583%25D8%25A7%25D9%2586-%25D9%2584%25D9%2584%25D9%2585%25D8%25BA%25D8%25A7%25D8%25AF%25D8%25B1%25D8%25A9" } python-0.7.4/tests/mock-data/request/eng-doc-categories.json 0000664 0000000 0000000 00000004661 12636317025 0024103 0 ustar 00root root 0000000 0000000 { "content": "Samsung Can Sell Its Tablet In The U.S. Market\n\n\nThe war between Samsung Electronics and Apple seems to be never ending. The companies have engaged in an international warfare, across continents, with more than 20 cases in 10 countries. The latest news in the Samsung vs. Apple conflict comes from U.S. where a judge decided that Samsung can sell its tablet in the U.S. market.\n\nIn United States, Apple initiated a legal action against Samsung in April, claiming that the South Korean smartphones and tablets “slavishly” copy the iPhone and the iPad. As a result, Apple requested that Samsung will be prohibited from selling the gadgets in the U.S. market. The much expected ruling came late on Friday, as U.S. District Judge Lucy Koh denied Apple’s request for a preliminary injuction against Samsung.\n\nU.S. District Judge Lucy Koh said that “It is not clear than an injuction on Samsung’s accused devices would prevent Apple from being irreparably harmed”. As a result, Koh rejected Apple’s request to bid sales of three Samsung smartphones models and the Samsung Tab 10.1. In the third quarter, Samsung had 23.8 percent of the global smartphone market, nine points higher than Apple.\n\nThe U.S. judge wrote that “Apple has established a likelihood of success on the merits at trial” regarding some of Samsung’s smartphones. Apple would likely prove Samsung infringed one of its tablet patents, but it did not show that it was likely to overcome Samsung’s challenges to the patent’s validity.\n\nAlthough this might be a minor victory for Samsung, as Apple still has high changes of winning the overall lawsuit, Koh’s decision makes it possible for the South Korean company to start Christmas sales.\n\nAnalysts say that global tablet sales are expected to boost to more than 50 million this year, with Apple still the leader of the market. The Silicon Valley based company sold 11.12 million units during the September quarter. So far, Apple sold more than 30 million iPads worldwide.\n\nLast week, a judge in Australia ruled in favor of Apple by extending a ban on Samsung’s iPad sales within the country. Australia is a key market for Samsung Galaxy Tablet and two weeks of banned sales isn’t much, but it can get urgent if Samsung won’t start selling the gadget before Christmas.\n\n\n\nhttp://newsinabox.net/2202/samsung-can-sell-its-tablet-in-the-u-s-market.html\n2011.12.05", "language": "eng", "unit": "doc" } python-0.7.4/tests/mock-data/request/eng-doc-entities.json 0000664 0000000 0000000 00000004661 12636317025 0023602 0 ustar 00root root 0000000 0000000 { "content": "Samsung Can Sell Its Tablet In The U.S. Market\n\n\nThe war between Samsung Electronics and Apple seems to be never ending. The companies have engaged in an international warfare, across continents, with more than 20 cases in 10 countries. The latest news in the Samsung vs. Apple conflict comes from U.S. where a judge decided that Samsung can sell its tablet in the U.S. market.\n\nIn United States, Apple initiated a legal action against Samsung in April, claiming that the South Korean smartphones and tablets “slavishly” copy the iPhone and the iPad. As a result, Apple requested that Samsung will be prohibited from selling the gadgets in the U.S. market. The much expected ruling came late on Friday, as U.S. District Judge Lucy Koh denied Apple’s request for a preliminary injuction against Samsung.\n\nU.S. District Judge Lucy Koh said that “It is not clear than an injuction on Samsung’s accused devices would prevent Apple from being irreparably harmed”. As a result, Koh rejected Apple’s request to bid sales of three Samsung smartphones models and the Samsung Tab 10.1. In the third quarter, Samsung had 23.8 percent of the global smartphone market, nine points higher than Apple.\n\nThe U.S. judge wrote that “Apple has established a likelihood of success on the merits at trial” regarding some of Samsung’s smartphones. Apple would likely prove Samsung infringed one of its tablet patents, but it did not show that it was likely to overcome Samsung’s challenges to the patent’s validity.\n\nAlthough this might be a minor victory for Samsung, as Apple still has high changes of winning the overall lawsuit, Koh’s decision makes it possible for the South Korean company to start Christmas sales.\n\nAnalysts say that global tablet sales are expected to boost to more than 50 million this year, with Apple still the leader of the market. The Silicon Valley based company sold 11.12 million units during the September quarter. So far, Apple sold more than 30 million iPads worldwide.\n\nLast week, a judge in Australia ruled in favor of Apple by extending a ban on Samsung’s iPad sales within the country. Australia is a key market for Samsung Galaxy Tablet and two weeks of banned sales isn’t much, but it can get urgent if Samsung won’t start selling the gadget before Christmas.\n\n\n\nhttp://newsinabox.net/2202/samsung-can-sell-its-tablet-in-the-u-s-market.html\n2011.12.05", "language": "eng", "unit": "doc" } python-0.7.4/tests/mock-data/request/eng-doc-entities_linked.json 0000664 0000000 0000000 00000004661 12636317025 0025130 0 ustar 00root root 0000000 0000000 { "content": "Samsung Can Sell Its Tablet In The U.S. Market\n\n\nThe war between Samsung Electronics and Apple seems to be never ending. The companies have engaged in an international warfare, across continents, with more than 20 cases in 10 countries. The latest news in the Samsung vs. Apple conflict comes from U.S. where a judge decided that Samsung can sell its tablet in the U.S. market.\n\nIn United States, Apple initiated a legal action against Samsung in April, claiming that the South Korean smartphones and tablets “slavishly” copy the iPhone and the iPad. As a result, Apple requested that Samsung will be prohibited from selling the gadgets in the U.S. market. The much expected ruling came late on Friday, as U.S. District Judge Lucy Koh denied Apple’s request for a preliminary injuction against Samsung.\n\nU.S. District Judge Lucy Koh said that “It is not clear than an injuction on Samsung’s accused devices would prevent Apple from being irreparably harmed”. As a result, Koh rejected Apple’s request to bid sales of three Samsung smartphones models and the Samsung Tab 10.1. In the third quarter, Samsung had 23.8 percent of the global smartphone market, nine points higher than Apple.\n\nThe U.S. judge wrote that “Apple has established a likelihood of success on the merits at trial” regarding some of Samsung’s smartphones. Apple would likely prove Samsung infringed one of its tablet patents, but it did not show that it was likely to overcome Samsung’s challenges to the patent’s validity.\n\nAlthough this might be a minor victory for Samsung, as Apple still has high changes of winning the overall lawsuit, Koh’s decision makes it possible for the South Korean company to start Christmas sales.\n\nAnalysts say that global tablet sales are expected to boost to more than 50 million this year, with Apple still the leader of the market. The Silicon Valley based company sold 11.12 million units during the September quarter. So far, Apple sold more than 30 million iPads worldwide.\n\nLast week, a judge in Australia ruled in favor of Apple by extending a ban on Samsung’s iPad sales within the country. Australia is a key market for Samsung Galaxy Tablet and two weeks of banned sales isn’t much, but it can get urgent if Samsung won’t start selling the gadget before Christmas.\n\n\n\nhttp://newsinabox.net/2202/samsung-can-sell-its-tablet-in-the-u-s-market.html\n2011.12.05", "language": "eng", "unit": "doc" } python-0.7.4/tests/mock-data/request/eng-doc-language.json 0000664 0000000 0000000 00000004661 12636317025 0023541 0 ustar 00root root 0000000 0000000 { "content": "Samsung Can Sell Its Tablet In The U.S. Market\n\n\nThe war between Samsung Electronics and Apple seems to be never ending. The companies have engaged in an international warfare, across continents, with more than 20 cases in 10 countries. The latest news in the Samsung vs. Apple conflict comes from U.S. where a judge decided that Samsung can sell its tablet in the U.S. market.\n\nIn United States, Apple initiated a legal action against Samsung in April, claiming that the South Korean smartphones and tablets “slavishly” copy the iPhone and the iPad. As a result, Apple requested that Samsung will be prohibited from selling the gadgets in the U.S. market. The much expected ruling came late on Friday, as U.S. District Judge Lucy Koh denied Apple’s request for a preliminary injuction against Samsung.\n\nU.S. District Judge Lucy Koh said that “It is not clear than an injuction on Samsung’s accused devices would prevent Apple from being irreparably harmed”. As a result, Koh rejected Apple’s request to bid sales of three Samsung smartphones models and the Samsung Tab 10.1. In the third quarter, Samsung had 23.8 percent of the global smartphone market, nine points higher than Apple.\n\nThe U.S. judge wrote that “Apple has established a likelihood of success on the merits at trial” regarding some of Samsung’s smartphones. Apple would likely prove Samsung infringed one of its tablet patents, but it did not show that it was likely to overcome Samsung’s challenges to the patent’s validity.\n\nAlthough this might be a minor victory for Samsung, as Apple still has high changes of winning the overall lawsuit, Koh’s decision makes it possible for the South Korean company to start Christmas sales.\n\nAnalysts say that global tablet sales are expected to boost to more than 50 million this year, with Apple still the leader of the market. The Silicon Valley based company sold 11.12 million units during the September quarter. So far, Apple sold more than 30 million iPads worldwide.\n\nLast week, a judge in Australia ruled in favor of Apple by extending a ban on Samsung’s iPad sales within the country. Australia is a key market for Samsung Galaxy Tablet and two weeks of banned sales isn’t much, but it can get urgent if Samsung won’t start selling the gadget before Christmas.\n\n\n\nhttp://newsinabox.net/2202/samsung-can-sell-its-tablet-in-the-u-s-market.html\n2011.12.05", "language": "eng", "unit": "doc" } python-0.7.4/tests/mock-data/request/eng-doc-morphology_complete.json 0000664 0000000 0000000 00000004661 12636317025 0026045 0 ustar 00root root 0000000 0000000 { "content": "Samsung Can Sell Its Tablet In The U.S. Market\n\n\nThe war between Samsung Electronics and Apple seems to be never ending. The companies have engaged in an international warfare, across continents, with more than 20 cases in 10 countries. The latest news in the Samsung vs. Apple conflict comes from U.S. where a judge decided that Samsung can sell its tablet in the U.S. market.\n\nIn United States, Apple initiated a legal action against Samsung in April, claiming that the South Korean smartphones and tablets “slavishly” copy the iPhone and the iPad. As a result, Apple requested that Samsung will be prohibited from selling the gadgets in the U.S. market. The much expected ruling came late on Friday, as U.S. District Judge Lucy Koh denied Apple’s request for a preliminary injuction against Samsung.\n\nU.S. District Judge Lucy Koh said that “It is not clear than an injuction on Samsung’s accused devices would prevent Apple from being irreparably harmed”. As a result, Koh rejected Apple’s request to bid sales of three Samsung smartphones models and the Samsung Tab 10.1. In the third quarter, Samsung had 23.8 percent of the global smartphone market, nine points higher than Apple.\n\nThe U.S. judge wrote that “Apple has established a likelihood of success on the merits at trial” regarding some of Samsung’s smartphones. Apple would likely prove Samsung infringed one of its tablet patents, but it did not show that it was likely to overcome Samsung’s challenges to the patent’s validity.\n\nAlthough this might be a minor victory for Samsung, as Apple still has high changes of winning the overall lawsuit, Koh’s decision makes it possible for the South Korean company to start Christmas sales.\n\nAnalysts say that global tablet sales are expected to boost to more than 50 million this year, with Apple still the leader of the market. The Silicon Valley based company sold 11.12 million units during the September quarter. So far, Apple sold more than 30 million iPads worldwide.\n\nLast week, a judge in Australia ruled in favor of Apple by extending a ban on Samsung’s iPad sales within the country. Australia is a key market for Samsung Galaxy Tablet and two weeks of banned sales isn’t much, but it can get urgent if Samsung won’t start selling the gadget before Christmas.\n\n\n\nhttp://newsinabox.net/2202/samsung-can-sell-its-tablet-in-the-u-s-market.html\n2011.12.05", "language": "eng", "unit": "doc" } python-0.7.4/tests/mock-data/request/eng-doc-relationships.json 0000664 0000000 0000000 00000004661 12636317025 0024642 0 ustar 00root root 0000000 0000000 { "content": "Samsung Can Sell Its Tablet In The U.S. Market\n\n\nThe war between Samsung Electronics and Apple seems to be never ending. The companies have engaged in an international warfare, across continents, with more than 20 cases in 10 countries. The latest news in the Samsung vs. Apple conflict comes from U.S. where a judge decided that Samsung can sell its tablet in the U.S. market.\n\nIn United States, Apple initiated a legal action against Samsung in April, claiming that the South Korean smartphones and tablets “slavishly” copy the iPhone and the iPad. As a result, Apple requested that Samsung will be prohibited from selling the gadgets in the U.S. market. The much expected ruling came late on Friday, as U.S. District Judge Lucy Koh denied Apple’s request for a preliminary injuction against Samsung.\n\nU.S. District Judge Lucy Koh said that “It is not clear than an injuction on Samsung’s accused devices would prevent Apple from being irreparably harmed”. As a result, Koh rejected Apple’s request to bid sales of three Samsung smartphones models and the Samsung Tab 10.1. In the third quarter, Samsung had 23.8 percent of the global smartphone market, nine points higher than Apple.\n\nThe U.S. judge wrote that “Apple has established a likelihood of success on the merits at trial” regarding some of Samsung’s smartphones. Apple would likely prove Samsung infringed one of its tablet patents, but it did not show that it was likely to overcome Samsung’s challenges to the patent’s validity.\n\nAlthough this might be a minor victory for Samsung, as Apple still has high changes of winning the overall lawsuit, Koh’s decision makes it possible for the South Korean company to start Christmas sales.\n\nAnalysts say that global tablet sales are expected to boost to more than 50 million this year, with Apple still the leader of the market. The Silicon Valley based company sold 11.12 million units during the September quarter. So far, Apple sold more than 30 million iPads worldwide.\n\nLast week, a judge in Australia ruled in favor of Apple by extending a ban on Samsung’s iPad sales within the country. Australia is a key market for Samsung Galaxy Tablet and two weeks of banned sales isn’t much, but it can get urgent if Samsung won’t start selling the gadget before Christmas.\n\n\n\nhttp://newsinabox.net/2202/samsung-can-sell-its-tablet-in-the-u-s-market.html\n2011.12.05", "language": "eng", "unit": "doc" } python-0.7.4/tests/mock-data/request/eng-doc-sentiment.json 0000664 0000000 0000000 00000004661 12636317025 0023764 0 ustar 00root root 0000000 0000000 { "content": "Samsung Can Sell Its Tablet In The U.S. Market\n\n\nThe war between Samsung Electronics and Apple seems to be never ending. The companies have engaged in an international warfare, across continents, with more than 20 cases in 10 countries. The latest news in the Samsung vs. Apple conflict comes from U.S. where a judge decided that Samsung can sell its tablet in the U.S. market.\n\nIn United States, Apple initiated a legal action against Samsung in April, claiming that the South Korean smartphones and tablets “slavishly” copy the iPhone and the iPad. As a result, Apple requested that Samsung will be prohibited from selling the gadgets in the U.S. market. The much expected ruling came late on Friday, as U.S. District Judge Lucy Koh denied Apple’s request for a preliminary injuction against Samsung.\n\nU.S. District Judge Lucy Koh said that “It is not clear than an injuction on Samsung’s accused devices would prevent Apple from being irreparably harmed”. As a result, Koh rejected Apple’s request to bid sales of three Samsung smartphones models and the Samsung Tab 10.1. In the third quarter, Samsung had 23.8 percent of the global smartphone market, nine points higher than Apple.\n\nThe U.S. judge wrote that “Apple has established a likelihood of success on the merits at trial” regarding some of Samsung’s smartphones. Apple would likely prove Samsung infringed one of its tablet patents, but it did not show that it was likely to overcome Samsung’s challenges to the patent’s validity.\n\nAlthough this might be a minor victory for Samsung, as Apple still has high changes of winning the overall lawsuit, Koh’s decision makes it possible for the South Korean company to start Christmas sales.\n\nAnalysts say that global tablet sales are expected to boost to more than 50 million this year, with Apple still the leader of the market. The Silicon Valley based company sold 11.12 million units during the September quarter. So far, Apple sold more than 30 million iPads worldwide.\n\nLast week, a judge in Australia ruled in favor of Apple by extending a ban on Samsung’s iPad sales within the country. Australia is a key market for Samsung Galaxy Tablet and two weeks of banned sales isn’t much, but it can get urgent if Samsung won’t start selling the gadget before Christmas.\n\n\n\nhttp://newsinabox.net/2202/samsung-can-sell-its-tablet-in-the-u-s-market.html\n2011.12.05", "language": "eng", "unit": "doc" } python-0.7.4/tests/mock-data/request/eng-sentence-categories.json 0000664 0000000 0000000 00000000544 12636317025 0025136 0 ustar 00root root 0000000 0000000 { "content": "He also acknowledged the ongoing U.S. conflicts in Iraq and Afghanistan, noting that he is the \"commander in chief of a country that is responsible for ending a war and working in another theater to confront a ruthless adversary that directly threatens the American people\" and U.S. allies.", "language": "eng", "unit": "sentence" } python-0.7.4/tests/mock-data/request/eng-sentence-entities.json 0000664 0000000 0000000 00000000544 12636317025 0024635 0 ustar 00root root 0000000 0000000 { "content": "He also acknowledged the ongoing U.S. conflicts in Iraq and Afghanistan, noting that he is the \"commander in chief of a country that is responsible for ending a war and working in another theater to confront a ruthless adversary that directly threatens the American people\" and U.S. allies.", "language": "eng", "unit": "sentence" } python-0.7.4/tests/mock-data/request/eng-sentence-entities_linked.json 0000664 0000000 0000000 00000000544 12636317025 0026163 0 ustar 00root root 0000000 0000000 { "content": "He also acknowledged the ongoing U.S. conflicts in Iraq and Afghanistan, noting that he is the \"commander in chief of a country that is responsible for ending a war and working in another theater to confront a ruthless adversary that directly threatens the American people\" and U.S. allies.", "language": "eng", "unit": "sentence" } python-0.7.4/tests/mock-data/request/eng-sentence-language.json 0000664 0000000 0000000 00000000544 12636317025 0024574 0 ustar 00root root 0000000 0000000 { "content": "He also acknowledged the ongoing U.S. conflicts in Iraq and Afghanistan, noting that he is the \"commander in chief of a country that is responsible for ending a war and working in another theater to confront a ruthless adversary that directly threatens the American people\" and U.S. allies.", "language": "eng", "unit": "sentence" } python-0.7.4/tests/mock-data/request/eng-sentence-morphology_complete.json 0000664 0000000 0000000 00000000544 12636317025 0027100 0 ustar 00root root 0000000 0000000 { "content": "He also acknowledged the ongoing U.S. conflicts in Iraq and Afghanistan, noting that he is the \"commander in chief of a country that is responsible for ending a war and working in another theater to confront a ruthless adversary that directly threatens the American people\" and U.S. allies.", "language": "eng", "unit": "sentence" } python-0.7.4/tests/mock-data/request/eng-sentence-relationships.json 0000664 0000000 0000000 00000000234 12636317025 0025671 0 ustar 00root root 0000000 0000000 { "content": "The first men to reach the moon were Mr. Armstrong and his co-pilot, Col. Edwin E. Aldrin.", "language": "eng", "unit": "sentence" } python-0.7.4/tests/mock-data/request/eng-sentence-sentiment.json 0000664 0000000 0000000 00000000544 12636317025 0025017 0 ustar 00root root 0000000 0000000 { "content": "He also acknowledged the ongoing U.S. conflicts in Iraq and Afghanistan, noting that he is the \"commander in chief of a country that is responsible for ending a war and working in another theater to confront a ruthless adversary that directly threatens the American people\" and U.S. allies.", "language": "eng", "unit": "sentence" } python-0.7.4/tests/mock-data/request/eng-url-categories.json 0000664 0000000 0000000 00000000457 12636317025 0024137 0 ustar 00root root 0000000 0000000 { "contentUri": "http://news.google.com/news/url?sa=t&fd=R&ct2=us&usg=AFQjCNGOuNpkO_3eDYWh76D8lZDl5jI_pQ&clid=c3a7d30bb8a4878e06b80cf16b898331&cid=52778830388718&ei=bwNNVfDFItjU3AGy-4HQDQ&url=http://www.usatoday.com/story/news/politics/2015/05/08/obama-nike-visit-free-trade-jobs-protests/26974883/" } python-0.7.4/tests/mock-data/request/eng-url-entities.json 0000664 0000000 0000000 00000000457 12636317025 0023636 0 ustar 00root root 0000000 0000000 { "contentUri": "http://news.google.com/news/url?sa=t&fd=R&ct2=us&usg=AFQjCNGOuNpkO_3eDYWh76D8lZDl5jI_pQ&clid=c3a7d30bb8a4878e06b80cf16b898331&cid=52778830388718&ei=bwNNVfDFItjU3AGy-4HQDQ&url=http://www.usatoday.com/story/news/politics/2015/05/08/obama-nike-visit-free-trade-jobs-protests/26974883/" } python-0.7.4/tests/mock-data/request/eng-url-entities_linked.json 0000664 0000000 0000000 00000000457 12636317025 0025164 0 ustar 00root root 0000000 0000000 { "contentUri": "http://news.google.com/news/url?sa=t&fd=R&ct2=us&usg=AFQjCNGOuNpkO_3eDYWh76D8lZDl5jI_pQ&clid=c3a7d30bb8a4878e06b80cf16b898331&cid=52778830388718&ei=bwNNVfDFItjU3AGy-4HQDQ&url=http://www.usatoday.com/story/news/politics/2015/05/08/obama-nike-visit-free-trade-jobs-protests/26974883/" } python-0.7.4/tests/mock-data/request/eng-url-language.json 0000664 0000000 0000000 00000000457 12636317025 0023575 0 ustar 00root root 0000000 0000000 { "contentUri": "http://news.google.com/news/url?sa=t&fd=R&ct2=us&usg=AFQjCNGOuNpkO_3eDYWh76D8lZDl5jI_pQ&clid=c3a7d30bb8a4878e06b80cf16b898331&cid=52778830388718&ei=bwNNVfDFItjU3AGy-4HQDQ&url=http://www.usatoday.com/story/news/politics/2015/05/08/obama-nike-visit-free-trade-jobs-protests/26974883/" } python-0.7.4/tests/mock-data/request/eng-url-morphology_complete.json 0000664 0000000 0000000 00000000457 12636317025 0026101 0 ustar 00root root 0000000 0000000 { "contentUri": "http://news.google.com/news/url?sa=t&fd=R&ct2=us&usg=AFQjCNGOuNpkO_3eDYWh76D8lZDl5jI_pQ&clid=c3a7d30bb8a4878e06b80cf16b898331&cid=52778830388718&ei=bwNNVfDFItjU3AGy-4HQDQ&url=http://www.usatoday.com/story/news/politics/2015/05/08/obama-nike-visit-free-trade-jobs-protests/26974883/" } python-0.7.4/tests/mock-data/request/eng-url-relationships.json 0000664 0000000 0000000 00000000460 12636317025 0024670 0 ustar 00root root 0000000 0000000 { "contentUri": "http://news.google.com/news/url?sa=t&fd=R&ct2=us&usg=AFQjCNGOuNpkO_3eDYWh76D8lZDl5jI_pQ&clid=c3a7d30bb8a4878e06b80cf16b898331&cid=52778830388718&ei=bwNNVfDFItjU3AGy-4HQDQ&url=http://www.usatoday.com/story/news/politics/2015/05/08/obama-nike-visit-free-trade-jobs-protests/26974883/" } python-0.7.4/tests/mock-data/request/eng-url-sentiment.json 0000664 0000000 0000000 00000000457 12636317025 0024020 0 ustar 00root root 0000000 0000000 { "contentUri": "http://news.google.com/news/url?sa=t&fd=R&ct2=us&usg=AFQjCNGOuNpkO_3eDYWh76D8lZDl5jI_pQ&clid=c3a7d30bb8a4878e06b80cf16b898331&cid=52778830388718&ei=bwNNVfDFItjU3AGy-4HQDQ&url=http://www.usatoday.com/story/news/politics/2015/05/08/obama-nike-visit-free-trade-jobs-protests/26974883/" } python-0.7.4/tests/mock-data/request/fra-doc-categories.json 0000664 0000000 0000000 00000014322 12636317025 0024075 0 ustar 00root root 0000000 0000000 { "content": "Les Etats-Unis face au défi persistant du chômage\n\nUn chômeur américain sur deux dit souffrir d'anxiété ou de dépression et a dû emprunter de l'argent à des amis. Selon une enquête publiée, lundi 18 janvier, par le Census Bureau (équivalent de l'Insee), en deux ans, le nombre de couples au chômage avec enfants mineurs a doublé. Près de 40 % des ces parents notent des \"modifications de comportement\" chez leurs enfants qu'ils attribuent à leur perte du travail. La moitié évoquent une \"transformation fondamentale\" de leur existence - le premier des changements consistant en la perte presque instantanée de toute couverture sociale.\nDurant tout le mois de décembre, à l'approche de l'anniversaire de la prise de fonctions du président Barack Obama, le 20 janvier 2009, les reportages et les enquêtes sur les conséquences de ces destructions d'emploi sont devenus une préoccupation obsédante dans les médias. \"Je me sens comme la lie de la terre\", disait récemment un chômeur à une heure de grande écoute. Alors, l'Amérique découvre sur les écrans tous ces visages ravagés qui évoquent leur \"honte\" et s'interroge : 10 % de chômage, comment en est-on arrivé là ?\n\nPour beaucoup d'analystes, c'est pour avoir négligé l'impact du chômage alors que se profilaient des signes de reprise économique (et surtout financière) que la Maison Blanche et le Parti démocrate se trouvent confrontés à une forte désaffection de l'opinion à dix mois des élections à mi-mandat de novembre.\n\nAlors que le thème de l'emploi envahissait le champ des préoccupations, M. Obama a continué de donner la priorité à la réforme de la santé, à la lutte contre le réchauffement climatique ou la régulation financière. Tous sujets essentiels mais \"bien moins palpables, dans une période de crise aiguë, que le chômage, qui arase tout\", note Dean Baker, codirecteur du Centre de recherches sur les politiques économiques, un groupe de réflexion démocrate à Washington.\n\nUne étude du département du travail, publiée le 8 janvier, montre une différence essentielle entre l'impact de la crise actuelle sur l'emploi et les précédentes récessions. Lors de celles de 1974-1976 et de 1990-1993, le chômage était moins important, tant en chiffres absolus qu'en durée. Cette comparaison reste valide pour la récession de 1981-1983, qui vit le président républicain Ronald Reagan, un an après son élection, enregistrer son plus bas soutien dans l'opinion.\n\nPour résumer le désastre actuel : les Etats-Unis ont perdu depuis deux ans 5,24 % de leur emploi, alors que la chute n'avait été que de 1,4 % à 3 %, au pire, lors des récessions précédentes. Entre chômage total et partiel, la crise touche le travail de près d' un Américain sur cinq. N'ayant cessé de répéter que son pays affrontait \"la pire crise depuis la Grande Dépression\" des années 1930, Barack Obama avait donné le sentiment d'être très conscient du problème. Or là est le paradoxe : une fois élu, le président est apparu comme un dirigeant qui a fait un diagnostic correct mais n'en a tiré aucune conclusion.\n\nL'Amérique avait perdu 3 078 000 chômeurs lors de la dernière année du mandat de George Bush ; elle en a perdu 4 228 000 en un an de présidence Obama ! Le 10 janvier, invoquant \"l'urgence\", Christina Romer, présidente du conseil économique de M. Obama, a appelé à vite injecter 75 milliards de dollars supplémentaires pour régénérer l'emploi. Nul ne doute que M. Obama privilégiera cette nécessité en 2010.\n\nComment remédier au problème ? La plupart des analystes, constatant le \"découplage\" entre la reprise économique et celle de l'emploi, sont circonspects. Chef économiste de Goldman Sachs, Jan Hatzius, dans un texte intitulé \"10 questions pour 2010\", s'attend \"à un solde positif de 100 000 emplois par mois dès le second trimestre, insuffisant pour modifier significativement le taux de chômage\". Compte tenu de leur évolution démographique, les Etats-Unis doivent en effet créer 100 000 emplois mensuels pour juste stabiliser l'emploi.\n\nDean Baker explique encore que la marge de manoeuvre présidentielle est restreinte : \"Obama a raté le coche en limitant son plan de relance. Maintenant, il lui est politiquement impossible de retourner devant le Congrès pour l'augmenter. Les conséquences sont désastreuses. Même s'il lui reste 200 milliards de dollars à dépenser (sur 787 milliards), l'essentiel de l'impact du plan est passé.\"\n\nLe pire, selon lui, est que le président a fait son choix en toute connaissance de cause, pour \"privilégier la politique\". C'est-à-dire un compromis avec certains républicains qu'il n'a jamais obtenu. Pour M. Baker, cette quête du \"consensus\" a entraîné son parti dans l'état où il est. Et de conclure : \"Les républicains ont une stratégie efficace : ils bloquent tout changement pour dénoncer ensuite un président qui n'agit pas. Il est temps que celui-ci dénonce ce comportement de sabotage de l'économie nationale.\"\n\nMercredi, M. Obama a dit \"regretter d'avoir perdu le sens du contact direct avec les Américains sur leurs valeurs essentielles\". Son principal conseiller, David Axelrod, a évoqué \"les salaires bloqués, les emplois perdus\". Pour autant, changera-t-il d'attitude vis-à-vis du Congrès ? Peu y croient.\n\nLa Chambre a voté en décembre 2009 une loi sur la création d'emplois de 174 milliards de dollars non encore adoptée au Sénat. Les républicains assimilent désormais toute dépense publique à une gabegie. Harry Reid, le leader des démocrates au Sénat, négocierait déjà avec eux. Certains imaginent un abandon, pourtant peu probable, du plan d'assurance santé afin de parvenir à un soutien républicain aux embauches dans les PME. D'autres envisagent d'affecter à l'emploi 75 milliards de dollars pris sur le plan de sauvetage de la finance américaine (dit TARP). Plus encore que M. Obama, c'est son parti, tétanisé par la perspective d'une défaite électorale dans dix mois, qui a besoin de mesures rapides.\n\n\n\nhttp://www.lemonde.fr/ameriques/article/2010/01/21/les-etats-unis-face-au-defi-persistant-du-chomage_1294839_3222.html#xtor=RSS-3210\n2010.01.21", "language": "fra", "unit": "doc" } python-0.7.4/tests/mock-data/request/fra-doc-entities.json 0000664 0000000 0000000 00000014322 12636317025 0023574 0 ustar 00root root 0000000 0000000 { "content": "Les Etats-Unis face au défi persistant du chômage\n\nUn chômeur américain sur deux dit souffrir d'anxiété ou de dépression et a dû emprunter de l'argent à des amis. Selon une enquête publiée, lundi 18 janvier, par le Census Bureau (équivalent de l'Insee), en deux ans, le nombre de couples au chômage avec enfants mineurs a doublé. Près de 40 % des ces parents notent des \"modifications de comportement\" chez leurs enfants qu'ils attribuent à leur perte du travail. La moitié évoquent une \"transformation fondamentale\" de leur existence - le premier des changements consistant en la perte presque instantanée de toute couverture sociale.\nDurant tout le mois de décembre, à l'approche de l'anniversaire de la prise de fonctions du président Barack Obama, le 20 janvier 2009, les reportages et les enquêtes sur les conséquences de ces destructions d'emploi sont devenus une préoccupation obsédante dans les médias. \"Je me sens comme la lie de la terre\", disait récemment un chômeur à une heure de grande écoute. Alors, l'Amérique découvre sur les écrans tous ces visages ravagés qui évoquent leur \"honte\" et s'interroge : 10 % de chômage, comment en est-on arrivé là ?\n\nPour beaucoup d'analystes, c'est pour avoir négligé l'impact du chômage alors que se profilaient des signes de reprise économique (et surtout financière) que la Maison Blanche et le Parti démocrate se trouvent confrontés à une forte désaffection de l'opinion à dix mois des élections à mi-mandat de novembre.\n\nAlors que le thème de l'emploi envahissait le champ des préoccupations, M. Obama a continué de donner la priorité à la réforme de la santé, à la lutte contre le réchauffement climatique ou la régulation financière. Tous sujets essentiels mais \"bien moins palpables, dans une période de crise aiguë, que le chômage, qui arase tout\", note Dean Baker, codirecteur du Centre de recherches sur les politiques économiques, un groupe de réflexion démocrate à Washington.\n\nUne étude du département du travail, publiée le 8 janvier, montre une différence essentielle entre l'impact de la crise actuelle sur l'emploi et les précédentes récessions. Lors de celles de 1974-1976 et de 1990-1993, le chômage était moins important, tant en chiffres absolus qu'en durée. Cette comparaison reste valide pour la récession de 1981-1983, qui vit le président républicain Ronald Reagan, un an après son élection, enregistrer son plus bas soutien dans l'opinion.\n\nPour résumer le désastre actuel : les Etats-Unis ont perdu depuis deux ans 5,24 % de leur emploi, alors que la chute n'avait été que de 1,4 % à 3 %, au pire, lors des récessions précédentes. Entre chômage total et partiel, la crise touche le travail de près d' un Américain sur cinq. N'ayant cessé de répéter que son pays affrontait \"la pire crise depuis la Grande Dépression\" des années 1930, Barack Obama avait donné le sentiment d'être très conscient du problème. Or là est le paradoxe : une fois élu, le président est apparu comme un dirigeant qui a fait un diagnostic correct mais n'en a tiré aucune conclusion.\n\nL'Amérique avait perdu 3 078 000 chômeurs lors de la dernière année du mandat de George Bush ; elle en a perdu 4 228 000 en un an de présidence Obama ! Le 10 janvier, invoquant \"l'urgence\", Christina Romer, présidente du conseil économique de M. Obama, a appelé à vite injecter 75 milliards de dollars supplémentaires pour régénérer l'emploi. Nul ne doute que M. Obama privilégiera cette nécessité en 2010.\n\nComment remédier au problème ? La plupart des analystes, constatant le \"découplage\" entre la reprise économique et celle de l'emploi, sont circonspects. Chef économiste de Goldman Sachs, Jan Hatzius, dans un texte intitulé \"10 questions pour 2010\", s'attend \"à un solde positif de 100 000 emplois par mois dès le second trimestre, insuffisant pour modifier significativement le taux de chômage\". Compte tenu de leur évolution démographique, les Etats-Unis doivent en effet créer 100 000 emplois mensuels pour juste stabiliser l'emploi.\n\nDean Baker explique encore que la marge de manoeuvre présidentielle est restreinte : \"Obama a raté le coche en limitant son plan de relance. Maintenant, il lui est politiquement impossible de retourner devant le Congrès pour l'augmenter. Les conséquences sont désastreuses. Même s'il lui reste 200 milliards de dollars à dépenser (sur 787 milliards), l'essentiel de l'impact du plan est passé.\"\n\nLe pire, selon lui, est que le président a fait son choix en toute connaissance de cause, pour \"privilégier la politique\". C'est-à-dire un compromis avec certains républicains qu'il n'a jamais obtenu. Pour M. Baker, cette quête du \"consensus\" a entraîné son parti dans l'état où il est. Et de conclure : \"Les républicains ont une stratégie efficace : ils bloquent tout changement pour dénoncer ensuite un président qui n'agit pas. Il est temps que celui-ci dénonce ce comportement de sabotage de l'économie nationale.\"\n\nMercredi, M. Obama a dit \"regretter d'avoir perdu le sens du contact direct avec les Américains sur leurs valeurs essentielles\". Son principal conseiller, David Axelrod, a évoqué \"les salaires bloqués, les emplois perdus\". Pour autant, changera-t-il d'attitude vis-à-vis du Congrès ? Peu y croient.\n\nLa Chambre a voté en décembre 2009 une loi sur la création d'emplois de 174 milliards de dollars non encore adoptée au Sénat. Les républicains assimilent désormais toute dépense publique à une gabegie. Harry Reid, le leader des démocrates au Sénat, négocierait déjà avec eux. Certains imaginent un abandon, pourtant peu probable, du plan d'assurance santé afin de parvenir à un soutien républicain aux embauches dans les PME. D'autres envisagent d'affecter à l'emploi 75 milliards de dollars pris sur le plan de sauvetage de la finance américaine (dit TARP). Plus encore que M. Obama, c'est son parti, tétanisé par la perspective d'une défaite électorale dans dix mois, qui a besoin de mesures rapides.\n\n\n\nhttp://www.lemonde.fr/ameriques/article/2010/01/21/les-etats-unis-face-au-defi-persistant-du-chomage_1294839_3222.html#xtor=RSS-3210\n2010.01.21", "language": "fra", "unit": "doc" } python-0.7.4/tests/mock-data/request/fra-doc-entities_linked.json 0000664 0000000 0000000 00000014322 12636317025 0025122 0 ustar 00root root 0000000 0000000 { "content": "Les Etats-Unis face au défi persistant du chômage\n\nUn chômeur américain sur deux dit souffrir d'anxiété ou de dépression et a dû emprunter de l'argent à des amis. Selon une enquête publiée, lundi 18 janvier, par le Census Bureau (équivalent de l'Insee), en deux ans, le nombre de couples au chômage avec enfants mineurs a doublé. Près de 40 % des ces parents notent des \"modifications de comportement\" chez leurs enfants qu'ils attribuent à leur perte du travail. La moitié évoquent une \"transformation fondamentale\" de leur existence - le premier des changements consistant en la perte presque instantanée de toute couverture sociale.\nDurant tout le mois de décembre, à l'approche de l'anniversaire de la prise de fonctions du président Barack Obama, le 20 janvier 2009, les reportages et les enquêtes sur les conséquences de ces destructions d'emploi sont devenus une préoccupation obsédante dans les médias. \"Je me sens comme la lie de la terre\", disait récemment un chômeur à une heure de grande écoute. Alors, l'Amérique découvre sur les écrans tous ces visages ravagés qui évoquent leur \"honte\" et s'interroge : 10 % de chômage, comment en est-on arrivé là ?\n\nPour beaucoup d'analystes, c'est pour avoir négligé l'impact du chômage alors que se profilaient des signes de reprise économique (et surtout financière) que la Maison Blanche et le Parti démocrate se trouvent confrontés à une forte désaffection de l'opinion à dix mois des élections à mi-mandat de novembre.\n\nAlors que le thème de l'emploi envahissait le champ des préoccupations, M. Obama a continué de donner la priorité à la réforme de la santé, à la lutte contre le réchauffement climatique ou la régulation financière. Tous sujets essentiels mais \"bien moins palpables, dans une période de crise aiguë, que le chômage, qui arase tout\", note Dean Baker, codirecteur du Centre de recherches sur les politiques économiques, un groupe de réflexion démocrate à Washington.\n\nUne étude du département du travail, publiée le 8 janvier, montre une différence essentielle entre l'impact de la crise actuelle sur l'emploi et les précédentes récessions. Lors de celles de 1974-1976 et de 1990-1993, le chômage était moins important, tant en chiffres absolus qu'en durée. Cette comparaison reste valide pour la récession de 1981-1983, qui vit le président républicain Ronald Reagan, un an après son élection, enregistrer son plus bas soutien dans l'opinion.\n\nPour résumer le désastre actuel : les Etats-Unis ont perdu depuis deux ans 5,24 % de leur emploi, alors que la chute n'avait été que de 1,4 % à 3 %, au pire, lors des récessions précédentes. Entre chômage total et partiel, la crise touche le travail de près d' un Américain sur cinq. N'ayant cessé de répéter que son pays affrontait \"la pire crise depuis la Grande Dépression\" des années 1930, Barack Obama avait donné le sentiment d'être très conscient du problème. Or là est le paradoxe : une fois élu, le président est apparu comme un dirigeant qui a fait un diagnostic correct mais n'en a tiré aucune conclusion.\n\nL'Amérique avait perdu 3 078 000 chômeurs lors de la dernière année du mandat de George Bush ; elle en a perdu 4 228 000 en un an de présidence Obama ! Le 10 janvier, invoquant \"l'urgence\", Christina Romer, présidente du conseil économique de M. Obama, a appelé à vite injecter 75 milliards de dollars supplémentaires pour régénérer l'emploi. Nul ne doute que M. Obama privilégiera cette nécessité en 2010.\n\nComment remédier au problème ? La plupart des analystes, constatant le \"découplage\" entre la reprise économique et celle de l'emploi, sont circonspects. Chef économiste de Goldman Sachs, Jan Hatzius, dans un texte intitulé \"10 questions pour 2010\", s'attend \"à un solde positif de 100 000 emplois par mois dès le second trimestre, insuffisant pour modifier significativement le taux de chômage\". Compte tenu de leur évolution démographique, les Etats-Unis doivent en effet créer 100 000 emplois mensuels pour juste stabiliser l'emploi.\n\nDean Baker explique encore que la marge de manoeuvre présidentielle est restreinte : \"Obama a raté le coche en limitant son plan de relance. Maintenant, il lui est politiquement impossible de retourner devant le Congrès pour l'augmenter. Les conséquences sont désastreuses. Même s'il lui reste 200 milliards de dollars à dépenser (sur 787 milliards), l'essentiel de l'impact du plan est passé.\"\n\nLe pire, selon lui, est que le président a fait son choix en toute connaissance de cause, pour \"privilégier la politique\". C'est-à-dire un compromis avec certains républicains qu'il n'a jamais obtenu. Pour M. Baker, cette quête du \"consensus\" a entraîné son parti dans l'état où il est. Et de conclure : \"Les républicains ont une stratégie efficace : ils bloquent tout changement pour dénoncer ensuite un président qui n'agit pas. Il est temps que celui-ci dénonce ce comportement de sabotage de l'économie nationale.\"\n\nMercredi, M. Obama a dit \"regretter d'avoir perdu le sens du contact direct avec les Américains sur leurs valeurs essentielles\". Son principal conseiller, David Axelrod, a évoqué \"les salaires bloqués, les emplois perdus\". Pour autant, changera-t-il d'attitude vis-à-vis du Congrès ? Peu y croient.\n\nLa Chambre a voté en décembre 2009 une loi sur la création d'emplois de 174 milliards de dollars non encore adoptée au Sénat. Les républicains assimilent désormais toute dépense publique à une gabegie. Harry Reid, le leader des démocrates au Sénat, négocierait déjà avec eux. Certains imaginent un abandon, pourtant peu probable, du plan d'assurance santé afin de parvenir à un soutien républicain aux embauches dans les PME. D'autres envisagent d'affecter à l'emploi 75 milliards de dollars pris sur le plan de sauvetage de la finance américaine (dit TARP). Plus encore que M. Obama, c'est son parti, tétanisé par la perspective d'une défaite électorale dans dix mois, qui a besoin de mesures rapides.\n\n\n\nhttp://www.lemonde.fr/ameriques/article/2010/01/21/les-etats-unis-face-au-defi-persistant-du-chomage_1294839_3222.html#xtor=RSS-3210\n2010.01.21", "language": "fra", "unit": "doc" } python-0.7.4/tests/mock-data/request/fra-doc-language.json 0000664 0000000 0000000 00000014322 12636317025 0023533 0 ustar 00root root 0000000 0000000 { "content": "Les Etats-Unis face au défi persistant du chômage\n\nUn chômeur américain sur deux dit souffrir d'anxiété ou de dépression et a dû emprunter de l'argent à des amis. Selon une enquête publiée, lundi 18 janvier, par le Census Bureau (équivalent de l'Insee), en deux ans, le nombre de couples au chômage avec enfants mineurs a doublé. Près de 40 % des ces parents notent des \"modifications de comportement\" chez leurs enfants qu'ils attribuent à leur perte du travail. La moitié évoquent une \"transformation fondamentale\" de leur existence - le premier des changements consistant en la perte presque instantanée de toute couverture sociale.\nDurant tout le mois de décembre, à l'approche de l'anniversaire de la prise de fonctions du président Barack Obama, le 20 janvier 2009, les reportages et les enquêtes sur les conséquences de ces destructions d'emploi sont devenus une préoccupation obsédante dans les médias. \"Je me sens comme la lie de la terre\", disait récemment un chômeur à une heure de grande écoute. Alors, l'Amérique découvre sur les écrans tous ces visages ravagés qui évoquent leur \"honte\" et s'interroge : 10 % de chômage, comment en est-on arrivé là ?\n\nPour beaucoup d'analystes, c'est pour avoir négligé l'impact du chômage alors que se profilaient des signes de reprise économique (et surtout financière) que la Maison Blanche et le Parti démocrate se trouvent confrontés à une forte désaffection de l'opinion à dix mois des élections à mi-mandat de novembre.\n\nAlors que le thème de l'emploi envahissait le champ des préoccupations, M. Obama a continué de donner la priorité à la réforme de la santé, à la lutte contre le réchauffement climatique ou la régulation financière. Tous sujets essentiels mais \"bien moins palpables, dans une période de crise aiguë, que le chômage, qui arase tout\", note Dean Baker, codirecteur du Centre de recherches sur les politiques économiques, un groupe de réflexion démocrate à Washington.\n\nUne étude du département du travail, publiée le 8 janvier, montre une différence essentielle entre l'impact de la crise actuelle sur l'emploi et les précédentes récessions. Lors de celles de 1974-1976 et de 1990-1993, le chômage était moins important, tant en chiffres absolus qu'en durée. Cette comparaison reste valide pour la récession de 1981-1983, qui vit le président républicain Ronald Reagan, un an après son élection, enregistrer son plus bas soutien dans l'opinion.\n\nPour résumer le désastre actuel : les Etats-Unis ont perdu depuis deux ans 5,24 % de leur emploi, alors que la chute n'avait été que de 1,4 % à 3 %, au pire, lors des récessions précédentes. Entre chômage total et partiel, la crise touche le travail de près d' un Américain sur cinq. N'ayant cessé de répéter que son pays affrontait \"la pire crise depuis la Grande Dépression\" des années 1930, Barack Obama avait donné le sentiment d'être très conscient du problème. Or là est le paradoxe : une fois élu, le président est apparu comme un dirigeant qui a fait un diagnostic correct mais n'en a tiré aucune conclusion.\n\nL'Amérique avait perdu 3 078 000 chômeurs lors de la dernière année du mandat de George Bush ; elle en a perdu 4 228 000 en un an de présidence Obama ! Le 10 janvier, invoquant \"l'urgence\", Christina Romer, présidente du conseil économique de M. Obama, a appelé à vite injecter 75 milliards de dollars supplémentaires pour régénérer l'emploi. Nul ne doute que M. Obama privilégiera cette nécessité en 2010.\n\nComment remédier au problème ? La plupart des analystes, constatant le \"découplage\" entre la reprise économique et celle de l'emploi, sont circonspects. Chef économiste de Goldman Sachs, Jan Hatzius, dans un texte intitulé \"10 questions pour 2010\", s'attend \"à un solde positif de 100 000 emplois par mois dès le second trimestre, insuffisant pour modifier significativement le taux de chômage\". Compte tenu de leur évolution démographique, les Etats-Unis doivent en effet créer 100 000 emplois mensuels pour juste stabiliser l'emploi.\n\nDean Baker explique encore que la marge de manoeuvre présidentielle est restreinte : \"Obama a raté le coche en limitant son plan de relance. Maintenant, il lui est politiquement impossible de retourner devant le Congrès pour l'augmenter. Les conséquences sont désastreuses. Même s'il lui reste 200 milliards de dollars à dépenser (sur 787 milliards), l'essentiel de l'impact du plan est passé.\"\n\nLe pire, selon lui, est que le président a fait son choix en toute connaissance de cause, pour \"privilégier la politique\". C'est-à-dire un compromis avec certains républicains qu'il n'a jamais obtenu. Pour M. Baker, cette quête du \"consensus\" a entraîné son parti dans l'état où il est. Et de conclure : \"Les républicains ont une stratégie efficace : ils bloquent tout changement pour dénoncer ensuite un président qui n'agit pas. Il est temps que celui-ci dénonce ce comportement de sabotage de l'économie nationale.\"\n\nMercredi, M. Obama a dit \"regretter d'avoir perdu le sens du contact direct avec les Américains sur leurs valeurs essentielles\". Son principal conseiller, David Axelrod, a évoqué \"les salaires bloqués, les emplois perdus\". Pour autant, changera-t-il d'attitude vis-à-vis du Congrès ? Peu y croient.\n\nLa Chambre a voté en décembre 2009 une loi sur la création d'emplois de 174 milliards de dollars non encore adoptée au Sénat. Les républicains assimilent désormais toute dépense publique à une gabegie. Harry Reid, le leader des démocrates au Sénat, négocierait déjà avec eux. Certains imaginent un abandon, pourtant peu probable, du plan d'assurance santé afin de parvenir à un soutien républicain aux embauches dans les PME. D'autres envisagent d'affecter à l'emploi 75 milliards de dollars pris sur le plan de sauvetage de la finance américaine (dit TARP). Plus encore que M. Obama, c'est son parti, tétanisé par la perspective d'une défaite électorale dans dix mois, qui a besoin de mesures rapides.\n\n\n\nhttp://www.lemonde.fr/ameriques/article/2010/01/21/les-etats-unis-face-au-defi-persistant-du-chomage_1294839_3222.html#xtor=RSS-3210\n2010.01.21", "language": "fra", "unit": "doc" } python-0.7.4/tests/mock-data/request/fra-doc-morphology_complete.json 0000664 0000000 0000000 00000014322 12636317025 0026037 0 ustar 00root root 0000000 0000000 { "content": "Les Etats-Unis face au défi persistant du chômage\n\nUn chômeur américain sur deux dit souffrir d'anxiété ou de dépression et a dû emprunter de l'argent à des amis. Selon une enquête publiée, lundi 18 janvier, par le Census Bureau (équivalent de l'Insee), en deux ans, le nombre de couples au chômage avec enfants mineurs a doublé. Près de 40 % des ces parents notent des \"modifications de comportement\" chez leurs enfants qu'ils attribuent à leur perte du travail. La moitié évoquent une \"transformation fondamentale\" de leur existence - le premier des changements consistant en la perte presque instantanée de toute couverture sociale.\nDurant tout le mois de décembre, à l'approche de l'anniversaire de la prise de fonctions du président Barack Obama, le 20 janvier 2009, les reportages et les enquêtes sur les conséquences de ces destructions d'emploi sont devenus une préoccupation obsédante dans les médias. \"Je me sens comme la lie de la terre\", disait récemment un chômeur à une heure de grande écoute. Alors, l'Amérique découvre sur les écrans tous ces visages ravagés qui évoquent leur \"honte\" et s'interroge : 10 % de chômage, comment en est-on arrivé là ?\n\nPour beaucoup d'analystes, c'est pour avoir négligé l'impact du chômage alors que se profilaient des signes de reprise économique (et surtout financière) que la Maison Blanche et le Parti démocrate se trouvent confrontés à une forte désaffection de l'opinion à dix mois des élections à mi-mandat de novembre.\n\nAlors que le thème de l'emploi envahissait le champ des préoccupations, M. Obama a continué de donner la priorité à la réforme de la santé, à la lutte contre le réchauffement climatique ou la régulation financière. Tous sujets essentiels mais \"bien moins palpables, dans une période de crise aiguë, que le chômage, qui arase tout\", note Dean Baker, codirecteur du Centre de recherches sur les politiques économiques, un groupe de réflexion démocrate à Washington.\n\nUne étude du département du travail, publiée le 8 janvier, montre une différence essentielle entre l'impact de la crise actuelle sur l'emploi et les précédentes récessions. Lors de celles de 1974-1976 et de 1990-1993, le chômage était moins important, tant en chiffres absolus qu'en durée. Cette comparaison reste valide pour la récession de 1981-1983, qui vit le président républicain Ronald Reagan, un an après son élection, enregistrer son plus bas soutien dans l'opinion.\n\nPour résumer le désastre actuel : les Etats-Unis ont perdu depuis deux ans 5,24 % de leur emploi, alors que la chute n'avait été que de 1,4 % à 3 %, au pire, lors des récessions précédentes. Entre chômage total et partiel, la crise touche le travail de près d' un Américain sur cinq. N'ayant cessé de répéter que son pays affrontait \"la pire crise depuis la Grande Dépression\" des années 1930, Barack Obama avait donné le sentiment d'être très conscient du problème. Or là est le paradoxe : une fois élu, le président est apparu comme un dirigeant qui a fait un diagnostic correct mais n'en a tiré aucune conclusion.\n\nL'Amérique avait perdu 3 078 000 chômeurs lors de la dernière année du mandat de George Bush ; elle en a perdu 4 228 000 en un an de présidence Obama ! Le 10 janvier, invoquant \"l'urgence\", Christina Romer, présidente du conseil économique de M. Obama, a appelé à vite injecter 75 milliards de dollars supplémentaires pour régénérer l'emploi. Nul ne doute que M. Obama privilégiera cette nécessité en 2010.\n\nComment remédier au problème ? La plupart des analystes, constatant le \"découplage\" entre la reprise économique et celle de l'emploi, sont circonspects. Chef économiste de Goldman Sachs, Jan Hatzius, dans un texte intitulé \"10 questions pour 2010\", s'attend \"à un solde positif de 100 000 emplois par mois dès le second trimestre, insuffisant pour modifier significativement le taux de chômage\". Compte tenu de leur évolution démographique, les Etats-Unis doivent en effet créer 100 000 emplois mensuels pour juste stabiliser l'emploi.\n\nDean Baker explique encore que la marge de manoeuvre présidentielle est restreinte : \"Obama a raté le coche en limitant son plan de relance. Maintenant, il lui est politiquement impossible de retourner devant le Congrès pour l'augmenter. Les conséquences sont désastreuses. Même s'il lui reste 200 milliards de dollars à dépenser (sur 787 milliards), l'essentiel de l'impact du plan est passé.\"\n\nLe pire, selon lui, est que le président a fait son choix en toute connaissance de cause, pour \"privilégier la politique\". C'est-à-dire un compromis avec certains républicains qu'il n'a jamais obtenu. Pour M. Baker, cette quête du \"consensus\" a entraîné son parti dans l'état où il est. Et de conclure : \"Les républicains ont une stratégie efficace : ils bloquent tout changement pour dénoncer ensuite un président qui n'agit pas. Il est temps que celui-ci dénonce ce comportement de sabotage de l'économie nationale.\"\n\nMercredi, M. Obama a dit \"regretter d'avoir perdu le sens du contact direct avec les Américains sur leurs valeurs essentielles\". Son principal conseiller, David Axelrod, a évoqué \"les salaires bloqués, les emplois perdus\". Pour autant, changera-t-il d'attitude vis-à-vis du Congrès ? Peu y croient.\n\nLa Chambre a voté en décembre 2009 une loi sur la création d'emplois de 174 milliards de dollars non encore adoptée au Sénat. Les républicains assimilent désormais toute dépense publique à une gabegie. Harry Reid, le leader des démocrates au Sénat, négocierait déjà avec eux. Certains imaginent un abandon, pourtant peu probable, du plan d'assurance santé afin de parvenir à un soutien républicain aux embauches dans les PME. D'autres envisagent d'affecter à l'emploi 75 milliards de dollars pris sur le plan de sauvetage de la finance américaine (dit TARP). Plus encore que M. Obama, c'est son parti, tétanisé par la perspective d'une défaite électorale dans dix mois, qui a besoin de mesures rapides.\n\n\n\nhttp://www.lemonde.fr/ameriques/article/2010/01/21/les-etats-unis-face-au-defi-persistant-du-chomage_1294839_3222.html#xtor=RSS-3210\n2010.01.21", "language": "fra", "unit": "doc" } python-0.7.4/tests/mock-data/request/fra-doc-sentiment.json 0000664 0000000 0000000 00000014322 12636317025 0023756 0 ustar 00root root 0000000 0000000 { "content": "Les Etats-Unis face au défi persistant du chômage\n\nUn chômeur américain sur deux dit souffrir d'anxiété ou de dépression et a dû emprunter de l'argent à des amis. Selon une enquête publiée, lundi 18 janvier, par le Census Bureau (équivalent de l'Insee), en deux ans, le nombre de couples au chômage avec enfants mineurs a doublé. Près de 40 % des ces parents notent des \"modifications de comportement\" chez leurs enfants qu'ils attribuent à leur perte du travail. La moitié évoquent une \"transformation fondamentale\" de leur existence - le premier des changements consistant en la perte presque instantanée de toute couverture sociale.\nDurant tout le mois de décembre, à l'approche de l'anniversaire de la prise de fonctions du président Barack Obama, le 20 janvier 2009, les reportages et les enquêtes sur les conséquences de ces destructions d'emploi sont devenus une préoccupation obsédante dans les médias. \"Je me sens comme la lie de la terre\", disait récemment un chômeur à une heure de grande écoute. Alors, l'Amérique découvre sur les écrans tous ces visages ravagés qui évoquent leur \"honte\" et s'interroge : 10 % de chômage, comment en est-on arrivé là ?\n\nPour beaucoup d'analystes, c'est pour avoir négligé l'impact du chômage alors que se profilaient des signes de reprise économique (et surtout financière) que la Maison Blanche et le Parti démocrate se trouvent confrontés à une forte désaffection de l'opinion à dix mois des élections à mi-mandat de novembre.\n\nAlors que le thème de l'emploi envahissait le champ des préoccupations, M. Obama a continué de donner la priorité à la réforme de la santé, à la lutte contre le réchauffement climatique ou la régulation financière. Tous sujets essentiels mais \"bien moins palpables, dans une période de crise aiguë, que le chômage, qui arase tout\", note Dean Baker, codirecteur du Centre de recherches sur les politiques économiques, un groupe de réflexion démocrate à Washington.\n\nUne étude du département du travail, publiée le 8 janvier, montre une différence essentielle entre l'impact de la crise actuelle sur l'emploi et les précédentes récessions. Lors de celles de 1974-1976 et de 1990-1993, le chômage était moins important, tant en chiffres absolus qu'en durée. Cette comparaison reste valide pour la récession de 1981-1983, qui vit le président républicain Ronald Reagan, un an après son élection, enregistrer son plus bas soutien dans l'opinion.\n\nPour résumer le désastre actuel : les Etats-Unis ont perdu depuis deux ans 5,24 % de leur emploi, alors que la chute n'avait été que de 1,4 % à 3 %, au pire, lors des récessions précédentes. Entre chômage total et partiel, la crise touche le travail de près d' un Américain sur cinq. N'ayant cessé de répéter que son pays affrontait \"la pire crise depuis la Grande Dépression\" des années 1930, Barack Obama avait donné le sentiment d'être très conscient du problème. Or là est le paradoxe : une fois élu, le président est apparu comme un dirigeant qui a fait un diagnostic correct mais n'en a tiré aucune conclusion.\n\nL'Amérique avait perdu 3 078 000 chômeurs lors de la dernière année du mandat de George Bush ; elle en a perdu 4 228 000 en un an de présidence Obama ! Le 10 janvier, invoquant \"l'urgence\", Christina Romer, présidente du conseil économique de M. Obama, a appelé à vite injecter 75 milliards de dollars supplémentaires pour régénérer l'emploi. Nul ne doute que M. Obama privilégiera cette nécessité en 2010.\n\nComment remédier au problème ? La plupart des analystes, constatant le \"découplage\" entre la reprise économique et celle de l'emploi, sont circonspects. Chef économiste de Goldman Sachs, Jan Hatzius, dans un texte intitulé \"10 questions pour 2010\", s'attend \"à un solde positif de 100 000 emplois par mois dès le second trimestre, insuffisant pour modifier significativement le taux de chômage\". Compte tenu de leur évolution démographique, les Etats-Unis doivent en effet créer 100 000 emplois mensuels pour juste stabiliser l'emploi.\n\nDean Baker explique encore que la marge de manoeuvre présidentielle est restreinte : \"Obama a raté le coche en limitant son plan de relance. Maintenant, il lui est politiquement impossible de retourner devant le Congrès pour l'augmenter. Les conséquences sont désastreuses. Même s'il lui reste 200 milliards de dollars à dépenser (sur 787 milliards), l'essentiel de l'impact du plan est passé.\"\n\nLe pire, selon lui, est que le président a fait son choix en toute connaissance de cause, pour \"privilégier la politique\". C'est-à-dire un compromis avec certains républicains qu'il n'a jamais obtenu. Pour M. Baker, cette quête du \"consensus\" a entraîné son parti dans l'état où il est. Et de conclure : \"Les républicains ont une stratégie efficace : ils bloquent tout changement pour dénoncer ensuite un président qui n'agit pas. Il est temps que celui-ci dénonce ce comportement de sabotage de l'économie nationale.\"\n\nMercredi, M. Obama a dit \"regretter d'avoir perdu le sens du contact direct avec les Américains sur leurs valeurs essentielles\". Son principal conseiller, David Axelrod, a évoqué \"les salaires bloqués, les emplois perdus\". Pour autant, changera-t-il d'attitude vis-à-vis du Congrès ? Peu y croient.\n\nLa Chambre a voté en décembre 2009 une loi sur la création d'emplois de 174 milliards de dollars non encore adoptée au Sénat. Les républicains assimilent désormais toute dépense publique à une gabegie. Harry Reid, le leader des démocrates au Sénat, négocierait déjà avec eux. Certains imaginent un abandon, pourtant peu probable, du plan d'assurance santé afin de parvenir à un soutien républicain aux embauches dans les PME. D'autres envisagent d'affecter à l'emploi 75 milliards de dollars pris sur le plan de sauvetage de la finance américaine (dit TARP). Plus encore que M. Obama, c'est son parti, tétanisé par la perspective d'une défaite électorale dans dix mois, qui a besoin de mesures rapides.\n\n\n\nhttp://www.lemonde.fr/ameriques/article/2010/01/21/les-etats-unis-face-au-defi-persistant-du-chomage_1294839_3222.html#xtor=RSS-3210\n2010.01.21", "language": "fra", "unit": "doc" } python-0.7.4/tests/mock-data/request/fra-sentence-categories.json 0000664 0000000 0000000 00000001072 12636317025 0025132 0 ustar 00root root 0000000 0000000 { "content": "Richard Holbrooke veut souligner à quel point l'administration Obama est engagée dans un \"intense processus diplomatique\" pour prendre en compte la dimension régionale du conflit en Afghanistan. \"Il n'y a pas d'issue en Afghanistan sans prendre en compte tous ceux qui ont un intérêt stratégique (dans la région), tous les acteurs, y compris ceux qui n'ont pas de frontière commune avec ce pays\", dit-il, en mentionnant l'Inde, la Russie, la Turquie, l'Arabie saoudite, les Emirats arabes unis.", "language": "fra", "unit": "sentence" } python-0.7.4/tests/mock-data/request/fra-sentence-entities.json 0000664 0000000 0000000 00000001072 12636317025 0024631 0 ustar 00root root 0000000 0000000 { "content": "Richard Holbrooke veut souligner à quel point l'administration Obama est engagée dans un \"intense processus diplomatique\" pour prendre en compte la dimension régionale du conflit en Afghanistan. \"Il n'y a pas d'issue en Afghanistan sans prendre en compte tous ceux qui ont un intérêt stratégique (dans la région), tous les acteurs, y compris ceux qui n'ont pas de frontière commune avec ce pays\", dit-il, en mentionnant l'Inde, la Russie, la Turquie, l'Arabie saoudite, les Emirats arabes unis.", "language": "fra", "unit": "sentence" } python-0.7.4/tests/mock-data/request/fra-sentence-entities_linked.json 0000664 0000000 0000000 00000001072 12636317025 0026157 0 ustar 00root root 0000000 0000000 { "content": "Richard Holbrooke veut souligner à quel point l'administration Obama est engagée dans un \"intense processus diplomatique\" pour prendre en compte la dimension régionale du conflit en Afghanistan. \"Il n'y a pas d'issue en Afghanistan sans prendre en compte tous ceux qui ont un intérêt stratégique (dans la région), tous les acteurs, y compris ceux qui n'ont pas de frontière commune avec ce pays\", dit-il, en mentionnant l'Inde, la Russie, la Turquie, l'Arabie saoudite, les Emirats arabes unis.", "language": "fra", "unit": "sentence" } python-0.7.4/tests/mock-data/request/fra-sentence-language.json 0000664 0000000 0000000 00000001072 12636317025 0024570 0 ustar 00root root 0000000 0000000 { "content": "Richard Holbrooke veut souligner à quel point l'administration Obama est engagée dans un \"intense processus diplomatique\" pour prendre en compte la dimension régionale du conflit en Afghanistan. \"Il n'y a pas d'issue en Afghanistan sans prendre en compte tous ceux qui ont un intérêt stratégique (dans la région), tous les acteurs, y compris ceux qui n'ont pas de frontière commune avec ce pays\", dit-il, en mentionnant l'Inde, la Russie, la Turquie, l'Arabie saoudite, les Emirats arabes unis.", "language": "fra", "unit": "sentence" } python-0.7.4/tests/mock-data/request/fra-sentence-morphology_complete.json 0000664 0000000 0000000 00000001072 12636317025 0027074 0 ustar 00root root 0000000 0000000 { "content": "Richard Holbrooke veut souligner à quel point l'administration Obama est engagée dans un \"intense processus diplomatique\" pour prendre en compte la dimension régionale du conflit en Afghanistan. \"Il n'y a pas d'issue en Afghanistan sans prendre en compte tous ceux qui ont un intérêt stratégique (dans la région), tous les acteurs, y compris ceux qui n'ont pas de frontière commune avec ce pays\", dit-il, en mentionnant l'Inde, la Russie, la Turquie, l'Arabie saoudite, les Emirats arabes unis.", "language": "fra", "unit": "sentence" } python-0.7.4/tests/mock-data/request/fra-sentence-sentiment.json 0000664 0000000 0000000 00000001072 12636317025 0025013 0 ustar 00root root 0000000 0000000 { "content": "Richard Holbrooke veut souligner à quel point l'administration Obama est engagée dans un \"intense processus diplomatique\" pour prendre en compte la dimension régionale du conflit en Afghanistan. \"Il n'y a pas d'issue en Afghanistan sans prendre en compte tous ceux qui ont un intérêt stratégique (dans la région), tous les acteurs, y compris ceux qui n'ont pas de frontière commune avec ce pays\", dit-il, en mentionnant l'Inde, la Russie, la Turquie, l'Arabie saoudite, les Emirats arabes unis.", "language": "fra", "unit": "sentence" } python-0.7.4/tests/mock-data/request/fra-url-categories.json 0000664 0000000 0000000 00000000456 12636317025 0024135 0 ustar 00root root 0000000 0000000 { "contentUri": "http://news.google.com/news/url?sa=t&fd=R&ct2=fr&usg=AFQjCNGx9U_7Ggby5-rrhbrITDDnWavJrQ&clid=c3a7d30bb8a4878e06b80cf16b898331&cid=52779379029255&ei=ZwNNVcDDKILd3QHIhYDIBg&url=http://www.challenges.fr/europe/20150508.CHA5663/elections-britanniques-le-triomphe-de-david-cameron.html" } python-0.7.4/tests/mock-data/request/fra-url-entities.json 0000664 0000000 0000000 00000000456 12636317025 0023634 0 ustar 00root root 0000000 0000000 { "contentUri": "http://news.google.com/news/url?sa=t&fd=R&ct2=fr&usg=AFQjCNGx9U_7Ggby5-rrhbrITDDnWavJrQ&clid=c3a7d30bb8a4878e06b80cf16b898331&cid=52779379029255&ei=ZwNNVcDDKILd3QHIhYDIBg&url=http://www.challenges.fr/europe/20150508.CHA5663/elections-britanniques-le-triomphe-de-david-cameron.html" } python-0.7.4/tests/mock-data/request/fra-url-entities_linked.json 0000664 0000000 0000000 00000000456 12636317025 0025162 0 ustar 00root root 0000000 0000000 { "contentUri": "http://news.google.com/news/url?sa=t&fd=R&ct2=fr&usg=AFQjCNGx9U_7Ggby5-rrhbrITDDnWavJrQ&clid=c3a7d30bb8a4878e06b80cf16b898331&cid=52779379029255&ei=ZwNNVcDDKILd3QHIhYDIBg&url=http://www.challenges.fr/europe/20150508.CHA5663/elections-britanniques-le-triomphe-de-david-cameron.html" } python-0.7.4/tests/mock-data/request/fra-url-language.json 0000664 0000000 0000000 00000000456 12636317025 0023573 0 ustar 00root root 0000000 0000000 { "contentUri": "http://news.google.com/news/url?sa=t&fd=R&ct2=fr&usg=AFQjCNGx9U_7Ggby5-rrhbrITDDnWavJrQ&clid=c3a7d30bb8a4878e06b80cf16b898331&cid=52779379029255&ei=ZwNNVcDDKILd3QHIhYDIBg&url=http://www.challenges.fr/europe/20150508.CHA5663/elections-britanniques-le-triomphe-de-david-cameron.html" } python-0.7.4/tests/mock-data/request/fra-url-morphology_complete.json 0000664 0000000 0000000 00000000456 12636317025 0026077 0 ustar 00root root 0000000 0000000 { "contentUri": "http://news.google.com/news/url?sa=t&fd=R&ct2=fr&usg=AFQjCNGx9U_7Ggby5-rrhbrITDDnWavJrQ&clid=c3a7d30bb8a4878e06b80cf16b898331&cid=52779379029255&ei=ZwNNVcDDKILd3QHIhYDIBg&url=http://www.challenges.fr/europe/20150508.CHA5663/elections-britanniques-le-triomphe-de-david-cameron.html" } python-0.7.4/tests/mock-data/request/fra-url-sentiment.json 0000664 0000000 0000000 00000000456 12636317025 0024016 0 ustar 00root root 0000000 0000000 { "contentUri": "http://news.google.com/news/url?sa=t&fd=R&ct2=fr&usg=AFQjCNGx9U_7Ggby5-rrhbrITDDnWavJrQ&clid=c3a7d30bb8a4878e06b80cf16b898331&cid=52779379029255&ei=ZwNNVcDDKILd3QHIhYDIBg&url=http://www.challenges.fr/europe/20150508.CHA5663/elections-britanniques-le-triomphe-de-david-cameron.html" } python-0.7.4/tests/mock-data/request/jpn-doc-categories.json 0000664 0000000 0000000 00000006230 12636317025 0024113 0 ustar 00root root 0000000 0000000 { "content": "ケネディはマサチューセッツ州ブルックラインで、アイルランド系移民の子孫で投資家のジョセフ・P・ケネディ・シニアの次男として生まれた。名前は母方の祖父でボストン市長も勤めたジョン・F・フィッツジェラルドにちなむ。13歳のときにチョート・スクール（コネチカット州ウォリングフォードの寄宿学校）に入学し、その後1935年にイギリスのロンドン・スクール・オブ・エコノミクスに1年間留学した。帰国後ハーバード大学に入学を認められていたものの、親しい友人が進学を決めたプリンストン大学に入学することにした。しかし、クリスマス休暇中にかかった黄疸のため退学している。\n\n1936年の秋にはハーバード大学に転校したが、在学中にフットボールの試合で背中をひどく痛めた。在学中ヨーロッパへ2度旅行しており、2度目の旅行では父親が大使を務めていたイギリスを訪れている。1940年6月、1938年のミュンヘン協定におけるイギリス外交政策の分析についての卒論『イギリスはなぜ眠ったか』を書き、ハーバードを優等で卒業した。\n\n第二次世界大戦後、彼は戦死した兄ジョセフ・P・ケネディ・ジュニアに代わり政界に入った。1946年にジェームズ・M・カーレイがボストン市長になるために民主党下院議員を辞職した時、ケネディはその議席をかけた補欠選挙に立候補した。父のジョセフが実業家であったこともあり、政治資金には困らなかったので、実現不可能な公約をする必要はなく理想主義を語ることができた。長く精力的なキャンペーンの末に、大差で共和党候補に勝ち、29歳で下院議員となった。当初は父のジョセフとコネがあった同じアイルランド系のジョセフ・マッカーシー上院議員の赤狩りに協力していた。リベラル派のエレノア・ルーズヴェルトはそのことを忘れず、後々までケネディを嫌っていた。下院3期目の1952年には上院議員選挙に出馬し、約70,000票の大差で共和党候補ヘンリー・カボット・ロッジ・ジュニアを破った。以後の彼の支持基盤は北部都市圏のリベラル派インテリ層となる。\n\nケネディは1953年9月12日にフランス系移民の名門の娘であるジャクリーン・リー・ブーヴィエと結婚した。彼はその後2年間に多数回の脊柱の手術を受け上院本会議を長期にわたって欠席したが、手術から回復するまでの間、8名の上院議員の政治的に勇敢であった行為についての本『勇気ある人々』を出版した。この本はその後ピューリツァー賞を受賞した。賞金は黒人の通う学校へ寄付したと言われている。\n\n\n\nhttp://ja.wikipedia.org/wiki/%E3%82%B8%E3%83%A7%E3%83%B3%E3%83%BBF%E3%83%BB%E3%82%B1%E3%83%8D%E3%83%87%E3%82%A3\n2010.01.26", "language": "jpn", "unit": "doc" } python-0.7.4/tests/mock-data/request/jpn-doc-entities.json 0000664 0000000 0000000 00000006230 12636317025 0023612 0 ustar 00root root 0000000 0000000 { "content": "ケネディはマサチューセッツ州ブルックラインで、アイルランド系移民の子孫で投資家のジョセフ・P・ケネディ・シニアの次男として生まれた。名前は母方の祖父でボストン市長も勤めたジョン・F・フィッツジェラルドにちなむ。13歳のときにチョート・スクール（コネチカット州ウォリングフォードの寄宿学校）に入学し、その後1935年にイギリスのロンドン・スクール・オブ・エコノミクスに1年間留学した。帰国後ハーバード大学に入学を認められていたものの、親しい友人が進学を決めたプリンストン大学に入学することにした。しかし、クリスマス休暇中にかかった黄疸のため退学している。\n\n1936年の秋にはハーバード大学に転校したが、在学中にフットボールの試合で背中をひどく痛めた。在学中ヨーロッパへ2度旅行しており、2度目の旅行では父親が大使を務めていたイギリスを訪れている。1940年6月、1938年のミュンヘン協定におけるイギリス外交政策の分析についての卒論『イギリスはなぜ眠ったか』を書き、ハーバードを優等で卒業した。\n\n第二次世界大戦後、彼は戦死した兄ジョセフ・P・ケネディ・ジュニアに代わり政界に入った。1946年にジェームズ・M・カーレイがボストン市長になるために民主党下院議員を辞職した時、ケネディはその議席をかけた補欠選挙に立候補した。父のジョセフが実業家であったこともあり、政治資金には困らなかったので、実現不可能な公約をする必要はなく理想主義を語ることができた。長く精力的なキャンペーンの末に、大差で共和党候補に勝ち、29歳で下院議員となった。当初は父のジョセフとコネがあった同じアイルランド系のジョセフ・マッカーシー上院議員の赤狩りに協力していた。リベラル派のエレノア・ルーズヴェルトはそのことを忘れず、後々までケネディを嫌っていた。下院3期目の1952年には上院議員選挙に出馬し、約70,000票の大差で共和党候補ヘンリー・カボット・ロッジ・ジュニアを破った。以後の彼の支持基盤は北部都市圏のリベラル派インテリ層となる。\n\nケネディは1953年9月12日にフランス系移民の名門の娘であるジャクリーン・リー・ブーヴィエと結婚した。彼はその後2年間に多数回の脊柱の手術を受け上院本会議を長期にわたって欠席したが、手術から回復するまでの間、8名の上院議員の政治的に勇敢であった行為についての本『勇気ある人々』を出版した。この本はその後ピューリツァー賞を受賞した。賞金は黒人の通う学校へ寄付したと言われている。\n\n\n\nhttp://ja.wikipedia.org/wiki/%E3%82%B8%E3%83%A7%E3%83%B3%E3%83%BBF%E3%83%BB%E3%82%B1%E3%83%8D%E3%83%87%E3%82%A3\n2010.01.26", "language": "jpn", "unit": "doc" } python-0.7.4/tests/mock-data/request/jpn-doc-entities_linked.json 0000664 0000000 0000000 00000006230 12636317025 0025140 0 ustar 00root root 0000000 0000000 { "content": "ケネディはマサチューセッツ州ブルックラインで、アイルランド系移民の子孫で投資家のジョセフ・P・ケネディ・シニアの次男として生まれた。名前は母方の祖父でボストン市長も勤めたジョン・F・フィッツジェラルドにちなむ。13歳のときにチョート・スクール（コネチカット州ウォリングフォードの寄宿学校）に入学し、その後1935年にイギリスのロンドン・スクール・オブ・エコノミクスに1年間留学した。帰国後ハーバード大学に入学を認められていたものの、親しい友人が進学を決めたプリンストン大学に入学することにした。しかし、クリスマス休暇中にかかった黄疸のため退学している。\n\n1936年の秋にはハーバード大学に転校したが、在学中にフットボールの試合で背中をひどく痛めた。在学中ヨーロッパへ2度旅行しており、2度目の旅行では父親が大使を務めていたイギリスを訪れている。1940年6月、1938年のミュンヘン協定におけるイギリス外交政策の分析についての卒論『イギリスはなぜ眠ったか』を書き、ハーバードを優等で卒業した。\n\n第二次世界大戦後、彼は戦死した兄ジョセフ・P・ケネディ・ジュニアに代わり政界に入った。1946年にジェームズ・M・カーレイがボストン市長になるために民主党下院議員を辞職した時、ケネディはその議席をかけた補欠選挙に立候補した。父のジョセフが実業家であったこともあり、政治資金には困らなかったので、実現不可能な公約をする必要はなく理想主義を語ることができた。長く精力的なキャンペーンの末に、大差で共和党候補に勝ち、29歳で下院議員となった。当初は父のジョセフとコネがあった同じアイルランド系のジョセフ・マッカーシー上院議員の赤狩りに協力していた。リベラル派のエレノア・ルーズヴェルトはそのことを忘れず、後々までケネディを嫌っていた。下院3期目の1952年には上院議員選挙に出馬し、約70,000票の大差で共和党候補ヘンリー・カボット・ロッジ・ジュニアを破った。以後の彼の支持基盤は北部都市圏のリベラル派インテリ層となる。\n\nケネディは1953年9月12日にフランス系移民の名門の娘であるジャクリーン・リー・ブーヴィエと結婚した。彼はその後2年間に多数回の脊柱の手術を受け上院本会議を長期にわたって欠席したが、手術から回復するまでの間、8名の上院議員の政治的に勇敢であった行為についての本『勇気ある人々』を出版した。この本はその後ピューリツァー賞を受賞した。賞金は黒人の通う学校へ寄付したと言われている。\n\n\n\nhttp://ja.wikipedia.org/wiki/%E3%82%B8%E3%83%A7%E3%83%B3%E3%83%BBF%E3%83%BB%E3%82%B1%E3%83%8D%E3%83%87%E3%82%A3\n2010.01.26", "language": "jpn", "unit": "doc" } python-0.7.4/tests/mock-data/request/jpn-doc-language.json 0000664 0000000 0000000 00000006230 12636317025 0023551 0 ustar 00root root 0000000 0000000 { "content": "ケネディはマサチューセッツ州ブルックラインで、アイルランド系移民の子孫で投資家のジョセフ・P・ケネディ・シニアの次男として生まれた。名前は母方の祖父でボストン市長も勤めたジョン・F・フィッツジェラルドにちなむ。13歳のときにチョート・スクール（コネチカット州ウォリングフォードの寄宿学校）に入学し、その後1935年にイギリスのロンドン・スクール・オブ・エコノミクスに1年間留学した。帰国後ハーバード大学に入学を認められていたものの、親しい友人が進学を決めたプリンストン大学に入学することにした。しかし、クリスマス休暇中にかかった黄疸のため退学している。\n\n1936年の秋にはハーバード大学に転校したが、在学中にフットボールの試合で背中をひどく痛めた。在学中ヨーロッパへ2度旅行しており、2度目の旅行では父親が大使を務めていたイギリスを訪れている。1940年6月、1938年のミュンヘン協定におけるイギリス外交政策の分析についての卒論『イギリスはなぜ眠ったか』を書き、ハーバードを優等で卒業した。\n\n第二次世界大戦後、彼は戦死した兄ジョセフ・P・ケネディ・ジュニアに代わり政界に入った。1946年にジェームズ・M・カーレイがボストン市長になるために民主党下院議員を辞職した時、ケネディはその議席をかけた補欠選挙に立候補した。父のジョセフが実業家であったこともあり、政治資金には困らなかったので、実現不可能な公約をする必要はなく理想主義を語ることができた。長く精力的なキャンペーンの末に、大差で共和党候補に勝ち、29歳で下院議員となった。当初は父のジョセフとコネがあった同じアイルランド系のジョセフ・マッカーシー上院議員の赤狩りに協力していた。リベラル派のエレノア・ルーズヴェルトはそのことを忘れず、後々までケネディを嫌っていた。下院3期目の1952年には上院議員選挙に出馬し、約70,000票の大差で共和党候補ヘンリー・カボット・ロッジ・ジュニアを破った。以後の彼の支持基盤は北部都市圏のリベラル派インテリ層となる。\n\nケネディは1953年9月12日にフランス系移民の名門の娘であるジャクリーン・リー・ブーヴィエと結婚した。彼はその後2年間に多数回の脊柱の手術を受け上院本会議を長期にわたって欠席したが、手術から回復するまでの間、8名の上院議員の政治的に勇敢であった行為についての本『勇気ある人々』を出版した。この本はその後ピューリツァー賞を受賞した。賞金は黒人の通う学校へ寄付したと言われている。\n\n\n\nhttp://ja.wikipedia.org/wiki/%E3%82%B8%E3%83%A7%E3%83%B3%E3%83%BBF%E3%83%BB%E3%82%B1%E3%83%8D%E3%83%87%E3%82%A3\n2010.01.26", "language": "jpn", "unit": "doc" } python-0.7.4/tests/mock-data/request/jpn-doc-morphology_complete.json 0000664 0000000 0000000 00000006230 12636317025 0026055 0 ustar 00root root 0000000 0000000 { "content": "ケネディはマサチューセッツ州ブルックラインで、アイルランド系移民の子孫で投資家のジョセフ・P・ケネディ・シニアの次男として生まれた。名前は母方の祖父でボストン市長も勤めたジョン・F・フィッツジェラルドにちなむ。13歳のときにチョート・スクール（コネチカット州ウォリングフォードの寄宿学校）に入学し、その後1935年にイギリスのロンドン・スクール・オブ・エコノミクスに1年間留学した。帰国後ハーバード大学に入学を認められていたものの、親しい友人が進学を決めたプリンストン大学に入学することにした。しかし、クリスマス休暇中にかかった黄疸のため退学している。\n\n1936年の秋にはハーバード大学に転校したが、在学中にフットボールの試合で背中をひどく痛めた。在学中ヨーロッパへ2度旅行しており、2度目の旅行では父親が大使を務めていたイギリスを訪れている。1940年6月、1938年のミュンヘン協定におけるイギリス外交政策の分析についての卒論『イギリスはなぜ眠ったか』を書き、ハーバードを優等で卒業した。\n\n第二次世界大戦後、彼は戦死した兄ジョセフ・P・ケネディ・ジュニアに代わり政界に入った。1946年にジェームズ・M・カーレイがボストン市長になるために民主党下院議員を辞職した時、ケネディはその議席をかけた補欠選挙に立候補した。父のジョセフが実業家であったこともあり、政治資金には困らなかったので、実現不可能な公約をする必要はなく理想主義を語ることができた。長く精力的なキャンペーンの末に、大差で共和党候補に勝ち、29歳で下院議員となった。当初は父のジョセフとコネがあった同じアイルランド系のジョセフ・マッカーシー上院議員の赤狩りに協力していた。リベラル派のエレノア・ルーズヴェルトはそのことを忘れず、後々までケネディを嫌っていた。下院3期目の1952年には上院議員選挙に出馬し、約70,000票の大差で共和党候補ヘンリー・カボット・ロッジ・ジュニアを破った。以後の彼の支持基盤は北部都市圏のリベラル派インテリ層となる。\n\nケネディは1953年9月12日にフランス系移民の名門の娘であるジャクリーン・リー・ブーヴィエと結婚した。彼はその後2年間に多数回の脊柱の手術を受け上院本会議を長期にわたって欠席したが、手術から回復するまでの間、8名の上院議員の政治的に勇敢であった行為についての本『勇気ある人々』を出版した。この本はその後ピューリツァー賞を受賞した。賞金は黒人の通う学校へ寄付したと言われている。\n\n\n\nhttp://ja.wikipedia.org/wiki/%E3%82%B8%E3%83%A7%E3%83%B3%E3%83%BBF%E3%83%BB%E3%82%B1%E3%83%8D%E3%83%87%E3%82%A3\n2010.01.26", "language": "jpn", "unit": "doc" } python-0.7.4/tests/mock-data/request/jpn-doc-sentiment.json 0000664 0000000 0000000 00000006230 12636317025 0023774 0 ustar 00root root 0000000 0000000 { "content": "ケネディはマサチューセッツ州ブルックラインで、アイルランド系移民の子孫で投資家のジョセフ・P・ケネディ・シニアの次男として生まれた。名前は母方の祖父でボストン市長も勤めたジョン・F・フィッツジェラルドにちなむ。13歳のときにチョート・スクール（コネチカット州ウォリングフォードの寄宿学校）に入学し、その後1935年にイギリスのロンドン・スクール・オブ・エコノミクスに1年間留学した。帰国後ハーバード大学に入学を認められていたものの、親しい友人が進学を決めたプリンストン大学に入学することにした。しかし、クリスマス休暇中にかかった黄疸のため退学している。\n\n1936年の秋にはハーバード大学に転校したが、在学中にフットボールの試合で背中をひどく痛めた。在学中ヨーロッパへ2度旅行しており、2度目の旅行では父親が大使を務めていたイギリスを訪れている。1940年6月、1938年のミュンヘン協定におけるイギリス外交政策の分析についての卒論『イギリスはなぜ眠ったか』を書き、ハーバードを優等で卒業した。\n\n第二次世界大戦後、彼は戦死した兄ジョセフ・P・ケネディ・ジュニアに代わり政界に入った。1946年にジェームズ・M・カーレイがボストン市長になるために民主党下院議員を辞職した時、ケネディはその議席をかけた補欠選挙に立候補した。父のジョセフが実業家であったこともあり、政治資金には困らなかったので、実現不可能な公約をする必要はなく理想主義を語ることができた。長く精力的なキャンペーンの末に、大差で共和党候補に勝ち、29歳で下院議員となった。当初は父のジョセフとコネがあった同じアイルランド系のジョセフ・マッカーシー上院議員の赤狩りに協力していた。リベラル派のエレノア・ルーズヴェルトはそのことを忘れず、後々までケネディを嫌っていた。下院3期目の1952年には上院議員選挙に出馬し、約70,000票の大差で共和党候補ヘンリー・カボット・ロッジ・ジュニアを破った。以後の彼の支持基盤は北部都市圏のリベラル派インテリ層となる。\n\nケネディは1953年9月12日にフランス系移民の名門の娘であるジャクリーン・リー・ブーヴィエと結婚した。彼はその後2年間に多数回の脊柱の手術を受け上院本会議を長期にわたって欠席したが、手術から回復するまでの間、8名の上院議員の政治的に勇敢であった行為についての本『勇気ある人々』を出版した。この本はその後ピューリツァー賞を受賞した。賞金は黒人の通う学校へ寄付したと言われている。\n\n\n\nhttp://ja.wikipedia.org/wiki/%E3%82%B8%E3%83%A7%E3%83%B3%E3%83%BBF%E3%83%BB%E3%82%B1%E3%83%8D%E3%83%87%E3%82%A3\n2010.01.26", "language": "jpn", "unit": "doc" } python-0.7.4/tests/mock-data/request/jpn-sentence-categories.json 0000664 0000000 0000000 00000001771 12636317025 0025157 0 ustar 00root root 0000000 0000000 { "content": "政治家を志したきっかけは中川一郎の存在だったという[3]。1986年、第38回衆議院議員総選挙で、自民党の公認を得た田中派新人として、鳩山家が牧場を所有し鳩山神社という神社がある祖父の代からの地盤北海道から[4]、出馬した。鳩山事務所側は、「立候補の直接のきっかけは三枝三郎衆議院議員の引退がきっかけ」と主張している[5]。初の選挙スローガンは科学者を志望していた自身の経歴をアピールした「政治を科学する」であった[6]。得票数では同じ自民党の高橋辰夫に次いで2番目の得票数で当選した。小選挙区になった1996年以降は、鳩山家が開拓した地域は鳩山の選挙区から外れた[7]。なお、地方区分の選挙区自体は祖父と重複していないため、祖父の地盤を世襲していないと扱われている[8]。", "language": "jpn", "unit": "sentence" } python-0.7.4/tests/mock-data/request/jpn-sentence-entities.json 0000664 0000000 0000000 00000001771 12636317025 0024656 0 ustar 00root root 0000000 0000000 { "content": "政治家を志したきっかけは中川一郎の存在だったという[3]。1986年、第38回衆議院議員総選挙で、自民党の公認を得た田中派新人として、鳩山家が牧場を所有し鳩山神社という神社がある祖父の代からの地盤北海道から[4]、出馬した。鳩山事務所側は、「立候補の直接のきっかけは三枝三郎衆議院議員の引退がきっかけ」と主張している[5]。初の選挙スローガンは科学者を志望していた自身の経歴をアピールした「政治を科学する」であった[6]。得票数では同じ自民党の高橋辰夫に次いで2番目の得票数で当選した。小選挙区になった1996年以降は、鳩山家が開拓した地域は鳩山の選挙区から外れた[7]。なお、地方区分の選挙区自体は祖父と重複していないため、祖父の地盤を世襲していないと扱われている[8]。", "language": "jpn", "unit": "sentence" } python-0.7.4/tests/mock-data/request/jpn-sentence-entities_linked.json 0000664 0000000 0000000 00000001771 12636317025 0026204 0 ustar 00root root 0000000 0000000 { "content": "政治家を志したきっかけは中川一郎の存在だったという[3]。1986年、第38回衆議院議員総選挙で、自民党の公認を得た田中派新人として、鳩山家が牧場を所有し鳩山神社という神社がある祖父の代からの地盤北海道から[4]、出馬した。鳩山事務所側は、「立候補の直接のきっかけは三枝三郎衆議院議員の引退がきっかけ」と主張している[5]。初の選挙スローガンは科学者を志望していた自身の経歴をアピールした「政治を科学する」であった[6]。得票数では同じ自民党の高橋辰夫に次いで2番目の得票数で当選した。小選挙区になった1996年以降は、鳩山家が開拓した地域は鳩山の選挙区から外れた[7]。なお、地方区分の選挙区自体は祖父と重複していないため、祖父の地盤を世襲していないと扱われている[8]。", "language": "jpn", "unit": "sentence" } python-0.7.4/tests/mock-data/request/jpn-sentence-language.json 0000664 0000000 0000000 00000001771 12636317025 0024615 0 ustar 00root root 0000000 0000000 { "content": "政治家を志したきっかけは中川一郎の存在だったという[3]。1986年、第38回衆議院議員総選挙で、自民党の公認を得た田中派新人として、鳩山家が牧場を所有し鳩山神社という神社がある祖父の代からの地盤北海道から[4]、出馬した。鳩山事務所側は、「立候補の直接のきっかけは三枝三郎衆議院議員の引退がきっかけ」と主張している[5]。初の選挙スローガンは科学者を志望していた自身の経歴をアピールした「政治を科学する」であった[6]。得票数では同じ自民党の高橋辰夫に次いで2番目の得票数で当選した。小選挙区になった1996年以降は、鳩山家が開拓した地域は鳩山の選挙区から外れた[7]。なお、地方区分の選挙区自体は祖父と重複していないため、祖父の地盤を世襲していないと扱われている[8]。", "language": "jpn", "unit": "sentence" } python-0.7.4/tests/mock-data/request/jpn-sentence-morphology_complete.json 0000664 0000000 0000000 00000001771 12636317025 0027121 0 ustar 00root root 0000000 0000000 { "content": "政治家を志したきっかけは中川一郎の存在だったという[3]。1986年、第38回衆議院議員総選挙で、自民党の公認を得た田中派新人として、鳩山家が牧場を所有し鳩山神社という神社がある祖父の代からの地盤北海道から[4]、出馬した。鳩山事務所側は、「立候補の直接のきっかけは三枝三郎衆議院議員の引退がきっかけ」と主張している[5]。初の選挙スローガンは科学者を志望していた自身の経歴をアピールした「政治を科学する」であった[6]。得票数では同じ自民党の高橋辰夫に次いで2番目の得票数で当選した。小選挙区になった1996年以降は、鳩山家が開拓した地域は鳩山の選挙区から外れた[7]。なお、地方区分の選挙区自体は祖父と重複していないため、祖父の地盤を世襲していないと扱われている[8]。", "language": "jpn", "unit": "sentence" } python-0.7.4/tests/mock-data/request/jpn-sentence-sentiment.json 0000664 0000000 0000000 00000001771 12636317025 0025040 0 ustar 00root root 0000000 0000000 { "content": "政治家を志したきっかけは中川一郎の存在だったという[3]。1986年、第38回衆議院議員総選挙で、自民党の公認を得た田中派新人として、鳩山家が牧場を所有し鳩山神社という神社がある祖父の代からの地盤北海道から[4]、出馬した。鳩山事務所側は、「立候補の直接のきっかけは三枝三郎衆議院議員の引退がきっかけ」と主張している[5]。初の選挙スローガンは科学者を志望していた自身の経歴をアピールした「政治を科学する」であった[6]。得票数では同じ自民党の高橋辰夫に次いで2番目の得票数で当選した。小選挙区になった1996年以降は、鳩山家が開拓した地域は鳩山の選挙区から外れた[7]。なお、地方区分の選挙区自体は祖父と重複していないため、祖父の地盤を世襲していないと扱われている[8]。", "language": "jpn", "unit": "sentence" } python-0.7.4/tests/mock-data/request/pus-doc-categories.json 0000664 0000000 0000000 00000010763 12636317025 0024141 0 ustar 00root root 0000000 0000000 { "content": "د افغانستان د كابيني لوي لست\nد افغانستان ولسمشر حامد كرزي په خپله نوي كابينه كي د بهرنيو چارو د وزير په توګه د امنيت په برخه كي خپل سلاكار زلمي رسول نوماند كړي دي .\n\n\nد افغانستان ولسمشر حامد كرزي په خپله نوي كابينه كي د بهرنيو چارو د وزير په توګه د امنيت په برخه كي خپل سلاكار زلمي رسول نوماند كړي دي .\nنن د نوموړي هيواد د ولسمشر مرستيال كريم خليلي په پارلمان كي د نوي كابيني د ۱۶ تنو وزيرانو نومونه ولوستل . همداشان كريم خليلي د پاتو دوه تنو وزيرانو د نومونو په اړه څه ونه ويل .\nد ويلو ده چي په نوموړي نوي لست كي د هغه وزيرانو نومونه هم شامل دي چي تيره اووني يي د پارلمان نه د اعتماد رايي نوي ترلاسه كړي .\nد يادولو وړ ده چي د افغانستان پارلمان تيره اووني په خپله عمومي ناسته كي د ۲۴ تنو وزيرانو د جمع نه ۷ تنو ته د اعتماد راي وركړه . ۱- د بهرنيو چارو نوماند وزير: زلمی رسول نوموړی د ولسمشر امنيتي سلاکار دی او په طب کې دوکتورا لري . ٢- د عدليې نوماند وزير : حبيب الله غالب غالب په شرعياتو کې دوکتورا لري چې ويل کېږي چې د عبدرب رسول سياف لخوا معرفي شوی دی . ٣- د لوړو زده کړو نوماند وزير : محمد هاشم عصمت الهي په اړيکو او ورځپاڼه ليکلوو ليکلو کې دوکتورا لري او د اصف محسني کس دی . ٤- د حج او ارشاد نوماند وزير : ډاکټر محمد يوسف نيازی ښاغلی نيازی په اسلامي زده کړو کې دوکتورا لري . ٥- د فوايد عامې نوماند وزير : محمد بشير لعلي ٦- د عامې روغتيا نوماند وزير: ډاکټر ثريا دليل د طب په مديريتي برخه کې دوکتورا لري، په قام ازبکه ده او په کينيا او افغانستان کې يې يونيسف کې کارکړی دی . ٧- د اقتصاد نوماند وزير : عبدالهادي ارغنديوال ښاغلی ارغنديوال په اقتصاد کې ليسانس لري . ٨- د سوداګرۍ او صنايعو نوماند وزير : محمد هادي حکيمي ښاغلی حکيمي په حقوقو او نړيواله سوداګرۍ کې يې زده کړې کړې دي . ٩- د کليو د پراختيا او بيا رغاونې نوماند وزير: جارالله منصوري منصوري په سياسي علومو کې يې لوړې زده کړې کړې دي . ١٠ - د ټولنيزو چارو، شهيدانو او معلولينو نوماند وزير: امنه افضلي اغلې افضلي په چاپېريال ساتنه کې لوړې زده کړې لري . ١١- د ترانسپورت او هوايي چلند وزير : عبدالرحيم اوراز ښاغلی اوراز ساختماني انجنير او په بهرنيو چارو وزارت کې يې کار کړی، ويل کېږي چې د ملی جنبش لخوا معرفي شوی . ١٢- د ښځو چارو نومانده وزيره : پلوشه حسن اغلې حسن د بيارغاونې په چارو کې ليسانس لري . ١٣- د کډوالو او راستنېدونکو چارو نوماند وزير : انجنير عبدالرحيم نوموړی انجنير دی . ١٤- د سرحدونو چارو، قامونو او قبايلو نوماند وزير : ارسلا جمال ښاغلی جمال په اقتصاد کې ليسانس لري او مخکې د خوست والي و . ١٥- له نشه يي توکيو سره د مبارزې نوماند وزير: ضرار احمد مقبل ښاغلی مقبل د کرزي په تېره دوره کې د څه مودې لپاره د کورنيو چار وزير و . ١٦- د ښاري پراختيا نوماند وزير : انجنير سلطان حسين حصاري ښاغلی حصاري د ښار جوړونې په برخه کې دوکتورا لري\n\n\n\nhttp://www.trtpashto.com/trtinternational/pa/newsDetail.aspx?HaberKodu=efb3ec08-e5d5-4007-addc-0cc81652bc62\n2010.01.24", "language": "pus", "unit": "doc" } python-0.7.4/tests/mock-data/request/pus-doc-entities.json 0000664 0000000 0000000 00000010763 12636317025 0023640 0 ustar 00root root 0000000 0000000 { "content": "د افغانستان د كابيني لوي لست\nد افغانستان ولسمشر حامد كرزي په خپله نوي كابينه كي د بهرنيو چارو د وزير په توګه د امنيت په برخه كي خپل سلاكار زلمي رسول نوماند كړي دي .\n\n\nد افغانستان ولسمشر حامد كرزي په خپله نوي كابينه كي د بهرنيو چارو د وزير په توګه د امنيت په برخه كي خپل سلاكار زلمي رسول نوماند كړي دي .\nنن د نوموړي هيواد د ولسمشر مرستيال كريم خليلي په پارلمان كي د نوي كابيني د ۱۶ تنو وزيرانو نومونه ولوستل . همداشان كريم خليلي د پاتو دوه تنو وزيرانو د نومونو په اړه څه ونه ويل .\nد ويلو ده چي په نوموړي نوي لست كي د هغه وزيرانو نومونه هم شامل دي چي تيره اووني يي د پارلمان نه د اعتماد رايي نوي ترلاسه كړي .\nد يادولو وړ ده چي د افغانستان پارلمان تيره اووني په خپله عمومي ناسته كي د ۲۴ تنو وزيرانو د جمع نه ۷ تنو ته د اعتماد راي وركړه . ۱- د بهرنيو چارو نوماند وزير: زلمی رسول نوموړی د ولسمشر امنيتي سلاکار دی او په طب کې دوکتورا لري . ٢- د عدليې نوماند وزير : حبيب الله غالب غالب په شرعياتو کې دوکتورا لري چې ويل کېږي چې د عبدرب رسول سياف لخوا معرفي شوی دی . ٣- د لوړو زده کړو نوماند وزير : محمد هاشم عصمت الهي په اړيکو او ورځپاڼه ليکلوو ليکلو کې دوکتورا لري او د اصف محسني کس دی . ٤- د حج او ارشاد نوماند وزير : ډاکټر محمد يوسف نيازی ښاغلی نيازی په اسلامي زده کړو کې دوکتورا لري . ٥- د فوايد عامې نوماند وزير : محمد بشير لعلي ٦- د عامې روغتيا نوماند وزير: ډاکټر ثريا دليل د طب په مديريتي برخه کې دوکتورا لري، په قام ازبکه ده او په کينيا او افغانستان کې يې يونيسف کې کارکړی دی . ٧- د اقتصاد نوماند وزير : عبدالهادي ارغنديوال ښاغلی ارغنديوال په اقتصاد کې ليسانس لري . ٨- د سوداګرۍ او صنايعو نوماند وزير : محمد هادي حکيمي ښاغلی حکيمي په حقوقو او نړيواله سوداګرۍ کې يې زده کړې کړې دي . ٩- د کليو د پراختيا او بيا رغاونې نوماند وزير: جارالله منصوري منصوري په سياسي علومو کې يې لوړې زده کړې کړې دي . ١٠ - د ټولنيزو چارو، شهيدانو او معلولينو نوماند وزير: امنه افضلي اغلې افضلي په چاپېريال ساتنه کې لوړې زده کړې لري . ١١- د ترانسپورت او هوايي چلند وزير : عبدالرحيم اوراز ښاغلی اوراز ساختماني انجنير او په بهرنيو چارو وزارت کې يې کار کړی، ويل کېږي چې د ملی جنبش لخوا معرفي شوی . ١٢- د ښځو چارو نومانده وزيره : پلوشه حسن اغلې حسن د بيارغاونې په چارو کې ليسانس لري . ١٣- د کډوالو او راستنېدونکو چارو نوماند وزير : انجنير عبدالرحيم نوموړی انجنير دی . ١٤- د سرحدونو چارو، قامونو او قبايلو نوماند وزير : ارسلا جمال ښاغلی جمال په اقتصاد کې ليسانس لري او مخکې د خوست والي و . ١٥- له نشه يي توکيو سره د مبارزې نوماند وزير: ضرار احمد مقبل ښاغلی مقبل د کرزي په تېره دوره کې د څه مودې لپاره د کورنيو چار وزير و . ١٦- د ښاري پراختيا نوماند وزير : انجنير سلطان حسين حصاري ښاغلی حصاري د ښار جوړونې په برخه کې دوکتورا لري\n\n\n\nhttp://www.trtpashto.com/trtinternational/pa/newsDetail.aspx?HaberKodu=efb3ec08-e5d5-4007-addc-0cc81652bc62\n2010.01.24", "language": "pus", "unit": "doc" } python-0.7.4/tests/mock-data/request/pus-doc-entities_linked.json 0000664 0000000 0000000 00000010763 12636317025 0025166 0 ustar 00root root 0000000 0000000 { "content": "د افغانستان د كابيني لوي لست\nد افغانستان ولسمشر حامد كرزي په خپله نوي كابينه كي د بهرنيو چارو د وزير په توګه د امنيت په برخه كي خپل سلاكار زلمي رسول نوماند كړي دي .\n\n\nد افغانستان ولسمشر حامد كرزي په خپله نوي كابينه كي د بهرنيو چارو د وزير په توګه د امنيت په برخه كي خپل سلاكار زلمي رسول نوماند كړي دي .\nنن د نوموړي هيواد د ولسمشر مرستيال كريم خليلي په پارلمان كي د نوي كابيني د ۱۶ تنو وزيرانو نومونه ولوستل . همداشان كريم خليلي د پاتو دوه تنو وزيرانو د نومونو په اړه څه ونه ويل .\nد ويلو ده چي په نوموړي نوي لست كي د هغه وزيرانو نومونه هم شامل دي چي تيره اووني يي د پارلمان نه د اعتماد رايي نوي ترلاسه كړي .\nد يادولو وړ ده چي د افغانستان پارلمان تيره اووني په خپله عمومي ناسته كي د ۲۴ تنو وزيرانو د جمع نه ۷ تنو ته د اعتماد راي وركړه . ۱- د بهرنيو چارو نوماند وزير: زلمی رسول نوموړی د ولسمشر امنيتي سلاکار دی او په طب کې دوکتورا لري . ٢- د عدليې نوماند وزير : حبيب الله غالب غالب په شرعياتو کې دوکتورا لري چې ويل کېږي چې د عبدرب رسول سياف لخوا معرفي شوی دی . ٣- د لوړو زده کړو نوماند وزير : محمد هاشم عصمت الهي په اړيکو او ورځپاڼه ليکلوو ليکلو کې دوکتورا لري او د اصف محسني کس دی . ٤- د حج او ارشاد نوماند وزير : ډاکټر محمد يوسف نيازی ښاغلی نيازی په اسلامي زده کړو کې دوکتورا لري . ٥- د فوايد عامې نوماند وزير : محمد بشير لعلي ٦- د عامې روغتيا نوماند وزير: ډاکټر ثريا دليل د طب په مديريتي برخه کې دوکتورا لري، په قام ازبکه ده او په کينيا او افغانستان کې يې يونيسف کې کارکړی دی . ٧- د اقتصاد نوماند وزير : عبدالهادي ارغنديوال ښاغلی ارغنديوال په اقتصاد کې ليسانس لري . ٨- د سوداګرۍ او صنايعو نوماند وزير : محمد هادي حکيمي ښاغلی حکيمي په حقوقو او نړيواله سوداګرۍ کې يې زده کړې کړې دي . ٩- د کليو د پراختيا او بيا رغاونې نوماند وزير: جارالله منصوري منصوري په سياسي علومو کې يې لوړې زده کړې کړې دي . ١٠ - د ټولنيزو چارو، شهيدانو او معلولينو نوماند وزير: امنه افضلي اغلې افضلي په چاپېريال ساتنه کې لوړې زده کړې لري . ١١- د ترانسپورت او هوايي چلند وزير : عبدالرحيم اوراز ښاغلی اوراز ساختماني انجنير او په بهرنيو چارو وزارت کې يې کار کړی، ويل کېږي چې د ملی جنبش لخوا معرفي شوی . ١٢- د ښځو چارو نومانده وزيره : پلوشه حسن اغلې حسن د بيارغاونې په چارو کې ليسانس لري . ١٣- د کډوالو او راستنېدونکو چارو نوماند وزير : انجنير عبدالرحيم نوموړی انجنير دی . ١٤- د سرحدونو چارو، قامونو او قبايلو نوماند وزير : ارسلا جمال ښاغلی جمال په اقتصاد کې ليسانس لري او مخکې د خوست والي و . ١٥- له نشه يي توکيو سره د مبارزې نوماند وزير: ضرار احمد مقبل ښاغلی مقبل د کرزي په تېره دوره کې د څه مودې لپاره د کورنيو چار وزير و . ١٦- د ښاري پراختيا نوماند وزير : انجنير سلطان حسين حصاري ښاغلی حصاري د ښار جوړونې په برخه کې دوکتورا لري\n\n\n\nhttp://www.trtpashto.com/trtinternational/pa/newsDetail.aspx?HaberKodu=efb3ec08-e5d5-4007-addc-0cc81652bc62\n2010.01.24", "language": "pus", "unit": "doc" } python-0.7.4/tests/mock-data/request/pus-doc-language.json 0000664 0000000 0000000 00000010763 12636317025 0023577 0 ustar 00root root 0000000 0000000 { "content": "د افغانستان د كابيني لوي لست\nد افغانستان ولسمشر حامد كرزي په خپله نوي كابينه كي د بهرنيو چارو د وزير په توګه د امنيت په برخه كي خپل سلاكار زلمي رسول نوماند كړي دي .\n\n\nد افغانستان ولسمشر حامد كرزي په خپله نوي كابينه كي د بهرنيو چارو د وزير په توګه د امنيت په برخه كي خپل سلاكار زلمي رسول نوماند كړي دي .\nنن د نوموړي هيواد د ولسمشر مرستيال كريم خليلي په پارلمان كي د نوي كابيني د ۱۶ تنو وزيرانو نومونه ولوستل . همداشان كريم خليلي د پاتو دوه تنو وزيرانو د نومونو په اړه څه ونه ويل .\nد ويلو ده چي په نوموړي نوي لست كي د هغه وزيرانو نومونه هم شامل دي چي تيره اووني يي د پارلمان نه د اعتماد رايي نوي ترلاسه كړي .\nد يادولو وړ ده چي د افغانستان پارلمان تيره اووني په خپله عمومي ناسته كي د ۲۴ تنو وزيرانو د جمع نه ۷ تنو ته د اعتماد راي وركړه . ۱- د بهرنيو چارو نوماند وزير: زلمی رسول نوموړی د ولسمشر امنيتي سلاکار دی او په طب کې دوکتورا لري . ٢- د عدليې نوماند وزير : حبيب الله غالب غالب په شرعياتو کې دوکتورا لري چې ويل کېږي چې د عبدرب رسول سياف لخوا معرفي شوی دی . ٣- د لوړو زده کړو نوماند وزير : محمد هاشم عصمت الهي په اړيکو او ورځپاڼه ليکلوو ليکلو کې دوکتورا لري او د اصف محسني کس دی . ٤- د حج او ارشاد نوماند وزير : ډاکټر محمد يوسف نيازی ښاغلی نيازی په اسلامي زده کړو کې دوکتورا لري . ٥- د فوايد عامې نوماند وزير : محمد بشير لعلي ٦- د عامې روغتيا نوماند وزير: ډاکټر ثريا دليل د طب په مديريتي برخه کې دوکتورا لري، په قام ازبکه ده او په کينيا او افغانستان کې يې يونيسف کې کارکړی دی . ٧- د اقتصاد نوماند وزير : عبدالهادي ارغنديوال ښاغلی ارغنديوال په اقتصاد کې ليسانس لري . ٨- د سوداګرۍ او صنايعو نوماند وزير : محمد هادي حکيمي ښاغلی حکيمي په حقوقو او نړيواله سوداګرۍ کې يې زده کړې کړې دي . ٩- د کليو د پراختيا او بيا رغاونې نوماند وزير: جارالله منصوري منصوري په سياسي علومو کې يې لوړې زده کړې کړې دي . ١٠ - د ټولنيزو چارو، شهيدانو او معلولينو نوماند وزير: امنه افضلي اغلې افضلي په چاپېريال ساتنه کې لوړې زده کړې لري . ١١- د ترانسپورت او هوايي چلند وزير : عبدالرحيم اوراز ښاغلی اوراز ساختماني انجنير او په بهرنيو چارو وزارت کې يې کار کړی، ويل کېږي چې د ملی جنبش لخوا معرفي شوی . ١٢- د ښځو چارو نومانده وزيره : پلوشه حسن اغلې حسن د بيارغاونې په چارو کې ليسانس لري . ١٣- د کډوالو او راستنېدونکو چارو نوماند وزير : انجنير عبدالرحيم نوموړی انجنير دی . ١٤- د سرحدونو چارو، قامونو او قبايلو نوماند وزير : ارسلا جمال ښاغلی جمال په اقتصاد کې ليسانس لري او مخکې د خوست والي و . ١٥- له نشه يي توکيو سره د مبارزې نوماند وزير: ضرار احمد مقبل ښاغلی مقبل د کرزي په تېره دوره کې د څه مودې لپاره د کورنيو چار وزير و . ١٦- د ښاري پراختيا نوماند وزير : انجنير سلطان حسين حصاري ښاغلی حصاري د ښار جوړونې په برخه کې دوکتورا لري\n\n\n\nhttp://www.trtpashto.com/trtinternational/pa/newsDetail.aspx?HaberKodu=efb3ec08-e5d5-4007-addc-0cc81652bc62\n2010.01.24", "language": "pus", "unit": "doc" } python-0.7.4/tests/mock-data/request/pus-doc-morphology_complete.json 0000664 0000000 0000000 00000010763 12636317025 0026103 0 ustar 00root root 0000000 0000000 { "content": "د افغانستان د كابيني لوي لست\nد افغانستان ولسمشر حامد كرزي په خپله نوي كابينه كي د بهرنيو چارو د وزير په توګه د امنيت په برخه كي خپل سلاكار زلمي رسول نوماند كړي دي .\n\n\nد افغانستان ولسمشر حامد كرزي په خپله نوي كابينه كي د بهرنيو چارو د وزير په توګه د امنيت په برخه كي خپل سلاكار زلمي رسول نوماند كړي دي .\nنن د نوموړي هيواد د ولسمشر مرستيال كريم خليلي په پارلمان كي د نوي كابيني د ۱۶ تنو وزيرانو نومونه ولوستل . همداشان كريم خليلي د پاتو دوه تنو وزيرانو د نومونو په اړه څه ونه ويل .\nد ويلو ده چي په نوموړي نوي لست كي د هغه وزيرانو نومونه هم شامل دي چي تيره اووني يي د پارلمان نه د اعتماد رايي نوي ترلاسه كړي .\nد يادولو وړ ده چي د افغانستان پارلمان تيره اووني په خپله عمومي ناسته كي د ۲۴ تنو وزيرانو د جمع نه ۷ تنو ته د اعتماد راي وركړه . ۱- د بهرنيو چارو نوماند وزير: زلمی رسول نوموړی د ولسمشر امنيتي سلاکار دی او په طب کې دوکتورا لري . ٢- د عدليې نوماند وزير : حبيب الله غالب غالب په شرعياتو کې دوکتورا لري چې ويل کېږي چې د عبدرب رسول سياف لخوا معرفي شوی دی . ٣- د لوړو زده کړو نوماند وزير : محمد هاشم عصمت الهي په اړيکو او ورځپاڼه ليکلوو ليکلو کې دوکتورا لري او د اصف محسني کس دی . ٤- د حج او ارشاد نوماند وزير : ډاکټر محمد يوسف نيازی ښاغلی نيازی په اسلامي زده کړو کې دوکتورا لري . ٥- د فوايد عامې نوماند وزير : محمد بشير لعلي ٦- د عامې روغتيا نوماند وزير: ډاکټر ثريا دليل د طب په مديريتي برخه کې دوکتورا لري، په قام ازبکه ده او په کينيا او افغانستان کې يې يونيسف کې کارکړی دی . ٧- د اقتصاد نوماند وزير : عبدالهادي ارغنديوال ښاغلی ارغنديوال په اقتصاد کې ليسانس لري . ٨- د سوداګرۍ او صنايعو نوماند وزير : محمد هادي حکيمي ښاغلی حکيمي په حقوقو او نړيواله سوداګرۍ کې يې زده کړې کړې دي . ٩- د کليو د پراختيا او بيا رغاونې نوماند وزير: جارالله منصوري منصوري په سياسي علومو کې يې لوړې زده کړې کړې دي . ١٠ - د ټولنيزو چارو، شهيدانو او معلولينو نوماند وزير: امنه افضلي اغلې افضلي په چاپېريال ساتنه کې لوړې زده کړې لري . ١١- د ترانسپورت او هوايي چلند وزير : عبدالرحيم اوراز ښاغلی اوراز ساختماني انجنير او په بهرنيو چارو وزارت کې يې کار کړی، ويل کېږي چې د ملی جنبش لخوا معرفي شوی . ١٢- د ښځو چارو نومانده وزيره : پلوشه حسن اغلې حسن د بيارغاونې په چارو کې ليسانس لري . ١٣- د کډوالو او راستنېدونکو چارو نوماند وزير : انجنير عبدالرحيم نوموړی انجنير دی . ١٤- د سرحدونو چارو، قامونو او قبايلو نوماند وزير : ارسلا جمال ښاغلی جمال په اقتصاد کې ليسانس لري او مخکې د خوست والي و . ١٥- له نشه يي توکيو سره د مبارزې نوماند وزير: ضرار احمد مقبل ښاغلی مقبل د کرزي په تېره دوره کې د څه مودې لپاره د کورنيو چار وزير و . ١٦- د ښاري پراختيا نوماند وزير : انجنير سلطان حسين حصاري ښاغلی حصاري د ښار جوړونې په برخه کې دوکتورا لري\n\n\n\nhttp://www.trtpashto.com/trtinternational/pa/newsDetail.aspx?HaberKodu=efb3ec08-e5d5-4007-addc-0cc81652bc62\n2010.01.24", "language": "pus", "unit": "doc" } python-0.7.4/tests/mock-data/request/pus-doc-sentiment.json 0000664 0000000 0000000 00000010763 12636317025 0024022 0 ustar 00root root 0000000 0000000 { "content": "د افغانستان د كابيني لوي لست\nد افغانستان ولسمشر حامد كرزي په خپله نوي كابينه كي د بهرنيو چارو د وزير په توګه د امنيت په برخه كي خپل سلاكار زلمي رسول نوماند كړي دي .\n\n\nد افغانستان ولسمشر حامد كرزي په خپله نوي كابينه كي د بهرنيو چارو د وزير په توګه د امنيت په برخه كي خپل سلاكار زلمي رسول نوماند كړي دي .\nنن د نوموړي هيواد د ولسمشر مرستيال كريم خليلي په پارلمان كي د نوي كابيني د ۱۶ تنو وزيرانو نومونه ولوستل . همداشان كريم خليلي د پاتو دوه تنو وزيرانو د نومونو په اړه څه ونه ويل .\nد ويلو ده چي په نوموړي نوي لست كي د هغه وزيرانو نومونه هم شامل دي چي تيره اووني يي د پارلمان نه د اعتماد رايي نوي ترلاسه كړي .\nد يادولو وړ ده چي د افغانستان پارلمان تيره اووني په خپله عمومي ناسته كي د ۲۴ تنو وزيرانو د جمع نه ۷ تنو ته د اعتماد راي وركړه . ۱- د بهرنيو چارو نوماند وزير: زلمی رسول نوموړی د ولسمشر امنيتي سلاکار دی او په طب کې دوکتورا لري . ٢- د عدليې نوماند وزير : حبيب الله غالب غالب په شرعياتو کې دوکتورا لري چې ويل کېږي چې د عبدرب رسول سياف لخوا معرفي شوی دی . ٣- د لوړو زده کړو نوماند وزير : محمد هاشم عصمت الهي په اړيکو او ورځپاڼه ليکلوو ليکلو کې دوکتورا لري او د اصف محسني کس دی . ٤- د حج او ارشاد نوماند وزير : ډاکټر محمد يوسف نيازی ښاغلی نيازی په اسلامي زده کړو کې دوکتورا لري . ٥- د فوايد عامې نوماند وزير : محمد بشير لعلي ٦- د عامې روغتيا نوماند وزير: ډاکټر ثريا دليل د طب په مديريتي برخه کې دوکتورا لري، په قام ازبکه ده او په کينيا او افغانستان کې يې يونيسف کې کارکړی دی . ٧- د اقتصاد نوماند وزير : عبدالهادي ارغنديوال ښاغلی ارغنديوال په اقتصاد کې ليسانس لري . ٨- د سوداګرۍ او صنايعو نوماند وزير : محمد هادي حکيمي ښاغلی حکيمي په حقوقو او نړيواله سوداګرۍ کې يې زده کړې کړې دي . ٩- د کليو د پراختيا او بيا رغاونې نوماند وزير: جارالله منصوري منصوري په سياسي علومو کې يې لوړې زده کړې کړې دي . ١٠ - د ټولنيزو چارو، شهيدانو او معلولينو نوماند وزير: امنه افضلي اغلې افضلي په چاپېريال ساتنه کې لوړې زده کړې لري . ١١- د ترانسپورت او هوايي چلند وزير : عبدالرحيم اوراز ښاغلی اوراز ساختماني انجنير او په بهرنيو چارو وزارت کې يې کار کړی، ويل کېږي چې د ملی جنبش لخوا معرفي شوی . ١٢- د ښځو چارو نومانده وزيره : پلوشه حسن اغلې حسن د بيارغاونې په چارو کې ليسانس لري . ١٣- د کډوالو او راستنېدونکو چارو نوماند وزير : انجنير عبدالرحيم نوموړی انجنير دی . ١٤- د سرحدونو چارو، قامونو او قبايلو نوماند وزير : ارسلا جمال ښاغلی جمال په اقتصاد کې ليسانس لري او مخکې د خوست والي و . ١٥- له نشه يي توکيو سره د مبارزې نوماند وزير: ضرار احمد مقبل ښاغلی مقبل د کرزي په تېره دوره کې د څه مودې لپاره د کورنيو چار وزير و . ١٦- د ښاري پراختيا نوماند وزير : انجنير سلطان حسين حصاري ښاغلی حصاري د ښار جوړونې په برخه کې دوکتورا لري\n\n\n\nhttp://www.trtpashto.com/trtinternational/pa/newsDetail.aspx?HaberKodu=efb3ec08-e5d5-4007-addc-0cc81652bc62\n2010.01.24", "language": "pus", "unit": "doc" } python-0.7.4/tests/mock-data/request/pus-sentence-categories.json 0000664 0000000 0000000 00000002244 12636317025 0025173 0 ustar 00root root 0000000 0000000 { "content": "د پښتو ادب په کلاسیکه شاعرۍ کې خوشال هغه علامه ، نابغه ، ستر شاعر او لوی ادیب دی ، چې د څه کم څلورسو کالو راهسې دده کلتوري خزانه تر ننه پورې دافغان ولس د نړۍ د لویو پوهانو او پوهنيزو مرکزونو د پاملرنې او څیړنې وړ کرځیدلې ده . د څیړونکو ځیرکتنه به تر هغې پورې دغه کلتوري میراث ته وجود ولری ، څو چې په نړۍ کې ولسونه په پوهنه او څیړنه بو خت وي . له خوشال څخه کوټې کوټې موضوعات او درانه درانه اثار په میراث راپاتې دي . دده اثار د شعر ، ادب ، ژبپوهنې او نورو بېلا بېلو پوهنو او څیړنو لپاره لوی دریاب دی ، چې لامبوزن هم پکې سټر کیږی خو دده برید ، پوله ، سر او تل به تر خپلې لامبو لاندې داخیل نه کړی او د ژوند تر پایه به پکې ستړی او ستومانه وي .", "language": "pus", "unit": "sentence" } python-0.7.4/tests/mock-data/request/pus-sentence-entities.json 0000664 0000000 0000000 00000002244 12636317025 0024672 0 ustar 00root root 0000000 0000000 { "content": "د پښتو ادب په کلاسیکه شاعرۍ کې خوشال هغه علامه ، نابغه ، ستر شاعر او لوی ادیب دی ، چې د څه کم څلورسو کالو راهسې دده کلتوري خزانه تر ننه پورې دافغان ولس د نړۍ د لویو پوهانو او پوهنيزو مرکزونو د پاملرنې او څیړنې وړ کرځیدلې ده . د څیړونکو ځیرکتنه به تر هغې پورې دغه کلتوري میراث ته وجود ولری ، څو چې په نړۍ کې ولسونه په پوهنه او څیړنه بو خت وي . له خوشال څخه کوټې کوټې موضوعات او درانه درانه اثار په میراث راپاتې دي . دده اثار د شعر ، ادب ، ژبپوهنې او نورو بېلا بېلو پوهنو او څیړنو لپاره لوی دریاب دی ، چې لامبوزن هم پکې سټر کیږی خو دده برید ، پوله ، سر او تل به تر خپلې لامبو لاندې داخیل نه کړی او د ژوند تر پایه به پکې ستړی او ستومانه وي .", "language": "pus", "unit": "sentence" } python-0.7.4/tests/mock-data/request/pus-sentence-entities_linked.json 0000664 0000000 0000000 00000002244 12636317025 0026220 0 ustar 00root root 0000000 0000000 { "content": "د پښتو ادب په کلاسیکه شاعرۍ کې خوشال هغه علامه ، نابغه ، ستر شاعر او لوی ادیب دی ، چې د څه کم څلورسو کالو راهسې دده کلتوري خزانه تر ننه پورې دافغان ولس د نړۍ د لویو پوهانو او پوهنيزو مرکزونو د پاملرنې او څیړنې وړ کرځیدلې ده . د څیړونکو ځیرکتنه به تر هغې پورې دغه کلتوري میراث ته وجود ولری ، څو چې په نړۍ کې ولسونه په پوهنه او څیړنه بو خت وي . له خوشال څخه کوټې کوټې موضوعات او درانه درانه اثار په میراث راپاتې دي . دده اثار د شعر ، ادب ، ژبپوهنې او نورو بېلا بېلو پوهنو او څیړنو لپاره لوی دریاب دی ، چې لامبوزن هم پکې سټر کیږی خو دده برید ، پوله ، سر او تل به تر خپلې لامبو لاندې داخیل نه کړی او د ژوند تر پایه به پکې ستړی او ستومانه وي .", "language": "pus", "unit": "sentence" } python-0.7.4/tests/mock-data/request/pus-sentence-language.json 0000664 0000000 0000000 00000002244 12636317025 0024631 0 ustar 00root root 0000000 0000000 { "content": "د پښتو ادب په کلاسیکه شاعرۍ کې خوشال هغه علامه ، نابغه ، ستر شاعر او لوی ادیب دی ، چې د څه کم څلورسو کالو راهسې دده کلتوري خزانه تر ننه پورې دافغان ولس د نړۍ د لویو پوهانو او پوهنيزو مرکزونو د پاملرنې او څیړنې وړ کرځیدلې ده . د څیړونکو ځیرکتنه به تر هغې پورې دغه کلتوري میراث ته وجود ولری ، څو چې په نړۍ کې ولسونه په پوهنه او څیړنه بو خت وي . له خوشال څخه کوټې کوټې موضوعات او درانه درانه اثار په میراث راپاتې دي . دده اثار د شعر ، ادب ، ژبپوهنې او نورو بېلا بېلو پوهنو او څیړنو لپاره لوی دریاب دی ، چې لامبوزن هم پکې سټر کیږی خو دده برید ، پوله ، سر او تل به تر خپلې لامبو لاندې داخیل نه کړی او د ژوند تر پایه به پکې ستړی او ستومانه وي .", "language": "pus", "unit": "sentence" } python-0.7.4/tests/mock-data/request/pus-sentence-morphology_complete.json 0000664 0000000 0000000 00000002244 12636317025 0027135 0 ustar 00root root 0000000 0000000 { "content": "د پښتو ادب په کلاسیکه شاعرۍ کې خوشال هغه علامه ، نابغه ، ستر شاعر او لوی ادیب دی ، چې د څه کم څلورسو کالو راهسې دده کلتوري خزانه تر ننه پورې دافغان ولس د نړۍ د لویو پوهانو او پوهنيزو مرکزونو د پاملرنې او څیړنې وړ کرځیدلې ده . د څیړونکو ځیرکتنه به تر هغې پورې دغه کلتوري میراث ته وجود ولری ، څو چې په نړۍ کې ولسونه په پوهنه او څیړنه بو خت وي . له خوشال څخه کوټې کوټې موضوعات او درانه درانه اثار په میراث راپاتې دي . دده اثار د شعر ، ادب ، ژبپوهنې او نورو بېلا بېلو پوهنو او څیړنو لپاره لوی دریاب دی ، چې لامبوزن هم پکې سټر کیږی خو دده برید ، پوله ، سر او تل به تر خپلې لامبو لاندې داخیل نه کړی او د ژوند تر پایه به پکې ستړی او ستومانه وي .", "language": "pus", "unit": "sentence" } python-0.7.4/tests/mock-data/request/pus-sentence-sentiment.json 0000664 0000000 0000000 00000002244 12636317025 0025054 0 ustar 00root root 0000000 0000000 { "content": "د پښتو ادب په کلاسیکه شاعرۍ کې خوشال هغه علامه ، نابغه ، ستر شاعر او لوی ادیب دی ، چې د څه کم څلورسو کالو راهسې دده کلتوري خزانه تر ننه پورې دافغان ولس د نړۍ د لویو پوهانو او پوهنيزو مرکزونو د پاملرنې او څیړنې وړ کرځیدلې ده . د څیړونکو ځیرکتنه به تر هغې پورې دغه کلتوري میراث ته وجود ولری ، څو چې په نړۍ کې ولسونه په پوهنه او څیړنه بو خت وي . له خوشال څخه کوټې کوټې موضوعات او درانه درانه اثار په میراث راپاتې دي . دده اثار د شعر ، ادب ، ژبپوهنې او نورو بېلا بېلو پوهنو او څیړنو لپاره لوی دریاب دی ، چې لامبوزن هم پکې سټر کیږی خو دده برید ، پوله ، سر او تل به تر خپلې لامبو لاندې داخیل نه کړی او د ژوند تر پایه به پکې ستړی او ستومانه وي .", "language": "pus", "unit": "sentence" } python-0.7.4/tests/mock-data/request/rni-1-matched-name.json 0000664 0000000 0000000 00000000355 12636317025 0023707 0 ustar 00root root 0000000 0000000 { "name1": { "entityType": "PERSON", "language": "eng", "script": "Latn", "text": "John Doe" }, "name2": { "entityType": "PERSON", "language": "fra", "script": "Latn", "text": "Jane Doe" } } python-0.7.4/tests/mock-data/request/rnt-1-translated-name.json 0000664 0000000 0000000 00000000354 12636317025 0024455 0 ustar 00root root 0000000 0000000 { "entityType": "PERSON", "name": "毛泽东", "sourceLanguageOfOrigin": "zho", "sourceLanguageOfUse": "zho", "sourceScript": "Hani", "targetLanguage": "eng", "targetScheme": "HYPY_TONED", "targetScript": "Latn" } python-0.7.4/tests/mock-data/request/spa-doc-categories.json 0000664 0000000 0000000 00000004227 12636317025 0024113 0 ustar 00root root 0000000 0000000 { "content": "\"Entrega el mar, devuelve el mar...\", gritaron algunos de los ciudadanos paceños apostados en la Plaza Murillo, a las afueras del palacio de gobierno y la sede del Congreso de Bolivia, mientras la Presidenta Michelle Bachelet salía de la extensa ceremonia en que Evo Morales renovó por cinco años más como Mandatario de ese país.\nLa Presidenta ya había abordado el tema marítimo a primera hora de ayer, mientras visitaba un hospital para niños. Ahí, Bachelet destacó que en 2006 había acordado con Morales una agenda de 13 puntos, en la que \"hemos hecho progresos importantes\". \"Y todos esperamos que en los años venideros nuestros Estados continúen profundizándola\", agregó.\nAludía así a la agenda que, en su punto sexto, contempla el \"tema marítimo\", pero cuyos detalles son poco conocidos.\nPor lo mismo, cuando fue consultada sobre qué esperaría que hiciera sobre este punto específico su sucesor, Sebastián Piñera, ella reforzó su mensaje. \"Lo que tiene que hacer cualquier gobierno en Chile es seguir profundizando todos los puntos de trabajo en una agenda que ha sido concordada en común\", dijo la Mandataria.\nLa postura asumida ayer por Bachelet se produjo sólo días después de que Evo Morales dejara entrever su inquietud por la actitud que tendrá Piñera ante la aspiración boliviana de una salida al mar. En La Paz creen que el nuevo gobernante chileno restringirá al máximo el diálogo sobre este punto.\nDicha inquietud tuvo su origen en el debate presidencial de hace dos semanas entre Piñera y Eduardo Frei, cuando el actual Presidente electo dijo que no conversaría sobre cesión de soberanía y que sólo tenía en carpeta mejorar el acceso boliviano al Pacífico, frase que es leída en la diplomacia boliviana como \"simples facilidades portuarias\". Morales respondió el martes que \"cualquier compromiso es de Estado a Estado\", y su canciller, David Choquehuanca, pidió mantener la agenda bilateral.\n\n\n\nhttp://diario.elmercurio.com/2010/01/23/nacional/politica/noticias/47D6CA26-B011-40B5-AEAB-D0E6A5F52E59.htm?id={47D6CA26-B011-40B5-AEAB-D0E6A5F52E59}\n2010.01.23", "language": "spa", "unit": "doc" } python-0.7.4/tests/mock-data/request/spa-doc-entities.json 0000664 0000000 0000000 00000004227 12636317025 0023612 0 ustar 00root root 0000000 0000000 { "content": "\"Entrega el mar, devuelve el mar...\", gritaron algunos de los ciudadanos paceños apostados en la Plaza Murillo, a las afueras del palacio de gobierno y la sede del Congreso de Bolivia, mientras la Presidenta Michelle Bachelet salía de la extensa ceremonia en que Evo Morales renovó por cinco años más como Mandatario de ese país.\nLa Presidenta ya había abordado el tema marítimo a primera hora de ayer, mientras visitaba un hospital para niños. Ahí, Bachelet destacó que en 2006 había acordado con Morales una agenda de 13 puntos, en la que \"hemos hecho progresos importantes\". \"Y todos esperamos que en los años venideros nuestros Estados continúen profundizándola\", agregó.\nAludía así a la agenda que, en su punto sexto, contempla el \"tema marítimo\", pero cuyos detalles son poco conocidos.\nPor lo mismo, cuando fue consultada sobre qué esperaría que hiciera sobre este punto específico su sucesor, Sebastián Piñera, ella reforzó su mensaje. \"Lo que tiene que hacer cualquier gobierno en Chile es seguir profundizando todos los puntos de trabajo en una agenda que ha sido concordada en común\", dijo la Mandataria.\nLa postura asumida ayer por Bachelet se produjo sólo días después de que Evo Morales dejara entrever su inquietud por la actitud que tendrá Piñera ante la aspiración boliviana de una salida al mar. En La Paz creen que el nuevo gobernante chileno restringirá al máximo el diálogo sobre este punto.\nDicha inquietud tuvo su origen en el debate presidencial de hace dos semanas entre Piñera y Eduardo Frei, cuando el actual Presidente electo dijo que no conversaría sobre cesión de soberanía y que sólo tenía en carpeta mejorar el acceso boliviano al Pacífico, frase que es leída en la diplomacia boliviana como \"simples facilidades portuarias\". Morales respondió el martes que \"cualquier compromiso es de Estado a Estado\", y su canciller, David Choquehuanca, pidió mantener la agenda bilateral.\n\n\n\nhttp://diario.elmercurio.com/2010/01/23/nacional/politica/noticias/47D6CA26-B011-40B5-AEAB-D0E6A5F52E59.htm?id={47D6CA26-B011-40B5-AEAB-D0E6A5F52E59}\n2010.01.23", "language": "spa", "unit": "doc" } python-0.7.4/tests/mock-data/request/spa-doc-entities_linked.json 0000664 0000000 0000000 00000004227 12636317025 0025140 0 ustar 00root root 0000000 0000000 { "content": "\"Entrega el mar, devuelve el mar...\", gritaron algunos de los ciudadanos paceños apostados en la Plaza Murillo, a las afueras del palacio de gobierno y la sede del Congreso de Bolivia, mientras la Presidenta Michelle Bachelet salía de la extensa ceremonia en que Evo Morales renovó por cinco años más como Mandatario de ese país.\nLa Presidenta ya había abordado el tema marítimo a primera hora de ayer, mientras visitaba un hospital para niños. Ahí, Bachelet destacó que en 2006 había acordado con Morales una agenda de 13 puntos, en la que \"hemos hecho progresos importantes\". \"Y todos esperamos que en los años venideros nuestros Estados continúen profundizándola\", agregó.\nAludía así a la agenda que, en su punto sexto, contempla el \"tema marítimo\", pero cuyos detalles son poco conocidos.\nPor lo mismo, cuando fue consultada sobre qué esperaría que hiciera sobre este punto específico su sucesor, Sebastián Piñera, ella reforzó su mensaje. \"Lo que tiene que hacer cualquier gobierno en Chile es seguir profundizando todos los puntos de trabajo en una agenda que ha sido concordada en común\", dijo la Mandataria.\nLa postura asumida ayer por Bachelet se produjo sólo días después de que Evo Morales dejara entrever su inquietud por la actitud que tendrá Piñera ante la aspiración boliviana de una salida al mar. En La Paz creen que el nuevo gobernante chileno restringirá al máximo el diálogo sobre este punto.\nDicha inquietud tuvo su origen en el debate presidencial de hace dos semanas entre Piñera y Eduardo Frei, cuando el actual Presidente electo dijo que no conversaría sobre cesión de soberanía y que sólo tenía en carpeta mejorar el acceso boliviano al Pacífico, frase que es leída en la diplomacia boliviana como \"simples facilidades portuarias\". Morales respondió el martes que \"cualquier compromiso es de Estado a Estado\", y su canciller, David Choquehuanca, pidió mantener la agenda bilateral.\n\n\n\nhttp://diario.elmercurio.com/2010/01/23/nacional/politica/noticias/47D6CA26-B011-40B5-AEAB-D0E6A5F52E59.htm?id={47D6CA26-B011-40B5-AEAB-D0E6A5F52E59}\n2010.01.23", "language": "spa", "unit": "doc" } python-0.7.4/tests/mock-data/request/spa-doc-language.json 0000664 0000000 0000000 00000004227 12636317025 0023551 0 ustar 00root root 0000000 0000000 { "content": "\"Entrega el mar, devuelve el mar...\", gritaron algunos de los ciudadanos paceños apostados en la Plaza Murillo, a las afueras del palacio de gobierno y la sede del Congreso de Bolivia, mientras la Presidenta Michelle Bachelet salía de la extensa ceremonia en que Evo Morales renovó por cinco años más como Mandatario de ese país.\nLa Presidenta ya había abordado el tema marítimo a primera hora de ayer, mientras visitaba un hospital para niños. Ahí, Bachelet destacó que en 2006 había acordado con Morales una agenda de 13 puntos, en la que \"hemos hecho progresos importantes\". \"Y todos esperamos que en los años venideros nuestros Estados continúen profundizándola\", agregó.\nAludía así a la agenda que, en su punto sexto, contempla el \"tema marítimo\", pero cuyos detalles son poco conocidos.\nPor lo mismo, cuando fue consultada sobre qué esperaría que hiciera sobre este punto específico su sucesor, Sebastián Piñera, ella reforzó su mensaje. \"Lo que tiene que hacer cualquier gobierno en Chile es seguir profundizando todos los puntos de trabajo en una agenda que ha sido concordada en común\", dijo la Mandataria.\nLa postura asumida ayer por Bachelet se produjo sólo días después de que Evo Morales dejara entrever su inquietud por la actitud que tendrá Piñera ante la aspiración boliviana de una salida al mar. En La Paz creen que el nuevo gobernante chileno restringirá al máximo el diálogo sobre este punto.\nDicha inquietud tuvo su origen en el debate presidencial de hace dos semanas entre Piñera y Eduardo Frei, cuando el actual Presidente electo dijo que no conversaría sobre cesión de soberanía y que sólo tenía en carpeta mejorar el acceso boliviano al Pacífico, frase que es leída en la diplomacia boliviana como \"simples facilidades portuarias\". Morales respondió el martes que \"cualquier compromiso es de Estado a Estado\", y su canciller, David Choquehuanca, pidió mantener la agenda bilateral.\n\n\n\nhttp://diario.elmercurio.com/2010/01/23/nacional/politica/noticias/47D6CA26-B011-40B5-AEAB-D0E6A5F52E59.htm?id={47D6CA26-B011-40B5-AEAB-D0E6A5F52E59}\n2010.01.23", "language": "spa", "unit": "doc" } python-0.7.4/tests/mock-data/request/spa-doc-morphology_complete.json 0000664 0000000 0000000 00000004227 12636317025 0026055 0 ustar 00root root 0000000 0000000 { "content": "\"Entrega el mar, devuelve el mar...\", gritaron algunos de los ciudadanos paceños apostados en la Plaza Murillo, a las afueras del palacio de gobierno y la sede del Congreso de Bolivia, mientras la Presidenta Michelle Bachelet salía de la extensa ceremonia en que Evo Morales renovó por cinco años más como Mandatario de ese país.\nLa Presidenta ya había abordado el tema marítimo a primera hora de ayer, mientras visitaba un hospital para niños. Ahí, Bachelet destacó que en 2006 había acordado con Morales una agenda de 13 puntos, en la que \"hemos hecho progresos importantes\". \"Y todos esperamos que en los años venideros nuestros Estados continúen profundizándola\", agregó.\nAludía así a la agenda que, en su punto sexto, contempla el \"tema marítimo\", pero cuyos detalles son poco conocidos.\nPor lo mismo, cuando fue consultada sobre qué esperaría que hiciera sobre este punto específico su sucesor, Sebastián Piñera, ella reforzó su mensaje. \"Lo que tiene que hacer cualquier gobierno en Chile es seguir profundizando todos los puntos de trabajo en una agenda que ha sido concordada en común\", dijo la Mandataria.\nLa postura asumida ayer por Bachelet se produjo sólo días después de que Evo Morales dejara entrever su inquietud por la actitud que tendrá Piñera ante la aspiración boliviana de una salida al mar. En La Paz creen que el nuevo gobernante chileno restringirá al máximo el diálogo sobre este punto.\nDicha inquietud tuvo su origen en el debate presidencial de hace dos semanas entre Piñera y Eduardo Frei, cuando el actual Presidente electo dijo que no conversaría sobre cesión de soberanía y que sólo tenía en carpeta mejorar el acceso boliviano al Pacífico, frase que es leída en la diplomacia boliviana como \"simples facilidades portuarias\". Morales respondió el martes que \"cualquier compromiso es de Estado a Estado\", y su canciller, David Choquehuanca, pidió mantener la agenda bilateral.\n\n\n\nhttp://diario.elmercurio.com/2010/01/23/nacional/politica/noticias/47D6CA26-B011-40B5-AEAB-D0E6A5F52E59.htm?id={47D6CA26-B011-40B5-AEAB-D0E6A5F52E59}\n2010.01.23", "language": "spa", "unit": "doc" } python-0.7.4/tests/mock-data/request/spa-doc-sentiment.json 0000664 0000000 0000000 00000004227 12636317025 0023774 0 ustar 00root root 0000000 0000000 { "content": "\"Entrega el mar, devuelve el mar...\", gritaron algunos de los ciudadanos paceños apostados en la Plaza Murillo, a las afueras del palacio de gobierno y la sede del Congreso de Bolivia, mientras la Presidenta Michelle Bachelet salía de la extensa ceremonia en que Evo Morales renovó por cinco años más como Mandatario de ese país.\nLa Presidenta ya había abordado el tema marítimo a primera hora de ayer, mientras visitaba un hospital para niños. Ahí, Bachelet destacó que en 2006 había acordado con Morales una agenda de 13 puntos, en la que \"hemos hecho progresos importantes\". \"Y todos esperamos que en los años venideros nuestros Estados continúen profundizándola\", agregó.\nAludía así a la agenda que, en su punto sexto, contempla el \"tema marítimo\", pero cuyos detalles son poco conocidos.\nPor lo mismo, cuando fue consultada sobre qué esperaría que hiciera sobre este punto específico su sucesor, Sebastián Piñera, ella reforzó su mensaje. \"Lo que tiene que hacer cualquier gobierno en Chile es seguir profundizando todos los puntos de trabajo en una agenda que ha sido concordada en común\", dijo la Mandataria.\nLa postura asumida ayer por Bachelet se produjo sólo días después de que Evo Morales dejara entrever su inquietud por la actitud que tendrá Piñera ante la aspiración boliviana de una salida al mar. En La Paz creen que el nuevo gobernante chileno restringirá al máximo el diálogo sobre este punto.\nDicha inquietud tuvo su origen en el debate presidencial de hace dos semanas entre Piñera y Eduardo Frei, cuando el actual Presidente electo dijo que no conversaría sobre cesión de soberanía y que sólo tenía en carpeta mejorar el acceso boliviano al Pacífico, frase que es leída en la diplomacia boliviana como \"simples facilidades portuarias\". Morales respondió el martes que \"cualquier compromiso es de Estado a Estado\", y su canciller, David Choquehuanca, pidió mantener la agenda bilateral.\n\n\n\nhttp://diario.elmercurio.com/2010/01/23/nacional/politica/noticias/47D6CA26-B011-40B5-AEAB-D0E6A5F52E59.htm?id={47D6CA26-B011-40B5-AEAB-D0E6A5F52E59}\n2010.01.23", "language": "spa", "unit": "doc" } python-0.7.4/tests/mock-data/request/spa-sentence-categories.json 0000664 0000000 0000000 00000001036 12636317025 0025145 0 ustar 00root root 0000000 0000000 { "content": "La crisis se ha producido en un tiempo de transición burocrática. La nueva zarina de la Política Exterior de la UE, Catherine Ashton, debe aún afianzarse en su puesto y el Parlamento Europeo ha impedido el nombramiento de la designada comisaria Rumiana Jeleva, cuyo cometido incluía la ayuda humanitaria. Como resultado, la respuesta de la UE parece revestir todos los signos de la política previa al Tratado de Lisboa: lenta, tecnocrática y eclipsada por Estados Unidos.", "language": "spa", "unit": "sentence" } python-0.7.4/tests/mock-data/request/spa-sentence-entities.json 0000664 0000000 0000000 00000001036 12636317025 0024644 0 ustar 00root root 0000000 0000000 { "content": "La crisis se ha producido en un tiempo de transición burocrática. La nueva zarina de la Política Exterior de la UE, Catherine Ashton, debe aún afianzarse en su puesto y el Parlamento Europeo ha impedido el nombramiento de la designada comisaria Rumiana Jeleva, cuyo cometido incluía la ayuda humanitaria. Como resultado, la respuesta de la UE parece revestir todos los signos de la política previa al Tratado de Lisboa: lenta, tecnocrática y eclipsada por Estados Unidos.", "language": "spa", "unit": "sentence" } python-0.7.4/tests/mock-data/request/spa-sentence-entities_linked.json 0000664 0000000 0000000 00000001036 12636317025 0026172 0 ustar 00root root 0000000 0000000 { "content": "La crisis se ha producido en un tiempo de transición burocrática. La nueva zarina de la Política Exterior de la UE, Catherine Ashton, debe aún afianzarse en su puesto y el Parlamento Europeo ha impedido el nombramiento de la designada comisaria Rumiana Jeleva, cuyo cometido incluía la ayuda humanitaria. Como resultado, la respuesta de la UE parece revestir todos los signos de la política previa al Tratado de Lisboa: lenta, tecnocrática y eclipsada por Estados Unidos.", "language": "spa", "unit": "sentence" } python-0.7.4/tests/mock-data/request/spa-sentence-language.json 0000664 0000000 0000000 00000001036 12636317025 0024603 0 ustar 00root root 0000000 0000000 { "content": "La crisis se ha producido en un tiempo de transición burocrática. La nueva zarina de la Política Exterior de la UE, Catherine Ashton, debe aún afianzarse en su puesto y el Parlamento Europeo ha impedido el nombramiento de la designada comisaria Rumiana Jeleva, cuyo cometido incluía la ayuda humanitaria. Como resultado, la respuesta de la UE parece revestir todos los signos de la política previa al Tratado de Lisboa: lenta, tecnocrática y eclipsada por Estados Unidos.", "language": "spa", "unit": "sentence" } python-0.7.4/tests/mock-data/request/spa-sentence-morphology_complete.json 0000664 0000000 0000000 00000001036 12636317025 0027107 0 ustar 00root root 0000000 0000000 { "content": "La crisis se ha producido en un tiempo de transición burocrática. La nueva zarina de la Política Exterior de la UE, Catherine Ashton, debe aún afianzarse en su puesto y el Parlamento Europeo ha impedido el nombramiento de la designada comisaria Rumiana Jeleva, cuyo cometido incluía la ayuda humanitaria. Como resultado, la respuesta de la UE parece revestir todos los signos de la política previa al Tratado de Lisboa: lenta, tecnocrática y eclipsada por Estados Unidos.", "language": "spa", "unit": "sentence" } python-0.7.4/tests/mock-data/request/spa-sentence-sentiment.json 0000664 0000000 0000000 00000001036 12636317025 0025026 0 ustar 00root root 0000000 0000000 { "content": "La crisis se ha producido en un tiempo de transición burocrática. La nueva zarina de la Política Exterior de la UE, Catherine Ashton, debe aún afianzarse en su puesto y el Parlamento Europeo ha impedido el nombramiento de la designada comisaria Rumiana Jeleva, cuyo cometido incluía la ayuda humanitaria. Como resultado, la respuesta de la UE parece revestir todos los signos de la política previa al Tratado de Lisboa: lenta, tecnocrática y eclipsada por Estados Unidos.", "language": "spa", "unit": "sentence" } python-0.7.4/tests/mock-data/request/spa-url-categories.json 0000664 0000000 0000000 00000000445 12636317025 0024146 0 ustar 00root root 0000000 0000000 { "contentUri": "http://news.google.com/news/url?sa=t&fd=R&ct2=es_mx&usg=AFQjCNGyGPteDB3v0v5HPmqBDVQ3CYDPRA&clid=c3a7d30bb8a4878e06b80cf16b898331&cid=52779247028501&ei=XQNNVfrXD9qs3AHr-4CADg&url=http://eleconomista.com.mx/sociedad/2015/05/08/mexico-colombia-naciones-objetivos-comunes-epn" } python-0.7.4/tests/mock-data/request/spa-url-entities.json 0000664 0000000 0000000 00000000445 12636317025 0023645 0 ustar 00root root 0000000 0000000 { "contentUri": "http://news.google.com/news/url?sa=t&fd=R&ct2=es_mx&usg=AFQjCNGyGPteDB3v0v5HPmqBDVQ3CYDPRA&clid=c3a7d30bb8a4878e06b80cf16b898331&cid=52779247028501&ei=XQNNVfrXD9qs3AHr-4CADg&url=http://eleconomista.com.mx/sociedad/2015/05/08/mexico-colombia-naciones-objetivos-comunes-epn" } python-0.7.4/tests/mock-data/request/spa-url-entities_linked.json 0000664 0000000 0000000 00000000445 12636317025 0025173 0 ustar 00root root 0000000 0000000 { "contentUri": "http://news.google.com/news/url?sa=t&fd=R&ct2=es_mx&usg=AFQjCNGyGPteDB3v0v5HPmqBDVQ3CYDPRA&clid=c3a7d30bb8a4878e06b80cf16b898331&cid=52779247028501&ei=XQNNVfrXD9qs3AHr-4CADg&url=http://eleconomista.com.mx/sociedad/2015/05/08/mexico-colombia-naciones-objetivos-comunes-epn" } python-0.7.4/tests/mock-data/request/spa-url-language.json 0000664 0000000 0000000 00000000445 12636317025 0023604 0 ustar 00root root 0000000 0000000 { "contentUri": "http://news.google.com/news/url?sa=t&fd=R&ct2=es_mx&usg=AFQjCNGyGPteDB3v0v5HPmqBDVQ3CYDPRA&clid=c3a7d30bb8a4878e06b80cf16b898331&cid=52779247028501&ei=XQNNVfrXD9qs3AHr-4CADg&url=http://eleconomista.com.mx/sociedad/2015/05/08/mexico-colombia-naciones-objetivos-comunes-epn" } python-0.7.4/tests/mock-data/request/spa-url-morphology_complete.json 0000664 0000000 0000000 00000000445 12636317025 0026110 0 ustar 00root root 0000000 0000000 { "contentUri": "http://news.google.com/news/url?sa=t&fd=R&ct2=es_mx&usg=AFQjCNGyGPteDB3v0v5HPmqBDVQ3CYDPRA&clid=c3a7d30bb8a4878e06b80cf16b898331&cid=52779247028501&ei=XQNNVfrXD9qs3AHr-4CADg&url=http://eleconomista.com.mx/sociedad/2015/05/08/mexico-colombia-naciones-objetivos-comunes-epn" } python-0.7.4/tests/mock-data/request/spa-url-sentiment.json 0000664 0000000 0000000 00000000445 12636317025 0024027 0 ustar 00root root 0000000 0000000 { "contentUri": "http://news.google.com/news/url?sa=t&fd=R&ct2=es_mx&usg=AFQjCNGyGPteDB3v0v5HPmqBDVQ3CYDPRA&clid=c3a7d30bb8a4878e06b80cf16b898331&cid=52779247028501&ei=XQNNVfrXD9qs3AHr-4CADg&url=http://eleconomista.com.mx/sociedad/2015/05/08/mexico-colombia-naciones-objetivos-comunes-epn" } python-0.7.4/tests/mock-data/request/xxx-doc-categories.json 0000664 0000000 0000000 00000002712 12636317025 0024154 0 ustar 00root root 0000000 0000000 { "content": "3.11.06 - Not und Elend in ihren Heimatländern lassen immer mehr Afrikaner die Reise nach Europa antreten. Insbesondere Spanien ist betroffen - allein 24.000 Flüchtlinge sind in diesem Jahr in Teneriffa angekommen. Nun berät die Europäische Union über Maßnahmen gegen den Flüchtlingsstrom. Nicht alle Länder sehen darin ein Gemeinschaftsproblem - der deutsche Innenminister Schäuble appelliert an die Eigenverantwortung der Länder.\n\nDie Flüchtlinge, die auf Teneriffa im Lager ausharren, kommen aus Ländern, in denen sie kaum existieren können - auch wegen der Konkurrenz aus Europa, wie Professor Klaus J. Bade, Migrationsforscher an der Universität Osnabrück weiß: \"Unsere Textilsammlungen landen auf kommerziellen Märkten und ruinieren die Textilindustrie. Und die schwimmenden Fischfabriken - Fisch unten rein, Dose oben raus - vor den afrikanischen Küsten ruinieren die Küstenfischerei. Ergebnis: In Somalia transportieren inzwischen ruinierte Fischer mit ihren Booten die Illegalen in Richtung Europa.\"\n\nDoch sich vor Illegalen zu schützen, damit müsse jedes Land selbst fertig werden, wie Wolfgang Schäuble (CDU) betont: \"In Brüssel ist der Ruf immer wohlfeil: Es muss alles europäisch gemacht werden. Jedes Land mit Außengrenzen muss seine Außengrenzen schon selber kontrollieren. Wenn wir die Verantwortung nach Europa schieben, wird es weder bürgernäher noch effizienter, sondern ganz im Gegenteil.\"", "unit": "doc" } python-0.7.4/tests/mock-data/request/xxx-doc-entities.json 0000664 0000000 0000000 00000002712 12636317025 0023653 0 ustar 00root root 0000000 0000000 { "content": "3.11.06 - Not und Elend in ihren Heimatländern lassen immer mehr Afrikaner die Reise nach Europa antreten. Insbesondere Spanien ist betroffen - allein 24.000 Flüchtlinge sind in diesem Jahr in Teneriffa angekommen. Nun berät die Europäische Union über Maßnahmen gegen den Flüchtlingsstrom. Nicht alle Länder sehen darin ein Gemeinschaftsproblem - der deutsche Innenminister Schäuble appelliert an die Eigenverantwortung der Länder.\n\nDie Flüchtlinge, die auf Teneriffa im Lager ausharren, kommen aus Ländern, in denen sie kaum existieren können - auch wegen der Konkurrenz aus Europa, wie Professor Klaus J. Bade, Migrationsforscher an der Universität Osnabrück weiß: \"Unsere Textilsammlungen landen auf kommerziellen Märkten und ruinieren die Textilindustrie. Und die schwimmenden Fischfabriken - Fisch unten rein, Dose oben raus - vor den afrikanischen Küsten ruinieren die Küstenfischerei. Ergebnis: In Somalia transportieren inzwischen ruinierte Fischer mit ihren Booten die Illegalen in Richtung Europa.\"\n\nDoch sich vor Illegalen zu schützen, damit müsse jedes Land selbst fertig werden, wie Wolfgang Schäuble (CDU) betont: \"In Brüssel ist der Ruf immer wohlfeil: Es muss alles europäisch gemacht werden. Jedes Land mit Außengrenzen muss seine Außengrenzen schon selber kontrollieren. Wenn wir die Verantwortung nach Europa schieben, wird es weder bürgernäher noch effizienter, sondern ganz im Gegenteil.\"", "unit": "doc" } python-0.7.4/tests/mock-data/request/xxx-doc-entities_linked.json 0000664 0000000 0000000 00000002712 12636317025 0025201 0 ustar 00root root 0000000 0000000 { "content": "3.11.06 - Not und Elend in ihren Heimatländern lassen immer mehr Afrikaner die Reise nach Europa antreten. Insbesondere Spanien ist betroffen - allein 24.000 Flüchtlinge sind in diesem Jahr in Teneriffa angekommen. Nun berät die Europäische Union über Maßnahmen gegen den Flüchtlingsstrom. Nicht alle Länder sehen darin ein Gemeinschaftsproblem - der deutsche Innenminister Schäuble appelliert an die Eigenverantwortung der Länder.\n\nDie Flüchtlinge, die auf Teneriffa im Lager ausharren, kommen aus Ländern, in denen sie kaum existieren können - auch wegen der Konkurrenz aus Europa, wie Professor Klaus J. Bade, Migrationsforscher an der Universität Osnabrück weiß: \"Unsere Textilsammlungen landen auf kommerziellen Märkten und ruinieren die Textilindustrie. Und die schwimmenden Fischfabriken - Fisch unten rein, Dose oben raus - vor den afrikanischen Küsten ruinieren die Küstenfischerei. Ergebnis: In Somalia transportieren inzwischen ruinierte Fischer mit ihren Booten die Illegalen in Richtung Europa.\"\n\nDoch sich vor Illegalen zu schützen, damit müsse jedes Land selbst fertig werden, wie Wolfgang Schäuble (CDU) betont: \"In Brüssel ist der Ruf immer wohlfeil: Es muss alles europäisch gemacht werden. Jedes Land mit Außengrenzen muss seine Außengrenzen schon selber kontrollieren. Wenn wir die Verantwortung nach Europa schieben, wird es weder bürgernäher noch effizienter, sondern ganz im Gegenteil.\"", "unit": "doc" } python-0.7.4/tests/mock-data/request/xxx-doc-language.json 0000664 0000000 0000000 00000002712 12636317025 0023612 0 ustar 00root root 0000000 0000000 { "content": "3.11.06 - Not und Elend in ihren Heimatländern lassen immer mehr Afrikaner die Reise nach Europa antreten. Insbesondere Spanien ist betroffen - allein 24.000 Flüchtlinge sind in diesem Jahr in Teneriffa angekommen. Nun berät die Europäische Union über Maßnahmen gegen den Flüchtlingsstrom. Nicht alle Länder sehen darin ein Gemeinschaftsproblem - der deutsche Innenminister Schäuble appelliert an die Eigenverantwortung der Länder.\n\nDie Flüchtlinge, die auf Teneriffa im Lager ausharren, kommen aus Ländern, in denen sie kaum existieren können - auch wegen der Konkurrenz aus Europa, wie Professor Klaus J. Bade, Migrationsforscher an der Universität Osnabrück weiß: \"Unsere Textilsammlungen landen auf kommerziellen Märkten und ruinieren die Textilindustrie. Und die schwimmenden Fischfabriken - Fisch unten rein, Dose oben raus - vor den afrikanischen Küsten ruinieren die Küstenfischerei. Ergebnis: In Somalia transportieren inzwischen ruinierte Fischer mit ihren Booten die Illegalen in Richtung Europa.\"\n\nDoch sich vor Illegalen zu schützen, damit müsse jedes Land selbst fertig werden, wie Wolfgang Schäuble (CDU) betont: \"In Brüssel ist der Ruf immer wohlfeil: Es muss alles europäisch gemacht werden. Jedes Land mit Außengrenzen muss seine Außengrenzen schon selber kontrollieren. Wenn wir die Verantwortung nach Europa schieben, wird es weder bürgernäher noch effizienter, sondern ganz im Gegenteil.\"", "unit": "doc" } python-0.7.4/tests/mock-data/request/xxx-doc-morphology_complete.json 0000664 0000000 0000000 00000002712 12636317025 0026116 0 ustar 00root root 0000000 0000000 { "content": "3.11.06 - Not und Elend in ihren Heimatländern lassen immer mehr Afrikaner die Reise nach Europa antreten. Insbesondere Spanien ist betroffen - allein 24.000 Flüchtlinge sind in diesem Jahr in Teneriffa angekommen. Nun berät die Europäische Union über Maßnahmen gegen den Flüchtlingsstrom. Nicht alle Länder sehen darin ein Gemeinschaftsproblem - der deutsche Innenminister Schäuble appelliert an die Eigenverantwortung der Länder.\n\nDie Flüchtlinge, die auf Teneriffa im Lager ausharren, kommen aus Ländern, in denen sie kaum existieren können - auch wegen der Konkurrenz aus Europa, wie Professor Klaus J. Bade, Migrationsforscher an der Universität Osnabrück weiß: \"Unsere Textilsammlungen landen auf kommerziellen Märkten und ruinieren die Textilindustrie. Und die schwimmenden Fischfabriken - Fisch unten rein, Dose oben raus - vor den afrikanischen Küsten ruinieren die Küstenfischerei. Ergebnis: In Somalia transportieren inzwischen ruinierte Fischer mit ihren Booten die Illegalen in Richtung Europa.\"\n\nDoch sich vor Illegalen zu schützen, damit müsse jedes Land selbst fertig werden, wie Wolfgang Schäuble (CDU) betont: \"In Brüssel ist der Ruf immer wohlfeil: Es muss alles europäisch gemacht werden. Jedes Land mit Außengrenzen muss seine Außengrenzen schon selber kontrollieren. Wenn wir die Verantwortung nach Europa schieben, wird es weder bürgernäher noch effizienter, sondern ganz im Gegenteil.\"", "unit": "doc" } python-0.7.4/tests/mock-data/request/xxx-doc-sentiment.json 0000664 0000000 0000000 00000002712 12636317025 0024035 0 ustar 00root root 0000000 0000000 { "content": "3.11.06 - Not und Elend in ihren Heimatländern lassen immer mehr Afrikaner die Reise nach Europa antreten. Insbesondere Spanien ist betroffen - allein 24.000 Flüchtlinge sind in diesem Jahr in Teneriffa angekommen. Nun berät die Europäische Union über Maßnahmen gegen den Flüchtlingsstrom. Nicht alle Länder sehen darin ein Gemeinschaftsproblem - der deutsche Innenminister Schäuble appelliert an die Eigenverantwortung der Länder.\n\nDie Flüchtlinge, die auf Teneriffa im Lager ausharren, kommen aus Ländern, in denen sie kaum existieren können - auch wegen der Konkurrenz aus Europa, wie Professor Klaus J. Bade, Migrationsforscher an der Universität Osnabrück weiß: \"Unsere Textilsammlungen landen auf kommerziellen Märkten und ruinieren die Textilindustrie. Und die schwimmenden Fischfabriken - Fisch unten rein, Dose oben raus - vor den afrikanischen Küsten ruinieren die Küstenfischerei. Ergebnis: In Somalia transportieren inzwischen ruinierte Fischer mit ihren Booten die Illegalen in Richtung Europa.\"\n\nDoch sich vor Illegalen zu schützen, damit müsse jedes Land selbst fertig werden, wie Wolfgang Schäuble (CDU) betont: \"In Brüssel ist der Ruf immer wohlfeil: Es muss alles europäisch gemacht werden. Jedes Land mit Außengrenzen muss seine Außengrenzen schon selber kontrollieren. Wenn wir die Verantwortung nach Europa schieben, wird es weder bürgernäher noch effizienter, sondern ganz im Gegenteil.\"", "unit": "doc" } python-0.7.4/tests/mock-data/request/xxx-null-categories.json 0000664 0000000 0000000 00000007517 12636317025 0024371 0 ustar 00root root 0000000 0000000 { "content": "김일성(金日成, 1912년 4월 15일 ~ 1994년 7월 8일)은 한국의 독립운동가이자 조선민주주의\n인민공화국의 정치인이다. 만주 조선공산주의청년동맹, 조선혁명군, 반일인민유격대(그후 조선인민혁명군으로 개편) 등을 조직했다. 해방 후 1948년부터 1972년까지는 조선민주주의인민공화국의 총리, 1972년부터는 인민공화국 국가주석이었고, 1990년 국가주석에 재선되었다. 원래 이름은 김성주(金成柱[1][2] 또는 金聖柱[3][4])였는데, 항일 투쟁을 하면서[3][4][5] 김일성으로 개명[3][4][6]하였다. 1966년 10월 당중앙위원회 제4기 14차전원회의에서 조선로동당 중앙위원회 총비서로 선출되었고 1970\n년에 진행된 제5차전당대회와 1980년 10월에의 6차전당대회에서 당중앙위원회 총비서로 또다시 재선\n되었다. 대한민국에서는 한국전쟁을 발발하게 한 장본인중 한사람으로 지목되어 최근까지 부정적인\n평가를 받아 왔다. 1994년 절대권력의 상징이었던 그가 사망하면서 아들 김정일에게 모든 권력을 승\n계하였다.\n\n\n어린 시절과 가계 [편집]\n\n김일성의 생가\n김일성은 1912년 4월 15일에 평안남도 대동군 고평면(古平面) 하리 칠곡(외가가 있었던 곳으로, 오늘날 평양 만경대)[6]에서 아버지 김형직(金亨稷, 1894년 7월 10일~1926년)과 어머니 강반석(康盤石,[7] 1892년~1932년)의 삼형제의 맏아들로 태어났다. 김일성의 전주 김씨 12대조 김계상이 전라북도 전\n주에서 평양으로 이주하였으며,[6][8] 이후 농업에 종사하였으며, 증조부 김응우는 제너럴 셔먼호 사건에 종군하였다. 북조선에서는 김응우가 제너럴 셔먼 호 격퇴의 지휘관이라 주장한다. 그의 생가는 만경대라는 이름으로 보존, 관리되고 있다. 김형직은 할아버지 이래로 지주 집안의 묘지기였으며,[9] 일본 제국주의에 대항하여 항일무장투쟁을 벌인 한국의 독립 운동가로 알려져 있다.[3] 어머니 강반석은 기독교 장로교 신도였고, 외할아버지 강돈욱[9]는 칠골교회의 장로[10]였다.[3] 김일성의 외가\n는 큰 외삼촌 강진석(康晋錫)을 비롯하여 일찍부터 항일 민족운동과 관련을 맺고 있었으며, 강돈욱은 평생을 교육사업에 헌신한 기독교인이었다.[9] 아버지 김형직 또는 할아버지 김보현이 기둥이 되라\n는 뜻에서 그의 이름을 성주(成柱) 또는 성주(聖柱)라 지었다고 한다.\n어려서 부모를 따라 만주 지린성(吉林省) 무송(撫松)으로 이사했다. 1919년 일곱 살이었던 김일성은 민족주의 계열의 독립운동을 하던 아버지 김형직을 따라 만주로 건너가 장백현 팔도구에서 팔도구소\n학교를 다녔다. 그 뒤 자식의 장래를 생각한 김형직의 결심에 따라 1923년 초부터 1925년 초까지 평\n안도 대동군 용산면 하리(下里) 칠골에 있는 외가에서 머물면서 창덕소학교에 다녔다.[9] 창덕학교는 1907년 하리 장로교회가 중심이 되어 세운 5년제 학교인데, 김일성의 외할아버지인 강돈욱도 설립자 가운데 한 사람이며, 한때 창덕학교의 교감과 교장을 맡기도 했다. 아버지 김형직의 권고로 중국말\n을 배우고 중국인소학교에서 중어공부를 하여 중어를 자유롭게 구사할수 있었다.[11]\n창덕학교로의 진학과정에 대하여 략력에서는 아버지 김형직이 '혁명을 하자면 자기 나라를 알아야 한다고 말한 권고를 받고 1923년 3월 중국 팔도구로부터 만경대까지배움의 천리길을 걸어 통학하며 외\n가집이 있는 칠골 창덕학교에서 공부하였다는 것이다." } python-0.7.4/tests/mock-data/request/xxx-null-entities.json 0000664 0000000 0000000 00000007517 12636317025 0024070 0 ustar 00root root 0000000 0000000 { "content": "김일성(金日成, 1912년 4월 15일 ~ 1994년 7월 8일)은 한국의 독립운동가이자 조선민주주의\n인민공화국의 정치인이다. 만주 조선공산주의청년동맹, 조선혁명군, 반일인민유격대(그후 조선인민혁명군으로 개편) 등을 조직했다. 해방 후 1948년부터 1972년까지는 조선민주주의인민공화국의 총리, 1972년부터는 인민공화국 국가주석이었고, 1990년 국가주석에 재선되었다. 원래 이름은 김성주(金成柱[1][2] 또는 金聖柱[3][4])였는데, 항일 투쟁을 하면서[3][4][5] 김일성으로 개명[3][4][6]하였다. 1966년 10월 당중앙위원회 제4기 14차전원회의에서 조선로동당 중앙위원회 총비서로 선출되었고 1970\n년에 진행된 제5차전당대회와 1980년 10월에의 6차전당대회에서 당중앙위원회 총비서로 또다시 재선\n되었다. 대한민국에서는 한국전쟁을 발발하게 한 장본인중 한사람으로 지목되어 최근까지 부정적인\n평가를 받아 왔다. 1994년 절대권력의 상징이었던 그가 사망하면서 아들 김정일에게 모든 권력을 승\n계하였다.\n\n\n어린 시절과 가계 [편집]\n\n김일성의 생가\n김일성은 1912년 4월 15일에 평안남도 대동군 고평면(古平面) 하리 칠곡(외가가 있었던 곳으로, 오늘날 평양 만경대)[6]에서 아버지 김형직(金亨稷, 1894년 7월 10일~1926년)과 어머니 강반석(康盤石,[7] 1892년~1932년)의 삼형제의 맏아들로 태어났다. 김일성의 전주 김씨 12대조 김계상이 전라북도 전\n주에서 평양으로 이주하였으며,[6][8] 이후 농업에 종사하였으며, 증조부 김응우는 제너럴 셔먼호 사건에 종군하였다. 북조선에서는 김응우가 제너럴 셔먼 호 격퇴의 지휘관이라 주장한다. 그의 생가는 만경대라는 이름으로 보존, 관리되고 있다. 김형직은 할아버지 이래로 지주 집안의 묘지기였으며,[9] 일본 제국주의에 대항하여 항일무장투쟁을 벌인 한국의 독립 운동가로 알려져 있다.[3] 어머니 강반석은 기독교 장로교 신도였고, 외할아버지 강돈욱[9]는 칠골교회의 장로[10]였다.[3] 김일성의 외가\n는 큰 외삼촌 강진석(康晋錫)을 비롯하여 일찍부터 항일 민족운동과 관련을 맺고 있었으며, 강돈욱은 평생을 교육사업에 헌신한 기독교인이었다.[9] 아버지 김형직 또는 할아버지 김보현이 기둥이 되라\n는 뜻에서 그의 이름을 성주(成柱) 또는 성주(聖柱)라 지었다고 한다.\n어려서 부모를 따라 만주 지린성(吉林省) 무송(撫松)으로 이사했다. 1919년 일곱 살이었던 김일성은 민족주의 계열의 독립운동을 하던 아버지 김형직을 따라 만주로 건너가 장백현 팔도구에서 팔도구소\n학교를 다녔다. 그 뒤 자식의 장래를 생각한 김형직의 결심에 따라 1923년 초부터 1925년 초까지 평\n안도 대동군 용산면 하리(下里) 칠골에 있는 외가에서 머물면서 창덕소학교에 다녔다.[9] 창덕학교는 1907년 하리 장로교회가 중심이 되어 세운 5년제 학교인데, 김일성의 외할아버지인 강돈욱도 설립자 가운데 한 사람이며, 한때 창덕학교의 교감과 교장을 맡기도 했다. 아버지 김형직의 권고로 중국말\n을 배우고 중국인소학교에서 중어공부를 하여 중어를 자유롭게 구사할수 있었다.[11]\n창덕학교로의 진학과정에 대하여 략력에서는 아버지 김형직이 '혁명을 하자면 자기 나라를 알아야 한다고 말한 권고를 받고 1923년 3월 중국 팔도구로부터 만경대까지배움의 천리길을 걸어 통학하며 외\n가집이 있는 칠골 창덕학교에서 공부하였다는 것이다." } python-0.7.4/tests/mock-data/request/xxx-null-entities_linked.json 0000664 0000000 0000000 00000007517 12636317025 0025416 0 ustar 00root root 0000000 0000000 { "content": "김일성(金日成, 1912년 4월 15일 ~ 1994년 7월 8일)은 한국의 독립운동가이자 조선민주주의\n인민공화국의 정치인이다. 만주 조선공산주의청년동맹, 조선혁명군, 반일인민유격대(그후 조선인민혁명군으로 개편) 등을 조직했다. 해방 후 1948년부터 1972년까지는 조선민주주의인민공화국의 총리, 1972년부터는 인민공화국 국가주석이었고, 1990년 국가주석에 재선되었다. 원래 이름은 김성주(金成柱[1][2] 또는 金聖柱[3][4])였는데, 항일 투쟁을 하면서[3][4][5] 김일성으로 개명[3][4][6]하였다. 1966년 10월 당중앙위원회 제4기 14차전원회의에서 조선로동당 중앙위원회 총비서로 선출되었고 1970\n년에 진행된 제5차전당대회와 1980년 10월에의 6차전당대회에서 당중앙위원회 총비서로 또다시 재선\n되었다. 대한민국에서는 한국전쟁을 발발하게 한 장본인중 한사람으로 지목되어 최근까지 부정적인\n평가를 받아 왔다. 1994년 절대권력의 상징이었던 그가 사망하면서 아들 김정일에게 모든 권력을 승\n계하였다.\n\n\n어린 시절과 가계 [편집]\n\n김일성의 생가\n김일성은 1912년 4월 15일에 평안남도 대동군 고평면(古平面) 하리 칠곡(외가가 있었던 곳으로, 오늘날 평양 만경대)[6]에서 아버지 김형직(金亨稷, 1894년 7월 10일~1926년)과 어머니 강반석(康盤石,[7] 1892년~1932년)의 삼형제의 맏아들로 태어났다. 김일성의 전주 김씨 12대조 김계상이 전라북도 전\n주에서 평양으로 이주하였으며,[6][8] 이후 농업에 종사하였으며, 증조부 김응우는 제너럴 셔먼호 사건에 종군하였다. 북조선에서는 김응우가 제너럴 셔먼 호 격퇴의 지휘관이라 주장한다. 그의 생가는 만경대라는 이름으로 보존, 관리되고 있다. 김형직은 할아버지 이래로 지주 집안의 묘지기였으며,[9] 일본 제국주의에 대항하여 항일무장투쟁을 벌인 한국의 독립 운동가로 알려져 있다.[3] 어머니 강반석은 기독교 장로교 신도였고, 외할아버지 강돈욱[9]는 칠골교회의 장로[10]였다.[3] 김일성의 외가\n는 큰 외삼촌 강진석(康晋錫)을 비롯하여 일찍부터 항일 민족운동과 관련을 맺고 있었으며, 강돈욱은 평생을 교육사업에 헌신한 기독교인이었다.[9] 아버지 김형직 또는 할아버지 김보현이 기둥이 되라\n는 뜻에서 그의 이름을 성주(成柱) 또는 성주(聖柱)라 지었다고 한다.\n어려서 부모를 따라 만주 지린성(吉林省) 무송(撫松)으로 이사했다. 1919년 일곱 살이었던 김일성은 민족주의 계열의 독립운동을 하던 아버지 김형직을 따라 만주로 건너가 장백현 팔도구에서 팔도구소\n학교를 다녔다. 그 뒤 자식의 장래를 생각한 김형직의 결심에 따라 1923년 초부터 1925년 초까지 평\n안도 대동군 용산면 하리(下里) 칠골에 있는 외가에서 머물면서 창덕소학교에 다녔다.[9] 창덕학교는 1907년 하리 장로교회가 중심이 되어 세운 5년제 학교인데, 김일성의 외할아버지인 강돈욱도 설립자 가운데 한 사람이며, 한때 창덕학교의 교감과 교장을 맡기도 했다. 아버지 김형직의 권고로 중국말\n을 배우고 중국인소학교에서 중어공부를 하여 중어를 자유롭게 구사할수 있었다.[11]\n창덕학교로의 진학과정에 대하여 략력에서는 아버지 김형직이 '혁명을 하자면 자기 나라를 알아야 한다고 말한 권고를 받고 1923년 3월 중국 팔도구로부터 만경대까지배움의 천리길을 걸어 통학하며 외\n가집이 있는 칠골 창덕학교에서 공부하였다는 것이다." } python-0.7.4/tests/mock-data/request/xxx-null-language.json 0000664 0000000 0000000 00000007517 12636317025 0024027 0 ustar 00root root 0000000 0000000 { "content": "김일성(金日成, 1912년 4월 15일 ~ 1994년 7월 8일)은 한국의 독립운동가이자 조선민주주의\n인민공화국의 정치인이다. 만주 조선공산주의청년동맹, 조선혁명군, 반일인민유격대(그후 조선인민혁명군으로 개편) 등을 조직했다. 해방 후 1948년부터 1972년까지는 조선민주주의인민공화국의 총리, 1972년부터는 인민공화국 국가주석이었고, 1990년 국가주석에 재선되었다. 원래 이름은 김성주(金成柱[1][2] 또는 金聖柱[3][4])였는데, 항일 투쟁을 하면서[3][4][5] 김일성으로 개명[3][4][6]하였다. 1966년 10월 당중앙위원회 제4기 14차전원회의에서 조선로동당 중앙위원회 총비서로 선출되었고 1970\n년에 진행된 제5차전당대회와 1980년 10월에의 6차전당대회에서 당중앙위원회 총비서로 또다시 재선\n되었다. 대한민국에서는 한국전쟁을 발발하게 한 장본인중 한사람으로 지목되어 최근까지 부정적인\n평가를 받아 왔다. 1994년 절대권력의 상징이었던 그가 사망하면서 아들 김정일에게 모든 권력을 승\n계하였다.\n\n\n어린 시절과 가계 [편집]\n\n김일성의 생가\n김일성은 1912년 4월 15일에 평안남도 대동군 고평면(古平面) 하리 칠곡(외가가 있었던 곳으로, 오늘날 평양 만경대)[6]에서 아버지 김형직(金亨稷, 1894년 7월 10일~1926년)과 어머니 강반석(康盤石,[7] 1892년~1932년)의 삼형제의 맏아들로 태어났다. 김일성의 전주 김씨 12대조 김계상이 전라북도 전\n주에서 평양으로 이주하였으며,[6][8] 이후 농업에 종사하였으며, 증조부 김응우는 제너럴 셔먼호 사건에 종군하였다. 북조선에서는 김응우가 제너럴 셔먼 호 격퇴의 지휘관이라 주장한다. 그의 생가는 만경대라는 이름으로 보존, 관리되고 있다. 김형직은 할아버지 이래로 지주 집안의 묘지기였으며,[9] 일본 제국주의에 대항하여 항일무장투쟁을 벌인 한국의 독립 운동가로 알려져 있다.[3] 어머니 강반석은 기독교 장로교 신도였고, 외할아버지 강돈욱[9]는 칠골교회의 장로[10]였다.[3] 김일성의 외가\n는 큰 외삼촌 강진석(康晋錫)을 비롯하여 일찍부터 항일 민족운동과 관련을 맺고 있었으며, 강돈욱은 평생을 교육사업에 헌신한 기독교인이었다.[9] 아버지 김형직 또는 할아버지 김보현이 기둥이 되라\n는 뜻에서 그의 이름을 성주(成柱) 또는 성주(聖柱)라 지었다고 한다.\n어려서 부모를 따라 만주 지린성(吉林省) 무송(撫松)으로 이사했다. 1919년 일곱 살이었던 김일성은 민족주의 계열의 독립운동을 하던 아버지 김형직을 따라 만주로 건너가 장백현 팔도구에서 팔도구소\n학교를 다녔다. 그 뒤 자식의 장래를 생각한 김형직의 결심에 따라 1923년 초부터 1925년 초까지 평\n안도 대동군 용산면 하리(下里) 칠골에 있는 외가에서 머물면서 창덕소학교에 다녔다.[9] 창덕학교는 1907년 하리 장로교회가 중심이 되어 세운 5년제 학교인데, 김일성의 외할아버지인 강돈욱도 설립자 가운데 한 사람이며, 한때 창덕학교의 교감과 교장을 맡기도 했다. 아버지 김형직의 권고로 중국말\n을 배우고 중국인소학교에서 중어공부를 하여 중어를 자유롭게 구사할수 있었다.[11]\n창덕학교로의 진학과정에 대하여 략력에서는 아버지 김형직이 '혁명을 하자면 자기 나라를 알아야 한다고 말한 권고를 받고 1923년 3월 중국 팔도구로부터 만경대까지배움의 천리길을 걸어 통학하며 외\n가집이 있는 칠골 창덕학교에서 공부하였다는 것이다." } python-0.7.4/tests/mock-data/request/xxx-null-morphology_complete.json 0000664 0000000 0000000 00000007517 12636317025 0026333 0 ustar 00root root 0000000 0000000 { "content": "김일성(金日成, 1912년 4월 15일 ~ 1994년 7월 8일)은 한국의 독립운동가이자 조선민주주의\n인민공화국의 정치인이다. 만주 조선공산주의청년동맹, 조선혁명군, 반일인민유격대(그후 조선인민혁명군으로 개편) 등을 조직했다. 해방 후 1948년부터 1972년까지는 조선민주주의인민공화국의 총리, 1972년부터는 인민공화국 국가주석이었고, 1990년 국가주석에 재선되었다. 원래 이름은 김성주(金成柱[1][2] 또는 金聖柱[3][4])였는데, 항일 투쟁을 하면서[3][4][5] 김일성으로 개명[3][4][6]하였다. 1966년 10월 당중앙위원회 제4기 14차전원회의에서 조선로동당 중앙위원회 총비서로 선출되었고 1970\n년에 진행된 제5차전당대회와 1980년 10월에의 6차전당대회에서 당중앙위원회 총비서로 또다시 재선\n되었다. 대한민국에서는 한국전쟁을 발발하게 한 장본인중 한사람으로 지목되어 최근까지 부정적인\n평가를 받아 왔다. 1994년 절대권력의 상징이었던 그가 사망하면서 아들 김정일에게 모든 권력을 승\n계하였다.\n\n\n어린 시절과 가계 [편집]\n\n김일성의 생가\n김일성은 1912년 4월 15일에 평안남도 대동군 고평면(古平面) 하리 칠곡(외가가 있었던 곳으로, 오늘날 평양 만경대)[6]에서 아버지 김형직(金亨稷, 1894년 7월 10일~1926년)과 어머니 강반석(康盤石,[7] 1892년~1932년)의 삼형제의 맏아들로 태어났다. 김일성의 전주 김씨 12대조 김계상이 전라북도 전\n주에서 평양으로 이주하였으며,[6][8] 이후 농업에 종사하였으며, 증조부 김응우는 제너럴 셔먼호 사건에 종군하였다. 북조선에서는 김응우가 제너럴 셔먼 호 격퇴의 지휘관이라 주장한다. 그의 생가는 만경대라는 이름으로 보존, 관리되고 있다. 김형직은 할아버지 이래로 지주 집안의 묘지기였으며,[9] 일본 제국주의에 대항하여 항일무장투쟁을 벌인 한국의 독립 운동가로 알려져 있다.[3] 어머니 강반석은 기독교 장로교 신도였고, 외할아버지 강돈욱[9]는 칠골교회의 장로[10]였다.[3] 김일성의 외가\n는 큰 외삼촌 강진석(康晋錫)을 비롯하여 일찍부터 항일 민족운동과 관련을 맺고 있었으며, 강돈욱은 평생을 교육사업에 헌신한 기독교인이었다.[9] 아버지 김형직 또는 할아버지 김보현이 기둥이 되라\n는 뜻에서 그의 이름을 성주(成柱) 또는 성주(聖柱)라 지었다고 한다.\n어려서 부모를 따라 만주 지린성(吉林省) 무송(撫松)으로 이사했다. 1919년 일곱 살이었던 김일성은 민족주의 계열의 독립운동을 하던 아버지 김형직을 따라 만주로 건너가 장백현 팔도구에서 팔도구소\n학교를 다녔다. 그 뒤 자식의 장래를 생각한 김형직의 결심에 따라 1923년 초부터 1925년 초까지 평\n안도 대동군 용산면 하리(下里) 칠골에 있는 외가에서 머물면서 창덕소학교에 다녔다.[9] 창덕학교는 1907년 하리 장로교회가 중심이 되어 세운 5년제 학교인데, 김일성의 외할아버지인 강돈욱도 설립자 가운데 한 사람이며, 한때 창덕학교의 교감과 교장을 맡기도 했다. 아버지 김형직의 권고로 중국말\n을 배우고 중국인소학교에서 중어공부를 하여 중어를 자유롭게 구사할수 있었다.[11]\n창덕학교로의 진학과정에 대하여 략력에서는 아버지 김형직이 '혁명을 하자면 자기 나라를 알아야 한다고 말한 권고를 받고 1923년 3월 중국 팔도구로부터 만경대까지배움의 천리길을 걸어 통학하며 외\n가집이 있는 칠골 창덕학교에서 공부하였다는 것이다." } python-0.7.4/tests/mock-data/request/xxx-null-sentiment.json 0000664 0000000 0000000 00000007517 12636317025 0024252 0 ustar 00root root 0000000 0000000 { "content": "김일성(金日成, 1912년 4월 15일 ~ 1994년 7월 8일)은 한국의 독립운동가이자 조선민주주의\n인민공화국의 정치인이다. 만주 조선공산주의청년동맹, 조선혁명군, 반일인민유격대(그후 조선인민혁명군으로 개편) 등을 조직했다. 해방 후 1948년부터 1972년까지는 조선민주주의인민공화국의 총리, 1972년부터는 인민공화국 국가주석이었고, 1990년 국가주석에 재선되었다. 원래 이름은 김성주(金成柱[1][2] 또는 金聖柱[3][4])였는데, 항일 투쟁을 하면서[3][4][5] 김일성으로 개명[3][4][6]하였다. 1966년 10월 당중앙위원회 제4기 14차전원회의에서 조선로동당 중앙위원회 총비서로 선출되었고 1970\n년에 진행된 제5차전당대회와 1980년 10월에의 6차전당대회에서 당중앙위원회 총비서로 또다시 재선\n되었다. 대한민국에서는 한국전쟁을 발발하게 한 장본인중 한사람으로 지목되어 최근까지 부정적인\n평가를 받아 왔다. 1994년 절대권력의 상징이었던 그가 사망하면서 아들 김정일에게 모든 권력을 승\n계하였다.\n\n\n어린 시절과 가계 [편집]\n\n김일성의 생가\n김일성은 1912년 4월 15일에 평안남도 대동군 고평면(古平面) 하리 칠곡(외가가 있었던 곳으로, 오늘날 평양 만경대)[6]에서 아버지 김형직(金亨稷, 1894년 7월 10일~1926년)과 어머니 강반석(康盤石,[7] 1892년~1932년)의 삼형제의 맏아들로 태어났다. 김일성의 전주 김씨 12대조 김계상이 전라북도 전\n주에서 평양으로 이주하였으며,[6][8] 이후 농업에 종사하였으며, 증조부 김응우는 제너럴 셔먼호 사건에 종군하였다. 북조선에서는 김응우가 제너럴 셔먼 호 격퇴의 지휘관이라 주장한다. 그의 생가는 만경대라는 이름으로 보존, 관리되고 있다. 김형직은 할아버지 이래로 지주 집안의 묘지기였으며,[9] 일본 제국주의에 대항하여 항일무장투쟁을 벌인 한국의 독립 운동가로 알려져 있다.[3] 어머니 강반석은 기독교 장로교 신도였고, 외할아버지 강돈욱[9]는 칠골교회의 장로[10]였다.[3] 김일성의 외가\n는 큰 외삼촌 강진석(康晋錫)을 비롯하여 일찍부터 항일 민족운동과 관련을 맺고 있었으며, 강돈욱은 평생을 교육사업에 헌신한 기독교인이었다.[9] 아버지 김형직 또는 할아버지 김보현이 기둥이 되라\n는 뜻에서 그의 이름을 성주(成柱) 또는 성주(聖柱)라 지었다고 한다.\n어려서 부모를 따라 만주 지린성(吉林省) 무송(撫松)으로 이사했다. 1919년 일곱 살이었던 김일성은 민족주의 계열의 독립운동을 하던 아버지 김형직을 따라 만주로 건너가 장백현 팔도구에서 팔도구소\n학교를 다녔다. 그 뒤 자식의 장래를 생각한 김형직의 결심에 따라 1923년 초부터 1925년 초까지 평\n안도 대동군 용산면 하리(下里) 칠골에 있는 외가에서 머물면서 창덕소학교에 다녔다.[9] 창덕학교는 1907년 하리 장로교회가 중심이 되어 세운 5년제 학교인데, 김일성의 외할아버지인 강돈욱도 설립자 가운데 한 사람이며, 한때 창덕학교의 교감과 교장을 맡기도 했다. 아버지 김형직의 권고로 중국말\n을 배우고 중국인소학교에서 중어공부를 하여 중어를 자유롭게 구사할수 있었다.[11]\n창덕학교로의 진학과정에 대하여 략력에서는 아버지 김형직이 '혁명을 하자면 자기 나라를 알아야 한다고 말한 권고를 받고 1923년 3월 중국 팔도구로부터 만경대까지배움의 천리길을 걸어 통학하며 외\n가집이 있는 칠골 창덕학교에서 공부하였다는 것이다." } python-0.7.4/tests/mock-data/request/xxx-sentence-categories.json 0000664 0000000 0000000 00000001111 12636317025 0025203 0 ustar 00root root 0000000 0000000 { "content": "Практически сразу после соревнований в Таллинне стартуют Олимпийские игры в Ванкувере. Однако Олег Овсянников уточнил, что времени и на отдых, и на акклиматизацию будет предостаточно. \"Сборная России будет вылетать несколькими этапами. С 31 января начнутся первые вылеты в Ванкувер\", - сообщил он.", "unit": "sentence" } python-0.7.4/tests/mock-data/request/xxx-sentence-entities.json 0000664 0000000 0000000 00000001111 12636317025 0024702 0 ustar 00root root 0000000 0000000 { "content": "Практически сразу после соревнований в Таллинне стартуют Олимпийские игры в Ванкувере. Однако Олег Овсянников уточнил, что времени и на отдых, и на акклиматизацию будет предостаточно. \"Сборная России будет вылетать несколькими этапами. С 31 января начнутся первые вылеты в Ванкувер\", - сообщил он.", "unit": "sentence" } python-0.7.4/tests/mock-data/request/xxx-sentence-entities_linked.json 0000664 0000000 0000000 00000001111 12636317025 0026230 0 ustar 00root root 0000000 0000000 { "content": "Практически сразу после соревнований в Таллинне стартуют Олимпийские игры в Ванкувере. Однако Олег Овсянников уточнил, что времени и на отдых, и на акклиматизацию будет предостаточно. \"Сборная России будет вылетать несколькими этапами. С 31 января начнутся первые вылеты в Ванкувер\", - сообщил он.", "unit": "sentence" } python-0.7.4/tests/mock-data/request/xxx-sentence-language.json 0000664 0000000 0000000 00000001111 12636317025 0024641 0 ustar 00root root 0000000 0000000 { "content": "Практически сразу после соревнований в Таллинне стартуют Олимпийские игры в Ванкувере. Однако Олег Овсянников уточнил, что времени и на отдых, и на акклиматизацию будет предостаточно. \"Сборная России будет вылетать несколькими этапами. С 31 января начнутся первые вылеты в Ванкувер\", - сообщил он.", "unit": "sentence" } python-0.7.4/tests/mock-data/request/xxx-sentence-morphology_complete.json 0000664 0000000 0000000 00000001111 12636317025 0027145 0 ustar 00root root 0000000 0000000 { "content": "Практически сразу после соревнований в Таллинне стартуют Олимпийские игры в Ванкувере. Однако Олег Овсянников уточнил, что времени и на отдых, и на акклиматизацию будет предостаточно. \"Сборная России будет вылетать несколькими этапами. С 31 января начнутся первые вылеты в Ванкувер\", - сообщил он.", "unit": "sentence" } python-0.7.4/tests/mock-data/request/xxx-sentence-sentiment.json 0000664 0000000 0000000 00000001111 12636317025 0025064 0 ustar 00root root 0000000 0000000 { "content": "Практически сразу после соревнований в Таллинне стартуют Олимпийские игры в Ванкувере. Однако Олег Овсянников уточнил, что времени и на отдых, и на акклиматизацию будет предостаточно. \"Сборная России будет вылетать несколькими этапами. С 31 января начнутся первые вылеты в Ванкувер\", - сообщил он.", "unit": "sentence" } python-0.7.4/tests/mock-data/request/zho-doc-categories.json 0000664 0000000 0000000 00000001636 12636317025 0024131 0 ustar 00root root 0000000 0000000 { "content": "新华网联合国１月２２日电（记者 白洁 王湘江）第６４届联合国大会２２日一致通过决议，呼吁１９２个成员国尽快响应联合国发起的海地救援紧急募捐呼吁，强调各国应对联合国主导的救灾工作予以支持。\n\n联大当天在纽约联合国总部就海地地震举行全体会议。第６４届联大代理主席、哈萨克斯坦常驻联合国代表艾季莫娃在致辞中说，海地灾后的长期重建和发展工作需要国际社会在未来几个月甚至几年内长期关注。\n\n她说，海底地震后，国际社会立即做出反应，对海地人民和政府予以声援和支持。已交付的人道主义援助物资满足了海地人民的一些迫切需求，但还有许多工作要做。\n\n\n\nhttp://news.xinhuanet.com/world/2010-01/23/content_12860329.htm\n2010.01.24", "language": "zho", "unit": "doc" } python-0.7.4/tests/mock-data/request/zho-doc-entities.json 0000664 0000000 0000000 00000001636 12636317025 0023630 0 ustar 00root root 0000000 0000000 { "content": "新华网联合国１月２２日电（记者 白洁 王湘江）第６４届联合国大会２２日一致通过决议，呼吁１９２个成员国尽快响应联合国发起的海地救援紧急募捐呼吁，强调各国应对联合国主导的救灾工作予以支持。\n\n联大当天在纽约联合国总部就海地地震举行全体会议。第６４届联大代理主席、哈萨克斯坦常驻联合国代表艾季莫娃在致辞中说，海地灾后的长期重建和发展工作需要国际社会在未来几个月甚至几年内长期关注。\n\n她说，海底地震后，国际社会立即做出反应，对海地人民和政府予以声援和支持。已交付的人道主义援助物资满足了海地人民的一些迫切需求，但还有许多工作要做。\n\n\n\nhttp://news.xinhuanet.com/world/2010-01/23/content_12860329.htm\n2010.01.24", "language": "zho", "unit": "doc" } python-0.7.4/tests/mock-data/request/zho-doc-entities_linked.json 0000664 0000000 0000000 00000001636 12636317025 0025156 0 ustar 00root root 0000000 0000000 { "content": "新华网联合国１月２２日电（记者 白洁 王湘江）第６４届联合国大会２２日一致通过决议，呼吁１９２个成员国尽快响应联合国发起的海地救援紧急募捐呼吁，强调各国应对联合国主导的救灾工作予以支持。\n\n联大当天在纽约联合国总部就海地地震举行全体会议。第６４届联大代理主席、哈萨克斯坦常驻联合国代表艾季莫娃在致辞中说，海地灾后的长期重建和发展工作需要国际社会在未来几个月甚至几年内长期关注。\n\n她说，海底地震后，国际社会立即做出反应，对海地人民和政府予以声援和支持。已交付的人道主义援助物资满足了海地人民的一些迫切需求，但还有许多工作要做。\n\n\n\nhttp://news.xinhuanet.com/world/2010-01/23/content_12860329.htm\n2010.01.24", "language": "zho", "unit": "doc" } python-0.7.4/tests/mock-data/request/zho-doc-language.json 0000664 0000000 0000000 00000001636 12636317025 0023567 0 ustar 00root root 0000000 0000000 { "content": "新华网联合国１月２２日电（记者 白洁 王湘江）第６４届联合国大会２２日一致通过决议，呼吁１９２个成员国尽快响应联合国发起的海地救援紧急募捐呼吁，强调各国应对联合国主导的救灾工作予以支持。\n\n联大当天在纽约联合国总部就海地地震举行全体会议。第６４届联大代理主席、哈萨克斯坦常驻联合国代表艾季莫娃在致辞中说，海地灾后的长期重建和发展工作需要国际社会在未来几个月甚至几年内长期关注。\n\n她说，海底地震后，国际社会立即做出反应，对海地人民和政府予以声援和支持。已交付的人道主义援助物资满足了海地人民的一些迫切需求，但还有许多工作要做。\n\n\n\nhttp://news.xinhuanet.com/world/2010-01/23/content_12860329.htm\n2010.01.24", "language": "zho", "unit": "doc" } python-0.7.4/tests/mock-data/request/zho-doc-morphology_complete.json 0000664 0000000 0000000 00000001636 12636317025 0026073 0 ustar 00root root 0000000 0000000 { "content": "新华网联合国１月２２日电（记者 白洁 王湘江）第６４届联合国大会２２日一致通过决议，呼吁１９２个成员国尽快响应联合国发起的海地救援紧急募捐呼吁，强调各国应对联合国主导的救灾工作予以支持。\n\n联大当天在纽约联合国总部就海地地震举行全体会议。第６４届联大代理主席、哈萨克斯坦常驻联合国代表艾季莫娃在致辞中说，海地灾后的长期重建和发展工作需要国际社会在未来几个月甚至几年内长期关注。\n\n她说，海底地震后，国际社会立即做出反应，对海地人民和政府予以声援和支持。已交付的人道主义援助物资满足了海地人民的一些迫切需求，但还有许多工作要做。\n\n\n\nhttp://news.xinhuanet.com/world/2010-01/23/content_12860329.htm\n2010.01.24", "language": "zho", "unit": "doc" } python-0.7.4/tests/mock-data/request/zho-doc-sentiment.json 0000664 0000000 0000000 00000001636 12636317025 0024012 0 ustar 00root root 0000000 0000000 { "content": "新华网联合国１月２２日电（记者 白洁 王湘江）第６４届联合国大会２２日一致通过决议，呼吁１９２个成员国尽快响应联合国发起的海地救援紧急募捐呼吁，强调各国应对联合国主导的救灾工作予以支持。\n\n联大当天在纽约联合国总部就海地地震举行全体会议。第６４届联大代理主席、哈萨克斯坦常驻联合国代表艾季莫娃在致辞中说，海地灾后的长期重建和发展工作需要国际社会在未来几个月甚至几年内长期关注。\n\n她说，海底地震后，国际社会立即做出反应，对海地人民和政府予以声援和支持。已交付的人道主义援助物资满足了海地人民的一些迫切需求，但还有许多工作要做。\n\n\n\nhttp://news.xinhuanet.com/world/2010-01/23/content_12860329.htm\n2010.01.24", "language": "zho", "unit": "doc" } python-0.7.4/tests/mock-data/request/zho-sentence-categories.json 0000664 0000000 0000000 00000000613 12636317025 0025162 0 ustar 00root root 0000000 0000000 { "content": "５月的莫斯科，草木葱茏，旌旗飘扬，呈现出浓郁的节日气氛。从当地时间9时开始，胡锦涛同其他国家领导人相继来到克里姆林宫，同在那里迎候的俄罗斯总统梅德韦杰夫亲切握手。随后，胡锦涛同出席庆典的其他贵宾前往红场，在红场观礼台就座。", "language": "zho", "unit": "sentence" } python-0.7.4/tests/mock-data/request/zho-sentence-entities.json 0000664 0000000 0000000 00000000613 12636317025 0024661 0 ustar 00root root 0000000 0000000 { "content": "５月的莫斯科，草木葱茏，旌旗飘扬，呈现出浓郁的节日气氛。从当地时间9时开始，胡锦涛同其他国家领导人相继来到克里姆林宫，同在那里迎候的俄罗斯总统梅德韦杰夫亲切握手。随后，胡锦涛同出席庆典的其他贵宾前往红场，在红场观礼台就座。", "language": "zho", "unit": "sentence" } python-0.7.4/tests/mock-data/request/zho-sentence-entities_linked.json 0000664 0000000 0000000 00000000613 12636317025 0026207 0 ustar 00root root 0000000 0000000 { "content": "５月的莫斯科，草木葱茏，旌旗飘扬，呈现出浓郁的节日气氛。从当地时间9时开始，胡锦涛同其他国家领导人相继来到克里姆林宫，同在那里迎候的俄罗斯总统梅德韦杰夫亲切握手。随后，胡锦涛同出席庆典的其他贵宾前往红场，在红场观礼台就座。", "language": "zho", "unit": "sentence" } python-0.7.4/tests/mock-data/request/zho-sentence-language.json 0000664 0000000 0000000 00000000613 12636317025 0024620 0 ustar 00root root 0000000 0000000 { "content": "５月的莫斯科，草木葱茏，旌旗飘扬，呈现出浓郁的节日气氛。从当地时间9时开始，胡锦涛同其他国家领导人相继来到克里姆林宫，同在那里迎候的俄罗斯总统梅德韦杰夫亲切握手。随后，胡锦涛同出席庆典的其他贵宾前往红场，在红场观礼台就座。", "language": "zho", "unit": "sentence" } python-0.7.4/tests/mock-data/request/zho-sentence-morphology_complete.json 0000664 0000000 0000000 00000000613 12636317025 0027124 0 ustar 00root root 0000000 0000000 { "content": "５月的莫斯科，草木葱茏，旌旗飘扬，呈现出浓郁的节日气氛。从当地时间9时开始，胡锦涛同其他国家领导人相继来到克里姆林宫，同在那里迎候的俄罗斯总统梅德韦杰夫亲切握手。随后，胡锦涛同出席庆典的其他贵宾前往红场，在红场观礼台就座。", "language": "zho", "unit": "sentence" } python-0.7.4/tests/mock-data/request/zho-sentence-sentiment.json 0000664 0000000 0000000 00000000613 12636317025 0025043 0 ustar 00root root 0000000 0000000 { "content": "５月的莫斯科，草木葱茏，旌旗飘扬，呈现出浓郁的节日气氛。从当地时间9时开始，胡锦涛同其他国家领导人相继来到克里姆林宫，同在那里迎候的俄罗斯总统梅德韦杰夫亲切握手。随后，胡锦涛同出席庆典的其他贵宾前往红场，在红场观礼台就座。", "language": "zho", "unit": "sentence" } python-0.7.4/tests/mock-data/request/zho-url-categories.json 0000664 0000000 0000000 00000000366 12636317025 0024165 0 ustar 00root root 0000000 0000000 { "contentUri": "http://news.google.com/news/url?sa=t&fd=R&ct2=cn&usg=AFQjCNH5oqwj5vM9tKXcryaZYQt4j52GYA&clid=c3a7d30bb8a4878e06b80cf16b898331&cid=52779210797701&ei=awNNVbCiGc_p3AGt7oCoDg&url=http://news.ifeng.com/a/20150508/43720010_0.shtml" } python-0.7.4/tests/mock-data/request/zho-url-entities.json 0000664 0000000 0000000 00000000366 12636317025 0023664 0 ustar 00root root 0000000 0000000 { "contentUri": "http://news.google.com/news/url?sa=t&fd=R&ct2=cn&usg=AFQjCNH5oqwj5vM9tKXcryaZYQt4j52GYA&clid=c3a7d30bb8a4878e06b80cf16b898331&cid=52779210797701&ei=awNNVbCiGc_p3AGt7oCoDg&url=http://news.ifeng.com/a/20150508/43720010_0.shtml" } python-0.7.4/tests/mock-data/request/zho-url-entities_linked.json 0000664 0000000 0000000 00000000366 12636317025 0025212 0 ustar 00root root 0000000 0000000 { "contentUri": "http://news.google.com/news/url?sa=t&fd=R&ct2=cn&usg=AFQjCNH5oqwj5vM9tKXcryaZYQt4j52GYA&clid=c3a7d30bb8a4878e06b80cf16b898331&cid=52779210797701&ei=awNNVbCiGc_p3AGt7oCoDg&url=http://news.ifeng.com/a/20150508/43720010_0.shtml" } python-0.7.4/tests/mock-data/request/zho-url-language.json 0000664 0000000 0000000 00000000366 12636317025 0023623 0 ustar 00root root 0000000 0000000 { "contentUri": "http://news.google.com/news/url?sa=t&fd=R&ct2=cn&usg=AFQjCNH5oqwj5vM9tKXcryaZYQt4j52GYA&clid=c3a7d30bb8a4878e06b80cf16b898331&cid=52779210797701&ei=awNNVbCiGc_p3AGt7oCoDg&url=http://news.ifeng.com/a/20150508/43720010_0.shtml" } python-0.7.4/tests/mock-data/request/zho-url-morphology_complete.json 0000664 0000000 0000000 00000000366 12636317025 0026127 0 ustar 00root root 0000000 0000000 { "contentUri": "http://news.google.com/news/url?sa=t&fd=R&ct2=cn&usg=AFQjCNH5oqwj5vM9tKXcryaZYQt4j52GYA&clid=c3a7d30bb8a4878e06b80cf16b898331&cid=52779210797701&ei=awNNVbCiGc_p3AGt7oCoDg&url=http://news.ifeng.com/a/20150508/43720010_0.shtml" } python-0.7.4/tests/mock-data/request/zho-url-sentiment.json 0000664 0000000 0000000 00000000366 12636317025 0024046 0 ustar 00root root 0000000 0000000 { "contentUri": "http://news.google.com/news/url?sa=t&fd=R&ct2=cn&usg=AFQjCNH5oqwj5vM9tKXcryaZYQt4j52GYA&clid=c3a7d30bb8a4878e06b80cf16b898331&cid=52779210797701&ei=awNNVbCiGc_p3AGt7oCoDg&url=http://news.ifeng.com/a/20150508/43720010_0.shtml" } python-0.7.4/tests/mock-data/response/ 0000775 0000000 0000000 00000000000 12636317025 0017710 5 ustar 00root root 0000000 0000000 python-0.7.4/tests/mock-data/response/ara-doc-categories.json 0000664 0000000 0000000 00000000233 12636317025 0024232 0 ustar 00root root 0000000 0000000 { "code": "unsupportedLanguage", "message": "Arabic is not supported by Rosette Categorizer", "requestId": "de587a1c-a23a-4d4a-a52e-1fa96fe13f33" } python-0.7.4/tests/mock-data/response/ara-doc-categories.status 0000664 0000000 0000000 00000000003 12636317025 0024577 0 ustar 00root root 0000000 0000000 415 python-0.7.4/tests/mock-data/response/ara-doc-entities.json 0000664 0000000 0000000 00000012333 12636317025 0023735 0 ustar 00root root 0000000 0000000 { "entities": [ { "confidence": 0.020943284034729004, "count": 4, "indocChainId": 6, "mention": "أفغانستان", "normalized": "أفغانستان", "type": "LOCATION" }, { "confidence": 1.0, "count": 3, "indocChainId": 15, "mention": "الأفغانية", "normalized": "الأفغانية", "type": "NATIONALITY" }, { "confidence": 0.013337045907974243, "count": 2, "indocChainId": 2, "mention": "ناتو", "normalized": "ناتو", "type": "ORGANIZATION" }, { "confidence": 0.021363019943237305, "count": 2, "indocChainId": 3, "mention": "لأفغانستان", "normalized": "لأفغانستان", "type": "LOCATION" }, { "confidence": 0.03828367590904236, "count": 2, "indocChainId": 8, "mention": "السفير", "normalized": "السفير", "type": "TITLE" }, { "confidence": 1.0, "count": 2, "indocChainId": 9, "mention": "البريطاني", "normalized": "البريطاني", "type": "NATIONALITY" }, { "confidence": 0.03427225351333618, "count": 2, "indocChainId": 10, "mention": "كابل", "normalized": "كابل", "type": "LOCATION" }, { "confidence": 1.0, "count": 2, "indocChainId": 14, "mention": "الولايات المتحدة", "normalized": "الولايات المتحدة", "type": "LOCATION" }, { "confidence": 0.009779423475265503, "count": 2, "indocChainId": 22, "mention": "حلف الأطلسي", "normalized": "حلف الأطلسي", "type": "ORGANIZATION" }, { "confidence": 0.01446753740310669, "count": 1, "indocChainId": 0, "mention": "مكة المكرمة", "normalized": "مكة المكرمة", "type": "LOCATION" }, { "confidence": 0.01943296194076538, "count": 1, "indocChainId": 1, "mention": "غرينتش", "normalized": "غرينتش", "type": "LOCATION" }, { "confidence": 0.012137770652770996, "count": 1, "indocChainId": 4, "mention": "حلف شمال الأطلسي", "normalized": "حلف شمال الأطلسي", "type": "ORGANIZATION" }, { "confidence": 0.0020059943199157715, "count": 1, "indocChainId": 7, "mention": "وول ستريت", "normalized": "وول ستريت", "type": "ORGANIZATION" }, { "confidence": 0.03418374061584473, "count": 1, "indocChainId": 12, "mention": "لندن", "normalized": "لندن", "type": "LOCATION" }, { "confidence": 0.00932997465133667, "count": 1, "indocChainId": 17, "mention": "الأمين العام", "normalized": "الأمين العام", "type": "TITLE" }, { "confidence": 0.01955312490463257, "count": 1, "indocChainId": 18, "mention": "للأمم المتحدة", "normalized": "لأمم المتحدة", "type": "ORGANIZATION" }, { "confidence": 0.008319079875946045, "count": 1, "indocChainId": 19, "mention": "بان كي مون", "normalized": "بان كي مون", "type": "PERSON" }, { "confidence": 0.02144944667816162, "count": 1, "indocChainId": 21, "mention": "إيساف", "normalized": "إيساف", "type": "ORGANIZATION" }, { "confidence": 0.006335079669952393, "count": 1, "indocChainId": 23, "mention": "الولايات", "normalized": "الولايات", "type": "LOCATION" }, { "confidence": 1.0, "count": 1, "indocChainId": 25, "mention": "للأميركي", "normalized": "لأميركي", "type": "NATIONALITY" }, { "confidence": 0.0270041823387146, "count": 1, "indocChainId": 26, "mention": "ستانلي ماكريستال", "normalized": "ستانلي ماكريستال", "type": "PERSON" }, { "confidence": 0.03057950735092163, "count": 1, "indocChainId": 27, "mention": "قائد", "normalized": "قائد", "type": "TITLE" }, { "confidence": 1.0, "count": 1, "indocChainId": 28, "mention": "الأميركية", "normalized": "الأميركية", "type": "NATIONALITY" }, { "confidence": 0.015597224235534668, "count": 1, "indocChainId": 32, "mention": "لحركة طالبان", "normalized": "حركة طالبان", "type": "ORGANIZATION" }, { "confidence": 0.05023258924484253, "count": 1, "indocChainId": 35, "mention": "مارك سيدويل", "normalized": "مارك سيدويل", "type": "PERSON" } ], "requestId": "f1c7d4d6-a219-42b2-9b30-b636a80d3746", "timers": { "rblJe": 84, "rexJe": 59, "rliJe": 3 } } python-0.7.4/tests/mock-data/response/ara-doc-entities.status 0000664 0000000 0000000 00000000003 12636317025 0024276 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/ara-doc-entities_linked.json 0000664 0000000 0000000 00000005506 12636317025 0025267 0 ustar 00root root 0000000 0000000 { "entities": [ { "confidence": 0.39940380363670086, "entityId": "NEW-CLUSTER", "indocChainId": 0, "mention": "مكة المكرمة" }, { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 1, "mention": "غرينتش" }, { "confidence": 0.29350423961888833, "entityId": "NEW-CLUSTER", "indocChainId": 2, "mention": "ناتو" }, { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 3, "mention": "لأفغانستان" }, { "confidence": 0.35041779388669325, "entityId": "NEW-CLUSTER", "indocChainId": 4, "mention": "حلف شمال الأطلسي" }, { "confidence": 0.10983116823066236, "entityId": "Q889", "indocChainId": 6, "mention": "أفغانستان" }, { "confidence": 0.030689190138138037, "entityId": "NEW-CLUSTER", "indocChainId": 7, "mention": "وول ستريت" }, { "confidence": 0.03803483756221173, "entityId": "NEW-CLUSTER", "indocChainId": 10, "mention": "كابل" }, { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 12, "mention": "لندن" }, { "confidence": 0.040624368693206604, "entityId": "NEW-CLUSTER", "indocChainId": 14, "mention": "الولايات المتحدة" }, { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 18, "mention": "لأمم المتحدة" }, { "confidence": 0.08879232079319452, "entityId": "NEW-CLUSTER", "indocChainId": 19, "mention": "بان كي مون" }, { "confidence": 0.10803231598208785, "entityId": "NEW-CLUSTER", "indocChainId": 21, "mention": "إيساف" }, { "confidence": 0.4570567600989213, "entityId": "NEW-CLUSTER", "indocChainId": 22, "mention": "حلف الأطلسي" }, { "confidence": 0.690947400428972, "entityId": "NEW-CLUSTER", "indocChainId": 23, "mention": "الولايات" }, { "confidence": 0.08819493903532481, "entityId": "NEW-CLUSTER", "indocChainId": 26, "mention": "ستانلي ماكريستال" }, { "confidence": 0.3024394928526506, "entityId": "NEW-CLUSTER", "indocChainId": 32, "mention": "حركة طالبان" }, { "confidence": 0.11780238382065118, "entityId": "NEW-CLUSTER", "indocChainId": 35, "mention": "مارك سيدويل" } ], "requestId": "25ccf022-1278-483b-9c99-5dd6af4b692d", "timers": { "rblJe": 65, "res": 1485, "rexJe": 18, "rliJe": 3 } } python-0.7.4/tests/mock-data/response/ara-doc-entities_linked.status 0000664 0000000 0000000 00000000003 12636317025 0025624 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/ara-doc-language.json 0000664 0000000 0000000 00000001015 12636317025 0023667 0 ustar 00root root 0000000 0000000 { "languageDetections": [ { "confidence": 0.09657184540132002, "language": "ara" }, { "confidence": 0.03240820376340581, "language": "fas" }, { "confidence": 0.028112492087846386, "language": "urd" }, { "confidence": 0.018090782073154954, "language": "kur" }, { "confidence": 0.016795236230892185, "language": "pus" } ], "requestId": "e8fdda60-83a2-4366-beeb-c1d10bb24027", "timers": { "rliJe": 4 } } python-0.7.4/tests/mock-data/response/ara-doc-language.status 0000664 0000000 0000000 00000000003 12636317025 0024235 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/ara-doc-morphology_complete.json 0000664 0000000 0000000 00000103331 12636317025 0026177 0 ustar 00root root 0000000 0000000 { "compounds": [], "hanReadings": [], "lemmas": [ { "lemma": "خَمِيس", "text": "الخميس" }, { "lemma": "5", "text": "5" }, { "lemma": "/", "text": "/" }, { "lemma": "2", "text": "2" }, { "lemma": "/", "text": "/" }, { "lemma": "1431", "text": "1431" }, { "lemma": "ه", "text": "هـ" }, { "lemma": "-", "text": "-" }, { "lemma": "مُوافِق", "text": "الموافق" }, { "lemma": "21", "text": "21" }, { "lemma": "/", "text": "/" }, { "lemma": "1", "text": "1" }, { "lemma": "/", "text": "/" }, { "lemma": "2010", "text": "2010" }, { "lemma": "م", "text": "م" }, { "lemma": "(", "text": "(" }, { "lemma": "آخِر", "text": "آخر" }, { "lemma": "تَحْدِيث", "text": "تحديث" }, { "lemma": ")", "text": ")" }, { "lemma": "ساعَة", "text": "الساعة" }, { "lemma": "10:01", "text": "10:01" }, { "lemma": "(", "text": "(" }, { "lemma": "مَكَّة", "text": "مكة" }, { "lemma": "مُكَرَّم", "text": "المكرمة" }, { "lemma": ")", "text": ")" }, { "lemma": "،", "text": "،" }, { "lemma": "7:01", "text": "7:01" }, { "lemma": "(", "text": "(" }, { "lemma": "جرِينِتْش", "text": "غرينتش" }, { "lemma": ")", "text": ")" }, { "lemma": "ناتُو", "text": "ناتو" }, { "lemma": "فَكَّر", "text": "يفكر" }, { "lemma": "مَسْؤُول", "text": "بمسؤول" }, { "lemma": "مَدَنِيّ", "text": "مدني" }, { "lemma": "لأفغانستان", "text": "لأفغانستان" }, { "lemma": "خَطَّط", "text": "يخطط" }, { "lemma": "حَلْف", "text": "حلف" }, { "lemma": "شَمال", "text": "شمال" }, { "lemma": "أَطْلَسِيّ", "text": "الأطلسي" }, { "lemma": "(", "text": "(" }, { "lemma": "ناتُو", "text": "ناتو" }, { "lemma": ")", "text": ")" }, { "lemma": "تَعْيِين", "text": "لتعيين" }, { "lemma": "مَسْؤُول", "text": "مسؤول" }, { "lemma": "مَدَنِيّ", "text": "مدني" }, { "lemma": "كَبِير", "text": "كبير" }, { "lemma": "فِي", "text": "في" }, { "lemma": "أَفْغانِسْتان", "text": "أفغانستان" }, { "lemma": "،", "text": "،" }, { "lemma": "وَسْطَ", "text": "وسط" }, { "lemma": "دَعْوَة", "text": "دعوات" }, { "lemma": "تَحْسِين", "text": "لتحسين" }, { "lemma": "تَنْسِيق", "text": "التنسيق" }, { "lemma": "سِياسِيّ", "text": "السياسي" }, { "lemma": "تَنْمَوِيّ", "text": "والتنموي" }, { "lemma": "فِي", "text": "في" }, { "lemma": "بَلَد", "text": "البلاد" }, { "lemma": "وِفْقَ", "text": "وفق" }, { "lemma": "ما", "text": "ما" }, { "lemma": "نَقَل", "text": "نقلته" }, { "lemma": "صَحِيفَة", "text": "صحيفة" }, { "lemma": "وُول", "text": "وول" }, { "lemma": "سترِيت", "text": "ستريت" }, { "lemma": ".", "text": "." }, { "lemma": "قال", "text": "وقالت" }, { "lemma": "صَحِيفَة", "text": "الصحيفة" }, { "lemma": "إِن", "text": "إن" }, { "lemma": "سَفِير", "text": "السفير" }, { "lemma": "برِيطانِيّ", "text": "البريطاني" }, { "lemma": "فِي", "text": "في" }, { "lemma": "كابِل", "text": "كابل" }, { "lemma": "فِي", "text": "في" }, { "lemma": "مُقَدِّم", "text": "مقدمة" }, { "lemma": "مُرَشَّح", "text": "المرشحين" }, { "lemma": "هٰذا", "text": "لهذا" }, { "lemma": "مَنْصِب", "text": "المنصب" }, { "lemma": "الَّذِي", "text": "والذي" }, { "lemma": "مِن", "text": "من" }, { "lemma": "مُحْتَمَل", "text": "المحتمل" }, { "lemma": "أَن", "text": "أن" }, { "lemma": "أَعْلَن", "text": "يعلن" }, { "lemma": "تَزامُن", "text": "بالتزامن" }, { "lemma": "مَعَ", "text": "مع" }, { "lemma": "مُؤْتَمَر", "text": "مؤتمر" }, { "lemma": "دَوْلِيّ", "text": "دولي" }, { "lemma": "عَن", "text": "عن" }, { "lemma": "مُسْتَقْبِل", "text": "مستقبل" }, { "lemma": "أَفْغانِسْتان", "text": "أفغانستان" }, { "lemma": "مُقَرَّر", "text": "المقرر" }, { "lemma": "عَقَد", "text": "عقده" }, { "lemma": "فِي", "text": "في" }, { "lemma": "لَنْدَن", "text": "لندن" }, { "lemma": "فِي", "text": "في" }, { "lemma": "28", "text": "28" }, { "lemma": "يَنايِر", "text": "يناير" }, { "lemma": "/", "text": "/" }, { "lemma": "كانُون", "text": "كانون" }, { "lemma": "ثانِي", "text": "الثاني" }, { "lemma": "مُقْبِل", "text": "المقبل" }, { "lemma": ".", "text": "." }, { "lemma": "أَضاف", "text": "وأضافت" }, { "lemma": "صَحِيفَة", "text": "الصحيفة" }, { "lemma": "-", "text": "-" }, { "lemma": "فِي", "text": "في" }, { "lemma": "تَقْرِير", "text": "تقرير" }, { "lemma": "لِ", "text": "لها" }, { "lemma": "مِن", "text": "من" }, { "lemma": "كابِل", "text": "كابل" }, { "lemma": "-", "text": "-" }, { "lemma": "أَن", "text": "أن" }, { "lemma": "مَسْؤُول", "text": "المسؤول" }, { "lemma": "جَدِيد", "text": "الجديد" }, { "lemma": "تَرَأَّس", "text": "سيترأس" }, { "lemma": "دِعامَة", "text": "دعامة" }, { "lemma": "مَدَنِيّ", "text": "مدنية" }, { "lemma": "تَحالُف", "text": "للتحالف" }, { "lemma": "الَّذِي", "text": "الذي" }, { "lemma": "قاد", "text": "تقوده" }, { "lemma": "وِلايَة", "text": "الولايات" }, { "lemma": "مُتَّحِد", "text": "المتحدة" }, { "lemma": "إِدارَة", "text": "لإدارة" }, { "lemma": "تَمْوِيل", "text": "التمويل" }, { "lemma": "مُساعِد", "text": "والمساعدات" }, { "lemma": "وِلايَة", "text": "للولايات" }, { "lemma": "أَفْغانِيّ", "text": "الأفغانية" }, { "lemma": "تَحاشِي", "text": "لتحاشي" }, { "lemma": "مُؤَسَّسَة", "text": "المؤسسات" }, { "lemma": "أَفْغانِيّ", "text": "الأفغانية" }, { "lemma": "فاسِد", "text": "الفاسدة" }, { "lemma": "\"", "text": "\"" }, { "lemma": ".", "text": "." }, { "lemma": "كان", "text": "وكان" }, { "lemma": "أَمِين", "text": "الأمين" }, { "lemma": "عامّ", "text": "العام" }, { "lemma": "أُمَّة", "text": "للأمم" }, { "lemma": "مُتَّحِد", "text": "المتحدة" }, { "lemma": "أَن", "text": "بان" }, { "lemma": "كَي", "text": "كي" }, { "lemma": "مَوَّن", "text": "مون" }, { "lemma": "دَعا", "text": "دعا" }, { "lemma": "هٰذا", "text": "هذا" }, { "lemma": "شَهْر", "text": "الشهر" }, { "lemma": "تَعْيِين", "text": "لتعيين" }, { "lemma": "مَسْؤُول", "text": "مسؤول" }, { "lemma": "مَدَنِيّ", "text": "مدني" }, { "lemma": "رَفِيع", "text": "رفيع" }, { "lemma": "ضِمْنَ", "text": "ضمن" }, { "lemma": "قُوَّة", "text": "قوة" }, { "lemma": "مُساعِد", "text": "المساعدة" }, { "lemma": "دَوْلِيّ", "text": "الدولية" }, { "lemma": "إِرْساء", "text": "لإرساء" }, { "lemma": "أَمَنّ", "text": "الأمن" }, { "lemma": "فِي", "text": "في" }, { "lemma": "أَفْغانِسْتان", "text": "أفغانستان" }, { "lemma": "(", "text": "(" }, { "lemma": "إِيساف", "text": "إيساف" }, { "lemma": ")", "text": ")" }, { "lemma": "الَّذِي", "text": "التي" }, { "lemma": "قاد", "text": "يقودها" }, { "lemma": "حَلْف", "text": "حلف" }, { "lemma": "أَطْلَسِيّ", "text": "الأطلسي" }, { "lemma": "مُساعِد", "text": "للمساعدة" }, { "lemma": "فِي", "text": "في" }, { "lemma": "تَنْسِيق", "text": "تنسيق" }, { "lemma": "جَهْد", "text": "الجهود" }, { "lemma": "سِياسِيّ", "text": "السياسية" }, { "lemma": "تَنْمَوِيّ", "text": "والتنموية" }, { "lemma": "فِي", "text": "في" }, { "lemma": "حَرْب", "text": "الحرب" }, { "lemma": "الَّذِي", "text": "التي" }, { "lemma": "دَخَل", "text": "دخلت" }, { "lemma": "عام", "text": "عامها" }, { "lemma": "تاسِع", "text": "التاسع" }, { "lemma": ".", "text": "." }, { "lemma": "أَضاف", "text": "وأضاف" }, { "lemma": "أَن", "text": "أن" }, { "lemma": "تَعْيِين", "text": "تعيين" }, { "lemma": "هٰذا", "text": "هذا" }, { "lemma": "مَسْؤُول", "text": "المسؤول" }, { "lemma": "أَتاح", "text": "سيتيح" }, { "lemma": "تَحْسِين", "text": "تحسين" }, { "lemma": "تَنْسِيق", "text": "التنسيق" }, { "lemma": "بَيْنَ", "text": "بين" }, { "lemma": "عَمَل", "text": "العمل" }, { "lemma": "سِياسِيّ", "text": "السياسي" }, { "lemma": "تَنْمَوِيّ", "text": "والتنموي" }, { "lemma": "خُصُوص", "text": "وخصوصا" }, { "lemma": "عَبْرَ", "text": "عبر" }, { "lemma": "فَرْق", "text": "فرق" }, { "lemma": "إِعادَة", "text": "إعادة" }, { "lemma": "بِناء", "text": "البناء" }, { "lemma": "فِي", "text": "في" }, { "lemma": "وِلايَة", "text": "الولايات" }, { "lemma": "أَفْغانِيّ", "text": "الأفغانية" }, { "lemma": ".", "text": "." }, { "lemma": "قال", "text": "وقالت" }, { "lemma": "جُورْنال", "text": "جورنال" }, { "lemma": "سترِيت", "text": "ستريت" }, { "lemma": "إِن", "text": "إن" }, { "lemma": "مَنْصِب", "text": "المنصب" }, { "lemma": "جَدِيد", "text": "الجديد" }, { "lemma": "كان", "text": "سيكون" }, { "lemma": "نَظِير", "text": "نظيرا" }, { "lemma": "أَمْرِيكِيّ", "text": "للأميركي" }, { "lemma": "ستانْلِي", "text": "ستانلي" }, { "lemma": "ماكرِيسْتال", "text": "ماكريستال" }, { "lemma": "قائِد", "text": "قائد" }, { "lemma": "قُوَّة", "text": "القوات" }, { "lemma": "أَمْرِيكِيّ", "text": "الأميركية" }, { "lemma": "قُوَّة", "text": "وقوات" }, { "lemma": "حَلْف", "text": "حلف" }, { "lemma": "أَطْلَسِيّ", "text": "الأطلسي" }, { "lemma": "فِي", "text": "في" }, { "lemma": "أَفْغانِسْتان", "text": "أفغانستان" }, { "lemma": ".", "text": "." }, { "lemma": "تَوَقَّع", "text": "ويتوقع" }, { "lemma": "وُصُول", "text": "وصول" }, { "lemma": "أَرْبَعُون", "text": "أربعين" }, { "lemma": "أَلْف", "text": "ألف" }, { "lemma": "جُنْدِيّ", "text": "جندي" }, { "lemma": "آخِر", "text": "آخرين" }, { "lemma": "أَفْغانِسْتان", "text": "لأفغانستان" }, { "lemma": "فِي", "text": "في" }, { "lemma": "شَهْر", "text": "الأشهر" }, { "lemma": "قَلِيل", "text": "القليلة" }, { "lemma": "مُقْبِل", "text": "المقبلة" }, { "lemma": "فِي", "text": "في" }, { "lemma": "إِطار", "text": "إطار" }, { "lemma": "إِسْتراتِيجِيّ", "text": "إستراتيجية" }, { "lemma": "مُجابَهَة", "text": "لمجابهة" }, { "lemma": "عَمَلِيَّة", "text": "العمليات" }, { "lemma": "مُسَلَّح", "text": "المسلحة" }, { "lemma": "حَرَكَة", "text": "لحركة" }, { "lemma": "طالِبان", "text": "طالبان" }, { "lemma": ".", "text": "." }, { "lemma": "أَشار", "text": "وأشارت" }, { "lemma": "صَحِيفَة", "text": "الصحيفة" }, { "lemma": "إِلَى", "text": "إلى" }, { "lemma": "أَن", "text": "أن" }, { "lemma": "خُطَّة", "text": "خطة" }, { "lemma": "تَعْيِين", "text": "تعيين" }, { "lemma": "سَفِير", "text": "السفير" }, { "lemma": "برِيطانِيّ", "text": "البريطاني" }, { "lemma": "مارْك", "text": "مارك" }, { "lemma": "سيدويل", "text": "سيدويل" }, { "lemma": "جَدّ", "text": "وجدت" }, { "lemma": "تَأْيِيد", "text": "تأييد" }, { "lemma": "وِلايَة", "text": "الولايات" }, { "lemma": "مُتَّحِد", "text": "المتحدة" }, { "lemma": "مِن", "text": "ومن" }, { "lemma": "مُرَجِّح", "text": "المرجح" }, { "lemma": "أَن", "text": "أن" }, { "lemma": "صادَق", "text": "يصادق" }, { "lemma": "عَلَى", "text": "عليها" }, { "lemma": "باقِي", "text": "باقي" }, { "lemma": "حَلِيف", "text": "الحلفاء" }, { "lemma": ".", "text": "." } ], "posTags": [ { "pos": "NOUN", "text": "الخميس" }, { "pos": "NUM", "text": "5" }, { "pos": "PUNC", "text": "/" }, { "pos": "NUM", "text": "2" }, { "pos": "PUNC", "text": "/" }, { "pos": "NUM", "text": "1431" }, { "pos": "ABBREV", "text": "هـ" }, { "pos": "PUNC", "text": "-" }, { "pos": "ADJ", "text": "الموافق" }, { "pos": "NUM", "text": "21" }, { "pos": "PUNC", "text": "/" }, { "pos": "NUM", "text": "1" }, { "pos": "PUNC", "text": "/" }, { "pos": "NUM", "text": "2010" }, { "pos": "ABBREV", "text": "م" }, { "pos": "PUNC", "text": "(" }, { "pos": "ADJ", "text": "آخر" }, { "pos": "NOUN", "text": "تحديث" }, { "pos": "PUNC", "text": ")" }, { "pos": "NOUN", "text": "الساعة" }, { "pos": "NON_ARABIC", "text": "10:01" }, { "pos": "PUNC", "text": "(" }, { "pos": "NOUN_PROP", "text": "مكة" }, { "pos": "ADJ", "text": "المكرمة" }, { "pos": "PUNC", "text": ")" }, { "pos": "PUNC", "text": "،" }, { "pos": "NON_ARABIC", "text": "7:01" }, { "pos": "PUNC", "text": "(" }, { "pos": "NOUN_PROP", "text": "غرينتش" }, { "pos": "PUNC", "text": ")" }, { "pos": "NOUN_PROP", "text": "ناتو" }, { "pos": "IV", "text": "يفكر" }, { "pos": "NOUN", "text": "بمسؤول" }, { "pos": "NOUN", "text": "مدني" }, { "pos": "NOUN_PROP", "text": "لأفغانستان" }, { "pos": "IV", "text": "يخطط" }, { "pos": "NOUN", "text": "حلف" }, { "pos": "NOUN", "text": "شمال" }, { "pos": "NOUN", "text": "الأطلسي" }, { "pos": "PUNC", "text": "(" }, { "pos": "NOUN_PROP", "text": "ناتو" }, { "pos": "PUNC", "text": ")" }, { "pos": "NOUN", "text": "لتعيين" }, { "pos": "NOUN", "text": "مسؤول" }, { "pos": "NOUN", "text": "مدني" }, { "pos": "ADJ", "text": "كبير" }, { "pos": "PREP", "text": "في" }, { "pos": "NOUN_PROP", "text": "أفغانستان" }, { "pos": "PUNC", "text": "،" }, { "pos": "NOUN", "text": "وسط" }, { "pos": "NOUN", "text": "دعوات" }, { "pos": "NOUN", "text": "لتحسين" }, { "pos": "NOUN", "text": "التنسيق" }, { "pos": "ADJ", "text": "السياسي" }, { "pos": "ADJ", "text": "والتنموي" }, { "pos": "PREP", "text": "في" }, { "pos": "NOUN", "text": "البلاد" }, { "pos": "PREP", "text": "وفق" }, { "pos": "REL_PRON", "text": "ما" }, { "pos": "PV", "text": "نقلته" }, { "pos": "NOUN", "text": "صحيفة" }, { "pos": "NOUN_PROP", "text": "وول" }, { "pos": "NOUN_PROP", "text": "ستريت" }, { "pos": "EOS", "text": "." }, { "pos": "PV", "text": "وقالت" }, { "pos": "NOUN", "text": "الصحيفة" }, { "pos": "SUB_CONJ", "text": "إن" }, { "pos": "NOUN", "text": "السفير" }, { "pos": "ADJ", "text": "البريطاني" }, { "pos": "PREP", "text": "في" }, { "pos": "NOUN", "text": "كابل" }, { "pos": "PREP", "text": "في" }, { "pos": "NOUN", "text": "مقدمة" }, { "pos": "NOUN", "text": "المرشحين" }, { "pos": "DEM_PRON", "text": "لهذا" }, { "pos": "NOUN", "text": "المنصب" }, { "pos": "REL_PRON", "text": "والذي" }, { "pos": "PREP", "text": "من" }, { "pos": "NOUN", "text": "المحتمل" }, { "pos": "SUB_CONJ", "text": "أن" }, { "pos": "IV", "text": "يعلن" }, { "pos": "NOUN", "text": "بالتزامن" }, { "pos": "PREP", "text": "مع" }, { "pos": "NOUN", "text": "مؤتمر" }, { "pos": "ADJ", "text": "دولي" }, { "pos": "PREP", "text": "عن" }, { "pos": "NOUN", "text": "مستقبل" }, { "pos": "NOUN_PROP", "text": "أفغانستان" }, { "pos": "ADJ", "text": "المقرر" }, { "pos": "PV", "text": "عقده" }, { "pos": "PREP", "text": "في" }, { "pos": "NOUN_PROP", "text": "لندن" }, { "pos": "PREP", "text": "في" }, { "pos": "NUM", "text": "28" }, { "pos": "NOUN_PROP", "text": "يناير" }, { "pos": "PUNC", "text": "/" }, { "pos": "NOUN_PROP", "text": "كانون" }, { "pos": "ADJ", "text": "الثاني" }, { "pos": "ADJ", "text": "المقبل" }, { "pos": "EOS", "text": "." }, { "pos": "PV", "text": "وأضافت" }, { "pos": "NOUN", "text": "الصحيفة" }, { "pos": "PUNC", "text": "-" }, { "pos": "PREP", "text": "في" }, { "pos": "NOUN", "text": "تقرير" }, { "pos": "PRONOUN", "text": "لها" }, { "pos": "PREP", "text": "من" }, { "pos": "NOUN", "text": "كابل" }, { "pos": "PUNC", "text": "-" }, { "pos": "SUB_CONJ", "text": "أن" }, { "pos": "NOUN", "text": "المسؤول" }, { "pos": "ADJ", "text": "الجديد" }, { "pos": "IV", "text": "سيترأس" }, { "pos": "NOUN", "text": "دعامة" }, { "pos": "ADJ", "text": "مدنية" }, { "pos": "NOUN", "text": "للتحالف" }, { "pos": "REL_PRON", "text": "الذي" }, { "pos": "IV", "text": "تقوده" }, { "pos": "NOUN", "text": "الولايات" }, { "pos": "ADJ", "text": "المتحدة" }, { "pos": "NOUN", "text": "لإدارة" }, { "pos": "NOUN", "text": "التمويل" }, { "pos": "NOUN", "text": "والمساعدات" }, { "pos": "NOUN", "text": "للولايات" }, { "pos": "ADJ", "text": "الأفغانية" }, { "pos": "NOUN", "text": "لتحاشي" }, { "pos": "NOUN", "text": "المؤسسات" }, { "pos": "ADJ", "text": "الأفغانية" }, { "pos": "ADJ", "text": "الفاسدة" }, { "pos": "PUNC", "text": "\"" }, { "pos": "EOS", "text": "." }, { "pos": "PV", "text": "وكان" }, { "pos": "NOUN", "text": "الأمين" }, { "pos": "ADJ", "text": "العام" }, { "pos": "NOUN", "text": "للأمم" }, { "pos": "ADJ", "text": "المتحدة" }, { "pos": "SUB_CONJ", "text": "بان" }, { "pos": "SUB_CONJ", "text": "كي" }, { "pos": "PV", "text": "مون" }, { "pos": "PV", "text": "دعا" }, { "pos": "DEM_PRON", "text": "هذا" }, { "pos": "NOUN", "text": "الشهر" }, { "pos": "NOUN", "text": "لتعيين" }, { "pos": "NOUN", "text": "مسؤول" }, { "pos": "ADJ", "text": "مدني" }, { "pos": "ADJ", "text": "رفيع" }, { "pos": "PREP", "text": "ضمن" }, { "pos": "NOUN", "text": "قوة" }, { "pos": "NOUN", "text": "المساعدة" }, { "pos": "ADJ", "text": "الدولية" }, { "pos": "NOUN", "text": "لإرساء" }, { "pos": "ADJ", "text": "الأمن" }, { "pos": "PREP", "text": "في" }, { "pos": "NOUN_PROP", "text": "أفغانستان" }, { "pos": "PUNC", "text": "(" }, { "pos": "NOUN_PROP", "text": "إيساف" }, { "pos": "PUNC", "text": ")" }, { "pos": "REL_PRON", "text": "التي" }, { "pos": "IV", "text": "يقودها" }, { "pos": "NOUN", "text": "حلف" }, { "pos": "ADJ", "text": "الأطلسي" }, { "pos": "NOUN", "text": "للمساعدة" }, { "pos": "PREP", "text": "في" }, { "pos": "NOUN", "text": "تنسيق" }, { "pos": "NOUN", "text": "الجهود" }, { "pos": "ADJ", "text": "السياسية" }, { "pos": "ADJ", "text": "والتنموية" }, { "pos": "PREP", "text": "في" }, { "pos": "NOUN", "text": "الحرب" }, { "pos": "REL_PRON", "text": "التي" }, { "pos": "PV", "text": "دخلت" }, { "pos": "NOUN", "text": "عامها" }, { "pos": "ADJ", "text": "التاسع" }, { "pos": "EOS", "text": "." }, { "pos": "PV", "text": "وأضاف" }, { "pos": "SUB_CONJ", "text": "أن" }, { "pos": "NOUN", "text": "تعيين" }, { "pos": "DEM_PRON", "text": "هذا" }, { "pos": "NOUN", "text": "المسؤول" }, { "pos": "IV", "text": "سيتيح" }, { "pos": "NOUN", "text": "تحسين" }, { "pos": "NOUN", "text": "التنسيق" }, { "pos": "PREP", "text": "بين" }, { "pos": "NOUN", "text": "العمل" }, { "pos": "ADJ", "text": "السياسي" }, { "pos": "ADJ", "text": "والتنموي" }, { "pos": "NOUN", "text": "وخصوصا" }, { "pos": "PREP", "text": "عبر" }, { "pos": "NOUN", "text": "فرق" }, { "pos": "NOUN", "text": "إعادة" }, { "pos": "NOUN", "text": "البناء" }, { "pos": "PREP", "text": "في" }, { "pos": "NOUN", "text": "الولايات" }, { "pos": "ADJ", "text": "الأفغانية" }, { "pos": "EOS", "text": "." }, { "pos": "PV", "text": "وقالت" }, { "pos": "NOUN_PROP", "text": "جورنال" }, { "pos": "NOUN_PROP", "text": "ستريت" }, { "pos": "SUB_CONJ", "text": "إن" }, { "pos": "NOUN", "text": "المنصب" }, { "pos": "ADJ", "text": "الجديد" }, { "pos": "IV", "text": "سيكون" }, { "pos": "NOUN", "text": "نظيرا" }, { "pos": "NOUN", "text": "للأميركي" }, { "pos": "NOUN_PROP", "text": "ستانلي" }, { "pos": "NOUN_PROP", "text": "ماكريستال" }, { "pos": "NOUN", "text": "قائد" }, { "pos": "NOUN", "text": "القوات" }, { "pos": "ADJ", "text": "الأميركية" }, { "pos": "NOUN", "text": "وقوات" }, { "pos": "NOUN", "text": "حلف" }, { "pos": "ADJ", "text": "الأطلسي" }, { "pos": "PREP", "text": "في" }, { "pos": "NOUN_PROP", "text": "أفغانستان" }, { "pos": "EOS", "text": "." }, { "pos": "IV_PASS", "text": "ويتوقع" }, { "pos": "NOUN", "text": "وصول" }, { "pos": "NUM", "text": "أربعين" }, { "pos": "NUM", "text": "ألف" }, { "pos": "NOUN", "text": "جندي" }, { "pos": "ADJ", "text": "آخرين" }, { "pos": "NOUN_PROP", "text": "لأفغانستان" }, { "pos": "PREP", "text": "في" }, { "pos": "NOUN", "text": "الأشهر" }, { "pos": "ADJ", "text": "القليلة" }, { "pos": "ADJ", "text": "المقبلة" }, { "pos": "PREP", "text": "في" }, { "pos": "NOUN", "text": "إطار" }, { "pos": "ADJ", "text": "إستراتيجية" }, { "pos": "NOUN", "text": "لمجابهة" }, { "pos": "NOUN", "text": "العمليات" }, { "pos": "ADJ", "text": "المسلحة" }, { "pos": "NOUN", "text": "لحركة" }, { "pos": "NOUN_PROP", "text": "طالبان" }, { "pos": "EOS", "text": "." }, { "pos": "PV", "text": "وأشارت" }, { "pos": "NOUN", "text": "الصحيفة" }, { "pos": "PREP", "text": "إلى" }, { "pos": "SUB_CONJ", "text": "أن" }, { "pos": "NOUN", "text": "خطة" }, { "pos": "NOUN", "text": "تعيين" }, { "pos": "NOUN", "text": "السفير" }, { "pos": "ADJ", "text": "البريطاني" }, { "pos": "NOUN_PROP", "text": "مارك" }, { "pos": "NOUN_PROP", "text": "سيدويل" }, { "pos": "PV", "text": "وجدت" }, { "pos": "NOUN", "text": "تأييد" }, { "pos": "NOUN", "text": "الولايات" }, { "pos": "ADJ", "text": "المتحدة" }, { "pos": "PREP", "text": "ومن" }, { "pos": "NOUN", "text": "المرجح" }, { "pos": "SUB_CONJ", "text": "أن" }, { "pos": "IV", "text": "يصادق" }, { "pos": "PRONOUN", "text": "عليها" }, { "pos": "NOUN", "text": "باقي" }, { "pos": "NOUN", "text": "الحلفاء" }, { "pos": "EOS", "text": "." } ], "requestId": "35ee0654-64f5-4450-96cd-a914b0a719b9", "timers": { "rblJe": 223, "rliJe": 4 } } python-0.7.4/tests/mock-data/response/ara-doc-morphology_complete.status 0000664 0000000 0000000 00000000003 12636317025 0026541 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/ara-doc-sentiment.json 0000664 0000000 0000000 00000000242 12636317025 0024113 0 ustar 00root root 0000000 0000000 { "code": "unsupportedLanguage", "message": "Arabic is not supported by Rosette Sentiment Analyzer", "requestId": "4ec010c9-c196-4062-a890-55e975d8ac8f" } python-0.7.4/tests/mock-data/response/ara-doc-sentiment.status 0000664 0000000 0000000 00000000003 12636317025 0024460 0 ustar 00root root 0000000 0000000 415 python-0.7.4/tests/mock-data/response/ara-sentence-categories.json 0000664 0000000 0000000 00000000233 12636317025 0025271 0 ustar 00root root 0000000 0000000 { "code": "unsupportedLanguage", "message": "Arabic is not supported by Rosette Categorizer", "requestId": "4586af26-3bd5-4bb4-9cee-3ad136985798" } python-0.7.4/tests/mock-data/response/ara-sentence-categories.status 0000664 0000000 0000000 00000000003 12636317025 0025636 0 ustar 00root root 0000000 0000000 415 python-0.7.4/tests/mock-data/response/ara-sentence-entities.json 0000664 0000000 0000000 00000003347 12636317025 0025001 0 ustar 00root root 0000000 0000000 { "entities": [ { "confidence": 0.004119843244552612, "count": 2, "indocChainId": 0, "mention": "دبي", "normalized": "دبي", "type": "LOCATION" }, { "confidence": 1.0, "count": 1, "indocChainId": 1, "mention": "أميركي", "normalized": "أميركي", "type": "NATIONALITY" }, { "confidence": 0.006177842617034912, "count": 1, "indocChainId": 2, "mention": "الشيخ", "normalized": "الشيخ", "type": "TITLE" }, { "confidence": 0.003537893295288086, "count": 1, "indocChainId": 3, "mention": "محمد بن راشد آل مكتوم", "normalized": "محمد بن راشد آل مكتوم", "type": "PERSON" }, { "confidence": 1.0, "count": 1, "indocChainId": 5, "mention": "Samsung", "normalized": "Samsung", "type": "ORGANIZATION" }, { "confidence": 0.009773313999176025, "count": 1, "indocChainId": 6, "mention": "روبرت بوث", "normalized": "روبرت بوث", "type": "PERSON" }, { "confidence": 0.006055951118469238, "count": 1, "indocChainId": 7, "mention": "المدير التنفيذي", "normalized": "المدير التنفيذي", "type": "TITLE" }, { "confidence": 1.0, "count": 1, "indocChainId": 8, "mention": "الإماراتية", "normalized": "الإماراتية", "type": "NATIONALITY" } ], "requestId": "4c66ed2d-a835-474a-9a27-3f4fca707756", "timers": { "rblJe": 39, "rexJe": 10, "rliJe": 3 } } python-0.7.4/tests/mock-data/response/ara-sentence-entities.status 0000664 0000000 0000000 00000000003 12636317025 0025335 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/ara-sentence-entities_linked.json 0000664 0000000 0000000 00000001376 12636317025 0026327 0 ustar 00root root 0000000 0000000 { "entities": [ { "confidence": 0.13091593098927945, "entityId": "NEW-CLUSTER", "indocChainId": 0, "mention": "دبي" }, { "confidence": 0.045611566485458166, "entityId": "Q57655", "indocChainId": 3, "mention": "محمد بن راشد آل مكتوم" }, { "confidence": 0.4783586575981415, "entityId": "Q20716", "indocChainId": 5, "mention": "Samsung" }, { "confidence": 0.14019590499206971, "entityId": "NEW-CLUSTER", "indocChainId": 6, "mention": "روبرت بوث" } ], "requestId": "bb952f0c-cb75-4025-a082-2efacbae855e", "timers": { "rblJe": 27, "res": 329, "rexJe": 9, "rliJe": 6 } } python-0.7.4/tests/mock-data/response/ara-sentence-entities_linked.status 0000664 0000000 0000000 00000000003 12636317025 0026663 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/ara-sentence-language.json 0000664 0000000 0000000 00000001014 12636317025 0024725 0 ustar 00root root 0000000 0000000 { "languageDetections": [ { "confidence": 0.09218922116434847, "language": "ara" }, { "confidence": 0.03582179959693543, "language": "fas" }, { "confidence": 0.02983419791161146, "language": "urd" }, { "confidence": 0.020947593192964797, "language": "kur" }, { "confidence": 0.017229542996230474, "language": "pus" } ], "requestId": "06094a3c-c665-47bc-b90a-29760b6a8b9b", "timers": { "rliJe": 6 } } python-0.7.4/tests/mock-data/response/ara-sentence-language.status 0000664 0000000 0000000 00000000003 12636317025 0025274 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/ara-sentence-morphology_complete.json 0000664 0000000 0000000 00000053674 12636317025 0027254 0 ustar 00root root 0000000 0000000 { "compounds": [], "hanReadings": [], "lemmas": [ { "lemma": "بَدَأ", "text": "بدأ" }, { "lemma": "عَمَل", "text": "العمل" }, { "lemma": "فِي", "text": "في" }, { "lemma": "يَنايِر", "text": "يناير" }, { "lemma": "2004", "text": "2004" }, { "lemma": "الَّذِي", "text": "الذي" }, { "lemma": "تَمّ", "text": "يتم" }, { "lemma": "بِناء", "text": "بناءه" }, { "lemma": "فِي", "text": "في" }, { "lemma": "وَسْطَ", "text": "وسط" }, { "lemma": "دُبَيّ", "text": "دبي" }, { "lemma": "بَلَغ", "text": "وبلغت" }, { "lemma": "تَكْلِيف", "text": "تكلفته" }, { "lemma": "إِجْمالِيّ", "text": "الإجمالية" }, { "lemma": "1.5", "text": "1.5" }, { "lemma": "مِلْيار", "text": "مليار" }, { "lemma": "دُولار", "text": "دولار" }, { "lemma": "أَمْرِيكِيّ", "text": "أميركي" }, { "lemma": "[", "text": "[" }, { "lemma": "5", "text": "5" }, { "lemma": "]", "text": "]" }, { "lemma": "؛", "text": "؛" }, { "lemma": "تَمّ", "text": "وتم" }, { "lemma": "اِفْتِتاح", "text": "افتتاحه" }, { "lemma": "فِي", "text": "في" }, { "lemma": "4", "text": "4" }, { "lemma": "يَنايِر", "text": "يناير" }, { "lemma": "2010", "text": "2010" }, { "lemma": "بحضور", "text": "بحضور" }, { "lemma": "شَيْخ", "text": "الشيخ" }, { "lemma": "مُحَمَّد", "text": "محمد" }, { "lemma": "بِن", "text": "بن" }, { "lemma": "راشِد", "text": "راشد" }, { "lemma": "آل", "text": "آل" }, { "lemma": "مَكْتُوم", "text": "مكتوم" }, { "lemma": "حاكِم", "text": "حاكم" }, { "lemma": "دُبِّيّ", "text": "دبي" }, { "lemma": ".", "text": "." }, { "lemma": "بَلُغ", "text": "ويبلغ" }, { "lemma": "طُول", "text": "طول" }, { "lemma": "بُرْج", "text": "البرج" }, { "lemma": "828", "text": "828" }, { "lemma": "مِتْر", "text": "مترا" }, { "lemma": "كان", "text": "وستكون" }, { "lemma": "مَسّاح", "text": "المساحة" }, { "lemma": "إِجْمالِيّ", "text": "الإجمالية" }, { "lemma": "4000000", "text": "4,000,000" }, { "lemma": "مِتْر", "text": "متر" }, { "lemma": "مُرَبَّع", "text": "مربع" }, { "lemma": "ضَمّ", "text": "وسيضم" }, { "lemma": "37", "text": "37" }, { "lemma": "طابِق", "text": "طابقاً" }, { "lemma": "كفندق", "text": "كفندق" }, { "lemma": "ضَمّ", "text": "ليضم" }, { "lemma": "403", "text": "403" }, { "lemma": "جُناح", "text": "جناح" }, { "lemma": "فُنْدُقِيّ", "text": "فندقي" }, { "lemma": "،", "text": "،" }, { "lemma": "ضَمّ", "text": "وسيضم" }, { "lemma": "57", "text": "57" }, { "lemma": "مِصْعَد", "text": "مصعد" }, { "lemma": "كَهْرَبائِيّ", "text": "كهربائي" }, { "lemma": "كان", "text": "وسيكون" }, { "lemma": "أَسْرَع", "text": "أسرعهم" }, { "lemma": "10م", "text": "10م" }, { "lemma": "/", "text": "/" }, { "lemma": "ثانِي", "text": "ثانية" }, { "lemma": "،", "text": "،" }, { "lemma": "وُصُول", "text": "وللوصول" }, { "lemma": "إِلَى", "text": "إلى" }, { "lemma": "500", "text": "500" }, { "lemma": "م", "text": "م" }, { "lemma": "اِحْتاج", "text": "تحتاج" }, { "lemma": "إِلَى", "text": "إلى" }, { "lemma": "55", "text": "55" }, { "lemma": "ثانِي", "text": "ثانية" }, { "lemma": "اِمْتَلَك", "text": "وتمتلكه" }, { "lemma": "شَرِكَة", "text": "شركة" }, { "lemma": "إِعْمار", "text": "إعمار" }, { "lemma": "عَقارِيّ", "text": "العقارية" }, { "lemma": "عَدّ", "text": "وتعد" }, { "lemma": "واحِد", "text": "واحدة" }, { "lemma": "مِن", "text": "من" }, { "lemma": "أَكْبَر", "text": "أكبر" }, { "lemma": "شَرِكَة", "text": "الشركات" }, { "lemma": "عَقارِيّ", "text": "العقارية" }, { "lemma": "فِي", "text": "في" }, { "lemma": "العالم.و", "text": "العالم.و" }, { "lemma": "قَد", "text": "قد" }, { "lemma": "تَوَلَّى", "text": "تولت" }, { "lemma": "عَمَلِيَّة", "text": "عملية" }, { "lemma": "بِناء", "text": "البناء" }, { "lemma": "شَرِكَة", "text": "شركة" }, { "lemma": "Samsung", "text": "Samsung" }, { "lemma": "C", "text": "C" }, { "lemma": "&", "text": "&" }, { "lemma": "T.", "text": "T." }, { "lemma": "هٰذا", "text": "وهذا" }, { "lemma": "بُرْج", "text": "البرج" }, { "lemma": "الَّذِي", "text": "الذي" }, { "lemma": "اِرْتَفَع", "text": "يرتفع" }, { "lemma": "سُرْعَة", "text": "بسرعة" }, { "lemma": "طابِق", "text": "طابق" }, { "lemma": "كُلّ", "text": "كل" }, { "lemma": "ثَلاث", "text": "ثلاث" }, { "lemma": "يَوْم", "text": "أيام" }, { "lemma": "(", "text": "(" }, { "lemma": "تَقْرِيب", "text": "تقريبا" }, { "lemma": ")", "text": ")" }, { "lemma": "شَكَل", "text": "شكل" }, { "lemma": "بِناء", "text": "البناء" }, { "lemma": "رَئِيسِيّ", "text": "الرئيسي" }, { "lemma": "فِي", "text": "في" }, { "lemma": "مَشْرُوع", "text": "مشروع" }, { "lemma": "عُمْرانِيّ", "text": "عمراني" }, { "lemma": "ضَخْم", "text": "ضخم" }, { "lemma": "قِيمَة", "text": "بقيمة" }, { "lemma": "20", "text": "20" }, { "lemma": "مِلْيار", "text": "مليار" }, { "lemma": "دُولار", "text": "دولار" }, { "lemma": "تَوَقَّع", "text": "يتوقع" }, { "lemma": "أَن", "text": "أن" }, { "lemma": "أَغار", "text": "يغير" }, { "lemma": "مَلْمَح", "text": "ملامح" }, { "lemma": "مُدِين", "text": "المدينة" }, { "lemma": ".", "text": "." }, { "lemma": "أَوْضَح", "text": "وأوضح" }, { "lemma": "رُوبِرْت", "text": "روبرت" }, { "lemma": "بوث", "text": "بوث" }, { "lemma": "مُدِير", "text": "المدير" }, { "lemma": "تَنْفِيذِيّ", "text": "التنفيذي" }, { "lemma": "فِي", "text": "في" }, { "lemma": "شَرِكَة", "text": "الشركة" }, { "lemma": "إِماراتِيّ", "text": "الإماراتية" }, { "lemma": "الَّذِي", "text": "التي" }, { "lemma": "نَفَذ", "text": "تنفذ" }, { "lemma": "مَشْرُوع", "text": "المشروع" }, { "lemma": "أَنَّ", "text": "أنه" }, { "lemma": "تَمّ", "text": "سيتم" }, { "lemma": "اِسْتِخْدام", "text": "استخدام" }, { "lemma": "مَبْنِيّ", "text": "المبنى" }, { "lemma": "غَرَض", "text": "لأغراض" }, { "lemma": "مُتَعَدِّد", "text": "متعددة" }, { "lemma": "،", "text": "،" }, { "lemma": "ضَمّ", "text": "وسيضم" }, { "lemma": "مَبْنَى", "text": "المبنى" }, { "lemma": "مَحَلَّة", "text": "محلات" }, { "lemma": "تِجارِيّ", "text": "تجارية" }, { "lemma": "مَكان", "text": "وأماكن" }, { "lemma": "للترفيه", "text": "للترفيه" }, { "lemma": "فُنْدُق", "text": "وفندقاً" }, { "lemma": "وَحْدَة", "text": "ووحدات" }, { "lemma": "سَكَنِيّ", "text": "سكنية" }, { "lemma": "جَناح", "text": "وأجنحة" }, { "lemma": "خاصّ", "text": "خاصة" }, { "lemma": "مُؤَسَّسَة", "text": "للمؤسسات" }, { "lemma": "حَدِيقَة", "text": "وحديقة" }, { "lemma": "بانُورامِيّ", "text": "بانورامية" }, { "lemma": ".", "text": "." }, { "lemma": "تَمّ", "text": "وتم" }, { "lemma": "اِفْتِتاح", "text": "افتتاحه" }, { "lemma": "فِي", "text": "في" }, { "lemma": "4", "text": "4" }, { "lemma": "يَنايِر", "text": "يناير" }, { "lemma": "2010", "text": "2010" }, { "lemma": "مُكَوِّن", "text": "والمكون" }, { "lemma": "مِن", "text": "من" }, { "lemma": "124", "text": "124" }, { "lemma": "طابِق", "text": "طابقا" }, { "lemma": ".", "text": "." } ], "posTags": [ { "pos": "PV", "text": "بدأ" }, { "pos": "NOUN", "text": "العمل" }, { "pos": "PREP", "text": "في" }, { "pos": "NOUN_PROP", "text": "يناير" }, { "pos": "NUM", "text": "2004" }, { "pos": "REL_PRON", "text": "الذي" }, { "pos": "IV", "text": "يتم" }, { "pos": "NOUN", "text": "بناءه" }, { "pos": "PREP", "text": "في" }, { "pos": "NOUN", "text": "وسط" }, { "pos": "NOUN_PROP", "text": "دبي" }, { "pos": "PV", "text": "وبلغت" }, { "pos": "NOUN", "text": "تكلفته" }, { "pos": "ADJ", "text": "الإجمالية" }, { "pos": "NUM", "text": "1.5" }, { "pos": "NUM", "text": "مليار" }, { "pos": "NOUN", "text": "دولار" }, { "pos": "NOUN", "text": "أميركي" }, { "pos": "PUNC", "text": "[" }, { "pos": "NUM", "text": "5" }, { "pos": "PUNC", "text": "]" }, { "pos": "PUNC", "text": "؛" }, { "pos": "PV", "text": "وتم" }, { "pos": "NOUN", "text": "افتتاحه" }, { "pos": "PREP", "text": "في" }, { "pos": "NUM", "text": "4" }, { "pos": "NOUN_PROP", "text": "يناير" }, { "pos": "NUM", "text": "2010" }, { "pos": "NOUN_PROP", "text": "بحضور" }, { "pos": "NOUN_PROP", "text": "الشيخ" }, { "pos": "NOUN_PROP", "text": "محمد" }, { "pos": "NOUN_PROP", "text": "بن" }, { "pos": "NOUN_PROP", "text": "راشد" }, { "pos": "NOUN_PROP", "text": "آل" }, { "pos": "ADJ", "text": "مكتوم" }, { "pos": "NOUN", "text": "حاكم" }, { "pos": "ADJ", "text": "دبي" }, { "pos": "EOS", "text": "." }, { "pos": "IV", "text": "ويبلغ" }, { "pos": "NOUN", "text": "طول" }, { "pos": "NOUN", "text": "البرج" }, { "pos": "NUM", "text": "828" }, { "pos": "NOUN", "text": "مترا" }, { "pos": "IV", "text": "وستكون" }, { "pos": "NOUN", "text": "المساحة" }, { "pos": "ADJ", "text": "الإجمالية" }, { "pos": "NUM", "text": "4,000,000" }, { "pos": "NOUN", "text": "متر" }, { "pos": "ADJ", "text": "مربع" }, { "pos": "IV", "text": "وسيضم" }, { "pos": "NUM", "text": "37" }, { "pos": "NOUN", "text": "طابقاً" }, { "pos": "NOUN_PROP", "text": "كفندق" }, { "pos": "IV", "text": "ليضم" }, { "pos": "NUM", "text": "403" }, { "pos": "NOUN", "text": "جناح" }, { "pos": "ADJ", "text": "فندقي" }, { "pos": "PUNC", "text": "،" }, { "pos": "IV", "text": "وسيضم" }, { "pos": "NUM", "text": "57" }, { "pos": "NOUN", "text": "مصعد" }, { "pos": "ADJ", "text": "كهربائي" }, { "pos": "IV", "text": "وسيكون" }, { "pos": "ADJ", "text": "أسرعهم" }, { "pos": "NON_ARABIC", "text": "10م" }, { "pos": "PUNC", "text": "/" }, { "pos": "ADJ", "text": "ثانية" }, { "pos": "PUNC", "text": "،" }, { "pos": "NOUN", "text": "وللوصول" }, { "pos": "PREP", "text": "إلى" }, { "pos": "NUM", "text": "500" }, { "pos": "ABBREV", "text": "م" }, { "pos": "IV", "text": "تحتاج" }, { "pos": "PREP", "text": "إلى" }, { "pos": "NUM", "text": "55" }, { "pos": "ADJ", "text": "ثانية" }, { "pos": "IV", "text": "وتمتلكه" }, { "pos": "NOUN", "text": "شركة" }, { "pos": "NOUN", "text": "إعمار" }, { "pos": "ADJ", "text": "العقارية" }, { "pos": "IV", "text": "وتعد" }, { "pos": "ADJ", "text": "واحدة" }, { "pos": "PREP", "text": "من" }, { "pos": "ADJ", "text": "أكبر" }, { "pos": "NOUN", "text": "الشركات" }, { "pos": "ADJ", "text": "العقارية" }, { "pos": "PREP", "text": "في" }, { "pos": "NON_ARABIC", "text": "العالم.و" }, { "pos": "VERB_PART", "text": "قد" }, { "pos": "PV", "text": "تولت" }, { "pos": "NOUN", "text": "عملية" }, { "pos": "NOUN", "text": "البناء" }, { "pos": "NOUN", "text": "شركة" }, { "pos": "NON_ARABIC", "text": "Samsung" }, { "pos": "NON_ARABIC", "text": "C" }, { "pos": "PUNC", "text": "&" }, { "pos": "NON_ARABIC", "text": "T." }, { "pos": "DEM_PRON", "text": "وهذا" }, { "pos": "NOUN", "text": "البرج" }, { "pos": "REL_PRON", "text": "الذي" }, { "pos": "IV", "text": "يرتفع" }, { "pos": "NOUN", "text": "بسرعة" }, { "pos": "NOUN", "text": "طابق" }, { "pos": "NOUN", "text": "كل" }, { "pos": "NUM", "text": "ثلاث" }, { "pos": "NOUN", "text": "أيام" }, { "pos": "PUNC", "text": "(" }, { "pos": "NOUN", "text": "تقريبا" }, { "pos": "PUNC", "text": ")" }, { "pos": "PV", "text": "شكل" }, { "pos": "NOUN", "text": "البناء" }, { "pos": "ADJ", "text": "الرئيسي" }, { "pos": "PREP", "text": "في" }, { "pos": "NOUN", "text": "مشروع" }, { "pos": "ADJ", "text": "عمراني" }, { "pos": "ADJ", "text": "ضخم" }, { "pos": "NOUN", "text": "بقيمة" }, { "pos": "NUM", "text": "20" }, { "pos": "NUM", "text": "مليار" }, { "pos": "NOUN", "text": "دولار" }, { "pos": "IV_PASS", "text": "يتوقع" }, { "pos": "SUB_CONJ", "text": "أن" }, { "pos": "IV", "text": "يغير" }, { "pos": "NOUN", "text": "ملامح" }, { "pos": "NOUN", "text": "المدينة" }, { "pos": "EOS", "text": "." }, { "pos": "PV", "text": "وأوضح" }, { "pos": "NOUN_PROP", "text": "روبرت" }, { "pos": "NOUN_PROP", "text": "بوث" }, { "pos": "NOUN", "text": "المدير" }, { "pos": "ADJ", "text": "التنفيذي" }, { "pos": "PREP", "text": "في" }, { "pos": "NOUN", "text": "الشركة" }, { "pos": "ADJ", "text": "الإماراتية" }, { "pos": "REL_PRON", "text": "التي" }, { "pos": "IV", "text": "تنفذ" }, { "pos": "NOUN", "text": "المشروع" }, { "pos": "PRONOUN", "text": "أنه" }, { "pos": "IV", "text": "سيتم" }, { "pos": "NOUN", "text": "استخدام" }, { "pos": "ADJ", "text": "المبنى" }, { "pos": "NOUN", "text": "لأغراض" }, { "pos": "ADJ", "text": "متعددة" }, { "pos": "PUNC", "text": "،" }, { "pos": "IV", "text": "وسيضم" }, { "pos": "NOUN", "text": "المبنى" }, { "pos": "NOUN", "text": "محلات" }, { "pos": "ADJ", "text": "تجارية" }, { "pos": "NOUN", "text": "وأماكن" }, { "pos": "NOUN_PROP", "text": "للترفيه" }, { "pos": "NOUN", "text": "وفندقاً" }, { "pos": "NOUN", "text": "ووحدات" }, { "pos": "ADJ", "text": "سكنية" }, { "pos": "NOUN", "text": "وأجنحة" }, { "pos": "ADJ", "text": "خاصة" }, { "pos": "NOUN", "text": "للمؤسسات" }, { "pos": "NOUN", "text": "وحديقة" }, { "pos": "ADJ", "text": "بانورامية" }, { "pos": "EOS", "text": "." }, { "pos": "PV", "text": "وتم" }, { "pos": "NOUN", "text": "افتتاحه" }, { "pos": "PREP", "text": "في" }, { "pos": "NUM", "text": "4" }, { "pos": "NOUN_PROP", "text": "يناير" }, { "pos": "NUM", "text": "2010" }, { "pos": "NOUN", "text": "والمكون" }, { "pos": "PREP", "text": "من" }, { "pos": "NUM", "text": "124" }, { "pos": "NOUN", "text": "طابقا" }, { "pos": "EOS", "text": "." } ], "requestId": "4ef4e74b-e9c6-4eda-914b-d3f3a099cb18", "timers": { "rblJe": 40, "rliJe": 5 } } python-0.7.4/tests/mock-data/response/ara-sentence-morphology_complete.status 0000664 0000000 0000000 00000000003 12636317025 0027600 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/ara-sentence-sentiment.json 0000664 0000000 0000000 00000000242 12636317025 0025152 0 ustar 00root root 0000000 0000000 { "code": "unsupportedLanguage", "message": "Arabic is not supported by Rosette Sentiment Analyzer", "requestId": "71656965-fa52-4618-9ab2-35147bf888a2" } python-0.7.4/tests/mock-data/response/ara-sentence-sentiment.status 0000664 0000000 0000000 00000000003 12636317025 0025517 0 ustar 00root root 0000000 0000000 415 python-0.7.4/tests/mock-data/response/ara-url-categories.json 0000664 0000000 0000000 00000000233 12636317025 0024267 0 ustar 00root root 0000000 0000000 { "code": "unsupportedLanguage", "message": "Arabic is not supported by Rosette Categorizer", "requestId": "346d155f-757e-4da3-871c-66eaedeead83" } python-0.7.4/tests/mock-data/response/ara-url-categories.status 0000664 0000000 0000000 00000000003 12636317025 0024634 0 ustar 00root root 0000000 0000000 415 python-0.7.4/tests/mock-data/response/ara-url-entities.json 0000664 0000000 0000000 00000012221 12636317025 0023766 0 ustar 00root root 0000000 0000000 { "entities": [ { "confidence": 0.01820140414767795, "count": 9, "indocChainId": 2, "mention": "صعدة", "normalized": "صعدة", "type": "LOCATION" }, { "confidence": 0.013964295387268066, "count": 6, "indocChainId": 9, "mention": "الجزيرة", "normalized": "الجزيرة", "type": "ORGANIZATION" }, { "confidence": 0.02017374833424886, "count": 3, "indocChainId": 6, "mention": "قيادة التحالف", "normalized": "قيادة التحالف", "type": "ORGANIZATION" }, { "confidence": 0.01915818452835083, "count": 3, "indocChainId": 12, "mention": "قوات التحالف", "normalized": "قوات التحالف", "type": "ORGANIZATION" }, { "confidence": 0.01995900273323059, "count": 2, "indocChainId": 3, "mention": "شبوة", "normalized": "شبوه", "type": "LOCATION" }, { "confidence": 0.016160041093826294, "count": 2, "indocChainId": 8, "mention": "اليمن", "normalized": "اليمن", "type": "LOCATION" }, { "confidence": 0.012926608324050903, "count": 2, "indocChainId": 19, "mention": "طيران التحالف", "normalized": "طيران التحالف", "type": "ORGANIZATION" }, { "confidence": 0.02015608549118042, "count": 2, "indocChainId": 22, "mention": "السعودية", "normalized": "السعودية", "type": "LOCATION" }, { "confidence": 0.029470980167388916, "count": 2, "indocChainId": 29, "mention": "عسيري", "normalized": "عسيري", "type": "PERSON" }, { "confidence": 0.008821934461593628, "count": 2, "indocChainId": 29, "mention": "أحمد عسيري", "normalized": "أحمد عسيري", "type": "PERSON" }, { "confidence": 0.00783047080039978, "count": 2, "indocChainId": 35, "mention": "أمس", "normalized": "أمس", "type": "LOCATION" }, { "confidence": 0.011575579643249512, "count": 1, "indocChainId": 0, "mention": "مكة المكرمة", "normalized": "مكة المكرمة", "type": "LOCATION" }, { "confidence": 1.0, "count": 1, "indocChainId": 1, "mention": "عربي", "normalized": "عربي", "type": "NATIONALITY" }, { "confidence": 0.013428866863250732, "count": 1, "indocChainId": 4, "mention": "وعدن", "normalized": "عدن", "type": "LOCATION" }, { "confidence": 0.007166385650634766, "count": 1, "indocChainId": 5, "mention": "وتعز", "normalized": "تعز", "type": "LOCATION" }, { "confidence": 0.0020186901092529297, "count": 1, "indocChainId": 10, "mention": "مركز وبرج الاتصالات", "normalized": "مركز وبرج الاتصالات", "type": "ORGANIZATION" }, { "confidence": 0.006102204322814941, "count": 1, "indocChainId": 13, "mention": "جماعة الحوثي", "normalized": "جماعة الحوثي", "type": "ORGANIZATION" }, { "confidence": 0.013759136199951172, "count": 1, "indocChainId": 16, "mention": "ضحيان", "normalized": "ضحيان", "type": "LOCATION" }, { "confidence": 0.008876323699951172, "count": 1, "indocChainId": 17, "mention": "مذاب الصفراء", "normalized": "مذاب الصفراء", "type": "LOCATION" }, { "confidence": 0.007346391677856445, "count": 1, "indocChainId": 20, "mention": "رازح", "normalized": "رازح", "type": "LOCATION" }, { "confidence": 1.0, "count": 1, "indocChainId": 30, "mention": "اليمنيين", "normalized": "اليمنيين", "type": "NATIONALITY" }, { "confidence": 0.027194619178771973, "count": 1, "indocChainId": 33, "mention": "عتق", "normalized": "عتق", "type": "LOCATION" }, { "confidence": 0.038842201232910156, "count": 1, "indocChainId": 34, "mention": "عدن", "normalized": "عدن", "type": "LOCATION" }, { "confidence": 1.0, "count": 1, "indocChainId": 43, "mention": "اليمنية", "normalized": "اليمنية", "type": "NATIONALITY" }, { "confidence": 0.02414029836654663, "count": 1, "indocChainId": 44, "mention": "نجران", "normalized": "نجران", "type": "LOCATION" } ], "requestId": "82b6d07c-87c2-4f2d-afac-7dde3d420af6", "timers": { "rblJe": 53, "rexJe": 228, "rliJe": 5, "textExtractor": 49, "urlContentDownloader": 168 } } python-0.7.4/tests/mock-data/response/ara-url-entities.status 0000664 0000000 0000000 00000000003 12636317025 0024333 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/ara-url-entities_linked.json 0000664 0000000 0000000 00000006326 12636317025 0025325 0 ustar 00root root 0000000 0000000 { "entities": [ { "confidence": 0.4180757450854853, "entityId": "NEW-CLUSTER", "indocChainId": 0, "mention": "مكة المكرمة" }, { "confidence": 0.5178530081219924, "entityId": "NEW-CLUSTER", "indocChainId": 2, "mention": "صعدة" }, { "confidence": 0.1557383262524555, "entityId": "NEW-CLUSTER", "indocChainId": 3, "mention": "شبوه" }, { "confidence": 0.5016791841319038, "entityId": "NEW-CLUSTER", "indocChainId": 4, "mention": "عدن" }, { "confidence": 0.39822414545725726, "entityId": "Q466216", "indocChainId": 5, "mention": "تعز" }, { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 6, "mention": "قيادة التحالف" }, { "confidence": 0.6117159114135108, "entityId": "Q805", "indocChainId": 8, "mention": "اليمن" }, { "confidence": 0.5203183336875661, "entityId": "Q13477", "indocChainId": 9, "mention": "الجزيرة" }, { "confidence": 0.7308444368302152, "entityId": "NEW-CLUSTER", "indocChainId": 10, "mention": "مركز وبرج الاتصالات" }, { "confidence": 0.623258178252376, "entityId": "NEW-CLUSTER", "indocChainId": 12, "mention": "قوات التحالف" }, { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 13, "mention": "جماعة الحوثي" }, { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 16, "mention": "ضحيان" }, { "confidence": 0.09139991340373968, "entityId": "NEW-CLUSTER", "indocChainId": 17, "mention": "مذاب الصفراء" }, { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 19, "mention": "طيران التحالف" }, { "confidence": 0.3224708373992394, "entityId": "NEW-CLUSTER", "indocChainId": 20, "mention": "رازح" }, { "confidence": 0.5380180683126542, "entityId": "NEW-CLUSTER", "indocChainId": 22, "mention": "السعودية" }, { "confidence": 0.03212408218368355, "entityId": "Q4695759", "indocChainId": 29, "mention": "أحمد عسيري" }, { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 33, "mention": "عتق" }, { "confidence": 0.5045473626996668, "entityId": "Q131694", "indocChainId": 34, "mention": "عدن" }, { "confidence": 0.14623359675528494, "entityId": "NEW-CLUSTER", "indocChainId": 35, "mention": "أمس" }, { "confidence": 0.3954942431664408, "entityId": "NEW-CLUSTER", "indocChainId": 44, "mention": "نجران" } ], "requestId": "04d771f1-7664-4c39-9dd6-59b38a9bec01", "timers": { "rblJe": 50, "res": 546, "rexJe": 22, "rliJe": 5, "textExtractor": 51, "urlContentDownloader": 99 } } python-0.7.4/tests/mock-data/response/ara-url-entities_linked.status 0000664 0000000 0000000 00000000003 12636317025 0025661 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/ara-url-language.json 0000664 0000000 0000000 00000001110 12636317025 0023720 0 ustar 00root root 0000000 0000000 { "languageDetections": [ { "confidence": 0.0988872524018034, "language": "ara" }, { "confidence": 0.036170580117678375, "language": "fas" }, { "confidence": 0.029597728143163304, "language": "urd" }, { "confidence": 0.01726359977805403, "language": "kur" }, { "confidence": 0.015814756231594562, "language": "pus" } ], "requestId": "e6e44b35-db49-4e47-b51b-5fc92c204ca2", "timers": { "rliJe": 4, "textExtractor": 60, "urlContentDownloader": 159 } } python-0.7.4/tests/mock-data/response/ara-url-language.status 0000664 0000000 0000000 00000000003 12636317025 0024272 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/ara-url-morphology_complete.json 0000664 0000000 0000000 00000155350 12636317025 0026244 0 ustar 00root root 0000000 0000000 { "compounds": [], "hanReadings": [], "lemmas": [ { "lemma": "جُمْعَة", "text": "الجمعة" }, { "lemma": "8", "text": "8" }, { "lemma": "/", "text": "/" }, { "lemma": "5", "text": "5" }, { "lemma": "/", "text": "/" }, { "lemma": "2015", "text": "2015" }, { "lemma": "م", "text": "م" }, { "lemma": "(", "text": "(" }, { "lemma": "آخِر", "text": "آخر" }, { "lemma": "تَحْدِيث", "text": "تحديث" }, { "lemma": ")", "text": ")" }, { "lemma": "ساعَة", "text": "الساعة" }, { "lemma": "21:12", "text": "21:12" }, { "lemma": "(", "text": "(" }, { "lemma": "مَكَّة", "text": "مكة" }, { "lemma": "مُكَرَّم", "text": "المكرمة" }, { "lemma": ")", "text": ")" }, { "lemma": "خَبَر", "text": "الأخبار" }, { "lemma": "عَرَبِيّ", "text": "عربي" }, { "lemma": "غارَة", "text": "غارات" }, { "lemma": "تَحالُف", "text": "للتحالف" }, { "lemma": "عَلَى", "text": "على" }, { "lemma": "صَعْدَة", "text": "صعدة" }, { "lemma": "بَعْدَ", "text": "بعد" }, { "lemma": "إِعْلان", "text": "إعلانها" }, { "lemma": "مِنْطَقَة", "text": "منطقة" }, { "lemma": "اِسْتِهْداف", "text": "استهداف" }, { "lemma": "طائِرَة", "text": "طائرات" }, { "lemma": "تَحالُف", "text": "التحالف" }, { "lemma": "هاجَم", "text": "هاجمت" }, { "lemma": "مَوْقِع", "text": "مواقع" }, { "lemma": "عَسْكَرِيّ", "text": "عسكرية" }, { "lemma": "للحوثيين", "text": "للحوثيين" }, { "lemma": "شارَك", "text": "شارك" }, { "lemma": "قَتِيل", "text": "قتلى" }, { "lemma": "مِن", "text": "من" }, { "lemma": "الحوثيين", "text": "الحوثيين" }, { "lemma": "مُقاوِم", "text": "والمقاومة" }, { "lemma": "فِي", "text": "في" }, { "lemma": "مَعْرَكَة", "text": "معارك" }, { "lemma": "شبوة", "text": "شبوة" }, { "lemma": "عَدَن", "text": "وعدن" }, { "lemma": "عَزّ", "text": "وتعز" }, { "lemma": "دَخْل", "text": "دخل" }, { "lemma": "قَرار", "text": "قرار" }, { "lemma": "قِيادَة", "text": "قيادة" }, { "lemma": "تَحالُف", "text": "التحالف" }, { "lemma": "تَحْوِيل", "text": "تحويل" }, { "lemma": "مُدِين", "text": "مدينة" }, { "lemma": "صَعْدَة", "text": "صعدة" }, { "lemma": "(", "text": "(" }, { "lemma": "شَمال", "text": "شمال" }, { "lemma": "يَمَن", "text": "اليمن" }, { "lemma": ")", "text": ")" }, { "lemma": "كامِل", "text": "بكاملها" }, { "lemma": "إِلَى", "text": "إلى" }, { "lemma": "مِنْطَقَة", "text": "منطقة" }, { "lemma": "اِسْتِهْداف", "text": "استهداف" }, { "lemma": "عَسْكَرِيّ", "text": "عسكري" }, { "lemma": "حَيِّز", "text": "حيز" }, { "lemma": "تَنْفِيذ", "text": "التنفيذ" }, { "lemma": "،", "text": "،" }, { "lemma": "أَظْهَر", "text": "وأظهرت" }, { "lemma": "صُورَة", "text": "صورٌ" }, { "lemma": "خاصّ", "text": "خاصة" }, { "lemma": "حَصَل", "text": "حصلت" }, { "lemma": "جَزِيرَة", "text": "الجزيرة" }, { "lemma": "عَلَى", "text": "عليها" }, { "lemma": "تَدْمِير", "text": "تدمير" }, { "lemma": "مَرْكَز", "text": "مركز" }, { "lemma": "بُرْج", "text": "وبرج" }, { "lemma": "اِتِّصال", "text": "الاتصالات" }, { "lemma": "فِي", "text": "في" }, { "lemma": "صَعْدَة", "text": "صعدة" }, { "lemma": "بَعْدَ", "text": "بعد" }, { "lemma": "قَصْف", "text": "قصفه" }, { "lemma": "مِن", "text": "من" }, { "lemma": "قُوَّة", "text": "قوات" }, { "lemma": "تَحالُف", "text": "التحالف" }, { "lemma": "،", "text": "،" }, { "lemma": "كان", "text": "كان" }, { "lemma": "اِسْتَخْدَم", "text": "تستخدمه" }, { "lemma": "جَماعَة", "text": "جماعة" }, { "lemma": "الحوثي", "text": "الحوثي" }, { "lemma": "مَقَرّ", "text": "مقرا" }, { "lemma": "عَسْكَرِيّ", "text": "عسكريا" }, { "lemma": ".", "text": "." }, { "lemma": "قَد", "text": "وقد" }, { "lemma": "أَفاد", "text": "أفاد" }, { "lemma": "مُراسِل", "text": "مراسل" }, { "lemma": "جَزِيرَة", "text": "الجزيرة" }, { "lemma": "أَن", "text": "بأن" }, { "lemma": "قُوَّة", "text": "قوات" }, { "lemma": "تَحالُف", "text": "التحالف" }, { "lemma": "دَمَر", "text": "دمرت" }, { "lemma": "مَقَرّ", "text": "مقرين" }, { "lemma": "قِياد", "text": "لقيادة" }, { "lemma": "الحوثيين", "text": "الحوثيين" }, { "lemma": "،", "text": "،" }, { "lemma": "فِي", "text": "في" }, { "lemma": "مِنْطَقَة", "text": "منطقتي" }, { "lemma": "ضحيان", "text": "ضحيان" }, { "lemma": "وَ", "text": "و" }, { "lemma": "\"", "text": "\"" }, { "lemma": "مذاب", "text": "مذاب" }, { "lemma": "أَصْفَر", "text": "الصفراء" }, { "lemma": "\"", "text": "\"" }, { "lemma": "(", "text": "(" }, { "lemma": "شَمال", "text": "شمال" }, { "lemma": "مُدِين", "text": "مدين" }, { "lemma": "صَعْدَة", "text": "صعدة" }, { "lemma": ")", "text": ")" }, { "lemma": ".", "text": "." }, { "lemma": "أَشار", "text": "وأشار" }, { "lemma": "إِلَى", "text": "إلى" }, { "lemma": "أَن", "text": "أن" }, { "lemma": "طَيَران", "text": "طيران" }, { "lemma": "تَحالُف", "text": "التحالف" }, { "lemma": "شَنّ", "text": "شن" }, { "lemma": "قَصْف", "text": "قصفا" }, { "lemma": "هُوَ", "text": "هو" }, { "lemma": "أَعْنَف", "text": "الأعنف" }, { "lemma": "فِي", "text": "في" }, { "lemma": "مُدِيرِيَّة", "text": "مديريات" }, { "lemma": "رازِح", "text": "رازح" }, { "lemma": "شَدا", "text": "وشدا" }, { "lemma": "ظاهِر", "text": "والظاهر" }, { "lemma": "جَبَل", "text": "وجبل" }, { "lemma": "ذُو", "text": "ذي" }, { "lemma": "مَرّ", "text": "نمر" }, { "lemma": "مُحافِظ", "text": "بمحافظة" }, { "lemma": "صَعْدَة", "text": "صعدة" }, { "lemma": "عَلَى", "text": "على" }, { "lemma": "حَدّ", "text": "الحدود" }, { "lemma": "مَعَ", "text": "مع" }, { "lemma": "سَعُودِيَّة", "text": "السعودية" }, { "lemma": ".", "text": "." }, { "lemma": "مَنْشُور", "text": "منشورات" }, { "lemma": "كان", "text": "وكانت" }, { "lemma": "قِيادَة", "text": "قيادة" }, { "lemma": "تَحالُف", "text": "التحالف" }, { "lemma": "الَّذِي", "text": "الذي" }, { "lemma": "قاد", "text": "تقوده" }, { "lemma": "سَعُودِيَّة", "text": "السعودية" }, { "lemma": "دَعّ", "text": "دعت" }, { "lemma": "عَبْرَ", "text": "عبر" }, { "lemma": "مَنْشُور", "text": "منشورات" }, { "lemma": "أَسْقَط", "text": "أسقطتها" }, { "lemma": "طائِرَة", "text": "طائراتها" }, { "lemma": "مَدَنِيّ", "text": "المدنيين" }, { "lemma": "إِلَى", "text": "إلى" }, { "lemma": "إِسْراع", "text": "الإسراع" }, { "lemma": "مُغادَرَة", "text": "بمغادرة" }, { "lemma": "صَعْدَة", "text": "صعدة" }, { "lemma": "،", "text": "،" }, { "lemma": "قال", "text": "وقالت" }, { "lemma": "إِن", "text": "إن" }, { "lemma": "طَرِيق", "text": "الطرق" }, { "lemma": "رَئِيسِيّ", "text": "الرئيسية" }, { "lemma": "فِي", "text": "في" }, { "lemma": "صَعْدَة", "text": "صعدة" }, { "lemma": "أَتاح", "text": "ستتاح" }, { "lemma": "مُغادَرَة", "text": "لمغادرة" }, { "lemma": "مَدَنِيّ", "text": "المدنيين" }, { "lemma": "حَتَّى", "text": "حتى" }, { "lemma": "غُرُوب", "text": "غروب" }, { "lemma": "شَمْس", "text": "شمس" }, { "lemma": "يَوْم", "text": "اليوم" }, { "lemma": ".", "text": "." }, { "lemma": "مَوْقِع", "text": "مواقع" }, { "lemma": "فِي", "text": "في" }, { "lemma": "صَعْدَة", "text": "صعدة" }, { "lemma": "اِسْتَهْدَف", "text": "استهدفها" }, { "lemma": "طَيَران", "text": "طيران" }, { "lemma": "تَحالُف", "text": "التحالف" }, { "lemma": "(", "text": "(" }, { "lemma": "ناشِط", "text": "ناشطون" }, { "lemma": ")", "text": ")" }, { "lemma": "نَقَل", "text": "ونقلت" }, { "lemma": "قَناة", "text": "القناة" }, { "lemma": "إِخْبارِيّ", "text": "الإخبارية" }, { "lemma": "سَعُودِيّ", "text": "السعودية" }, { "lemma": "عَن", "text": "عن" }, { "lemma": "مُتَحَدِّث", "text": "المتحدث" }, { "lemma": "اِسْم", "text": "باسم" }, { "lemma": "تَحالُف", "text": "تحالف" }, { "lemma": "عَمَلِيَّة", "text": "عملية" }, { "lemma": "إِعادَة", "text": "إعادة" }, { "lemma": "أَمَل", "text": "الأمل" }, { "lemma": "عَمِيد", "text": "العميد" }, { "lemma": "رُكْن", "text": "الركن" }, { "lemma": "أَحْمَد", "text": "أحمد" }, { "lemma": "عَسِيرِيّ", "text": "عسيري" }, { "lemma": "قَوْل", "text": "قوله" }, { "lemma": "\"", "text": "\"" }, { "lemma": "وَجَّه", "text": "وجهنا" }, { "lemma": "رِسالَة", "text": "رسالة" }, { "lemma": "إِلَى", "text": "إلى" }, { "lemma": "شَقِيق", "text": "أشقائنا" }, { "lemma": "مُواطِن", "text": "المواطنين" }, { "lemma": "يَمَنِيّ", "text": "اليمنيين" }, { "lemma": "مِن", "text": "من" }, { "lemma": "خِلالَ", "text": "خلال" }, { "lemma": "مُخْتَلَف", "text": "مختلف" }, { "lemma": "وَسِيلَة", "text": "الوسائل" }, { "lemma": "إِعْلامِيّ", "text": "الإعلامية" }, { "lemma": "أَن", "text": "بأن" }, { "lemma": "اِبْتَعَد", "text": "يبتعدوا" }, { "lemma": "عَن", "text": "عن" }, { "lemma": "مِيلِيشِيا", "text": "المليشيات" }, { "lemma": "الحوثية", "text": "الحوثية" }, { "lemma": "مُعَسْكَر", "text": "والمعسكرات" }, { "lemma": "عَسْكَرِيّ", "text": "العسكرية" }, { "lemma": "الَّذِي", "text": "التي" }, { "lemma": "تَحَصَّن", "text": "تتحصن" }, { "lemma": "فِي", "text": "فيها" }, { "lemma": "حِفاظ", "text": "حفاظا" }, { "lemma": "عَلَى", "text": "على" }, { "lemma": "سَلامَة", "text": "سلامتهم" }, { "lemma": "\"", "text": "\"" }, { "lemma": ".", "text": "." }, { "lemma": "فِي", "text": "وفي" }, { "lemma": "مُحافِظ", "text": "محافظة" }, { "lemma": "شبوة", "text": "شبوة" }, { "lemma": "(", "text": "(" }, { "lemma": "جَنُوب", "text": "جنوب" }, { "lemma": "شَرْق", "text": "شرق" }, { "lemma": "يَمَن", "text": "اليمن" }, { "lemma": ")", "text": ")" }, { "lemma": "،", "text": "،" }, { "lemma": "قال", "text": "قالت" }, { "lemma": "مَصْدَر", "text": "مصادر" }, { "lemma": "مَحَلِّيّ", "text": "محلية" }, { "lemma": "إِن", "text": "إن" }, { "lemma": "طائِرَة", "text": "طائرات" }, { "lemma": "تَحالُف", "text": "التحالف" }, { "lemma": "شَنّ", "text": "شنت" }, { "lemma": "خَمْس", "text": "خمس" }, { "lemma": "غارَة", "text": "غارات" }, { "lemma": "جَوِّيّ", "text": "جوية" }, { "lemma": "عَلَى", "text": "على" }, { "lemma": "أَقَلّ", "text": "الأقل" }, { "lemma": "فِي", "text": "في" }, { "lemma": "مُحِيط", "text": "محيط" }, { "lemma": "مَطار", "text": "مطار" }, { "lemma": "مُدِين", "text": "مدينة" }, { "lemma": "عِتْق", "text": "عتق" }, { "lemma": "فِي", "text": "وفي" }, { "lemma": "مُدِين", "text": "المدينة" }, { "lemma": "نَفْس", "text": "نفسها" }, { "lemma": ".", "text": "." }, { "lemma": "شَنّ", "text": "وشنت" }, { "lemma": "طائِرَة", "text": "الطائرات" }, { "lemma": "غارَة", "text": "غارات" }, { "lemma": "أَيْض", "text": "أيضا" }, { "lemma": "فِي", "text": "في" }, { "lemma": "مُدِين", "text": "مدينة" }, { "lemma": "عَدَن", "text": "عدن" }, { "lemma": "فِي", "text": "في" }, { "lemma": "وَقْت", "text": "وقت" }, { "lemma": "مُتَأَخِّر", "text": "متأخر" }, { "lemma": "لَيْلَة", "text": "ليلة" }, { "lemma": "أَمْسِ", "text": "أمس" }, { "lemma": "خَمِيس", "text": "الخميس" }, { "lemma": "،", "text": "،" }, { "lemma": "فِي", "text": "وفي" }, { "lemma": "وَقْت", "text": "وقت" }, { "lemma": "مُبَكِّر", "text": "مبكر" }, { "lemma": "مِن", "text": "من" }, { "lemma": "صَباح", "text": "صباح" }, { "lemma": "يَوْم", "text": "اليوم" }, { "lemma": "جُمْعَة", "text": "الجمعة" }, { "lemma": ".", "text": "." }, { "lemma": "أَتَى", "text": "ويأتي" }, { "lemma": "هٰذا", "text": "هذا" }, { "lemma": "تَصْعِيد", "text": "التصعيد" }, { "lemma": "بَعْدَ", "text": "بعد" }, { "lemma": "إِعْلان", "text": "إعلان" }, { "lemma": "عَمِيد", "text": "العميد" }, { "lemma": "عَسِيرِيّ", "text": "عسيري" }, { "lemma": "أَن", "text": "أن" }, { "lemma": "مُعادَلَة", "text": "المعادلة" }, { "lemma": "اِخْتَلَف", "text": "اختلفت" }, { "lemma": "،", "text": "،" }, { "lemma": "أَن", "text": "وأن" }, { "lemma": "قُوَّة", "text": "قوات" }, { "lemma": "تَحالُف", "text": "التحالف" }, { "lemma": "قُوَّة", "text": "والقوات" }, { "lemma": "سَعُودِيّ", "text": "السعودية" }, { "lemma": "مُسَلَّح", "text": "المسلحة" }, { "lemma": "رَدّ", "text": "سترد" }, { "lemma": "عَلَى", "text": "على" }, { "lemma": "اِعْتِداء", "text": "اعتداءات" }, { "lemma": "الحوثيين", "text": "الحوثيين" }, { "lemma": "قُوَّة", "text": "بقوة" }, { "lemma": "،", "text": "،" }, { "lemma": "شَكْل", "text": "وبشكل" }, { "lemma": "غَيْر", "text": "غير" }, { "lemma": "مَحْدُود", "text": "محدود" }, { "lemma": "زَمان", "text": "بزمان" }, { "lemma": "أَو", "text": "أو" }, { "lemma": "مَكان", "text": "مكان" }, { "lemma": ".", "text": "." }, { "lemma": "أَكَّد", "text": "وأكد" }, { "lemma": "عَسِيرِيّ", "text": "عسيري" }, { "lemma": "أَن", "text": "أن" }, { "lemma": "قِيادَة", "text": "قيادة" }, { "lemma": "تَحالُف", "text": "التحالف" }, { "lemma": "سَوْفَ", "text": "سوف" }, { "lemma": "أَغار", "text": "تغير" }, { "lemma": "رَدّ", "text": "ردها" }, { "lemma": "،", "text": "،" }, { "lemma": "سَوْفَ", "text": "وسوف" }, { "lemma": "اِسْتَهْدَف", "text": "تستهدف" }, { "lemma": "مِيلِيشِيا", "text": "المليشيات" }, { "lemma": "قائِد", "text": "وقادتها" }, { "lemma": "،", "text": "،" }, { "lemma": "أَضاف", "text": "وأضاف" }, { "lemma": "أَن", "text": "أن" }, { "lemma": "رَدّ", "text": "الرد" }, { "lemma": "اِسْتَهْدَف", "text": "سيستهدف" }, { "lemma": "صَعْدَة", "text": "صعدة" }, { "lemma": "مِران", "text": "ومرّان" }, { "lemma": "مِنْطَقَة", "text": "ومناطق" }, { "lemma": "أُخْرَى", "text": "أخرى" }, { "lemma": "،", "text": "،" }, { "lemma": "لَن", "text": "ولن" }, { "lemma": "اِقْتَصَر", "text": "يقتصر" }, { "lemma": "عَلَى", "text": "على" }, { "lemma": "مِنْطَقَة", "text": "المناطق" }, { "lemma": "حُدُودِيّ", "text": "الحدودية" }, { "lemma": ".", "text": "." }, { "lemma": "كان", "text": "وكان" }, { "lemma": "مُراسِل", "text": "مراسل" }, { "lemma": "جَزِيرَة", "text": "الجزيرة" }, { "lemma": "أَفاد", "text": "أفاد" }, { "lemma": "تَجَدُّد", "text": "بتجدد" }, { "lemma": "سُقُوط", "text": "سقوط" }, { "lemma": "قَذِيفَة", "text": "القذائف" }, { "lemma": "مَساء", "text": "مساء" }, { "lemma": "أَمْسِ", "text": "أمس" }, { "lemma": "خَمِيس", "text": "الخميس" }, { "lemma": "قُرْبَ", "text": "قرب" }, { "lemma": "حَدّ", "text": "الحدود" }, { "lemma": "يَمَنِيّ", "text": "اليمنية" }, { "lemma": "بَعْدَ", "text": "بعد" }, { "lemma": "يَوْم", "text": "يوم" }, { "lemma": "مِن", "text": "من" }, { "lemma": "مَقْتَل", "text": "مقتل" }, { "lemma": "خَمْس", "text": "خمسة" }, { "lemma": "-", "text": "-" }, { "lemma": "بَيْنَ", "text": "بينهم" }, { "lemma": "شُرْطِيّ", "text": "شرطي" }, { "lemma": "-", "text": "-" }, { "lemma": "إِصابَة", "text": "وإصابة" }, { "lemma": "11", "text": "11" }, { "lemma": "مَدَنِيّ", "text": "مدنيا" }, { "lemma": "جَرّاءَ", "text": "جراء" }, { "lemma": "قَصْف", "text": "قصف" }, { "lemma": "بقذائف", "text": "بقذائف" }, { "lemma": "هاوُن", "text": "الهاون" }, { "lemma": "اِسْتَهْدَف", "text": "استهدف" }, { "lemma": "مِنْطَقَة", "text": "مناطق" }, { "lemma": "عِدَّة", "text": "عدة" }, { "lemma": "فِي", "text": "في" }, { "lemma": "نَجْران", "text": "نجران" }, { "lemma": ".", "text": "." }, { "lemma": "مُصَدِّر", "text": "المصدر" }, { "lemma": ":", "text": ":" }, { "lemma": "وِكالَة", "text": "وكالات" }, { "lemma": ",", "text": "," }, { "lemma": "جَزِيرَة", "text": "الجزيرة" }, { "lemma": "مُقَطَّع", "text": "مقطع" }, { "lemma": "مِن", "text": "من" }, { "lemma": "لِقاء", "text": "لقاء" }, { "lemma": "يَوْم", "text": "اليوم" }, { "lemma": "مَعَ", "text": "مع" }, { "lemma": "عَمِيد", "text": "العميد" }, { "lemma": "رُكْن", "text": "الركن" }, { "lemma": "أَحْمَد", "text": "أحمد" }, { "lemma": "عَسِيرِيّ", "text": "عسيري" }, { "lemma": "شارَك", "text": "شارك" }, { "lemma": "رَأْي", "text": "برأيك" }, { "lemma": "تَعْلِيق", "text": "التعليقات" }, { "lemma": "مَنْشُور", "text": "المنشورة" }, { "lemma": "لا", "text": "لا" }, { "lemma": "عَبَر", "text": "تعبر" }, { "lemma": "عَن", "text": "عن" }, { "lemma": "رَأْي", "text": "رأي" }, { "lemma": "جَزِيرَة", "text": "الجزيرة" }, { "lemma": "إِنَّما", "text": "وإنما" }, { "lemma": "عَبَر", "text": "تعبر" }, { "lemma": "عَن", "text": "عن" }, { "lemma": "رَأْي", "text": "رأي" }, { "lemma": "صاحِب", "text": "أصحابها" }, { "lemma": "انشر", "text": "انشر" }, { "lemma": "تعليقك", "text": "تعليقك" }, { "lemma": "عَن", "text": "عن" }, { "lemma": "طَرِيق", "text": "طريق" }, { "lemma": ":", "text": ":" }, { "lemma": "تَعْلِيق", "text": "التعليق" }, { "lemma": "أَحْدَث", "text": "الأحدث" }, { "lemma": "إِظْهار", "text": "إظهار" }, { "lemma": "0", "text": "0" }, { "lemma": "/", "text": "/" }, { "lemma": "0", "text": "0" }, { "lemma": "تَعْلِيق", "text": "تعليقات" }, { "lemma": "أَظْهَر", "text": "أظهر" }, { "lemma": "تَعْلِيق", "text": "تعليقات" }, { "lemma": "أَكْثَر", "text": "أكثر" }, { "lemma": "أَقْرَأ", "text": "اقرأ" }, { "lemma": "أَيْض", "text": "أيضاً" }, { "lemma": "جَمِيع", "text": "جميع" }, { "lemma": "حَقّ", "text": "الحقوق" }, { "lemma": "مَحْفُوظ", "text": "محفوظة" }, { "lemma": "©", "text": "©" }, { "lemma": "2015", "text": "2015" }, { "lemma": "جَزِيرَة", "text": "الجزيرة" }, { "lemma": "|", "text": "|" }, { "lemma": ":", "text": ":" }, { "lemma": "Powerd", "text": "Powerd" }, { "lemma": "by", "text": "by" } ], "posTags": [ { "pos": "NOUN", "text": "الجمعة" }, { "pos": "NUM", "text": "8" }, { "pos": "PUNC", "text": "/" }, { "pos": "NUM", "text": "5" }, { "pos": "PUNC", "text": "/" }, { "pos": "NUM", "text": "2015" }, { "pos": "ABBREV", "text": "م" }, { "pos": "PUNC", "text": "(" }, { "pos": "ADJ", "text": "آخر" }, { "pos": "NOUN", "text": "تحديث" }, { "pos": "PUNC", "text": ")" }, { "pos": "NOUN", "text": "الساعة" }, { "pos": "NON_ARABIC", "text": "21:12" }, { "pos": "PUNC", "text": "(" }, { "pos": "NOUN_PROP", "text": "مكة" }, { "pos": "ADJ", "text": "المكرمة" }, { "pos": "PUNC", "text": ")" }, { "pos": "NOUN", "text": "الأخبار" }, { "pos": "ADJ", "text": "عربي" }, { "pos": "NOUN", "text": "غارات" }, { "pos": "NOUN", "text": "للتحالف" }, { "pos": "PREP", "text": "على" }, { "pos": "NOUN", "text": "صعدة" }, { "pos": "PREP", "text": "بعد" }, { "pos": "NOUN", "text": "إعلانها" }, { "pos": "NOUN", "text": "منطقة" }, { "pos": "NOUN", "text": "استهداف" }, { "pos": "NOUN", "text": "طائرات" }, { "pos": "NOUN", "text": "التحالف" }, { "pos": "PV", "text": "هاجمت" }, { "pos": "NOUN", "text": "مواقع" }, { "pos": "ADJ", "text": "عسكرية" }, { "pos": "NOUN_PROP", "text": "للحوثيين" }, { "pos": "PV", "text": "شارك" }, { "pos": "NOUN", "text": "قتلى" }, { "pos": "PREP", "text": "من" }, { "pos": "NOUN_PROP", "text": "الحوثيين" }, { "pos": "NOUN", "text": "والمقاومة" }, { "pos": "PREP", "text": "في" }, { "pos": "NOUN", "text": "معارك" }, { "pos": "NOUN_PROP", "text": "شبوة" }, { "pos": "NOUN_PROP", "text": "وعدن" }, { "pos": "IV", "text": "وتعز" }, { "pos": "NOUN", "text": "دخل" }, { "pos": "NOUN", "text": "قرار" }, { "pos": "NOUN", "text": "قيادة" }, { "pos": "NOUN", "text": "التحالف" }, { "pos": "NOUN", "text": "تحويل" }, { "pos": "NOUN", "text": "مدينة" }, { "pos": "NOUN_PROP", "text": "صعدة" }, { "pos": "PUNC", "text": "(" }, { "pos": "NOUN", "text": "شمال" }, { "pos": "NOUN_PROP", "text": "اليمن" }, { "pos": "PUNC", "text": ")" }, { "pos": "NOUN", "text": "بكاملها" }, { "pos": "PREP", "text": "إلى" }, { "pos": "NOUN", "text": "منطقة" }, { "pos": "NOUN", "text": "استهداف" }, { "pos": "ADJ", "text": "عسكري" }, { "pos": "NOUN", "text": "حيز" }, { "pos": "NOUN", "text": "التنفيذ" }, { "pos": "PUNC", "text": "،" }, { "pos": "PV", "text": "وأظهرت" }, { "pos": "NOUN", "text": "صورٌ" }, { "pos": "ADJ", "text": "خاصة" }, { "pos": "PV", "text": "حصلت" }, { "pos": "NOUN", "text": "الجزيرة" }, { "pos": "PRONOUN", "text": "عليها" }, { "pos": "NOUN", "text": "تدمير" }, { "pos": "NOUN", "text": "مركز" }, { "pos": "NOUN", "text": "وبرج" }, { "pos": "NOUN", "text": "الاتصالات" }, { "pos": "PREP", "text": "في" }, { "pos": "NOUN", "text": "صعدة" }, { "pos": "PREP", "text": "بعد" }, { "pos": "NOUN", "text": "قصفه" }, { "pos": "PREP", "text": "من" }, { "pos": "NOUN", "text": "قوات" }, { "pos": "NOUN", "text": "التحالف" }, { "pos": "PUNC", "text": "،" }, { "pos": "PV", "text": "كان" }, { "pos": "IV", "text": "تستخدمه" }, { "pos": "NOUN", "text": "جماعة" }, { "pos": "NOUN_PROP", "text": "الحوثي" }, { "pos": "NOUN", "text": "مقرا" }, { "pos": "ADJ", "text": "عسكريا" }, { "pos": "EOS", "text": "." }, { "pos": "VERB_PART", "text": "وقد" }, { "pos": "PV", "text": "أفاد" }, { "pos": "NOUN", "text": "مراسل" }, { "pos": "NOUN", "text": "الجزيرة" }, { "pos": "SUB_CONJ", "text": "بأن" }, { "pos": "NOUN", "text": "قوات" }, { "pos": "NOUN", "text": "التحالف" }, { "pos": "PV", "text": "دمرت" }, { "pos": "NOUN", "text": "مقرين" }, { "pos": "NOUN", "text": "لقيادة" }, { "pos": "NOUN_PROP", "text": "الحوثيين" }, { "pos": "PUNC", "text": "،" }, { "pos": "PREP", "text": "في" }, { "pos": "NOUN", "text": "منطقتي" }, { "pos": "NOUN_PROP", "text": "ضحيان" }, { "pos": "CONJ", "text": "و" }, { "pos": "PUNC", "text": "\"" }, { "pos": "NOUN_PROP", "text": "مذاب" }, { "pos": "ADJ", "text": "الصفراء" }, { "pos": "PUNC", "text": "\"" }, { "pos": "PUNC", "text": "(" }, { "pos": "NOUN", "text": "شمال" }, { "pos": "NOUN", "text": "مدين" }, { "pos": "NOUN_PROP", "text": "صعدة" }, { "pos": "PUNC", "text": ")" }, { "pos": "EOS", "text": "." }, { "pos": "PV", "text": "وأشار" }, { "pos": "PREP", "text": "إلى" }, { "pos": "SUB_CONJ", "text": "أن" }, { "pos": "NOUN", "text": "طيران" }, { "pos": "NOUN", "text": "التحالف" }, { "pos": "PV", "text": "شن" }, { "pos": "NOUN", "text": "قصفا" }, { "pos": "PRONOUN", "text": "هو" }, { "pos": "ADJ", "text": "الأعنف" }, { "pos": "PREP", "text": "في" }, { "pos": "NOUN", "text": "مديريات" }, { "pos": "ADJ", "text": "رازح" }, { "pos": "PV", "text": "وشدا" }, { "pos": "NOUN", "text": "والظاهر" }, { "pos": "PV", "text": "وجبل" }, { "pos": "DEM_PRON", "text": "ذي" }, { "pos": "IV", "text": "نمر" }, { "pos": "NOUN", "text": "بمحافظة" }, { "pos": "NOUN", "text": "صعدة" }, { "pos": "PREP", "text": "على" }, { "pos": "NOUN", "text": "الحدود" }, { "pos": "PREP", "text": "مع" }, { "pos": "NOUN_PROP", "text": "السعودية" }, { "pos": "EOS", "text": "." }, { "pos": "NOUN", "text": "منشورات" }, { "pos": "PV", "text": "وكانت" }, { "pos": "NOUN", "text": "قيادة" }, { "pos": "NOUN", "text": "التحالف" }, { "pos": "REL_PRON", "text": "الذي" }, { "pos": "IV", "text": "تقوده" }, { "pos": "NOUN_PROP", "text": "السعودية" }, { "pos": "PV", "text": "دعت" }, { "pos": "PREP", "text": "عبر" }, { "pos": "NOUN", "text": "منشورات" }, { "pos": "PV", "text": "أسقطتها" }, { "pos": "NOUN", "text": "طائراتها" }, { "pos": "ADJ", "text": "المدنيين" }, { "pos": "PREP", "text": "إلى" }, { "pos": "NOUN", "text": "الإسراع" }, { "pos": "NOUN", "text": "بمغادرة" }, { "pos": "NOUN_PROP", "text": "صعدة" }, { "pos": "PUNC", "text": "،" }, { "pos": "PV", "text": "وقالت" }, { "pos": "SUB_CONJ", "text": "إن" }, { "pos": "NOUN", "text": "الطرق" }, { "pos": "ADJ", "text": "الرئيسية" }, { "pos": "PREP", "text": "في" }, { "pos": "NOUN_PROP", "text": "صعدة" }, { "pos": "IV_PASS", "text": "ستتاح" }, { "pos": "NOUN", "text": "لمغادرة" }, { "pos": "NOUN", "text": "المدنيين" }, { "pos": "PREP", "text": "حتى" }, { "pos": "NOUN", "text": "غروب" }, { "pos": "NOUN", "text": "شمس" }, { "pos": "NOUN", "text": "اليوم" }, { "pos": "EOS", "text": "." }, { "pos": "NOUN", "text": "مواقع" }, { "pos": "PREP", "text": "في" }, { "pos": "NOUN", "text": "صعدة" }, { "pos": "PV", "text": "استهدفها" }, { "pos": "NOUN", "text": "طيران" }, { "pos": "NOUN", "text": "التحالف" }, { "pos": "PUNC", "text": "(" }, { "pos": "NOUN", "text": "ناشطون" }, { "pos": "PUNC", "text": ")" }, { "pos": "PV", "text": "ونقلت" }, { "pos": "NOUN", "text": "القناة" }, { "pos": "ADJ", "text": "الإخبارية" }, { "pos": "ADJ", "text": "السعودية" }, { "pos": "PREP", "text": "عن" }, { "pos": "NOUN", "text": "المتحدث" }, { "pos": "NOUN", "text": "باسم" }, { "pos": "NOUN", "text": "تحالف" }, { "pos": "NOUN", "text": "عملية" }, { "pos": "NOUN", "text": "إعادة" }, { "pos": "NOUN", "text": "الأمل" }, { "pos": "NOUN", "text": "العميد" }, { "pos": "NOUN", "text": "الركن" }, { "pos": "ADJ", "text": "أحمد" }, { "pos": "NOUN", "text": "عسيري" }, { "pos": "NOUN", "text": "قوله" }, { "pos": "PUNC", "text": "\"" }, { "pos": "PV", "text": "وجهنا" }, { "pos": "NOUN", "text": "رسالة" }, { "pos": "PREP", "text": "إلى" }, { "pos": "NOUN", "text": "أشقائنا" }, { "pos": "NOUN", "text": "المواطنين" }, { "pos": "ADJ", "text": "اليمنيين" }, { "pos": "PREP", "text": "من" }, { "pos": "NOUN", "text": "خلال" }, { "pos": "ADJ", "text": "مختلف" }, { "pos": "NOUN", "text": "الوسائل" }, { "pos": "ADJ", "text": "الإعلامية" }, { "pos": "SUB_CONJ", "text": "بأن" }, { "pos": "IV", "text": "يبتعدوا" }, { "pos": "PREP", "text": "عن" }, { "pos": "NOUN", "text": "المليشيات" }, { "pos": "NOUN_PROP", "text": "الحوثية" }, { "pos": "NOUN", "text": "والمعسكرات" }, { "pos": "ADJ", "text": "العسكرية" }, { "pos": "REL_PRON", "text": "التي" }, { "pos": "IV", "text": "تتحصن" }, { "pos": "PRONOUN", "text": "فيها" }, { "pos": "NOUN", "text": "حفاظا" }, { "pos": "PREP", "text": "على" }, { "pos": "NOUN", "text": "سلامتهم" }, { "pos": "PUNC", "text": "\"" }, { "pos": "EOS", "text": "." }, { "pos": "PREP", "text": "وفي" }, { "pos": "NOUN", "text": "محافظة" }, { "pos": "NOUN_PROP", "text": "شبوة" }, { "pos": "PUNC", "text": "(" }, { "pos": "NOUN", "text": "جنوب" }, { "pos": "NOUN", "text": "شرق" }, { "pos": "NOUN_PROP", "text": "اليمن" }, { "pos": "PUNC", "text": ")" }, { "pos": "PUNC", "text": "،" }, { "pos": "PV", "text": "قالت" }, { "pos": "NOUN", "text": "مصادر" }, { "pos": "ADJ", "text": "محلية" }, { "pos": "SUB_CONJ", "text": "إن" }, { "pos": "NOUN", "text": "طائرات" }, { "pos": "NOUN", "text": "التحالف" }, { "pos": "PV", "text": "شنت" }, { "pos": "NUM", "text": "خمس" }, { "pos": "NOUN", "text": "غارات" }, { "pos": "ADJ", "text": "جوية" }, { "pos": "PREP", "text": "على" }, { "pos": "NOUN", "text": "الأقل" }, { "pos": "PREP", "text": "في" }, { "pos": "NOUN", "text": "محيط" }, { "pos": "NOUN", "text": "مطار" }, { "pos": "NOUN", "text": "مدينة" }, { "pos": "NOUN", "text": "عتق" }, { "pos": "PREP", "text": "وفي" }, { "pos": "NOUN", "text": "المدينة" }, { "pos": "NOUN", "text": "نفسها" }, { "pos": "EOS", "text": "." }, { "pos": "PV", "text": "وشنت" }, { "pos": "NOUN", "text": "الطائرات" }, { "pos": "NOUN", "text": "غارات" }, { "pos": "ADV", "text": "أيضا" }, { "pos": "PREP", "text": "في" }, { "pos": "NOUN", "text": "مدينة" }, { "pos": "NOUN_PROP", "text": "عدن" }, { "pos": "PREP", "text": "في" }, { "pos": "NOUN", "text": "وقت" }, { "pos": "ADJ", "text": "متأخر" }, { "pos": "NOUN", "text": "ليلة" }, { "pos": "ADV", "text": "أمس" }, { "pos": "NOUN", "text": "الخميس" }, { "pos": "PUNC", "text": "،" }, { "pos": "PREP", "text": "وفي" }, { "pos": "NOUN", "text": "وقت" }, { "pos": "ADJ", "text": "مبكر" }, { "pos": "PREP", "text": "من" }, { "pos": "NOUN", "text": "صباح" }, { "pos": "NOUN", "text": "اليوم" }, { "pos": "NOUN", "text": "الجمعة" }, { "pos": "EOS", "text": "." }, { "pos": "IV", "text": "ويأتي" }, { "pos": "DEM_PRON", "text": "هذا" }, { "pos": "NOUN", "text": "التصعيد" }, { "pos": "PREP", "text": "بعد" }, { "pos": "NOUN", "text": "إعلان" }, { "pos": "NOUN", "text": "العميد" }, { "pos": "NOUN", "text": "عسيري" }, { "pos": "SUB_CONJ", "text": "أن" }, { "pos": "NOUN", "text": "المعادلة" }, { "pos": "PV", "text": "اختلفت" }, { "pos": "PUNC", "text": "،" }, { "pos": "SUB_CONJ", "text": "وأن" }, { "pos": "NOUN", "text": "قوات" }, { "pos": "NOUN", "text": "التحالف" }, { "pos": "NOUN", "text": "والقوات" }, { "pos": "ADJ", "text": "السعودية" }, { "pos": "ADJ", "text": "المسلحة" }, { "pos": "IV", "text": "سترد" }, { "pos": "PREP", "text": "على" }, { "pos": "NOUN", "text": "اعتداءات" }, { "pos": "NOUN_PROP", "text": "الحوثيين" }, { "pos": "NOUN", "text": "بقوة" }, { "pos": "PUNC", "text": "،" }, { "pos": "NOUN", "text": "وبشكل" }, { "pos": "NEG_PART", "text": "غير" }, { "pos": "ADJ", "text": "محدود" }, { "pos": "NOUN", "text": "بزمان" }, { "pos": "CONJ", "text": "أو" }, { "pos": "NOUN", "text": "مكان" }, { "pos": "EOS", "text": "." }, { "pos": "PV", "text": "وأكد" }, { "pos": "NOUN", "text": "عسيري" }, { "pos": "SUB_CONJ", "text": "أن" }, { "pos": "NOUN", "text": "قيادة" }, { "pos": "NOUN", "text": "التحالف" }, { "pos": "FUT_PART", "text": "سوف" }, { "pos": "IV", "text": "تغير" }, { "pos": "NOUN", "text": "ردها" }, { "pos": "PUNC", "text": "،" }, { "pos": "FUT_PART", "text": "وسوف" }, { "pos": "IV", "text": "تستهدف" }, { "pos": "NOUN", "text": "المليشيات" }, { "pos": "NOUN", "text": "وقادتها" }, { "pos": "PUNC", "text": "،" }, { "pos": "PV", "text": "وأضاف" }, { "pos": "SUB_CONJ", "text": "أن" }, { "pos": "NOUN", "text": "الرد" }, { "pos": "IV", "text": "سيستهدف" }, { "pos": "NOUN", "text": "صعدة" }, { "pos": "NOUN", "text": "ومرّان" }, { "pos": "NOUN", "text": "ومناطق" }, { "pos": "ADJ", "text": "أخرى" }, { "pos": "PUNC", "text": "،" }, { "pos": "NEG_PART", "text": "ولن" }, { "pos": "IV", "text": "يقتصر" }, { "pos": "PREP", "text": "على" }, { "pos": "NOUN", "text": "المناطق" }, { "pos": "ADJ", "text": "الحدودية" }, { "pos": "EOS", "text": "." }, { "pos": "PV", "text": "وكان" }, { "pos": "NOUN", "text": "مراسل" }, { "pos": "NOUN", "text": "الجزيرة" }, { "pos": "PV", "text": "أفاد" }, { "pos": "NOUN", "text": "بتجدد" }, { "pos": "NOUN", "text": "سقوط" }, { "pos": "NOUN", "text": "القذائف" }, { "pos": "NOUN", "text": "مساء" }, { "pos": "ADV", "text": "أمس" }, { "pos": "NOUN", "text": "الخميس" }, { "pos": "PREP", "text": "قرب" }, { "pos": "NOUN", "text": "الحدود" }, { "pos": "ADJ", "text": "اليمنية" }, { "pos": "PREP", "text": "بعد" }, { "pos": "NOUN", "text": "يوم" }, { "pos": "PREP", "text": "من" }, { "pos": "NOUN", "text": "مقتل" }, { "pos": "NUM", "text": "خمسة" }, { "pos": "PUNC", "text": "-" }, { "pos": "PRONOUN", "text": "بينهم" }, { "pos": "NOUN", "text": "شرطي" }, { "pos": "PUNC", "text": "-" }, { "pos": "NOUN", "text": "وإصابة" }, { "pos": "NUM", "text": "11" }, { "pos": "NOUN", "text": "مدنيا" }, { "pos": "PREP", "text": "جراء" }, { "pos": "NOUN", "text": "قصف" }, { "pos": "NOUN_PROP", "text": "بقذائف" }, { "pos": "NOUN", "text": "الهاون" }, { "pos": "PV", "text": "استهدف" }, { "pos": "NOUN", "text": "مناطق" }, { "pos": "ADJ", "text": "عدة" }, { "pos": "PREP", "text": "في" }, { "pos": "NOUN_PROP", "text": "نجران" }, { "pos": "EOS", "text": "." }, { "pos": "NOUN", "text": "المصدر" }, { "pos": "PUNC", "text": ":" }, { "pos": "NOUN", "text": "وكالات" }, { "pos": "PUNC", "text": "," }, { "pos": "NOUN", "text": "الجزيرة" }, { "pos": "ADJ", "text": "مقطع" }, { "pos": "PREP", "text": "من" }, { "pos": "NOUN", "text": "لقاء" }, { "pos": "NOUN", "text": "اليوم" }, { "pos": "PREP", "text": "مع" }, { "pos": "NOUN", "text": "العميد" }, { "pos": "NOUN", "text": "الركن" }, { "pos": "ADJ", "text": "أحمد" }, { "pos": "NOUN", "text": "عسيري" }, { "pos": "PV", "text": "شارك" }, { "pos": "NOUN", "text": "برأيك" }, { "pos": "NOUN", "text": "التعليقات" }, { "pos": "ADJ", "text": "المنشورة" }, { "pos": "NEG_PART", "text": "لا" }, { "pos": "IV", "text": "تعبر" }, { "pos": "PREP", "text": "عن" }, { "pos": "NOUN", "text": "رأي" }, { "pos": "NOUN", "text": "الجزيرة" }, { "pos": "SUB_CONJ", "text": "وإنما" }, { "pos": "IV", "text": "تعبر" }, { "pos": "PREP", "text": "عن" }, { "pos": "NOUN", "text": "رأي" }, { "pos": "NOUN", "text": "أصحابها" }, { "pos": "NOUN_PROP", "text": "انشر" }, { "pos": "NOUN_PROP", "text": "تعليقك" }, { "pos": "PREP", "text": "عن" }, { "pos": "NOUN", "text": "طريق" }, { "pos": "PUNC", "text": ":" }, { "pos": "NOUN", "text": "التعليق" }, { "pos": "ADJ", "text": "الأحدث" }, { "pos": "NOUN", "text": "إظهار" }, { "pos": "NUM", "text": "0" }, { "pos": "PUNC", "text": "/" }, { "pos": "NUM", "text": "0" }, { "pos": "NOUN", "text": "تعليقات" }, { "pos": "ADJ", "text": "أظهر" }, { "pos": "NOUN", "text": "تعليقات" }, { "pos": "ADJ", "text": "أكثر" }, { "pos": "PV", "text": "اقرأ" }, { "pos": "ADV", "text": "أيضاً" }, { "pos": "NOUN", "text": "جميع" }, { "pos": "NOUN", "text": "الحقوق" }, { "pos": "NOUN", "text": "محفوظة" }, { "pos": "NON_ARABIC", "text": "©" }, { "pos": "NUM", "text": "2015" }, { "pos": "NOUN", "text": "الجزيرة" }, { "pos": "PUNC", "text": "|" }, { "pos": "PUNC", "text": ":" }, { "pos": "NON_ARABIC", "text": "Powerd" }, { "pos": "NON_ARABIC", "text": "by" } ], "requestId": "8ea04ca1-c708-4bb1-a652-1599fc02268a", "timers": { "rblJe": 58, "rliJe": 4, "textExtractor": 48, "urlContentDownloader": 166 } } python-0.7.4/tests/mock-data/response/ara-url-morphology_complete.status 0000664 0000000 0000000 00000000003 12636317025 0026576 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/ara-url-sentiment.json 0000664 0000000 0000000 00000000242 12636317025 0024150 0 ustar 00root root 0000000 0000000 { "code": "unsupportedLanguage", "message": "Arabic is not supported by Rosette Sentiment Analyzer", "requestId": "1800a8e9-1f9f-4ca4-b49c-387933f5dd6e" } python-0.7.4/tests/mock-data/response/ara-url-sentiment.status 0000664 0000000 0000000 00000000003 12636317025 0024515 0 ustar 00root root 0000000 0000000 415 python-0.7.4/tests/mock-data/response/bad_info.json 0000664 0000000 0000000 00000000167 12636317025 0022350 0 ustar 00root root 0000000 0000000 { "buildNumber": "6bafb29d", "buildTime": "2015.05.08_12:31:26", "name": "Rosette API", "version": "0.3.0" } python-0.7.4/tests/mock-data/response/bad_info.status 0000664 0000000 0000000 00000000003 12636317025 0022707 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/checkVersion.json 0000664 0000000 0000000 00000000223 12636317025 0023223 0 ustar 00root root 0000000 0000000 { "buildNumber": "6bafb29d", "buildTime": "2015.05.08_12:31:26", "name": "Rosette API", "version": "0.4.0", "versionChecked": false } python-0.7.4/tests/mock-data/response/checkVersion.status 0000664 0000000 0000000 00000000004 12636317025 0023572 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/eng-doc-categories.json 0000664 0000000 0000000 00000000367 12636317025 0024250 0 ustar 00root root 0000000 0000000 { "categories": [ { "confidence": 0.22093012022706549, "label": "TECHNOLOGY_AND_COMPUTING" } ], "requestId": "297a0f9c-7a94-4ecd-ae76-0c08ebce3ce9", "timers": { "cat": 57, "rblJe": 15, "rliJe": 21 } } python-0.7.4/tests/mock-data/response/eng-doc-categories.status 0000664 0000000 0000000 00000000003 12636317025 0024605 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/eng-doc-entities.json 0000664 0000000 0000000 00000007061 12636317025 0023745 0 ustar 00root root 0000000 0000000 { "entities": [ { "confidence": 1.0, "count": 17, "indocChainId": 0, "mention": "Samsung", "normalized": "Samsung", "type": "ORGANIZATION" }, { "confidence": 0.04526931473187038, "count": 14, "indocChainId": 3, "mention": "Apple", "normalized": "Apple", "type": "ORGANIZATION" }, { "confidence": 1.0, "count": 7, "indocChainId": 10, "mention": "U.S.", "normalized": "U.S.", "type": "LOCATION" }, { "confidence": 0.026389598846435547, "count": 3, "indocChainId": 7, "mention": "judge", "normalized": "judge", "type": "TITLE" }, { "confidence": 1.0, "count": 2, "indocChainId": 13, "mention": "South Korean", "normalized": "South Korean", "type": "NATIONALITY" }, { "confidence": 0.03619256615638733, "count": 2, "indocChainId": 15, "mention": "iPad", "normalized": "iPad", "type": "PRODUCT" }, { "confidence": 0.026187777519226074, "count": 2, "indocChainId": 20, "mention": "District Judge", "normalized": "District Judge", "type": "TITLE" }, { "confidence": 0.028430074453353882, "count": 2, "indocChainId": 21, "mention": "Lucy Koh", "normalized": "Lucy Koh", "type": "PERSON" }, { "confidence": 0.011759281158447266, "count": 2, "indocChainId": 21, "mention": "Koh", "normalized": "Koh", "type": "PERSON" }, { "confidence": 1.0, "count": 2, "indocChainId": 52, "mention": "Australia", "normalized": "Australia", "type": "LOCATION" }, { "confidence": 1.0, "count": 1, "indocChainId": 2, "mention": "Samsung Electronics", "normalized": "Samsung Electronics", "type": "ORGANIZATION" }, { "confidence": 1.0, "count": 1, "indocChainId": 10, "mention": "United States", "normalized": "United States", "type": "LOCATION" }, { "confidence": 0.02483654022216797, "count": 1, "indocChainId": 14, "mention": "iPhone", "normalized": "iPhone", "type": "PRODUCT" }, { "confidence": 0.018296480178833008, "count": 1, "indocChainId": 33, "mention": "Tab 10.1", "normalized": "Tab 10.1", "type": "PRODUCT" }, { "confidence": 0.04169809818267822, "count": 1, "indocChainId": 48, "mention": "Silicon Valley", "normalized": "Silicon Valley", "type": "LOCATION" }, { "confidence": 0.026794254779815674, "count": 1, "indocChainId": 50, "mention": "iPads", "normalized": "iPads", "type": "PRODUCT" }, { "confidence": 0.009662508964538574, "count": 1, "indocChainId": 58, "mention": "Galaxy Tablet", "normalized": "Galaxy Tablet", "type": "PRODUCT" }, { "confidence": 1.0, "count": 1, "indocChainId": 60, "mention": "http://newsinabox.net/2202/samsung-can-sell-its-tablet-in-the-u-s-market.html", "normalized": "http://newsinabox.net/2202/samsung-can-sell-its-tablet-in-the-u-s-market.html", "type": "IDENTIFIER:URL" } ], "requestId": "2be64f9f-6246-4366-aab3-16f635ed87a5", "timers": { "rblJe": 29, "rexJe": 656, "rliJe": 35 } } python-0.7.4/tests/mock-data/response/eng-doc-entities.status 0000664 0000000 0000000 00000000003 12636317025 0024304 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/eng-doc-entities_linked.json 0000664 0000000 0000000 00000002203 12636317025 0025264 0 ustar 00root root 0000000 0000000 { "entities": [ { "confidence": 0.6282070187492331, "entityId": "Q20716", "indocChainId": 0, "mention": "Samsung" }, { "confidence": 0.6082548910251077, "entityId": "Q20718", "indocChainId": 2, "mention": "Samsung Electronics" }, { "confidence": 0.4768006169371888, "entityId": "Q312", "indocChainId": 3, "mention": "Apple" }, { "confidence": 0.18249321564878832, "entityId": "Q30", "indocChainId": 10, "mention": "United States" }, { "confidence": 0.7551336788984114, "entityId": "Q6698345", "indocChainId": 21, "mention": "Lucy Koh" }, { "confidence": 0.6516717886866707, "entityId": "Q163820", "indocChainId": 48, "mention": "Silicon Valley" }, { "confidence": 0.10282757678523663, "entityId": "Q408", "indocChainId": 52, "mention": "Australia" } ], "requestId": "547f4ef0-8052-41bc-b019-bbc78330150b", "timers": { "rblJe": 25, "res": 1996, "rexJe": 117, "rliJe": 28 } } python-0.7.4/tests/mock-data/response/eng-doc-entities_linked.status 0000664 0000000 0000000 00000000003 12636317025 0025632 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/eng-doc-language.json 0000664 0000000 0000000 00000001023 12636317025 0023674 0 ustar 00root root 0000000 0000000 { "languageDetections": [ { "confidence": 0.031016215246239986, "language": "eng" }, { "confidence": 0.0038646976772234165, "language": "nor" }, { "confidence": 0.0038272337158813396, "language": "ita" }, { "confidence": 0.003474111402636648, "language": "fra" }, { "confidence": 0.0034140923041809934, "language": "deu" } ], "requestId": "331b2b91-872a-4b03-8791-6676f228824b", "timers": { "rliJe": 57 } } python-0.7.4/tests/mock-data/response/eng-doc-language.status 0000664 0000000 0000000 00000000003 12636317025 0024243 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/eng-doc-morphology_complete.json 0000664 0000000 0000000 00000150717 12636317025 0026217 0 ustar 00root root 0000000 0000000 { "compounds": [], "hanReadings": [], "lemmas": [ { "lemma": "Samsung", "text": "Samsung" }, { "lemma": "can", "text": "Can" }, { "lemma": "sell", "text": "Sell" }, { "lemma": "it", "text": "Its" }, { "lemma": "tablet", "text": "Tablet" }, { "lemma": "in", "text": "In" }, { "lemma": "the", "text": "The" }, { "lemma": "U.S.", "text": "U.S." }, { "lemma": "market", "text": "Market" }, { "lemma": "the", "text": "The" }, { "lemma": "war", "text": "war" }, { "lemma": "between", "text": "between" }, { "lemma": "Samsung", "text": "Samsung" }, { "lemma": "Electronic", "text": "Electronics" }, { "lemma": "and", "text": "and" }, { "lemma": "apple", "text": "Apple" }, { "lemma": "seem", "text": "seems" }, { "lemma": "to", "text": "to" }, { "lemma": "be", "text": "be" }, { "lemma": "never", "text": "never" }, { "lemma": "end", "text": "ending" }, { "lemma": ".", "text": "." }, { "lemma": "the", "text": "The" }, { "lemma": "company", "text": "companies" }, { "lemma": "have", "text": "have" }, { "lemma": "engage", "text": "engaged" }, { "lemma": "in", "text": "in" }, { "lemma": "an", "text": "an" }, { "lemma": "international", "text": "international" }, { "lemma": "warfare", "text": "warfare" }, { "lemma": ",", "text": "," }, { "lemma": "across", "text": "across" }, { "lemma": "continent", "text": "continents" }, { "lemma": ",", "text": "," }, { "lemma": "with", "text": "with" }, { "lemma": "more", "text": "more" }, { "lemma": "than", "text": "than" }, { "lemma": "20", "text": "20" }, { "lemma": "case", "text": "cases" }, { "lemma": "in", "text": "in" }, { "lemma": "10", "text": "10" }, { "lemma": "country", "text": "countries" }, { "lemma": ".", "text": "." }, { "lemma": "the", "text": "The" }, { "lemma": "late", "text": "latest" }, { "lemma": "news", "text": "news" }, { "lemma": "in", "text": "in" }, { "lemma": "the", "text": "the" }, { "lemma": "Samsung", "text": "Samsung" }, { "lemma": "vs", "text": "vs" }, { "lemma": ".", "text": "." }, { "lemma": "apple", "text": "Apple" }, { "lemma": "conflict", "text": "conflict" }, { "lemma": "come", "text": "comes" }, { "lemma": "from", "text": "from" }, { "lemma": "U.S.", "text": "U.S." }, { "lemma": "where", "text": "where" }, { "lemma": "a", "text": "a" }, { "lemma": "judge", "text": "judge" }, { "lemma": "decide", "text": "decided" }, { "lemma": "that", "text": "that" }, { "lemma": "Samsung", "text": "Samsung" }, { "lemma": "can", "text": "can" }, { "lemma": "sell", "text": "sell" }, { "lemma": "it", "text": "its" }, { "lemma": "tablet", "text": "tablet" }, { "lemma": "in", "text": "in" }, { "lemma": "the", "text": "the" }, { "lemma": "U.S.", "text": "U.S." }, { "lemma": "market", "text": "market" }, { "lemma": ".", "text": "." }, { "lemma": "in", "text": "In" }, { "lemma": "United", "text": "United" }, { "lemma": "State", "text": "States" }, { "lemma": ",", "text": "," }, { "lemma": "apple", "text": "Apple" }, { "lemma": "initiate", "text": "initiated" }, { "lemma": "a", "text": "a" }, { "lemma": "legal", "text": "legal" }, { "lemma": "action", "text": "action" }, { "lemma": "against", "text": "against" }, { "lemma": "Samsung", "text": "Samsung" }, { "lemma": "in", "text": "in" }, { "lemma": "April", "text": "April" }, { "lemma": ",", "text": "," }, { "lemma": "claim", "text": "claiming" }, { "lemma": "that", "text": "that" }, { "lemma": "the", "text": "the" }, { "lemma": "South", "text": "South" }, { "lemma": "Korean", "text": "Korean" }, { "lemma": "smartphones", "text": "smartphones" }, { "lemma": "and", "text": "and" }, { "lemma": "tablet", "text": "tablets" }, { "lemma": "“", "text": "“" }, { "lemma": "slavishly", "text": "slavishly" }, { "lemma": "”", "text": "”" }, { "lemma": "copy", "text": "copy" }, { "lemma": "the", "text": "the" }, { "lemma": "iPhone", "text": "iPhone" }, { "lemma": "and", "text": "and" }, { "lemma": "the", "text": "the" }, { "lemma": "iPad", "text": "iPad" }, { "lemma": ".", "text": "." }, { "lemma": "as", "text": "As" }, { "lemma": "a", "text": "a" }, { "lemma": "result", "text": "result" }, { "lemma": ",", "text": "," }, { "lemma": "apple", "text": "Apple" }, { "lemma": "request", "text": "requested" }, { "lemma": "that", "text": "that" }, { "lemma": "Samsung", "text": "Samsung" }, { "lemma": "will", "text": "will" }, { "lemma": "be", "text": "be" }, { "lemma": "prohibit", "text": "prohibited" }, { "lemma": "from", "text": "from" }, { "lemma": "sell", "text": "selling" }, { "lemma": "the", "text": "the" }, { "lemma": "gadget", "text": "gadgets" }, { "lemma": "in", "text": "in" }, { "lemma": "the", "text": "the" }, { "lemma": "U.S.", "text": "U.S." }, { "lemma": "market", "text": "market" }, { "lemma": ".", "text": "." }, { "lemma": "the", "text": "The" }, { "lemma": "much", "text": "much" }, { "lemma": "expected", "text": "expected" }, { "lemma": "ruling", "text": "ruling" }, { "lemma": "come", "text": "came" }, { "lemma": "late", "text": "late" }, { "lemma": "on", "text": "on" }, { "lemma": "Friday", "text": "Friday" }, { "lemma": ",", "text": "," }, { "lemma": "as", "text": "as" }, { "lemma": "U.S.", "text": "U.S." }, { "lemma": "District", "text": "District" }, { "lemma": "judge", "text": "Judge" }, { "lemma": "Lucy", "text": "Lucy" }, { "lemma": "Koh", "text": "Koh" }, { "lemma": "deny", "text": "denied" }, { "lemma": "apple", "text": "Apple" }, { "lemma": "'s", "text": "’s" }, { "lemma": "request", "text": "request" }, { "lemma": "for", "text": "for" }, { "lemma": "a", "text": "a" }, { "lemma": "preliminary", "text": "preliminary" }, { "lemma": "injuction", "text": "injuction" }, { "lemma": "against", "text": "against" }, { "lemma": "Samsung", "text": "Samsung" }, { "lemma": ".", "text": "." }, { "lemma": "U.S.", "text": "U.S." }, { "lemma": "District", "text": "District" }, { "lemma": "judge", "text": "Judge" }, { "lemma": "Lucy", "text": "Lucy" }, { "lemma": "Koh", "text": "Koh" }, { "lemma": "say", "text": "said" }, { "lemma": "that", "text": "that" }, { "lemma": "“", "text": "“" }, { "lemma": "it", "text": "It" }, { "lemma": "be", "text": "is" }, { "lemma": "not", "text": "not" }, { "lemma": "clear", "text": "clear" }, { "lemma": "than", "text": "than" }, { "lemma": "an", "text": "an" }, { "lemma": "injuction", "text": "injuction" }, { "lemma": "on", "text": "on" }, { "lemma": "Samsung", "text": "Samsung" }, { "lemma": "'s", "text": "’s" }, { "lemma": "accused", "text": "accused" }, { "lemma": "device", "text": "devices" }, { "lemma": "would", "text": "would" }, { "lemma": "prevent", "text": "prevent" }, { "lemma": "apple", "text": "Apple" }, { "lemma": "from", "text": "from" }, { "lemma": "be", "text": "being" }, { "lemma": "irreparably", "text": "irreparably" }, { "lemma": "harm", "text": "harmed" }, { "lemma": "”", "text": "”" }, { "lemma": ".", "text": "." }, { "lemma": "as", "text": "As" }, { "lemma": "a", "text": "a" }, { "lemma": "result", "text": "result" }, { "lemma": ",", "text": "," }, { "lemma": "Koh", "text": "Koh" }, { "lemma": "reject", "text": "rejected" }, { "lemma": "apple", "text": "Apple" }, { "lemma": "'s", "text": "’s" }, { "lemma": "request", "text": "request" }, { "lemma": "to", "text": "to" }, { "lemma": "bid", "text": "bid" }, { "lemma": "sale", "text": "sales" }, { "lemma": "of", "text": "of" }, { "lemma": "three", "text": "three" }, { "lemma": "Samsung", "text": "Samsung" }, { "lemma": "smartphones", "text": "smartphones" }, { "lemma": "model", "text": "models" }, { "lemma": "and", "text": "and" }, { "lemma": "the", "text": "the" }, { "lemma": "Samsung", "text": "Samsung" }, { "lemma": "Tab", "text": "Tab" }, { "lemma": "10.1", "text": "10.1" }, { "lemma": ".", "text": "." }, { "lemma": "in", "text": "In" }, { "lemma": "the", "text": "the" }, { "lemma": "three", "text": "third" }, { "lemma": "quarter", "text": "quarter" }, { "lemma": ",", "text": "," }, { "lemma": "Samsung", "text": "Samsung" }, { "lemma": "have", "text": "had" }, { "lemma": "23.8", "text": "23.8" }, { "lemma": "percent", "text": "percent" }, { "lemma": "of", "text": "of" }, { "lemma": "the", "text": "the" }, { "lemma": "global", "text": "global" }, { "lemma": "smartphone", "text": "smartphone" }, { "lemma": "market", "text": "market" }, { "lemma": ",", "text": "," }, { "lemma": "nine", "text": "nine" }, { "lemma": "point", "text": "points" }, { "lemma": "high", "text": "higher" }, { "lemma": "than", "text": "than" }, { "lemma": "apple", "text": "Apple" }, { "lemma": ".", "text": "." }, { "lemma": "the", "text": "The" }, { "lemma": "U.S.", "text": "U.S." }, { "lemma": "judge", "text": "judge" }, { "lemma": "write", "text": "wrote" }, { "lemma": "that", "text": "that" }, { "lemma": "“", "text": "“" }, { "lemma": "apple", "text": "Apple" }, { "lemma": "have", "text": "has" }, { "lemma": "establish", "text": "established" }, { "lemma": "a", "text": "a" }, { "lemma": "likelihood", "text": "likelihood" }, { "lemma": "of", "text": "of" }, { "lemma": "success", "text": "success" }, { "lemma": "on", "text": "on" }, { "lemma": "the", "text": "the" }, { "lemma": "merit", "text": "merits" }, { "lemma": "at", "text": "at" }, { "lemma": "trial", "text": "trial" }, { "lemma": "”", "text": "”" }, { "lemma": "regard", "text": "regarding" }, { "lemma": "some", "text": "some" }, { "lemma": "of", "text": "of" }, { "lemma": "Samsung", "text": "Samsung" }, { "lemma": "'s", "text": "’s" }, { "lemma": "smartphones", "text": "smartphones" }, { "lemma": ".", "text": "." }, { "lemma": "apple", "text": "Apple" }, { "lemma": "would", "text": "would" }, { "lemma": "likely", "text": "likely" }, { "lemma": "prove", "text": "prove" }, { "lemma": "Samsung", "text": "Samsung" }, { "lemma": "infringe", "text": "infringed" }, { "lemma": "one", "text": "one" }, { "lemma": "of", "text": "of" }, { "lemma": "it", "text": "its" }, { "lemma": "tablet", "text": "tablet" }, { "lemma": "patent", "text": "patents" }, { "lemma": ",", "text": "," }, { "lemma": "but", "text": "but" }, { "lemma": "it", "text": "it" }, { "lemma": "do", "text": "did" }, { "lemma": "not", "text": "not" }, { "lemma": "show", "text": "show" }, { "lemma": "that", "text": "that" }, { "lemma": "it", "text": "it" }, { "lemma": "be", "text": "was" }, { "lemma": "likely", "text": "likely" }, { "lemma": "to", "text": "to" }, { "lemma": "overcome", "text": "overcome" }, { "lemma": "Samsung", "text": "Samsung" }, { "lemma": "'s", "text": "’s" }, { "lemma": "challenge", "text": "challenges" }, { "lemma": "to", "text": "to" }, { "lemma": "the", "text": "the" }, { "lemma": "patent", "text": "patent" }, { "lemma": "'s", "text": "’s" }, { "lemma": "validity", "text": "validity" }, { "lemma": ".", "text": "." }, { "lemma": "although", "text": "Although" }, { "lemma": "this", "text": "this" }, { "lemma": "might", "text": "might" }, { "lemma": "be", "text": "be" }, { "lemma": "a", "text": "a" }, { "lemma": "minor", "text": "minor" }, { "lemma": "victory", "text": "victory" }, { "lemma": "for", "text": "for" }, { "lemma": "Samsung", "text": "Samsung" }, { "lemma": ",", "text": "," }, { "lemma": "as", "text": "as" }, { "lemma": "apple", "text": "Apple" }, { "lemma": "still", "text": "still" }, { "lemma": "have", "text": "has" }, { "lemma": "high", "text": "high" }, { "lemma": "change", "text": "changes" }, { "lemma": "of", "text": "of" }, { "lemma": "win", "text": "winning" }, { "lemma": "the", "text": "the" }, { "lemma": "overall", "text": "overall" }, { "lemma": "lawsuit", "text": "lawsuit" }, { "lemma": ",", "text": "," }, { "lemma": "Koh", "text": "Koh" }, { "lemma": "'s", "text": "’s" }, { "lemma": "decision", "text": "decision" }, { "lemma": "make", "text": "makes" }, { "lemma": "it", "text": "it" }, { "lemma": "possible", "text": "possible" }, { "lemma": "for", "text": "for" }, { "lemma": "the", "text": "the" }, { "lemma": "South", "text": "South" }, { "lemma": "Korean", "text": "Korean" }, { "lemma": "company", "text": "company" }, { "lemma": "to", "text": "to" }, { "lemma": "start", "text": "start" }, { "lemma": "Christmas", "text": "Christmas" }, { "lemma": "sale", "text": "sales" }, { "lemma": ".", "text": "." }, { "lemma": "analyst", "text": "Analysts" }, { "lemma": "say", "text": "say" }, { "lemma": "that", "text": "that" }, { "lemma": "global", "text": "global" }, { "lemma": "tablet", "text": "tablet" }, { "lemma": "sale", "text": "sales" }, { "lemma": "be", "text": "are" }, { "lemma": "expect", "text": "expected" }, { "lemma": "to", "text": "to" }, { "lemma": "boost", "text": "boost" }, { "lemma": "to", "text": "to" }, { "lemma": "more", "text": "more" }, { "lemma": "than", "text": "than" }, { "lemma": "50", "text": "50" }, { "lemma": "million", "text": "million" }, { "lemma": "this", "text": "this" }, { "lemma": "year", "text": "year" }, { "lemma": ",", "text": "," }, { "lemma": "with", "text": "with" }, { "lemma": "apple", "text": "Apple" }, { "lemma": "still", "text": "still" }, { "lemma": "the", "text": "the" }, { "lemma": "leader", "text": "leader" }, { "lemma": "of", "text": "of" }, { "lemma": "the", "text": "the" }, { "lemma": "market", "text": "market" }, { "lemma": ".", "text": "." }, { "lemma": "the", "text": "The" }, { "lemma": "silicone", "text": "Silicon" }, { "lemma": "valley", "text": "Valley" }, { "lemma": "base", "text": "based" }, { "lemma": "company", "text": "company" }, { "lemma": "sell", "text": "sold" }, { "lemma": "11.12", "text": "11.12" }, { "lemma": "million", "text": "million" }, { "lemma": "unit", "text": "units" }, { "lemma": "during", "text": "during" }, { "lemma": "the", "text": "the" }, { "lemma": "September", "text": "September" }, { "lemma": "quarter", "text": "quarter" }, { "lemma": ".", "text": "." }, { "lemma": "so", "text": "So" }, { "lemma": "far", "text": "far" }, { "lemma": ",", "text": "," }, { "lemma": "apple", "text": "Apple" }, { "lemma": "sell", "text": "sold" }, { "lemma": "more", "text": "more" }, { "lemma": "than", "text": "than" }, { "lemma": "30", "text": "30" }, { "lemma": "million", "text": "million" }, { "lemma": "iPads", "text": "iPads" }, { "lemma": "worldwide", "text": "worldwide" }, { "lemma": ".", "text": "." }, { "lemma": "last", "text": "Last" }, { "lemma": "week", "text": "week" }, { "lemma": ",", "text": "," }, { "lemma": "a", "text": "a" }, { "lemma": "judge", "text": "judge" }, { "lemma": "in", "text": "in" }, { "lemma": "Australia", "text": "Australia" }, { "lemma": "rule", "text": "ruled" }, { "lemma": "in", "text": "in" }, { "lemma": "favor", "text": "favor" }, { "lemma": "of", "text": "of" }, { "lemma": "apple", "text": "Apple" }, { "lemma": "by", "text": "by" }, { "lemma": "extend", "text": "extending" }, { "lemma": "a", "text": "a" }, { "lemma": "ban", "text": "ban" }, { "lemma": "on", "text": "on" }, { "lemma": "Samsung", "text": "Samsung" }, { "lemma": "'s", "text": "’s" }, { "lemma": "iPad", "text": "iPad" }, { "lemma": "sale", "text": "sales" }, { "lemma": "within", "text": "within" }, { "lemma": "the", "text": "the" }, { "lemma": "country", "text": "country" }, { "lemma": ".", "text": "." }, { "lemma": "Australia", "text": "Australia" }, { "lemma": "be", "text": "is" }, { "lemma": "a", "text": "a" }, { "lemma": "key", "text": "key" }, { "lemma": "market", "text": "market" }, { "lemma": "for", "text": "for" }, { "lemma": "Samsung", "text": "Samsung" }, { "lemma": "galaxy", "text": "Galaxy" }, { "lemma": "tablet", "text": "Tablet" }, { "lemma": "and", "text": "and" }, { "lemma": "two", "text": "two" }, { "lemma": "week", "text": "weeks" }, { "lemma": "of", "text": "of" }, { "lemma": "banned", "text": "banned" }, { "lemma": "sale", "text": "sales" }, { "lemma": "be not", "text": "isn’t" }, { "lemma": "much", "text": "much" }, { "lemma": ",", "text": "," }, { "lemma": "but", "text": "but" }, { "lemma": "it", "text": "it" }, { "lemma": "can", "text": "can" }, { "lemma": "get", "text": "get" }, { "lemma": "urgent", "text": "urgent" }, { "lemma": "if", "text": "if" }, { "lemma": "Samsung", "text": "Samsung" }, { "lemma": "will not", "text": "won’t" }, { "lemma": "start", "text": "start" }, { "lemma": "sell", "text": "selling" }, { "lemma": "the", "text": "the" }, { "lemma": "gadget", "text": "gadget" }, { "lemma": "before", "text": "before" }, { "lemma": "Christmas", "text": "Christmas" }, { "lemma": ".", "text": "." }, { "lemma": "http", "text": "http" }, { "lemma": ":", "text": ":" }, { "lemma": "/", "text": "/" }, { "lemma": "/", "text": "/" }, { "lemma": "newsinabox.net", "text": "newsinabox.net" }, { "lemma": "/", "text": "/" }, { "lemma": "2202", "text": "2202" }, { "lemma": "/", "text": "/" }, { "lemma": "samsung", "text": "samsung" }, { "lemma": "-", "text": "-" }, { "lemma": "can", "text": "can" }, { "lemma": "-", "text": "-" }, { "lemma": "sell", "text": "sell" }, { "lemma": "-", "text": "-" }, { "lemma": "it", "text": "its" }, { "lemma": "-", "text": "-" }, { "lemma": "tablet", "text": "tablet" }, { "lemma": "-", "text": "-" }, { "lemma": "in", "text": "in" }, { "lemma": "-", "text": "-" }, { "lemma": "the", "text": "the" }, { "lemma": "-", "text": "-" }, { "lemma": "u", "text": "u" }, { "lemma": "-", "text": "-" }, { "lemma": "s", "text": "s" }, { "lemma": "-", "text": "-" }, { "lemma": "market.html", "text": "market.html" }, { "lemma": "2011.12.05", "text": "2011.12.05" } ], "posTags": [ { "pos": "PROP", "text": "Samsung" }, { "pos": "VAUX", "text": "Can" }, { "pos": "VI", "text": "Sell" }, { "pos": "DET", "text": "Its" }, { "pos": "NOUN", "text": "Tablet" }, { "pos": "PREP", "text": "In" }, { "pos": "DET", "text": "The" }, { "pos": "PROP", "text": "U.S." }, { "pos": "VPRES", "text": "Market" }, { "pos": "DET", "text": "The" }, { "pos": "NOUN", "text": "war" }, { "pos": "PREP", "text": "between" }, { "pos": "PROP", "text": "Samsung" }, { "pos": "PROP", "text": "Electronics" }, { "pos": "COORD", "text": "and" }, { "pos": "NOUN", "text": "Apple" }, { "pos": "VPRES", "text": "seems" }, { "pos": "INFTO", "text": "to" }, { "pos": "VBI", "text": "be" }, { "pos": "ADV", "text": "never" }, { "pos": "PARTPRES", "text": "ending" }, { "pos": "SENT", "text": "." }, { "pos": "DET", "text": "The" }, { "pos": "NOUN", "text": "companies" }, { "pos": "VHPRES", "text": "have" }, { "pos": "VPAP", "text": "engaged" }, { "pos": "PREP", "text": "in" }, { "pos": "DET", "text": "an" }, { "pos": "ADJ", "text": "international" }, { "pos": "NOUN", "text": "warfare" }, { "pos": "CM", "text": "," }, { "pos": "PREP", "text": "across" }, { "pos": "NOUN", "text": "continents" }, { "pos": "CM", "text": "," }, { "pos": "PREP", "text": "with" }, { "pos": "QUANTCMP", "text": "more" }, { "pos": "COTHAN", "text": "than" }, { "pos": "CARD", "text": "20" }, { "pos": "NOUN", "text": "cases" }, { "pos": "PREP", "text": "in" }, { "pos": "CARD", "text": "10" }, { "pos": "NOUN", "text": "countries" }, { "pos": "SENT", "text": "." }, { "pos": "DET", "text": "The" }, { "pos": "ADJSUP", "text": "latest" }, { "pos": "NOUN", "text": "news" }, { "pos": "PREP", "text": "in" }, { "pos": "DET", "text": "the" }, { "pos": "PROP", "text": "Samsung" }, { "pos": "PREP", "text": "vs" }, { "pos": "SENT", "text": "." }, { "pos": "NOUN", "text": "Apple" }, { "pos": "NOUN", "text": "conflict" }, { "pos": "VPRES", "text": "comes" }, { "pos": "PREP", "text": "from" }, { "pos": "PROP", "text": "U.S." }, { "pos": "COSUB", "text": "where" }, { "pos": "DET", "text": "a" }, { "pos": "NOUN", "text": "judge" }, { "pos": "VPAST", "text": "decided" }, { "pos": "COSUB", "text": "that" }, { "pos": "PROP", "text": "Samsung" }, { "pos": "VAUX", "text": "can" }, { "pos": "VI", "text": "sell" }, { "pos": "DET", "text": "its" }, { "pos": "NOUN", "text": "tablet" }, { "pos": "PREP", "text": "in" }, { "pos": "DET", "text": "the" }, { "pos": "PROP", "text": "U.S." }, { "pos": "NOUN", "text": "market" }, { "pos": "SENT", "text": "." }, { "pos": "PREP", "text": "In" }, { "pos": "PROP", "text": "United" }, { "pos": "PROP", "text": "States" }, { "pos": "CM", "text": "," }, { "pos": "NOUN", "text": "Apple" }, { "pos": "VPAST", "text": "initiated" }, { "pos": "DET", "text": "a" }, { "pos": "ADJ", "text": "legal" }, { "pos": "NOUN", "text": "action" }, { "pos": "PREP", "text": "against" }, { "pos": "PROP", "text": "Samsung" }, { "pos": "PREP", "text": "in" }, { "pos": "PROP", "text": "April" }, { "pos": "CM", "text": "," }, { "pos": "PARTPRES", "text": "claiming" }, { "pos": "COSUB", "text": "that" }, { "pos": "DET", "text": "the" }, { "pos": "PROP", "text": "South" }, { "pos": "ADJ", "text": "Korean" }, { "pos": "NOUN", "text": "smartphones" }, { "pos": "COORD", "text": "and" }, { "pos": "NOUN", "text": "tablets" }, { "pos": "PUNCT", "text": "“" }, { "pos": "ADV", "text": "slavishly" }, { "pos": "PUNCT", "text": "”" }, { "pos": "VPRES", "text": "copy" }, { "pos": "DET", "text": "the" }, { "pos": "PROP", "text": "iPhone" }, { "pos": "COORD", "text": "and" }, { "pos": "DET", "text": "the" }, { "pos": "PROP", "text": "iPad" }, { "pos": "SENT", "text": "." }, { "pos": "PREPADVAS", "text": "As" }, { "pos": "DET", "text": "a" }, { "pos": "NOUN", "text": "result" }, { "pos": "CM", "text": "," }, { "pos": "NOUN", "text": "Apple" }, { "pos": "VPAST", "text": "requested" }, { "pos": "COSUB", "text": "that" }, { "pos": "PROP", "text": "Samsung" }, { "pos": "VAUX", "text": "will" }, { "pos": "VBI", "text": "be" }, { "pos": "VPAP", "text": "prohibited" }, { "pos": "PREP", "text": "from" }, { "pos": "PARTPRES", "text": "selling" }, { "pos": "DET", "text": "the" }, { "pos": "NOUN", "text": "gadgets" }, { "pos": "PREP", "text": "in" }, { "pos": "DET", "text": "the" }, { "pos": "PROP", "text": "U.S." }, { "pos": "NOUN", "text": "market" }, { "pos": "SENT", "text": "." }, { "pos": "DET", "text": "The" }, { "pos": "QUANTADV", "text": "much" }, { "pos": "ADJPAP", "text": "expected" }, { "pos": "NOUNING", "text": "ruling" }, { "pos": "VPAST", "text": "came" }, { "pos": "ADV", "text": "late" }, { "pos": "PREP", "text": "on" }, { "pos": "NOUN", "text": "Friday" }, { "pos": "CM", "text": "," }, { "pos": "PREPADVAS", "text": "as" }, { "pos": "PROP", "text": "U.S." }, { "pos": "PROP", "text": "District" }, { "pos": "NOUN", "text": "Judge" }, { "pos": "PROP", "text": "Lucy" }, { "pos": "PROP", "text": "Koh" }, { "pos": "VPAST", "text": "denied" }, { "pos": "NOUN", "text": "Apple" }, { "pos": "POSS", "text": "’s" }, { "pos": "NOUN", "text": "request" }, { "pos": "PREP", "text": "for" }, { "pos": "DET", "text": "a" }, { "pos": "ADJ", "text": "preliminary" }, { "pos": "NOUN", "text": "injuction" }, { "pos": "PREP", "text": "against" }, { "pos": "PROP", "text": "Samsung" }, { "pos": "SENT", "text": "." }, { "pos": "PROP", "text": "U.S." }, { "pos": "PROP", "text": "District" }, { "pos": "NOUN", "text": "Judge" }, { "pos": "PROP", "text": "Lucy" }, { "pos": "PROP", "text": "Koh" }, { "pos": "VPAST", "text": "said" }, { "pos": "COSUB", "text": "that" }, { "pos": "PUNCT", "text": "“" }, { "pos": "PRONPERS", "text": "It" }, { "pos": "VBPRES", "text": "is" }, { "pos": "NOT", "text": "not" }, { "pos": "VI", "text": "clear" }, { "pos": "COTHAN", "text": "than" }, { "pos": "DET", "text": "an" }, { "pos": "NOUN", "text": "injuction" }, { "pos": "PREP", "text": "on" }, { "pos": "PROP", "text": "Samsung" }, { "pos": "POSS", "text": "’s" }, { "pos": "ADJPAP", "text": "accused" }, { "pos": "NOUN", "text": "devices" }, { "pos": "VAUX", "text": "would" }, { "pos": "VI", "text": "prevent" }, { "pos": "NOUN", "text": "Apple" }, { "pos": "PREP", "text": "from" }, { "pos": "PARTPRES", "text": "being" }, { "pos": "ADV", "text": "irreparably" }, { "pos": "VPAP", "text": "harmed" }, { "pos": "PUNCT", "text": "”" }, { "pos": "SENT", "text": "." }, { "pos": "PREPADVAS", "text": "As" }, { "pos": "DET", "text": "a" }, { "pos": "NOUN", "text": "result" }, { "pos": "CM", "text": "," }, { "pos": "PROP", "text": "Koh" }, { "pos": "VPAST", "text": "rejected" }, { "pos": "NOUN", "text": "Apple" }, { "pos": "POSS", "text": "’s" }, { "pos": "NOUN", "text": "request" }, { "pos": "INFTO", "text": "to" }, { "pos": "VI", "text": "bid" }, { "pos": "NOUN", "text": "sales" }, { "pos": "PREP", "text": "of" }, { "pos": "CARD", "text": "three" }, { "pos": "PROP", "text": "Samsung" }, { "pos": "ADJ", "text": "smartphones" }, { "pos": "NOUN", "text": "models" }, { "pos": "COORD", "text": "and" }, { "pos": "DET", "text": "the" }, { "pos": "PROP", "text": "Samsung" }, { "pos": "PROP", "text": "Tab" }, { "pos": "CARD", "text": "10.1" }, { "pos": "SENT", "text": "." }, { "pos": "PREP", "text": "In" }, { "pos": "DET", "text": "the" }, { "pos": "ORD", "text": "third" }, { "pos": "NOUN", "text": "quarter" }, { "pos": "CM", "text": "," }, { "pos": "PROP", "text": "Samsung" }, { "pos": "VHPAST", "text": "had" }, { "pos": "CARD", "text": "23.8" }, { "pos": "NOUN", "text": "percent" }, { "pos": "PREP", "text": "of" }, { "pos": "DET", "text": "the" }, { "pos": "ADJ", "text": "global" }, { "pos": "ADJ", "text": "smartphone" }, { "pos": "NOUN", "text": "market" }, { "pos": "CM", "text": "," }, { "pos": "CARD", "text": "nine" }, { "pos": "NOUN", "text": "points" }, { "pos": "ADJCMP", "text": "higher" }, { "pos": "COTHAN", "text": "than" }, { "pos": "NOUN", "text": "Apple" }, { "pos": "SENT", "text": "." }, { "pos": "DET", "text": "The" }, { "pos": "PROP", "text": "U.S." }, { "pos": "NOUN", "text": "judge" }, { "pos": "VPAST", "text": "wrote" }, { "pos": "COSUB", "text": "that" }, { "pos": "PUNCT", "text": "“" }, { "pos": "NOUN", "text": "Apple" }, { "pos": "VHPRES", "text": "has" }, { "pos": "VPAP", "text": "established" }, { "pos": "DET", "text": "a" }, { "pos": "NOUN", "text": "likelihood" }, { "pos": "PREP", "text": "of" }, { "pos": "NOUN", "text": "success" }, { "pos": "PREP", "text": "on" }, { "pos": "DET", "text": "the" }, { "pos": "NOUN", "text": "merits" }, { "pos": "PREP", "text": "at" }, { "pos": "NOUN", "text": "trial" }, { "pos": "PUNCT", "text": "”" }, { "pos": "PARTPRES", "text": "regarding" }, { "pos": "QUANT", "text": "some" }, { "pos": "PREP", "text": "of" }, { "pos": "PROP", "text": "Samsung" }, { "pos": "POSS", "text": "’s" }, { "pos": "ADJ", "text": "smartphones" }, { "pos": "SENT", "text": "." }, { "pos": "NOUN", "text": "Apple" }, { "pos": "VAUX", "text": "would" }, { "pos": "ADJ", "text": "likely" }, { "pos": "VI", "text": "prove" }, { "pos": "PROP", "text": "Samsung" }, { "pos": "VPAST", "text": "infringed" }, { "pos": "PRONONE", "text": "one" }, { "pos": "PREP", "text": "of" }, { "pos": "DET", "text": "its" }, { "pos": "NOUN", "text": "tablet" }, { "pos": "NOUN", "text": "patents" }, { "pos": "CM", "text": "," }, { "pos": "COSUB", "text": "but" }, { "pos": "PRONPERS", "text": "it" }, { "pos": "VDPAST", "text": "did" }, { "pos": "NOT", "text": "not" }, { "pos": "VI", "text": "show" }, { "pos": "COSUB", "text": "that" }, { "pos": "PRONPERS", "text": "it" }, { "pos": "VBPAST", "text": "was" }, { "pos": "ADJ", "text": "likely" }, { "pos": "INFTO", "text": "to" }, { "pos": "VI", "text": "overcome" }, { "pos": "PROP", "text": "Samsung" }, { "pos": "POSS", "text": "’s" }, { "pos": "NOUN", "text": "challenges" }, { "pos": "PREP", "text": "to" }, { "pos": "DET", "text": "the" }, { "pos": "NOUN", "text": "patent" }, { "pos": "POSS", "text": "’s" }, { "pos": "NOUN", "text": "validity" }, { "pos": "SENT", "text": "." }, { "pos": "COSUB", "text": "Although" }, { "pos": "PRON", "text": "this" }, { "pos": "VAUX", "text": "might" }, { "pos": "VBI", "text": "be" }, { "pos": "DET", "text": "a" }, { "pos": "ADJ", "text": "minor" }, { "pos": "NOUN", "text": "victory" }, { "pos": "PREP", "text": "for" }, { "pos": "PROP", "text": "Samsung" }, { "pos": "CM", "text": "," }, { "pos": "PREPADVAS", "text": "as" }, { "pos": "NOUN", "text": "Apple" }, { "pos": "ADV", "text": "still" }, { "pos": "VHPRES", "text": "has" }, { "pos": "ADJ", "text": "high" }, { "pos": "NOUN", "text": "changes" }, { "pos": "PREP", "text": "of" }, { "pos": "PARTPRES", "text": "winning" }, { "pos": "DET", "text": "the" }, { "pos": "ADJ", "text": "overall" }, { "pos": "NOUN", "text": "lawsuit" }, { "pos": "CM", "text": "," }, { "pos": "PROP", "text": "Koh" }, { "pos": "POSS", "text": "’s" }, { "pos": "NOUN", "text": "decision" }, { "pos": "VPRES", "text": "makes" }, { "pos": "PRONPERS", "text": "it" }, { "pos": "ADJ", "text": "possible" }, { "pos": "PREP", "text": "for" }, { "pos": "DET", "text": "the" }, { "pos": "PROP", "text": "South" }, { "pos": "ADJ", "text": "Korean" }, { "pos": "NOUN", "text": "company" }, { "pos": "INFTO", "text": "to" }, { "pos": "VI", "text": "start" }, { "pos": "PROP", "text": "Christmas" }, { "pos": "NOUN", "text": "sales" }, { "pos": "SENT", "text": "." }, { "pos": "NOUN", "text": "Analysts" }, { "pos": "VPRES", "text": "say" }, { "pos": "DET", "text": "that" }, { "pos": "ADJ", "text": "global" }, { "pos": "NOUN", "text": "tablet" }, { "pos": "NOUN", "text": "sales" }, { "pos": "VBPRES", "text": "are" }, { "pos": "VPAP", "text": "expected" }, { "pos": "INFTO", "text": "to" }, { "pos": "VI", "text": "boost" }, { "pos": "PREP", "text": "to" }, { "pos": "QUANTCMP", "text": "more" }, { "pos": "COTHAN", "text": "than" }, { "pos": "CARD", "text": "50" }, { "pos": "CARD", "text": "million" }, { "pos": "DET", "text": "this" }, { "pos": "NOUN", "text": "year" }, { "pos": "CM", "text": "," }, { "pos": "PREP", "text": "with" }, { "pos": "NOUN", "text": "Apple" }, { "pos": "ADV", "text": "still" }, { "pos": "DET", "text": "the" }, { "pos": "NOUN", "text": "leader" }, { "pos": "PREP", "text": "of" }, { "pos": "DET", "text": "the" }, { "pos": "NOUN", "text": "market" }, { "pos": "SENT", "text": "." }, { "pos": "DET", "text": "The" }, { "pos": "NOUN", "text": "Silicon" }, { "pos": "NOUN", "text": "Valley" }, { "pos": "VPAST", "text": "based" }, { "pos": "NOUN", "text": "company" }, { "pos": "VPAST", "text": "sold" }, { "pos": "CARD", "text": "11.12" }, { "pos": "CARD", "text": "million" }, { "pos": "NOUN", "text": "units" }, { "pos": "PREP", "text": "during" }, { "pos": "DET", "text": "the" }, { "pos": "PROP", "text": "September" }, { "pos": "NOUN", "text": "quarter" }, { "pos": "SENT", "text": "." }, { "pos": "ADV", "text": "So" }, { "pos": "ADV", "text": "far" }, { "pos": "CM", "text": "," }, { "pos": "NOUN", "text": "Apple" }, { "pos": "VPAST", "text": "sold" }, { "pos": "QUANTCMP", "text": "more" }, { "pos": "COTHAN", "text": "than" }, { "pos": "CARD", "text": "30" }, { "pos": "CARD", "text": "million" }, { "pos": "PROP", "text": "iPads" }, { "pos": "ADJ", "text": "worldwide" }, { "pos": "SENT", "text": "." }, { "pos": "ADJ", "text": "Last" }, { "pos": "NOUN", "text": "week" }, { "pos": "CM", "text": "," }, { "pos": "DET", "text": "a" }, { "pos": "NOUN", "text": "judge" }, { "pos": "PREP", "text": "in" }, { "pos": "PROP", "text": "Australia" }, { "pos": "VPAST", "text": "ruled" }, { "pos": "PREP", "text": "in" }, { "pos": "NOUN", "text": "favor" }, { "pos": "PREP", "text": "of" }, { "pos": "NOUN", "text": "Apple" }, { "pos": "PREP", "text": "by" }, { "pos": "PARTPRES", "text": "extending" }, { "pos": "DET", "text": "a" }, { "pos": "NOUN", "text": "ban" }, { "pos": "PREP", "text": "on" }, { "pos": "PROP", "text": "Samsung" }, { "pos": "POSS", "text": "’s" }, { "pos": "ADJ", "text": "iPad" }, { "pos": "NOUN", "text": "sales" }, { "pos": "PREP", "text": "within" }, { "pos": "DET", "text": "the" }, { "pos": "NOUN", "text": "country" }, { "pos": "SENT", "text": "." }, { "pos": "PROP", "text": "Australia" }, { "pos": "VBPRES", "text": "is" }, { "pos": "DET", "text": "a" }, { "pos": "NOUN", "text": "key" }, { "pos": "NOUN", "text": "market" }, { "pos": "PREP", "text": "for" }, { "pos": "PROP", "text": "Samsung" }, { "pos": "NOUN", "text": "Galaxy" }, { "pos": "NOUN", "text": "Tablet" }, { "pos": "COORD", "text": "and" }, { "pos": "CARD", "text": "two" }, { "pos": "NOUN", "text": "weeks" }, { "pos": "PREP", "text": "of" }, { "pos": "ADJPAP", "text": "banned" }, { "pos": "NOUN", "text": "sales" }, { "pos": "VBPRES", "text": "isn’t" }, { "pos": "QUANTADV", "text": "much" }, { "pos": "CM", "text": "," }, { "pos": "COSUB", "text": "but" }, { "pos": "PRONPERS", "text": "it" }, { "pos": "VAUX", "text": "can" }, { "pos": "VI", "text": "get" }, { "pos": "ADJ", "text": "urgent" }, { "pos": "COSUB", "text": "if" }, { "pos": "PROP", "text": "Samsung" }, { "pos": "VAUX", "text": "won’t" }, { "pos": "VI", "text": "start" }, { "pos": "PARTPRES", "text": "selling" }, { "pos": "DET", "text": "the" }, { "pos": "NOUN", "text": "gadget" }, { "pos": "PREP", "text": "before" }, { "pos": "PROP", "text": "Christmas" }, { "pos": "SENT", "text": "." }, { "pos": "ADJ", "text": "http" }, { "pos": "SENT", "text": ":" }, { "pos": "PUNCT", "text": "/" }, { "pos": "PUNCT", "text": "/" }, { "pos": "PROP", "text": "newsinabox.net" }, { "pos": "PUNCT", "text": "/" }, { "pos": "CARD", "text": "2202" }, { "pos": "PUNCT", "text": "/" }, { "pos": "ADJ", "text": "samsung" }, { "pos": "PUNCT", "text": "-" }, { "pos": "NOUN", "text": "can" }, { "pos": "PUNCT", "text": "-" }, { "pos": "VPRES", "text": "sell" }, { "pos": "PUNCT", "text": "-" }, { "pos": "PRON", "text": "its" }, { "pos": "PUNCT", "text": "-" }, { "pos": "NOUN", "text": "tablet" }, { "pos": "PUNCT", "text": "-" }, { "pos": "PREP", "text": "in" }, { "pos": "PUNCT", "text": "-" }, { "pos": "DET", "text": "the" }, { "pos": "PUNCT", "text": "-" }, { "pos": "PROP", "text": "u" }, { "pos": "PUNCT", "text": "-" }, { "pos": "PROP", "text": "s" }, { "pos": "PUNCT", "text": "-" }, { "pos": "PROP", "text": "market.html" }, { "pos": "PROP", "text": "2011.12.05" } ], "requestId": "ef1351d7-17dc-4d25-bf1f-50209902a475", "timers": { "rblJe": 75, "rliJe": 39 } } python-0.7.4/tests/mock-data/response/eng-doc-morphology_complete.status 0000664 0000000 0000000 00000000003 12636317025 0026547 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/eng-doc-relationships.json 0000664 0000000 0000000 00000010567 12636317025 0025012 0 ustar 00root root 0000000 0000000 { "requestId": "f2bd0e5d-f9c8-4525-93fd-816025b291de", "relationships": [ { "predicate": "seems", "arg1": "The war between Samsung Electronics", "arg2": "to be never ending" }, { "predicate": "Can Sell", "arg1": "Samsung", "arg2": "Its Tablet" }, { "predicate": "decided", "arg1": "a judge", "arg2": "that Samsung can sell its tablet in the U.S. market" }, { "predicate": "comes", "arg1": "Apple conflict", "locatives": [ "from U.S." ] }, { "predicate": "can sell", "arg1": "Samsung", "arg2": "its tablet", "adjuncts": [ "in the U.S. market" ] }, { "predicate": "claiming", "arg1": "Apple", "arg2": "copy the iPhone" }, { "predicate": "copy", "arg1": "tablets", "arg2": "the iPhone" }, { "predicate": "copy", "arg1": "tablets", "arg2": "the iPad" }, { "predicate": "copy", "arg1": "the South Korean smartphones", "arg2": "the iPhone" }, { "predicate": "initiated", "arg1": "Apple", "arg2": "a legal action against Samsung", "locatives": [ "In United States" ], "adjuncts": [ "claiming that the South Korean smartphones", "in April" ] }, { "predicate": "copy", "arg1": "the South Korean smartphones", "arg2": "the iPad" }, { "predicate": "will be prohibited", "arg1": "Samsung", "adjuncts": [ "from selling the gadgets in the U.S. market" ] }, { "predicate": "requested", "arg1": "Apple", "arg2": "that Samsung will be prohibited", "adjuncts": [ "As a result" ] }, { "predicate": "came late", "arg1": "The much expected ruling", "adjuncts": [ "on Friday", "as U.S. District Judge Lucy Koh denied Apple’s request for a preliminary injuction against Samsung" ] }, { "predicate": "denied", "arg1": "U.S. District Judge Lucy Koh", "arg2": "Apple’s request for a preliminary injuction against Samsung" }, { "predicate": "said", "arg1": "U.S. District Judge Lucy Koh", "arg2": "It is not clear than an injuction on Samsung’s accused devices would prevent Apple from being irreparably harmed" }, { "predicate": "rejected", "arg1": "Koh", "arg2": "Apple’s request", "adjuncts": [ "As a result" ] }, { "predicate": "had", "arg1": "Samsung", "arg2": "23.8 percent of the global smartphone market", "adjuncts": [ "In the third quarter" ] }, { "predicate": "wrote", "arg1": "The U.S. judge", "arg2": "Apple has established a likelihood of success on the merits at trial" }, { "predicate": "has established", "arg1": "Apple", "arg2": "a likelihood of success on the merits at trial" }, { "predicate": "infringed", "arg1": "Samsung", "arg2": "one of its tablet patents" }, { "predicate": "still has", "arg1": "Apple", "arg2": "high changes of winning the overall lawsuit" }, { "predicate": "makes", "arg1": "Koh’s decision", "arg2": "it possible for the South Korean company to start Christmas sales" }, { "predicate": "are expected", "arg1": "global tablet sales", "arg2": "to boost to more than 50 million this year", "adjuncts": [ "with Apple still the leader of the market" ] }, { "predicate": "sold", "arg1": "Apple", "arg2": "more than 30 million iPads worldwide" }, { "predicate": "by extending", "arg1": "a judge in Australia", "arg2": "a ban on Samsung’s iPad sales within the country" }, { "predicate": "ruled", "arg1": "a judge in Australia", "adjuncts": [ "Last week", "in favor of Apple", "by extending a ban on Samsung’s iPad sales within the country" ] }, { "predicate": "is", "arg1": "Australia", "arg2": "a key market for Samsung Galaxy Tablet" }, { "predicate": "is a key market", "arg1": "Australia", "adjuncts": [ "for Samsung Galaxy Tablet" ] } ] } python-0.7.4/tests/mock-data/response/eng-doc-relationships.status 0000664 0000000 0000000 00000000004 12636317025 0025345 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/eng-doc-sentiment.json 0000664 0000000 0000000 00000000456 12636317025 0024130 0 ustar 00root root 0000000 0000000 { "requestId": "406f10ca-ca7b-4ea2-ba81-103df64202c7", "sentiment": [ { "confidence": 0.8017006157160519, "label": "neg" }, { "confidence": 0.19829938428394817, "label": "pos" } ], "timers": { "rblJe": 11, "rliJe": 21, "sent": 39 } } python-0.7.4/tests/mock-data/response/eng-doc-sentiment.status 0000664 0000000 0000000 00000000003 12636317025 0024466 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/eng-sentence-categories.json 0000664 0000000 0000000 00000000370 12636317025 0025301 0 ustar 00root root 0000000 0000000 { "categories": [ { "confidence": 0.07808597563331034, "label": "LAW_GOVERNMENT_AND_POLITICS" } ], "requestId": "6ad3ca89-792f-486b-a837-13565bb9d9f8", "timers": { "cat": 4, "rblJe": 3, "rliJe": 17 } } python-0.7.4/tests/mock-data/response/eng-sentence-categories.status 0000664 0000000 0000000 00000000003 12636317025 0025644 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/eng-sentence-entities.json 0000664 0000000 0000000 00000002017 12636317025 0025000 0 ustar 00root root 0000000 0000000 { "entities": [ { "confidence": 1.0, "count": 2, "indocChainId": 0, "mention": "U.S.", "normalized": "U.S.", "type": "LOCATION" }, { "confidence": 1.0, "count": 1, "indocChainId": 1, "mention": "Iraq", "normalized": "Iraq", "type": "LOCATION" }, { "confidence": 1.0, "count": 1, "indocChainId": 2, "mention": "Afghanistan", "normalized": "Afghanistan", "type": "LOCATION" }, { "confidence": 0.009895622730255127, "count": 1, "indocChainId": 3, "mention": "commander in chief", "normalized": "commander in chief", "type": "TITLE" }, { "confidence": 1.0, "count": 1, "indocChainId": 4, "mention": "American", "normalized": "American", "type": "NATIONALITY" } ], "requestId": "75686168-76e1-490c-b960-a4d3a4b0cf5d", "timers": { "rblJe": 3, "rexJe": 5, "rliJe": 14 } } python-0.7.4/tests/mock-data/response/eng-sentence-entities.status 0000664 0000000 0000000 00000000003 12636317025 0025343 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/eng-sentence-entities_linked.json 0000664 0000000 0000000 00000001070 12636317025 0026324 0 ustar 00root root 0000000 0000000 { "entities": [ { "confidence": 0.7663931614955327, "entityId": "Q30", "indocChainId": 0, "mention": "U.S." }, { "confidence": 0.29775268161399915, "entityId": "Q796", "indocChainId": 1, "mention": "Iraq" }, { "confidence": 0.23271222742588785, "entityId": "Q889", "indocChainId": 2, "mention": "Afghanistan" } ], "requestId": "8e106556-7bf6-4dbf-82e5-393d4cdebaee", "timers": { "rblJe": 2, "res": 188, "rexJe": 4, "rliJe": 13 } } python-0.7.4/tests/mock-data/response/eng-sentence-entities_linked.status 0000664 0000000 0000000 00000000003 12636317025 0026671 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/eng-sentence-language.json 0000664 0000000 0000000 00000001023 12636317025 0024733 0 ustar 00root root 0000000 0000000 { "languageDetections": [ { "confidence": 0.028765618006176497, "language": "eng" }, { "confidence": 0.004481894946904208, "language": "nld" }, { "confidence": 0.0036288946024011226, "language": "ita" }, { "confidence": 0.0034046431861963766, "language": "nor" }, { "confidence": 0.0033029370995759644, "language": "fra" } ], "requestId": "80dd91b6-26cd-4c42-99b6-6ee6cbaf7ad5", "timers": { "rliJe": 14 } } python-0.7.4/tests/mock-data/response/eng-sentence-language.status 0000664 0000000 0000000 00000000003 12636317025 0025302 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/eng-sentence-morphology_complete.json 0000664 0000000 0000000 00000014304 12636317025 0027245 0 ustar 00root root 0000000 0000000 { "compounds": [], "hanReadings": [], "lemmas": [ { "lemma": "he", "text": "He" }, { "lemma": "also", "text": "also" }, { "lemma": "acknowledge", "text": "acknowledged" }, { "lemma": "the", "text": "the" }, { "lemma": "ongoing", "text": "ongoing" }, { "lemma": "U.S.", "text": "U.S." }, { "lemma": "conflict", "text": "conflicts" }, { "lemma": "in", "text": "in" }, { "lemma": "Iraq", "text": "Iraq" }, { "lemma": "and", "text": "and" }, { "lemma": "Afghanistan", "text": "Afghanistan" }, { "lemma": ",", "text": "," }, { "lemma": "note", "text": "noting" }, { "lemma": "that", "text": "that" }, { "lemma": "he", "text": "he" }, { "lemma": "be", "text": "is" }, { "lemma": "the", "text": "the" }, { "lemma": "\"", "text": "\"" }, { "lemma": "commander", "text": "commander" }, { "lemma": "in", "text": "in" }, { "lemma": "chief", "text": "chief" }, { "lemma": "of", "text": "of" }, { "lemma": "a", "text": "a" }, { "lemma": "country", "text": "country" }, { "lemma": "that", "text": "that" }, { "lemma": "be", "text": "is" }, { "lemma": "responsible", "text": "responsible" }, { "lemma": "for", "text": "for" }, { "lemma": "end", "text": "ending" }, { "lemma": "a", "text": "a" }, { "lemma": "war", "text": "war" }, { "lemma": "and", "text": "and" }, { "lemma": "working", "text": "working" }, { "lemma": "in", "text": "in" }, { "lemma": "another", "text": "another" }, { "lemma": "theater", "text": "theater" }, { "lemma": "to", "text": "to" }, { "lemma": "confront", "text": "confront" }, { "lemma": "a", "text": "a" }, { "lemma": "ruthless", "text": "ruthless" }, { "lemma": "adversary", "text": "adversary" }, { "lemma": "that", "text": "that" }, { "lemma": "directly", "text": "directly" }, { "lemma": "threaten", "text": "threatens" }, { "lemma": "the", "text": "the" }, { "lemma": "American", "text": "American" }, { "lemma": "people", "text": "people" }, { "lemma": "\"", "text": "\"" }, { "lemma": "and", "text": "and" }, { "lemma": "U.S.", "text": "U.S." }, { "lemma": "ally", "text": "allies" }, { "lemma": ".", "text": "." } ], "posTags": [ { "pos": "PRONPERS", "text": "He" }, { "pos": "ADV", "text": "also" }, { "pos": "VPAST", "text": "acknowledged" }, { "pos": "DET", "text": "the" }, { "pos": "ADJ", "text": "ongoing" }, { "pos": "PROP", "text": "U.S." }, { "pos": "NOUN", "text": "conflicts" }, { "pos": "PREP", "text": "in" }, { "pos": "PROP", "text": "Iraq" }, { "pos": "COORD", "text": "and" }, { "pos": "PROP", "text": "Afghanistan" }, { "pos": "CM", "text": "," }, { "pos": "PARTPRES", "text": "noting" }, { "pos": "COSUB", "text": "that" }, { "pos": "PRONPERS", "text": "he" }, { "pos": "VBPRES", "text": "is" }, { "pos": "DET", "text": "the" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "NOUN", "text": "commander" }, { "pos": "PREP", "text": "in" }, { "pos": "ADJ", "text": "chief" }, { "pos": "PREP", "text": "of" }, { "pos": "DET", "text": "a" }, { "pos": "NOUN", "text": "country" }, { "pos": "PRONREL", "text": "that" }, { "pos": "VBPRES", "text": "is" }, { "pos": "ADJ", "text": "responsible" }, { "pos": "PREP", "text": "for" }, { "pos": "PARTPRES", "text": "ending" }, { "pos": "DET", "text": "a" }, { "pos": "NOUN", "text": "war" }, { "pos": "COORD", "text": "and" }, { "pos": "NOUNING", "text": "working" }, { "pos": "PREP", "text": "in" }, { "pos": "DET", "text": "another" }, { "pos": "NOUN", "text": "theater" }, { "pos": "INFTO", "text": "to" }, { "pos": "VI", "text": "confront" }, { "pos": "DET", "text": "a" }, { "pos": "ADJ", "text": "ruthless" }, { "pos": "NOUN", "text": "adversary" }, { "pos": "COSUB", "text": "that" }, { "pos": "ADV", "text": "directly" }, { "pos": "VPRES", "text": "threatens" }, { "pos": "DET", "text": "the" }, { "pos": "ADJ", "text": "American" }, { "pos": "NOUN", "text": "people" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "COORD", "text": "and" }, { "pos": "PROP", "text": "U.S." }, { "pos": "NOUN", "text": "allies" }, { "pos": "SENT", "text": "." } ], "requestId": "a635d13f-4e4f-444c-9396-92efab9a6b78", "timers": { "rblJe": 3, "rliJe": 20 } } python-0.7.4/tests/mock-data/response/eng-sentence-morphology_complete.status 0000664 0000000 0000000 00000000003 12636317025 0027606 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/eng-sentence-relationships.json 0000664 0000000 0000000 00000000471 12636317025 0026042 0 ustar 00root root 0000000 0000000 { "requestId": "eaee652e-a6bf-4a32-a159-0a612d2c080a", "relationships": [ { "predicate": "were", "arg1": "The first men to reach the moon", "arg2": "Mr. Armstrong" }, { "predicate": "is", "arg1": "were Mr. Armstrong", "arg2": "Col. Edwin E. Aldrin" } ] } python-0.7.4/tests/mock-data/response/eng-sentence-relationships.status 0000664 0000000 0000000 00000000004 12636317025 0026404 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/eng-sentence-sentiment.json 0000664 0000000 0000000 00000000454 12636317025 0025165 0 ustar 00root root 0000000 0000000 { "requestId": "edf8d7f7-b99b-4b8d-9407-985439d4929c", "sentiment": [ { "confidence": 0.6363532196732291, "label": "pos" }, { "confidence": 0.36364678032677095, "label": "neg" } ], "timers": { "rblJe": 2, "rliJe": 12, "sent": 2 } } python-0.7.4/tests/mock-data/response/eng-sentence-sentiment.status 0000664 0000000 0000000 00000000003 12636317025 0025525 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/eng-url-categories.json 0000664 0000000 0000000 00000000463 12636317025 0024302 0 ustar 00root root 0000000 0000000 { "categories": [ { "confidence": 0.2761922221442117, "label": "LAW_GOVERNMENT_AND_POLITICS" } ], "requestId": "b9aa3bdd-9ebe-4d11-a29d-2bad619c0ae4", "timers": { "cat": 25, "rblJe": 6, "rliJe": 5, "textExtractor": 16, "urlContentDownloader": 101 } } python-0.7.4/tests/mock-data/response/eng-url-categories.status 0000664 0000000 0000000 00000000003 12636317025 0024642 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/eng-url-entities.json 0000664 0000000 0000000 00000020110 12636317025 0023770 0 ustar 00root root 0000000 0000000 { "entities": [ { "confidence": 1.0, "count": 18, "indocChainId": 4, "mention": "Nike", "normalized": "Nike", "type": "ORGANIZATION" }, { "confidence": 0.026053469628095627, "count": 16, "indocChainId": 6, "mention": "Obama", "normalized": "Obama", "type": "PERSON" }, { "confidence": 0.0356166809797287, "count": 8, "indocChainId": 5, "mention": "President", "normalized": "President", "type": "TITLE" }, { "confidence": 1.0, "count": 4, "indocChainId": 23, "mention": "USA", "normalized": "USA", "type": "LOCATION" }, { "confidence": 1.0, "count": 4, "indocChainId": 35, "mention": "American", "normalized": "American", "type": "NATIONALITY" }, { "confidence": 1.0, "count": 3, "indocChainId": 9, "mention": "Facebook", "normalized": "Facebook", "type": "ORGANIZATION" }, { "confidence": 1.0, "count": 3, "indocChainId": 43, "mention": "Vietnam", "normalized": "Vietnam", "type": "LOCATION" }, { "confidence": 1.0, "count": 2, "indocChainId": 1, "mention": "Twitter", "normalized": "Twitter", "type": "ORGANIZATION" }, { "confidence": 1.0, "count": 2, "indocChainId": 17, "mention": "http://usat.ly/1bDiUq2", "normalized": "http://usat.ly/1bDiUq2", "type": "IDENTIFIER:URL" }, { "confidence": 0.016632944345474243, "count": 2, "indocChainId": 31, "mention": "AP", "normalized": "AP", "type": "ORGANIZATION" }, { "confidence": 0.01539921760559082, "count": 2, "indocChainId": 34, "mention": "Pacific", "normalized": "Pacific", "type": "LOCATION" }, { "confidence": 1.0, "count": 2, "indocChainId": 54, "mention": "U.S.", "normalized": "U.S.", "type": "LOCATION" }, { "confidence": 0.020548731088638306, "count": 2, "indocChainId": 56, "mention": "Congress", "normalized": "Congress", "type": "ORGANIZATION" }, { "confidence": 0.03334552049636841, "count": 2, "indocChainId": 73, "mention": "Democratic", "normalized": "Democratic", "type": "ORGANIZATION" }, { "confidence": 0.022478938102722168, "count": 2, "indocChainId": 74, "mention": "White House", "normalized": "White House", "type": "ORGANIZATION" }, { "confidence": 0.0002225041389465332, "count": 1, "indocChainId": 0, "mention": "City, State", "normalized": "City, State", "type": "LOCATION" }, { "confidence": 1.0, "count": 1, "indocChainId": 2, "mention": "Google", "normalized": "Google", "type": "ORGANIZATION" }, { "confidence": 1.0, "count": 1, "indocChainId": 3, "mention": "LinkedIn", "normalized": "LinkedIn", "type": "ORGANIZATION" }, { "confidence": 1.0, "count": 1, "indocChainId": 16, "mention": "USATODAY.com", "normalized": "USATODAY.com", "type": "IDENTIFIER:URL" }, { "confidence": 0.01601588726043701, "count": 1, "indocChainId": 22, "mention": "Gregory Korte", "normalized": "Gregory Korte", "type": "PERSON" }, { "confidence": 1.0, "count": 1, "indocChainId": 27, "mention": "Ore.", "normalized": "Ore.", "type": "LOCATION" }, { "confidence": 0.023429572582244873, "count": 1, "indocChainId": 29, "mention": "Democrats", "normalized": "Democrats", "type": "ORGANIZATION" }, { "confidence": 0.009600162506103516, "count": 1, "indocChainId": 30, "mention": "Pablo Martinez Monsivais", "normalized": "Pablo Martinez Monsivais", "type": "PERSON" }, { "confidence": 1.0, "count": 1, "indocChainId": 39, "mention": "Vermont", "normalized": "Vermont", "type": "LOCATION" }, { "confidence": 0.01797032356262207, "count": 1, "indocChainId": 40, "mention": "Sen.", "normalized": "Sen.", "type": "TITLE" }, { "confidence": 0.029442191123962402, "count": 1, "indocChainId": 41, "mention": "Bernie Sanders", "normalized": "Bernie Sanders", "type": "PERSON" }, { "confidence": 1.0, "count": 1, "indocChainId": 49, "mention": "Portland", "normalized": "Portland", "type": "LOCATION" }, { "confidence": 0.0008523464202880859, "count": 1, "indocChainId": 51, "mention": "Senate", "normalized": "Senate", "type": "ORGANIZATION" }, { "confidence": 1.0, "count": 1, "indocChainId": 54, "mention": "United States", "normalized": "United States", "type": "LOCATION" }, { "confidence": 0.02184152603149414, "count": 1, "indocChainId": 60, "mention": "Parker", "normalized": "Parker", "type": "PERSON" }, { "confidence": 0.027263343334197998, "count": 1, "indocChainId": 60, "mention": "Mark Parker", "normalized": "Mark Parker", "type": "PERSON" }, { "confidence": 0.07037776708602905, "count": 1, "indocChainId": 65, "mention": "Eric Hauser", "normalized": "Eric Hauser", "type": "PERSON" }, { "confidence": 0.017060577869415283, "count": 1, "indocChainId": 66, "mention": "AFL-CIO", "normalized": "AFL-CIO", "type": "ORGANIZATION" }, { "confidence": 0.021783530712127686, "count": 1, "indocChainId": 71, "mention": "Clinton", "normalized": "Clinton", "type": "PERSON" }, { "confidence": 0.01363682746887207, "count": 1, "indocChainId": 75, "mention": "Trans-Pacific", "normalized": "Trans-Pacific", "type": "LOCATION" }, { "confidence": 0.00797349214553833, "count": 1, "indocChainId": 84, "mention": "TPP", "normalized": "TPP", "type": "ORGANIZATION" }, { "confidence": 0.025950074195861816, "count": 1, "indocChainId": 85, "mention": "Murshed Zaheed", "normalized": "Murshed Zaheed", "type": "PERSON" }, { "confidence": 0.0026077628135681152, "count": 1, "indocChainId": 86, "mention": "Credo Action", "normalized": "Credo Action", "type": "ORGANIZATION" }, { "confidence": 0.03961271047592163, "count": 1, "indocChainId": 88, "mention": "Asia", "normalized": "Asia", "type": "LOCATION" }, { "confidence": 0.022504746913909912, "count": 1, "indocChainId": 90, "mention": "Sentinel Hotel", "normalized": "Sentinel Hotel", "type": "LOCATION" }, { "confidence": 0.019158661365509033, "count": 1, "indocChainId": 94, "mention": "Thomas Boyd", "normalized": "Thomas Boyd", "type": "PERSON" }, { "confidence": 0.012987256050109863, "count": 1, "indocChainId": 98, "mention": "Michael Wolff", "normalized": "Michael Wolff", "type": "PERSON" }, { "confidence": 1.0, "count": 1, "indocChainId": 99, "mention": "Britain", "normalized": "Britain", "type": "LOCATION" } ], "requestId": "20cc0667-b5d1-45ca-8649-388b42695ed6", "timers": { "rblJe": 6, "rexJe": 194, "rliJe": 6, "textExtractor": 14, "urlContentDownloader": 117 } } python-0.7.4/tests/mock-data/response/eng-url-entities.status 0000664 0000000 0000000 00000000003 12636317025 0024341 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/eng-url-entities_linked.json 0000664 0000000 0000000 00000012216 12636317025 0025326 0 ustar 00root root 0000000 0000000 { "entities": [ { "confidence": 0.09260963387673546, "entityId": "NEW-CLUSTER", "indocChainId": 0, "mention": "City, State" }, { "confidence": 0.7363573634794515, "entityId": "Q918", "indocChainId": 1, "mention": "Twitter" }, { "confidence": 0.8558907150896853, "entityId": "Q95", "indocChainId": 2, "mention": "Google" }, { "confidence": 0.7989502467143261, "entityId": "Q213660", "indocChainId": 3, "mention": "LinkedIn" }, { "confidence": 0.6261777456363734, "entityId": "Q165023", "indocChainId": 4, "mention": "Nike" }, { "confidence": 0.580918930055919, "entityId": "Q76", "indocChainId": 6, "mention": "Obama" }, { "confidence": 0.8198021796089213, "entityId": "Q355", "indocChainId": 9, "mention": "Facebook" }, { "confidence": 0.48472828194168266, "entityId": "NEW-CLUSTER", "indocChainId": 22, "mention": "Gregory Korte" }, { "confidence": 0.934688817800125, "entityId": "Q30", "indocChainId": 23, "mention": "USA" }, { "confidence": 0.6674546995482082, "entityId": "Q824", "indocChainId": 27, "mention": "Ore." }, { "confidence": 0.47112052899963985, "entityId": "Q29552", "indocChainId": 29, "mention": "Democrats" }, { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 30, "mention": "Pablo Martinez Monsivais" }, { "confidence": 0.2034163102133998, "entityId": "Q40469", "indocChainId": 31, "mention": "AP" }, { "confidence": 0.15449450932471964, "entityId": "Q98", "indocChainId": 34, "mention": "Pacific" }, { "confidence": 0.23079330313599078, "entityId": "Q16551", "indocChainId": 39, "mention": "Vermont" }, { "confidence": 0.8339844509143421, "entityId": "Q359442", "indocChainId": 41, "mention": "Bernie Sanders" }, { "confidence": 0.2171907026020583, "entityId": "Q881", "indocChainId": 43, "mention": "Vietnam" }, { "confidence": 0.052853329084155916, "entityId": "Q6106", "indocChainId": 49, "mention": "Portland" }, { "confidence": 0.06500005510445091, "entityId": "Q66096", "indocChainId": 51, "mention": "Senate" }, { "confidence": 0.4966018948670623, "entityId": "Q30", "indocChainId": 54, "mention": "United States" }, { "confidence": 0.12517966475058961, "entityId": "Q11268", "indocChainId": 56, "mention": "Congress" }, { "confidence": 0.5401864536008631, "entityId": "Q1900344", "indocChainId": 60, "mention": "Mark Parker" }, { "confidence": 0.3672055307109911, "entityId": "NEW-CLUSTER", "indocChainId": 65, "mention": "Eric Hauser" }, { "confidence": 0.8073673635923817, "entityId": "Q464271", "indocChainId": 66, "mention": "AFL-CIO" }, { "confidence": 0.0754921314204974, "entityId": "Q1124", "indocChainId": 71, "mention": "Clinton" }, { "confidence": 0.8733602619662788, "entityId": "Q29552", "indocChainId": 73, "mention": "Democratic" }, { "confidence": 0.2071496461994983, "entityId": "Q35525", "indocChainId": 74, "mention": "White House" }, { "confidence": 0.1337796168379229, "entityId": "NEW-CLUSTER", "indocChainId": 75, "mention": "Trans-Pacific" }, { "confidence": 0.3347718004129003, "entityId": "NEW-CLUSTER", "indocChainId": 84, "mention": "TPP" }, { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 85, "mention": "Murshed Zaheed" }, { "confidence": 0.4449559756113517, "entityId": "NEW-CLUSTER", "indocChainId": 86, "mention": "Credo Action" }, { "confidence": 0.20568806272114726, "entityId": "Q48", "indocChainId": 88, "mention": "Asia" }, { "confidence": 0.5279031985169756, "entityId": "NEW-CLUSTER", "indocChainId": 90, "mention": "Sentinel Hotel" }, { "confidence": 0.2557855226598088, "entityId": "NEW-CLUSTER", "indocChainId": 94, "mention": "Thomas Boyd" }, { "confidence": 0.3050614695591455, "entityId": "Q439955", "indocChainId": 98, "mention": "Michael Wolff" }, { "confidence": 0.21278551689928094, "entityId": "Q145", "indocChainId": 99, "mention": "Britain" } ], "requestId": "5de2e00b-efcd-4fd0-a404-f9629dc60619", "timers": { "rblJe": 7, "res": 1408, "rexJe": 68, "rliJe": 5, "textExtractor": 19, "urlContentDownloader": 103 } } python-0.7.4/tests/mock-data/response/eng-url-entities_linked.status 0000664 0000000 0000000 00000000003 12636317025 0025667 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/eng-url-language.json 0000664 0000000 0000000 00000001113 12636317025 0023731 0 ustar 00root root 0000000 0000000 { "languageDetections": [ { "confidence": 0.03778571148423149, "language": "eng" }, { "confidence": 0.004662049438325155, "language": "ita" }, { "confidence": 0.004196223037494229, "language": "fra" }, { "confidence": 0.004017692353779911, "language": "ron" }, { "confidence": 0.0036722928060302085, "language": "nor" } ], "requestId": "7174fbf8-a58e-4ec4-9ac4-92fee2bd5b40", "timers": { "rliJe": 5, "textExtractor": 20, "urlContentDownloader": 159 } } python-0.7.4/tests/mock-data/response/eng-url-language.status 0000664 0000000 0000000 00000000003 12636317025 0024300 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/eng-url-morphology_complete.json 0000664 0000000 0000000 00000400456 12636317025 0026252 0 ustar 00root root 0000000 0000000 { "compounds": [], "hanReadings": [], "lemmas": [ { "lemma": "enter", "text": "Enter" }, { "lemma": "City", "text": "City" }, { "lemma": ",", "text": "," }, { "lemma": "State", "text": "State" }, { "lemma": "or", "text": "or" }, { "lemma": "zip", "text": "Zip" }, { "lemma": "cancel", "text": "Cancel" }, { "lemma": "logarithm", "text": "Log" }, { "lemma": "out", "text": "out" }, { "lemma": "sign", "text": "Sign" }, { "lemma": "in", "text": "In" }, { "lemma": "FAQ", "text": "FAQ" }, { "lemma": "get", "text": "Get" }, { "lemma": "the", "text": "the" }, { "lemma": "news", "text": "news" }, { "lemma": "FacebookEmail", "text": "FacebookEmail" }, { "lemma": "twitter", "text": "Twitter" }, { "lemma": "Google", "text": "Google" }, { "lemma": "+", "text": "+" }, { "lemma": "LinkedIn", "text": "LinkedIn" }, { "lemma": "Pinterest", "text": "Pinterest" }, { "lemma": "Obama", "text": "Obama" }, { "lemma": ",", "text": "," }, { "lemma": "at", "text": "at" }, { "lemma": "Nike", "text": "Nike" }, { "lemma": "HQ", "text": "HQ" }, { "lemma": ",", "text": "," }, { "lemma": "make", "text": "makes" }, { "lemma": "progressive", "text": "progressive" }, { "lemma": "case", "text": "case" }, { "lemma": "for", "text": "for" }, { "lemma": "trade", "text": "trade" }, { "lemma": "President", "text": "President" }, { "lemma": "Obama", "text": "Obama" }, { "lemma": "take", "text": "took" }, { "lemma": "he", "text": "his" }, { "lemma": "campaign", "text": "campaign" }, { "lemma": "for", "text": "for" }, { "lemma": "a", "text": "a" }, { "lemma": "free", "text": "free" }, { "lemma": "trade", "text": "trade" }, { "lemma": "deal", "text": "deal" }, { "lemma": "to", "text": "to" }, { "lemma": "the", "text": "the" }, { "lemma": "world", "text": "world" }, { "lemma": "headquarters", "text": "headquarters" }, { "lemma": "of", "text": "of" }, { "lemma": "Nike", "text": "Nike" }, { "lemma": "Friday", "text": "Friday" }, { "lemma": ",", "text": "," }, { "lemma": "where", "text": "where" }, { "lemma": "he", "text": "he" }, { "lemma": "have", "text": "'s" }, { "lemma": "extract", "text": "extracted" }, { "lemma": "a", "text": "a" }, { "lemma": "pledge", "text": "pledge" }, { "lemma": "from", "text": "from" }, { "lemma": "the", "text": "the" }, { "lemma": "world", "text": "world" }, { "lemma": "'s", "text": "'s" }, { "lemma": "large", "text": "largest" }, { "lemma": "athletic", "text": "athletic" }, { "lemma": "shoe", "text": "shoe" }, { "lemma": "company", "text": "company" }, { "lemma": "that", "text": "that" }, { "lemma": "it", "text": "it" }, { "lemma": "will", "text": "will" }, { "lemma": "add", "text": "add" }, { "lemma": "10000", "text": "10,000" }, { "lemma": "U.S.", "text": "U.S." }, { "lemma": "job", "text": "jobs" }, { "lemma": ".", "text": "." }, { "lemma": "post", "text": "Post" }, { "lemma": "to", "text": "to" }, { "lemma": "Facebook", "text": "Facebook" }, { "lemma": "Obama", "text": "Obama" }, { "lemma": ",", "text": "," }, { "lemma": "at", "text": "at" }, { "lemma": "Nike", "text": "Nike" }, { "lemma": "HQ", "text": "HQ" }, { "lemma": ",", "text": "," }, { "lemma": "make", "text": "makes" }, { "lemma": "progressive", "text": "progressive" }, { "lemma": "case", "text": "case" }, { "lemma": "for", "text": "for" }, { "lemma": "trade", "text": "trade" }, { "lemma": "President", "text": "President" }, { "lemma": "Obama", "text": "Obama" }, { "lemma": "take", "text": "took" }, { "lemma": "he", "text": "his" }, { "lemma": "campaign", "text": "campaign" }, { "lemma": "for", "text": "for" }, { "lemma": "a", "text": "a" }, { "lemma": "free", "text": "free" }, { "lemma": "trade", "text": "trade" }, { "lemma": "deal", "text": "deal" }, { "lemma": "to", "text": "to" }, { "lemma": "the", "text": "the" }, { "lemma": "world", "text": "world" }, { "lemma": "headquarters", "text": "headquarters" }, { "lemma": "of", "text": "of" }, { "lemma": "Nike", "text": "Nike" }, { "lemma": "Friday", "text": "Friday" }, { "lemma": ",", "text": "," }, { "lemma": "where", "text": "where" }, { "lemma": "he", "text": "he" }, { "lemma": "have", "text": "'s" }, { "lemma": "extract", "text": "extracted" }, { "lemma": "a", "text": "a" }, { "lemma": "pledge", "text": "pledge" }, { "lemma": "from", "text": "from" }, { "lemma": "the", "text": "the" }, { "lemma": "world", "text": "world" }, { "lemma": "'s", "text": "'s" }, { "lemma": "large", "text": "largest" }, { "lemma": "athletic", "text": "athletic" }, { "lemma": "shoe", "text": "shoe" }, { "lemma": "company", "text": "company" }, { "lemma": "that", "text": "that" }, { "lemma": "it", "text": "it" }, { "lemma": "will", "text": "will" }, { "lemma": "add", "text": "add" }, { "lemma": "10000", "text": "10,000" }, { "lemma": "U.S.", "text": "U.S." }, { "lemma": "job", "text": "jobs" }, { "lemma": ".", "text": "." }, { "lemma": "check", "text": "Check" }, { "lemma": "out", "text": "out" }, { "lemma": "this", "text": "this" }, { "lemma": "story", "text": "story" }, { "lemma": "on", "text": "on" }, { "lemma": "USATODAY.com", "text": "USATODAY.com" }, { "lemma": ":", "text": ":" }, { "lemma": "http", "text": "http" }, { "lemma": ":", "text": ":" }, { "lemma": "/", "text": "/" }, { "lemma": "/", "text": "/" }, { "lemma": "usat.ly", "text": "usat.ly" }, { "lemma": "/", "text": "/" }, { "lemma": "1bDiUq2", "text": "1bDiUq2" }, { "lemma": "{", "text": "{" }, { "lemma": "#", "text": "#" }, { "lemma": "#", "text": "#" }, { "lemma": "}", "text": "}" }, { "lemma": "CancelSend", "text": "CancelSend" }, { "lemma": "a", "text": "A" }, { "lemma": "link", "text": "link" }, { "lemma": "have", "text": "has" }, { "lemma": "be", "text": "been" }, { "lemma": "send", "text": "sent" }, { "lemma": "to", "text": "to" }, { "lemma": "you", "text": "your" }, { "lemma": "friend", "text": "friend" }, { "lemma": "'s", "text": "'s" }, { "lemma": "email", "text": "email" }, { "lemma": "address", "text": "address" }, { "lemma": ".", "text": "." }, { "lemma": "post", "text": "Posted" }, { "lemma": "!", "text": "!" }, { "lemma": "a", "text": "A" }, { "lemma": "link", "text": "link" }, { "lemma": "have", "text": "has" }, { "lemma": "be", "text": "been" }, { "lemma": "post", "text": "posted" }, { "lemma": "to", "text": "to" }, { "lemma": "you", "text": "your" }, { "lemma": "facebook", "text": "Facebook" }, { "lemma": "feed", "text": "feed" }, { "lemma": ".", "text": "." }, { "lemma": "54", "text": "54" }, { "lemma": "to", "text": "To" }, { "lemma": "find", "text": "find" }, { "lemma": "out", "text": "out" }, { "lemma": "more", "text": "more" }, { "lemma": "about", "text": "about" }, { "lemma": "Facebook", "text": "Facebook" }, { "lemma": "comment", "text": "commenting" }, { "lemma": "please", "text": "please" }, { "lemma": "read", "text": "read" }, { "lemma": "the", "text": "the" }, { "lemma": "conversation", "text": "Conversation" }, { "lemma": "guideline", "text": "Guidelines" }, { "lemma": "and", "text": "and" }, { "lemma": "FAQs", "text": "FAQs" }, { "lemma": "Obama", "text": "Obama" }, { "lemma": ",", "text": "," }, { "lemma": "at", "text": "at" }, { "lemma": "Nike", "text": "Nike" }, { "lemma": "HQ", "text": "HQ" }, { "lemma": ",", "text": "," }, { "lemma": "make", "text": "makes" }, { "lemma": "progressive", "text": "progressive" }, { "lemma": "case", "text": "case" }, { "lemma": "for", "text": "for" }, { "lemma": "trade", "text": "trade" }, { "lemma": "Gregory", "text": "Gregory" }, { "lemma": "Korte", "text": "Korte" }, { "lemma": ",", "text": "," }, { "lemma": "USA", "text": "USA" }, { "lemma": "today", "text": "TODAY" }, { "lemma": "2:25", "text": "2:25" }, { "lemma": "p.m.", "text": "p.m." }, { "lemma": "EDT", "text": "EDT" }, { "lemma": "May", "text": "May" }, { "lemma": "8", "text": "8" }, { "lemma": ",", "text": "," }, { "lemma": "2015", "text": "2015" }, { "lemma": "president", "text": "President" }, { "lemma": "Obama", "text": "Obama" }, { "lemma": "take", "text": "takes" }, { "lemma": "the", "text": "the" }, { "lemma": "stage", "text": "stage" }, { "lemma": "before", "text": "before" }, { "lemma": "speak", "text": "speaking" }, { "lemma": "at", "text": "at" }, { "lemma": "Nike", "text": "Nike" }, { "lemma": "headquarters", "text": "headquarters" }, { "lemma": "in", "text": "in" }, { "lemma": "Beaverton", "text": "Beaverton" }, { "lemma": ",", "text": "," }, { "lemma": "Ore.", "text": "Ore." }, { "lemma": "Friday", "text": "Friday" }, { "lemma": ".", "text": "." }, { "lemma": "Obama", "text": "Obama" }, { "lemma": "visit", "text": "visited" }, { "lemma": "the", "text": "the" }, { "lemma": "giant", "text": "giant" }, { "lemma": "athletic", "text": "athletic" }, { "lemma": "apparel", "text": "apparel" }, { "lemma": "company", "text": "company" }, { "lemma": "to", "text": "to" }, { "lemma": "make", "text": "make" }, { "lemma": "he", "text": "his" }, { "lemma": "trade", "text": "trade" }, { "lemma": "policy", "text": "policy" }, { "lemma": "pitch", "text": "pitch" }, { "lemma": "as", "text": "as" }, { "lemma": "he", "text": "he" }, { "lemma": "struggle", "text": "struggles" }, { "lemma": "to", "text": "to" }, { "lemma": "win", "text": "win" }, { "lemma": "over", "text": "over" }, { "lemma": "democrat", "text": "Democrats" }, { "lemma": "for", "text": "for" }, { "lemma": "what", "text": "what" }, { "lemma": "could", "text": "could" }, { "lemma": "be", "text": "be" }, { "lemma": "the", "text": "the" }, { "lemma": "last", "text": "last" }, { "lemma": "major", "text": "major" }, { "lemma": "legislative", "text": "legislative" }, { "lemma": "push", "text": "push" }, { "lemma": "of", "text": "of" }, { "lemma": "he", "text": "his" }, { "lemma": "presidency", "text": "presidency" }, { "lemma": ".", "text": "." }, { "lemma": "(", "text": "(" }, { "lemma": "photo", "text": "Photo" }, { "lemma": ":", "text": ":" }, { "lemma": "Pablo", "text": "Pablo" }, { "lemma": "Martinez", "text": "Martinez" }, { "lemma": "Monsivais", "text": "Monsivais" }, { "lemma": ",", "text": "," }, { "lemma": "AP", "text": "AP" }, { "lemma": ")", "text": ")" }, { "lemma": "438", "text": "438" }, { "lemma": "connect", "text": "CONNECT" }, { "lemma": "142", "text": "142" }, { "lemma": "tweet", "text": "TWEET" }, { "lemma": "18", "text": "18" }, { "lemma": "LINKEDIN", "text": "LINKEDIN" }, { "lemma": "54", "text": "54" }, { "lemma": "COMMENTEMAILMORE", "text": "COMMENTEMAILMORE" }, { "lemma": "President", "text": "President" }, { "lemma": "Obama", "text": "Obama" }, { "lemma": "dress", "text": "dressed" }, { "lemma": "he", "text": "his" }, { "lemma": "campaign", "text": "campaign" }, { "lemma": "for", "text": "for" }, { "lemma": "free", "text": "free" }, { "lemma": "trade", "text": "trade" }, { "lemma": "in", "text": "in" }, { "lemma": "the", "text": "the" }, { "lemma": "clothing", "text": "clothing" }, { "lemma": "of", "text": "of" }, { "lemma": "\"", "text": "\"" }, { "lemma": "middle", "text": "middle" }, { "lemma": "class", "text": "class" }, { "lemma": "economics", "text": "economics" }, { "lemma": "\"", "text": "\"" }, { "lemma": "Friday", "text": "Friday" }, { "lemma": ",", "text": "," }, { "lemma": "appeal", "text": "appealing" }, { "lemma": "to", "text": "to" }, { "lemma": "he", "text": "his" }, { "lemma": "liberal", "text": "liberal" }, { "lemma": "base", "text": "base" }, { "lemma": "to", "text": "to" }, { "lemma": "support", "text": "support" }, { "lemma": "a", "text": "a" }, { "lemma": "pacific", "text": "Pacific" }, { "lemma": "trade", "text": "trade" }, { "lemma": "deal", "text": "deal" }, { "lemma": "he", "text": "he" }, { "lemma": "say", "text": "said" }, { "lemma": "would", "text": "would" }, { "lemma": "help", "text": "help" }, { "lemma": "American", "text": "American" }, { "lemma": "worker", "text": "workers" }, { "lemma": ".", "text": "." }, { "lemma": "speak", "text": "Speaking" }, { "lemma": "at", "text": "at" }, { "lemma": "the", "text": "the" }, { "lemma": "world", "text": "world" }, { "lemma": "headquarters", "text": "headquarters" }, { "lemma": "of", "text": "of" }, { "lemma": "Nike", "text": "Nike" }, { "lemma": "Friday", "text": "Friday" }, { "lemma": ",", "text": "," }, { "lemma": "Obama", "text": "Obama" }, { "lemma": "cast", "text": "cast" }, { "lemma": "free", "text": "free" }, { "lemma": "trade", "text": "trade" }, { "lemma": "in", "text": "in" }, { "lemma": "the", "text": "the" }, { "lemma": "same", "text": "same" }, { "lemma": "term", "text": "terms" }, { "lemma": "as", "text": "as" }, { "lemma": "he", "text": "his" }, { "lemma": "effort", "text": "efforts" }, { "lemma": "to", "text": "to" }, { "lemma": "pass", "text": "pass" }, { "lemma": "universal", "text": "universal" }, { "lemma": "health", "text": "health" }, { "lemma": "care", "text": "care" }, { "lemma": ",", "text": "," }, { "lemma": "adopt", "text": "adopt" }, { "lemma": "clean", "text": "clean" }, { "lemma": "energy", "text": "energy" }, { "lemma": "and", "text": "and" }, { "lemma": "raise", "text": "raise" }, { "lemma": "the", "text": "the" }, { "lemma": "minimum", "text": "minimum" }, { "lemma": "wage", "text": "wage" }, { "lemma": ".", "text": "." }, { "lemma": "\"", "text": "\"" }, { "lemma": "passing", "text": "Passing" }, { "lemma": "trade", "text": "trade" }, { "lemma": "agreement", "text": "agreements" }, { "lemma": "be", "text": "is" }, { "lemma": "part", "text": "part" }, { "lemma": "of", "text": "of" }, { "lemma": "that", "text": "that" }, { "lemma": "agenda", "text": "agenda" }, { "lemma": "—", "text": "—" }, { "lemma": "if", "text": "if" }, { "lemma": "those", "text": "those" }, { "lemma": "trade", "text": "trade" }, { "lemma": "agreement", "text": "agreements" }, { "lemma": "be", "text": "are" }, { "lemma": "the", "text": "the" }, { "lemma": "right", "text": "right" }, { "lemma": "kind", "text": "kinds" }, { "lemma": "of", "text": "of" }, { "lemma": "trade", "text": "trade" }, { "lemma": "agreement", "text": "agreements" }, { "lemma": ",", "text": "," }, { "lemma": "\"", "text": "\"" }, { "lemma": "he", "text": "he" }, { "lemma": "say", "text": "said" }, { "lemma": ".", "text": "." }, { "lemma": "\"", "text": "\"" }, { "lemma": "like", "text": "Like" }, { "lemma": "other", "text": "other" }, { "lemma": "issue", "text": "issues" }, { "lemma": "we", "text": "we" }, { "lemma": "have", "text": "'ve" }, { "lemma": "wage", "text": "waged" }, { "lemma": "slow", "text": "slow" }, { "lemma": ",", "text": "," }, { "lemma": "steady", "text": "steady" }, { "lemma": "fight", "text": "fights" }, { "lemma": "on", "text": "on" }, { "lemma": "over", "text": "over" }, { "lemma": "the", "text": "the" }, { "lemma": "last", "text": "last" }, { "lemma": "seven", "text": "seven" }, { "lemma": "year", "text": "years" }, { "lemma": ",", "text": "," }, { "lemma": ".", "text": "." }, { "lemma": "this", "text": "this" }, { "lemma": "be", "text": "is" }, { "lemma": "also", "text": "also" }, { "lemma": "a", "text": "a" }, { "lemma": "question", "text": "question" }, { "lemma": "of", "text": "of" }, { "lemma": "the", "text": "the" }, { "lemma": "past", "text": "past" }, { "lemma": "versus", "text": "versus" }, { "lemma": "the", "text": "the" }, { "lemma": "present", "text": "present" }, { "lemma": ",", "text": "," }, { "lemma": "\"", "text": "\"" }, { "lemma": "he", "text": "he" }, { "lemma": "say", "text": "said" }, { "lemma": ".", "text": "." }, { "lemma": "but", "text": "But" }, { "lemma": "Obama", "text": "Obama" }, { "lemma": "make", "text": "made" }, { "lemma": "he", "text": "his" }, { "lemma": "case", "text": "case" }, { "lemma": "for", "text": "for" }, { "lemma": "free", "text": "free" }, { "lemma": "trade", "text": "trade" }, { "lemma": "at", "text": "at" }, { "lemma": "a", "text": "a" }, { "lemma": "company", "text": "company" }, { "lemma": "that", "text": "that" }, { "lemma": "many", "text": "many" }, { "lemma": "liberal", "text": "liberals" }, { "lemma": "—", "text": "—" }, { "lemma": "notably", "text": "notably" }, { "lemma": "Vermont", "text": "Vermont" }, { "lemma": "Senator", "text": "Sen." }, { "lemma": "Bernie", "text": "Bernie" }, { "lemma": "Sanders", "text": "Sanders" }, { "lemma": ",", "text": "," }, { "lemma": "a", "text": "a" }, { "lemma": "presidential", "text": "presidential" }, { "lemma": "candidate", "text": "candidate" }, { "lemma": "—", "text": "—" }, { "lemma": "see", "text": "see" }, { "lemma": "as", "text": "as" }, { "lemma": "a", "text": "a" }, { "lemma": "symbol", "text": "symbol" }, { "lemma": "of", "text": "of" }, { "lemma": "failed", "text": "failed" }, { "lemma": "trade", "text": "trade" }, { "lemma": "policy", "text": "policies" }, { "lemma": ".", "text": "." }, { "lemma": "Nike", "text": "Nike" }, { "lemma": ",", "text": "," }, { "lemma": "the", "text": "the" }, { "lemma": "world", "text": "world" }, { "lemma": "'s", "text": "'s" }, { "lemma": "large", "text": "largest" }, { "lemma": "athletic", "text": "athletic" }, { "lemma": "shoe", "text": "shoe" }, { "lemma": "manufacturer", "text": "manufacturer" }, { "lemma": ",", "text": "," }, { "lemma": "import", "text": "imports" }, { "lemma": "shoe", "text": "shoes" }, { "lemma": "from", "text": "from" }, { "lemma": "contract", "text": "contract" }, { "lemma": "factory", "text": "factories" }, { "lemma": "in", "text": "in" }, { "lemma": "place", "text": "places" }, { "lemma": "like", "text": "like" }, { "lemma": "Vietnam", "text": "Vietnam" }, { "lemma": ",", "text": "," }, { "lemma": "where", "text": "where" }, { "lemma": "the", "text": "the" }, { "lemma": "minimum", "text": "minimum" }, { "lemma": "wage", "text": "wage" }, { "lemma": "be", "text": "is" }, { "lemma": "56", "text": "56" }, { "lemma": "cent", "text": "cents" }, { "lemma": "an", "text": "an" }, { "lemma": "hour", "text": "hour" }, { "lemma": ".", "text": "." }, { "lemma": "Obama", "text": "Obama" }, { "lemma": "say", "text": "said" }, { "lemma": "Vietnam", "text": "Vietnam" }, { "lemma": ",", "text": "," }, { "lemma": "where", "text": "where" }, { "lemma": "330000", "text": "330,000" }, { "lemma": "worker", "text": "workers" }, { "lemma": "make", "text": "make" }, { "lemma": "Nike", "text": "Nike" }, { "lemma": "shoe", "text": "shoes" }, { "lemma": ",", "text": "," }, { "lemma": "would", "text": "would" }, { "lemma": "have", "text": "have" }, { "lemma": "to", "text": "to" }, { "lemma": "increase", "text": "increase" }, { "lemma": "the", "text": "the" }, { "lemma": "minimum", "text": "minimum" }, { "lemma": "wage", "text": "wage" }, { "lemma": ",", "text": "," }, { "lemma": "improve", "text": "improve" }, { "lemma": "working", "text": "working" }, { "lemma": "condition", "text": "conditions" }, { "lemma": "and", "text": "and" }, { "lemma": "even", "text": "even" }, { "lemma": "establish", "text": "establish" }, { "lemma": "the", "text": "the" }, { "lemma": "right", "text": "right" }, { "lemma": "of", "text": "of" }, { "lemma": "worker", "text": "workers" }, { "lemma": "to", "text": "to" }, { "lemma": "join", "text": "join" }, { "lemma": "a", "text": "a" }, { "lemma": "union", "text": "union" }, { "lemma": ".", "text": "." }, { "lemma": "\"", "text": "\"" }, { "lemma": "it", "text": "It" }, { "lemma": "do not", "text": "doesn't" }, { "lemma": "mean", "text": "mean" }, { "lemma": "that", "text": "that" }, { "lemma": "suddenly", "text": "suddenly" }, { "lemma": "working", "text": "working" }, { "lemma": "condition", "text": "conditions" }, { "lemma": "in", "text": "in" }, { "lemma": "Vietnam", "text": "Vietnam" }, { "lemma": "will", "text": "will" }, { "lemma": "be", "text": "be" }, { "lemma": "like", "text": "like" }, { "lemma": "they", "text": "they" }, { "lemma": "be", "text": "are" }, { "lemma": "here", "text": "here" }, { "lemma": "at", "text": "at" }, { "lemma": "Nike", "text": "Nike" }, { "lemma": ",", "text": "," }, { "lemma": "or", "text": "or" }, { "lemma": "here", "text": "here" }, { "lemma": "in", "text": "in" }, { "lemma": "Portland", "text": "Portland" }, { "lemma": "right", "text": "right" }, { "lemma": "away", "text": "away" }, { "lemma": ",", "text": "," }, { "lemma": "but", "text": "but" }, { "lemma": "it", "text": "it" }, { "lemma": "move", "text": "moves" }, { "lemma": "we", "text": "us" }, { "lemma": "in", "text": "in" }, { "lemma": "the", "text": "the" }, { "lemma": "right", "text": "right" }, { "lemma": "direction", "text": "direction" }, { "lemma": ",", "text": "," }, { "lemma": "\"", "text": "\"" }, { "lemma": "he", "text": "he" }, { "lemma": "say", "text": "said" }, { "lemma": ".", "text": "." }, { "lemma": "\"", "text": "\"" }, { "lemma": "if", "text": "If" }, { "lemma": "you", "text": "you" }, { "lemma": "be", "text": "'re" }, { "lemma": "a", "text": "a" }, { "lemma": "country", "text": "country" }, { "lemma": "that", "text": "that" }, { "lemma": "want", "text": "wants" }, { "lemma": "into", "text": "into" }, { "lemma": "this", "text": "this" }, { "lemma": "agreement", "text": "agreement" }, { "lemma": ",", "text": "," }, { "lemma": "you", "text": "you" }, { "lemma": "have", "text": "have" }, { "lemma": "to", "text": "to" }, { "lemma": "meet", "text": "meet" }, { "lemma": "high", "text": "higher" }, { "lemma": "standard", "text": "standards" }, { "lemma": ".", "text": "." }, { "lemma": "if", "text": "If" }, { "lemma": "you", "text": "you" }, { "lemma": "do not", "text": "don't" }, { "lemma": "you", "text": "you" }, { "lemma": "be", "text": "'re" }, { "lemma": "out", "text": "out" }, { "lemma": ".", "text": "." }, { "lemma": "\"", "text": "\"" }, { "lemma": "USA", "text": "USA" }, { "lemma": "today", "text": "TODAY" }, { "lemma": "senate", "text": "Senate" }, { "lemma": "panel", "text": "panel" }, { "lemma": "approve", "text": "approves" }, { "lemma": "'s", "text": "'" }, { "lemma": "fast", "text": "fast" }, { "lemma": "track", "text": "track" }, { "lemma": "'s", "text": "'" }, { "lemma": "trade", "text": "trade" }, { "lemma": "bill", "text": "bill" }, { "lemma": "at", "text": "At" }, { "lemma": "one", "text": "first" }, { "lemma": ",", "text": "," }, { "lemma": "Nike", "text": "Nike" }, { "lemma": "seem", "text": "seemed" }, { "lemma": "like", "text": "like" }, { "lemma": "an", "text": "an" }, { "lemma": "unlikely", "text": "unlikely" }, { "lemma": "venue", "text": "venue" }, { "lemma": "for", "text": "for" }, { "lemma": "a", "text": "a" }, { "lemma": "speech", "text": "speech" }, { "lemma": "tout", "text": "touting" }, { "lemma": "the", "text": "the" }, { "lemma": "virtue", "text": "virtues" }, { "lemma": "of", "text": "of" }, { "lemma": "free", "text": "free" }, { "lemma": "trade", "text": "trade" }, { "lemma": ".", "text": "." }, { "lemma": "but", "text": "But" }, { "lemma": "hour", "text": "hours" }, { "lemma": "before", "text": "before" }, { "lemma": "the", "text": "the" }, { "lemma": "speech", "text": "speech" }, { "lemma": ",", "text": "," }, { "lemma": "Nike", "text": "Nike" }, { "lemma": "announce", "text": "announced" }, { "lemma": "it", "text": "it" }, { "lemma": "would", "text": "would" }, { "lemma": "hire", "text": "hire" }, { "lemma": "10000", "text": "10,000" }, { "lemma": "worker", "text": "workers" }, { "lemma": "in", "text": "in" }, { "lemma": "the", "text": "the" }, { "lemma": "united", "text": "United" }, { "lemma": "state", "text": "States" }, { "lemma": "over", "text": "over" }, { "lemma": "the", "text": "the" }, { "lemma": "next", "text": "next" }, { "lemma": "decade", "text": "decade" }, { "lemma": "if", "text": "if" }, { "lemma": "a", "text": "a" }, { "lemma": "pacific", "text": "Pacific" }, { "lemma": "trade", "text": "trade" }, { "lemma": "agreement", "text": "agreement" }, { "lemma": "pass", "text": "passes" }, { "lemma": "congress", "text": "Congress" }, { "lemma": ".", "text": "." }, { "lemma": "introduce", "text": "Introducing" }, { "lemma": "Obama", "text": "Obama" }, { "lemma": ",", "text": "," }, { "lemma": "Nike", "text": "Nike" }, { "lemma": "President", "text": "President" }, { "lemma": "Mark", "text": "Mark" }, { "lemma": "Parker", "text": "Parker" }, { "lemma": "say", "text": "said" }, { "lemma": "Nike", "text": "Nike" }, { "lemma": "'s", "text": "'s" }, { "lemma": "fast", "text": "fast" }, { "lemma": "-", "text": "-" }, { "lemma": "growth", "text": "growth" }, { "lemma": "success", "text": "success" }, { "lemma": "story", "text": "story" }, { "lemma": "\"", "text": "\"" }, { "lemma": "be", "text": "was" }, { "lemma": "make", "text": "made" }, { "lemma": "possible", "text": "possible" }, { "lemma": "because", "text": "because" }, { "lemma": "of", "text": "of" }, { "lemma": "the", "text": "the" }, { "lemma": "power", "text": "power" }, { "lemma": "of", "text": "of" }, { "lemma": "trade", "text": "trade" }, { "lemma": ".", "text": "." }, { "lemma": "\"", "text": "\"" }, { "lemma": "\"", "text": "\"" }, { "lemma": "we", "text": "We" }, { "lemma": "be", "text": "are" }, { "lemma": "also", "text": "also" }, { "lemma": "proof", "text": "proof" }, { "lemma": "that", "text": "that" }, { "lemma": "trade", "text": "trade" }, { "lemma": "work", "text": "works" }, { "lemma": ",", "text": "," }, { "lemma": "and", "text": "and" }, { "lemma": "we", "text": "we" }, { "lemma": "believe", "text": "believe" }, { "lemma": "that", "text": "that" }, { "lemma": "company", "text": "companies" }, { "lemma": "should", "text": "should" }, { "lemma": "see", "text": "see" }, { "lemma": "that", "text": "that" }, { "lemma": "kind", "text": "kind" }, { "lemma": "of", "text": "of" }, { "lemma": "success", "text": "success" }, { "lemma": "—", "text": "—" }, { "lemma": "all", "text": "all" }, { "lemma": "company", "text": "companies" }, { "lemma": ",", "text": "," }, { "lemma": "\"", "text": "\"" }, { "lemma": "Parker", "text": "Parker" }, { "lemma": "say", "text": "said" }, { "lemma": ".", "text": "." }, { "lemma": "labor", "text": "Labor" }, { "lemma": "group", "text": "groups" }, { "lemma": "say", "text": "said" }, { "lemma": "that", "text": "that" }, { "lemma": "if", "text": "if" }, { "lemma": "Nike", "text": "Nike" }, { "lemma": "want", "text": "wants" }, { "lemma": "to", "text": "to" }, { "lemma": "hire", "text": "hire" }, { "lemma": "American", "text": "American" }, { "lemma": "worker", "text": "workers" }, { "lemma": ",", "text": "," }, { "lemma": "it", "text": "it" }, { "lemma": "should not", "text": "shouldn't" }, { "lemma": "be", "text": "be" }, { "lemma": "contingent", "text": "contingent" }, { "lemma": "on", "text": "on" }, { "lemma": "a", "text": "a" }, { "lemma": "trade", "text": "trade" }, { "lemma": "deal", "text": "deal" }, { "lemma": ".", "text": "." }, { "lemma": "\"", "text": "\"" }, { "lemma": "we", "text": "We" }, { "lemma": "have", "text": "have" }, { "lemma": "hear", "text": "heard" }, { "lemma": "similar", "text": "similar" }, { "lemma": "promise", "text": "promises" }, { "lemma": "from", "text": "from" }, { "lemma": "company", "text": "companies" }, { "lemma": "before", "text": "before" }, { "lemma": ",", "text": "," }, { "lemma": "and", "text": "and" }, { "lemma": "very", "text": "very" }, { "lemma": "few", "text": "few" }, { "lemma": "have", "text": "have" }, { "lemma": "pan", "text": "panned" }, { "lemma": "out", "text": "out" }, { "lemma": ".", "text": "." }, { "lemma": "we", "text": "We" }, { "lemma": "hope", "text": "hope" }, { "lemma": "this", "text": "this" }, { "lemma": "time", "text": "time" }, { "lemma": "be", "text": "is" }, { "lemma": "different", "text": "different" }, { "lemma": ",", "text": "," }, { "lemma": "\"", "text": "\"" }, { "lemma": "say", "text": "said" }, { "lemma": "Eric", "text": "Eric" }, { "lemma": "Hauser", "text": "Hauser" }, { "lemma": "of", "text": "of" }, { "lemma": "the", "text": "the" }, { "lemma": "AFL", "text": "AFL" }, { "lemma": "-", "text": "-" }, { "lemma": "CIO", "text": "CIO" }, { "lemma": ".", "text": "." }, { "lemma": "\"", "text": "\"" }, { "lemma": "decade", "text": "Decades" }, { "lemma": "of", "text": "of" }, { "lemma": "experience", "text": "experience" }, { "lemma": "have", "text": "have" }, { "lemma": "teach", "text": "taught" }, { "lemma": "we", "text": "us" }, { "lemma": "that", "text": "that" }, { "lemma": "corporate", "text": "corporate" }, { "lemma": "-", "text": "-" }, { "lemma": "driven", "text": "driven" }, { "lemma": "trade", "text": "trade" }, { "lemma": "policy", "text": "policy" }, { "lemma": "too", "text": "too" }, { "lemma": "often", "text": "often" }, { "lemma": "accelerate", "text": "accelerates" }, { "lemma": "a", "text": "a" }, { "lemma": "global", "text": "global" }, { "lemma": "race", "text": "race" }, { "lemma": "to", "text": "to" }, { "lemma": "the", "text": "the" }, { "lemma": "bottom", "text": "bottom" }, { "lemma": ".", "text": "." }, { "lemma": "\"", "text": "\"" }, { "lemma": "USA", "text": "USA" }, { "lemma": "today", "text": "TODAY" }, { "lemma": "free", "text": "Free" }, { "lemma": "trade", "text": "trade" }, { "lemma": "critic", "text": "critics" }, { "lemma": "hit", "text": "hit" }, { "lemma": "Obama", "text": "Obama" }, { "lemma": "over", "text": "over" }, { "lemma": "Nike", "text": "Nike" }, { "lemma": "visit", "text": "visit" }, { "lemma": "like", "text": "Like" }, { "lemma": "President", "text": "President" }, { "lemma": "Clinton", "text": "Clinton" }, { "lemma": "before", "text": "before" }, { "lemma": "he", "text": "him" }, { "lemma": ",", "text": "," }, { "lemma": "Obama", "text": "Obama" }, { "lemma": "'s", "text": "'s" }, { "lemma": "free", "text": "free" }, { "lemma": "trade", "text": "trade" }, { "lemma": "push", "text": "push" }, { "lemma": "have", "text": "has" }, { "lemma": "meet", "text": "met" }, { "lemma": "resistance", "text": "resistance" }, { "lemma": "from", "text": "from" }, { "lemma": "within", "text": "within" }, { "lemma": "he", "text": "his" }, { "lemma": "own", "text": "own" }, { "lemma": "democratic", "text": "Democratic" }, { "lemma": "party", "text": "party" }, { "lemma": ".", "text": "." }, { "lemma": "the", "text": "The" }, { "lemma": "white", "text": "White" }, { "lemma": "house", "text": "House" }, { "lemma": "have", "text": "has" }, { "lemma": "argue", "text": "argued" }, { "lemma": "that", "text": "that" }, { "lemma": "the", "text": "the" }, { "lemma": "Trans", "text": "Trans" }, { "lemma": "-", "text": "-" }, { "lemma": "Pacific", "text": "Pacific" }, { "lemma": "partnership", "text": "Partnership" }, { "lemma": "will", "text": "will" }, { "lemma": "have", "text": "have" }, { "lemma": "more", "text": "more" }, { "lemma": "labor", "text": "labor" }, { "lemma": "and", "text": "and" }, { "lemma": "environmental", "text": "environmental" }, { "lemma": "protection", "text": "protections" }, { "lemma": "than", "text": "than" }, { "lemma": "previous", "text": "previous" }, { "lemma": "trade", "text": "trade" }, { "lemma": "agreement", "text": "agreements" }, { "lemma": ".", "text": "." }, { "lemma": "but", "text": "But" }, { "lemma": "he", "text": "he" }, { "lemma": "have", "text": "'s" }, { "lemma": "also", "text": "also" }, { "lemma": "push", "text": "pushing" }, { "lemma": "for", "text": "for" }, { "lemma": "\"", "text": "\"" }, { "lemma": "fast", "text": "fast" }, { "lemma": "-", "text": "-" }, { "lemma": "track", "text": "track" }, { "lemma": "\"", "text": "\"" }, { "lemma": "negotiating", "text": "negotiating" }, { "lemma": "rule", "text": "rules" }, { "lemma": "—", "text": "—" }, { "lemma": "know", "text": "known" }, { "lemma": "as", "text": "as" }, { "lemma": "trade", "text": "trade" }, { "lemma": "promotion", "text": "promotion" }, { "lemma": "authority", "text": "authority" }, { "lemma": "—", "text": "—" }, { "lemma": "that", "text": "that" }, { "lemma": "would", "text": "would" }, { "lemma": "make", "text": "make" }, { "lemma": "it", "text": "it" }, { "lemma": "impossible", "text": "impossible" }, { "lemma": "for", "text": "for" }, { "lemma": "Congress", "text": "Congress" }, { "lemma": "to", "text": "to" }, { "lemma": "insist", "text": "insist" }, { "lemma": "on", "text": "on" }, { "lemma": "strong", "text": "stronger" }, { "lemma": "provision", "text": "provisions" }, { "lemma": "before", "text": "before" }, { "lemma": "an", "text": "an" }, { "lemma": "up", "text": "up" }, { "lemma": "-", "text": "-" }, { "lemma": "or", "text": "or" }, { "lemma": "-", "text": "-" }, { "lemma": "down", "text": "down" }, { "lemma": "vote", "text": "vote" }, { "lemma": "on", "text": "on" }, { "lemma": "passage", "text": "passage" }, { "lemma": ".", "text": "." }, { "lemma": "Obama", "text": "Obama" }, { "lemma": "acknowledge", "text": "acknowledged" }, { "lemma": "that", "text": "that" }, { "lemma": "intra", "text": "intra" }, { "lemma": "-", "text": "-" }, { "lemma": "party", "text": "party" }, { "lemma": "debate", "text": "debate" }, { "lemma": "Friday", "text": "Friday" }, { "lemma": ",", "text": "," }, { "lemma": "say", "text": "saying" }, { "lemma": ",", "text": "," }, { "lemma": "\"", "text": "\"" }, { "lemma": "some", "text": "Some" }, { "lemma": "of", "text": "of" }, { "lemma": "I", "text": "my" }, { "lemma": "dear", "text": "dearest" }, { "lemma": "friend", "text": "friends" }, { "lemma": "be", "text": "are" }, { "lemma": "wrong", "text": "wrong" }, { "lemma": ".", "text": "." }, { "lemma": "\"", "text": "\"" }, { "lemma": "\"", "text": "\"" }, { "lemma": "they", "text": "They" }, { "lemma": "be", "text": "'re" }, { "lemma": "I", "text": "my" }, { "lemma": "fellow", "text": "fellow" }, { "lemma": "traveler", "text": "travelers" }, { "lemma": "on", "text": "on" }, { "lemma": "minimum", "text": "minimum" }, { "lemma": "wage", "text": "wage" }, { "lemma": ",", "text": "," }, { "lemma": "and", "text": "and" }, { "lemma": "job", "text": "job" }, { "lemma": "train", "text": "training" }, { "lemma": "and", "text": "and" }, { "lemma": "clean", "text": "clean" }, { "lemma": "energy", "text": "energy" }, { "lemma": ".", "text": "." }, { "lemma": "they", "text": "They" }, { "lemma": "be", "text": "'re" }, { "lemma": "with", "text": "with" }, { "lemma": "I", "text": "me" }, { "lemma": "on", "text": "on" }, { "lemma": "every", "text": "every" }, { "lemma": "progressive", "text": "progressive" }, { "lemma": "issue", "text": "issue" }, { "lemma": ",", "text": "," }, { "lemma": "and", "text": "and" }, { "lemma": "then", "text": "then" }, { "lemma": "on", "text": "on" }, { "lemma": "this", "text": "this" }, { "lemma": "one", "text": "one" }, { "lemma": ",", "text": "," }, { "lemma": "they", "text": "they" }, { "lemma": "be", "text": "'re" }, { "lemma": "whupping", "text": "whupping" }, { "lemma": "on", "text": "on" }, { "lemma": "I", "text": "me" }, { "lemma": ",", "text": "," }, { "lemma": "\"", "text": "\"" }, { "lemma": "he", "text": "he" }, { "lemma": "say", "text": "said" }, { "lemma": ".", "text": "." }, { "lemma": "but", "text": "But" }, { "lemma": "he", "text": "he" }, { "lemma": "say", "text": "said" }, { "lemma": "he", "text": "he" }, { "lemma": "have", "text": "has" }, { "lemma": "no", "text": "no" }, { "lemma": "political", "text": "political" }, { "lemma": "reason", "text": "reason" }, { "lemma": "to", "text": "to" }, { "lemma": "turn", "text": "turn" }, { "lemma": "he", "text": "his" }, { "lemma": "back", "text": "back" }, { "lemma": "on", "text": "on" }, { "lemma": "those", "text": "those" }, { "lemma": "group", "text": "groups" }, { "lemma": ".", "text": "." }, { "lemma": "\"", "text": "\"" }, { "lemma": "I", "text": "I" }, { "lemma": "have", "text": "'ve" }, { "lemma": "run", "text": "run" }, { "lemma": "I", "text": "my" }, { "lemma": "last", "text": "last" }, { "lemma": "election", "text": "election" }, { "lemma": ".", "text": "." }, { "lemma": "the", "text": "The" }, { "lemma": "only", "text": "only" }, { "lemma": "reason", "text": "reason" }, { "lemma": "I", "text": "I" }, { "lemma": "be", "text": "'m" }, { "lemma": "do", "text": "doing" }, { "lemma": "something", "text": "something" }, { "lemma": "be", "text": "is" }, { "lemma": "because", "text": "because" }, { "lemma": "I", "text": "I" }, { "lemma": "think", "text": "think" }, { "lemma": "it", "text": "it" }, { "lemma": "have", "text": "'s" }, { "lemma": "well", "text": "best" }, { "lemma": "for", "text": "for" }, { "lemma": "American", "text": "American" }, { "lemma": "worker", "text": "workers" }, { "lemma": "and", "text": "and" }, { "lemma": "the", "text": "the" }, { "lemma": "American", "text": "American" }, { "lemma": "economy", "text": "economy" }, { "lemma": ".", "text": "." }, { "lemma": "\"", "text": "\"" }, { "lemma": "ever", "text": "Ever" }, { "lemma": "since", "text": "since" }, { "lemma": "the", "text": "the" }, { "lemma": "white", "text": "White" }, { "lemma": "house", "text": "House" }, { "lemma": "announce", "text": "announced" }, { "lemma": "the", "text": "the" }, { "lemma": "Nike", "text": "Nike" }, { "lemma": "visit", "text": "visit" }, { "lemma": ",", "text": "," }, { "lemma": "critic", "text": "critics" }, { "lemma": "of", "text": "of" }, { "lemma": "the", "text": "the" }, { "lemma": "proposed", "text": "proposed" }, { "lemma": "trade", "text": "trade" }, { "lemma": "deal", "text": "deal" }, { "lemma": "have", "text": "have" }, { "lemma": "question", "text": "questioned" }, { "lemma": "the", "text": "the" }, { "lemma": "appearance", "text": "appearances" }, { "lemma": "of", "text": "of" }, { "lemma": "use", "text": "using" }, { "lemma": "a", "text": "a" }, { "lemma": "company", "text": "company" }, { "lemma": "know", "text": "known" }, { "lemma": "for", "text": "for" }, { "lemma": "outsourcing", "text": "outsourcing" }, { "lemma": "to", "text": "to" }, { "lemma": "promote", "text": "promote" }, { "lemma": "free", "text": "free" }, { "lemma": "trade", "text": "trade" }, { "lemma": ".", "text": "." }, { "lemma": "\"", "text": "\"" }, { "lemma": "it", "text": "It" }, { "lemma": "be", "text": "is" }, { "lemma": "sad", "text": "sad" }, { "lemma": "to", "text": "to" }, { "lemma": "see", "text": "see" }, { "lemma": "how", "text": "how" }, { "lemma": "detach", "text": "detached" }, { "lemma": "from", "text": "from" }, { "lemma": "reality", "text": "reality" }, { "lemma": "President", "text": "President" }, { "lemma": "Obama", "text": "Obama" }, { "lemma": "be", "text": "is" }, { "lemma": "when", "text": "when" }, { "lemma": "it", "text": "it" }, { "lemma": "come", "text": "comes" }, { "lemma": "to", "text": "to" }, { "lemma": "TPP", "text": "TPP" }, { "lemma": ",", "text": "," }, { "lemma": "\"", "text": "\"" }, { "lemma": "say", "text": "said" }, { "lemma": "Murshed", "text": "Murshed" }, { "lemma": "Zaheed", "text": "Zaheed" }, { "lemma": "of", "text": "of" }, { "lemma": "credo", "text": "Credo" }, { "lemma": "action", "text": "Action" }, { "lemma": ",", "text": "," }, { "lemma": "a", "text": "a" }, { "lemma": "progressive", "text": "progressive" }, { "lemma": "activist", "text": "activist" }, { "lemma": "group", "text": "group" }, { "lemma": ".", "text": "." }, { "lemma": "\"", "text": "\"" }, { "lemma": "the", "text": "The" }, { "lemma": "symbolism", "text": "symbolism" }, { "lemma": "of", "text": "of" }, { "lemma": "he", "text": "his" }, { "lemma": "speech", "text": "speech" }, { "lemma": "be", "text": "is" }, { "lemma": "stagger", "text": "staggering" }, { "lemma": "—", "text": "—" }, { "lemma": "the", "text": "the" }, { "lemma": "Nike", "text": "Nike" }, { "lemma": "brand", "text": "brand" }, { "lemma": "be", "text": "was" }, { "lemma": "build", "text": "built" }, { "lemma": "by", "text": "by" }, { "lemma": "outsourcing", "text": "outsourcing" }, { "lemma": "manufacturing", "text": "manufacturing" }, { "lemma": "to", "text": "to" }, { "lemma": "sweatshop", "text": "sweatshops" }, { "lemma": "in", "text": "in" }, { "lemma": "Asia", "text": "Asia" }, { "lemma": ".", "text": "." }, { "lemma": "\"", "text": "\"" }, { "lemma": "follow", "text": "Follow" }, { "lemma": "@", "text": "@" }, { "lemma": "gregorykorte", "text": "gregorykorte" }, { "lemma": "on", "text": "on" }, { "lemma": "twitter", "text": "Twitter" }, { "lemma": ".", "text": "." }, { "lemma": "demonstrator", "text": "Demonstrators" }, { "lemma": "gather", "text": "gather" }, { "lemma": "near", "text": "near" }, { "lemma": "the", "text": "the" }, { "lemma": "sentinel", "text": "Sentinel" }, { "lemma": "hotel", "text": "Hotel" }, { "lemma": "where", "text": "where" }, { "lemma": "President", "text": "President" }, { "lemma": "Obama", "text": "Obama" }, { "lemma": "speak", "text": "spoke" }, { "lemma": "at", "text": "at" }, { "lemma": "a", "text": "a" }, { "lemma": "democratic", "text": "Democratic" }, { "lemma": "fundraiser", "text": "fundraiser" }, { "lemma": "Thursday", "text": "Thursday" }, { "lemma": ".", "text": "." }, { "lemma": "(", "text": "(" }, { "lemma": "photo", "text": "Photo" }, { "lemma": ":", "text": ":" }, { "lemma": "Thomas", "text": "Thomas" }, { "lemma": "Boyd", "text": "Boyd" }, { "lemma": ",", "text": "," }, { "lemma": "AP", "text": "AP" }, { "lemma": ")", "text": ")" }, { "lemma": "438", "text": "438" }, { "lemma": "connect", "text": "CONNECT" }, { "lemma": "142", "text": "142" }, { "lemma": "tweet", "text": "TWEET" }, { "lemma": "18", "text": "18" }, { "lemma": "LINKEDIN", "text": "LINKEDIN" }, { "lemma": "54", "text": "54" }, { "lemma": "COMMENTEMAILMORE", "text": "COMMENTEMAILMORE" }, { "lemma": "Read", "text": "Read" }, { "lemma": "or", "text": "or" }, { "lemma": "share", "text": "Share" }, { "lemma": "this", "text": "this" }, { "lemma": "story", "text": "story" }, { "lemma": ":", "text": ":" }, { "lemma": "http", "text": "http" }, { "lemma": ":", "text": ":" }, { "lemma": "/", "text": "/" }, { "lemma": "/", "text": "/" }, { "lemma": "usat.ly", "text": "usat.ly" }, { "lemma": "/", "text": "/" }, { "lemma": "1bDiUq2", "text": "1bDiUq2" }, { "lemma": "USA", "text": "USA" }, { "lemma": "Now", "text": "NOW" }, { "lemma": "Michael", "text": "Michael" }, { "lemma": "Wolff", "text": "Wolff" }, { "lemma": ":", "text": ":" }, { "lemma": "Britain", "text": "Britain" }, { "lemma": "be", "text": "is" }, { "lemma": "a", "text": "a" }, { "lemma": "very", "text": "very" }, { "lemma": "conservative", "text": "conservative" }, { "lemma": "nation", "text": "nation" }, { "lemma": "May", "text": "May" }, { "lemma": "08", "text": "08" }, { "lemma": ",", "text": "," }, { "lemma": "2015", "text": "2015" } ], "posTags": [ { "pos": "VI", "text": "Enter" }, { "pos": "PROP", "text": "City" }, { "pos": "CM", "text": "," }, { "pos": "PROP", "text": "State" }, { "pos": "COORD", "text": "or" }, { "pos": "NOUN", "text": "Zip" }, { "pos": "NOUN", "text": "Cancel" }, { "pos": "NOUN", "text": "Log" }, { "pos": "ADV", "text": "out" }, { "pos": "NOUN", "text": "Sign" }, { "pos": "PREP", "text": "In" }, { "pos": "PROP", "text": "FAQ" }, { "pos": "VPRES", "text": "Get" }, { "pos": "DET", "text": "the" }, { "pos": "NOUN", "text": "news" }, { "pos": "PROP", "text": "FacebookEmail" }, { "pos": "NOUN", "text": "Twitter" }, { "pos": "PROP", "text": "Google" }, { "pos": "PUNCT", "text": "+" }, { "pos": "PROP", "text": "LinkedIn" }, { "pos": "PROP", "text": "Pinterest" }, { "pos": "PROP", "text": "Obama" }, { "pos": "CM", "text": "," }, { "pos": "PREP", "text": "at" }, { "pos": "PROP", "text": "Nike" }, { "pos": "NOUN", "text": "HQ" }, { "pos": "CM", "text": "," }, { "pos": "VPRES", "text": "makes" }, { "pos": "ADJ", "text": "progressive" }, { "pos": "NOUN", "text": "case" }, { "pos": "PREP", "text": "for" }, { "pos": "NOUN", "text": "trade" }, { "pos": "TIT", "text": "President" }, { "pos": "PROP", "text": "Obama" }, { "pos": "VPAST", "text": "took" }, { "pos": "DET", "text": "his" }, { "pos": "NOUN", "text": "campaign" }, { "pos": "PREP", "text": "for" }, { "pos": "DET", "text": "a" }, { "pos": "ADJ", "text": "free" }, { "pos": "NOUN", "text": "trade" }, { "pos": "NOUN", "text": "deal" }, { "pos": "PREP", "text": "to" }, { "pos": "DET", "text": "the" }, { "pos": "NOUN", "text": "world" }, { "pos": "NOUN", "text": "headquarters" }, { "pos": "PREP", "text": "of" }, { "pos": "PROP", "text": "Nike" }, { "pos": "NOUN", "text": "Friday" }, { "pos": "CM", "text": "," }, { "pos": "COSUB", "text": "where" }, { "pos": "PRONPERS", "text": "he" }, { "pos": "VS", "text": "'s" }, { "pos": "VPAP", "text": "extracted" }, { "pos": "DET", "text": "a" }, { "pos": "NOUN", "text": "pledge" }, { "pos": "PREP", "text": "from" }, { "pos": "DET", "text": "the" }, { "pos": "NOUN", "text": "world" }, { "pos": "POSS", "text": "'s" }, { "pos": "ADJSUP", "text": "largest" }, { "pos": "ADJ", "text": "athletic" }, { "pos": "NOUN", "text": "shoe" }, { "pos": "NOUN", "text": "company" }, { "pos": "COSUB", "text": "that" }, { "pos": "PRONPERS", "text": "it" }, { "pos": "VAUX", "text": "will" }, { "pos": "VI", "text": "add" }, { "pos": "CARD", "text": "10,000" }, { "pos": "PROP", "text": "U.S." }, { "pos": "NOUN", "text": "jobs" }, { "pos": "SENT", "text": "." }, { "pos": "NOUN", "text": "Post" }, { "pos": "PREP", "text": "to" }, { "pos": "PROP", "text": "Facebook" }, { "pos": "PROP", "text": "Obama" }, { "pos": "CM", "text": "," }, { "pos": "PREP", "text": "at" }, { "pos": "PROP", "text": "Nike" }, { "pos": "NOUN", "text": "HQ" }, { "pos": "CM", "text": "," }, { "pos": "VPRES", "text": "makes" }, { "pos": "ADJ", "text": "progressive" }, { "pos": "NOUN", "text": "case" }, { "pos": "PREP", "text": "for" }, { "pos": "NOUN", "text": "trade" }, { "pos": "TIT", "text": "President" }, { "pos": "PROP", "text": "Obama" }, { "pos": "VPAST", "text": "took" }, { "pos": "DET", "text": "his" }, { "pos": "NOUN", "text": "campaign" }, { "pos": "PREP", "text": "for" }, { "pos": "DET", "text": "a" }, { "pos": "ADJ", "text": "free" }, { "pos": "NOUN", "text": "trade" }, { "pos": "NOUN", "text": "deal" }, { "pos": "PREP", "text": "to" }, { "pos": "DET", "text": "the" }, { "pos": "NOUN", "text": "world" }, { "pos": "NOUN", "text": "headquarters" }, { "pos": "PREP", "text": "of" }, { "pos": "PROP", "text": "Nike" }, { "pos": "NOUN", "text": "Friday" }, { "pos": "CM", "text": "," }, { "pos": "COSUB", "text": "where" }, { "pos": "PRONPERS", "text": "he" }, { "pos": "VS", "text": "'s" }, { "pos": "VPAP", "text": "extracted" }, { "pos": "DET", "text": "a" }, { "pos": "NOUN", "text": "pledge" }, { "pos": "PREP", "text": "from" }, { "pos": "DET", "text": "the" }, { "pos": "NOUN", "text": "world" }, { "pos": "POSS", "text": "'s" }, { "pos": "ADJSUP", "text": "largest" }, { "pos": "ADJ", "text": "athletic" }, { "pos": "NOUN", "text": "shoe" }, { "pos": "NOUN", "text": "company" }, { "pos": "COSUB", "text": "that" }, { "pos": "PRONPERS", "text": "it" }, { "pos": "VAUX", "text": "will" }, { "pos": "VI", "text": "add" }, { "pos": "CARD", "text": "10,000" }, { "pos": "PROP", "text": "U.S." }, { "pos": "NOUN", "text": "jobs" }, { "pos": "SENT", "text": "." }, { "pos": "NOUN", "text": "Check" }, { "pos": "ADV", "text": "out" }, { "pos": "DET", "text": "this" }, { "pos": "NOUN", "text": "story" }, { "pos": "PREP", "text": "on" }, { "pos": "PROP", "text": "USATODAY.com" }, { "pos": "SENT", "text": ":" }, { "pos": "ADJ", "text": "http" }, { "pos": "SENT", "text": ":" }, { "pos": "PUNCT", "text": "/" }, { "pos": "PUNCT", "text": "/" }, { "pos": "PROP", "text": "usat.ly" }, { "pos": "PUNCT", "text": "/" }, { "pos": "PROP", "text": "1bDiUq2" }, { "pos": "PUNCT", "text": "{" }, { "pos": "MEAS", "text": "#" }, { "pos": "MEAS", "text": "#" }, { "pos": "PUNCT", "text": "}" }, { "pos": "PROP", "text": "CancelSend" }, { "pos": "DET", "text": "A" }, { "pos": "NOUN", "text": "link" }, { "pos": "VHPRES", "text": "has" }, { "pos": "VBPAP", "text": "been" }, { "pos": "VPAP", "text": "sent" }, { "pos": "PREP", "text": "to" }, { "pos": "DET", "text": "your" }, { "pos": "NOUN", "text": "friend" }, { "pos": "POSS", "text": "'s" }, { "pos": "NOUN", "text": "email" }, { "pos": "NOUN", "text": "address" }, { "pos": "SENT", "text": "." }, { "pos": "PARTPAST", "text": "Posted" }, { "pos": "SENT", "text": "!" }, { "pos": "DET", "text": "A" }, { "pos": "NOUN", "text": "link" }, { "pos": "VHPRES", "text": "has" }, { "pos": "VBPAP", "text": "been" }, { "pos": "VPAP", "text": "posted" }, { "pos": "PREP", "text": "to" }, { "pos": "DET", "text": "your" }, { "pos": "ADJ", "text": "Facebook" }, { "pos": "NOUN", "text": "feed" }, { "pos": "SENT", "text": "." }, { "pos": "CARD", "text": "54" }, { "pos": "INFTO", "text": "To" }, { "pos": "VI", "text": "find" }, { "pos": "ADV", "text": "out" }, { "pos": "QUANTCMP", "text": "more" }, { "pos": "PREP", "text": "about" }, { "pos": "PROP", "text": "Facebook" }, { "pos": "PARTPRES", "text": "commenting" }, { "pos": "ADV", "text": "please" }, { "pos": "VPAST", "text": "read" }, { "pos": "DET", "text": "the" }, { "pos": "NOUN", "text": "Conversation" }, { "pos": "NOUN", "text": "Guidelines" }, { "pos": "COORD", "text": "and" }, { "pos": "PROP", "text": "FAQs" }, { "pos": "PROP", "text": "Obama" }, { "pos": "CM", "text": "," }, { "pos": "PREP", "text": "at" }, { "pos": "PROP", "text": "Nike" }, { "pos": "NOUN", "text": "HQ" }, { "pos": "CM", "text": "," }, { "pos": "VPRES", "text": "makes" }, { "pos": "ADJ", "text": "progressive" }, { "pos": "NOUN", "text": "case" }, { "pos": "PREP", "text": "for" }, { "pos": "NOUN", "text": "trade" }, { "pos": "PROP", "text": "Gregory" }, { "pos": "PROP", "text": "Korte" }, { "pos": "CM", "text": "," }, { "pos": "PROP", "text": "USA" }, { "pos": "ADV", "text": "TODAY" }, { "pos": "CARD", "text": "2:25" }, { "pos": "ADV", "text": "p.m." }, { "pos": "NOUN", "text": "EDT" }, { "pos": "PROP", "text": "May" }, { "pos": "CARD", "text": "8" }, { "pos": "CM", "text": "," }, { "pos": "CARD", "text": "2015" }, { "pos": "NOUN", "text": "President" }, { "pos": "PROP", "text": "Obama" }, { "pos": "VPRES", "text": "takes" }, { "pos": "DET", "text": "the" }, { "pos": "NOUN", "text": "stage" }, { "pos": "PREP", "text": "before" }, { "pos": "PARTPRES", "text": "speaking" }, { "pos": "PREP", "text": "at" }, { "pos": "PROP", "text": "Nike" }, { "pos": "NOUN", "text": "headquarters" }, { "pos": "PREP", "text": "in" }, { "pos": "PROP", "text": "Beaverton" }, { "pos": "CM", "text": "," }, { "pos": "PROP", "text": "Ore." }, { "pos": "NOUN", "text": "Friday" }, { "pos": "SENT", "text": "." }, { "pos": "PROP", "text": "Obama" }, { "pos": "VPAST", "text": "visited" }, { "pos": "DET", "text": "the" }, { "pos": "ADJ", "text": "giant" }, { "pos": "ADJ", "text": "athletic" }, { "pos": "NOUN", "text": "apparel" }, { "pos": "NOUN", "text": "company" }, { "pos": "INFTO", "text": "to" }, { "pos": "VI", "text": "make" }, { "pos": "DET", "text": "his" }, { "pos": "NOUN", "text": "trade" }, { "pos": "NOUN", "text": "policy" }, { "pos": "NOUN", "text": "pitch" }, { "pos": "PREPADVAS", "text": "as" }, { "pos": "PRONPERS", "text": "he" }, { "pos": "VPRES", "text": "struggles" }, { "pos": "INFTO", "text": "to" }, { "pos": "VI", "text": "win" }, { "pos": "PREP", "text": "over" }, { "pos": "NOUN", "text": "Democrats" }, { "pos": "PREP", "text": "for" }, { "pos": "WPRON", "text": "what" }, { "pos": "VAUX", "text": "could" }, { "pos": "VBI", "text": "be" }, { "pos": "DET", "text": "the" }, { "pos": "ADJ", "text": "last" }, { "pos": "ADJ", "text": "major" }, { "pos": "ADJ", "text": "legislative" }, { "pos": "NOUN", "text": "push" }, { "pos": "PREP", "text": "of" }, { "pos": "DET", "text": "his" }, { "pos": "NOUN", "text": "presidency" }, { "pos": "SENT", "text": "." }, { "pos": "PUNCT", "text": "(" }, { "pos": "NOUN", "text": "Photo" }, { "pos": "SENT", "text": ":" }, { "pos": "PROP", "text": "Pablo" }, { "pos": "PROP", "text": "Martinez" }, { "pos": "PROP", "text": "Monsivais" }, { "pos": "CM", "text": "," }, { "pos": "PROP", "text": "AP" }, { "pos": "PUNCT", "text": ")" }, { "pos": "CARD", "text": "438" }, { "pos": "VI", "text": "CONNECT" }, { "pos": "CARD", "text": "142" }, { "pos": "NOUN", "text": "TWEET" }, { "pos": "CARD", "text": "18" }, { "pos": "PROP", "text": "LINKEDIN" }, { "pos": "CARD", "text": "54" }, { "pos": "PROP", "text": "COMMENTEMAILMORE" }, { "pos": "TIT", "text": "President" }, { "pos": "PROP", "text": "Obama" }, { "pos": "VPAST", "text": "dressed" }, { "pos": "DET", "text": "his" }, { "pos": "NOUN", "text": "campaign" }, { "pos": "PREP", "text": "for" }, { "pos": "ADJ", "text": "free" }, { "pos": "NOUN", "text": "trade" }, { "pos": "PREP", "text": "in" }, { "pos": "DET", "text": "the" }, { "pos": "NOUN", "text": "clothing" }, { "pos": "PREP", "text": "of" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "ADJ", "text": "middle" }, { "pos": "NOUN", "text": "class" }, { "pos": "NOUN", "text": "economics" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "NOUN", "text": "Friday" }, { "pos": "CM", "text": "," }, { "pos": "PARTPRES", "text": "appealing" }, { "pos": "PREP", "text": "to" }, { "pos": "DET", "text": "his" }, { "pos": "ADJ", "text": "liberal" }, { "pos": "NOUN", "text": "base" }, { "pos": "INFTO", "text": "to" }, { "pos": "VI", "text": "support" }, { "pos": "DET", "text": "a" }, { "pos": "ADJ", "text": "Pacific" }, { "pos": "NOUN", "text": "trade" }, { "pos": "NOUN", "text": "deal" }, { "pos": "PRONPERS", "text": "he" }, { "pos": "VPAST", "text": "said" }, { "pos": "VAUX", "text": "would" }, { "pos": "VI", "text": "help" }, { "pos": "ADJ", "text": "American" }, { "pos": "NOUN", "text": "workers" }, { "pos": "SENT", "text": "." }, { "pos": "PARTPRES", "text": "Speaking" }, { "pos": "PREP", "text": "at" }, { "pos": "DET", "text": "the" }, { "pos": "NOUN", "text": "world" }, { "pos": "NOUN", "text": "headquarters" }, { "pos": "PREP", "text": "of" }, { "pos": "PROP", "text": "Nike" }, { "pos": "NOUN", "text": "Friday" }, { "pos": "CM", "text": "," }, { "pos": "PROP", "text": "Obama" }, { "pos": "VPAST", "text": "cast" }, { "pos": "ADJ", "text": "free" }, { "pos": "NOUN", "text": "trade" }, { "pos": "PREP", "text": "in" }, { "pos": "DET", "text": "the" }, { "pos": "ADJPRON", "text": "same" }, { "pos": "NOUN", "text": "terms" }, { "pos": "PREPADVAS", "text": "as" }, { "pos": "DET", "text": "his" }, { "pos": "NOUN", "text": "efforts" }, { "pos": "INFTO", "text": "to" }, { "pos": "VI", "text": "pass" }, { "pos": "ADJ", "text": "universal" }, { "pos": "NOUN", "text": "health" }, { "pos": "NOUN", "text": "care" }, { "pos": "CM", "text": "," }, { "pos": "VPRES", "text": "adopt" }, { "pos": "ADJ", "text": "clean" }, { "pos": "NOUN", "text": "energy" }, { "pos": "COORD", "text": "and" }, { "pos": "VI", "text": "raise" }, { "pos": "DET", "text": "the" }, { "pos": "ADJ", "text": "minimum" }, { "pos": "NOUN", "text": "wage" }, { "pos": "SENT", "text": "." }, { "pos": "PUNCT", "text": "\"" }, { "pos": "ADJING", "text": "Passing" }, { "pos": "NOUN", "text": "trade" }, { "pos": "NOUN", "text": "agreements" }, { "pos": "VBPRES", "text": "is" }, { "pos": "NOUN", "text": "part" }, { "pos": "PREP", "text": "of" }, { "pos": "DET", "text": "that" }, { "pos": "NOUN", "text": "agenda" }, { "pos": "PUNCT", "text": "—" }, { "pos": "COSUB", "text": "if" }, { "pos": "DET", "text": "those" }, { "pos": "NOUN", "text": "trade" }, { "pos": "NOUN", "text": "agreements" }, { "pos": "VBPRES", "text": "are" }, { "pos": "DET", "text": "the" }, { "pos": "ADJ", "text": "right" }, { "pos": "NOUN", "text": "kinds" }, { "pos": "PREP", "text": "of" }, { "pos": "NOUN", "text": "trade" }, { "pos": "NOUN", "text": "agreements" }, { "pos": "CM", "text": "," }, { "pos": "PUNCT", "text": "\"" }, { "pos": "PRONPERS", "text": "he" }, { "pos": "VPAST", "text": "said" }, { "pos": "SENT", "text": "." }, { "pos": "PUNCT", "text": "\"" }, { "pos": "PREP", "text": "Like" }, { "pos": "ADJPRON", "text": "other" }, { "pos": "NOUN", "text": "issues" }, { "pos": "PRONPERS", "text": "we" }, { "pos": "VHPRES", "text": "'ve" }, { "pos": "VPAP", "text": "waged" }, { "pos": "ADJ", "text": "slow" }, { "pos": "CM", "text": "," }, { "pos": "ADJ", "text": "steady" }, { "pos": "NOUN", "text": "fights" }, { "pos": "ADV", "text": "on" }, { "pos": "PREP", "text": "over" }, { "pos": "DET", "text": "the" }, { "pos": "ADJ", "text": "last" }, { "pos": "CARD", "text": "seven" }, { "pos": "NOUN", "text": "years" }, { "pos": "CM", "text": "," }, { "pos": "SENT", "text": "." }, { "pos": "PRON", "text": "this" }, { "pos": "VBPRES", "text": "is" }, { "pos": "ADV", "text": "also" }, { "pos": "DET", "text": "a" }, { "pos": "NOUN", "text": "question" }, { "pos": "PREP", "text": "of" }, { "pos": "DET", "text": "the" }, { "pos": "NOUN", "text": "past" }, { "pos": "PREP", "text": "versus" }, { "pos": "DET", "text": "the" }, { "pos": "NOUN", "text": "present" }, { "pos": "CM", "text": "," }, { "pos": "PUNCT", "text": "\"" }, { "pos": "PRONPERS", "text": "he" }, { "pos": "VPAST", "text": "said" }, { "pos": "SENT", "text": "." }, { "pos": "COSUB", "text": "But" }, { "pos": "PROP", "text": "Obama" }, { "pos": "VPAST", "text": "made" }, { "pos": "DET", "text": "his" }, { "pos": "NOUN", "text": "case" }, { "pos": "PREP", "text": "for" }, { "pos": "ADJ", "text": "free" }, { "pos": "NOUN", "text": "trade" }, { "pos": "PREP", "text": "at" }, { "pos": "DET", "text": "a" }, { "pos": "NOUN", "text": "company" }, { "pos": "COSUB", "text": "that" }, { "pos": "QUANT", "text": "many" }, { "pos": "NOUN", "text": "liberals" }, { "pos": "PUNCT", "text": "—" }, { "pos": "ADV", "text": "notably" }, { "pos": "PROP", "text": "Vermont" }, { "pos": "TIT", "text": "Sen." }, { "pos": "PROP", "text": "Bernie" }, { "pos": "PROP", "text": "Sanders" }, { "pos": "CM", "text": "," }, { "pos": "DET", "text": "a" }, { "pos": "ADJ", "text": "presidential" }, { "pos": "NOUN", "text": "candidate" }, { "pos": "PUNCT", "text": "—" }, { "pos": "NOUN", "text": "see" }, { "pos": "PREPADVAS", "text": "as" }, { "pos": "DET", "text": "a" }, { "pos": "NOUN", "text": "symbol" }, { "pos": "PREP", "text": "of" }, { "pos": "ADJPAP", "text": "failed" }, { "pos": "NOUN", "text": "trade" }, { "pos": "NOUN", "text": "policies" }, { "pos": "SENT", "text": "." }, { "pos": "PROP", "text": "Nike" }, { "pos": "CM", "text": "," }, { "pos": "DET", "text": "the" }, { "pos": "NOUN", "text": "world" }, { "pos": "POSS", "text": "'s" }, { "pos": "ADJSUP", "text": "largest" }, { "pos": "ADJ", "text": "athletic" }, { "pos": "NOUN", "text": "shoe" }, { "pos": "NOUN", "text": "manufacturer" }, { "pos": "CM", "text": "," }, { "pos": "NOUN", "text": "imports" }, { "pos": "NOUN", "text": "shoes" }, { "pos": "PREP", "text": "from" }, { "pos": "NOUN", "text": "contract" }, { "pos": "NOUN", "text": "factories" }, { "pos": "PREP", "text": "in" }, { "pos": "NOUN", "text": "places" }, { "pos": "PREP", "text": "like" }, { "pos": "PROP", "text": "Vietnam" }, { "pos": "CM", "text": "," }, { "pos": "COSUB", "text": "where" }, { "pos": "DET", "text": "the" }, { "pos": "ADJ", "text": "minimum" }, { "pos": "NOUN", "text": "wage" }, { "pos": "VBPRES", "text": "is" }, { "pos": "CARD", "text": "56" }, { "pos": "NOUN", "text": "cents" }, { "pos": "DET", "text": "an" }, { "pos": "NOUN", "text": "hour" }, { "pos": "SENT", "text": "." }, { "pos": "PROP", "text": "Obama" }, { "pos": "VPAST", "text": "said" }, { "pos": "PROP", "text": "Vietnam" }, { "pos": "CM", "text": "," }, { "pos": "COSUB", "text": "where" }, { "pos": "CARD", "text": "330,000" }, { "pos": "NOUN", "text": "workers" }, { "pos": "VPRES", "text": "make" }, { "pos": "PROP", "text": "Nike" }, { "pos": "NOUN", "text": "shoes" }, { "pos": "CM", "text": "," }, { "pos": "VAUX", "text": "would" }, { "pos": "VHI", "text": "have" }, { "pos": "INFTO", "text": "to" }, { "pos": "VI", "text": "increase" }, { "pos": "DET", "text": "the" }, { "pos": "ADJ", "text": "minimum" }, { "pos": "NOUN", "text": "wage" }, { "pos": "CM", "text": "," }, { "pos": "VPRES", "text": "improve" }, { "pos": "ADJING", "text": "working" }, { "pos": "NOUN", "text": "conditions" }, { "pos": "COORD", "text": "and" }, { "pos": "ADV", "text": "even" }, { "pos": "VI", "text": "establish" }, { "pos": "DET", "text": "the" }, { "pos": "ADJ", "text": "right" }, { "pos": "PREP", "text": "of" }, { "pos": "NOUN", "text": "workers" }, { "pos": "INFTO", "text": "to" }, { "pos": "VI", "text": "join" }, { "pos": "DET", "text": "a" }, { "pos": "NOUN", "text": "union" }, { "pos": "SENT", "text": "." }, { "pos": "PUNCT", "text": "\"" }, { "pos": "PRONPERS", "text": "It" }, { "pos": "VDPRES", "text": "doesn't" }, { "pos": "VI", "text": "mean" }, { "pos": "COSUB", "text": "that" }, { "pos": "ADV", "text": "suddenly" }, { "pos": "ADJING", "text": "working" }, { "pos": "NOUN", "text": "conditions" }, { "pos": "PREP", "text": "in" }, { "pos": "PROP", "text": "Vietnam" }, { "pos": "VAUX", "text": "will" }, { "pos": "VBI", "text": "be" }, { "pos": "PREP", "text": "like" }, { "pos": "PRONPERS", "text": "they" }, { "pos": "VBPRES", "text": "are" }, { "pos": "ADV", "text": "here" }, { "pos": "PREP", "text": "at" }, { "pos": "PROP", "text": "Nike" }, { "pos": "CM", "text": "," }, { "pos": "COORD", "text": "or" }, { "pos": "ADV", "text": "here" }, { "pos": "PREP", "text": "in" }, { "pos": "PROP", "text": "Portland" }, { "pos": "ADV", "text": "right" }, { "pos": "ADV", "text": "away" }, { "pos": "CM", "text": "," }, { "pos": "COSUB", "text": "but" }, { "pos": "PRONPERS", "text": "it" }, { "pos": "VPRES", "text": "moves" }, { "pos": "PRONPERS", "text": "us" }, { "pos": "PREP", "text": "in" }, { "pos": "DET", "text": "the" }, { "pos": "ADJ", "text": "right" }, { "pos": "NOUN", "text": "direction" }, { "pos": "CM", "text": "," }, { "pos": "PUNCT", "text": "\"" }, { "pos": "PRONPERS", "text": "he" }, { "pos": "VPAST", "text": "said" }, { "pos": "SENT", "text": "." }, { "pos": "PUNCT", "text": "\"" }, { "pos": "COSUB", "text": "If" }, { "pos": "PRONPERS", "text": "you" }, { "pos": "VBPRES", "text": "'re" }, { "pos": "DET", "text": "a" }, { "pos": "NOUN", "text": "country" }, { "pos": "PRONREL", "text": "that" }, { "pos": "VPRES", "text": "wants" }, { "pos": "PREP", "text": "into" }, { "pos": "DET", "text": "this" }, { "pos": "NOUN", "text": "agreement" }, { "pos": "CM", "text": "," }, { "pos": "PRONPERS", "text": "you" }, { "pos": "VHPRES", "text": "have" }, { "pos": "INFTO", "text": "to" }, { "pos": "VI", "text": "meet" }, { "pos": "ADJCMP", "text": "higher" }, { "pos": "NOUN", "text": "standards" }, { "pos": "SENT", "text": "." }, { "pos": "COSUB", "text": "If" }, { "pos": "PRONPERS", "text": "you" }, { "pos": "VDPRES", "text": "don't" }, { "pos": "PRONPERS", "text": "you" }, { "pos": "VBPRES", "text": "'re" }, { "pos": "ADV", "text": "out" }, { "pos": "SENT", "text": "." }, { "pos": "PUNCT", "text": "\"" }, { "pos": "PROP", "text": "USA" }, { "pos": "ADV", "text": "TODAY" }, { "pos": "NOUN", "text": "Senate" }, { "pos": "NOUN", "text": "panel" }, { "pos": "VPRES", "text": "approves" }, { "pos": "POSS", "text": "'" }, { "pos": "ADJ", "text": "fast" }, { "pos": "NOUN", "text": "track" }, { "pos": "POSS", "text": "'" }, { "pos": "NOUN", "text": "trade" }, { "pos": "NOUN", "text": "bill" }, { "pos": "PREP", "text": "At" }, { "pos": "ORD", "text": "first" }, { "pos": "CM", "text": "," }, { "pos": "PROP", "text": "Nike" }, { "pos": "VPAST", "text": "seemed" }, { "pos": "PREP", "text": "like" }, { "pos": "DET", "text": "an" }, { "pos": "ADJ", "text": "unlikely" }, { "pos": "NOUN", "text": "venue" }, { "pos": "PREP", "text": "for" }, { "pos": "DET", "text": "a" }, { "pos": "NOUN", "text": "speech" }, { "pos": "PARTPRES", "text": "touting" }, { "pos": "DET", "text": "the" }, { "pos": "NOUN", "text": "virtues" }, { "pos": "PREP", "text": "of" }, { "pos": "ADJ", "text": "free" }, { "pos": "NOUN", "text": "trade" }, { "pos": "SENT", "text": "." }, { "pos": "COSUB", "text": "But" }, { "pos": "NOUN", "text": "hours" }, { "pos": "PREP", "text": "before" }, { "pos": "DET", "text": "the" }, { "pos": "NOUN", "text": "speech" }, { "pos": "CM", "text": "," }, { "pos": "PROP", "text": "Nike" }, { "pos": "VPAST", "text": "announced" }, { "pos": "PRONPERS", "text": "it" }, { "pos": "VAUX", "text": "would" }, { "pos": "VI", "text": "hire" }, { "pos": "CARD", "text": "10,000" }, { "pos": "NOUN", "text": "workers" }, { "pos": "PREP", "text": "in" }, { "pos": "DET", "text": "the" }, { "pos": "ADJPAP", "text": "United" }, { "pos": "NOUN", "text": "States" }, { "pos": "PREP", "text": "over" }, { "pos": "DET", "text": "the" }, { "pos": "ADJ", "text": "next" }, { "pos": "NOUN", "text": "decade" }, { "pos": "COSUB", "text": "if" }, { "pos": "DET", "text": "a" }, { "pos": "ADJ", "text": "Pacific" }, { "pos": "NOUN", "text": "trade" }, { "pos": "NOUN", "text": "agreement" }, { "pos": "NOUN", "text": "passes" }, { "pos": "NOUN", "text": "Congress" }, { "pos": "SENT", "text": "." }, { "pos": "PARTPRES", "text": "Introducing" }, { "pos": "PROP", "text": "Obama" }, { "pos": "CM", "text": "," }, { "pos": "PROP", "text": "Nike" }, { "pos": "TIT", "text": "President" }, { "pos": "PROP", "text": "Mark" }, { "pos": "PROP", "text": "Parker" }, { "pos": "VPAST", "text": "said" }, { "pos": "PROP", "text": "Nike" }, { "pos": "POSS", "text": "'s" }, { "pos": "ADJ", "text": "fast" }, { "pos": "PUNCT", "text": "-" }, { "pos": "NOUN", "text": "growth" }, { "pos": "NOUN", "text": "success" }, { "pos": "NOUN", "text": "story" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "VBPAST", "text": "was" }, { "pos": "VPAP", "text": "made" }, { "pos": "ADJ", "text": "possible" }, { "pos": "COSUB", "text": "because" }, { "pos": "PREP", "text": "of" }, { "pos": "DET", "text": "the" }, { "pos": "NOUN", "text": "power" }, { "pos": "PREP", "text": "of" }, { "pos": "NOUN", "text": "trade" }, { "pos": "SENT", "text": "." }, { "pos": "PUNCT", "text": "\"" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "PRONPERS", "text": "We" }, { "pos": "VBPRES", "text": "are" }, { "pos": "ADV", "text": "also" }, { "pos": "ADJ", "text": "proof" }, { "pos": "COSUB", "text": "that" }, { "pos": "NOUN", "text": "trade" }, { "pos": "NOUN", "text": "works" }, { "pos": "CM", "text": "," }, { "pos": "COORD", "text": "and" }, { "pos": "PRONPERS", "text": "we" }, { "pos": "VPRES", "text": "believe" }, { "pos": "DET", "text": "that" }, { "pos": "NOUN", "text": "companies" }, { "pos": "VAUX", "text": "should" }, { "pos": "VI", "text": "see" }, { "pos": "DET", "text": "that" }, { "pos": "NOUN", "text": "kind" }, { "pos": "PREP", "text": "of" }, { "pos": "NOUN", "text": "success" }, { "pos": "PUNCT", "text": "—" }, { "pos": "QUANT", "text": "all" }, { "pos": "NOUN", "text": "companies" }, { "pos": "CM", "text": "," }, { "pos": "PUNCT", "text": "\"" }, { "pos": "PROP", "text": "Parker" }, { "pos": "VPAST", "text": "said" }, { "pos": "SENT", "text": "." }, { "pos": "NOUN", "text": "Labor" }, { "pos": "NOUN", "text": "groups" }, { "pos": "VPAST", "text": "said" }, { "pos": "COSUB", "text": "that" }, { "pos": "COSUB", "text": "if" }, { "pos": "PROP", "text": "Nike" }, { "pos": "NOUN", "text": "wants" }, { "pos": "INFTO", "text": "to" }, { "pos": "VI", "text": "hire" }, { "pos": "ADJ", "text": "American" }, { "pos": "NOUN", "text": "workers" }, { "pos": "CM", "text": "," }, { "pos": "PRONPERS", "text": "it" }, { "pos": "VAUX", "text": "shouldn't" }, { "pos": "VBI", "text": "be" }, { "pos": "ADJ", "text": "contingent" }, { "pos": "PREP", "text": "on" }, { "pos": "DET", "text": "a" }, { "pos": "NOUN", "text": "trade" }, { "pos": "NOUN", "text": "deal" }, { "pos": "SENT", "text": "." }, { "pos": "PUNCT", "text": "\"" }, { "pos": "PRONPERS", "text": "We" }, { "pos": "VHPRES", "text": "have" }, { "pos": "VPAP", "text": "heard" }, { "pos": "ADJ", "text": "similar" }, { "pos": "NOUN", "text": "promises" }, { "pos": "PREP", "text": "from" }, { "pos": "NOUN", "text": "companies" }, { "pos": "COSUB", "text": "before" }, { "pos": "CM", "text": "," }, { "pos": "COORD", "text": "and" }, { "pos": "ADV", "text": "very" }, { "pos": "QUANT", "text": "few" }, { "pos": "VHI", "text": "have" }, { "pos": "VPAP", "text": "panned" }, { "pos": "ADV", "text": "out" }, { "pos": "SENT", "text": "." }, { "pos": "PRONPERS", "text": "We" }, { "pos": "VPRES", "text": "hope" }, { "pos": "DET", "text": "this" }, { "pos": "NOUN", "text": "time" }, { "pos": "VBPRES", "text": "is" }, { "pos": "ADJ", "text": "different" }, { "pos": "CM", "text": "," }, { "pos": "PUNCT", "text": "\"" }, { "pos": "VPAST", "text": "said" }, { "pos": "PROP", "text": "Eric" }, { "pos": "PROP", "text": "Hauser" }, { "pos": "PREP", "text": "of" }, { "pos": "DET", "text": "the" }, { "pos": "PROP", "text": "AFL" }, { "pos": "PUNCT", "text": "-" }, { "pos": "PROP", "text": "CIO" }, { "pos": "SENT", "text": "." }, { "pos": "PUNCT", "text": "\"" }, { "pos": "NOUN", "text": "Decades" }, { "pos": "PREP", "text": "of" }, { "pos": "NOUN", "text": "experience" }, { "pos": "VHPRES", "text": "have" }, { "pos": "VPAP", "text": "taught" }, { "pos": "PRONPERS", "text": "us" }, { "pos": "COSUB", "text": "that" }, { "pos": "ADJ", "text": "corporate" }, { "pos": "PUNCT", "text": "-" }, { "pos": "ADJPAP", "text": "driven" }, { "pos": "NOUN", "text": "trade" }, { "pos": "NOUN", "text": "policy" }, { "pos": "ADV", "text": "too" }, { "pos": "ADV", "text": "often" }, { "pos": "VPRES", "text": "accelerates" }, { "pos": "DET", "text": "a" }, { "pos": "ADJ", "text": "global" }, { "pos": "NOUN", "text": "race" }, { "pos": "PREP", "text": "to" }, { "pos": "DET", "text": "the" }, { "pos": "NOUN", "text": "bottom" }, { "pos": "SENT", "text": "." }, { "pos": "PUNCT", "text": "\"" }, { "pos": "PROP", "text": "USA" }, { "pos": "ADV", "text": "TODAY" }, { "pos": "ADJ", "text": "Free" }, { "pos": "NOUN", "text": "trade" }, { "pos": "NOUN", "text": "critics" }, { "pos": "VPAST", "text": "hit" }, { "pos": "PROP", "text": "Obama" }, { "pos": "PREP", "text": "over" }, { "pos": "PROP", "text": "Nike" }, { "pos": "NOUN", "text": "visit" }, { "pos": "PREP", "text": "Like" }, { "pos": "TIT", "text": "President" }, { "pos": "PROP", "text": "Clinton" }, { "pos": "COSUB", "text": "before" }, { "pos": "PRONPERS", "text": "him" }, { "pos": "CM", "text": "," }, { "pos": "PROP", "text": "Obama" }, { "pos": "POSS", "text": "'s" }, { "pos": "ADJ", "text": "free" }, { "pos": "NOUN", "text": "trade" }, { "pos": "NOUN", "text": "push" }, { "pos": "VHPRES", "text": "has" }, { "pos": "VPAP", "text": "met" }, { "pos": "NOUN", "text": "resistance" }, { "pos": "PREP", "text": "from" }, { "pos": "PREP", "text": "within" }, { "pos": "DET", "text": "his" }, { "pos": "ADJ", "text": "own" }, { "pos": "ADJ", "text": "Democratic" }, { "pos": "NOUN", "text": "party" }, { "pos": "SENT", "text": "." }, { "pos": "DET", "text": "The" }, { "pos": "ADJ", "text": "White" }, { "pos": "NOUN", "text": "House" }, { "pos": "VHPRES", "text": "has" }, { "pos": "VPAP", "text": "argued" }, { "pos": "COSUB", "text": "that" }, { "pos": "DET", "text": "the" }, { "pos": "PROP", "text": "Trans" }, { "pos": "PUNCT", "text": "-" }, { "pos": "PROP", "text": "Pacific" }, { "pos": "NOUN", "text": "Partnership" }, { "pos": "VAUX", "text": "will" }, { "pos": "VHI", "text": "have" }, { "pos": "QUANTCMP", "text": "more" }, { "pos": "NOUN", "text": "labor" }, { "pos": "COORD", "text": "and" }, { "pos": "ADJ", "text": "environmental" }, { "pos": "NOUN", "text": "protections" }, { "pos": "COTHAN", "text": "than" }, { "pos": "ADJ", "text": "previous" }, { "pos": "NOUN", "text": "trade" }, { "pos": "NOUN", "text": "agreements" }, { "pos": "SENT", "text": "." }, { "pos": "COSUB", "text": "But" }, { "pos": "PRONPERS", "text": "he" }, { "pos": "VS", "text": "'s" }, { "pos": "ADV", "text": "also" }, { "pos": "PARTPRES", "text": "pushing" }, { "pos": "PREP", "text": "for" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "ADJ", "text": "fast" }, { "pos": "PUNCT", "text": "-" }, { "pos": "NOUN", "text": "track" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "ADJING", "text": "negotiating" }, { "pos": "NOUN", "text": "rules" }, { "pos": "PUNCT", "text": "—" }, { "pos": "PARTPAST", "text": "known" }, { "pos": "PREPADVAS", "text": "as" }, { "pos": "NOUN", "text": "trade" }, { "pos": "NOUN", "text": "promotion" }, { "pos": "NOUN", "text": "authority" }, { "pos": "PUNCT", "text": "—" }, { "pos": "PRON", "text": "that" }, { "pos": "VAUX", "text": "would" }, { "pos": "VI", "text": "make" }, { "pos": "PRONPERS", "text": "it" }, { "pos": "ADJ", "text": "impossible" }, { "pos": "PREP", "text": "for" }, { "pos": "PROP", "text": "Congress" }, { "pos": "INFTO", "text": "to" }, { "pos": "VI", "text": "insist" }, { "pos": "PREP", "text": "on" }, { "pos": "ADJCMP", "text": "stronger" }, { "pos": "NOUN", "text": "provisions" }, { "pos": "PREP", "text": "before" }, { "pos": "DET", "text": "an" }, { "pos": "ADV", "text": "up" }, { "pos": "PUNCT", "text": "-" }, { "pos": "COORD", "text": "or" }, { "pos": "PUNCT", "text": "-" }, { "pos": "ADV", "text": "down" }, { "pos": "NOUN", "text": "vote" }, { "pos": "PREP", "text": "on" }, { "pos": "NOUN", "text": "passage" }, { "pos": "SENT", "text": "." }, { "pos": "PROP", "text": "Obama" }, { "pos": "VPAST", "text": "acknowledged" }, { "pos": "COSUB", "text": "that" }, { "pos": "ADJ", "text": "intra" }, { "pos": "PUNCT", "text": "-" }, { "pos": "NOUN", "text": "party" }, { "pos": "NOUN", "text": "debate" }, { "pos": "NOUN", "text": "Friday" }, { "pos": "CM", "text": "," }, { "pos": "PARTPRES", "text": "saying" }, { "pos": "CM", "text": "," }, { "pos": "PUNCT", "text": "\"" }, { "pos": "QUANT", "text": "Some" }, { "pos": "PREP", "text": "of" }, { "pos": "DET", "text": "my" }, { "pos": "ADJSUP", "text": "dearest" }, { "pos": "NOUN", "text": "friends" }, { "pos": "VBPRES", "text": "are" }, { "pos": "ADJ", "text": "wrong" }, { "pos": "SENT", "text": "." }, { "pos": "PUNCT", "text": "\"" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "PRONPERS", "text": "They" }, { "pos": "VBPRES", "text": "'re" }, { "pos": "DET", "text": "my" }, { "pos": "NOUN", "text": "fellow" }, { "pos": "NOUN", "text": "travelers" }, { "pos": "PREP", "text": "on" }, { "pos": "ADJ", "text": "minimum" }, { "pos": "NOUN", "text": "wage" }, { "pos": "CM", "text": "," }, { "pos": "COORD", "text": "and" }, { "pos": "NOUN", "text": "job" }, { "pos": "PARTPRES", "text": "training" }, { "pos": "COORD", "text": "and" }, { "pos": "ADJ", "text": "clean" }, { "pos": "NOUN", "text": "energy" }, { "pos": "SENT", "text": "." }, { "pos": "PRONPERS", "text": "They" }, { "pos": "VBPRES", "text": "'re" }, { "pos": "PREP", "text": "with" }, { "pos": "PRONPERS", "text": "me" }, { "pos": "PREP", "text": "on" }, { "pos": "QUANT", "text": "every" }, { "pos": "ADJ", "text": "progressive" }, { "pos": "NOUN", "text": "issue" }, { "pos": "CM", "text": "," }, { "pos": "COORD", "text": "and" }, { "pos": "ADV", "text": "then" }, { "pos": "PREP", "text": "on" }, { "pos": "DET", "text": "this" }, { "pos": "PRONONE", "text": "one" }, { "pos": "CM", "text": "," }, { "pos": "PRONPERS", "text": "they" }, { "pos": "VBPRES", "text": "'re" }, { "pos": "VPROG", "text": "whupping" }, { "pos": "PREP", "text": "on" }, { "pos": "PRONPERS", "text": "me" }, { "pos": "CM", "text": "," }, { "pos": "PUNCT", "text": "\"" }, { "pos": "PRONPERS", "text": "he" }, { "pos": "VPAST", "text": "said" }, { "pos": "SENT", "text": "." }, { "pos": "COSUB", "text": "But" }, { "pos": "PRONPERS", "text": "he" }, { "pos": "VPAST", "text": "said" }, { "pos": "PRONPERS", "text": "he" }, { "pos": "VHPRES", "text": "has" }, { "pos": "DET", "text": "no" }, { "pos": "ADJ", "text": "political" }, { "pos": "NOUN", "text": "reason" }, { "pos": "INFTO", "text": "to" }, { "pos": "VI", "text": "turn" }, { "pos": "DET", "text": "his" }, { "pos": "NOUN", "text": "back" }, { "pos": "PREP", "text": "on" }, { "pos": "DET", "text": "those" }, { "pos": "NOUN", "text": "groups" }, { "pos": "SENT", "text": "." }, { "pos": "PUNCT", "text": "\"" }, { "pos": "PRONPERS", "text": "I" }, { "pos": "VHPRES", "text": "'ve" }, { "pos": "VPAP", "text": "run" }, { "pos": "DET", "text": "my" }, { "pos": "ADJ", "text": "last" }, { "pos": "NOUN", "text": "election" }, { "pos": "SENT", "text": "." }, { "pos": "DET", "text": "The" }, { "pos": "ADJ", "text": "only" }, { "pos": "NOUN", "text": "reason" }, { "pos": "PRONPERS", "text": "I" }, { "pos": "VBPRES", "text": "'m" }, { "pos": "VDPROG", "text": "doing" }, { "pos": "PRON", "text": "something" }, { "pos": "VBPRES", "text": "is" }, { "pos": "COSUB", "text": "because" }, { "pos": "PRONPERS", "text": "I" }, { "pos": "VPRES", "text": "think" }, { "pos": "PRONPERS", "text": "it" }, { "pos": "VS", "text": "'s" }, { "pos": "ADVSUP", "text": "best" }, { "pos": "PREP", "text": "for" }, { "pos": "ADJ", "text": "American" }, { "pos": "NOUN", "text": "workers" }, { "pos": "COORD", "text": "and" }, { "pos": "DET", "text": "the" }, { "pos": "ADJ", "text": "American" }, { "pos": "NOUN", "text": "economy" }, { "pos": "SENT", "text": "." }, { "pos": "PUNCT", "text": "\"" }, { "pos": "ADV", "text": "Ever" }, { "pos": "COSUB", "text": "since" }, { "pos": "DET", "text": "the" }, { "pos": "ADJ", "text": "White" }, { "pos": "NOUN", "text": "House" }, { "pos": "VPAST", "text": "announced" }, { "pos": "DET", "text": "the" }, { "pos": "PROP", "text": "Nike" }, { "pos": "NOUN", "text": "visit" }, { "pos": "CM", "text": "," }, { "pos": "NOUN", "text": "critics" }, { "pos": "PREP", "text": "of" }, { "pos": "DET", "text": "the" }, { "pos": "ADJPAP", "text": "proposed" }, { "pos": "NOUN", "text": "trade" }, { "pos": "NOUN", "text": "deal" }, { "pos": "VHPRES", "text": "have" }, { "pos": "VPAP", "text": "questioned" }, { "pos": "DET", "text": "the" }, { "pos": "NOUN", "text": "appearances" }, { "pos": "PREP", "text": "of" }, { "pos": "PARTPRES", "text": "using" }, { "pos": "DET", "text": "a" }, { "pos": "NOUN", "text": "company" }, { "pos": "PARTPAST", "text": "known" }, { "pos": "PREP", "text": "for" }, { "pos": "PARTPRES", "text": "outsourcing" }, { "pos": "INFTO", "text": "to" }, { "pos": "VI", "text": "promote" }, { "pos": "ADJ", "text": "free" }, { "pos": "NOUN", "text": "trade" }, { "pos": "SENT", "text": "." }, { "pos": "PUNCT", "text": "\"" }, { "pos": "PRONPERS", "text": "It" }, { "pos": "VBPRES", "text": "is" }, { "pos": "ADJ", "text": "sad" }, { "pos": "INFTO", "text": "to" }, { "pos": "VI", "text": "see" }, { "pos": "WADV", "text": "how" }, { "pos": "PARTPAST", "text": "detached" }, { "pos": "PREP", "text": "from" }, { "pos": "NOUN", "text": "reality" }, { "pos": "TIT", "text": "President" }, { "pos": "PROP", "text": "Obama" }, { "pos": "VBPRES", "text": "is" }, { "pos": "COSUB", "text": "when" }, { "pos": "PRONPERS", "text": "it" }, { "pos": "VPRES", "text": "comes" }, { "pos": "PREP", "text": "to" }, { "pos": "PROP", "text": "TPP" }, { "pos": "CM", "text": "," }, { "pos": "PUNCT", "text": "\"" }, { "pos": "VPAST", "text": "said" }, { "pos": "PROP", "text": "Murshed" }, { "pos": "PROP", "text": "Zaheed" }, { "pos": "PREP", "text": "of" }, { "pos": "NOUN", "text": "Credo" }, { "pos": "NOUN", "text": "Action" }, { "pos": "CM", "text": "," }, { "pos": "DET", "text": "a" }, { "pos": "ADJ", "text": "progressive" }, { "pos": "NOUN", "text": "activist" }, { "pos": "NOUN", "text": "group" }, { "pos": "SENT", "text": "." }, { "pos": "PUNCT", "text": "\"" }, { "pos": "DET", "text": "The" }, { "pos": "NOUN", "text": "symbolism" }, { "pos": "PREP", "text": "of" }, { "pos": "DET", "text": "his" }, { "pos": "NOUN", "text": "speech" }, { "pos": "VBPRES", "text": "is" }, { "pos": "VPROG", "text": "staggering" }, { "pos": "PUNCT", "text": "—" }, { "pos": "DET", "text": "the" }, { "pos": "PROP", "text": "Nike" }, { "pos": "NOUN", "text": "brand" }, { "pos": "VBPAST", "text": "was" }, { "pos": "VPAP", "text": "built" }, { "pos": "PREP", "text": "by" }, { "pos": "PARTPRES", "text": "outsourcing" }, { "pos": "NOUNING", "text": "manufacturing" }, { "pos": "PREP", "text": "to" }, { "pos": "NOUN", "text": "sweatshops" }, { "pos": "PREP", "text": "in" }, { "pos": "PROP", "text": "Asia" }, { "pos": "SENT", "text": "." }, { "pos": "PUNCT", "text": "\"" }, { "pos": "VI", "text": "Follow" }, { "pos": "MEAS", "text": "@" }, { "pos": "ADJ", "text": "gregorykorte" }, { "pos": "PREP", "text": "on" }, { "pos": "NOUN", "text": "Twitter" }, { "pos": "SENT", "text": "." }, { "pos": "NOUN", "text": "Demonstrators" }, { "pos": "NOUN", "text": "gather" }, { "pos": "PREP", "text": "near" }, { "pos": "DET", "text": "the" }, { "pos": "NOUN", "text": "Sentinel" }, { "pos": "NOUN", "text": "Hotel" }, { "pos": "COSUB", "text": "where" }, { "pos": "TIT", "text": "President" }, { "pos": "PROP", "text": "Obama" }, { "pos": "VPAST", "text": "spoke" }, { "pos": "PREP", "text": "at" }, { "pos": "DET", "text": "a" }, { "pos": "ADJ", "text": "Democratic" }, { "pos": "NOUN", "text": "fundraiser" }, { "pos": "NOUN", "text": "Thursday" }, { "pos": "SENT", "text": "." }, { "pos": "PUNCT", "text": "(" }, { "pos": "NOUN", "text": "Photo" }, { "pos": "SENT", "text": ":" }, { "pos": "PROP", "text": "Thomas" }, { "pos": "PROP", "text": "Boyd" }, { "pos": "CM", "text": "," }, { "pos": "PROP", "text": "AP" }, { "pos": "PUNCT", "text": ")" }, { "pos": "CARD", "text": "438" }, { "pos": "VI", "text": "CONNECT" }, { "pos": "CARD", "text": "142" }, { "pos": "NOUN", "text": "TWEET" }, { "pos": "CARD", "text": "18" }, { "pos": "PROP", "text": "LINKEDIN" }, { "pos": "CARD", "text": "54" }, { "pos": "PROP", "text": "COMMENTEMAILMORE" }, { "pos": "PROP", "text": "Read" }, { "pos": "COORD", "text": "or" }, { "pos": "VI", "text": "Share" }, { "pos": "DET", "text": "this" }, { "pos": "NOUN", "text": "story" }, { "pos": "SENT", "text": ":" }, { "pos": "ADJ", "text": "http" }, { "pos": "SENT", "text": ":" }, { "pos": "PUNCT", "text": "/" }, { "pos": "PUNCT", "text": "/" }, { "pos": "PROP", "text": "usat.ly" }, { "pos": "PUNCT", "text": "/" }, { "pos": "PROP", "text": "1bDiUq2" }, { "pos": "PROP", "text": "USA" }, { "pos": "PROP", "text": "NOW" }, { "pos": "PROP", "text": "Michael" }, { "pos": "PROP", "text": "Wolff" }, { "pos": "SENT", "text": ":" }, { "pos": "PROP", "text": "Britain" }, { "pos": "VBPRES", "text": "is" }, { "pos": "DET", "text": "a" }, { "pos": "ADJ", "text": "very" }, { "pos": "ADJ", "text": "conservative" }, { "pos": "NOUN", "text": "nation" }, { "pos": "PROP", "text": "May" }, { "pos": "CARD", "text": "08" }, { "pos": "CM", "text": "," }, { "pos": "CARD", "text": "2015" } ], "requestId": "7298beee-a818-4102-9842-1e54b7bb9eec", "timers": { "rblJe": 10, "rliJe": 5, "textExtractor": 17, "urlContentDownloader": 181 } } python-0.7.4/tests/mock-data/response/eng-url-morphology_complete.status 0000664 0000000 0000000 00000000003 12636317025 0026604 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/eng-url-relationships.json 0000664 0000000 0000000 00000057546 12636317025 0025057 0 ustar 00root root 0000000 0000000 { "requestId": "8143276a-b6c5-4b5c-957b-f2c12b4378a8", "relationships": [ { "predicate": "makes", "arg1": "progressive case for trade\nPresident Obama", "arg2": "took his campaign for a free trade deal to the world headquarters of Nike Friday" }, { "predicate": "makes", "arg1": "Log out Sign In FAQ\nGet the news\nFacebookEmail Twitter Google", "arg2": "progressive case for trade\nPresident Obama took his campaign for a free trade deal to the world headquarters of Nike Friday" }, { "predicate": "took", "arg1": "progressive case for trade\nPresident Obama", "arg2": "his campaign", "adjuncts": [ "for a free trade deal to the world headquarters of Nike", "where he's extracted a pledge from the world's largest athletic shoe company that it will add 10,000 U.S. jobs" ] }, { "predicate": "took", "arg1": "progressive case for trade President Obama", "arg2": "his campaign", "adjuncts": [ "for a free trade deal to the world headquarters of Nike", "where he's extracted a pledge from the world's largest athletic shoe company that it will add 10,000 U.S. jobs" ] }, { "predicate": "makes", "arg1": "progressive case for trade President Obama", "arg2": "took his campaign for a free trade deal to the world headquarters of Nike Friday" }, { "predicate": "makes", "arg1": "Post to Facebook Obama", "arg2": "progressive case for trade President Obama took his campaign for a free trade deal to the world headquarters of Nike Friday" }, { "predicate": "has", "arg1": "CancelSend\nA link", "arg2": "been sent to your friend's email address" }, { "predicate": "has been sent", "arg1": "CancelSend\nA link", "adjuncts": [ "to your friend's email address" ] }, { "predicate": "has", "arg1": "A link", "arg2": "been posted to your Facebook feed" }, { "predicate": "has been posted", "arg1": "A link", "adjuncts": [ "to your Facebook feed" ] }, { "predicate": "makes", "arg1": "179\nTo find out more about Facebook commenting please read the Conversation Guidelines", "arg2": "progressive case for trade\nGregory Korte" }, { "predicate": "commenting please read", "arg1": "more about Facebook", "arg2": "the Conversation Guidelines" }, { "predicate": "is", "arg1": "May 8", "arg2": "2015\nPresident Obama" }, { "predicate": "takes", "arg1": "trade\nGregory Korte", "arg2": "USA TODAY", "arg3": "the stage" }, { "predicate": "takes", "arg1": "trade\nGregory Korte", "arg2": "May 8", "arg3": "the stage" }, { "predicate": "visited", "arg1": "Obama", "arg2": "the giant athletic apparel company", "arg3": "to make his trade policy pitch as he struggles to win over Democrats" }, { "predicate": "dressed", "arg1": "58 LINKEDIN 179 COMMENTEMAILMORE\nPresident Obama", "arg2": "his campaign for free trade in the clothing of" }, { "predicate": "would help", "arg1": "a Pacific trade deal", "arg2": "American workers" }, { "predicate": "cast", "arg1": "Obama", "arg2": "free trade", "adjuncts": [ "adopt clean energy", "in the same terms", "as his efforts to pass universal health care" ] }, { "predicate": "cast", "arg1": "Obama", "arg2": "free trade", "adjuncts": [ "raise the minimum wage", "in the same terms", "as his efforts to pass universal health care" ] }, { "predicate": "visited", "arg1": "President Barack Obama", "arg2": "Nike headquarters", "adjuncts": [ "to promote his trade agenda" ] }, { "predicate": "says", "arg1": "a Trans-Pacific trade deal", "arg2": "would allow it to benefit from lower tariffs on shoes" }, { "predicate": "is", "arg1": "notably Vermont Sen. Bernie Sanders", "arg2": "a presidential candidate" }, { "predicate": "says", "arg1": "Nike", "arg2": "a Trans-Pacific trade deal would allow it to benefit from lower tariffs on shoes" }, { "predicate": "see", "arg1": "many liberals", "adjuncts": [ "as a symbol of failed trade policies" ] }, { "predicate": "is", "arg1": "the minimum wage", "arg2": "56 cents an hour" }, { "predicate": "make", "arg1": "330,000 workers", "arg2": "Nike shoes" }, { "predicate": "said", "arg1": "Obama", "arg2": "would have to increase the minimum wage" }, { "predicate": "seemed", "arg1": "Nike", "adjuncts": [ "like an unlikely venue for a speech" ] }, { "predicate": "approves", "arg1": "USA TODAY\nSenate panel", "arg2": "trade bill", "adjuncts": [ "At first" ] }, { "predicate": "announced", "arg1": "Nike", "arg2": "it would hire 10,000 workers in the United States over the next decade" }, { "predicate": "passes", "arg1": "a Pacific trade agreement", "arg2": "Congress" }, { "predicate": "was made", "arg1": "Nike's fast-growth success story", "arg2": "possible", "adjuncts": [ "because of the power of trade" ] }, { "predicate": "said", "arg1": "Nike President Mark Parker", "arg2": "was made possible because of the power of trade" }, { "predicate": "said", "arg1": "Introducing Obama", "arg2": "was made possible because of the power of trade" }, { "predicate": "should see", "arg1": "companies", "arg2": "that kind of success" }, { "predicate": "wants", "arg1": "Nike", "arg2": "to hire American workers" }, { "predicate": "said", "arg1": "Labor groups", "arg2": "if Nike wants to hire American workers, it shouldn't be contingent on a trade deal" }, { "predicate": "is", "arg1": "this time", "arg2": "different" }, { "predicate": "has met", "arg1": "Obama's free trade push", "arg2": "resistance from within his own Democratic party" }, { "predicate": "hit", "arg1": "USA TODAY\nFree trade critics", "arg2": "Obama", "adjuncts": [ "over Nike visit\nLike President Clinton", "before him" ] }, { "predicate": "will have", "arg1": "the Trans-Pacific Partnership", "arg2": "more labor" }, { "predicate": "has argued", "arg1": "The White House", "arg2": "that the Trans-Pacific Partnership will have more labor" }, { "predicate": "to insist", "arg1": "Congress", "adjuncts": [ "on stronger provisions before an up-or-down vote on passage" ] }, { "predicate": "acknowledged", "arg1": "Obama", "arg2": "that intra-party debate Friday" }, { "predicate": "announced", "arg1": "the White House", "arg2": "have questioned the appearances" }, { "predicate": "have questioned", "arg1": "the Nike visit", "arg2": "the appearances of using a company" }, { "predicate": "was built", "arg1": "the Nike brand", "adjuncts": [ "by outsourcing manufacturing to sweatshops in Asia" ] }, { "predicate": "is", "arg1": "The symbolism of his speech", "arg2": "staggering" }, { "predicate": "gather", "arg1": "Demonstrators", "locatives": [ "near the Sentinel Hotel" ] }, { "predicate": "spoke", "arg1": "President Obama", "adjuncts": [ "at a Democratic fundraiser" ] }, { "predicate": "is", "arg1": "Thomas Boyd", "arg2": "VIDEO" }, { "predicate": "based", "arg1": "valuable states in America", "adjuncts": [ "on value of land per acre" ] }, { "predicate": "is", "arg1": "Aziz Hamzaogullari", "arg2": "portfolio manager for the Loomis Sayles Growth Fund" }, { "predicate": "are wired", "arg1": "THE DAY IN MONEYAmazon", "arg2": "to keep growing market share" }, { "predicate": "is", "arg1": "00:59\nUnity Stoakes", "arg2": "co-founder of StartUp Health" }, { "predicate": "|", "arg1": "THE DAY IN MONEYHealth care technology booms", "arg2": "00:59\nUnity Stoakes" }, { "predicate": "added", "arg1": "Hamzaogullari", "arg2": "that the anti-trust suit against Newslook\n2 of 42\nVIDEO" }, { "predicate": "is", "arg1": "Trisha Thadani", "arg2": "Collin Brennan\n3 of 42\nVIDEO" }, { "predicate": "share", "arg1": "Buzz60's Leigh Scheps", "arg2": "some tops" }, { "predicate": "is", "arg1": "Buzz60's Leigh Scheps", "arg2": "@LeighTVReporters" }, { "predicate": "introduced", "arg1": "THE DAY IN MONEYAmazon launches", "arg2": "free shipping for small" }, { "predicate": "|", "arg1": "free shipping on small items", "arg2": "00:40\nAmazon", "adjuncts": [ "on Tuesday" ] }, { "predicate": "has stabilized", "arg1": "04:40\nThe high yield bond market", "arg2": "since worries about falling energy prices dragged it down last winter" }, { "predicate": "says", "arg1": "Morgan Stanley", "arg2": "| 04:40\nThe high yield bond market has stabilized since worries about falling energy prices dragged it down last winter" }, { "predicate": "|", "arg1": "Morgan Stanley", "arg2": "04:40\nThe high yield bond market has stabilized since worries about falling energy prices dragged it down last winter" }, { "predicate": "says", "arg1": "Richard Lindquist", "arg2": "the good times will continue" }, { "predicate": "says", "arg1": "the good times", "arg2": "will continue" }, { "predicate": "is", "arg1": "Richard Lindquist", "arg2": "head of high yield at Morgan Stanley Investment Management" }, { "predicate": "ended", "arg1": "00:55\nShares of PVH Corp.", "arg2": "making it TheStreet's Move of the Day", "adjuncts": [ "up 7 percent" ] }, { "predicate": "came", "arg1": "Earnings per share", "adjuncts": [ "in at $0.71", "were looking for" ] }, { "predicate": "polled", "arg1": "the $0.59 analysts", "adjuncts": [ "by Thomson Reuters" ] }, { "predicate": "is keeping", "arg1": "FireEye | 01:00\nTheStreet's Jim Cramer", "arg2": "an eye on shares of FireEye" }, { "predicate": "says", "arg1": "one of his favorite themes for 2015", "arg2": "is cyber security" }, { "predicate": "says", "arg1": "Cramer", "arg2": "is cyber security" }, { "predicate": "is", "arg1": "one of his favorite themes for 2015", "arg2": "cyber security" }, { "predicate": "quashes", "arg1": "THE DAY IN MONEYNintendo", "arg2": "rumors of future deal with android | 02:00\nRumors of a Nintendo Android deal" }, { "predicate": "were dismissed", "arg1": "THE DAY IN MONEYNintendo quashes rumors of future deal with android | 02:00\nRumors of a Nintendo Android deal", "adjuncts": [ "by the big N", "on Tuesday" ] }, { "predicate": "provided", "arg1": "Video", "adjuncts": [ "by Newsy Newslook\n11 of 42\nVIDEO" ] }, { "predicate": "are under pressure", "arg1": "U.S.-bred poultry suppliers", "adjuncts": [ "with the U.S. Department of Agriculture" ] }, { "predicate": "explains", "arg1": "RealMoney Pro contributor", "arg2": "how to cut your exposure to stocks" }, { "predicate": "|", "arg1": "Avoid companies with egg dependencies", "arg2": "01:45" }, { "predicate": "|", "arg1": "earnings estimates", "arg2": "stocks are" }, { "predicate": "reported", "arg1": "the company", "arg2": "earnings on Tuesday" }, { "predicate": "beats", "arg1": "THE DAY IN MONEYCracker Barrel", "arg2": "earnings estimates | 00:49\nCracker Barrel" }, { "predicate": "beats", "arg1": "earnings estimates", "arg2": "| 00:49\nCracker Barrel" }, { "predicate": "buys", "arg1": "THE DAY IN MONEYBoot Barn", "arg2": "western lifestyle retailer Sheplers", "adjuncts": [ "for $147M | 01:29\nBoot Barn Holdings Inc. said June 1 it has agreed to buy fellow western lifestyle retailer Sheplers Inc. for $147 million in cash" ] }, { "predicate": "said", "arg1": "Boot Barn Holdings Inc.", "arg2": "it has agreed to buy fellow western lifestyle retailer Sheplers Inc. for $147 million in cash" }, { "predicate": "is", "arg1": "The seller", "arg2": "San Francisco-based private equity firm Gryphon Investors" }, { "predicate": "slip", "arg1": "factory orders", "arg2": "shares" }, { "predicate": "told", "arg1": "A source", "arg2": "The Deal's Richard Collings tha Newslook\n15 of 42\nVIDEO", "adjuncts": [ "THE DAY IN MONEYGM" ] }, { "predicate": "reported", "arg1": "the automaker", "arg2": "a 3 percent increase in domestic sales in May" }, { "predicate": "beat", "arg1": "Ford", "arg2": "monthly sales forecasts" }, { "predicate": "also beat", "arg1": "Ford", "arg2": "estimates", "adjuncts": [ "falling at a slower-than-expected pace in May" ] }, { "predicate": "announced", "arg1": "the company", "arg2": "a new camera" }, { "predicate": "jumped", "arg1": "Touchscreen", "arg2": "as much as 7%", "adjuncts": [ "on Monday", "after the company announced a new camera" ] }, { "predicate": "announced", "arg1": "THE DAY IN MONEYGoPro", "arg2": "a new camera with Touchscreen, Stock skyrockets | 01:01\nGoPro (GPRO) shares jumped as much as 7% on Monday" }, { "predicate": "according to", "arg1": "that features a built-in screen", "arg2": "CNET" }, { "predicate": "is", "arg1": "The GoPro Hero", "arg2": "a touchscreen camera that's only its second offering" }, { "predicate": "|", "arg1": "| America's Markets", "arg2": "01:37\nUSA" }, { "predicate": "might outsmart", "arg1": "investors", "arg2": "the usual June gloom", "adjuncts": [ "in this edition of America's Markets" ] }, { "predicate": "has", "arg1": "Krystin Goodwin", "arg2": "five things airlines don't want you to know" }, { "predicate": "is", "arg1": "Krystin Goodwin", "arg2": "@Krystingoodwin" }, { "predicate": "has", "arg1": "five things airlines", "arg2": "don't want you to know" }, { "predicate": "drops", "arg1": "THE DAY IN MONEYMacau's casino revenue", "arg2": "37%", "adjuncts": [ "in twelve month" ] }, { "predicate": "has dropped", "arg1": "casino revenue for the Chinese peninsula", "arg2": "37.1 percent", "adjuncts": [ "in May", "from last year's numbers" ] }, { "predicate": "opens", "arg1": "THE DAY IN MONEYDenver", "arg2": "its first marijuana-friendly hotel | 01:03\nThe Nativ is Colorado's first openly pot-friendly hotel" }, { "predicate": "is", "arg1": "The Nativ", "arg2": "Colorado's first openly pot-friendly hotel" }, { "predicate": "has", "arg1": "TC Newman", "arg2": "the details" }, { "predicate": "Find out", "arg1": "01:24", "adjuncts": [ "from a Halstead Property executive" ] }, { "predicate": "sits down", "arg1": "Brian Lewis", "arg2": "to discuss this exclusive market", "adjuncts": [ "with Fortune's Leigh Gallagher" ] }, { "predicate": "is", "arg1": "Brian Lewis", "arg2": "Executive VP of Halstead Property" }, { "predicate": "may endorse", "arg1": "the AFL CIO", "adjuncts": [ "in 2016" ] }, { "predicate": "is", "arg1": "| 04:42\nMichael Lin", "arg2": "president of the Taiwan Stock Exchange" }, { "predicate": "talks", "arg1": "more links", "arg2": "| 04:42\nMichael Lin", "adjuncts": [ "about the planned trading link with Singapore" ] }, { "predicate": "seeks", "arg1": "THE DAY IN MONEYTaiwan Exchange Chief", "arg2": "more links with Singapore | 04:42\nMichael Lin, president of the Taiwan Stock Exchange, talks about the planned trading link with Singapore" }, { "predicate": "are using", "arg1": "THE DAY IN MONEYThe central bankers", "arg2": "tomatoes", "arg3": "to fight inflation" }, { "predicate": "is struggling", "arg1": "02:19\nIndonesia", "arg2": "to fight its highest rate of inflation" }, { "predicate": "makes", "arg1": "Netflix", "arg2": "a good graduation gift | 01:59\nTheStreet's Jim Cramer answers your Twitter questions about Blackstone (BX" }, { "predicate": "says", "arg1": "Netflix", "arg2": "makes a good graduation gift" }, { "predicate": "says", "arg1": "THE DAY IN MONEYJim Cramer", "arg2": "Netflix makes a good graduation gift" }, { "predicate": "answers", "arg1": "your Twitter", "arg2": "questions about Blackstone" }, { "predicate": "answers", "arg1": "a good graduation gift", "arg2": "| 01:59\nTheStreet's Jim Cramer", "arg3": "your Twitter questions about Blackstone" }, { "predicate": "said", "arg1": "the Commerce Department", "adjuncts": [ "on Friday" ] }, { "predicate": "fell", "arg1": "First-quarter gross domestic product", "arg2": "0.7 percent" }, { "predicate": "have", "arg1": "Nebraska", "arg2": "the lowest unemployment rates" }, { "predicate": "have", "arg1": "Utah", "arg2": "the lowest unemployment rates" }, { "predicate": "have", "arg1": "North Dakota", "arg2": "the lowest unemployment rates" }, { "predicate": "has", "arg1": "Douglas McIntyre of 24/7 Wall Street", "arg2": "the details" }, { "predicate": "are demanding", "arg1": "action | 01:29\nWorried that their reputations will be tarnished by their links to FIFA", "adjuncts": [ "even warning it is prepared to jump ship", "with Visa" ] }, { "predicate": "will be tarnished", "arg1": "their reputations", "adjuncts": [ "by their links to FIFA" ] }, { "predicate": "just sped", "arg1": "shuttle people between Los Angeles", "arg2": "a bit closer to reality" }, { "predicate": "is Getting", "arg1": "THE DAY IN MONEYHyperloop", "arg2": "a Test Track in California | 00:52\nThe" }, { "predicate": "is returning", "arg1": "THE DAY IN MONEYSkyMall", "arg2": "online" }, { "predicate": "found", "arg1": "the quirky items", "adjuncts": [ "in the catalog returning to an airplane seat pocket near you" ] }, { "predicate": "shows", "arg1": "TC Newman", "arg2": "you some of the quirky items" }, { "predicate": "was the next development", "arg1": "The buzz at Google I/O", "adjuncts": [ "Google's partnership with GoPro" ] }, { "predicate": "is coming", "arg1": "THE DAY IN MONEYVirtual reality", "adjuncts": [ "to YouTube | 00:44" ] }, { "predicate": "was the next development", "arg1": "The buzz at Google I/O", "adjuncts": [ "of its Cardboard VR viewing device" ] }, { "predicate": "was", "arg1": "The buzz at Google I/O", "arg2": "the next development of its Cardboard VR viewing device" }, { "predicate": "will record", "arg1": "GoPro", "arg2": "whose camera sets", "arg3": "VR-ready videos" }, { "predicate": "is offering", "arg1": "| 00:50\nAmazon", "arg2": "free same-day shipping for its Prime subscribers", "adjuncts": [ "in some of its key markets" ] }, { "predicate": "plans", "arg1": "no one", "arg2": "to slow oil production" }, { "predicate": "shows", "arg1": "OPEC", "arg2": "thinks no one plans to slow oil production" }, { "predicate": "announced", "arg1": "Google's upgrades to Android", "adjuncts": [ "at Google I/O" ] }, { "predicate": "is", "arg1": "05:25\nJuan Benitez", "arg2": "chief technology officer at Braintree" }, { "predicate": "will end", "arg1": "oil glut", "adjuncts": [ "until at least 2017 | 01:50\nThe 12-nation conglomerate's long-term strategy report" ] }, { "predicate": "thinks", "arg1": "OPEC", "arg2": "no one plans to slow oil production" }, { "predicate": "is", "arg1": "Bloomberg's Cory Johnson", "arg2": "chief technology officer at Braintree" }, { "predicate": "thinks", "arg1": "no one", "arg2": "plans to slow oil production" }, { "predicate": "ended", "arg1": "| 00:49\nShares of data storage company Western Digital", "adjuncts": [ "following Goldman Sachs upgrade" ] }, { "predicate": "upgraded", "arg1": "Goldman Sachs", "arg2": "the stock", "adjuncts": [ "to BUY from NEUTRAL" ] }, { "predicate": "says", "arg1": "North America's bandwidth", "arg2": "| 01:21\nA new study", "arg3": "Netflix accounts for about 37 percent of North American Internet traffic during peak hours" }, { "predicate": "is apparently hogging", "arg1": "THE DAY IN MONEYNetflix", "arg2": "North America's bandwidth" }, { "predicate": "is", "arg1": "| 04:34\nSuccess", "arg2": "life on your own terms" }, { "predicate": "is", "arg1": "The Dealmaker’s Ten Commandments", "arg2": "a methodology for figuring out what the terms are for yourself" }, { "predicate": "provided", "arg1": "Video", "adjuncts": [ "by Newsy Newslook\n41 of 42\nVIDEO" ] }, { "predicate": "says", "arg1": "The Dealmaker’s Ten Commandments", "arg2": "is a methodology for figuring out what the terms are for yourself" }, { "predicate": "is life", "arg1": "| 04:34\nSuccess", "adjuncts": [ "on your own terms" ] }, { "predicate": "says", "arg1": "THE DAY IN MONEYThe Hollywood Dealmaker’s Guide", "arg2": "his book The Dealmaker’s Ten Commandments is a methodology for figuring out what the terms are for yourself" } ] } python-0.7.4/tests/mock-data/response/eng-url-relationships.status 0000664 0000000 0000000 00000000004 12636317025 0025402 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/eng-url-sentiment.json 0000664 0000000 0000000 00000000551 12636317025 0024161 0 ustar 00root root 0000000 0000000 { "requestId": "8e277ba2-00e9-46ec-bd30-04d885b1882d", "sentiment": [ { "confidence": 0.9156604769654398, "label": "pos" }, { "confidence": 0.08433952303456017, "label": "neg" } ], "timers": { "rblJe": 3, "rliJe": 5, "sent": 133, "textExtractor": 14, "urlContentDownloader": 105 } } python-0.7.4/tests/mock-data/response/eng-url-sentiment.status 0000664 0000000 0000000 00000000003 12636317025 0024523 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/fra-doc-categories.json 0000664 0000000 0000000 00000000233 12636317025 0024237 0 ustar 00root root 0000000 0000000 { "code": "unsupportedLanguage", "message": "French is not supported by Rosette Categorizer", "requestId": "956f3423-e3dc-4b30-a5ff-bca0478fe408" } python-0.7.4/tests/mock-data/response/fra-doc-categories.status 0000664 0000000 0000000 00000000003 12636317025 0024604 0 ustar 00root root 0000000 0000000 415 python-0.7.4/tests/mock-data/response/fra-doc-entities.json 0000664 0000000 0000000 00000013663 12636317025 0023751 0 ustar 00root root 0000000 0000000 { "entities": [ { "confidence": 0.05105915239879063, "count": 7, "indocChainId": 4, "mention": "Obama", "normalized": "Obama", "type": "PERSON" }, { "confidence": 0.03971593578656515, "count": 6, "indocChainId": 8, "mention": "M.", "normalized": "M.", "type": "TITLE" }, { "confidence": 0.028711426258087158, "count": 5, "indocChainId": 3, "mention": "président", "normalized": "président", "type": "TITLE" }, { "confidence": 0.031732420126597084, "count": 3, "indocChainId": 0, "mention": "Etats-Unis", "normalized": "Etats-Unis", "type": "LOCATION" }, { "confidence": 0.03095032771428426, "count": 3, "indocChainId": 35, "mention": "républicains", "normalized": "républicains", "type": "ORGANIZATION" }, { "confidence": 0.01543426513671875, "count": 2, "indocChainId": 4, "mention": "Barack Obama", "normalized": "Barack Obama", "type": "PERSON" }, { "confidence": 0.019789844751358032, "count": 2, "indocChainId": 5, "mention": "Amérique", "normalized": "Amérique", "type": "LOCATION" }, { "confidence": 0.018558651208877563, "count": 2, "indocChainId": 10, "mention": "Dean Baker", "normalized": "Dean Baker", "type": "PERSON" }, { "confidence": 0.00832781195640564, "count": 2, "indocChainId": 14, "mention": "républicain", "normalized": "républicain", "type": "ORGANIZATION" }, { "confidence": 0.011866271495819092, "count": 2, "indocChainId": 33, "mention": "Congrès", "normalized": "Congrès", "type": "ORGANIZATION" }, { "confidence": 0.03181558847427368, "count": 2, "indocChainId": 44, "mention": "Sénat", "normalized": "Sénat", "type": "ORGANIZATION" }, { "confidence": 0.016073524951934814, "count": 1, "indocChainId": 1, "mention": "Census Bureau", "normalized": "Census Bureau", "type": "ORGANIZATION" }, { "confidence": 0.013657450675964355, "count": 1, "indocChainId": 2, "mention": "Insee", "normalized": "Insee", "type": "ORGANIZATION" }, { "confidence": 0.009501934051513672, "count": 1, "indocChainId": 6, "mention": "Maison Blanche", "normalized": "Maison Blanche", "type": "ORGANIZATION" }, { "confidence": 0.01004105806350708, "count": 1, "indocChainId": 7, "mention": "Parti démocrate", "normalized": "Parti démocrate", "type": "ORGANIZATION" }, { "confidence": 0.03106057643890381, "count": 1, "indocChainId": 10, "mention": "Baker", "normalized": "Baker", "type": "PERSON" }, { "confidence": 0.006049156188964844, "count": 1, "indocChainId": 11, "mention": "démocrate", "normalized": "démocrate", "type": "ORGANIZATION" }, { "confidence": 0.011113584041595459, "count": 1, "indocChainId": 12, "mention": "Washington", "normalized": "Washington", "type": "LOCATION" }, { "confidence": 0.010755836963653564, "count": 1, "indocChainId": 15, "mention": "Ronald Reagan", "normalized": "Ronald Reagan", "type": "PERSON" }, { "confidence": 0.020975351333618164, "count": 1, "indocChainId": 20, "mention": "George Bush", "normalized": "George Bush", "type": "PERSON" }, { "confidence": 0.01764160394668579, "count": 1, "indocChainId": 22, "mention": "Christina Romer", "normalized": "Christina Romer", "type": "PERSON" }, { "confidence": 0.003275454044342041, "count": 1, "indocChainId": 23, "mention": "présidente du conseil économique", "normalized": "présidente du conseil économique", "type": "TITLE" }, { "confidence": 1.0, "count": 1, "indocChainId": 28, "mention": "Goldman Sachs", "normalized": "Goldman Sachs", "type": "ORGANIZATION" }, { "confidence": 0.014990746974945068, "count": 1, "indocChainId": 29, "mention": "Jan Hatzius", "normalized": "Jan Hatzius", "type": "PERSON" }, { "confidence": 0.03833216428756714, "count": 1, "indocChainId": 42, "mention": "David Axelrod", "normalized": "David Axelrod", "type": "PERSON" }, { "confidence": 0.05773395299911499, "count": 1, "indocChainId": 46, "mention": "Harry Reid", "normalized": "Harry Reid", "type": "PERSON" }, { "confidence": 0.022663354873657227, "count": 1, "indocChainId": 47, "mention": "démocrates", "normalized": "démocrates", "type": "ORGANIZATION" }, { "confidence": 0.004793286323547363, "count": 1, "indocChainId": 50, "mention": "TARP", "normalized": "TARP", "type": "ORGANIZATION" }, { "confidence": 1.0, "count": 1, "indocChainId": 53, "mention": "http://www.lemonde.fr/ameriques/article/2010/01/21/les-etats-unis-face-au-defi-persistant-du-chomage_1294839_3222.html#xtor=RSS-3210", "normalized": "http://www.lemonde.fr/ameriques/article/2010/01/21/les-etats-unis-face-au-defi-persistant-du-chomage_1294839_3222.html#xtor=RSS-3210", "type": "IDENTIFIER:URL" } ], "requestId": "fe809e0f-8caf-4180-8f1a-cbd27258df14", "timers": { "rblJe": 13, "rexJe": 54, "rliJe": 6 } } python-0.7.4/tests/mock-data/response/fra-doc-entities.status 0000664 0000000 0000000 00000000003 12636317025 0024303 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/fra-doc-entities_linked.json 0000664 0000000 0000000 00000006562 12636317025 0025277 0 ustar 00root root 0000000 0000000 { "entities": [ { "confidence": 0.7399947032225278, "entityId": "Q30", "indocChainId": 0, "mention": "Etats-Unis" }, { "confidence": 0.7695386692779599, "entityId": "Q637413", "indocChainId": 1, "mention": "Census Bureau" }, { "confidence": 0.5632621294140603, "entityId": "Q156616", "indocChainId": 2, "mention": "Insee" }, { "confidence": 0.5647101952655027, "entityId": "Q76", "indocChainId": 4, "mention": "Barack Obama" }, { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 5, "mention": "Amérique" }, { "confidence": 0.33092102218083125, "entityId": "Q12061445", "indocChainId": 6, "mention": "Maison Blanche" }, { "confidence": 0.6351177924228053, "entityId": "Q587370", "indocChainId": 7, "mention": "Parti démocrate" }, { "confidence": 0.4383803078324337, "entityId": "Q222122", "indocChainId": 10, "mention": "Dean Baker" }, { "confidence": 0.4106734597843912, "entityId": "NEW-CLUSTER", "indocChainId": 11, "mention": "démocrate" }, { "confidence": 0.030134547096501898, "entityId": "Q61", "indocChainId": 12, "mention": "Washington" }, { "confidence": 0.09650250560984247, "entityId": "NEW-CLUSTER", "indocChainId": 14, "mention": "républicain" }, { "confidence": 0.5634191715704597, "entityId": "Q9960", "indocChainId": 15, "mention": "Ronald Reagan" }, { "confidence": 0.32451423678740127, "entityId": "Q207", "indocChainId": 20, "mention": "George Bush" }, { "confidence": 0.5312767444554036, "entityId": "Q270379", "indocChainId": 22, "mention": "Christina Romer" }, { "confidence": 0.741644907969852, "entityId": "Q193326", "indocChainId": 28, "mention": "Goldman Sachs" }, { "confidence": 0.5171464236003176, "entityId": "NEW-CLUSTER", "indocChainId": 29, "mention": "Jan Hatzius" }, { "confidence": 0.41208003203903637, "entityId": "Q2495862", "indocChainId": 33, "mention": "Congrès" }, { "confidence": 0.10281969831910404, "entityId": "NEW-CLUSTER", "indocChainId": 35, "mention": "républicains" }, { "confidence": 0.2681724823103919, "entityId": "Q519838", "indocChainId": 42, "mention": "David Axelrod" }, { "confidence": 0.626544968074185, "entityId": "Q215987", "indocChainId": 44, "mention": "Sénat" }, { "confidence": 0.3161503511291147, "entityId": "Q314459", "indocChainId": 46, "mention": "Harry Reid" }, { "confidence": 0.09461631971440848, "entityId": "Q1185830", "indocChainId": 47, "mention": "démocrates" }, { "confidence": 0.7608374999013565, "entityId": "Q2097742", "indocChainId": 50, "mention": "TARP" } ], "requestId": "88f85c50-081d-49bd-9105-2e040c50735e", "timers": { "rblJe": 10, "res": 822, "rexJe": 46, "rliJe": 6 } } python-0.7.4/tests/mock-data/response/fra-doc-entities_linked.status 0000664 0000000 0000000 00000000003 12636317025 0025631 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/fra-doc-language.json 0000664 0000000 0000000 00000001014 12636317025 0023673 0 ustar 00root root 0000000 0000000 { "languageDetections": [ { "confidence": 0.03904621249856588, "language": "fra" }, { "confidence": 0.013008506693825472, "language": "cat" }, { "confidence": 0.0122736724745941, "language": "spa" }, { "confidence": 0.009873975012486658, "language": "ron" }, { "confidence": 0.009735170679701866, "language": "por" } ], "requestId": "128145b1-fd6f-4492-899d-a68ec9d2e60a", "timers": { "rliJe": 4 } } python-0.7.4/tests/mock-data/response/fra-doc-language.status 0000664 0000000 0000000 00000000003 12636317025 0024242 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/fra-doc-morphology_complete.json 0000664 0000000 0000000 00000430631 12636317025 0026212 0 ustar 00root root 0000000 0000000 { "compounds": [], "hanReadings": [], "lemmas": [ { "lemma": "le", "text": "Les" }, { "lemma": "état", "text": "Etats" }, { "lemma": "-", "text": "-" }, { "lemma": "unir", "text": "Unis" }, { "lemma": "face", "text": "face" }, { "lemma": "à le", "text": "au" }, { "lemma": "défi", "text": "défi" }, { "lemma": "persistant", "text": "persistant" }, { "lemma": "de le", "text": "du" }, { "lemma": "chômage", "text": "chômage" }, { "lemma": "un", "text": "Un" }, { "lemma": "chômeur", "text": "chômeur" }, { "lemma": "américain", "text": "américain" }, { "lemma": "sur", "text": "sur" }, { "lemma": "deux", "text": "deux" }, { "lemma": "dire", "text": "dit" }, { "lemma": "souffrir", "text": "souffrir" }, { "lemma": "de", "text": "d'" }, { "lemma": "anxiété", "text": "anxiété" }, { "lemma": "ou", "text": "ou" }, { "lemma": "de", "text": "de" }, { "lemma": "dépression", "text": "dépression" }, { "lemma": "et", "text": "et" }, { "lemma": "avoir", "text": "a" }, { "lemma": "devoir", "text": "dû" }, { "lemma": "emprunter", "text": "emprunter" }, { "lemma": "de", "text": "de" }, { "lemma": "le", "text": "l'" }, { "lemma": "argent", "text": "argent" }, { "lemma": "à", "text": "à" }, { "lemma": "un", "text": "des" }, { "lemma": "ami", "text": "amis" }, { "lemma": ".", "text": "." }, { "lemma": "selon", "text": "Selon" }, { "lemma": "un", "text": "une" }, { "lemma": "enquête", "text": "enquête" }, { "lemma": "publier", "text": "publiée" }, { "lemma": ",", "text": "," }, { "lemma": "lundi", "text": "lundi" }, { "lemma": "18", "text": "18" }, { "lemma": "janvier", "text": "janvier" }, { "lemma": ",", "text": "," }, { "lemma": "par", "text": "par" }, { "lemma": "le", "text": "le" }, { "lemma": "Census", "text": "Census" }, { "lemma": "bureau", "text": "Bureau" }, { "lemma": "(", "text": "(" }, { "lemma": "équivalent", "text": "équivalent" }, { "lemma": "de", "text": "de" }, { "lemma": "le", "text": "l'" }, { "lemma": "Insee", "text": "Insee" }, { "lemma": ")", "text": ")" }, { "lemma": ",", "text": "," }, { "lemma": "en", "text": "en" }, { "lemma": "deux", "text": "deux" }, { "lemma": "an", "text": "ans" }, { "lemma": ",", "text": "," }, { "lemma": "le", "text": "le" }, { "lemma": "nombre", "text": "nombre" }, { "lemma": "de", "text": "de" }, { "lemma": "couple", "text": "couples" }, { "lemma": "à le", "text": "au" }, { "lemma": "chômage", "text": "chômage" }, { "lemma": "avec", "text": "avec" }, { "lemma": "enfant", "text": "enfants" }, { "lemma": "mineur", "text": "mineurs" }, { "lemma": "avoir", "text": "a" }, { "lemma": "doubler", "text": "doublé" }, { "lemma": ".", "text": "." }, { "lemma": "près", "text": "Près" }, { "lemma": "de", "text": "de" }, { "lemma": "40", "text": "40" }, { "lemma": "%", "text": "%" }, { "lemma": "de le", "text": "des" }, { "lemma": "ce", "text": "ces" }, { "lemma": "parent", "text": "parents" }, { "lemma": "noter", "text": "notent" }, { "lemma": "de le", "text": "des" }, { "lemma": "\"", "text": "\"" }, { "lemma": "modification", "text": "modifications" }, { "lemma": "de", "text": "de" }, { "lemma": "comportement", "text": "comportement" }, { "lemma": "\"", "text": "\"" }, { "lemma": "chez", "text": "chez" }, { "lemma": "leur", "text": "leurs" }, { "lemma": "enfant", "text": "enfants" }, { "lemma": "que", "text": "qu'" }, { "lemma": "il", "text": "ils" }, { "lemma": "attribuer", "text": "attribuent" }, { "lemma": "à", "text": "à" }, { "lemma": "leur", "text": "leur" }, { "lemma": "perte", "text": "perte" }, { "lemma": "de le", "text": "du" }, { "lemma": "travail", "text": "travail" }, { "lemma": ".", "text": "." }, { "lemma": "le", "text": "La" }, { "lemma": "moitié", "text": "moitié" }, { "lemma": "évoquer", "text": "évoquent" }, { "lemma": "un", "text": "une" }, { "lemma": "\"", "text": "\"" }, { "lemma": "transformation", "text": "transformation" }, { "lemma": "fondamental", "text": "fondamentale" }, { "lemma": "\"", "text": "\"" }, { "lemma": "de", "text": "de" }, { "lemma": "leur", "text": "leur" }, { "lemma": "existence", "text": "existence" }, { "lemma": "-", "text": "-" }, { "lemma": "le", "text": "le" }, { "lemma": "premier", "text": "premier" }, { "lemma": "de le", "text": "des" }, { "lemma": "changement", "text": "changements" }, { "lemma": "consister", "text": "consistant" }, { "lemma": "en", "text": "en" }, { "lemma": "le", "text": "la" }, { "lemma": "perte", "text": "perte" }, { "lemma": "presque", "text": "presque" }, { "lemma": "instantané", "text": "instantanée" }, { "lemma": "de", "text": "de" }, { "lemma": "tout", "text": "toute" }, { "lemma": "couverture", "text": "couverture" }, { "lemma": "social", "text": "sociale" }, { "lemma": ".", "text": "." }, { "lemma": "durant", "text": "Durant" }, { "lemma": "tout", "text": "tout" }, { "lemma": "le", "text": "le" }, { "lemma": "mois", "text": "mois" }, { "lemma": "de", "text": "de" }, { "lemma": "décembre", "text": "décembre" }, { "lemma": ",", "text": "," }, { "lemma": "à", "text": "à" }, { "lemma": "le", "text": "l'" }, { "lemma": "approche", "text": "approche" }, { "lemma": "de", "text": "de" }, { "lemma": "le", "text": "l'" }, { "lemma": "anniversaire", "text": "anniversaire" }, { "lemma": "de", "text": "de" }, { "lemma": "le", "text": "la" }, { "lemma": "prise", "text": "prise" }, { "lemma": "de", "text": "de" }, { "lemma": "fonction", "text": "fonctions" }, { "lemma": "de le", "text": "du" }, { "lemma": "président", "text": "président" }, { "lemma": "Barack", "text": "Barack" }, { "lemma": "Obama", "text": "Obama" }, { "lemma": ",", "text": "," }, { "lemma": "le", "text": "le" }, { "lemma": "20", "text": "20" }, { "lemma": "janvier", "text": "janvier" }, { "lemma": "2009", "text": "2009" }, { "lemma": ",", "text": "," }, { "lemma": "le", "text": "les" }, { "lemma": "reportage", "text": "reportages" }, { "lemma": "et", "text": "et" }, { "lemma": "le", "text": "les" }, { "lemma": "enquête", "text": "enquêtes" }, { "lemma": "sur", "text": "sur" }, { "lemma": "le", "text": "les" }, { "lemma": "conséquence", "text": "conséquences" }, { "lemma": "de", "text": "de" }, { "lemma": "ce", "text": "ces" }, { "lemma": "destruction", "text": "destructions" }, { "lemma": "de", "text": "d'" }, { "lemma": "emploi", "text": "emploi" }, { "lemma": "être", "text": "sont" }, { "lemma": "devenir", "text": "devenus" }, { "lemma": "un", "text": "une" }, { "lemma": "préoccupation", "text": "préoccupation" }, { "lemma": "obsédant", "text": "obsédante" }, { "lemma": "dans", "text": "dans" }, { "lemma": "le", "text": "les" }, { "lemma": "médias", "text": "médias" }, { "lemma": ".", "text": "." }, { "lemma": "\"", "text": "\"" }, { "lemma": "je", "text": "Je" }, { "lemma": "me", "text": "me" }, { "lemma": "sentir", "text": "sens" }, { "lemma": "comme", "text": "comme" }, { "lemma": "le", "text": "la" }, { "lemma": "lie", "text": "lie" }, { "lemma": "de", "text": "de" }, { "lemma": "le", "text": "la" }, { "lemma": "terre", "text": "terre" }, { "lemma": "\"", "text": "\"" }, { "lemma": ",", "text": "," }, { "lemma": "dire", "text": "disait" }, { "lemma": "récemment", "text": "récemment" }, { "lemma": "un", "text": "un" }, { "lemma": "chômeur", "text": "chômeur" }, { "lemma": "à", "text": "à" }, { "lemma": "un", "text": "une" }, { "lemma": "heure", "text": "heure" }, { "lemma": "de", "text": "de" }, { "lemma": "grand", "text": "grande" }, { "lemma": "écoute", "text": "écoute" }, { "lemma": ".", "text": "." }, { "lemma": "alors", "text": "Alors" }, { "lemma": ",", "text": "," }, { "lemma": "le", "text": "l'" }, { "lemma": "Amérique", "text": "Amérique" }, { "lemma": "découvrir", "text": "découvre" }, { "lemma": "sur", "text": "sur" }, { "lemma": "le", "text": "les" }, { "lemma": "écran", "text": "écrans" }, { "lemma": "tout", "text": "tous" }, { "lemma": "ce", "text": "ces" }, { "lemma": "visage", "text": "visages" }, { "lemma": "ravager", "text": "ravagés" }, { "lemma": "qui", "text": "qui" }, { "lemma": "évoquer", "text": "évoquent" }, { "lemma": "leur", "text": "leur" }, { "lemma": "\"", "text": "\"" }, { "lemma": "honte", "text": "honte" }, { "lemma": "\"", "text": "\"" }, { "lemma": "et", "text": "et" }, { "lemma": "se", "text": "s'" }, { "lemma": "interroger", "text": "interroge" }, { "lemma": ":", "text": ":" }, { "lemma": "10", "text": "10" }, { "lemma": "%", "text": "%" }, { "lemma": "de", "text": "de" }, { "lemma": "chômage", "text": "chômage" }, { "lemma": ",", "text": "," }, { "lemma": "comment", "text": "comment" }, { "lemma": "en", "text": "en" }, { "lemma": "est", "text": "est" }, { "lemma": "-", "text": "-" }, { "lemma": "on", "text": "on" }, { "lemma": "arriver", "text": "arrivé" }, { "lemma": "là", "text": "là" }, { "lemma": "?", "text": "?" }, { "lemma": "pour", "text": "Pour" }, { "lemma": "beaucoup", "text": "beaucoup" }, { "lemma": "de", "text": "d'" }, { "lemma": "analyste", "text": "analystes" }, { "lemma": ",", "text": "," }, { "lemma": "ce", "text": "c'" }, { "lemma": "être", "text": "est" }, { "lemma": "pour", "text": "pour" }, { "lemma": "avoir", "text": "avoir" }, { "lemma": "négliger", "text": "négligé" }, { "lemma": "le", "text": "l'" }, { "lemma": "impact", "text": "impact" }, { "lemma": "de le", "text": "du" }, { "lemma": "chômage", "text": "chômage" }, { "lemma": "alors", "text": "alors" }, { "lemma": "que", "text": "que" }, { "lemma": "se", "text": "se" }, { "lemma": "profiler", "text": "profilaient" }, { "lemma": "de le", "text": "des" }, { "lemma": "signe", "text": "signes" }, { "lemma": "de", "text": "de" }, { "lemma": "reprise", "text": "reprise" }, { "lemma": "économique", "text": "économique" }, { "lemma": "(", "text": "(" }, { "lemma": "et", "text": "et" }, { "lemma": "surtout", "text": "surtout" }, { "lemma": "financier", "text": "financière" }, { "lemma": ")", "text": ")" }, { "lemma": "que", "text": "que" }, { "lemma": "le", "text": "la" }, { "lemma": "maison", "text": "Maison" }, { "lemma": "blanc", "text": "Blanche" }, { "lemma": "et", "text": "et" }, { "lemma": "le", "text": "le" }, { "lemma": "parti", "text": "Parti" }, { "lemma": "démocrate", "text": "démocrate" }, { "lemma": "se", "text": "se" }, { "lemma": "trouver", "text": "trouvent" }, { "lemma": "confronter", "text": "confrontés" }, { "lemma": "à", "text": "à" }, { "lemma": "un", "text": "une" }, { "lemma": "fort", "text": "forte" }, { "lemma": "désaffection", "text": "désaffection" }, { "lemma": "de", "text": "de" }, { "lemma": "le", "text": "l'" }, { "lemma": "opinion", "text": "opinion" }, { "lemma": "à", "text": "à" }, { "lemma": "dix", "text": "dix" }, { "lemma": "mois", "text": "mois" }, { "lemma": "de le", "text": "des" }, { "lemma": "élection", "text": "élections" }, { "lemma": "à", "text": "à" }, { "lemma": "mi", "text": "mi" }, { "lemma": "-", "text": "-" }, { "lemma": "mandat", "text": "mandat" }, { "lemma": "de", "text": "de" }, { "lemma": "novembre", "text": "novembre" }, { "lemma": ".", "text": "." }, { "lemma": "alors", "text": "Alors" }, { "lemma": "que", "text": "que" }, { "lemma": "le", "text": "le" }, { "lemma": "thème", "text": "thème" }, { "lemma": "de", "text": "de" }, { "lemma": "le", "text": "l'" }, { "lemma": "emploi", "text": "emploi" }, { "lemma": "envahir", "text": "envahissait" }, { "lemma": "le", "text": "le" }, { "lemma": "champ", "text": "champ" }, { "lemma": "de le", "text": "des" }, { "lemma": "préoccupation", "text": "préoccupations" }, { "lemma": ",", "text": "," }, { "lemma": "M.", "text": "M." }, { "lemma": "Obama", "text": "Obama" }, { "lemma": "avoir", "text": "a" }, { "lemma": "continuer", "text": "continué" }, { "lemma": "de", "text": "de" }, { "lemma": "donner", "text": "donner" }, { "lemma": "le", "text": "la" }, { "lemma": "priorité", "text": "priorité" }, { "lemma": "à", "text": "à" }, { "lemma": "le", "text": "la" }, { "lemma": "réforme", "text": "réforme" }, { "lemma": "de", "text": "de" }, { "lemma": "le", "text": "la" }, { "lemma": "santé", "text": "santé" }, { "lemma": ",", "text": "," }, { "lemma": "à", "text": "à" }, { "lemma": "le", "text": "la" }, { "lemma": "lutte", "text": "lutte" }, { "lemma": "contre", "text": "contre" }, { "lemma": "le", "text": "le" }, { "lemma": "réchauffement", "text": "réchauffement" }, { "lemma": "climatique", "text": "climatique" }, { "lemma": "ou", "text": "ou" }, { "lemma": "le", "text": "la" }, { "lemma": "régulation", "text": "régulation" }, { "lemma": "financier", "text": "financière" }, { "lemma": ".", "text": "." }, { "lemma": "tout", "text": "Tous" }, { "lemma": "sujet", "text": "sujets" }, { "lemma": "essentiel", "text": "essentiels" }, { "lemma": "mais", "text": "mais" }, { "lemma": "\"", "text": "\"" }, { "lemma": "bien", "text": "bien" }, { "lemma": "moins", "text": "moins" }, { "lemma": "palpable", "text": "palpables" }, { "lemma": ",", "text": "," }, { "lemma": "dans", "text": "dans" }, { "lemma": "un", "text": "une" }, { "lemma": "période", "text": "période" }, { "lemma": "de", "text": "de" }, { "lemma": "crise", "text": "crise" }, { "lemma": "aigu", "text": "aiguë" }, { "lemma": ",", "text": "," }, { "lemma": "que", "text": "que" }, { "lemma": "le", "text": "le" }, { "lemma": "chômage", "text": "chômage" }, { "lemma": ",", "text": "," }, { "lemma": "qui", "text": "qui" }, { "lemma": "araser", "text": "arase" }, { "lemma": "tout", "text": "tout" }, { "lemma": "\"", "text": "\"" }, { "lemma": ",", "text": "," }, { "lemma": "note", "text": "note" }, { "lemma": "Dean", "text": "Dean" }, { "lemma": "Baker", "text": "Baker" }, { "lemma": ",", "text": "," }, { "lemma": "codirecteur", "text": "codirecteur" }, { "lemma": "de le", "text": "du" }, { "lemma": "centre", "text": "Centre" }, { "lemma": "de", "text": "de" }, { "lemma": "recherche", "text": "recherches" }, { "lemma": "sur", "text": "sur" }, { "lemma": "le", "text": "les" }, { "lemma": "politique", "text": "politiques" }, { "lemma": "économique", "text": "économiques" }, { "lemma": ",", "text": "," }, { "lemma": "un", "text": "un" }, { "lemma": "groupe", "text": "groupe" }, { "lemma": "de", "text": "de" }, { "lemma": "réflexion", "text": "réflexion" }, { "lemma": "démocrate", "text": "démocrate" }, { "lemma": "à", "text": "à" }, { "lemma": "Washington", "text": "Washington" }, { "lemma": ".", "text": "." }, { "lemma": "un", "text": "Une" }, { "lemma": "étude", "text": "étude" }, { "lemma": "de le", "text": "du" }, { "lemma": "département", "text": "département" }, { "lemma": "de le", "text": "du" }, { "lemma": "travail", "text": "travail" }, { "lemma": ",", "text": "," }, { "lemma": "publier", "text": "publiée" }, { "lemma": "le", "text": "le" }, { "lemma": "8", "text": "8" }, { "lemma": "janvier", "text": "janvier" }, { "lemma": ",", "text": "," }, { "lemma": "montrer", "text": "montre" }, { "lemma": "un", "text": "une" }, { "lemma": "différence", "text": "différence" }, { "lemma": "essentiel", "text": "essentielle" }, { "lemma": "entre", "text": "entre" }, { "lemma": "le", "text": "l'" }, { "lemma": "impact", "text": "impact" }, { "lemma": "de", "text": "de" }, { "lemma": "le", "text": "la" }, { "lemma": "crise", "text": "crise" }, { "lemma": "actuel", "text": "actuelle" }, { "lemma": "sur", "text": "sur" }, { "lemma": "le", "text": "l'" }, { "lemma": "emploi", "text": "emploi" }, { "lemma": "et", "text": "et" }, { "lemma": "le", "text": "les" }, { "lemma": "précédent", "text": "précédentes" }, { "lemma": "récession", "text": "récessions" }, { "lemma": ".", "text": "." }, { "lemma": "lors", "text": "Lors" }, { "lemma": "de", "text": "de" }, { "lemma": "celui", "text": "celles" }, { "lemma": "de", "text": "de" }, { "lemma": "1974", "text": "1974" }, { "lemma": "-", "text": "-" }, { "lemma": "1976", "text": "1976" }, { "lemma": "et", "text": "et" }, { "lemma": "de", "text": "de" }, { "lemma": "1990", "text": "1990" }, { "lemma": "-", "text": "-" }, { "lemma": "1993", "text": "1993" }, { "lemma": ",", "text": "," }, { "lemma": "le", "text": "le" }, { "lemma": "chômage", "text": "chômage" }, { "lemma": "être", "text": "était" }, { "lemma": "moins", "text": "moins" }, { "lemma": "important", "text": "important" }, { "lemma": ",", "text": "," }, { "lemma": "tant", "text": "tant" }, { "lemma": "en", "text": "en" }, { "lemma": "chiffre", "text": "chiffres" }, { "lemma": "absolu", "text": "absolus" }, { "lemma": "que", "text": "qu'" }, { "lemma": "en", "text": "en" }, { "lemma": "durée", "text": "durée" }, { "lemma": ".", "text": "." }, { "lemma": "ce", "text": "Cette" }, { "lemma": "comparaison", "text": "comparaison" }, { "lemma": "reste", "text": "reste" }, { "lemma": "valide", "text": "valide" }, { "lemma": "pour", "text": "pour" }, { "lemma": "le", "text": "la" }, { "lemma": "récession", "text": "récession" }, { "lemma": "de", "text": "de" }, { "lemma": "1981", "text": "1981" }, { "lemma": "-", "text": "-" }, { "lemma": "1983", "text": "1983" }, { "lemma": ",", "text": "," }, { "lemma": "qui", "text": "qui" }, { "lemma": "vivre", "text": "vit" }, { "lemma": "le", "text": "le" }, { "lemma": "président", "text": "président" }, { "lemma": "républicain", "text": "républicain" }, { "lemma": "Ronald", "text": "Ronald" }, { "lemma": "Reagan", "text": "Reagan" }, { "lemma": ",", "text": "," }, { "lemma": "un", "text": "un" }, { "lemma": "an", "text": "an" }, { "lemma": "après", "text": "après" }, { "lemma": "son", "text": "son" }, { "lemma": "élection", "text": "élection" }, { "lemma": ",", "text": "," }, { "lemma": "enregistrer", "text": "enregistrer" }, { "lemma": "son", "text": "son" }, { "lemma": "plus", "text": "plus" }, { "lemma": "bas", "text": "bas" }, { "lemma": "soutien", "text": "soutien" }, { "lemma": "dans", "text": "dans" }, { "lemma": "le", "text": "l'" }, { "lemma": "opinion", "text": "opinion" }, { "lemma": ".", "text": "." }, { "lemma": "pour", "text": "Pour" }, { "lemma": "résumer", "text": "résumer" }, { "lemma": "le", "text": "le" }, { "lemma": "désastre", "text": "désastre" }, { "lemma": "actuel", "text": "actuel" }, { "lemma": ":", "text": ":" }, { "lemma": "le", "text": "les" }, { "lemma": "état", "text": "Etats" }, { "lemma": "-", "text": "-" }, { "lemma": "uni", "text": "Unis" }, { "lemma": "avoir", "text": "ont" }, { "lemma": "perdre", "text": "perdu" }, { "lemma": "depuis", "text": "depuis" }, { "lemma": "deux", "text": "deux" }, { "lemma": "an", "text": "ans" }, { "lemma": "5,24", "text": "5,24" }, { "lemma": "%", "text": "%" }, { "lemma": "de", "text": "de" }, { "lemma": "leur", "text": "leur" }, { "lemma": "emploi", "text": "emploi" }, { "lemma": ",", "text": "," }, { "lemma": "alors", "text": "alors" }, { "lemma": "que", "text": "que" }, { "lemma": "le", "text": "la" }, { "lemma": "chute", "text": "chute" }, { "lemma": "ne", "text": "n'" }, { "lemma": "avoir", "text": "avait" }, { "lemma": "être", "text": "été" }, { "lemma": "que", "text": "que" }, { "lemma": "de", "text": "de" }, { "lemma": "1,4", "text": "1,4" }, { "lemma": "%", "text": "%" }, { "lemma": "à", "text": "à" }, { "lemma": "3", "text": "3" }, { "lemma": "%", "text": "%" }, { "lemma": ",", "text": "," }, { "lemma": "à le", "text": "au" }, { "lemma": "pire", "text": "pire" }, { "lemma": ",", "text": "," }, { "lemma": "lors", "text": "lors" }, { "lemma": "de le", "text": "des" }, { "lemma": "récession", "text": "récessions" }, { "lemma": "précédent", "text": "précédentes" }, { "lemma": ".", "text": "." }, { "lemma": "entre", "text": "Entre" }, { "lemma": "chômage", "text": "chômage" }, { "lemma": "total", "text": "total" }, { "lemma": "et", "text": "et" }, { "lemma": "partiel", "text": "partiel" }, { "lemma": ",", "text": "," }, { "lemma": "le", "text": "la" }, { "lemma": "crise", "text": "crise" }, { "lemma": "toucher", "text": "touche" }, { "lemma": "le", "text": "le" }, { "lemma": "travail", "text": "travail" }, { "lemma": "de", "text": "de" }, { "lemma": "près", "text": "près" }, { "lemma": "d", "text": "d" }, { "lemma": "'", "text": "'" }, { "lemma": "un", "text": "un" }, { "lemma": "américain", "text": "Américain" }, { "lemma": "sur", "text": "sur" }, { "lemma": "cinq", "text": "cinq" }, { "lemma": ".", "text": "." }, { "lemma": "ne", "text": "N'" }, { "lemma": "avoir", "text": "ayant" }, { "lemma": "cesser", "text": "cessé" }, { "lemma": "de", "text": "de" }, { "lemma": "répéter", "text": "répéter" }, { "lemma": "que", "text": "que" }, { "lemma": "son", "text": "son" }, { "lemma": "pays", "text": "pays" }, { "lemma": "affronter", "text": "affrontait" }, { "lemma": "\"", "text": "\"" }, { "lemma": "le", "text": "la" }, { "lemma": "pire", "text": "pire" }, { "lemma": "crise", "text": "crise" }, { "lemma": "depuis", "text": "depuis" }, { "lemma": "le", "text": "la" }, { "lemma": "grand", "text": "Grande" }, { "lemma": "dépression", "text": "Dépression" }, { "lemma": "\"", "text": "\"" }, { "lemma": "de le", "text": "des" }, { "lemma": "année", "text": "années" }, { "lemma": "1930", "text": "1930" }, { "lemma": ",", "text": "," }, { "lemma": "Barack", "text": "Barack" }, { "lemma": "Obama", "text": "Obama" }, { "lemma": "avoir", "text": "avait" }, { "lemma": "donner", "text": "donné" }, { "lemma": "le", "text": "le" }, { "lemma": "sentiment", "text": "sentiment" }, { "lemma": "de", "text": "d'" }, { "lemma": "être", "text": "être" }, { "lemma": "très", "text": "très" }, { "lemma": "conscient", "text": "conscient" }, { "lemma": "de le", "text": "du" }, { "lemma": "problème", "text": "problème" }, { "lemma": ".", "text": "." }, { "lemma": "or", "text": "Or" }, { "lemma": "là", "text": "là" }, { "lemma": "être", "text": "est" }, { "lemma": "le", "text": "le" }, { "lemma": "paradoxe", "text": "paradoxe" }, { "lemma": ":", "text": ":" }, { "lemma": "un", "text": "une" }, { "lemma": "fois", "text": "fois" }, { "lemma": "élu", "text": "élu" }, { "lemma": ",", "text": "," }, { "lemma": "le", "text": "le" }, { "lemma": "président", "text": "président" }, { "lemma": "être", "text": "est" }, { "lemma": "apparaître", "text": "apparu" }, { "lemma": "comme", "text": "comme" }, { "lemma": "un", "text": "un" }, { "lemma": "dirigeant", "text": "dirigeant" }, { "lemma": "qui", "text": "qui" }, { "lemma": "avoir", "text": "a" }, { "lemma": "faire", "text": "fait" }, { "lemma": "un", "text": "un" }, { "lemma": "diagnostic", "text": "diagnostic" }, { "lemma": "correct", "text": "correct" }, { "lemma": "mais", "text": "mais" }, { "lemma": "ne", "text": "n'" }, { "lemma": "en", "text": "en" }, { "lemma": "avoir", "text": "a" }, { "lemma": "tirer", "text": "tiré" }, { "lemma": "aucun", "text": "aucune" }, { "lemma": "conclusion", "text": "conclusion" }, { "lemma": ".", "text": "." }, { "lemma": "le", "text": "L'" }, { "lemma": "Amérique", "text": "Amérique" }, { "lemma": "avoir", "text": "avait" }, { "lemma": "perdre", "text": "perdu" }, { "lemma": "3078000", "text": "3 078 000" }, { "lemma": "chômeur", "text": "chômeurs" }, { "lemma": "lors", "text": "lors" }, { "lemma": "de", "text": "de" }, { "lemma": "le", "text": "la" }, { "lemma": "dernier", "text": "dernière" }, { "lemma": "année", "text": "année" }, { "lemma": "de le", "text": "du" }, { "lemma": "mandat", "text": "mandat" }, { "lemma": "de", "text": "de" }, { "lemma": "George", "text": "George" }, { "lemma": "Bush", "text": "Bush" }, { "lemma": ";", "text": ";" }, { "lemma": "il", "text": "elle" }, { "lemma": "en", "text": "en" }, { "lemma": "avoir", "text": "a" }, { "lemma": "perdre", "text": "perdu" }, { "lemma": "4228000", "text": "4 228 000" }, { "lemma": "en", "text": "en" }, { "lemma": "un", "text": "un" }, { "lemma": "an", "text": "an" }, { "lemma": "de", "text": "de" }, { "lemma": "présidence", "text": "présidence" }, { "lemma": "Obama", "text": "Obama" }, { "lemma": "!", "text": "!" }, { "lemma": "le", "text": "Le" }, { "lemma": "10", "text": "10" }, { "lemma": "janvier", "text": "janvier" }, { "lemma": ",", "text": "," }, { "lemma": "invoquer", "text": "invoquant" }, { "lemma": "\"", "text": "\"" }, { "lemma": "le", "text": "l'" }, { "lemma": "urgence", "text": "urgence" }, { "lemma": "\"", "text": "\"" }, { "lemma": ",", "text": "," }, { "lemma": "Christina", "text": "Christina" }, { "lemma": "Romer", "text": "Romer" }, { "lemma": ",", "text": "," }, { "lemma": "président", "text": "présidente" }, { "lemma": "de le", "text": "du" }, { "lemma": "conseil", "text": "conseil" }, { "lemma": "économique", "text": "économique" }, { "lemma": "de", "text": "de" }, { "lemma": "M.", "text": "M." }, { "lemma": "Obama", "text": "Obama" }, { "lemma": ",", "text": "," }, { "lemma": "avoir", "text": "a" }, { "lemma": "appeler", "text": "appelé" }, { "lemma": "à", "text": "à" }, { "lemma": "vite", "text": "vite" }, { "lemma": "injecter", "text": "injecter" }, { "lemma": "75", "text": "75" }, { "lemma": "milliard", "text": "milliards" }, { "lemma": "de", "text": "de" }, { "lemma": "dollar", "text": "dollars" }, { "lemma": "supplémentaire", "text": "supplémentaires" }, { "lemma": "pour", "text": "pour" }, { "lemma": "régénérer", "text": "régénérer" }, { "lemma": "le", "text": "l'" }, { "lemma": "emploi", "text": "emploi" }, { "lemma": ".", "text": "." }, { "lemma": "nul", "text": "Nul" }, { "lemma": "ne", "text": "ne" }, { "lemma": "douter", "text": "doute" }, { "lemma": "que", "text": "que" }, { "lemma": "M.", "text": "M." }, { "lemma": "Obama", "text": "Obama" }, { "lemma": "privilégier", "text": "privilégiera" }, { "lemma": "ce", "text": "cette" }, { "lemma": "nécessité", "text": "nécessité" }, { "lemma": "en", "text": "en" }, { "lemma": "2010", "text": "2010" }, { "lemma": ".", "text": "." }, { "lemma": "comment", "text": "Comment" }, { "lemma": "remédier", "text": "remédier" }, { "lemma": "à le", "text": "au" }, { "lemma": "problème", "text": "problème" }, { "lemma": "?", "text": "?" }, { "lemma": "le", "text": "La" }, { "lemma": "plupart", "text": "plupart" }, { "lemma": "de le", "text": "des" }, { "lemma": "analyste", "text": "analystes" }, { "lemma": ",", "text": "," }, { "lemma": "constater", "text": "constatant" }, { "lemma": "le", "text": "le" }, { "lemma": "\"", "text": "\"" }, { "lemma": "découplage", "text": "découplage" }, { "lemma": "\"", "text": "\"" }, { "lemma": "entre", "text": "entre" }, { "lemma": "le", "text": "la" }, { "lemma": "reprise", "text": "reprise" }, { "lemma": "économique", "text": "économique" }, { "lemma": "et", "text": "et" }, { "lemma": "celui", "text": "celle" }, { "lemma": "de", "text": "de" }, { "lemma": "le", "text": "l'" }, { "lemma": "emploi", "text": "emploi" }, { "lemma": ",", "text": "," }, { "lemma": "être", "text": "sont" }, { "lemma": "circonspect", "text": "circonspects" }, { "lemma": ".", "text": "." }, { "lemma": "chef", "text": "Chef" }, { "lemma": "économiste", "text": "économiste" }, { "lemma": "de", "text": "de" }, { "lemma": "Goldman", "text": "Goldman" }, { "lemma": "Sachs", "text": "Sachs" }, { "lemma": ",", "text": "," }, { "lemma": "jan", "text": "Jan" }, { "lemma": "Hatzius", "text": "Hatzius" }, { "lemma": ",", "text": "," }, { "lemma": "dans", "text": "dans" }, { "lemma": "un", "text": "un" }, { "lemma": "texte", "text": "texte" }, { "lemma": "intituler", "text": "intitulé" }, { "lemma": "\"", "text": "\"" }, { "lemma": "10", "text": "10" }, { "lemma": "question", "text": "questions" }, { "lemma": "pour", "text": "pour" }, { "lemma": "2010", "text": "2010" }, { "lemma": "\"", "text": "\"" }, { "lemma": ",", "text": "," }, { "lemma": "se", "text": "s'" }, { "lemma": "attendre", "text": "attend" }, { "lemma": "\"", "text": "\"" }, { "lemma": "à", "text": "à" }, { "lemma": "un", "text": "un" }, { "lemma": "solde", "text": "solde" }, { "lemma": "positif", "text": "positif" }, { "lemma": "de", "text": "de" }, { "lemma": "100000", "text": "100 000" }, { "lemma": "emploi", "text": "emplois" }, { "lemma": "par", "text": "par" }, { "lemma": "mois", "text": "mois" }, { "lemma": "dès", "text": "dès" }, { "lemma": "le", "text": "le" }, { "lemma": "second", "text": "second" }, { "lemma": "trimestre", "text": "trimestre" }, { "lemma": ",", "text": "," }, { "lemma": "insuffisant", "text": "insuffisant" }, { "lemma": "pour", "text": "pour" }, { "lemma": "modifier", "text": "modifier" }, { "lemma": "significativement", "text": "significativement" }, { "lemma": "le", "text": "le" }, { "lemma": "taux", "text": "taux" }, { "lemma": "de", "text": "de" }, { "lemma": "chômage", "text": "chômage" }, { "lemma": "\"", "text": "\"" }, { "lemma": ".", "text": "." }, { "lemma": "compte", "text": "Compte" }, { "lemma": "tenu", "text": "tenu" }, { "lemma": "de", "text": "de" }, { "lemma": "leur", "text": "leur" }, { "lemma": "évolution", "text": "évolution" }, { "lemma": "démographique", "text": "démographique" }, { "lemma": ",", "text": "," }, { "lemma": "le", "text": "les" }, { "lemma": "état", "text": "Etats" }, { "lemma": "-", "text": "-" }, { "lemma": "uni", "text": "Unis" }, { "lemma": "devoir", "text": "doivent" }, { "lemma": "en", "text": "en" }, { "lemma": "effet", "text": "effet" }, { "lemma": "créer", "text": "créer" }, { "lemma": "100000", "text": "100 000" }, { "lemma": "emploi", "text": "emplois" }, { "lemma": "mensuel", "text": "mensuels" }, { "lemma": "pour", "text": "pour" }, { "lemma": "juste", "text": "juste" }, { "lemma": "stabiliser", "text": "stabiliser" }, { "lemma": "le", "text": "l'" }, { "lemma": "emploi", "text": "emploi" }, { "lemma": ".", "text": "." }, { "lemma": "Dean", "text": "Dean" }, { "lemma": "Baker", "text": "Baker" }, { "lemma": "expliquer", "text": "explique" }, { "lemma": "encore", "text": "encore" }, { "lemma": "que", "text": "que" }, { "lemma": "le", "text": "la" }, { "lemma": "marge", "text": "marge" }, { "lemma": "de", "text": "de" }, { "lemma": "manoeuvre", "text": "manoeuvre" }, { "lemma": "présidentiel", "text": "présidentielle" }, { "lemma": "être", "text": "est" }, { "lemma": "restreindre", "text": "restreinte" }, { "lemma": ":", "text": ":" }, { "lemma": "\"", "text": "\"" }, { "lemma": "Obama", "text": "Obama" }, { "lemma": "avoir", "text": "a" }, { "lemma": "rater", "text": "raté" }, { "lemma": "le", "text": "le" }, { "lemma": "coche", "text": "coche" }, { "lemma": "en", "text": "en" }, { "lemma": "limiter", "text": "limitant" }, { "lemma": "son", "text": "son" }, { "lemma": "plan", "text": "plan" }, { "lemma": "de", "text": "de" }, { "lemma": "relance", "text": "relance" }, { "lemma": ".", "text": "." }, { "lemma": "maintenant", "text": "Maintenant" }, { "lemma": ",", "text": "," }, { "lemma": "il", "text": "il" }, { "lemma": "lui", "text": "lui" }, { "lemma": "être", "text": "est" }, { "lemma": "politiquement", "text": "politiquement" }, { "lemma": "impossible", "text": "impossible" }, { "lemma": "de", "text": "de" }, { "lemma": "retourner", "text": "retourner" }, { "lemma": "devant", "text": "devant" }, { "lemma": "le", "text": "le" }, { "lemma": "congrès", "text": "Congrès" }, { "lemma": "pour", "text": "pour" }, { "lemma": "le", "text": "l'" }, { "lemma": "augmenter", "text": "augmenter" }, { "lemma": ".", "text": "." }, { "lemma": "le", "text": "Les" }, { "lemma": "conséquence", "text": "conséquences" }, { "lemma": "être", "text": "sont" }, { "lemma": "désastreux", "text": "désastreuses" }, { "lemma": ".", "text": "." }, { "lemma": "même", "text": "Même" }, { "lemma": "si", "text": "s'" }, { "lemma": "il", "text": "il" }, { "lemma": "lui", "text": "lui" }, { "lemma": "rester", "text": "reste" }, { "lemma": "200", "text": "200" }, { "lemma": "milliard", "text": "milliards" }, { "lemma": "de", "text": "de" }, { "lemma": "dollar", "text": "dollars" }, { "lemma": "à", "text": "à" }, { "lemma": "dépenser", "text": "dépenser" }, { "lemma": "(", "text": "(" }, { "lemma": "sur", "text": "sur" }, { "lemma": "787", "text": "787" }, { "lemma": "milliard", "text": "milliards" }, { "lemma": ")", "text": ")" }, { "lemma": ",", "text": "," }, { "lemma": "le", "text": "l'" }, { "lemma": "essentiel", "text": "essentiel" }, { "lemma": "de", "text": "de" }, { "lemma": "le", "text": "l'" }, { "lemma": "impact", "text": "impact" }, { "lemma": "de le", "text": "du" }, { "lemma": "plan", "text": "plan" }, { "lemma": "être", "text": "est" }, { "lemma": "passer", "text": "passé" }, { "lemma": ".", "text": "." }, { "lemma": "\"", "text": "\"" }, { "lemma": "le", "text": "Le" }, { "lemma": "pire", "text": "pire" }, { "lemma": ",", "text": "," }, { "lemma": "selon", "text": "selon" }, { "lemma": "lui", "text": "lui" }, { "lemma": ",", "text": "," }, { "lemma": "être", "text": "est" }, { "lemma": "que", "text": "que" }, { "lemma": "le", "text": "le" }, { "lemma": "président", "text": "président" }, { "lemma": "avoir", "text": "a" }, { "lemma": "faire", "text": "fait" }, { "lemma": "son", "text": "son" }, { "lemma": "choix", "text": "choix" }, { "lemma": "en", "text": "en" }, { "lemma": "tout", "text": "toute" }, { "lemma": "connaissance", "text": "connaissance" }, { "lemma": "de", "text": "de" }, { "lemma": "cause", "text": "cause" }, { "lemma": ",", "text": "," }, { "lemma": "pour", "text": "pour" }, { "lemma": "\"", "text": "\"" }, { "lemma": "privilégier", "text": "privilégier" }, { "lemma": "le", "text": "la" }, { "lemma": "politique", "text": "politique" }, { "lemma": "\"", "text": "\"" }, { "lemma": ".", "text": "." }, { "lemma": "ce", "text": "C'" }, { "lemma": "être", "text": "est" }, { "lemma": "-", "text": "-" }, { "lemma": "à", "text": "à" }, { "lemma": "-", "text": "-" }, { "lemma": "dire", "text": "dire" }, { "lemma": "un", "text": "un" }, { "lemma": "compromis", "text": "compromis" }, { "lemma": "avec", "text": "avec" }, { "lemma": "certain", "text": "certains" }, { "lemma": "républicain", "text": "républicains" }, { "lemma": "que", "text": "qu'" }, { "lemma": "il", "text": "il" }, { "lemma": "ne", "text": "n'" }, { "lemma": "avoir", "text": "a" }, { "lemma": "jamais", "text": "jamais" }, { "lemma": "obtenir", "text": "obtenu" }, { "lemma": ".", "text": "." }, { "lemma": "pour", "text": "Pour" }, { "lemma": "M.", "text": "M." }, { "lemma": "Baker", "text": "Baker" }, { "lemma": ",", "text": "," }, { "lemma": "ce", "text": "cette" }, { "lemma": "quête", "text": "quête" }, { "lemma": "de le", "text": "du" }, { "lemma": "\"", "text": "\"" }, { "lemma": "consensus", "text": "consensus" }, { "lemma": "\"", "text": "\"" }, { "lemma": "avoir", "text": "a" }, { "lemma": "entraîner", "text": "entraîné" }, { "lemma": "son", "text": "son" }, { "lemma": "parti", "text": "parti" }, { "lemma": "dans", "text": "dans" }, { "lemma": "le", "text": "l'" }, { "lemma": "état", "text": "état" }, { "lemma": "où", "text": "où" }, { "lemma": "il", "text": "il" }, { "lemma": "être", "text": "est" }, { "lemma": ".", "text": "." }, { "lemma": "et", "text": "Et" }, { "lemma": "de", "text": "de" }, { "lemma": "conclure", "text": "conclure" }, { "lemma": ":", "text": ":" }, { "lemma": "\"", "text": "\"" }, { "lemma": "le", "text": "Les" }, { "lemma": "républicain", "text": "républicains" }, { "lemma": "avoir", "text": "ont" }, { "lemma": "un", "text": "une" }, { "lemma": "stratégie", "text": "stratégie" }, { "lemma": "efficace", "text": "efficace" }, { "lemma": ":", "text": ":" }, { "lemma": "il", "text": "ils" }, { "lemma": "bloquer", "text": "bloquent" }, { "lemma": "tout", "text": "tout" }, { "lemma": "changement", "text": "changement" }, { "lemma": "pour", "text": "pour" }, { "lemma": "dénoncer", "text": "dénoncer" }, { "lemma": "ensuite", "text": "ensuite" }, { "lemma": "un", "text": "un" }, { "lemma": "président", "text": "président" }, { "lemma": "qui", "text": "qui" }, { "lemma": "ne", "text": "n'" }, { "lemma": "agir", "text": "agit" }, { "lemma": "pas", "text": "pas" }, { "lemma": ".", "text": "." }, { "lemma": "il", "text": "Il" }, { "lemma": "être", "text": "est" }, { "lemma": "temps", "text": "temps" }, { "lemma": "que", "text": "que" }, { "lemma": "celui", "text": "celui" }, { "lemma": "-", "text": "-" }, { "lemma": "ci", "text": "ci" }, { "lemma": "dénoncer", "text": "dénonce" }, { "lemma": "ce", "text": "ce" }, { "lemma": "comportement", "text": "comportement" }, { "lemma": "de", "text": "de" }, { "lemma": "sabotage", "text": "sabotage" }, { "lemma": "de", "text": "de" }, { "lemma": "le", "text": "l'" }, { "lemma": "économie", "text": "économie" }, { "lemma": "national", "text": "nationale" }, { "lemma": ".", "text": "." }, { "lemma": "\"", "text": "\"" }, { "lemma": "mercredi", "text": "Mercredi" }, { "lemma": ",", "text": "," }, { "lemma": "M.", "text": "M." }, { "lemma": "Obama", "text": "Obama" }, { "lemma": "avoir", "text": "a" }, { "lemma": "dire", "text": "dit" }, { "lemma": "\"", "text": "\"" }, { "lemma": "regretter", "text": "regretter" }, { "lemma": "de", "text": "d'" }, { "lemma": "avoir", "text": "avoir" }, { "lemma": "perdre", "text": "perdu" }, { "lemma": "le", "text": "le" }, { "lemma": "sens", "text": "sens" }, { "lemma": "de le", "text": "du" }, { "lemma": "contact", "text": "contact" }, { "lemma": "direct", "text": "direct" }, { "lemma": "avec", "text": "avec" }, { "lemma": "le", "text": "les" }, { "lemma": "américain", "text": "Américains" }, { "lemma": "sur", "text": "sur" }, { "lemma": "leur", "text": "leurs" }, { "lemma": "valeur", "text": "valeurs" }, { "lemma": "essentiel", "text": "essentielles" }, { "lemma": "\"", "text": "\"" }, { "lemma": ".", "text": "." }, { "lemma": "son", "text": "Son" }, { "lemma": "principal", "text": "principal" }, { "lemma": "conseiller", "text": "conseiller" }, { "lemma": ",", "text": "," }, { "lemma": "David", "text": "David" }, { "lemma": "Axelrod", "text": "Axelrod" }, { "lemma": ",", "text": "," }, { "lemma": "avoir", "text": "a" }, { "lemma": "évoquer", "text": "évoqué" }, { "lemma": "\"", "text": "\"" }, { "lemma": "le", "text": "les" }, { "lemma": "salaire", "text": "salaires" }, { "lemma": "bloquer", "text": "bloqués" }, { "lemma": ",", "text": "," }, { "lemma": "le", "text": "les" }, { "lemma": "emploi", "text": "emplois" }, { "lemma": "perdu", "text": "perdus" }, { "lemma": "\"", "text": "\"" }, { "lemma": ".", "text": "." }, { "lemma": "pour", "text": "Pour" }, { "lemma": "autant", "text": "autant" }, { "lemma": ",", "text": "," }, { "lemma": "changer", "text": "changera" }, { "lemma": "-", "text": "-" }, { "lemma": "t", "text": "t" }, { "lemma": "-", "text": "-" }, { "lemma": "il", "text": "il" }, { "lemma": "de", "text": "d'" }, { "lemma": "attitude", "text": "attitude" }, { "lemma": "vis", "text": "vis" }, { "lemma": "-", "text": "-" }, { "lemma": "à", "text": "à" }, { "lemma": "-", "text": "-" }, { "lemma": "vis", "text": "vis" }, { "lemma": "de le", "text": "du" }, { "lemma": "congrès", "text": "Congrès" }, { "lemma": "?", "text": "?" }, { "lemma": "peu", "text": "Peu" }, { "lemma": "y", "text": "y" }, { "lemma": "croire", "text": "croient" }, { "lemma": ".", "text": "." }, { "lemma": "le", "text": "La" }, { "lemma": "chambre", "text": "Chambre" }, { "lemma": "avoir", "text": "a" }, { "lemma": "voter", "text": "voté" }, { "lemma": "en", "text": "en" }, { "lemma": "décembre", "text": "décembre" }, { "lemma": "2009", "text": "2009" }, { "lemma": "un", "text": "une" }, { "lemma": "loi", "text": "loi" }, { "lemma": "sur", "text": "sur" }, { "lemma": "le", "text": "la" }, { "lemma": "création", "text": "création" }, { "lemma": "de", "text": "d'" }, { "lemma": "emploi", "text": "emplois" }, { "lemma": "de", "text": "de" }, { "lemma": "174", "text": "174" }, { "lemma": "milliard", "text": "milliards" }, { "lemma": "de", "text": "de" }, { "lemma": "dollar", "text": "dollars" }, { "lemma": "non", "text": "non" }, { "lemma": "encore", "text": "encore" }, { "lemma": "adopter", "text": "adoptée" }, { "lemma": "à le", "text": "au" }, { "lemma": "sénat", "text": "Sénat" }, { "lemma": ".", "text": "." }, { "lemma": "le", "text": "Les" }, { "lemma": "républicain", "text": "républicains" }, { "lemma": "assimiler", "text": "assimilent" }, { "lemma": "désormais", "text": "désormais" }, { "lemma": "tout", "text": "toute" }, { "lemma": "dépense", "text": "dépense" }, { "lemma": "public", "text": "publique" }, { "lemma": "à", "text": "à" }, { "lemma": "un", "text": "une" }, { "lemma": "gabegie", "text": "gabegie" }, { "lemma": ".", "text": "." }, { "lemma": "Harry", "text": "Harry" }, { "lemma": "Reid", "text": "Reid" }, { "lemma": ",", "text": "," }, { "lemma": "le", "text": "le" }, { "lemma": "leader", "text": "leader" }, { "lemma": "de le", "text": "des" }, { "lemma": "démocrate", "text": "démocrates" }, { "lemma": "à le", "text": "au" }, { "lemma": "sénat", "text": "Sénat" }, { "lemma": ",", "text": "," }, { "lemma": "négocier", "text": "négocierait" }, { "lemma": "déjà", "text": "déjà" }, { "lemma": "avec", "text": "avec" }, { "lemma": "lui", "text": "eux" }, { "lemma": ".", "text": "." }, { "lemma": "certains", "text": "Certains" }, { "lemma": "imaginer", "text": "imaginent" }, { "lemma": "un", "text": "un" }, { "lemma": "abandon", "text": "abandon" }, { "lemma": ",", "text": "," }, { "lemma": "pourtant", "text": "pourtant" }, { "lemma": "peu", "text": "peu" }, { "lemma": "probable", "text": "probable" }, { "lemma": ",", "text": "," }, { "lemma": "de le", "text": "du" }, { "lemma": "plan", "text": "plan" }, { "lemma": "de", "text": "d'" }, { "lemma": "assurance", "text": "assurance" }, { "lemma": "santé", "text": "santé" }, { "lemma": "afin", "text": "afin" }, { "lemma": "de", "text": "de" }, { "lemma": "parvenir", "text": "parvenir" }, { "lemma": "à", "text": "à" }, { "lemma": "un", "text": "un" }, { "lemma": "soutien", "text": "soutien" }, { "lemma": "républicain", "text": "républicain" }, { "lemma": "à le", "text": "aux" }, { "lemma": "embauche", "text": "embauches" }, { "lemma": "dans", "text": "dans" }, { "lemma": "le", "text": "les" }, { "lemma": "PME", "text": "PME" }, { "lemma": ".", "text": "." }, { "lemma": "de", "text": "D'" }, { "lemma": "autre", "text": "autres" }, { "lemma": "envisager", "text": "envisagent" }, { "lemma": "de", "text": "d'" }, { "lemma": "affecter", "text": "affecter" }, { "lemma": "à", "text": "à" }, { "lemma": "le", "text": "l'" }, { "lemma": "emploi", "text": "emploi" }, { "lemma": "75", "text": "75" }, { "lemma": "milliard", "text": "milliards" }, { "lemma": "de", "text": "de" }, { "lemma": "dollar", "text": "dollars" }, { "lemma": "pris", "text": "pris" }, { "lemma": "sur", "text": "sur" }, { "lemma": "le", "text": "le" }, { "lemma": "plan", "text": "plan" }, { "lemma": "de", "text": "de" }, { "lemma": "sauvetage", "text": "sauvetage" }, { "lemma": "de", "text": "de" }, { "lemma": "le", "text": "la" }, { "lemma": "finance", "text": "finance" }, { "lemma": "américain", "text": "américaine" }, { "lemma": "(", "text": "(" }, { "lemma": "dit", "text": "dit" }, { "lemma": "TARP", "text": "TARP" }, { "lemma": ")", "text": ")" }, { "lemma": ".", "text": "." }, { "lemma": "plus", "text": "Plus" }, { "lemma": "encore", "text": "encore" }, { "lemma": "que", "text": "que" }, { "lemma": "M.", "text": "M." }, { "lemma": "Obama", "text": "Obama" }, { "lemma": ",", "text": "," }, { "lemma": "ce", "text": "c'" }, { "lemma": "être", "text": "est" }, { "lemma": "son", "text": "son" }, { "lemma": "parti", "text": "parti" }, { "lemma": ",", "text": "," }, { "lemma": "tétaniser", "text": "tétanisé" }, { "lemma": "par", "text": "par" }, { "lemma": "le", "text": "la" }, { "lemma": "perspective", "text": "perspective" }, { "lemma": "de", "text": "d'" }, { "lemma": "un", "text": "une" }, { "lemma": "défaite", "text": "défaite" }, { "lemma": "électoral", "text": "électorale" }, { "lemma": "dans", "text": "dans" }, { "lemma": "dix", "text": "dix" }, { "lemma": "mois", "text": "mois" }, { "lemma": ",", "text": "," }, { "lemma": "qui", "text": "qui" }, { "lemma": "avoir", "text": "a" }, { "lemma": "besoin", "text": "besoin" }, { "lemma": "de", "text": "de" }, { "lemma": "mesure", "text": "mesures" }, { "lemma": "rapide", "text": "rapides" }, { "lemma": ".", "text": "." }, { "lemma": "http", "text": "http" }, { "lemma": ":", "text": ":" }, { "lemma": "/", "text": "/" }, { "lemma": "/", "text": "/" }, { "lemma": "www.lemonde.fr", "text": "www.lemonde.fr" }, { "lemma": "/", "text": "/" }, { "lemma": "amerique", "text": "ameriques" }, { "lemma": "/", "text": "/" }, { "lemma": "article", "text": "article" }, { "lemma": "/", "text": "/" }, { "lemma": "2010", "text": "2010" }, { "lemma": "/", "text": "/" }, { "lemma": "01", "text": "01" }, { "lemma": "/", "text": "/" }, { "lemma": "21", "text": "21" }, { "lemma": "/", "text": "/" }, { "lemma": "le", "text": "les" }, { "lemma": "-", "text": "-" }, { "lemma": "état", "text": "etats" }, { "lemma": "-", "text": "-" }, { "lemma": "uni", "text": "unis" }, { "lemma": "-", "text": "-" }, { "lemma": "face", "text": "face" }, { "lemma": "-", "text": "-" }, { "lemma": "à le", "text": "au" }, { "lemma": "-", "text": "-" }, { "lemma": "défi", "text": "defi" }, { "lemma": "-", "text": "-" }, { "lemma": "persistant", "text": "persistant" }, { "lemma": "-", "text": "-" }, { "lemma": "de le", "text": "du" }, { "lemma": "-", "text": "-" }, { "lemma": "chômage", "text": "chomage" }, { "lemma": "_", "text": "_" }, { "lemma": "1294839", "text": "1294839" }, { "lemma": "_", "text": "_" }, { "lemma": "3222", "text": "3222" }, { "lemma": ".", "text": "." }, { "lemma": "html", "text": "html" }, { "lemma": "#", "text": "#" }, { "lemma": "xtor", "text": "xtor" }, { "lemma": "=", "text": "=" }, { "lemma": "RSS", "text": "RSS" }, { "lemma": "-", "text": "-" }, { "lemma": "3210", "text": "3210" }, { "lemma": "2010.01.21", "text": "2010.01.21" } ], "posTags": [ { "pos": "DET_PL", "text": "Les" }, { "pos": "NOUN_PL", "text": "Etats" }, { "pos": "PUNCT", "text": "-" }, { "pos": "ADJ_PL", "text": "Unis" }, { "pos": "NOUN_SG", "text": "face" }, { "pos": "PREP_A", "text": "au" }, { "pos": "NOUN_SG", "text": "défi" }, { "pos": "ADJ_SG", "text": "persistant" }, { "pos": "PREP_DE", "text": "du" }, { "pos": "NOUN_SG", "text": "chômage" }, { "pos": "DET_SG", "text": "Un" }, { "pos": "NOUN_SG", "text": "chômeur" }, { "pos": "ADJ_SG", "text": "américain" }, { "pos": "PREP", "text": "sur" }, { "pos": "NUM", "text": "deux" }, { "pos": "VERB_P3SG", "text": "dit" }, { "pos": "VERB_INF", "text": "souffrir" }, { "pos": "PREP_DE", "text": "d'" }, { "pos": "NOUN_SG", "text": "anxiété" }, { "pos": "COORD", "text": "ou" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NOUN_SG", "text": "dépression" }, { "pos": "COORD", "text": "et" }, { "pos": "VAUX_P3SG", "text": "a" }, { "pos": "PAP_SG", "text": "dû" }, { "pos": "VERB_INF", "text": "emprunter" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "DET_SG", "text": "l'" }, { "pos": "NOUN_SG", "text": "argent" }, { "pos": "PREP_A", "text": "à" }, { "pos": "DET_PL", "text": "des" }, { "pos": "NOUN_PL", "text": "amis" }, { "pos": "SENT", "text": "." }, { "pos": "PREP", "text": "Selon" }, { "pos": "DET_SG", "text": "une" }, { "pos": "NOUN_SG", "text": "enquête" }, { "pos": "ADJ_SG", "text": "publiée" }, { "pos": "CM", "text": "," }, { "pos": "NOUN_SG", "text": "lundi" }, { "pos": "NUM", "text": "18" }, { "pos": "NOUN_SG", "text": "janvier" }, { "pos": "CM", "text": "," }, { "pos": "PREP", "text": "par" }, { "pos": "DET_SG", "text": "le" }, { "pos": "NOUN_INV", "text": "Census" }, { "pos": "NOUN_SG", "text": "Bureau" }, { "pos": "PUNCT", "text": "(" }, { "pos": "NOUN_SG", "text": "équivalent" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "DET_SG", "text": "l'" }, { "pos": "NOUN_INV", "text": "Insee" }, { "pos": "PUNCT", "text": ")" }, { "pos": "CM", "text": "," }, { "pos": "PREP", "text": "en" }, { "pos": "NUM", "text": "deux" }, { "pos": "NOUN_PL", "text": "ans" }, { "pos": "CM", "text": "," }, { "pos": "DET_SG", "text": "le" }, { "pos": "NOUN_SG", "text": "nombre" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NOUN_PL", "text": "couples" }, { "pos": "PREP_A", "text": "au" }, { "pos": "NOUN_SG", "text": "chômage" }, { "pos": "PREP", "text": "avec" }, { "pos": "NOUN_PL", "text": "enfants" }, { "pos": "ADJ_PL", "text": "mineurs" }, { "pos": "VAUX_P3SG", "text": "a" }, { "pos": "PAP_SG", "text": "doublé" }, { "pos": "SENT", "text": "." }, { "pos": "PREP", "text": "Près" }, { "pos": "DET_PL", "text": "de" }, { "pos": "NUM", "text": "40" }, { "pos": "SYM", "text": "%" }, { "pos": "PREP_DE", "text": "des" }, { "pos": "DET_PL", "text": "ces" }, { "pos": "NOUN_PL", "text": "parents" }, { "pos": "VERB_P3PL", "text": "notent" }, { "pos": "PREP_DE", "text": "des" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "NOUN_PL", "text": "modifications" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NOUN_SG", "text": "comportement" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "PREP", "text": "chez" }, { "pos": "DET_PL", "text": "leurs" }, { "pos": "NOUN_PL", "text": "enfants" }, { "pos": "CONJQUE", "text": "qu'" }, { "pos": "PRON", "text": "ils" }, { "pos": "VERB_P3PL", "text": "attribuent" }, { "pos": "PREP_A", "text": "à" }, { "pos": "DET_SG", "text": "leur" }, { "pos": "NOUN_SG", "text": "perte" }, { "pos": "PREP_DE", "text": "du" }, { "pos": "NOUN_SG", "text": "travail" }, { "pos": "SENT", "text": "." }, { "pos": "DET_SG", "text": "La" }, { "pos": "NOUN_SG", "text": "moitié" }, { "pos": "VERB_P3PL", "text": "évoquent" }, { "pos": "DET_SG", "text": "une" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "NOUN_SG", "text": "transformation" }, { "pos": "ADJ_SG", "text": "fondamentale" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "DET_SG", "text": "leur" }, { "pos": "NOUN_SG", "text": "existence" }, { "pos": "PUNCT", "text": "-" }, { "pos": "DET_SG", "text": "le" }, { "pos": "NOUN_SG", "text": "premier" }, { "pos": "PREP_DE", "text": "des" }, { "pos": "NOUN_PL", "text": "changements" }, { "pos": "VERB_PRP", "text": "consistant" }, { "pos": "PREP", "text": "en" }, { "pos": "DET_SG", "text": "la" }, { "pos": "NOUN_SG", "text": "perte" }, { "pos": "ADV", "text": "presque" }, { "pos": "ADJ_SG", "text": "instantanée" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "DET_SG", "text": "toute" }, { "pos": "NOUN_SG", "text": "couverture" }, { "pos": "ADJ_SG", "text": "sociale" }, { "pos": "SENT", "text": "." }, { "pos": "PREP", "text": "Durant" }, { "pos": "ADV", "text": "tout" }, { "pos": "DET_SG", "text": "le" }, { "pos": "NOUN_INV", "text": "mois" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NOUN_SG", "text": "décembre" }, { "pos": "CM", "text": "," }, { "pos": "PREP_A", "text": "à" }, { "pos": "DET_SG", "text": "l'" }, { "pos": "NOUN_SG", "text": "approche" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "DET_SG", "text": "l'" }, { "pos": "NOUN_SG", "text": "anniversaire" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "DET_SG", "text": "la" }, { "pos": "NOUN_SG", "text": "prise" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NOUN_PL", "text": "fonctions" }, { "pos": "PREP_DE", "text": "du" }, { "pos": "NOUN_SG", "text": "président" }, { "pos": "NOUN_INV", "text": "Barack" }, { "pos": "NOUN_INV", "text": "Obama" }, { "pos": "CM", "text": "," }, { "pos": "DET_SG", "text": "le" }, { "pos": "NUM", "text": "20" }, { "pos": "NOUN_SG", "text": "janvier" }, { "pos": "NUM", "text": "2009" }, { "pos": "CM", "text": "," }, { "pos": "DET_PL", "text": "les" }, { "pos": "NOUN_PL", "text": "reportages" }, { "pos": "COORD", "text": "et" }, { "pos": "DET_PL", "text": "les" }, { "pos": "NOUN_PL", "text": "enquêtes" }, { "pos": "PREP", "text": "sur" }, { "pos": "DET_PL", "text": "les" }, { "pos": "NOUN_PL", "text": "conséquences" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "DET_PL", "text": "ces" }, { "pos": "NOUN_PL", "text": "destructions" }, { "pos": "PREP_DE", "text": "d'" }, { "pos": "NOUN_SG", "text": "emploi" }, { "pos": "VAUX_P3PL", "text": "sont" }, { "pos": "PAP_PL", "text": "devenus" }, { "pos": "DET_SG", "text": "une" }, { "pos": "NOUN_SG", "text": "préoccupation" }, { "pos": "ADJ_SG", "text": "obsédante" }, { "pos": "PREP", "text": "dans" }, { "pos": "DET_PL", "text": "les" }, { "pos": "NOUN_PL", "text": "médias" }, { "pos": "SENT", "text": "." }, { "pos": "PUNCT", "text": "\"" }, { "pos": "PRON_P1P2", "text": "Je" }, { "pos": "PC", "text": "me" }, { "pos": "VERB_P1P2", "text": "sens" }, { "pos": "COMME", "text": "comme" }, { "pos": "DET_SG", "text": "la" }, { "pos": "NOUN_SG", "text": "lie" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "DET_SG", "text": "la" }, { "pos": "NOUN_SG", "text": "terre" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "CM", "text": "," }, { "pos": "VERB_P3SG", "text": "disait" }, { "pos": "ADV", "text": "récemment" }, { "pos": "DET_SG", "text": "un" }, { "pos": "NOUN_SG", "text": "chômeur" }, { "pos": "PREP_A", "text": "à" }, { "pos": "DET_SG", "text": "une" }, { "pos": "NOUN_SG", "text": "heure" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "ADJ2_SG", "text": "grande" }, { "pos": "NOUN_SG", "text": "écoute" }, { "pos": "SENT", "text": "." }, { "pos": "ADV", "text": "Alors" }, { "pos": "CM", "text": "," }, { "pos": "DET_SG", "text": "l'" }, { "pos": "NOUN_SG", "text": "Amérique" }, { "pos": "VERB_P3SG", "text": "découvre" }, { "pos": "PREP", "text": "sur" }, { "pos": "DET_PL", "text": "les" }, { "pos": "NOUN_PL", "text": "écrans" }, { "pos": "PRON", "text": "tous" }, { "pos": "DET_PL", "text": "ces" }, { "pos": "NOUN_PL", "text": "visages" }, { "pos": "ADJ_PL", "text": "ravagés" }, { "pos": "RELPRO", "text": "qui" }, { "pos": "VERB_P3PL", "text": "évoquent" }, { "pos": "DET_SG", "text": "leur" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "NOUN_SG", "text": "honte" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "COORD", "text": "et" }, { "pos": "PC", "text": "s'" }, { "pos": "VERB_P3SG", "text": "interroge" }, { "pos": "PUNCT", "text": ":" }, { "pos": "NUM", "text": "10" }, { "pos": "SYM", "text": "%" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NOUN_SG", "text": "chômage" }, { "pos": "CM", "text": "," }, { "pos": "CONN", "text": "comment" }, { "pos": "PREP", "text": "en" }, { "pos": "NOUN_SG", "text": "est" }, { "pos": "PUNCT", "text": "-" }, { "pos": "PRON", "text": "on" }, { "pos": "PAP_SG", "text": "arrivé" }, { "pos": "ADV", "text": "là" }, { "pos": "SENT", "text": "?" }, { "pos": "PREP", "text": "Pour" }, { "pos": "ADV", "text": "beaucoup" }, { "pos": "PREP_DE", "text": "d'" }, { "pos": "NOUN_PL", "text": "analystes" }, { "pos": "CM", "text": "," }, { "pos": "PRON", "text": "c'" }, { "pos": "VAUX_P3SG", "text": "est" }, { "pos": "PREP", "text": "pour" }, { "pos": "VAUX_INF", "text": "avoir" }, { "pos": "PAP_SG", "text": "négligé" }, { "pos": "DET_SG", "text": "l'" }, { "pos": "NOUN_SG", "text": "impact" }, { "pos": "PREP_DE", "text": "du" }, { "pos": "NOUN_SG", "text": "chômage" }, { "pos": "ADV", "text": "alors" }, { "pos": "CONJQUE", "text": "que" }, { "pos": "PC", "text": "se" }, { "pos": "VERB_P3PL", "text": "profilaient" }, { "pos": "PREP_DE", "text": "des" }, { "pos": "NOUN_PL", "text": "signes" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NOUN_SG", "text": "reprise" }, { "pos": "ADJ_SG", "text": "économique" }, { "pos": "PUNCT", "text": "(" }, { "pos": "COORD", "text": "et" }, { "pos": "ADV", "text": "surtout" }, { "pos": "ADJ_SG", "text": "financière" }, { "pos": "PUNCT", "text": ")" }, { "pos": "CONJQUE", "text": "que" }, { "pos": "DET_SG", "text": "la" }, { "pos": "NOUN_SG", "text": "Maison" }, { "pos": "ADJ_SG", "text": "Blanche" }, { "pos": "COORD", "text": "et" }, { "pos": "DET_SG", "text": "le" }, { "pos": "NOUN_SG", "text": "Parti" }, { "pos": "ADJ_SG", "text": "démocrate" }, { "pos": "PC", "text": "se" }, { "pos": "VERB_P3PL", "text": "trouvent" }, { "pos": "ADJ_PL", "text": "confrontés" }, { "pos": "PREP_A", "text": "à" }, { "pos": "DET_SG", "text": "une" }, { "pos": "ADJ_SG", "text": "forte" }, { "pos": "NOUN_SG", "text": "désaffection" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "DET_SG", "text": "l'" }, { "pos": "NOUN_SG", "text": "opinion" }, { "pos": "PREP_A", "text": "à" }, { "pos": "NUM", "text": "dix" }, { "pos": "NOUN_INV", "text": "mois" }, { "pos": "PREP_DE", "text": "des" }, { "pos": "NOUN_PL", "text": "élections" }, { "pos": "PREP_A", "text": "à" }, { "pos": "NOUN_INV", "text": "mi" }, { "pos": "PUNCT", "text": "-" }, { "pos": "NOUN_SG", "text": "mandat" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NOUN_SG", "text": "novembre" }, { "pos": "SENT", "text": "." }, { "pos": "ADV", "text": "Alors" }, { "pos": "CONJQUE", "text": "que" }, { "pos": "DET_SG", "text": "le" }, { "pos": "NOUN_SG", "text": "thème" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "DET_SG", "text": "l'" }, { "pos": "NOUN_SG", "text": "emploi" }, { "pos": "VERB_P3SG", "text": "envahissait" }, { "pos": "DET_SG", "text": "le" }, { "pos": "NOUN_SG", "text": "champ" }, { "pos": "PREP_DE", "text": "des" }, { "pos": "NOUN_PL", "text": "préoccupations" }, { "pos": "CM", "text": "," }, { "pos": "NOUN_SG", "text": "M." }, { "pos": "NOUN_INV", "text": "Obama" }, { "pos": "VAUX_P3SG", "text": "a" }, { "pos": "PAP_SG", "text": "continué" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "VERB_INF", "text": "donner" }, { "pos": "DET_SG", "text": "la" }, { "pos": "NOUN_SG", "text": "priorité" }, { "pos": "PREP_A", "text": "à" }, { "pos": "DET_SG", "text": "la" }, { "pos": "NOUN_SG", "text": "réforme" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "DET_SG", "text": "la" }, { "pos": "NOUN_SG", "text": "santé" }, { "pos": "CM", "text": "," }, { "pos": "PREP_A", "text": "à" }, { "pos": "DET_SG", "text": "la" }, { "pos": "NOUN_SG", "text": "lutte" }, { "pos": "PREP", "text": "contre" }, { "pos": "DET_SG", "text": "le" }, { "pos": "NOUN_SG", "text": "réchauffement" }, { "pos": "ADJ_SG", "text": "climatique" }, { "pos": "COORD", "text": "ou" }, { "pos": "DET_SG", "text": "la" }, { "pos": "NOUN_SG", "text": "régulation" }, { "pos": "ADJ_SG", "text": "financière" }, { "pos": "SENT", "text": "." }, { "pos": "DET_PL", "text": "Tous" }, { "pos": "NOUN_PL", "text": "sujets" }, { "pos": "ADJ_PL", "text": "essentiels" }, { "pos": "COORD", "text": "mais" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "ADV", "text": "bien" }, { "pos": "ADV", "text": "moins" }, { "pos": "ADJ_PL", "text": "palpables" }, { "pos": "CM", "text": "," }, { "pos": "PREP", "text": "dans" }, { "pos": "DET_SG", "text": "une" }, { "pos": "NOUN_SG", "text": "période" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NOUN_SG", "text": "crise" }, { "pos": "ADJ_SG", "text": "aiguë" }, { "pos": "CM", "text": "," }, { "pos": "CONJQUE", "text": "que" }, { "pos": "DET_SG", "text": "le" }, { "pos": "NOUN_SG", "text": "chômage" }, { "pos": "CM", "text": "," }, { "pos": "RELPRO", "text": "qui" }, { "pos": "VERB_P3SG", "text": "arase" }, { "pos": "ADV", "text": "tout" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "CM", "text": "," }, { "pos": "NOUN_SG", "text": "note" }, { "pos": "NOUN_INV", "text": "Dean" }, { "pos": "NOUN_INV", "text": "Baker" }, { "pos": "CM", "text": "," }, { "pos": "NOUN_SG", "text": "codirecteur" }, { "pos": "PREP_DE", "text": "du" }, { "pos": "NOUN_SG", "text": "Centre" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NOUN_PL", "text": "recherches" }, { "pos": "PREP", "text": "sur" }, { "pos": "DET_PL", "text": "les" }, { "pos": "NOUN_PL", "text": "politiques" }, { "pos": "ADJ_PL", "text": "économiques" }, { "pos": "CM", "text": "," }, { "pos": "DET_SG", "text": "un" }, { "pos": "NOUN_SG", "text": "groupe" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NOUN_SG", "text": "réflexion" }, { "pos": "ADJ_SG", "text": "démocrate" }, { "pos": "PREP_A", "text": "à" }, { "pos": "NOUN_INV", "text": "Washington" }, { "pos": "SENT", "text": "." }, { "pos": "DET_SG", "text": "Une" }, { "pos": "NOUN_SG", "text": "étude" }, { "pos": "PREP_DE", "text": "du" }, { "pos": "NOUN_SG", "text": "département" }, { "pos": "PREP_DE", "text": "du" }, { "pos": "NOUN_SG", "text": "travail" }, { "pos": "CM", "text": "," }, { "pos": "PAP_SG", "text": "publiée" }, { "pos": "DET_SG", "text": "le" }, { "pos": "NUM", "text": "8" }, { "pos": "NOUN_SG", "text": "janvier" }, { "pos": "CM", "text": "," }, { "pos": "VERB_P3SG", "text": "montre" }, { "pos": "DET_SG", "text": "une" }, { "pos": "NOUN_SG", "text": "différence" }, { "pos": "ADJ_SG", "text": "essentielle" }, { "pos": "PREP", "text": "entre" }, { "pos": "DET_SG", "text": "l'" }, { "pos": "NOUN_SG", "text": "impact" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "DET_SG", "text": "la" }, { "pos": "NOUN_SG", "text": "crise" }, { "pos": "ADJ_SG", "text": "actuelle" }, { "pos": "PREP", "text": "sur" }, { "pos": "DET_SG", "text": "l'" }, { "pos": "NOUN_SG", "text": "emploi" }, { "pos": "COORD", "text": "et" }, { "pos": "DET_PL", "text": "les" }, { "pos": "ADJ_PL", "text": "précédentes" }, { "pos": "NOUN_PL", "text": "récessions" }, { "pos": "SENT", "text": "." }, { "pos": "ADV", "text": "Lors" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "PRON", "text": "celles" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NUM", "text": "1974" }, { "pos": "PUNCT", "text": "-" }, { "pos": "NUM", "text": "1976" }, { "pos": "COORD", "text": "et" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NUM", "text": "1990" }, { "pos": "PUNCT", "text": "-" }, { "pos": "NUM", "text": "1993" }, { "pos": "CM", "text": "," }, { "pos": "DET_SG", "text": "le" }, { "pos": "NOUN_SG", "text": "chômage" }, { "pos": "VAUX_P3SG", "text": "était" }, { "pos": "ADV", "text": "moins" }, { "pos": "ADJ_SG", "text": "important" }, { "pos": "CM", "text": "," }, { "pos": "ADV", "text": "tant" }, { "pos": "PREP", "text": "en" }, { "pos": "NOUN_PL", "text": "chiffres" }, { "pos": "NOUN_PL", "text": "absolus" }, { "pos": "CONJQUE", "text": "qu'" }, { "pos": "PREP", "text": "en" }, { "pos": "NOUN_SG", "text": "durée" }, { "pos": "SENT", "text": "." }, { "pos": "DET_SG", "text": "Cette" }, { "pos": "NOUN_SG", "text": "comparaison" }, { "pos": "NOUN_SG", "text": "reste" }, { "pos": "ADJ_SG", "text": "valide" }, { "pos": "PREP", "text": "pour" }, { "pos": "DET_SG", "text": "la" }, { "pos": "NOUN_SG", "text": "récession" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NUM", "text": "1981" }, { "pos": "PUNCT", "text": "-" }, { "pos": "NUM", "text": "1983" }, { "pos": "CM", "text": "," }, { "pos": "RELPRO", "text": "qui" }, { "pos": "VERB_P3SG", "text": "vit" }, { "pos": "DET_SG", "text": "le" }, { "pos": "NOUN_SG", "text": "président" }, { "pos": "ADJ_SG", "text": "républicain" }, { "pos": "NOUN_INV", "text": "Ronald" }, { "pos": "NOUN_INV", "text": "Reagan" }, { "pos": "CM", "text": "," }, { "pos": "DET_SG", "text": "un" }, { "pos": "NOUN_SG", "text": "an" }, { "pos": "PREP", "text": "après" }, { "pos": "DET_SG", "text": "son" }, { "pos": "NOUN_SG", "text": "élection" }, { "pos": "CM", "text": "," }, { "pos": "VERB_INF", "text": "enregistrer" }, { "pos": "DET_SG", "text": "son" }, { "pos": "NOUN_INV", "text": "plus" }, { "pos": "NOUN_INV", "text": "bas" }, { "pos": "NOUN_SG", "text": "soutien" }, { "pos": "PREP", "text": "dans" }, { "pos": "DET_SG", "text": "l'" }, { "pos": "NOUN_SG", "text": "opinion" }, { "pos": "SENT", "text": "." }, { "pos": "PREP", "text": "Pour" }, { "pos": "VERB_INF", "text": "résumer" }, { "pos": "DET_SG", "text": "le" }, { "pos": "NOUN_SG", "text": "désastre" }, { "pos": "ADJ_SG", "text": "actuel" }, { "pos": "PUNCT", "text": ":" }, { "pos": "DET_PL", "text": "les" }, { "pos": "NOUN_PL", "text": "Etats" }, { "pos": "PUNCT", "text": "-" }, { "pos": "NOUN_PL", "text": "Unis" }, { "pos": "VAUX_P3PL", "text": "ont" }, { "pos": "PAP_SG", "text": "perdu" }, { "pos": "PREP", "text": "depuis" }, { "pos": "NUM", "text": "deux" }, { "pos": "NOUN_PL", "text": "ans" }, { "pos": "NUM", "text": "5,24" }, { "pos": "SYM", "text": "%" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "DET_SG", "text": "leur" }, { "pos": "NOUN_SG", "text": "emploi" }, { "pos": "CM", "text": "," }, { "pos": "ADV", "text": "alors" }, { "pos": "CONJQUE", "text": "que" }, { "pos": "DET_SG", "text": "la" }, { "pos": "NOUN_SG", "text": "chute" }, { "pos": "NEG", "text": "n'" }, { "pos": "VAUX_P3SG", "text": "avait" }, { "pos": "VAUX_PAP", "text": "été" }, { "pos": "CONJQUE", "text": "que" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NUM", "text": "1,4" }, { "pos": "SYM", "text": "%" }, { "pos": "PREP_A", "text": "à" }, { "pos": "NUM", "text": "3" }, { "pos": "SYM", "text": "%" }, { "pos": "CM", "text": "," }, { "pos": "PREP_A", "text": "au" }, { "pos": "NOUN_SG", "text": "pire" }, { "pos": "CM", "text": "," }, { "pos": "ADV", "text": "lors" }, { "pos": "PREP_DE", "text": "des" }, { "pos": "NOUN_PL", "text": "récessions" }, { "pos": "ADJ_PL", "text": "précédentes" }, { "pos": "SENT", "text": "." }, { "pos": "PREP", "text": "Entre" }, { "pos": "NOUN_SG", "text": "chômage" }, { "pos": "ADJ_SG", "text": "total" }, { "pos": "COORD", "text": "et" }, { "pos": "ADJ_SG", "text": "partiel" }, { "pos": "CM", "text": "," }, { "pos": "DET_SG", "text": "la" }, { "pos": "NOUN_SG", "text": "crise" }, { "pos": "VERB_P3SG", "text": "touche" }, { "pos": "DET_SG", "text": "le" }, { "pos": "NOUN_SG", "text": "travail" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "PREP", "text": "près" }, { "pos": "NOUN_INV", "text": "d" }, { "pos": "PUNCT", "text": "'" }, { "pos": "DET_SG", "text": "un" }, { "pos": "NOUN_SG", "text": "Américain" }, { "pos": "PREP", "text": "sur" }, { "pos": "NUM", "text": "cinq" }, { "pos": "SENT", "text": "." }, { "pos": "NEG", "text": "N'" }, { "pos": "VAUX_PRP", "text": "ayant" }, { "pos": "PAP_SG", "text": "cessé" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "VERB_INF", "text": "répéter" }, { "pos": "CONJQUE", "text": "que" }, { "pos": "DET_SG", "text": "son" }, { "pos": "NOUN_INV", "text": "pays" }, { "pos": "VERB_P3SG", "text": "affrontait" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "DET_SG", "text": "la" }, { "pos": "ADJ_SG", "text": "pire" }, { "pos": "NOUN_SG", "text": "crise" }, { "pos": "PREP", "text": "depuis" }, { "pos": "DET_SG", "text": "la" }, { "pos": "ADJ2_SG", "text": "Grande" }, { "pos": "NOUN_SG", "text": "Dépression" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "PREP_DE", "text": "des" }, { "pos": "NOUN_PL", "text": "années" }, { "pos": "NUM", "text": "1930" }, { "pos": "CM", "text": "," }, { "pos": "NOUN_INV", "text": "Barack" }, { "pos": "NOUN_INV", "text": "Obama" }, { "pos": "VAUX_P3SG", "text": "avait" }, { "pos": "PAP_SG", "text": "donné" }, { "pos": "DET_SG", "text": "le" }, { "pos": "NOUN_SG", "text": "sentiment" }, { "pos": "PREP_DE", "text": "d'" }, { "pos": "VAUX_INF", "text": "être" }, { "pos": "ADV", "text": "très" }, { "pos": "ADJ_SG", "text": "conscient" }, { "pos": "PREP_DE", "text": "du" }, { "pos": "NOUN_SG", "text": "problème" }, { "pos": "SENT", "text": "." }, { "pos": "COORD", "text": "Or" }, { "pos": "ADV", "text": "là" }, { "pos": "VAUX_P3SG", "text": "est" }, { "pos": "DET_SG", "text": "le" }, { "pos": "NOUN_SG", "text": "paradoxe" }, { "pos": "PUNCT", "text": ":" }, { "pos": "DET_SG", "text": "une" }, { "pos": "NOUN_INV", "text": "fois" }, { "pos": "ADJ_SG", "text": "élu" }, { "pos": "CM", "text": "," }, { "pos": "DET_SG", "text": "le" }, { "pos": "NOUN_SG", "text": "président" }, { "pos": "VAUX_P3SG", "text": "est" }, { "pos": "PAP_SG", "text": "apparu" }, { "pos": "COMME", "text": "comme" }, { "pos": "DET_SG", "text": "un" }, { "pos": "NOUN_SG", "text": "dirigeant" }, { "pos": "RELPRO", "text": "qui" }, { "pos": "VAUX_P3SG", "text": "a" }, { "pos": "PAP_SG", "text": "fait" }, { "pos": "DET_SG", "text": "un" }, { "pos": "NOUN_SG", "text": "diagnostic" }, { "pos": "ADJ_SG", "text": "correct" }, { "pos": "COORD", "text": "mais" }, { "pos": "NEG", "text": "n'" }, { "pos": "PC", "text": "en" }, { "pos": "VAUX_P3SG", "text": "a" }, { "pos": "PAP_SG", "text": "tiré" }, { "pos": "DET_SG", "text": "aucune" }, { "pos": "NOUN_SG", "text": "conclusion" }, { "pos": "SENT", "text": "." }, { "pos": "DET_SG", "text": "L'" }, { "pos": "NOUN_SG", "text": "Amérique" }, { "pos": "VAUX_P3SG", "text": "avait" }, { "pos": "PAP_SG", "text": "perdu" }, { "pos": "NUM", "text": "3 078 000" }, { "pos": "NOUN_PL", "text": "chômeurs" }, { "pos": "ADV", "text": "lors" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "DET_SG", "text": "la" }, { "pos": "ADJ2_SG", "text": "dernière" }, { "pos": "NOUN_SG", "text": "année" }, { "pos": "PREP_DE", "text": "du" }, { "pos": "NOUN_SG", "text": "mandat" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NOUN_INV", "text": "George" }, { "pos": "NOUN_INV", "text": "Bush" }, { "pos": "PUNCT", "text": ";" }, { "pos": "PRON", "text": "elle" }, { "pos": "PC", "text": "en" }, { "pos": "VAUX_P3SG", "text": "a" }, { "pos": "PAP_SG", "text": "perdu" }, { "pos": "NUM", "text": "4 228 000" }, { "pos": "PREP", "text": "en" }, { "pos": "DET_SG", "text": "un" }, { "pos": "NOUN_SG", "text": "an" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NOUN_SG", "text": "présidence" }, { "pos": "NOUN_INV", "text": "Obama" }, { "pos": "SENT", "text": "!" }, { "pos": "DET_SG", "text": "Le" }, { "pos": "NUM", "text": "10" }, { "pos": "NOUN_SG", "text": "janvier" }, { "pos": "CM", "text": "," }, { "pos": "VERB_PRP", "text": "invoquant" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "DET_SG", "text": "l'" }, { "pos": "NOUN_SG", "text": "urgence" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "CM", "text": "," }, { "pos": "NOUN_INV", "text": "Christina" }, { "pos": "NOUN_INV", "text": "Romer" }, { "pos": "CM", "text": "," }, { "pos": "NOUN_SG", "text": "présidente" }, { "pos": "PREP_DE", "text": "du" }, { "pos": "NOUN_SG", "text": "conseil" }, { "pos": "ADJ_SG", "text": "économique" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NOUN_SG", "text": "M." }, { "pos": "NOUN_INV", "text": "Obama" }, { "pos": "CM", "text": "," }, { "pos": "VAUX_P3SG", "text": "a" }, { "pos": "PAP_SG", "text": "appelé" }, { "pos": "PREP_A", "text": "à" }, { "pos": "ADV", "text": "vite" }, { "pos": "VERB_INF", "text": "injecter" }, { "pos": "NUM", "text": "75" }, { "pos": "NOUN_PL", "text": "milliards" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NOUN_PL", "text": "dollars" }, { "pos": "ADJ_PL", "text": "supplémentaires" }, { "pos": "PREP", "text": "pour" }, { "pos": "VERB_INF", "text": "régénérer" }, { "pos": "DET_SG", "text": "l'" }, { "pos": "NOUN_SG", "text": "emploi" }, { "pos": "SENT", "text": "." }, { "pos": "PRON", "text": "Nul" }, { "pos": "NEG", "text": "ne" }, { "pos": "VERB_P3SG", "text": "doute" }, { "pos": "CONJQUE", "text": "que" }, { "pos": "NOUN_SG", "text": "M." }, { "pos": "NOUN_INV", "text": "Obama" }, { "pos": "VERB_P3SG", "text": "privilégiera" }, { "pos": "DET_SG", "text": "cette" }, { "pos": "NOUN_SG", "text": "nécessité" }, { "pos": "PREP", "text": "en" }, { "pos": "NUM", "text": "2010" }, { "pos": "SENT", "text": "." }, { "pos": "CONN", "text": "Comment" }, { "pos": "VERB_INF", "text": "remédier" }, { "pos": "PREP_A", "text": "au" }, { "pos": "NOUN_SG", "text": "problème" }, { "pos": "SENT", "text": "?" }, { "pos": "DET_SG", "text": "La" }, { "pos": "NOUN_SG", "text": "plupart" }, { "pos": "PREP_DE", "text": "des" }, { "pos": "NOUN_PL", "text": "analystes" }, { "pos": "CM", "text": "," }, { "pos": "VERB_PRP", "text": "constatant" }, { "pos": "DET_SG", "text": "le" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "NOUN_SG", "text": "découplage" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "PREP", "text": "entre" }, { "pos": "DET_SG", "text": "la" }, { "pos": "NOUN_SG", "text": "reprise" }, { "pos": "ADJ_SG", "text": "économique" }, { "pos": "COORD", "text": "et" }, { "pos": "PRON", "text": "celle" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "DET_SG", "text": "l'" }, { "pos": "NOUN_SG", "text": "emploi" }, { "pos": "CM", "text": "," }, { "pos": "VAUX_P3PL", "text": "sont" }, { "pos": "ADJ_PL", "text": "circonspects" }, { "pos": "SENT", "text": "." }, { "pos": "NOUN_SG", "text": "Chef" }, { "pos": "NOUN_SG", "text": "économiste" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NOUN_INV", "text": "Goldman" }, { "pos": "NOUN_INV", "text": "Sachs" }, { "pos": "CM", "text": "," }, { "pos": "NOUN_SG", "text": "Jan" }, { "pos": "NOUN_INV", "text": "Hatzius" }, { "pos": "CM", "text": "," }, { "pos": "PREP", "text": "dans" }, { "pos": "DET_SG", "text": "un" }, { "pos": "NOUN_SG", "text": "texte" }, { "pos": "ADJ_SG", "text": "intitulé" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "NUM", "text": "10" }, { "pos": "NOUN_PL", "text": "questions" }, { "pos": "PREP", "text": "pour" }, { "pos": "NUM", "text": "2010" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "CM", "text": "," }, { "pos": "PC", "text": "s'" }, { "pos": "VERB_P3SG", "text": "attend" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "PREP_A", "text": "à" }, { "pos": "DET_SG", "text": "un" }, { "pos": "NOUN_SG", "text": "solde" }, { "pos": "ADJ_SG", "text": "positif" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NUM", "text": "100 000" }, { "pos": "NOUN_PL", "text": "emplois" }, { "pos": "PREP", "text": "par" }, { "pos": "NOUN_INV", "text": "mois" }, { "pos": "PREP", "text": "dès" }, { "pos": "DET_SG", "text": "le" }, { "pos": "ADJ2_SG", "text": "second" }, { "pos": "NOUN_SG", "text": "trimestre" }, { "pos": "CM", "text": "," }, { "pos": "ADJ_SG", "text": "insuffisant" }, { "pos": "PREP", "text": "pour" }, { "pos": "VERB_INF", "text": "modifier" }, { "pos": "ADV", "text": "significativement" }, { "pos": "DET_SG", "text": "le" }, { "pos": "NOUN_INV", "text": "taux" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NOUN_SG", "text": "chômage" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "SENT", "text": "." }, { "pos": "NOUN_SG", "text": "Compte" }, { "pos": "ADJ_SG", "text": "tenu" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "DET_SG", "text": "leur" }, { "pos": "NOUN_SG", "text": "évolution" }, { "pos": "ADJ_SG", "text": "démographique" }, { "pos": "CM", "text": "," }, { "pos": "DET_PL", "text": "les" }, { "pos": "NOUN_PL", "text": "Etats" }, { "pos": "PUNCT", "text": "-" }, { "pos": "NOUN_PL", "text": "Unis" }, { "pos": "VERB_P3PL", "text": "doivent" }, { "pos": "PREP", "text": "en" }, { "pos": "NOUN_SG", "text": "effet" }, { "pos": "VERB_INF", "text": "créer" }, { "pos": "NUM", "text": "100 000" }, { "pos": "NOUN_PL", "text": "emplois" }, { "pos": "ADJ_PL", "text": "mensuels" }, { "pos": "PREP", "text": "pour" }, { "pos": "ADJ_SG", "text": "juste" }, { "pos": "VERB_INF", "text": "stabiliser" }, { "pos": "DET_SG", "text": "l'" }, { "pos": "NOUN_SG", "text": "emploi" }, { "pos": "SENT", "text": "." }, { "pos": "NOUN_INV", "text": "Dean" }, { "pos": "NOUN_INV", "text": "Baker" }, { "pos": "VERB_P3SG", "text": "explique" }, { "pos": "ADV", "text": "encore" }, { "pos": "CONJQUE", "text": "que" }, { "pos": "DET_SG", "text": "la" }, { "pos": "NOUN_SG", "text": "marge" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NOUN_SG", "text": "manoeuvre" }, { "pos": "ADJ_SG", "text": "présidentielle" }, { "pos": "VAUX_P3SG", "text": "est" }, { "pos": "PAP_SG", "text": "restreinte" }, { "pos": "PUNCT", "text": ":" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "NOUN_INV", "text": "Obama" }, { "pos": "VAUX_P3SG", "text": "a" }, { "pos": "PAP_SG", "text": "raté" }, { "pos": "DET_SG", "text": "le" }, { "pos": "NOUN_SG", "text": "coche" }, { "pos": "PREP", "text": "en" }, { "pos": "VERB_PRP", "text": "limitant" }, { "pos": "DET_SG", "text": "son" }, { "pos": "NOUN_SG", "text": "plan" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NOUN_SG", "text": "relance" }, { "pos": "SENT", "text": "." }, { "pos": "ADV", "text": "Maintenant" }, { "pos": "CM", "text": "," }, { "pos": "PRON", "text": "il" }, { "pos": "PC", "text": "lui" }, { "pos": "VAUX_P3SG", "text": "est" }, { "pos": "ADV", "text": "politiquement" }, { "pos": "ADJ_SG", "text": "impossible" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "VERB_INF", "text": "retourner" }, { "pos": "PREP", "text": "devant" }, { "pos": "DET_SG", "text": "le" }, { "pos": "NOUN_INV", "text": "Congrès" }, { "pos": "PREP", "text": "pour" }, { "pos": "PC", "text": "l'" }, { "pos": "VERB_INF", "text": "augmenter" }, { "pos": "SENT", "text": "." }, { "pos": "DET_PL", "text": "Les" }, { "pos": "NOUN_PL", "text": "conséquences" }, { "pos": "VAUX_P3PL", "text": "sont" }, { "pos": "ADJ_PL", "text": "désastreuses" }, { "pos": "SENT", "text": "." }, { "pos": "ADV", "text": "Même" }, { "pos": "CONN", "text": "s'" }, { "pos": "PRON", "text": "il" }, { "pos": "PC", "text": "lui" }, { "pos": "VERB_P3SG", "text": "reste" }, { "pos": "NUM", "text": "200" }, { "pos": "NOUN_PL", "text": "milliards" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NOUN_PL", "text": "dollars" }, { "pos": "PREP_A", "text": "à" }, { "pos": "VERB_INF", "text": "dépenser" }, { "pos": "PUNCT", "text": "(" }, { "pos": "PREP", "text": "sur" }, { "pos": "NUM", "text": "787" }, { "pos": "NOUN_PL", "text": "milliards" }, { "pos": "PUNCT", "text": ")" }, { "pos": "CM", "text": "," }, { "pos": "DET_SG", "text": "l'" }, { "pos": "NOUN_SG", "text": "essentiel" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "DET_SG", "text": "l'" }, { "pos": "NOUN_SG", "text": "impact" }, { "pos": "PREP_DE", "text": "du" }, { "pos": "NOUN_SG", "text": "plan" }, { "pos": "VAUX_P3SG", "text": "est" }, { "pos": "PAP_SG", "text": "passé" }, { "pos": "SENT", "text": "." }, { "pos": "PUNCT", "text": "\"" }, { "pos": "DET_SG", "text": "Le" }, { "pos": "NOUN_SG", "text": "pire" }, { "pos": "CM", "text": "," }, { "pos": "PREP", "text": "selon" }, { "pos": "PRON", "text": "lui" }, { "pos": "CM", "text": "," }, { "pos": "VAUX_P3SG", "text": "est" }, { "pos": "CONJQUE", "text": "que" }, { "pos": "DET_SG", "text": "le" }, { "pos": "NOUN_SG", "text": "président" }, { "pos": "VAUX_P3SG", "text": "a" }, { "pos": "PAP_SG", "text": "fait" }, { "pos": "DET_SG", "text": "son" }, { "pos": "NOUN_INV", "text": "choix" }, { "pos": "PREP", "text": "en" }, { "pos": "DET_SG", "text": "toute" }, { "pos": "NOUN_SG", "text": "connaissance" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NOUN_SG", "text": "cause" }, { "pos": "CM", "text": "," }, { "pos": "PREP", "text": "pour" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "VERB_INF", "text": "privilégier" }, { "pos": "DET_SG", "text": "la" }, { "pos": "NOUN_SG", "text": "politique" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "SENT", "text": "." }, { "pos": "PRON", "text": "C'" }, { "pos": "VAUX_P3SG", "text": "est" }, { "pos": "PUNCT", "text": "-" }, { "pos": "PREP_A", "text": "à" }, { "pos": "PUNCT", "text": "-" }, { "pos": "VERB_INF", "text": "dire" }, { "pos": "DET_SG", "text": "un" }, { "pos": "NOUN_INV", "text": "compromis" }, { "pos": "PREP", "text": "avec" }, { "pos": "DET_PL", "text": "certains" }, { "pos": "NOUN_PL", "text": "républicains" }, { "pos": "CONJQUE", "text": "qu'" }, { "pos": "PRON", "text": "il" }, { "pos": "NEG", "text": "n'" }, { "pos": "VAUX_P3SG", "text": "a" }, { "pos": "ADV", "text": "jamais" }, { "pos": "PAP_SG", "text": "obtenu" }, { "pos": "SENT", "text": "." }, { "pos": "PREP", "text": "Pour" }, { "pos": "NOUN_SG", "text": "M." }, { "pos": "NOUN_INV", "text": "Baker" }, { "pos": "CM", "text": "," }, { "pos": "DET_SG", "text": "cette" }, { "pos": "NOUN_SG", "text": "quête" }, { "pos": "PREP_DE", "text": "du" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "NOUN_INV", "text": "consensus" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "VAUX_P3SG", "text": "a" }, { "pos": "PAP_SG", "text": "entraîné" }, { "pos": "DET_SG", "text": "son" }, { "pos": "NOUN_SG", "text": "parti" }, { "pos": "PREP", "text": "dans" }, { "pos": "DET_SG", "text": "l'" }, { "pos": "NOUN_SG", "text": "état" }, { "pos": "CONN", "text": "où" }, { "pos": "PRON", "text": "il" }, { "pos": "VAUX_P3SG", "text": "est" }, { "pos": "SENT", "text": "." }, { "pos": "COORD", "text": "Et" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "VERB_INF", "text": "conclure" }, { "pos": "PUNCT", "text": ":" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "DET_PL", "text": "Les" }, { "pos": "NOUN_PL", "text": "républicains" }, { "pos": "VAUX_P3PL", "text": "ont" }, { "pos": "DET_SG", "text": "une" }, { "pos": "NOUN_SG", "text": "stratégie" }, { "pos": "ADJ_SG", "text": "efficace" }, { "pos": "PUNCT", "text": ":" }, { "pos": "PRON", "text": "ils" }, { "pos": "VERB_P3PL", "text": "bloquent" }, { "pos": "DET_SG", "text": "tout" }, { "pos": "NOUN_SG", "text": "changement" }, { "pos": "PREP", "text": "pour" }, { "pos": "VERB_INF", "text": "dénoncer" }, { "pos": "ADV", "text": "ensuite" }, { "pos": "DET_SG", "text": "un" }, { "pos": "NOUN_SG", "text": "président" }, { "pos": "RELPRO", "text": "qui" }, { "pos": "NEG", "text": "n'" }, { "pos": "VERB_P3SG", "text": "agit" }, { "pos": "ADV", "text": "pas" }, { "pos": "SENT", "text": "." }, { "pos": "PRON", "text": "Il" }, { "pos": "VAUX_P3SG", "text": "est" }, { "pos": "NOUN_INV", "text": "temps" }, { "pos": "CONJQUE", "text": "que" }, { "pos": "PRON", "text": "celui" }, { "pos": "PUNCT", "text": "-" }, { "pos": "ADV", "text": "ci" }, { "pos": "VERB_P1P2", "text": "dénonce" }, { "pos": "DET_SG", "text": "ce" }, { "pos": "NOUN_SG", "text": "comportement" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NOUN_SG", "text": "sabotage" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "DET_SG", "text": "l'" }, { "pos": "NOUN_SG", "text": "économie" }, { "pos": "ADJ_SG", "text": "nationale" }, { "pos": "SENT", "text": "." }, { "pos": "PUNCT", "text": "\"" }, { "pos": "NOUN_SG", "text": "Mercredi" }, { "pos": "CM", "text": "," }, { "pos": "NOUN_SG", "text": "M." }, { "pos": "NOUN_INV", "text": "Obama" }, { "pos": "VAUX_P3SG", "text": "a" }, { "pos": "PAP_SG", "text": "dit" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "VERB_INF", "text": "regretter" }, { "pos": "PREP_DE", "text": "d'" }, { "pos": "VAUX_INF", "text": "avoir" }, { "pos": "PAP_SG", "text": "perdu" }, { "pos": "DET_SG", "text": "le" }, { "pos": "NOUN_INV", "text": "sens" }, { "pos": "PREP_DE", "text": "du" }, { "pos": "NOUN_SG", "text": "contact" }, { "pos": "ADJ_SG", "text": "direct" }, { "pos": "PREP", "text": "avec" }, { "pos": "DET_PL", "text": "les" }, { "pos": "NOUN_PL", "text": "Américains" }, { "pos": "PREP", "text": "sur" }, { "pos": "DET_PL", "text": "leurs" }, { "pos": "NOUN_PL", "text": "valeurs" }, { "pos": "ADJ_PL", "text": "essentielles" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "SENT", "text": "." }, { "pos": "DET_SG", "text": "Son" }, { "pos": "ADJ2_SG", "text": "principal" }, { "pos": "NOUN_SG", "text": "conseiller" }, { "pos": "CM", "text": "," }, { "pos": "NOUN_INV", "text": "David" }, { "pos": "NOUN_INV", "text": "Axelrod" }, { "pos": "CM", "text": "," }, { "pos": "VAUX_P3SG", "text": "a" }, { "pos": "PAP_SG", "text": "évoqué" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "DET_PL", "text": "les" }, { "pos": "NOUN_PL", "text": "salaires" }, { "pos": "ADJ_PL", "text": "bloqués" }, { "pos": "CM", "text": "," }, { "pos": "DET_PL", "text": "les" }, { "pos": "NOUN_PL", "text": "emplois" }, { "pos": "ADJ_PL", "text": "perdus" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "SENT", "text": "." }, { "pos": "PREP", "text": "Pour" }, { "pos": "ADV", "text": "autant" }, { "pos": "CM", "text": "," }, { "pos": "VERB_P3SG", "text": "changera" }, { "pos": "PUNCT", "text": "-" }, { "pos": "NOUN_INV", "text": "t" }, { "pos": "PUNCT", "text": "-" }, { "pos": "PRON", "text": "il" }, { "pos": "PREP_DE", "text": "d'" }, { "pos": "NOUN_SG", "text": "attitude" }, { "pos": "NOUN_INV", "text": "vis" }, { "pos": "PUNCT", "text": "-" }, { "pos": "PREP_A", "text": "à" }, { "pos": "PUNCT", "text": "-" }, { "pos": "NOUN_INV", "text": "vis" }, { "pos": "PREP_DE", "text": "du" }, { "pos": "NOUN_INV", "text": "Congrès" }, { "pos": "SENT", "text": "?" }, { "pos": "PRON", "text": "Peu" }, { "pos": "PC", "text": "y" }, { "pos": "VERB_P3PL", "text": "croient" }, { "pos": "SENT", "text": "." }, { "pos": "DET_SG", "text": "La" }, { "pos": "NOUN_SG", "text": "Chambre" }, { "pos": "VAUX_P3SG", "text": "a" }, { "pos": "PAP_SG", "text": "voté" }, { "pos": "PREP", "text": "en" }, { "pos": "NOUN_SG", "text": "décembre" }, { "pos": "NUM", "text": "2009" }, { "pos": "DET_SG", "text": "une" }, { "pos": "NOUN_SG", "text": "loi" }, { "pos": "PREP", "text": "sur" }, { "pos": "DET_SG", "text": "la" }, { "pos": "NOUN_SG", "text": "création" }, { "pos": "PREP_DE", "text": "d'" }, { "pos": "NOUN_PL", "text": "emplois" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NUM", "text": "174" }, { "pos": "NOUN_PL", "text": "milliards" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NOUN_PL", "text": "dollars" }, { "pos": "ADV", "text": "non" }, { "pos": "ADV", "text": "encore" }, { "pos": "PAP_SG", "text": "adoptée" }, { "pos": "PREP_A", "text": "au" }, { "pos": "NOUN_SG", "text": "Sénat" }, { "pos": "SENT", "text": "." }, { "pos": "DET_PL", "text": "Les" }, { "pos": "NOUN_PL", "text": "républicains" }, { "pos": "VERB_P3PL", "text": "assimilent" }, { "pos": "ADV", "text": "désormais" }, { "pos": "DET_SG", "text": "toute" }, { "pos": "NOUN_SG", "text": "dépense" }, { "pos": "ADJ_SG", "text": "publique" }, { "pos": "PREP_A", "text": "à" }, { "pos": "DET_SG", "text": "une" }, { "pos": "NOUN_SG", "text": "gabegie" }, { "pos": "SENT", "text": "." }, { "pos": "NOUN_INV", "text": "Harry" }, { "pos": "NOUN_INV", "text": "Reid" }, { "pos": "CM", "text": "," }, { "pos": "DET_SG", "text": "le" }, { "pos": "NOUN_SG", "text": "leader" }, { "pos": "PREP_DE", "text": "des" }, { "pos": "NOUN_PL", "text": "démocrates" }, { "pos": "PREP_A", "text": "au" }, { "pos": "NOUN_SG", "text": "Sénat" }, { "pos": "CM", "text": "," }, { "pos": "VERB_P3SG", "text": "négocierait" }, { "pos": "ADV", "text": "déjà" }, { "pos": "PREP", "text": "avec" }, { "pos": "PRON", "text": "eux" }, { "pos": "SENT", "text": "." }, { "pos": "PRON", "text": "Certains" }, { "pos": "VERB_P3PL", "text": "imaginent" }, { "pos": "DET_SG", "text": "un" }, { "pos": "NOUN_SG", "text": "abandon" }, { "pos": "CM", "text": "," }, { "pos": "ADV", "text": "pourtant" }, { "pos": "ADV", "text": "peu" }, { "pos": "ADJ_SG", "text": "probable" }, { "pos": "CM", "text": "," }, { "pos": "PREP_DE", "text": "du" }, { "pos": "NOUN_SG", "text": "plan" }, { "pos": "PREP_DE", "text": "d'" }, { "pos": "NOUN_SG", "text": "assurance" }, { "pos": "NOUN_SG", "text": "santé" }, { "pos": "MISC", "text": "afin" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "VERB_INF", "text": "parvenir" }, { "pos": "PREP_A", "text": "à" }, { "pos": "DET_SG", "text": "un" }, { "pos": "NOUN_SG", "text": "soutien" }, { "pos": "ADJ_SG", "text": "républicain" }, { "pos": "PREP_A", "text": "aux" }, { "pos": "NOUN_PL", "text": "embauches" }, { "pos": "PREP", "text": "dans" }, { "pos": "DET_PL", "text": "les" }, { "pos": "NOUN_INV", "text": "PME" }, { "pos": "SENT", "text": "." }, { "pos": "DET_PL", "text": "D'" }, { "pos": "ADJ_PL", "text": "autres" }, { "pos": "VERB_P3PL", "text": "envisagent" }, { "pos": "PREP_DE", "text": "d'" }, { "pos": "VERB_INF", "text": "affecter" }, { "pos": "PREP_A", "text": "à" }, { "pos": "DET_SG", "text": "l'" }, { "pos": "NOUN_SG", "text": "emploi" }, { "pos": "NUM", "text": "75" }, { "pos": "NOUN_PL", "text": "milliards" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NOUN_PL", "text": "dollars" }, { "pos": "ADJ_INV", "text": "pris" }, { "pos": "PREP", "text": "sur" }, { "pos": "DET_SG", "text": "le" }, { "pos": "NOUN_SG", "text": "plan" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NOUN_SG", "text": "sauvetage" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "DET_SG", "text": "la" }, { "pos": "NOUN_SG", "text": "finance" }, { "pos": "ADJ_SG", "text": "américaine" }, { "pos": "PUNCT", "text": "(" }, { "pos": "NOUN_SG", "text": "dit" }, { "pos": "NOUN_INV", "text": "TARP" }, { "pos": "PUNCT", "text": ")" }, { "pos": "SENT", "text": "." }, { "pos": "ADV", "text": "Plus" }, { "pos": "ADV", "text": "encore" }, { "pos": "CONJQUE", "text": "que" }, { "pos": "NOUN_SG", "text": "M." }, { "pos": "NOUN_INV", "text": "Obama" }, { "pos": "CM", "text": "," }, { "pos": "PRON", "text": "c'" }, { "pos": "VAUX_P3SG", "text": "est" }, { "pos": "DET_SG", "text": "son" }, { "pos": "NOUN_SG", "text": "parti" }, { "pos": "CM", "text": "," }, { "pos": "ADJ_SG", "text": "tétanisé" }, { "pos": "PREP", "text": "par" }, { "pos": "DET_SG", "text": "la" }, { "pos": "NOUN_SG", "text": "perspective" }, { "pos": "PREP_DE", "text": "d'" }, { "pos": "DET_SG", "text": "une" }, { "pos": "NOUN_SG", "text": "défaite" }, { "pos": "ADJ_SG", "text": "électorale" }, { "pos": "PREP", "text": "dans" }, { "pos": "NUM", "text": "dix" }, { "pos": "NOUN_INV", "text": "mois" }, { "pos": "CM", "text": "," }, { "pos": "RELPRO", "text": "qui" }, { "pos": "VAUX_P3SG", "text": "a" }, { "pos": "NOUN_SG", "text": "besoin" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NOUN_PL", "text": "mesures" }, { "pos": "ADJ_PL", "text": "rapides" }, { "pos": "SENT", "text": "." }, { "pos": "NOUN_SG", "text": "http" }, { "pos": "PUNCT", "text": ":" }, { "pos": "PUNCT", "text": "/" }, { "pos": "PUNCT", "text": "/" }, { "pos": "NOUN_INV", "text": "www.lemonde.fr" }, { "pos": "PUNCT", "text": "/" }, { "pos": "NOUN_PL", "text": "ameriques" }, { "pos": "PUNCT", "text": "/" }, { "pos": "NOUN_SG", "text": "article" }, { "pos": "PUNCT", "text": "/" }, { "pos": "NUM", "text": "2010" }, { "pos": "PUNCT", "text": "/" }, { "pos": "NUM", "text": "01" }, { "pos": "PUNCT", "text": "/" }, { "pos": "NUM", "text": "21" }, { "pos": "PUNCT", "text": "/" }, { "pos": "DET_PL", "text": "les" }, { "pos": "PUNCT", "text": "-" }, { "pos": "NOUN_PL", "text": "etats" }, { "pos": "PUNCT", "text": "-" }, { "pos": "NOUN_PL", "text": "unis" }, { "pos": "PUNCT", "text": "-" }, { "pos": "NOUN_SG", "text": "face" }, { "pos": "PUNCT", "text": "-" }, { "pos": "PREP_A", "text": "au" }, { "pos": "PUNCT", "text": "-" }, { "pos": "NOUN_SG", "text": "defi" }, { "pos": "PUNCT", "text": "-" }, { "pos": "ADJ_SG", "text": "persistant" }, { "pos": "PUNCT", "text": "-" }, { "pos": "PREP_DE", "text": "du" }, { "pos": "PUNCT", "text": "-" }, { "pos": "NOUN_SG", "text": "chomage" }, { "pos": "SYM", "text": "_" }, { "pos": "NUM", "text": "1294839" }, { "pos": "SYM", "text": "_" }, { "pos": "NUM", "text": "3222" }, { "pos": "SENT", "text": "." }, { "pos": "NOUN_SG", "text": "html" }, { "pos": "SYM", "text": "#" }, { "pos": "NOUN_SG", "text": "xtor" }, { "pos": "SYM", "text": "=" }, { "pos": "NOUN_INV", "text": "RSS" }, { "pos": "PUNCT", "text": "-" }, { "pos": "NUM", "text": "3210" }, { "pos": "NUM", "text": "2010.01.21" } ], "requestId": "c4bdf301-9d26-41cf-b9ef-26f83ded0fb9", "timers": { "rblJe": 535, "rliJe": 4 } } python-0.7.4/tests/mock-data/response/fra-doc-morphology_complete.status 0000664 0000000 0000000 00000000003 12636317025 0026546 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/fra-doc-sentiment.json 0000664 0000000 0000000 00000000242 12636317025 0024120 0 ustar 00root root 0000000 0000000 { "code": "unsupportedLanguage", "message": "French is not supported by Rosette Sentiment Analyzer", "requestId": "a2c25ed3-7a25-4174-94df-81f1a858a00c" } python-0.7.4/tests/mock-data/response/fra-doc-sentiment.status 0000664 0000000 0000000 00000000003 12636317025 0024465 0 ustar 00root root 0000000 0000000 415 python-0.7.4/tests/mock-data/response/fra-sentence-categories.json 0000664 0000000 0000000 00000000233 12636317025 0025276 0 ustar 00root root 0000000 0000000 { "code": "unsupportedLanguage", "message": "French is not supported by Rosette Categorizer", "requestId": "699101dd-4350-4c3f-afe4-7fea556f140c" } python-0.7.4/tests/mock-data/response/fra-sentence-categories.status 0000664 0000000 0000000 00000000003 12636317025 0025643 0 ustar 00root root 0000000 0000000 415 python-0.7.4/tests/mock-data/response/fra-sentence-entities.json 0000664 0000000 0000000 00000003244 12636317025 0025002 0 ustar 00root root 0000000 0000000 { "entities": [ { "confidence": 0.005682140588760376, "count": 2, "indocChainId": 2, "mention": "Afghanistan", "normalized": "Afghanistan", "type": "LOCATION" }, { "confidence": 0.005184590816497803, "count": 1, "indocChainId": 0, "mention": "Richard Holbrooke", "normalized": "Richard Holbrooke", "type": "PERSON" }, { "confidence": 0.006463110446929932, "count": 1, "indocChainId": 1, "mention": "Obama", "normalized": "Obama", "type": "PERSON" }, { "confidence": 0.007083892822265625, "count": 1, "indocChainId": 4, "mention": "Inde", "normalized": "Inde", "type": "LOCATION" }, { "confidence": 0.00651097297668457, "count": 1, "indocChainId": 5, "mention": "Russie", "normalized": "Russie", "type": "LOCATION" }, { "confidence": 0.006072402000427246, "count": 1, "indocChainId": 6, "mention": "Turquie", "normalized": "Turquie", "type": "LOCATION" }, { "confidence": 0.005214691162109375, "count": 1, "indocChainId": 7, "mention": "Arabie saoudite", "normalized": "Arabie saoudite", "type": "LOCATION" }, { "confidence": 0.00521475076675415, "count": 1, "indocChainId": 8, "mention": "Emirats arabes unis", "normalized": "Emirats arabes unis", "type": "LOCATION" } ], "requestId": "a153dfb0-d82c-40f3-82d8-f6da36b7901a", "timers": { "rblJe": 1, "rexJe": 9, "rliJe": 4 } } python-0.7.4/tests/mock-data/response/fra-sentence-entities.status 0000664 0000000 0000000 00000000003 12636317025 0025342 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/fra-sentence-entities_linked.json 0000664 0000000 0000000 00000002372 12636317025 0026331 0 ustar 00root root 0000000 0000000 { "entities": [ { "confidence": 0.5999774000449077, "entityId": "Q155649", "indocChainId": 0, "mention": "Richard Holbrooke" }, { "confidence": 0.5542817281359562, "entityId": "Q76", "indocChainId": 1, "mention": "Obama" }, { "confidence": 0.344601070328921, "entityId": "Q889", "indocChainId": 2, "mention": "Afghanistan" }, { "confidence": 0.48661730641588585, "entityId": "Q153317", "indocChainId": 4, "mention": "Inde" }, { "confidence": 0.6275727091341415, "entityId": "Q159", "indocChainId": 5, "mention": "Russie" }, { "confidence": 0.6695511508771029, "entityId": "Q43", "indocChainId": 6, "mention": "Turquie" }, { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 7, "mention": "Arabie saoudite" }, { "confidence": 0.5250845514345862, "entityId": "NEW-CLUSTER", "indocChainId": 8, "mention": "Emirats arabes unis" } ], "requestId": "bfffb197-066d-4282-96e6-c6b5adb6b91d", "timers": { "rblJe": 2, "res": 113, "rexJe": 5, "rliJe": 4 } } python-0.7.4/tests/mock-data/response/fra-sentence-entities_linked.status 0000664 0000000 0000000 00000000003 12636317025 0026670 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/fra-sentence-language.json 0000664 0000000 0000000 00000001017 12636317025 0024735 0 ustar 00root root 0000000 0000000 { "languageDetections": [ { "confidence": 0.022020024095284807, "language": "fra" }, { "confidence": 0.007541103556368278, "language": "cat" }, { "confidence": 0.007162807923754788, "language": "spa" }, { "confidence": 0.005914737677344184, "language": "eng" }, { "confidence": 0.005347023739733947, "language": "ron" } ], "requestId": "c6e91eff-63f2-49b1-9f4e-8573d4a4ffee", "timers": { "rliJe": 3 } } python-0.7.4/tests/mock-data/response/fra-sentence-language.status 0000664 0000000 0000000 00000000003 12636317025 0025301 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/fra-sentence-morphology_complete.json 0000664 0000000 0000000 00000027613 12636317025 0027253 0 ustar 00root root 0000000 0000000 { "compounds": [], "hanReadings": [], "lemmas": [ { "lemma": "Richard", "text": "Richard" }, { "lemma": "Holbrooke", "text": "Holbrooke" }, { "lemma": "vouloir", "text": "veut" }, { "lemma": "souligner", "text": "souligner" }, { "lemma": "à", "text": "à" }, { "lemma": "quel", "text": "quel" }, { "lemma": "point", "text": "point" }, { "lemma": "le", "text": "l'" }, { "lemma": "administration", "text": "administration" }, { "lemma": "Obama", "text": "Obama" }, { "lemma": "être", "text": "est" }, { "lemma": "engager", "text": "engagée" }, { "lemma": "dans", "text": "dans" }, { "lemma": "un", "text": "un" }, { "lemma": "\"", "text": "\"" }, { "lemma": "intense", "text": "intense" }, { "lemma": "processus", "text": "processus" }, { "lemma": "diplomatique", "text": "diplomatique" }, { "lemma": "\"", "text": "\"" }, { "lemma": "pour", "text": "pour" }, { "lemma": "prendre", "text": "prendre" }, { "lemma": "en", "text": "en" }, { "lemma": "compte", "text": "compte" }, { "lemma": "le", "text": "la" }, { "lemma": "dimension", "text": "dimension" }, { "lemma": "régional", "text": "régionale" }, { "lemma": "de le", "text": "du" }, { "lemma": "conflit", "text": "conflit" }, { "lemma": "en", "text": "en" }, { "lemma": "Afghanistan", "text": "Afghanistan" }, { "lemma": ".", "text": "." }, { "lemma": "\"", "text": "\"" }, { "lemma": "il", "text": "Il" }, { "lemma": "ne", "text": "n'" }, { "lemma": "y", "text": "y" }, { "lemma": "avoir", "text": "a" }, { "lemma": "pas", "text": "pas" }, { "lemma": "de", "text": "d'" }, { "lemma": "issue", "text": "issue" }, { "lemma": "en", "text": "en" }, { "lemma": "Afghanistan", "text": "Afghanistan" }, { "lemma": "sans", "text": "sans" }, { "lemma": "prendre", "text": "prendre" }, { "lemma": "en", "text": "en" }, { "lemma": "compte", "text": "compte" }, { "lemma": "tout", "text": "tous" }, { "lemma": "celui", "text": "ceux" }, { "lemma": "qui", "text": "qui" }, { "lemma": "avoir", "text": "ont" }, { "lemma": "un", "text": "un" }, { "lemma": "intérêt", "text": "intérêt" }, { "lemma": "stratégique", "text": "stratégique" }, { "lemma": "(", "text": "(" }, { "lemma": "dans", "text": "dans" }, { "lemma": "le", "text": "la" }, { "lemma": "région", "text": "région" }, { "lemma": ")", "text": ")" }, { "lemma": ",", "text": "," }, { "lemma": "tout", "text": "tous" }, { "lemma": "le", "text": "les" }, { "lemma": "acteur", "text": "acteurs" }, { "lemma": ",", "text": "," }, { "lemma": "y", "text": "y" }, { "lemma": "comprendre", "text": "compris" }, { "lemma": "celui", "text": "ceux" }, { "lemma": "qui", "text": "qui" }, { "lemma": "ne", "text": "n'" }, { "lemma": "avoir", "text": "ont" }, { "lemma": "pas", "text": "pas" }, { "lemma": "de", "text": "de" }, { "lemma": "frontière", "text": "frontière" }, { "lemma": "commun", "text": "commune" }, { "lemma": "avec", "text": "avec" }, { "lemma": "ce", "text": "ce" }, { "lemma": "pays", "text": "pays" }, { "lemma": "\"", "text": "\"" }, { "lemma": ",", "text": "," }, { "lemma": "dire", "text": "dit" }, { "lemma": "-", "text": "-" }, { "lemma": "il", "text": "il" }, { "lemma": ",", "text": "," }, { "lemma": "en", "text": "en" }, { "lemma": "mentionner", "text": "mentionnant" }, { "lemma": "le", "text": "l'" }, { "lemma": "Inde", "text": "Inde" }, { "lemma": ",", "text": "," }, { "lemma": "le", "text": "la" }, { "lemma": "Russie", "text": "Russie" }, { "lemma": ",", "text": "," }, { "lemma": "le", "text": "la" }, { "lemma": "Turquie", "text": "Turquie" }, { "lemma": ",", "text": "," }, { "lemma": "le", "text": "l'" }, { "lemma": "Arabie", "text": "Arabie" }, { "lemma": "saoudite", "text": "saoudite" }, { "lemma": ",", "text": "," }, { "lemma": "le", "text": "les" }, { "lemma": "émirat", "text": "Emirats" }, { "lemma": "arabe", "text": "arabes" }, { "lemma": "uni", "text": "unis" }, { "lemma": ".", "text": "." } ], "posTags": [ { "pos": "NOUN_INV", "text": "Richard" }, { "pos": "NOUN_INV", "text": "Holbrooke" }, { "pos": "VERB_P3SG", "text": "veut" }, { "pos": "VERB_INF", "text": "souligner" }, { "pos": "PREP_A", "text": "à" }, { "pos": "DET_SG", "text": "quel" }, { "pos": "NOUN_SG", "text": "point" }, { "pos": "DET_SG", "text": "l'" }, { "pos": "NOUN_SG", "text": "administration" }, { "pos": "NOUN_INV", "text": "Obama" }, { "pos": "VAUX_P3SG", "text": "est" }, { "pos": "PAP_SG", "text": "engagée" }, { "pos": "PREP", "text": "dans" }, { "pos": "DET_SG", "text": "un" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "ADJ_SG", "text": "intense" }, { "pos": "NOUN_INV", "text": "processus" }, { "pos": "ADJ_SG", "text": "diplomatique" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "PREP", "text": "pour" }, { "pos": "VERB_INF", "text": "prendre" }, { "pos": "PREP", "text": "en" }, { "pos": "NOUN_SG", "text": "compte" }, { "pos": "DET_SG", "text": "la" }, { "pos": "NOUN_SG", "text": "dimension" }, { "pos": "ADJ_SG", "text": "régionale" }, { "pos": "PREP_DE", "text": "du" }, { "pos": "NOUN_SG", "text": "conflit" }, { "pos": "PREP", "text": "en" }, { "pos": "NOUN_INV", "text": "Afghanistan" }, { "pos": "SENT", "text": "." }, { "pos": "PUNCT", "text": "\"" }, { "pos": "PRON", "text": "Il" }, { "pos": "NEG", "text": "n'" }, { "pos": "PC", "text": "y" }, { "pos": "VAUX_P3SG", "text": "a" }, { "pos": "ADV", "text": "pas" }, { "pos": "PREP_DE", "text": "d'" }, { "pos": "NOUN_SG", "text": "issue" }, { "pos": "PREP", "text": "en" }, { "pos": "NOUN_INV", "text": "Afghanistan" }, { "pos": "PREP", "text": "sans" }, { "pos": "VERB_INF", "text": "prendre" }, { "pos": "PREP", "text": "en" }, { "pos": "NOUN_SG", "text": "compte" }, { "pos": "DET_PL", "text": "tous" }, { "pos": "PRON", "text": "ceux" }, { "pos": "RELPRO", "text": "qui" }, { "pos": "VAUX_P3PL", "text": "ont" }, { "pos": "DET_SG", "text": "un" }, { "pos": "NOUN_SG", "text": "intérêt" }, { "pos": "ADJ_SG", "text": "stratégique" }, { "pos": "PUNCT", "text": "(" }, { "pos": "PREP", "text": "dans" }, { "pos": "DET_SG", "text": "la" }, { "pos": "NOUN_SG", "text": "région" }, { "pos": "PUNCT", "text": ")" }, { "pos": "CM", "text": "," }, { "pos": "PRON", "text": "tous" }, { "pos": "DET_PL", "text": "les" }, { "pos": "NOUN_PL", "text": "acteurs" }, { "pos": "CM", "text": "," }, { "pos": "PC", "text": "y" }, { "pos": "VERB_P1P2", "text": "compris" }, { "pos": "PRON", "text": "ceux" }, { "pos": "RELPRO", "text": "qui" }, { "pos": "NEG", "text": "n'" }, { "pos": "VAUX_P3PL", "text": "ont" }, { "pos": "ADV", "text": "pas" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NOUN_SG", "text": "frontière" }, { "pos": "ADJ_SG", "text": "commune" }, { "pos": "PREP", "text": "avec" }, { "pos": "DET_SG", "text": "ce" }, { "pos": "NOUN_INV", "text": "pays" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "CM", "text": "," }, { "pos": "VERB_P3SG", "text": "dit" }, { "pos": "PUNCT", "text": "-" }, { "pos": "PRON", "text": "il" }, { "pos": "CM", "text": "," }, { "pos": "PREP", "text": "en" }, { "pos": "VERB_PRP", "text": "mentionnant" }, { "pos": "DET_SG", "text": "l'" }, { "pos": "NOUN_INV", "text": "Inde" }, { "pos": "CM", "text": "," }, { "pos": "DET_SG", "text": "la" }, { "pos": "NOUN_INV", "text": "Russie" }, { "pos": "CM", "text": "," }, { "pos": "DET_SG", "text": "la" }, { "pos": "NOUN_INV", "text": "Turquie" }, { "pos": "CM", "text": "," }, { "pos": "DET_SG", "text": "l'" }, { "pos": "NOUN_INV", "text": "Arabie" }, { "pos": "ADJ_SG", "text": "saoudite" }, { "pos": "CM", "text": "," }, { "pos": "DET_PL", "text": "les" }, { "pos": "NOUN_PL", "text": "Emirats" }, { "pos": "ADJ_PL", "text": "arabes" }, { "pos": "NOUN_PL", "text": "unis" }, { "pos": "SENT", "text": "." } ], "requestId": "128a54c2-5721-4313-9583-f3d8ec527182", "timers": { "rblJe": 2, "rliJe": 4 } } python-0.7.4/tests/mock-data/response/fra-sentence-morphology_complete.status 0000664 0000000 0000000 00000000003 12636317025 0027605 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/fra-sentence-sentiment.json 0000664 0000000 0000000 00000000242 12636317025 0025157 0 ustar 00root root 0000000 0000000 { "code": "unsupportedLanguage", "message": "French is not supported by Rosette Sentiment Analyzer", "requestId": "f9c728f7-24d7-4cdf-ba62-65f75fa890e8" } python-0.7.4/tests/mock-data/response/fra-sentence-sentiment.status 0000664 0000000 0000000 00000000003 12636317025 0025524 0 ustar 00root root 0000000 0000000 415 python-0.7.4/tests/mock-data/response/fra-url-categories.json 0000664 0000000 0000000 00000000233 12636317025 0024274 0 ustar 00root root 0000000 0000000 { "code": "unsupportedLanguage", "message": "French is not supported by Rosette Categorizer", "requestId": "9ed4ec63-536a-465a-b6cc-0f37fe5a9ca5" } python-0.7.4/tests/mock-data/response/fra-url-categories.status 0000664 0000000 0000000 00000000003 12636317025 0024641 0 ustar 00root root 0000000 0000000 415 python-0.7.4/tests/mock-data/response/fra-url-entities.json 0000664 0000000 0000000 00000021470 12636317025 0024001 0 ustar 00root root 0000000 0000000 { "entities": [ { "confidence": 0.02106780807177226, "count": 6, "indocChainId": 0, "mention": "David Cameron", "normalized": "David Cameron", "type": "PERSON" }, { "confidence": 0.012439978122711182, "count": 5, "indocChainId": 14, "mention": "SNP", "normalized": "SNP", "type": "ORGANIZATION" }, { "confidence": 0.013739681243896485, "count": 5, "indocChainId": 18, "mention": "Ecosse", "normalized": "Ecosse", "type": "LOCATION" }, { "confidence": 0.016117572784423828, "count": 3, "indocChainId": 12, "mention": "démocrates", "normalized": "démocrates", "type": "ORGANIZATION" }, { "confidence": 0.015858054161071777, "count": 3, "indocChainId": 16, "mention": "Ukip", "normalized": "Ukip", "type": "ORGANIZATION" }, { "confidence": 0.008270978927612305, "count": 3, "indocChainId": 17, "mention": "Labour", "normalized": "Labour", "type": "ORGANIZATION" }, { "confidence": 0.02269589900970459, "count": 2, "indocChainId": 5, "mention": "Royaume-Uni", "normalized": "Royaume-Uni", "type": "LOCATION" }, { "confidence": 0.021167248487472534, "count": 2, "indocChainId": 6, "mention": "Union européenne", "normalized": "Union européenne", "type": "LOCATION" }, { "confidence": 0.014843016862869263, "count": 2, "indocChainId": 37, "mention": "député", "normalized": "député", "type": "TITLE" }, { "confidence": 0.011724323034286499, "count": 2, "indocChainId": 48, "mention": "Bourse de Londres", "normalized": "Bourse de Londres", "type": "ORGANIZATION" }, { "confidence": 0.0036743879318237305, "count": 1, "indocChainId": 0, "mention": "David Cameron\nChallenges", "normalized": "David Cameron Challenges", "type": "PERSON" }, { "confidence": 0.0036674141883850098, "count": 1, "indocChainId": 1, "mention": "Europe", "normalized": "Europe", "type": "LOCATION" }, { "confidence": 0.004899203777313232, "count": 1, "indocChainId": 8, "mention": "Kirsty Wigglesworth", "normalized": "Kirsty Wigglesworth", "type": "PERSON" }, { "confidence": 0.002910017967224121, "count": 1, "indocChainId": 9, "mention": "AP", "normalized": "AP", "type": "ORGANIZATION" }, { "confidence": 0.009074151515960693, "count": 1, "indocChainId": 10, "mention": "Elizabeth II", "normalized": "Elizabeth II", "type": "PERSON" }, { "confidence": 0.00494539737701416, "count": 1, "indocChainId": 11, "mention": "Buckingham", "normalized": "Buckingham", "type": "LOCATION" }, { "confidence": 0.006138741970062256, "count": 1, "indocChainId": 13, "mention": "députés", "normalized": "députés", "type": "TITLE" }, { "confidence": 0.014360666275024414, "count": 1, "indocChainId": 20, "mention": "Nigel Farage", "normalized": "Nigel Farage", "type": "PERSON" }, { "confidence": 0.014366745948791504, "count": 1, "indocChainId": 21, "mention": "chef", "normalized": "chef", "type": "TITLE" }, { "confidence": 0.0030326247215270996, "count": 1, "indocChainId": 23, "mention": "South Thanet", "normalized": "South Thanet", "type": "LOCATION" }, { "confidence": 0.01049792766571045, "count": 1, "indocChainId": 25, "mention": "démocrate", "normalized": "démocrate", "type": "ORGANIZATION" }, { "confidence": 0.021206259727478027, "count": 1, "indocChainId": 26, "mention": "Nick Clegg", "normalized": "Nick Clegg", "type": "PERSON" }, { "confidence": 0.004912674427032471, "count": 1, "indocChainId": 27, "mention": "Miliband", "normalized": "Miliband", "type": "PERSON" }, { "confidence": 0.0247611403465271, "count": 1, "indocChainId": 27, "mention": "Ed Miliband", "normalized": "Ed Miliband", "type": "PERSON" }, { "confidence": 0.032201409339904785, "count": 1, "indocChainId": 32, "mention": "Chambre des Communes", "normalized": "Chambre des Communes", "type": "ORGANIZATION" }, { "confidence": 0.03113532066345215, "count": 1, "indocChainId": 33, "mention": "Alex Salmond", "normalized": "Alex Salmond", "type": "PERSON" }, { "confidence": 0.009601056575775146, "count": 1, "indocChainId": 35, "mention": "Mhairi Black", "normalized": "Mhairi Black", "type": "PERSON" }, { "confidence": 0.008572161197662354, "count": 1, "indocChainId": 36, "mention": "Westminster", "normalized": "Westminster", "type": "LOCATION" }, { "confidence": 0.00962144136428833, "count": 1, "indocChainId": 38, "mention": "Labour Douglas Alexander", "normalized": "Labour Douglas Alexander", "type": "ORGANIZATION" }, { "confidence": 0.011308491230010986, "count": 1, "indocChainId": 39, "mention": "Ed Balls", "normalized": "Ed Balls", "type": "PERSON" }, { "confidence": 0.0160825252532959, "count": 1, "indocChainId": 41, "mention": "Jim Murphy", "normalized": "Jim Murphy", "type": "PERSON" }, { "confidence": 0.002979457378387451, "count": 1, "indocChainId": 44, "mention": "Vince Cable", "normalized": "Vince Cable", "type": "PERSON" }, { "confidence": 0.008275032043457031, "count": 1, "indocChainId": 45, "mention": "ministre", "normalized": "ministre", "type": "TITLE" }, { "confidence": 0.011619985103607178, "count": 1, "indocChainId": 50, "mention": "UE", "normalized": "UE", "type": "LOCATION" }, { "confidence": 0.022272944450378418, "count": 1, "indocChainId": 54, "mention": "Glasgow", "normalized": "Glasgow", "type": "LOCATION" }, { "confidence": 0.003254711627960205, "count": 1, "indocChainId": 55, "mention": "Edimbourg", "normalized": "Edimbourg", "type": "LOCATION" }, { "confidence": 0.019964516162872314, "count": 1, "indocChainId": 57, "mention": "Patrick Dunleavy", "normalized": "Patrick Dunleavy", "type": "PERSON" }, { "confidence": 0.01763540506362915, "count": 1, "indocChainId": 58, "mention": "London School of Economics", "normalized": "London School of Economics", "type": "ORGANIZATION" }, { "confidence": 0.008434712886810303, "count": 1, "indocChainId": 58, "mention": "LSE", "normalized": "LSE", "type": "ORGANIZATION" }, { "confidence": 0.025185048580169678, "count": 1, "indocChainId": 60, "mention": "Premier ministre", "normalized": "Premier ministre", "type": "TITLE" }, { "confidence": 0.0143471360206604, "count": 1, "indocChainId": 61, "mention": "maire", "normalized": "maire", "type": "TITLE" }, { "confidence": 0.009080350399017334, "count": 1, "indocChainId": 62, "mention": "Londres", "normalized": "Londres", "type": "LOCATION" }, { "confidence": 0.015038907527923584, "count": 1, "indocChainId": 63, "mention": "Boris Johnson", "normalized": "Boris Johnson", "type": "PERSON" }, { "confidence": 0.009148657321929932, "count": 1, "indocChainId": 65, "mention": "Uxbridge", "normalized": "Uxbridge", "type": "LOCATION" }, { "confidence": 0.1097421646118164, "count": 1, "indocChainId": 67, "mention": "AFP", "normalized": "AFP", "type": "ORGANIZATION" } ], "requestId": "aa75dc98-1189-4f37-a623-8a804d788ee7", "timers": { "rblJe": 4, "rexJe": 231, "rliJe": 5, "textExtractor": 22, "urlContentDownloader": 74 } } python-0.7.4/tests/mock-data/response/fra-url-entities.status 0000664 0000000 0000000 00000000003 12636317025 0024340 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/fra-url-entities_linked.json 0000664 0000000 0000000 00000012340 12636317025 0025323 0 ustar 00root root 0000000 0000000 { "entities": [ { "confidence": 0.487369937159575, "entityId": "Q192", "indocChainId": 0, "mention": "David Cameron Challenges" }, { "confidence": 0.5411345883548877, "entityId": "Q46", "indocChainId": 1, "mention": "Europe" }, { "confidence": 0.7207765469292666, "entityId": "Q145", "indocChainId": 5, "mention": "Royaume-Uni" }, { "confidence": 0.26558639130170675, "entityId": "Q458", "indocChainId": 6, "mention": "Union européenne" }, { "confidence": 0.8390447767541483, "entityId": "NEW-CLUSTER", "indocChainId": 8, "mention": "Kirsty Wigglesworth" }, { "confidence": 0.21607979033495858, "entityId": "Q40469", "indocChainId": 9, "mention": "AP" }, { "confidence": 0.8751098420612002, "entityId": "Q9682", "indocChainId": 10, "mention": "Elizabeth II" }, { "confidence": 0.08751416407915574, "entityId": "Q23229", "indocChainId": 11, "mention": "Buckingham" }, { "confidence": 0.09432890294643219, "entityId": "Q1185830", "indocChainId": 12, "mention": "démocrates" }, { "confidence": 0.5410398782455267, "entityId": "Q10658", "indocChainId": 14, "mention": "SNP" }, { "confidence": 0.7840718470407755, "entityId": "Q10647", "indocChainId": 16, "mention": "Ukip" }, { "confidence": 0.35499804903332943, "entityId": "Q9630", "indocChainId": 17, "mention": "Labour" }, { "confidence": 0.6897989554049982, "entityId": "Q22", "indocChainId": 18, "mention": "Ecosse" }, { "confidence": 0.6382972614940312, "entityId": "Q318471", "indocChainId": 20, "mention": "Nigel Farage" }, { "confidence": 0.6252531222570918, "entityId": "Q988835", "indocChainId": 23, "mention": "South Thanet" }, { "confidence": 0.42886951782887706, "entityId": "NEW-CLUSTER", "indocChainId": 25, "mention": "démocrate" }, { "confidence": 0.6586169984625931, "entityId": "Q189947", "indocChainId": 26, "mention": "Nick Clegg" }, { "confidence": 0.6859030458013254, "entityId": "Q216594", "indocChainId": 27, "mention": "Ed Miliband" }, { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 32, "mention": "Chambre des Communes" }, { "confidence": 0.6711155231554004, "entityId": "Q10652", "indocChainId": 33, "mention": "Alex Salmond" }, { "confidence": 0.14035519084151224, "entityId": "NEW-CLUSTER", "indocChainId": 35, "mention": "Mhairi Black" }, { "confidence": 0.06297074414148623, "entityId": "Q5933", "indocChainId": 36, "mention": "Westminster" }, { "confidence": 0.3147751315322906, "entityId": "NEW-CLUSTER", "indocChainId": 38, "mention": "Labour Douglas Alexander" }, { "confidence": 0.7066427879428141, "entityId": "Q260464", "indocChainId": 39, "mention": "Ed Balls" }, { "confidence": 0.326144884684962, "entityId": "Q333702", "indocChainId": 41, "mention": "Jim Murphy" }, { "confidence": 0.6630758149696234, "entityId": "Q244312", "indocChainId": 44, "mention": "Vince Cable" }, { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 48, "mention": "Bourse de Londres" }, { "confidence": 0.5026706356051871, "entityId": "Q458", "indocChainId": 50, "mention": "UE" }, { "confidence": 0.08400702472233276, "entityId": "Q4093", "indocChainId": 54, "mention": "Glasgow" }, { "confidence": 0.6032523276618472, "entityId": "NEW-CLUSTER", "indocChainId": 55, "mention": "Edimbourg" }, { "confidence": 0.5800514092105746, "entityId": "Q7146420", "indocChainId": 57, "mention": "Patrick Dunleavy" }, { "confidence": 0.7817361386181069, "entityId": "Q174570", "indocChainId": 58, "mention": "London School of Economics" }, { "confidence": 0.8823916944348363, "entityId": "Q84", "indocChainId": 62, "mention": "Londres" }, { "confidence": 0.5246796846919077, "entityId": "Q180589", "indocChainId": 63, "mention": "Boris Johnson" }, { "confidence": 0.17523536683256627, "entityId": "Q3552816", "indocChainId": 65, "mention": "Uxbridge" }, { "confidence": 0.23969179335946114, "entityId": "Q40464", "indocChainId": 67, "mention": "AFP" } ], "requestId": "6954f9b9-f2c5-421b-b3ee-741cd09e8386", "timers": { "rblJe": 4, "res": 1143, "rexJe": 35, "rliJe": 5, "textExtractor": 33, "urlContentDownloader": 83 } } python-0.7.4/tests/mock-data/response/fra-url-entities_linked.status 0000664 0000000 0000000 00000000003 12636317025 0025666 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/fra-url-language.json 0000664 0000000 0000000 00000001107 12636317025 0023733 0 ustar 00root root 0000000 0000000 { "languageDetections": [ { "confidence": 0.0376633577964306, "language": "fra" }, { "confidence": 0.011350827336480962, "language": "cat" }, { "confidence": 0.01042540417014437, "language": "spa" }, { "confidence": 0.00913729347637604, "language": "ron" }, { "confidence": 0.007858062386031262, "language": "por" } ], "requestId": "cdd7a5c2-1cec-4391-808e-2917851016f4", "timers": { "rliJe": 5, "textExtractor": 33, "urlContentDownloader": 342 } } python-0.7.4/tests/mock-data/response/fra-url-language.status 0000664 0000000 0000000 00000000003 12636317025 0024277 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/fra-url-morphology_complete.json 0000664 0000000 0000000 00000361527 12636317025 0026256 0 ustar 00root root 0000000 0000000 { "compounds": [], "hanReadings": [], "lemmas": [ { "lemma": "élection", "text": "Elections" }, { "lemma": "britannique", "text": "britanniques" }, { "lemma": ":", "text": ":" }, { "lemma": "triomphe", "text": "triomphe" }, { "lemma": "éclatant", "text": "éclatant" }, { "lemma": "pour", "text": "pour" }, { "lemma": "David", "text": "David" }, { "lemma": "Cameron", "text": "Cameron" }, { "lemma": "challenge", "text": "Challenges" }, { "lemma": ">", "text": ">" }, { "lemma": "Europe", "text": "Europe" }, { "lemma": ">", "text": ">" }, { "lemma": "élection", "text": "Elections" }, { "lemma": "britannique", "text": "britanniques" }, { "lemma": ":", "text": ":" }, { "lemma": "triomphe", "text": "triomphe" }, { "lemma": "éclatant", "text": "éclatant" }, { "lemma": "pour", "text": "pour" }, { "lemma": "David", "text": "David" }, { "lemma": "Cameron", "text": "Cameron" }, { "lemma": "élection", "text": "Elections" }, { "lemma": "britannique", "text": "britanniques" }, { "lemma": ":", "text": ":" }, { "lemma": "triomphe", "text": "triomphe" }, { "lemma": "éclatant", "text": "éclatant" }, { "lemma": "pour", "text": "pour" }, { "lemma": "David", "text": "David" }, { "lemma": "Cameron", "text": "Cameron" }, { "lemma": "voir", "text": "Voir" }, { "lemma": "tout", "text": "tous" }, { "lemma": "son", "text": "ses" }, { "lemma": "article", "text": "articles" }, { "lemma": "publier", "text": "Publié" }, { "lemma": "le", "text": "le" }, { "lemma": "08", "text": "08" }, { "lemma": "-", "text": "-" }, { "lemma": "05", "text": "05" }, { "lemma": "-", "text": "-" }, { "lemma": "2015", "text": "2015" }, { "lemma": "à", "text": "à" }, { "lemma": "17h57", "text": "17h57" }, { "lemma": "mettre", "text": "Mis" }, { "lemma": "à", "text": "à" }, { "lemma": "jour", "text": "jour" }, { "lemma": "à", "text": "à" }, { "lemma": "19h13", "text": "19h13" }, { "lemma": "à", "text": "A" }, { "lemma": "+", "text": "+" }, { "lemma": "à", "text": "A" }, { "lemma": "-", "text": "-" }, { "lemma": "David", "text": "David" }, { "lemma": "Cameron", "text": "Cameron" }, { "lemma": "avoir", "text": "a" }, { "lemma": "brillamment", "text": "brillamment" }, { "lemma": "remporter", "text": "remporté" }, { "lemma": "de le", "text": "des" }, { "lemma": "législatives", "text": "législatives" }, { "lemma": "britannique", "text": "britanniques" }, { "lemma": "qui", "text": "qui" }, { "lemma": "faire", "text": "font" }, { "lemma": "planer", "text": "planer" }, { "lemma": "le", "text": "la" }, { "lemma": "menace", "text": "menace" }, { "lemma": "de", "text": "d'" }, { "lemma": "un", "text": "une" }, { "lemma": "sortie", "text": "sortie" }, { "lemma": "de le", "text": "du" }, { "lemma": "royaume", "text": "Royaume" }, { "lemma": "-", "text": "-" }, { "lemma": "uni", "text": "Uni" }, { "lemma": "de", "text": "de" }, { "lemma": "le", "text": "l'" }, { "lemma": "union", "text": "Union" }, { "lemma": "européen", "text": "européenne" }, { "lemma": "et", "text": "et" }, { "lemma": "consacrer", "text": "consacrent" }, { "lemma": "le", "text": "le" }, { "lemma": "succès", "text": "succès" }, { "lemma": "de le", "text": "des" }, { "lemma": "nationaliste", "text": "nationalistes" }, { "lemma": "écossais", "text": "écossais" }, { "lemma": ".", "text": "." }, { "lemma": "David", "text": "David" }, { "lemma": "Cameron", "text": "Cameron" }, { "lemma": "élection", "text": "élection" }, { "lemma": "mai", "text": "mai" }, { "lemma": "2015", "text": "2015" }, { "lemma": "(", "text": "(" }, { "lemma": "Kirsty", "text": "Kirsty" }, { "lemma": "Wigglesworth", "text": "Wigglesworth" }, { "lemma": "/", "text": "/" }, { "lemma": "AP", "text": "AP" }, { "lemma": "/", "text": "/" }, { "lemma": "SIPA", "text": "SIPA" }, { "lemma": ")", "text": ")" }, { "lemma": "conforter", "text": "Conforté" }, { "lemma": "par", "text": "par" }, { "lemma": "un", "text": "un" }, { "lemma": "résultat", "text": "résultat" }, { "lemma": "inespéré", "text": "inespéré" }, { "lemma": ",", "text": "," }, { "lemma": "le", "text": "le" }, { "lemma": "leader", "text": "leader" }, { "lemma": "de le", "text": "des" }, { "lemma": "tory", "text": "Tories" }, { "lemma": "avoir", "text": "a" }, { "lemma": "rendre", "text": "rendu" }, { "lemma": "visite", "text": "visite" }, { "lemma": "en", "text": "en" }, { "lemma": "tout", "text": "tout" }, { "lemma": "début", "text": "début" }, { "lemma": "de", "text": "d'" }, { "lemma": "après", "text": "après" }, { "lemma": "-", "text": "-" }, { "lemma": "midi", "text": "midi" }, { "lemma": "à", "text": "à" }, { "lemma": "le", "text": "la" }, { "lemma": "reine", "text": "reine" }, { "lemma": "Elizabeth", "text": "Elizabeth" }, { "lemma": "II", "text": "II" }, { "lemma": ",", "text": "," }, { "lemma": "à le", "text": "au" }, { "lemma": "palais", "text": "palais" }, { "lemma": "de", "text": "de" }, { "lemma": "Buckingham", "text": "Buckingham" }, { "lemma": ",", "text": "," }, { "lemma": "afin", "text": "afin" }, { "lemma": "de", "text": "de" }, { "lemma": "recueillir", "text": "recueillir" }, { "lemma": "son", "text": "son" }, { "lemma": "assentiment", "text": "assentiment" }, { "lemma": "formel", "text": "formel" }, { "lemma": "en", "text": "en" }, { "lemma": "vue", "text": "vue" }, { "lemma": "de", "text": "de" }, { "lemma": "former", "text": "former" }, { "lemma": "le", "text": "le" }, { "lemma": "prochain", "text": "prochain" }, { "lemma": "gouvernement", "text": "gouvernement" }, { "lemma": ".", "text": "." }, { "lemma": "\"", "text": "\"" }, { "lemma": "je", "text": "Je" }, { "lemma": "aller", "text": "vais" }, { "lemma": "maintenant", "text": "maintenant" }, { "lemma": "former", "text": "former" }, { "lemma": "un", "text": "un" }, { "lemma": "gouvernement", "text": "gouvernement" }, { "lemma": "conservateur", "text": "conservateur" }, { "lemma": "de", "text": "de" }, { "lemma": "majorité", "text": "majorité" }, { "lemma": "\"", "text": "\"" }, { "lemma": ",", "text": "," }, { "lemma": "avoir", "text": "a" }, { "lemma": "-", "text": "-" }, { "lemma": "t", "text": "t" }, { "lemma": "-", "text": "-" }, { "lemma": "il", "text": "il" }, { "lemma": "annoncer", "text": "annoncé" }, { "lemma": "à le", "text": "au" }, { "lemma": "premier", "text": "premier" }, { "lemma": "jour", "text": "jour" }, { "lemma": "de", "text": "de" }, { "lemma": "son", "text": "son" }, { "lemma": "second", "text": "second" }, { "lemma": "mandat", "text": "mandat" }, { "lemma": ".", "text": "." }, { "lemma": "en", "text": "En" }, { "lemma": "2010", "text": "2010" }, { "lemma": ",", "text": "," }, { "lemma": "le", "text": "les" }, { "lemma": "tory", "text": "Tories" }, { "lemma": "avoir", "text": "avaient" }, { "lemma": "avoir", "text": "eu" }, { "lemma": "besoin", "text": "besoin" }, { "lemma": "de le", "text": "des" }, { "lemma": "libéral", "text": "libéraux" }, { "lemma": "-", "text": "-" }, { "lemma": "démocrate", "text": "démocrates" }, { "lemma": "pour", "text": "pour" }, { "lemma": "gouverner", "text": "gouverner" }, { "lemma": ".", "text": "." }, { "lemma": "\"", "text": "\"" }, { "lemma": "un", "text": "Un" }, { "lemma": "gouvernement", "text": "gouvernement" }, { "lemma": "de", "text": "de" }, { "lemma": "majorité", "text": "majorité" }, { "lemma": "\"", "text": "\"" }, { "lemma": "le", "text": "Les" }, { "lemma": "résultat", "text": "résultats" }, { "lemma": "définitif", "text": "définitifs" }, { "lemma": "après", "text": "après" }, { "lemma": "dépouillement", "text": "dépouillement" }, { "lemma": "de le", "text": "des" }, { "lemma": "650", "text": "650" }, { "lemma": "circonscription", "text": "circonscriptions" }, { "lemma": "allouer", "text": "allouent" }, { "lemma": "331", "text": "331" }, { "lemma": "député", "text": "députés" }, { "lemma": "à le", "text": "aux" }, { "lemma": "conservateur", "text": "conservateurs" }, { "lemma": "(", "text": "(" }, { "lemma": "+", "text": "+" }, { "lemma": "24", "text": "24" }, { "lemma": ")", "text": ")" }, { "lemma": ",", "text": "," }, { "lemma": "232", "text": "232" }, { "lemma": "à le", "text": "aux" }, { "lemma": "travailliste", "text": "travaillistes" }, { "lemma": "(", "text": "(" }, { "lemma": "-", "text": "-" }, { "lemma": "26", "text": "26" }, { "lemma": ")", "text": ")" }, { "lemma": ",", "text": "," }, { "lemma": "56", "text": "56" }, { "lemma": "à le", "text": "au" }, { "lemma": "SNP", "text": "SNP" }, { "lemma": "(", "text": "(" }, { "lemma": "+", "text": "+" }, { "lemma": "50", "text": "50" }, { "lemma": ")", "text": ")" }, { "lemma": ",", "text": "," }, { "lemma": "8", "text": "8" }, { "lemma": "à le", "text": "aux" }, { "lemma": "libéral", "text": "libéraux" }, { "lemma": "démocrate", "text": "démocrates" }, { "lemma": "(", "text": "(" }, { "lemma": "-", "text": "-" }, { "lemma": "49", "text": "49" }, { "lemma": ")", "text": ")" }, { "lemma": ",", "text": "," }, { "lemma": "1", "text": "1" }, { "lemma": "à", "text": "à" }, { "lemma": "le", "text": "l'" }, { "lemma": "Ukip", "text": "Ukip" }, { "lemma": "(", "text": "(" }, { "lemma": "-", "text": "-" }, { "lemma": "1", "text": "1" }, { "lemma": ")", "text": ")" }, { "lemma": ".", "text": "." }, { "lemma": "le", "text": "Le" }, { "lemma": "labour", "text": "Labour" }, { "lemma": "avoir", "text": "a" }, { "lemma": "être", "text": "été" }, { "lemma": "laminer", "text": "laminé" }, { "lemma": "en", "text": "en" }, { "lemma": "Écosse", "text": "Ecosse" }, { "lemma": ",", "text": "," }, { "lemma": "où", "text": "où" }, { "lemma": "le", "text": "les" }, { "lemma": "indépendantiste", "text": "indépendantistes" }, { "lemma": "de le", "text": "du" }, { "lemma": "SNP", "text": "SNP" }, { "lemma": "avoir", "text": "ont" }, { "lemma": "rafler", "text": "raflé" }, { "lemma": "56", "text": "56" }, { "lemma": "de le", "text": "des" }, { "lemma": "59", "text": "59" }, { "lemma": "siège", "text": "sièges" }, { "lemma": "en", "text": "en" }, { "lemma": "jeu", "text": "jeu" }, { "lemma": "dans", "text": "dans" }, { "lemma": "leur", "text": "leur" }, { "lemma": "région", "text": "région" }, { "lemma": "autonome", "text": "autonome" }, { "lemma": ",", "text": "," }, { "lemma": "jusqu'", "text": "jusqu'" }, { "lemma": "ici", "text": "ici" }, { "lemma": "considérer", "text": "considérée" }, { "lemma": "comme", "text": "comme" }, { "lemma": "un", "text": "un" }, { "lemma": "fief", "text": "fief" }, { "lemma": "travailliste", "text": "travailliste" }, { "lemma": "inexpugnable", "text": "inexpugnable" }, { "lemma": ".", "text": "." }, { "lemma": "nombre", "text": "Nombre" }, { "lemma": "de", "text": "d'" }, { "lemma": "analyste", "text": "analystes" }, { "lemma": "avoir", "text": "avaient" }, { "lemma": "prédire", "text": "prédit" }, { "lemma": "\"", "text": "\"" }, { "lemma": "un", "text": "un" }, { "lemma": "bain", "text": "bain" }, { "lemma": "de", "text": "de" }, { "lemma": "sang", "text": "sang" }, { "lemma": "\"", "text": "\"" }, { "lemma": "politique", "text": "politique" }, { "lemma": ",", "text": "," }, { "lemma": "et", "text": "et" }, { "lemma": "il", "text": "ils" }, { "lemma": "avoir", "text": "avaient" }, { "lemma": "raison", "text": "raison" }, { "lemma": "sur", "text": "sur" }, { "lemma": "ce", "text": "ce" }, { "lemma": "point", "text": "point" }, { "lemma": ".", "text": "." }, { "lemma": "\"", "text": "\"" }, { "lemma": "bain", "text": "Bain" }, { "lemma": "de", "text": "de" }, { "lemma": "sang", "text": "sang" }, { "lemma": "politique", "text": "politique" }, { "lemma": "\"", "text": "\"" }, { "lemma": "Nigel", "text": "Nigel" }, { "lemma": "Farage", "text": "Farage" }, { "lemma": ",", "text": "," }, { "lemma": "le", "text": "le" }, { "lemma": "chef", "text": "chef" }, { "lemma": "de", "text": "de" }, { "lemma": "file", "text": "file" }, { "lemma": "de le", "text": "du" }, { "lemma": "parti", "text": "parti" }, { "lemma": "europhobere", "text": "europhobe" }, { "lemma": "Ukip", "text": "Ukip" }, { "lemma": ",", "text": "," }, { "lemma": "battre", "text": "battu" }, { "lemma": "à", "text": "à" }, { "lemma": "South", "text": "South" }, { "lemma": "Thanet", "text": "Thanet" }, { "lemma": ",", "text": "," }, { "lemma": "avoir", "text": "a" }, { "lemma": "être", "text": "été" }, { "lemma": "le", "text": "le" }, { "lemma": "premier", "text": "premier" }, { "lemma": "à", "text": "à" }, { "lemma": "démissionner", "text": "démissionner" }, { "lemma": ",", "text": "," }, { "lemma": "mettre", "text": "mettant" }, { "lemma": "à", "text": "à" }, { "lemma": "exécution", "text": "exécution" }, { "lemma": "son", "text": "sa" }, { "lemma": "promesse", "text": "promesse" }, { "lemma": "de", "text": "de" }, { "lemma": "\"", "text": "\"" }, { "lemma": "tirer", "text": "tirer" }, { "lemma": "le", "text": "le" }, { "lemma": "rideau", "text": "rideau" }, { "lemma": "\"", "text": "\"" }, { "lemma": "en", "text": "en" }, { "lemma": "cas", "text": "cas" }, { "lemma": "de", "text": "d'" }, { "lemma": "échec", "text": "échec" }, { "lemma": ".", "text": "." }, { "lemma": "son", "text": "Son" }, { "lemma": "départ", "text": "départ" }, { "lemma": "porter", "text": "porte" }, { "lemma": "un", "text": "un" }, { "lemma": "coup", "text": "coup" }, { "lemma": "extrêmement", "text": "extrêmement" }, { "lemma": "sévère", "text": "sévère" }, { "lemma": "à", "text": "à" }, { "lemma": "son", "text": "son" }, { "lemma": "parti", "text": "parti" }, { "lemma": ",", "text": "," }, { "lemma": "pourtant", "text": "pourtant" }, { "lemma": "créditer", "text": "crédité" }, { "lemma": "de", "text": "d'" }, { "lemma": "un", "text": "un" }, { "lemma": "score", "text": "score" }, { "lemma": "flatteur", "text": "flatteur" }, { "lemma": "de", "text": "de" }, { "lemma": "près", "text": "près" }, { "lemma": "de", "text": "de" }, { "lemma": "13", "text": "13" }, { "lemma": "%", "text": "%" }, { "lemma": "en", "text": "en" }, { "lemma": "voix", "text": "voix" }, { "lemma": ".", "text": "." }, { "lemma": "le", "text": "L'" }, { "lemma": "homme", "text": "homme" }, { "lemma": "-", "text": "-" }, { "lemma": "orchestre", "text": "orchestre" }, { "lemma": "de", "text": "de" }, { "lemma": "le", "text": "l'" }, { "lemma": "Ukip", "text": "Ukip" }, { "lemma": "ne", "text": "n'" }, { "lemma": "avoir", "text": "a" }, { "lemma": "toutefois", "text": "toutefois" }, { "lemma": "pas", "text": "pas" }, { "lemma": "exclure", "text": "exclu" }, { "lemma": "un", "text": "un" }, { "lemma": "\"", "text": "\"" }, { "lemma": "comere", "text": "come" }, { "lemma": "back", "text": "back" }, { "lemma": "\"", "text": "\"" }, { "lemma": ".", "text": "." }, { "lemma": "peu", "text": "Peu" }, { "lemma": "après", "text": "après" }, { "lemma": ",", "text": "," }, { "lemma": "le", "text": "le" }, { "lemma": "leader", "text": "leader" }, { "lemma": "libéral", "text": "libéral" }, { "lemma": "-", "text": "-" }, { "lemma": "démocrate", "text": "démocrate" }, { "lemma": "Nick", "text": "Nick" }, { "lemma": "Clegg", "text": "Clegg" }, { "lemma": ",", "text": "," }, { "lemma": "48", "text": "48" }, { "lemma": "an", "text": "ans" }, { "lemma": ",", "text": "," }, { "lemma": "avoir", "text": "a" }, { "lemma": "jeter", "text": "jeté" }, { "lemma": "le", "text": "l'" }, { "lemma": "éponge", "text": "éponge" }, { "lemma": "à le", "text": "au" }, { "lemma": "sortir", "text": "sortir" }, { "lemma": "de", "text": "d'" }, { "lemma": "un", "text": "une" }, { "lemma": "nuit", "text": "nuit" }, { "lemma": "\"", "text": "\"" }, { "lemma": "dévastateur", "text": "dévastatrice" }, { "lemma": "\"", "text": "\"" }, { "lemma": ",", "text": "," }, { "lemma": "selon", "text": "selon" }, { "lemma": "son", "text": "sa" }, { "lemma": "propre", "text": "propre" }, { "lemma": "expression", "text": "expression" }, { "lemma": ".", "text": "." }, { "lemma": "Ed", "text": "Ed" }, { "lemma": "Miliband", "text": "Miliband" }, { "lemma": ",", "text": "," }, { "lemma": "45", "text": "45" }, { "lemma": "an", "text": "ans" }, { "lemma": ",", "text": "," }, { "lemma": "le", "text": "le" }, { "lemma": "patron", "text": "patron" }, { "lemma": "de le", "text": "des" }, { "lemma": "travailliste", "text": "travaillistes" }, { "lemma": ",", "text": "," }, { "lemma": "avoir", "text": "a" }, { "lemma": "suivre", "text": "suivi" }, { "lemma": "le", "text": "le" }, { "lemma": "même", "text": "même" }, { "lemma": "chemin", "text": "chemin" }, { "lemma": ",", "text": "," }, { "lemma": "en", "text": "en" }, { "lemma": "endosser", "text": "endossant" }, { "lemma": "\"", "text": "\"" }, { "lemma": "le", "text": "l'" }, { "lemma": "entier", "text": "entière" }, { "lemma": "responsabilité", "text": "responsabilité" }, { "lemma": "de", "text": "de" }, { "lemma": "le", "text": "la" }, { "lemma": "défaite", "text": "défaite" }, { "lemma": "\"", "text": "\"" }, { "lemma": ".", "text": "." }, { "lemma": "\"", "text": "\"" }, { "lemma": "tsunami", "text": "Tsunami" }, { "lemma": "nationaliste", "text": "nationaliste" }, { "lemma": "\"", "text": "\"" }, { "lemma": "sur", "text": "sur" }, { "lemma": "le", "text": "l'" }, { "lemma": "Écosse", "text": "Ecosse" }, { "lemma": "le", "text": "Les" }, { "lemma": "autre", "text": "autres" }, { "lemma": "grand", "text": "grands" }, { "lemma": "perdant", "text": "perdants" }, { "lemma": "de le", "text": "du" }, { "lemma": "scrutin", "text": "scrutin" }, { "lemma": "être", "text": "sont" }, { "lemma": "le", "text": "les" }, { "lemma": "institut", "text": "instituts" }, { "lemma": "de", "text": "de" }, { "lemma": "sondage", "text": "sondages" }, { "lemma": "qui", "text": "qui" }, { "lemma": "ne", "text": "n'" }, { "lemma": "avoir", "text": "ont" }, { "lemma": "cesser", "text": "cessé" }, { "lemma": "de", "text": "de" }, { "lemma": "prédire", "text": "prédire" }, { "lemma": "un", "text": "un" }, { "lemma": "résultat", "text": "résultat" }, { "lemma": "ultra", "text": "ultra" }, { "lemma": "serrer", "text": "serré" }, { "lemma": ",", "text": "," }, { "lemma": "renvoyer", "text": "renvoyant" }, { "lemma": "dos", "text": "dos" }, { "lemma": "à", "text": "à" }, { "lemma": "dos", "text": "dos" }, { "lemma": "le", "text": "les" }, { "lemma": "deux", "text": "deux" }, { "lemma": "parti", "text": "partis" }, { "lemma": "traditionnel", "text": "traditionnels" }, { "lemma": "frapper", "text": "frappés" }, { "lemma": "de", "text": "de" }, { "lemma": "déclin", "text": "déclin" }, { "lemma": "dans", "text": "dans" }, { "lemma": "un", "text": "un" }, { "lemma": "paysage", "text": "paysage" }, { "lemma": "caractériser", "text": "caractérisé" }, { "lemma": "par", "text": "par" }, { "lemma": "le", "text": "le" }, { "lemma": "multipartisme", "text": "multipartisme" }, { "lemma": ".", "text": "." }, { "lemma": "le", "text": "Le" }, { "lemma": "labour", "text": "Labour" }, { "lemma": "être", "text": "est" }, { "lemma": "de", "text": "d'" }, { "lemma": "abord", "text": "abord" }, { "lemma": "et", "text": "et" }, { "lemma": "avant", "text": "avant" }, { "lemma": "tout", "text": "tout" }, { "lemma": "victime", "text": "victime" }, { "lemma": "de le", "text": "du" }, { "lemma": "tsunami", "text": "tsunami" }, { "lemma": "nationaliste", "text": "nationaliste" }, { "lemma": "qui", "text": "qui" }, { "lemma": "avoir", "text": "a" }, { "lemma": "déferler", "text": "déferlé" }, { "lemma": "sur", "text": "sur" }, { "lemma": "le", "text": "l'" }, { "lemma": "Écosse", "text": "Ecosse" }, { "lemma": ",", "text": "," }, { "lemma": "le", "text": "le" }, { "lemma": "SNP", "text": "SNP" }, { "lemma": "décupler", "text": "décuplant" }, { "lemma": "presque", "text": "presque" }, { "lemma": "son", "text": "sa" }, { "lemma": "représentation", "text": "représentation" }, { "lemma": "à", "text": "à" }, { "lemma": "le", "text": "la" }, { "lemma": "chambre", "text": "Chambre" }, { "lemma": "de le", "text": "des" }, { "lemma": "commune", "text": "Communes" }, { "lemma": ".", "text": "." }, { "lemma": "\"", "text": "\"" }, { "lemma": "le", "text": "Le" }, { "lemma": "lion", "text": "lion" }, { "lemma": "écossais", "text": "écossais" }, { "lemma": "avoir", "text": "a" }, { "lemma": "rugir", "text": "rugi" }, { "lemma": "ce", "text": "cette" }, { "lemma": "nuit", "text": "nuit" }, { "lemma": "\"", "text": "\"" }, { "lemma": ",", "text": "," }, { "lemma": "se", "text": "s'" }, { "lemma": "être", "text": "est" }, { "lemma": "féliciter", "text": "félicité" }, { "lemma": "son", "text": "son" }, { "lemma": "ancien", "text": "ancien" }, { "lemma": "leader", "text": "leader" }, { "lemma": ",", "text": "," }, { "lemma": "Alex", "text": "Alex" }, { "lemma": "Salmond", "text": "Salmond" }, { "lemma": ".", "text": "." }, { "lemma": "le", "text": "Le" }, { "lemma": "triomphe", "text": "triomphe" }, { "lemma": "de le", "text": "du" }, { "lemma": "SNP", "text": "SNP" }, { "lemma": "être", "text": "est" }, { "lemma": "symboliser", "text": "symbolisé" }, { "lemma": "par", "text": "par" }, { "lemma": "le", "text": "l'" }, { "lemma": "élection", "text": "élection" }, { "lemma": "de", "text": "de" }, { "lemma": "Mhairi", "text": "Mhairi" }, { "lemma": "black", "text": "Black" }, { "lemma": ",", "text": "," }, { "lemma": "un", "text": "une" }, { "lemma": "étudiant", "text": "étudiante" }, { "lemma": "de", "text": "de" }, { "lemma": "20", "text": "20" }, { "lemma": "an", "text": "ans" }, { "lemma": "qui", "text": "qui" }, { "lemma": "devenir", "text": "devient" }, { "lemma": "le", "text": "la" }, { "lemma": "plus", "text": "plus" }, { "lemma": "jeune", "text": "jeune" }, { "lemma": "députer", "text": "députée" }, { "lemma": "de", "text": "de" }, { "lemma": "Westminster", "text": "Westminster" }, { "lemma": "depuis", "text": "depuis" }, { "lemma": "1667", "text": "1667" }, { "lemma": ",", "text": "," }, { "lemma": "à le", "text": "aux" }, { "lemma": "dépens", "text": "dépens" }, { "lemma": "de le", "text": "du" }, { "lemma": "député", "text": "député" }, { "lemma": "sortant", "text": "sortant" }, { "lemma": "et", "text": "et" }, { "lemma": "cadre", "text": "cadre" }, { "lemma": "de le", "text": "du" }, { "lemma": "labour", "text": "Labour" }, { "lemma": "Douglas", "text": "Douglas" }, { "lemma": "Alexander", "text": "Alexander" }, { "lemma": ".", "text": "." }, { "lemma": "le", "text": "La" }, { "lemma": "tentation", "text": "tentation" }, { "lemma": "de le", "text": "du" }, { "lemma": "\"", "text": "\"" }, { "lemma": "Brexit", "text": "Brexit" }, { "lemma": "\"", "text": "\"" }, { "lemma": "Ed", "text": "Ed" }, { "lemma": "Balls", "text": "Balls" }, { "lemma": ",", "text": "," }, { "lemma": "le", "text": "le" }, { "lemma": "bras", "text": "bras" }, { "lemma": "droit", "text": "droit" }, { "lemma": "de", "text": "de" }, { "lemma": "Miliband", "text": "Miliband" }, { "lemma": ",", "text": "," }, { "lemma": "Jim", "text": "Jim" }, { "lemma": "Murphy", "text": "Murphy" }, { "lemma": ",", "text": "," }, { "lemma": "patron", "text": "patron" }, { "lemma": "de le", "text": "du" }, { "lemma": "labour", "text": "Labour" }, { "lemma": "en", "text": "en" }, { "lemma": "Écosse", "text": "Ecosse" }, { "lemma": ",", "text": "," }, { "lemma": "et", "text": "et" }, { "lemma": "Vince", "text": "Vince" }, { "lemma": "Câble", "text": "Cable" }, { "lemma": ",", "text": "," }, { "lemma": "ancien", "text": "ancien" }, { "lemma": "ministre", "text": "ministre" }, { "lemma": "lib", "text": "lib" }, { "lemma": "-", "text": "-" }, { "lemma": "dem", "text": "dem" }, { "lemma": "de le", "text": "du" }, { "lemma": "commerce", "text": "Commerce" }, { "lemma": ",", "text": "," }, { "lemma": "faire", "text": "font" }, { "lemma": "partie", "text": "partie" }, { "lemma": "de le", "text": "des" }, { "lemma": "autre", "text": "autres" }, { "lemma": "victime", "text": "victimes" }, { "lemma": "de", "text": "de" }, { "lemma": "marque", "text": "marque" }, { "lemma": "de", "text": "d'" }, { "lemma": "un", "text": "un" }, { "lemma": "scrutin", "text": "scrutin" }, { "lemma": "assassin", "text": "assassin" }, { "lemma": ".", "text": "." }, { "lemma": "David", "text": "David" }, { "lemma": "Cameron", "text": "Cameron" }, { "lemma": "avoir", "text": "avait" }, { "lemma": "être", "text": "été" }, { "lemma": "critiquer", "text": "critiqué" }, { "lemma": "pour", "text": "pour" }, { "lemma": "son", "text": "son" }, { "lemma": "manque", "text": "manque" }, { "lemma": "de", "text": "d'" }, { "lemma": "engagement", "text": "engagement" }, { "lemma": "en", "text": "en" }, { "lemma": "début", "text": "début" }, { "lemma": "de", "text": "de" }, { "lemma": "campagne", "text": "campagne" }, { "lemma": ".", "text": "." }, { "lemma": "à", "text": "A" }, { "lemma": "peine", "text": "peine" }, { "lemma": "réélire", "text": "réélu" }, { "lemma": ",", "text": "," }, { "lemma": "il", "text": "il" }, { "lemma": "avoir", "text": "a" }, { "lemma": "réitérer", "text": "réitéré" }, { "lemma": "son", "text": "sa" }, { "lemma": "principal", "text": "principale" }, { "lemma": "promesse", "text": "promesse" }, { "lemma": ":", "text": ":" }, { "lemma": "le", "text": "l'" }, { "lemma": "organisation", "text": "organisation" }, { "lemma": "de", "text": "d'" }, { "lemma": "ici", "text": "ici" }, { "lemma": "2017", "text": "2017" }, { "lemma": "de", "text": "d'" }, { "lemma": "un", "text": "un" }, { "lemma": "référendum", "text": "référendum" }, { "lemma": "sur", "text": "sur" }, { "lemma": "le", "text": "le" }, { "lemma": "maintien", "text": "maintien" }, { "lemma": "ou", "text": "ou" }, { "lemma": "pas", "text": "pas" }, { "lemma": "de le", "text": "du" }, { "lemma": "pays", "text": "pays" }, { "lemma": "dans", "text": "dans" }, { "lemma": "le", "text": "l'" }, { "lemma": "union", "text": "Union" }, { "lemma": "européen", "text": "européenne" }, { "lemma": ".", "text": "." }, { "lemma": "un", "text": "Une" }, { "lemma": "perspective", "text": "perspective" }, { "lemma": "qui", "text": "qui" }, { "lemma": "inquiéter", "text": "inquiète" }, { "lemma": "son", "text": "ses" }, { "lemma": "partenaire", "text": "partenaires" }, { "lemma": "européen", "text": "européens" }, { "lemma": "en", "text": "en" }, { "lemma": "raison", "text": "raison" }, { "lemma": "de", "text": "de" }, { "lemma": "le", "text": "la" }, { "lemma": "possibilité", "text": "possibilité" }, { "lemma": "de", "text": "d'" }, { "lemma": "un", "text": "un" }, { "lemma": "\"", "text": "\"" }, { "lemma": "Brexit", "text": "Brexit" }, { "lemma": "\"", "text": "\"" }, { "lemma": ",", "text": "," }, { "lemma": "un", "text": "un" }, { "lemma": "acronyme", "text": "acronyme" }, { "lemma": "désigner", "text": "désignant" }, { "lemma": "un", "text": "une" }, { "lemma": "sortie", "text": "sortie" }, { "lemma": "de le", "text": "du" }, { "lemma": "club", "text": "club" }, { "lemma": "de le", "text": "des" }, { "lemma": "28", "text": "28" }, { "lemma": ".", "text": "." }, { "lemma": "le", "text": "La" }, { "lemma": "nouvelle", "text": "nouvelle" }, { "lemma": "de", "text": "de" }, { "lemma": "le", "text": "la" }, { "lemma": "victoire", "text": "victoire" }, { "lemma": "de le", "text": "des" }, { "lemma": "conservateur", "text": "conservateurs" }, { "lemma": "se", "text": "s'" }, { "lemma": "être", "text": "est" }, { "lemma": "traduire", "text": "traduite" }, { "lemma": "par", "text": "par" }, { "lemma": "un", "text": "un" }, { "lemma": "bond", "text": "bond" }, { "lemma": "de", "text": "de" }, { "lemma": "le", "text": "la" }, { "lemma": "livre", "text": "livre" }, { "lemma": "britannique", "text": "britannique" }, { "lemma": "face", "text": "face" }, { "lemma": "à le", "text": "au" }, { "lemma": "dollar", "text": "dollar" }, { "lemma": "et", "text": "et" }, { "lemma": "à", "text": "à" }, { "lemma": "le", "text": "l'" }, { "lemma": "euro", "text": "euro" }, { "lemma": "vendredi", "text": "vendredi" }, { "lemma": "sur", "text": "sur" }, { "lemma": "le", "text": "les" }, { "lemma": "marché", "text": "marchés" }, { "lemma": "asiatique", "text": "asiatiques" }, { "lemma": ".", "text": "." }, { "lemma": "le", "text": "La" }, { "lemma": "bourse", "text": "Bourse" }, { "lemma": "de", "text": "de" }, { "lemma": "Londres", "text": "Londres" }, { "lemma": "évoluer", "text": "évoluait" }, { "lemma": "également", "text": "également" }, { "lemma": "en", "text": "en" }, { "lemma": "hausser", "text": "hausse" }, { "lemma": "vendredi", "text": "vendredi" }, { "lemma": ",", "text": "," }, { "lemma": "malgré", "text": "malgré" }, { "lemma": "un", "text": "des" }, { "lemma": "incertitude", "text": "incertitudes" }, { "lemma": "européen", "text": "européennes" }, { "lemma": "potentiellement", "text": "potentiellement" }, { "lemma": "préjudiciable", "text": "préjudiciables" }, { "lemma": "à le", "text": "aux" }, { "lemma": "affaire", "text": "affaires" }, { "lemma": ".", "text": "." }, { "lemma": "le", "text": "La" }, { "lemma": "bourse", "text": "Bourse" }, { "lemma": "de", "text": "de" }, { "lemma": "Londres", "text": "Londres" }, { "lemma": "à le", "text": "au" }, { "lemma": "diapason", "text": "diapason" }, { "lemma": "qui", "text": "Qui" }, { "lemma": "plus", "text": "plus" }, { "lemma": "être", "text": "est" }, { "lemma": ",", "text": "," }, { "lemma": "un", "text": "une" }, { "lemma": "éventuel", "text": "éventuelle" }, { "lemma": "sortie", "text": "sortie" }, { "lemma": "de", "text": "de" }, { "lemma": "le", "text": "l'" }, { "lemma": "UE", "text": "UE" }, { "lemma": "pouvoir", "text": "pourrait" }, { "lemma": "avoir", "text": "avoir" }, { "lemma": "par", "text": "par" }, { "lemma": "contrecoup", "text": "contrecoup" }, { "lemma": "de le", "text": "des" }, { "lemma": "répercussion", "text": "répercussions" }, { "lemma": "profond", "text": "profondes" }, { "lemma": "sur", "text": "sur" }, { "lemma": "le", "text": "le" }, { "lemma": "maintien", "text": "maintien" }, { "lemma": "de", "text": "de" }, { "lemma": "l", "text": "l" }, { "lemma": "'", "text": "'" }, { "lemma": "Écosse", "text": "Ecosse" }, { "lemma": ",", "text": "," }, { "lemma": "largement", "text": "largement" }, { "lemma": "pro", "text": "pro" }, { "lemma": "-", "text": "-" }, { "lemma": "européen", "text": "européenne" }, { "lemma": ",", "text": "," }, { "lemma": "à le", "text": "au" }, { "lemma": "sein", "text": "sein" }, { "lemma": "de le", "text": "du" }, { "lemma": "royaume", "text": "Royaume" }, { "lemma": "-", "text": "-" }, { "lemma": "uni", "text": "Uni" }, { "lemma": ".", "text": "." }, { "lemma": "tout", "text": "Toute" }, { "lemma": "le", "text": "la" }, { "lemma": "journée", "text": "journée" }, { "lemma": "de", "text": "de" }, { "lemma": "jeudi", "text": "jeudi" }, { "lemma": ",", "text": "," }, { "lemma": "le", "text": "les" }, { "lemma": "militant", "text": "militants" }, { "lemma": "SNP", "text": "SNP" }, { "lemma": "sortir", "text": "sortant" }, { "lemma": "de", "text": "de" }, { "lemma": "le", "text": "l'" }, { "lemma": "isoloir", "text": "isoloir" }, { "lemma": "à", "text": "à" }, { "lemma": "Glasgow", "text": "Glasgow" }, { "lemma": "ou", "text": "ou" }, { "lemma": "Édimbourg", "text": "Edimbourg" }, { "lemma": "ne", "text": "ne" }, { "lemma": "faire", "text": "faisaient" }, { "lemma": "pas", "text": "pas" }, { "lemma": "mystère", "text": "mystère" }, { "lemma": "de", "text": "de" }, { "lemma": "leur", "text": "leur" }, { "lemma": "volonté", "text": "volonté" }, { "lemma": "\"", "text": "\"" }, { "lemma": "de", "text": "de" }, { "lemma": "revanche", "text": "revanche" }, { "lemma": "\"", "text": "\"" }, { "lemma": ".", "text": "." }, { "lemma": "il", "text": "Ils" }, { "lemma": "aspirer", "text": "aspirent" }, { "lemma": "en", "text": "en" }, { "lemma": "effet", "text": "effet" }, { "lemma": "à", "text": "à" }, { "lemma": "le", "text": "la" }, { "lemma": "tenue", "text": "tenue" }, { "lemma": "de", "text": "d'" }, { "lemma": "un", "text": "un" }, { "lemma": "nouveau", "text": "nouveau" }, { "lemma": "référendum", "text": "référendum" }, { "lemma": "de", "text": "d'" }, { "lemma": "indépendance", "text": "indépendance" }, { "lemma": ",", "text": "," }, { "lemma": "après", "text": "après" }, { "lemma": "un", "text": "un" }, { "lemma": "premier", "text": "premier" }, { "lemma": "rendre", "text": "rendez" }, { "lemma": "-", "text": "-" }, { "lemma": "vous", "text": "vous" }, { "lemma": "manquer", "text": "manqué" }, { "lemma": "en", "text": "en" }, { "lemma": "septembre", "text": "septembre" }, { "lemma": ".", "text": "." }, { "lemma": "il", "text": "Il" }, { "lemma": "se", "text": "s'" }, { "lemma": "agir", "text": "agit" }, { "lemma": "là", "text": "là" }, { "lemma": "de", "text": "d'" }, { "lemma": "un", "text": "une" }, { "lemma": "menace", "text": "menace" }, { "lemma": "non", "text": "non" }, { "lemma": "négligeable", "text": "négligeable" }, { "lemma": ",", "text": "," }, { "lemma": "même", "text": "même" }, { "lemma": "si", "text": "si" }, { "lemma": "\"", "text": "\"" }, { "lemma": "David", "text": "David" }, { "lemma": "Cameron", "text": "Cameron" }, { "lemma": "avoir", "text": "a" }, { "lemma": "sensiblement", "text": "sensiblement" }, { "lemma": "accroire", "text": "accru" }, { "lemma": "son", "text": "sa" }, { "lemma": "stature", "text": "stature" }, { "lemma": "\"", "text": "\"" }, { "lemma": ",", "text": "," }, { "lemma": "selon", "text": "selon" }, { "lemma": "Patrick", "text": "Patrick" }, { "lemma": "Dunleavy", "text": "Dunleavy" }, { "lemma": ",", "text": "," }, { "lemma": "expert", "text": "expert" }, { "lemma": "à", "text": "à" }, { "lemma": "le", "text": "la" }, { "lemma": "London", "text": "London" }, { "lemma": "School", "text": "School" }, { "lemma": "of", "text": "of" }, { "lemma": "Economics", "text": "Economics" }, { "lemma": "(", "text": "(" }, { "lemma": "LSE", "text": "LSE" }, { "lemma": ")", "text": ")" }, { "lemma": ".", "text": "." }, { "lemma": "le", "text": "Le" }, { "lemma": "plus", "text": "plus" }, { "lemma": "jeune", "text": "jeune" }, { "lemma": "premier", "text": "Premier" }, { "lemma": "ministre", "text": "ministre" }, { "lemma": "britannique", "text": "britannique" }, { "lemma": "en", "text": "en" }, { "lemma": "deux", "text": "deux" }, { "lemma": "siècle", "text": "siècles" }, { "lemma": "se", "text": "s'" }, { "lemma": "être", "text": "est" }, { "lemma": "comporter", "text": "comporté" }, { "lemma": "bien", "text": "bien" }, { "lemma": "mieux", "text": "mieux" }, { "lemma": "que", "text": "que" }, { "lemma": "prévoir", "text": "prévu" }, { "lemma": "dans", "text": "dans" }, { "lemma": "le", "text": "les" }, { "lemma": "urne", "text": "urnes" }, { "lemma": ",", "text": "," }, { "lemma": "mais", "text": "mais" }, { "lemma": "pouvoir", "text": "pourrait" }, { "lemma": "avoir", "text": "avoir" }, { "lemma": "un", "text": "des" }, { "lemma": "difficulté", "text": "difficultés" }, { "lemma": "\"", "text": "\"" }, { "lemma": "à", "text": "à" }, { "lemma": "faire", "text": "faire" }, { "lemma": "quoi", "text": "quoi" }, { "lemma": "que", "text": "que" }, { "lemma": "ce", "text": "ce" }, { "lemma": "être", "text": "soit" }, { "lemma": "de", "text": "de" }, { "lemma": "radical", "text": "radical" }, { "lemma": "\"", "text": "\"" }, { "lemma": ",", "text": "," }, { "lemma": "avoir", "text": "a" }, { "lemma": "-", "text": "-" }, { "lemma": "t", "text": "t" }, { "lemma": "-", "text": "-" }, { "lemma": "il", "text": "il" }, { "lemma": "ajouter", "text": "ajouté" }, { "lemma": ".", "text": "." }, { "lemma": "de", "text": "De" }, { "lemma": "nouveau", "text": "nouveaux" }, { "lemma": "ambitieux", "text": "ambitieux" }, { "lemma": "Cameron", "text": "Cameron" }, { "lemma": "devoir", "text": "devra" }, { "lemma": "de", "text": "de" }, { "lemma": "faire", "text": "fait" }, { "lemma": "contenir", "text": "contenir" }, { "lemma": "le", "text": "la" }, { "lemma": "grogne", "text": "grogne" }, { "lemma": "de", "text": "de" }, { "lemma": "le", "text": "la" }, { "lemma": "frange", "text": "frange" }, { "lemma": "eurosceptique", "text": "eurosceptique" }, { "lemma": "de", "text": "de" }, { "lemma": "son", "text": "son" }, { "lemma": "parti", "text": "parti" }, { "lemma": "et", "text": "et" }, { "lemma": "tenir", "text": "tenir" }, { "lemma": "à", "text": "à" }, { "lemma": "distance", "text": "distance" }, { "lemma": "le", "text": "les" }, { "lemma": "prétendant", "text": "prétendants" }, { "lemma": "à", "text": "à" }, { "lemma": "son", "text": "sa" }, { "lemma": "succession", "text": "succession" }, { "lemma": ",", "text": "," }, { "lemma": "alors", "text": "alors" }, { "lemma": "que", "text": "qu'" }, { "lemma": "il", "text": "il" }, { "lemma": "avoir", "text": "a" }, { "lemma": "annoncer", "text": "annoncé" }, { "lemma": "pendant", "text": "pendant" }, { "lemma": "le", "text": "la" }, { "lemma": "campagne", "text": "campagne" }, { "lemma": "que", "text": "qu'" }, { "lemma": "il", "text": "il" }, { "lemma": "ne", "text": "ne" }, { "lemma": "briguer", "text": "briguerait" }, { "lemma": "pas", "text": "pas" }, { "lemma": "de", "text": "de" }, { "lemma": "troisième", "text": "troisième" }, { "lemma": "mandat", "text": "mandat" }, { "lemma": ".", "text": "." }, { "lemma": "le", "text": "L'" }, { "lemma": "un", "text": "un" }, { "lemma": "deux", "text": "deux" }, { "lemma": ",", "text": "," }, { "lemma": "le", "text": "le" }, { "lemma": "bouillir", "text": "bouillant" }, { "lemma": "maire", "text": "maire" }, { "lemma": "de", "text": "de" }, { "lemma": "Londres", "text": "Londres" }, { "lemma": "Boris", "text": "Boris" }, { "lemma": "Johnson", "text": "Johnson" }, { "lemma": ",", "text": "," }, { "lemma": "se", "text": "s'" }, { "lemma": "être", "text": "est" }, { "lemma": "faire", "text": "fait" }, { "lemma": "élire", "text": "élire" }, { "lemma": "député", "text": "député" }, { "lemma": "à", "text": "à" }, { "lemma": "Uxbridge", "text": "Uxbridge" }, { "lemma": ",", "text": "," }, { "lemma": "un", "text": "une" }, { "lemma": "étape", "text": "étape" }, { "lemma": "essentiel", "text": "essentielle" }, { "lemma": "pour", "text": "pour" }, { "lemma": "prétendre", "text": "prétendre" }, { "lemma": "à", "text": "à" }, { "lemma": "le", "text": "la" }, { "lemma": "direction", "text": "direction" }, { "lemma": "de le", "text": "du" }, { "lemma": "parti", "text": "parti" }, { "lemma": ".", "text": "." }, { "lemma": "dans", "text": "Dans" }, { "lemma": "le", "text": "l'" }, { "lemma": "immédiat", "text": "immédiat" }, { "lemma": ",", "text": "," }, { "lemma": "il", "text": "il" }, { "lemma": "appartenir", "text": "appartenait" }, { "lemma": "à le", "text": "aux" }, { "lemma": "travailliste", "text": "travaillistes" }, { "lemma": "et", "text": "et" }, { "lemma": "libéral", "text": "libéraux" }, { "lemma": "démocrate", "text": "démocrates" }, { "lemma": "de", "text": "de" }, { "lemma": "retrousser", "text": "retrousser" }, { "lemma": "le", "text": "les" }, { "lemma": "manche", "text": "manches" }, { "lemma": "pour", "text": "pour" }, { "lemma": "se", "text": "s'" }, { "lemma": "attaquer", "text": "attaquer" }, { "lemma": "à le", "text": "au" }, { "lemma": "pénible", "text": "pénible" }, { "lemma": "chantier", "text": "chantier" }, { "lemma": "de", "text": "de" }, { "lemma": "reconstruction", "text": "reconstruction" }, { "lemma": ".", "text": "." }, { "lemma": "(", "text": "(" }, { "lemma": "avec", "text": "Avec" }, { "lemma": "AFP", "text": "AFP" }, { "lemma": ")", "text": ")" } ], "posTags": [ { "pos": "NOUN_PL", "text": "Elections" }, { "pos": "ADJ_PL", "text": "britanniques" }, { "pos": "PUNCT", "text": ":" }, { "pos": "NOUN_SG", "text": "triomphe" }, { "pos": "ADJ_SG", "text": "éclatant" }, { "pos": "PREP", "text": "pour" }, { "pos": "NOUN_INV", "text": "David" }, { "pos": "NOUN_INV", "text": "Cameron" }, { "pos": "NOUN_PL", "text": "Challenges" }, { "pos": "SYM", "text": ">" }, { "pos": "NOUN_INV", "text": "Europe" }, { "pos": "SYM", "text": ">" }, { "pos": "NOUN_PL", "text": "Elections" }, { "pos": "ADJ_PL", "text": "britanniques" }, { "pos": "PUNCT", "text": ":" }, { "pos": "NOUN_SG", "text": "triomphe" }, { "pos": "ADJ_SG", "text": "éclatant" }, { "pos": "PREP", "text": "pour" }, { "pos": "NOUN_INV", "text": "David" }, { "pos": "NOUN_INV", "text": "Cameron" }, { "pos": "NOUN_PL", "text": "Elections" }, { "pos": "ADJ_PL", "text": "britanniques" }, { "pos": "PUNCT", "text": ":" }, { "pos": "NOUN_SG", "text": "triomphe" }, { "pos": "ADJ_SG", "text": "éclatant" }, { "pos": "PREP", "text": "pour" }, { "pos": "NOUN_INV", "text": "David" }, { "pos": "NOUN_INV", "text": "Cameron" }, { "pos": "VERB_INF", "text": "Voir" }, { "pos": "DET_PL", "text": "tous" }, { "pos": "DET_PL", "text": "ses" }, { "pos": "NOUN_PL", "text": "articles" }, { "pos": "ADJ_SG", "text": "Publié" }, { "pos": "DET_SG", "text": "le" }, { "pos": "NUM", "text": "08" }, { "pos": "PUNCT", "text": "-" }, { "pos": "NUM", "text": "05" }, { "pos": "PUNCT", "text": "-" }, { "pos": "NUM", "text": "2015" }, { "pos": "PREP_A", "text": "à" }, { "pos": "NOUN_INV", "text": "17h57" }, { "pos": "PAP_INV", "text": "Mis" }, { "pos": "PREP_A", "text": "à" }, { "pos": "NOUN_SG", "text": "jour" }, { "pos": "PREP_A", "text": "à" }, { "pos": "NOUN_INV", "text": "19h13" }, { "pos": "PREP_A", "text": "A" }, { "pos": "SYM", "text": "+" }, { "pos": "PREP_A", "text": "A" }, { "pos": "PUNCT", "text": "-" }, { "pos": "NOUN_INV", "text": "David" }, { "pos": "NOUN_INV", "text": "Cameron" }, { "pos": "VAUX_P3SG", "text": "a" }, { "pos": "ADV", "text": "brillamment" }, { "pos": "PAP_SG", "text": "remporté" }, { "pos": "PREP_DE", "text": "des" }, { "pos": "NOUN_PL", "text": "législatives" }, { "pos": "ADJ_PL", "text": "britanniques" }, { "pos": "RELPRO", "text": "qui" }, { "pos": "VERB_P3PL", "text": "font" }, { "pos": "VERB_INF", "text": "planer" }, { "pos": "DET_SG", "text": "la" }, { "pos": "NOUN_SG", "text": "menace" }, { "pos": "PREP_DE", "text": "d'" }, { "pos": "DET_SG", "text": "une" }, { "pos": "NOUN_SG", "text": "sortie" }, { "pos": "PREP_DE", "text": "du" }, { "pos": "NOUN_SG", "text": "Royaume" }, { "pos": "PUNCT", "text": "-" }, { "pos": "NOUN_SG", "text": "Uni" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "DET_SG", "text": "l'" }, { "pos": "NOUN_SG", "text": "Union" }, { "pos": "ADJ_SG", "text": "européenne" }, { "pos": "COORD", "text": "et" }, { "pos": "VERB_P3PL", "text": "consacrent" }, { "pos": "DET_SG", "text": "le" }, { "pos": "NOUN_INV", "text": "succès" }, { "pos": "PREP_DE", "text": "des" }, { "pos": "NOUN_PL", "text": "nationalistes" }, { "pos": "ADJ_INV", "text": "écossais" }, { "pos": "SENT", "text": "." }, { "pos": "NOUN_INV", "text": "David" }, { "pos": "NOUN_INV", "text": "Cameron" }, { "pos": "NOUN_SG", "text": "élection" }, { "pos": "NOUN_SG", "text": "mai" }, { "pos": "NUM", "text": "2015" }, { "pos": "PUNCT", "text": "(" }, { "pos": "NOUN_INV", "text": "Kirsty" }, { "pos": "NOUN_INV", "text": "Wigglesworth" }, { "pos": "PUNCT", "text": "/" }, { "pos": "NOUN_INV", "text": "AP" }, { "pos": "PUNCT", "text": "/" }, { "pos": "NOUN_INV", "text": "SIPA" }, { "pos": "PUNCT", "text": ")" }, { "pos": "ADJ_SG", "text": "Conforté" }, { "pos": "PREP", "text": "par" }, { "pos": "DET_SG", "text": "un" }, { "pos": "NOUN_SG", "text": "résultat" }, { "pos": "ADJ_SG", "text": "inespéré" }, { "pos": "CM", "text": "," }, { "pos": "DET_SG", "text": "le" }, { "pos": "NOUN_SG", "text": "leader" }, { "pos": "PREP_DE", "text": "des" }, { "pos": "NOUN_PL", "text": "Tories" }, { "pos": "VAUX_P3SG", "text": "a" }, { "pos": "PAP_SG", "text": "rendu" }, { "pos": "NOUN_SG", "text": "visite" }, { "pos": "PREP", "text": "en" }, { "pos": "DET_SG", "text": "tout" }, { "pos": "NOUN_SG", "text": "début" }, { "pos": "PREP_DE", "text": "d'" }, { "pos": "ADV", "text": "après" }, { "pos": "PUNCT", "text": "-" }, { "pos": "NOUN_SG", "text": "midi" }, { "pos": "PREP_A", "text": "à" }, { "pos": "DET_SG", "text": "la" }, { "pos": "NOUN_SG", "text": "reine" }, { "pos": "NOUN_INV", "text": "Elizabeth" }, { "pos": "NUM", "text": "II" }, { "pos": "CM", "text": "," }, { "pos": "PREP_A", "text": "au" }, { "pos": "NOUN_INV", "text": "palais" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NOUN_INV", "text": "Buckingham" }, { "pos": "CM", "text": "," }, { "pos": "MISC", "text": "afin" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "VERB_INF", "text": "recueillir" }, { "pos": "DET_SG", "text": "son" }, { "pos": "NOUN_SG", "text": "assentiment" }, { "pos": "ADJ_SG", "text": "formel" }, { "pos": "PREP", "text": "en" }, { "pos": "NOUN_SG", "text": "vue" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "VERB_INF", "text": "former" }, { "pos": "DET_SG", "text": "le" }, { "pos": "ADJ2_SG", "text": "prochain" }, { "pos": "NOUN_SG", "text": "gouvernement" }, { "pos": "SENT", "text": "." }, { "pos": "PUNCT", "text": "\"" }, { "pos": "PRON_P1P2", "text": "Je" }, { "pos": "VERB_P1P2", "text": "vais" }, { "pos": "ADV", "text": "maintenant" }, { "pos": "VERB_INF", "text": "former" }, { "pos": "DET_SG", "text": "un" }, { "pos": "NOUN_SG", "text": "gouvernement" }, { "pos": "ADJ_SG", "text": "conservateur" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NOUN_SG", "text": "majorité" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "CM", "text": "," }, { "pos": "VAUX_P3SG", "text": "a" }, { "pos": "PUNCT", "text": "-" }, { "pos": "NOUN_INV", "text": "t" }, { "pos": "PUNCT", "text": "-" }, { "pos": "PRON", "text": "il" }, { "pos": "PAP_SG", "text": "annoncé" }, { "pos": "PREP_A", "text": "au" }, { "pos": "ADJ2_SG", "text": "premier" }, { "pos": "NOUN_SG", "text": "jour" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "DET_SG", "text": "son" }, { "pos": "ADJ2_SG", "text": "second" }, { "pos": "NOUN_SG", "text": "mandat" }, { "pos": "SENT", "text": "." }, { "pos": "PREP", "text": "En" }, { "pos": "NUM", "text": "2010" }, { "pos": "CM", "text": "," }, { "pos": "DET_PL", "text": "les" }, { "pos": "NOUN_PL", "text": "Tories" }, { "pos": "VAUX_P3PL", "text": "avaient" }, { "pos": "VAUX_PAP", "text": "eu" }, { "pos": "NOUN_SG", "text": "besoin" }, { "pos": "PREP_DE", "text": "des" }, { "pos": "NOUN_PL", "text": "libéraux" }, { "pos": "PUNCT", "text": "-" }, { "pos": "NOUN_PL", "text": "démocrates" }, { "pos": "PREP", "text": "pour" }, { "pos": "VERB_INF", "text": "gouverner" }, { "pos": "SENT", "text": "." }, { "pos": "PUNCT", "text": "\"" }, { "pos": "DET_SG", "text": "Un" }, { "pos": "NOUN_SG", "text": "gouvernement" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NOUN_SG", "text": "majorité" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "DET_PL", "text": "Les" }, { "pos": "NOUN_PL", "text": "résultats" }, { "pos": "ADJ_PL", "text": "définitifs" }, { "pos": "PREP", "text": "après" }, { "pos": "NOUN_SG", "text": "dépouillement" }, { "pos": "PREP_DE", "text": "des" }, { "pos": "NUM", "text": "650" }, { "pos": "NOUN_PL", "text": "circonscriptions" }, { "pos": "VERB_P3PL", "text": "allouent" }, { "pos": "NUM", "text": "331" }, { "pos": "NOUN_PL", "text": "députés" }, { "pos": "PREP_A", "text": "aux" }, { "pos": "NOUN_PL", "text": "conservateurs" }, { "pos": "PUNCT", "text": "(" }, { "pos": "SYM", "text": "+" }, { "pos": "NUM", "text": "24" }, { "pos": "PUNCT", "text": ")" }, { "pos": "CM", "text": "," }, { "pos": "NUM", "text": "232" }, { "pos": "PREP_A", "text": "aux" }, { "pos": "NOUN_PL", "text": "travaillistes" }, { "pos": "PUNCT", "text": "(" }, { "pos": "PUNCT", "text": "-" }, { "pos": "NUM", "text": "26" }, { "pos": "PUNCT", "text": ")" }, { "pos": "CM", "text": "," }, { "pos": "NUM", "text": "56" }, { "pos": "PREP_A", "text": "au" }, { "pos": "NOUN_INV", "text": "SNP" }, { "pos": "PUNCT", "text": "(" }, { "pos": "SYM", "text": "+" }, { "pos": "NUM", "text": "50" }, { "pos": "PUNCT", "text": ")" }, { "pos": "CM", "text": "," }, { "pos": "NUM", "text": "8" }, { "pos": "PREP_A", "text": "aux" }, { "pos": "NOUN_PL", "text": "libéraux" }, { "pos": "ADJ_PL", "text": "démocrates" }, { "pos": "PUNCT", "text": "(" }, { "pos": "PUNCT", "text": "-" }, { "pos": "NUM", "text": "49" }, { "pos": "PUNCT", "text": ")" }, { "pos": "CM", "text": "," }, { "pos": "NUM", "text": "1" }, { "pos": "PREP_A", "text": "à" }, { "pos": "DET_SG", "text": "l'" }, { "pos": "NOUN_INV", "text": "Ukip" }, { "pos": "PUNCT", "text": "(" }, { "pos": "PUNCT", "text": "-" }, { "pos": "NUM", "text": "1" }, { "pos": "PUNCT", "text": ")" }, { "pos": "SENT", "text": "." }, { "pos": "DET_SG", "text": "Le" }, { "pos": "NOUN_SG", "text": "Labour" }, { "pos": "VAUX_P3SG", "text": "a" }, { "pos": "VAUX_PAP", "text": "été" }, { "pos": "PAP_SG", "text": "laminé" }, { "pos": "PREP", "text": "en" }, { "pos": "NOUN_INV", "text": "Ecosse" }, { "pos": "CM", "text": "," }, { "pos": "CONN", "text": "où" }, { "pos": "DET_PL", "text": "les" }, { "pos": "NOUN_PL", "text": "indépendantistes" }, { "pos": "PREP_DE", "text": "du" }, { "pos": "NOUN_INV", "text": "SNP" }, { "pos": "VAUX_P3PL", "text": "ont" }, { "pos": "PAP_SG", "text": "raflé" }, { "pos": "NUM", "text": "56" }, { "pos": "PREP_DE", "text": "des" }, { "pos": "NUM", "text": "59" }, { "pos": "NOUN_PL", "text": "sièges" }, { "pos": "PREP", "text": "en" }, { "pos": "NOUN_SG", "text": "jeu" }, { "pos": "PREP", "text": "dans" }, { "pos": "DET_SG", "text": "leur" }, { "pos": "NOUN_SG", "text": "région" }, { "pos": "ADJ_SG", "text": "autonome" }, { "pos": "CM", "text": "," }, { "pos": "PREP", "text": "jusqu'" }, { "pos": "ADV", "text": "ici" }, { "pos": "PAP_SG", "text": "considérée" }, { "pos": "COMME", "text": "comme" }, { "pos": "DET_SG", "text": "un" }, { "pos": "NOUN_SG", "text": "fief" }, { "pos": "ADJ_SG", "text": "travailliste" }, { "pos": "ADJ_SG", "text": "inexpugnable" }, { "pos": "SENT", "text": "." }, { "pos": "NOUN_SG", "text": "Nombre" }, { "pos": "PREP_DE", "text": "d'" }, { "pos": "NOUN_PL", "text": "analystes" }, { "pos": "VAUX_P3PL", "text": "avaient" }, { "pos": "PAP_SG", "text": "prédit" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "DET_SG", "text": "un" }, { "pos": "NOUN_SG", "text": "bain" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NOUN_SG", "text": "sang" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "ADJ_SG", "text": "politique" }, { "pos": "CM", "text": "," }, { "pos": "COORD", "text": "et" }, { "pos": "PRON", "text": "ils" }, { "pos": "VAUX_P3PL", "text": "avaient" }, { "pos": "NOUN_SG", "text": "raison" }, { "pos": "PREP", "text": "sur" }, { "pos": "DET_SG", "text": "ce" }, { "pos": "NOUN_SG", "text": "point" }, { "pos": "SENT", "text": "." }, { "pos": "PUNCT", "text": "\"" }, { "pos": "NOUN_SG", "text": "Bain" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NOUN_SG", "text": "sang" }, { "pos": "ADJ_SG", "text": "politique" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "NOUN_INV", "text": "Nigel" }, { "pos": "NOUN_INV", "text": "Farage" }, { "pos": "CM", "text": "," }, { "pos": "DET_SG", "text": "le" }, { "pos": "NOUN_SG", "text": "chef" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NOUN_SG", "text": "file" }, { "pos": "PREP_DE", "text": "du" }, { "pos": "NOUN_SG", "text": "parti" }, { "pos": "VERB_P3SG", "text": "europhobe" }, { "pos": "NOUN_INV", "text": "Ukip" }, { "pos": "CM", "text": "," }, { "pos": "PAP_SG", "text": "battu" }, { "pos": "PREP_A", "text": "à" }, { "pos": "NOUN_INV", "text": "South" }, { "pos": "NOUN_INV", "text": "Thanet" }, { "pos": "CM", "text": "," }, { "pos": "VAUX_P3SG", "text": "a" }, { "pos": "VAUX_PAP", "text": "été" }, { "pos": "DET_SG", "text": "le" }, { "pos": "ADJ2_SG", "text": "premier" }, { "pos": "PREP_A", "text": "à" }, { "pos": "VERB_INF", "text": "démissionner" }, { "pos": "CM", "text": "," }, { "pos": "VERB_PRP", "text": "mettant" }, { "pos": "PREP_A", "text": "à" }, { "pos": "NOUN_SG", "text": "exécution" }, { "pos": "DET_SG", "text": "sa" }, { "pos": "NOUN_SG", "text": "promesse" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "VERB_INF", "text": "tirer" }, { "pos": "DET_SG", "text": "le" }, { "pos": "NOUN_SG", "text": "rideau" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "PREP", "text": "en" }, { "pos": "NOUN_INV", "text": "cas" }, { "pos": "PREP_DE", "text": "d'" }, { "pos": "NOUN_SG", "text": "échec" }, { "pos": "SENT", "text": "." }, { "pos": "DET_SG", "text": "Son" }, { "pos": "NOUN_SG", "text": "départ" }, { "pos": "VERB_P3SG", "text": "porte" }, { "pos": "DET_SG", "text": "un" }, { "pos": "NOUN_SG", "text": "coup" }, { "pos": "ADV", "text": "extrêmement" }, { "pos": "ADJ_SG", "text": "sévère" }, { "pos": "PREP_A", "text": "à" }, { "pos": "DET_SG", "text": "son" }, { "pos": "NOUN_SG", "text": "parti" }, { "pos": "CM", "text": "," }, { "pos": "ADV", "text": "pourtant" }, { "pos": "PAP_SG", "text": "crédité" }, { "pos": "PREP_DE", "text": "d'" }, { "pos": "DET_SG", "text": "un" }, { "pos": "NOUN_SG", "text": "score" }, { "pos": "ADJ_SG", "text": "flatteur" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "ADV", "text": "près" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NUM", "text": "13" }, { "pos": "SYM", "text": "%" }, { "pos": "PREP", "text": "en" }, { "pos": "NOUN_INV", "text": "voix" }, { "pos": "SENT", "text": "." }, { "pos": "DET_SG", "text": "L'" }, { "pos": "NOUN_SG", "text": "homme" }, { "pos": "PUNCT", "text": "-" }, { "pos": "NOUN_SG", "text": "orchestre" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "DET_SG", "text": "l'" }, { "pos": "NOUN_INV", "text": "Ukip" }, { "pos": "NEG", "text": "n'" }, { "pos": "VAUX_P3SG", "text": "a" }, { "pos": "ADV", "text": "toutefois" }, { "pos": "ADV", "text": "pas" }, { "pos": "PAP_SG", "text": "exclu" }, { "pos": "DET_SG", "text": "un" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "VERB_P3SG", "text": "come" }, { "pos": "NOUN_SG", "text": "back" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "SENT", "text": "." }, { "pos": "ADV", "text": "Peu" }, { "pos": "ADV", "text": "après" }, { "pos": "CM", "text": "," }, { "pos": "DET_SG", "text": "le" }, { "pos": "NOUN_SG", "text": "leader" }, { "pos": "ADJ_SG", "text": "libéral" }, { "pos": "PUNCT", "text": "-" }, { "pos": "NOUN_SG", "text": "démocrate" }, { "pos": "NOUN_INV", "text": "Nick" }, { "pos": "NOUN_INV", "text": "Clegg" }, { "pos": "CM", "text": "," }, { "pos": "NUM", "text": "48" }, { "pos": "NOUN_PL", "text": "ans" }, { "pos": "CM", "text": "," }, { "pos": "VAUX_P3SG", "text": "a" }, { "pos": "PAP_SG", "text": "jeté" }, { "pos": "DET_SG", "text": "l'" }, { "pos": "NOUN_SG", "text": "éponge" }, { "pos": "PREP_A", "text": "au" }, { "pos": "VERB_INF", "text": "sortir" }, { "pos": "PREP_DE", "text": "d'" }, { "pos": "DET_SG", "text": "une" }, { "pos": "NOUN_SG", "text": "nuit" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "ADJ_SG", "text": "dévastatrice" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "CM", "text": "," }, { "pos": "PREP", "text": "selon" }, { "pos": "DET_SG", "text": "sa" }, { "pos": "ADJ2_SG", "text": "propre" }, { "pos": "NOUN_SG", "text": "expression" }, { "pos": "SENT", "text": "." }, { "pos": "NOUN_INV", "text": "Ed" }, { "pos": "NOUN_INV", "text": "Miliband" }, { "pos": "CM", "text": "," }, { "pos": "NUM", "text": "45" }, { "pos": "NOUN_PL", "text": "ans" }, { "pos": "CM", "text": "," }, { "pos": "DET_SG", "text": "le" }, { "pos": "NOUN_SG", "text": "patron" }, { "pos": "PREP_DE", "text": "des" }, { "pos": "NOUN_PL", "text": "travaillistes" }, { "pos": "CM", "text": "," }, { "pos": "VAUX_P3SG", "text": "a" }, { "pos": "PAP_SG", "text": "suivi" }, { "pos": "DET_SG", "text": "le" }, { "pos": "ADJ_SG", "text": "même" }, { "pos": "NOUN_SG", "text": "chemin" }, { "pos": "CM", "text": "," }, { "pos": "PREP", "text": "en" }, { "pos": "VERB_PRP", "text": "endossant" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "DET_SG", "text": "l'" }, { "pos": "ADJ_SG", "text": "entière" }, { "pos": "NOUN_SG", "text": "responsabilité" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "DET_SG", "text": "la" }, { "pos": "NOUN_SG", "text": "défaite" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "SENT", "text": "." }, { "pos": "PUNCT", "text": "\"" }, { "pos": "NOUN_SG", "text": "Tsunami" }, { "pos": "ADJ_SG", "text": "nationaliste" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "PREP", "text": "sur" }, { "pos": "DET_SG", "text": "l'" }, { "pos": "NOUN_INV", "text": "Ecosse" }, { "pos": "DET_PL", "text": "Les" }, { "pos": "NOUN_PL", "text": "autres" }, { "pos": "ADJ2_PL", "text": "grands" }, { "pos": "NOUN_PL", "text": "perdants" }, { "pos": "PREP_DE", "text": "du" }, { "pos": "NOUN_SG", "text": "scrutin" }, { "pos": "VAUX_P3PL", "text": "sont" }, { "pos": "DET_PL", "text": "les" }, { "pos": "NOUN_PL", "text": "instituts" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NOUN_PL", "text": "sondages" }, { "pos": "RELPRO", "text": "qui" }, { "pos": "NEG", "text": "n'" }, { "pos": "VAUX_P3PL", "text": "ont" }, { "pos": "PAP_SG", "text": "cessé" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "VERB_INF", "text": "prédire" }, { "pos": "DET_SG", "text": "un" }, { "pos": "NOUN_SG", "text": "résultat" }, { "pos": "ADJ_SG", "text": "ultra" }, { "pos": "ADJ_SG", "text": "serré" }, { "pos": "CM", "text": "," }, { "pos": "VERB_PRP", "text": "renvoyant" }, { "pos": "NOUN_INV", "text": "dos" }, { "pos": "PREP_A", "text": "à" }, { "pos": "NOUN_INV", "text": "dos" }, { "pos": "DET_PL", "text": "les" }, { "pos": "NUM", "text": "deux" }, { "pos": "NOUN_PL", "text": "partis" }, { "pos": "ADJ_PL", "text": "traditionnels" }, { "pos": "ADJ_PL", "text": "frappés" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NOUN_SG", "text": "déclin" }, { "pos": "PREP", "text": "dans" }, { "pos": "DET_SG", "text": "un" }, { "pos": "NOUN_SG", "text": "paysage" }, { "pos": "ADJ_SG", "text": "caractérisé" }, { "pos": "PREP", "text": "par" }, { "pos": "DET_SG", "text": "le" }, { "pos": "NOUN_SG", "text": "multipartisme" }, { "pos": "SENT", "text": "." }, { "pos": "DET_SG", "text": "Le" }, { "pos": "NOUN_SG", "text": "Labour" }, { "pos": "VAUX_P3SG", "text": "est" }, { "pos": "PREP_DE", "text": "d'" }, { "pos": "NOUN_SG", "text": "abord" }, { "pos": "COORD", "text": "et" }, { "pos": "PREP", "text": "avant" }, { "pos": "DET_SG", "text": "tout" }, { "pos": "NOUN_SG", "text": "victime" }, { "pos": "PREP_DE", "text": "du" }, { "pos": "NOUN_SG", "text": "tsunami" }, { "pos": "ADJ_SG", "text": "nationaliste" }, { "pos": "RELPRO", "text": "qui" }, { "pos": "VAUX_P3SG", "text": "a" }, { "pos": "PAP_SG", "text": "déferlé" }, { "pos": "PREP", "text": "sur" }, { "pos": "DET_SG", "text": "l'" }, { "pos": "NOUN_INV", "text": "Ecosse" }, { "pos": "CM", "text": "," }, { "pos": "DET_SG", "text": "le" }, { "pos": "NOUN_INV", "text": "SNP" }, { "pos": "VERB_PRP", "text": "décuplant" }, { "pos": "ADV", "text": "presque" }, { "pos": "DET_SG", "text": "sa" }, { "pos": "NOUN_SG", "text": "représentation" }, { "pos": "PREP_A", "text": "à" }, { "pos": "DET_SG", "text": "la" }, { "pos": "NOUN_SG", "text": "Chambre" }, { "pos": "PREP_DE", "text": "des" }, { "pos": "NOUN_PL", "text": "Communes" }, { "pos": "SENT", "text": "." }, { "pos": "PUNCT", "text": "\"" }, { "pos": "DET_SG", "text": "Le" }, { "pos": "NOUN_SG", "text": "lion" }, { "pos": "NOUN_INV", "text": "écossais" }, { "pos": "VAUX_P3SG", "text": "a" }, { "pos": "PAP_SG", "text": "rugi" }, { "pos": "DET_SG", "text": "cette" }, { "pos": "NOUN_SG", "text": "nuit" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "CM", "text": "," }, { "pos": "PC", "text": "s'" }, { "pos": "VAUX_P3SG", "text": "est" }, { "pos": "PAP_SG", "text": "félicité" }, { "pos": "DET_SG", "text": "son" }, { "pos": "ADJ2_SG", "text": "ancien" }, { "pos": "NOUN_SG", "text": "leader" }, { "pos": "CM", "text": "," }, { "pos": "NOUN_INV", "text": "Alex" }, { "pos": "NOUN_INV", "text": "Salmond" }, { "pos": "SENT", "text": "." }, { "pos": "DET_SG", "text": "Le" }, { "pos": "NOUN_SG", "text": "triomphe" }, { "pos": "PREP_DE", "text": "du" }, { "pos": "NOUN_INV", "text": "SNP" }, { "pos": "VAUX_P3SG", "text": "est" }, { "pos": "PAP_SG", "text": "symbolisé" }, { "pos": "PREP", "text": "par" }, { "pos": "DET_SG", "text": "l'" }, { "pos": "NOUN_SG", "text": "élection" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NOUN_INV", "text": "Mhairi" }, { "pos": "NOUN_SG", "text": "Black" }, { "pos": "CM", "text": "," }, { "pos": "DET_SG", "text": "une" }, { "pos": "NOUN_SG", "text": "étudiante" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NUM", "text": "20" }, { "pos": "NOUN_PL", "text": "ans" }, { "pos": "RELPRO", "text": "qui" }, { "pos": "VERB_P3SG", "text": "devient" }, { "pos": "DET_SG", "text": "la" }, { "pos": "ADV", "text": "plus" }, { "pos": "ADJ2_SG", "text": "jeune" }, { "pos": "PAP_SG", "text": "députée" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NOUN_INV", "text": "Westminster" }, { "pos": "PREP", "text": "depuis" }, { "pos": "NUM", "text": "1667" }, { "pos": "CM", "text": "," }, { "pos": "PREP_A", "text": "aux" }, { "pos": "NOUN_PL", "text": "dépens" }, { "pos": "PREP_DE", "text": "du" }, { "pos": "NOUN_SG", "text": "député" }, { "pos": "NOUN_SG", "text": "sortant" }, { "pos": "COORD", "text": "et" }, { "pos": "NOUN_SG", "text": "cadre" }, { "pos": "PREP_DE", "text": "du" }, { "pos": "NOUN_SG", "text": "Labour" }, { "pos": "NOUN_INV", "text": "Douglas" }, { "pos": "NOUN_INV", "text": "Alexander" }, { "pos": "SENT", "text": "." }, { "pos": "DET_SG", "text": "La" }, { "pos": "NOUN_SG", "text": "tentation" }, { "pos": "PREP_DE", "text": "du" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "NOUN_INV", "text": "Brexit" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "NOUN_INV", "text": "Ed" }, { "pos": "NOUN_INV", "text": "Balls" }, { "pos": "CM", "text": "," }, { "pos": "DET_SG", "text": "le" }, { "pos": "NOUN_INV", "text": "bras" }, { "pos": "ADJ_SG", "text": "droit" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NOUN_INV", "text": "Miliband" }, { "pos": "CM", "text": "," }, { "pos": "NOUN_INV", "text": "Jim" }, { "pos": "NOUN_INV", "text": "Murphy" }, { "pos": "CM", "text": "," }, { "pos": "NOUN_SG", "text": "patron" }, { "pos": "PREP_DE", "text": "du" }, { "pos": "NOUN_SG", "text": "Labour" }, { "pos": "PREP", "text": "en" }, { "pos": "NOUN_INV", "text": "Ecosse" }, { "pos": "CM", "text": "," }, { "pos": "COORD", "text": "et" }, { "pos": "NOUN_INV", "text": "Vince" }, { "pos": "NOUN_INV", "text": "Cable" }, { "pos": "CM", "text": "," }, { "pos": "ADJ2_SG", "text": "ancien" }, { "pos": "NOUN_SG", "text": "ministre" }, { "pos": "NOUN_SG", "text": "lib" }, { "pos": "PUNCT", "text": "-" }, { "pos": "NOUN_SG", "text": "dem" }, { "pos": "PREP_DE", "text": "du" }, { "pos": "NOUN_SG", "text": "Commerce" }, { "pos": "CM", "text": "," }, { "pos": "VERB_P3PL", "text": "font" }, { "pos": "NOUN_SG", "text": "partie" }, { "pos": "PREP_DE", "text": "des" }, { "pos": "ADJ_PL", "text": "autres" }, { "pos": "NOUN_PL", "text": "victimes" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NOUN_SG", "text": "marque" }, { "pos": "PREP_DE", "text": "d'" }, { "pos": "DET_SG", "text": "un" }, { "pos": "NOUN_SG", "text": "scrutin" }, { "pos": "ADJ_SG", "text": "assassin" }, { "pos": "SENT", "text": "." }, { "pos": "NOUN_INV", "text": "David" }, { "pos": "NOUN_INV", "text": "Cameron" }, { "pos": "VAUX_P3SG", "text": "avait" }, { "pos": "VAUX_PAP", "text": "été" }, { "pos": "PAP_SG", "text": "critiqué" }, { "pos": "PREP", "text": "pour" }, { "pos": "DET_SG", "text": "son" }, { "pos": "NOUN_SG", "text": "manque" }, { "pos": "PREP_DE", "text": "d'" }, { "pos": "NOUN_SG", "text": "engagement" }, { "pos": "PREP", "text": "en" }, { "pos": "NOUN_SG", "text": "début" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NOUN_SG", "text": "campagne" }, { "pos": "SENT", "text": "." }, { "pos": "PREP_A", "text": "A" }, { "pos": "NOUN_SG", "text": "peine" }, { "pos": "ADJ_SG", "text": "réélu" }, { "pos": "CM", "text": "," }, { "pos": "PRON", "text": "il" }, { "pos": "VAUX_P3SG", "text": "a" }, { "pos": "PAP_SG", "text": "réitéré" }, { "pos": "DET_SG", "text": "sa" }, { "pos": "ADJ2_SG", "text": "principale" }, { "pos": "NOUN_SG", "text": "promesse" }, { "pos": "PUNCT", "text": ":" }, { "pos": "DET_SG", "text": "l'" }, { "pos": "NOUN_SG", "text": "organisation" }, { "pos": "PREP_DE", "text": "d'" }, { "pos": "ADV", "text": "ici" }, { "pos": "NUM", "text": "2017" }, { "pos": "PREP_DE", "text": "d'" }, { "pos": "DET_SG", "text": "un" }, { "pos": "NOUN_SG", "text": "référendum" }, { "pos": "PREP", "text": "sur" }, { "pos": "DET_SG", "text": "le" }, { "pos": "NOUN_SG", "text": "maintien" }, { "pos": "COORD", "text": "ou" }, { "pos": "ADV", "text": "pas" }, { "pos": "PREP_DE", "text": "du" }, { "pos": "NOUN_INV", "text": "pays" }, { "pos": "PREP", "text": "dans" }, { "pos": "DET_SG", "text": "l'" }, { "pos": "NOUN_SG", "text": "Union" }, { "pos": "ADJ_SG", "text": "européenne" }, { "pos": "SENT", "text": "." }, { "pos": "DET_SG", "text": "Une" }, { "pos": "NOUN_SG", "text": "perspective" }, { "pos": "RELPRO", "text": "qui" }, { "pos": "VERB_P3SG", "text": "inquiète" }, { "pos": "DET_PL", "text": "ses" }, { "pos": "NOUN_PL", "text": "partenaires" }, { "pos": "ADJ_PL", "text": "européens" }, { "pos": "PREP", "text": "en" }, { "pos": "NOUN_SG", "text": "raison" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "DET_SG", "text": "la" }, { "pos": "NOUN_SG", "text": "possibilité" }, { "pos": "PREP_DE", "text": "d'" }, { "pos": "DET_SG", "text": "un" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "NOUN_INV", "text": "Brexit" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "CM", "text": "," }, { "pos": "DET_SG", "text": "un" }, { "pos": "NOUN_SG", "text": "acronyme" }, { "pos": "VERB_PRP", "text": "désignant" }, { "pos": "DET_SG", "text": "une" }, { "pos": "NOUN_SG", "text": "sortie" }, { "pos": "PREP_DE", "text": "du" }, { "pos": "NOUN_SG", "text": "club" }, { "pos": "PREP_DE", "text": "des" }, { "pos": "NUM", "text": "28" }, { "pos": "SENT", "text": "." }, { "pos": "DET_SG", "text": "La" }, { "pos": "NOUN_SG", "text": "nouvelle" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "DET_SG", "text": "la" }, { "pos": "NOUN_SG", "text": "victoire" }, { "pos": "PREP_DE", "text": "des" }, { "pos": "NOUN_PL", "text": "conservateurs" }, { "pos": "PC", "text": "s'" }, { "pos": "VAUX_P3SG", "text": "est" }, { "pos": "PAP_SG", "text": "traduite" }, { "pos": "PREP", "text": "par" }, { "pos": "DET_SG", "text": "un" }, { "pos": "NOUN_SG", "text": "bond" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "DET_SG", "text": "la" }, { "pos": "NOUN_SG", "text": "livre" }, { "pos": "ADJ_SG", "text": "britannique" }, { "pos": "NOUN_SG", "text": "face" }, { "pos": "PREP_A", "text": "au" }, { "pos": "NOUN_SG", "text": "dollar" }, { "pos": "COORD", "text": "et" }, { "pos": "PREP_A", "text": "à" }, { "pos": "DET_SG", "text": "l'" }, { "pos": "NOUN_SG", "text": "euro" }, { "pos": "NOUN_SG", "text": "vendredi" }, { "pos": "PREP", "text": "sur" }, { "pos": "DET_PL", "text": "les" }, { "pos": "NOUN_PL", "text": "marchés" }, { "pos": "ADJ_PL", "text": "asiatiques" }, { "pos": "SENT", "text": "." }, { "pos": "DET_SG", "text": "La" }, { "pos": "NOUN_SG", "text": "Bourse" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NOUN_INV", "text": "Londres" }, { "pos": "VERB_P3SG", "text": "évoluait" }, { "pos": "ADV", "text": "également" }, { "pos": "PC", "text": "en" }, { "pos": "VERB_P3SG", "text": "hausse" }, { "pos": "NOUN_SG", "text": "vendredi" }, { "pos": "CM", "text": "," }, { "pos": "PREP", "text": "malgré" }, { "pos": "DET_PL", "text": "des" }, { "pos": "NOUN_PL", "text": "incertitudes" }, { "pos": "ADJ_PL", "text": "européennes" }, { "pos": "ADV", "text": "potentiellement" }, { "pos": "ADJ_PL", "text": "préjudiciables" }, { "pos": "PREP_A", "text": "aux" }, { "pos": "NOUN_PL", "text": "affaires" }, { "pos": "SENT", "text": "." }, { "pos": "DET_SG", "text": "La" }, { "pos": "NOUN_SG", "text": "Bourse" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NOUN_INV", "text": "Londres" }, { "pos": "PREP_A", "text": "au" }, { "pos": "NOUN_SG", "text": "diapason" }, { "pos": "RELPRO", "text": "Qui" }, { "pos": "NOUN_INV", "text": "plus" }, { "pos": "VAUX_P3SG", "text": "est" }, { "pos": "CM", "text": "," }, { "pos": "DET_SG", "text": "une" }, { "pos": "ADJ_SG", "text": "éventuelle" }, { "pos": "NOUN_SG", "text": "sortie" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "DET_SG", "text": "l'" }, { "pos": "NOUN_INV", "text": "UE" }, { "pos": "VERB_P3SG", "text": "pourrait" }, { "pos": "VAUX_INF", "text": "avoir" }, { "pos": "PREP", "text": "par" }, { "pos": "NOUN_SG", "text": "contrecoup" }, { "pos": "PREP_DE", "text": "des" }, { "pos": "NOUN_PL", "text": "répercussions" }, { "pos": "ADJ_PL", "text": "profondes" }, { "pos": "PREP", "text": "sur" }, { "pos": "DET_SG", "text": "le" }, { "pos": "NOUN_SG", "text": "maintien" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NOUN_INV", "text": "l" }, { "pos": "PUNCT", "text": "'" }, { "pos": "NOUN_INV", "text": "Ecosse" }, { "pos": "CM", "text": "," }, { "pos": "ADV", "text": "largement" }, { "pos": "ADJ_INV", "text": "pro" }, { "pos": "PUNCT", "text": "-" }, { "pos": "ADJ_SG", "text": "européenne" }, { "pos": "CM", "text": "," }, { "pos": "PREP_A", "text": "au" }, { "pos": "NOUN_SG", "text": "sein" }, { "pos": "PREP_DE", "text": "du" }, { "pos": "NOUN_SG", "text": "Royaume" }, { "pos": "PUNCT", "text": "-" }, { "pos": "NOUN_SG", "text": "Uni" }, { "pos": "SENT", "text": "." }, { "pos": "PRON", "text": "Toute" }, { "pos": "DET_SG", "text": "la" }, { "pos": "NOUN_SG", "text": "journée" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NOUN_SG", "text": "jeudi" }, { "pos": "CM", "text": "," }, { "pos": "DET_PL", "text": "les" }, { "pos": "NOUN_PL", "text": "militants" }, { "pos": "NOUN_INV", "text": "SNP" }, { "pos": "VERB_PRP", "text": "sortant" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "DET_SG", "text": "l'" }, { "pos": "NOUN_SG", "text": "isoloir" }, { "pos": "PREP_A", "text": "à" }, { "pos": "NOUN_INV", "text": "Glasgow" }, { "pos": "COORD", "text": "ou" }, { "pos": "NOUN_INV", "text": "Edimbourg" }, { "pos": "NEG", "text": "ne" }, { "pos": "VERB_P3PL", "text": "faisaient" }, { "pos": "ADV", "text": "pas" }, { "pos": "NOUN_SG", "text": "mystère" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "DET_SG", "text": "leur" }, { "pos": "NOUN_SG", "text": "volonté" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NOUN_SG", "text": "revanche" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "SENT", "text": "." }, { "pos": "PRON", "text": "Ils" }, { "pos": "VERB_P3PL", "text": "aspirent" }, { "pos": "PREP", "text": "en" }, { "pos": "NOUN_SG", "text": "effet" }, { "pos": "PREP_A", "text": "à" }, { "pos": "DET_SG", "text": "la" }, { "pos": "NOUN_SG", "text": "tenue" }, { "pos": "PREP_DE", "text": "d'" }, { "pos": "DET_SG", "text": "un" }, { "pos": "ADJ2_SG", "text": "nouveau" }, { "pos": "NOUN_SG", "text": "référendum" }, { "pos": "PREP_DE", "text": "d'" }, { "pos": "NOUN_SG", "text": "indépendance" }, { "pos": "CM", "text": "," }, { "pos": "PREP", "text": "après" }, { "pos": "DET_SG", "text": "un" }, { "pos": "ADJ2_SG", "text": "premier" }, { "pos": "VERB_P1P2", "text": "rendez" }, { "pos": "PUNCT", "text": "-" }, { "pos": "PRON_P1P2", "text": "vous" }, { "pos": "PAP_SG", "text": "manqué" }, { "pos": "PREP", "text": "en" }, { "pos": "NOUN_SG", "text": "septembre" }, { "pos": "SENT", "text": "." }, { "pos": "PRON", "text": "Il" }, { "pos": "PC", "text": "s'" }, { "pos": "VERB_P3SG", "text": "agit" }, { "pos": "ADV", "text": "là" }, { "pos": "PREP_DE", "text": "d'" }, { "pos": "DET_SG", "text": "une" }, { "pos": "NOUN_SG", "text": "menace" }, { "pos": "ADV", "text": "non" }, { "pos": "ADJ_SG", "text": "négligeable" }, { "pos": "CM", "text": "," }, { "pos": "ADV", "text": "même" }, { "pos": "CONN", "text": "si" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "NOUN_INV", "text": "David" }, { "pos": "NOUN_INV", "text": "Cameron" }, { "pos": "VAUX_P3SG", "text": "a" }, { "pos": "ADV", "text": "sensiblement" }, { "pos": "PAP_SG", "text": "accru" }, { "pos": "DET_SG", "text": "sa" }, { "pos": "NOUN_SG", "text": "stature" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "CM", "text": "," }, { "pos": "PREP", "text": "selon" }, { "pos": "NOUN_INV", "text": "Patrick" }, { "pos": "NOUN_INV", "text": "Dunleavy" }, { "pos": "CM", "text": "," }, { "pos": "ADJ_SG", "text": "expert" }, { "pos": "PREP_A", "text": "à" }, { "pos": "DET_SG", "text": "la" }, { "pos": "NOUN_INV", "text": "London" }, { "pos": "NOUN_INV", "text": "School" }, { "pos": "NOUN_SG", "text": "of" }, { "pos": "NOUN_INV", "text": "Economics" }, { "pos": "PUNCT", "text": "(" }, { "pos": "NOUN_INV", "text": "LSE" }, { "pos": "PUNCT", "text": ")" }, { "pos": "SENT", "text": "." }, { "pos": "DET_SG", "text": "Le" }, { "pos": "ADV", "text": "plus" }, { "pos": "ADJ2_SG", "text": "jeune" }, { "pos": "ADJ2_SG", "text": "Premier" }, { "pos": "NOUN_SG", "text": "ministre" }, { "pos": "ADJ_SG", "text": "britannique" }, { "pos": "PREP", "text": "en" }, { "pos": "NUM", "text": "deux" }, { "pos": "NOUN_PL", "text": "siècles" }, { "pos": "PC", "text": "s'" }, { "pos": "VAUX_P3SG", "text": "est" }, { "pos": "PAP_SG", "text": "comporté" }, { "pos": "ADV", "text": "bien" }, { "pos": "ADV", "text": "mieux" }, { "pos": "CONJQUE", "text": "que" }, { "pos": "ADJ_SG", "text": "prévu" }, { "pos": "PREP", "text": "dans" }, { "pos": "DET_PL", "text": "les" }, { "pos": "NOUN_PL", "text": "urnes" }, { "pos": "CM", "text": "," }, { "pos": "COORD", "text": "mais" }, { "pos": "VERB_P3SG", "text": "pourrait" }, { "pos": "VAUX_INF", "text": "avoir" }, { "pos": "DET_PL", "text": "des" }, { "pos": "NOUN_PL", "text": "difficultés" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "PREP_A", "text": "à" }, { "pos": "VERB_INF", "text": "faire" }, { "pos": "RELPRO", "text": "quoi" }, { "pos": "CONJQUE", "text": "que" }, { "pos": "PRON", "text": "ce" }, { "pos": "VAUX_P3SG", "text": "soit" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NOUN_SG", "text": "radical" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "CM", "text": "," }, { "pos": "VAUX_P3SG", "text": "a" }, { "pos": "PUNCT", "text": "-" }, { "pos": "NOUN_INV", "text": "t" }, { "pos": "PUNCT", "text": "-" }, { "pos": "PRON", "text": "il" }, { "pos": "PAP_SG", "text": "ajouté" }, { "pos": "SENT", "text": "." }, { "pos": "DET_PL", "text": "De" }, { "pos": "ADJ2_PL", "text": "nouveaux" }, { "pos": "NOUN_INV", "text": "ambitieux" }, { "pos": "NOUN_INV", "text": "Cameron" }, { "pos": "VERB_P3SG", "text": "devra" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "VERB_P3SG", "text": "fait" }, { "pos": "VERB_INF", "text": "contenir" }, { "pos": "DET_SG", "text": "la" }, { "pos": "NOUN_SG", "text": "grogne" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "DET_SG", "text": "la" }, { "pos": "NOUN_SG", "text": "frange" }, { "pos": "ADJ_SG", "text": "eurosceptique" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "DET_SG", "text": "son" }, { "pos": "NOUN_SG", "text": "parti" }, { "pos": "COORD", "text": "et" }, { "pos": "VERB_INF", "text": "tenir" }, { "pos": "PREP_A", "text": "à" }, { "pos": "NOUN_SG", "text": "distance" }, { "pos": "DET_PL", "text": "les" }, { "pos": "NOUN_PL", "text": "prétendants" }, { "pos": "PREP_A", "text": "à" }, { "pos": "DET_SG", "text": "sa" }, { "pos": "NOUN_SG", "text": "succession" }, { "pos": "CM", "text": "," }, { "pos": "ADV", "text": "alors" }, { "pos": "CONJQUE", "text": "qu'" }, { "pos": "PRON", "text": "il" }, { "pos": "VAUX_P3SG", "text": "a" }, { "pos": "PAP_SG", "text": "annoncé" }, { "pos": "PREP", "text": "pendant" }, { "pos": "DET_SG", "text": "la" }, { "pos": "NOUN_SG", "text": "campagne" }, { "pos": "CONJQUE", "text": "qu'" }, { "pos": "PRON", "text": "il" }, { "pos": "NEG", "text": "ne" }, { "pos": "VERB_P3SG", "text": "briguerait" }, { "pos": "ADV", "text": "pas" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "ADJ2_SG", "text": "troisième" }, { "pos": "NOUN_SG", "text": "mandat" }, { "pos": "SENT", "text": "." }, { "pos": "DET_SG", "text": "L'" }, { "pos": "NUM", "text": "un" }, { "pos": "NUM", "text": "deux" }, { "pos": "CM", "text": "," }, { "pos": "PC", "text": "le" }, { "pos": "VERB_PRP", "text": "bouillant" }, { "pos": "NOUN_SG", "text": "maire" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NOUN_INV", "text": "Londres" }, { "pos": "NOUN_INV", "text": "Boris" }, { "pos": "NOUN_INV", "text": "Johnson" }, { "pos": "CM", "text": "," }, { "pos": "PC", "text": "s'" }, { "pos": "VAUX_P3SG", "text": "est" }, { "pos": "PAP_SG", "text": "fait" }, { "pos": "VERB_INF", "text": "élire" }, { "pos": "NOUN_SG", "text": "député" }, { "pos": "PREP_A", "text": "à" }, { "pos": "NOUN_INV", "text": "Uxbridge" }, { "pos": "CM", "text": "," }, { "pos": "DET_SG", "text": "une" }, { "pos": "NOUN_SG", "text": "étape" }, { "pos": "ADJ_SG", "text": "essentielle" }, { "pos": "PREP", "text": "pour" }, { "pos": "VERB_INF", "text": "prétendre" }, { "pos": "PREP_A", "text": "à" }, { "pos": "DET_SG", "text": "la" }, { "pos": "NOUN_SG", "text": "direction" }, { "pos": "PREP_DE", "text": "du" }, { "pos": "NOUN_SG", "text": "parti" }, { "pos": "SENT", "text": "." }, { "pos": "PREP", "text": "Dans" }, { "pos": "DET_SG", "text": "l'" }, { "pos": "NOUN_SG", "text": "immédiat" }, { "pos": "CM", "text": "," }, { "pos": "PRON", "text": "il" }, { "pos": "VERB_P3SG", "text": "appartenait" }, { "pos": "PREP_A", "text": "aux" }, { "pos": "NOUN_PL", "text": "travaillistes" }, { "pos": "COORD", "text": "et" }, { "pos": "NOUN_PL", "text": "libéraux" }, { "pos": "ADJ_PL", "text": "démocrates" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "VERB_INF", "text": "retrousser" }, { "pos": "DET_PL", "text": "les" }, { "pos": "NOUN_PL", "text": "manches" }, { "pos": "PREP", "text": "pour" }, { "pos": "PC", "text": "s'" }, { "pos": "VERB_INF", "text": "attaquer" }, { "pos": "PREP_A", "text": "au" }, { "pos": "ADJ_SG", "text": "pénible" }, { "pos": "NOUN_SG", "text": "chantier" }, { "pos": "PREP_DE", "text": "de" }, { "pos": "NOUN_SG", "text": "reconstruction" }, { "pos": "SENT", "text": "." }, { "pos": "PUNCT", "text": "(" }, { "pos": "PREP", "text": "Avec" }, { "pos": "NOUN_INV", "text": "AFP" }, { "pos": "PUNCT", "text": ")" } ], "requestId": "cc8adc05-b9f9-4c9d-b9fb-0e80536ce175", "timers": { "rblJe": 14, "rliJe": 4, "textExtractor": 103, "urlContentDownloader": 140 } } python-0.7.4/tests/mock-data/response/fra-url-morphology_complete.status 0000664 0000000 0000000 00000000003 12636317025 0026603 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/fra-url-sentiment.json 0000664 0000000 0000000 00000000242 12636317025 0024155 0 ustar 00root root 0000000 0000000 { "code": "unsupportedLanguage", "message": "French is not supported by Rosette Sentiment Analyzer", "requestId": "b2f2f3f8-b1db-4a3b-b44e-450793ef2733" } python-0.7.4/tests/mock-data/response/fra-url-sentiment.status 0000664 0000000 0000000 00000000003 12636317025 0024522 0 ustar 00root root 0000000 0000000 415 python-0.7.4/tests/mock-data/response/info.json 0000664 0000000 0000000 00000000222 12636317025 0021532 0 ustar 00root root 0000000 0000000 { "buildNumber": "6bafb29d", "buildTime": "2015.05.08_12:31:26", "name": "Rosette API", "version": "0.5.0", "versionChecked": true } python-0.7.4/tests/mock-data/response/info.status 0000664 0000000 0000000 00000000003 12636317025 0022101 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/jpn-doc-categories.json 0000664 0000000 0000000 00000000235 12636317025 0024260 0 ustar 00root root 0000000 0000000 { "code": "unsupportedLanguage", "message": "Japanese is not supported by Rosette Categorizer", "requestId": "01656884-41ba-4a87-b40a-37f78ace7a23" } python-0.7.4/tests/mock-data/response/jpn-doc-categories.status 0000664 0000000 0000000 00000000003 12636317025 0024623 0 ustar 00root root 0000000 0000000 415 python-0.7.4/tests/mock-data/response/jpn-doc-entities.json 0000664 0000000 0000000 00000017270 12636317025 0023766 0 ustar 00root root 0000000 0000000 { "entities": [ { "confidence": 0.005091860890388489, "count": 4, "indocChainId": 11, "mention": "イギリス", "normalized": "イギリス", "type": "ORGANIZATION" }, { "confidence": 1.0, "count": 3, "indocChainId": 29, "mention": "下院", "normalized": "下院", "type": "ORGANIZATION" }, { "confidence": 1.0, "count": 3, "indocChainId": 37, "mention": "上院", "normalized": "上院", "type": "ORGANIZATION" }, { "confidence": 0.007921993732452393, "count": 2, "indocChainId": 2, "mention": "アイルランド", "normalized": "アイルランド", "type": "LOCATION" }, { "confidence": 0.029875636100769043, "count": 2, "indocChainId": 3, "mention": "ジョセフ・P・ケネディ", "normalized": "ジョセフ・P・ケネディ", "type": "PERSON" }, { "confidence": 0.009616047143936157, "count": 2, "indocChainId": 3, "mention": "ジョセフ", "normalized": "ジョセフ", "type": "PERSON" }, { "confidence": 0.005369991064071655, "count": 2, "indocChainId": 3, "mention": "ケネディ", "normalized": "ケネディ", "type": "PERSON" }, { "confidence": 0.007853776216506958, "count": 2, "indocChainId": 5, "mention": "ボストン", "normalized": "ボストン", "type": "LOCATION" }, { "confidence": 0.007853776216506958, "count": 2, "indocChainId": 6, "mention": "市長", "normalized": "市長", "type": "TITLE" }, { "confidence": 1.0, "count": 2, "indocChainId": 14, "mention": "ハーバード大学", "normalized": "ハーバード大学", "type": "ORGANIZATION" }, { "confidence": 1.0, "count": 2, "indocChainId": 32, "mention": "共和党", "normalized": "共和党", "type": "ORGANIZATION" }, { "confidence": 0.015272259712219238, "count": 1, "indocChainId": 0, "mention": "マサチューセッツ州", "normalized": "マサチューセッツ州", "type": "LOCATION" }, { "confidence": 0.00015401840209960938, "count": 1, "indocChainId": 1, "mention": "ブルックライン", "normalized": "ブルックライン", "type": "LOCATION" }, { "confidence": 0.0026397705078125, "count": 1, "indocChainId": 4, "mention": "シニア", "normalized": "シニア", "type": "ORGANIZATION" }, { "confidence": 0.019479751586914062, "count": 1, "indocChainId": 7, "mention": "ジョン・F・フィッツジェラルド", "normalized": "ジョン・F・フィッツジェラルド", "type": "PERSON" }, { "confidence": 0.005173742771148682, "count": 1, "indocChainId": 8, "mention": "チョート・スクール", "normalized": "チョート・スクール", "type": "PERSON" }, { "confidence": 0.01989346742630005, "count": 1, "indocChainId": 9, "mention": "コネチカット州", "normalized": "コネチカット州", "type": "LOCATION" }, { "confidence": 0.027547240257263184, "count": 1, "indocChainId": 10, "mention": "ウォリングフォード", "normalized": "ウォリングフォード", "type": "LOCATION" }, { "confidence": 0.0014181733131408691, "count": 1, "indocChainId": 12, "mention": "ロンドン", "normalized": "ロンドン", "type": "LOCATION" }, { "confidence": 0.0014181733131408691, "count": 1, "indocChainId": 13, "mention": "オブ・エコノミクス", "normalized": "オブ・エコノミクス", "type": "ORGANIZATION" }, { "confidence": 1.0, "count": 1, "indocChainId": 15, "mention": "プリンストン大学", "normalized": "プリンストン大学", "type": "ORGANIZATION" }, { "confidence": 0.012808084487915039, "count": 1, "indocChainId": 17, "mention": "ヨーロッパ", "normalized": "ヨーロッパ", "type": "LOCATION" }, { "confidence": 0.012429237365722656, "count": 1, "indocChainId": 18, "mention": "大使", "normalized": "大使", "type": "TITLE" }, { "confidence": 0.010786056518554688, "count": 1, "indocChainId": 20, "mention": "ミュンヘン", "normalized": "ミュンヘン", "type": "LOCATION" }, { "confidence": 1.0, "count": 1, "indocChainId": 23, "mention": "ハーバード", "normalized": "ハーバード", "type": "ORGANIZATION" }, { "confidence": 0.0019164681434631348, "count": 1, "indocChainId": 25, "mention": "ジェームズ・M・カーレイ", "normalized": "ジェームズ・M・カーレイ", "type": "ORGANIZATION" }, { "confidence": 1.0, "count": 1, "indocChainId": 28, "mention": "民主党", "normalized": "民主党", "type": "ORGANIZATION" }, { "confidence": 0.04107320308685303, "count": 1, "indocChainId": 36, "mention": "ジョセフ・マッカーシー", "normalized": "ジョセフ・マッカーシー", "type": "PERSON" }, { "confidence": 0.0024489164352416992, "count": 1, "indocChainId": 38, "mention": "赤狩り", "normalized": "赤狩り", "type": "ORGANIZATION" }, { "confidence": 0.01878488063812256, "count": 1, "indocChainId": 39, "mention": "エレノア・ルーズヴェルト", "normalized": "エレノア・ルーズヴェルト", "type": "PERSON" }, { "confidence": 0.010483860969543457, "count": 1, "indocChainId": 44, "mention": "ヘンリー・カボット・ロッジ", "normalized": "ヘンリー・カボット・ロッジ", "type": "PERSON" }, { "confidence": 0.03342700004577637, "count": 1, "indocChainId": 45, "mention": "都市", "normalized": "都市", "type": "LOCATION" }, { "confidence": 0.021946430206298828, "count": 1, "indocChainId": 46, "mention": "フランス", "normalized": "フランス", "type": "LOCATION" }, { "confidence": 0.009429752826690674, "count": 1, "indocChainId": 47, "mention": "ジャクリーン・リー・ブーヴィエ", "normalized": "ジャクリーン・リー・ブーヴィエ", "type": "PERSON" }, { "confidence": 1.0, "count": 1, "indocChainId": 49, "mention": "黒人", "normalized": "黒人", "type": "NATIONALITY" }, { "confidence": 1.0, "count": 1, "indocChainId": 50, "mention": "http://ja.wikipedia.org/wiki/%E3%82%B8%E3%83%A7%E3%83%B3%E3%83%BBF%E3%83%BB%E3%82%B1%E3%83%8D%E3%83%87%E3%82%A3", "normalized": "http://ja.wikipedia.org/wiki/%E3%82%B8%E3%83%A7%E3%83%B3%E3%83%BBF%E3%83%BB%E3%82%B1%E3%83%8D%E3%83%87%E3%82%A3", "type": "IDENTIFIER:URL" } ], "requestId": "d32a9669-1a57-40ee-8f8d-893d2c9ac20f", "timers": { "rblJe": 27, "rexJe": 67, "rliJe": 3 } } python-0.7.4/tests/mock-data/response/jpn-doc-entities.status 0000664 0000000 0000000 00000000003 12636317025 0024322 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/jpn-doc-entities_linked.json 0000664 0000000 0000000 00000011137 12636317025 0025310 0 ustar 00root root 0000000 0000000 { "entities": [ { "confidence": 0.08150000324031924, "entityId": "Q771", "indocChainId": 0, "mention": "マサチューセッツ州" }, { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 1, "mention": "ブルックライン" }, { "confidence": 0.16966375669187272, "entityId": "NEW-CLUSTER", "indocChainId": 2, "mention": "アイルランド" }, { "confidence": 0.100839351669203, "entityId": "Q313696", "indocChainId": 3, "mention": "ジョセフ・P・ケネディ" }, { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 4, "mention": "シニア" }, { "confidence": 0.033937314067048835, "entityId": "Q100", "indocChainId": 5, "mention": "ボストン" }, { "confidence": 0.028870970503669564, "entityId": "Q966182", "indocChainId": 7, "mention": "ジョン・F・フィッツジェラルド" }, { "confidence": 0.07038684983544333, "entityId": "NEW-CLUSTER", "indocChainId": 8, "mention": "チョート・スクール" }, { "confidence": 0.11103028837021027, "entityId": "NEW-CLUSTER", "indocChainId": 9, "mention": "コネチカット州" }, { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 10, "mention": "ウォリングフォード" }, { "confidence": 0.6875075771342374, "entityId": "NEW-CLUSTER", "indocChainId": 11, "mention": "イギリス" }, { "confidence": 0.12140031445941092, "entityId": "NEW-CLUSTER", "indocChainId": 12, "mention": "ロンドン" }, { "confidence": 0.6673219386000714, "entityId": "NEW-CLUSTER", "indocChainId": 13, "mention": "オブ・エコノミクス" }, { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 14, "mention": "ハーバード大学" }, { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 15, "mention": "プリンストン大学" }, { "confidence": 0.06520242712260711, "entityId": "NEW-CLUSTER", "indocChainId": 17, "mention": "ヨーロッパ" }, { "confidence": 0.040417151292228386, "entityId": "NEW-CLUSTER", "indocChainId": 20, "mention": "ミュンヘン" }, { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 23, "mention": "ハーバード" }, { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 25, "mention": "ジェームズ・M・カーレイ" }, { "confidence": 0.11350495815962937, "entityId": "Q29552", "indocChainId": 28, "mention": "民主党" }, { "confidence": 0.3333333632677906, "entityId": "Q11005", "indocChainId": 29, "mention": "下院" }, { "confidence": 0.3912032605265454, "entityId": "Q29468", "indocChainId": 32, "mention": "共和党" }, { "confidence": 0.1206641893744556, "entityId": "NEW-CLUSTER", "indocChainId": 36, "mention": "ジョセフ・マッカーシー" }, { "confidence": 0.3074277973114097, "entityId": "Q11007", "indocChainId": 37, "mention": "上院" }, { "confidence": 0.4368364492353905, "entityId": "NEW-CLUSTER", "indocChainId": 38, "mention": "赤狩り" }, { "confidence": 0.04372667301381498, "entityId": "NEW-CLUSTER", "indocChainId": 39, "mention": "エレノア・ルーズヴェルト" }, { "confidence": 0.5769489100481775, "entityId": "NEW-CLUSTER", "indocChainId": 44, "mention": "ヘンリー・カボット・ロッジ" }, { "confidence": 0.5370148902457523, "entityId": "Q515", "indocChainId": 45, "mention": "都市" }, { "confidence": 0.03999527640034162, "entityId": "NEW-CLUSTER", "indocChainId": 46, "mention": "フランス" }, { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 47, "mention": "ジャクリーン・リー・ブーヴィエ" } ], "requestId": "3e0c19b1-b6c1-4a75-b67c-45a0d428b2a7", "timers": { "rblJe": 13, "res": 2505, "rexJe": 22, "rliJe": 5 } } python-0.7.4/tests/mock-data/response/jpn-doc-entities_linked.status 0000664 0000000 0000000 00000000003 12636317025 0025650 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/jpn-doc-language.json 0000664 0000000 0000000 00000001021 12636317025 0023710 0 ustar 00root root 0000000 0000000 { "languageDetections": [ { "confidence": 0.2908416241876388, "language": "jpn" }, { "confidence": 0.004286980665607287, "language": "zho" }, { "confidence": 0.004103465870464618, "language": "zho" }, { "confidence": 2.1297604570036377e-05, "language": "ron" }, { "confidence": 2.0531535010803736e-05, "language": "por" } ], "requestId": "db66a1df-b686-4e38-b12c-0c5994e6e5a0", "timers": { "rliJe": 2 } } python-0.7.4/tests/mock-data/response/jpn-doc-language.status 0000664 0000000 0000000 00000000003 12636317025 0024261 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/jpn-doc-morphology_complete.json 0000664 0000000 0000000 00000373475 12636317025 0026245 0 ustar 00root root 0000000 0000000 { "compounds": [], "hanReadings": [ { "hanReadings": [ "ハ" ], "text": "は" }, { "hanReadings": [ "マサチューセッツ" ], "text": "マサチューセッツ" }, { "hanReadings": [ "ス" ], "text": "州" }, { "hanReadings": [ "デ" ], "text": "で" }, { "hanReadings": [ "、" ], "text": "、" }, { "hanReadings": [ "アイルランド" ], "text": "アイルランド" }, { "hanReadings": [ "ケイ" ], "text": "系" }, { "hanReadings": [ "イミン" ], "text": "移民" }, { "hanReadings": [ "ノ" ], "text": "の" }, { "hanReadings": [ "シソン" ], "text": "子孫" }, { "hanReadings": [ "デ" ], "text": "で" }, { "hanReadings": [ "トウシ" ], "text": "投資" }, { "hanReadings": [ "カ" ], "text": "家" }, { "hanReadings": [ "ノ" ], "text": "の" }, { "hanReadings": [ "ジョセフ" ], "text": "ジョセフ" }, { "hanReadings": [ "・" ], "text": "・" }, { "hanReadings": [ "ピー" ], "text": "P" }, { "hanReadings": [ "・" ], "text": "・" }, { "hanReadings": [ "ケネディ" ], "text": "ケネディ" }, { "hanReadings": [ "・" ], "text": "・" }, { "hanReadings": [ "シニア" ], "text": "シニア" }, { "hanReadings": [ "ノ" ], "text": "の" }, { "hanReadings": [ "ジナン" ], "text": "次男" }, { "hanReadings": [ "ト" ], "text": "と" }, { "hanReadings": [ "シ" ], "text": "し" }, { "hanReadings": [ "テ" ], "text": "て" }, { "hanReadings": [ "ウマレ" ], "text": "生まれ" }, { "hanReadings": [ "タ" ], "text": "た" }, { "hanReadings": [ "。" ], "text": "。" }, { "hanReadings": [ "ナマエ" ], "text": "名前" }, { "hanReadings": [ "ハ" ], "text": "は" }, { "hanReadings": [ "ハハカタ" ], "text": "母方" }, { "hanReadings": [ "ノ" ], "text": "の" }, { "hanReadings": [ "ソフ" ], "text": "祖父" }, { "hanReadings": [ "デ" ], "text": "で" }, { "hanReadings": [ "ボストン" ], "text": "ボストン" }, { "hanReadings": [ "シチョウ" ], "text": "市長" }, { "hanReadings": [ "モ" ], "text": "も" }, { "hanReadings": [ "ツトメ" ], "text": "勤め" }, { "hanReadings": [ "タ" ], "text": "た" }, { "hanReadings": [ "ジョン" ], "text": "ジョン" }, { "hanReadings": [ "・" ], "text": "・" }, { "hanReadings": [ "エフ" ], "text": "F" }, { "hanReadings": [ "・" ], "text": "・" }, { "hanReadings": [ "ニ" ], "text": "に" }, { "hanReadings": [ "チナム" ], "text": "ちなむ" }, { "hanReadings": [ "。" ], "text": "。" }, { "hanReadings": [ "サイ" ], "text": "歳" }, { "hanReadings": [ "ノ" ], "text": "の" }, { "hanReadings": [ "トキ" ], "text": "とき" }, { "hanReadings": [ "ニ" ], "text": "に" }, { "hanReadings": [ "・" ], "text": "・" }, { "hanReadings": [ "スクール" ], "text": "スクール" }, { "hanReadings": [ "ス" ], "text": "州" }, { "hanReadings": [ "ノ" ], "text": "の" }, { "hanReadings": [ "キシュク" ], "text": "寄宿" }, { "hanReadings": [ "ガッコウ" ], "text": "学校" }, { "hanReadings": [ "ニ" ], "text": "に" }, { "hanReadings": [ "ニュウガク" ], "text": "入学" }, { "hanReadings": [ "シ" ], "text": "し" }, { "hanReadings": [ "、" ], "text": "、" }, { "hanReadings": [ "ソノ" ], "text": "その" }, { "hanReadings": [ "コウ" ], "text": "後" }, { "hanReadings": [ "ネン" ], "text": "年" }, { "hanReadings": [ "ニ" ], "text": "に" }, { "hanReadings": [ "イギリス" ], "text": "イギリス" }, { "hanReadings": [ "ノ" ], "text": "の" }, { "hanReadings": [ "ロンドン" ], "text": "ロンドン" }, { "hanReadings": [ "・" ], "text": "・" }, { "hanReadings": [ "スクール" ], "text": "スクール" }, { "hanReadings": [ "・" ], "text": "・" }, { "hanReadings": [ "オブ" ], "text": "オブ" }, { "hanReadings": [ "・" ], "text": "・" }, { "hanReadings": [ "ニ" ], "text": "に" }, { "hanReadings": [ "ネンカン" ], "text": "年間" }, { "hanReadings": [ "リュウガク" ], "text": "留学" }, { "hanReadings": [ "シ" ], "text": "し" }, { "hanReadings": [ "タ" ], "text": "た" }, { "hanReadings": [ "。" ], "text": "。" }, { "hanReadings": [ "キコク" ], "text": "帰国" }, { "hanReadings": [ "コウ" ], "text": "後" }, { "hanReadings": [ "ハーバード" ], "text": "ハーバード" }, { "hanReadings": [ "ダイガク" ], "text": "大学" }, { "hanReadings": [ "ニ" ], "text": "に" }, { "hanReadings": [ "ニュウガク" ], "text": "入学" }, { "hanReadings": [ "ヲ" ], "text": "を" }, { "hanReadings": [ "ミトメ" ], "text": "認め" }, { "hanReadings": [ "ラレ" ], "text": "られ" }, { "hanReadings": [ "テ" ], "text": "て" }, { "hanReadings": [ "イ" ], "text": "い" }, { "hanReadings": [ "タ" ], "text": "た" }, { "hanReadings": [ "モノ" ], "text": "もの" }, { "hanReadings": [ "ノ" ], "text": "の" }, { "hanReadings": [ "、" ], "text": "、" }, { "hanReadings": [ "シタシイ" ], "text": "親しい" }, { "hanReadings": [ "ユウジン" ], "text": "友人" }, { "hanReadings": [ "ガ" ], "text": "が" }, { "hanReadings": [ "シンガク" ], "text": "進学" }, { "hanReadings": [ "ヲ" ], "text": "を" }, { "hanReadings": [ "ギメ" ], "text": "決め" }, { "hanReadings": [ "タ" ], "text": "た" }, { "hanReadings": [ "プリンストン" ], "text": "プリンストン" }, { "hanReadings": [ "ダイガク" ], "text": "大学" }, { "hanReadings": [ "ニ" ], "text": "に" }, { "hanReadings": [ "ニュウガク" ], "text": "入学" }, { "hanReadings": [ "スル" ], "text": "する" }, { "hanReadings": [ "コト" ], "text": "こと" }, { "hanReadings": [ "ニ" ], "text": "に" }, { "hanReadings": [ "シ" ], "text": "し" }, { "hanReadings": [ "タ" ], "text": "た" }, { "hanReadings": [ "。" ], "text": "。" }, { "hanReadings": [ "シカシ" ], "text": "しかし" }, { "hanReadings": [ "、" ], "text": "、" }, { "hanReadings": [ "クリスマス" ], "text": "クリスマス" }, { "hanReadings": [ "キュウカ" ], "text": "休暇" }, { "hanReadings": [ "チュウ" ], "text": "中" }, { "hanReadings": [ "ニ" ], "text": "に" }, { "hanReadings": [ "カカッ" ], "text": "かかっ" }, { "hanReadings": [ "タ" ], "text": "た" }, { "hanReadings": [ "オウダン" ], "text": "黄疸" }, { "hanReadings": [ "ノ" ], "text": "の" }, { "hanReadings": [ "タメ" ], "text": "ため" }, { "hanReadings": [ "タイガク" ], "text": "退学" }, { "hanReadings": [ "シ" ], "text": "し" }, { "hanReadings": [ "テ" ], "text": "て" }, { "hanReadings": [ "イル" ], "text": "いる" }, { "hanReadings": [ "。" ], "text": "。" }, { "hanReadings": [ "ネン" ], "text": "年" }, { "hanReadings": [ "ノ" ], "text": "の" }, { "hanReadings": [ "アキ" ], "text": "秋" }, { "hanReadings": [ "ニ" ], "text": "に" }, { "hanReadings": [ "ハ" ], "text": "は" }, { "hanReadings": [ "ハーバード" ], "text": "ハーバード" }, { "hanReadings": [ "ダイガク" ], "text": "大学" }, { "hanReadings": [ "ニ" ], "text": "に" }, { "hanReadings": [ "テンコウ" ], "text": "転校" }, { "hanReadings": [ "シ" ], "text": "し" }, { "hanReadings": [ "タ" ], "text": "た" }, { "hanReadings": [ "ガ" ], "text": "が" }, { "hanReadings": [ "、" ], "text": "、" }, { "hanReadings": [ "ザイガク" ], "text": "在学" }, { "hanReadings": [ "ナカ" ], "text": "中" }, { "hanReadings": [ "ニ" ], "text": "に" }, { "hanReadings": [ "フットボール" ], "text": "フットボール" }, { "hanReadings": [ "ノ" ], "text": "の" }, { "hanReadings": [ "シアイ" ], "text": "試合" }, { "hanReadings": [ "デ" ], "text": "で" }, { "hanReadings": [ "セナカ" ], "text": "背中" }, { "hanReadings": [ "ヲ" ], "text": "を" }, { "hanReadings": [ "ヒドク" ], "text": "ひどく" }, { "hanReadings": [ "イタメ" ], "text": "痛め" }, { "hanReadings": [ "タ" ], "text": "た" }, { "hanReadings": [ "。" ], "text": "。" }, { "hanReadings": [ "ヨーロッパ" ], "text": "ヨーロッパ" }, { "hanReadings": [ "ヘ" ], "text": "へ" }, { "hanReadings": [ "ド" ], "text": "度" }, { "hanReadings": [ "リョコウ" ], "text": "旅行" }, { "hanReadings": [ "シ" ], "text": "し" }, { "hanReadings": [ "テ" ], "text": "て" }, { "hanReadings": [ "オリ" ], "text": "おり" }, { "hanReadings": [ "、" ], "text": "、" }, { "hanReadings": [ "タビ" ], "text": "度" }, { "hanReadings": [ "メ" ], "text": "目" }, { "hanReadings": [ "ノ" ], "text": "の" }, { "hanReadings": [ "リョコウ" ], "text": "旅行" }, { "hanReadings": [ "デ" ], "text": "で" }, { "hanReadings": [ "ハ" ], "text": "は" }, { "hanReadings": [ "チチオヤ" ], "text": "父親" }, { "hanReadings": [ "ガ" ], "text": "が" }, { "hanReadings": [ "タイシ" ], "text": "大使" }, { "hanReadings": [ "ヲ" ], "text": "を" }, { "hanReadings": [ "ツトメ" ], "text": "務め" }, { "hanReadings": [ "テ" ], "text": "て" }, { "hanReadings": [ "イ" ], "text": "い" }, { "hanReadings": [ "タ" ], "text": "た" }, { "hanReadings": [ "イギリス" ], "text": "イギリス" }, { "hanReadings": [ "ヲ" ], "text": "を" }, { "hanReadings": [ "オトズレレ" ], "text": "訪れ" }, { "hanReadings": [ "テ" ], "text": "て" }, { "hanReadings": [ "イル" ], "text": "いる" }, { "hanReadings": [ "。" ], "text": "。" }, { "hanReadings": [ "ネン" ], "text": "年" }, { "hanReadings": [ "ガツ" ], "text": "月" }, { "hanReadings": [ "、" ], "text": "、" }, { "hanReadings": [ "ネン" ], "text": "年" }, { "hanReadings": [ "ノ" ], "text": "の" }, { "hanReadings": [ "ミュンヘン" ], "text": "ミュンヘン" }, { "hanReadings": [ "キョウテイ" ], "text": "協定" }, { "hanReadings": [ "ニ" ], "text": "に" }, { "hanReadings": [ "オケ" ], "text": "おけ" }, { "hanReadings": [ "ル" ], "text": "る" }, { "hanReadings": [ "イギリス" ], "text": "イギリス" }, { "hanReadings": [ "ガイコウ" ], "text": "外交" }, { "hanReadings": [ "セイサク" ], "text": "政策" }, { "hanReadings": [ "ノ" ], "text": "の" }, { "hanReadings": [ "ブンセキ" ], "text": "分析" }, { "hanReadings": [ "ニ" ], "text": "に" }, { "hanReadings": [ "ツイ" ], "text": "つい" }, { "hanReadings": [ "テ" ], "text": "て" }, { "hanReadings": [ "ノ" ], "text": "の" }, { "hanReadings": [ "ソツロン" ], "text": "卒論" }, { "hanReadings": [ "『" ], "text": "『" }, { "hanReadings": [ "イギリス" ], "text": "イギリス" }, { "hanReadings": [ "ハ" ], "text": "は" }, { "hanReadings": [ "ナゼ" ], "text": "なぜ" }, { "hanReadings": [ "ネムッ" ], "text": "眠っ" }, { "hanReadings": [ "タ" ], "text": "た" }, { "hanReadings": [ "カ" ], "text": "か" }, { "hanReadings": [ "』" ], "text": "』" }, { "hanReadings": [ "ヲ" ], "text": "を" }, { "hanReadings": [ "ガキ" ], "text": "書き" }, { "hanReadings": [ "、" ], "text": "、" }, { "hanReadings": [ "ハーバード" ], "text": "ハーバード" }, { "hanReadings": [ "ヲ" ], "text": "を" }, { "hanReadings": [ "ユウトウ" ], "text": "優等" }, { "hanReadings": [ "デ" ], "text": "で" }, { "hanReadings": [ "ソツギョウ" ], "text": "卒業" }, { "hanReadings": [ "シ" ], "text": "し" }, { "hanReadings": [ "タ" ], "text": "た" }, { "hanReadings": [ "。" ], "text": "。" }, { "hanReadings": [ "ダイ" ], "text": "第" }, { "hanReadings": [ "ニ" ], "text": "二" }, { "hanReadings": [ "ジ" ], "text": "次" }, { "hanReadings": [ "セカイ" ], "text": "世界" }, { "hanReadings": [ "タイセン" ], "text": "大戦" }, { "hanReadings": [ "コウ" ], "text": "後" }, { "hanReadings": [ "、" ], "text": "、" }, { "hanReadings": [ "カレ" ], "text": "彼" }, { "hanReadings": [ "ハ" ], "text": "は" }, { "hanReadings": [ "センシ" ], "text": "戦死" }, { "hanReadings": [ "シ" ], "text": "し" }, { "hanReadings": [ "タ" ], "text": "た" }, { "hanReadings": [ "アニ" ], "text": "兄" }, { "hanReadings": [ "ジョセフ" ], "text": "ジョセフ" }, { "hanReadings": [ "・" ], "text": "・" }, { "hanReadings": [ "ピー" ], "text": "P" }, { "hanReadings": [ "・" ], "text": "・" }, { "hanReadings": [ "ケネディ" ], "text": "ケネディ" }, { "hanReadings": [ "・" ], "text": "・" }, { "hanReadings": [ "ジュニア" ], "text": "ジュニア" }, { "hanReadings": [ "ニ" ], "text": "に" }, { "hanReadings": [ "カワリ" ], "text": "代わり" }, { "hanReadings": [ "セイカイ" ], "text": "政界" }, { "hanReadings": [ "ニ" ], "text": "に" }, { "hanReadings": [ "イッ" ], "text": "入っ" }, { "hanReadings": [ "タ" ], "text": "た" }, { "hanReadings": [ "。" ], "text": "。" }, { "hanReadings": [ "ネン" ], "text": "年" }, { "hanReadings": [ "ニ" ], "text": "に" }, { "hanReadings": [ "ジェームズ" ], "text": "ジェームズ" }, { "hanReadings": [ "・" ], "text": "・" }, { "hanReadings": [ "メガ" ], "text": "M" }, { "hanReadings": [ "・" ], "text": "・" }, { "hanReadings": [ "カー" ], "text": "カー" }, { "hanReadings": [ "レイ" ], "text": "レイ" }, { "hanReadings": [ "ガ" ], "text": "が" }, { "hanReadings": [ "ボストン" ], "text": "ボストン" }, { "hanReadings": [ "シチョウ" ], "text": "市長" }, { "hanReadings": [ "ニ" ], "text": "に" }, { "hanReadings": [ "ナル" ], "text": "なる" }, { "hanReadings": [ "タメ" ], "text": "ため" }, { "hanReadings": [ "ニ" ], "text": "に" }, { "hanReadings": [ "ミンシュ" ], "text": "民主" }, { "hanReadings": [ "トウ" ], "text": "党" }, { "hanReadings": [ "カイン" ], "text": "下院" }, { "hanReadings": [ "ギイン" ], "text": "議員" }, { "hanReadings": [ "ヲ" ], "text": "を" }, { "hanReadings": [ "ジショク" ], "text": "辞職" }, { "hanReadings": [ "シ" ], "text": "し" }, { "hanReadings": [ "タ" ], "text": "た" }, { "hanReadings": [ "トキ" ], "text": "時" }, { "hanReadings": [ "、" ], "text": "、" }, { "hanReadings": [ "ケネディ" ], "text": "ケネディ" }, { "hanReadings": [ "ハ" ], "text": "は" }, { "hanReadings": [ "ソノ" ], "text": "その" }, { "hanReadings": [ "ギセキ" ], "text": "議席" }, { "hanReadings": [ "ヲ" ], "text": "を" }, { "hanReadings": [ "カケ" ], "text": "かけ" }, { "hanReadings": [ "タ" ], "text": "た" }, { "hanReadings": [ "ホケツ" ], "text": "補欠" }, { "hanReadings": [ "センキョ" ], "text": "選挙" }, { "hanReadings": [ "ニ" ], "text": "に" }, { "hanReadings": [ "タテ" ], "text": "立" }, { "hanReadings": [ "コウホ" ], "text": "候補" }, { "hanReadings": [ "シ" ], "text": "し" }, { "hanReadings": [ "タ" ], "text": "た" }, { "hanReadings": [ "。" ], "text": "。" }, { "hanReadings": [ "チャン" ], "text": "父" }, { "hanReadings": [ "ノ" ], "text": "の" }, { "hanReadings": [ "ジョセフ" ], "text": "ジョセフ" }, { "hanReadings": [ "ガ" ], "text": "が" }, { "hanReadings": [ "ジツギョウ" ], "text": "実業" }, { "hanReadings": [ "カ" ], "text": "家" }, { "hanReadings": [ "デ" ], "text": "で" }, { "hanReadings": [ "アッ" ], "text": "あっ" }, { "hanReadings": [ "タ" ], "text": "た" }, { "hanReadings": [ "コト" ], "text": "こと" }, { "hanReadings": [ "モ" ], "text": "も" }, { "hanReadings": [ "アリ" ], "text": "あり" }, { "hanReadings": [ "、" ], "text": "、" }, { "hanReadings": [ "セイジ" ], "text": "政治" }, { "hanReadings": [ "シキン" ], "text": "資金" }, { "hanReadings": [ "ニ" ], "text": "に" }, { "hanReadings": [ "ハ" ], "text": "は" }, { "hanReadings": [ "コマラ" ], "text": "困ら" }, { "hanReadings": [ "ナカッ" ], "text": "なかっ" }, { "hanReadings": [ "タ" ], "text": "た" }, { "hanReadings": [ "ノ" ], "text": "の" }, { "hanReadings": [ "デ" ], "text": "で" }, { "hanReadings": [ "、" ], "text": "、" }, { "hanReadings": [ "ジツゲン" ], "text": "実現" }, { "hanReadings": [ "フ" ], "text": "不" }, { "hanReadings": [ "カノウ" ], "text": "可能" }, { "hanReadings": [ "ナ" ], "text": "な" }, { "hanReadings": [ "コウヤク" ], "text": "公約" }, { "hanReadings": [ "ヲ" ], "text": "を" }, { "hanReadings": [ "スル" ], "text": "する" }, { "hanReadings": [ "ヒツヨウ" ], "text": "必要" }, { "hanReadings": [ "ハ" ], "text": "は" }, { "hanReadings": [ "ナク" ], "text": "なく" }, { "hanReadings": [ "リソウ" ], "text": "理想" }, { "hanReadings": [ "シュギ" ], "text": "主義" }, { "hanReadings": [ "ヲ" ], "text": "を" }, { "hanReadings": [ "カタル" ], "text": "語る" }, { "hanReadings": [ "コト" ], "text": "こと" }, { "hanReadings": [ "ガ" ], "text": "が" }, { "hanReadings": [ "デキ" ], "text": "でき" }, { "hanReadings": [ "タ" ], "text": "た" }, { "hanReadings": [ "。" ], "text": "。" }, { "hanReadings": [ "ナガク" ], "text": "長く" }, { "hanReadings": [ "セイリョク" ], "text": "精力" }, { "hanReadings": [ "テキ" ], "text": "的" }, { "hanReadings": [ "ナ" ], "text": "な" }, { "hanReadings": [ "キャンペーン" ], "text": "キャンペーン" }, { "hanReadings": [ "ノ" ], "text": "の" }, { "hanReadings": [ "マツ" ], "text": "末" }, { "hanReadings": [ "ニ" ], "text": "に" }, { "hanReadings": [ "、" ], "text": "、" }, { "hanReadings": [ "タイサ" ], "text": "大差" }, { "hanReadings": [ "デ" ], "text": "で" }, { "hanReadings": [ "キョウワ" ], "text": "共和" }, { "hanReadings": [ "トウ" ], "text": "党" }, { "hanReadings": [ "コウホ" ], "text": "候補" }, { "hanReadings": [ "ニ" ], "text": "に" }, { "hanReadings": [ "カチ" ], "text": "勝ち" }, { "hanReadings": [ "、" ], "text": "、" }, { "hanReadings": [ "サイ" ], "text": "歳" }, { "hanReadings": [ "デ" ], "text": "で" }, { "hanReadings": [ "カイン" ], "text": "下院" }, { "hanReadings": [ "ギイン" ], "text": "議員" }, { "hanReadings": [ "ト" ], "text": "と" }, { "hanReadings": [ "ナッ" ], "text": "なっ" }, { "hanReadings": [ "タ" ], "text": "た" }, { "hanReadings": [ "。" ], "text": "。" }, { "hanReadings": [ "トウショ" ], "text": "当初" }, { "hanReadings": [ "ハ" ], "text": "は" }, { "hanReadings": [ "チャン" ], "text": "父" }, { "hanReadings": [ "ノ" ], "text": "の" }, { "hanReadings": [ "ジョセフ" ], "text": "ジョセフ" }, { "hanReadings": [ "ト" ], "text": "と" }, { "hanReadings": [ "コネ" ], "text": "コネ" }, { "hanReadings": [ "ガ" ], "text": "が" }, { "hanReadings": [ "アッ" ], "text": "あっ" }, { "hanReadings": [ "タ" ], "text": "た" }, { "hanReadings": [ "オナジ" ], "text": "同じ" }, { "hanReadings": [ "アイルランド" ], "text": "アイルランド" }, { "hanReadings": [ "ケイ" ], "text": "系" }, { "hanReadings": [ "ノ" ], "text": "の" }, { "hanReadings": [ "ジョセフ" ], "text": "ジョセフ" }, { "hanReadings": [ "・" ], "text": "・" }, { "hanReadings": [ "マッカーシー" ], "text": "マッカーシー" }, { "hanReadings": [ "ジョウイン" ], "text": "上院" }, { "hanReadings": [ "ギイン" ], "text": "議員" }, { "hanReadings": [ "ノ" ], "text": "の" }, { "hanReadings": [ "アカガリ" ], "text": "赤狩り" }, { "hanReadings": [ "ニ" ], "text": "に" }, { "hanReadings": [ "キョウリョク" ], "text": "協力" }, { "hanReadings": [ "シ" ], "text": "し" }, { "hanReadings": [ "テ" ], "text": "て" }, { "hanReadings": [ "イ" ], "text": "い" }, { "hanReadings": [ "タ" ], "text": "た" }, { "hanReadings": [ "。" ], "text": "。" }, { "hanReadings": [ "リベラル" ], "text": "リベラル" }, { "hanReadings": [ "ハ" ], "text": "派" }, { "hanReadings": [ "ノ" ], "text": "の" }, { "hanReadings": [ "・" ], "text": "・" }, { "hanReadings": [ "ハ" ], "text": "は" }, { "hanReadings": [ "ソノ" ], "text": "その" }, { "hanReadings": [ "コト" ], "text": "こと" }, { "hanReadings": [ "ヲ" ], "text": "を" }, { "hanReadings": [ "ワスレ" ], "text": "忘れ" }, { "hanReadings": [ "ズ" ], "text": "ず" }, { "hanReadings": [ "、" ], "text": "、" }, { "hanReadings": [ "アトアト" ], "text": "後々" }, { "hanReadings": [ "マデ" ], "text": "まで" }, { "hanReadings": [ "ケネディ" ], "text": "ケネディ" }, { "hanReadings": [ "ヲ" ], "text": "を" }, { "hanReadings": [ "キラッ" ], "text": "嫌っ" }, { "hanReadings": [ "テ" ], "text": "て" }, { "hanReadings": [ "イ" ], "text": "い" }, { "hanReadings": [ "タ" ], "text": "た" }, { "hanReadings": [ "。" ], "text": "。" }, { "hanReadings": [ "カイン" ], "text": "下院" }, { "hanReadings": [ "キ" ], "text": "期" }, { "hanReadings": [ "メ" ], "text": "目" }, { "hanReadings": [ "ノ" ], "text": "の" }, { "hanReadings": [ "ネン" ], "text": "年" }, { "hanReadings": [ "ニ" ], "text": "に" }, { "hanReadings": [ "ハ" ], "text": "は" }, { "hanReadings": [ "ジョウイン" ], "text": "上院" }, { "hanReadings": [ "ギイン" ], "text": "議員" }, { "hanReadings": [ "センキョ" ], "text": "選挙" }, { "hanReadings": [ "ニ" ], "text": "に" }, { "hanReadings": [ "シュツバ" ], "text": "出馬" }, { "hanReadings": [ "シ" ], "text": "し" }, { "hanReadings": [ "、" ], "text": "、" }, { "hanReadings": [ "ヤク" ], "text": "約" }, { "hanReadings": [ "ヒョウ" ], "text": "票" }, { "hanReadings": [ "ノ" ], "text": "の" }, { "hanReadings": [ "タイサ" ], "text": "大差" }, { "hanReadings": [ "デ" ], "text": "で" }, { "hanReadings": [ "キョウワ" ], "text": "共和" }, { "hanReadings": [ "トウ" ], "text": "党" }, { "hanReadings": [ "コウホ" ], "text": "候補" }, { "hanReadings": [ "ヘンリー" ], "text": "ヘンリー" }, { "hanReadings": [ "・" ], "text": "・" }, { "hanReadings": [ "・" ], "text": "・" }, { "hanReadings": [ "ロッジ" ], "text": "ロッジ" }, { "hanReadings": [ "・" ], "text": "・" }, { "hanReadings": [ "ジュニア" ], "text": "ジュニア" }, { "hanReadings": [ "ヲ" ], "text": "を" }, { "hanReadings": [ "ヤブッ" ], "text": "破っ" }, { "hanReadings": [ "タ" ], "text": "た" }, { "hanReadings": [ "。" ], "text": "。" }, { "hanReadings": [ "イゴ" ], "text": "以後" }, { "hanReadings": [ "ノ" ], "text": "の" }, { "hanReadings": [ "カレ" ], "text": "彼" }, { "hanReadings": [ "ノ" ], "text": "の" }, { "hanReadings": [ "シジ" ], "text": "支持" }, { "hanReadings": [ "キバン" ], "text": "基盤" }, { "hanReadings": [ "ハ" ], "text": "は" }, { "hanReadings": [ "ホクブ" ], "text": "北部" }, { "hanReadings": [ "トシ" ], "text": "都市" }, { "hanReadings": [ "ケン" ], "text": "圏" }, { "hanReadings": [ "ノ" ], "text": "の" }, { "hanReadings": [ "リベラル" ], "text": "リベラル" }, { "hanReadings": [ "ハ" ], "text": "派" }, { "hanReadings": [ "インテリ" ], "text": "インテリ" }, { "hanReadings": [ "ソウ" ], "text": "層" }, { "hanReadings": [ "ト" ], "text": "と" }, { "hanReadings": [ "ナル" ], "text": "なる" }, { "hanReadings": [ "。" ], "text": "。" }, { "hanReadings": [ "ハ" ], "text": "は" }, { "hanReadings": [ "ネン" ], "text": "年" }, { "hanReadings": [ "ガツ" ], "text": "月" }, { "hanReadings": [ "ニチ" ], "text": "日" }, { "hanReadings": [ "ニ" ], "text": "に" }, { "hanReadings": [ "フランス" ], "text": "フランス" }, { "hanReadings": [ "ケイ" ], "text": "系" }, { "hanReadings": [ "イミン" ], "text": "移民" }, { "hanReadings": [ "ノ" ], "text": "の" }, { "hanReadings": [ "メイモン" ], "text": "名門" }, { "hanReadings": [ "ノ" ], "text": "の" }, { "hanReadings": [ "ムスメ" ], "text": "娘" }, { "hanReadings": [ "デ" ], "text": "で" }, { "hanReadings": [ "アル" ], "text": "ある" }, { "hanReadings": [ "・" ], "text": "・" }, { "hanReadings": [ "リー" ], "text": "リー" }, { "hanReadings": [ "・" ], "text": "・" }, { "hanReadings": [ "ト" ], "text": "と" }, { "hanReadings": [ "ケッコン" ], "text": "結婚" }, { "hanReadings": [ "シ" ], "text": "し" }, { "hanReadings": [ "タ" ], "text": "た" }, { "hanReadings": [ "。" ], "text": "。" }, { "hanReadings": [ "カレ" ], "text": "彼" }, { "hanReadings": [ "ハ" ], "text": "は" }, { "hanReadings": [ "ソノ" ], "text": "その" }, { "hanReadings": [ "コウ" ], "text": "後" }, { "hanReadings": [ "ネンカン" ], "text": "年間" }, { "hanReadings": [ "ニ" ], "text": "に" }, { "hanReadings": [ "タスウ" ], "text": "多数" }, { "hanReadings": [ "カイ" ], "text": "回" }, { "hanReadings": [ "ノ" ], "text": "の" }, { "hanReadings": [ "セキチュウ" ], "text": "脊柱" }, { "hanReadings": [ "ノ" ], "text": "の" }, { "hanReadings": [ "シュジュツ" ], "text": "手術" }, { "hanReadings": [ "ヲ" ], "text": "を" }, { "hanReadings": [ "ホン" ], "text": "本" }, { "hanReadings": [ "カイギ" ], "text": "会議" }, { "hanReadings": [ "ヲ" ], "text": "を" }, { "hanReadings": [ "チョウキ" ], "text": "長期" }, { "hanReadings": [ "ニ" ], "text": "に" }, { "hanReadings": [ "ワタッ" ], "text": "わたっ" }, { "hanReadings": [ "テ" ], "text": "て" }, { "hanReadings": [ "ケッセキ" ], "text": "欠席" }, { "hanReadings": [ "シ" ], "text": "し" }, { "hanReadings": [ "タ" ], "text": "た" }, { "hanReadings": [ "ガ" ], "text": "が" }, { "hanReadings": [ "、" ], "text": "、" }, { "hanReadings": [ "シュジュツ" ], "text": "手術" }, { "hanReadings": [ "カラ" ], "text": "から" }, { "hanReadings": [ "カイフク" ], "text": "回復" }, { "hanReadings": [ "スル" ], "text": "する" }, { "hanReadings": [ "マデ" ], "text": "まで" }, { "hanReadings": [ "ノ" ], "text": "の" }, { "hanReadings": [ "マ" ], "text": "間" }, { "hanReadings": [ "、" ], "text": "、" }, { "hanReadings": [ "ナ" ], "text": "名" }, { "hanReadings": [ "ノ" ], "text": "の" }, { "hanReadings": [ "ジョウイン" ], "text": "上院" }, { "hanReadings": [ "ギイン" ], "text": "議員" }, { "hanReadings": [ "ノ" ], "text": "の" }, { "hanReadings": [ "セイジ" ], "text": "政治" }, { "hanReadings": [ "テキ" ], "text": "的" }, { "hanReadings": [ "ニ" ], "text": "に" }, { "hanReadings": [ "ユウカン" ], "text": "勇敢" }, { "hanReadings": [ "デ" ], "text": "で" }, { "hanReadings": [ "アッ" ], "text": "あっ" }, { "hanReadings": [ "タ" ], "text": "た" }, { "hanReadings": [ "コウイ" ], "text": "行為" }, { "hanReadings": [ "ニ" ], "text": "に" }, { "hanReadings": [ "ツイ" ], "text": "つい" }, { "hanReadings": [ "テ" ], "text": "て" }, { "hanReadings": [ "ノ" ], "text": "の" }, { "hanReadings": [ "モト" ], "text": "本" }, { "hanReadings": [ "『" ], "text": "『" }, { "hanReadings": [ "ユウキ" ], "text": "勇気" }, { "hanReadings": [ "アル" ], "text": "ある" }, { "hanReadings": [ "ヒトビト" ], "text": "人々" }, { "hanReadings": [ "』" ], "text": "』" }, { "hanReadings": [ "ヲ" ], "text": "を" }, { "hanReadings": [ "シュッパン" ], "text": "出版" }, { "hanReadings": [ "シ" ], "text": "し" }, { "hanReadings": [ "タ" ], "text": "た" }, { "hanReadings": [ "。" ], "text": "。" }, { "hanReadings": [ "コノ" ], "text": "この" }, { "hanReadings": [ "モト" ], "text": "本" }, { "hanReadings": [ "ハ" ], "text": "は" }, { "hanReadings": [ "ソノ" ], "text": "その" }, { "hanReadings": [ "コウ" ], "text": "後" }, { "hanReadings": [ "ショウ" ], "text": "賞" }, { "hanReadings": [ "ヲ" ], "text": "を" }, { "hanReadings": [ "ジュショウ" ], "text": "受賞" }, { "hanReadings": [ "シ" ], "text": "し" }, { "hanReadings": [ "タ" ], "text": "た" }, { "hanReadings": [ "。" ], "text": "。" }, { "hanReadings": [ "ショウキン" ], "text": "賞金" }, { "hanReadings": [ "ハ" ], "text": "は" }, { "hanReadings": [ "コクジン" ], "text": "黒人" }, { "hanReadings": [ "ノ" ], "text": "の" }, { "hanReadings": [ "カヨウ" ], "text": "通う" }, { "hanReadings": [ "ガッコウ" ], "text": "学校" }, { "hanReadings": [ "ヘ" ], "text": "へ" }, { "hanReadings": [ "ヨセツケ" ], "text": "寄付" }, { "hanReadings": [ "シ" ], "text": "し" }, { "hanReadings": [ "タ" ], "text": "た" }, { "hanReadings": [ "ト" ], "text": "と" }, { "hanReadings": [ "ユワ" ], "text": "言わ" }, { "hanReadings": [ "レ" ], "text": "れ" }, { "hanReadings": [ "テ" ], "text": "て" }, { "hanReadings": [ "イル" ], "text": "いる" }, { "hanReadings": [ "。" ], "text": "。" }, { "hanReadings": [ ":" ], "text": ":" }, { "hanReadings": [ "/" ], "text": "/" }, { "hanReadings": [ "/" ], "text": "/" }, { "hanReadings": [ "/" ], "text": "/" }, { "hanReadings": [ "/" ], "text": "/" }, { "hanReadings": [ "%" ], "text": "%" }, { "hanReadings": [ "%" ], "text": "%" }, { "hanReadings": [ "%" ], "text": "%" }, { "hanReadings": [ "%" ], "text": "%" }, { "hanReadings": [ "%" ], "text": "%" }, { "hanReadings": [ "%" ], "text": "%" }, { "hanReadings": [ "%" ], "text": "%" }, { "hanReadings": [ "%" ], "text": "%" }, { "hanReadings": [ "%" ], "text": "%" }, { "hanReadings": [ "%" ], "text": "%" }, { "hanReadings": [ "%" ], "text": "%" }, { "hanReadings": [ "%" ], "text": "%" }, { "hanReadings": [ "%" ], "text": "%" }, { "hanReadings": [ "%" ], "text": "%" }, { "hanReadings": [ "%" ], "text": "%" }, { "hanReadings": [ "%" ], "text": "%" }, { "hanReadings": [ "%" ], "text": "%" }, { "hanReadings": [ "%" ], "text": "%" }, { "hanReadings": [ "%" ], "text": "%" }, { "hanReadings": [ "%" ], "text": "%" }, { "hanReadings": [ "%" ], "text": "%" }, { "hanReadings": [ "%" ], "text": "%" }, { "hanReadings": [ "%" ], "text": "%" }, { "hanReadings": [ "%" ], "text": "%" }, { "hanReadings": [ "%" ], "text": "%" }, { "hanReadings": [ "%" ], "text": "%" }, { "hanReadings": [ "%" ], "text": "%" } ], "lemmas": [ { "lemma": "ケ", "text": "ケ" }, { "lemma": "ネディ", "text": "ネディ" }, { "lemma": "は", "text": "は" }, { "lemma": "マサチューセッツ", "text": "マサチューセッツ" }, { "lemma": "州", "text": "州" }, { "lemma": "ブルックライン", "text": "ブルックライン" }, { "lemma": "で", "text": "で" }, { "lemma": "、", "text": "、" }, { "lemma": "アイルランド", "text": "アイルランド" }, { "lemma": "系", "text": "系" }, { "lemma": "移民", "text": "移民" }, { "lemma": "の", "text": "の" }, { "lemma": "子孫", "text": "子孫" }, { "lemma": "で", "text": "で" }, { "lemma": "投資", "text": "投資" }, { "lemma": "家", "text": "家" }, { "lemma": "の", "text": "の" }, { "lemma": "ジョセフ", "text": "ジョセフ" }, { "lemma": "・", "text": "・" }, { "lemma": "P", "text": "P" }, { "lemma": "・", "text": "・" }, { "lemma": "ケネディ", "text": "ケネディ" }, { "lemma": "・", "text": "・" }, { "lemma": "シニア", "text": "シニア" }, { "lemma": "の", "text": "の" }, { "lemma": "次男", "text": "次男" }, { "lemma": "と", "text": "と" }, { "lemma": "する", "text": "し" }, { "lemma": "て", "text": "て" }, { "lemma": "生まれる", "text": "生まれ" }, { "lemma": "た", "text": "た" }, { "lemma": "。", "text": "。" }, { "lemma": "名前", "text": "名前" }, { "lemma": "は", "text": "は" }, { "lemma": "母方", "text": "母方" }, { "lemma": "の", "text": "の" }, { "lemma": "祖父", "text": "祖父" }, { "lemma": "で", "text": "で" }, { "lemma": "ボストン", "text": "ボストン" }, { "lemma": "市長", "text": "市長" }, { "lemma": "も", "text": "も" }, { "lemma": "勤める", "text": "勤め" }, { "lemma": "た", "text": "た" }, { "lemma": "ジョン", "text": "ジョン" }, { "lemma": "・", "text": "・" }, { "lemma": "F", "text": "F" }, { "lemma": "・", "text": "・" }, { "lemma": "フィッツジェラルド", "text": "フィッツジェラルド" }, { "lemma": "に", "text": "に" }, { "lemma": "ちなむ", "text": "ちなむ" }, { "lemma": "。", "text": "。" }, { "lemma": "13", "text": "13" }, { "lemma": "歳", "text": "歳" }, { "lemma": "の", "text": "の" }, { "lemma": "とき", "text": "とき" }, { "lemma": "に", "text": "に" }, { "lemma": "チョート", "text": "チョート" }, { "lemma": "・", "text": "・" }, { "lemma": "スクール", "text": "スクール" }, { "lemma": "（", "text": "（" }, { "lemma": "コネチカット", "text": "コネチカット" }, { "lemma": "州", "text": "州" }, { "lemma": "ウォリングフォード", "text": "ウォリングフォード" }, { "lemma": "の", "text": "の" }, { "lemma": "寄宿", "text": "寄宿" }, { "lemma": "学校", "text": "学校" }, { "lemma": "）", "text": "）" }, { "lemma": "にる", "text": "に" }, { "lemma": "入学", "text": "入学" }, { "lemma": "し", "text": "し" }, { "lemma": "、", "text": "、" }, { "lemma": "その", "text": "その" }, { "lemma": "後", "text": "後" }, { "lemma": "1935", "text": "1935" }, { "lemma": "年", "text": "年" }, { "lemma": "に", "text": "に" }, { "lemma": "イギリス", "text": "イギリス" }, { "lemma": "の", "text": "の" }, { "lemma": "ロンドン", "text": "ロンドン" }, { "lemma": "・", "text": "・" }, { "lemma": "スクール", "text": "スクール" }, { "lemma": "・", "text": "・" }, { "lemma": "オブ", "text": "オブ" }, { "lemma": "・", "text": "・" }, { "lemma": "エコノミクス", "text": "エコノミクス" }, { "lemma": "に", "text": "に" }, { "lemma": "1", "text": "1" }, { "lemma": "年間", "text": "年間" }, { "lemma": "留学", "text": "留学" }, { "lemma": "き", "text": "し" }, { "lemma": "た", "text": "た" }, { "lemma": "。", "text": "。" }, { "lemma": "帰国", "text": "帰国" }, { "lemma": "後", "text": "後" }, { "lemma": "ハーバード", "text": "ハーバード" }, { "lemma": "大学", "text": "大学" }, { "lemma": "に", "text": "に" }, { "lemma": "入学", "text": "入学" }, { "lemma": "を", "text": "を" }, { "lemma": "認める", "text": "認め" }, { "lemma": "られる", "text": "られ" }, { "lemma": "て", "text": "て" }, { "lemma": "いる", "text": "い" }, { "lemma": "た", "text": "た" }, { "lemma": "もの", "text": "もの" }, { "lemma": "の", "text": "の" }, { "lemma": "、", "text": "、" }, { "lemma": "親しい", "text": "親しい" }, { "lemma": "友人", "text": "友人" }, { "lemma": "が", "text": "が" }, { "lemma": "進学", "text": "進学" }, { "lemma": "を", "text": "を" }, { "lemma": "決める", "text": "決め" }, { "lemma": "た", "text": "た" }, { "lemma": "プリンストン", "text": "プリンストン" }, { "lemma": "大学", "text": "大学" }, { "lemma": "に", "text": "に" }, { "lemma": "入学", "text": "入学" }, { "lemma": "する", "text": "する" }, { "lemma": "こと", "text": "こと" }, { "lemma": "に", "text": "に" }, { "lemma": "する", "text": "し" }, { "lemma": "た", "text": "た" }, { "lemma": "。", "text": "。" }, { "lemma": "しかし", "text": "しかし" }, { "lemma": "、", "text": "、" }, { "lemma": "クリスマス", "text": "クリスマス" }, { "lemma": "休暇", "text": "休暇" }, { "lemma": "中", "text": "中" }, { "lemma": "に", "text": "に" }, { "lemma": "かかる", "text": "かかっ" }, { "lemma": "た", "text": "た" }, { "lemma": "黄疸", "text": "黄疸" }, { "lemma": "の", "text": "の" }, { "lemma": "ため", "text": "ため" }, { "lemma": "退学", "text": "退学" }, { "lemma": "き", "text": "し" }, { "lemma": "て", "text": "て" }, { "lemma": "いる", "text": "いる" }, { "lemma": "。", "text": "。" }, { "lemma": "1936", "text": "1936" }, { "lemma": "年", "text": "年" }, { "lemma": "の", "text": "の" }, { "lemma": "秋", "text": "秋" }, { "lemma": "に", "text": "に" }, { "lemma": "は", "text": "は" }, { "lemma": "ハーバード", "text": "ハーバード" }, { "lemma": "大学", "text": "大学" }, { "lemma": "に", "text": "に" }, { "lemma": "転校", "text": "転校" }, { "lemma": "き", "text": "し" }, { "lemma": "た", "text": "た" }, { "lemma": "が", "text": "が" }, { "lemma": "、", "text": "、" }, { "lemma": "在学", "text": "在学" }, { "lemma": "中", "text": "中" }, { "lemma": "に", "text": "に" }, { "lemma": "フットボール", "text": "フットボール" }, { "lemma": "の", "text": "の" }, { "lemma": "試合", "text": "試合" }, { "lemma": "で", "text": "で" }, { "lemma": "背中", "text": "背中" }, { "lemma": "を", "text": "を" }, { "lemma": "ひどい", "text": "ひどく" }, { "lemma": "痛む", "text": "痛め" }, { "lemma": "た", "text": "た" }, { "lemma": "。", "text": "。" }, { "lemma": "在学中", "text": "在学中" }, { "lemma": "ヨーロッパ", "text": "ヨーロッパ" }, { "lemma": "へ", "text": "へ" }, { "lemma": "2", "text": "2" }, { "lemma": "度", "text": "度" }, { "lemma": "旅行", "text": "旅行" }, { "lemma": "き", "text": "し" }, { "lemma": "て", "text": "て" }, { "lemma": "おる", "text": "おり" }, { "lemma": "、", "text": "、" }, { "lemma": "2", "text": "2" }, { "lemma": "度", "text": "度" }, { "lemma": "目", "text": "目" }, { "lemma": "の", "text": "の" }, { "lemma": "旅行", "text": "旅行" }, { "lemma": "だ", "text": "で" }, { "lemma": "は", "text": "は" }, { "lemma": "父親", "text": "父親" }, { "lemma": "が", "text": "が" }, { "lemma": "大使", "text": "大使" }, { "lemma": "を", "text": "を" }, { "lemma": "務める", "text": "務め" }, { "lemma": "て", "text": "て" }, { "lemma": "いる", "text": "い" }, { "lemma": "た", "text": "た" }, { "lemma": "イギリス", "text": "イギリス" }, { "lemma": "を", "text": "を" }, { "lemma": "訪る", "text": "訪れ" }, { "lemma": "て", "text": "て" }, { "lemma": "いる", "text": "いる" }, { "lemma": "。", "text": "。" }, { "lemma": "1940", "text": "1940" }, { "lemma": "年", "text": "年" }, { "lemma": "6", "text": "6" }, { "lemma": "月", "text": "月" }, { "lemma": "、", "text": "、" }, { "lemma": "1938", "text": "1938" }, { "lemma": "年", "text": "年" }, { "lemma": "の", "text": "の" }, { "lemma": "ミュンヘン", "text": "ミュンヘン" }, { "lemma": "協定", "text": "協定" }, { "lemma": "に", "text": "に" }, { "lemma": "おく", "text": "おけ" }, { "lemma": "り", "text": "る" }, { "lemma": "イギリス", "text": "イギリス" }, { "lemma": "外交", "text": "外交" }, { "lemma": "政策", "text": "政策" }, { "lemma": "の", "text": "の" }, { "lemma": "分析", "text": "分析" }, { "lemma": "に", "text": "に" }, { "lemma": "つぐ", "text": "つい" }, { "lemma": "て", "text": "て" }, { "lemma": "の", "text": "の" }, { "lemma": "卒論", "text": "卒論" }, { "lemma": "『", "text": "『" }, { "lemma": "イギリス", "text": "イギリス" }, { "lemma": "は", "text": "は" }, { "lemma": "なぜ", "text": "なぜ" }, { "lemma": "眠る", "text": "眠っ" }, { "lemma": "た", "text": "た" }, { "lemma": "か", "text": "か" }, { "lemma": "』", "text": "』" }, { "lemma": "を", "text": "を" }, { "lemma": "書く", "text": "書き" }, { "lemma": "、", "text": "、" }, { "lemma": "ハーバード", "text": "ハーバード" }, { "lemma": "を", "text": "を" }, { "lemma": "優等", "text": "優等" }, { "lemma": "だ", "text": "で" }, { "lemma": "卒業", "text": "卒業" }, { "lemma": "き", "text": "し" }, { "lemma": "た", "text": "た" }, { "lemma": "。", "text": "。" }, { "lemma": "第", "text": "第" }, { "lemma": "2", "text": "二" }, { "lemma": "次", "text": "次" }, { "lemma": "世界", "text": "世界" }, { "lemma": "大戦", "text": "大戦" }, { "lemma": "後", "text": "後" }, { "lemma": "、", "text": "、" }, { "lemma": "彼", "text": "彼" }, { "lemma": "は", "text": "は" }, { "lemma": "戦死", "text": "戦死" }, { "lemma": "き", "text": "し" }, { "lemma": "た", "text": "た" }, { "lemma": "兄", "text": "兄" }, { "lemma": "ジョセフ", "text": "ジョセフ" }, { "lemma": "・", "text": "・" }, { "lemma": "P", "text": "P" }, { "lemma": "・", "text": "・" }, { "lemma": "ケネディ", "text": "ケネディ" }, { "lemma": "・", "text": "・" }, { "lemma": "ジュニア", "text": "ジュニア" }, { "lemma": "に", "text": "に" }, { "lemma": "代わり", "text": "代わり" }, { "lemma": "政界", "text": "政界" }, { "lemma": "に", "text": "に" }, { "lemma": "入る", "text": "入っ" }, { "lemma": "た", "text": "た" }, { "lemma": "。", "text": "。" }, { "lemma": "1946", "text": "1946" }, { "lemma": "年", "text": "年" }, { "lemma": "に", "text": "に" }, { "lemma": "ジェームズ", "text": "ジェームズ" }, { "lemma": "・", "text": "・" }, { "lemma": "M", "text": "M" }, { "lemma": "・", "text": "・" }, { "lemma": "カー", "text": "カー" }, { "lemma": "レイ", "text": "レイ" }, { "lemma": "が", "text": "が" }, { "lemma": "ボストン", "text": "ボストン" }, { "lemma": "市長", "text": "市長" }, { "lemma": "に", "text": "に" }, { "lemma": "なる", "text": "なる" }, { "lemma": "ため", "text": "ため" }, { "lemma": "に", "text": "に" }, { "lemma": "民主", "text": "民主" }, { "lemma": "党", "text": "党" }, { "lemma": "下院", "text": "下院" }, { "lemma": "議員", "text": "議員" }, { "lemma": "を", "text": "を" }, { "lemma": "辞職", "text": "辞職" }, { "lemma": "き", "text": "し" }, { "lemma": "た", "text": "た" }, { "lemma": "時", "text": "時" }, { "lemma": "、", "text": "、" }, { "lemma": "ケネディ", "text": "ケネディ" }, { "lemma": "は", "text": "は" }, { "lemma": "その", "text": "その" }, { "lemma": "議席", "text": "議席" }, { "lemma": "を", "text": "を" }, { "lemma": "かく", "text": "かけ" }, { "lemma": "た", "text": "た" }, { "lemma": "補欠", "text": "補欠" }, { "lemma": "選挙", "text": "選挙" }, { "lemma": "に", "text": "に" }, { "lemma": "立", "text": "立" }, { "lemma": "候補", "text": "候補" }, { "lemma": "する", "text": "し" }, { "lemma": "た", "text": "た" }, { "lemma": "。", "text": "。" }, { "lemma": "父", "text": "父" }, { "lemma": "の", "text": "の" }, { "lemma": "ジョセフ", "text": "ジョセフ" }, { "lemma": "が", "text": "が" }, { "lemma": "実業", "text": "実業" }, { "lemma": "家", "text": "家" }, { "lemma": "だ", "text": "で" }, { "lemma": "ある", "text": "あっ" }, { "lemma": "た", "text": "た" }, { "lemma": "こと", "text": "こと" }, { "lemma": "も", "text": "も" }, { "lemma": "あり", "text": "あり" }, { "lemma": "、", "text": "、" }, { "lemma": "政治", "text": "政治" }, { "lemma": "資金", "text": "資金" }, { "lemma": "に", "text": "に" }, { "lemma": "は", "text": "は" }, { "lemma": "困る", "text": "困ら" }, { "lemma": "ない", "text": "なかっ" }, { "lemma": "た", "text": "た" }, { "lemma": "の", "text": "の" }, { "lemma": "だ", "text": "で" }, { "lemma": "、", "text": "、" }, { "lemma": "実現", "text": "実現" }, { "lemma": "不", "text": "不" }, { "lemma": "可能", "text": "可能" }, { "lemma": "な", "text": "な" }, { "lemma": "公約", "text": "公約" }, { "lemma": "を", "text": "を" }, { "lemma": "する", "text": "する" }, { "lemma": "必要", "text": "必要" }, { "lemma": "は", "text": "は" }, { "lemma": "ない", "text": "なく" }, { "lemma": "理想", "text": "理想" }, { "lemma": "主義", "text": "主義" }, { "lemma": "を", "text": "を" }, { "lemma": "語る", "text": "語る" }, { "lemma": "こと", "text": "こと" }, { "lemma": "が", "text": "が" }, { "lemma": "できる", "text": "でき" }, { "lemma": "た", "text": "た" }, { "lemma": "。", "text": "。" }, { "lemma": "長い", "text": "長く" }, { "lemma": "精力", "text": "精力" }, { "lemma": "的", "text": "的" }, { "lemma": "ない", "text": "な" }, { "lemma": "キャンペーン", "text": "キャンペーン" }, { "lemma": "の", "text": "の" }, { "lemma": "末", "text": "末" }, { "lemma": "に", "text": "に" }, { "lemma": "、", "text": "、" }, { "lemma": "大差", "text": "大差" }, { "lemma": "で", "text": "で" }, { "lemma": "共和", "text": "共和" }, { "lemma": "党", "text": "党" }, { "lemma": "候補", "text": "候補" }, { "lemma": "に", "text": "に" }, { "lemma": "勝つ", "text": "勝ち" }, { "lemma": "、", "text": "、" }, { "lemma": "29", "text": "29" }, { "lemma": "歳", "text": "歳" }, { "lemma": "で", "text": "で" }, { "lemma": "下院", "text": "下院" }, { "lemma": "議員", "text": "議員" }, { "lemma": "と", "text": "と" }, { "lemma": "なる", "text": "なっ" }, { "lemma": "た", "text": "た" }, { "lemma": "。", "text": "。" }, { "lemma": "当初", "text": "当初" }, { "lemma": "は", "text": "は" }, { "lemma": "父", "text": "父" }, { "lemma": "の", "text": "の" }, { "lemma": "ジョセフ", "text": "ジョセフ" }, { "lemma": "と", "text": "と" }, { "lemma": "コネ", "text": "コネ" }, { "lemma": "が", "text": "が" }, { "lemma": "ある", "text": "あっ" }, { "lemma": "た", "text": "た" }, { "lemma": "同じ", "text": "同じ" }, { "lemma": "アイルランド", "text": "アイルランド" }, { "lemma": "系", "text": "系" }, { "lemma": "の", "text": "の" }, { "lemma": "ジョセフ", "text": "ジョセフ" }, { "lemma": "・", "text": "・" }, { "lemma": "マッカーシー", "text": "マッカーシー" }, { "lemma": "上院", "text": "上院" }, { "lemma": "議員", "text": "議員" }, { "lemma": "の", "text": "の" }, { "lemma": "赤狩り", "text": "赤狩り" }, { "lemma": "にる", "text": "に" }, { "lemma": "協力", "text": "協力" }, { "lemma": "き", "text": "し" }, { "lemma": "て", "text": "て" }, { "lemma": "いる", "text": "い" }, { "lemma": "た", "text": "た" }, { "lemma": "。", "text": "。" }, { "lemma": "リベラル", "text": "リベラル" }, { "lemma": "派", "text": "派" }, { "lemma": "の", "text": "の" }, { "lemma": "エレノア", "text": "エレノア" }, { "lemma": "・", "text": "・" }, { "lemma": "ルーズヴェルト", "text": "ルーズヴェルト" }, { "lemma": "は", "text": "は" }, { "lemma": "その", "text": "その" }, { "lemma": "こと", "text": "こと" }, { "lemma": "を", "text": "を" }, { "lemma": "忘れる", "text": "忘れ" }, { "lemma": "ぬ", "text": "ず" }, { "lemma": "、", "text": "、" }, { "lemma": "後々", "text": "後々" }, { "lemma": "まで", "text": "まで" }, { "lemma": "ケネディ", "text": "ケネディ" }, { "lemma": "を", "text": "を" }, { "lemma": "嫌う", "text": "嫌っ" }, { "lemma": "て", "text": "て" }, { "lemma": "いる", "text": "い" }, { "lemma": "た", "text": "た" }, { "lemma": "。", "text": "。" }, { "lemma": "下院", "text": "下院" }, { "lemma": "3", "text": "3" }, { "lemma": "期", "text": "期" }, { "lemma": "目", "text": "目" }, { "lemma": "の", "text": "の" }, { "lemma": "1952", "text": "1952" }, { "lemma": "年", "text": "年" }, { "lemma": "に", "text": "に" }, { "lemma": "は", "text": "は" }, { "lemma": "上院", "text": "上院" }, { "lemma": "議員", "text": "議員" }, { "lemma": "選挙", "text": "選挙" }, { "lemma": "にる", "text": "に" }, { "lemma": "出馬", "text": "出馬" }, { "lemma": "し", "text": "し" }, { "lemma": "、", "text": "、" }, { "lemma": "約", "text": "約" }, { "lemma": "70000", "text": "70,000" }, { "lemma": "票", "text": "票" }, { "lemma": "の", "text": "の" }, { "lemma": "大差", "text": "大差" }, { "lemma": "で", "text": "で" }, { "lemma": "共和", "text": "共和" }, { "lemma": "党", "text": "党" }, { "lemma": "候補", "text": "候補" }, { "lemma": "ヘンリー", "text": "ヘンリー" }, { "lemma": "・", "text": "・" }, { "lemma": "カボット", "text": "カボット" }, { "lemma": "・", "text": "・" }, { "lemma": "ロッジ", "text": "ロッジ" }, { "lemma": "・", "text": "・" }, { "lemma": "ジュニア", "text": "ジュニア" }, { "lemma": "を", "text": "を" }, { "lemma": "破る", "text": "破っ" }, { "lemma": "た", "text": "た" }, { "lemma": "。", "text": "。" }, { "lemma": "以後", "text": "以後" }, { "lemma": "の", "text": "の" }, { "lemma": "彼", "text": "彼" }, { "lemma": "の", "text": "の" }, { "lemma": "支持", "text": "支持" }, { "lemma": "基盤", "text": "基盤" }, { "lemma": "は", "text": "は" }, { "lemma": "北部", "text": "北部" }, { "lemma": "都市", "text": "都市" }, { "lemma": "圏", "text": "圏" }, { "lemma": "の", "text": "の" }, { "lemma": "リベラル", "text": "リベラル" }, { "lemma": "派", "text": "派" }, { "lemma": "インテリ", "text": "インテリ" }, { "lemma": "層", "text": "層" }, { "lemma": "と", "text": "と" }, { "lemma": "なる", "text": "なる" }, { "lemma": "。", "text": "。" }, { "lemma": "ケ", "text": "ケ" }, { "lemma": "ネディ", "text": "ネディ" }, { "lemma": "は", "text": "は" }, { "lemma": "1953", "text": "1953" }, { "lemma": "年", "text": "年" }, { "lemma": "9", "text": "9" }, { "lemma": "月", "text": "月" }, { "lemma": "12", "text": "12" }, { "lemma": "日", "text": "日" }, { "lemma": "に", "text": "に" }, { "lemma": "フランス", "text": "フランス" }, { "lemma": "系", "text": "系" }, { "lemma": "移民", "text": "移民" }, { "lemma": "の", "text": "の" }, { "lemma": "名門", "text": "名門" }, { "lemma": "の", "text": "の" }, { "lemma": "娘", "text": "娘" }, { "lemma": "だ", "text": "で" }, { "lemma": "ある", "text": "ある" }, { "lemma": "ジャクリーン", "text": "ジャクリーン" }, { "lemma": "・", "text": "・" }, { "lemma": "リー", "text": "リー" }, { "lemma": "・", "text": "・" }, { "lemma": "ブーヴィエ", "text": "ブーヴィエ" }, { "lemma": "と", "text": "と" }, { "lemma": "結婚", "text": "結婚" }, { "lemma": "す", "text": "し" }, { "lemma": "た", "text": "た" }, { "lemma": "。", "text": "。" }, { "lemma": "彼", "text": "彼" }, { "lemma": "は", "text": "は" }, { "lemma": "その", "text": "その" }, { "lemma": "後", "text": "後" }, { "lemma": "2", "text": "2" }, { "lemma": "年間", "text": "年間" }, { "lemma": "に", "text": "に" }, { "lemma": "多数", "text": "多数" }, { "lemma": "回", "text": "回" }, { "lemma": "の", "text": "の" }, { "lemma": "脊柱", "text": "脊柱" }, { "lemma": "の", "text": "の" }, { "lemma": "手術", "text": "手術" }, { "lemma": "を", "text": "を" }, { "lemma": "受け上院", "text": "受け上院" }, { "lemma": "本", "text": "本" }, { "lemma": "会議", "text": "会議" }, { "lemma": "を", "text": "を" }, { "lemma": "長期", "text": "長期" }, { "lemma": "に", "text": "に" }, { "lemma": "わたる", "text": "わたっ" }, { "lemma": "つ", "text": "て" }, { "lemma": "欠席", "text": "欠席" }, { "lemma": "き", "text": "し" }, { "lemma": "た", "text": "た" }, { "lemma": "が", "text": "が" }, { "lemma": "、", "text": "、" }, { "lemma": "手術", "text": "手術" }, { "lemma": "からい", "text": "から" }, { "lemma": "回復", "text": "回復" }, { "lemma": "する", "text": "する" }, { "lemma": "まで", "text": "まで" }, { "lemma": "の", "text": "の" }, { "lemma": "間", "text": "間" }, { "lemma": "、", "text": "、" }, { "lemma": "8", "text": "8" }, { "lemma": "名", "text": "名" }, { "lemma": "の", "text": "の" }, { "lemma": "上院", "text": "上院" }, { "lemma": "議員", "text": "議員" }, { "lemma": "の", "text": "の" }, { "lemma": "政治", "text": "政治" }, { "lemma": "的", "text": "的" }, { "lemma": "に", "text": "に" }, { "lemma": "勇敢", "text": "勇敢" }, { "lemma": "だ", "text": "で" }, { "lemma": "ある", "text": "あっ" }, { "lemma": "た", "text": "た" }, { "lemma": "行為", "text": "行為" }, { "lemma": "に", "text": "に" }, { "lemma": "つぐ", "text": "つい" }, { "lemma": "て", "text": "て" }, { "lemma": "の", "text": "の" }, { "lemma": "本", "text": "本" }, { "lemma": "『", "text": "『" }, { "lemma": "勇気", "text": "勇気" }, { "lemma": "ある", "text": "ある" }, { "lemma": "人々", "text": "人々" }, { "lemma": "』", "text": "』" }, { "lemma": "を", "text": "を" }, { "lemma": "出版", "text": "出版" }, { "lemma": "き", "text": "し" }, { "lemma": "た", "text": "た" }, { "lemma": "。", "text": "。" }, { "lemma": "この", "text": "この" }, { "lemma": "本", "text": "本" }, { "lemma": "は", "text": "は" }, { "lemma": "その", "text": "その" }, { "lemma": "後", "text": "後" }, { "lemma": "ピューリツァー", "text": "ピューリツァー" }, { "lemma": "賞", "text": "賞" }, { "lemma": "を", "text": "を" }, { "lemma": "受賞", "text": "受賞" }, { "lemma": "き", "text": "し" }, { "lemma": "た", "text": "た" }, { "lemma": "。", "text": "。" }, { "lemma": "賞金", "text": "賞金" }, { "lemma": "は", "text": "は" }, { "lemma": "黒人", "text": "黒人" }, { "lemma": "の", "text": "の" }, { "lemma": "通う", "text": "通う" }, { "lemma": "学校", "text": "学校" }, { "lemma": "へ", "text": "へ" }, { "lemma": "寄付る", "text": "寄付" }, { "lemma": "する", "text": "し" }, { "lemma": "た", "text": "た" }, { "lemma": "と", "text": "と" }, { "lemma": "言う", "text": "言わ" }, { "lemma": "る", "text": "れ" }, { "lemma": "て", "text": "て" }, { "lemma": "いる", "text": "いる" }, { "lemma": "。", "text": "。" }, { "lemma": "http", "text": "http" }, { "lemma": ":", "text": ":" }, { "lemma": "/", "text": "/" }, { "lemma": "/", "text": "/" }, { "lemma": "ja.wikipedia.org", "text": "ja.wikipedia.org" }, { "lemma": "/", "text": "/" }, { "lemma": "wiki", "text": "wiki" }, { "lemma": "/", "text": "/" }, { "lemma": "%", "text": "%" }, { "lemma": "E3", "text": "E3" }, { "lemma": "%", "text": "%" }, { "lemma": "82", "text": "82" }, { "lemma": "%", "text": "%" }, { "lemma": "B8", "text": "B8" }, { "lemma": "%", "text": "%" }, { "lemma": "E3", "text": "E3" }, { "lemma": "%", "text": "%" }, { "lemma": "83", "text": "83" }, { "lemma": "%", "text": "%" }, { "lemma": "A7", "text": "A7" }, { "lemma": "%", "text": "%" }, { "lemma": "E3", "text": "E3" }, { "lemma": "%", "text": "%" }, { "lemma": "83", "text": "83" }, { "lemma": "%", "text": "%" }, { "lemma": "B3", "text": "B3" }, { "lemma": "%", "text": "%" }, { "lemma": "E3", "text": "E3" }, { "lemma": "%", "text": "%" }, { "lemma": "83", "text": "83" }, { "lemma": "%", "text": "%" }, { "lemma": "BBF", "text": "BBF" }, { "lemma": "%", "text": "%" }, { "lemma": "E3", "text": "E3" }, { "lemma": "%", "text": "%" }, { "lemma": "83", "text": "83" }, { "lemma": "%", "text": "%" }, { "lemma": "BB", "text": "BB" }, { "lemma": "%", "text": "%" }, { "lemma": "E3", "text": "E3" }, { "lemma": "%", "text": "%" }, { "lemma": "82", "text": "82" }, { "lemma": "%", "text": "%" }, { "lemma": "B1", "text": "B1" }, { "lemma": "%", "text": "%" }, { "lemma": "E3", "text": "E3" }, { "lemma": "%", "text": "%" }, { "lemma": "83", "text": "83" }, { "lemma": "%", "text": "%" }, { "lemma": "8D", "text": "8D" }, { "lemma": "%", "text": "%" }, { "lemma": "E3", "text": "E3" }, { "lemma": "%", "text": "%" }, { "lemma": "83", "text": "83" }, { "lemma": "%", "text": "%" }, { "lemma": "87", "text": "87" }, { "lemma": "%", "text": "%" }, { "lemma": "E3", "text": "E3" }, { "lemma": "%", "text": "%" }, { "lemma": "82", "text": "82" }, { "lemma": "%", "text": "%" }, { "lemma": "A3", "text": "A3" }, { "lemma": "2010.01.26", "text": "2010.01.26" } ], "posTags": [ { "pos": "GUESS", "text": "ケ" }, { "pos": "GUESS", "text": "ネディ" }, { "pos": "PL", "text": "は" }, { "pos": "NP", "text": "マサチューセッツ" }, { "pos": "NC", "text": "州" }, { "pos": "GUESS", "text": "ブルックライン" }, { "pos": "PL", "text": "で" }, { "pos": "PUNCT", "text": "、" }, { "pos": "NP", "text": "アイルランド" }, { "pos": "WS", "text": "系" }, { "pos": "VN", "text": "移民" }, { "pos": "PL", "text": "の" }, { "pos": "NC", "text": "子孫" }, { "pos": "J", "text": "で" }, { "pos": "VN", "text": "投資" }, { "pos": "WS", "text": "家" }, { "pos": "PL", "text": "の" }, { "pos": "NP", "text": "ジョセフ" }, { "pos": "PUNCT", "text": "・" }, { "pos": "NP", "text": "P" }, { "pos": "PUNCT", "text": "・" }, { "pos": "NP", "text": "ケネディ" }, { "pos": "PUNCT", "text": "・" }, { "pos": "NC", "text": "シニア" }, { "pos": "PL", "text": "の" }, { "pos": "NC", "text": "次男" }, { "pos": "PL", "text": "と" }, { "pos": "V", "text": "し" }, { "pos": "PL", "text": "て" }, { "pos": "V", "text": "生まれ" }, { "pos": "AUXVB", "text": "た" }, { "pos": "PUNCT", "text": "。" }, { "pos": "NC", "text": "名前" }, { "pos": "PL", "text": "は" }, { "pos": "NC", "text": "母方" }, { "pos": "PL", "text": "の" }, { "pos": "NC", "text": "祖父" }, { "pos": "PL", "text": "で" }, { "pos": "NP", "text": "ボストン" }, { "pos": "NC", "text": "市長" }, { "pos": "PL", "text": "も" }, { "pos": "V", "text": "勤め" }, { "pos": "AUXVB", "text": "た" }, { "pos": "NP", "text": "ジョン" }, { "pos": "PUNCT", "text": "・" }, { "pos": "NU", "text": "F" }, { "pos": "PUNCT", "text": "・" }, { "pos": "GUESS", "text": "フィッツジェラルド" }, { "pos": "PL", "text": "に" }, { "pos": "V", "text": "ちなむ" }, { "pos": "PUNCT", "text": "。" }, { "pos": "GUESS", "text": "13" }, { "pos": "NC", "text": "歳" }, { "pos": "PL", "text": "の" }, { "pos": "NC", "text": "とき" }, { "pos": "PL", "text": "に" }, { "pos": "GUESS", "text": "チョート" }, { "pos": "PUNCT", "text": "・" }, { "pos": "NC", "text": "スクール" }, { "pos": "GUESS", "text": "（" }, { "pos": "GUESS", "text": "コネチカット" }, { "pos": "NC", "text": "州" }, { "pos": "GUESS", "text": "ウォリングフォード" }, { "pos": "PL", "text": "の" }, { "pos": "VN", "text": "寄宿" }, { "pos": "NC", "text": "学校" }, { "pos": "GUESS", "text": "）" }, { "pos": "V", "text": "に" }, { "pos": "VN", "text": "入学" }, { "pos": "PL", "text": "し" }, { "pos": "PUNCT", "text": "、" }, { "pos": "I", "text": "その" }, { "pos": "NC", "text": "後" }, { "pos": "GUESS", "text": "1935" }, { "pos": "NC", "text": "年" }, { "pos": "PL", "text": "に" }, { "pos": "NP", "text": "イギリス" }, { "pos": "PL", "text": "の" }, { "pos": "NP", "text": "ロンドン" }, { "pos": "PUNCT", "text": "・" }, { "pos": "NC", "text": "スクール" }, { "pos": "PUNCT", "text": "・" }, { "pos": "NC", "text": "オブ" }, { "pos": "PUNCT", "text": "・" }, { "pos": "GUESS", "text": "エコノミクス" }, { "pos": "PL", "text": "に" }, { "pos": "GUESS", "text": "1" }, { "pos": "NU", "text": "年間" }, { "pos": "VN", "text": "留学" }, { "pos": "AUXVB", "text": "し" }, { "pos": "AUXVB", "text": "た" }, { "pos": "PUNCT", "text": "。" }, { "pos": "VN", "text": "帰国" }, { "pos": "WP", "text": "後" }, { "pos": "NP", "text": "ハーバード" }, { "pos": "NC", "text": "大学" }, { "pos": "PL", "text": "に" }, { "pos": "VN", "text": "入学" }, { "pos": "PL", "text": "を" }, { "pos": "V", "text": "認め" }, { "pos": "FS", "text": "られ" }, { "pos": "PL", "text": "て" }, { "pos": "V", "text": "い" }, { "pos": "AUXVB", "text": "た" }, { "pos": "NC", "text": "もの" }, { "pos": "PL", "text": "の" }, { "pos": "PUNCT", "text": "、" }, { "pos": "AJ", "text": "親しい" }, { "pos": "NC", "text": "友人" }, { "pos": "J", "text": "が" }, { "pos": "VN", "text": "進学" }, { "pos": "PL", "text": "を" }, { "pos": "V", "text": "決め" }, { "pos": "AUXVB", "text": "た" }, { "pos": "NP", "text": "プリンストン" }, { "pos": "NC", "text": "大学" }, { "pos": "PL", "text": "に" }, { "pos": "VN", "text": "入学" }, { "pos": "V", "text": "する" }, { "pos": "NC", "text": "こと" }, { "pos": "PL", "text": "に" }, { "pos": "V", "text": "し" }, { "pos": "AUXVB", "text": "た" }, { "pos": "PUNCT", "text": "。" }, { "pos": "J", "text": "しかし" }, { "pos": "PUNCT", "text": "、" }, { "pos": "NC", "text": "クリスマス" }, { "pos": "NC", "text": "休暇" }, { "pos": "NC", "text": "中" }, { "pos": "PL", "text": "に" }, { "pos": "V", "text": "かかっ" }, { "pos": "AUXVB", "text": "た" }, { "pos": "NC", "text": "黄疸" }, { "pos": "PL", "text": "の" }, { "pos": "NC", "text": "ため" }, { "pos": "VN", "text": "退学" }, { "pos": "AUXVB", "text": "し" }, { "pos": "PL", "text": "て" }, { "pos": "V", "text": "いる" }, { "pos": "PUNCT", "text": "。" }, { "pos": "GUESS", "text": "1936" }, { "pos": "NC", "text": "年" }, { "pos": "PL", "text": "の" }, { "pos": "NC", "text": "秋" }, { "pos": "PL", "text": "に" }, { "pos": "PL", "text": "は" }, { "pos": "NP", "text": "ハーバード" }, { "pos": "NC", "text": "大学" }, { "pos": "PL", "text": "に" }, { "pos": "VN", "text": "転校" }, { "pos": "AUXVB", "text": "し" }, { "pos": "AUXVB", "text": "た" }, { "pos": "PL", "text": "が" }, { "pos": "PUNCT", "text": "、" }, { "pos": "VN", "text": "在学" }, { "pos": "NP", "text": "中" }, { "pos": "PL", "text": "に" }, { "pos": "NC", "text": "フットボール" }, { "pos": "PL", "text": "の" }, { "pos": "VN", "text": "試合" }, { "pos": "PL", "text": "で" }, { "pos": "NC", "text": "背中" }, { "pos": "PL", "text": "を" }, { "pos": "AJ", "text": "ひどく" }, { "pos": "V", "text": "痛め" }, { "pos": "AUXVB", "text": "た" }, { "pos": "PUNCT", "text": "。" }, { "pos": "GUESS", "text": "在学中" }, { "pos": "NP", "text": "ヨーロッパ" }, { "pos": "PL", "text": "へ" }, { "pos": "GUESS", "text": "2" }, { "pos": "NU", "text": "度" }, { "pos": "VN", "text": "旅行" }, { "pos": "AUXVB", "text": "し" }, { "pos": "PL", "text": "て" }, { "pos": "V", "text": "おり" }, { "pos": "PUNCT", "text": "、" }, { "pos": "GUESS", "text": "2" }, { "pos": "NC", "text": "度" }, { "pos": "WS", "text": "目" }, { "pos": "PL", "text": "の" }, { "pos": "VN", "text": "旅行" }, { "pos": "AUXVB", "text": "で" }, { "pos": "PL", "text": "は" }, { "pos": "NC", "text": "父親" }, { "pos": "PL", "text": "が" }, { "pos": "NC", "text": "大使" }, { "pos": "PL", "text": "を" }, { "pos": "V", "text": "務め" }, { "pos": "PL", "text": "て" }, { "pos": "V", "text": "い" }, { "pos": "AUXVB", "text": "た" }, { "pos": "NP", "text": "イギリス" }, { "pos": "PL", "text": "を" }, { "pos": "V", "text": "訪れ" }, { "pos": "PL", "text": "て" }, { "pos": "V", "text": "いる" }, { "pos": "PUNCT", "text": "。" }, { "pos": "GUESS", "text": "1940" }, { "pos": "NC", "text": "年" }, { "pos": "GUESS", "text": "6" }, { "pos": "NC", "text": "月" }, { "pos": "PUNCT", "text": "、" }, { "pos": "GUESS", "text": "1938" }, { "pos": "NC", "text": "年" }, { "pos": "PL", "text": "の" }, { "pos": "NP", "text": "ミュンヘン" }, { "pos": "VN", "text": "協定" }, { "pos": "PL", "text": "に" }, { "pos": "V", "text": "おけ" }, { "pos": "AUXVB", "text": "る" }, { "pos": "NP", "text": "イギリス" }, { "pos": "NC", "text": "外交" }, { "pos": "NC", "text": "政策" }, { "pos": "PL", "text": "の" }, { "pos": "VN", "text": "分析" }, { "pos": "PL", "text": "に" }, { "pos": "V", "text": "つい" }, { "pos": "PL", "text": "て" }, { "pos": "PL", "text": "の" }, { "pos": "NC", "text": "卒論" }, { "pos": "PUNCT", "text": "『" }, { "pos": "NP", "text": "イギリス" }, { "pos": "PL", "text": "は" }, { "pos": "D", "text": "なぜ" }, { "pos": "V", "text": "眠っ" }, { "pos": "AUXVB", "text": "た" }, { "pos": "PL", "text": "か" }, { "pos": "PUNCT", "text": "』" }, { "pos": "PL", "text": "を" }, { "pos": "V", "text": "書き" }, { "pos": "PUNCT", "text": "、" }, { "pos": "NP", "text": "ハーバード" }, { "pos": "PL", "text": "を" }, { "pos": "NC", "text": "優等" }, { "pos": "AUXVB", "text": "で" }, { "pos": "VN", "text": "卒業" }, { "pos": "AUXVB", "text": "し" }, { "pos": "AUXVB", "text": "た" }, { "pos": "PUNCT", "text": "。" }, { "pos": "WP", "text": "第" }, { "pos": "NN", "text": "二" }, { "pos": "WS", "text": "次" }, { "pos": "NC", "text": "世界" }, { "pos": "NC", "text": "大戦" }, { "pos": "NC", "text": "後" }, { "pos": "PUNCT", "text": "、" }, { "pos": "NR", "text": "彼" }, { "pos": "PL", "text": "は" }, { "pos": "VN", "text": "戦死" }, { "pos": "AUXVB", "text": "し" }, { "pos": "AUXVB", "text": "た" }, { "pos": "NC", "text": "兄" }, { "pos": "NP", "text": "ジョセフ" }, { "pos": "PUNCT", "text": "・" }, { "pos": "NP", "text": "P" }, { "pos": "PUNCT", "text": "・" }, { "pos": "NP", "text": "ケネディ" }, { "pos": "PUNCT", "text": "・" }, { "pos": "NC", "text": "ジュニア" }, { "pos": "PL", "text": "に" }, { "pos": "NC", "text": "代わり" }, { "pos": "NC", "text": "政界" }, { "pos": "PL", "text": "に" }, { "pos": "V", "text": "入っ" }, { "pos": "AUXVB", "text": "た" }, { "pos": "PUNCT", "text": "。" }, { "pos": "GUESS", "text": "1946" }, { "pos": "NC", "text": "年" }, { "pos": "PL", "text": "に" }, { "pos": "NP", "text": "ジェームズ" }, { "pos": "PUNCT", "text": "・" }, { "pos": "NU", "text": "M" }, { "pos": "PUNCT", "text": "・" }, { "pos": "NC", "text": "カー" }, { "pos": "NC", "text": "レイ" }, { "pos": "PL", "text": "が" }, { "pos": "NP", "text": "ボストン" }, { "pos": "NC", "text": "市長" }, { "pos": "PL", "text": "に" }, { "pos": "V", "text": "なる" }, { "pos": "NC", "text": "ため" }, { "pos": "PL", "text": "に" }, { "pos": "NC", "text": "民主" }, { "pos": "WS", "text": "党" }, { "pos": "NP", "text": "下院" }, { "pos": "NC", "text": "議員" }, { "pos": "PL", "text": "を" }, { "pos": "VN", "text": "辞職" }, { "pos": "AUXVB", "text": "し" }, { "pos": "AUXVB", "text": "た" }, { "pos": "NC", "text": "時" }, { "pos": "PUNCT", "text": "、" }, { "pos": "NP", "text": "ケネディ" }, { "pos": "PL", "text": "は" }, { "pos": "I", "text": "その" }, { "pos": "NC", "text": "議席" }, { "pos": "PL", "text": "を" }, { "pos": "V", "text": "かけ" }, { "pos": "AUXVB", "text": "た" }, { "pos": "NC", "text": "補欠" }, { "pos": "VN", "text": "選挙" }, { "pos": "PL", "text": "に" }, { "pos": "WP", "text": "立" }, { "pos": "NC", "text": "候補" }, { "pos": "V", "text": "し" }, { "pos": "AUXVB", "text": "た" }, { "pos": "PUNCT", "text": "。" }, { "pos": "NC", "text": "父" }, { "pos": "PL", "text": "の" }, { "pos": "NP", "text": "ジョセフ" }, { "pos": "PL", "text": "が" }, { "pos": "NC", "text": "実業" }, { "pos": "WS", "text": "家" }, { "pos": "AUXVB", "text": "で" }, { "pos": "V", "text": "あっ" }, { "pos": "AUXVB", "text": "た" }, { "pos": "NC", "text": "こと" }, { "pos": "PL", "text": "も" }, { "pos": "V", "text": "あり" }, { "pos": "PUNCT", "text": "、" }, { "pos": "NC", "text": "政治" }, { "pos": "NC", "text": "資金" }, { "pos": "PL", "text": "に" }, { "pos": "PL", "text": "は" }, { "pos": "V", "text": "困ら" }, { "pos": "AUXVB", "text": "なかっ" }, { "pos": "AUXVB", "text": "た" }, { "pos": "PL", "text": "の" }, { "pos": "AUXVB", "text": "で" }, { "pos": "PUNCT", "text": "、" }, { "pos": "VN", "text": "実現" }, { "pos": "WP", "text": "不" }, { "pos": "AN", "text": "可能" }, { "pos": "I", "text": "な" }, { "pos": "VN", "text": "公約" }, { "pos": "PL", "text": "を" }, { "pos": "V", "text": "する" }, { "pos": "AN", "text": "必要" }, { "pos": "PL", "text": "は" }, { "pos": "AJ", "text": "なく" }, { "pos": "NC", "text": "理想" }, { "pos": "NC", "text": "主義" }, { "pos": "PL", "text": "を" }, { "pos": "V", "text": "語る" }, { "pos": "NC", "text": "こと" }, { "pos": "PL", "text": "が" }, { "pos": "V", "text": "でき" }, { "pos": "AUXVB", "text": "た" }, { "pos": "PUNCT", "text": "。" }, { "pos": "AJ", "text": "長く" }, { "pos": "NC", "text": "精力" }, { "pos": "WS", "text": "的" }, { "pos": "AUXVB", "text": "な" }, { "pos": "NC", "text": "キャンペーン" }, { "pos": "PL", "text": "の" }, { "pos": "NC", "text": "末" }, { "pos": "PL", "text": "に" }, { "pos": "PUNCT", "text": "、" }, { "pos": "NC", "text": "大差" }, { "pos": "PL", "text": "で" }, { "pos": "NC", "text": "共和" }, { "pos": "WS", "text": "党" }, { "pos": "NC", "text": "候補" }, { "pos": "PL", "text": "に" }, { "pos": "V", "text": "勝ち" }, { "pos": "PUNCT", "text": "、" }, { "pos": "GUESS", "text": "29" }, { "pos": "NC", "text": "歳" }, { "pos": "PL", "text": "で" }, { "pos": "NP", "text": "下院" }, { "pos": "NC", "text": "議員" }, { "pos": "PL", "text": "と" }, { "pos": "V", "text": "なっ" }, { "pos": "AUXVB", "text": "た" }, { "pos": "PUNCT", "text": "。" }, { "pos": "NC", "text": "当初" }, { "pos": "PL", "text": "は" }, { "pos": "NC", "text": "父" }, { "pos": "PL", "text": "の" }, { "pos": "NP", "text": "ジョセフ" }, { "pos": "PL", "text": "と" }, { "pos": "NC", "text": "コネ" }, { "pos": "PL", "text": "が" }, { "pos": "V", "text": "あっ" }, { "pos": "AUXVB", "text": "た" }, { "pos": "AN", "text": "同じ" }, { "pos": "NP", "text": "アイルランド" }, { "pos": "WS", "text": "系" }, { "pos": "PL", "text": "の" }, { "pos": "NP", "text": "ジョセフ" }, { "pos": "PUNCT", "text": "・" }, { "pos": "NP", "text": "マッカーシー" }, { "pos": "NP", "text": "上院" }, { "pos": "NC", "text": "議員" }, { "pos": "PL", "text": "の" }, { "pos": "NC", "text": "赤狩り" }, { "pos": "V", "text": "に" }, { "pos": "VN", "text": "協力" }, { "pos": "AUXVB", "text": "し" }, { "pos": "PL", "text": "て" }, { "pos": "V", "text": "い" }, { "pos": "AUXVB", "text": "た" }, { "pos": "PUNCT", "text": "。" }, { "pos": "AN", "text": "リベラル" }, { "pos": "WS", "text": "派" }, { "pos": "PL", "text": "の" }, { "pos": "GUESS", "text": "エレノア" }, { "pos": "PUNCT", "text": "・" }, { "pos": "GUESS", "text": "ルーズヴェルト" }, { "pos": "PL", "text": "は" }, { "pos": "I", "text": "その" }, { "pos": "NC", "text": "こと" }, { "pos": "PL", "text": "を" }, { "pos": "V", "text": "忘れ" }, { "pos": "AUXVB", "text": "ず" }, { "pos": "PUNCT", "text": "、" }, { "pos": "NC", "text": "後々" }, { "pos": "PL", "text": "まで" }, { "pos": "NP", "text": "ケネディ" }, { "pos": "PL", "text": "を" }, { "pos": "V", "text": "嫌っ" }, { "pos": "PL", "text": "て" }, { "pos": "V", "text": "い" }, { "pos": "AUXVB", "text": "た" }, { "pos": "PUNCT", "text": "。" }, { "pos": "NP", "text": "下院" }, { "pos": "GUESS", "text": "3" }, { "pos": "NC", "text": "期" }, { "pos": "WS", "text": "目" }, { "pos": "PL", "text": "の" }, { "pos": "GUESS", "text": "1952" }, { "pos": "NC", "text": "年" }, { "pos": "PL", "text": "に" }, { "pos": "PL", "text": "は" }, { "pos": "NP", "text": "上院" }, { "pos": "NC", "text": "議員" }, { "pos": "VN", "text": "選挙" }, { "pos": "V", "text": "に" }, { "pos": "VN", "text": "出馬" }, { "pos": "PL", "text": "し" }, { "pos": "PUNCT", "text": "、" }, { "pos": "WP", "text": "約" }, { "pos": "GUESS", "text": "70,000" }, { "pos": "NC", "text": "票" }, { "pos": "PL", "text": "の" }, { "pos": "NC", "text": "大差" }, { "pos": "PL", "text": "で" }, { "pos": "NC", "text": "共和" }, { "pos": "WS", "text": "党" }, { "pos": "NC", "text": "候補" }, { "pos": "NP", "text": "ヘンリー" }, { "pos": "PUNCT", "text": "・" }, { "pos": "GUESS", "text": "カボット" }, { "pos": "NN", "text": "・" }, { "pos": "NC", "text": "ロッジ" }, { "pos": "PUNCT", "text": "・" }, { "pos": "NC", "text": "ジュニア" }, { "pos": "PL", "text": "を" }, { "pos": "V", "text": "破っ" }, { "pos": "AUXVB", "text": "た" }, { "pos": "PUNCT", "text": "。" }, { "pos": "NC", "text": "以後" }, { "pos": "PL", "text": "の" }, { "pos": "NR", "text": "彼" }, { "pos": "PL", "text": "の" }, { "pos": "VN", "text": "支持" }, { "pos": "NC", "text": "基盤" }, { "pos": "PL", "text": "は" }, { "pos": "NC", "text": "北部" }, { "pos": "NC", "text": "都市" }, { "pos": "WS", "text": "圏" }, { "pos": "PL", "text": "の" }, { "pos": "AN", "text": "リベラル" }, { "pos": "WS", "text": "派" }, { "pos": "NC", "text": "インテリ" }, { "pos": "NC", "text": "層" }, { "pos": "PL", "text": "と" }, { "pos": "V", "text": "なる" }, { "pos": "PUNCT", "text": "。" }, { "pos": "GUESS", "text": "ケ" }, { "pos": "GUESS", "text": "ネディ" }, { "pos": "PL", "text": "は" }, { "pos": "GUESS", "text": "1953" }, { "pos": "NC", "text": "年" }, { "pos": "GUESS", "text": "9" }, { "pos": "NC", "text": "月" }, { "pos": "GUESS", "text": "12" }, { "pos": "NC", "text": "日" }, { "pos": "PL", "text": "に" }, { "pos": "NP", "text": "フランス" }, { "pos": "WS", "text": "系" }, { "pos": "VN", "text": "移民" }, { "pos": "PL", "text": "の" }, { "pos": "NC", "text": "名門" }, { "pos": "PL", "text": "の" }, { "pos": "NC", "text": "娘" }, { "pos": "AUXVB", "text": "で" }, { "pos": "V", "text": "ある" }, { "pos": "GUESS", "text": "ジャクリーン" }, { "pos": "PUNCT", "text": "・" }, { "pos": "NP", "text": "リー" }, { "pos": "PUNCT", "text": "・" }, { "pos": "GUESS", "text": "ブーヴィエ" }, { "pos": "PL", "text": "と" }, { "pos": "VN", "text": "結婚" }, { "pos": "FS", "text": "し" }, { "pos": "AUXVB", "text": "た" }, { "pos": "PUNCT", "text": "。" }, { "pos": "NR", "text": "彼" }, { "pos": "PL", "text": "は" }, { "pos": "I", "text": "その" }, { "pos": "NC", "text": "後" }, { "pos": "GUESS", "text": "2" }, { "pos": "NC", "text": "年間" }, { "pos": "PL", "text": "に" }, { "pos": "NC", "text": "多数" }, { "pos": "NC", "text": "回" }, { "pos": "PL", "text": "の" }, { "pos": "NC", "text": "脊柱" }, { "pos": "PL", "text": "の" }, { "pos": "VN", "text": "手術" }, { "pos": "PL", "text": "を" }, { "pos": "GUESS", "text": "受け上院" }, { "pos": "NU", "text": "本" }, { "pos": "VN", "text": "会議" }, { "pos": "PL", "text": "を" }, { "pos": "NC", "text": "長期" }, { "pos": "PL", "text": "に" }, { "pos": "V", "text": "わたっ" }, { "pos": "AUXVB", "text": "て" }, { "pos": "VN", "text": "欠席" }, { "pos": "AUXVB", "text": "し" }, { "pos": "AUXVB", "text": "た" }, { "pos": "PL", "text": "が" }, { "pos": "PUNCT", "text": "、" }, { "pos": "VN", "text": "手術" }, { "pos": "AJ", "text": "から" }, { "pos": "VN", "text": "回復" }, { "pos": "V", "text": "する" }, { "pos": "PL", "text": "まで" }, { "pos": "PL", "text": "の" }, { "pos": "NC", "text": "間" }, { "pos": "PUNCT", "text": "、" }, { "pos": "GUESS", "text": "8" }, { "pos": "NC", "text": "名" }, { "pos": "PL", "text": "の" }, { "pos": "NP", "text": "上院" }, { "pos": "NC", "text": "議員" }, { "pos": "PL", "text": "の" }, { "pos": "NC", "text": "政治" }, { "pos": "WS", "text": "的" }, { "pos": "PL", "text": "に" }, { "pos": "NC", "text": "勇敢" }, { "pos": "AUXVB", "text": "で" }, { "pos": "V", "text": "あっ" }, { "pos": "AUXVB", "text": "た" }, { "pos": "VN", "text": "行為" }, { "pos": "PL", "text": "に" }, { "pos": "V", "text": "つい" }, { "pos": "PL", "text": "て" }, { "pos": "PL", "text": "の" }, { "pos": "NC", "text": "本" }, { "pos": "PUNCT", "text": "『" }, { "pos": "NC", "text": "勇気" }, { "pos": "V", "text": "ある" }, { "pos": "NC", "text": "人々" }, { "pos": "PUNCT", "text": "』" }, { "pos": "PL", "text": "を" }, { "pos": "VN", "text": "出版" }, { "pos": "AUXVB", "text": "し" }, { "pos": "AUXVB", "text": "た" }, { "pos": "PUNCT", "text": "。" }, { "pos": "AA", "text": "この" }, { "pos": "NC", "text": "本" }, { "pos": "PL", "text": "は" }, { "pos": "I", "text": "その" }, { "pos": "NC", "text": "後" }, { "pos": "GUESS", "text": "ピューリツァー" }, { "pos": "NC", "text": "賞" }, { "pos": "PL", "text": "を" }, { "pos": "VN", "text": "受賞" }, { "pos": "AUXVB", "text": "し" }, { "pos": "AUXVB", "text": "た" }, { "pos": "PUNCT", "text": "。" }, { "pos": "NC", "text": "賞金" }, { "pos": "PL", "text": "は" }, { "pos": "NC", "text": "黒人" }, { "pos": "PL", "text": "の" }, { "pos": "V", "text": "通う" }, { "pos": "NC", "text": "学校" }, { "pos": "PL", "text": "へ" }, { "pos": "V", "text": "寄付" }, { "pos": "V", "text": "し" }, { "pos": "AUXVB", "text": "た" }, { "pos": "PL", "text": "と" }, { "pos": "V", "text": "言わ" }, { "pos": "AUXVB", "text": "れ" }, { "pos": "PL", "text": "て" }, { "pos": "V", "text": "いる" }, { "pos": "PUNCT", "text": "。" }, { "pos": "GUESS", "text": "http" }, { "pos": "PUNCT", "text": ":" }, { "pos": "PUNCT", "text": "/" }, { "pos": "PUNCT", "text": "/" }, { "pos": "GUESS", "text": "ja.wikipedia.org" }, { "pos": "PUNCT", "text": "/" }, { "pos": "GUESS", "text": "wiki" }, { "pos": "PUNCT", "text": "/" }, { "pos": "PUNCT", "text": "%" }, { "pos": "GUESS", "text": "E3" }, { "pos": "PUNCT", "text": "%" }, { "pos": "GUESS", "text": "82" }, { "pos": "PUNCT", "text": "%" }, { "pos": "GUESS", "text": "B8" }, { "pos": "PUNCT", "text": "%" }, { "pos": "GUESS", "text": "E3" }, { "pos": "PUNCT", "text": "%" }, { "pos": "GUESS", "text": "83" }, { "pos": "PUNCT", "text": "%" }, { "pos": "GUESS", "text": "A7" }, { "pos": "PUNCT", "text": "%" }, { "pos": "GUESS", "text": "E3" }, { "pos": "PUNCT", "text": "%" }, { "pos": "GUESS", "text": "83" }, { "pos": "PUNCT", "text": "%" }, { "pos": "GUESS", "text": "B3" }, { "pos": "PUNCT", "text": "%" }, { "pos": "GUESS", "text": "E3" }, { "pos": "PUNCT", "text": "%" }, { "pos": "GUESS", "text": "83" }, { "pos": "PUNCT", "text": "%" }, { "pos": "GUESS", "text": "BBF" }, { "pos": "PUNCT", "text": "%" }, { "pos": "GUESS", "text": "E3" }, { "pos": "PUNCT", "text": "%" }, { "pos": "GUESS", "text": "83" }, { "pos": "PUNCT", "text": "%" }, { "pos": "GUESS", "text": "BB" }, { "pos": "PUNCT", "text": "%" }, { "pos": "GUESS", "text": "E3" }, { "pos": "PUNCT", "text": "%" }, { "pos": "GUESS", "text": "82" }, { "pos": "PUNCT", "text": "%" }, { "pos": "GUESS", "text": "B1" }, { "pos": "PUNCT", "text": "%" }, { "pos": "GUESS", "text": "E3" }, { "pos": "PUNCT", "text": "%" }, { "pos": "GUESS", "text": "83" }, { "pos": "PUNCT", "text": "%" }, { "pos": "GUESS", "text": "8D" }, { "pos": "PUNCT", "text": "%" }, { "pos": "GUESS", "text": "E3" }, { "pos": "PUNCT", "text": "%" }, { "pos": "GUESS", "text": "83" }, { "pos": "PUNCT", "text": "%" }, { "pos": "GUESS", "text": "87" }, { "pos": "PUNCT", "text": "%" }, { "pos": "GUESS", "text": "E3" }, { "pos": "PUNCT", "text": "%" }, { "pos": "GUESS", "text": "82" }, { "pos": "PUNCT", "text": "%" }, { "pos": "GUESS", "text": "A3" }, { "pos": "GUESS", "text": "2010.01.26" } ], "requestId": "f808038e-ba8f-4dff-9eae-548084ca75bd", "timers": { "rblJe": 132, "rliJe": 3 } } python-0.7.4/tests/mock-data/response/jpn-doc-morphology_complete.status 0000664 0000000 0000000 00000000003 12636317025 0026565 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/jpn-doc-sentiment.json 0000664 0000000 0000000 00000000244 12636317025 0024141 0 ustar 00root root 0000000 0000000 { "code": "unsupportedLanguage", "message": "Japanese is not supported by Rosette Sentiment Analyzer", "requestId": "dd12b715-0ece-4027-9301-b0aa8a0b057f" } python-0.7.4/tests/mock-data/response/jpn-doc-sentiment.status 0000664 0000000 0000000 00000000003 12636317025 0024504 0 ustar 00root root 0000000 0000000 415 python-0.7.4/tests/mock-data/response/jpn-sentence-categories.json 0000664 0000000 0000000 00000000235 12636317025 0025317 0 ustar 00root root 0000000 0000000 { "code": "unsupportedLanguage", "message": "Japanese is not supported by Rosette Categorizer", "requestId": "60becbc7-8833-47c5-923b-4560efb13683" } python-0.7.4/tests/mock-data/response/jpn-sentence-categories.status 0000664 0000000 0000000 00000000003 12636317025 0025662 0 ustar 00root root 0000000 0000000 415 python-0.7.4/tests/mock-data/response/jpn-sentence-entities.json 0000664 0000000 0000000 00000003476 12636317025 0025030 0 ustar 00root root 0000000 0000000 { "entities": [ { "confidence": 1.0, "count": 2, "indocChainId": 1, "mention": "衆議院", "normalized": "衆議院", "type": "ORGANIZATION" }, { "confidence": 1.0, "count": 2, "indocChainId": 2, "mention": "自民党", "normalized": "自民党", "type": "ORGANIZATION" }, { "confidence": 1.1920928955078125e-06, "count": 2, "indocChainId": 4, "mention": "鳩山家", "normalized": "鳩山家", "type": "ORGANIZATION" }, { "confidence": 0.0009242594242095947, "count": 2, "indocChainId": 6, "mention": "鳩山", "normalized": "鳩山", "type": "PERSON" }, { "confidence": 0.002387821674346924, "count": 1, "indocChainId": 0, "mention": "中川一郎", "normalized": "中川一郎", "type": "PERSON" }, { "confidence": 0.00404590368270874, "count": 1, "indocChainId": 3, "mention": "田中", "normalized": "田中", "type": "PERSON" }, { "confidence": 0.0023449063301086426, "count": 1, "indocChainId": 5, "mention": "北海道", "normalized": "北海道", "type": "LOCATION" }, { "confidence": 0.002293109893798828, "count": 1, "indocChainId": 7, "mention": "三枝三郎", "normalized": "三枝三郎", "type": "PERSON" }, { "confidence": 0.0010268688201904297, "count": 1, "indocChainId": 10, "mention": "高橋辰夫", "normalized": "高橋辰夫", "type": "PERSON" } ], "requestId": "361f92b3-b229-4750-911e-6a30b9edff77", "timers": { "rblJe": 8, "rexJe": 15, "rliJe": 5 } } python-0.7.4/tests/mock-data/response/jpn-sentence-entities.status 0000664 0000000 0000000 00000000003 12636317025 0025361 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/jpn-sentence-entities_linked.json 0000664 0000000 0000000 00000002654 12636317025 0026353 0 ustar 00root root 0000000 0000000 { "entities": [ { "confidence": 0.5804911233166798, "entityId": "Q615236", "indocChainId": 0, "mention": "中川一郎" }, { "confidence": 0.3325862488651135, "entityId": "NEW-CLUSTER", "indocChainId": 1, "mention": "衆議院" }, { "confidence": 0.3035061601648603, "entityId": "Q232595", "indocChainId": 2, "mention": "自民党" }, { "confidence": 0.3020758136528464, "entityId": "NEW-CLUSTER", "indocChainId": 3, "mention": "田中" }, { "confidence": 0.39123757908924967, "entityId": "NEW-CLUSTER", "indocChainId": 4, "mention": "鳩山家" }, { "confidence": 0.5767181759128862, "entityId": "Q35581", "indocChainId": 5, "mention": "北海道" }, { "confidence": 0.5719175959113528, "entityId": "NEW-CLUSTER", "indocChainId": 6, "mention": "鳩山" }, { "confidence": 0.18809272778462766, "entityId": "NEW-CLUSTER", "indocChainId": 7, "mention": "三枝三郎" }, { "confidence": 0.2377751769118006, "entityId": "NEW-CLUSTER", "indocChainId": 10, "mention": "高橋辰夫" } ], "requestId": "2ddce92c-9a0c-4f17-9a5c-5abc3cdde474", "timers": { "rblJe": 8, "res": 808, "rexJe": 8, "rliJe": 4 } } python-0.7.4/tests/mock-data/response/jpn-sentence-entities_linked.status 0000664 0000000 0000000 00000000003 12636317025 0026707 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/jpn-sentence-language.json 0000664 0000000 0000000 00000001000 12636317025 0024744 0 ustar 00root root 0000000 0000000 { "languageDetections": [ { "confidence": 0.18632915896411573, "language": "jpn" }, { "confidence": 0.005708728566174215, "language": "zho" }, { "confidence": 0.0053253763489605754, "language": "zho" }, { "confidence": 3.1152313146431965e-05, "language": "jpn" }, { "confidence": 0.0, "language": "ara" } ], "requestId": "e7e86b2e-113a-4bd1-bcea-b7d5d1f4d691", "timers": { "rliJe": 2 } }python-0.7.4/tests/mock-data/response/jpn-sentence-language.status 0000664 0000000 0000000 00000000003 12636317025 0025320 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/jpn-sentence-morphology_complete.json 0000664 0000000 0000000 00000131351 12636317025 0027265 0 ustar 00root root 0000000 0000000 { "compounds": [], "hanReadings": [ { "hanReadings": [ "セイジ" ], "text": "政治" }, { "hanReadings": [ "カ" ], "text": "家" }, { "hanReadings": [ "ヲ" ], "text": "を" }, { "hanReadings": [ "ココロザシ" ], "text": "志し" }, { "hanReadings": [ "タ" ], "text": "た" }, { "hanReadings": [ "キッカケ" ], "text": "きっかけ" }, { "hanReadings": [ "ハ" ], "text": "は" }, { "hanReadings": [ "ナカガワ" ], "text": "中川" }, { "hanReadings": [ "イチロウ" ], "text": "一郎" }, { "hanReadings": [ "ノ" ], "text": "の" }, { "hanReadings": [ "ソンザイ" ], "text": "存在" }, { "hanReadings": [ "ダッ" ], "text": "だっ" }, { "hanReadings": [ "タ" ], "text": "た" }, { "hanReadings": [ "ト" ], "text": "と" }, { "hanReadings": [ "ユウ" ], "text": "いう" }, { "hanReadings": [ "[" ], "text": "[" }, { "hanReadings": [ "]" ], "text": "]" }, { "hanReadings": [ "。" ], "text": "。" }, { "hanReadings": [ "ネン" ], "text": "年" }, { "hanReadings": [ "、" ], "text": "、" }, { "hanReadings": [ "ダイ" ], "text": "第" }, { "hanReadings": [ "カイ" ], "text": "回" }, { "hanReadings": [ "シュウギ" ], "text": "衆議" }, { "hanReadings": [ "イン" ], "text": "院" }, { "hanReadings": [ "ギイン" ], "text": "議員" }, { "hanReadings": [ "ソウ" ], "text": "総" }, { "hanReadings": [ "センキョ" ], "text": "選挙" }, { "hanReadings": [ "デ" ], "text": "で" }, { "hanReadings": [ "、" ], "text": "、" }, { "hanReadings": [ "ジミン" ], "text": "自民" }, { "hanReadings": [ "トウ" ], "text": "党" }, { "hanReadings": [ "ノ" ], "text": "の" }, { "hanReadings": [ "コウニン" ], "text": "公認" }, { "hanReadings": [ "ヲ" ], "text": "を" }, { "hanReadings": [ "ウ" ], "text": "得" }, { "hanReadings": [ "タ" ], "text": "た" }, { "hanReadings": [ "タナカ" ], "text": "田中" }, { "hanReadings": [ "ハ" ], "text": "派" }, { "hanReadings": [ "シンジン" ], "text": "新人" }, { "hanReadings": [ "ト" ], "text": "と" }, { "hanReadings": [ "シ" ], "text": "し" }, { "hanReadings": [ "テ" ], "text": "て" }, { "hanReadings": [ "、" ], "text": "、" }, { "hanReadings": [ "ハトヤマ" ], "text": "鳩山" }, { "hanReadings": [ "カ" ], "text": "家" }, { "hanReadings": [ "ガ" ], "text": "が" }, { "hanReadings": [ "ボクジョウ" ], "text": "牧場" }, { "hanReadings": [ "ヲ" ], "text": "を" }, { "hanReadings": [ "ショユウ" ], "text": "所有" }, { "hanReadings": [ "シ" ], "text": "し" }, { "hanReadings": [ "ハトヤマ" ], "text": "鳩山" }, { "hanReadings": [ "ジンジャ" ], "text": "神社" }, { "hanReadings": [ "ト" ], "text": "と" }, { "hanReadings": [ "ユウ" ], "text": "いう" }, { "hanReadings": [ "ジンジャ" ], "text": "神社" }, { "hanReadings": [ "ガ" ], "text": "が" }, { "hanReadings": [ "アル" ], "text": "ある" }, { "hanReadings": [ "ソフ" ], "text": "祖父" }, { "hanReadings": [ "ノ" ], "text": "の" }, { "hanReadings": [ "ダイ" ], "text": "代" }, { "hanReadings": [ "カラ" ], "text": "から" }, { "hanReadings": [ "ノ" ], "text": "の" }, { "hanReadings": [ "ジバン" ], "text": "地盤" }, { "hanReadings": [ "ホッカイドウ" ], "text": "北海道" }, { "hanReadings": [ "カラ" ], "text": "から" }, { "hanReadings": [ "[" ], "text": "[" }, { "hanReadings": [ "]" ], "text": "]" }, { "hanReadings": [ "、" ], "text": "、" }, { "hanReadings": [ "シュツバ" ], "text": "出馬" }, { "hanReadings": [ "シ" ], "text": "し" }, { "hanReadings": [ "タ" ], "text": "た" }, { "hanReadings": [ "。" ], "text": "。" }, { "hanReadings": [ "ハトヤマ" ], "text": "鳩山" }, { "hanReadings": [ "ジム" ], "text": "事務" }, { "hanReadings": [ "ドコロ" ], "text": "所" }, { "hanReadings": [ "ソバ" ], "text": "側" }, { "hanReadings": [ "ハ" ], "text": "は" }, { "hanReadings": [ "、" ], "text": "、" }, { "hanReadings": [ "「" ], "text": "「" }, { "hanReadings": [ "タテ" ], "text": "立" }, { "hanReadings": [ "コウホ" ], "text": "候補" }, { "hanReadings": [ "ノ" ], "text": "の" }, { "hanReadings": [ "チョクセツ" ], "text": "直接" }, { "hanReadings": [ "ノ" ], "text": "の" }, { "hanReadings": [ "キッカケ" ], "text": "きっかけ" }, { "hanReadings": [ "ハ" ], "text": "は" }, { "hanReadings": [ "サエグサ" ], "text": "三枝" }, { "hanReadings": [ "サブロウ" ], "text": "三郎" }, { "hanReadings": [ "シュウギ" ], "text": "衆議" }, { "hanReadings": [ "イン" ], "text": "院" }, { "hanReadings": [ "ギイン" ], "text": "議員" }, { "hanReadings": [ "ノ" ], "text": "の" }, { "hanReadings": [ "ヒキノケ" ], "text": "引退" }, { "hanReadings": [ "ガ" ], "text": "が" }, { "hanReadings": [ "キッカケ" ], "text": "きっかけ" }, { "hanReadings": [ "」" ], "text": "」" }, { "hanReadings": [ "ト" ], "text": "と" }, { "hanReadings": [ "シュチョウ" ], "text": "主張" }, { "hanReadings": [ "シ" ], "text": "し" }, { "hanReadings": [ "テ" ], "text": "て" }, { "hanReadings": [ "イル" ], "text": "いる" }, { "hanReadings": [ "[" ], "text": "[" }, { "hanReadings": [ "]" ], "text": "]" }, { "hanReadings": [ "。" ], "text": "。" }, { "hanReadings": [ "ハツ" ], "text": "初" }, { "hanReadings": [ "ノ" ], "text": "の" }, { "hanReadings": [ "センキョ" ], "text": "選挙" }, { "hanReadings": [ "スローガン" ], "text": "スローガン" }, { "hanReadings": [ "ハ" ], "text": "は" }, { "hanReadings": [ "カガク" ], "text": "科学" }, { "hanReadings": [ "シャ" ], "text": "者" }, { "hanReadings": [ "ヲ" ], "text": "を" }, { "hanReadings": [ "シボウ" ], "text": "志望" }, { "hanReadings": [ "シ" ], "text": "し" }, { "hanReadings": [ "テ" ], "text": "て" }, { "hanReadings": [ "イ" ], "text": "い" }, { "hanReadings": [ "タ" ], "text": "た" }, { "hanReadings": [ "ジシン" ], "text": "自身" }, { "hanReadings": [ "ノ" ], "text": "の" }, { "hanReadings": [ "ケイレキ" ], "text": "経歴" }, { "hanReadings": [ "ヲ" ], "text": "を" }, { "hanReadings": [ "アピール" ], "text": "アピール" }, { "hanReadings": [ "シ" ], "text": "し" }, { "hanReadings": [ "タ" ], "text": "た" }, { "hanReadings": [ "「" ], "text": "「" }, { "hanReadings": [ "セイジ" ], "text": "政治" }, { "hanReadings": [ "ヲ" ], "text": "を" }, { "hanReadings": [ "カガク" ], "text": "科学" }, { "hanReadings": [ "スル" ], "text": "する" }, { "hanReadings": [ "」" ], "text": "」" }, { "hanReadings": [ "デ" ], "text": "で" }, { "hanReadings": [ "アッ" ], "text": "あっ" }, { "hanReadings": [ "タ" ], "text": "た" }, { "hanReadings": [ "[" ], "text": "[" }, { "hanReadings": [ "]" ], "text": "]" }, { "hanReadings": [ "。" ], "text": "。" }, { "hanReadings": [ "トク" ], "text": "得" }, { "hanReadings": [ "ヒョウスウ" ], "text": "票数" }, { "hanReadings": [ "デ" ], "text": "で" }, { "hanReadings": [ "ハ" ], "text": "は" }, { "hanReadings": [ "オナジ" ], "text": "同じ" }, { "hanReadings": [ "ジミン" ], "text": "自民" }, { "hanReadings": [ "トウ" ], "text": "党" }, { "hanReadings": [ "ノ" ], "text": "の" }, { "hanReadings": [ "タカバシ" ], "text": "高橋" }, { "hanReadings": [ "タツオ" ], "text": "辰夫" }, { "hanReadings": [ "ニ" ], "text": "に" }, { "hanReadings": [ "ツイ" ], "text": "次い" }, { "hanReadings": [ "デ" ], "text": "で" }, { "hanReadings": [ "ツガイ" ], "text": "番" }, { "hanReadings": [ "メ" ], "text": "目" }, { "hanReadings": [ "ノ" ], "text": "の" }, { "hanReadings": [ "トクヒョウ" ], "text": "得票" }, { "hanReadings": [ "スウ" ], "text": "数" }, { "hanReadings": [ "デ" ], "text": "で" }, { "hanReadings": [ "トウセン" ], "text": "当選" }, { "hanReadings": [ "シ" ], "text": "し" }, { "hanReadings": [ "タ" ], "text": "た" }, { "hanReadings": [ "。" ], "text": "。" }, { "hanReadings": [ "コ" ], "text": "小" }, { "hanReadings": [ "センキョ" ], "text": "選挙" }, { "hanReadings": [ "ク" ], "text": "区" }, { "hanReadings": [ "ニ" ], "text": "に" }, { "hanReadings": [ "ナッ" ], "text": "なっ" }, { "hanReadings": [ "タ" ], "text": "た" }, { "hanReadings": [ "ネン" ], "text": "年" }, { "hanReadings": [ "イコウ" ], "text": "以降" }, { "hanReadings": [ "ハ" ], "text": "は" }, { "hanReadings": [ "、" ], "text": "、" }, { "hanReadings": [ "ハトヤマ" ], "text": "鳩山" }, { "hanReadings": [ "カ" ], "text": "家" }, { "hanReadings": [ "ガ" ], "text": "が" }, { "hanReadings": [ "カイタク" ], "text": "開拓" }, { "hanReadings": [ "シ" ], "text": "し" }, { "hanReadings": [ "タ" ], "text": "た" }, { "hanReadings": [ "チイキ" ], "text": "地域" }, { "hanReadings": [ "ハ" ], "text": "は" }, { "hanReadings": [ "ハトヤマ" ], "text": "鳩山" }, { "hanReadings": [ "ノ" ], "text": "の" }, { "hanReadings": [ "センキョ" ], "text": "選挙" }, { "hanReadings": [ "ク" ], "text": "区" }, { "hanReadings": [ "カラ" ], "text": "から" }, { "hanReadings": [ "ハズレ" ], "text": "外れ" }, { "hanReadings": [ "タ" ], "text": "た" }, { "hanReadings": [ "[" ], "text": "[" }, { "hanReadings": [ "]" ], "text": "]" }, { "hanReadings": [ "。" ], "text": "。" }, { "hanReadings": [ "ナオ" ], "text": "なお" }, { "hanReadings": [ "、" ], "text": "、" }, { "hanReadings": [ "チホウ" ], "text": "地方" }, { "hanReadings": [ "クワケ" ], "text": "区分" }, { "hanReadings": [ "ノ" ], "text": "の" }, { "hanReadings": [ "センキョ" ], "text": "選挙" }, { "hanReadings": [ "ク" ], "text": "区" }, { "hanReadings": [ "ジタイ" ], "text": "自体" }, { "hanReadings": [ "ハ" ], "text": "は" }, { "hanReadings": [ "ソフ" ], "text": "祖父" }, { "hanReadings": [ "ト" ], "text": "と" }, { "hanReadings": [ "チョウフク" ], "text": "重複" }, { "hanReadings": [ "シ" ], "text": "し" }, { "hanReadings": [ "テ" ], "text": "て" }, { "hanReadings": [ "イ" ], "text": "い" }, { "hanReadings": [ "ナイ" ], "text": "ない" }, { "hanReadings": [ "タメ" ], "text": "ため" }, { "hanReadings": [ "、" ], "text": "、" }, { "hanReadings": [ "ソフ" ], "text": "祖父" }, { "hanReadings": [ "ノ" ], "text": "の" }, { "hanReadings": [ "ジバン" ], "text": "地盤" }, { "hanReadings": [ "ヲ" ], "text": "を" }, { "hanReadings": [ "セシュウ" ], "text": "世襲" }, { "hanReadings": [ "シ" ], "text": "し" }, { "hanReadings": [ "テ" ], "text": "て" }, { "hanReadings": [ "イ" ], "text": "い" }, { "hanReadings": [ "ナイ" ], "text": "ない" }, { "hanReadings": [ "ト" ], "text": "と" }, { "hanReadings": [ "アツカワ" ], "text": "扱わ" }, { "hanReadings": [ "レ" ], "text": "れ" }, { "hanReadings": [ "テ" ], "text": "て" }, { "hanReadings": [ "イル" ], "text": "いる" }, { "hanReadings": [ "[" ], "text": "[" }, { "hanReadings": [ "]" ], "text": "]" }, { "hanReadings": [ "。" ], "text": "。" } ], "lemmas": [ { "lemma": "政治", "text": "政治" }, { "lemma": "家", "text": "家" }, { "lemma": "を", "text": "を" }, { "lemma": "志す", "text": "志し" }, { "lemma": "た", "text": "た" }, { "lemma": "きっかけ", "text": "きっかけ" }, { "lemma": "は", "text": "は" }, { "lemma": "中川", "text": "中川" }, { "lemma": "一郎", "text": "一郎" }, { "lemma": "の", "text": "の" }, { "lemma": "存在", "text": "存在" }, { "lemma": "だ", "text": "だっ" }, { "lemma": "た", "text": "た" }, { "lemma": "と", "text": "と" }, { "lemma": "いう", "text": "いう" }, { "lemma": "[", "text": "[" }, { "lemma": "3", "text": "3" }, { "lemma": "]", "text": "]" }, { "lemma": "。", "text": "。" }, { "lemma": "1986", "text": "1986" }, { "lemma": "年", "text": "年" }, { "lemma": "、", "text": "、" }, { "lemma": "第", "text": "第" }, { "lemma": "38", "text": "38" }, { "lemma": "回", "text": "回" }, { "lemma": "衆議", "text": "衆議" }, { "lemma": "院", "text": "院" }, { "lemma": "議員", "text": "議員" }, { "lemma": "総", "text": "総" }, { "lemma": "選挙", "text": "選挙" }, { "lemma": "だ", "text": "で" }, { "lemma": "、", "text": "、" }, { "lemma": "自民", "text": "自民" }, { "lemma": "党", "text": "党" }, { "lemma": "の", "text": "の" }, { "lemma": "公認", "text": "公認" }, { "lemma": "を", "text": "を" }, { "lemma": "得", "text": "得" }, { "lemma": "た", "text": "た" }, { "lemma": "田中", "text": "田中" }, { "lemma": "派", "text": "派" }, { "lemma": "新人", "text": "新人" }, { "lemma": "と", "text": "と" }, { "lemma": "する", "text": "し" }, { "lemma": "て", "text": "て" }, { "lemma": "、", "text": "、" }, { "lemma": "鳩山", "text": "鳩山" }, { "lemma": "家", "text": "家" }, { "lemma": "が", "text": "が" }, { "lemma": "牧場", "text": "牧場" }, { "lemma": "を", "text": "を" }, { "lemma": "所有", "text": "所有" }, { "lemma": "す", "text": "し" }, { "lemma": "鳩山", "text": "鳩山" }, { "lemma": "神社", "text": "神社" }, { "lemma": "と", "text": "と" }, { "lemma": "いう", "text": "いう" }, { "lemma": "神社", "text": "神社" }, { "lemma": "が", "text": "が" }, { "lemma": "ある", "text": "ある" }, { "lemma": "祖父", "text": "祖父" }, { "lemma": "の", "text": "の" }, { "lemma": "代", "text": "代" }, { "lemma": "から", "text": "から" }, { "lemma": "の", "text": "の" }, { "lemma": "地盤", "text": "地盤" }, { "lemma": "北海道", "text": "北海道" }, { "lemma": "から", "text": "から" }, { "lemma": "[", "text": "[" }, { "lemma": "4", "text": "4" }, { "lemma": "]", "text": "]" }, { "lemma": "、", "text": "、" }, { "lemma": "出馬", "text": "出馬" }, { "lemma": "き", "text": "し" }, { "lemma": "た", "text": "た" }, { "lemma": "。", "text": "。" }, { "lemma": "鳩山", "text": "鳩山" }, { "lemma": "事務", "text": "事務" }, { "lemma": "所", "text": "所" }, { "lemma": "側", "text": "側" }, { "lemma": "は", "text": "は" }, { "lemma": "、", "text": "、" }, { "lemma": "「", "text": "「" }, { "lemma": "立", "text": "立" }, { "lemma": "候補", "text": "候補" }, { "lemma": "の", "text": "の" }, { "lemma": "直接", "text": "直接" }, { "lemma": "の", "text": "の" }, { "lemma": "きっかけ", "text": "きっかけ" }, { "lemma": "は", "text": "は" }, { "lemma": "三枝", "text": "三枝" }, { "lemma": "三郎", "text": "三郎" }, { "lemma": "衆議", "text": "衆議" }, { "lemma": "院", "text": "院" }, { "lemma": "議員", "text": "議員" }, { "lemma": "の", "text": "の" }, { "lemma": "引退る", "text": "引退" }, { "lemma": "が", "text": "が" }, { "lemma": "きっかけ", "text": "きっかけ" }, { "lemma": "」", "text": "」" }, { "lemma": "と", "text": "と" }, { "lemma": "主張", "text": "主張" }, { "lemma": "き", "text": "し" }, { "lemma": "て", "text": "て" }, { "lemma": "いる", "text": "いる" }, { "lemma": "[", "text": "[" }, { "lemma": "5", "text": "5" }, { "lemma": "]", "text": "]" }, { "lemma": "。", "text": "。" }, { "lemma": "初", "text": "初" }, { "lemma": "の", "text": "の" }, { "lemma": "選挙", "text": "選挙" }, { "lemma": "スローガン", "text": "スローガン" }, { "lemma": "は", "text": "は" }, { "lemma": "科学", "text": "科学" }, { "lemma": "者", "text": "者" }, { "lemma": "を", "text": "を" }, { "lemma": "志望", "text": "志望" }, { "lemma": "き", "text": "し" }, { "lemma": "て", "text": "て" }, { "lemma": "いる", "text": "い" }, { "lemma": "た", "text": "た" }, { "lemma": "自身", "text": "自身" }, { "lemma": "の", "text": "の" }, { "lemma": "経歴", "text": "経歴" }, { "lemma": "を", "text": "を" }, { "lemma": "アピール", "text": "アピール" }, { "lemma": "き", "text": "し" }, { "lemma": "た", "text": "た" }, { "lemma": "「", "text": "「" }, { "lemma": "政治", "text": "政治" }, { "lemma": "を", "text": "を" }, { "lemma": "科学", "text": "科学" }, { "lemma": "する", "text": "する" }, { "lemma": "」", "text": "」" }, { "lemma": "だ", "text": "で" }, { "lemma": "ある", "text": "あっ" }, { "lemma": "た", "text": "た" }, { "lemma": "[", "text": "[" }, { "lemma": "6", "text": "6" }, { "lemma": "]", "text": "]" }, { "lemma": "。", "text": "。" }, { "lemma": "得", "text": "得" }, { "lemma": "票数", "text": "票数" }, { "lemma": "で", "text": "で" }, { "lemma": "は", "text": "は" }, { "lemma": "同じ", "text": "同じ" }, { "lemma": "自民", "text": "自民" }, { "lemma": "党", "text": "党" }, { "lemma": "の", "text": "の" }, { "lemma": "高橋", "text": "高橋" }, { "lemma": "辰夫", "text": "辰夫" }, { "lemma": "に", "text": "に" }, { "lemma": "次ぐ", "text": "次い" }, { "lemma": "で", "text": "で" }, { "lemma": "2", "text": "2" }, { "lemma": "番", "text": "番" }, { "lemma": "目", "text": "目" }, { "lemma": "の", "text": "の" }, { "lemma": "得票", "text": "得票" }, { "lemma": "数", "text": "数" }, { "lemma": "で", "text": "で" }, { "lemma": "当選", "text": "当選" }, { "lemma": "き", "text": "し" }, { "lemma": "た", "text": "た" }, { "lemma": "。", "text": "。" }, { "lemma": "小", "text": "小" }, { "lemma": "選挙", "text": "選挙" }, { "lemma": "区", "text": "区" }, { "lemma": "に", "text": "に" }, { "lemma": "なる", "text": "なっ" }, { "lemma": "た", "text": "た" }, { "lemma": "1996", "text": "1996" }, { "lemma": "年", "text": "年" }, { "lemma": "以降", "text": "以降" }, { "lemma": "は", "text": "は" }, { "lemma": "、", "text": "、" }, { "lemma": "鳩山", "text": "鳩山" }, { "lemma": "家", "text": "家" }, { "lemma": "が", "text": "が" }, { "lemma": "開拓", "text": "開拓" }, { "lemma": "す", "text": "し" }, { "lemma": "た", "text": "た" }, { "lemma": "地域", "text": "地域" }, { "lemma": "は", "text": "は" }, { "lemma": "鳩山", "text": "鳩山" }, { "lemma": "の", "text": "の" }, { "lemma": "選挙", "text": "選挙" }, { "lemma": "区", "text": "区" }, { "lemma": "から", "text": "から" }, { "lemma": "外れる", "text": "外れ" }, { "lemma": "た", "text": "た" }, { "lemma": "[", "text": "[" }, { "lemma": "7", "text": "7" }, { "lemma": "]", "text": "]" }, { "lemma": "。", "text": "。" }, { "lemma": "なお", "text": "なお" }, { "lemma": "、", "text": "、" }, { "lemma": "地方", "text": "地方" }, { "lemma": "区分", "text": "区分" }, { "lemma": "の", "text": "の" }, { "lemma": "選挙", "text": "選挙" }, { "lemma": "区", "text": "区" }, { "lemma": "自体", "text": "自体" }, { "lemma": "は", "text": "は" }, { "lemma": "祖父", "text": "祖父" }, { "lemma": "と", "text": "と" }, { "lemma": "重複", "text": "重複" }, { "lemma": "き", "text": "し" }, { "lemma": "て", "text": "て" }, { "lemma": "いる", "text": "い" }, { "lemma": "ない", "text": "ない" }, { "lemma": "ため", "text": "ため" }, { "lemma": "、", "text": "、" }, { "lemma": "祖父", "text": "祖父" }, { "lemma": "の", "text": "の" }, { "lemma": "地盤", "text": "地盤" }, { "lemma": "を", "text": "を" }, { "lemma": "世襲", "text": "世襲" }, { "lemma": "き", "text": "し" }, { "lemma": "て", "text": "て" }, { "lemma": "いる", "text": "い" }, { "lemma": "ない", "text": "ない" }, { "lemma": "と", "text": "と" }, { "lemma": "扱う", "text": "扱わ" }, { "lemma": "る", "text": "れ" }, { "lemma": "て", "text": "て" }, { "lemma": "いる", "text": "いる" }, { "lemma": "[", "text": "[" }, { "lemma": "8", "text": "8" }, { "lemma": "]", "text": "]" }, { "lemma": "。", "text": "。" } ], "posTags": [ { "pos": "NC", "text": "政治" }, { "pos": "WS", "text": "家" }, { "pos": "PL", "text": "を" }, { "pos": "V", "text": "志し" }, { "pos": "AUXVB", "text": "た" }, { "pos": "NC", "text": "きっかけ" }, { "pos": "PL", "text": "は" }, { "pos": "NP", "text": "中川" }, { "pos": "NP", "text": "一郎" }, { "pos": "PL", "text": "の" }, { "pos": "VN", "text": "存在" }, { "pos": "AUXVB", "text": "だっ" }, { "pos": "AUXVB", "text": "た" }, { "pos": "PL", "text": "と" }, { "pos": "V", "text": "いう" }, { "pos": "PUNCT", "text": "[" }, { "pos": "GUESS", "text": "3" }, { "pos": "PUNCT", "text": "]" }, { "pos": "PUNCT", "text": "。" }, { "pos": "GUESS", "text": "1986" }, { "pos": "NC", "text": "年" }, { "pos": "PUNCT", "text": "、" }, { "pos": "WP", "text": "第" }, { "pos": "GUESS", "text": "38" }, { "pos": "NC", "text": "回" }, { "pos": "NC", "text": "衆議" }, { "pos": "WS", "text": "院" }, { "pos": "NC", "text": "議員" }, { "pos": "WP", "text": "総" }, { "pos": "VN", "text": "選挙" }, { "pos": "AUXVB", "text": "で" }, { "pos": "PUNCT", "text": "、" }, { "pos": "NP", "text": "自民" }, { "pos": "WS", "text": "党" }, { "pos": "PL", "text": "の" }, { "pos": "VN", "text": "公認" }, { "pos": "PL", "text": "を" }, { "pos": "V", "text": "得" }, { "pos": "AUXVB", "text": "た" }, { "pos": "NP", "text": "田中" }, { "pos": "WS", "text": "派" }, { "pos": "NC", "text": "新人" }, { "pos": "PL", "text": "と" }, { "pos": "V", "text": "し" }, { "pos": "PL", "text": "て" }, { "pos": "PUNCT", "text": "、" }, { "pos": "NP", "text": "鳩山" }, { "pos": "WS", "text": "家" }, { "pos": "PL", "text": "が" }, { "pos": "NC", "text": "牧場" }, { "pos": "PL", "text": "を" }, { "pos": "VN", "text": "所有" }, { "pos": "FS", "text": "し" }, { "pos": "NP", "text": "鳩山" }, { "pos": "NC", "text": "神社" }, { "pos": "PL", "text": "と" }, { "pos": "V", "text": "いう" }, { "pos": "NC", "text": "神社" }, { "pos": "PL", "text": "が" }, { "pos": "V", "text": "ある" }, { "pos": "NC", "text": "祖父" }, { "pos": "PL", "text": "の" }, { "pos": "NC", "text": "代" }, { "pos": "PL", "text": "から" }, { "pos": "PL", "text": "の" }, { "pos": "NC", "text": "地盤" }, { "pos": "NP", "text": "北海道" }, { "pos": "PL", "text": "から" }, { "pos": "PUNCT", "text": "[" }, { "pos": "GUESS", "text": "4" }, { "pos": "PUNCT", "text": "]" }, { "pos": "PUNCT", "text": "、" }, { "pos": "VN", "text": "出馬" }, { "pos": "AUXVB", "text": "し" }, { "pos": "AUXVB", "text": "た" }, { "pos": "PUNCT", "text": "。" }, { "pos": "NP", "text": "鳩山" }, { "pos": "NC", "text": "事務" }, { "pos": "WS", "text": "所" }, { "pos": "NC", "text": "側" }, { "pos": "PL", "text": "は" }, { "pos": "PUNCT", "text": "、" }, { "pos": "PUNCT", "text": "「" }, { "pos": "WP", "text": "立" }, { "pos": "NC", "text": "候補" }, { "pos": "PL", "text": "の" }, { "pos": "NC", "text": "直接" }, { "pos": "PL", "text": "の" }, { "pos": "NC", "text": "きっかけ" }, { "pos": "PL", "text": "は" }, { "pos": "NP", "text": "三枝" }, { "pos": "NP", "text": "三郎" }, { "pos": "NC", "text": "衆議" }, { "pos": "WS", "text": "院" }, { "pos": "NC", "text": "議員" }, { "pos": "PL", "text": "の" }, { "pos": "V", "text": "引退" }, { "pos": "PL", "text": "が" }, { "pos": "NC", "text": "きっかけ" }, { "pos": "PUNCT", "text": "」" }, { "pos": "PL", "text": "と" }, { "pos": "VN", "text": "主張" }, { "pos": "AUXVB", "text": "し" }, { "pos": "PL", "text": "て" }, { "pos": "V", "text": "いる" }, { "pos": "PUNCT", "text": "[" }, { "pos": "GUESS", "text": "5" }, { "pos": "PUNCT", "text": "]" }, { "pos": "PUNCT", "text": "。" }, { "pos": "NC", "text": "初" }, { "pos": "PL", "text": "の" }, { "pos": "VN", "text": "選挙" }, { "pos": "NC", "text": "スローガン" }, { "pos": "PL", "text": "は" }, { "pos": "NC", "text": "科学" }, { "pos": "WS", "text": "者" }, { "pos": "PL", "text": "を" }, { "pos": "VN", "text": "志望" }, { "pos": "AUXVB", "text": "し" }, { "pos": "PL", "text": "て" }, { "pos": "V", "text": "い" }, { "pos": "AUXVB", "text": "た" }, { "pos": "NC", "text": "自身" }, { "pos": "PL", "text": "の" }, { "pos": "NC", "text": "経歴" }, { "pos": "PL", "text": "を" }, { "pos": "VN", "text": "アピール" }, { "pos": "AUXVB", "text": "し" }, { "pos": "AUXVB", "text": "た" }, { "pos": "PUNCT", "text": "「" }, { "pos": "NC", "text": "政治" }, { "pos": "PL", "text": "を" }, { "pos": "NC", "text": "科学" }, { "pos": "V", "text": "する" }, { "pos": "PUNCT", "text": "」" }, { "pos": "AUXVB", "text": "で" }, { "pos": "V", "text": "あっ" }, { "pos": "AUXVB", "text": "た" }, { "pos": "PUNCT", "text": "[" }, { "pos": "GUESS", "text": "6" }, { "pos": "PUNCT", "text": "]" }, { "pos": "PUNCT", "text": "。" }, { "pos": "NC", "text": "得" }, { "pos": "NC", "text": "票数" }, { "pos": "PL", "text": "で" }, { "pos": "PL", "text": "は" }, { "pos": "NC", "text": "同じ" }, { "pos": "NP", "text": "自民" }, { "pos": "WS", "text": "党" }, { "pos": "PL", "text": "の" }, { "pos": "NP", "text": "高橋" }, { "pos": "NP", "text": "辰夫" }, { "pos": "PL", "text": "に" }, { "pos": "V", "text": "次い" }, { "pos": "PL", "text": "で" }, { "pos": "GUESS", "text": "2" }, { "pos": "NC", "text": "番" }, { "pos": "WS", "text": "目" }, { "pos": "PL", "text": "の" }, { "pos": "VN", "text": "得票" }, { "pos": "NN", "text": "数" }, { "pos": "J", "text": "で" }, { "pos": "VN", "text": "当選" }, { "pos": "AUXVB", "text": "し" }, { "pos": "AUXVB", "text": "た" }, { "pos": "PUNCT", "text": "。" }, { "pos": "WP", "text": "小" }, { "pos": "VN", "text": "選挙" }, { "pos": "NC", "text": "区" }, { "pos": "PL", "text": "に" }, { "pos": "V", "text": "なっ" }, { "pos": "AUXVB", "text": "た" }, { "pos": "GUESS", "text": "1996" }, { "pos": "NC", "text": "年" }, { "pos": "NC", "text": "以降" }, { "pos": "PL", "text": "は" }, { "pos": "PUNCT", "text": "、" }, { "pos": "NP", "text": "鳩山" }, { "pos": "WS", "text": "家" }, { "pos": "J", "text": "が" }, { "pos": "VN", "text": "開拓" }, { "pos": "FS", "text": "し" }, { "pos": "AUXVB", "text": "た" }, { "pos": "NC", "text": "地域" }, { "pos": "PL", "text": "は" }, { "pos": "NP", "text": "鳩山" }, { "pos": "PL", "text": "の" }, { "pos": "VN", "text": "選挙" }, { "pos": "WS", "text": "区" }, { "pos": "PL", "text": "から" }, { "pos": "V", "text": "外れ" }, { "pos": "AUXVB", "text": "た" }, { "pos": "PUNCT", "text": "[" }, { "pos": "GUESS", "text": "7" }, { "pos": "PUNCT", "text": "]" }, { "pos": "PUNCT", "text": "。" }, { "pos": "J", "text": "なお" }, { "pos": "PUNCT", "text": "、" }, { "pos": "NC", "text": "地方" }, { "pos": "VN", "text": "区分" }, { "pos": "PL", "text": "の" }, { "pos": "VN", "text": "選挙" }, { "pos": "NU", "text": "区" }, { "pos": "NC", "text": "自体" }, { "pos": "PL", "text": "は" }, { "pos": "NC", "text": "祖父" }, { "pos": "PL", "text": "と" }, { "pos": "VN", "text": "重複" }, { "pos": "AUXVB", "text": "し" }, { "pos": "PL", "text": "て" }, { "pos": "V", "text": "い" }, { "pos": "AUXVB", "text": "ない" }, { "pos": "NC", "text": "ため" }, { "pos": "PUNCT", "text": "、" }, { "pos": "NC", "text": "祖父" }, { "pos": "PL", "text": "の" }, { "pos": "NC", "text": "地盤" }, { "pos": "PL", "text": "を" }, { "pos": "VN", "text": "世襲" }, { "pos": "AUXVB", "text": "し" }, { "pos": "PL", "text": "て" }, { "pos": "V", "text": "い" }, { "pos": "AUXVB", "text": "ない" }, { "pos": "PL", "text": "と" }, { "pos": "V", "text": "扱わ" }, { "pos": "AUXVB", "text": "れ" }, { "pos": "PL", "text": "て" }, { "pos": "V", "text": "いる" }, { "pos": "PUNCT", "text": "[" }, { "pos": "GUESS", "text": "8" }, { "pos": "PUNCT", "text": "]" }, { "pos": "PUNCT", "text": "。" } ], "requestId": "30a0ae17-9293-40d6-9d1a-8ddeca752939", "timers": { "rblJe": 7, "rliJe": 4 } } python-0.7.4/tests/mock-data/response/jpn-sentence-morphology_complete.status 0000664 0000000 0000000 00000000003 12636317025 0027624 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/jpn-sentence-sentiment.json 0000664 0000000 0000000 00000000244 12636317025 0025200 0 ustar 00root root 0000000 0000000 { "code": "unsupportedLanguage", "message": "Japanese is not supported by Rosette Sentiment Analyzer", "requestId": "8b433d8f-c56b-4392-abb9-694a956af778" } python-0.7.4/tests/mock-data/response/jpn-sentence-sentiment.status 0000664 0000000 0000000 00000000003 12636317025 0025543 0 ustar 00root root 0000000 0000000 415 python-0.7.4/tests/mock-data/response/ping.json 0000664 0000000 0000000 00000000112 12636317025 0021532 0 ustar 00root root 0000000 0000000 { "message":"Rosette API at your service", "time":1433962008758 } python-0.7.4/tests/mock-data/response/ping.status 0000664 0000000 0000000 00000000004 12636317025 0022104 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/pus-doc-categories.json 0000664 0000000 0000000 00000000234 12636317025 0024277 0 ustar 00root root 0000000 0000000 { "code": "unsupportedLanguage", "message": "Persian is not supported by Rosette Categorizer", "requestId": "b5178a55-1144-46b9-bb2a-aeeb154d3928" } python-0.7.4/tests/mock-data/response/pus-doc-categories.status 0000664 0000000 0000000 00000000003 12636317025 0024643 0 ustar 00root root 0000000 0000000 415 python-0.7.4/tests/mock-data/response/pus-doc-entities.json 0000664 0000000 0000000 00000032637 12636317025 0024012 0 ustar 00root root 0000000 0000000 { "entities": [ { "confidence": 0.03916314670017788, "count": 7, "indocChainId": 35, "mention": "ښاغلی", "normalized": "ښاغلی", "type": "TITLE" }, { "confidence": 0.007801820834477742, "count": 6, "indocChainId": 29, "mention": "نوماند وزير", "normalized": "نوماند وزير", "type": "TITLE" }, { "confidence": 0.03787636756896973, "count": 5, "indocChainId": 0, "mention": "افغانستان", "normalized": "افغانستان", "type": "LOCATION" }, { "confidence": 0.029533326625823975, "count": 3, "indocChainId": 15, "mention": "پارلمان", "normalized": "پارلمان", "type": "ORGANIZATION" }, { "confidence": 0.03755847613016764, "count": 3, "indocChainId": 63, "mention": "انجنير", "normalized": "انجنير", "type": "TITLE" }, { "confidence": 0.05754426121711731, "count": 2, "indocChainId": 2, "mention": "ولسمشر", "normalized": "ولسمشر", "type": "TITLE" }, { "confidence": 0.033583104610443115, "count": 2, "indocChainId": 3, "mention": "حامد كرزي", "normalized": "حامد كرزي", "type": "PERSON" }, { "confidence": 0.031616926193237305, "count": 2, "indocChainId": 4, "mention": "بهرنيو چارو د وزير", "normalized": "بهرنيو چارو د وزير", "type": "TITLE" }, { "confidence": 0.00478130578994751, "count": 2, "indocChainId": 5, "mention": "سلاكار", "normalized": "سلاكار", "type": "TITLE" }, { "confidence": 0.022341817617416382, "count": 2, "indocChainId": 6, "mention": "زلمي رسول", "normalized": "زلمي رسول", "type": "PERSON" }, { "confidence": 0.04105132818222046, "count": 2, "indocChainId": 14, "mention": "كريم خليلي", "normalized": "كريم خليلي", "type": "PERSON" }, { "confidence": 0.00576329231262207, "count": 2, "indocChainId": 17, "mention": "وزيرانو", "normalized": "وزيرانو", "type": "TITLE" }, { "confidence": 0.030164211988449097, "count": 2, "indocChainId": 33, "mention": "ډاکټر", "normalized": "ډاکټر", "type": "TITLE" }, { "confidence": 0.02519279718399048, "count": 2, "indocChainId": 57, "mention": "اغلې", "normalized": "اغلې", "type": "TITLE" }, { "confidence": 0.019838571548461914, "count": 1, "indocChainId": 13, "mention": "ولسمشر مرستيال", "normalized": "ولسمشر مرستيال", "type": "TITLE" }, { "confidence": 0.030272245407104492, "count": 1, "indocChainId": 22, "mention": "بهرنيو چارو نوماند وزير", "normalized": "بهرنيو چارو نوماند وزير", "type": "TITLE" }, { "confidence": 0.04382455348968506, "count": 1, "indocChainId": 23, "mention": "زلمی رسول", "normalized": "زلمی رسول", "type": "PERSON" }, { "confidence": 0.0041877031326293945, "count": 1, "indocChainId": 24, "mention": "ولسمشر امنيتي سلاکار", "normalized": "ولسمشر امنيتي سلاکار", "type": "TITLE" }, { "confidence": 0.028324902057647705, "count": 1, "indocChainId": 25, "mention": "عدليې نوماند وزير", "normalized": "عدليې نوماند وزير", "type": "TITLE" }, { "confidence": 0.004933297634124756, "count": 1, "indocChainId": 26, "mention": "حبيب الله غالب غالب", "normalized": "حبيب الله غالب غالب", "type": "PERSON" }, { "confidence": 0.005223214626312256, "count": 1, "indocChainId": 27, "mention": "شرعياتو", "normalized": "شرعياتو", "type": "LOCATION" }, { "confidence": 0.02999025583267212, "count": 1, "indocChainId": 28, "mention": "عبدرب رسول سياف", "normalized": "عبدرب رسول سياف", "type": "PERSON" }, { "confidence": 0.012441575527191162, "count": 1, "indocChainId": 30, "mention": "محمد هاشم عصمت الهي", "normalized": "محمد هاشم عصمت الهي", "type": "PERSON" }, { "confidence": 0.02618861198425293, "count": 1, "indocChainId": 31, "mention": "اصف محسني", "normalized": "اصف محسني", "type": "PERSON" }, { "confidence": 0.009061336517333984, "count": 1, "indocChainId": 34, "mention": "نيازی", "normalized": "نيازی", "type": "PERSON" }, { "confidence": 0.00313723087310791, "count": 1, "indocChainId": 34, "mention": "محمد يوسف نيازی", "normalized": "محمد يوسف نيازی", "type": "PERSON" }, { "confidence": 0.0046912431716918945, "count": 1, "indocChainId": 37, "mention": "عامې نوماند وزير", "normalized": "عامې نوماند وزير", "type": "TITLE" }, { "confidence": 2.962350845336914e-05, "count": 1, "indocChainId": 38, "mention": "محمد بشير لعلي", "normalized": "محمد بشير لعلي", "type": "PERSON" }, { "confidence": 0.0180090069770813, "count": 1, "indocChainId": 39, "mention": "عامې روغتيا نوماند وزير", "normalized": "عامې روغتيا نوماند وزير", "type": "TITLE" }, { "confidence": 0.01904827356338501, "count": 1, "indocChainId": 41, "mention": "ثريا", "normalized": "ثريا", "type": "PERSON" }, { "confidence": 0.002719104290008545, "count": 1, "indocChainId": 42, "mention": "کينيا", "normalized": "کينيا", "type": "LOCATION" }, { "confidence": 0.004633128643035889, "count": 1, "indocChainId": 44, "mention": "يونيسف", "normalized": "يونيسف", "type": "ORGANIZATION" }, { "confidence": 0.018250882625579834, "count": 1, "indocChainId": 45, "mention": "اقتصاد نوماند وزير", "normalized": "اقتصاد نوماند وزير", "type": "TITLE" }, { "confidence": 0.03505206108093262, "count": 1, "indocChainId": 46, "mention": "عبدالهادي ارغنديوال", "normalized": "عبدالهادي ارغنديوال", "type": "PERSON" }, { "confidence": 0.05095309019088745, "count": 1, "indocChainId": 46, "mention": "ارغنديوال", "normalized": "ارغنديوال", "type": "PERSON" }, { "confidence": 0.00369340181350708, "count": 1, "indocChainId": 49, "mention": "سوداګرۍ او صنايعو نوماند وزير", "normalized": "سوداګرۍ او صنايعو نوماند وزير", "type": "TITLE" }, { "confidence": 0.013631701469421387, "count": 1, "indocChainId": 50, "mention": "محمد هادي حکيمي", "normalized": "محمد هادي حکيمي", "type": "PERSON" }, { "confidence": 0.029611587524414062, "count": 1, "indocChainId": 50, "mention": "حکيمي", "normalized": "حکيمي", "type": "PERSON" }, { "confidence": 0.0037049055099487305, "count": 1, "indocChainId": 54, "mention": "جارالله", "normalized": "جارالله", "type": "PERSON" }, { "confidence": 0.004224538803100586, "count": 1, "indocChainId": 55, "mention": "معلولينو نوماند وزير", "normalized": "معلولينو نوماند وزير", "type": "TITLE" }, { "confidence": 0.01109844446182251, "count": 1, "indocChainId": 56, "mention": "امنه افضلي", "normalized": "امنه افضلي", "type": "PERSON" }, { "confidence": 0.034655988216400146, "count": 1, "indocChainId": 56, "mention": "افضلي", "normalized": "افضلي", "type": "PERSON" }, { "confidence": 0.010983049869537354, "count": 1, "indocChainId": 59, "mention": "چلند وزير", "normalized": "چلند وزير", "type": "TITLE" }, { "confidence": 0.004098773002624512, "count": 1, "indocChainId": 60, "mention": "عبدالرحيم اوراز", "normalized": "عبدالرحيم اوراز", "type": "PERSON" }, { "confidence": 0.08212143182754517, "count": 1, "indocChainId": 60, "mention": "عبدالرحيم", "normalized": "عبدالرحيم", "type": "PERSON" }, { "confidence": 0.004256248474121094, "count": 1, "indocChainId": 60, "mention": "اوراز", "normalized": "اوراز", "type": "PERSON" }, { "confidence": 0.03391331434249878, "count": 1, "indocChainId": 64, "mention": "بهرنيو چارو وزارت", "normalized": "بهرنيو چارو وزارت", "type": "ORGANIZATION" }, { "confidence": 0.021835267543792725, "count": 1, "indocChainId": 65, "mention": "ښځو چارو نومانده وزيره", "normalized": "ښځو چارو نومانده وزيره", "type": "TITLE" }, { "confidence": 0.004233062267303467, "count": 1, "indocChainId": 66, "mention": "پلوشه حسن", "normalized": "پلوشه حسن", "type": "PERSON" }, { "confidence": 0.03508961200714111, "count": 1, "indocChainId": 66, "mention": "حسن", "normalized": "حسن", "type": "PERSON" }, { "confidence": 0.027159810066223145, "count": 1, "indocChainId": 69, "mention": "کډوالو او راستنېدونکو چارو نوماند وزير", "normalized": "کډوالو او راستنېدونکو چارو نوماند وزير", "type": "TITLE" }, { "confidence": 0.0005469918251037598, "count": 1, "indocChainId": 72, "mention": "سرحدونو", "normalized": "سرحدونو", "type": "ORGANIZATION" }, { "confidence": 0.029864192008972168, "count": 1, "indocChainId": 74, "mention": "جمال", "normalized": "جمال", "type": "PERSON" }, { "confidence": 0.029639482498168945, "count": 1, "indocChainId": 74, "mention": "ارسلا جمال", "normalized": "ارسلا جمال", "type": "PERSON" }, { "confidence": 0.04481011629104614, "count": 1, "indocChainId": 77, "mention": "خوست", "normalized": "خوست", "type": "LOCATION" }, { "confidence": 0.022002756595611572, "count": 1, "indocChainId": 79, "mention": "مقبل", "normalized": "مقبل", "type": "PERSON" }, { "confidence": 0.019781112670898438, "count": 1, "indocChainId": 79, "mention": "ضرار احمد مقبل", "normalized": "ضرار احمد مقبل", "type": "PERSON" }, { "confidence": 0.0150221586227417, "count": 1, "indocChainId": 82, "mention": "کرزي", "normalized": "کرزي", "type": "PERSON" }, { "confidence": 0.036535441875457764, "count": 1, "indocChainId": 83, "mention": "کورنيو چار وزير", "normalized": "کورنيو چار وزير", "type": "TITLE" }, { "confidence": 0.0030456185340881348, "count": 1, "indocChainId": 86, "mention": "سلطان حسين حصاري", "normalized": "سلطان حسين حصاري", "type": "PERSON" }, { "confidence": 0.009828627109527588, "count": 1, "indocChainId": 86, "mention": "حصاري", "normalized": "حصاري", "type": "PERSON" }, { "confidence": 1.0, "count": 1, "indocChainId": 89, "mention": "http://www.trtpashto.com/trtinternational/pa/newsDetail.aspx?HaberKodu=efb3ec08-e5d5-4007-addc-0cc81652bc62", "normalized": "http://www.trtpashto.com/trtinternational/pa/newsDetail.aspx?HaberKodu=efb3ec08-e5d5-4007-addc-0cc81652bc62", "type": "IDENTIFIER:URL" } ], "requestId": "517da744-d53c-46a0-bf0a-c0f179966dbe", "timers": { "rblJe": 2, "rexJe": 42, "rliJe": 5 } } python-0.7.4/tests/mock-data/response/pus-doc-entities.status 0000664 0000000 0000000 00000000003 12636317025 0024342 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/pus-doc-entities_linked.json 0000664 0000000 0000000 00000010475 12636317025 0025334 0 ustar 00root root 0000000 0000000 { "entities": [ { "confidence": 0.6891193173120407, "entityId": "Q889", "indocChainId": 0, "mention": "افغانستان" }, { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 3, "mention": "حامد كرزي" }, { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 6, "mention": "زلمي رسول" }, { "confidence": 0.04106755494589285, "entityId": "NEW-CLUSTER", "indocChainId": 14, "mention": "كريم خليلي" }, { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 15, "mention": "پارلمان" }, { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 23, "mention": "زلمی رسول" }, { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 26, "mention": "حبيب الله غالب غالب" }, { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 27, "mention": "شرعياتو" }, { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 28, "mention": "عبدرب رسول سياف" }, { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 30, "mention": "محمد هاشم عصمت الهي" }, { "confidence": 0.19077566505957252, "entityId": "NEW-CLUSTER", "indocChainId": 31, "mention": "اصف محسني" }, { "confidence": 0.546001935291275, "entityId": "NEW-CLUSTER", "indocChainId": 34, "mention": "محمد يوسف نيازی" }, { "confidence": 0.2984344326272448, "entityId": "NEW-CLUSTER", "indocChainId": 38, "mention": "محمد بشير لعلي" }, { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 41, "mention": "ثريا" }, { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 42, "mention": "کينيا" }, { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 44, "mention": "يونيسف" }, { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 46, "mention": "عبدالهادي ارغنديوال" }, { "confidence": 0.6088921292450847, "entityId": "NEW-CLUSTER", "indocChainId": 50, "mention": "محمد هادي حکيمي" }, { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 54, "mention": "جارالله" }, { "confidence": 0.35966351039847877, "entityId": "NEW-CLUSTER", "indocChainId": 56, "mention": "امنه افضلي" }, { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 60, "mention": "عبدالرحيم اوراز" }, { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 64, "mention": "بهرنيو چارو وزارت" }, { "confidence": 0.054531806939826635, "entityId": "NEW-CLUSTER", "indocChainId": 66, "mention": "پلوشه حسن" }, { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 72, "mention": "سرحدونو" }, { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 74, "mention": "ارسلا جمال" }, { "confidence": 0.3728095979250402, "entityId": "NEW-CLUSTER", "indocChainId": 77, "mention": "خوست" }, { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 79, "mention": "ضرار احمد مقبل" }, { "confidence": 0.5933805019138657, "entityId": "NEW-CLUSTER", "indocChainId": 82, "mention": "کرزي" }, { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 86, "mention": "سلطان حسين حصاري" } ], "requestId": "3b69c759-74c9-49eb-a7f3-cbff8f7b865c", "timers": { "rblJe": 2, "res": 909, "rexJe": 27, "rliJe": 4 } } python-0.7.4/tests/mock-data/response/pus-doc-entities_linked.status 0000664 0000000 0000000 00000000003 12636317025 0025670 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/pus-doc-language.json 0000664 0000000 0000000 00000001013 12636317025 0023731 0 ustar 00root root 0000000 0000000 { "languageDetections": [ { "confidence": 0.04555813341358239, "language": "fas" }, { "confidence": 0.04536807488441863, "language": "ara" }, { "confidence": 0.040006929182747064, "language": "pus" }, { "confidence": 0.03774301454514406, "language": "kur" }, { "confidence": 0.03640237440391736, "language": "urd" } ], "requestId": "3347e76d-4bdc-4754-9adf-ee589a7e96ad", "timers": { "rliJe": 5 } } python-0.7.4/tests/mock-data/response/pus-doc-language.status 0000664 0000000 0000000 00000000003 12636317025 0024301 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/pus-doc-morphology_complete.json 0000664 0000000 0000000 00000000272 12636317025 0026243 0 ustar 00root root 0000000 0000000 { "compounds": [], "hanReadings": [], "lemmas": [], "posTags": [], "requestId": "f4eaf1f3-363a-4e56-a7b7-caf07ba6f671", "timers": { "rblJe": 2, "rliJe": 5 } } python-0.7.4/tests/mock-data/response/pus-doc-morphology_complete.status 0000664 0000000 0000000 00000000003 12636317025 0026605 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/pus-doc-sentiment.json 0000664 0000000 0000000 00000000243 12636317025 0024160 0 ustar 00root root 0000000 0000000 { "code": "unsupportedLanguage", "message": "Persian is not supported by Rosette Sentiment Analyzer", "requestId": "708e21fd-3fd8-4164-bf41-44655a81b2bb" } python-0.7.4/tests/mock-data/response/pus-doc-sentiment.status 0000664 0000000 0000000 00000000003 12636317025 0024524 0 ustar 00root root 0000000 0000000 415 python-0.7.4/tests/mock-data/response/pus-sentence-categories.json 0000664 0000000 0000000 00000000234 12636317025 0025336 0 ustar 00root root 0000000 0000000 { "code": "unsupportedLanguage", "message": "Persian is not supported by Rosette Categorizer", "requestId": "2c597ca3-a70b-4d73-bd4d-139402571fc4" } python-0.7.4/tests/mock-data/response/pus-sentence-categories.status 0000664 0000000 0000000 00000000003 12636317025 0025702 0 ustar 00root root 0000000 0000000 415 python-0.7.4/tests/mock-data/response/pus-sentence-entities.json 0000664 0000000 0000000 00000001020 12636317025 0025027 0 ustar 00root root 0000000 0000000 { "entities": [ { "confidence": 0.002526581287384033, "count": 2, "indocChainId": 1, "mention": "کوټې", "normalized": "کوټې", "type": "LOCATION" }, { "confidence": 0.0011008381843566895, "count": 1, "indocChainId": 0, "mention": "علامه", "normalized": "علامه", "type": "TITLE" } ], "requestId": "d5f167c6-4fe3-44b5-b753-b047989f58c7", "timers": { "rblJe": 0, "rexJe": 9, "rliJe": 2 } } python-0.7.4/tests/mock-data/response/pus-sentence-entities.status 0000664 0000000 0000000 00000000003 12636317025 0025401 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/pus-sentence-entities_linked.json 0000664 0000000 0000000 00000000442 12636317025 0026364 0 ustar 00root root 0000000 0000000 { "entities": [ { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 1, "mention": "کوټې" } ], "requestId": "e512c2b4-eabe-46dd-bf4c-3d758542e32a", "timers": { "rblJe": 1, "res": 27, "rexJe": 4, "rliJe": 2 } } python-0.7.4/tests/mock-data/response/pus-sentence-entities_linked.status 0000664 0000000 0000000 00000000003 12636317025 0026727 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/pus-sentence-language.json 0000664 0000000 0000000 00000001014 12636317025 0024771 0 ustar 00root root 0000000 0000000 { "languageDetections": [ { "confidence": 0.05156068771246869, "language": "fas" }, { "confidence": 0.04944655193168801, "language": "kur" }, { "confidence": 0.04115942089539337, "language": "urd" }, { "confidence": 0.040492240791045075, "language": "pus" }, { "confidence": 0.032893289522712754, "language": "ara" } ], "requestId": "44be1e91-1dbd-4bbf-9a80-fe05f3973a4c", "timers": { "rliJe": 4 } } python-0.7.4/tests/mock-data/response/pus-sentence-language.status 0000664 0000000 0000000 00000000003 12636317025 0025340 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/pus-sentence-morphology_complete.json 0000664 0000000 0000000 00000000272 12636317025 0027302 0 ustar 00root root 0000000 0000000 { "compounds": [], "hanReadings": [], "lemmas": [], "posTags": [], "requestId": "b690bd9a-845e-4418-a7d4-583c9e52071d", "timers": { "rblJe": 1, "rliJe": 4 } } python-0.7.4/tests/mock-data/response/pus-sentence-morphology_complete.status 0000664 0000000 0000000 00000000003 12636317025 0027644 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/pus-sentence-sentiment.json 0000664 0000000 0000000 00000000243 12636317025 0025217 0 ustar 00root root 0000000 0000000 { "code": "unsupportedLanguage", "message": "Persian is not supported by Rosette Sentiment Analyzer", "requestId": "94b2ac8e-150c-4566-82aa-91e8ae55e1c7" } python-0.7.4/tests/mock-data/response/pus-sentence-sentiment.status 0000664 0000000 0000000 00000000003 12636317025 0025563 0 ustar 00root root 0000000 0000000 415 python-0.7.4/tests/mock-data/response/retry-fail.json 0000664 0000000 0000000 00000000000 12636317025 0022647 0 ustar 00root root 0000000 0000000 python-0.7.4/tests/mock-data/response/retry-fail.status 0000664 0000000 0000000 00000000003 12636317025 0023224 0 ustar 00root root 0000000 0000000 600 python-0.7.4/tests/mock-data/response/rni-1-matched-name.json 0000664 0000000 0000000 00000000216 12636317025 0024051 0 ustar 00root root 0000000 0000000 { "requestId": "80dbad15-042d-4ed0-a8d7-ca26a7f4fbf9", "result": { "score": 0.8081265839595974 }, "timers": { "rni": 1 } } python-0.7.4/tests/mock-data/response/rni-1-matched-name.status 0000664 0000000 0000000 00000000003 12636317025 0024415 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/rnt-1-translated-name.json 0000664 0000000 0000000 00000000552 12636317025 0024623 0 ustar 00root root 0000000 0000000 { "requestId": "3ff324ef-b5b5-4777-b516-b4291770f038", "result": { "confidence": 1.0, "sourceLanguageOfOrigin": "zho", "sourceLanguageOfUse": "zho", "sourceScript": "Hani", "targetLanguage": "eng", "targetScheme": "HYPY_TONED", "targetScript": "Latn", "translation": "mao zedong" }, "timers": { "rnt": 2 } } python-0.7.4/tests/mock-data/response/rnt-1-translated-name.status 0000664 0000000 0000000 00000000003 12636317025 0025164 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/spa-doc-categories.json 0000664 0000000 0000000 00000000234 12636317025 0024253 0 ustar 00root root 0000000 0000000 { "code": "unsupportedLanguage", "message": "Spanish is not supported by Rosette Categorizer", "requestId": "fb4bbccf-44e0-4fd8-8a57-60a774a3c4bb" } python-0.7.4/tests/mock-data/response/spa-doc-categories.status 0000664 0000000 0000000 00000000003 12636317025 0024617 0 ustar 00root root 0000000 0000000 415 python-0.7.4/tests/mock-data/response/spa-doc-entities.json 0000664 0000000 0000000 00000007511 12636317025 0023757 0 ustar 00root root 0000000 0000000 { "entities": [ { "confidence": 0.022009849548339844, "count": 2, "indocChainId": 3, "mention": "Presidenta", "normalized": "Presidenta", "type": "TITLE" }, { "confidence": 0.027858316898345947, "count": 2, "indocChainId": 4, "mention": "Bachelet", "normalized": "Bachelet", "type": "PERSON" }, { "confidence": 0.022280961275100708, "count": 2, "indocChainId": 5, "mention": "Morales", "normalized": "Morales", "type": "PERSON" }, { "confidence": 0.014749795198440552, "count": 2, "indocChainId": 5, "mention": "Evo Morales", "normalized": "Evo Morales", "type": "PERSON" }, { "confidence": 0.015497177839279175, "count": 2, "indocChainId": 9, "mention": "Piñera", "normalized": "Piñera", "type": "PERSON" }, { "confidence": 0.0006507039070129395, "count": 1, "indocChainId": 0, "mention": "Plaza Murillo", "normalized": "Plaza Murillo", "type": "PERSON" }, { "confidence": 0.014606237411499023, "count": 1, "indocChainId": 1, "mention": "Congreso", "normalized": "Congreso", "type": "ORGANIZATION" }, { "confidence": 0.0029370784759521484, "count": 1, "indocChainId": 2, "mention": "Bolivia", "normalized": "Bolivia", "type": "LOCATION" }, { "confidence": 0.00901263952255249, "count": 1, "indocChainId": 4, "mention": "Michelle Bachelet", "normalized": "Michelle Bachelet", "type": "PERSON" }, { "confidence": 0.028369784355163574, "count": 1, "indocChainId": 9, "mention": "Sebastián Piñera", "normalized": "Sebastián Piñera", "type": "PERSON" }, { "confidence": 0.03386145830154419, "count": 1, "indocChainId": 10, "mention": "Chile", "normalized": "Chile", "type": "LOCATION" }, { "confidence": 0.002088606357574463, "count": 1, "indocChainId": 11, "mention": "Mandataria", "normalized": "Mandataria", "type": "ORGANIZATION" }, { "confidence": 0.03489595651626587, "count": 1, "indocChainId": 15, "mention": "La Paz", "normalized": "La Paz", "type": "LOCATION" }, { "confidence": 0.013820111751556396, "count": 1, "indocChainId": 17, "mention": "Eduardo Frei", "normalized": "Eduardo Frei", "type": "PERSON" }, { "confidence": 0.015299737453460693, "count": 1, "indocChainId": 18, "mention": "Presidente", "normalized": "Presidente", "type": "TITLE" }, { "confidence": 0.0008376836776733398, "count": 1, "indocChainId": 19, "mention": "Pacífico", "normalized": "Pacífico", "type": "ORGANIZATION" }, { "confidence": 0.02315753698348999, "count": 1, "indocChainId": 21, "mention": "David Choquehuanca", "normalized": "David Choquehuanca", "type": "PERSON" }, { "confidence": 1.0, "count": 1, "indocChainId": 22, "mention": "http://diario.elmercurio.com/2010/01/23/nacional/politica/noticias/47D6CA26-B011-40B5-AEAB-D0E6A5F52E59.htm?id={47D6CA26-B011-40B5-AEAB-D0E6A5F52E59}", "normalized": "http://diario.elmercurio.com/2010/01/23/nacional/politica/noticias/47D6CA26-B011-40B5-AEAB-D0E6A5F52E59.htm?id={47D6CA26-B011-40B5-AEAB-D0E6A5F52E59}", "type": "IDENTIFIER:URL" } ], "requestId": "c3de7a33-2be8-41ea-9b4b-bd683be93442", "timers": { "rblJe": 8, "rexJe": 31, "rliJe": 4 } } python-0.7.4/tests/mock-data/response/spa-doc-entities.status 0000664 0000000 0000000 00000000003 12636317025 0024316 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/spa-doc-entities_linked.json 0000664 0000000 0000000 00000003512 12636317025 0025302 0 ustar 00root root 0000000 0000000 { "entities": [ { "confidence": 0.8757866343012634, "entityId": "Q1538109", "indocChainId": 0, "mention": "Plaza Murillo" }, { "confidence": 0.23325987595467873, "entityId": "Q1968468", "indocChainId": 1, "mention": "Congreso" }, { "confidence": 0.4943574784967166, "entityId": "Q750", "indocChainId": 2, "mention": "Bolivia" }, { "confidence": 0.9709488590752338, "entityId": "Q320", "indocChainId": 4, "mention": "Michelle Bachelet" }, { "confidence": 0.9073784117252339, "entityId": "Q42410", "indocChainId": 5, "mention": "Evo Morales" }, { "confidence": 0.9782520190044777, "entityId": "Q306", "indocChainId": 9, "mention": "Sebastián Piñera" }, { "confidence": 0.44526039329725764, "entityId": "Q298", "indocChainId": 10, "mention": "Chile" }, { "confidence": 0.41413787584636874, "entityId": "NEW-CLUSTER", "indocChainId": 11, "mention": "Mandataria" }, { "confidence": 0.12817777394769103, "entityId": "Q1491", "indocChainId": 15, "mention": "La Paz" }, { "confidence": 0.40243466858079857, "entityId": "Q326", "indocChainId": 17, "mention": "Eduardo Frei" }, { "confidence": 0.34244930604731305, "entityId": "Q98", "indocChainId": 19, "mention": "Pacífico" }, { "confidence": 0.8375832214872945, "entityId": "Q58136", "indocChainId": 21, "mention": "David Choquehuanca" } ], "requestId": "702b7c21-68f4-4250-bd30-2b82eb9f5736", "timers": { "rblJe": 5, "res": 1429, "rexJe": 18, "rliJe": 3 } } python-0.7.4/tests/mock-data/response/spa-doc-entities_linked.status 0000664 0000000 0000000 00000000003 12636317025 0025644 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/spa-doc-language.json 0000664 0000000 0000000 00000001013 12636317025 0023705 0 ustar 00root root 0000000 0000000 { "languageDetections": [ { "confidence": 0.02950734817618006, "language": "spa" }, { "confidence": 0.01730801427514239, "language": "cat" }, { "confidence": 0.013157204456583083, "language": "por" }, { "confidence": 0.00902805215860436, "language": "fra" }, { "confidence": 0.00806757405890135, "language": "ron" } ], "requestId": "001a51b4-5923-4e69-8958-b661a6cc9bc5", "timers": { "rliJe": 7 } } python-0.7.4/tests/mock-data/response/spa-doc-language.status 0000664 0000000 0000000 00000000003 12636317025 0024255 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/spa-doc-morphology_complete.json 0000664 0000000 0000000 00000135026 12636317025 0026225 0 ustar 00root root 0000000 0000000 { "compounds": [], "hanReadings": [], "lemmas": [ { "lemma": "\"", "text": "\"" }, { "lemma": "entregar", "text": "Entrega" }, { "lemma": "el", "text": "el" }, { "lemma": "mar", "text": "mar" }, { "lemma": ",", "text": "," }, { "lemma": "devolver", "text": "devuelve" }, { "lemma": "el", "text": "el" }, { "lemma": "mar", "text": "mar" }, { "lemma": ".", "text": "." }, { "lemma": ".", "text": "." }, { "lemma": ".", "text": "." }, { "lemma": "\"", "text": "\"" }, { "lemma": ",", "text": "," }, { "lemma": "gritar", "text": "gritaron" }, { "lemma": "alguno", "text": "algunos" }, { "lemma": "de", "text": "de" }, { "lemma": "el", "text": "los" }, { "lemma": "ciudadano", "text": "ciudadanos" }, { "lemma": "paceño", "text": "paceños" }, { "lemma": "apostar", "text": "apostados" }, { "lemma": "en", "text": "en" }, { "lemma": "el", "text": "la" }, { "lemma": "Plaza", "text": "Plaza" }, { "lemma": "Murillo", "text": "Murillo" }, { "lemma": ",", "text": "," }, { "lemma": "a", "text": "a" }, { "lemma": "el", "text": "las" }, { "lemma": "afueras", "text": "afueras" }, { "lemma": "de el", "text": "del" }, { "lemma": "palacio", "text": "palacio" }, { "lemma": "de", "text": "de" }, { "lemma": "gobierno", "text": "gobierno" }, { "lemma": "y", "text": "y" }, { "lemma": "el", "text": "la" }, { "lemma": "sede", "text": "sede" }, { "lemma": "de el", "text": "del" }, { "lemma": "congreso", "text": "Congreso" }, { "lemma": "de", "text": "de" }, { "lemma": "Bolivia", "text": "Bolivia" }, { "lemma": ",", "text": "," }, { "lemma": "mientras", "text": "mientras" }, { "lemma": "el", "text": "la" }, { "lemma": "presidente", "text": "Presidenta" }, { "lemma": "Michelle", "text": "Michelle" }, { "lemma": "Bachelet", "text": "Bachelet" }, { "lemma": "salir", "text": "salía" }, { "lemma": "de", "text": "de" }, { "lemma": "el", "text": "la" }, { "lemma": "extenso", "text": "extensa" }, { "lemma": "ceremonia", "text": "ceremonia" }, { "lemma": "en", "text": "en" }, { "lemma": "que", "text": "que" }, { "lemma": "Evo", "text": "Evo" }, { "lemma": "Morales", "text": "Morales" }, { "lemma": "renovar", "text": "renovó" }, { "lemma": "por", "text": "por" }, { "lemma": "cinco", "text": "cinco" }, { "lemma": "año", "text": "años" }, { "lemma": "más", "text": "más" }, { "lemma": "como", "text": "como" }, { "lemma": "mandatario", "text": "Mandatario" }, { "lemma": "de", "text": "de" }, { "lemma": "ese", "text": "ese" }, { "lemma": "país", "text": "país" }, { "lemma": ".", "text": "." }, { "lemma": "el", "text": "La" }, { "lemma": "presidente", "text": "Presidenta" }, { "lemma": "ya", "text": "ya" }, { "lemma": "haber", "text": "había" }, { "lemma": "abordar", "text": "abordado" }, { "lemma": "el", "text": "el" }, { "lemma": "tema", "text": "tema" }, { "lemma": "marítimo", "text": "marítimo" }, { "lemma": "a", "text": "a" }, { "lemma": "primero", "text": "primera" }, { "lemma": "hora", "text": "hora" }, { "lemma": "de", "text": "de" }, { "lemma": "ayer", "text": "ayer" }, { "lemma": ",", "text": "," }, { "lemma": "mientras", "text": "mientras" }, { "lemma": "visitar", "text": "visitaba" }, { "lemma": "un", "text": "un" }, { "lemma": "hospital", "text": "hospital" }, { "lemma": "para", "text": "para" }, { "lemma": "niño", "text": "niños" }, { "lemma": ".", "text": "." }, { "lemma": "ahí", "text": "Ahí" }, { "lemma": ",", "text": "," }, { "lemma": "Bachelet", "text": "Bachelet" }, { "lemma": "destacar", "text": "destacó" }, { "lemma": "que", "text": "que" }, { "lemma": "en", "text": "en" }, { "lemma": "2006", "text": "2006" }, { "lemma": "haber", "text": "había" }, { "lemma": "acordar", "text": "acordado" }, { "lemma": "con", "text": "con" }, { "lemma": "moral", "text": "Morales" }, { "lemma": "un", "text": "una" }, { "lemma": "agenda", "text": "agenda" }, { "lemma": "de", "text": "de" }, { "lemma": "13", "text": "13" }, { "lemma": "punto", "text": "puntos" }, { "lemma": ",", "text": "," }, { "lemma": "en", "text": "en" }, { "lemma": "el", "text": "la" }, { "lemma": "que", "text": "que" }, { "lemma": "\"", "text": "\"" }, { "lemma": "haber", "text": "hemos" }, { "lemma": "hacer", "text": "hecho" }, { "lemma": "progreso", "text": "progresos" }, { "lemma": "importante", "text": "importantes" }, { "lemma": "\"", "text": "\"" }, { "lemma": ".", "text": "." }, { "lemma": "\"", "text": "\"" }, { "lemma": "y", "text": "Y" }, { "lemma": "todo", "text": "todos" }, { "lemma": "esperar", "text": "esperamos" }, { "lemma": "que", "text": "que" }, { "lemma": "en", "text": "en" }, { "lemma": "el", "text": "los" }, { "lemma": "año", "text": "años" }, { "lemma": "venidero", "text": "venideros" }, { "lemma": "nosotros", "text": "nuestros" }, { "lemma": "estado", "text": "Estados" }, { "lemma": "continuar", "text": "continúen" }, { "lemma": "profundizar él", "text": "profundizándola" }, { "lemma": "\"", "text": "\"" }, { "lemma": ",", "text": "," }, { "lemma": "agregar", "text": "agregó" }, { "lemma": ".", "text": "." }, { "lemma": "aludir", "text": "Aludía" }, { "lemma": "así", "text": "así" }, { "lemma": "a", "text": "a" }, { "lemma": "el", "text": "la" }, { "lemma": "agenda", "text": "agenda" }, { "lemma": "que", "text": "que" }, { "lemma": ",", "text": "," }, { "lemma": "en", "text": "en" }, { "lemma": "él", "text": "su" }, { "lemma": "punto", "text": "punto" }, { "lemma": "sexto", "text": "sexto" }, { "lemma": ",", "text": "," }, { "lemma": "contemplar", "text": "contempla" }, { "lemma": "el", "text": "el" }, { "lemma": "\"", "text": "\"" }, { "lemma": "tema", "text": "tema" }, { "lemma": "marítimo", "text": "marítimo" }, { "lemma": "\"", "text": "\"" }, { "lemma": ",", "text": "," }, { "lemma": "pero", "text": "pero" }, { "lemma": "cuyo", "text": "cuyos" }, { "lemma": "detalle", "text": "detalles" }, { "lemma": "ser", "text": "son" }, { "lemma": "poco", "text": "poco" }, { "lemma": "conocer", "text": "conocidos" }, { "lemma": ".", "text": "." }, { "lemma": "por", "text": "Por" }, { "lemma": "el", "text": "lo" }, { "lemma": "mismo", "text": "mismo" }, { "lemma": ",", "text": "," }, { "lemma": "cuando", "text": "cuando" }, { "lemma": "ser", "text": "fue" }, { "lemma": "consultar", "text": "consultada" }, { "lemma": "sobre", "text": "sobre" }, { "lemma": "qué", "text": "qué" }, { "lemma": "esperar", "text": "esperaría" }, { "lemma": "que", "text": "que" }, { "lemma": "hacer", "text": "hiciera" }, { "lemma": "sobre", "text": "sobre" }, { "lemma": "este", "text": "este" }, { "lemma": "punto", "text": "punto" }, { "lemma": "específico", "text": "específico" }, { "lemma": "él", "text": "su" }, { "lemma": "sucesor", "text": "sucesor" }, { "lemma": ",", "text": "," }, { "lemma": "Sebastián", "text": "Sebastián" }, { "lemma": "Piñera", "text": "Piñera" }, { "lemma": ",", "text": "," }, { "lemma": "él", "text": "ella" }, { "lemma": "reforzar", "text": "reforzó" }, { "lemma": "él", "text": "su" }, { "lemma": "mensaje", "text": "mensaje" }, { "lemma": ".", "text": "." }, { "lemma": "\"", "text": "\"" }, { "lemma": "el", "text": "Lo" }, { "lemma": "que", "text": "que" }, { "lemma": "tener", "text": "tiene" }, { "lemma": "que", "text": "que" }, { "lemma": "hacer", "text": "hacer" }, { "lemma": "cualquier", "text": "cualquier" }, { "lemma": "gobierno", "text": "gobierno" }, { "lemma": "en", "text": "en" }, { "lemma": "Chile", "text": "Chile" }, { "lemma": "ser", "text": "es" }, { "lemma": "seguir", "text": "seguir" }, { "lemma": "profundizar", "text": "profundizando" }, { "lemma": "todo", "text": "todos" }, { "lemma": "el", "text": "los" }, { "lemma": "punto", "text": "puntos" }, { "lemma": "de", "text": "de" }, { "lemma": "trabajo", "text": "trabajo" }, { "lemma": "en", "text": "en" }, { "lemma": "un", "text": "una" }, { "lemma": "agenda", "text": "agenda" }, { "lemma": "que", "text": "que" }, { "lemma": "haber", "text": "ha" }, { "lemma": "ser", "text": "sido" }, { "lemma": "concordar", "text": "concordada" }, { "lemma": "en", "text": "en" }, { "lemma": "común", "text": "común" }, { "lemma": "\"", "text": "\"" }, { "lemma": ",", "text": "," }, { "lemma": "decir", "text": "dijo" }, { "lemma": "el", "text": "la" }, { "lemma": "Mandataria", "text": "Mandataria" }, { "lemma": ".", "text": "." }, { "lemma": "el", "text": "La" }, { "lemma": "postura", "text": "postura" }, { "lemma": "asumir", "text": "asumida" }, { "lemma": "ayer", "text": "ayer" }, { "lemma": "por", "text": "por" }, { "lemma": "Bachelet", "text": "Bachelet" }, { "lemma": "se", "text": "se" }, { "lemma": "producir", "text": "produjo" }, { "lemma": "sólo", "text": "sólo" }, { "lemma": "día", "text": "días" }, { "lemma": "después", "text": "después" }, { "lemma": "de", "text": "de" }, { "lemma": "que", "text": "que" }, { "lemma": "Evo", "text": "Evo" }, { "lemma": "Morales", "text": "Morales" }, { "lemma": "dejar", "text": "dejara" }, { "lemma": "entrever", "text": "entrever" }, { "lemma": "él", "text": "su" }, { "lemma": "inquietud", "text": "inquietud" }, { "lemma": "por", "text": "por" }, { "lemma": "el", "text": "la" }, { "lemma": "actitud", "text": "actitud" }, { "lemma": "que", "text": "que" }, { "lemma": "tener", "text": "tendrá" }, { "lemma": "Piñera", "text": "Piñera" }, { "lemma": "ante", "text": "ante" }, { "lemma": "el", "text": "la" }, { "lemma": "aspiración", "text": "aspiración" }, { "lemma": "boliviano", "text": "boliviana" }, { "lemma": "de", "text": "de" }, { "lemma": "un", "text": "una" }, { "lemma": "salida", "text": "salida" }, { "lemma": "a el", "text": "al" }, { "lemma": "mar", "text": "mar" }, { "lemma": ".", "text": "." }, { "lemma": "en", "text": "En" }, { "lemma": "el", "text": "La" }, { "lemma": "paz", "text": "Paz" }, { "lemma": "creer", "text": "creen" }, { "lemma": "que", "text": "que" }, { "lemma": "el", "text": "el" }, { "lemma": "nuevo", "text": "nuevo" }, { "lemma": "gobernante", "text": "gobernante" }, { "lemma": "chileno", "text": "chileno" }, { "lemma": "restringir", "text": "restringirá" }, { "lemma": "a el", "text": "al" }, { "lemma": "grande", "text": "máximo" }, { "lemma": "el", "text": "el" }, { "lemma": "diálogo", "text": "diálogo" }, { "lemma": "sobre", "text": "sobre" }, { "lemma": "este", "text": "este" }, { "lemma": "punto", "text": "punto" }, { "lemma": ".", "text": "." }, { "lemma": "dicho", "text": "Dicha" }, { "lemma": "inquietud", "text": "inquietud" }, { "lemma": "tener", "text": "tuvo" }, { "lemma": "él", "text": "su" }, { "lemma": "origen", "text": "origen" }, { "lemma": "en", "text": "en" }, { "lemma": "el", "text": "el" }, { "lemma": "debate", "text": "debate" }, { "lemma": "presidencial", "text": "presidencial" }, { "lemma": "de", "text": "de" }, { "lemma": "hacer", "text": "hace" }, { "lemma": "dos", "text": "dos" }, { "lemma": "semana", "text": "semanas" }, { "lemma": "entre", "text": "entre" }, { "lemma": "Piñera", "text": "Piñera" }, { "lemma": "y", "text": "y" }, { "lemma": "Eduardo", "text": "Eduardo" }, { "lemma": "freír", "text": "Frei" }, { "lemma": ",", "text": "," }, { "lemma": "cuando", "text": "cuando" }, { "lemma": "el", "text": "el" }, { "lemma": "actual", "text": "actual" }, { "lemma": "presidente", "text": "Presidente" }, { "lemma": "electo", "text": "electo" }, { "lemma": "decir", "text": "dijo" }, { "lemma": "que", "text": "que" }, { "lemma": "no", "text": "no" }, { "lemma": "conversar", "text": "conversaría" }, { "lemma": "sobre", "text": "sobre" }, { "lemma": "cesión", "text": "cesión" }, { "lemma": "de", "text": "de" }, { "lemma": "soberanía", "text": "soberanía" }, { "lemma": "y", "text": "y" }, { "lemma": "que", "text": "que" }, { "lemma": "sólo", "text": "sólo" }, { "lemma": "tener", "text": "tenía" }, { "lemma": "en", "text": "en" }, { "lemma": "carpeta", "text": "carpeta" }, { "lemma": "mejorar", "text": "mejorar" }, { "lemma": "el", "text": "el" }, { "lemma": "acceso", "text": "acceso" }, { "lemma": "boliviano", "text": "boliviano" }, { "lemma": "a el", "text": "al" }, { "lemma": "pacífico", "text": "Pacífico" }, { "lemma": ",", "text": "," }, { "lemma": "frase", "text": "frase" }, { "lemma": "que", "text": "que" }, { "lemma": "ser", "text": "es" }, { "lemma": "leer", "text": "leída" }, { "lemma": "en", "text": "en" }, { "lemma": "el", "text": "la" }, { "lemma": "diplomacia", "text": "diplomacia" }, { "lemma": "boliviano", "text": "boliviana" }, { "lemma": "como", "text": "como" }, { "lemma": "\"", "text": "\"" }, { "lemma": "simple", "text": "simples" }, { "lemma": "facilidad", "text": "facilidades" }, { "lemma": "portuario", "text": "portuarias" }, { "lemma": "\"", "text": "\"" }, { "lemma": ".", "text": "." }, { "lemma": "Morales", "text": "Morales" }, { "lemma": "responder", "text": "respondió" }, { "lemma": "el", "text": "el" }, { "lemma": "martes", "text": "martes" }, { "lemma": "que", "text": "que" }, { "lemma": "\"", "text": "\"" }, { "lemma": "cualquier", "text": "cualquier" }, { "lemma": "compromiso", "text": "compromiso" }, { "lemma": "ser", "text": "es" }, { "lemma": "de", "text": "de" }, { "lemma": "estado", "text": "Estado" }, { "lemma": "a", "text": "a" }, { "lemma": "estado", "text": "Estado" }, { "lemma": "\"", "text": "\"" }, { "lemma": ",", "text": "," }, { "lemma": "y", "text": "y" }, { "lemma": "él", "text": "su" }, { "lemma": "canciller", "text": "canciller" }, { "lemma": ",", "text": "," }, { "lemma": "David", "text": "David" }, { "lemma": "Choquehuanca", "text": "Choquehuanca" }, { "lemma": ",", "text": "," }, { "lemma": "pedir", "text": "pidió" }, { "lemma": "mantener", "text": "mantener" }, { "lemma": "el", "text": "la" }, { "lemma": "agenda", "text": "agenda" }, { "lemma": "bilateral", "text": "bilateral" }, { "lemma": ".", "text": "." }, { "lemma": "http", "text": "http" }, { "lemma": ":", "text": ":" }, { "lemma": "/", "text": "/" }, { "lemma": "/", "text": "/" }, { "lemma": "diario.elmercurio.com", "text": "diario.elmercurio.com" }, { "lemma": "/", "text": "/" }, { "lemma": "2010", "text": "2010" }, { "lemma": "/", "text": "/" }, { "lemma": "01", "text": "01" }, { "lemma": "/", "text": "/" }, { "lemma": "23", "text": "23" }, { "lemma": "/", "text": "/" }, { "lemma": "nacional", "text": "nacional" }, { "lemma": "/", "text": "/" }, { "lemma": "política", "text": "politica" }, { "lemma": "/", "text": "/" }, { "lemma": "noticia", "text": "noticias" }, { "lemma": "/", "text": "/" }, { "lemma": "47D6CA26", "text": "47D6CA26" }, { "lemma": "-", "text": "-" }, { "lemma": "B011", "text": "B011" }, { "lemma": "-", "text": "-" }, { "lemma": "40B5", "text": "40B5" }, { "lemma": "-", "text": "-" }, { "lemma": "AEAB", "text": "AEAB" }, { "lemma": "-", "text": "-" }, { "lemma": "D0E6A5F52E59", "text": "D0E6A5F52E59" }, { "lemma": ".", "text": "." }, { "lemma": "htm", "text": "htm" }, { "lemma": "?", "text": "?" }, { "lemma": "ir", "text": "id" }, { "lemma": "=", "text": "=" }, { "lemma": "{", "text": "{" }, { "lemma": "47D6CA26", "text": "47D6CA26" }, { "lemma": "-", "text": "-" }, { "lemma": "B011", "text": "B011" }, { "lemma": "-", "text": "-" }, { "lemma": "40B5", "text": "40B5" }, { "lemma": "-", "text": "-" }, { "lemma": "AEAB", "text": "AEAB" }, { "lemma": "-", "text": "-" }, { "lemma": "D0E6A5F52E59", "text": "D0E6A5F52E59" }, { "lemma": "}", "text": "}" }, { "lemma": "2010.01.23", "text": "2010.01.23" } ], "posTags": [ { "pos": "PUNCT", "text": "\"" }, { "pos": "VERBFIN", "text": "Entrega" }, { "pos": "DETSG", "text": "el" }, { "pos": "NOUNSG", "text": "mar" }, { "pos": "CM", "text": "," }, { "pos": "VERBFIN", "text": "devuelve" }, { "pos": "DETSG", "text": "el" }, { "pos": "NOUNSG", "text": "mar" }, { "pos": "SENT", "text": "." }, { "pos": "SENT", "text": "." }, { "pos": "SENT", "text": "." }, { "pos": "PUNCT", "text": "\"" }, { "pos": "CM", "text": "," }, { "pos": "VERBFIN", "text": "gritaron" }, { "pos": "ADJPL", "text": "algunos" }, { "pos": "PREP", "text": "de" }, { "pos": "DETPL", "text": "los" }, { "pos": "NOUNPL", "text": "ciudadanos" }, { "pos": "ADJPL", "text": "paceños" }, { "pos": "PAPPL", "text": "apostados" }, { "pos": "PREP", "text": "en" }, { "pos": "DETSG", "text": "la" }, { "pos": "PROP", "text": "Plaza" }, { "pos": "PROP", "text": "Murillo" }, { "pos": "CM", "text": "," }, { "pos": "PREP", "text": "a" }, { "pos": "DETPL", "text": "las" }, { "pos": "NOUNPL", "text": "afueras" }, { "pos": "PREPDET", "text": "del" }, { "pos": "NOUNSG", "text": "palacio" }, { "pos": "PREP", "text": "de" }, { "pos": "NOUNSG", "text": "gobierno" }, { "pos": "CONJ", "text": "y" }, { "pos": "DETSG", "text": "la" }, { "pos": "NOUNSG", "text": "sede" }, { "pos": "PREPDET", "text": "del" }, { "pos": "NOUNSG", "text": "Congreso" }, { "pos": "PREP", "text": "de" }, { "pos": "PROP", "text": "Bolivia" }, { "pos": "CM", "text": "," }, { "pos": "ADV", "text": "mientras" }, { "pos": "DETSG", "text": "la" }, { "pos": "NOUNSG", "text": "Presidenta" }, { "pos": "PROP", "text": "Michelle" }, { "pos": "PROP", "text": "Bachelet" }, { "pos": "VERBFIN", "text": "salía" }, { "pos": "PREP", "text": "de" }, { "pos": "DETSG", "text": "la" }, { "pos": "ADJSG", "text": "extensa" }, { "pos": "NOUNSG", "text": "ceremonia" }, { "pos": "PREP", "text": "en" }, { "pos": "QUE", "text": "que" }, { "pos": "PROP", "text": "Evo" }, { "pos": "PROP", "text": "Morales" }, { "pos": "VERBFIN", "text": "renovó" }, { "pos": "PREP", "text": "por" }, { "pos": "NUM", "text": "cinco" }, { "pos": "NOUNPL", "text": "años" }, { "pos": "ADV", "text": "más" }, { "pos": "COMO", "text": "como" }, { "pos": "NOUNSG", "text": "Mandatario" }, { "pos": "PREP", "text": "de" }, { "pos": "DETSG", "text": "ese" }, { "pos": "NOUNSG", "text": "país" }, { "pos": "SENT", "text": "." }, { "pos": "DETSG", "text": "La" }, { "pos": "NOUNSG", "text": "Presidenta" }, { "pos": "ADV", "text": "ya" }, { "pos": "HAB", "text": "había" }, { "pos": "PAPSG", "text": "abordado" }, { "pos": "DETSG", "text": "el" }, { "pos": "NOUNSG", "text": "tema" }, { "pos": "ADJSG", "text": "marítimo" }, { "pos": "PREP", "text": "a" }, { "pos": "ADJSG", "text": "primera" }, { "pos": "NOUNSG", "text": "hora" }, { "pos": "PREP", "text": "de" }, { "pos": "ADV", "text": "ayer" }, { "pos": "CM", "text": "," }, { "pos": "ADV", "text": "mientras" }, { "pos": "VERBFIN", "text": "visitaba" }, { "pos": "DETQUANTSG", "text": "un" }, { "pos": "NOUNSG", "text": "hospital" }, { "pos": "PREP", "text": "para" }, { "pos": "NOUNPL", "text": "niños" }, { "pos": "SENT", "text": "." }, { "pos": "ADV", "text": "Ahí" }, { "pos": "CM", "text": "," }, { "pos": "PROP", "text": "Bachelet" }, { "pos": "VERBFIN", "text": "destacó" }, { "pos": "QUE", "text": "que" }, { "pos": "PREP", "text": "en" }, { "pos": "DIG", "text": "2006" }, { "pos": "HAB", "text": "había" }, { "pos": "PAPSG", "text": "acordado" }, { "pos": "PREP", "text": "con" }, { "pos": "ADJPL", "text": "Morales" }, { "pos": "DETQUANTSG", "text": "una" }, { "pos": "NOUNSG", "text": "agenda" }, { "pos": "PREP", "text": "de" }, { "pos": "DIG", "text": "13" }, { "pos": "NOUNPL", "text": "puntos" }, { "pos": "CM", "text": "," }, { "pos": "PREP", "text": "en" }, { "pos": "DETSG", "text": "la" }, { "pos": "QUE", "text": "que" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "HAB", "text": "hemos" }, { "pos": "PAPSG", "text": "hecho" }, { "pos": "NOUNPL", "text": "progresos" }, { "pos": "ADJPL", "text": "importantes" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "SENT", "text": "." }, { "pos": "PUNCT", "text": "\"" }, { "pos": "CONJ", "text": "Y" }, { "pos": "PRON", "text": "todos" }, { "pos": "VERBFIN", "text": "esperamos" }, { "pos": "QUE", "text": "que" }, { "pos": "PREP", "text": "en" }, { "pos": "DETPL", "text": "los" }, { "pos": "NOUNPL", "text": "años" }, { "pos": "ADJPL", "text": "venideros" }, { "pos": "DETPL", "text": "nuestros" }, { "pos": "NOUNPL", "text": "Estados" }, { "pos": "VERBFIN", "text": "continúen" }, { "pos": "VERBPRPCL", "text": "profundizándola" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "CM", "text": "," }, { "pos": "VERBFIN", "text": "agregó" }, { "pos": "SENT", "text": "." }, { "pos": "VERBFIN", "text": "Aludía" }, { "pos": "ADV", "text": "así" }, { "pos": "PREP", "text": "a" }, { "pos": "DETSG", "text": "la" }, { "pos": "NOUNSG", "text": "agenda" }, { "pos": "QUE", "text": "que" }, { "pos": "CM", "text": "," }, { "pos": "PREP", "text": "en" }, { "pos": "DETSG", "text": "su" }, { "pos": "NOUNSG", "text": "punto" }, { "pos": "ADJSG", "text": "sexto" }, { "pos": "CM", "text": "," }, { "pos": "VERBFIN", "text": "contempla" }, { "pos": "DETSG", "text": "el" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "NOUNSG", "text": "tema" }, { "pos": "ADJSG", "text": "marítimo" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "CM", "text": "," }, { "pos": "CONJ", "text": "pero" }, { "pos": "PRONREL", "text": "cuyos" }, { "pos": "NOUNPL", "text": "detalles" }, { "pos": "AUX", "text": "son" }, { "pos": "ADV", "text": "poco" }, { "pos": "PAPPL", "text": "conocidos" }, { "pos": "SENT", "text": "." }, { "pos": "PREP", "text": "Por" }, { "pos": "DETSG", "text": "lo" }, { "pos": "ADJSG", "text": "mismo" }, { "pos": "CM", "text": "," }, { "pos": "CONADV", "text": "cuando" }, { "pos": "AUX", "text": "fue" }, { "pos": "PAPSG", "text": "consultada" }, { "pos": "PREP", "text": "sobre" }, { "pos": "PRONINT", "text": "qué" }, { "pos": "VERBFIN", "text": "esperaría" }, { "pos": "QUE", "text": "que" }, { "pos": "VERBFIN", "text": "hiciera" }, { "pos": "PREP", "text": "sobre" }, { "pos": "DETSG", "text": "este" }, { "pos": "NOUNSG", "text": "punto" }, { "pos": "ADJSG", "text": "específico" }, { "pos": "DETSG", "text": "su" }, { "pos": "NOUNSG", "text": "sucesor" }, { "pos": "CM", "text": "," }, { "pos": "PROP", "text": "Sebastián" }, { "pos": "PROP", "text": "Piñera" }, { "pos": "CM", "text": "," }, { "pos": "PRON", "text": "ella" }, { "pos": "VERBFIN", "text": "reforzó" }, { "pos": "DETSG", "text": "su" }, { "pos": "NOUNSG", "text": "mensaje" }, { "pos": "SENT", "text": "." }, { "pos": "PUNCT", "text": "\"" }, { "pos": "DETSG", "text": "Lo" }, { "pos": "QUE", "text": "que" }, { "pos": "VERBFIN", "text": "tiene" }, { "pos": "QUE", "text": "que" }, { "pos": "VERBINF", "text": "hacer" }, { "pos": "DETQUANTSG", "text": "cualquier" }, { "pos": "NOUNSG", "text": "gobierno" }, { "pos": "PREP", "text": "en" }, { "pos": "PROP", "text": "Chile" }, { "pos": "AUX", "text": "es" }, { "pos": "VERBINF", "text": "seguir" }, { "pos": "VERBPRP", "text": "profundizando" }, { "pos": "PREDETPL", "text": "todos" }, { "pos": "DETPL", "text": "los" }, { "pos": "NOUNPL", "text": "puntos" }, { "pos": "PREP", "text": "de" }, { "pos": "NOUNSG", "text": "trabajo" }, { "pos": "PREP", "text": "en" }, { "pos": "DETQUANTSG", "text": "una" }, { "pos": "NOUNSG", "text": "agenda" }, { "pos": "QUE", "text": "que" }, { "pos": "HAB", "text": "ha" }, { "pos": "PAPSG", "text": "sido" }, { "pos": "PAPSG", "text": "concordada" }, { "pos": "PREP", "text": "en" }, { "pos": "ADJSG", "text": "común" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "CM", "text": "," }, { "pos": "VERBFIN", "text": "dijo" }, { "pos": "DETSG", "text": "la" }, { "pos": "PROP", "text": "Mandataria" }, { "pos": "SENT", "text": "." }, { "pos": "DETSG", "text": "La" }, { "pos": "NOUNSG", "text": "postura" }, { "pos": "PAPSG", "text": "asumida" }, { "pos": "ADV", "text": "ayer" }, { "pos": "PREP", "text": "por" }, { "pos": "PROP", "text": "Bachelet" }, { "pos": "SE", "text": "se" }, { "pos": "VERBFIN", "text": "produjo" }, { "pos": "ADV", "text": "sólo" }, { "pos": "NOUNPL", "text": "días" }, { "pos": "ADV", "text": "después" }, { "pos": "PREP", "text": "de" }, { "pos": "QUE", "text": "que" }, { "pos": "PROP", "text": "Evo" }, { "pos": "PROP", "text": "Morales" }, { "pos": "VERBFIN", "text": "dejara" }, { "pos": "VERBINF", "text": "entrever" }, { "pos": "DETSG", "text": "su" }, { "pos": "NOUNSG", "text": "inquietud" }, { "pos": "PREP", "text": "por" }, { "pos": "DETSG", "text": "la" }, { "pos": "NOUNSG", "text": "actitud" }, { "pos": "QUE", "text": "que" }, { "pos": "VERBFIN", "text": "tendrá" }, { "pos": "PROP", "text": "Piñera" }, { "pos": "PREP", "text": "ante" }, { "pos": "DETSG", "text": "la" }, { "pos": "NOUNSG", "text": "aspiración" }, { "pos": "ADJSG", "text": "boliviana" }, { "pos": "PREP", "text": "de" }, { "pos": "DETQUANTSG", "text": "una" }, { "pos": "NOUNSG", "text": "salida" }, { "pos": "PREPDET", "text": "al" }, { "pos": "NOUNSG", "text": "mar" }, { "pos": "SENT", "text": "." }, { "pos": "PREP", "text": "En" }, { "pos": "DETSG", "text": "La" }, { "pos": "NOUNSG", "text": "Paz" }, { "pos": "VERBFIN", "text": "creen" }, { "pos": "QUE", "text": "que" }, { "pos": "DETSG", "text": "el" }, { "pos": "ADJSG", "text": "nuevo" }, { "pos": "NOUNSG", "text": "gobernante" }, { "pos": "ADJSG", "text": "chileno" }, { "pos": "VERBFIN", "text": "restringirá" }, { "pos": "PREPDET", "text": "al" }, { "pos": "ADJSG", "text": "máximo" }, { "pos": "DETSG", "text": "el" }, { "pos": "NOUNSG", "text": "diálogo" }, { "pos": "PREP", "text": "sobre" }, { "pos": "DETSG", "text": "este" }, { "pos": "NOUNSG", "text": "punto" }, { "pos": "SENT", "text": "." }, { "pos": "DETSG", "text": "Dicha" }, { "pos": "NOUNSG", "text": "inquietud" }, { "pos": "VERBFIN", "text": "tuvo" }, { "pos": "DETSG", "text": "su" }, { "pos": "NOUNSG", "text": "origen" }, { "pos": "PREP", "text": "en" }, { "pos": "DETSG", "text": "el" }, { "pos": "NOUNSG", "text": "debate" }, { "pos": "ADJSG", "text": "presidencial" }, { "pos": "PREP", "text": "de" }, { "pos": "VERBFIN", "text": "hace" }, { "pos": "NUM", "text": "dos" }, { "pos": "NOUNPL", "text": "semanas" }, { "pos": "PREP", "text": "entre" }, { "pos": "PROP", "text": "Piñera" }, { "pos": "CONJ", "text": "y" }, { "pos": "PROP", "text": "Eduardo" }, { "pos": "VERBFIN", "text": "Frei" }, { "pos": "CM", "text": "," }, { "pos": "CONADV", "text": "cuando" }, { "pos": "DETSG", "text": "el" }, { "pos": "ADJSG", "text": "actual" }, { "pos": "NOUNSG", "text": "Presidente" }, { "pos": "ADJSG", "text": "electo" }, { "pos": "VERBFIN", "text": "dijo" }, { "pos": "QUE", "text": "que" }, { "pos": "ADVNEG", "text": "no" }, { "pos": "VERBFIN", "text": "conversaría" }, { "pos": "PREP", "text": "sobre" }, { "pos": "NOUNSG", "text": "cesión" }, { "pos": "PREP", "text": "de" }, { "pos": "NOUNSG", "text": "soberanía" }, { "pos": "CONJ", "text": "y" }, { "pos": "QUE", "text": "que" }, { "pos": "ADV", "text": "sólo" }, { "pos": "VERBFIN", "text": "tenía" }, { "pos": "PREP", "text": "en" }, { "pos": "NOUNSG", "text": "carpeta" }, { "pos": "VERBINF", "text": "mejorar" }, { "pos": "DETSG", "text": "el" }, { "pos": "NOUNSG", "text": "acceso" }, { "pos": "ADJSG", "text": "boliviano" }, { "pos": "PREPDET", "text": "al" }, { "pos": "ADJSG", "text": "Pacífico" }, { "pos": "CM", "text": "," }, { "pos": "NOUNSG", "text": "frase" }, { "pos": "QUE", "text": "que" }, { "pos": "AUX", "text": "es" }, { "pos": "PAPSG", "text": "leída" }, { "pos": "PREP", "text": "en" }, { "pos": "DETSG", "text": "la" }, { "pos": "NOUNSG", "text": "diplomacia" }, { "pos": "ADJSG", "text": "boliviana" }, { "pos": "COMO", "text": "como" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "ADJPL", "text": "simples" }, { "pos": "NOUNPL", "text": "facilidades" }, { "pos": "ADJPL", "text": "portuarias" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "SENT", "text": "." }, { "pos": "PROP", "text": "Morales" }, { "pos": "VERBFIN", "text": "respondió" }, { "pos": "DETSG", "text": "el" }, { "pos": "NOUN", "text": "martes" }, { "pos": "QUE", "text": "que" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "DETQUANTSG", "text": "cualquier" }, { "pos": "NOUNSG", "text": "compromiso" }, { "pos": "AUX", "text": "es" }, { "pos": "PREP", "text": "de" }, { "pos": "NOUNSG", "text": "Estado" }, { "pos": "PREP", "text": "a" }, { "pos": "NOUNSG", "text": "Estado" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "CM", "text": "," }, { "pos": "CONJ", "text": "y" }, { "pos": "DETSG", "text": "su" }, { "pos": "NOUNSG", "text": "canciller" }, { "pos": "CM", "text": "," }, { "pos": "PROP", "text": "David" }, { "pos": "PROP", "text": "Choquehuanca" }, { "pos": "CM", "text": "," }, { "pos": "VERBFIN", "text": "pidió" }, { "pos": "VERBINF", "text": "mantener" }, { "pos": "DETSG", "text": "la" }, { "pos": "NOUNSG", "text": "agenda" }, { "pos": "ADJSG", "text": "bilateral" }, { "pos": "SENT", "text": "." }, { "pos": "PROP", "text": "http" }, { "pos": "PUNCT", "text": ":" }, { "pos": "PUNCT", "text": "/" }, { "pos": "PUNCT", "text": "/" }, { "pos": "PROP", "text": "diario.elmercurio.com" }, { "pos": "PUNCT", "text": "/" }, { "pos": "DIG", "text": "2010" }, { "pos": "PUNCT", "text": "/" }, { "pos": "DIG", "text": "01" }, { "pos": "PUNCT", "text": "/" }, { "pos": "DIG", "text": "23" }, { "pos": "PUNCT", "text": "/" }, { "pos": "ADJSG", "text": "nacional" }, { "pos": "PUNCT", "text": "/" }, { "pos": "NOUNSG", "text": "politica" }, { "pos": "PUNCT", "text": "/" }, { "pos": "NOUNPL", "text": "noticias" }, { "pos": "PUNCT", "text": "/" }, { "pos": "PROP", "text": "47D6CA26" }, { "pos": "PUNCT", "text": "-" }, { "pos": "PROP", "text": "B011" }, { "pos": "PUNCT", "text": "-" }, { "pos": "PROP", "text": "40B5" }, { "pos": "PUNCT", "text": "-" }, { "pos": "PROP", "text": "AEAB" }, { "pos": "PUNCT", "text": "-" }, { "pos": "PROP", "text": "D0E6A5F52E59" }, { "pos": "SENT", "text": "." }, { "pos": "PROP", "text": "htm" }, { "pos": "SENT", "text": "?" }, { "pos": "VERBIMP", "text": "id" }, { "pos": "PUNCT", "text": "=" }, { "pos": "PUNCT", "text": "{" }, { "pos": "PROP", "text": "47D6CA26" }, { "pos": "PUNCT", "text": "-" }, { "pos": "PROP", "text": "B011" }, { "pos": "PUNCT", "text": "-" }, { "pos": "PROP", "text": "40B5" }, { "pos": "PUNCT", "text": "-" }, { "pos": "PROP", "text": "AEAB" }, { "pos": "PUNCT", "text": "-" }, { "pos": "PROP", "text": "D0E6A5F52E59" }, { "pos": "PUNCT", "text": "}" }, { "pos": "DIG", "text": "2010.01.23" } ], "requestId": "adcc0f54-1882-44af-ae25-2de733ee5ca0", "timers": { "rblJe": 76, "rliJe": 3 } } python-0.7.4/tests/mock-data/response/spa-doc-morphology_complete.status 0000664 0000000 0000000 00000000003 12636317025 0026561 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/spa-doc-sentiment.json 0000664 0000000 0000000 00000000243 12636317025 0024134 0 ustar 00root root 0000000 0000000 { "code": "unsupportedLanguage", "message": "Spanish is not supported by Rosette Sentiment Analyzer", "requestId": "d28578c3-6f62-4285-8dcb-059b41bab1bf" } python-0.7.4/tests/mock-data/response/spa-doc-sentiment.status 0000664 0000000 0000000 00000000003 12636317025 0024500 0 ustar 00root root 0000000 0000000 415 python-0.7.4/tests/mock-data/response/spa-sentence-categories.json 0000664 0000000 0000000 00000000234 12636317025 0025312 0 ustar 00root root 0000000 0000000 { "code": "unsupportedLanguage", "message": "Spanish is not supported by Rosette Categorizer", "requestId": "ecb91ac3-13e4-4c26-9647-6cd970e45ca1" } python-0.7.4/tests/mock-data/response/spa-sentence-categories.status 0000664 0000000 0000000 00000000003 12636317025 0025656 0 ustar 00root root 0000000 0000000 415 python-0.7.4/tests/mock-data/response/spa-sentence-entities.json 0000664 0000000 0000000 00000002465 12636317025 0025021 0 ustar 00root root 0000000 0000000 { "entities": [ { "confidence": 0.0033197999000549316, "count": 2, "indocChainId": 0, "mention": "UE", "normalized": "UE", "type": "LOCATION" }, { "confidence": 0.009455502033233643, "count": 1, "indocChainId": 1, "mention": "Catherine Ashton", "normalized": "Catherine Ashton", "type": "PERSON" }, { "confidence": 0.0019090771675109863, "count": 1, "indocChainId": 2, "mention": "Parlamento Europeo", "normalized": "Parlamento Europeo", "type": "ORGANIZATION" }, { "confidence": 0.005295395851135254, "count": 1, "indocChainId": 3, "mention": "Rumiana Jeleva", "normalized": "Rumiana Jeleva", "type": "PERSON" }, { "confidence": 0.0053885579109191895, "count": 1, "indocChainId": 5, "mention": "Lisboa", "normalized": "Lisboa", "type": "LOCATION" }, { "confidence": 0.01570659875869751, "count": 1, "indocChainId": 6, "mention": "Estados Unidos", "normalized": "Estados Unidos", "type": "LOCATION" } ], "requestId": "e47ff33c-c014-4d19-8a7f-1f226b23ce3d", "timers": { "rblJe": 2, "rexJe": 11, "rliJe": 5 } } python-0.7.4/tests/mock-data/response/spa-sentence-entities.status 0000664 0000000 0000000 00000000003 12636317025 0025355 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/spa-sentence-entities_linked.json 0000664 0000000 0000000 00000001756 12636317025 0026351 0 ustar 00root root 0000000 0000000 { "entities": [ { "confidence": 0.6557350718108463, "entityId": "Q458", "indocChainId": 0, "mention": "UE" }, { "confidence": 0.7240138955711336, "entityId": "Q105667", "indocChainId": 1, "mention": "Catherine Ashton" }, { "confidence": 0.7886346514534216, "entityId": "Q8889", "indocChainId": 2, "mention": "Parlamento Europeo" }, { "confidence": 0.6030876370798988, "entityId": "Q242313", "indocChainId": 3, "mention": "Rumiana Jeleva" }, { "confidence": 0.5486312188826928, "entityId": "Q597", "indocChainId": 5, "mention": "Lisboa" }, { "confidence": 0.6532048679662522, "entityId": "Q30", "indocChainId": 6, "mention": "Estados Unidos" } ], "requestId": "e8f5ca40-71c8-40d8-98b3-0b6b7d61e309", "timers": { "rblJe": 2, "res": 86, "rexJe": 4, "rliJe": 4 } } python-0.7.4/tests/mock-data/response/spa-sentence-entities_linked.status 0000664 0000000 0000000 00000000003 12636317025 0026703 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/spa-sentence-language.json 0000664 0000000 0000000 00000001016 12636317025 0024747 0 ustar 00root root 0000000 0000000 { "languageDetections": [ { "confidence": 0.02481541281976518, "language": "spa" }, { "confidence": 0.013600772881528722, "language": "cat" }, { "confidence": 0.012785839526927134, "language": "por" }, { "confidence": 0.010117305737785909, "language": "ron" }, { "confidence": 0.007932821892276065, "language": "fra" } ], "requestId": "669af974-87e6-465f-bec2-3b3d3f01eadf", "timers": { "rliJe": 3 } } python-0.7.4/tests/mock-data/response/spa-sentence-language.status 0000664 0000000 0000000 00000000003 12636317025 0025314 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/spa-sentence-morphology_complete.json 0000664 0000000 0000000 00000024111 12636317025 0027254 0 ustar 00root root 0000000 0000000 { "compounds": [], "hanReadings": [], "lemmas": [ { "lemma": "el", "text": "La" }, { "lemma": "crisis", "text": "crisis" }, { "lemma": "se", "text": "se" }, { "lemma": "haber", "text": "ha" }, { "lemma": "producir", "text": "producido" }, { "lemma": "en", "text": "en" }, { "lemma": "un", "text": "un" }, { "lemma": "tiempo", "text": "tiempo" }, { "lemma": "de", "text": "de" }, { "lemma": "transición", "text": "transición" }, { "lemma": "burocrático", "text": "burocrática" }, { "lemma": ".", "text": "." }, { "lemma": "el", "text": "La" }, { "lemma": "nuevo", "text": "nueva" }, { "lemma": "zarina", "text": "zarina" }, { "lemma": "de", "text": "de" }, { "lemma": "el", "text": "la" }, { "lemma": "política", "text": "Política" }, { "lemma": "exterior", "text": "Exterior" }, { "lemma": "de", "text": "de" }, { "lemma": "el", "text": "la" }, { "lemma": "UE", "text": "UE" }, { "lemma": ",", "text": "," }, { "lemma": "Catherine", "text": "Catherine" }, { "lemma": "Ashton", "text": "Ashton" }, { "lemma": ",", "text": "," }, { "lemma": "deber", "text": "debe" }, { "lemma": "aún", "text": "aún" }, { "lemma": "afianzar se", "text": "afianzarse" }, { "lemma": "en", "text": "en" }, { "lemma": "él", "text": "su" }, { "lemma": "puesto", "text": "puesto" }, { "lemma": "y", "text": "y" }, { "lemma": "el", "text": "el" }, { "lemma": "parlamento", "text": "Parlamento" }, { "lemma": "europeo", "text": "Europeo" }, { "lemma": "haber", "text": "ha" }, { "lemma": "impedir", "text": "impedido" }, { "lemma": "el", "text": "el" }, { "lemma": "nombramiento", "text": "nombramiento" }, { "lemma": "de", "text": "de" }, { "lemma": "el", "text": "la" }, { "lemma": "designar", "text": "designada" }, { "lemma": "comisario", "text": "comisaria" }, { "lemma": "Rumiana", "text": "Rumiana" }, { "lemma": "Jeleva", "text": "Jeleva" }, { "lemma": ",", "text": "," }, { "lemma": "cuyo", "text": "cuyo" }, { "lemma": "cometer", "text": "cometido" }, { "lemma": "incluir", "text": "incluía" }, { "lemma": "el", "text": "la" }, { "lemma": "ayuda", "text": "ayuda" }, { "lemma": "humanitario", "text": "humanitaria" }, { "lemma": ".", "text": "." }, { "lemma": "como", "text": "Como" }, { "lemma": "resultado", "text": "resultado" }, { "lemma": ",", "text": "," }, { "lemma": "el", "text": "la" }, { "lemma": "respuesta", "text": "respuesta" }, { "lemma": "de", "text": "de" }, { "lemma": "el", "text": "la" }, { "lemma": "UE", "text": "UE" }, { "lemma": "parecer", "text": "parece" }, { "lemma": "revestir", "text": "revestir" }, { "lemma": "todo", "text": "todos" }, { "lemma": "el", "text": "los" }, { "lemma": "signo", "text": "signos" }, { "lemma": "de", "text": "de" }, { "lemma": "el", "text": "la" }, { "lemma": "política", "text": "política" }, { "lemma": "previo", "text": "previa" }, { "lemma": "a el", "text": "al" }, { "lemma": "tratado", "text": "Tratado" }, { "lemma": "de", "text": "de" }, { "lemma": "Lisboa", "text": "Lisboa" }, { "lemma": ":", "text": ":" }, { "lemma": "lento", "text": "lenta" }, { "lemma": ",", "text": "," }, { "lemma": "tecnocrático", "text": "tecnocrática" }, { "lemma": "y", "text": "y" }, { "lemma": "eclipsar", "text": "eclipsada" }, { "lemma": "por", "text": "por" }, { "lemma": "estado", "text": "Estados" }, { "lemma": "unir", "text": "Unidos" }, { "lemma": ".", "text": "." } ], "posTags": [ { "pos": "DETSG", "text": "La" }, { "pos": "NOUN", "text": "crisis" }, { "pos": "SE", "text": "se" }, { "pos": "HAB", "text": "ha" }, { "pos": "PAPSG", "text": "producido" }, { "pos": "PREP", "text": "en" }, { "pos": "DETQUANTSG", "text": "un" }, { "pos": "NOUNSG", "text": "tiempo" }, { "pos": "PREP", "text": "de" }, { "pos": "NOUNSG", "text": "transición" }, { "pos": "ADJSG", "text": "burocrática" }, { "pos": "SENT", "text": "." }, { "pos": "DETSG", "text": "La" }, { "pos": "ADJSG", "text": "nueva" }, { "pos": "NOUNSG", "text": "zarina" }, { "pos": "PREP", "text": "de" }, { "pos": "DETSG", "text": "la" }, { "pos": "NOUNSG", "text": "Política" }, { "pos": "ADJSG", "text": "Exterior" }, { "pos": "PREP", "text": "de" }, { "pos": "DETSG", "text": "la" }, { "pos": "PROP", "text": "UE" }, { "pos": "CM", "text": "," }, { "pos": "PROP", "text": "Catherine" }, { "pos": "PROP", "text": "Ashton" }, { "pos": "CM", "text": "," }, { "pos": "VERBFIN", "text": "debe" }, { "pos": "ADV", "text": "aún" }, { "pos": "VERBINFCL", "text": "afianzarse" }, { "pos": "PREP", "text": "en" }, { "pos": "DETSG", "text": "su" }, { "pos": "NOUNSG", "text": "puesto" }, { "pos": "CONJ", "text": "y" }, { "pos": "DETSG", "text": "el" }, { "pos": "NOUNSG", "text": "Parlamento" }, { "pos": "ADJSG", "text": "Europeo" }, { "pos": "HAB", "text": "ha" }, { "pos": "PAPSG", "text": "impedido" }, { "pos": "DETSG", "text": "el" }, { "pos": "NOUNSG", "text": "nombramiento" }, { "pos": "PREP", "text": "de" }, { "pos": "DETSG", "text": "la" }, { "pos": "PAPSG", "text": "designada" }, { "pos": "NOUNSG", "text": "comisaria" }, { "pos": "PROP", "text": "Rumiana" }, { "pos": "PROP", "text": "Jeleva" }, { "pos": "CM", "text": "," }, { "pos": "PRONREL", "text": "cuyo" }, { "pos": "PAPSG", "text": "cometido" }, { "pos": "VERBFIN", "text": "incluía" }, { "pos": "DETSG", "text": "la" }, { "pos": "NOUNSG", "text": "ayuda" }, { "pos": "ADJSG", "text": "humanitaria" }, { "pos": "SENT", "text": "." }, { "pos": "COMO", "text": "Como" }, { "pos": "NOUNSG", "text": "resultado" }, { "pos": "CM", "text": "," }, { "pos": "DETSG", "text": "la" }, { "pos": "NOUNSG", "text": "respuesta" }, { "pos": "PREP", "text": "de" }, { "pos": "DETSG", "text": "la" }, { "pos": "PROP", "text": "UE" }, { "pos": "VERBFIN", "text": "parece" }, { "pos": "VERBINF", "text": "revestir" }, { "pos": "PREDETPL", "text": "todos" }, { "pos": "DETPL", "text": "los" }, { "pos": "NOUNPL", "text": "signos" }, { "pos": "PREP", "text": "de" }, { "pos": "DETSG", "text": "la" }, { "pos": "NOUNSG", "text": "política" }, { "pos": "ADJSG", "text": "previa" }, { "pos": "PREPDET", "text": "al" }, { "pos": "NOUNSG", "text": "Tratado" }, { "pos": "PREP", "text": "de" }, { "pos": "PROP", "text": "Lisboa" }, { "pos": "PUNCT", "text": ":" }, { "pos": "ADJSG", "text": "lenta" }, { "pos": "CM", "text": "," }, { "pos": "ADJSG", "text": "tecnocrática" }, { "pos": "CONJ", "text": "y" }, { "pos": "PAPSG", "text": "eclipsada" }, { "pos": "PREP", "text": "por" }, { "pos": "NOUNPL", "text": "Estados" }, { "pos": "PAPPL", "text": "Unidos" }, { "pos": "SENT", "text": "." } ], "requestId": "efce6fd2-297f-4cde-8f10-b253185d677d", "timers": { "rblJe": 6, "rliJe": 2 } } python-0.7.4/tests/mock-data/response/spa-sentence-morphology_complete.status 0000664 0000000 0000000 00000000003 12636317025 0027620 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/spa-sentence-sentiment.json 0000664 0000000 0000000 00000000243 12636317025 0025173 0 ustar 00root root 0000000 0000000 { "code": "unsupportedLanguage", "message": "Spanish is not supported by Rosette Sentiment Analyzer", "requestId": "56586ce3-fffe-4571-8035-1e5fc595ca48" } python-0.7.4/tests/mock-data/response/spa-sentence-sentiment.status 0000664 0000000 0000000 00000000003 12636317025 0025537 0 ustar 00root root 0000000 0000000 415 python-0.7.4/tests/mock-data/response/spa-url-categories.json 0000664 0000000 0000000 00000000234 12636317025 0024310 0 ustar 00root root 0000000 0000000 { "code": "unsupportedLanguage", "message": "Spanish is not supported by Rosette Categorizer", "requestId": "57859621-291e-4bb1-bc36-f39fadf7ce37" } python-0.7.4/tests/mock-data/response/spa-url-categories.status 0000664 0000000 0000000 00000000003 12636317025 0024654 0 ustar 00root root 0000000 0000000 415 python-0.7.4/tests/mock-data/response/spa-url-entities.json 0000664 0000000 0000000 00000005657 12636317025 0024025 0 ustar 00root root 0000000 0000000 { "entities": [ { "confidence": 0.011255035797754923, "count": 6, "indocChainId": 1, "mention": "Colombia", "normalized": "Colombia", "type": "LOCATION" }, { "confidence": 0.026651740074157715, "count": 4, "indocChainId": 8, "mention": "México", "normalized": "México", "type": "LOCATION" }, { "confidence": 0.017740070819854736, "count": 2, "indocChainId": 3, "mention": "presidente", "normalized": "presidente", "type": "TITLE" }, { "confidence": 0.012101918458938599, "count": 2, "indocChainId": 6, "mention": "Enrique Peña Nieto", "normalized": "Enrique Peña Nieto", "type": "PERSON" }, { "confidence": 0.01789921522140503, "count": 2, "indocChainId": 11, "mention": "Juan Manuel Santos", "normalized": "Juan Manuel Santos", "type": "PERSON" }, { "confidence": 0.0028449296951293945, "count": 1, "indocChainId": 0, "mention": "SECCIONES\nSociedad\nMéxico", "normalized": "SECCIONES Sociedad México", "type": "ORGANIZATION" }, { "confidence": 0.007503092288970947, "count": 1, "indocChainId": 2, "mention": "EPN", "normalized": "EPN", "type": "ORGANIZATION" }, { "confidence": 0.00871974229812622, "count": 1, "indocChainId": 11, "mention": "Manuel Santos", "normalized": "Manuel Santos", "type": "PERSON" }, { "confidence": 0.027437686920166016, "count": 1, "indocChainId": 18, "mention": "Alianza Pacífico", "normalized": "Alianza Pacífico", "type": "ORGANIZATION" }, { "confidence": 0.056813716888427734, "count": 1, "indocChainId": 20, "mention": "Perú", "normalized": "Perú", "type": "LOCATION" }, { "confidence": 0.062174439430236816, "count": 1, "indocChainId": 21, "mention": "Chile", "normalized": "Chile", "type": "LOCATION" }, { "confidence": 0.04952973127365112, "count": 1, "indocChainId": 22, "mention": "América Latina", "normalized": "América Latina", "type": "LOCATION" }, { "confidence": 0.014632940292358398, "count": 1, "indocChainId": 23, "mention": "Pacífico", "normalized": "Pacífico", "type": "LOCATION" }, { "confidence": 0.02009981870651245, "count": 1, "indocChainId": 24, "mention": "Peña Nieto Ver", "normalized": "Peña Nieto Ver", "type": "PERSON" } ], "requestId": "f0cfd156-e9cd-4c97-bb0e-0337fad05458", "timers": { "rblJe": 1, "rexJe": 60, "rliJe": 4, "textExtractor": 18, "urlContentDownloader": 243 } } python-0.7.4/tests/mock-data/response/spa-url-entities.status 0000664 0000000 0000000 00000000003 12636317025 0024353 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/spa-url-entities_linked.json 0000664 0000000 0000000 00000003612 12636317025 0025340 0 ustar 00root root 0000000 0000000 { "entities": [ { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 0, "mention": "SECCIONES Sociedad México" }, { "confidence": 0.3842942678466512, "entityId": "Q739", "indocChainId": 1, "mention": "Colombia" }, { "confidence": 0.29145007042506105, "entityId": "Q296741", "indocChainId": 2, "mention": "EPN" }, { "confidence": 0.9576033902530637, "entityId": "Q296741", "indocChainId": 6, "mention": "Enrique Peña Nieto" }, { "confidence": 0.25986302388359683, "entityId": "Q96", "indocChainId": 8, "mention": "México" }, { "confidence": 0.8635177623456834, "entityId": "Q57311", "indocChainId": 11, "mention": "Juan Manuel Santos" }, { "confidence": 0.31713577301095347, "entityId": "Q7122288", "indocChainId": 18, "mention": "Alianza Pacífico" }, { "confidence": 0.5114125729137015, "entityId": "Q419", "indocChainId": 20, "mention": "Perú" }, { "confidence": 0.30983850993114276, "entityId": "Q298", "indocChainId": 21, "mention": "Chile" }, { "confidence": 0.8050428060258218, "entityId": "Q12585", "indocChainId": 22, "mention": "América Latina" }, { "confidence": 0.41896853374939264, "entityId": "Q98", "indocChainId": 23, "mention": "Pacífico" }, { "confidence": 0.9132640852566012, "entityId": "NEW-CLUSTER", "indocChainId": 24, "mention": "Peña Nieto Ver" } ], "requestId": "f7202522-6e5c-4635-ba9d-867f4b96352f", "timers": { "rblJe": 1, "res": 944, "rexJe": 12, "rliJe": 4, "textExtractor": 14, "urlContentDownloader": 279 } } python-0.7.4/tests/mock-data/response/spa-url-entities_linked.status 0000664 0000000 0000000 00000000003 12636317025 0025701 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/spa-url-language.json 0000664 0000000 0000000 00000001114 12636317025 0023744 0 ustar 00root root 0000000 0000000 { "languageDetections": [ { "confidence": 0.029893909972914412, "language": "spa" }, { "confidence": 0.01496215995459671, "language": "cat" }, { "confidence": 0.012349912140416586, "language": "por" }, { "confidence": 0.009009841891852277, "language": "fra" }, { "confidence": 0.007744138165555303, "language": "ita" } ], "requestId": "7f05d390-d540-4cfd-acbc-ffc00a594318", "timers": { "rliJe": 2, "textExtractor": 160, "urlContentDownloader": 2190 } } python-0.7.4/tests/mock-data/response/spa-url-language.status 0000664 0000000 0000000 00000000003 12636317025 0024312 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/spa-url-morphology_complete.json 0000664 0000000 0000000 00000066425 12636317025 0026270 0 ustar 00root root 0000000 0000000 { "compounds": [], "hanReadings": [], "lemmas": [ { "lemma": "00", "text": "00" }, { "lemma": "00", "text": "00" }, { "lemma": "00", "text": "00" }, { "lemma": "|", "text": "|" }, { "lemma": "00:00", "text": "00:00" }, { "lemma": "sección", "text": "SECCIONES" }, { "lemma": "sociedad", "text": "Sociedad" }, { "lemma": "México", "text": "México" }, { "lemma": "y", "text": "y" }, { "lemma": "Colombia", "text": "Colombia" }, { "lemma": ",", "text": "," }, { "lemma": "nación", "text": "naciones" }, { "lemma": "con", "text": "con" }, { "lemma": "objetivo", "text": "objetivos" }, { "lemma": "común", "text": "comunes" }, { "lemma": ":", "text": ":" }, { "lemma": "EPN", "text": "EPN" }, { "lemma": "en", "text": "En" }, { "lemma": "el", "text": "el" }, { "lemma": "marco", "text": "marco" }, { "lemma": "de", "text": "de" }, { "lemma": "el", "text": "la" }, { "lemma": "visita", "text": "visita" }, { "lemma": "de", "text": "de" }, { "lemma": "estado", "text": "Estado" }, { "lemma": "y", "text": "y" }, { "lemma": "el", "text": "la" }, { "lemma": "ceremonia", "text": "ceremonia" }, { "lemma": "oficial", "text": "oficial" }, { "lemma": "de", "text": "de" }, { "lemma": "bienvenido", "text": "bienvenida" }, { "lemma": "a el", "text": "al" }, { "lemma": "presidente", "text": "presidente" }, { "lemma": "de", "text": "de" }, { "lemma": "Colombia", "text": "Colombia" }, { "lemma": ",", "text": "," }, { "lemma": "juan", "text": "juan" }, { "lemma": "Manuel", "text": "Manuel" }, { "lemma": "Santos", "text": "Santos" }, { "lemma": ",", "text": "," }, { "lemma": "el", "text": "el" }, { "lemma": "mandatario", "text": "mandatario" }, { "lemma": "mexicano", "text": "mexicano" }, { "lemma": ",", "text": "," }, { "lemma": "Enrique", "text": "Enrique" }, { "lemma": "Peña", "text": "Peña" }, { "lemma": "Nieto", "text": "Nieto" }, { "lemma": "destacar", "text": "destacó" }, { "lemma": "que", "text": "que" }, { "lemma": "Colombia", "text": "Colombia" }, { "lemma": "y", "text": "y" }, { "lemma": "México", "text": "México" }, { "lemma": "ser", "text": "son" }, { "lemma": "dos", "text": "dos" }, { "lemma": "nación", "text": "naciones" }, { "lemma": "hermano", "text": "hermanas" }, { "lemma": ",", "text": "," }, { "lemma": "unir", "text": "unidas" }, { "lemma": "por", "text": "por" }, { "lemma": "valor", "text": "valores" }, { "lemma": ",", "text": "," }, { "lemma": "afecto", "text": "afectos" }, { "lemma": "y", "text": "y" }, { "lemma": "objetivo", "text": "objetivos" }, { "lemma": "común", "text": "comunes" }, { "lemma": ".", "text": "." }, { "lemma": "compartir", "text": "compartir" }, { "lemma": "en", "text": "en" }, { "lemma": ":", "text": ":" }, { "lemma": "por", "text": "Por" }, { "lemma": ":", "text": ":" }, { "lemma": "redacción", "text": "Redacción" }, { "lemma": "viernes", "text": "Viernes" }, { "lemma": "08", "text": "08" }, { "lemma": "05", "text": "05" }, { "lemma": "15", "text": "15" }, { "lemma": "en", "text": "En" }, { "lemma": "el", "text": "el" }, { "lemma": "marco", "text": "marco" }, { "lemma": "de", "text": "de" }, { "lemma": "el", "text": "la" }, { "lemma": "visita", "text": "visita" }, { "lemma": "de", "text": "de" }, { "lemma": "estado", "text": "Estado" }, { "lemma": "y", "text": "y" }, { "lemma": "el", "text": "la" }, { "lemma": "ceremonia", "text": "ceremonia" }, { "lemma": "oficial", "text": "oficial" }, { "lemma": "de", "text": "de" }, { "lemma": "bienvenido", "text": "bienvenida" }, { "lemma": "a el", "text": "al" }, { "lemma": "presidente", "text": "presidente" }, { "lemma": "de", "text": "de" }, { "lemma": "Colombia", "text": "Colombia" }, { "lemma": ",", "text": "," }, { "lemma": "Juan", "text": "Juan" }, { "lemma": "Manuel", "text": "Manuel" }, { "lemma": "Santos", "text": "Santos" }, { "lemma": ",", "text": "," }, { "lemma": "el", "text": "el" }, { "lemma": "mandatario", "text": "mandatario" }, { "lemma": "mexicano", "text": "mexicano" }, { "lemma": ",", "text": "," }, { "lemma": "Enrique", "text": "Enrique" }, { "lemma": "Peña", "text": "Peña" }, { "lemma": "Nieto", "text": "Nieto" }, { "lemma": "destacar", "text": "destacó" }, { "lemma": "que", "text": "que" }, { "lemma": "Colombia", "text": "Colombia" }, { "lemma": "y", "text": "y" }, { "lemma": "México", "text": "México" }, { "lemma": "ser", "text": "son" }, { "lemma": "dos", "text": "dos" }, { "lemma": "nación", "text": "naciones" }, { "lemma": "hermano", "text": "hermanas" }, { "lemma": ",", "text": "," }, { "lemma": "unir", "text": "unidas" }, { "lemma": "por", "text": "por" }, { "lemma": "valor", "text": "valores" }, { "lemma": ",", "text": "," }, { "lemma": "afecto", "text": "afectos" }, { "lemma": "y", "text": "y" }, { "lemma": "objetivo", "text": "objetivos" }, { "lemma": "común", "text": "comunes" }, { "lemma": ".", "text": "." }, { "lemma": "sostener", "text": "Sostuvo" }, { "lemma": "que", "text": "que" }, { "lemma": "el", "text": "el" }, { "lemma": "comercio", "text": "comercio" }, { "lemma": "bilateral", "text": "bilateral" }, { "lemma": "entre", "text": "entre" }, { "lemma": "ambos", "text": "ambas" }, { "lemma": "nación", "text": "naciones" }, { "lemma": "haber", "text": "ha" }, { "lemma": "crecer", "text": "crecido" }, { "lemma": "14", "text": "14" }, { "lemma": "%", "text": "%" }, { "lemma": "a el", "text": "al" }, { "lemma": "año", "text": "año" }, { "lemma": "y", "text": "y" }, { "lemma": "hoy", "text": "hoy" }, { "lemma": "ser", "text": "es" }, { "lemma": "12", "text": "12" }, { "lemma": "vez", "text": "veces" }, { "lemma": "más", "text": "más" }, { "lemma": "grande", "text": "grande" }, { "lemma": "que", "text": "que" }, { "lemma": "hacer", "text": "hace" }, { "lemma": "apenas", "text": "apenas" }, { "lemma": "dos", "text": "dos" }, { "lemma": "década", "text": "décadas" }, { "lemma": ".", "text": "." }, { "lemma": "por", "text": "Por" }, { "lemma": "él", "text": "su" }, { "lemma": "parte", "text": "parte" }, { "lemma": "el", "text": "el" }, { "lemma": "mandatario", "text": "mandatario" }, { "lemma": "Juan", "text": "Juan" }, { "lemma": "Manuel", "text": "Manuel" }, { "lemma": "Santos", "text": "Santos" }, { "lemma": "decir", "text": "dijo" }, { "lemma": "que", "text": "que" }, { "lemma": "el", "text": "las" }, { "lemma": "relación", "text": "relaciones" }, { "lemma": "entre", "text": "entre" }, { "lemma": "México", "text": "México" }, { "lemma": "y", "text": "y" }, { "lemma": "Colombia", "text": "Colombia" }, { "lemma": "se", "text": "se" }, { "lemma": "elevar", "text": "elevarán" }, { "lemma": "a el", "text": "al" }, { "lemma": "rango", "text": "rango" }, { "lemma": "de", "text": "de" }, { "lemma": "asociación", "text": "asociación" }, { "lemma": "estratégico", "text": "estratégica" }, { "lemma": ".", "text": "." }, { "lemma": "destacar", "text": "Destacó" }, { "lemma": "que", "text": "que" }, { "lemma": "“", "text": "“" }, { "lemma": "el", "text": "la" }, { "lemma": "alianza", "text": "Alianza" }, { "lemma": "pacífico", "text": "Pacífico" }, { "lemma": "haber", "text": "ha" }, { "lemma": "potenciar", "text": "potenciado" }, { "lemma": "nosotros", "text": "nuestro" }, { "lemma": "papel", "text": "papel" }, { "lemma": "en", "text": "en" }, { "lemma": "el", "text": "la" }, { "lemma": "región", "text": "región" }, { "lemma": ".", "text": "." }, { "lemma": "junto", "text": "Junto" }, { "lemma": "con", "text": "con" }, { "lemma": "México", "text": "México" }, { "lemma": ",", "text": "," }, { "lemma": "Perú", "text": "Perú" }, { "lemma": "y", "text": "y" }, { "lemma": "chile", "text": "Chile" }, { "lemma": "equivaler", "text": "equivalemos" }, { "lemma": "a", "text": "a" }, { "lemma": "el", "text": "la" }, { "lemma": "sexto", "text": "sexta" }, { "lemma": "economía", "text": "economía" }, { "lemma": "de el", "text": "del" }, { "lemma": "mundo", "text": "mundo" }, { "lemma": ".", "text": "." }, { "lemma": "el", "text": "La" }, { "lemma": "alianza", "text": "alianza" }, { "lemma": "ser", "text": "es" }, { "lemma": "el", "text": "el" }, { "lemma": "proceso", "text": "proceso" }, { "lemma": "de", "text": "de" }, { "lemma": "integración", "text": "integración" }, { "lemma": "más", "text": "más" }, { "lemma": "exitoso", "text": "exitoso" }, { "lemma": "de", "text": "de" }, { "lemma": "América", "text": "América" }, { "lemma": "Latina", "text": "Latina" }, { "lemma": "”", "text": "”" }, { "lemma": ".", "text": "." }, { "lemma": "Alianza", "text": "Alianza" }, { "lemma": "de el", "text": "del" }, { "lemma": "pacífico", "text": "Pacífico" }, { "lemma": ",", "text": "," }, { "lemma": "abrir", "text": "abierta" }, { "lemma": "a el", "text": "al" }, { "lemma": "libre", "text": "libre" }, { "lemma": "comercio", "text": "comercio" }, { "lemma": ":", "text": ":" }, { "lemma": "Peña", "text": "Peña" }, { "lemma": "Nieto", "text": "Nieto" }, { "lemma": "ver", "text": "Ver" }, { "lemma": "nota", "text": "nota" }, { "lemma": ".", "text": "." }, { "lemma": "mrc", "text": "mrc" } ], "posTags": [ { "pos": "DIG", "text": "00" }, { "pos": "DIG", "text": "00" }, { "pos": "DIG", "text": "00" }, { "pos": "PUNCT", "text": "|" }, { "pos": "DIG", "text": "00:00" }, { "pos": "NOUNPL", "text": "SECCIONES" }, { "pos": "NOUNSG", "text": "Sociedad" }, { "pos": "PROP", "text": "México" }, { "pos": "CONJ", "text": "y" }, { "pos": "PROP", "text": "Colombia" }, { "pos": "CM", "text": "," }, { "pos": "NOUNPL", "text": "naciones" }, { "pos": "PREP", "text": "con" }, { "pos": "NOUNPL", "text": "objetivos" }, { "pos": "ADJPL", "text": "comunes" }, { "pos": "PUNCT", "text": ":" }, { "pos": "PROP", "text": "EPN" }, { "pos": "PREP", "text": "En" }, { "pos": "DETSG", "text": "el" }, { "pos": "NOUNSG", "text": "marco" }, { "pos": "PREP", "text": "de" }, { "pos": "DETSG", "text": "la" }, { "pos": "NOUNSG", "text": "visita" }, { "pos": "PREP", "text": "de" }, { "pos": "NOUNSG", "text": "Estado" }, { "pos": "CONJ", "text": "y" }, { "pos": "DETSG", "text": "la" }, { "pos": "NOUNSG", "text": "ceremonia" }, { "pos": "ADJSG", "text": "oficial" }, { "pos": "PREP", "text": "de" }, { "pos": "ADJSG", "text": "bienvenida" }, { "pos": "PREPDET", "text": "al" }, { "pos": "NOUNSG", "text": "presidente" }, { "pos": "PREP", "text": "de" }, { "pos": "PROP", "text": "Colombia" }, { "pos": "CM", "text": "," }, { "pos": "PROP", "text": "juan" }, { "pos": "PROP", "text": "Manuel" }, { "pos": "PROP", "text": "Santos" }, { "pos": "CM", "text": "," }, { "pos": "DETSG", "text": "el" }, { "pos": "NOUNSG", "text": "mandatario" }, { "pos": "ADJSG", "text": "mexicano" }, { "pos": "CM", "text": "," }, { "pos": "PROP", "text": "Enrique" }, { "pos": "PROP", "text": "Peña" }, { "pos": "PROP", "text": "Nieto" }, { "pos": "VERBFIN", "text": "destacó" }, { "pos": "QUE", "text": "que" }, { "pos": "PROP", "text": "Colombia" }, { "pos": "CONJ", "text": "y" }, { "pos": "PROP", "text": "México" }, { "pos": "AUX", "text": "son" }, { "pos": "NUM", "text": "dos" }, { "pos": "NOUNPL", "text": "naciones" }, { "pos": "NOUNPL", "text": "hermanas" }, { "pos": "CM", "text": "," }, { "pos": "PAPPL", "text": "unidas" }, { "pos": "PREP", "text": "por" }, { "pos": "NOUNPL", "text": "valores" }, { "pos": "CM", "text": "," }, { "pos": "NOUNPL", "text": "afectos" }, { "pos": "CONJ", "text": "y" }, { "pos": "NOUNPL", "text": "objetivos" }, { "pos": "ADJPL", "text": "comunes" }, { "pos": "SENT", "text": "." }, { "pos": "VERBINF", "text": "compartir" }, { "pos": "PREP", "text": "en" }, { "pos": "PUNCT", "text": ":" }, { "pos": "PREP", "text": "Por" }, { "pos": "PUNCT", "text": ":" }, { "pos": "NOUNSG", "text": "Redacción" }, { "pos": "NOUN", "text": "Viernes" }, { "pos": "DIG", "text": "08" }, { "pos": "DIG", "text": "05" }, { "pos": "DIG", "text": "15" }, { "pos": "PREP", "text": "En" }, { "pos": "DETSG", "text": "el" }, { "pos": "NOUNSG", "text": "marco" }, { "pos": "PREP", "text": "de" }, { "pos": "DETSG", "text": "la" }, { "pos": "NOUNSG", "text": "visita" }, { "pos": "PREP", "text": "de" }, { "pos": "NOUNSG", "text": "Estado" }, { "pos": "CONJ", "text": "y" }, { "pos": "DETSG", "text": "la" }, { "pos": "NOUNSG", "text": "ceremonia" }, { "pos": "ADJSG", "text": "oficial" }, { "pos": "PREP", "text": "de" }, { "pos": "ADJSG", "text": "bienvenida" }, { "pos": "PREPDET", "text": "al" }, { "pos": "NOUNSG", "text": "presidente" }, { "pos": "PREP", "text": "de" }, { "pos": "PROP", "text": "Colombia" }, { "pos": "CM", "text": "," }, { "pos": "PROP", "text": "Juan" }, { "pos": "PROP", "text": "Manuel" }, { "pos": "PROP", "text": "Santos" }, { "pos": "CM", "text": "," }, { "pos": "DETSG", "text": "el" }, { "pos": "NOUNSG", "text": "mandatario" }, { "pos": "ADJSG", "text": "mexicano" }, { "pos": "CM", "text": "," }, { "pos": "PROP", "text": "Enrique" }, { "pos": "PROP", "text": "Peña" }, { "pos": "PROP", "text": "Nieto" }, { "pos": "VERBFIN", "text": "destacó" }, { "pos": "QUE", "text": "que" }, { "pos": "PROP", "text": "Colombia" }, { "pos": "CONJ", "text": "y" }, { "pos": "PROP", "text": "México" }, { "pos": "AUX", "text": "son" }, { "pos": "NUM", "text": "dos" }, { "pos": "NOUNPL", "text": "naciones" }, { "pos": "NOUNPL", "text": "hermanas" }, { "pos": "CM", "text": "," }, { "pos": "PAPPL", "text": "unidas" }, { "pos": "PREP", "text": "por" }, { "pos": "NOUNPL", "text": "valores" }, { "pos": "CM", "text": "," }, { "pos": "NOUNPL", "text": "afectos" }, { "pos": "CONJ", "text": "y" }, { "pos": "NOUNPL", "text": "objetivos" }, { "pos": "ADJPL", "text": "comunes" }, { "pos": "SENT", "text": "." }, { "pos": "VERBFIN", "text": "Sostuvo" }, { "pos": "QUE", "text": "que" }, { "pos": "DETSG", "text": "el" }, { "pos": "NOUNSG", "text": "comercio" }, { "pos": "ADJSG", "text": "bilateral" }, { "pos": "PREP", "text": "entre" }, { "pos": "DETQUANTPL", "text": "ambas" }, { "pos": "NOUNPL", "text": "naciones" }, { "pos": "HAB", "text": "ha" }, { "pos": "PAPSG", "text": "crecido" }, { "pos": "DIG", "text": "14" }, { "pos": "PUNCT", "text": "%" }, { "pos": "PREPDET", "text": "al" }, { "pos": "NOUNSG", "text": "año" }, { "pos": "CONJ", "text": "y" }, { "pos": "ADV", "text": "hoy" }, { "pos": "AUX", "text": "es" }, { "pos": "DIG", "text": "12" }, { "pos": "NOUNPL", "text": "veces" }, { "pos": "ADV", "text": "más" }, { "pos": "ADJSG", "text": "grande" }, { "pos": "QUE", "text": "que" }, { "pos": "VERBFIN", "text": "hace" }, { "pos": "ADV", "text": "apenas" }, { "pos": "NUM", "text": "dos" }, { "pos": "NOUNPL", "text": "décadas" }, { "pos": "SENT", "text": "." }, { "pos": "PREP", "text": "Por" }, { "pos": "DETSG", "text": "su" }, { "pos": "NOUNSG", "text": "parte" }, { "pos": "DETSG", "text": "el" }, { "pos": "NOUNSG", "text": "mandatario" }, { "pos": "PROP", "text": "Juan" }, { "pos": "PROP", "text": "Manuel" }, { "pos": "PROP", "text": "Santos" }, { "pos": "VERBFIN", "text": "dijo" }, { "pos": "QUE", "text": "que" }, { "pos": "DETPL", "text": "las" }, { "pos": "NOUNPL", "text": "relaciones" }, { "pos": "PREP", "text": "entre" }, { "pos": "PROP", "text": "México" }, { "pos": "CONJ", "text": "y" }, { "pos": "PROP", "text": "Colombia" }, { "pos": "SE", "text": "se" }, { "pos": "VERBFIN", "text": "elevarán" }, { "pos": "PREPDET", "text": "al" }, { "pos": "NOUNSG", "text": "rango" }, { "pos": "PREP", "text": "de" }, { "pos": "NOUNSG", "text": "asociación" }, { "pos": "ADJSG", "text": "estratégica" }, { "pos": "SENT", "text": "." }, { "pos": "VERBFIN", "text": "Destacó" }, { "pos": "QUE", "text": "que" }, { "pos": "PUNCT", "text": "“" }, { "pos": "DETSG", "text": "la" }, { "pos": "NOUNSG", "text": "Alianza" }, { "pos": "ADJSG", "text": "Pacífico" }, { "pos": "HAB", "text": "ha" }, { "pos": "PAPSG", "text": "potenciado" }, { "pos": "DETSG", "text": "nuestro" }, { "pos": "NOUNSG", "text": "papel" }, { "pos": "PREP", "text": "en" }, { "pos": "DETSG", "text": "la" }, { "pos": "NOUNSG", "text": "región" }, { "pos": "SENT", "text": "." }, { "pos": "ADV", "text": "Junto" }, { "pos": "PREP", "text": "con" }, { "pos": "PROP", "text": "México" }, { "pos": "CM", "text": "," }, { "pos": "PROP", "text": "Perú" }, { "pos": "CONJ", "text": "y" }, { "pos": "NOUNSG", "text": "Chile" }, { "pos": "VERBFIN", "text": "equivalemos" }, { "pos": "PREP", "text": "a" }, { "pos": "DETSG", "text": "la" }, { "pos": "ADJSG", "text": "sexta" }, { "pos": "NOUNSG", "text": "economía" }, { "pos": "PREPDET", "text": "del" }, { "pos": "NOUNSG", "text": "mundo" }, { "pos": "SENT", "text": "." }, { "pos": "DETSG", "text": "La" }, { "pos": "NOUNSG", "text": "alianza" }, { "pos": "AUX", "text": "es" }, { "pos": "DETSG", "text": "el" }, { "pos": "NOUNSG", "text": "proceso" }, { "pos": "PREP", "text": "de" }, { "pos": "NOUNSG", "text": "integración" }, { "pos": "ADV", "text": "más" }, { "pos": "ADJSG", "text": "exitoso" }, { "pos": "PREP", "text": "de" }, { "pos": "PROP", "text": "América" }, { "pos": "PROP", "text": "Latina" }, { "pos": "PUNCT", "text": "”" }, { "pos": "SENT", "text": "." }, { "pos": "PROP", "text": "Alianza" }, { "pos": "PREPDET", "text": "del" }, { "pos": "ADJSG", "text": "Pacífico" }, { "pos": "CM", "text": "," }, { "pos": "PAPSG", "text": "abierta" }, { "pos": "PREPDET", "text": "al" }, { "pos": "ADJSG", "text": "libre" }, { "pos": "NOUNSG", "text": "comercio" }, { "pos": "PUNCT", "text": ":" }, { "pos": "PROP", "text": "Peña" }, { "pos": "PROP", "text": "Nieto" }, { "pos": "VERBINF", "text": "Ver" }, { "pos": "NOUNSG", "text": "nota" }, { "pos": "SENT", "text": "." }, { "pos": "PROP", "text": "mrc" } ], "requestId": "c77f0d0f-1474-4d2c-b6cc-a88bcc32f4cb", "timers": { "rblJe": 3, "rliJe": 2, "textExtractor": 16, "urlContentDownloader": 394 } } python-0.7.4/tests/mock-data/response/spa-url-morphology_complete.status 0000664 0000000 0000000 00000000003 12636317025 0026616 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/spa-url-sentiment.json 0000664 0000000 0000000 00000000243 12636317025 0024171 0 ustar 00root root 0000000 0000000 { "code": "unsupportedLanguage", "message": "Spanish is not supported by Rosette Sentiment Analyzer", "requestId": "ee40ebe3-dea8-4e97-8fc5-70c8dd98063c" } python-0.7.4/tests/mock-data/response/spa-url-sentiment.status 0000664 0000000 0000000 00000000003 12636317025 0024535 0 ustar 00root root 0000000 0000000 415 python-0.7.4/tests/mock-data/response/xxx-doc-categories.json 0000664 0000000 0000000 00000000233 12636317025 0024316 0 ustar 00root root 0000000 0000000 { "code": "unsupportedLanguage", "message": "German is not supported by Rosette Categorizer", "requestId": "8074661f-0d89-4a61-a8c1-4c87da01a745" } python-0.7.4/tests/mock-data/response/xxx-doc-categories.status 0000664 0000000 0000000 00000000003 12636317025 0024663 0 ustar 00root root 0000000 0000000 415 python-0.7.4/tests/mock-data/response/xxx-doc-entities.json 0000664 0000000 0000000 00000005474 12636317025 0024031 0 ustar 00root root 0000000 0000000 { "entities": [ { "confidence": 0.05986414849758148, "count": 4, "indocChainId": 0, "mention": "Europa", "normalized": "Europa", "type": "LOCATION" }, { "confidence": 0.008987635374069214, "count": 2, "indocChainId": 2, "mention": "Teneriffa", "normalized": "Teneriffa", "type": "LOCATION" }, { "confidence": 0.035944998264312744, "count": 1, "indocChainId": 1, "mention": "Spanien", "normalized": "Spanien", "type": "LOCATION" }, { "confidence": 0.03711158037185669, "count": 1, "indocChainId": 3, "mention": "Europäische Union", "normalized": "Europäische Union", "type": "LOCATION" }, { "confidence": 0.03636401891708374, "count": 1, "indocChainId": 4, "mention": "Innenminister", "normalized": "Innenminister", "type": "TITLE" }, { "confidence": 0.01726752519607544, "count": 1, "indocChainId": 8, "mention": "Professor", "normalized": "Professor", "type": "TITLE" }, { "confidence": 0.00736004114151001, "count": 1, "indocChainId": 9, "mention": "Klaus J. Bade", "normalized": "Klaus J. Bade", "type": "PERSON" }, { "confidence": 0.013958752155303955, "count": 1, "indocChainId": 10, "mention": "Universität Osnabrück", "normalized": "Universität Osnabrück", "type": "ORGANIZATION" }, { "confidence": 0.03818148374557495, "count": 1, "indocChainId": 11, "mention": "Somalia", "normalized": "Somalia", "type": "LOCATION" }, { "confidence": 0.03774428367614746, "count": 1, "indocChainId": 12, "mention": "Fischer", "normalized": "Fischer", "type": "PERSON" }, { "confidence": 0.019688069820404053, "count": 1, "indocChainId": 14, "mention": "Wolfgang Schäuble", "normalized": "Wolfgang Schäuble", "type": "PERSON" }, { "confidence": 0.06329077482223511, "count": 1, "indocChainId": 14, "mention": "Schäuble", "normalized": "Schäuble", "type": "PERSON" }, { "confidence": 0.024634122848510742, "count": 1, "indocChainId": 15, "mention": "CDU", "normalized": "CDU", "type": "ORGANIZATION" }, { "confidence": 0.023647606372833252, "count": 1, "indocChainId": 16, "mention": "Brüssel", "normalized": "Brüssel", "type": "LOCATION" } ], "requestId": "31401656-5766-4965-a472-51e3744b87bb", "timers": { "rblJe": 4, "rexJe": 23, "rliJe": 3 } } python-0.7.4/tests/mock-data/response/xxx-doc-entities.status 0000664 0000000 0000000 00000000003 12636317025 0024362 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/xxx-doc-entities_linked.json 0000664 0000000 0000000 00000003272 12636317025 0025351 0 ustar 00root root 0000000 0000000 { "entities": [ { "confidence": 0.2346810319289934, "entityId": "Q46", "indocChainId": 0, "mention": "Europa" }, { "confidence": 0.5356297063629705, "entityId": "Q29", "indocChainId": 1, "mention": "Spanien" }, { "confidence": 0.7032609592639487, "entityId": "Q40846", "indocChainId": 2, "mention": "Teneriffa" }, { "confidence": 0.41392398168592914, "entityId": "Q458", "indocChainId": 3, "mention": "Europäische Union" }, { "confidence": 0.33153175597287526, "entityId": "NEW-CLUSTER", "indocChainId": 9, "mention": "Klaus J. Bade" }, { "confidence": 0.8090162845122769, "entityId": "Q702499", "indocChainId": 10, "mention": "Universität Osnabrück" }, { "confidence": 0.2187509737947439, "entityId": "Q1045", "indocChainId": 11, "mention": "Somalia" }, { "confidence": 0.07623418348028191, "entityId": "NEW-CLUSTER", "indocChainId": 12, "mention": "Fischer" }, { "confidence": 0.6626603339839126, "entityId": "Q16019", "indocChainId": 14, "mention": "Wolfgang Schäuble" }, { "confidence": 0.3004908400632998, "entityId": "Q49762", "indocChainId": 15, "mention": "CDU" }, { "confidence": 0.6103951759428435, "entityId": "Q240", "indocChainId": 16, "mention": "Brüssel" } ], "requestId": "c184acbe-d6e4-4db7-b599-9dc31dc07a08", "timers": { "rblJe": 5, "res": 249, "rexJe": 15, "rliJe": 4 } } python-0.7.4/tests/mock-data/response/xxx-doc-entities_linked.status 0000664 0000000 0000000 00000000003 12636317025 0025710 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/xxx-doc-language.json 0000664 0000000 0000000 00000001017 12636317025 0023755 0 ustar 00root root 0000000 0000000 { "languageDetections": [ { "confidence": 0.023407053954701884, "language": "deu" }, { "confidence": 0.008063001331808373, "language": "nld" }, { "confidence": 0.006120518059292035, "language": "swe" }, { "confidence": 0.005709172789692851, "language": "nor" }, { "confidence": 0.005298351817899061, "language": "eng" } ], "requestId": "1b3fc281-9fcb-4d89-a2a6-0abaf47171cb", "timers": { "rliJe": 5 } } python-0.7.4/tests/mock-data/response/xxx-doc-language.status 0000664 0000000 0000000 00000000003 12636317025 0024321 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/xxx-doc-morphology_complete.json 0000664 0000000 0000000 00000070556 12636317025 0026277 0 ustar 00root root 0000000 0000000 { "compounds": [ { "compoundComponents": [ "Heimat", "Land" ], "text": "Heimatländern" }, { "compoundComponents": [ "Flüchtling", "Strom" ], "text": "Flüchtlingsstrom" }, { "compoundComponents": [ "Gemeinschaft", "Problem" ], "text": "Gemeinschaftsproblem" }, { "compoundComponents": [ "eignen", "Verantwortung" ], "text": "Eigenverantwortung" }, { "compoundComponents": [ "Migration", "Forscher" ], "text": "Migrationsforscher" }, { "compoundComponents": [ "textil", "Sammlung" ], "text": "Textilsammlungen" }, { "compoundComponents": [ "textil", "Industrie" ], "text": "Textilindustrie" }, { "compoundComponents": [ "Fisch", "Fabrik" ], "text": "Fischfabriken" }, { "compoundComponents": [ "Küste", "Fischerei" ], "text": "Küstenfischerei" }, { "compoundComponents": [ "Außen", "Grenze" ], "text": "Außengrenzen" }, { "compoundComponents": [ "Außen", "Grenze" ], "text": "Außengrenzen" }, { "compoundComponents": [ "Bürger", "nah" ], "text": "bürgernäher" } ], "hanReadings": [], "lemmas": [ { "lemma": "3.11.06", "text": "3.11.06" }, { "lemma": "-", "text": "-" }, { "lemma": "not", "text": "Not" }, { "lemma": "und", "text": "und" }, { "lemma": "Elend", "text": "Elend" }, { "lemma": "in", "text": "in" }, { "lemma": "ihr", "text": "ihren" }, { "lemma": "Heimatland", "text": "Heimatländern" }, { "lemma": "lassen", "text": "lassen" }, { "lemma": "immer", "text": "immer" }, { "lemma": "mehr", "text": "mehr" }, { "lemma": "Afrikaner", "text": "Afrikaner" }, { "lemma": "die", "text": "die" }, { "lemma": "Reise", "text": "Reise" }, { "lemma": "nach", "text": "nach" }, { "lemma": "Europa", "text": "Europa" }, { "lemma": "antreten", "text": "antreten" }, { "lemma": ".", "text": "." }, { "lemma": "insbesondere", "text": "Insbesondere" }, { "lemma": "Spanien", "text": "Spanien" }, { "lemma": "sein", "text": "ist" }, { "lemma": "betreffen", "text": "betroffen" }, { "lemma": "-", "text": "-" }, { "lemma": "allein", "text": "allein" }, { "lemma": "24.000", "text": "24.000" }, { "lemma": "Flüchtling", "text": "Flüchtlinge" }, { "lemma": "sein", "text": "sind" }, { "lemma": "in", "text": "in" }, { "lemma": "dies", "text": "diesem" }, { "lemma": "Jahr", "text": "Jahr" }, { "lemma": "in", "text": "in" }, { "lemma": "Teneriffa", "text": "Teneriffa" }, { "lemma": "ankommen", "text": "angekommen" }, { "lemma": ".", "text": "." }, { "lemma": "nun", "text": "Nun" }, { "lemma": "beraten", "text": "berät" }, { "lemma": "die", "text": "die" }, { "lemma": "europäisch", "text": "Europäische" }, { "lemma": "Union", "text": "Union" }, { "lemma": "über", "text": "über" }, { "lemma": "Maßnahme", "text": "Maßnahmen" }, { "lemma": "gegen", "text": "gegen" }, { "lemma": "der", "text": "den" }, { "lemma": "Flüchtlingsstrom", "text": "Flüchtlingsstrom" }, { "lemma": ".", "text": "." }, { "lemma": "nicht", "text": "Nicht" }, { "lemma": "alle", "text": "alle" }, { "lemma": "Länder", "text": "Länder" }, { "lemma": "sehen", "text": "sehen" }, { "lemma": "darin", "text": "darin" }, { "lemma": "ein", "text": "ein" }, { "lemma": "Gemeinschaftsproblem", "text": "Gemeinschaftsproblem" }, { "lemma": "-", "text": "-" }, { "lemma": "der", "text": "der" }, { "lemma": "deutsch", "text": "deutsche" }, { "lemma": "Innenminister", "text": "Innenminister" }, { "lemma": "Schäuble", "text": "Schäuble" }, { "lemma": "appellieren", "text": "appelliert" }, { "lemma": "an", "text": "an" }, { "lemma": "die", "text": "die" }, { "lemma": "Eigenverantwortung", "text": "Eigenverantwortung" }, { "lemma": "der", "text": "der" }, { "lemma": "Länder", "text": "Länder" }, { "lemma": ".", "text": "." }, { "lemma": "die", "text": "Die" }, { "lemma": "Flüchtling", "text": "Flüchtlinge" }, { "lemma": ",", "text": "," }, { "lemma": "die", "text": "die" }, { "lemma": "auf", "text": "auf" }, { "lemma": "Teneriffa", "text": "Teneriffa" }, { "lemma": "in der", "text": "im" }, { "lemma": "Lager", "text": "Lager" }, { "lemma": "ausharren", "text": "ausharren" }, { "lemma": ",", "text": "," }, { "lemma": "kommen", "text": "kommen" }, { "lemma": "aus", "text": "aus" }, { "lemma": "Land", "text": "Ländern" }, { "lemma": ",", "text": "," }, { "lemma": "in", "text": "in" }, { "lemma": "die", "text": "denen" }, { "lemma": "sie", "text": "sie" }, { "lemma": "kaum", "text": "kaum" }, { "lemma": "existieren", "text": "existieren" }, { "lemma": "können", "text": "können" }, { "lemma": "-", "text": "-" }, { "lemma": "auch", "text": "auch" }, { "lemma": "wegen", "text": "wegen" }, { "lemma": "der", "text": "der" }, { "lemma": "Konkurrenz", "text": "Konkurrenz" }, { "lemma": "aus", "text": "aus" }, { "lemma": "Europa", "text": "Europa" }, { "lemma": ",", "text": "," }, { "lemma": "wie", "text": "wie" }, { "lemma": "Professor", "text": "Professor" }, { "lemma": "Klaus", "text": "Klaus" }, { "lemma": "J.", "text": "J." }, { "lemma": "Bad", "text": "Bade" }, { "lemma": ",", "text": "," }, { "lemma": "Migrationsforscher", "text": "Migrationsforscher" }, { "lemma": "an", "text": "an" }, { "lemma": "der", "text": "der" }, { "lemma": "Universität", "text": "Universität" }, { "lemma": "Osnabrück", "text": "Osnabrück" }, { "lemma": "wissen", "text": "weiß" }, { "lemma": ":", "text": ":" }, { "lemma": "\"", "text": "\"" }, { "lemma": "unser", "text": "Unsere" }, { "lemma": "Textilsammlung", "text": "Textilsammlungen" }, { "lemma": "landen", "text": "landen" }, { "lemma": "auf", "text": "auf" }, { "lemma": "kommerziell", "text": "kommerziellen" }, { "lemma": "Markt", "text": "Märkten" }, { "lemma": "und", "text": "und" }, { "lemma": "ruinieren", "text": "ruinieren" }, { "lemma": "die", "text": "die" }, { "lemma": "Textilindustrie", "text": "Textilindustrie" }, { "lemma": ".", "text": "." }, { "lemma": "und", "text": "Und" }, { "lemma": "die", "text": "die" }, { "lemma": "schwimmen", "text": "schwimmenden" }, { "lemma": "Fischfabrik", "text": "Fischfabriken" }, { "lemma": "-", "text": "-" }, { "lemma": "Fisch", "text": "Fisch" }, { "lemma": "unten", "text": "unten" }, { "lemma": "rein", "text": "rein" }, { "lemma": ",", "text": "," }, { "lemma": "Dose", "text": "Dose" }, { "lemma": "oben", "text": "oben" }, { "lemma": "raus", "text": "raus" }, { "lemma": "-", "text": "-" }, { "lemma": "vor", "text": "vor" }, { "lemma": "der", "text": "den" }, { "lemma": "afrikanisch", "text": "afrikanischen" }, { "lemma": "Küste", "text": "Küsten" }, { "lemma": "ruinieren", "text": "ruinieren" }, { "lemma": "die", "text": "die" }, { "lemma": "Küstenfischerei", "text": "Küstenfischerei" }, { "lemma": ".", "text": "." }, { "lemma": "Ergebnis", "text": "Ergebnis" }, { "lemma": ":", "text": ":" }, { "lemma": "in", "text": "In" }, { "lemma": "Somalia", "text": "Somalia" }, { "lemma": "transportieren", "text": "transportieren" }, { "lemma": "inzwischen", "text": "inzwischen" }, { "lemma": "ruinieren", "text": "ruinierte" }, { "lemma": "Fischer", "text": "Fischer" }, { "lemma": "mit", "text": "mit" }, { "lemma": "ihr", "text": "ihren" }, { "lemma": "Boot", "text": "Booten" }, { "lemma": "die", "text": "die" }, { "lemma": "illegal", "text": "Illegalen" }, { "lemma": "in", "text": "in" }, { "lemma": "Richtung", "text": "Richtung" }, { "lemma": "Europa", "text": "Europa" }, { "lemma": ".", "text": "." }, { "lemma": "\"", "text": "\"" }, { "lemma": "doch", "text": "Doch" }, { "lemma": "sich", "text": "sich" }, { "lemma": "vor", "text": "vor" }, { "lemma": "illegal", "text": "Illegalen" }, { "lemma": "zu", "text": "zu" }, { "lemma": "schützen", "text": "schützen" }, { "lemma": ",", "text": "," }, { "lemma": "damit", "text": "damit" }, { "lemma": "müssen", "text": "müsse" }, { "lemma": "jede", "text": "jedes" }, { "lemma": "Land", "text": "Land" }, { "lemma": "selbst", "text": "selbst" }, { "lemma": "fertig", "text": "fertig" }, { "lemma": "werden", "text": "werden" }, { "lemma": ",", "text": "," }, { "lemma": "wie", "text": "wie" }, { "lemma": "Wolfgang", "text": "Wolfgang" }, { "lemma": "Schäuble", "text": "Schäuble" }, { "lemma": "(", "text": "(" }, { "lemma": "CDU", "text": "CDU" }, { "lemma": ")", "text": ")" }, { "lemma": "betonen", "text": "betont" }, { "lemma": ":", "text": ":" }, { "lemma": "\"", "text": "\"" }, { "lemma": "in", "text": "In" }, { "lemma": "Brüssel", "text": "Brüssel" }, { "lemma": "sein", "text": "ist" }, { "lemma": "der", "text": "der" }, { "lemma": "Ruf", "text": "Ruf" }, { "lemma": "immer", "text": "immer" }, { "lemma": "wohlfeil", "text": "wohlfeil" }, { "lemma": ":", "text": ":" }, { "lemma": "es", "text": "Es" }, { "lemma": "müssen", "text": "muss" }, { "lemma": "alles", "text": "alles" }, { "lemma": "europäisch", "text": "europäisch" }, { "lemma": "machen", "text": "gemacht" }, { "lemma": "werden", "text": "werden" }, { "lemma": ".", "text": "." }, { "lemma": "jede", "text": "Jedes" }, { "lemma": "Land", "text": "Land" }, { "lemma": "mit", "text": "mit" }, { "lemma": "Außengrenze", "text": "Außengrenzen" }, { "lemma": "müssen", "text": "muss" }, { "lemma": "sein", "text": "seine" }, { "lemma": "Außengrenze", "text": "Außengrenzen" }, { "lemma": "schon", "text": "schon" }, { "lemma": "selber", "text": "selber" }, { "lemma": "kontrollieren", "text": "kontrollieren" }, { "lemma": ".", "text": "." }, { "lemma": "wenn", "text": "Wenn" }, { "lemma": "wir", "text": "wir" }, { "lemma": "die", "text": "die" }, { "lemma": "Verantwortung", "text": "Verantwortung" }, { "lemma": "nach", "text": "nach" }, { "lemma": "Europa", "text": "Europa" }, { "lemma": "schieben", "text": "schieben" }, { "lemma": ",", "text": "," }, { "lemma": "werden", "text": "wird" }, { "lemma": "es", "text": "es" }, { "lemma": "weder", "text": "weder" }, { "lemma": "Bürgernah", "text": "bürgernäher" }, { "lemma": "noch", "text": "noch" }, { "lemma": "effizient", "text": "effizienter" }, { "lemma": ",", "text": "," }, { "lemma": "sondern", "text": "sondern" }, { "lemma": "ganz", "text": "ganz" }, { "lemma": "in der", "text": "im" }, { "lemma": "Gegenteil", "text": "Gegenteil" }, { "lemma": ".", "text": "." }, { "lemma": "\"", "text": "\"" } ], "posTags": [ { "pos": "CARD", "text": "3.11.06" }, { "pos": "PUNCT", "text": "-" }, { "pos": "ADV", "text": "Not" }, { "pos": "COORD", "text": "und" }, { "pos": "NOUN", "text": "Elend" }, { "pos": "PREP", "text": "in" }, { "pos": "POSDET", "text": "ihren" }, { "pos": "NOUN", "text": "Heimatländern" }, { "pos": "VVFIN", "text": "lassen" }, { "pos": "ADV", "text": "immer" }, { "pos": "INDADJ", "text": "mehr" }, { "pos": "NOUN", "text": "Afrikaner" }, { "pos": "ART", "text": "die" }, { "pos": "NOUN", "text": "Reise" }, { "pos": "PREP", "text": "nach" }, { "pos": "NOUN", "text": "Europa" }, { "pos": "VVINF", "text": "antreten" }, { "pos": "SENT", "text": "." }, { "pos": "ADV", "text": "Insbesondere" }, { "pos": "NOUN", "text": "Spanien" }, { "pos": "VAFIN", "text": "ist" }, { "pos": "VVPP", "text": "betroffen" }, { "pos": "PUNCT", "text": "-" }, { "pos": "ADV", "text": "allein" }, { "pos": "CARD", "text": "24.000" }, { "pos": "NOUN", "text": "Flüchtlinge" }, { "pos": "VAFIN", "text": "sind" }, { "pos": "PREP", "text": "in" }, { "pos": "DEMDET", "text": "diesem" }, { "pos": "NOUN", "text": "Jahr" }, { "pos": "PREP", "text": "in" }, { "pos": "NOUN", "text": "Teneriffa" }, { "pos": "VVPP", "text": "angekommen" }, { "pos": "SENT", "text": "." }, { "pos": "ADV", "text": "Nun" }, { "pos": "VVFIN", "text": "berät" }, { "pos": "ART", "text": "die" }, { "pos": "ADJA", "text": "Europäische" }, { "pos": "NOUN", "text": "Union" }, { "pos": "PREP", "text": "über" }, { "pos": "NOUN", "text": "Maßnahmen" }, { "pos": "PREP", "text": "gegen" }, { "pos": "ART", "text": "den" }, { "pos": "NOUN", "text": "Flüchtlingsstrom" }, { "pos": "SENT", "text": "." }, { "pos": "PTKNEG", "text": "Nicht" }, { "pos": "INDDET", "text": "alle" }, { "pos": "NOUN", "text": "Länder" }, { "pos": "VVFIN", "text": "sehen" }, { "pos": "ADV", "text": "darin" }, { "pos": "ART", "text": "ein" }, { "pos": "NOUN", "text": "Gemeinschaftsproblem" }, { "pos": "PUNCT", "text": "-" }, { "pos": "ART", "text": "der" }, { "pos": "ADJA", "text": "deutsche" }, { "pos": "NOUN", "text": "Innenminister" }, { "pos": "NOUN", "text": "Schäuble" }, { "pos": "VVFIN", "text": "appelliert" }, { "pos": "PREP", "text": "an" }, { "pos": "ART", "text": "die" }, { "pos": "NOUN", "text": "Eigenverantwortung" }, { "pos": "ART", "text": "der" }, { "pos": "NOUN", "text": "Länder" }, { "pos": "SENT", "text": "." }, { "pos": "ART", "text": "Die" }, { "pos": "NOUN", "text": "Flüchtlinge" }, { "pos": "CM", "text": "," }, { "pos": "RELPRO", "text": "die" }, { "pos": "PREP", "text": "auf" }, { "pos": "NOUN", "text": "Teneriffa" }, { "pos": "PREPART", "text": "im" }, { "pos": "NOUN", "text": "Lager" }, { "pos": "VVINF", "text": "ausharren" }, { "pos": "CM", "text": "," }, { "pos": "VVFIN", "text": "kommen" }, { "pos": "PREP", "text": "aus" }, { "pos": "NOUN", "text": "Ländern" }, { "pos": "CM", "text": "," }, { "pos": "PREP", "text": "in" }, { "pos": "RELPRO", "text": "denen" }, { "pos": "PERSPRO", "text": "sie" }, { "pos": "ADV", "text": "kaum" }, { "pos": "VVINF", "text": "existieren" }, { "pos": "VMFIN", "text": "können" }, { "pos": "PUNCT", "text": "-" }, { "pos": "ADV", "text": "auch" }, { "pos": "PREP", "text": "wegen" }, { "pos": "ART", "text": "der" }, { "pos": "NOUN", "text": "Konkurrenz" }, { "pos": "PREP", "text": "aus" }, { "pos": "NOUN", "text": "Europa" }, { "pos": "CM", "text": "," }, { "pos": "COWIE", "text": "wie" }, { "pos": "NOUN", "text": "Professor" }, { "pos": "NOUN", "text": "Klaus" }, { "pos": "NOUN", "text": "J." }, { "pos": "NOUN", "text": "Bade" }, { "pos": "CM", "text": "," }, { "pos": "NOUN", "text": "Migrationsforscher" }, { "pos": "PREP", "text": "an" }, { "pos": "ART", "text": "der" }, { "pos": "NOUN", "text": "Universität" }, { "pos": "NOUN", "text": "Osnabrück" }, { "pos": "VVFIN", "text": "weiß" }, { "pos": "PUNCT", "text": ":" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "POSDET", "text": "Unsere" }, { "pos": "NOUN", "text": "Textilsammlungen" }, { "pos": "VVFIN", "text": "landen" }, { "pos": "PREP", "text": "auf" }, { "pos": "ADJA", "text": "kommerziellen" }, { "pos": "NOUN", "text": "Märkten" }, { "pos": "COORD", "text": "und" }, { "pos": "VVFIN", "text": "ruinieren" }, { "pos": "ART", "text": "die" }, { "pos": "NOUN", "text": "Textilindustrie" }, { "pos": "SENT", "text": "." }, { "pos": "COORD", "text": "Und" }, { "pos": "ART", "text": "die" }, { "pos": "ADJA", "text": "schwimmenden" }, { "pos": "NOUN", "text": "Fischfabriken" }, { "pos": "PUNCT", "text": "-" }, { "pos": "NOUN", "text": "Fisch" }, { "pos": "ADV", "text": "unten" }, { "pos": "ADJD", "text": "rein" }, { "pos": "CM", "text": "," }, { "pos": "NOUN", "text": "Dose" }, { "pos": "ADV", "text": "oben" }, { "pos": "VPREF", "text": "raus" }, { "pos": "PUNCT", "text": "-" }, { "pos": "PREP", "text": "vor" }, { "pos": "ART", "text": "den" }, { "pos": "ADJA", "text": "afrikanischen" }, { "pos": "NOUN", "text": "Küsten" }, { "pos": "VVFIN", "text": "ruinieren" }, { "pos": "ART", "text": "die" }, { "pos": "NOUN", "text": "Küstenfischerei" }, { "pos": "SENT", "text": "." }, { "pos": "NOUN", "text": "Ergebnis" }, { "pos": "PUNCT", "text": ":" }, { "pos": "PREP", "text": "In" }, { "pos": "NOUN", "text": "Somalia" }, { "pos": "VVFIN", "text": "transportieren" }, { "pos": "ADV", "text": "inzwischen" }, { "pos": "ADJA", "text": "ruinierte" }, { "pos": "NOUN", "text": "Fischer" }, { "pos": "PREP", "text": "mit" }, { "pos": "POSDET", "text": "ihren" }, { "pos": "NOUN", "text": "Booten" }, { "pos": "ART", "text": "die" }, { "pos": "NOUN", "text": "Illegalen" }, { "pos": "PREP", "text": "in" }, { "pos": "NOUN", "text": "Richtung" }, { "pos": "NOUN", "text": "Europa" }, { "pos": "SENT", "text": "." }, { "pos": "PUNCT", "text": "\"" }, { "pos": "COADV", "text": "Doch" }, { "pos": "REFLPRO", "text": "sich" }, { "pos": "PREP", "text": "vor" }, { "pos": "NOUN", "text": "Illegalen" }, { "pos": "PTKINF", "text": "zu" }, { "pos": "VVINF", "text": "schützen" }, { "pos": "CM", "text": "," }, { "pos": "ADV", "text": "damit" }, { "pos": "VMFIN", "text": "müsse" }, { "pos": "INDDET", "text": "jedes" }, { "pos": "NOUN", "text": "Land" }, { "pos": "ADV", "text": "selbst" }, { "pos": "ADJD", "text": "fertig" }, { "pos": "VAINF", "text": "werden" }, { "pos": "CM", "text": "," }, { "pos": "COWIE", "text": "wie" }, { "pos": "NOUN", "text": "Wolfgang" }, { "pos": "NOUN", "text": "Schäuble" }, { "pos": "PUNCT", "text": "(" }, { "pos": "NOUN", "text": "CDU" }, { "pos": "PUNCT", "text": ")" }, { "pos": "VVPP", "text": "betont" }, { "pos": "PUNCT", "text": ":" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "PREP", "text": "In" }, { "pos": "NOUN", "text": "Brüssel" }, { "pos": "VAFIN", "text": "ist" }, { "pos": "ART", "text": "der" }, { "pos": "NOUN", "text": "Ruf" }, { "pos": "ADV", "text": "immer" }, { "pos": "ADJD", "text": "wohlfeil" }, { "pos": "PUNCT", "text": ":" }, { "pos": "PERSPRO", "text": "Es" }, { "pos": "VMFIN", "text": "muss" }, { "pos": "INDPRO", "text": "alles" }, { "pos": "ADJD", "text": "europäisch" }, { "pos": "VVPP", "text": "gemacht" }, { "pos": "VAINF", "text": "werden" }, { "pos": "SENT", "text": "." }, { "pos": "INDDET", "text": "Jedes" }, { "pos": "NOUN", "text": "Land" }, { "pos": "PREP", "text": "mit" }, { "pos": "NOUN", "text": "Außengrenzen" }, { "pos": "VMFIN", "text": "muss" }, { "pos": "POSDET", "text": "seine" }, { "pos": "NOUN", "text": "Außengrenzen" }, { "pos": "ADV", "text": "schon" }, { "pos": "ADV", "text": "selber" }, { "pos": "VVINF", "text": "kontrollieren" }, { "pos": "SENT", "text": "." }, { "pos": "COSUB", "text": "Wenn" }, { "pos": "PERSPRO", "text": "wir" }, { "pos": "ART", "text": "die" }, { "pos": "NOUN", "text": "Verantwortung" }, { "pos": "PREP", "text": "nach" }, { "pos": "NOUN", "text": "Europa" }, { "pos": "VVINF", "text": "schieben" }, { "pos": "CM", "text": "," }, { "pos": "VAFIN", "text": "wird" }, { "pos": "PERSPRO", "text": "es" }, { "pos": "COP1", "text": "weder" }, { "pos": "ADJD2", "text": "bürgernäher" }, { "pos": "ADV", "text": "noch" }, { "pos": "ADJD2", "text": "effizienter" }, { "pos": "CM", "text": "," }, { "pos": "COORD", "text": "sondern" }, { "pos": "ADJD", "text": "ganz" }, { "pos": "PREPART", "text": "im" }, { "pos": "NOUN", "text": "Gegenteil" }, { "pos": "SENT", "text": "." }, { "pos": "PUNCT", "text": "\"" } ], "requestId": "4e114334-6092-497f-9c00-93cacd700ebf", "timers": { "rblJe": 133, "rliJe": 4 } } python-0.7.4/tests/mock-data/response/xxx-doc-morphology_complete.status 0000664 0000000 0000000 00000000003 12636317025 0026625 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/xxx-doc-sentiment.json 0000664 0000000 0000000 00000000242 12636317025 0024177 0 ustar 00root root 0000000 0000000 { "code": "unsupportedLanguage", "message": "German is not supported by Rosette Sentiment Analyzer", "requestId": "17bcc28d-06ee-4f13-97bc-0cbc8a8892d3" } python-0.7.4/tests/mock-data/response/xxx-doc-sentiment.status 0000664 0000000 0000000 00000000003 12636317025 0024544 0 ustar 00root root 0000000 0000000 415 python-0.7.4/tests/mock-data/response/xxx-null-categories.json 0000664 0000000 0000000 00000000233 12636317025 0024523 0 ustar 00root root 0000000 0000000 { "code": "unsupportedLanguage", "message": "Korean is not supported by Rosette Categorizer", "requestId": "91544ea7-3081-433d-94f7-6add50121419" } python-0.7.4/tests/mock-data/response/xxx-null-categories.status 0000664 0000000 0000000 00000000003 12636317025 0025070 0 ustar 00root root 0000000 0000000 415 python-0.7.4/tests/mock-data/response/xxx-null-entities.json 0000664 0000000 0000000 00000023371 12636317025 0024232 0 ustar 00root root 0000000 0000000 { "entities": [ { "confidence": 0.03028862178325653, "count": 4, "indocChainId": 18, "mention": "김일성의", "normalized": "김일성", "type": "PERSON" }, { "confidence": 0.04124155640602112, "count": 2, "indocChainId": 2, "mention": "한국의", "normalized": "한국", "type": "LOCATION" }, { "confidence": 0.015332251787185669, "count": 2, "indocChainId": 13, "mention": "총비서로", "normalized": "총비서로", "type": "TITLE" }, { "confidence": 0.031436413526535034, "count": 2, "indocChainId": 19, "mention": "김일성은", "normalized": "김일성", "type": "PERSON" }, { "confidence": 0.01727735996246338, "count": 2, "indocChainId": 21, "mention": "대동군", "normalized": "대동군", "type": "LOCATION" }, { "confidence": 0.006769031286239624, "count": 2, "indocChainId": 25, "mention": "김형직", "normalized": "김형직", "type": "PERSON" }, { "confidence": 0.03579825162887573, "count": 1, "indocChainId": 0, "mention": "김일성", "normalized": "김일성", "type": "PERSON" }, { "confidence": 0.031337738037109375, "count": 1, "indocChainId": 1, "mention": "金日成", "normalized": "金日成", "type": "PERSON" }, { "confidence": 0.003444194793701172, "count": 1, "indocChainId": 3, "mention": "만주 조선공산주의청년동맹", "normalized": "만주 조선공산주의청년동맹", "type": "ORGANIZATION" }, { "confidence": 0.0034142136573791504, "count": 1, "indocChainId": 4, "mention": "조선혁명군", "normalized": "조선혁명군", "type": "ORGANIZATION" }, { "confidence": 0.004472017288208008, "count": 1, "indocChainId": 5, "mention": "조선인민혁명군으로", "normalized": "조선인민혁명군", "type": "ORGANIZATION" }, { "confidence": 0.022660374641418457, "count": 1, "indocChainId": 6, "mention": "조선민주주의인민공화국의", "normalized": "조선민주주의인민공화국", "type": "ORGANIZATION" }, { "confidence": 0.06643146276473999, "count": 1, "indocChainId": 7, "mention": "총리", "normalized": "총리", "type": "TITLE" }, { "confidence": 0.0021535754203796387, "count": 1, "indocChainId": 8, "mention": "김성주", "normalized": "김성주", "type": "PERSON" }, { "confidence": 0.0018841028213500977, "count": 1, "indocChainId": 9, "mention": "金成柱", "normalized": "金成柱", "type": "PERSON" }, { "confidence": 0.00426030158996582, "count": 1, "indocChainId": 10, "mention": "金聖柱", "normalized": "金聖柱", "type": "PERSON" }, { "confidence": 0.0010657310485839844, "count": 1, "indocChainId": 10, "mention": "聖柱", "normalized": "聖柱", "type": "PERSON" }, { "confidence": 0.005452632904052734, "count": 1, "indocChainId": 11, "mention": "김일성으로", "normalized": "김일성", "type": "PERSON" }, { "confidence": 0.007513463497161865, "count": 1, "indocChainId": 12, "mention": "조선로동당 중앙위원회", "normalized": "조선로동당 중앙위원회", "type": "ORGANIZATION" }, { "confidence": 0.008457183837890625, "count": 1, "indocChainId": 14, "mention": "당중앙위원회", "normalized": "당중앙위원회", "type": "PERSON" }, { "confidence": 0.055203258991241455, "count": 1, "indocChainId": 16, "mention": "대한민국에서는", "normalized": "대한민국", "type": "LOCATION" }, { "confidence": 0.014769792556762695, "count": 1, "indocChainId": 17, "mention": "한국전쟁을", "normalized": "한국전쟁", "type": "LOCATION" }, { "confidence": 0.0021106600761413574, "count": 1, "indocChainId": 20, "mention": "평안남도", "normalized": "평안남도", "type": "LOCATION" }, { "confidence": 0.0016984343528747559, "count": 1, "indocChainId": 22, "mention": "고평면", "normalized": "고평면", "type": "LOCATION" }, { "confidence": 0.008638203144073486, "count": 1, "indocChainId": 23, "mention": "평양", "normalized": "평양", "type": "LOCATION" }, { "confidence": 0.0007074475288391113, "count": 1, "indocChainId": 24, "mention": "만경대", "normalized": "만경대", "type": "ORGANIZATION" }, { "confidence": 0.006536602973937988, "count": 1, "indocChainId": 26, "mention": "金亨稷", "normalized": "金亨稷", "type": "PERSON" }, { "confidence": 0.0037943124771118164, "count": 1, "indocChainId": 28, "mention": "전주", "normalized": "전주", "type": "LOCATION" }, { "confidence": 0.012494027614593506, "count": 1, "indocChainId": 29, "mention": "김씨", "normalized": "김", "type": "PERSON" }, { "confidence": 0.01468271017074585, "count": 1, "indocChainId": 30, "mention": "전라북도", "normalized": "전라북도", "type": "ORGANIZATION" }, { "confidence": 0.008353173732757568, "count": 1, "indocChainId": 31, "mention": "평양으로", "normalized": "평양", "type": "LOCATION" }, { "confidence": 0.024269163608551025, "count": 1, "indocChainId": 32, "mention": "셔먼", "normalized": "셔먼", "type": "PERSON" }, { "confidence": 0.024208784103393555, "count": 1, "indocChainId": 33, "mention": "일본", "normalized": "일본", "type": "LOCATION" }, { "confidence": 1.0, "count": 1, "indocChainId": 35, "mention": "기독교", "normalized": "기독교", "type": "RELIGION" }, { "confidence": 1.0, "count": 1, "indocChainId": 36, "mention": "장로교", "normalized": "장로교", "type": "RELIGION" }, { "confidence": 0.01832038164138794, "count": 1, "indocChainId": 37, "mention": "칠골교회의", "normalized": "칠골교회", "type": "ORGANIZATION" }, { "confidence": 0.00029218196868896484, "count": 1, "indocChainId": 39, "mention": "강진석", "normalized": "강진석", "type": "PERSON" }, { "confidence": 0.007561743259429932, "count": 1, "indocChainId": 40, "mention": "康晋錫", "normalized": "康晋錫", "type": "PERSON" }, { "confidence": 0.0018424391746520996, "count": 1, "indocChainId": 42, "mention": "성주", "normalized": "성주", "type": "PERSON" }, { "confidence": 0.010734498500823975, "count": 1, "indocChainId": 44, "mention": "지린성", "normalized": "지린성", "type": "ORGANIZATION" }, { "confidence": 0.00962001085281372, "count": 1, "indocChainId": 45, "mention": "吉林省", "normalized": "吉林省", "type": "LOCATION" }, { "confidence": 0.011630892753601074, "count": 1, "indocChainId": 47, "mention": "만주로", "normalized": "만주", "type": "LOCATION" }, { "confidence": 0.014584720134735107, "count": 1, "indocChainId": 49, "mention": "용산면", "normalized": "용산면", "type": "LOCATION" }, { "confidence": 0.018989503383636475, "count": 1, "indocChainId": 50, "mention": "칠골에", "normalized": "칠골", "type": "LOCATION" }, { "confidence": 0.005848109722137451, "count": 1, "indocChainId": 51, "mention": "창덕학교는", "normalized": "창덕학교", "type": "ORGANIZATION" }, { "confidence": 0.006634712219238281, "count": 1, "indocChainId": 53, "mention": "교장을", "normalized": "교장", "type": "TITLE" }, { "confidence": 0.004437685012817383, "count": 1, "indocChainId": 54, "mention": "중국말", "normalized": "중국말", "type": "LOCATION" }, { "confidence": 0.0015404820442199707, "count": 1, "indocChainId": 55, "mention": "창덕학교로의", "normalized": "창덕학교", "type": "ORGANIZATION" }, { "confidence": 0.020579516887664795, "count": 1, "indocChainId": 56, "mention": "중국", "normalized": "중국", "type": "LOCATION" }, { "confidence": 0.0038282275199890137, "count": 1, "indocChainId": 57, "mention": "칠골", "normalized": "칠고", "type": "PERSON" } ], "requestId": "6df84631-22d5-484a-b044-26929d7d70cd", "timers": { "rblJe": 15, "rexJe": 38, "rliJe": 4 } } python-0.7.4/tests/mock-data/response/xxx-null-entities.status 0000664 0000000 0000000 00000000003 12636317025 0024567 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/xxx-null-entities_linked.json 0000664 0000000 0000000 00000014375 12636317025 0025564 0 ustar 00root root 0000000 0000000 { "entities": [ { "confidence": 0.8489604344623649, "entityId": "Q41117", "indocChainId": 0, "mention": "김일성" }, { "confidence": 0.7067528050136327, "entityId": "Q41117", "indocChainId": 1, "mention": "金日成" }, { "confidence": 0.6840614198452438, "entityId": "Q884", "indocChainId": 2, "mention": "한국" }, { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 3, "mention": "만주 조선공산주의청년동맹" }, { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 4, "mention": "조선혁명군" }, { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 5, "mention": "조선인민혁명군" }, { "confidence": 0.5089752589326131, "entityId": "Q423", "indocChainId": 6, "mention": "조선민주주의인민공화국" }, { "confidence": 0.13860603828715395, "entityId": "NEW-CLUSTER", "indocChainId": 8, "mention": "김성주" }, { "confidence": 0.8331319603922426, "entityId": "Q41117", "indocChainId": 9, "mention": "金成柱" }, { "confidence": 0.2485642196994468, "entityId": "NEW-CLUSTER", "indocChainId": 10, "mention": "金聖柱" }, { "confidence": 0.8176772941578195, "entityId": "Q41117", "indocChainId": 11, "mention": "김일성" }, { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 12, "mention": "조선로동당 중앙위원회" }, { "confidence": 0.47046726511234904, "entityId": "NEW-CLUSTER", "indocChainId": 14, "mention": "당중앙위원회" }, { "confidence": 0.5327457921949627, "entityId": "Q884", "indocChainId": 16, "mention": "대한민국" }, { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 17, "mention": "한국전쟁" }, { "confidence": 0.8177571139954269, "entityId": "Q41117", "indocChainId": 18, "mention": "김일성" }, { "confidence": 0.8177030933146751, "entityId": "Q41117", "indocChainId": 19, "mention": "김일성" }, { "confidence": 0.5512206112575233, "entityId": "NEW-CLUSTER", "indocChainId": 20, "mention": "평안남도" }, { "confidence": 0.27147192435349504, "entityId": "NEW-CLUSTER", "indocChainId": 21, "mention": "대동군" }, { "confidence": 0.47722873529626136, "entityId": "NEW-CLUSTER", "indocChainId": 22, "mention": "고평면" }, { "confidence": 0.5777448106600542, "entityId": "Q18808", "indocChainId": 23, "mention": "평양" }, { "confidence": 0.4057503169230009, "entityId": "Q15244757", "indocChainId": 24, "mention": "만경대" }, { "confidence": 0.7876031545345472, "entityId": "Q489279", "indocChainId": 25, "mention": "김형직" }, { "confidence": 0.8343778214073765, "entityId": "Q489279", "indocChainId": 26, "mention": "金亨稷" }, { "confidence": 0.5366624538403322, "entityId": "Q42140", "indocChainId": 28, "mention": "전주" }, { "confidence": 0.03926331392845221, "entityId": "NEW-CLUSTER", "indocChainId": 29, "mention": "김" }, { "confidence": 0.5105738037644278, "entityId": "Q41157", "indocChainId": 30, "mention": "전라북도" }, { "confidence": 0.5838088908707967, "entityId": "Q18808", "indocChainId": 31, "mention": "평양" }, { "confidence": 0.041272329702973974, "entityId": "NEW-CLUSTER", "indocChainId": 32, "mention": "셔먼" }, { "confidence": 0.4542268299993202, "entityId": "NEW-CLUSTER", "indocChainId": 33, "mention": "일본" }, { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 37, "mention": "칠골교회" }, { "confidence": 0.45826704226055154, "entityId": "NEW-CLUSTER", "indocChainId": 39, "mention": "강진석" }, { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 40, "mention": "康晋錫" }, { "confidence": 0.24114628980747507, "entityId": "NEW-CLUSTER", "indocChainId": 42, "mention": "성주" }, { "confidence": 0.6479660059521329, "entityId": "NEW-CLUSTER", "indocChainId": 44, "mention": "지린성" }, { "confidence": 0.45290427147832335, "entityId": "Q45208", "indocChainId": 45, "mention": "吉林省" }, { "confidence": 0.07353817177994378, "entityId": "NEW-CLUSTER", "indocChainId": 47, "mention": "만주" }, { "confidence": 0.6646454916440627, "entityId": "NEW-CLUSTER", "indocChainId": 49, "mention": "용산면" }, { "confidence": 0.31371754515329237, "entityId": "NEW-CLUSTER", "indocChainId": 50, "mention": "칠골" }, { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 51, "mention": "창덕학교" }, { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 54, "mention": "중국말" }, { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 55, "mention": "창덕학교" }, { "confidence": 0.7540118355486469, "entityId": "NEW-CLUSTER", "indocChainId": 56, "mention": "중국" }, { "confidence": 0.03286639397910264, "entityId": "NEW-CLUSTER", "indocChainId": 57, "mention": "칠고" } ], "requestId": "0203e6c8-aee4-48ca-9279-cfecd0e65ded", "timers": { "rblJe": 13, "res": 5414, "rexJe": 23, "rliJe": 2 } } python-0.7.4/tests/mock-data/response/xxx-null-entities_linked.status 0000664 0000000 0000000 00000000003 12636317025 0026115 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/xxx-null-language.json 0000664 0000000 0000000 00000001001 12636317025 0024153 0 ustar 00root root 0000000 0000000 { "languageDetections": [ { "confidence": 0.2576247444801467, "language": "kor" }, { "confidence": 0.0002490209464562909, "language": "zho" }, { "confidence": 0.00021850038841830788, "language": "zho" }, { "confidence": 0.00010487340166964731, "language": "jpn" }, { "confidence": 0.0, "language": "ara" } ], "requestId": "7abef8d4-b045-41d3-a3d4-00b5ef1fd6a4", "timers": { "rliJe": 5 } } python-0.7.4/tests/mock-data/response/xxx-null-language.status 0000664 0000000 0000000 00000000003 12636317025 0024526 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/xxx-null-morphology_complete.json 0000664 0000000 0000000 00000202336 12636317025 0026475 0 ustar 00root root 0000000 0000000 { "compounds": [ { "compoundComponents": [ "독립", "운동가" ], "text": "독립운동가이자" }, { "compoundComponents": [ "조선", "민주주의" ], "text": "조선민주주의" }, { "compoundComponents": [ "인민", "공화국" ], "text": "인민공화국의" }, { "compoundComponents": [ "조선", "공산주의", "청년", "동맹" ], "text": "조선공산주의청년동맹" }, { "compoundComponents": [ "조선", "혁명군" ], "text": "조선혁명군" }, { "compoundComponents": [ "반일", "인민", "유격대" ], "text": "반일인민유격대" }, { "compoundComponents": [ "조선", "인민", "혁명군" ], "text": "조선인민혁명군으로" }, { "compoundComponents": [ "조선", "민주주의", "인민", "공화국" ], "text": "조선민주주의인민공화국의" }, { "compoundComponents": [ "인민", "공화국" ], "text": "인민공화국" }, { "compoundComponents": [ "국가", "주석" ], "text": "국가주석이었고" }, { "compoundComponents": [ "국가", "주석" ], "text": "국가주석에" }, { "compoundComponents": [ "당중앙", "위원회" ], "text": "당중앙위원회" }, { "compoundComponents": [ "중앙", "위원회" ], "text": "중앙위원회" }, { "compoundComponents": [ "총비", "서로" ], "text": "총비서로" }, { "compoundComponents": [ "당중앙", "위원회" ], "text": "당중앙위원회" }, { "compoundComponents": [ "총비", "서로" ], "text": "총비서로" }, { "compoundComponents": [ "한국", "전쟁" ], "text": "한국전쟁을" }, { "compoundComponents": [ "장본인", "중" ], "text": "장본인중" }, { "compoundComponents": [ "절대", "권력" ], "text": "절대권력의" }, { "compoundComponents": [ "삼형", "제의" ], "text": "삼형제의" }, { "compoundComponents": [ "셔먼", "호" ], "text": "셔먼호" }, { "compoundComponents": [ "항일", "무장", "투쟁" ], "text": "항일무장투쟁을" }, { "compoundComponents": [ "민족", "운동" ], "text": "민족운동과" }, { "compoundComponents": [ "교육", "사업" ], "text": "교육사업에" }, { "compoundComponents": [ "독립", "운동" ], "text": "독립운동을" }, { "compoundComponents": [ "팔", "도구" ], "text": "팔도구에서" }, { "compoundComponents": [ "팔도", "구소" ], "text": "팔도구소" }, { "compoundComponents": [ "창덕", "소학교" ], "text": "창덕소학교에" }, { "compoundComponents": [ "창덕", "학교" ], "text": "창덕학교는" }, { "compoundComponents": [ "장로", "교회" ], "text": "장로교회가" }, { "compoundComponents": [ "창덕", "학교" ], "text": "창덕학교의" }, { "compoundComponents": [ "중국인", "소학교" ], "text": "중국인소학교에서" }, { "compoundComponents": [ "중어", "공부" ], "text": "중어공부를" }, { "compoundComponents": [ "창덕", "학교" ], "text": "창덕학교로의" }, { "compoundComponents": [ "진학", "과정" ], "text": "진학과정에" }, { "compoundComponents": [ "팔", "도구" ], "text": "팔도구로부터" }, { "compoundComponents": [ "창덕", "학교" ], "text": "창덕학교에서" } ], "hanReadings": [], "lemmas": [ { "lemma": "김일성", "text": "김일성" }, { "lemma": "(", "text": "(" }, { "lemma": "金", "text": "金" }, { "lemma": "日", "text": "日" }, { "lemma": "成", "text": "成" }, { "lemma": ",", "text": "," }, { "lemma": "년", "text": "1912년" }, { "lemma": "월", "text": "4월" }, { "lemma": "일", "text": "15일" }, { "lemma": "~", "text": "~" }, { "lemma": "년", "text": "1994년" }, { "lemma": "월", "text": "7월" }, { "lemma": "일", "text": "8일" }, { "lemma": ")", "text": ")" }, { "lemma": "은", "text": "은" }, { "lemma": "한국", "text": "한국의" }, { "lemma": "독립운동가", "text": "독립운동가이자" }, { "lemma": "조선민주주의", "text": "조선민주주의" }, { "lemma": "인민공화국", "text": "인민공화국의" }, { "lemma": "정치인", "text": "정치인이다" }, { "lemma": ".", "text": "." }, { "lemma": "만주", "text": "만주" }, { "lemma": "조선공산주의청년동맹", "text": "조선공산주의청년동맹" }, { "lemma": ",", "text": "," }, { "lemma": "조선혁명군", "text": "조선혁명군" }, { "lemma": ",", "text": "," }, { "lemma": "반일인민유격대", "text": "반일인민유격대" }, { "lemma": "(", "text": "(" }, { "lemma": "그후", "text": "그후" }, { "lemma": "조선인민혁명군", "text": "조선인민혁명군으로" }, { "lemma": "개편", "text": "개편" }, { "lemma": ")", "text": ")" }, { "lemma": "등", "text": "등을" }, { "lemma": "조직", "text": "조직했다" }, { "lemma": ".", "text": "." }, { "lemma": "해방", "text": "해방" }, { "lemma": "후", "text": "후" }, { "lemma": "년", "text": "1948년부터" }, { "lemma": "년", "text": "1972년까지는" }, { "lemma": "조선민주주의인민공화국", "text": "조선민주주의인민공화국의" }, { "lemma": "총리", "text": "총리" }, { "lemma": ",", "text": "," }, { "lemma": "년", "text": "1972년부터는" }, { "lemma": "인민공화국", "text": "인민공화국" }, { "lemma": "국가주석", "text": "국가주석이었고" }, { "lemma": ",", "text": "," }, { "lemma": "년", "text": "1990년" }, { "lemma": "국가주석", "text": "국가주석에" }, { "lemma": "재선", "text": "재선되었다" }, { "lemma": ".", "text": "." }, { "lemma": "원래", "text": "원래" }, { "lemma": "이름", "text": "이름은" }, { "lemma": "김성주", "text": "김성주" }, { "lemma": "(", "text": "(" }, { "lemma": "金", "text": "金" }, { "lemma": "成", "text": "成" }, { "lemma": "柱", "text": "柱" }, { "lemma": "[", "text": "[" }, { "lemma": "1", "text": "1" }, { "lemma": "]", "text": "]" }, { "lemma": "[", "text": "[" }, { "lemma": "2", "text": "2" }, { "lemma": "]", "text": "]" }, { "lemma": "또는", "text": "또는" }, { "lemma": "金", "text": "金" }, { "lemma": "聖", "text": "聖" }, { "lemma": "柱", "text": "柱" }, { "lemma": "[", "text": "[" }, { "lemma": "3", "text": "3" }, { "lemma": "]", "text": "]" }, { "lemma": "[", "text": "[" }, { "lemma": "4", "text": "4" }, { "lemma": "]", "text": "]" }, { "lemma": ")", "text": ")" }, { "lemma": "이다", "text": "였는데" }, { "lemma": ",", "text": "," }, { "lemma": "항일", "text": "항일" }, { "lemma": "투쟁", "text": "투쟁을" }, { "lemma": "하다", "text": "하면서" }, { "lemma": "[", "text": "[" }, { "lemma": "3", "text": "3" }, { "lemma": "]", "text": "]" }, { "lemma": "[", "text": "[" }, { "lemma": "4", "text": "4" }, { "lemma": "]", "text": "]" }, { "lemma": "[", "text": "[" }, { "lemma": "5", "text": "5" }, { "lemma": "]", "text": "]" }, { "lemma": "김일성", "text": "김일성으로" }, { "lemma": "개명", "text": "개명" }, { "lemma": "[", "text": "[" }, { "lemma": "3", "text": "3" }, { "lemma": "]", "text": "]" }, { "lemma": "[", "text": "[" }, { "lemma": "4", "text": "4" }, { "lemma": "]", "text": "]" }, { "lemma": "[", "text": "[" }, { "lemma": "6", "text": "6" }, { "lemma": "]", "text": "]" }, { "lemma": "하다", "text": "하였다" }, { "lemma": ".", "text": "." }, { "lemma": "년", "text": "1966년" }, { "lemma": "월", "text": "10월" }, { "lemma": "당중앙위원회", "text": "당중앙위원회" }, { "lemma": "제4기", "text": "제4기" }, { "lemma": "14차전원회의에서", "text": "14차전원회의에서" }, { "lemma": "조선로동당", "text": "조선로동당" }, { "lemma": "중앙위원회", "text": "중앙위원회" }, { "lemma": "총비서로", "text": "총비서로" }, { "lemma": "선출", "text": "선출되었고" }, { "lemma": "1970", "text": "1970" }, { "lemma": "년", "text": "년에" }, { "lemma": "진행", "text": "진행된" }, { "lemma": "제5차전당대회와", "text": "제5차전당대회와" }, { "lemma": "년", "text": "1980년" }, { "lemma": "월", "text": "10월에의" }, { "lemma": "6차전당대회에서", "text": "6차전당대회에서" }, { "lemma": "당중앙위원회", "text": "당중앙위원회" }, { "lemma": "총비서로", "text": "총비서로" }, { "lemma": "또다시", "text": "또다시" }, { "lemma": "재서", "text": "재선" }, { "lemma": "되", "text": "되었다" }, { "lemma": ".", "text": "." }, { "lemma": "대한민국", "text": "대한민국에서는" }, { "lemma": "한국전쟁", "text": "한국전쟁을" }, { "lemma": "발발", "text": "발발하게" }, { "lemma": "하", "text": "한" }, { "lemma": "장본인중", "text": "장본인중" }, { "lemma": "한사람", "text": "한사람으로" }, { "lemma": "지목", "text": "지목되어" }, { "lemma": "최근", "text": "최근까지" }, { "lemma": "부정", "text": "부정적인" }, { "lemma": "평가", "text": "평가를" }, { "lemma": "받다", "text": "받아" }, { "lemma": "오", "text": "왔다" }, { "lemma": ".", "text": "." }, { "lemma": "년", "text": "1994년" }, { "lemma": "절대권력", "text": "절대권력의" }, { "lemma": "상징", "text": "상징이었던" }, { "lemma": "그", "text": "그가" }, { "lemma": "사망", "text": "사망하면서" }, { "lemma": "아들", "text": "아들" }, { "lemma": "김정일", "text": "김정일에게" }, { "lemma": "모든", "text": "모든" }, { "lemma": "권력", "text": "권력을" }, { "lemma": "승", "text": "승" }, { "lemma": "계하", "text": "계하였다" }, { "lemma": ".", "text": "." }, { "lemma": "어리", "text": "어린" }, { "lemma": "시절", "text": "시절과" }, { "lemma": "가계", "text": "가계" }, { "lemma": "[", "text": "[" }, { "lemma": "편집", "text": "편집" }, { "lemma": "]", "text": "]" }, { "lemma": "김일성", "text": "김일성의" }, { "lemma": "생가", "text": "생가" }, { "lemma": "김일성", "text": "김일성은" }, { "lemma": "년", "text": "1912년" }, { "lemma": "월", "text": "4월" }, { "lemma": "일", "text": "15일에" }, { "lemma": "평안남도", "text": "평안남도" }, { "lemma": "대동군", "text": "대동군" }, { "lemma": "고평면", "text": "고평면" }, { "lemma": "(", "text": "(" }, { "lemma": "古", "text": "古" }, { "lemma": "平", "text": "平" }, { "lemma": "面", "text": "面" }, { "lemma": ")", "text": ")" }, { "lemma": "하리", "text": "하리" }, { "lemma": "칠곡", "text": "칠곡" }, { "lemma": "(", "text": "(" }, { "lemma": "외가", "text": "외가가" }, { "lemma": "있", "text": "있었던" }, { "lemma": "곳", "text": "곳으로" }, { "lemma": ",", "text": "," }, { "lemma": "오늘날", "text": "오늘날" }, { "lemma": "평양", "text": "평양" }, { "lemma": "만경대", "text": "만경대" }, { "lemma": ")", "text": ")" }, { "lemma": "[", "text": "[" }, { "lemma": "6", "text": "6" }, { "lemma": "]", "text": "]" }, { "lemma": "에서", "text": "에서" }, { "lemma": "아버지", "text": "아버지" }, { "lemma": "김형직", "text": "김형직" }, { "lemma": "(", "text": "(" }, { "lemma": "金", "text": "金" }, { "lemma": "亨", "text": "亨" }, { "lemma": "稷", "text": "稷" }, { "lemma": ",", "text": "," }, { "lemma": "년", "text": "1894년" }, { "lemma": "월", "text": "7월" }, { "lemma": "일", "text": "10일" }, { "lemma": "~", "text": "~" }, { "lemma": "년", "text": "1926년" }, { "lemma": ")", "text": ")" }, { "lemma": "과", "text": "과" }, { "lemma": "어머니", "text": "어머니" }, { "lemma": "강반석", "text": "강반석" }, { "lemma": "(", "text": "(" }, { "lemma": "康", "text": "康" }, { "lemma": "盤", "text": "盤" }, { "lemma": "石", "text": "石" }, { "lemma": ",", "text": "," }, { "lemma": "[", "text": "[" }, { "lemma": "7", "text": "7" }, { "lemma": "]", "text": "]" }, { "lemma": "년", "text": "1892년" }, { "lemma": "~", "text": "~" }, { "lemma": "년", "text": "1932년" }, { "lemma": ")", "text": ")" }, { "lemma": "의", "text": "의" }, { "lemma": "삼형제의", "text": "삼형제의" }, { "lemma": "맏아", "text": "맏아들로" }, { "lemma": "태어나다", "text": "태어났다" }, { "lemma": ".", "text": "." }, { "lemma": "김일성", "text": "김일성의" }, { "lemma": "전주", "text": "전주" }, { "lemma": "김", "text": "김씨" }, { "lemma": "12대조", "text": "12대조" }, { "lemma": "김계상", "text": "김계상이" }, { "lemma": "전라북도", "text": "전라북도" }, { "lemma": "전", "text": "전" }, { "lemma": "주", "text": "주에서" }, { "lemma": "평양", "text": "평양으로" }, { "lemma": "이주", "text": "이주하였으며" }, { "lemma": ",", "text": "," }, { "lemma": "[", "text": "[" }, { "lemma": "6", "text": "6" }, { "lemma": "]", "text": "]" }, { "lemma": "[", "text": "[" }, { "lemma": "8", "text": "8" }, { "lemma": "]", "text": "]" }, { "lemma": "이후", "text": "이후" }, { "lemma": "농업", "text": "농업에" }, { "lemma": "종사", "text": "종사하였으며" }, { "lemma": ",", "text": "," }, { "lemma": "증조부", "text": "증조부" }, { "lemma": "김응우", "text": "김응우는" }, { "lemma": "제너럴", "text": "제너럴" }, { "lemma": "셔먼호", "text": "셔먼호" }, { "lemma": "사건", "text": "사건에" }, { "lemma": "종군", "text": "종군하였다" }, { "lemma": ".", "text": "." }, { "lemma": "북조선", "text": "북조선에서는" }, { "lemma": "김응우", "text": "김응우가" }, { "lemma": "제너럴", "text": "제너럴" }, { "lemma": "셔먼", "text": "셔먼" }, { "lemma": "호", "text": "호" }, { "lemma": "격퇴", "text": "격퇴의" }, { "lemma": "지휘관", "text": "지휘관이라" }, { "lemma": "주장", "text": "주장한다" }, { "lemma": ".", "text": "." }, { "lemma": "그", "text": "그의" }, { "lemma": "생가", "text": "생가는" }, { "lemma": "만경대", "text": "만경대라는" }, { "lemma": "이름", "text": "이름으로" }, { "lemma": "보존", "text": "보존" }, { "lemma": ",", "text": "," }, { "lemma": "관리", "text": "관리되고" }, { "lemma": "있", "text": "있다" }, { "lemma": ".", "text": "." }, { "lemma": "김형직", "text": "김형직은" }, { "lemma": "할아버지", "text": "할아버지" }, { "lemma": "이래", "text": "이래로" }, { "lemma": "지주", "text": "지주" }, { "lemma": "집안", "text": "집안의" }, { "lemma": "묘지기", "text": "묘지기였으며" }, { "lemma": ",", "text": "," }, { "lemma": "[", "text": "[" }, { "lemma": "9", "text": "9" }, { "lemma": "]", "text": "]" }, { "lemma": "일본", "text": "일본" }, { "lemma": "제국주의", "text": "제국주의에" }, { "lemma": "대항", "text": "대항하여" }, { "lemma": "항일무장투쟁", "text": "항일무장투쟁을" }, { "lemma": "벌이다", "text": "벌인" }, { "lemma": "한국", "text": "한국의" }, { "lemma": "독립", "text": "독립" }, { "lemma": "운동가", "text": "운동가로" }, { "lemma": "알려지다", "text": "알려져" }, { "lemma": "있", "text": "있다" }, { "lemma": ".", "text": "." }, { "lemma": "[", "text": "[" }, { "lemma": "3", "text": "3" }, { "lemma": "]", "text": "]" }, { "lemma": "어머니", "text": "어머니" }, { "lemma": "강반석", "text": "강반석은" }, { "lemma": "기독교", "text": "기독교" }, { "lemma": "장로교", "text": "장로교" }, { "lemma": "신도", "text": "신도였고" }, { "lemma": ",", "text": "," }, { "lemma": "외할아버지", "text": "외할아버지" }, { "lemma": "강돈욱", "text": "강돈욱" }, { "lemma": "[", "text": "[" }, { "lemma": "9", "text": "9" }, { "lemma": "]", "text": "]" }, { "lemma": "늘", "text": "는" }, { "lemma": "칠골교회", "text": "칠골교회의" }, { "lemma": "장로", "text": "장로" }, { "lemma": "[", "text": "[" }, { "lemma": "10", "text": "10" }, { "lemma": "]", "text": "]" }, { "lemma": "이다", "text": "였다" }, { "lemma": ".", "text": "." }, { "lemma": "[", "text": "[" }, { "lemma": "3", "text": "3" }, { "lemma": "]", "text": "]" }, { "lemma": "김일성", "text": "김일성의" }, { "lemma": "외", "text": "외가" }, { "lemma": "늘다", "text": "는" }, { "lemma": "크", "text": "큰" }, { "lemma": "외삼촌", "text": "외삼촌" }, { "lemma": "강진석", "text": "강진석" }, { "lemma": "(", "text": "(" }, { "lemma": "康", "text": "康" }, { "lemma": "晋", "text": "晋" }, { "lemma": "錫", "text": "錫" }, { "lemma": ")", "text": ")" }, { "lemma": "을", "text": "을" }, { "lemma": "비롯", "text": "비롯하여" }, { "lemma": "일찍부터", "text": "일찍부터" }, { "lemma": "항일", "text": "항일" }, { "lemma": "민족운동", "text": "민족운동과" }, { "lemma": "관련", "text": "관련을" }, { "lemma": "맺다", "text": "맺고" }, { "lemma": "있", "text": "있었으며" }, { "lemma": ",", "text": "," }, { "lemma": "강돈욱", "text": "강돈욱은" }, { "lemma": "평생", "text": "평생을" }, { "lemma": "교육사업", "text": "교육사업에" }, { "lemma": "헌신", "text": "헌신한" }, { "lemma": "기독교인", "text": "기독교인이었다" }, { "lemma": ".", "text": "." }, { "lemma": "[", "text": "[" }, { "lemma": "9", "text": "9" }, { "lemma": "]", "text": "]" }, { "lemma": "아버지", "text": "아버지" }, { "lemma": "김형직", "text": "김형직" }, { "lemma": "또는", "text": "또는" }, { "lemma": "할아버지", "text": "할아버지" }, { "lemma": "김보현", "text": "김보현이" }, { "lemma": "기둥이", "text": "기둥이" }, { "lemma": "되", "text": "되라" }, { "lemma": "늘", "text": "는" }, { "lemma": "뜻", "text": "뜻에서" }, { "lemma": "그", "text": "그의" }, { "lemma": "이름", "text": "이름을" }, { "lemma": "성주", "text": "성주" }, { "lemma": "(", "text": "(" }, { "lemma": "成", "text": "成" }, { "lemma": "柱", "text": "柱" }, { "lemma": ")", "text": ")" }, { "lemma": "또는", "text": "또는" }, { "lemma": "성주", "text": "성주" }, { "lemma": "(", "text": "(" }, { "lemma": "聖", "text": "聖" }, { "lemma": "柱", "text": "柱" }, { "lemma": ")", "text": ")" }, { "lemma": "라", "text": "라" }, { "lemma": "짓다", "text": "지었다고" }, { "lemma": "하", "text": "한다" }, { "lemma": ".", "text": "." }, { "lemma": "어려서", "text": "어려서" }, { "lemma": "부모", "text": "부모를" }, { "lemma": "따르다", "text": "따라" }, { "lemma": "주", "text": "만주" }, { "lemma": "지린성", "text": "지린성" }, { "lemma": "(", "text": "(" }, { "lemma": "吉", "text": "吉" }, { "lemma": "林", "text": "林" }, { "lemma": "省", "text": "省" }, { "lemma": ")", "text": ")" }, { "lemma": "무송", "text": "무송" }, { "lemma": "(", "text": "(" }, { "lemma": "撫", "text": "撫" }, { "lemma": "松", "text": "松" }, { "lemma": ")", "text": ")" }, { "lemma": "으로", "text": "으로" }, { "lemma": "이사", "text": "이사했다" }, { "lemma": ".", "text": "." }, { "lemma": "년", "text": "1919년" }, { "lemma": "일곱", "text": "일곱" }, { "lemma": "살", "text": "살이었던" }, { "lemma": "김일성", "text": "김일성은" }, { "lemma": "민족주의", "text": "민족주의" }, { "lemma": "계열", "text": "계열의" }, { "lemma": "독립운동", "text": "독립운동을" }, { "lemma": "하다", "text": "하던" }, { "lemma": "아버지", "text": "아버지" }, { "lemma": "김형직", "text": "김형직을" }, { "lemma": "따르다", "text": "따라" }, { "lemma": "만주", "text": "만주로" }, { "lemma": "건너", "text": "건너가" }, { "lemma": "장백현", "text": "장백현" }, { "lemma": "팔도구", "text": "팔도구에서" }, { "lemma": "팔도구소", "text": "팔도구소" }, { "lemma": "학교", "text": "학교를" }, { "lemma": "다니다", "text": "다녔다" }, { "lemma": ".", "text": "." }, { "lemma": "그", "text": "그" }, { "lemma": "뒤", "text": "뒤" }, { "lemma": "자식", "text": "자식의" }, { "lemma": "장래", "text": "장래를" }, { "lemma": "생각", "text": "생각한" }, { "lemma": "김형직", "text": "김형직의" }, { "lemma": "결심", "text": "결심에" }, { "lemma": "따르다", "text": "따라" }, { "lemma": "년", "text": "1923년" }, { "lemma": "초", "text": "초부터" }, { "lemma": "년", "text": "1925년" }, { "lemma": "초", "text": "초까지" }, { "lemma": "평", "text": "평" }, { "lemma": "안", "text": "안도" }, { "lemma": "대동군", "text": "대동군" }, { "lemma": "용산면", "text": "용산면" }, { "lemma": "하리", "text": "하리" }, { "lemma": "(", "text": "(" }, { "lemma": "下", "text": "下" }, { "lemma": "里", "text": "里" }, { "lemma": ")", "text": ")" }, { "lemma": "칠골", "text": "칠골에" }, { "lemma": "있", "text": "있는" }, { "lemma": "외가", "text": "외가에서" }, { "lemma": "머물다", "text": "머물면서" }, { "lemma": "창덕소학교", "text": "창덕소학교에" }, { "lemma": "다니다", "text": "다녔다" }, { "lemma": ".", "text": "." }, { "lemma": "[", "text": "[" }, { "lemma": "9", "text": "9" }, { "lemma": "]", "text": "]" }, { "lemma": "창덕학교", "text": "창덕학교는" }, { "lemma": "년", "text": "1907년" }, { "lemma": "하리", "text": "하리" }, { "lemma": "장로교회", "text": "장로교회가" }, { "lemma": "중심", "text": "중심이" }, { "lemma": "되다", "text": "되어" }, { "lemma": "세운", "text": "세운" }, { "lemma": "년제", "text": "5년제" }, { "lemma": "학교", "text": "학교인데" }, { "lemma": ",", "text": "," }, { "lemma": "김일성", "text": "김일성의" }, { "lemma": "외할아버지", "text": "외할아버지인" }, { "lemma": "강돈욱", "text": "강돈욱도" }, { "lemma": "설립자", "text": "설립자" }, { "lemma": "가운데", "text": "가운데" }, { "lemma": "한", "text": "한" }, { "lemma": "사람", "text": "사람이며" }, { "lemma": ",", "text": "," }, { "lemma": "한때", "text": "한때" }, { "lemma": "창덕학교", "text": "창덕학교의" }, { "lemma": "교감", "text": "교감과" }, { "lemma": "교장", "text": "교장을" }, { "lemma": "맡다", "text": "맡기도" }, { "lemma": "하", "text": "했다" }, { "lemma": ".", "text": "." }, { "lemma": "아버지", "text": "아버지" }, { "lemma": "김형직", "text": "김형직의" }, { "lemma": "권고", "text": "권고로" }, { "lemma": "중국말", "text": "중국말" }, { "lemma": "을", "text": "을" }, { "lemma": "배우다", "text": "배우고" }, { "lemma": "중국인소학교", "text": "중국인소학교에서" }, { "lemma": "중어공부", "text": "중어공부를" }, { "lemma": "하다", "text": "하여" }, { "lemma": "중어", "text": "중어를" }, { "lemma": "자유롭", "text": "자유롭게" }, { "lemma": "구사할수", "text": "구사할수" }, { "lemma": "있", "text": "있었다" }, { "lemma": ".", "text": "." }, { "lemma": "[", "text": "[" }, { "lemma": "11", "text": "11" }, { "lemma": "]", "text": "]" }, { "lemma": "창덕학교", "text": "창덕학교로의" }, { "lemma": "진학과정", "text": "진학과정에" }, { "lemma": "대하다", "text": "대하여" }, { "lemma": "략력", "text": "략력에서는" }, { "lemma": "아버지", "text": "아버지" }, { "lemma": "김형직", "text": "김형직이" }, { "lemma": "'", "text": "'" }, { "lemma": "혁명", "text": "혁명을" }, { "lemma": "하다", "text": "하자면" }, { "lemma": "자기", "text": "자기" }, { "lemma": "나라", "text": "나라를" }, { "lemma": "알다", "text": "알아야" }, { "lemma": "하", "text": "한다고" }, { "lemma": "말하다", "text": "말한" }, { "lemma": "권고", "text": "권고를" }, { "lemma": "받다", "text": "받고" }, { "lemma": "년", "text": "1923년" }, { "lemma": "월", "text": "3월" }, { "lemma": "중국", "text": "중국" }, { "lemma": "팔도구", "text": "팔도구로부터" }, { "lemma": "만경대까지배움", "text": "만경대까지배움의" }, { "lemma": "천리길", "text": "천리길을" }, { "lemma": "걷다", "text": "걸어" }, { "lemma": "통학", "text": "통학하며" }, { "lemma": "외", "text": "외" }, { "lemma": "가집", "text": "가집이" }, { "lemma": "있", "text": "있는" }, { "lemma": "칠고", "text": "칠골" }, { "lemma": "창덕학교", "text": "창덕학교에서" }, { "lemma": "공부", "text": "공부하였다는" }, { "lemma": "것", "text": "것이다" }, { "lemma": ".", "text": "." } ], "posTags": [ { "pos": "NPR", "text": "김일성" }, { "pos": "SLQ", "text": "(" }, { "pos": "UNK", "text": "金" }, { "pos": "UNK", "text": "日" }, { "pos": "UNK", "text": "成" }, { "pos": "SCM", "text": "," }, { "pos": "NNU", "text": "1912년" }, { "pos": "NNU", "text": "4월" }, { "pos": "NNU", "text": "15일" }, { "pos": "SSY", "text": "~" }, { "pos": "NNU", "text": "1994년" }, { "pos": "NNU", "text": "7월" }, { "pos": "NNU", "text": "8일" }, { "pos": "SRQ", "text": ")" }, { "pos": "NPR", "text": "은" }, { "pos": "NPR", "text": "한국의" }, { "pos": "NNC", "text": "독립운동가이자" }, { "pos": "NNC", "text": "조선민주주의" }, { "pos": "NNC", "text": "인민공화국의" }, { "pos": "NPR", "text": "정치인이다" }, { "pos": "SSY", "text": "." }, { "pos": "NPR", "text": "만주" }, { "pos": "NNC", "text": "조선공산주의청년동맹" }, { "pos": "SCM", "text": "," }, { "pos": "NNC", "text": "조선혁명군" }, { "pos": "SCM", "text": "," }, { "pos": "NNC", "text": "반일인민유격대" }, { "pos": "SLQ", "text": "(" }, { "pos": "NNC", "text": "그후" }, { "pos": "NNC", "text": "조선인민혁명군으로" }, { "pos": "NNC", "text": "개편" }, { "pos": "SRQ", "text": ")" }, { "pos": "NNX", "text": "등을" }, { "pos": "NNC", "text": "조직했다" }, { "pos": "SFN", "text": "." }, { "pos": "NNC", "text": "해방" }, { "pos": "NNC", "text": "후" }, { "pos": "NNU", "text": "1948년부터" }, { "pos": "NNU", "text": "1972년까지는" }, { "pos": "NNC", "text": "조선민주주의인민공화국의" }, { "pos": "NNC", "text": "총리" }, { "pos": "SCM", "text": "," }, { "pos": "NNU", "text": "1972년부터는" }, { "pos": "NNC", "text": "인민공화국" }, { "pos": "NNC", "text": "국가주석이었고" }, { "pos": "SCM", "text": "," }, { "pos": "NNU", "text": "1990년" }, { "pos": "NNC", "text": "국가주석에" }, { "pos": "NNC", "text": "재선되었다" }, { "pos": "SFN", "text": "." }, { "pos": "NNC", "text": "원래" }, { "pos": "NNC", "text": "이름은" }, { "pos": "NPR", "text": "김성주" }, { "pos": "SLQ", "text": "(" }, { "pos": "UNK", "text": "金" }, { "pos": "UNK", "text": "成" }, { "pos": "UNK", "text": "柱" }, { "pos": "SLQ", "text": "[" }, { "pos": "NNU", "text": "1" }, { "pos": "SRQ", "text": "]" }, { "pos": "SLQ", "text": "[" }, { "pos": "NNU", "text": "2" }, { "pos": "SRQ", "text": "]" }, { "pos": "ADC", "text": "또는" }, { "pos": "UNK", "text": "金" }, { "pos": "UNK", "text": "聖" }, { "pos": "UNK", "text": "柱" }, { "pos": "SLQ", "text": "[" }, { "pos": "NNU", "text": "3" }, { "pos": "SRQ", "text": "]" }, { "pos": "SLQ", "text": "[" }, { "pos": "NNU", "text": "4" }, { "pos": "SRQ", "text": "]" }, { "pos": "SRQ", "text": ")" }, { "pos": "VV", "text": "였는데" }, { "pos": "SCM", "text": "," }, { "pos": "NNC", "text": "항일" }, { "pos": "NNC", "text": "투쟁을" }, { "pos": "VV", "text": "하면서" }, { "pos": "SLQ", "text": "[" }, { "pos": "NNU", "text": "3" }, { "pos": "SRQ", "text": "]" }, { "pos": "SLQ", "text": "[" }, { "pos": "NNU", "text": "4" }, { "pos": "SRQ", "text": "]" }, { "pos": "SLQ", "text": "[" }, { "pos": "NNU", "text": "5" }, { "pos": "SRQ", "text": "]" }, { "pos": "NPR", "text": "김일성으로" }, { "pos": "NNC", "text": "개명" }, { "pos": "SLQ", "text": "[" }, { "pos": "NNU", "text": "3" }, { "pos": "SRQ", "text": "]" }, { "pos": "SLQ", "text": "[" }, { "pos": "NNU", "text": "4" }, { "pos": "SRQ", "text": "]" }, { "pos": "SLQ", "text": "[" }, { "pos": "NNU", "text": "6" }, { "pos": "SRQ", "text": "]" }, { "pos": "VV", "text": "하였다" }, { "pos": "SFN", "text": "." }, { "pos": "NNU", "text": "1966년" }, { "pos": "NNU", "text": "10월" }, { "pos": "NNC", "text": "당중앙위원회" }, { "pos": "UNK", "text": "제4기" }, { "pos": "UNK", "text": "14차전원회의에서" }, { "pos": "NPR", "text": "조선로동당" }, { "pos": "NPR", "text": "중앙위원회" }, { "pos": "NNC", "text": "총비서로" }, { "pos": "NNC", "text": "선출되었고" }, { "pos": "NNU", "text": "1970" }, { "pos": "NNX", "text": "년에" }, { "pos": "NNC", "text": "진행된" }, { "pos": "UNK", "text": "제5차전당대회와" }, { "pos": "NNU", "text": "1980년" }, { "pos": "NNU", "text": "10월에의" }, { "pos": "UNK", "text": "6차전당대회에서" }, { "pos": "NNC", "text": "당중앙위원회" }, { "pos": "NNC", "text": "총비서로" }, { "pos": "ADV", "text": "또다시" }, { "pos": "NNC", "text": "재선" }, { "pos": "VJ", "text": "되었다" }, { "pos": "SFN", "text": "." }, { "pos": "NPR", "text": "대한민국에서는" }, { "pos": "NPR", "text": "한국전쟁을" }, { "pos": "NNC", "text": "발발하게" }, { "pos": "VX", "text": "한" }, { "pos": "NNC", "text": "장본인중" }, { "pos": "NNC", "text": "한사람으로" }, { "pos": "NNC", "text": "지목되어" }, { "pos": "NNC", "text": "최근까지" }, { "pos": "NNC", "text": "부정적인" }, { "pos": "NNC", "text": "평가를" }, { "pos": "VV", "text": "받아" }, { "pos": "VX", "text": "왔다" }, { "pos": "SFN", "text": "." }, { "pos": "NNU", "text": "1994년" }, { "pos": "NNC", "text": "절대권력의" }, { "pos": "NNC", "text": "상징이었던" }, { "pos": "NPN", "text": "그가" }, { "pos": "NNC", "text": "사망하면서" }, { "pos": "NNC", "text": "아들" }, { "pos": "NPR", "text": "김정일에게" }, { "pos": "DAN", "text": "모든" }, { "pos": "NNC", "text": "권력을" }, { "pos": "NPR", "text": "승" }, { "pos": "NNC", "text": "계하였다" }, { "pos": "SFN", "text": "." }, { "pos": "VJ", "text": "어린" }, { "pos": "NNC", "text": "시절과" }, { "pos": "NNC", "text": "가계" }, { "pos": "SLQ", "text": "[" }, { "pos": "NNC", "text": "편집" }, { "pos": "SRQ", "text": "]" }, { "pos": "NPR", "text": "김일성의" }, { "pos": "NNC", "text": "생가" }, { "pos": "NPR", "text": "김일성은" }, { "pos": "NNU", "text": "1912년" }, { "pos": "NNU", "text": "4월" }, { "pos": "NNU", "text": "15일에" }, { "pos": "NPR", "text": "평안남도" }, { "pos": "NPR", "text": "대동군" }, { "pos": "NPR", "text": "고평면" }, { "pos": "SLQ", "text": "(" }, { "pos": "UNK", "text": "古" }, { "pos": "UNK", "text": "平" }, { "pos": "UNK", "text": "面" }, { "pos": "SRQ", "text": ")" }, { "pos": "NNC", "text": "하리" }, { "pos": "NPR", "text": "칠곡" }, { "pos": "SLQ", "text": "(" }, { "pos": "NNC", "text": "외가가" }, { "pos": "VJ", "text": "있었던" }, { "pos": "NNC", "text": "곳으로" }, { "pos": "SCM", "text": "," }, { "pos": "NNC", "text": "오늘날" }, { "pos": "NPR", "text": "평양" }, { "pos": "NPR", "text": "만경대" }, { "pos": "SRQ", "text": ")" }, { "pos": "SLQ", "text": "[" }, { "pos": "NNU", "text": "6" }, { "pos": "SRQ", "text": "]" }, { "pos": "NPR", "text": "에서" }, { "pos": "NNC", "text": "아버지" }, { "pos": "NPR", "text": "김형직" }, { "pos": "SLQ", "text": "(" }, { "pos": "UNK", "text": "金" }, { "pos": "UNK", "text": "亨" }, { "pos": "UNK", "text": "稷" }, { "pos": "SCM", "text": "," }, { "pos": "NNU", "text": "1894년" }, { "pos": "NNU", "text": "7월" }, { "pos": "NNU", "text": "10일" }, { "pos": "SSY", "text": "~" }, { "pos": "NNU", "text": "1926년" }, { "pos": "SRQ", "text": ")" }, { "pos": "NNC", "text": "과" }, { "pos": "NNC", "text": "어머니" }, { "pos": "NPR", "text": "강반석" }, { "pos": "SLQ", "text": "(" }, { "pos": "UNK", "text": "康" }, { "pos": "UNK", "text": "盤" }, { "pos": "UNK", "text": "石" }, { "pos": "SCM", "text": "," }, { "pos": "SLQ", "text": "[" }, { "pos": "NNU", "text": "7" }, { "pos": "SRQ", "text": "]" }, { "pos": "NNU", "text": "1892년" }, { "pos": "SSY", "text": "~" }, { "pos": "NNU", "text": "1932년" }, { "pos": "SRQ", "text": ")" }, { "pos": "NNC", "text": "의" }, { "pos": "NNC", "text": "삼형제의" }, { "pos": "NNC", "text": "맏아들로" }, { "pos": "VV", "text": "태어났다" }, { "pos": "SFN", "text": "." }, { "pos": "NPR", "text": "김일성의" }, { "pos": "NNC", "text": "전주" }, { "pos": "NPR", "text": "김씨" }, { "pos": "UNK", "text": "12대조" }, { "pos": "NPR", "text": "김계상이" }, { "pos": "NPR", "text": "전라북도" }, { "pos": "NNC", "text": "전" }, { "pos": "NNX", "text": "주에서" }, { "pos": "NPR", "text": "평양으로" }, { "pos": "NNC", "text": "이주하였으며" }, { "pos": "SCM", "text": "," }, { "pos": "SLQ", "text": "[" }, { "pos": "NNU", "text": "6" }, { "pos": "SRQ", "text": "]" }, { "pos": "SLQ", "text": "[" }, { "pos": "NNU", "text": "8" }, { "pos": "SRQ", "text": "]" }, { "pos": "NNC", "text": "이후" }, { "pos": "NNC", "text": "농업에" }, { "pos": "NNC", "text": "종사하였으며" }, { "pos": "SCM", "text": "," }, { "pos": "NNC", "text": "증조부" }, { "pos": "NPR", "text": "김응우는" }, { "pos": "NPR", "text": "제너럴" }, { "pos": "NPR", "text": "셔먼호" }, { "pos": "NNC", "text": "사건에" }, { "pos": "NNC", "text": "종군하였다" }, { "pos": "SFN", "text": "." }, { "pos": "NNC", "text": "북조선에서는" }, { "pos": "NPR", "text": "김응우가" }, { "pos": "ADV", "text": "제너럴" }, { "pos": "NPR", "text": "셔먼" }, { "pos": "NNX", "text": "호" }, { "pos": "NNC", "text": "격퇴의" }, { "pos": "NNC", "text": "지휘관이라" }, { "pos": "NNC", "text": "주장한다" }, { "pos": "SFN", "text": "." }, { "pos": "NPN", "text": "그의" }, { "pos": "NNC", "text": "생가는" }, { "pos": "NPR", "text": "만경대라는" }, { "pos": "NNC", "text": "이름으로" }, { "pos": "NNC", "text": "보존" }, { "pos": "SCM", "text": "," }, { "pos": "NNC", "text": "관리되고" }, { "pos": "VX", "text": "있다" }, { "pos": "SFN", "text": "." }, { "pos": "NPR", "text": "김형직은" }, { "pos": "NNC", "text": "할아버지" }, { "pos": "NNX", "text": "이래로" }, { "pos": "NNC", "text": "지주" }, { "pos": "NNC", "text": "집안의" }, { "pos": "NNC", "text": "묘지기였으며" }, { "pos": "SCM", "text": "," }, { "pos": "SLQ", "text": "[" }, { "pos": "NNU", "text": "9" }, { "pos": "SRQ", "text": "]" }, { "pos": "NPR", "text": "일본" }, { "pos": "NNC", "text": "제국주의에" }, { "pos": "NNC", "text": "대항하여" }, { "pos": "NNC", "text": "항일무장투쟁을" }, { "pos": "VV", "text": "벌인" }, { "pos": "NPR", "text": "한국의" }, { "pos": "NNC", "text": "독립" }, { "pos": "NNC", "text": "운동가로" }, { "pos": "VV", "text": "알려져" }, { "pos": "VX", "text": "있다" }, { "pos": "SFN", "text": "." }, { "pos": "SLQ", "text": "[" }, { "pos": "NNU", "text": "3" }, { "pos": "SRQ", "text": "]" }, { "pos": "NNC", "text": "어머니" }, { "pos": "NPR", "text": "강반석은" }, { "pos": "NNC", "text": "기독교" }, { "pos": "NNC", "text": "장로교" }, { "pos": "NNC", "text": "신도였고" }, { "pos": "SCM", "text": "," }, { "pos": "NNC", "text": "외할아버지" }, { "pos": "NPR", "text": "강돈욱" }, { "pos": "SLQ", "text": "[" }, { "pos": "NNU", "text": "9" }, { "pos": "SRQ", "text": "]" }, { "pos": "VJ", "text": "는" }, { "pos": "NNC", "text": "칠골교회의" }, { "pos": "NNC", "text": "장로" }, { "pos": "SLQ", "text": "[" }, { "pos": "NNU", "text": "10" }, { "pos": "SRQ", "text": "]" }, { "pos": "VV", "text": "였다" }, { "pos": "SFN", "text": "." }, { "pos": "SLQ", "text": "[" }, { "pos": "NNU", "text": "3" }, { "pos": "SRQ", "text": "]" }, { "pos": "NPR", "text": "김일성의" }, { "pos": "NNC", "text": "외가" }, { "pos": "VV", "text": "는" }, { "pos": "VJ", "text": "큰" }, { "pos": "NNC", "text": "외삼촌" }, { "pos": "NPR", "text": "강진석" }, { "pos": "SLQ", "text": "(" }, { "pos": "UNK", "text": "康" }, { "pos": "UNK", "text": "晋" }, { "pos": "UNK", "text": "錫" }, { "pos": "SRQ", "text": ")" }, { "pos": "NNC", "text": "을" }, { "pos": "NNC", "text": "비롯하여" }, { "pos": "NPR", "text": "일찍부터" }, { "pos": "NNC", "text": "항일" }, { "pos": "NNC", "text": "민족운동과" }, { "pos": "NNC", "text": "관련을" }, { "pos": "VV", "text": "맺고" }, { "pos": "VX", "text": "있었으며" }, { "pos": "SCM", "text": "," }, { "pos": "NPR", "text": "강돈욱은" }, { "pos": "NNC", "text": "평생을" }, { "pos": "NNC", "text": "교육사업에" }, { "pos": "NNC", "text": "헌신한" }, { "pos": "NNC", "text": "기독교인이었다" }, { "pos": "SFN", "text": "." }, { "pos": "SLQ", "text": "[" }, { "pos": "NNU", "text": "9" }, { "pos": "SRQ", "text": "]" }, { "pos": "NNC", "text": "아버지" }, { "pos": "NPR", "text": "김형직" }, { "pos": "ADC", "text": "또는" }, { "pos": "NNC", "text": "할아버지" }, { "pos": "NPR", "text": "김보현이" }, { "pos": "NNC", "text": "기둥이" }, { "pos": "NNX", "text": "되라" }, { "pos": "VJ", "text": "는" }, { "pos": "NNC", "text": "뜻에서" }, { "pos": "NPN", "text": "그의" }, { "pos": "NNC", "text": "이름을" }, { "pos": "NNC", "text": "성주" }, { "pos": "SLQ", "text": "(" }, { "pos": "UNK", "text": "成" }, { "pos": "UNK", "text": "柱" }, { "pos": "SRQ", "text": ")" }, { "pos": "ADC", "text": "또는" }, { "pos": "NNC", "text": "성주" }, { "pos": "SLQ", "text": "(" }, { "pos": "UNK", "text": "聖" }, { "pos": "UNK", "text": "柱" }, { "pos": "SRQ", "text": ")" }, { "pos": "NPR", "text": "라" }, { "pos": "VV", "text": "지었다고" }, { "pos": "VX", "text": "한다" }, { "pos": "SFN", "text": "." }, { "pos": "NPR", "text": "어려서" }, { "pos": "NNC", "text": "부모를" }, { "pos": "VV", "text": "따라" }, { "pos": "NNU", "text": "만주" }, { "pos": "NPR", "text": "지린성" }, { "pos": "SLQ", "text": "(" }, { "pos": "UNK", "text": "吉" }, { "pos": "UNK", "text": "林" }, { "pos": "UNK", "text": "省" }, { "pos": "SRQ", "text": ")" }, { "pos": "NNC", "text": "무송" }, { "pos": "SLQ", "text": "(" }, { "pos": "UNK", "text": "撫" }, { "pos": "UNK", "text": "松" }, { "pos": "SRQ", "text": ")" }, { "pos": "NPR", "text": "으로" }, { "pos": "NNC", "text": "이사했다" }, { "pos": "SFN", "text": "." }, { "pos": "NNU", "text": "1919년" }, { "pos": "NNU", "text": "일곱" }, { "pos": "NNX", "text": "살이었던" }, { "pos": "NPR", "text": "김일성은" }, { "pos": "NNC", "text": "민족주의" }, { "pos": "NNC", "text": "계열의" }, { "pos": "NNC", "text": "독립운동을" }, { "pos": "VV", "text": "하던" }, { "pos": "NNC", "text": "아버지" }, { "pos": "NPR", "text": "김형직을" }, { "pos": "VV", "text": "따라" }, { "pos": "NPR", "text": "만주로" }, { "pos": "NNC", "text": "건너가" }, { "pos": "NPR", "text": "장백현" }, { "pos": "NNC", "text": "팔도구에서" }, { "pos": "NNC", "text": "팔도구소" }, { "pos": "NNC", "text": "학교를" }, { "pos": "VV", "text": "다녔다" }, { "pos": "SFN", "text": "." }, { "pos": "DAN", "text": "그" }, { "pos": "NNC", "text": "뒤" }, { "pos": "NNC", "text": "자식의" }, { "pos": "NNC", "text": "장래를" }, { "pos": "NNC", "text": "생각한" }, { "pos": "NPR", "text": "김형직의" }, { "pos": "NNC", "text": "결심에" }, { "pos": "VV", "text": "따라" }, { "pos": "NNU", "text": "1923년" }, { "pos": "NNX", "text": "초부터" }, { "pos": "NNU", "text": "1925년" }, { "pos": "NNX", "text": "초까지" }, { "pos": "NPR", "text": "평" }, { "pos": "NNC", "text": "안도" }, { "pos": "NPR", "text": "대동군" }, { "pos": "NPR", "text": "용산면" }, { "pos": "NNC", "text": "하리" }, { "pos": "SLQ", "text": "(" }, { "pos": "UNK", "text": "下" }, { "pos": "UNK", "text": "里" }, { "pos": "SRQ", "text": ")" }, { "pos": "NPR", "text": "칠골에" }, { "pos": "VJ", "text": "있는" }, { "pos": "NNC", "text": "외가에서" }, { "pos": "VV", "text": "머물면서" }, { "pos": "NPR", "text": "창덕소학교에" }, { "pos": "VV", "text": "다녔다" }, { "pos": "SFN", "text": "." }, { "pos": "SLQ", "text": "[" }, { "pos": "NNU", "text": "9" }, { "pos": "SRQ", "text": "]" }, { "pos": "NNC", "text": "창덕학교는" }, { "pos": "NNU", "text": "1907년" }, { "pos": "NNC", "text": "하리" }, { "pos": "NNC", "text": "장로교회가" }, { "pos": "NNC", "text": "중심이" }, { "pos": "VV", "text": "되어" }, { "pos": "NNC", "text": "세운" }, { "pos": "NNU", "text": "5년제" }, { "pos": "NNC", "text": "학교인데" }, { "pos": "SCM", "text": "," }, { "pos": "NPR", "text": "김일성의" }, { "pos": "NNC", "text": "외할아버지인" }, { "pos": "NPR", "text": "강돈욱도" }, { "pos": "NNC", "text": "설립자" }, { "pos": "NNC", "text": "가운데" }, { "pos": "NNU", "text": "한" }, { "pos": "NNC", "text": "사람이며" }, { "pos": "SCM", "text": "," }, { "pos": "NNC", "text": "한때" }, { "pos": "NNC", "text": "창덕학교의" }, { "pos": "NNC", "text": "교감과" }, { "pos": "NNC", "text": "교장을" }, { "pos": "VV", "text": "맡기도" }, { "pos": "VX", "text": "했다" }, { "pos": "SFN", "text": "." }, { "pos": "NNC", "text": "아버지" }, { "pos": "NPR", "text": "김형직의" }, { "pos": "NNC", "text": "권고로" }, { "pos": "NNC", "text": "중국말" }, { "pos": "NNC", "text": "을" }, { "pos": "VV", "text": "배우고" }, { "pos": "NNC", "text": "중국인소학교에서" }, { "pos": "NNC", "text": "중어공부를" }, { "pos": "VV", "text": "하여" }, { "pos": "NNC", "text": "중어를" }, { "pos": "VJ", "text": "자유롭게" }, { "pos": "ADV", "text": "구사할수" }, { "pos": "VJ", "text": "있었다" }, { "pos": "SFN", "text": "." }, { "pos": "SLQ", "text": "[" }, { "pos": "NNU", "text": "11" }, { "pos": "SRQ", "text": "]" }, { "pos": "NNC", "text": "창덕학교로의" }, { "pos": "NNC", "text": "진학과정에" }, { "pos": "VV", "text": "대하여" }, { "pos": "NNC", "text": "략력에서는" }, { "pos": "NNC", "text": "아버지" }, { "pos": "NPR", "text": "김형직이" }, { "pos": "SLQ", "text": "'" }, { "pos": "NNC", "text": "혁명을" }, { "pos": "VV", "text": "하자면" }, { "pos": "NPN", "text": "자기" }, { "pos": "NNC", "text": "나라를" }, { "pos": "VV", "text": "알아야" }, { "pos": "VX", "text": "한다고" }, { "pos": "VV", "text": "말한" }, { "pos": "NNC", "text": "권고를" }, { "pos": "VV", "text": "받고" }, { "pos": "NNU", "text": "1923년" }, { "pos": "NNU", "text": "3월" }, { "pos": "NPR", "text": "중국" }, { "pos": "NNC", "text": "팔도구로부터" }, { "pos": "NNC", "text": "만경대까지배움의" }, { "pos": "NPR", "text": "천리길을" }, { "pos": "VV", "text": "걸어" }, { "pos": "NNC", "text": "통학하며" }, { "pos": "NNX", "text": "외" }, { "pos": "NNC", "text": "가집이" }, { "pos": "VJ", "text": "있는" }, { "pos": "NNC", "text": "칠골" }, { "pos": "NNC", "text": "창덕학교에서" }, { "pos": "NNC", "text": "공부하였다는" }, { "pos": "NNX", "text": "것이다" }, { "pos": "SSY", "text": "." } ], "requestId": "b2fdf104-7ef4-44b4-8dc1-185a89118d73", "timers": { "rblJe": 589, "rliJe": 2 } } python-0.7.4/tests/mock-data/response/xxx-null-morphology_complete.status 0000664 0000000 0000000 00000000003 12636317025 0027032 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/xxx-null-sentiment.json 0000664 0000000 0000000 00000000242 12636317025 0024404 0 ustar 00root root 0000000 0000000 { "code": "unsupportedLanguage", "message": "Korean is not supported by Rosette Sentiment Analyzer", "requestId": "77a97067-d430-4db8-accc-31311d2c2641" } python-0.7.4/tests/mock-data/response/xxx-null-sentiment.status 0000664 0000000 0000000 00000000003 12636317025 0024751 0 ustar 00root root 0000000 0000000 415 python-0.7.4/tests/mock-data/response/xxx-sentence-categories.json 0000664 0000000 0000000 00000000234 12636317025 0025356 0 ustar 00root root 0000000 0000000 { "code": "unsupportedLanguage", "message": "Russian is not supported by Rosette Categorizer", "requestId": "8832c51d-7619-416c-9b75-88f38b5d7d32" } python-0.7.4/tests/mock-data/response/xxx-sentence-categories.status 0000664 0000000 0000000 00000000003 12636317025 0025722 0 ustar 00root root 0000000 0000000 415 python-0.7.4/tests/mock-data/response/xxx-sentence-entities.json 0000664 0000000 0000000 00000002316 12636317025 0025060 0 ustar 00root root 0000000 0000000 { "entities": [ { "confidence": 0.01676309108734131, "count": 1, "indocChainId": 0, "mention": "Таллинне", "normalized": "Таллинне", "type": "LOCATION" }, { "confidence": 0.014180123805999756, "count": 1, "indocChainId": 1, "mention": "Ванкувере", "normalized": "Ванкувере", "type": "LOCATION" }, { "confidence": 0.020513594150543213, "count": 1, "indocChainId": 2, "mention": "Олег Овсянников", "normalized": "Олег Овсянников", "type": "PERSON" }, { "confidence": 0.0016747713088989258, "count": 1, "indocChainId": 3, "mention": "Сборная России", "normalized": "Сборная России", "type": "ORGANIZATION" }, { "confidence": 0.01137775182723999, "count": 1, "indocChainId": 4, "mention": "Ванкувер", "normalized": "Ванкувер", "type": "LOCATION" } ], "requestId": "3d554165-486c-4716-aea7-868c316fb883", "timers": { "rblJe": 1, "rexJe": 29, "rliJe": 4 } } python-0.7.4/tests/mock-data/response/xxx-sentence-entities.status 0000664 0000000 0000000 00000000003 12636317025 0025421 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/xxx-sentence-entities_linked.json 0000664 0000000 0000000 00000001664 12636317025 0026413 0 ustar 00root root 0000000 0000000 { "entities": [ { "confidence": 0.037528832925525175, "entityId": "NEW-CLUSTER", "indocChainId": 0, "mention": "Таллинне" }, { "confidence": 0.03045373436092313, "entityId": "NEW-CLUSTER", "indocChainId": 1, "mention": "Ванкувере" }, { "confidence": 0.5122193352131024, "entityId": "NEW-CLUSTER", "indocChainId": 2, "mention": "Олег Овсянников" }, { "confidence": 0.1287762785119855, "entityId": "NEW-CLUSTER", "indocChainId": 3, "mention": "Сборная России" }, { "confidence": 0.03045373436092313, "entityId": "NEW-CLUSTER", "indocChainId": 4, "mention": "Ванкувер" } ], "requestId": "67c83ddd-463b-481b-b37a-266b034dfffc", "timers": { "rblJe": 1, "res": 501, "rexJe": 5, "rliJe": 4 } } python-0.7.4/tests/mock-data/response/xxx-sentence-entities_linked.status 0000664 0000000 0000000 00000000003 12636317025 0026747 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/xxx-sentence-language.json 0000664 0000000 0000000 00000001016 12636317025 0025013 0 ustar 00root root 0000000 0000000 { "languageDetections": [ { "confidence": 0.04609485438238292, "language": "rus" }, { "confidence": 0.016306702275895923, "language": "ukr" }, { "confidence": 0.013060697545012045, "language": "bul" }, { "confidence": 0.012652033408849128, "language": "srp" }, { "confidence": 0.009943176391118635, "language": "mkd" } ], "requestId": "7e7c95a1-0c0a-4558-b520-307e5691e9bd", "timers": { "rliJe": 4 } } python-0.7.4/tests/mock-data/response/xxx-sentence-language.status 0000664 0000000 0000000 00000000003 12636317025 0025360 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/xxx-sentence-morphology_complete.json 0000664 0000000 0000000 00000015503 12636317025 0027325 0 ustar 00root root 0000000 0000000 { "compounds": [], "hanReadings": [], "lemmas": [ { "lemma": "практически", "text": "Практически" }, { "lemma": "сразу", "text": "сразу" }, { "lemma": "после", "text": "после" }, { "lemma": "соревнование", "text": "соревнований" }, { "lemma": "в", "text": "в" }, { "lemma": "Таллинне", "text": "Таллинне" }, { "lemma": "стартовать", "text": "стартуют" }, { "lemma": "олимпийский", "text": "Олимпийские" }, { "lemma": "игра", "text": "игры" }, { "lemma": "в", "text": "в" }, { "lemma": "Ванкувер", "text": "Ванкувере" }, { "lemma": ".", "text": "." }, { "lemma": "однако", "text": "Однако" }, { "lemma": "Олег", "text": "Олег" }, { "lemma": "Овсянников", "text": "Овсянников" }, { "lemma": "уточнять", "text": "уточнил" }, { "lemma": ",", "text": "," }, { "lemma": "что", "text": "что" }, { "lemma": "время", "text": "времени" }, { "lemma": "и", "text": "и" }, { "lemma": "на", "text": "на" }, { "lemma": "отдых", "text": "отдых" }, { "lemma": ",", "text": "," }, { "lemma": "и", "text": "и" }, { "lemma": "на", "text": "на" }, { "lemma": "акклиматизация", "text": "акклиматизацию" }, { "lemma": "быть", "text": "будет" }, { "lemma": "предостаточно", "text": "предостаточно" }, { "lemma": ".", "text": "." }, { "lemma": "\"", "text": "\"" }, { "lemma": "сборная", "text": "Сборная" }, { "lemma": "Россия", "text": "России" }, { "lemma": "быть", "text": "будет" }, { "lemma": "вылетать", "text": "вылетать" }, { "lemma": "несколько", "text": "несколькими" }, { "lemma": "этап", "text": "этапами" }, { "lemma": ".", "text": "." }, { "lemma": "с", "text": "С" }, { "lemma": "31", "text": "31" }, { "lemma": "январь", "text": "января" }, { "lemma": "начинаться", "text": "начнутся" }, { "lemma": "первый", "text": "первые" }, { "lemma": "вылет", "text": "вылеты" }, { "lemma": "в", "text": "в" }, { "lemma": "Ванкувер", "text": "Ванкувер" }, { "lemma": "\"", "text": "\"" }, { "lemma": ",", "text": "," }, { "lemma": "-", "text": "-" }, { "lemma": "сообщать", "text": "сообщил" }, { "lemma": "он", "text": "он" }, { "lemma": ".", "text": "." } ], "posTags": [ { "pos": "ADV", "text": "Практически" }, { "pos": "ADV", "text": "сразу" }, { "pos": "PREP", "text": "после" }, { "pos": "NOUN", "text": "соревнований" }, { "pos": "PREP", "text": "в" }, { "pos": "PROP", "text": "Таллинне" }, { "pos": "VFIN", "text": "стартуют" }, { "pos": "ADJ", "text": "Олимпийские" }, { "pos": "NOUN", "text": "игры" }, { "pos": "PREP", "text": "в" }, { "pos": "PROP", "text": "Ванкувере" }, { "pos": "SENT", "text": "." }, { "pos": "CONJ", "text": "Однако" }, { "pos": "PROP", "text": "Олег" }, { "pos": "PROP", "text": "Овсянников" }, { "pos": "VFIN", "text": "уточнил" }, { "pos": "CM", "text": "," }, { "pos": "CONJ", "text": "что" }, { "pos": "NOUN", "text": "времени" }, { "pos": "CONJ", "text": "и" }, { "pos": "PREP", "text": "на" }, { "pos": "NOUN", "text": "отдых" }, { "pos": "CM", "text": "," }, { "pos": "CONJ", "text": "и" }, { "pos": "PREP", "text": "на" }, { "pos": "NOUN", "text": "акклиматизацию" }, { "pos": "VAUX", "text": "будет" }, { "pos": "ADV", "text": "предостаточно" }, { "pos": "SENT", "text": "." }, { "pos": "PUNCT", "text": "\"" }, { "pos": "NOUN", "text": "Сборная" }, { "pos": "PROP", "text": "России" }, { "pos": "VAUX", "text": "будет" }, { "pos": "VINF", "text": "вылетать" }, { "pos": "DET", "text": "несколькими" }, { "pos": "NOUN", "text": "этапами" }, { "pos": "SENT", "text": "." }, { "pos": "PREP", "text": "С" }, { "pos": "DIG", "text": "31" }, { "pos": "NOUN", "text": "января" }, { "pos": "VFIN", "text": "начнутся" }, { "pos": "ADJ", "text": "первые" }, { "pos": "NOUN", "text": "вылеты" }, { "pos": "PREP", "text": "в" }, { "pos": "PROP", "text": "Ванкувер" }, { "pos": "PUNCT", "text": "\"" }, { "pos": "CM", "text": "," }, { "pos": "PUNCT", "text": "-" }, { "pos": "VFIN", "text": "сообщил" }, { "pos": "PERS", "text": "он" }, { "pos": "SENT", "text": "." } ], "requestId": "3b2dcbb1-6eff-4e74-968b-653c4b9a6289", "timers": { "rblJe": 79, "rliJe": 5 } } python-0.7.4/tests/mock-data/response/xxx-sentence-morphology_complete.status 0000664 0000000 0000000 00000000003 12636317025 0027664 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/xxx-sentence-sentiment.json 0000664 0000000 0000000 00000000243 12636317025 0025237 0 ustar 00root root 0000000 0000000 { "code": "unsupportedLanguage", "message": "Russian is not supported by Rosette Sentiment Analyzer", "requestId": "4bf73901-20cc-4ff7-a361-8e4ecd2e37bd" } python-0.7.4/tests/mock-data/response/xxx-sentence-sentiment.status 0000664 0000000 0000000 00000000003 12636317025 0025603 0 ustar 00root root 0000000 0000000 415 python-0.7.4/tests/mock-data/response/zho-doc-categories.json 0000664 0000000 0000000 00000000234 12636317025 0024270 0 ustar 00root root 0000000 0000000 { "code": "unsupportedLanguage", "message": "Chinese is not supported by Rosette Categorizer", "requestId": "be9e6d61-9b73-4c86-b0be-e94a76f28a8e" } python-0.7.4/tests/mock-data/response/zho-doc-categories.status 0000664 0000000 0000000 00000000003 12636317025 0024634 0 ustar 00root root 0000000 0000000 415 python-0.7.4/tests/mock-data/response/zho-doc-entities.json 0000664 0000000 0000000 00000004501 12636317025 0023770 0 ustar 00root root 0000000 0000000 { "entities": [ { "confidence": 0.029630446434020997, "count": 5, "indocChainId": 1, "mention": "联合国", "normalized": "联合国", "type": "ORGANIZATION" }, { "confidence": 0.016980469226837158, "count": 5, "indocChainId": 6, "mention": "海地", "normalized": "海地", "type": "LOCATION" }, { "confidence": 0.032270610332489014, "count": 2, "indocChainId": 7, "mention": "联大", "normalized": "联大", "type": "ORGANIZATION" }, { "confidence": 0.011038780212402344, "count": 1, "indocChainId": 0, "mention": "新华网", "normalized": "新华网", "type": "ORGANIZATION" }, { "confidence": 0.022758543491363525, "count": 1, "indocChainId": 2, "mention": "记者", "normalized": "记者", "type": "TITLE" }, { "confidence": 0.00045305490493774414, "count": 1, "indocChainId": 3, "mention": "白洁 王湘江", "normalized": "白洁 王湘江", "type": "PERSON" }, { "confidence": 0.08852261304855347, "count": 1, "indocChainId": 8, "mention": "纽约", "normalized": "纽约", "type": "LOCATION" }, { "confidence": 0.005361199378967285, "count": 1, "indocChainId": 12, "mention": "主席", "normalized": "主席", "type": "TITLE" }, { "confidence": 0.015633702278137207, "count": 1, "indocChainId": 13, "mention": "哈萨克斯坦", "normalized": "哈萨克斯坦", "type": "LOCATION" }, { "confidence": 0.010837018489837646, "count": 1, "indocChainId": 15, "mention": "艾季莫娃", "normalized": "艾季莫娃", "type": "PERSON" }, { "confidence": 1.0, "count": 1, "indocChainId": 19, "mention": "http://news.xinhuanet.com/world/2010-01/23/content_12860329.htm", "normalized": "http://news.xinhuanet.com/world/2010-01/23/content_12860329.htm", "type": "IDENTIFIER:URL" } ], "requestId": "96870360-8add-4767-a808-aaccea4fb39a", "timers": { "rblJe": 40, "rexJe": 80, "rliJe": 10 } } python-0.7.4/tests/mock-data/response/zho-doc-entities.status 0000664 0000000 0000000 00000000003 12636317025 0024333 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/zho-doc-entities_linked.json 0000664 0000000 0000000 00000002373 12636317025 0025323 0 ustar 00root root 0000000 0000000 { "entities": [ { "confidence": 0.4725379856202875, "entityId": "Q11081577", "indocChainId": 0, "mention": "新华网" }, { "confidence": 0.7702512174279228, "entityId": "Q1065", "indocChainId": 1, "mention": "联合国" }, { "confidence": 1.0, "entityId": "NEW-CLUSTER", "indocChainId": 3, "mention": "白洁 王湘江" }, { "confidence": 0.7228798023445596, "entityId": "Q790", "indocChainId": 6, "mention": "海地" }, { "confidence": 0.6385152954821051, "entityId": "Q47423", "indocChainId": 7, "mention": "联大" }, { "confidence": 0.8059447327040058, "entityId": "Q60", "indocChainId": 8, "mention": "纽约" }, { "confidence": 0.7124248045099933, "entityId": "Q232", "indocChainId": 13, "mention": "哈萨克斯坦" }, { "confidence": 0.5555564094259866, "entityId": "Q4059015", "indocChainId": 15, "mention": "艾季莫娃" } ], "requestId": "5f2d0667-5e70-4378-881b-2a8f408e9a8c", "timers": { "rblJe": 18, "res": 3278, "rexJe": 11, "rliJe": 10 } } python-0.7.4/tests/mock-data/response/zho-doc-entities_linked.status 0000664 0000000 0000000 00000000003 12636317025 0025661 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/zho-doc-language.json 0000664 0000000 0000000 00000001022 12636317025 0023722 0 ustar 00root root 0000000 0000000 { "languageDetections": [ { "confidence": 0.04065858941640477, "language": "zho" }, { "confidence": 0.01644532195896431, "language": "zho" }, { "confidence": 0.004008360564392355, "language": "jpn" }, { "confidence": 0.00025639584075720645, "language": "eng" }, { "confidence": 0.00011789117134142213, "language": "ita" } ], "requestId": "936affd3-4f51-47f1-a2ff-4b7b9b89847d", "timers": { "rliJe": 10 } } python-0.7.4/tests/mock-data/response/zho-doc-language.status 0000664 0000000 0000000 00000000003 12636317025 0024272 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/zho-doc-morphology_complete.json 0000664 0000000 0000000 00000074424 12636317025 0026246 0 ustar 00root root 0000000 0000000 { "compounds": [], "hanReadings": [ { "hanReadings": [ "wang3" ], "text": "网" }, { "hanReadings": [ "Lian2-he2-guo2" ], "text": "联合国" }, { "hanReadings": [ "yue4" ], "text": "月" }, { "hanReadings": [ "ji4-zhe3" ], "text": "记者" }, { "hanReadings": [ "bai2-jie2" ], "text": "白洁" }, { "hanReadings": [ "wang2" ], "text": "王" }, { "hanReadings": [ "Xiang1-Jiang1" ], "text": "湘江" }, { "hanReadings": [ "di4" ], "text": "第" }, { "hanReadings": [ "jie4" ], "text": "届" }, { "hanReadings": [ "Lian2-he2-guo2" ], "text": "联合国" }, { "hanReadings": [ "da4-hui4" ], "text": "大会" }, { "hanReadings": [ "ri4" ], "text": "日" }, { "hanReadings": [ "yi1-zhi4" ], "text": "一致" }, { "hanReadings": [ "tong1-guo4" ], "text": "通过" }, { "hanReadings": [ "jue2-yi4" ], "text": "决议" }, { "hanReadings": [ "hu1-yu4" ], "text": "呼吁" }, { "hanReadings": [ "ge0" ], "text": "个" }, { "hanReadings": [ "cheng2-yuan2-guo2" ], "text": "成员国" }, { "hanReadings": [ "jin3-kuai4" ], "text": "尽快" }, { "hanReadings": [ "xiang3-ying4" ], "text": "响应" }, { "hanReadings": [ "Lian2-he2-guo2" ], "text": "联合国" }, { "hanReadings": [ "fa1-qi3" ], "text": "发起" }, { "hanReadings": [ "de0" ], "text": "的" }, { "hanReadings": [ "Hai3-di4" ], "text": "海地" }, { "hanReadings": [ "jiu4-yuan2" ], "text": "救援" }, { "hanReadings": [ "jin3-ji2" ], "text": "紧急" }, { "hanReadings": [ "mu4-juan1" ], "text": "募捐" }, { "hanReadings": [ "hu1-yu4" ], "text": "呼吁" }, { "hanReadings": [ "qiang2-diao4" ], "text": "强调" }, { "hanReadings": [ "ge4-guo2" ], "text": "各国" }, { "hanReadings": [ "zhu3-dao3" ], "text": "主导" }, { "hanReadings": [ "de0" ], "text": "的" }, { "hanReadings": [ "jiu4-zai1" ], "text": "救灾" }, { "hanReadings": [ "gong1-zuo4" ], "text": "工作" }, { "hanReadings": [ "yu3-yi3" ], "text": "予以" }, { "hanReadings": [ "zhi1-chi2" ], "text": "支持" }, { "hanReadings": [ "Lian2-Da4" ], "text": "联大" }, { "hanReadings": [ "dang1-tian1" ], "text": "当天" }, { "hanReadings": [ "zai4" ], "text": "在" }, { "hanReadings": [ "Niu3-yue1" ], "text": "纽约" }, { "hanReadings": [ "Lian2-he2-guo2" ], "text": "联合国" }, { "hanReadings": [ "zong3-bu4" ], "text": "总部" }, { "hanReadings": [ "jiu4" ], "text": "就" }, { "hanReadings": [ "Hai3-di4" ], "text": "海地" }, { "hanReadings": [ "di4-zhen4" ], "text": "地震" }, { "hanReadings": [ "ju3-xing2" ], "text": "举行" }, { "hanReadings": [ "quan2-ti3" ], "text": "全体" }, { "hanReadings": [ "hui4-yi4" ], "text": "会议" }, { "hanReadings": [ "di4" ], "text": "第" }, { "hanReadings": [ "jie4" ], "text": "届" }, { "hanReadings": [ "Lian2-Da4" ], "text": "联大" }, { "hanReadings": [ "dai4-li3" ], "text": "代理" }, { "hanReadings": [ "zhu3-xi2" ], "text": "主席" }, { "hanReadings": [ "chang2-zhu4" ], "text": "常驻" }, { "hanReadings": [ "Lian2-he2-guo2" ], "text": "联合国" }, { "hanReadings": [ "dai4-biao3" ], "text": "代表" }, { "hanReadings": [ "ai4" ], "text": "艾" }, { "hanReadings": [ "ji4" ], "text": "季" }, { "hanReadings": [ "zai4" ], "text": "在" }, { "hanReadings": [ "zhi4-ci2" ], "text": "致辞" }, { "hanReadings": [ "zhong1" ], "text": "中" }, { "hanReadings": [ "shui4" ], "text": "说" }, { "hanReadings": [ "Hai3-di4" ], "text": "海地" }, { "hanReadings": [ "zai1" ], "text": "灾" }, { "hanReadings": [ "hou4" ], "text": "后" }, { "hanReadings": [ "de0" ], "text": "的" }, { "hanReadings": [ "chang2-qi1" ], "text": "长期" }, { "hanReadings": [ "chong2-jian4" ], "text": "重建" }, { "hanReadings": [ "he1" ], "text": "和" }, { "hanReadings": [ "fa1-zhan3" ], "text": "发展" }, { "hanReadings": [ "gong1-zuo4" ], "text": "工作" }, { "hanReadings": [ "xu1-yao4" ], "text": "需要" }, { "hanReadings": [ "guo2-ji4" ], "text": "国际" }, { "hanReadings": [ "she4-hui4" ], "text": "社会" }, { "hanReadings": [ "zai4" ], "text": "在" }, { "hanReadings": [ "wei4-lai2" ], "text": "未来" }, { "hanReadings": [ "ji1" ], "text": "几" }, { "hanReadings": [ "ge0" ], "text": "个" }, { "hanReadings": [ "yue4" ], "text": "月" }, { "hanReadings": [ "shen4-zhi4" ], "text": "甚至" }, { "hanReadings": [ "ji1" ], "text": "几" }, { "hanReadings": [ "nian2" ], "text": "年" }, { "hanReadings": [ "nei4" ], "text": "内" }, { "hanReadings": [ "chang2-qi1" ], "text": "长期" }, { "hanReadings": [ "guan1-zhu4" ], "text": "关注" }, { "hanReadings": [ "ta1" ], "text": "她" }, { "hanReadings": [ "shui4" ], "text": "说" }, { "hanReadings": [ "hai3-di3" ], "text": "海底" }, { "hanReadings": [ "di4-zhen4" ], "text": "地震" }, { "hanReadings": [ "hou4" ], "text": "后" }, { "hanReadings": [ "guo2-ji4" ], "text": "国际" }, { "hanReadings": [ "she4-hui4" ], "text": "社会" }, { "hanReadings": [ "li4-ji2" ], "text": "立即" }, { "hanReadings": [ "zuo4-chu1" ], "text": "做出" }, { "hanReadings": [ "fan3-ying4" ], "text": "反应" }, { "hanReadings": [ "dui4" ], "text": "对" }, { "hanReadings": [ "Hai3-di4" ], "text": "海地" }, { "hanReadings": [ "ren2-min2" ], "text": "人民" }, { "hanReadings": [ "he1" ], "text": "和" }, { "hanReadings": [ "zheng4-fu3" ], "text": "政府" }, { "hanReadings": [ "yu3-yi3" ], "text": "予以" }, { "hanReadings": [ "sheng1-yuan2" ], "text": "声援" }, { "hanReadings": [ "he1" ], "text": "和" }, { "hanReadings": [ "zhi1-chi2" ], "text": "支持" }, { "hanReadings": [ "yi3" ], "text": "已" }, { "hanReadings": [ "jiao1-fu4" ], "text": "交付" }, { "hanReadings": [ "de0" ], "text": "的" }, { "hanReadings": [ "ren2-dao4-zhu3-yi4" ], "text": "人道主义" }, { "hanReadings": [ "yuan2-zhu4" ], "text": "援助" }, { "hanReadings": [ "wu4-zi1" ], "text": "物资" }, { "hanReadings": [ "man3-zu2" ], "text": "满足" }, { "hanReadings": [ "le0" ], "text": "了" }, { "hanReadings": [ "Hai3-di4" ], "text": "海地" }, { "hanReadings": [ "ren2-min2" ], "text": "人民" }, { "hanReadings": [ "de0" ], "text": "的" }, { "hanReadings": [ "yi1-xie1" ], "text": "一些" }, { "hanReadings": [ "po4-qie4" ], "text": "迫切" }, { "hanReadings": [ "xu1-qiu2" ], "text": "需求" }, { "hanReadings": [ "dan4" ], "text": "但" }, { "hanReadings": [ "hai2-you3" ], "text": "还有" }, { "hanReadings": [ "xu3-duo1" ], "text": "许多" }, { "hanReadings": [ "gong1-zuo4" ], "text": "工作" }, { "hanReadings": [ "yao1" ], "text": "要" }, { "hanReadings": [ "zuo4" ], "text": "做" } ], "lemmas": [ { "lemma": "新华", "text": "新华" }, { "lemma": "网", "text": "网" }, { "lemma": "联合国", "text": "联合国" }, { "lemma": "1", "text": "１" }, { "lemma": "月", "text": "月" }, { "lemma": "22", "text": "２２" }, { "lemma": "日电", "text": "日电" }, { "lemma": "（", "text": "（" }, { "lemma": "记者", "text": "记者" }, { "lemma": "白洁", "text": "白洁" }, { "lemma": "王", "text": "王" }, { "lemma": "湘江", "text": "湘江" }, { "lemma": "）", "text": "）" }, { "lemma": "第", "text": "第" }, { "lemma": "64", "text": "６４" }, { "lemma": "届", "text": "届" }, { "lemma": "联合国", "text": "联合国" }, { "lemma": "大会", "text": "大会" }, { "lemma": "22", "text": "２２" }, { "lemma": "日", "text": "日" }, { "lemma": "一致", "text": "一致" }, { "lemma": "通过", "text": "通过" }, { "lemma": "决议", "text": "决议" }, { "lemma": "，", "text": "，" }, { "lemma": "呼吁", "text": "呼吁" }, { "lemma": "192", "text": "１９２" }, { "lemma": "个", "text": "个" }, { "lemma": "成员国", "text": "成员国" }, { "lemma": "尽快", "text": "尽快" }, { "lemma": "响应", "text": "响应" }, { "lemma": "联合国", "text": "联合国" }, { "lemma": "发起", "text": "发起" }, { "lemma": "的", "text": "的" }, { "lemma": "海地", "text": "海地" }, { "lemma": "救援", "text": "救援" }, { "lemma": "紧急", "text": "紧急" }, { "lemma": "募捐", "text": "募捐" }, { "lemma": "呼吁", "text": "呼吁" }, { "lemma": "，", "text": "，" }, { "lemma": "强调", "text": "强调" }, { "lemma": "各国", "text": "各国" }, { "lemma": "应对联合国", "text": "应对联合国" }, { "lemma": "主导", "text": "主导" }, { "lemma": "的", "text": "的" }, { "lemma": "救灾", "text": "救灾" }, { "lemma": "工作", "text": "工作" }, { "lemma": "予以", "text": "予以" }, { "lemma": "支持", "text": "支持" }, { "lemma": "。", "text": "。" }, { "lemma": "联大", "text": "联大" }, { "lemma": "当天", "text": "当天" }, { "lemma": "在", "text": "在" }, { "lemma": "纽约", "text": "纽约" }, { "lemma": "联合国", "text": "联合国" }, { "lemma": "总部", "text": "总部" }, { "lemma": "就", "text": "就" }, { "lemma": "海地", "text": "海地" }, { "lemma": "地震", "text": "地震" }, { "lemma": "举行", "text": "举行" }, { "lemma": "全体", "text": "全体" }, { "lemma": "会议", "text": "会议" }, { "lemma": "。", "text": "。" }, { "lemma": "第", "text": "第" }, { "lemma": "64", "text": "６４" }, { "lemma": "届", "text": "届" }, { "lemma": "联大", "text": "联大" }, { "lemma": "代理", "text": "代理" }, { "lemma": "主席", "text": "主席" }, { "lemma": "、", "text": "、" }, { "lemma": "哈萨克斯坦", "text": "哈萨克斯坦" }, { "lemma": "常驻", "text": "常驻" }, { "lemma": "联合国", "text": "联合国" }, { "lemma": "代表", "text": "代表" }, { "lemma": "艾", "text": "艾" }, { "lemma": "季", "text": "季" }, { "lemma": "莫娃", "text": "莫娃" }, { "lemma": "在", "text": "在" }, { "lemma": "致辞", "text": "致辞" }, { "lemma": "中", "text": "中" }, { "lemma": "说", "text": "说" }, { "lemma": "，", "text": "，" }, { "lemma": "海地", "text": "海地" }, { "lemma": "灾", "text": "灾" }, { "lemma": "后", "text": "后" }, { "lemma": "的", "text": "的" }, { "lemma": "长期", "text": "长期" }, { "lemma": "重建", "text": "重建" }, { "lemma": "和", "text": "和" }, { "lemma": "发展", "text": "发展" }, { "lemma": "工作", "text": "工作" }, { "lemma": "需要", "text": "需要" }, { "lemma": "国际", "text": "国际" }, { "lemma": "社会", "text": "社会" }, { "lemma": "在", "text": "在" }, { "lemma": "未来", "text": "未来" }, { "lemma": "几", "text": "几" }, { "lemma": "个", "text": "个" }, { "lemma": "月", "text": "月" }, { "lemma": "甚至", "text": "甚至" }, { "lemma": "几", "text": "几" }, { "lemma": "年", "text": "年" }, { "lemma": "内", "text": "内" }, { "lemma": "长期", "text": "长期" }, { "lemma": "关注", "text": "关注" }, { "lemma": "。", "text": "。" }, { "lemma": "她", "text": "她" }, { "lemma": "说", "text": "说" }, { "lemma": "，", "text": "，" }, { "lemma": "海底", "text": "海底" }, { "lemma": "地震", "text": "地震" }, { "lemma": "后", "text": "后" }, { "lemma": "，", "text": "，" }, { "lemma": "国际", "text": "国际" }, { "lemma": "社会", "text": "社会" }, { "lemma": "立即", "text": "立即" }, { "lemma": "做出", "text": "做出" }, { "lemma": "反应", "text": "反应" }, { "lemma": "，", "text": "，" }, { "lemma": "对", "text": "对" }, { "lemma": "海地", "text": "海地" }, { "lemma": "人民", "text": "人民" }, { "lemma": "和", "text": "和" }, { "lemma": "政府", "text": "政府" }, { "lemma": "予以", "text": "予以" }, { "lemma": "声援", "text": "声援" }, { "lemma": "和", "text": "和" }, { "lemma": "支持", "text": "支持" }, { "lemma": "。", "text": "。" }, { "lemma": "已", "text": "已" }, { "lemma": "交付", "text": "交付" }, { "lemma": "的", "text": "的" }, { "lemma": "人道主义", "text": "人道主义" }, { "lemma": "援助", "text": "援助" }, { "lemma": "物资", "text": "物资" }, { "lemma": "满足", "text": "满足" }, { "lemma": "了", "text": "了" }, { "lemma": "海地", "text": "海地" }, { "lemma": "人民", "text": "人民" }, { "lemma": "的", "text": "的" }, { "lemma": "一些", "text": "一些" }, { "lemma": "迫切", "text": "迫切" }, { "lemma": "需求", "text": "需求" }, { "lemma": "，", "text": "，" }, { "lemma": "但", "text": "但" }, { "lemma": "还有", "text": "还有" }, { "lemma": "许多", "text": "许多" }, { "lemma": "工作", "text": "工作" }, { "lemma": "要", "text": "要" }, { "lemma": "做", "text": "做" }, { "lemma": "。", "text": "。" }, { "lemma": "http", "text": "http" }, { "lemma": ":", "text": ":" }, { "lemma": "/", "text": "/" }, { "lemma": "/", "text": "/" }, { "lemma": "news.xinhuanet.com", "text": "news.xinhuanet.com" }, { "lemma": "/", "text": "/" }, { "lemma": "world", "text": "world" }, { "lemma": "/", "text": "/" }, { "lemma": "2010", "text": "2010" }, { "lemma": "-", "text": "-" }, { "lemma": "01", "text": "01" }, { "lemma": "/", "text": "/" }, { "lemma": "23", "text": "23" }, { "lemma": "/", "text": "/" }, { "lemma": "content", "text": "content" }, { "lemma": "_", "text": "_" }, { "lemma": "12860329", "text": "12860329" }, { "lemma": ".", "text": "." }, { "lemma": "htm", "text": "htm" }, { "lemma": "2010.01.24", "text": "2010.01.24" } ], "posTags": [ { "pos": "GUESS", "text": "新华" }, { "pos": "NC", "text": "网" }, { "pos": "NP", "text": "联合国" }, { "pos": "GUESS", "text": "１" }, { "pos": "NC", "text": "月" }, { "pos": "GUESS", "text": "２２" }, { "pos": "GUESS", "text": "日电" }, { "pos": "GUESS", "text": "（" }, { "pos": "NC", "text": "记者" }, { "pos": "A", "text": "白洁" }, { "pos": "NC", "text": "王" }, { "pos": "NP", "text": "湘江" }, { "pos": "GUESS", "text": "）" }, { "pos": "W", "text": "第" }, { "pos": "GUESS", "text": "６４" }, { "pos": "NM", "text": "届" }, { "pos": "NP", "text": "联合国" }, { "pos": "NC", "text": "大会" }, { "pos": "GUESS", "text": "２２" }, { "pos": "NA", "text": "日" }, { "pos": "A", "text": "一致" }, { "pos": "PR", "text": "通过" }, { "pos": "NC", "text": "决议" }, { "pos": "GUESS", "text": "，" }, { "pos": "V", "text": "呼吁" }, { "pos": "GUESS", "text": "１９２" }, { "pos": "NM", "text": "个" }, { "pos": "NC", "text": "成员国" }, { "pos": "U", "text": "尽快" }, { "pos": "V", "text": "响应" }, { "pos": "NP", "text": "联合国" }, { "pos": "V", "text": "发起" }, { "pos": "OC", "text": "的" }, { "pos": "NP", "text": "海地" }, { "pos": "V", "text": "救援" }, { "pos": "A", "text": "紧急" }, { "pos": "NC", "text": "募捐" }, { "pos": "V", "text": "呼吁" }, { "pos": "GUESS", "text": "，" }, { "pos": "NC", "text": "强调" }, { "pos": "NC", "text": "各国" }, { "pos": "GUESS", "text": "应对联合国" }, { "pos": "A", "text": "主导" }, { "pos": "OC", "text": "的" }, { "pos": "V", "text": "救灾" }, { "pos": "NC", "text": "工作" }, { "pos": "V", "text": "予以" }, { "pos": "NC", "text": "支持" }, { "pos": "GUESS", "text": "。" }, { "pos": "NC", "text": "联大" }, { "pos": "NC", "text": "当天" }, { "pos": "D", "text": "在" }, { "pos": "NP", "text": "纽约" }, { "pos": "NP", "text": "联合国" }, { "pos": "NP", "text": "总部" }, { "pos": "D", "text": "就" }, { "pos": "NP", "text": "海地" }, { "pos": "NC", "text": "地震" }, { "pos": "V", "text": "举行" }, { "pos": "A", "text": "全体" }, { "pos": "NC", "text": "会议" }, { "pos": "GUESS", "text": "。" }, { "pos": "W", "text": "第" }, { "pos": "GUESS", "text": "６４" }, { "pos": "NM", "text": "届" }, { "pos": "NC", "text": "联大" }, { "pos": "A", "text": "代理" }, { "pos": "NC", "text": "主席" }, { "pos": "GUESS", "text": "、" }, { "pos": "GUESS", "text": "哈萨克斯坦" }, { "pos": "A", "text": "常驻" }, { "pos": "NP", "text": "联合国" }, { "pos": "NC", "text": "代表" }, { "pos": "NC", "text": "艾" }, { "pos": "NC", "text": "季" }, { "pos": "GUESS", "text": "莫娃" }, { "pos": "D", "text": "在" }, { "pos": "V", "text": "致辞" }, { "pos": "A", "text": "中" }, { "pos": "W", "text": "说" }, { "pos": "GUESS", "text": "，" }, { "pos": "NP", "text": "海地" }, { "pos": "W", "text": "灾" }, { "pos": "NC", "text": "后" }, { "pos": "OC", "text": "的" }, { "pos": "A", "text": "长期" }, { "pos": "V", "text": "重建" }, { "pos": "W", "text": "和" }, { "pos": "V", "text": "发展" }, { "pos": "NC", "text": "工作" }, { "pos": "NC", "text": "需要" }, { "pos": "A", "text": "国际" }, { "pos": "NC", "text": "社会" }, { "pos": "D", "text": "在" }, { "pos": "NC", "text": "未来" }, { "pos": "D", "text": "几" }, { "pos": "NM", "text": "个" }, { "pos": "NC", "text": "月" }, { "pos": "J", "text": "甚至" }, { "pos": "D", "text": "几" }, { "pos": "NC", "text": "年" }, { "pos": "A", "text": "内" }, { "pos": "A", "text": "长期" }, { "pos": "V", "text": "关注" }, { "pos": "GUESS", "text": "。" }, { "pos": "NR", "text": "她" }, { "pos": "W", "text": "说" }, { "pos": "GUESS", "text": "，" }, { "pos": "NC", "text": "海底" }, { "pos": "NC", "text": "地震" }, { "pos": "NC", "text": "后" }, { "pos": "GUESS", "text": "，" }, { "pos": "A", "text": "国际" }, { "pos": "NC", "text": "社会" }, { "pos": "D", "text": "立即" }, { "pos": "V", "text": "做出" }, { "pos": "NC", "text": "反应" }, { "pos": "GUESS", "text": "，" }, { "pos": "A", "text": "对" }, { "pos": "NP", "text": "海地" }, { "pos": "NC", "text": "人民" }, { "pos": "W", "text": "和" }, { "pos": "NP", "text": "政府" }, { "pos": "V", "text": "予以" }, { "pos": "V", "text": "声援" }, { "pos": "W", "text": "和" }, { "pos": "NC", "text": "支持" }, { "pos": "GUESS", "text": "。" }, { "pos": "D", "text": "已" }, { "pos": "V", "text": "交付" }, { "pos": "OC", "text": "的" }, { "pos": "NC", "text": "人道主义" }, { "pos": "NC", "text": "援助" }, { "pos": "NC", "text": "物资" }, { "pos": "A", "text": "满足" }, { "pos": "PL", "text": "了" }, { "pos": "NP", "text": "海地" }, { "pos": "NC", "text": "人民" }, { "pos": "OC", "text": "的" }, { "pos": "NC", "text": "一些" }, { "pos": "A", "text": "迫切" }, { "pos": "NC", "text": "需求" }, { "pos": "GUESS", "text": "，" }, { "pos": "D", "text": "但" }, { "pos": "E", "text": "还有" }, { "pos": "A", "text": "许多" }, { "pos": "NC", "text": "工作" }, { "pos": "W", "text": "要" }, { "pos": "V", "text": "做" }, { "pos": "GUESS", "text": "。" }, { "pos": "GUESS", "text": "http" }, { "pos": "GUESS", "text": ":" }, { "pos": "GUESS", "text": "/" }, { "pos": "GUESS", "text": "/" }, { "pos": "GUESS", "text": "news.xinhuanet.com" }, { "pos": "GUESS", "text": "/" }, { "pos": "GUESS", "text": "world" }, { "pos": "GUESS", "text": "/" }, { "pos": "GUESS", "text": "2010" }, { "pos": "GUESS", "text": "-" }, { "pos": "GUESS", "text": "01" }, { "pos": "GUESS", "text": "/" }, { "pos": "GUESS", "text": "23" }, { "pos": "GUESS", "text": "/" }, { "pos": "GUESS", "text": "content" }, { "pos": "GUESS", "text": "_" }, { "pos": "GUESS", "text": "12860329" }, { "pos": "GUESS", "text": "." }, { "pos": "GUESS", "text": "htm" }, { "pos": "GUESS", "text": "2010.01.24" } ], "requestId": "27a6d1e3-e53f-46c7-83cc-53195208c15e", "timers": { "rblJe": 226, "rliJe": 10 } } python-0.7.4/tests/mock-data/response/zho-doc-morphology_complete.status 0000664 0000000 0000000 00000000003 12636317025 0026576 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/zho-doc-sentiment.json 0000664 0000000 0000000 00000000243 12636317025 0024151 0 ustar 00root root 0000000 0000000 { "code": "unsupportedLanguage", "message": "Chinese is not supported by Rosette Sentiment Analyzer", "requestId": "11740a19-0684-46c9-90fb-a9039d74acef" } python-0.7.4/tests/mock-data/response/zho-doc-sentiment.status 0000664 0000000 0000000 00000000003 12636317025 0024515 0 ustar 00root root 0000000 0000000 415 python-0.7.4/tests/mock-data/response/zho-sentence-categories.json 0000664 0000000 0000000 00000000234 12636317025 0025327 0 ustar 00root root 0000000 0000000 { "code": "unsupportedLanguage", "message": "Chinese is not supported by Rosette Categorizer", "requestId": "a0b2fd85-9542-4b66-a72f-b026b039bb0e" } python-0.7.4/tests/mock-data/response/zho-sentence-categories.status 0000664 0000000 0000000 00000000003 12636317025 0025673 0 ustar 00root root 0000000 0000000 415 python-0.7.4/tests/mock-data/response/zho-sentence-entities.json 0000664 0000000 0000000 00000002105 12636317025 0025025 0 ustar 00root root 0000000 0000000 { "entities": [ { "confidence": 0.011167824268341064, "count": 2, "indocChainId": 1, "mention": "胡锦涛", "normalized": "胡锦涛", "type": "PERSON" }, { "confidence": 0.006879329681396484, "count": 1, "indocChainId": 0, "mention": "莫斯科", "normalized": "莫斯科", "type": "LOCATION" }, { "confidence": 0.017731547355651855, "count": 1, "indocChainId": 2, "mention": "俄罗斯", "normalized": "俄罗斯", "type": "LOCATION" }, { "confidence": 0.0106315016746521, "count": 1, "indocChainId": 3, "mention": "总统", "normalized": "总统", "type": "TITLE" }, { "confidence": 0.0061133503913879395, "count": 1, "indocChainId": 4, "mention": "梅德韦", "normalized": "梅德韦", "type": "PERSON" } ], "requestId": "f3a26bb9-ac45-4a30-8d90-f13fb2f1a736", "timers": { "rblJe": 5, "rexJe": 4, "rliJe": 11 } } python-0.7.4/tests/mock-data/response/zho-sentence-entities.status 0000664 0000000 0000000 00000000003 12636317025 0025372 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/zho-sentence-entities_linked.json 0000664 0000000 0000000 00000001321 12636317025 0026352 0 ustar 00root root 0000000 0000000 { "entities": [ { "confidence": 0.8299469495300511, "entityId": "Q649", "indocChainId": 0, "mention": "莫斯科" }, { "confidence": 0.8135346471109421, "entityId": "Q15029", "indocChainId": 1, "mention": "胡锦涛" }, { "confidence": 0.7906449835784752, "entityId": "Q159", "indocChainId": 2, "mention": "俄罗斯" }, { "confidence": 0.9342092498360748, "entityId": "NEW-CLUSTER", "indocChainId": 4, "mention": "梅德韦" } ], "requestId": "e02eebfa-e05e-49b9-b32d-f8284700e97d", "timers": { "rblJe": 4, "res": 136, "rexJe": 4, "rliJe": 10 } } python-0.7.4/tests/mock-data/response/zho-sentence-entities_linked.status 0000664 0000000 0000000 00000000003 12636317025 0026720 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/zho-sentence-language.json 0000664 0000000 0000000 00000000417 12636317025 0024770 0 ustar 00root root 0000000 0000000 { "languageDetections": [ { "confidence": 1.0, "language": "zho" }, { "confidence": 6.824907560735675e-36, "language": "jpn" } ], "requestId": "fb91e2e8-2141-432d-8039-13f847b0f9a8", "timers": { "rliJe": 1372 } } python-0.7.4/tests/mock-data/response/zho-sentence-language.status 0000664 0000000 0000000 00000000003 12636317025 0025331 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/zho-sentence-morphology_complete.json 0000664 0000000 0000000 00000030355 12636317025 0027300 0 ustar 00root root 0000000 0000000 { "compounds": [], "hanReadings": [ { "hanReadings": [ "yue4" ], "text": "月" }, { "hanReadings": [ "de0" ], "text": "的" }, { "hanReadings": [ "Mo4-si1-ke1" ], "text": "莫斯科" }, { "hanReadings": [ "cao3-mu4" ], "text": "草木" }, { "hanReadings": [ "cong1-long2" ], "text": "葱茏" }, { "hanReadings": [ "jing1-qi2" ], "text": "旌旗" }, { "hanReadings": [ "piao1-yang2" ], "text": "飘扬" }, { "hanReadings": [ "cheng2-xian4" ], "text": "呈现" }, { "hanReadings": [ "chu1" ], "text": "出" }, { "hanReadings": [ "nong2-yu4" ], "text": "浓郁" }, { "hanReadings": [ "de0" ], "text": "的" }, { "hanReadings": [ "jie2-ri4" ], "text": "节日" }, { "hanReadings": [ "qi4-fen1" ], "text": "气氛" }, { "hanReadings": [ "cong1" ], "text": "从" }, { "hanReadings": [ "dang1-di4" ], "text": "当地" }, { "hanReadings": [ "shi2-jian1" ], "text": "时间" }, { "hanReadings": [ "kai1-shi3" ], "text": "开始" }, { "hanReadings": [ "Hu2" ], "text": "胡" }, { "hanReadings": [ "tong2" ], "text": "同" }, { "hanReadings": [ "qi2-ta1" ], "text": "其他" }, { "hanReadings": [ "guo2-jia1" ], "text": "国家" }, { "hanReadings": [ "ling3-dao3-ren2" ], "text": "领导人" }, { "hanReadings": [ "xiang1-ji4" ], "text": "相继" }, { "hanReadings": [ "lai2-dao4" ], "text": "来到" }, { "hanReadings": [ "Ke4-li3-mu3-lin2-Gong1" ], "text": "克里姆林宫" }, { "hanReadings": [ "tong2" ], "text": "同" }, { "hanReadings": [ "zai4" ], "text": "在" }, { "hanReadings": [ "de0" ], "text": "的" }, { "hanReadings": [ "E2-luo2-si1" ], "text": "俄罗斯" }, { "hanReadings": [ "zong3-tong3" ], "text": "总统" }, { "hanReadings": [ "mei2" ], "text": "梅" }, { "hanReadings": [ "de2" ], "text": "德" }, { "hanReadings": [ "wei2" ], "text": "韦" }, { "hanReadings": [ "qin1-qie4" ], "text": "亲切" }, { "hanReadings": [ "wo4-shou3" ], "text": "握手" }, { "hanReadings": [ "sui2-hou4" ], "text": "随后" }, { "hanReadings": [ "Hu2" ], "text": "胡" }, { "hanReadings": [ "tong2" ], "text": "同" }, { "hanReadings": [ "chu1-xi2" ], "text": "出席" }, { "hanReadings": [ "qing4-dian3" ], "text": "庆典" }, { "hanReadings": [ "de0" ], "text": "的" }, { "hanReadings": [ "qi2-ta1" ], "text": "其他" }, { "hanReadings": [ "gui4-bin1" ], "text": "贵宾" }, { "hanReadings": [ "qian2-wang3" ], "text": "前往" }, { "hanReadings": [ "gong1" ], "text": "红" }, { "hanReadings": [ "chang2" ], "text": "场" }, { "hanReadings": [ "zai4" ], "text": "在" }, { "hanReadings": [ "gong1" ], "text": "红" }, { "hanReadings": [ "jiu4" ], "text": "就" }, { "hanReadings": [ "zuo4" ], "text": "座" } ], "lemmas": [ { "lemma": "5", "text": "５" }, { "lemma": "月", "text": "月" }, { "lemma": "的", "text": "的" }, { "lemma": "莫斯科", "text": "莫斯科" }, { "lemma": "，", "text": "，" }, { "lemma": "草木", "text": "草木" }, { "lemma": "葱茏", "text": "葱茏" }, { "lemma": "，", "text": "，" }, { "lemma": "旌旗", "text": "旌旗" }, { "lemma": "飘扬", "text": "飘扬" }, { "lemma": "，", "text": "，" }, { "lemma": "呈现", "text": "呈现" }, { "lemma": "出", "text": "出" }, { "lemma": "浓郁", "text": "浓郁" }, { "lemma": "的", "text": "的" }, { "lemma": "节日", "text": "节日" }, { "lemma": "气氛", "text": "气氛" }, { "lemma": "。", "text": "。" }, { "lemma": "从", "text": "从" }, { "lemma": "当地", "text": "当地" }, { "lemma": "时间", "text": "时间" }, { "lemma": "9时", "text": "9时" }, { "lemma": "开始", "text": "开始" }, { "lemma": "，", "text": "，" }, { "lemma": "胡", "text": "胡" }, { "lemma": "锦涛", "text": "锦涛" }, { "lemma": "同", "text": "同" }, { "lemma": "其他", "text": "其他" }, { "lemma": "国家", "text": "国家" }, { "lemma": "领导人", "text": "领导人" }, { "lemma": "相继", "text": "相继" }, { "lemma": "来到", "text": "来到" }, { "lemma": "克里姆林宫", "text": "克里姆林宫" }, { "lemma": "，", "text": "，" }, { "lemma": "同", "text": "同" }, { "lemma": "在", "text": "在" }, { "lemma": "那里迎候", "text": "那里迎候" }, { "lemma": "的", "text": "的" }, { "lemma": "俄罗斯", "text": "俄罗斯" }, { "lemma": "总统", "text": "总统" }, { "lemma": "梅", "text": "梅" }, { "lemma": "德", "text": "德" }, { "lemma": "韦", "text": "韦" }, { "lemma": "杰夫", "text": "杰夫" }, { "lemma": "亲切", "text": "亲切" }, { "lemma": "握手", "text": "握手" }, { "lemma": "。", "text": "。" }, { "lemma": "随后", "text": "随后" }, { "lemma": "，", "text": "，" }, { "lemma": "胡", "text": "胡" }, { "lemma": "锦涛", "text": "锦涛" }, { "lemma": "同", "text": "同" }, { "lemma": "出席", "text": "出席" }, { "lemma": "庆典", "text": "庆典" }, { "lemma": "的", "text": "的" }, { "lemma": "其他", "text": "其他" }, { "lemma": "贵宾", "text": "贵宾" }, { "lemma": "前往", "text": "前往" }, { "lemma": "红", "text": "红" }, { "lemma": "场", "text": "场" }, { "lemma": "，", "text": "，" }, { "lemma": "在", "text": "在" }, { "lemma": "红", "text": "红" }, { "lemma": "场观", "text": "场观" }, { "lemma": "礼台", "text": "礼台" }, { "lemma": "就", "text": "就" }, { "lemma": "座", "text": "座" }, { "lemma": "。", "text": "。" } ], "posTags": [ { "pos": "GUESS", "text": "５" }, { "pos": "NC", "text": "月" }, { "pos": "OC", "text": "的" }, { "pos": "NP", "text": "莫斯科" }, { "pos": "GUESS", "text": "，" }, { "pos": "NC", "text": "草木" }, { "pos": "E", "text": "葱茏" }, { "pos": "GUESS", "text": "，" }, { "pos": "NC", "text": "旌旗" }, { "pos": "V", "text": "飘扬" }, { "pos": "GUESS", "text": "，" }, { "pos": "V", "text": "呈现" }, { "pos": "NM", "text": "出" }, { "pos": "A", "text": "浓郁" }, { "pos": "OC", "text": "的" }, { "pos": "NC", "text": "节日" }, { "pos": "NC", "text": "气氛" }, { "pos": "GUESS", "text": "。" }, { "pos": "W", "text": "从" }, { "pos": "A", "text": "当地" }, { "pos": "NC", "text": "时间" }, { "pos": "GUESS", "text": "9时" }, { "pos": "NC", "text": "开始" }, { "pos": "GUESS", "text": "，" }, { "pos": "NC", "text": "胡" }, { "pos": "GUESS", "text": "锦涛" }, { "pos": "PR", "text": "同" }, { "pos": "NR", "text": "其他" }, { "pos": "NC", "text": "国家" }, { "pos": "NC", "text": "领导人" }, { "pos": "D", "text": "相继" }, { "pos": "V", "text": "来到" }, { "pos": "NP", "text": "克里姆林宫" }, { "pos": "GUESS", "text": "，" }, { "pos": "PR", "text": "同" }, { "pos": "D", "text": "在" }, { "pos": "GUESS", "text": "那里迎候" }, { "pos": "OC", "text": "的" }, { "pos": "NP", "text": "俄罗斯" }, { "pos": "NC", "text": "总统" }, { "pos": "NC", "text": "梅" }, { "pos": "W", "text": "德" }, { "pos": "NC", "text": "韦" }, { "pos": "GUESS", "text": "杰夫" }, { "pos": "A", "text": "亲切" }, { "pos": "V", "text": "握手" }, { "pos": "GUESS", "text": "。" }, { "pos": "D", "text": "随后" }, { "pos": "GUESS", "text": "，" }, { "pos": "NC", "text": "胡" }, { "pos": "GUESS", "text": "锦涛" }, { "pos": "PR", "text": "同" }, { "pos": "V", "text": "出席" }, { "pos": "NC", "text": "庆典" }, { "pos": "OC", "text": "的" }, { "pos": "NR", "text": "其他" }, { "pos": "NC", "text": "贵宾" }, { "pos": "V", "text": "前往" }, { "pos": "W", "text": "红" }, { "pos": "NM", "text": "场" }, { "pos": "GUESS", "text": "，" }, { "pos": "D", "text": "在" }, { "pos": "W", "text": "红" }, { "pos": "GUESS", "text": "场观" }, { "pos": "GUESS", "text": "礼台" }, { "pos": "D", "text": "就" }, { "pos": "NC", "text": "座" }, { "pos": "GUESS", "text": "。" } ], "requestId": "c88158cf-a99d-47a1-bbc8-440de49fa3fe", "timers": { "rblJe": 6, "rliJe": 11 } } python-0.7.4/tests/mock-data/response/zho-sentence-morphology_complete.status 0000664 0000000 0000000 00000000003 12636317025 0027635 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/zho-sentence-sentiment.json 0000664 0000000 0000000 00000000243 12636317025 0025210 0 ustar 00root root 0000000 0000000 { "code": "unsupportedLanguage", "message": "Chinese is not supported by Rosette Sentiment Analyzer", "requestId": "72dede04-32da-4c23-bfb0-60a8c8d2f67c" } python-0.7.4/tests/mock-data/response/zho-sentence-sentiment.status 0000664 0000000 0000000 00000000003 12636317025 0025554 0 ustar 00root root 0000000 0000000 415 python-0.7.4/tests/mock-data/response/zho-url-categories.json 0000664 0000000 0000000 00000000234 12636317025 0024325 0 ustar 00root root 0000000 0000000 { "code": "unsupportedLanguage", "message": "Chinese is not supported by Rosette Categorizer", "requestId": "884bfd8f-a753-4615-a0b4-aa952fce6d63" } python-0.7.4/tests/mock-data/response/zho-url-categories.status 0000664 0000000 0000000 00000000003 12636317025 0024671 0 ustar 00root root 0000000 0000000 415 python-0.7.4/tests/mock-data/response/zho-url-entities.json 0000664 0000000 0000000 00000012047 12636317025 0024031 0 ustar 00root root 0000000 0000000 { "entities": [ { "confidence": 0.01987546682357788, "count": 10, "indocChainId": 2, "mention": "俄", "normalized": "俄", "type": "LOCATION" }, { "confidence": 0.013244820965660943, "count": 9, "indocChainId": 17, "mention": "中", "normalized": "中", "type": "LOCATION" }, { "confidence": 0.03708694662366595, "count": 7, "indocChainId": 0, "mention": "习近平", "normalized": "习近平", "type": "PERSON" }, { "confidence": 0.0640413999557495, "count": 5, "indocChainId": 11, "mention": "普京", "normalized": "普京", "type": "PERSON" }, { "confidence": 0.028446480631828308, "count": 4, "indocChainId": 9, "mention": "俄罗斯", "normalized": "俄罗斯", "type": "LOCATION" }, { "confidence": 0.014063576857248941, "count": 3, "indocChainId": 21, "mention": "欧亚经济联盟", "normalized": "欧亚经济联盟", "type": "ORGANIZATION" }, { "confidence": 0.034951239824295044, "count": 2, "indocChainId": 4, "mention": "莫斯科", "normalized": "莫斯科", "type": "LOCATION" }, { "confidence": 0.03000470995903015, "count": 2, "indocChainId": 5, "mention": "记者", "normalized": "记者", "type": "TITLE" }, { "confidence": 0.008697807788848877, "count": 1, "indocChainId": 1, "mention": "京", "normalized": "京", "type": "LOCATION" }, { "confidence": 0.007232844829559326, "count": 1, "indocChainId": 3, "mention": "人民日报", "normalized": "人民日报", "type": "ORGANIZATION" }, { "confidence": 0.02314591407775879, "count": 1, "indocChainId": 6, "mention": "杜尚泽", "normalized": "杜尚泽", "type": "PERSON" }, { "confidence": 0.00882101058959961, "count": 1, "indocChainId": 7, "mention": "国家主席", "normalized": "国家主席", "type": "TITLE" }, { "confidence": 0.014860749244689941, "count": 1, "indocChainId": 10, "mention": "总统", "normalized": "总统", "type": "TITLE" }, { "confidence": 0.027349650859832764, "count": 1, "indocChainId": 24, "mention": "中国", "normalized": "中国", "type": "LOCATION" }, { "confidence": 0.015836060047149658, "count": 1, "indocChainId": 26, "mention": "亚洲", "normalized": "亚洲", "type": "LOCATION" }, { "confidence": 0.025710999965667725, "count": 1, "indocChainId": 27, "mention": "欧洲", "normalized": "欧洲", "type": "LOCATION" }, { "confidence": 0.01170969009399414, "count": 1, "indocChainId": 41, "mention": "主席", "normalized": "主席", "type": "TITLE" }, { "confidence": 0.005235791206359863, "count": 1, "indocChainId": 47, "mention": "欧", "normalized": "欧", "type": "LOCATION" }, { "confidence": 0.002737879753112793, "count": 1, "indocChainId": 48, "mention": "亚", "normalized": "亚", "type": "LOCATION" }, { "confidence": 0.0016486644744873047, "count": 1, "indocChainId": 49, "mention": "欧亚大陆", "normalized": "欧亚大陆", "type": "LOCATION" }, { "confidence": 0.006211519241333008, "count": 1, "indocChainId": 50, "mention": "远东", "normalized": "远东", "type": "LOCATION" }, { "confidence": 0.01225060224533081, "count": 1, "indocChainId": 51, "mention": "上海合作组织", "normalized": "上海合作组织", "type": "ORGANIZATION" }, { "confidence": 0.05038654804229736, "count": 1, "indocChainId": 52, "mention": "二十国集团", "normalized": "二十国集团", "type": "ORGANIZATION" }, { "confidence": 0.014413714408874512, "count": 1, "indocChainId": 53, "mention": "朝鲜半岛", "normalized": "朝鲜半岛", "type": "LOCATION" }, { "confidence": 0.007769942283630371, "count": 1, "indocChainId": 58, "mention": "深圳", "normalized": "深圳", "type": "LOCATION" }, { "confidence": 0.005864083766937256, "count": 1, "indocChainId": 59, "mention": "广西", "normalized": "广西", "type": "LOCATION" } ], "requestId": "e7dde9f7-cf2a-4eb7-9640-dbcb01876c84", "timers": { "rblJe": 9, "rexJe": 376, "rliJe": 3, "textExtractor": 23, "urlContentDownloader": 158 } } python-0.7.4/tests/mock-data/response/zho-url-entities.status 0000664 0000000 0000000 00000000003 12636317025 0024370 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/zho-url-entities_linked.json 0000664 0000000 0000000 00000006274 12636317025 0025364 0 ustar 00root root 0000000 0000000 { "entities": [ { "confidence": 0.899619272322934, "entityId": "Q15031", "indocChainId": 0, "mention": "习近平" }, { "confidence": 0.3528267721146622, "entityId": "Q956", "indocChainId": 1, "mention": "京" }, { "confidence": 0.5816475326681386, "entityId": "Q159", "indocChainId": 2, "mention": "俄" }, { "confidence": 0.9142187150598888, "entityId": "Q54340", "indocChainId": 3, "mention": "人民日报" }, { "confidence": 0.8608566483007024, "entityId": "Q649", "indocChainId": 4, "mention": "莫斯科" }, { "confidence": 0.5805713365753495, "entityId": "NEW-CLUSTER", "indocChainId": 6, "mention": "杜尚泽" }, { "confidence": 0.8702899453350353, "entityId": "Q159", "indocChainId": 9, "mention": "俄罗斯" }, { "confidence": 0.9856814786589845, "entityId": "Q7747", "indocChainId": 11, "mention": "普京" }, { "confidence": 0.4443587367642076, "entityId": "Q148", "indocChainId": 17, "mention": "中" }, { "confidence": 0.8823411560859947, "entityId": "Q474548", "indocChainId": 21, "mention": "欧亚经济联盟" }, { "confidence": 0.6130111295417227, "entityId": "Q148", "indocChainId": 24, "mention": "中国" }, { "confidence": 0.927725568096703, "entityId": "Q48", "indocChainId": 26, "mention": "亚洲" }, { "confidence": 0.897729266643381, "entityId": "Q46", "indocChainId": 27, "mention": "欧洲" }, { "confidence": 0.4847404303137973, "entityId": "Q46", "indocChainId": 47, "mention": "欧" }, { "confidence": 0.762793967436439, "entityId": "Q48", "indocChainId": 48, "mention": "亚" }, { "confidence": 0.8781700324275331, "entityId": "Q5401", "indocChainId": 49, "mention": "欧亚大陆" }, { "confidence": 0.8423861643310755, "entityId": "NEW-CLUSTER", "indocChainId": 50, "mention": "远东" }, { "confidence": 0.8908354747502565, "entityId": "Q485207", "indocChainId": 51, "mention": "上海合作组织" }, { "confidence": 0.8122172945191241, "entityId": "Q19771", "indocChainId": 52, "mention": "二十国集团" }, { "confidence": 0.794880223153438, "entityId": "Q483134", "indocChainId": 53, "mention": "朝鲜半岛" }, { "confidence": 0.4684058602808494, "entityId": "Q15174", "indocChainId": 58, "mention": "深圳" }, { "confidence": 0.5669229170882081, "entityId": "Q15176", "indocChainId": 59, "mention": "广西" } ], "requestId": "39c5cb0b-950a-4ae8-ba76-54f9983bcf68", "timers": { "rblJe": 9, "res": 886, "rexJe": 20, "rliJe": 3, "textExtractor": 21, "urlContentDownloader": 93 } } python-0.7.4/tests/mock-data/response/zho-url-entities_linked.status 0000664 0000000 0000000 00000000003 12636317025 0025716 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/zho-url-language.json 0000664 0000000 0000000 00000001051 12636317025 0023761 0 ustar 00root root 0000000 0000000 { "languageDetections": [ { "confidence": 0.056175227599422506, "language": "zho" }, { "confidence": 0.02074931407380365, "language": "zho" }, { "confidence": 0.004427018577772834, "language": "jpn" }, { "confidence": 0.0, "language": "ara" }, { "confidence": 0.0, "language": "ara" } ], "requestId": "fbbb8338-def4-4ad0-b685-78b2d08092d5", "timers": { "rliJe": 3, "textExtractor": 200, "urlContentDownloader": 711 } } python-0.7.4/tests/mock-data/response/zho-url-language.status 0000664 0000000 0000000 00000000003 12636317025 0024327 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/zho-url-morphology_complete.json 0000664 0000000 0000000 00000403707 12636317025 0026303 0 ustar 00root root 0000000 0000000 { "compounds": [], "hanReadings": [ { "hanReadings": [ "xi2" ], "text": "习" }, { "hanReadings": [ "jing1" ], "text": "京" }, { "hanReadings": [ "hui4-tan2" ], "text": "会谈" }, { "hanReadings": [ "zhong1" ], "text": "中" }, { "hanReadings": [ "e2" ], "text": "俄" }, { "hanReadings": [ "qian1" ], "text": "签" }, { "hanReadings": [ "fen4" ], "text": "份" }, { "hanReadings": [ "lian2-he2" ], "text": "联合" }, { "hanReadings": [ "sheng1-ming2" ], "text": "声明" }, { "hanReadings": [ "Ren2-min2-Ri4-bao4" ], "text": "人民日报" }, { "hanReadings": [ "quan2" ], "text": "全" }, { "hanReadings": [ "mei2-ti3" ], "text": "媒体" }, { "hanReadings": [ "ping2-tai2" ], "text": "平台" }, { "hanReadings": [ "Mo4-si1-ke1" ], "text": "莫斯科" }, { "hanReadings": [ "dian4" ], "text": "电" }, { "hanReadings": [ "ji4-zhe3" ], "text": "记者" }, { "hanReadings": [ "du4" ], "text": "杜" }, { "hanReadings": [ "dang1-di4" ], "text": "当地" }, { "hanReadings": [ "shi2-jian1" ], "text": "时间" }, { "hanReadings": [ "guo2-jia1" ], "text": "国家" }, { "hanReadings": [ "zhu3-xi2" ], "text": "主席" }, { "hanReadings": [ "xi2" ], "text": "习" }, { "hanReadings": [ "zai4" ], "text": "在" }, { "hanReadings": [ "tong2" ], "text": "同" }, { "hanReadings": [ "E2-luo2-si1" ], "text": "俄罗斯" }, { "hanReadings": [ "zong3-tong3" ], "text": "总统" }, { "hanReadings": [ "Pu3-jing1" ], "text": "普京" }, { "hanReadings": [ "ju3-xing2" ], "text": "举行" }, { "hanReadings": [ "hui4-tan2" ], "text": "会谈" }, { "hanReadings": [ "Pu3-jing1" ], "text": "普京" }, { "hanReadings": [ "re4-lie4" ], "text": "热烈" }, { "hanReadings": [ "huan1-ying2" ], "text": "欢迎" }, { "hanReadings": [ "xi2" ], "text": "习" }, { "hanReadings": [ "ying4-yao1" ], "text": "应邀" }, { "hanReadings": [ "qian2-lai2" ], "text": "前来" }, { "hanReadings": [ "chu1-xi2" ], "text": "出席" }, { "hanReadings": [ "guo2" ], "text": "国" }, { "hanReadings": [ "zhan4-zheng1" ], "text": "战争" }, { "hanReadings": [ "sheng4-li4" ], "text": "胜利" }, { "hanReadings": [ "zhou1-nian2" ], "text": "周年" }, { "hanReadings": [ "qing4-dian3" ], "text": "庆典" }, { "hanReadings": [ "Bing1" ], "text": "并" }, { "hanReadings": [ "fang3-wen4" ], "text": "访问" }, { "hanReadings": [ "E2-luo2-si1" ], "text": "俄罗斯" }, { "hanReadings": [ "xi2" ], "text": "习" }, { "hanReadings": [ "gan3-xie4" ], "text": "感谢" }, { "hanReadings": [ "Pu3-jing1" ], "text": "普京" }, { "hanReadings": [ "de0" ], "text": "的" }, { "hanReadings": [ "sheng4-qing2" ], "text": "盛情" }, { "hanReadings": [ "yao1-qing3" ], "text": "邀请" }, { "hanReadings": [ "liang3" ], "text": "两" }, { "hanReadings": [ "guo2" ], "text": "国" }, { "hanReadings": [ "yuan2-shou3" ], "text": "元首" }, { "hanReadings": [ "zai4" ], "text": "在" }, { "hanReadings": [ "qin1-qie4" ], "text": "亲切" }, { "hanReadings": [ "you3-hao3" ], "text": "友好" }, { "hanReadings": [ "de0" ], "text": "的" }, { "hanReadings": [ "qi4-fen1" ], "text": "气氛" }, { "hanReadings": [ "zhong1" ], "text": "中" }, { "hanReadings": [ "jiu4" ], "text": "就" }, { "hanReadings": [ "zhong1" ], "text": "中" }, { "hanReadings": [ "e2" ], "text": "俄" }, { "hanReadings": [ "guan1-xi0" ], "text": "关系" }, { "hanReadings": [ "he1" ], "text": "和" }, { "hanReadings": [ "bi3-ci3" ], "text": "彼此" }, { "hanReadings": [ "guan1-xin1" ], "text": "关心" }, { "hanReadings": [ "de0" ], "text": "的" }, { "hanReadings": [ "zhong4-da4" ], "text": "重大" }, { "hanReadings": [ "guo2-ji4" ], "text": "国际" }, { "hanReadings": [ "he1" ], "text": "和" }, { "hanReadings": [ "di4-qu1" ], "text": "地区" }, { "hanReadings": [ "wen4-ti2" ], "text": "问题" }, { "hanReadings": [ "chong1-fen4" ], "text": "充分" }, { "hanReadings": [ "jiao1-huan4" ], "text": "交换" }, { "hanReadings": [ "yi4-jian0" ], "text": "意见" }, { "hanReadings": [ "yi1-zhi4" ], "text": "一致" }, { "hanReadings": [ "tong2-yi4" ], "text": "同意" }, { "hanReadings": [ "zhong1" ], "text": "中" }, { "hanReadings": [ "e2" ], "text": "俄" }, { "hanReadings": [ "yao1" ], "text": "要" }, { "hanReadings": [ "gong4-tong2" ], "text": "共同" }, { "hanReadings": [ "wei2-hu4" ], "text": "维护" }, { "hanReadings": [ "di4-er4" ], "text": "第二" }, { "hanReadings": [ "ci4" ], "text": "次" }, { "hanReadings": [ "shi4-jie4-da4-zhan4" ], "text": "世界大战" }, { "hanReadings": [ "sheng4-li4" ], "text": "胜利" }, { "hanReadings": [ "cheng2-guo3" ], "text": "成果" }, { "hanReadings": [ "he1" ], "text": "和" }, { "hanReadings": [ "guo2-ji4" ], "text": "国际" }, { "hanReadings": [ "gong1-ping2" ], "text": "公平" }, { "hanReadings": [ "zheng4-yi4" ], "text": "正义" }, { "hanReadings": [ "tui1-jin4" ], "text": "推进" }, { "hanReadings": [ "Si1-chou2-zhi1-lu4" ], "text": "丝绸之路" }, { "hanReadings": [ "jing1-ji4" ], "text": "经济" }, { "hanReadings": [ "dai4" ], "text": "带" }, { "hanReadings": [ "jian4-she4" ], "text": "建设" }, { "hanReadings": [ "tong2" ], "text": "同" }, { "hanReadings": [ "Ou1-Ya4" ], "text": "欧亚" }, { "hanReadings": [ "jing1-ji4" ], "text": "经济" }, { "hanReadings": [ "lian2-meng2" ], "text": "联盟" }, { "hanReadings": [ "jian4-she4" ], "text": "建设" }, { "hanReadings": [ "dui4-jie1" ], "text": "对接" }, { "hanReadings": [ "xi2" ], "text": "习" }, { "hanReadings": [ "zhi3-chu1" ], "text": "指出" }, { "hanReadings": [ "hen3" ], "text": "很" }, { "hanReadings": [ "gao1-xing4" ], "text": "高兴" }, { "hanReadings": [ "lai2" ], "text": "来" }, { "hanReadings": [ "Mo4-si1-ke1" ], "text": "莫斯科" }, { "hanReadings": [ "chu1-xi2" ], "text": "出席" }, { "hanReadings": [ "guo2" ], "text": "国" }, { "hanReadings": [ "zhan4-zheng1" ], "text": "战争" }, { "hanReadings": [ "sheng4-li4" ], "text": "胜利" }, { "hanReadings": [ "zhou1-nian2" ], "text": "周年" }, { "hanReadings": [ "qing4-dian3" ], "text": "庆典" }, { "hanReadings": [ "Zhong1-guo2" ], "text": "中国" }, { "hanReadings": [ "he1" ], "text": "和" }, { "hanReadings": [ "E2-luo2-si1" ], "text": "俄罗斯" }, { "hanReadings": [ "fen1-bie2" ], "text": "分别" }, { "hanReadings": [ "shi4" ], "text": "是" }, { "hanReadings": [ "di4-er4" ], "text": "第二" }, { "hanReadings": [ "ci4" ], "text": "次" }, { "hanReadings": [ "shi4-jie4-da4-zhan4" ], "text": "世界大战" }, { "hanReadings": [ "Ya4-zhou1" ], "text": "亚洲" }, { "hanReadings": [ "he1" ], "text": "和" }, { "hanReadings": [ "Ou1-zhou1" ], "text": "欧洲" }, { "hanReadings": [ "zhu3-zhan4-chang3" ], "text": "主战场" }, { "hanReadings": [ "dou1" ], "text": "都" }, { "hanReadings": [ "wei2" ], "text": "为" }, { "hanReadings": [ "qu3-de2" ], "text": "取得" }, { "hanReadings": [ "di4-er4" ], "text": "第二" }, { "hanReadings": [ "ci4" ], "text": "次" }, { "hanReadings": [ "shi4-jie4-da4-zhan4" ], "text": "世界大战" }, { "hanReadings": [ "zui4-zhong1" ], "text": "最终" }, { "hanReadings": [ "sheng4-li4" ], "text": "胜利" }, { "hanReadings": [ "fu4-chu1" ], "text": "付出" }, { "hanReadings": [ "le0" ], "text": "了" }, { "hanReadings": [ "ju4-da4" ], "text": "巨大" }, { "hanReadings": [ "xi1-sheng1" ], "text": "牺牲" }, { "hanReadings": [ "le0" ], "text": "了" }, { "hanReadings": [ "zhong4-da4" ], "text": "重大" }, { "hanReadings": [ "gong4-xian4" ], "text": "贡献" }, { "hanReadings": [ "liang3" ], "text": "两" }, { "hanReadings": [ "guo2" ], "text": "国" }, { "hanReadings": [ "ren2-min2" ], "text": "人民" }, { "hanReadings": [ "ye3" ], "text": "也" }, { "hanReadings": [ "zai4" ], "text": "在" }, { "hanReadings": [ "bing4-jian1" ], "text": "并肩" }, { "hanReadings": [ "zhan4-dou4" ], "text": "战斗" }, { "hanReadings": [ "zhong1" ], "text": "中" }, { "hanReadings": [ "jie1" ], "text": "结" }, { "hanReadings": [ "xia4" ], "text": "下" }, { "hanReadings": [ "le0" ], "text": "了" }, { "hanReadings": [ "shen1-hou4" ], "text": "深厚" }, { "hanReadings": [ "you3-yi4" ], "text": "友谊" }, { "hanReadings": [ "zhong1" ], "text": "中" }, { "hanReadings": [ "e2" ], "text": "俄" }, { "hanReadings": [ "liang3" ], "text": "两" }, { "hanReadings": [ "guo2" ], "text": "国" }, { "hanReadings": [ "jin1-nian2" ], "text": "今年" }, { "hanReadings": [ "fen1-bie2" ], "text": "分别" }, { "hanReadings": [ "ju3-ban4" ], "text": "举办" }, { "hanReadings": [ "di4-er4" ], "text": "第二" }, { "hanReadings": [ "ci4" ], "text": "次" }, { "hanReadings": [ "shi4-jie4-da4-zhan4" ], "text": "世界大战" }, { "hanReadings": [ "sheng4-li4" ], "text": "胜利" }, { "hanReadings": [ "zhou1-nian2" ], "text": "周年" }, { "hanReadings": [ "xi4-lie4" ], "text": "系列" }, { "hanReadings": [ "qing4-zhu4" ], "text": "庆祝" }, { "hanReadings": [ "he1" ], "text": "和" }, { "hanReadings": [ "ji4-nian4" ], "text": "纪念" }, { "hanReadings": [ "huo2-dong4" ], "text": "活动" }, { "hanReadings": [ "mu4-di0" ], "text": "目的" }, { "hanReadings": [ "shi4" ], "text": "是" }, { "hanReadings": [ "ming2-ji4" ], "text": "铭记" }, { "hanReadings": [ "li4-shi3" ], "text": "历史" }, { "hanReadings": [ "mian3-huai2" ], "text": "缅怀" }, { "hanReadings": [ "xian1-lie4" ], "text": "先烈" }, { "hanReadings": [ "yao1" ], "text": "要" }, { "hanReadings": [ "tong2" ], "text": "同" }, { "hanReadings": [ "ge4-guo2" ], "text": "各国" }, { "hanReadings": [ "ren2-min2" ], "text": "人民" }, { "hanReadings": [ "yi1-dao4" ], "text": "一道" }, { "hanReadings": [ "zhen1-ai4" ], "text": "珍爱" }, { "hanReadings": [ "he1" ], "text": "和" }, { "hanReadings": [ "wei2-hu4" ], "text": "维护" }, { "hanReadings": [ "lai2-zhi1-bu4-yi4" ], "text": "来之不易" }, { "hanReadings": [ "de0" ], "text": "的" }, { "hanReadings": [ "he2-ping2" ], "text": "和平" }, { "hanReadings": [ "gong4" ], "text": "共" }, { "hanReadings": [ "chuang1" ], "text": "创" }, { "hanReadings": [ "quan2" ], "text": "全" }, { "hanReadings": [ "ren2-lei4" ], "text": "人类" }, { "hanReadings": [ "he2-ping2" ], "text": "和平" }, { "hanReadings": [ "yu2" ], "text": "与" }, { "hanReadings": [ "fa1-zhan3" ], "text": "发展" }, { "hanReadings": [ "de0" ], "text": "的" }, { "hanReadings": [ "mei3-hao3" ], "text": "美好" }, { "hanReadings": [ "wei4-lai2" ], "text": "未来" }, { "hanReadings": [ "xi2" ], "text": "习" }, { "hanReadings": [ "qiang2-diao4" ], "text": "强调" }, { "hanReadings": [ "wo3-men0" ], "text": "我们" }, { "hanReadings": [ "yuan4" ], "text": "愿" }, { "hanReadings": [ "shen1-hua4" ], "text": "深化" }, { "hanReadings": [ "tong2" ], "text": "同" }, { "hanReadings": [ "E2-luo2-si1" ], "text": "俄罗斯" }, { "hanReadings": [ "ren2-min2" ], "text": "人民" }, { "hanReadings": [ "chuan2-tong3" ], "text": "传统" }, { "hanReadings": [ "you3-yi4" ], "text": "友谊" }, { "hanReadings": [ "tui1-jin4" ], "text": "推进" }, { "hanReadings": [ "shuang1-fang1" ], "text": "双方" }, { "hanReadings": [ "fa1-zhan3" ], "text": "发展" }, { "hanReadings": [ "zhan4-lve4" ], "text": "战略" }, { "hanReadings": [ "dui4-jie1" ], "text": "对接" }, { "hanReadings": [ "gui1-hua4" ], "text": "规划" }, { "hanReadings": [ "liang3" ], "text": "两" }, { "hanReadings": [ "guo2" ], "text": "国" }, { "hanReadings": [ "you3-hao3" ], "text": "友好" }, { "hanReadings": [ "he2-zuo4" ], "text": "合作" }, { "hanReadings": [ "xin1" ], "text": "新" }, { "hanReadings": [ "wei4-lai2" ], "text": "未来" }, { "hanReadings": [ "tui1-dong4" ], "text": "推动" }, { "hanReadings": [ "zhong1" ], "text": "中" }, { "hanReadings": [ "e2" ], "text": "俄" }, { "hanReadings": [ "quan2-mian4" ], "text": "全面" }, { "hanReadings": [ "zhan4-lve4" ], "text": "战略" }, { "hanReadings": [ "xie2-zuo4" ], "text": "协作" }, { "hanReadings": [ "huo3-ban4" ], "text": "伙伴" }, { "hanReadings": [ "guan1-xi0" ], "text": "关系" }, { "hanReadings": [ "ji4-xu4" ], "text": "继续" }, { "hanReadings": [ "bao3-chi2" ], "text": "保持" }, { "hanReadings": [ "gao1" ], "text": "高" }, { "hanReadings": [ "shui3-ping2" ], "text": "水平" }, { "hanReadings": [ "fa1-zhan3" ], "text": "发展" }, { "hanReadings": [ "cu4-jin4" ], "text": "促进" }, { "hanReadings": [ "guo2-ji4" ], "text": "国际" }, { "hanReadings": [ "zhi4-xu4" ], "text": "秩序" }, { "hanReadings": [ "chao2-zhe0" ], "text": "朝着" }, { "hanReadings": [ "geng4-jia1" ], "text": "更加" }, { "hanReadings": [ "gong1-zheng4" ], "text": "公正" }, { "hanReadings": [ "he2-li3" ], "text": "合理" }, { "hanReadings": [ "de0" ], "text": "的" }, { "hanReadings": [ "fang1-xiang4" ], "text": "方向" }, { "hanReadings": [ "fa1-zhan3" ], "text": "发展" }, { "hanReadings": [ "wei2-hu4" ], "text": "维护" }, { "hanReadings": [ "di4-qu1" ], "text": "地区" }, { "hanReadings": [ "ji2" ], "text": "及" }, { "hanReadings": [ "shi4-jie4" ], "text": "世界" }, { "hanReadings": [ "he2-ping2" ], "text": "和平" }, { "hanReadings": [ "an1-quan2" ], "text": "安全" }, { "hanReadings": [ "wen3-ding4" ], "text": "稳定" }, { "hanReadings": [ "Pu3-jing1" ], "text": "普京" }, { "hanReadings": [ "gao1-du4" ], "text": "高度" }, { "hanReadings": [ "ping2-jia4" ], "text": "评价" }, { "hanReadings": [ "e2" ], "text": "俄" }, { "hanReadings": [ "zhong1" ], "text": "中" }, { "hanReadings": [ "liang3" ], "text": "两" }, { "hanReadings": [ "guo2" ], "text": "国" }, { "hanReadings": [ "guan1-xi0" ], "text": "关系" }, { "hanReadings": [ "fa1-zhan3" ], "text": "发展" }, { "hanReadings": [ "shui3-ping2" ], "text": "水平" }, { "hanReadings": [ "zhi3-chu1" ], "text": "指出" }, { "hanReadings": [ "e2" ], "text": "俄" }, { "hanReadings": [ "zhong1" ], "text": "中" }, { "hanReadings": [ "shi4" ], "text": "是" }, { "hanReadings": [ "zhen1-zheng4" ], "text": "真正" }, { "hanReadings": [ "de0" ], "text": "的" }, { "hanReadings": [ "quan2-mian4" ], "text": "全面" }, { "hanReadings": [ "zhan4-lve4" ], "text": "战略" }, { "hanReadings": [ "xie2-zuo4" ], "text": "协作" }, { "hanReadings": [ "huo3-ban4" ], "text": "伙伴" }, { "hanReadings": [ "zai4" ], "text": "在" }, { "hanReadings": [ "ge3" ], "text": "各" }, { "hanReadings": [ "ling3-yu4" ], "text": "领域" }, { "hanReadings": [ "ge3" ], "text": "各" }, { "hanReadings": [ "ceng2-mian4" ], "text": "层面" }, { "hanReadings": [ "dou1" ], "text": "都" }, { "hanReadings": [ "kai1-zhan3" ], "text": "开展" }, { "hanReadings": [ "le0" ], "text": "了" }, { "hanReadings": [ "zhuo2-you3-cheng2-xiao4" ], "text": "卓有成效" }, { "hanReadings": [ "de0" ], "text": "的" }, { "hanReadings": [ "jiao1-liu2" ], "text": "交流" }, { "hanReadings": [ "he2-zuo4" ], "text": "合作" }, { "hanReadings": [ "Pu3-jing1" ], "text": "普京" }, { "hanReadings": [ "biao3-shi4" ], "text": "表示" }, { "hanReadings": [ "wo3" ], "text": "我" }, { "hanReadings": [ "wan2-quan2" ], "text": "完全" }, { "hanReadings": [ "zan4-tong2" ], "text": "赞同" }, { "hanReadings": [ "xi2" ], "text": "习" }, { "hanReadings": [ "zhu3-xi2" ], "text": "主席" }, { "hanReadings": [ "dui4" ], "text": "对" }, { "hanReadings": [ "e2" ], "text": "俄" }, { "hanReadings": [ "zhong1" ], "text": "中" }, { "hanReadings": [ "liang3" ], "text": "两" }, { "hanReadings": [ "guo2" ], "text": "国" }, { "hanReadings": [ "zai4" ], "text": "在" }, { "hanReadings": [ "di4-er4" ], "text": "第二" }, { "hanReadings": [ "ci4" ], "text": "次" }, { "hanReadings": [ "shi4-jie4-da4-zhan4" ], "text": "世界大战" }, { "hanReadings": [ "zhong1" ], "text": "中" }, { "hanReadings": [ "li4-shi3" ], "text": "历史" }, { "hanReadings": [ "gong4-xian4" ], "text": "贡献" }, { "hanReadings": [ "de0" ], "text": "的" }, { "hanReadings": [ "ping2-jia4" ], "text": "评价" }, { "hanReadings": [ "liang3" ], "text": "两" }, { "hanReadings": [ "guo2" ], "text": "国" }, { "hanReadings": [ "jin1-nian2" ], "text": "今年" }, { "hanReadings": [ "jiang1" ], "text": "将" }, { "hanReadings": [ "ju3-ban4" ], "text": "举办" }, { "hanReadings": [ "qing4-zhu4" ], "text": "庆祝" }, { "hanReadings": [ "he1" ], "text": "和" }, { "hanReadings": [ "ji4-nian4" ], "text": "纪念" }, { "hanReadings": [ "huo2-dong4" ], "text": "活动" }, { "hanReadings": [ "fan3-dui4" ], "text": "反对" }, { "hanReadings": [ "ren4-he2" ], "text": "任何" }, { "hanReadings": [ "qi3-tu2" ], "text": "企图" }, { "hanReadings": [ "fou3-ren4" ], "text": "否认" }, { "hanReadings": [ "he1" ], "text": "和" }, { "hanReadings": [ "wai1-qu1" ], "text": "歪曲" }, { "hanReadings": [ "li4-shi3" ], "text": "历史" }, { "hanReadings": [ "de0" ], "text": "的" }, { "hanReadings": [ "tu2-mou2" ], "text": "图谋" }, { "hanReadings": [ "fan3-dui4" ], "text": "反对" }, { "hanReadings": [ "ren4-he2" ], "text": "任何" }, { "hanReadings": [ "mei3-hua4" ], "text": "美化" }, { "hanReadings": [ "fa3-xi1-si1" ], "text": "法西斯" }, { "hanReadings": [ "he1" ], "text": "和" }, { "hanReadings": [ "zhu3-yi4" ], "text": "主义" }, { "hanReadings": [ "fen1-zi3" ], "text": "分子" }, { "hanReadings": [ "mo3-hei1" ], "text": "抹黑" }, { "hanReadings": [ "jie3-fang4-zhe3" ], "text": "解放者" }, { "hanReadings": [ "de0" ], "text": "的" }, { "hanReadings": [ "xing2-wei2" ], "text": "行为" }, { "hanReadings": [ "guan1-yu2" ], "text": "关于" }, { "hanReadings": [ "zhong1" ], "text": "中" }, { "hanReadings": [ "e2" ], "text": "俄" }, { "hanReadings": [ "wu4-shi2" ], "text": "务实" }, { "hanReadings": [ "he2-zuo4" ], "text": "合作" }, { "hanReadings": [ "liang3" ], "text": "两" }, { "hanReadings": [ "guo2" ], "text": "国" }, { "hanReadings": [ "yuan2-shou3" ], "text": "元首" }, { "hanReadings": [ "shang1-ding4" ], "text": "商定" }, { "hanReadings": [ "jiang1" ], "text": "将" }, { "hanReadings": [ "Zhong1-fang1" ], "text": "中方" }, { "hanReadings": [ "Si1-chou2-zhi1-lu4" ], "text": "丝绸之路" }, { "hanReadings": [ "jing1-ji4" ], "text": "经济" }, { "hanReadings": [ "dai4" ], "text": "带" }, { "hanReadings": [ "jian4-she4" ], "text": "建设" }, { "hanReadings": [ "tong2" ], "text": "同" }, { "hanReadings": [ "Ou1-Ya4" ], "text": "欧亚" }, { "hanReadings": [ "jing1-ji4" ], "text": "经济" }, { "hanReadings": [ "lian2-meng2" ], "text": "联盟" }, { "hanReadings": [ "jian4-she4" ], "text": "建设" }, { "hanReadings": [ "dui4-jie1" ], "text": "对接" }, { "hanReadings": [ "cong1" ], "text": "从" }, { "hanReadings": [ "zhan4-lve4" ], "text": "战略" }, { "hanReadings": [ "gao1-du4" ], "text": "高度" }, { "hanReadings": [ "yi3" ], "text": "以" }, { "hanReadings": [ "geng1" ], "text": "更" }, { "hanReadings": [ "guang3" ], "text": "广" }, { "hanReadings": [ "shi4-ye3" ], "text": "视野" }, { "hanReadings": [ "quan2-mian4" ], "text": "全面" }, { "hanReadings": [ "kuo4-da4" ], "text": "扩大" }, { "hanReadings": [ "he1" ], "text": "和" }, { "hanReadings": [ "shen1-hua4" ], "text": "深化" }, { "hanReadings": [ "shuang1-fang1" ], "text": "双方" }, { "hanReadings": [ "wu4-shi2" ], "text": "务实" }, { "hanReadings": [ "he2-zuo4" ], "text": "合作" }, { "hanReadings": [ "kuo4-da4" ], "text": "扩大" }, { "hanReadings": [ "xiang1-hu4" ], "text": "相互" }, { "hanReadings": [ "kai1-fang4" ], "text": "开放" }, { "hanReadings": [ "shen1-hua4" ], "text": "深化" }, { "hanReadings": [ "li4-yi4" ], "text": "利益" }, { "hanReadings": [ "jiao1-rong2" ], "text": "交融" }, { "hanReadings": [ "geng1" ], "text": "更" }, { "hanReadings": [ "hao1" ], "text": "好" }, { "hanReadings": [ "cu4-jin4" ], "text": "促进" }, { "hanReadings": [ "liang3" ], "text": "两" }, { "hanReadings": [ "guo2" ], "text": "国" }, { "hanReadings": [ "fa1-zhan3" ], "text": "发展" }, { "hanReadings": [ "zhen4-xing1" ], "text": "振兴" }, { "hanReadings": [ "tuo4-zhan3" ], "text": "拓展" }, { "hanReadings": [ "Ou1" ], "text": "欧" }, { "hanReadings": [ "ya4" ], "text": "亚" }, { "hanReadings": [ "gong4-tong2" ], "text": "共同" }, { "hanReadings": [ "jing1-ji4" ], "text": "经济" }, { "hanReadings": [ "kong1-jian1" ], "text": "空间" }, { "hanReadings": [ "dai4-dong4" ], "text": "带动" }, { "hanReadings": [ "zheng3-ge4" ], "text": "整个" }, { "hanReadings": [ "Ou1" ], "text": "欧" }, { "hanReadings": [ "ya4" ], "text": "亚" }, { "hanReadings": [ "da4-lu4" ], "text": "大陆" }, { "hanReadings": [ "fa1-zhan3" ], "text": "发展" }, { "hanReadings": [ "he1" ], "text": "和" }, { "hanReadings": [ "wen3-ding4" ], "text": "稳定" }, { "hanReadings": [ "liang3" ], "text": "两" }, { "hanReadings": [ "guo2" ], "text": "国" }, { "hanReadings": [ "yuan2-shou3" ], "text": "元首" }, { "hanReadings": [ "tong2-yi4" ], "text": "同意" }, { "hanReadings": [ "wa1-jue2" ], "text": "挖掘" }, { "hanReadings": [ "he2-zuo4" ], "text": "合作" }, { "hanReadings": [ "qian2-li4" ], "text": "潜力" }, { "hanReadings": [ "he1" ], "text": "和" }, { "hanReadings": [ "you1-shi4" ], "text": "优势" }, { "hanReadings": [ "kuo4-da4" ], "text": "扩大" }, { "hanReadings": [ "liang3" ], "text": "两" }, { "hanReadings": [ "guo2" ], "text": "国" }, { "hanReadings": [ "neng2-yuan2" ], "text": "能源" }, { "hanReadings": [ "nong2-ye4" ], "text": "农业" }, { "hanReadings": [ "hang2-kong1" ], "text": "航空" }, { "hanReadings": [ "hang2-tian1" ], "text": "航天" }, { "hanReadings": [ "jin1-rong2" ], "text": "金融" }, { "hanReadings": [ "tou2-zi1" ], "text": "投资" }, { "hanReadings": [ "ling3-yu4" ], "text": "领域" }, { "hanReadings": [ "ji1-chu3" ], "text": "基础" }, { "hanReadings": [ "she4-shi1" ], "text": "设施" }, { "hanReadings": [ "jian4-she4" ], "text": "建设" }, { "hanReadings": [ "Yuan3-dong1" ], "text": "远东" }, { "hanReadings": [ "kai1-fa0" ], "text": "开发" }, { "hanReadings": [ "deng3" ], "text": "等" }, { "hanReadings": [ "fang1-mian4" ], "text": "方面" }, { "hanReadings": [ "he2-zuo4" ], "text": "合作" }, { "hanReadings": [ "kuo4-da4" ], "text": "扩大" }, { "hanReadings": [ "liang3" ], "text": "两" }, { "hanReadings": [ "guo2" ], "text": "国" }, { "hanReadings": [ "jiao4-yu4" ], "text": "教育" }, { "hanReadings": [ "wen2-hua4" ], "text": "文化" }, { "hanReadings": [ "wei4-sheng1" ], "text": "卫生" }, { "hanReadings": [ "lv3-you2" ], "text": "旅游" }, { "hanReadings": [ "deng3" ], "text": "等" }, { "hanReadings": [ "ren2-wen2" ], "text": "人文" }, { "hanReadings": [ "ling3-yu4" ], "text": "领域" }, { "hanReadings": [ "he2-zuo4" ], "text": "合作" }, { "hanReadings": [ "ji4-xu4" ], "text": "继续" }, { "hanReadings": [ "ban4" ], "text": "办" }, { "hanReadings": [ "hao1" ], "text": "好" }, { "hanReadings": [ "qing1-nian2" ], "text": "青年" }, { "hanReadings": [ "you3-hao3" ], "text": "友好" }, { "hanReadings": [ "jiao1-liu2" ], "text": "交流" }, { "hanReadings": [ "nian2" ], "text": "年" }, { "hanReadings": [ "mei2-ti3" ], "text": "媒体" }, { "hanReadings": [ "jiao1-liu2" ], "text": "交流" }, { "hanReadings": [ "nian2" ], "text": "年" }, { "hanReadings": [ "huo2-dong4" ], "text": "活动" }, { "hanReadings": [ "ji1-ji2" ], "text": "积极" }, { "hanReadings": [ "jia1-qiang2" ], "text": "加强" }, { "hanReadings": [ "liang3" ], "text": "两" }, { "hanReadings": [ "jun1" ], "text": "军" }, { "hanReadings": [ "jiao1-liu2" ], "text": "交流" }, { "hanReadings": [ "liang3" ], "text": "两" }, { "hanReadings": [ "guo2" ], "text": "国" }, { "hanReadings": [ "yuan2-shou3" ], "text": "元首" }, { "hanReadings": [ "tong2-yi4" ], "text": "同意" }, { "hanReadings": [ "jia1-qiang2" ], "text": "加强" }, { "hanReadings": [ "zai4" ], "text": "在" }, { "hanReadings": [ "Shang4-hai3" ], "text": "上海" }, { "hanReadings": [ "he2-zuo4" ], "text": "合作" }, { "hanReadings": [ "zu3-zhi1" ], "text": "组织" }, { "hanReadings": [ "jin1-zhuan1" ], "text": "金砖" }, { "hanReadings": [ "guo2-jia1" ], "text": "国家" }, { "hanReadings": [ "er4-shi2" ], "text": "二十" }, { "hanReadings": [ "guo2" ], "text": "国" }, { "hanReadings": [ "ji2-tuan2" ], "text": "集团" }, { "hanReadings": [ "kuang4-jia4" ], "text": "框架" }, { "hanReadings": [ "nei4" ], "text": "内" }, { "hanReadings": [ "de0" ], "text": "的" }, { "hanReadings": [ "he2-zuo4" ], "text": "合作" }, { "hanReadings": [ "shuang1-fang1" ], "text": "双方" }, { "hanReadings": [ "hai2" ], "text": "还" }, { "hanReadings": [ "jiu4" ], "text": "就" }, { "hanReadings": [ "Chao2-xian3" ], "text": "朝鲜" }, { "hanReadings": [ "ban4-dao3" ], "text": "半岛" }, { "hanReadings": [ "ju2-shi4" ], "text": "局势" }, { "hanReadings": [ "wen4-ti2" ], "text": "问题" }, { "hanReadings": [ "deng3" ], "text": "等" }, { "hanReadings": [ "gong4-tong2" ], "text": "共同" }, { "hanReadings": [ "guan1-xin1" ], "text": "关心" }, { "hanReadings": [ "de0" ], "text": "的" }, { "hanReadings": [ "guo2-ji4" ], "text": "国际" }, { "hanReadings": [ "he1" ], "text": "和" }, { "hanReadings": [ "di4-qu1" ], "text": "地区" }, { "hanReadings": [ "wen4-ti2" ], "text": "问题" }, { "hanReadings": [ "jiao1-huan4" ], "text": "交换" }, { "hanReadings": [ "le0" ], "text": "了" }, { "hanReadings": [ "yi4-jian0" ], "text": "意见" }, { "hanReadings": [ "yi1-zhi4" ], "text": "一致" }, { "hanReadings": [ "tong2-yi4" ], "text": "同意" }, { "hanReadings": [ "ji4-xu4" ], "text": "继续" }, { "hanReadings": [ "jiu4" ], "text": "就" }, { "hanReadings": [ "you3-guan1" ], "text": "有关" }, { "hanReadings": [ "wen4-ti2" ], "text": "问题" }, { "hanReadings": [ "bao3-chi2" ], "text": "保持" }, { "hanReadings": [ "mi4-qie4" ], "text": "密切" }, { "hanReadings": [ "gou1-tong1" ], "text": "沟通" }, { "hanReadings": [ "he1" ], "text": "和" }, { "hanReadings": [ "xie2-tiao2" ], "text": "协调" }, { "hanReadings": [ "hui4-tan2" ], "text": "会谈" }, { "hanReadings": [ "hou4" ], "text": "后" }, { "hanReadings": [ "liang3" ], "text": "两" }, { "hanReadings": [ "guo2" ], "text": "国" }, { "hanReadings": [ "yuan2-shou3" ], "text": "元首" }, { "hanReadings": [ "gong4-tong2" ], "text": "共同" }, { "hanReadings": [ "qian1-shu3" ], "text": "签署" }, { "hanReadings": [ "Bing1" ], "text": "并" }, { "hanReadings": [ "fa1-biao3" ], "text": "发表" }, { "hanReadings": [ "le0" ], "text": "了" }, { "hanReadings": [ "zhong1" ], "text": "中" }, { "hanReadings": [ "e2" ], "text": "俄" }, { "hanReadings": [ "liang3" ], "text": "两" }, { "hanReadings": [ "guo2" ], "text": "国" }, { "hanReadings": [ "guan1-yu2" ], "text": "关于" }, { "hanReadings": [ "shen1-hua4" ], "text": "深化" }, { "hanReadings": [ "quan2-mian4" ], "text": "全面" }, { "hanReadings": [ "zhan4-lve4" ], "text": "战略" }, { "hanReadings": [ "xie2-zuo4" ], "text": "协作" }, { "hanReadings": [ "huo3-ban4" ], "text": "伙伴" }, { "hanReadings": [ "guan1-xi0" ], "text": "关系" }, { "hanReadings": [ "chang4-dao3" ], "text": "倡导" }, { "hanReadings": [ "he2-zuo4" ], "text": "合作" }, { "hanReadings": [ "gong4" ], "text": "共" }, { "hanReadings": [ "ying2" ], "text": "赢" }, { "hanReadings": [ "de0" ], "text": "的" }, { "hanReadings": [ "lian2-he2" ], "text": "联合" }, { "hanReadings": [ "sheng1-ming2" ], "text": "声明" }, { "hanReadings": [ "guan1-yu2" ], "text": "关于" }, { "hanReadings": [ "Si1-chou2-zhi1-lu4" ], "text": "丝绸之路" }, { "hanReadings": [ "jing1-ji4" ], "text": "经济" }, { "hanReadings": [ "dai4" ], "text": "带" }, { "hanReadings": [ "jian4-she4" ], "text": "建设" }, { "hanReadings": [ "yu2" ], "text": "与" }, { "hanReadings": [ "Ou1-Ya4" ], "text": "欧亚" }, { "hanReadings": [ "jing1-ji4" ], "text": "经济" }, { "hanReadings": [ "lian2-meng2" ], "text": "联盟" }, { "hanReadings": [ "jian4-she4" ], "text": "建设" }, { "hanReadings": [ "dui4-jie1" ], "text": "对接" }, { "hanReadings": [ "he2-zuo4" ], "text": "合作" }, { "hanReadings": [ "de0" ], "text": "的" }, { "hanReadings": [ "lian2-he2" ], "text": "联合" }, { "hanReadings": [ "sheng1-ming2" ], "text": "声明" }, { "hanReadings": [ "Bing1" ], "text": "并" }, { "hanReadings": [ "jian4-zheng4" ], "text": "见证" }, { "hanReadings": [ "le0" ], "text": "了" }, { "hanReadings": [ "neng2-yuan2" ], "text": "能源" }, { "hanReadings": [ "jiao1-tong1" ], "text": "交通" }, { "hanReadings": [ "hang2-tian1" ], "text": "航天" }, { "hanReadings": [ "jin1-rong2" ], "text": "金融" }, { "hanReadings": [ "xin1-wen2" ], "text": "新闻" }, { "hanReadings": [ "mei2-ti3" ], "text": "媒体" }, { "hanReadings": [ "deng3" ], "text": "等" }, { "hanReadings": [ "ling3-yu4" ], "text": "领域" }, { "hanReadings": [ "duo1" ], "text": "多" }, { "hanReadings": [ "xiang4" ], "text": "项" }, { "hanReadings": [ "he2-zuo4" ], "text": "合作" }, { "hanReadings": [ "wen2-jian4" ], "text": "文件" }, { "hanReadings": [ "de0" ], "text": "的" }, { "hanReadings": [ "qian1-shu3" ], "text": "签署" }, { "hanReadings": [ "qian1-zi4" ], "text": "签字" }, { "hanReadings": [ "yi2-shi4" ], "text": "仪式" }, { "hanReadings": [ "hou4" ], "text": "后" }, { "hanReadings": [ "liang3" ], "text": "两" }, { "hanReadings": [ "guo2" ], "text": "国" }, { "hanReadings": [ "yuan2-shou3" ], "text": "元首" }, { "hanReadings": [ "gong4-tong2" ], "text": "共同" }, { "hanReadings": [ "hui4-jian4" ], "text": "会见" }, { "hanReadings": [ "le0" ], "text": "了" }, { "hanReadings": [ "ji4-zhe3" ], "text": "记者" }, { "hanReadings": [ "Shen1-zhen4" ], "text": "深圳" }, { "hanReadings": [ "wai4-wei2" ], "text": "外围" }, { "hanReadings": [ "nv3" ], "text": "女" }, { "hanReadings": [ "jia3-ban4" ], "text": "假扮" }, { "hanReadings": [ "jiao4" ], "text": "叫" }, { "hanReadings": [ "gao1" ], "text": "高" }, { "hanReadings": [ "Guang3-xi1" ], "text": "广西" }, { "hanReadings": [ "yi1" ], "text": "一" }, { "hanReadings": [ "ci4" ], "text": "次" }, { "hanReadings": [ "de0" ], "text": "的" }, { "hanReadings": [ "quan2" ], "text": "全" }, { "hanReadings": [ "guo4-cheng2" ], "text": "过程" } ], "lemmas": [ { "lemma": "习", "text": "习" }, { "lemma": "近平", "text": "近平" }, { "lemma": "同普", "text": "同普" }, { "lemma": "京", "text": "京" }, { "lemma": "会谈", "text": "会谈" }, { "lemma": "中", "text": "中" }, { "lemma": "俄", "text": "俄" }, { "lemma": "签", "text": "签" }, { "lemma": "2", "text": "2" }, { "lemma": "份", "text": "份" }, { "lemma": "联合", "text": "联合" }, { "lemma": "声明", "text": "声明" }, { "lemma": "人民日报", "text": "人民日报" }, { "lemma": "全", "text": "全" }, { "lemma": "媒体", "text": "媒体" }, { "lemma": "平台", "text": "平台" }, { "lemma": "莫斯科", "text": "莫斯科" }, { "lemma": "5月", "text": "5月" }, { "lemma": "8日", "text": "8日" }, { "lemma": "电", "text": "电" }, { "lemma": "（", "text": "（" }, { "lemma": "记者", "text": "记者" }, { "lemma": "杜", "text": "杜" }, { "lemma": "尚泽", "text": "尚泽" }, { "lemma": "）", "text": "）" }, { "lemma": "当地", "text": "当地" }, { "lemma": "时间", "text": "时间" }, { "lemma": "5月", "text": "5月" }, { "lemma": "8日", "text": "8日" }, { "lemma": "，", "text": "，" }, { "lemma": "国家", "text": "国家" }, { "lemma": "主席", "text": "主席" }, { "lemma": "习", "text": "习" }, { "lemma": "近平", "text": "近平" }, { "lemma": "在", "text": "在" }, { "lemma": "莫斯科克里姆林宫", "text": "莫斯科克里姆林宫" }, { "lemma": "同", "text": "同" }, { "lemma": "俄罗斯", "text": "俄罗斯" }, { "lemma": "总统", "text": "总统" }, { "lemma": "普京", "text": "普京" }, { "lemma": "举行", "text": "举行" }, { "lemma": "会谈", "text": "会谈" }, { "lemma": "。", "text": "。" }, { "lemma": "普京", "text": "普京" }, { "lemma": "热烈", "text": "热烈" }, { "lemma": "欢迎", "text": "欢迎" }, { "lemma": "习", "text": "习" }, { "lemma": "近平", "text": "近平" }, { "lemma": "应邀", "text": "应邀" }, { "lemma": "前来", "text": "前来" }, { "lemma": "出席", "text": "出席" }, { "lemma": "纪念卫", "text": "纪念卫" }, { "lemma": "国", "text": "国" }, { "lemma": "战争", "text": "战争" }, { "lemma": "胜利", "text": "胜利" }, { "lemma": "70", "text": "70" }, { "lemma": "周年", "text": "周年" }, { "lemma": "庆典", "text": "庆典" }, { "lemma": "并", "text": "并" }, { "lemma": "访问", "text": "访问" }, { "lemma": "俄罗斯", "text": "俄罗斯" }, { "lemma": "。", "text": "。" }, { "lemma": "习", "text": "习" }, { "lemma": "近平", "text": "近平" }, { "lemma": "感谢", "text": "感谢" }, { "lemma": "普京", "text": "普京" }, { "lemma": "的", "text": "的" }, { "lemma": "盛情", "text": "盛情" }, { "lemma": "邀请", "text": "邀请" }, { "lemma": "。", "text": "。" }, { "lemma": "2", "text": "两" }, { "lemma": "国", "text": "国" }, { "lemma": "元首", "text": "元首" }, { "lemma": "在", "text": "在" }, { "lemma": "亲切", "text": "亲切" }, { "lemma": "友好", "text": "友好" }, { "lemma": "的", "text": "的" }, { "lemma": "气氛", "text": "气氛" }, { "lemma": "中", "text": "中" }, { "lemma": "，", "text": "，" }, { "lemma": "就", "text": "就" }, { "lemma": "中", "text": "中" }, { "lemma": "俄", "text": "俄" }, { "lemma": "关系", "text": "关系" }, { "lemma": "和", "text": "和" }, { "lemma": "彼此", "text": "彼此" }, { "lemma": "关心", "text": "关心" }, { "lemma": "的", "text": "的" }, { "lemma": "重大", "text": "重大" }, { "lemma": "国际", "text": "国际" }, { "lemma": "和", "text": "和" }, { "lemma": "地区", "text": "地区" }, { "lemma": "问题", "text": "问题" }, { "lemma": "充分", "text": "充分" }, { "lemma": "交换", "text": "交换" }, { "lemma": "意见", "text": "意见" }, { "lemma": "，", "text": "，" }, { "lemma": "一致", "text": "一致" }, { "lemma": "同意", "text": "同意" }, { "lemma": "中", "text": "中" }, { "lemma": "俄", "text": "俄" }, { "lemma": "要", "text": "要" }, { "lemma": "共同", "text": "共同" }, { "lemma": "维护", "text": "维护" }, { "lemma": "第二", "text": "第二" }, { "lemma": "次", "text": "次" }, { "lemma": "世界大战", "text": "世界大战" }, { "lemma": "胜利", "text": "胜利" }, { "lemma": "成果", "text": "成果" }, { "lemma": "和", "text": "和" }, { "lemma": "国际", "text": "国际" }, { "lemma": "公平", "text": "公平" }, { "lemma": "正义", "text": "正义" }, { "lemma": "，", "text": "，" }, { "lemma": "推进", "text": "推进" }, { "lemma": "丝绸之路", "text": "丝绸之路" }, { "lemma": "经济", "text": "经济" }, { "lemma": "带", "text": "带" }, { "lemma": "建设", "text": "建设" }, { "lemma": "同", "text": "同" }, { "lemma": "欧亚", "text": "欧亚" }, { "lemma": "经济", "text": "经济" }, { "lemma": "联盟", "text": "联盟" }, { "lemma": "建设", "text": "建设" }, { "lemma": "对接", "text": "对接" }, { "lemma": "。", "text": "。" }, { "lemma": "习", "text": "习" }, { "lemma": "近平", "text": "近平" }, { "lemma": "指出", "text": "指出" }, { "lemma": "，", "text": "，" }, { "lemma": "很", "text": "很" }, { "lemma": "高兴", "text": "高兴" }, { "lemma": "来", "text": "来" }, { "lemma": "莫斯科", "text": "莫斯科" }, { "lemma": "出席", "text": "出席" }, { "lemma": "纪念卫", "text": "纪念卫" }, { "lemma": "国", "text": "国" }, { "lemma": "战争", "text": "战争" }, { "lemma": "胜利", "text": "胜利" }, { "lemma": "70", "text": "70" }, { "lemma": "周年", "text": "周年" }, { "lemma": "庆典", "text": "庆典" }, { "lemma": "。", "text": "。" }, { "lemma": "中国", "text": "中国" }, { "lemma": "和", "text": "和" }, { "lemma": "俄罗斯", "text": "俄罗斯" }, { "lemma": "分别", "text": "分别" }, { "lemma": "是", "text": "是" }, { "lemma": "第二", "text": "第二" }, { "lemma": "次", "text": "次" }, { "lemma": "世界大战", "text": "世界大战" }, { "lemma": "亚洲", "text": "亚洲" }, { "lemma": "和", "text": "和" }, { "lemma": "欧洲", "text": "欧洲" }, { "lemma": "主战场", "text": "主战场" }, { "lemma": "，", "text": "，" }, { "lemma": "都", "text": "都" }, { "lemma": "为", "text": "为" }, { "lemma": "取得", "text": "取得" }, { "lemma": "第二", "text": "第二" }, { "lemma": "次", "text": "次" }, { "lemma": "世界大战", "text": "世界大战" }, { "lemma": "最终", "text": "最终" }, { "lemma": "胜利", "text": "胜利" }, { "lemma": "付出", "text": "付出" }, { "lemma": "了", "text": "了" }, { "lemma": "巨大", "text": "巨大" }, { "lemma": "牺牲", "text": "牺牲" }, { "lemma": "、", "text": "、" }, { "lemma": "作出", "text": "作出" }, { "lemma": "了", "text": "了" }, { "lemma": "重大", "text": "重大" }, { "lemma": "贡献", "text": "贡献" }, { "lemma": "。", "text": "。" }, { "lemma": "2", "text": "两" }, { "lemma": "国", "text": "国" }, { "lemma": "人民", "text": "人民" }, { "lemma": "也", "text": "也" }, { "lemma": "在", "text": "在" }, { "lemma": "并肩", "text": "并肩" }, { "lemma": "战斗", "text": "战斗" }, { "lemma": "中", "text": "中" }, { "lemma": "结", "text": "结" }, { "lemma": "下", "text": "下" }, { "lemma": "了", "text": "了" }, { "lemma": "深厚", "text": "深厚" }, { "lemma": "友谊", "text": "友谊" }, { "lemma": "。", "text": "。" }, { "lemma": "中", "text": "中" }, { "lemma": "俄", "text": "俄" }, { "lemma": "2", "text": "两" }, { "lemma": "国", "text": "国" }, { "lemma": "今年", "text": "今年" }, { "lemma": "分别", "text": "分别" }, { "lemma": "举办", "text": "举办" }, { "lemma": "第二", "text": "第二" }, { "lemma": "次", "text": "次" }, { "lemma": "世界大战", "text": "世界大战" }, { "lemma": "胜利", "text": "胜利" }, { "lemma": "70", "text": "70" }, { "lemma": "周年", "text": "周年" }, { "lemma": "系列", "text": "系列" }, { "lemma": "庆祝", "text": "庆祝" }, { "lemma": "和", "text": "和" }, { "lemma": "纪念", "text": "纪念" }, { "lemma": "活动", "text": "活动" }, { "lemma": "，", "text": "，" }, { "lemma": "目的", "text": "目的" }, { "lemma": "是", "text": "是" }, { "lemma": "铭记", "text": "铭记" }, { "lemma": "历史", "text": "历史" }, { "lemma": "、", "text": "、" }, { "lemma": "缅怀", "text": "缅怀" }, { "lemma": "先烈", "text": "先烈" }, { "lemma": "，", "text": "，" }, { "lemma": "更是", "text": "更是" }, { "lemma": "要", "text": "要" }, { "lemma": "同", "text": "同" }, { "lemma": "各国", "text": "各国" }, { "lemma": "人民", "text": "人民" }, { "lemma": "一道", "text": "一道" }, { "lemma": "，", "text": "，" }, { "lemma": "珍爱", "text": "珍爱" }, { "lemma": "和", "text": "和" }, { "lemma": "维护", "text": "维护" }, { "lemma": "来之不易", "text": "来之不易" }, { "lemma": "的", "text": "的" }, { "lemma": "和平", "text": "和平" }, { "lemma": "，", "text": "，" }, { "lemma": "共", "text": "共" }, { "lemma": "创", "text": "创" }, { "lemma": "全", "text": "全" }, { "lemma": "人类", "text": "人类" }, { "lemma": "和平", "text": "和平" }, { "lemma": "与", "text": "与" }, { "lemma": "发展", "text": "发展" }, { "lemma": "的", "text": "的" }, { "lemma": "美好", "text": "美好" }, { "lemma": "未来", "text": "未来" }, { "lemma": "。", "text": "。" }, { "lemma": "习", "text": "习" }, { "lemma": "近平", "text": "近平" }, { "lemma": "强调", "text": "强调" }, { "lemma": "，", "text": "，" }, { "lemma": "我们", "text": "我们" }, { "lemma": "愿", "text": "愿" }, { "lemma": "深化", "text": "深化" }, { "lemma": "同", "text": "同" }, { "lemma": "俄罗斯", "text": "俄罗斯" }, { "lemma": "人民", "text": "人民" }, { "lemma": "传统", "text": "传统" }, { "lemma": "友谊", "text": "友谊" }, { "lemma": "，", "text": "，" }, { "lemma": "推进", "text": "推进" }, { "lemma": "双方", "text": "双方" }, { "lemma": "发展", "text": "发展" }, { "lemma": "战略", "text": "战略" }, { "lemma": "对接", "text": "对接" }, { "lemma": "，", "text": "，" }, { "lemma": "规划", "text": "规划" }, { "lemma": "2", "text": "两" }, { "lemma": "国", "text": "国" }, { "lemma": "友好", "text": "友好" }, { "lemma": "合作", "text": "合作" }, { "lemma": "新", "text": "新" }, { "lemma": "未来", "text": "未来" }, { "lemma": "，", "text": "，" }, { "lemma": "推动", "text": "推动" }, { "lemma": "中", "text": "中" }, { "lemma": "俄", "text": "俄" }, { "lemma": "全面", "text": "全面" }, { "lemma": "战略", "text": "战略" }, { "lemma": "协作", "text": "协作" }, { "lemma": "伙伴", "text": "伙伴" }, { "lemma": "关系", "text": "关系" }, { "lemma": "继续", "text": "继续" }, { "lemma": "保持", "text": "保持" }, { "lemma": "高", "text": "高" }, { "lemma": "水平", "text": "水平" }, { "lemma": "发展", "text": "发展" }, { "lemma": "，", "text": "，" }, { "lemma": "促进", "text": "促进" }, { "lemma": "国际", "text": "国际" }, { "lemma": "秩序", "text": "秩序" }, { "lemma": "朝着", "text": "朝着" }, { "lemma": "更加", "text": "更加" }, { "lemma": "公正", "text": "公正" }, { "lemma": "合理", "text": "合理" }, { "lemma": "的", "text": "的" }, { "lemma": "方向", "text": "方向" }, { "lemma": "发展", "text": "发展" }, { "lemma": "，", "text": "，" }, { "lemma": "维护", "text": "维护" }, { "lemma": "地区", "text": "地区" }, { "lemma": "及", "text": "及" }, { "lemma": "世界", "text": "世界" }, { "lemma": "和平", "text": "和平" }, { "lemma": "、", "text": "、" }, { "lemma": "安全", "text": "安全" }, { "lemma": "、", "text": "、" }, { "lemma": "稳定", "text": "稳定" }, { "lemma": "。", "text": "。" }, { "lemma": "普京", "text": "普京" }, { "lemma": "高度", "text": "高度" }, { "lemma": "评价", "text": "评价" }, { "lemma": "俄", "text": "俄" }, { "lemma": "中", "text": "中" }, { "lemma": "2", "text": "两" }, { "lemma": "国", "text": "国" }, { "lemma": "关系", "text": "关系" }, { "lemma": "发展", "text": "发展" }, { "lemma": "水平", "text": "水平" }, { "lemma": "，", "text": "，" }, { "lemma": "指出", "text": "指出" }, { "lemma": "俄", "text": "俄" }, { "lemma": "中", "text": "中" }, { "lemma": "是", "text": "是" }, { "lemma": "真正", "text": "真正" }, { "lemma": "的", "text": "的" }, { "lemma": "全面", "text": "全面" }, { "lemma": "战略", "text": "战略" }, { "lemma": "协作", "text": "协作" }, { "lemma": "伙伴", "text": "伙伴" }, { "lemma": "，", "text": "，" }, { "lemma": "在", "text": "在" }, { "lemma": "各", "text": "各" }, { "lemma": "领域", "text": "领域" }, { "lemma": "各", "text": "各" }, { "lemma": "层面", "text": "层面" }, { "lemma": "都", "text": "都" }, { "lemma": "开展", "text": "开展" }, { "lemma": "了", "text": "了" }, { "lemma": "卓有成效", "text": "卓有成效" }, { "lemma": "的", "text": "的" }, { "lemma": "交流", "text": "交流" }, { "lemma": "合作", "text": "合作" }, { "lemma": "。", "text": "。" }, { "lemma": "普京", "text": "普京" }, { "lemma": "表示", "text": "表示" }, { "lemma": "，", "text": "，" }, { "lemma": "我", "text": "我" }, { "lemma": "完全", "text": "完全" }, { "lemma": "赞同", "text": "赞同" }, { "lemma": "习", "text": "习" }, { "lemma": "近平", "text": "近平" }, { "lemma": "主席", "text": "主席" }, { "lemma": "对", "text": "对" }, { "lemma": "俄", "text": "俄" }, { "lemma": "中", "text": "中" }, { "lemma": "2", "text": "两" }, { "lemma": "国", "text": "国" }, { "lemma": "在", "text": "在" }, { "lemma": "第二", "text": "第二" }, { "lemma": "次", "text": "次" }, { "lemma": "世界大战", "text": "世界大战" }, { "lemma": "中", "text": "中" }, { "lemma": "历史", "text": "历史" }, { "lemma": "贡献", "text": "贡献" }, { "lemma": "的", "text": "的" }, { "lemma": "评价", "text": "评价" }, { "lemma": "。", "text": "。" }, { "lemma": "2", "text": "两" }, { "lemma": "国", "text": "国" }, { "lemma": "今年", "text": "今年" }, { "lemma": "将", "text": "将" }, { "lemma": "举办", "text": "举办" }, { "lemma": "庆祝", "text": "庆祝" }, { "lemma": "和", "text": "和" }, { "lemma": "纪念", "text": "纪念" }, { "lemma": "活动", "text": "活动" }, { "lemma": "，", "text": "，" }, { "lemma": "反对", "text": "反对" }, { "lemma": "任何", "text": "任何" }, { "lemma": "企图", "text": "企图" }, { "lemma": "否认", "text": "否认" }, { "lemma": "和", "text": "和" }, { "lemma": "歪曲", "text": "歪曲" }, { "lemma": "历史", "text": "历史" }, { "lemma": "的", "text": "的" }, { "lemma": "图谋", "text": "图谋" }, { "lemma": "，", "text": "，" }, { "lemma": "反对", "text": "反对" }, { "lemma": "任何", "text": "任何" }, { "lemma": "美化", "text": "美化" }, { "lemma": "法西斯", "text": "法西斯" }, { "lemma": "和", "text": "和" }, { "lemma": "军国", "text": "军国" }, { "lemma": "主义", "text": "主义" }, { "lemma": "分子", "text": "分子" }, { "lemma": "、", "text": "、" }, { "lemma": "抹黑", "text": "抹黑" }, { "lemma": "解放者", "text": "解放者" }, { "lemma": "的", "text": "的" }, { "lemma": "行为", "text": "行为" }, { "lemma": "。", "text": "。" }, { "lemma": "关于", "text": "关于" }, { "lemma": "中", "text": "中" }, { "lemma": "俄", "text": "俄" }, { "lemma": "务实", "text": "务实" }, { "lemma": "合作", "text": "合作" }, { "lemma": "，", "text": "，" }, { "lemma": "2", "text": "两" }, { "lemma": "国", "text": "国" }, { "lemma": "元首", "text": "元首" }, { "lemma": "商定", "text": "商定" }, { "lemma": "，", "text": "，" }, { "lemma": "将", "text": "将" }, { "lemma": "中方", "text": "中方" }, { "lemma": "丝绸之路", "text": "丝绸之路" }, { "lemma": "经济", "text": "经济" }, { "lemma": "带", "text": "带" }, { "lemma": "建设", "text": "建设" }, { "lemma": "同", "text": "同" }, { "lemma": "俄方", "text": "俄方" }, { "lemma": "欧亚", "text": "欧亚" }, { "lemma": "经济", "text": "经济" }, { "lemma": "联盟", "text": "联盟" }, { "lemma": "建设", "text": "建设" }, { "lemma": "对接", "text": "对接" }, { "lemma": "，", "text": "，" }, { "lemma": "从", "text": "从" }, { "lemma": "战略", "text": "战略" }, { "lemma": "高度", "text": "高度" }, { "lemma": "、", "text": "、" }, { "lemma": "以", "text": "以" }, { "lemma": "更", "text": "更" }, { "lemma": "广", "text": "广" }, { "lemma": "视野", "text": "视野" }, { "lemma": "全面", "text": "全面" }, { "lemma": "扩大", "text": "扩大" }, { "lemma": "和", "text": "和" }, { "lemma": "深化", "text": "深化" }, { "lemma": "双方", "text": "双方" }, { "lemma": "务实", "text": "务实" }, { "lemma": "合作", "text": "合作" }, { "lemma": "，", "text": "，" }, { "lemma": "扩大", "text": "扩大" }, { "lemma": "相互", "text": "相互" }, { "lemma": "开放", "text": "开放" }, { "lemma": "，", "text": "，" }, { "lemma": "深化", "text": "深化" }, { "lemma": "利益", "text": "利益" }, { "lemma": "交融", "text": "交融" }, { "lemma": "，", "text": "，" }, { "lemma": "更", "text": "更" }, { "lemma": "好", "text": "好" }, { "lemma": "促进", "text": "促进" }, { "lemma": "2", "text": "两" }, { "lemma": "国", "text": "国" }, { "lemma": "发展", "text": "发展" }, { "lemma": "振兴", "text": "振兴" }, { "lemma": "，", "text": "，" }, { "lemma": "拓展", "text": "拓展" }, { "lemma": "欧", "text": "欧" }, { "lemma": "亚", "text": "亚" }, { "lemma": "共同", "text": "共同" }, { "lemma": "经济", "text": "经济" }, { "lemma": "空间", "text": "空间" }, { "lemma": "，", "text": "，" }, { "lemma": "带动", "text": "带动" }, { "lemma": "整个", "text": "整个" }, { "lemma": "欧", "text": "欧" }, { "lemma": "亚", "text": "亚" }, { "lemma": "大陆", "text": "大陆" }, { "lemma": "发展", "text": "发展" }, { "lemma": "和", "text": "和" }, { "lemma": "稳定", "text": "稳定" }, { "lemma": "。", "text": "。" }, { "lemma": "2", "text": "两" }, { "lemma": "国", "text": "国" }, { "lemma": "元首", "text": "元首" }, { "lemma": "同意", "text": "同意" }, { "lemma": "，", "text": "，" }, { "lemma": "挖掘", "text": "挖掘" }, { "lemma": "合作", "text": "合作" }, { "lemma": "潜力", "text": "潜力" }, { "lemma": "和", "text": "和" }, { "lemma": "优势", "text": "优势" }, { "lemma": "，", "text": "，" }, { "lemma": "扩大", "text": "扩大" }, { "lemma": "2", "text": "两" }, { "lemma": "国", "text": "国" }, { "lemma": "能源", "text": "能源" }, { "lemma": "、", "text": "、" }, { "lemma": "农业", "text": "农业" }, { "lemma": "、", "text": "、" }, { "lemma": "高铁", "text": "高铁" }, { "lemma": "、", "text": "、" }, { "lemma": "航空", "text": "航空" }, { "lemma": "、", "text": "、" }, { "lemma": "航天", "text": "航天" }, { "lemma": "、", "text": "、" }, { "lemma": "金融", "text": "金融" }, { "lemma": "投资", "text": "投资" }, { "lemma": "领域", "text": "领域" }, { "lemma": "、", "text": "、" }, { "lemma": "基础", "text": "基础" }, { "lemma": "设施", "text": "设施" }, { "lemma": "建设", "text": "建设" }, { "lemma": "、", "text": "、" }, { "lemma": "远东", "text": "远东" }, { "lemma": "开发", "text": "开发" }, { "lemma": "等", "text": "等" }, { "lemma": "方面", "text": "方面" }, { "lemma": "合作", "text": "合作" }, { "lemma": "，", "text": "，" }, { "lemma": "扩大", "text": "扩大" }, { "lemma": "2", "text": "两" }, { "lemma": "国", "text": "国" }, { "lemma": "教育", "text": "教育" }, { "lemma": "、", "text": "、" }, { "lemma": "文化", "text": "文化" }, { "lemma": "、", "text": "、" }, { "lemma": "卫生", "text": "卫生" }, { "lemma": "、", "text": "、" }, { "lemma": "旅游", "text": "旅游" }, { "lemma": "等", "text": "等" }, { "lemma": "人文", "text": "人文" }, { "lemma": "领域", "text": "领域" }, { "lemma": "合作", "text": "合作" }, { "lemma": "，", "text": "，" }, { "lemma": "继续", "text": "继续" }, { "lemma": "办", "text": "办" }, { "lemma": "好", "text": "好" }, { "lemma": "青年", "text": "青年" }, { "lemma": "友好", "text": "友好" }, { "lemma": "交流", "text": "交流" }, { "lemma": "年", "text": "年" }, { "lemma": "、", "text": "、" }, { "lemma": "媒体", "text": "媒体" }, { "lemma": "交流", "text": "交流" }, { "lemma": "年", "text": "年" }, { "lemma": "活动", "text": "活动" }, { "lemma": "，", "text": "，" }, { "lemma": "积极", "text": "积极" }, { "lemma": "加强", "text": "加强" }, { "lemma": "2", "text": "两" }, { "lemma": "军", "text": "军" }, { "lemma": "交流", "text": "交流" }, { "lemma": "。", "text": "。" }, { "lemma": "2", "text": "两" }, { "lemma": "国", "text": "国" }, { "lemma": "元首", "text": "元首" }, { "lemma": "同意", "text": "同意" }, { "lemma": "加强", "text": "加强" }, { "lemma": "在", "text": "在" }, { "lemma": "上海", "text": "上海" }, { "lemma": "合作", "text": "合作" }, { "lemma": "组织", "text": "组织" }, { "lemma": "、", "text": "、" }, { "lemma": "金砖", "text": "金砖" }, { "lemma": "国家", "text": "国家" }, { "lemma": "、", "text": "、" }, { "lemma": "20", "text": "二十" }, { "lemma": "国", "text": "国" }, { "lemma": "集团", "text": "集团" }, { "lemma": "框架", "text": "框架" }, { "lemma": "内", "text": "内" }, { "lemma": "的", "text": "的" }, { "lemma": "合作", "text": "合作" }, { "lemma": "。", "text": "。" }, { "lemma": "双方", "text": "双方" }, { "lemma": "还", "text": "还" }, { "lemma": "就", "text": "就" }, { "lemma": "朝鲜", "text": "朝鲜" }, { "lemma": "半岛", "text": "半岛" }, { "lemma": "局势", "text": "局势" }, { "lemma": "、", "text": "、" }, { "lemma": "伊朗核", "text": "伊朗核" }, { "lemma": "问题", "text": "问题" }, { "lemma": "等", "text": "等" }, { "lemma": "共同", "text": "共同" }, { "lemma": "关心", "text": "关心" }, { "lemma": "的", "text": "的" }, { "lemma": "国际", "text": "国际" }, { "lemma": "和", "text": "和" }, { "lemma": "地区", "text": "地区" }, { "lemma": "问题", "text": "问题" }, { "lemma": "交换", "text": "交换" }, { "lemma": "了", "text": "了" }, { "lemma": "意见", "text": "意见" }, { "lemma": "，", "text": "，" }, { "lemma": "一致", "text": "一致" }, { "lemma": "同意", "text": "同意" }, { "lemma": "继续", "text": "继续" }, { "lemma": "就", "text": "就" }, { "lemma": "有关", "text": "有关" }, { "lemma": "问题", "text": "问题" }, { "lemma": "保持", "text": "保持" }, { "lemma": "密切", "text": "密切" }, { "lemma": "沟通", "text": "沟通" }, { "lemma": "和", "text": "和" }, { "lemma": "协调", "text": "协调" }, { "lemma": "。", "text": "。" }, { "lemma": "会谈", "text": "会谈" }, { "lemma": "后", "text": "后" }, { "lemma": "，", "text": "，" }, { "lemma": "2", "text": "两" }, { "lemma": "国", "text": "国" }, { "lemma": "元首", "text": "元首" }, { "lemma": "共同", "text": "共同" }, { "lemma": "签署", "text": "签署" }, { "lemma": "并", "text": "并" }, { "lemma": "发表", "text": "发表" }, { "lemma": "了", "text": "了" }, { "lemma": "《", "text": "《" }, { "lemma": "中", "text": "中" }, { "lemma": "俄", "text": "俄" }, { "lemma": "2", "text": "两" }, { "lemma": "国", "text": "国" }, { "lemma": "关于", "text": "关于" }, { "lemma": "深化", "text": "深化" }, { "lemma": "全面", "text": "全面" }, { "lemma": "战略", "text": "战略" }, { "lemma": "协作", "text": "协作" }, { "lemma": "伙伴", "text": "伙伴" }, { "lemma": "关系", "text": "关系" }, { "lemma": "、", "text": "、" }, { "lemma": "倡导", "text": "倡导" }, { "lemma": "合作", "text": "合作" }, { "lemma": "共", "text": "共" }, { "lemma": "赢", "text": "赢" }, { "lemma": "的", "text": "的" }, { "lemma": "联合", "text": "联合" }, { "lemma": "声明", "text": "声明" }, { "lemma": "》", "text": "》" }, { "lemma": "、", "text": "、" }, { "lemma": "《", "text": "《" }, { "lemma": "关于", "text": "关于" }, { "lemma": "丝绸之路", "text": "丝绸之路" }, { "lemma": "经济", "text": "经济" }, { "lemma": "带", "text": "带" }, { "lemma": "建设", "text": "建设" }, { "lemma": "与", "text": "与" }, { "lemma": "欧亚", "text": "欧亚" }, { "lemma": "经济", "text": "经济" }, { "lemma": "联盟", "text": "联盟" }, { "lemma": "建设", "text": "建设" }, { "lemma": "对接", "text": "对接" }, { "lemma": "合作", "text": "合作" }, { "lemma": "的", "text": "的" }, { "lemma": "联合", "text": "联合" }, { "lemma": "声明", "text": "声明" }, { "lemma": "》", "text": "》" }, { "lemma": "，", "text": "，" }, { "lemma": "并", "text": "并" }, { "lemma": "见证", "text": "见证" }, { "lemma": "了", "text": "了" }, { "lemma": "能源", "text": "能源" }, { "lemma": "、", "text": "、" }, { "lemma": "交通", "text": "交通" }, { "lemma": "、", "text": "、" }, { "lemma": "航天", "text": "航天" }, { "lemma": "、", "text": "、" }, { "lemma": "金融", "text": "金融" }, { "lemma": "、", "text": "、" }, { "lemma": "新闻", "text": "新闻" }, { "lemma": "媒体", "text": "媒体" }, { "lemma": "等", "text": "等" }, { "lemma": "领域", "text": "领域" }, { "lemma": "多", "text": "多" }, { "lemma": "项", "text": "项" }, { "lemma": "合作", "text": "合作" }, { "lemma": "文件", "text": "文件" }, { "lemma": "的", "text": "的" }, { "lemma": "签署", "text": "签署" }, { "lemma": "。", "text": "。" }, { "lemma": "签字", "text": "签字" }, { "lemma": "仪式", "text": "仪式" }, { "lemma": "后", "text": "后" }, { "lemma": "，", "text": "，" }, { "lemma": "2", "text": "两" }, { "lemma": "国", "text": "国" }, { "lemma": "元首", "text": "元首" }, { "lemma": "共同", "text": "共同" }, { "lemma": "会见", "text": "会见" }, { "lemma": "了", "text": "了" }, { "lemma": "记者", "text": "记者" }, { "lemma": "。", "text": "。" }, { "lemma": "3", "text": "3" }, { "lemma": "深圳", "text": "深圳" }, { "lemma": "“", "text": "“" }, { "lemma": "外围", "text": "外围" }, { "lemma": "女", "text": "女" }, { "lemma": "”", "text": "”" }, { "lemma": "假扮", "text": "假扮" }, { "lemma": "成明星", "text": "成明星" }, { "lemma": "叫", "text": "叫" }, { "lemma": "高", "text": "高" }, { "lemma": "价性", "text": "价性" }, { "lemma": "3667311", "text": "3667311" }, { "lemma": "7", "text": "7" }, { "lemma": "广西", "text": "广西" }, { "lemma": "：", "text": "：" }, { "lemma": "1", "text": "一" }, { "lemma": "次", "text": "次" }, { "lemma": "“", "text": "“" }, { "lemma": "碰瓷", "text": "碰瓷" }, { "lemma": "”", "text": "”" }, { "lemma": "的", "text": "的" }, { "lemma": "全", "text": "全" }, { "lemma": "过程", "text": "过程" }, { "lemma": "2717442", "text": "2717442" } ], "posTags": [ { "pos": "NC", "text": "习" }, { "pos": "GUESS", "text": "近平" }, { "pos": "GUESS", "text": "同普" }, { "pos": "NC", "text": "京" }, { "pos": "NC", "text": "会谈" }, { "pos": "A", "text": "中" }, { "pos": "NA", "text": "俄" }, { "pos": "NC", "text": "签" }, { "pos": "GUESS", "text": "2" }, { "pos": "NC", "text": "份" }, { "pos": "A", "text": "联合" }, { "pos": "NC", "text": "声明" }, { "pos": "NC", "text": "人民日报" }, { "pos": "A", "text": "全" }, { "pos": "NC", "text": "媒体" }, { "pos": "NC", "text": "平台" }, { "pos": "NP", "text": "莫斯科" }, { "pos": "GUESS", "text": "5月" }, { "pos": "GUESS", "text": "8日" }, { "pos": "NC", "text": "电" }, { "pos": "GUESS", "text": "（" }, { "pos": "NC", "text": "记者" }, { "pos": "NC", "text": "杜" }, { "pos": "GUESS", "text": "尚泽" }, { "pos": "GUESS", "text": "）" }, { "pos": "A", "text": "当地" }, { "pos": "NC", "text": "时间" }, { "pos": "GUESS", "text": "5月" }, { "pos": "GUESS", "text": "8日" }, { "pos": "GUESS", "text": "，" }, { "pos": "NC", "text": "国家" }, { "pos": "NC", "text": "主席" }, { "pos": "NC", "text": "习" }, { "pos": "GUESS", "text": "近平" }, { "pos": "D", "text": "在" }, { "pos": "GUESS", "text": "莫斯科克里姆林宫" }, { "pos": "PR", "text": "同" }, { "pos": "NP", "text": "俄罗斯" }, { "pos": "NC", "text": "总统" }, { "pos": "NC", "text": "普京" }, { "pos": "V", "text": "举行" }, { "pos": "NC", "text": "会谈" }, { "pos": "GUESS", "text": "。" }, { "pos": "NC", "text": "普京" }, { "pos": "A", "text": "热烈" }, { "pos": "V", "text": "欢迎" }, { "pos": "NC", "text": "习" }, { "pos": "GUESS", "text": "近平" }, { "pos": "V", "text": "应邀" }, { "pos": "V", "text": "前来" }, { "pos": "V", "text": "出席" }, { "pos": "GUESS", "text": "纪念卫" }, { "pos": "NC", "text": "国" }, { "pos": "NC", "text": "战争" }, { "pos": "D", "text": "胜利" }, { "pos": "GUESS", "text": "70" }, { "pos": "NC", "text": "周年" }, { "pos": "NC", "text": "庆典" }, { "pos": "NC", "text": "并" }, { "pos": "V", "text": "访问" }, { "pos": "NP", "text": "俄罗斯" }, { "pos": "GUESS", "text": "。" }, { "pos": "NC", "text": "习" }, { "pos": "GUESS", "text": "近平" }, { "pos": "NC", "text": "感谢" }, { "pos": "NC", "text": "普京" }, { "pos": "OC", "text": "的" }, { "pos": "NC", "text": "盛情" }, { "pos": "NC", "text": "邀请" }, { "pos": "GUESS", "text": "。" }, { "pos": "NN", "text": "两" }, { "pos": "NC", "text": "国" }, { "pos": "NC", "text": "元首" }, { "pos": "D", "text": "在" }, { "pos": "A", "text": "亲切" }, { "pos": "A", "text": "友好" }, { "pos": "OC", "text": "的" }, { "pos": "NC", "text": "气氛" }, { "pos": "A", "text": "中" }, { "pos": "GUESS", "text": "，" }, { "pos": "D", "text": "就" }, { "pos": "A", "text": "中" }, { "pos": "NA", "text": "俄" }, { "pos": "NC", "text": "关系" }, { "pos": "W", "text": "和" }, { "pos": "D", "text": "彼此" }, { "pos": "NC", "text": "关心" }, { "pos": "OC", "text": "的" }, { "pos": "E", "text": "重大" }, { "pos": "A", "text": "国际" }, { "pos": "W", "text": "和" }, { "pos": "NP", "text": "地区" }, { "pos": "NC", "text": "问题" }, { "pos": "A", "text": "充分" }, { "pos": "V", "text": "交换" }, { "pos": "NC", "text": "意见" }, { "pos": "GUESS", "text": "，" }, { "pos": "A", "text": "一致" }, { "pos": "V", "text": "同意" }, { "pos": "A", "text": "中" }, { "pos": "NA", "text": "俄" }, { "pos": "W", "text": "要" }, { "pos": "A", "text": "共同" }, { "pos": "V", "text": "维护" }, { "pos": "NN", "text": "第二" }, { "pos": "A", "text": "次" }, { "pos": "NC", "text": "世界大战" }, { "pos": "D", "text": "胜利" }, { "pos": "NC", "text": "成果" }, { "pos": "W", "text": "和" }, { "pos": "A", "text": "国际" }, { "pos": "A", "text": "公平" }, { "pos": "A", "text": "正义" }, { "pos": "GUESS", "text": "，" }, { "pos": "NC", "text": "推进" }, { "pos": "NP", "text": "丝绸之路" }, { "pos": "A", "text": "经济" }, { "pos": "NC", "text": "带" }, { "pos": "NC", "text": "建设" }, { "pos": "PR", "text": "同" }, { "pos": "NC", "text": "欧亚" }, { "pos": "A", "text": "经济" }, { "pos": "NC", "text": "联盟" }, { "pos": "NC", "text": "建设" }, { "pos": "NC", "text": "对接" }, { "pos": "GUESS", "text": "。" }, { "pos": "NC", "text": "习" }, { "pos": "GUESS", "text": "近平" }, { "pos": "V", "text": "指出" }, { "pos": "GUESS", "text": "，" }, { "pos": "D", "text": "很" }, { "pos": "A", "text": "高兴" }, { "pos": "D", "text": "来" }, { "pos": "NP", "text": "莫斯科" }, { "pos": "V", "text": "出席" }, { "pos": "GUESS", "text": "纪念卫" }, { "pos": "NC", "text": "国" }, { "pos": "NC", "text": "战争" }, { "pos": "D", "text": "胜利" }, { "pos": "GUESS", "text": "70" }, { "pos": "NC", "text": "周年" }, { "pos": "NC", "text": "庆典" }, { "pos": "GUESS", "text": "。" }, { "pos": "NP", "text": "中国" }, { "pos": "W", "text": "和" }, { "pos": "NP", "text": "俄罗斯" }, { "pos": "D", "text": "分别" }, { "pos": "A", "text": "是" }, { "pos": "NN", "text": "第二" }, { "pos": "A", "text": "次" }, { "pos": "NC", "text": "世界大战" }, { "pos": "NP", "text": "亚洲" }, { "pos": "W", "text": "和" }, { "pos": "NP", "text": "欧洲" }, { "pos": "NP", "text": "主战场" }, { "pos": "GUESS", "text": "，" }, { "pos": "D", "text": "都" }, { "pos": "OC", "text": "为" }, { "pos": "V", "text": "取得" }, { "pos": "NN", "text": "第二" }, { "pos": "A", "text": "次" }, { "pos": "NC", "text": "世界大战" }, { "pos": "A", "text": "最终" }, { "pos": "D", "text": "胜利" }, { "pos": "V", "text": "付出" }, { "pos": "PL", "text": "了" }, { "pos": "A", "text": "巨大" }, { "pos": "NC", "text": "牺牲" }, { "pos": "GUESS", "text": "、" }, { "pos": "GUESS", "text": "作出" }, { "pos": "PL", "text": "了" }, { "pos": "E", "text": "重大" }, { "pos": "NC", "text": "贡献" }, { "pos": "GUESS", "text": "。" }, { "pos": "NN", "text": "两" }, { "pos": "NC", "text": "国" }, { "pos": "NC", "text": "人民" }, { "pos": "D", "text": "也" }, { "pos": "D", "text": "在" }, { "pos": "D", "text": "并肩" }, { "pos": "A", "text": "战斗" }, { "pos": "A", "text": "中" }, { "pos": "V", "text": "结" }, { "pos": "D", "text": "下" }, { "pos": "PL", "text": "了" }, { "pos": "A", "text": "深厚" }, { "pos": "NC", "text": "友谊" }, { "pos": "GUESS", "text": "。" }, { "pos": "A", "text": "中" }, { "pos": "NA", "text": "俄" }, { "pos": "NN", "text": "两" }, { "pos": "NC", "text": "国" }, { "pos": "NC", "text": "今年" }, { "pos": "D", "text": "分别" }, { "pos": "V", "text": "举办" }, { "pos": "NN", "text": "第二" }, { "pos": "A", "text": "次" }, { "pos": "NC", "text": "世界大战" }, { "pos": "D", "text": "胜利" }, { "pos": "GUESS", "text": "70" }, { "pos": "NC", "text": "周年" }, { "pos": "NC", "text": "系列" }, { "pos": "V", "text": "庆祝" }, { "pos": "W", "text": "和" }, { "pos": "NC", "text": "纪念" }, { "pos": "A", "text": "活动" }, { "pos": "GUESS", "text": "，" }, { "pos": "U", "text": "目的" }, { "pos": "A", "text": "是" }, { "pos": "V", "text": "铭记" }, { "pos": "NC", "text": "历史" }, { "pos": "GUESS", "text": "、" }, { "pos": "V", "text": "缅怀" }, { "pos": "NC", "text": "先烈" }, { "pos": "GUESS", "text": "，" }, { "pos": "GUESS", "text": "更是" }, { "pos": "W", "text": "要" }, { "pos": "PR", "text": "同" }, { "pos": "NC", "text": "各国" }, { "pos": "NC", "text": "人民" }, { "pos": "D", "text": "一道" }, { "pos": "GUESS", "text": "，" }, { "pos": "V", "text": "珍爱" }, { "pos": "W", "text": "和" }, { "pos": "V", "text": "维护" }, { "pos": "E", "text": "来之不易" }, { "pos": "OC", "text": "的" }, { "pos": "E", "text": "和平" }, { "pos": "GUESS", "text": "，" }, { "pos": "D", "text": "共" }, { "pos": "W", "text": "创" }, { "pos": "A", "text": "全" }, { "pos": "NC", "text": "人类" }, { "pos": "E", "text": "和平" }, { "pos": "W", "text": "与" }, { "pos": "V", "text": "发展" }, { "pos": "OC", "text": "的" }, { "pos": "A", "text": "美好" }, { "pos": "NC", "text": "未来" }, { "pos": "GUESS", "text": "。" }, { "pos": "NC", "text": "习" }, { "pos": "GUESS", "text": "近平" }, { "pos": "NC", "text": "强调" }, { "pos": "GUESS", "text": "，" }, { "pos": "NR", "text": "我们" }, { "pos": "V", "text": "愿" }, { "pos": "V", "text": "深化" }, { "pos": "PR", "text": "同" }, { "pos": "NP", "text": "俄罗斯" }, { "pos": "NC", "text": "人民" }, { "pos": "NC", "text": "传统" }, { "pos": "NC", "text": "友谊" }, { "pos": "GUESS", "text": "，" }, { "pos": "NC", "text": "推进" }, { "pos": "NC", "text": "双方" }, { "pos": "V", "text": "发展" }, { "pos": "NC", "text": "战略" }, { "pos": "NC", "text": "对接" }, { "pos": "GUESS", "text": "，" }, { "pos": "V", "text": "规划" }, { "pos": "NN", "text": "两" }, { "pos": "NC", "text": "国" }, { "pos": "A", "text": "友好" }, { "pos": "NC", "text": "合作" }, { "pos": "A", "text": "新" }, { "pos": "NC", "text": "未来" }, { "pos": "GUESS", "text": "，" }, { "pos": "V", "text": "推动" }, { "pos": "A", "text": "中" }, { "pos": "NA", "text": "俄" }, { "pos": "A", "text": "全面" }, { "pos": "NC", "text": "战略" }, { "pos": "NC", "text": "协作" }, { "pos": "NC", "text": "伙伴" }, { "pos": "NC", "text": "关系" }, { "pos": "D", "text": "继续" }, { "pos": "V", "text": "保持" }, { "pos": "A", "text": "高" }, { "pos": "A", "text": "水平" }, { "pos": "V", "text": "发展" }, { "pos": "GUESS", "text": "，" }, { "pos": "V", "text": "促进" }, { "pos": "A", "text": "国际" }, { "pos": "NC", "text": "秩序" }, { "pos": "PR", "text": "朝着" }, { "pos": "D", "text": "更加" }, { "pos": "A", "text": "公正" }, { "pos": "A", "text": "合理" }, { "pos": "OC", "text": "的" }, { "pos": "NC", "text": "方向" }, { "pos": "V", "text": "发展" }, { "pos": "GUESS", "text": "，" }, { "pos": "V", "text": "维护" }, { "pos": "NP", "text": "地区" }, { "pos": "E", "text": "及" }, { "pos": "NP", "text": "世界" }, { "pos": "E", "text": "和平" }, { "pos": "GUESS", "text": "、" }, { "pos": "A", "text": "安全" }, { "pos": "GUESS", "text": "、" }, { "pos": "A", "text": "稳定" }, { "pos": "GUESS", "text": "。" }, { "pos": "NC", "text": "普京" }, { "pos": "NC", "text": "高度" }, { "pos": "NC", "text": "评价" }, { "pos": "NA", "text": "俄" }, { "pos": "A", "text": "中" }, { "pos": "NN", "text": "两" }, { "pos": "NC", "text": "国" }, { "pos": "NC", "text": "关系" }, { "pos": "V", "text": "发展" }, { "pos": "A", "text": "水平" }, { "pos": "GUESS", "text": "，" }, { "pos": "V", "text": "指出" }, { "pos": "NA", "text": "俄" }, { "pos": "A", "text": "中" }, { "pos": "A", "text": "是" }, { "pos": "A", "text": "真正" }, { "pos": "OC", "text": "的" }, { "pos": "A", "text": "全面" }, { "pos": "NC", "text": "战略" }, { "pos": "NC", "text": "协作" }, { "pos": "NC", "text": "伙伴" }, { "pos": "GUESS", "text": "，" }, { "pos": "D", "text": "在" }, { "pos": "W", "text": "各" }, { "pos": "NC", "text": "领域" }, { "pos": "W", "text": "各" }, { "pos": "NC", "text": "层面" }, { "pos": "D", "text": "都" }, { "pos": "A", "text": "开展" }, { "pos": "PL", "text": "了" }, { "pos": "E", "text": "卓有成效" }, { "pos": "OC", "text": "的" }, { "pos": "A", "text": "交流" }, { "pos": "NC", "text": "合作" }, { "pos": "GUESS", "text": "。" }, { "pos": "NC", "text": "普京" }, { "pos": "V", "text": "表示" }, { "pos": "GUESS", "text": "，" }, { "pos": "NR", "text": "我" }, { "pos": "D", "text": "完全" }, { "pos": "V", "text": "赞同" }, { "pos": "NC", "text": "习" }, { "pos": "GUESS", "text": "近平" }, { "pos": "NC", "text": "主席" }, { "pos": "A", "text": "对" }, { "pos": "NA", "text": "俄" }, { "pos": "A", "text": "中" }, { "pos": "NN", "text": "两" }, { "pos": "NC", "text": "国" }, { "pos": "D", "text": "在" }, { "pos": "NN", "text": "第二" }, { "pos": "A", "text": "次" }, { "pos": "NC", "text": "世界大战" }, { "pos": "A", "text": "中" }, { "pos": "NC", "text": "历史" }, { "pos": "NC", "text": "贡献" }, { "pos": "OC", "text": "的" }, { "pos": "NC", "text": "评价" }, { "pos": "GUESS", "text": "。" }, { "pos": "NN", "text": "两" }, { "pos": "NC", "text": "国" }, { "pos": "NC", "text": "今年" }, { "pos": "D", "text": "将" }, { "pos": "V", "text": "举办" }, { "pos": "V", "text": "庆祝" }, { "pos": "W", "text": "和" }, { "pos": "NC", "text": "纪念" }, { "pos": "A", "text": "活动" }, { "pos": "GUESS", "text": "，" }, { "pos": "V", "text": "反对" }, { "pos": "A", "text": "任何" }, { "pos": "NC", "text": "企图" }, { "pos": "V", "text": "否认" }, { "pos": "W", "text": "和" }, { "pos": "V", "text": "歪曲" }, { "pos": "NC", "text": "历史" }, { "pos": "OC", "text": "的" }, { "pos": "NC", "text": "图谋" }, { "pos": "GUESS", "text": "，" }, { "pos": "V", "text": "反对" }, { "pos": "A", "text": "任何" }, { "pos": "V", "text": "美化" }, { "pos": "NC", "text": "法西斯" }, { "pos": "W", "text": "和" }, { "pos": "GUESS", "text": "军国" }, { "pos": "NC", "text": "主义" }, { "pos": "NC", "text": "分子" }, { "pos": "GUESS", "text": "、" }, { "pos": "V", "text": "抹黑" }, { "pos": "NC", "text": "解放者" }, { "pos": "OC", "text": "的" }, { "pos": "NC", "text": "行为" }, { "pos": "GUESS", "text": "。" }, { "pos": "PR", "text": "关于" }, { "pos": "A", "text": "中" }, { "pos": "NA", "text": "俄" }, { "pos": "NC", "text": "务实" }, { "pos": "NC", "text": "合作" }, { "pos": "GUESS", "text": "，" }, { "pos": "NN", "text": "两" }, { "pos": "NC", "text": "国" }, { "pos": "NC", "text": "元首" }, { "pos": "V", "text": "商定" }, { "pos": "GUESS", "text": "，" }, { "pos": "D", "text": "将" }, { "pos": "NP", "text": "中方" }, { "pos": "NP", "text": "丝绸之路" }, { "pos": "A", "text": "经济" }, { "pos": "NC", "text": "带" }, { "pos": "NC", "text": "建设" }, { "pos": "PR", "text": "同" }, { "pos": "GUESS", "text": "俄方" }, { "pos": "NC", "text": "欧亚" }, { "pos": "A", "text": "经济" }, { "pos": "NC", "text": "联盟" }, { "pos": "NC", "text": "建设" }, { "pos": "NC", "text": "对接" }, { "pos": "GUESS", "text": "，" }, { "pos": "W", "text": "从" }, { "pos": "NC", "text": "战略" }, { "pos": "NC", "text": "高度" }, { "pos": "GUESS", "text": "、" }, { "pos": "OC", "text": "以" }, { "pos": "NC", "text": "更" }, { "pos": "A", "text": "广" }, { "pos": "NC", "text": "视野" }, { "pos": "A", "text": "全面" }, { "pos": "V", "text": "扩大" }, { "pos": "W", "text": "和" }, { "pos": "V", "text": "深化" }, { "pos": "NC", "text": "双方" }, { "pos": "NC", "text": "务实" }, { "pos": "NC", "text": "合作" }, { "pos": "GUESS", "text": "，" }, { "pos": "V", "text": "扩大" }, { "pos": "D", "text": "相互" }, { "pos": "V", "text": "开放" }, { "pos": "GUESS", "text": "，" }, { "pos": "V", "text": "深化" }, { "pos": "NC", "text": "利益" }, { "pos": "V", "text": "交融" }, { "pos": "GUESS", "text": "，" }, { "pos": "NC", "text": "更" }, { "pos": "W", "text": "好" }, { "pos": "V", "text": "促进" }, { "pos": "NN", "text": "两" }, { "pos": "NC", "text": "国" }, { "pos": "V", "text": "发展" }, { "pos": "V", "text": "振兴" }, { "pos": "GUESS", "text": "，" }, { "pos": "V", "text": "拓展" }, { "pos": "NC", "text": "欧" }, { "pos": "NA", "text": "亚" }, { "pos": "A", "text": "共同" }, { "pos": "A", "text": "经济" }, { "pos": "NC", "text": "空间" }, { "pos": "GUESS", "text": "，" }, { "pos": "V", "text": "带动" }, { "pos": "A", "text": "整个" }, { "pos": "NC", "text": "欧" }, { "pos": "NA", "text": "亚" }, { "pos": "NP", "text": "大陆" }, { "pos": "V", "text": "发展" }, { "pos": "W", "text": "和" }, { "pos": "A", "text": "稳定" }, { "pos": "GUESS", "text": "。" }, { "pos": "NN", "text": "两" }, { "pos": "NC", "text": "国" }, { "pos": "NC", "text": "元首" }, { "pos": "V", "text": "同意" }, { "pos": "GUESS", "text": "，" }, { "pos": "V", "text": "挖掘" }, { "pos": "NC", "text": "合作" }, { "pos": "NC", "text": "潜力" }, { "pos": "W", "text": "和" }, { "pos": "NC", "text": "优势" }, { "pos": "GUESS", "text": "，" }, { "pos": "V", "text": "扩大" }, { "pos": "NN", "text": "两" }, { "pos": "NC", "text": "国" }, { "pos": "NC", "text": "能源" }, { "pos": "GUESS", "text": "、" }, { "pos": "NC", "text": "农业" }, { "pos": "GUESS", "text": "、" }, { "pos": "GUESS", "text": "高铁" }, { "pos": "GUESS", "text": "、" }, { "pos": "NC", "text": "航空" }, { "pos": "GUESS", "text": "、" }, { "pos": "NC", "text": "航天" }, { "pos": "GUESS", "text": "、" }, { "pos": "NC", "text": "金融" }, { "pos": "NC", "text": "投资" }, { "pos": "NC", "text": "领域" }, { "pos": "GUESS", "text": "、" }, { "pos": "A", "text": "基础" }, { "pos": "NC", "text": "设施" }, { "pos": "NC", "text": "建设" }, { "pos": "GUESS", "text": "、" }, { "pos": "NC", "text": "远东" }, { "pos": "V", "text": "开发" }, { "pos": "V", "text": "等" }, { "pos": "NC", "text": "方面" }, { "pos": "NC", "text": "合作" }, { "pos": "GUESS", "text": "，" }, { "pos": "V", "text": "扩大" }, { "pos": "NN", "text": "两" }, { "pos": "NC", "text": "国" }, { "pos": "NC", "text": "教育" }, { "pos": "GUESS", "text": "、" }, { "pos": "NC", "text": "文化" }, { "pos": "GUESS", "text": "、" }, { "pos": "A", "text": "卫生" }, { "pos": "GUESS", "text": "、" }, { "pos": "NC", "text": "旅游" }, { "pos": "V", "text": "等" }, { "pos": "NC", "text": "人文" }, { "pos": "NC", "text": "领域" }, { "pos": "NC", "text": "合作" }, { "pos": "GUESS", "text": "，" }, { "pos": "D", "text": "继续" }, { "pos": "V", "text": "办" }, { "pos": "W", "text": "好" }, { "pos": "NC", "text": "青年" }, { "pos": "A", "text": "友好" }, { "pos": "A", "text": "交流" }, { "pos": "NC", "text": "年" }, { "pos": "GUESS", "text": "、" }, { "pos": "NC", "text": "媒体" }, { "pos": "A", "text": "交流" }, { "pos": "NC", "text": "年" }, { "pos": "A", "text": "活动" }, { "pos": "GUESS", "text": "，" }, { "pos": "A", "text": "积极" }, { "pos": "V", "text": "加强" }, { "pos": "NN", "text": "两" }, { "pos": "NC", "text": "军" }, { "pos": "A", "text": "交流" }, { "pos": "GUESS", "text": "。" }, { "pos": "NN", "text": "两" }, { "pos": "NC", "text": "国" }, { "pos": "NC", "text": "元首" }, { "pos": "V", "text": "同意" }, { "pos": "V", "text": "加强" }, { "pos": "D", "text": "在" }, { "pos": "NP", "text": "上海" }, { "pos": "NC", "text": "合作" }, { "pos": "NC", "text": "组织" }, { "pos": "GUESS", "text": "、" }, { "pos": "NC", "text": "金砖" }, { "pos": "NC", "text": "国家" }, { "pos": "GUESS", "text": "、" }, { "pos": "NN", "text": "二十" }, { "pos": "NC", "text": "国" }, { "pos": "NC", "text": "集团" }, { "pos": "NC", "text": "框架" }, { "pos": "A", "text": "内" }, { "pos": "OC", "text": "的" }, { "pos": "NC", "text": "合作" }, { "pos": "GUESS", "text": "。" }, { "pos": "NC", "text": "双方" }, { "pos": "D", "text": "还" }, { "pos": "D", "text": "就" }, { "pos": "NP", "text": "朝鲜" }, { "pos": "NC", "text": "半岛" }, { "pos": "NC", "text": "局势" }, { "pos": "GUESS", "text": "、" }, { "pos": "GUESS", "text": "伊朗核" }, { "pos": "NC", "text": "问题" }, { "pos": "V", "text": "等" }, { "pos": "A", "text": "共同" }, { "pos": "NC", "text": "关心" }, { "pos": "OC", "text": "的" }, { "pos": "A", "text": "国际" }, { "pos": "W", "text": "和" }, { "pos": "NP", "text": "地区" }, { "pos": "NC", "text": "问题" }, { "pos": "V", "text": "交换" }, { "pos": "PL", "text": "了" }, { "pos": "NC", "text": "意见" }, { "pos": "GUESS", "text": "，" }, { "pos": "A", "text": "一致" }, { "pos": "V", "text": "同意" }, { "pos": "D", "text": "继续" }, { "pos": "D", "text": "就" }, { "pos": "V", "text": "有关" }, { "pos": "NC", "text": "问题" }, { "pos": "V", "text": "保持" }, { "pos": "A", "text": "密切" }, { "pos": "V", "text": "沟通" }, { "pos": "W", "text": "和" }, { "pos": "A", "text": "协调" }, { "pos": "GUESS", "text": "。" }, { "pos": "NC", "text": "会谈" }, { "pos": "NC", "text": "后" }, { "pos": "GUESS", "text": "，" }, { "pos": "NN", "text": "两" }, { "pos": "NC", "text": "国" }, { "pos": "NC", "text": "元首" }, { "pos": "A", "text": "共同" }, { "pos": "V", "text": "签署" }, { "pos": "NC", "text": "并" }, { "pos": "V", "text": "发表" }, { "pos": "PL", "text": "了" }, { "pos": "GUESS", "text": "《" }, { "pos": "A", "text": "中" }, { "pos": "NA", "text": "俄" }, { "pos": "NN", "text": "两" }, { "pos": "NC", "text": "国" }, { "pos": "PR", "text": "关于" }, { "pos": "V", "text": "深化" }, { "pos": "A", "text": "全面" }, { "pos": "NC", "text": "战略" }, { "pos": "NC", "text": "协作" }, { "pos": "NC", "text": "伙伴" }, { "pos": "NC", "text": "关系" }, { "pos": "GUESS", "text": "、" }, { "pos": "NC", "text": "倡导" }, { "pos": "NC", "text": "合作" }, { "pos": "D", "text": "共" }, { "pos": "V", "text": "赢" }, { "pos": "OC", "text": "的" }, { "pos": "A", "text": "联合" }, { "pos": "NC", "text": "声明" }, { "pos": "GUESS", "text": "》" }, { "pos": "GUESS", "text": "、" }, { "pos": "GUESS", "text": "《" }, { "pos": "PR", "text": "关于" }, { "pos": "NP", "text": "丝绸之路" }, { "pos": "A", "text": "经济" }, { "pos": "NC", "text": "带" }, { "pos": "NC", "text": "建设" }, { "pos": "W", "text": "与" }, { "pos": "NC", "text": "欧亚" }, { "pos": "A", "text": "经济" }, { "pos": "NC", "text": "联盟" }, { "pos": "NC", "text": "建设" }, { "pos": "NC", "text": "对接" }, { "pos": "NC", "text": "合作" }, { "pos": "OC", "text": "的" }, { "pos": "A", "text": "联合" }, { "pos": "NC", "text": "声明" }, { "pos": "GUESS", "text": "》" }, { "pos": "GUESS", "text": "，" }, { "pos": "NC", "text": "并" }, { "pos": "NC", "text": "见证" }, { "pos": "PL", "text": "了" }, { "pos": "NC", "text": "能源" }, { "pos": "GUESS", "text": "、" }, { "pos": "A", "text": "交通" }, { "pos": "GUESS", "text": "、" }, { "pos": "NC", "text": "航天" }, { "pos": "GUESS", "text": "、" }, { "pos": "NC", "text": "金融" }, { "pos": "GUESS", "text": "、" }, { "pos": "NC", "text": "新闻" }, { "pos": "NC", "text": "媒体" }, { "pos": "V", "text": "等" }, { "pos": "NC", "text": "领域" }, { "pos": "A", "text": "多" }, { "pos": "NC", "text": "项" }, { "pos": "NC", "text": "合作" }, { "pos": "NC", "text": "文件" }, { "pos": "OC", "text": "的" }, { "pos": "V", "text": "签署" }, { "pos": "GUESS", "text": "。" }, { "pos": "NC", "text": "签字" }, { "pos": "NC", "text": "仪式" }, { "pos": "NC", "text": "后" }, { "pos": "GUESS", "text": "，" }, { "pos": "NN", "text": "两" }, { "pos": "NC", "text": "国" }, { "pos": "NC", "text": "元首" }, { "pos": "A", "text": "共同" }, { "pos": "V", "text": "会见" }, { "pos": "PL", "text": "了" }, { "pos": "NC", "text": "记者" }, { "pos": "GUESS", "text": "。" }, { "pos": "GUESS", "text": "3" }, { "pos": "NP", "text": "深圳" }, { "pos": "GUESS", "text": "“" }, { "pos": "NC", "text": "外围" }, { "pos": "W", "text": "女" }, { "pos": "GUESS", "text": "”" }, { "pos": "V", "text": "假扮" }, { "pos": "GUESS", "text": "成明星" }, { "pos": "PR", "text": "叫" }, { "pos": "A", "text": "高" }, { "pos": "GUESS", "text": "价性" }, { "pos": "GUESS", "text": "3667311" }, { "pos": "GUESS", "text": "7" }, { "pos": "NP", "text": "广西" }, { "pos": "GUESS", "text": "：" }, { "pos": "NN", "text": "一" }, { "pos": "A", "text": "次" }, { "pos": "GUESS", "text": "“" }, { "pos": "GUESS", "text": "碰瓷" }, { "pos": "GUESS", "text": "”" }, { "pos": "OC", "text": "的" }, { "pos": "A", "text": "全" }, { "pos": "NC", "text": "过程" }, { "pos": "GUESS", "text": "2717442" } ], "requestId": "b966f19b-6ccd-4202-9ed2-1427df4380d7", "timers": { "rblJe": 19, "rliJe": 5, "textExtractor": 28, "urlContentDownloader": 74 } } python-0.7.4/tests/mock-data/response/zho-url-morphology_complete.status 0000664 0000000 0000000 00000000003 12636317025 0026633 0 ustar 00root root 0000000 0000000 200 python-0.7.4/tests/mock-data/response/zho-url-sentiment.json 0000664 0000000 0000000 00000000243 12636317025 0024206 0 ustar 00root root 0000000 0000000 { "code": "unsupportedLanguage", "message": "Chinese is not supported by Rosette Sentiment Analyzer", "requestId": "51452bb2-871a-4c7a-9edd-fbb1bee8a96a" } python-0.7.4/tests/mock-data/response/zho-url-sentiment.status 0000664 0000000 0000000 00000000003 12636317025 0024552 0 ustar 00root root 0000000 0000000 415 python-0.7.4/tests/test_rosette_api.py 0000664 0000000 0000000 00000034157 12636317025 0020153 0 ustar 00root root 0000000 0000000 # -*- coding: utf-8 -*- """ Copyright (c) 2014-2015 Basis Technology Corporation. Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with the License. You may obtain a copy of the License at http://www.apache.org/licenses/LICENSE-2.0 Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions and limitations under the License. """ # To run tests, run `py.test test_rosette_api.py` import glob import httpretty import json import os import pytest import re import sys try: from StringIO import StringIO as streamIO except ImportError: from io import BytesIO as streamIO import gzip from rosette.api import API, DocumentParameters, NameTranslationParameters, NameMatchingParameters, RelationshipsParameters, RosetteException _IsPy3 = sys.version_info[0] == 3 request_file_dir = os.path.dirname(__file__) + "/mock-data/request/" response_file_dir = os.path.dirname(__file__) + "/mock-data/response/" # Define the regex pattern of file names. Example: eng-doc-categories.json filename_pattern = re.compile("(\w+-\w+-([a-z_-]+))[.]json") def get_file_content(filename): with open(filename, "r") as f: s = f.read() if len(s) > 200: out = streamIO() f1 = gzip.GzipFile(fileobj=out, mode="w") if _IsPy3: f1.write(bytes(s, 'UTF-8')) else: f1.write(s) f1.close() s = out.getvalue() return s # Run through all files in the mock-data directory, extract endpoint, and create a list of tuples of the form # (input filename, output status filename, output data filename, endpoint) as the elements def categorize_reqs(): files = [] # Loop through all file names in the mock-data/request directory for full_filename in glob.glob(request_file_dir + "*.json"): filename = os.path.basename(full_filename) # Extract the endpoint (the part after the first two "-" but before .json) endpoint = "/" + filename_pattern.match(filename).group(2).replace("_", "/") # Add (input, output status, output json, endpoint) to list of files files.append((filename_pattern.match(filename).group(1), response_file_dir + filename.replace("json", "status"), response_file_dir + filename, endpoint)) return files class RosetteTest: def __init__(self, filename=None): self.url = "https://api.rosette.com/rest/v1" # Set user key as filename as a workaround - tests don"t require user key # Filename is necessary to get the correct response in the mocked test self.api = API(user_key=filename) # Default to DocumentParameters as self.params self.params = DocumentParameters() if filename is not None: # Name matching endpoint requires NameMatchingParameters if "matched-name" in filename: self.params = NameMatchingParameters() # Name translation requires NameTranslationParameters elif "translated-name" in filename: self.params = NameTranslationParameters() # Relationships requires RelationshipParameters if user wants to specify options elif "relationships" in filename: self.params = RelationshipsParameters() # Find and load contents of request file into parameters with open(request_file_dir + filename + ".json", "r") as inp_file: params_dict = json.loads(inp_file.read()) for key in params_dict: self.params[key] = params_dict[key] # Setup for tests - register urls with HTTPretty and compile a list of all necessary information about each file # in mock-data/request so that tests can be run docs_list = categorize_reqs() # Test that pinging the API is working properly @httpretty.activate def test_ping(): with open(response_file_dir + "ping.json", "r") as ping_file: body = ping_file.read() httpretty.register_uri(httpretty.GET, "https://api.rosette.com/rest/v1/ping", body=body, status=200, content_type="application/json") test = RosetteTest(None) result = test.api.ping() assert result["message"] == "Rosette API at your service" # Test that getting the info about the API is being called correctly @httpretty.activate def test_info(): with open(response_file_dir + "info.json", "r") as info_file: body = info_file.read() httpretty.register_uri(httpretty.GET, "https://api.rosette.com/rest/v1/info", body=body, status=200, content_type="application/json") test = RosetteTest(None) result = test.api.info() assert result["buildNumber"] == "6bafb29d" assert result["name"] == "Rosette API" assert result["versionChecked"] is True # Test that retrying request retries the correct number of times @httpretty.activate def test_retryNum(): with open(response_file_dir + "info.json", "r") as info_file: body = info_file.read() httpretty.register_uri(httpretty.GET, "https://api.rosette.com/rest/v1/info", body=body, status=500, content_type="application/json") test = API(user_key=None, retries=5) try: result = test.info() assert False except RosetteException as e: assert e.message == "A retryable network operation has not succeeded after 5 attempts" assert e.status == "unknownError" # Test that retrying request throws the right error @httpretty.activate def test_retry500(): with open(response_file_dir + "info.json", "r") as info_file: body = {'message': 'We had a problem with our server. Try again later.', 'code': 'Internal Server Error'} httpretty.register_uri(httpretty.GET, "https://api.rosette.com/rest/v1/info", body=json.dumps(body), status=500, content_type="application/json") test = RosetteTest(None) try: result = test.api.info() assert False except RosetteException as e: assert e.message == "We had a problem with our server. Try again later." assert e.status == "Internal Server Error" @httpretty.activate def call_endpoint(input_filename, expected_status_filename, expected_output_filename, rest_endpoint): httpretty.register_uri(httpretty.POST, "https://api.rosette.com/rest/v1" + rest_endpoint, status=get_file_content(expected_status_filename), body=get_file_content(expected_output_filename), content_type="application/json") # need to mock /info call too because the api will call it implicitly with open(response_file_dir + "info.json", "r") as info_file: body = info_file.read() httpretty.register_uri(httpretty.GET, "https://api.rosette.com/rest/v1/info", body=body, status=200, content_type="application/json") httpretty.register_uri(httpretty.POST, "https://api.rosette.com/rest/v1/info", body=body, status=200, content_type="application/json") error_expected = False # Create an instance of the app, feeding the filename to be stored as the user key so the response will be correct test = RosetteTest(input_filename) # Open the expected response file and store the data with open(expected_output_filename, "r") as expected_file: expected_result = json.loads(expected_file.read()) # Check to see if this particular request should throw an exception for an unsupported language if "code" in expected_result: if expected_result["code"] == "unsupportedLanguage": error_expected = True functions = {"/categories": test.api.categories, "/entities": test.api.entities, "/entities/linked": test.api.entities, # (test.params, True) "/language": test.api.language, "/matched-name": test.api.matched_name, "/morphology/complete": test.api.morphology, "/relationships": test.api.relationships, "/sentiment": test.api.sentiment, "/translated-name": test.api.translated_name} # If the request is expected to throw an exception, try complete the operation and pass the test only if it fails if error_expected: try: functions[rest_endpoint](test.params) assert False except RosetteException as e: assert True return # Otherwise, actually complete the operation and check that it got the correct result # entities/linked must be handled separately because they require two arguments if "entities/linked" not in rest_endpoint: result = functions[rest_endpoint](test.params) else: result = functions[rest_endpoint](test.params, True) assert result == expected_result # Test all other endpoints # docs_list is the list of information from documents in the mock-data/request directory above # @pytest.mark.parametrize means that it will call the below test for each tuple # in the docs_list feeding the elements of the tuple as arguments to the test @pytest.mark.parametrize("input_filename, expected_status_filename, expected_output_filename, rest_endpoint", docs_list) def test_all(input_filename, expected_status_filename, expected_output_filename, rest_endpoint): # @httpretty and @pytest cannot co-exist, so separate the function definition call_endpoint(input_filename, expected_status_filename, expected_output_filename, rest_endpoint) # Test that debug flag is working properly @httpretty.activate def test_debug(): # Doesn't really matter what it returns for this test, so just making sure it catches all of them endpoints = ["categories", "entities", "entities/linked", "language", "matched-name", "morphology-complete", "sentiment", "translated-name", "relationships"] expected_status_filename = response_file_dir + "eng-sentence-entities.status" expected_output_filename = response_file_dir + "eng-sentence-entities.json" for rest_endpoint in endpoints: httpretty.register_uri(httpretty.POST, "https://api.rosette.com/rest/v1/" + rest_endpoint, status=get_file_content(expected_status_filename), body=get_file_content(expected_output_filename), content_type="application/json") with open(expected_output_filename, "r") as expected_file: expected_result = json.loads(expected_file.read()) # need to mock /info call too because the api will call it implicitly with open(response_file_dir + "info.json", "r") as info_file: body = info_file.read() httpretty.register_uri(httpretty.GET, "https://api.rosette.com/rest/v1/info", body=body, status=200, content_type="application/json") httpretty.register_uri(httpretty.POST, "https://api.rosette.com/rest/v1/info", body=body, status=200, content_type="application/json") api = API("0123456789", debug=True) content = "He also acknowledged the ongoing U.S. conflicts in Iraq and Afghanistan, noting that he is the \"commander in chief of a country that is responsible for ending a war and working in another theater to confront a ruthless adversary that directly threatens the American people\" and U.S. allies." params = DocumentParameters() params.__setitem__("content", content) api.entities(params) # Check that the most recent querystring had debug=true assert httpretty.last_request().querystring == {'debug': ['true']} # Test using text only input # To call entities: should work # To call matched-name and translated-name: should throw errors @httpretty.activate def test_just_text(): endpoints = ["categories", "entities", "entities/linked", "language", "matched-name", "morphology-complete", "sentiment", "translated-name", "relationships"] expected_status_filename = response_file_dir + "eng-sentence-entities.status" expected_output_filename = response_file_dir + "eng-sentence-entities.json" for rest_endpoint in endpoints: httpretty.register_uri(httpretty.POST, "https://api.rosette.com/rest/v1/" + rest_endpoint, status=get_file_content(expected_status_filename), body=get_file_content(expected_output_filename), content_type="application/json") with open(expected_output_filename, "r") as expected_file: expected_result = json.loads(expected_file.read()) # need to mock /info call too because the api will call it implicitly with open(response_file_dir + "info.json", "r") as info_file: body = info_file.read() httpretty.register_uri(httpretty.GET, "https://api.rosette.com/rest/v1/info", body=body, status=200, content_type="application/json") httpretty.register_uri(httpretty.POST, "https://api.rosette.com/rest/v1/info", body=body, status=200, content_type="application/json") api = API("0123456789") content = "He also acknowledged the ongoing U.S. conflicts in Iraq and Afghanistan, noting that he is the \"commander in chief of a country that is responsible for ending a war and working in another theater to confront a ruthless adversary that directly threatens the American people\" and U.S. allies." result = api.entities(content) # Check that it work for entities assert result == expected_result # Check that it throws the correct error for matched-name try: api.matched_name(content) assert False except RosetteException as e: assert e.status == "incompatible" # Check that it throws the correct error for translated-name try: api.translated_name(content) assert False except RosetteException as e: assert e.status == "incompatible" python-0.7.4/tox.ini 0000664 0000000 0000000 00000000715 12636317025 0014366 0 ustar 00root root 0000000 0000000 # Tox (http://tox.testrun.org/) is a tool for running tests # in multiple virtualenvs. This configuration file will run the # test suite on all supported python versions. To use it, "pip install tox" # and then run "tox" from this directory. [tox] skipsdist = True envlist = py26, py27, py33, py34 [testenv] commands = {envpython} setup.py install {envbindir}/py.test --pep8 deps = pytest pep8 pytest-pep8 httpretty==0.8.10 epydoc