import PyPDF4

columns=[VALUATION_DATE,SYS_CODE,COMPANY_CODE,STAT_ENTITY,LINE_OF_BUSINESS,POLICY_NO,BEN_SEQ,PARENT_BEN_SEQ,

PHASE_CODE,SUB_PHASE_CODE,RECORD_TYPE,POLICY_STATUS,TERM_REASON,PLAN_CODE,ADMIN_PLAN_CODE,LM_PLAN_CODE,

BEN_TYPE_CODE,PRODUCT_TYPE_CODE,SUPP_BEN_TYPE_CODE,STATEMENT_LOCATION,EXHIBIT_CODE,ANNUAL_STATEMENTLOB,

DESCRIPTION,ISSUE_DATE,ALT_ISSUE_DATE,FIRST_YEAR_INDICATOR,PAID_TO_DATE,DISABLEMENT_DATE,TERM_DATE,INTEREST_RATE_FIELD,

ISSUE_AGE,ATTAINED_AGE,DURATION,SEX_CODE,VANTAGE_PREMIUM_CLASS_CODE,RISK_CODE,CLASS_CODE,JL_STATUS,ISSUE_STATE,

RESIDENT_STATE,UNITS,AMOUNT_ISSUED,AMOUNT_INFORCE,GBL_ULTIMATE_DB,BEN_CODE,BEN_PATTERN_CODE,PREM_CODE,

ENDOW_PATTERN_CODE,LAPSE_FIELD1,EXPENSE_GROUP_FIELD1,EXPENSE_GROUP_FIELD2,GROSS_PREM_FIELD1,GROSS_PREM_FIELD2,

BILLING_FORM_MODE,ADMIN_SYSTEM_MODE,PREMIUM_MODE,GROSS_ANNUAL_PREM,MODAL_PREMIUM,

GROSS_ANNLZD_PREM,ADMINSYSTEM_CV,POLICY_LOAN,POLICY_LOAN_INTEREST,POLICY_LOAN_RATE,POLICY_LOAN_TYPE,

BIRTH_DATE,ISSUE_STATE_ZIP_CODE,RESIDENT_STATE_ZIP_CODE,DIT_ADMIN_COMPANY_CODE,LIFE_ADMIN_COMPANY_CODE,

ORIGINAL_ISSUE_AGE,ADMIN_ISSUE_AGE,ORIGINAL_ISSUE_DATE,ADMIN_ISSUE_DATE,DIT_LINE_OF_BUSINESS,MATURITY_EXPIRY_DATE,

ADMIN_PAID_TO_DATE,ORIGINAL_POLICY_NO,DIT_POLICY_NUMBER,ADMIN_PREMIUM_MODE,TRANSLATED_PREMIUM_MODE,DIT_ADMIN_SYSTEM,

VANTAGE_STATUS_CODE,ADMIN_UW_CLASS_CODE,ADMIN_RISK_CODE,MARKETING_SOURCE_CODE,INSURED_DIRECTORY_ID,ISSUE_YEAR,DIT_ISSUE_YEAR,

EXPENSE_GROUP_FIELD3,EXPENSE_GROUP_FIELD4,LAPSE_FIELD2,LAPSE_FIELD3,

LAPSE_ADJUSTMENT_FIELD1,LAPSE_ADJUSTMENT_FIELD2,SELECT_FACTOR_FIELD1,SELECT_FACTOR_FIELD2,SELECT_FACTOR_FIELD3,

SELECT_FACTOR_FIELD4,MORTALITY_RATE_FIELD1,MORTALITY_RATE_FIELD2,MORTALITY_RATE_FIELD3,MORTALITY_RATE_FIELD4,

X_FACTOR_FIELD2,OCC_CLASS_CODE,PUA_FACE,UNDWRTNG_CODE,REINS_PLAN_CODE,REINS_LM_PLAN_CODE,

REINS_PREMIUM_MODE,AMT_REINS_AT_ISSUE,AMT_RETAINED_AT_ISS,CURRENT_AMT_AT_RISK,REINS_GROSS_ANNLZD_PREM,

PAID_TO_DATE_00,RE_GROSS_PREM_FIELD1,RE_GROSS_PREM_FIELD2,MORTALITY_RATE_FIELD5,SELECT_FACTOR_FIELD5]

Import the mandatory modules

import os

import re

import sys

import argparse

class Text_search :

####layer 1

def __init__(self, string2, path1,i=None):

self.path1= path1

self.string1 = string2

self.i=i

if self.i:

string2 = string2.lower()

self.string2= re.compile(string2)

####layer 2

def txt_search(self):

file_number = 0

files = [f for f in os.listdir(self.path1) if os.path.isfile(self.path1+”/”+f)]

for file in files:

file_t = open(self.path1+”/”+file)

file_text= file_t.read()

if self.i:

file_text=file_text.lower()

file_t.close()

if re.search(self.string2, file_text):

print “The text “+self.string1+” found in “, file

file_number=file_number+1

print “total files are “,file_number

####layer 3

def txt_search_m(self):

files = [f for f in os.listdir(self.path1) if os.path.isfile(self.path1+"/"+f)]

file_number = 0

for file in files:

file_t = open(self.path1+"/"+file)

line_number=1

flag_file = 0

for line1 in file_t:

if self.i:

line1 = line1.lower()

if re.search(self.string2, line1):

flag_file= 1

print "The text "+self.string1+" found in ", file, " at line number ",line_number

line_number=line_number+1

if flag_file == 1:

file_number=file_number+1

flag_file=0

file_t.close()

print "total files are ",file_number

####layer 4

def txt_search_r(self):

file_number = 0

for root, dir, files in os.walk(self.path1, topdown = True):

files = [f for f in files if os.path.isfile(root+”/”+f)]

for file in files:

file= root+”/”+file

file_t = open(file)

line_number=1

flag_file = 0

for line1 in file_t:

if self.i:

line1=line1.lower()

if re.search(self.string2, line1):

flag_file= 1

print “The text “+self.string1+” found in “, file, “ at line number “,line_number

line_number=line_number+1

if flag_file == 1:

file_number=file_number+1

flag_file=0

file_t.close()

print “total files are “,file_number

####layer 5

def main():

parser = argparse.ArgumentParser(version=’1.0’)

parser.add_argument(‘-m’, nargs = 2, help = ‘To get files as well as line number of files ‘)

parser.add_argument(‘-s’, nargs = 2, help = ‘To get the files contain string ‘)

parser.add_argument(‘-r’, nargs = 2, help = ‘To search in recusrive order ‘)

parser.add_argument(‘-mi’, nargs = 2, help = ‘-m option with case insensitive ‘)

parser.add_argument(‘-si’, nargs = 2, help = ‘-s option with case insensitive ‘)

parser.add_argument(‘-ri’, nargs = 2, help = ‘-r option with case insensitive ‘)

args = parser.parse_args()