pax_global_header00006660000000000000000000000064125206161770014521gustar00rootroot0000000000000052 comment=728e151e7489c14f7001c6ab9971f3687a782c76 php-utf-8-1.2.1/000077500000000000000000000000001252061617700132525ustar00rootroot00000000000000php-utf-8-1.2.1/.gitignore000066400000000000000000000000271252061617700152410ustar00rootroot00000000000000/vendor /composer.phar php-utf-8-1.2.1/.travis.yml000066400000000000000000000003751252061617700153700ustar00rootroot00000000000000language: php php: - 5.4 - 5.5 - 5.6 matrix: allow_failures: - php: - hhvm install: composer install script: - phpunit --configuration native.xml --coverage-text - phpunit --configuration mbstring.xml --coverage-text php-utf-8-1.2.1/LICENSE000066400000000000000000000634651252061617700142750ustar00rootroot00000000000000 GNU LESSER GENERAL PUBLIC LICENSE Version 2.1, February 1999 Copyright (C) 1991, 1999 Free Software Foundation, Inc. 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA Everyone is permitted to copy and distribute verbatim copies of this license document, but changing it is not allowed. [This is the first released version of the Lesser GPL. It also counts as the successor of the GNU Library Public License, version 2, hence the version number 2.1.] Preamble The licenses for most software are designed to take away your freedom to share and change it. By contrast, the GNU General Public Licenses are intended to guarantee your freedom to share and change free software--to make sure the software is free for all its users. This license, the Lesser General Public License, applies to some specially designated software packages--typically libraries--of the Free Software Foundation and other authors who decide to use it. You can use it too, but we suggest you first think carefully about whether this license or the ordinary General Public License is the better strategy to use in any particular case, based on the explanations below. When we speak of free software, we are referring to freedom of use, not price. Our General Public Licenses are designed to make sure that you have the freedom to distribute copies of free software (and charge for this service if you wish); that you receive source code or can get it if you want it; that you can change the software and use pieces of it in new free programs; and that you are informed that you can do these things. To protect your rights, we need to make restrictions that forbid distributors to deny you these rights or to ask you to surrender these rights. These restrictions translate to certain responsibilities for you if you distribute copies of the library or if you modify it. For example, if you distribute copies of the library, whether gratis or for a fee, you must give the recipients all the rights that we gave you. You must make sure that they, too, receive or can get the source code. If you link other code with the library, you must provide complete object files to the recipients, so that they can relink them with the library after making changes to the library and recompiling it. And you must show them these terms so they know their rights. We protect your rights with a two-step method: (1) we copyright the library, and (2) we offer you this license, which gives you legal permission to copy, distribute and/or modify the library. To protect each distributor, we want to make it very clear that there is no warranty for the free library. Also, if the library is modified by someone else and passed on, the recipients should know that what they have is not the original version, so that the original author's reputation will not be affected by problems that might be introduced by others. Finally, software patents pose a constant threat to the existence of any free program. We wish to make sure that a company cannot effectively restrict the users of a free program by obtaining a restrictive license from a patent holder. Therefore, we insist that any patent license obtained for a version of the library must be consistent with the full freedom of use specified in this license. Most GNU software, including some libraries, is covered by the ordinary GNU General Public License. This license, the GNU Lesser General Public License, applies to certain designated libraries, and is quite different from the ordinary General Public License. We use this license for certain libraries in order to permit linking those libraries into non-free programs. When a program is linked with a library, whether statically or using a shared library, the combination of the two is legally speaking a combined work, a derivative of the original library. The ordinary General Public License therefore permits such linking only if the entire combination fits its criteria of freedom. The Lesser General Public License permits more lax criteria for linking other code with the library. We call this license the "Lesser" General Public License because it does Less to protect the user's freedom than the ordinary General Public License. It also provides other free software developers Less of an advantage over competing non-free programs. These disadvantages are the reason we use the ordinary General Public License for many libraries. However, the Lesser license provides advantages in certain special circumstances. For example, on rare occasions, there may be a special need to encourage the widest possible use of a certain library, so that it becomes a de-facto standard. To achieve this, non-free programs must be allowed to use the library. A more frequent case is that a free library does the same job as widely used non-free libraries. In this case, there is little to gain by limiting the free library to free software only, so we use the Lesser General Public License. In other cases, permission to use a particular library in non-free programs enables a greater number of people to use a large body of free software. For example, permission to use the GNU C Library in non-free programs enables many more people to use the whole GNU operating system, as well as its variant, the GNU/Linux operating system. Although the Lesser General Public License is Less protective of the users' freedom, it does ensure that the user of a program that is linked with the Library has the freedom and the wherewithal to run that program using a modified version of the Library. The precise terms and conditions for copying, distribution and modification follow. Pay close attention to the difference between a "work based on the library" and a "work that uses the library". The former contains code derived from the library, whereas the latter must be combined with the library in order to run. GNU LESSER GENERAL PUBLIC LICENSE TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION 0. This License Agreement applies to any software library or other program which contains a notice placed by the copyright holder or other authorized party saying it may be distributed under the terms of this Lesser General Public License (also called "this License"). Each licensee is addressed as "you". A "library" means a collection of software functions and/or data prepared so as to be conveniently linked with application programs (which use some of those functions and data) to form executables. The "Library", below, refers to any such software library or work which has been distributed under these terms. A "work based on the Library" means either the Library or any derivative work under copyright law: that is to say, a work containing the Library or a portion of it, either verbatim or with modifications and/or translated straightforwardly into another language. (Hereinafter, translation is included without limitation in the term "modification".) "Source code" for a work means the preferred form of the work for making modifications to it. For a library, complete source code means all the source code for all modules it contains, plus any associated interface definition files, plus the scripts used to control compilation and installation of the library. Activities other than copying, distribution and modification are not covered by this License; they are outside its scope. The act of running a program using the Library is not restricted, and output from such a program is covered only if its contents constitute a work based on the Library (independent of the use of the Library in a tool for writing it). Whether that is true depends on what the Library does and what the program that uses the Library does. 1. You may copy and distribute verbatim copies of the Library's complete source code as you receive it, in any medium, provided that you conspicuously and appropriately publish on each copy an appropriate copyright notice and disclaimer of warranty; keep intact all the notices that refer to this License and to the absence of any warranty; and distribute a copy of this License along with the Library. You may charge a fee for the physical act of transferring a copy, and you may at your option offer warranty protection in exchange for a fee. 2. You may modify your copy or copies of the Library or any portion of it, thus forming a work based on the Library, and copy and distribute such modifications or work under the terms of Section 1 above, provided that you also meet all of these conditions: a) The modified work must itself be a software library. b) You must cause the files modified to carry prominent notices stating that you changed the files and the date of any change. c) You must cause the whole of the work to be licensed at no charge to all third parties under the terms of this License. d) If a facility in the modified Library refers to a function or a table of data to be supplied by an application program that uses the facility, other than as an argument passed when the facility is invoked, then you must make a good faith effort to ensure that, in the event an application does not supply such function or table, the facility still operates, and performs whatever part of its purpose remains meaningful. (For example, a function in a library to compute square roots has a purpose that is entirely well-defined independent of the application. Therefore, Subsection 2d requires that any application-supplied function or table used by this function must be optional: if the application does not supply it, the square root function must still compute square roots.) These requirements apply to the modified work as a whole. If identifiable sections of that work are not derived from the Library, and can be reasonably considered independent and separate works in themselves, then this License, and its terms, do not apply to those sections when you distribute them as separate works. But when you distribute the same sections as part of a whole which is a work based on the Library, the distribution of the whole must be on the terms of this License, whose permissions for other licensees extend to the entire whole, and thus to each and every part regardless of who wrote it. Thus, it is not the intent of this section to claim rights or contest your rights to work written entirely by you; rather, the intent is to exercise the right to control the distribution of derivative or collective works based on the Library. In addition, mere aggregation of another work not based on the Library with the Library (or with a work based on the Library) on a volume of a storage or distribution medium does not bring the other work under the scope of this License. 3. You may opt to apply the terms of the ordinary GNU General Public License instead of this License to a given copy of the Library. To do this, you must alter all the notices that refer to this License, so that they refer to the ordinary GNU General Public License, version 2, instead of to this License. (If a newer version than version 2 of the ordinary GNU General Public License has appeared, then you can specify that version instead if you wish.) Do not make any other change in these notices. Once this change is made in a given copy, it is irreversible for that copy, so the ordinary GNU General Public License applies to all subsequent copies and derivative works made from that copy. This option is useful when you wish to copy part of the code of the Library into a program that is not a library. 4. You may copy and distribute the Library (or a portion or derivative of it, under Section 2) in object code or executable form under the terms of Sections 1 and 2 above provided that you accompany it with the complete corresponding machine-readable source code, which must be distributed under the terms of Sections 1 and 2 above on a medium customarily used for software interchange. If distribution of object code is made by offering access to copy from a designated place, then offering equivalent access to copy the source code from the same place satisfies the requirement to distribute the source code, even though third parties are not compelled to copy the source along with the object code. 5. A program that contains no derivative of any portion of the Library, but is designed to work with the Library by being compiled or linked with it, is called a "work that uses the Library". Such a work, in isolation, is not a derivative work of the Library, and therefore falls outside the scope of this License. However, linking a "work that uses the Library" with the Library creates an executable that is a derivative of the Library (because it contains portions of the Library), rather than a "work that uses the library". The executable is therefore covered by this License. Section 6 states terms for distribution of such executables. When a "work that uses the Library" uses material from a header file that is part of the Library, the object code for the work may be a derivative work of the Library even though the source code is not. Whether this is true is especially significant if the work can be linked without the Library, or if the work is itself a library. The threshold for this to be true is not precisely defined by law. If such an object file uses only numerical parameters, data structure layouts and accessors, and small macros and small inline functions (ten lines or less in length), then the use of the object file is unrestricted, regardless of whether it is legally a derivative work. (Executables containing this object code plus portions of the Library will still fall under Section 6.) Otherwise, if the work is a derivative of the Library, you may distribute the object code for the work under the terms of Section 6. Any executables containing that work also fall under Section 6, whether or not they are linked directly with the Library itself. 6. As an exception to the Sections above, you may also combine or link a "work that uses the Library" with the Library to produce a work containing portions of the Library, and distribute that work under terms of your choice, provided that the terms permit modification of the work for the customer's own use and reverse engineering for debugging such modifications. You must give prominent notice with each copy of the work that the Library is used in it and that the Library and its use are covered by this License. You must supply a copy of this License. If the work during execution displays copyright notices, you must include the copyright notice for the Library among them, as well as a reference directing the user to the copy of this License. Also, you must do one of these things: a) Accompany the work with the complete corresponding machine-readable source code for the Library including whatever changes were used in the work (which must be distributed under Sections 1 and 2 above); and, if the work is an executable linked with the Library, with the complete machine-readable "work that uses the Library", as object code and/or source code, so that the user can modify the Library and then relink to produce a modified executable containing the modified Library. (It is understood that the user who changes the contents of definitions files in the Library will not necessarily be able to recompile the application to use the modified definitions.) b) Use a suitable shared library mechanism for linking with the Library. A suitable mechanism is one that (1) uses at run time a copy of the library already present on the user's computer system, rather than copying library functions into the executable, and (2) will operate properly with a modified version of the library, if the user installs one, as long as the modified version is interface-compatible with the version that the work was made with. c) Accompany the work with a written offer, valid for at least three years, to give the same user the materials specified in Subsection 6a, above, for a charge no more than the cost of performing this distribution. d) If distribution of the work is made by offering access to copy from a designated place, offer equivalent access to copy the above specified materials from the same place. e) Verify that the user has already received a copy of these materials or that you have already sent this user a copy. For an executable, the required form of the "work that uses the Library" must include any data and utility programs needed for reproducing the executable from it. However, as a special exception, the materials to be distributed need not include anything that is normally distributed (in either source or binary form) with the major components (compiler, kernel, and so on) of the operating system on which the executable runs, unless that component itself accompanies the executable. It may happen that this requirement contradicts the license restrictions of other proprietary libraries that do not normally accompany the operating system. Such a contradiction means you cannot use both them and the Library together in an executable that you distribute. 7. You may place library facilities that are a work based on the Library side-by-side in a single library together with other library facilities not covered by this License, and distribute such a combined library, provided that the separate distribution of the work based on the Library and of the other library facilities is otherwise permitted, and provided that you do these two things: a) Accompany the combined library with a copy of the same work based on the Library, uncombined with any other library facilities. This must be distributed under the terms of the Sections above. b) Give prominent notice with the combined library of the fact that part of it is a work based on the Library, and explaining where to find the accompanying uncombined form of the same work. 8. You may not copy, modify, sublicense, link with, or distribute the Library except as expressly provided under this License. Any attempt otherwise to copy, modify, sublicense, link with, or distribute the Library is void, and will automatically terminate your rights under this License. However, parties who have received copies, or rights, from you under this License will not have their licenses terminated so long as such parties remain in full compliance. 9. You are not required to accept this License, since you have not signed it. However, nothing else grants you permission to modify or distribute the Library or its derivative works. These actions are prohibited by law if you do not accept this License. Therefore, by modifying or distributing the Library (or any work based on the Library), you indicate your acceptance of this License to do so, and all its terms and conditions for copying, distributing or modifying the Library or works based on it. 10. Each time you redistribute the Library (or any work based on the Library), the recipient automatically receives a license from the original licensor to copy, distribute, link with or modify the Library subject to these terms and conditions. You may not impose any further restrictions on the recipients' exercise of the rights granted herein. You are not responsible for enforcing compliance by third parties with this License. 11. If, as a consequence of a court judgment or allegation of patent infringement or for any other reason (not limited to patent issues), conditions are imposed on you (whether by court order, agreement or otherwise) that contradict the conditions of this License, they do not excuse you from the conditions of this License. If you cannot distribute so as to satisfy simultaneously your obligations under this License and any other pertinent obligations, then as a consequence you may not distribute the Library at all. For example, if a patent license would not permit royalty-free redistribution of the Library by all those who receive copies directly or indirectly through you, then the only way you could satisfy both it and this License would be to refrain entirely from distribution of the Library. If any portion of this section is held invalid or unenforceable under any particular circumstance, the balance of the section is intended to apply, and the section as a whole is intended to apply in other circumstances. It is not the purpose of this section to induce you to infringe any patents or other property right claims or to contest validity of any such claims; this section has the sole purpose of protecting the integrity of the free software distribution system which is implemented by public license practices. Many people have made generous contributions to the wide range of software distributed through that system in reliance on consistent application of that system; it is up to the author/donor to decide if he or she is willing to distribute software through any other system and a licensee cannot impose that choice. This section is intended to make thoroughly clear what is believed to be a consequence of the rest of this License. 12. If the distribution and/or use of the Library is restricted in certain countries either by patents or by copyrighted interfaces, the original copyright holder who places the Library under this License may add an explicit geographical distribution limitation excluding those countries, so that distribution is permitted only in or among countries not thus excluded. In such case, this License incorporates the limitation as if written in the body of this License. 13. The Free Software Foundation may publish revised and/or new versions of the Lesser General Public License from time to time. Such new versions will be similar in spirit to the present version, but may differ in detail to address new problems or concerns. Each version is given a distinguishing version number. If the Library specifies a version number of this License which applies to it and "any later version", you have the option of following the terms and conditions either of that version or of any later version published by the Free Software Foundation. If the Library does not specify a license version number, you may choose any version ever published by the Free Software Foundation. 14. If you wish to incorporate parts of the Library into other free programs whose distribution conditions are incompatible with these, write to the author to ask for permission. For software which is copyrighted by the Free Software Foundation, write to the Free Software Foundation; we sometimes make exceptions for this. Our decision will be guided by the two goals of preserving the free status of all derivatives of our free software and of promoting the sharing and reuse of software generally. NO WARRANTY 15. BECAUSE THE LIBRARY IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY FOR THE LIBRARY, TO THE EXTENT PERMITTED BY APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES PROVIDE THE LIBRARY "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE LIBRARY IS WITH YOU. SHOULD THE LIBRARY PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION. 16. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR REDISTRIBUTE THE LIBRARY AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE USE OR INABILITY TO USE THE LIBRARY (INCLUDING BUT NOT LIMITED TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD PARTIES OR A FAILURE OF THE LIBRARY TO OPERATE WITH ANY OTHER SOFTWARE), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES. END OF TERMS AND CONDITIONS How to Apply These Terms to Your New Libraries If you develop a new library, and you want it to be of the greatest possible use to the public, we recommend making it free software that everyone can redistribute and change. You can do so by permitting redistribution under these terms (or, alternatively, under the terms of the ordinary General Public License). To apply these terms, attach the following notices to the library. It is safest to attach them to the start of each source file to most effectively convey the exclusion of warranty; and each file should have at least the "copyright" line and a pointer to where the full notice is found. Copyright (C) This library is free software; you can redistribute it and/or modify it under the terms of the GNU Lesser General Public License as published by the Free Software Foundation; either version 2.1 of the License, or (at your option) any later version. This library is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public License for more details. You should have received a copy of the GNU Lesser General Public License along with this library; if not, write to the Free Software Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA Also add information on how to contact you by electronic and paper mail. You should also get your employer (if you work as a programmer) or your school, if any, to sign a "copyright disclaimer" for the library, if necessary. Here is a sample; alter the names: Yoyodyne, Inc., hereby disclaims all copyright interest in the library `Frob' (a library for tweaking knobs) written by James Random Hacker. , 1 April 1990 Ty Coon, President of Vice That's all there is to it! php-utf-8-1.2.1/README.md000066400000000000000000000107411252061617700145340ustar00rootroot00000000000000[![PHPCI](http://phpci.corpsee.com/build-status/image/2?branch=master&label=PHPCI&style=flat-square)](http://phpci.corpsee.com/build-status/view/2?branch=master) [![Travis](https://img.shields.io/travis/corpsee/php-utf-8/master.svg?label=Travis&style=flat-square)](https://travis-ci.org/corpsee/php-utf-8?branch=master) [![Latest Version](https://img.shields.io/packagist/v/corpsee/php-utf-8.svg?label=Version&style=flat-square)](https://packagist.org/packages/corpsee/php-utf-8) [![Total downloads](https://img.shields.io/packagist/dt/corpsee/php-utf-8.svg?label=Downloads&style=flat-square)](https://packagist.org/packages/corpsee/php-utf-8) [![License](https://img.shields.io/packagist/l/corpsee/php-utf-8.svg?label=License&style=flat-square)](https://packagist.org/packages/corpsee/php-utf-8) [![SensioLabs Insight](https://img.shields.io/sensiolabs/i/f348ff6a-40e9-4259-af1f-e88f5f9c588d.svg?label=Insight&style=flat-square)](https://insight.sensiolabs.com/projects/f348ff6a-40e9-4259-af1f-e88f5f9c588d) PHP-UTF-8 ========= This is fork of the [FSX/php-utf8][8] library. It was created because the author of origin library doesn`t support it. php-utf8 is a UTF-8 aware library of functions mirroring PHP's own string functions. Does not require PHP mbstring extension though will use it, if found, for a (small) performance gain. The project was initially on sourceforge where it died due to lack of development and support. This project has been forked and moved to github.com so that many more people can actually contribute with more ease. Use the [issue tracker][1] here on github.com, to post about problems and feature requests. Please feel free to fork and get back to us with fork requests for optimizations and new features. Documentation & Usage Information --------------------------------- Using the php-utf-8 library is quite easy. Just include the `php-utf8.php` and any additional functions that you may need from the `functions` folder. Sample Code: ```php // get the core functions included ... require('php-utf8_path/php-utf8.php'); // ... and any other functions/*.php or utils/*.php files you may need. require('php-utf8_path/functions/trim.php'); ``` Make sure that you are confident about using the library by reading [Character Sets / Character Encoding Issues][2] and [Handling UTF-8 with PHP][3]. Use these functions **only** if you really need them & you understand **why** you need to use them. In particular, do not blindly replace all use of PHP's string functions which functions found here. Most of the time you will not need to, and you will be introducing a significant performance overhead to your application. Most of the functions here are not operating *defensively*, mainly for performance reasons. For example there is no extensive parameter checking and it is assumed that they are fed with well formed UTF-8. This is particularly relevant when is comes to catching badly formed UTF-8. You should screen input on the *outer perimeter* with help from functions in the `utils/validation.php` and `utils/bad.php` files. Throughout the library **all** ASCII characters (*control characters included*) are treated as valid throughout the library. Make sure you take the appropriate measures before outputting into XML since it can become ill-formed with some control characters. [more info][5] Licensing --------- The initial code of php-utf-8 is published under LGPL. Please find a copy of the license in the LICENSE file. Parts of the code in this library come from other places, under different licenses. The authors involved have been contacted (see below). Attribution for which code came from elsewhere can be found in the source code itself. * Andreas Gohr / Chris Smith of Dokuwiki. *There is a fair degree of collaboration/exchange of ideas and code between [Dokuwiki's UTF-8 library][6] and phputf8. Although Dokuwiki is released under GPL, its UTF-8 library is released under LGPL, hence no conflict with phputf8* * Henri Sivonen ([site][7]) *has also given permission for his code to be released under the terms of the LGPL. He ported a Unicode / UTF-8 converter from the Mozilla codebase to PHP, which is re-used in php-utf-8.* [1]: https://github.com/corpsee/php-utf-8/issues [2]: http://www.phpwact.org/php/i18n/charsets [3]: http://www.phpwact.org/php/i18n/utf-8 [4]: http://www.phpwact.org/php/i18n/utf-8 [5]: http://hsivonen.iki.fi/producing-xml/#controlchar [6]: http://dev.splitbrain.org/view/darcs/dokuwiki/inc/utf8.php [7]: http://hsivonen.iki.fi/php-utf8/ [8]: https://github.com/FSX/php-utf8 php-utf-8-1.2.1/composer.json000066400000000000000000000020671252061617700160010ustar00rootroot00000000000000{ "name": "corpsee/php-utf-8", "type": "library", "description": "A library for UTF-8 in PHP providing UTF-8 aware functions to mirror PHP's own string functions. The library doesn't require PHP mbstring extension although, if found, it will use it to gain performance.", "keywords": ["utf8", "utf-8", "unicode", "i18n"], "homepage": "https://github.com/corpsee/php-utf-8", "license": "LGPL-2.1", "authors": [ { "name": "Frank Smit", "email": "frank@61924.nl", "homepage": "http://61924.nl", "role": "Developer" }, { "name": "Corpsee", "email": "poisoncorpsee@gmail.com", "homepage": "http://corpsee.com", "role": "Developer" }], "require": { "php": ">=5.4.0", "lib-pcre": "*" }, "require-dev": { "phpunit/phpunit": "4.*" }, "suggest": { "ext-mbstring": "Use Mbstring for best performance" }, "autoload": { "files": ["src/init.php"] } } php-utf-8-1.2.1/composer.lock000066400000000000000000001021121252061617700157500ustar00rootroot00000000000000{ "_readme": [ "This file locks the dependencies of your project to a known state", "Read more about it at http://getcomposer.org/doc/01-basic-usage.md#composer-lock-the-lock-file", "This file is @generated automatically" ], "hash": "2f5d1700f747ffce748f9a378e187f40", "packages": [], "packages-dev": [ { "name": "doctrine/instantiator", "version": "1.0.4", "source": { "type": "git", "url": "https://github.com/doctrine/instantiator.git", "reference": "f976e5de371104877ebc89bd8fecb0019ed9c119" }, "dist": { "type": "zip", "url": "https://api.github.com/repos/doctrine/instantiator/zipball/f976e5de371104877ebc89bd8fecb0019ed9c119", "reference": "f976e5de371104877ebc89bd8fecb0019ed9c119", "shasum": "" }, "require": { "php": ">=5.3,<8.0-DEV" }, "require-dev": { "athletic/athletic": "~0.1.8", "ext-pdo": "*", "ext-phar": "*", "phpunit/phpunit": "~4.0", "squizlabs/php_codesniffer": "2.0.*@ALPHA" }, "type": "library", "extra": { "branch-alias": { "dev-master": "1.0.x-dev" } }, "autoload": { "psr-0": { "Doctrine\\Instantiator\\": "src" } }, "notification-url": "https://packagist.org/downloads/", "license": [ "MIT" ], "authors": [ { "name": "Marco Pivetta", "email": "ocramius@gmail.com", "homepage": "http://ocramius.github.com/" } ], "description": "A small, lightweight utility to instantiate objects in PHP without invoking their constructors", "homepage": "https://github.com/doctrine/instantiator", "keywords": [ "constructor", "instantiate" ], "time": "2014-10-13 12:58:55" }, { "name": "phpdocumentor/reflection-docblock", "version": "2.0.4", "source": { "type": "git", "url": "https://github.com/phpDocumentor/ReflectionDocBlock.git", "reference": "d68dbdc53dc358a816f00b300704702b2eaff7b8" }, "dist": { "type": "zip", "url": "https://api.github.com/repos/phpDocumentor/ReflectionDocBlock/zipball/d68dbdc53dc358a816f00b300704702b2eaff7b8", "reference": "d68dbdc53dc358a816f00b300704702b2eaff7b8", "shasum": "" }, "require": { "php": ">=5.3.3" }, "require-dev": { "phpunit/phpunit": "~4.0" }, "suggest": { "dflydev/markdown": "~1.0", "erusev/parsedown": "~1.0" }, "type": "library", "extra": { "branch-alias": { "dev-master": "2.0.x-dev" } }, "autoload": { "psr-0": { "phpDocumentor": [ "src/" ] } }, "notification-url": "https://packagist.org/downloads/", "license": [ "MIT" ], "authors": [ { "name": "Mike van Riel", "email": "mike.vanriel@naenius.com" } ], "time": "2015-02-03 12:10:50" }, { "name": "phpspec/prophecy", "version": "v1.4.1", "source": { "type": "git", "url": "https://github.com/phpspec/prophecy.git", "reference": "3132b1f44c7bf2ec4c7eb2d3cb78fdeca760d373" }, "dist": { "type": "zip", "url": "https://api.github.com/repos/phpspec/prophecy/zipball/3132b1f44c7bf2ec4c7eb2d3cb78fdeca760d373", "reference": "3132b1f44c7bf2ec4c7eb2d3cb78fdeca760d373", "shasum": "" }, "require": { "doctrine/instantiator": "^1.0.2", "phpdocumentor/reflection-docblock": "~2.0", "sebastian/comparator": "~1.1" }, "require-dev": { "phpspec/phpspec": "~2.0" }, "type": "library", "extra": { "branch-alias": { "dev-master": "1.4.x-dev" } }, "autoload": { "psr-0": { "Prophecy\\": "src/" } }, "notification-url": "https://packagist.org/downloads/", "license": [ "MIT" ], "authors": [ { "name": "Konstantin Kudryashov", "email": "ever.zet@gmail.com", "homepage": "http://everzet.com" }, { "name": "Marcello Duarte", "email": "marcello.duarte@gmail.com" } ], "description": "Highly opinionated mocking framework for PHP 5.3+", "homepage": "https://github.com/phpspec/prophecy", "keywords": [ "Double", "Dummy", "fake", "mock", "spy", "stub" ], "time": "2015-04-27 22:15:08" }, { "name": "phpunit/php-code-coverage", "version": "2.0.16", "source": { "type": "git", "url": "https://github.com/sebastianbergmann/php-code-coverage.git", "reference": "934fd03eb6840508231a7f73eb8940cf32c3b66c" }, "dist": { "type": "zip", "url": "https://api.github.com/repos/sebastianbergmann/php-code-coverage/zipball/934fd03eb6840508231a7f73eb8940cf32c3b66c", "reference": "934fd03eb6840508231a7f73eb8940cf32c3b66c", "shasum": "" }, "require": { "php": ">=5.3.3", "phpunit/php-file-iterator": "~1.3", "phpunit/php-text-template": "~1.2", "phpunit/php-token-stream": "~1.3", "sebastian/environment": "~1.0", "sebastian/version": "~1.0" }, "require-dev": { "ext-xdebug": ">=2.1.4", "phpunit/phpunit": "~4" }, "suggest": { "ext-dom": "*", "ext-xdebug": ">=2.2.1", "ext-xmlwriter": "*" }, "type": "library", "extra": { "branch-alias": { "dev-master": "2.0.x-dev" } }, "autoload": { "classmap": [ "src/" ] }, "notification-url": "https://packagist.org/downloads/", "license": [ "BSD-3-Clause" ], "authors": [ { "name": "Sebastian Bergmann", "email": "sb@sebastian-bergmann.de", "role": "lead" } ], "description": "Library that provides collection, processing, and rendering functionality for PHP code coverage information.", "homepage": "https://github.com/sebastianbergmann/php-code-coverage", "keywords": [ "coverage", "testing", "xunit" ], "time": "2015-04-11 04:35:00" }, { "name": "phpunit/php-file-iterator", "version": "1.4.0", "source": { "type": "git", "url": "https://github.com/sebastianbergmann/php-file-iterator.git", "reference": "a923bb15680d0089e2316f7a4af8f437046e96bb" }, "dist": { "type": "zip", "url": "https://api.github.com/repos/sebastianbergmann/php-file-iterator/zipball/a923bb15680d0089e2316f7a4af8f437046e96bb", "reference": "a923bb15680d0089e2316f7a4af8f437046e96bb", "shasum": "" }, "require": { "php": ">=5.3.3" }, "type": "library", "extra": { "branch-alias": { "dev-master": "1.4.x-dev" } }, "autoload": { "classmap": [ "src/" ] }, "notification-url": "https://packagist.org/downloads/", "license": [ "BSD-3-Clause" ], "authors": [ { "name": "Sebastian Bergmann", "email": "sb@sebastian-bergmann.de", "role": "lead" } ], "description": "FilterIterator implementation that filters files based on a list of suffixes.", "homepage": "https://github.com/sebastianbergmann/php-file-iterator/", "keywords": [ "filesystem", "iterator" ], "time": "2015-04-02 05:19:05" }, { "name": "phpunit/php-text-template", "version": "1.2.0", "source": { "type": "git", "url": "https://github.com/sebastianbergmann/php-text-template.git", "reference": "206dfefc0ffe9cebf65c413e3d0e809c82fbf00a" }, "dist": { "type": "zip", "url": "https://api.github.com/repos/sebastianbergmann/php-text-template/zipball/206dfefc0ffe9cebf65c413e3d0e809c82fbf00a", "reference": "206dfefc0ffe9cebf65c413e3d0e809c82fbf00a", "shasum": "" }, "require": { "php": ">=5.3.3" }, "type": "library", "autoload": { "classmap": [ "Text/" ] }, "notification-url": "https://packagist.org/downloads/", "include-path": [ "" ], "license": [ "BSD-3-Clause" ], "authors": [ { "name": "Sebastian Bergmann", "email": "sb@sebastian-bergmann.de", "role": "lead" } ], "description": "Simple template engine.", "homepage": "https://github.com/sebastianbergmann/php-text-template/", "keywords": [ "template" ], "time": "2014-01-30 17:20:04" }, { "name": "phpunit/php-timer", "version": "1.0.5", "source": { "type": "git", "url": "https://github.com/sebastianbergmann/php-timer.git", "reference": "19689d4354b295ee3d8c54b4f42c3efb69cbc17c" }, "dist": { "type": "zip", "url": "https://api.github.com/repos/sebastianbergmann/php-timer/zipball/19689d4354b295ee3d8c54b4f42c3efb69cbc17c", "reference": "19689d4354b295ee3d8c54b4f42c3efb69cbc17c", "shasum": "" }, "require": { "php": ">=5.3.3" }, "type": "library", "autoload": { "classmap": [ "PHP/" ] }, "notification-url": "https://packagist.org/downloads/", "include-path": [ "" ], "license": [ "BSD-3-Clause" ], "authors": [ { "name": "Sebastian Bergmann", "email": "sb@sebastian-bergmann.de", "role": "lead" } ], "description": "Utility class for timing", "homepage": "https://github.com/sebastianbergmann/php-timer/", "keywords": [ "timer" ], "time": "2013-08-02 07:42:54" }, { "name": "phpunit/php-token-stream", "version": "1.4.1", "source": { "type": "git", "url": "https://github.com/sebastianbergmann/php-token-stream.git", "reference": "eab81d02569310739373308137284e0158424330" }, "dist": { "type": "zip", "url": "https://api.github.com/repos/sebastianbergmann/php-token-stream/zipball/eab81d02569310739373308137284e0158424330", "reference": "eab81d02569310739373308137284e0158424330", "shasum": "" }, "require": { "ext-tokenizer": "*", "php": ">=5.3.3" }, "require-dev": { "phpunit/phpunit": "~4.2" }, "type": "library", "extra": { "branch-alias": { "dev-master": "1.4-dev" } }, "autoload": { "classmap": [ "src/" ] }, "notification-url": "https://packagist.org/downloads/", "license": [ "BSD-3-Clause" ], "authors": [ { "name": "Sebastian Bergmann", "email": "sebastian@phpunit.de" } ], "description": "Wrapper around PHP's tokenizer extension.", "homepage": "https://github.com/sebastianbergmann/php-token-stream/", "keywords": [ "tokenizer" ], "time": "2015-04-08 04:46:07" }, { "name": "phpunit/phpunit", "version": "4.6.6", "source": { "type": "git", "url": "https://github.com/sebastianbergmann/phpunit.git", "reference": "3afe303d873a4d64c62ef84de491b97b006fbdac" }, "dist": { "type": "zip", "url": "https://api.github.com/repos/sebastianbergmann/phpunit/zipball/3afe303d873a4d64c62ef84de491b97b006fbdac", "reference": "3afe303d873a4d64c62ef84de491b97b006fbdac", "shasum": "" }, "require": { "ext-dom": "*", "ext-json": "*", "ext-pcre": "*", "ext-reflection": "*", "ext-spl": "*", "php": ">=5.3.3", "phpspec/prophecy": "~1.3,>=1.3.1", "phpunit/php-code-coverage": "~2.0,>=2.0.11", "phpunit/php-file-iterator": "~1.4", "phpunit/php-text-template": "~1.2", "phpunit/php-timer": "~1.0", "phpunit/phpunit-mock-objects": "~2.3", "sebastian/comparator": "~1.1", "sebastian/diff": "~1.2", "sebastian/environment": "~1.2", "sebastian/exporter": "~1.2", "sebastian/global-state": "~1.0", "sebastian/version": "~1.0", "symfony/yaml": "~2.1|~3.0" }, "suggest": { "phpunit/php-invoker": "~1.1" }, "bin": [ "phpunit" ], "type": "library", "extra": { "branch-alias": { "dev-master": "4.6.x-dev" } }, "autoload": { "classmap": [ "src/" ] }, "notification-url": "https://packagist.org/downloads/", "license": [ "BSD-3-Clause" ], "authors": [ { "name": "Sebastian Bergmann", "email": "sebastian@phpunit.de", "role": "lead" } ], "description": "The PHP Unit Testing framework.", "homepage": "https://phpunit.de/", "keywords": [ "phpunit", "testing", "xunit" ], "time": "2015-04-29 15:18:52" }, { "name": "phpunit/phpunit-mock-objects", "version": "2.3.1", "source": { "type": "git", "url": "https://github.com/sebastianbergmann/phpunit-mock-objects.git", "reference": "74ffb87f527f24616f72460e54b595f508dccb5c" }, "dist": { "type": "zip", "url": "https://api.github.com/repos/sebastianbergmann/phpunit-mock-objects/zipball/74ffb87f527f24616f72460e54b595f508dccb5c", "reference": "74ffb87f527f24616f72460e54b595f508dccb5c", "shasum": "" }, "require": { "doctrine/instantiator": "~1.0,>=1.0.2", "php": ">=5.3.3", "phpunit/php-text-template": "~1.2" }, "require-dev": { "phpunit/phpunit": "~4.4" }, "suggest": { "ext-soap": "*" }, "type": "library", "extra": { "branch-alias": { "dev-master": "2.3.x-dev" } }, "autoload": { "classmap": [ "src/" ] }, "notification-url": "https://packagist.org/downloads/", "license": [ "BSD-3-Clause" ], "authors": [ { "name": "Sebastian Bergmann", "email": "sb@sebastian-bergmann.de", "role": "lead" } ], "description": "Mock Object library for PHPUnit", "homepage": "https://github.com/sebastianbergmann/phpunit-mock-objects/", "keywords": [ "mock", "xunit" ], "time": "2015-04-02 05:36:41" }, { "name": "sebastian/comparator", "version": "1.1.1", "source": { "type": "git", "url": "https://github.com/sebastianbergmann/comparator.git", "reference": "1dd8869519a225f7f2b9eb663e225298fade819e" }, "dist": { "type": "zip", "url": "https://api.github.com/repos/sebastianbergmann/comparator/zipball/1dd8869519a225f7f2b9eb663e225298fade819e", "reference": "1dd8869519a225f7f2b9eb663e225298fade819e", "shasum": "" }, "require": { "php": ">=5.3.3", "sebastian/diff": "~1.2", "sebastian/exporter": "~1.2" }, "require-dev": { "phpunit/phpunit": "~4.4" }, "type": "library", "extra": { "branch-alias": { "dev-master": "1.1.x-dev" } }, "autoload": { "classmap": [ "src/" ] }, "notification-url": "https://packagist.org/downloads/", "license": [ "BSD-3-Clause" ], "authors": [ { "name": "Jeff Welch", "email": "whatthejeff@gmail.com" }, { "name": "Volker Dusch", "email": "github@wallbash.com" }, { "name": "Bernhard Schussek", "email": "bschussek@2bepublished.at" }, { "name": "Sebastian Bergmann", "email": "sebastian@phpunit.de" } ], "description": "Provides the functionality to compare PHP values for equality", "homepage": "http://www.github.com/sebastianbergmann/comparator", "keywords": [ "comparator", "compare", "equality" ], "time": "2015-01-29 16:28:08" }, { "name": "sebastian/diff", "version": "1.3.0", "source": { "type": "git", "url": "https://github.com/sebastianbergmann/diff.git", "reference": "863df9687835c62aa423a22412d26fa2ebde3fd3" }, "dist": { "type": "zip", "url": "https://api.github.com/repos/sebastianbergmann/diff/zipball/863df9687835c62aa423a22412d26fa2ebde3fd3", "reference": "863df9687835c62aa423a22412d26fa2ebde3fd3", "shasum": "" }, "require": { "php": ">=5.3.3" }, "require-dev": { "phpunit/phpunit": "~4.2" }, "type": "library", "extra": { "branch-alias": { "dev-master": "1.3-dev" } }, "autoload": { "classmap": [ "src/" ] }, "notification-url": "https://packagist.org/downloads/", "license": [ "BSD-3-Clause" ], "authors": [ { "name": "Kore Nordmann", "email": "mail@kore-nordmann.de" }, { "name": "Sebastian Bergmann", "email": "sebastian@phpunit.de" } ], "description": "Diff implementation", "homepage": "http://www.github.com/sebastianbergmann/diff", "keywords": [ "diff" ], "time": "2015-02-22 15:13:53" }, { "name": "sebastian/environment", "version": "1.2.2", "source": { "type": "git", "url": "https://github.com/sebastianbergmann/environment.git", "reference": "5a8c7d31914337b69923db26c4221b81ff5a196e" }, "dist": { "type": "zip", "url": "https://api.github.com/repos/sebastianbergmann/environment/zipball/5a8c7d31914337b69923db26c4221b81ff5a196e", "reference": "5a8c7d31914337b69923db26c4221b81ff5a196e", "shasum": "" }, "require": { "php": ">=5.3.3" }, "require-dev": { "phpunit/phpunit": "~4.4" }, "type": "library", "extra": { "branch-alias": { "dev-master": "1.3.x-dev" } }, "autoload": { "classmap": [ "src/" ] }, "notification-url": "https://packagist.org/downloads/", "license": [ "BSD-3-Clause" ], "authors": [ { "name": "Sebastian Bergmann", "email": "sebastian@phpunit.de" } ], "description": "Provides functionality to handle HHVM/PHP environments", "homepage": "http://www.github.com/sebastianbergmann/environment", "keywords": [ "Xdebug", "environment", "hhvm" ], "time": "2015-01-01 10:01:08" }, { "name": "sebastian/exporter", "version": "1.2.0", "source": { "type": "git", "url": "https://github.com/sebastianbergmann/exporter.git", "reference": "84839970d05254c73cde183a721c7af13aede943" }, "dist": { "type": "zip", "url": "https://api.github.com/repos/sebastianbergmann/exporter/zipball/84839970d05254c73cde183a721c7af13aede943", "reference": "84839970d05254c73cde183a721c7af13aede943", "shasum": "" }, "require": { "php": ">=5.3.3", "sebastian/recursion-context": "~1.0" }, "require-dev": { "phpunit/phpunit": "~4.4" }, "type": "library", "extra": { "branch-alias": { "dev-master": "1.2.x-dev" } }, "autoload": { "classmap": [ "src/" ] }, "notification-url": "https://packagist.org/downloads/", "license": [ "BSD-3-Clause" ], "authors": [ { "name": "Jeff Welch", "email": "whatthejeff@gmail.com" }, { "name": "Volker Dusch", "email": "github@wallbash.com" }, { "name": "Bernhard Schussek", "email": "bschussek@2bepublished.at" }, { "name": "Sebastian Bergmann", "email": "sebastian@phpunit.de" }, { "name": "Adam Harvey", "email": "aharvey@php.net" } ], "description": "Provides the functionality to export PHP variables for visualization", "homepage": "http://www.github.com/sebastianbergmann/exporter", "keywords": [ "export", "exporter" ], "time": "2015-01-27 07:23:06" }, { "name": "sebastian/global-state", "version": "1.0.0", "source": { "type": "git", "url": "https://github.com/sebastianbergmann/global-state.git", "reference": "c7428acdb62ece0a45e6306f1ae85e1c05b09c01" }, "dist": { "type": "zip", "url": "https://api.github.com/repos/sebastianbergmann/global-state/zipball/c7428acdb62ece0a45e6306f1ae85e1c05b09c01", "reference": "c7428acdb62ece0a45e6306f1ae85e1c05b09c01", "shasum": "" }, "require": { "php": ">=5.3.3" }, "require-dev": { "phpunit/phpunit": "~4.2" }, "suggest": { "ext-uopz": "*" }, "type": "library", "extra": { "branch-alias": { "dev-master": "1.0-dev" } }, "autoload": { "classmap": [ "src/" ] }, "notification-url": "https://packagist.org/downloads/", "license": [ "BSD-3-Clause" ], "authors": [ { "name": "Sebastian Bergmann", "email": "sebastian@phpunit.de" } ], "description": "Snapshotting of global state", "homepage": "http://www.github.com/sebastianbergmann/global-state", "keywords": [ "global state" ], "time": "2014-10-06 09:23:50" }, { "name": "sebastian/recursion-context", "version": "1.0.0", "source": { "type": "git", "url": "https://github.com/sebastianbergmann/recursion-context.git", "reference": "3989662bbb30a29d20d9faa04a846af79b276252" }, "dist": { "type": "zip", "url": "https://api.github.com/repos/sebastianbergmann/recursion-context/zipball/3989662bbb30a29d20d9faa04a846af79b276252", "reference": "3989662bbb30a29d20d9faa04a846af79b276252", "shasum": "" }, "require": { "php": ">=5.3.3" }, "require-dev": { "phpunit/phpunit": "~4.4" }, "type": "library", "extra": { "branch-alias": { "dev-master": "1.0.x-dev" } }, "autoload": { "classmap": [ "src/" ] }, "notification-url": "https://packagist.org/downloads/", "license": [ "BSD-3-Clause" ], "authors": [ { "name": "Jeff Welch", "email": "whatthejeff@gmail.com" }, { "name": "Sebastian Bergmann", "email": "sebastian@phpunit.de" }, { "name": "Adam Harvey", "email": "aharvey@php.net" } ], "description": "Provides functionality to recursively process PHP variables", "homepage": "http://www.github.com/sebastianbergmann/recursion-context", "time": "2015-01-24 09:48:32" }, { "name": "sebastian/version", "version": "1.0.5", "source": { "type": "git", "url": "https://github.com/sebastianbergmann/version.git", "reference": "ab931d46cd0d3204a91e1b9a40c4bc13032b58e4" }, "dist": { "type": "zip", "url": "https://api.github.com/repos/sebastianbergmann/version/zipball/ab931d46cd0d3204a91e1b9a40c4bc13032b58e4", "reference": "ab931d46cd0d3204a91e1b9a40c4bc13032b58e4", "shasum": "" }, "type": "library", "autoload": { "classmap": [ "src/" ] }, "notification-url": "https://packagist.org/downloads/", "license": [ "BSD-3-Clause" ], "authors": [ { "name": "Sebastian Bergmann", "email": "sebastian@phpunit.de", "role": "lead" } ], "description": "Library that helps with managing the version number of Git-hosted PHP projects", "homepage": "https://github.com/sebastianbergmann/version", "time": "2015-02-24 06:35:25" }, { "name": "symfony/yaml", "version": "v2.6.6", "target-dir": "Symfony/Component/Yaml", "source": { "type": "git", "url": "https://github.com/symfony/Yaml.git", "reference": "174f009ed36379a801109955fc5a71a49fe62dd4" }, "dist": { "type": "zip", "url": "https://api.github.com/repos/symfony/Yaml/zipball/174f009ed36379a801109955fc5a71a49fe62dd4", "reference": "174f009ed36379a801109955fc5a71a49fe62dd4", "shasum": "" }, "require": { "php": ">=5.3.3" }, "require-dev": { "symfony/phpunit-bridge": "~2.7" }, "type": "library", "extra": { "branch-alias": { "dev-master": "2.6-dev" } }, "autoload": { "psr-0": { "Symfony\\Component\\Yaml\\": "" } }, "notification-url": "https://packagist.org/downloads/", "license": [ "MIT" ], "authors": [ { "name": "Symfony Community", "homepage": "http://symfony.com/contributors" }, { "name": "Fabien Potencier", "email": "fabien@symfony.com" } ], "description": "Symfony Yaml Component", "homepage": "http://symfony.com", "time": "2015-03-30 15:54:10" } ], "aliases": [], "minimum-stability": "stable", "stability-flags": [], "prefer-stable": false, "prefer-lowest": false, "platform": { "php": ">=5.4.0", "lib-pcre": "*" }, "platform-dev": [] } php-utf-8-1.2.1/mbstring.xml000066400000000000000000000011741252061617700156240ustar00rootroot00000000000000 ./tests/cases php-utf-8-1.2.1/native.xml000066400000000000000000000011711252061617700152620ustar00rootroot00000000000000 ./tests/cases php-utf-8-1.2.1/phpci.yml000066400000000000000000000006131252061617700151000ustar00rootroot00000000000000build_settings: ignore: - "vendor" - "tests" setup: composer: action: "install" test: php_unit: config: - "native.xml" - "mbstring.xml" php_mess_detector: allow_failures: true php_cpd: allow_failures: true php_loc: allow_failures: true php_parallel_lint: allow_failures: true php-utf-8-1.2.1/src/000077500000000000000000000000001252061617700140415ustar00rootroot00000000000000php-utf-8-1.2.1/src/core/000077500000000000000000000000001252061617700147715ustar00rootroot00000000000000php-utf-8-1.2.1/src/core/mbstring.php000066400000000000000000000075721252061617700173420ustar00rootroot00000000000000 * * @param string $str * * @return integer */ function len($str) { return strlen(utf8_decode(bad_clean($str))); } /** * UTF-8 aware alternative to strpos. * * Find position of first occurrence of a string. * This will get alot slower if offset is used. * * @see http://www.php.net/strpos * @see utf8_strlen * @see utf8_substr * * @param string $str haystack * @param string $needle needle (you should validate this with utf8_is_valid) * @param integer|false $offset offset in characters (from left) * * @return mixed integer position or false on failure */ function pos($str, $needle, $offset = false) { if ($offset === false) { $ar = explode($needle, $str, 2); //if (count($ar) > 1) if (isset($ar[1])) { return len($ar[0]); } return false; } if (!is_int($offset)) { trigger_error('utf8_strpos: Offset must be an integer', E_USER_ERROR); return false; } $str = sub($str, $offset); if (($pos = pos($str, $needle)) !== false) { return $pos + $offset; } return false; } /** * UTF-8 aware alternative to strrpos. * * Find position of last occurrence of a char in a string. * This will get alot slower if offset is used * * @see http://www.php.net/strrpos * @see utf8_substr * @see utf8_strlen * * @param string $str haystack * @param string $needle needle (you should validate this with utf8_is_valid) * @param integer|false $offset (optional) offset (from left) * * @return mixed integer position or false on failure */ function rpos($str, $needle, $offset = false) { if ($offset === false) { $ar = explode($needle, $str); //if (count($ar) > 1) if (isset($ar[1])) { // Pop off the end of the string where the last match was made array_pop($ar); $str = implode($needle, $ar); return len($str); } return false; } if (!is_int($offset)) { trigger_error('utf8_strrpos expects parameter 3 to be long', E_USER_WARNING); return false; } $str = sub($str, $offset); if (($pos = rpos($str, $needle)) !== false) { return $pos + $offset; } return false; } /** * UTF-8 aware alternative to substr. * * Return part of a string given character offset (and optionally length) * * Compared to substr, if offset or length are not integers, this version will * not complain but rather massages them into an integer. * * Note on returned values: substr documentation states false can be returned * in some cases (e.g. offset > string length) mb_substr never returns false, * it will return an empty string instead. This adopts the mb_substr approach. * * Note on implementation: PCRE only supports repetitions of less than 65536, * in order to accept up to MAXINT values for offset and length, we'll repeat * a group of 65535 characters when needed. * * Note on implementation: calculating the number of characters in the string * is a relatively expensive operation, so we only carry it out when necessary. * It isn't necessary for +ve offsets and no specified length * * @author Chris Smith * * @param string $str * @param integer $offset number of UTF-8 characters offset (from left) * @param integer|false $length (optional) length in UTF-8 characters from offset * * @return mixed string or false if failure */ function sub($str, $offset, $length = false) { // Generates E_NOTICE for PHP4 objects, but not PHP5 objects $str = (string)$str; $offset = (int)$offset; if ($length) { $length = (int)$length; } // Handle trivial cases if ($length === 0) { return ''; } if ($offset < 0 && $length < 0 && $length < $offset) { return ''; } // Normalise negative offsets (we could use a tail // anchored pattern, but they are horribly slow!) if ($offset < 0) { // See notes $strlen = len($str); $offset = $strlen + $offset; if ($offset < 0) { $offset = 0; } } $offset_pattern = ''; $length_pattern = ''; // Establish a pattern for offset, a // non-captured group equal in length to offset if ($offset > 0) { $ox = (int)($offset / 65535); $oy = $offset % 65535; if ($ox) { $offset_pattern = '(?:.{65535}){' . $ox . '}'; } $offset_pattern = '^(?:' . $offset_pattern . '.{' . $oy . '})'; } else { $offset_pattern = '^'; } // Establish a pattern for length if (!$length) { $length_pattern = '(.*)$'; // The rest of the string } else { // See notes if (!isset($strlen)) { $strlen = len($str); } // Another trivial case if ($offset > $strlen) { return ''; } if ($length > 0) { // Reduce any length that would go passed the end of the string $length = min($strlen - $offset, $length); $lx = (int)($length / 65535); $ly = $length % 65535; // Negative length requires a captured group of length characters if ($lx) { $length_pattern = '(?:.{65535}){' . $lx . '}'; } $length_pattern = '(' . $length_pattern . '.{' . $ly . '})'; } elseif ($length < 0) { if ($length < ($offset - $strlen)) { return ''; } $lx = (int)((-$length) / 65535); $ly = (-$length) % 65535; // Negative length requires ... capture everything except a group of // -length characters anchored at the tail-end of the string if ($lx) { $length_pattern = '(?:.{65535}){' . $lx . '}'; } $length_pattern = '(.*)(?:' . $length_pattern . '.{' . $ly . '})$'; } } if (!preg_match('#' . $offset_pattern . $length_pattern . '#us', $str, $match)) { return ''; } return $match[1]; } /** * UTF-8 aware alternative to strtolower. * * Make a string lowercase. * * The concept of a characters "case" only exists is some alphabets such as * Latin, Greek, Cyrillic, Armenian and archaic Georgian - it does not exist in * the Chinese alphabet, for example. See Unicode Standard Annex #21: Case Mappings. * * @author Andreas Gohr * @see http://www.php.net/strtolower * @see utf8_to_unicode * @see utf8_from_unicode * @see http://www.unicode.org/reports/tr21/tr21-5.html * @see http://dev.splitbrain.org/view/darcs/dokuwiki/inc/utf8.php * * @param string $string * * @return mixed either string in lowercase or FALSE is UTF-8 invalid */ function to_lower($string) { static $UTF8_UPPER_TO_LOWER; $uni = to_unicode($string); if (!$uni) { return false; } if (!$UTF8_UPPER_TO_LOWER) { $UTF8_UPPER_TO_LOWER = array( 0x0041 => 0x0061, 0x03A6 => 0x03C6, 0x0162 => 0x0163, 0x00C5 => 0x00E5, 0x0042 => 0x0062, 0x0139 => 0x013A, 0x00C1 => 0x00E1, 0x0141 => 0x0142, 0x038E => 0x03CD, 0x0100 => 0x0101, 0x0490 => 0x0491, 0x0394 => 0x03B4, 0x015A => 0x015B, 0x0044 => 0x0064, 0x0393 => 0x03B3, 0x00D4 => 0x00F4, 0x042A => 0x044A, 0x0419 => 0x0439, 0x0112 => 0x0113, 0x041C => 0x043C, 0x015E => 0x015F, 0x0143 => 0x0144, 0x00CE => 0x00EE, 0x040E => 0x045E, 0x042F => 0x044F, 0x039A => 0x03BA, 0x0154 => 0x0155, 0x0049 => 0x0069, 0x0053 => 0x0073, 0x1E1E => 0x1E1F, 0x0134 => 0x0135, 0x0427 => 0x0447, 0x03A0 => 0x03C0, 0x0418 => 0x0438, 0x00D3 => 0x00F3, 0x0420 => 0x0440, 0x0404 => 0x0454, 0x0415 => 0x0435, 0x0429 => 0x0449, 0x014A => 0x014B, 0x0411 => 0x0431, 0x0409 => 0x0459, 0x1E02 => 0x1E03, 0x00D6 => 0x00F6, 0x00D9 => 0x00F9, 0x004E => 0x006E, 0x0401 => 0x0451, 0x03A4 => 0x03C4, 0x0423 => 0x0443, 0x015C => 0x015D, 0x0403 => 0x0453, 0x03A8 => 0x03C8, 0x0158 => 0x0159, 0x0047 => 0x0067, 0x00C4 => 0x00E4, 0x0386 => 0x03AC, 0x0389 => 0x03AE, 0x0166 => 0x0167, 0x039E => 0x03BE, 0x0164 => 0x0165, 0x0116 => 0x0117, 0x0108 => 0x0109, 0x0056 => 0x0076, 0x00DE => 0x00FE, 0x0156 => 0x0157, 0x00DA => 0x00FA, 0x1E60 => 0x1E61, 0x1E82 => 0x1E83, 0x00C2 => 0x00E2, 0x0118 => 0x0119, 0x0145 => 0x0146, 0x0050 => 0x0070, 0x0150 => 0x0151, 0x042E => 0x044E, 0x0128 => 0x0129, 0x03A7 => 0x03C7, 0x013D => 0x013E, 0x0422 => 0x0442, 0x005A => 0x007A, 0x0428 => 0x0448, 0x03A1 => 0x03C1, 0x1E80 => 0x1E81, 0x016C => 0x016D, 0x00D5 => 0x00F5, 0x0055 => 0x0075, 0x0176 => 0x0177, 0x00DC => 0x00FC, 0x1E56 => 0x1E57, 0x03A3 => 0x03C3, 0x041A => 0x043A, 0x004D => 0x006D, 0x016A => 0x016B, 0x0170 => 0x0171, 0x0424 => 0x0444, 0x00CC => 0x00EC, 0x0168 => 0x0169, 0x039F => 0x03BF, 0x004B => 0x006B, 0x00D2 => 0x00F2, 0x00C0 => 0x00E0, 0x0414 => 0x0434, 0x03A9 => 0x03C9, 0x1E6A => 0x1E6B, 0x00C3 => 0x00E3, 0x042D => 0x044D, 0x0416 => 0x0436, 0x01A0 => 0x01A1, 0x010C => 0x010D, 0x011C => 0x011D, 0x00D0 => 0x00F0, 0x013B => 0x013C, 0x040F => 0x045F, 0x040A => 0x045A, 0x00C8 => 0x00E8, 0x03A5 => 0x03C5, 0x0046 => 0x0066, 0x00DD => 0x00FD, 0x0043 => 0x0063, 0x021A => 0x021B, 0x00CA => 0x00EA, 0x0399 => 0x03B9, 0x0179 => 0x017A, 0x00CF => 0x00EF, 0x01AF => 0x01B0, 0x0045 => 0x0065, 0x039B => 0x03BB, 0x0398 => 0x03B8, 0x039C => 0x03BC, 0x040C => 0x045C, 0x041F => 0x043F, 0x042C => 0x044C, 0x00DE => 0x00FE, 0x00D0 => 0x00F0, 0x1EF2 => 0x1EF3, 0x0048 => 0x0068, 0x00CB => 0x00EB, 0x0110 => 0x0111, 0x0413 => 0x0433, 0x012E => 0x012F, 0x00C6 => 0x00E6, 0x0058 => 0x0078, 0x0160 => 0x0161, 0x016E => 0x016F, 0x0391 => 0x03B1, 0x0407 => 0x0457, 0x0172 => 0x0173, 0x0178 => 0x00FF, 0x004F => 0x006F, 0x041B => 0x043B, 0x0395 => 0x03B5, 0x0425 => 0x0445, 0x0120 => 0x0121, 0x017D => 0x017E, 0x017B => 0x017C, 0x0396 => 0x03B6, 0x0392 => 0x03B2, 0x0388 => 0x03AD, 0x1E84 => 0x1E85, 0x0174 => 0x0175, 0x0051 => 0x0071, 0x0417 => 0x0437, 0x1E0A => 0x1E0B, 0x0147 => 0x0148, 0x0104 => 0x0105, 0x0408 => 0x0458, 0x014C => 0x014D, 0x00CD => 0x00ED, 0x0059 => 0x0079, 0x010A => 0x010B, 0x038F => 0x03CE, 0x0052 => 0x0072, 0x0410 => 0x0430, 0x0405 => 0x0455, 0x0402 => 0x0452, 0x0126 => 0x0127, 0x0136 => 0x0137, 0x012A => 0x012B, 0x038A => 0x03AF, 0x042B => 0x044B, 0x004C => 0x006C, 0x0397 => 0x03B7, 0x0124 => 0x0125, 0x0218 => 0x0219, 0x00DB => 0x00FB, 0x011E => 0x011F, 0x041E => 0x043E, 0x1E40 => 0x1E41, 0x039D => 0x03BD, 0x0106 => 0x0107, 0x03AB => 0x03CB, 0x0426 => 0x0446, 0x00DE => 0x00FE, 0x00C7 => 0x00E7, 0x03AA => 0x03CA, 0x0421 => 0x0441, 0x0412 => 0x0432, 0x010E => 0x010F, 0x00D8 => 0x00F8, 0x0057 => 0x0077, 0x011A => 0x011B, 0x0054 => 0x0074, 0x004A => 0x006A, 0x040B => 0x045B, 0x0406 => 0x0456, 0x0102 => 0x0103, 0x039B => 0x03BB, 0x00D1 => 0x00F1, 0x041D => 0x043D, 0x038C => 0x03CC, 0x00C9 => 0x00E9, 0x00D0 => 0x00F0, 0x0407 => 0x0457, 0x0122 => 0x0123 ); } $cnt = count($uni); for ($i = 0; $i < $cnt; $i++) { if (isset($UTF8_UPPER_TO_LOWER[$uni[$i]])) { $uni[$i] = $UTF8_UPPER_TO_LOWER[$uni[$i]]; } } return from_unicode($uni); } /** * UTF-8 aware alternative to strtoupper. * * Make a string uppercase. * * The concept of a characters "case" only exists is some alphabets such as * Latin, Greek, Cyrillic, Armenian and archaic Georgian - it does not exist in * the Chinese alphabet, for example. See Unicode Standard Annex #21: Case Mappings. * * @author Andreas Gohr * @see http://www.php.net/strtoupper * @see utf8_to_unicode * @see utf8_from_unicode * @see http://www.unicode.org/reports/tr21/tr21-5.html * @see http://dev.splitbrain.org/view/darcs/dokuwiki/inc/utf8.php * * @param string $string * * @return mixed either string in lowercase or FALSE is UTF-8 invalid */ function to_upper($string) { static $UTF8_LOWER_TO_UPPER; $uni = to_unicode($string); if (!$uni) { return false; } if (!$UTF8_LOWER_TO_UPPER) { $UTF8_LOWER_TO_UPPER = array( 0x0061 => 0x0041, 0x03C6 => 0x03A6, 0x0163 => 0x0162, 0x00E5 => 0x00C5, 0x0062 => 0x0042, 0x013A => 0x0139, 0x00E1 => 0x00C1, 0x0142 => 0x0141, 0x03CD => 0x038E, 0x0101 => 0x0100, 0x0491 => 0x0490, 0x03B4 => 0x0394, 0x015B => 0x015A, 0x0064 => 0x0044, 0x03B3 => 0x0393, 0x00F4 => 0x00D4, 0x044A => 0x042A, 0x0439 => 0x0419, 0x0113 => 0x0112, 0x043C => 0x041C, 0x015F => 0x015E, 0x0144 => 0x0143, 0x00EE => 0x00CE, 0x045E => 0x040E, 0x044F => 0x042F, 0x03BA => 0x039A, 0x0155 => 0x0154, 0x0069 => 0x0049, 0x0073 => 0x0053, 0x1E1F => 0x1E1E, 0x0135 => 0x0134, 0x0447 => 0x0427, 0x03C0 => 0x03A0, 0x0438 => 0x0418, 0x00F3 => 0x00D3, 0x0440 => 0x0420, 0x0454 => 0x0404, 0x0435 => 0x0415, 0x0449 => 0x0429, 0x014B => 0x014A, 0x0431 => 0x0411, 0x0459 => 0x0409, 0x1E03 => 0x1E02, 0x00F6 => 0x00D6, 0x00F9 => 0x00D9, 0x006E => 0x004E, 0x0451 => 0x0401, 0x03C4 => 0x03A4, 0x0443 => 0x0423, 0x015D => 0x015C, 0x0453 => 0x0403, 0x03C8 => 0x03A8, 0x0159 => 0x0158, 0x0067 => 0x0047, 0x00E4 => 0x00C4, 0x03AC => 0x0386, 0x03AE => 0x0389, 0x0167 => 0x0166, 0x03BE => 0x039E, 0x0165 => 0x0164, 0x0117 => 0x0116, 0x0109 => 0x0108, 0x0076 => 0x0056, 0x00FE => 0x00DE, 0x0157 => 0x0156, 0x00FA => 0x00DA, 0x1E61 => 0x1E60, 0x1E83 => 0x1E82, 0x00E2 => 0x00C2, 0x0119 => 0x0118, 0x0146 => 0x0145, 0x0070 => 0x0050, 0x0151 => 0x0150, 0x044E => 0x042E, 0x0129 => 0x0128, 0x03C7 => 0x03A7, 0x013E => 0x013D, 0x0442 => 0x0422, 0x007A => 0x005A, 0x0448 => 0x0428, 0x03C1 => 0x03A1, 0x1E81 => 0x1E80, 0x016D => 0x016C, 0x00F5 => 0x00D5, 0x0075 => 0x0055, 0x0177 => 0x0176, 0x00FC => 0x00DC, 0x1E57 => 0x1E56, 0x03C3 => 0x03A3, 0x043A => 0x041A, 0x006D => 0x004D, 0x016B => 0x016A, 0x0171 => 0x0170, 0x0444 => 0x0424, 0x00EC => 0x00CC, 0x0169 => 0x0168, 0x03BF => 0x039F, 0x006B => 0x004B, 0x00F2 => 0x00D2, 0x00E0 => 0x00C0, 0x0434 => 0x0414, 0x03C9 => 0x03A9, 0x1E6B => 0x1E6A, 0x00E3 => 0x00C3, 0x044D => 0x042D, 0x0436 => 0x0416, 0x01A1 => 0x01A0, 0x010D => 0x010C, 0x011D => 0x011C, 0x00F0 => 0x00D0, 0x013C => 0x013B, 0x045F => 0x040F, 0x045A => 0x040A, 0x00E8 => 0x00C8, 0x03C5 => 0x03A5, 0x0066 => 0x0046, 0x00FD => 0x00DD, 0x0063 => 0x0043, 0x021B => 0x021A, 0x00EA => 0x00CA, 0x03B9 => 0x0399, 0x017A => 0x0179, 0x00EF => 0x00CF, 0x01B0 => 0x01AF, 0x0065 => 0x0045, 0x03BB => 0x039B, 0x03B8 => 0x0398, 0x03BC => 0x039C, 0x045C => 0x040C, 0x043F => 0x041F, 0x044C => 0x042C, 0x00FE => 0x00DE, 0x00F0 => 0x00D0, 0x1EF3 => 0x1EF2, 0x0068 => 0x0048, 0x00EB => 0x00CB, 0x0111 => 0x0110, 0x0433 => 0x0413, 0x012F => 0x012E, 0x00E6 => 0x00C6, 0x0078 => 0x0058, 0x0161 => 0x0160, 0x016F => 0x016E, 0x03B1 => 0x0391, 0x0457 => 0x0407, 0x0173 => 0x0172, 0x00FF => 0x0178, 0x006F => 0x004F, 0x043B => 0x041B, 0x03B5 => 0x0395, 0x0445 => 0x0425, 0x0121 => 0x0120, 0x017E => 0x017D, 0x017C => 0x017B, 0x03B6 => 0x0396, 0x03B2 => 0x0392, 0x03AD => 0x0388, 0x1E85 => 0x1E84, 0x0175 => 0x0174, 0x0071 => 0x0051, 0x0437 => 0x0417, 0x1E0B => 0x1E0A, 0x0148 => 0x0147, 0x0105 => 0x0104, 0x0458 => 0x0408, 0x014D => 0x014C, 0x00ED => 0x00CD, 0x0079 => 0x0059, 0x010B => 0x010A, 0x03CE => 0x038F, 0x0072 => 0x0052, 0x0430 => 0x0410, 0x0455 => 0x0405, 0x0452 => 0x0402, 0x0127 => 0x0126, 0x0137 => 0x0136, 0x012B => 0x012A, 0x03AF => 0x038A, 0x044B => 0x042B, 0x006C => 0x004C, 0x03B7 => 0x0397, 0x0125 => 0x0124, 0x0219 => 0x0218, 0x00FB => 0x00DB, 0x011F => 0x011E, 0x043E => 0x041E, 0x1E41 => 0x1E40, 0x03BD => 0x039D, 0x0107 => 0x0106, 0x03CB => 0x03AB, 0x0446 => 0x0426, 0x00FE => 0x00DE, 0x00E7 => 0x00C7, 0x03CA => 0x03AA, 0x0441 => 0x0421, 0x0432 => 0x0412, 0x010F => 0x010E, 0x00F8 => 0x00D8, 0x0077 => 0x0057, 0x011B => 0x011A, 0x0074 => 0x0054, 0x006A => 0x004A, 0x045B => 0x040B, 0x0456 => 0x0406, 0x0103 => 0x0102, 0x03BB => 0x039B, 0x00F1 => 0x00D1, 0x043D => 0x041D, 0x03CC => 0x038C, 0x00E9 => 0x00C9, 0x00F0 => 0x00D0, 0x0457 => 0x0407, 0x0123 => 0x0122 ); } $cnt = count($uni); for ($i = 0; $i < $cnt; $i++) { if (isset($UTF8_LOWER_TO_UPPER[$uni[$i]])) { $uni[$i] = $UTF8_LOWER_TO_UPPER[$uni[$i]]; } } return from_unicode($uni); } // Is needed by utf8_ucwords_callback() require_once PHP_UTF_8_DIR . '/functions/substr_replace.php'; /** * UTF-8 aware alternative to ucwords. * * Uppercase the first character of each word in a string * * @see http://php.net/manual/en/function.ucwords.php * @uses utf8_substr_replace * @uses utf8_strtoupper * * @param string * * @return string with first char of each word uppercase */ function ucwords($str) { // Note: [\x0c\x09\x0b\x0a\x0d\x20] matches; // Form feeds, horizontal tabs, vertical tabs, linefeeds and carriage returns // This corresponds to the definition of a "word" defined at http://www.php.net/ucwords $pattern = '/(^|([\x0c\x09\x0b\x0a\x0d\x20]+))([^\x0c\x09\x0b\x0a\x0d\x20]{1})[^\x0c\x09\x0b\x0a\x0d\x20]*/u'; return preg_replace_callback($pattern, function ($match) { $leadingws = $match[2]; $ucfirst = to_upper($match[3]); $ucword = sub_replace(ltrim($match[0]), $ucfirst, 0, 1); return $leadingws . $ucword; }, $str); } php-utf-8-1.2.1/src/functions/000077500000000000000000000000001252061617700160515ustar00rootroot00000000000000php-utf-8-1.2.1/src/functions/ord.php000066400000000000000000000041361252061617700173520ustar00rootroot00000000000000= 0 && $ord0 <= 127) { return $ord0; } if (!isset($chr[1])) { trigger_error('Short sequence - at least 2 bytes expected, only 1 seen'); return false; } $ord1 = \ord($chr[1]); if ($ord0 >= 192 && $ord0 <= 223) { return ($ord0 - 192) * 64 + ($ord1 - 128); } if (!isset($chr[2])) { trigger_error('Short sequence - at least 3 bytes expected, only 2 seen'); return false; } $ord2 = \ord($chr[2]); if ($ord0 >= 224 && $ord0 <= 239) { return ($ord0 - 224) * 4096 + ($ord1 - 128) * 64 + ($ord2 - 128); } if (!isset($chr[3])) { trigger_error('Short sequence - at least 4 bytes expected, only 3 seen'); return false; } $ord3 = \ord($chr[3]); if ($ord0 >= 240 && $ord0 <= 247) { return ($ord0 - 240) * 262144 + ($ord1 - 128) * 4096 + ($ord2 - 128) * 64 + ($ord3 - 128); } if (!isset($chr[4])) { trigger_error('Short sequence - at least 5 bytes expected, only 4 seen'); return false; } $ord4 = \ord($chr[4]); if ($ord0 >= 248 && $ord0 <= 251) { return ($ord0 - 248) * 16777216 + ($ord1 - 128) * 262144 + ($ord2 - 128) * 4096 + ($ord3 - 128) * 64 + ($ord4 - 128); } if (!isset($chr[5])) { trigger_error('Short sequence - at least 6 bytes expected, only 5 seen'); return false; } if ($ord0 >= 252 && $ord0 <= 253) { return ($ord0 - 252) * 1073741824 + ($ord1 - 128) * 16777216 + ($ord2 - 128) * 262144 + ($ord3 - 128) * 4096 + ($ord4 - 128) * 64 + (\ord($chr[5]) - 128); } if ($ord0 >= 254 && $ord0 <= 255) { trigger_error('Invalid UTF-8 with surrogate ordinal ' . $ord0); return false; } } php-utf-8-1.2.1/src/functions/str_ireplace.php000066400000000000000000000035561252061617700212470ustar00rootroot00000000000000 * @package php-utf-8 * @subpackage functions * @see http://www.php.net/str_pad * @uses utf8_substr * * @param string $input * @param int $length * @param string $pad_str * @param int $type (same constants as str_pad) * * @return string */ function pad($input, $length, $pad_str = ' ', $type = STR_PAD_RIGHT) { $input_len = len($input); if ($length <= $input_len) { return $input; } $pad_str_len = len($pad_str); $pad_len = $length - $input_len; if ($type == STR_PAD_RIGHT) { $repeat_times = ceil($pad_len / $pad_str_len); return sub($input . str_repeat($pad_str, $repeat_times), 0, $length); } if ($type == STR_PAD_LEFT) { $repeat_times = ceil($pad_len / $pad_str_len); return sub(str_repeat($pad_str, $repeat_times), 0, floor($pad_len)) . $input; } if ($type == STR_PAD_BOTH) { $pad_len /= 2; $pad_amount_left = floor($pad_len); $pad_amount_right = ceil($pad_len); $repeat_times_left = ceil($pad_amount_left / $pad_str_len); $repeat_times_right = ceil($pad_amount_right / $pad_str_len); $padding_left = sub(str_repeat($pad_str, $repeat_times_left), 0, $pad_amount_left); $padding_right = sub(str_repeat($pad_str, $repeat_times_right), 0, $pad_amount_right); return $padding_left . $input . $padding_right; } trigger_error('utf8_str_pad: Unknown padding type (' . $type . ')', E_USER_ERROR); } php-utf-8-1.2.1/src/functions/str_split.php000066400000000000000000000013451252061617700206100ustar00rootroot00000000000000 * @see http://www.php.net/ltrim * @see http://dev.splitbrain.org/view/darcs/dokuwiki/inc/utf8.php * * @param string $str * @param string $charlist * * @return string */ function ltrim($str, $charlist = '') { if (empty($charlist)) { return \ltrim($str); } // Quote charlist for use in a characterclass $charlist = preg_replace('!([\\\\\\-\\]\\[/^])!', '\\\${1}', $charlist); return preg_replace('/^[' . $charlist . ']+/u', '', $str); } /** * UTF-8 aware replacement for rtrim(). * * @author Andreas Gohr * @see http://www.php.net/rtrim * @see http://dev.splitbrain.org/view/darcs/dokuwiki/inc/utf8.php * * @param string $str * @param string $charlist * * @return string */ function rtrim($str, $charlist = '') { if (empty($charlist)) { return \rtrim($str); } // Quote charlist for use in a characterclass $charlist = preg_replace('!([\\\\\\-\\]\\[/^])!', '\\\${1}', $charlist); return preg_replace('/[' . $charlist . ']+$/u', '', $str); } /** * UTF-8 aware replacement for trim(). * * @author Andreas Gohr * @see http://www.php.net/trim * @see http://dev.splitbrain.org/view/darcs/dokuwiki/inc/utf8.php * * @param string $str * @param string $charlist * * @return string */ function trim($str, $charlist = '') { if (empty($charlist)) { return \trim($str); } return ltrim(rtrim($str, $charlist), $charlist); } php-utf-8-1.2.1/src/functions/ucfirst.php000066400000000000000000000012421252061617700202400ustar00rootroot00000000000000 $width) { $w = split($w); do { $result[] = implode('', array_slice($w, 0, $width)); $line = implode('', $w = array_slice($w, $width)); $line_len = $wLen -= $width; } while ($wLen > $width); $w = implode('', $w); } $line = $w; $line_len = $wLen; } } } $line && $result[] = $line; return implode($break, $result); } php-utf-8-1.2.1/src/init.php000066400000000000000000000025601252061617700155200ustar00rootroot00000000000000 * if ( utf8_is_ascii($someString) ) { * // It's just ASCII - use the native PHP version * $someString = strtolower($someString); * } else { * $someString = utf8_strtolower($someString); * } * * * Optionally the check can be performed with the control characters included. * * @param string $str * @param boolean $check_ctrl_chars_too * * @return boolean TRUE if it's all ASCII * @see utf8_is_ascii_ctrl */ function is_ascii($str, $check_ctrl_chars_too = false) { if (empty($str)) { return true; } $pattern = '/(?:[^\x00-\x7F])/'; if ($check_ctrl_chars_too) { $pattern = '/[^\x09\x0A\x0D\x20-\x7E]/'; } return (preg_match($pattern, $str) !== 1); } /** * Strip out all non-7bit ASCII bytes and, optionally, ASCII device control codes. * * If you need to transmit a string to system which you know can only support 7bit ASCII, you could use this function. * * Optionally strip out device control codes in the ASCII range which are not permitted in XML. * * Note that this leaves multi-byte characters untouched - it only removes device control codes * * @see http://hsivonen.iki.fi/producing-xml/#controlchar * * @param string $str * @param string $mode * * @return string control codes removed */ function to_ascii($str, $mode = 'non_ascii') { static $modes; if (!$modes) { $modes = array( 'non_ascii' => '^([\x00-\x7F]+)|([^\x00-\x7F]+)', 'ctrl_chars' => '^([^\x00-\x08\x0B\x0C\x0E-\x1F\x7F]+)|([\x00-\x08\x0B\x0C\x0E-\x1F\x7F]+)', 'both' => '^([\x09\x0A\x0D\x20-\x7E]+)|([^\x09\x0A\x0D\x20-\x7E]+)', ); } ob_start(); while (preg_match('/' . $modes[$mode] . '/S', $str, $matches)) { if (!isset($matches[2])) { echo $matches[0]; } $str = substr($str, strlen($matches[0])); } return ob_get_clean(); } /** * Replace accented UTF-8 characters by unaccented ASCII-7 "equivalents". * * The purpose of this function is to replace characters commonly found in Latin * alphabets with something more or less equivalent from the ASCII range. * This can be useful for converting a UTF-8 to something ready for a filename, * for example. * Following the use of this function, you would probably also pass the string * through utf8_strip_non_ascii to clean out any other non-ASCII chars * * Use the optional parameter to just deaccent lower ($case = -1) or * upper ($case = 1) letters. Default is to deaccent both cases ($case = 0) * * For a more complete implementation of transliteration, see the utf8_to_ascii * package available from the phputf8 project downloads: http://prdownloads.sourceforge.net/phputf8 * * @param string $str UTF-8 string * @param string $mode (optional) -1 lowercase only, +1 uppercase only, 1 both cases string UTF-8 with * accented characters replaced by ASCII chars * * @return string accented chars replaced with ascii equivalents * @author Andreas Gohr */ function accents_to_ascii($str, $mode = 'both') { static $accents; if (empty($str)) { return ''; } if (!$accents) { $accents = array( 'lower' => array( 'à' => 'a', 'ô' => 'o', 'ď' => 'd', 'ḟ' => 'f', 'ë' => 'e', 'š' => 's', 'ơ' => 'o', 'ß' => 'ss', 'ă' => 'a', 'ř' => 'r', 'ț' => 't', 'ň' => 'n', 'ā' => 'a', 'ķ' => 'k', 'ŝ' => 's', 'ỳ' => 'y', 'ņ' => 'n', 'ĺ' => 'l', 'ħ' => 'h', 'ṗ' => 'p', 'ó' => 'o', 'ú' => 'u', 'ě' => 'e', 'é' => 'e', 'ç' => 'c', 'ẁ' => 'w', 'ċ' => 'c', 'õ' => 'o', 'ṡ' => 's', 'ø' => 'o', 'ģ' => 'g', 'ŧ' => 't', 'ș' => 's', 'ė' => 'e', 'ĉ' => 'c', 'ś' => 's', 'î' => 'i', 'ű' => 'u', 'ć' => 'c', 'ę' => 'e', 'ŵ' => 'w', 'ṫ' => 't', 'ū' => 'u', 'č' => 'c', 'ö' => 'oe', 'è' => 'e', 'ŷ' => 'y', 'ą' => 'a', 'ł' => 'l', 'ų' => 'u', 'ů' => 'u', 'ş' => 's', 'ğ' => 'g', 'ļ' => 'l', 'ƒ' => 'f', 'ž' => 'z', 'ẃ' => 'w', 'ḃ' => 'b', 'å' => 'a', 'ì' => 'i', 'ï' => 'i', 'ḋ' => 'd', 'ť' => 't', 'ŗ' => 'r', 'ä' => 'ae', 'í' => 'i', 'ŕ' => 'r', 'ê' => 'e', 'ü' => 'ue', 'ò' => 'o', 'ē' => 'e', 'ñ' => 'n', 'ń' => 'n', 'ĥ' => 'h', 'ĝ' => 'g', 'đ' => 'd', 'ĵ' => 'j', 'ÿ' => 'y', 'ũ' => 'u', 'ŭ' => 'u', 'ư' => 'u', 'ţ' => 't', 'ý' => 'y', 'ő' => 'o', 'â' => 'a', 'ľ' => 'l', 'ẅ' => 'w', 'ż' => 'z', 'ī' => 'i', 'ã' => 'a', 'ġ' => 'g', 'ṁ' => 'm', 'ō' => 'o', 'ĩ' => 'i', 'ù' => 'u', 'į' => 'i', 'ź' => 'z', 'á' => 'a', 'û' => 'u', 'þ' => 'th', 'ð' => 'dh', 'æ' => 'ae', 'µ' => 'u', 'ĕ' => 'e', ), 'upper' => array( 'À' => 'A', 'Ô' => 'O', 'Ď' => 'D', 'Ḟ' => 'F', 'Ë' => 'E', 'Š' => 'S', 'Ơ' => 'O', 'Ă' => 'A', 'Ř' => 'R', 'Ț' => 'T', 'Ň' => 'N', 'Ā' => 'A', 'Ķ' => 'K', 'Ŝ' => 'S', 'Ỳ' => 'Y', 'Ņ' => 'N', 'Ĺ' => 'L', 'Ħ' => 'H', 'Ṗ' => 'P', 'Ó' => 'O', 'Ú' => 'U', 'Ě' => 'E', 'É' => 'E', 'Ç' => 'C', 'Ẁ' => 'W', 'Ċ' => 'C', 'Õ' => 'O', 'Ṡ' => 'S', 'Ø' => 'O', 'Ģ' => 'G', 'Ŧ' => 'T', 'Ș' => 'S', 'Ė' => 'E', 'Ĉ' => 'C', 'Ś' => 'S', 'Î' => 'I', 'Ű' => 'U', 'Ć' => 'C', 'Ę' => 'E', 'Ŵ' => 'W', 'Ṫ' => 'T', 'Ū' => 'U', 'Č' => 'C', 'Ö' => 'Oe', 'È' => 'E', 'Ŷ' => 'Y', 'Ą' => 'A', 'Ł' => 'L', 'Ų' => 'U', 'Ů' => 'U', 'Ş' => 'S', 'Ğ' => 'G', 'Ļ' => 'L', 'Ƒ' => 'F', 'Ž' => 'Z', 'Ẃ' => 'W', 'Ḃ' => 'B', 'Å' => 'A', 'Ì' => 'I', 'Ï' => 'I', 'Ḋ' => 'D', 'Ť' => 'T', 'Ŗ' => 'R', 'Ä' => 'Ae', 'Í' => 'I', 'Ŕ' => 'R', 'Ê' => 'E', 'Ü' => 'Ue', 'Ò' => 'O', 'Ē' => 'E', 'Ñ' => 'N', 'Ń' => 'N', 'Ĥ' => 'H', 'Ĝ' => 'G', 'Đ' => 'D', 'Ĵ' => 'J', 'Ÿ' => 'Y', 'Ũ' => 'U', 'Ŭ' => 'U', 'Ư' => 'U', 'Ţ' => 'T', 'Ý' => 'Y', 'Ő' => 'O', 'Â' => 'A', 'Ľ' => 'L', 'Ẅ' => 'W', 'Ż' => 'Z', 'Ī' => 'I', 'Ã' => 'A', 'Ġ' => 'G', 'Ṁ' => 'M', 'Ō' => 'O', 'Ĩ' => 'I', 'Ù' => 'U', 'Į' => 'I', 'Ź' => 'Z', 'Á' => 'A', 'Û' => 'U', 'Þ' => 'Th', 'Ð' => 'Dh', 'Æ' => 'Ae', 'Ĕ' => 'E', ) ); } return strtr($str, ($mode == 'both') ? array_merge($accents['lower'], $accents['upper']) : $accents[$mode]); } php-utf-8-1.2.1/src/utils/bad.php000066400000000000000000000223251252061617700164440ustar00rootroot00000000000000 * * @param string $str UTF-8 encoded string * * @return mixed $i integer constant describing problem or FALSE if valid UTF-8 * @see utf8_bad_explain * @see http://hsivonen.iki.fi/php-utf8/ */ function bad_identify($str, &$i) { $mState = 0; // Cached expected number of octets after the current octet // until the beginning of the next UTF8 character sequence $mUcs4 = 0; // Cached Unicode character $mBytes = 1; // Cached expected number of octets in the current sequence $len = strlen($str); for ($i = 0; $i < $len; $i++) { $in = \ord($str{$i}); if ($mState == 0) { // When mState is zero we expect either a US-ASCII character or a multi-octet sequence. if (0 == (0x80 & ($in))) { // US-ASCII, pass straight through. $mBytes = 1; } elseif (0xC0 == (0xE0 & ($in))) { // First octet of 2 octet sequence $mUcs4 = ($in); $mUcs4 = ($mUcs4 & 0x1F) << 6; $mState = 1; $mBytes = 2; } elseif (0xE0 == (0xF0 & ($in))) { // First octet of 3 octet sequence $mUcs4 = ($in); $mUcs4 = ($mUcs4 & 0x0F) << 12; $mState = 2; $mBytes = 3; } elseif (0xF0 == (0xF8 & ($in))) { // First octet of 4 octet sequence $mUcs4 = ($in); $mUcs4 = ($mUcs4 & 0x07) << 18; $mState = 3; $mBytes = 4; } elseif (0xF8 == (0xFC & ($in))) { /* First octet of 5 octet sequence. * * This is illegal because the encoded codepoint must be either * (a) not the shortest form or * (b) outside the Unicode range of 0-0x10FFFF. */ return BAD_5OCTET; } elseif (0xFC == (0xFE & ($in))) { // First octet of 6 octet sequence, see comments for 5 octet sequence. return BAD_6OCTET; } else { // Current octet is neither in the US-ASCII range nor a legal first // octet of a multi-octet sequence. return BAD_SEQID; } } else { // When mState is non-zero, we expect a continuation of the multi-octet sequence if (0x80 == (0xC0 & ($in))) { // Legal continuation. $shift = ($mState - 1) * 6; $tmp = $in; $tmp = ($tmp & 0x0000003F) << $shift; $mUcs4 |= $tmp; /** * End of the multi-octet sequence. mUcs4 now contains the final * Unicode codepoint to be output */ if (0 == --$mState) { // From Unicode 3.1, non-shortest form is illegal if (((2 == $mBytes) && ($mUcs4 < 0x0080)) || ((3 == $mBytes) && ($mUcs4 < 0x0800)) || ((4 == $mBytes) && ($mUcs4 < 0x10000))) { return BAD_NONSHORT; } elseif (($mUcs4 & 0xFFFFF800) == 0xD800) // From Unicode 3.2, surrogate characters are illegal { return BAD_SURROGATE; } elseif ($mUcs4 > 0x10FFFF) // Codepoints outside the Unicode range are illegal { return BAD_UNIOUTRANGE; } // Initialize UTF8 cache $mState = 0; $mUcs4 = 0; $mBytes = 1; } } else { // ((0xC0 & (*in) != 0x80) && (mState != 0)) // Incomplete multi-octet sequence. $i--; return BAD_SEQINCOMPLETE; } } } // Incomplete multi-octet sequence if ($mState != 0) { $i--; return BAD_SEQINCOMPLETE; } // No bad octets found $i = null; return false; } /** * Takes a return code from utf8_bad_identify() are returns a message (in English) * explaining what the problem is. * * @param int $code return code from utf8_bad_identify * * @return mixed string message or FALSE if return code unknown * @see utf8_bad_identify */ function bad_explain($code) { static $errors; if (!$errors) { $errors = array( BAD_5OCTET => 'Five octet sequences are valid UTF-8 but are not supported by Unicode', BAD_6OCTET => 'Six octet sequences are valid UTF-8 but are not supported by Unicode', BAD_SEQID => 'Invalid octet for use as start of multi-byte UTF-8 sequence', BAD_NONSHORT => 'From Unicode 3.1, non-shortest form is illegal', BAD_SURROGATE => 'From Unicode 3.2, surrogate characters are illegal', BAD_UNIOUTRANGE => 'Codepoints outside the Unicode range are illegal', BAD_SEQINCOMPLETE => 'Incomplete multi-octet sequence' ); } if (isset($errors[$code])) { trigger_error('Unknown error code: ' . $errors[$code], E_USER_WARNING); } return false; } php-utf-8-1.2.1/src/utils/patterns.php000066400000000000000000000040371252061617700175560ustar00rootroot00000000000000 * * @param string string to locate index in * @param int (n times) * * @return mixed - int if only one input int, array if more, boolean TRUE if it's all ASCII */ function byte_position() { $args = func_get_args(); $str = array_shift($args); if (!is_string($str)) { return false; } $result = array(); $prev = array(0, 0); // Trivial byte index, character offset pair $i = locate_next_chr($str, 300); // Use a short piece of str to estimate bytes per character. $i (& $j) -> byte indexes into $str $c = strlen(utf8_decode(substr($str, 0, $i))); // $c -> character offset into $str // Deal with arguments from lowest to highest sort($args); foreach ($args as $offset) { // Sanity checks FIXME // 0 is an easy check if ($offset == 0) { $result[] = 0; continue; } // Ensure no endless looping $safety_valve = 50; do { if (($c - $prev[1]) == 0) { // Hack: gone past end of string $error = 0; $i = strlen($str); break; } $j = $i + (int)(($offset - $c) * ($i - $prev[0]) / ($c - $prev[1])); $j = locate_next_chr($str, $j); // Correct to utf8 character boundary $prev = array($i, $c); // Save the index, offset for use next iteration if ($j > $i) { $c += strlen(utf8_decode(substr($str, $i, $j - $i))); // Determine new character offset } else { $c -= strlen(utf8_decode(substr($str, $j, $i - $j))); // Ditto } $error = abs($c - $offset); $i = $j; // Ready for next time around } while (($error > 7) && --$safety_valve); // From 7 it is faster to iterate over the string if ($error && $error <= 7) { if ($c < $offset) { // Move up while ($error--) { $i = locate_next_chr($str, ++$i); } } else { // Move down while ($error--) { $i = locate_current_chr($str, --$i); } } // Ready for next arg $c = $offset; } $result[] = $i; } if (count($result) == 1) { return $result[0]; } return $result; } /** * Given a string and any byte index, returns the byte index of the start of the * current UTF-8 character, relative to supplied position. * * If the current character begins at the same place as the supplied byte index, * that byte index will be returned. Otherwise this function will step backwards, * looking for the index where curent UTF-8 character begins. * * @author Chris Smith * * @param string $str * @param int $idx byte index in the string * * @return int byte index of start of next UTF-8 character */ function locate_current_chr(&$str, $idx) { if ($idx <= 0) { return 0; } $limit = strlen($str); if ($idx >= $limit) { return $limit; } // Binary value for any byte after the first in a multi-byte UTF-8 character // will be like 10xxxxxx so & 0xC0 can be used to detect this kind // of byte - assuming well formed UTF-8 while ($idx && ((\ord($str[$idx]) & 0xC0) == 0x80)) { $idx--; } return $idx; } /** * Given a string and any byte index, returns the byte index of the start of the * next UTF-8 character, relative to supplied position. * * If the next character begins at the same place as the supplied byte index, * that byte index will be returned. * * @author Chris Smith * * @param string $str * @param int $idx byte index in the string * * @return int byte index of start of next UTF-8 character */ function locate_next_chr(&$str, $idx) { if ($idx <= 0) { return 0; } $limit = strlen($str); if ($idx >= $limit) { return $limit; } // Binary value for any byte after the first in a multi-byte UTF-8 character // will be like 10xxxxxx so & 0xC0 can be used to detect this kind // of byte - assuming well formed UTF-8 while (($idx < $limit) && ((\ord($str[$idx]) & 0xC0) == 0x80)) { $idx++; } return $idx; } php-utf-8-1.2.1/src/utils/specials.php000066400000000000000000000303031252061617700175140ustar00rootroot00000000000000 * * @param string $string The UTF8 string to strip of special chars * @param string $repl (optional) Replace special with this string * * @return string with common non-alphanumeric characters removed */ function strip_specials($string, $repl = '') { return preg_replace(specials_pattern(), $repl, $string); } php-utf-8-1.2.1/src/utils/unicode.php000066400000000000000000000206221252061617700173420ustar00rootroot00000000000000 0xFFFF. * Occurrances of the BOM are ignored. Surrogates are not allowed. * Returns false if the input string isn't a valid UTF-8 octet sequence and raises a PHP error at level E_USER_WARNING * Note: this function has been modified slightly in this library to trigger errors on encountering bad bytes * * @author * * @param string $str UTF-8 encoded string * * @return mixed array of unicode code points or FALSE if UTF-8 invalid * @see utf8_from_unicode * @see http://hsivonen.iki.fi/php-utf8/ */ function to_unicode($str) { $mState = 0; // Cached expected number of octets after the current octet // until the beginning of the next UTF8 character sequence $mUcs4 = 0; // Cached Unicode character $mBytes = 1; // Cached expected number of octets in the current sequence $out = array(); $len = strlen($str); for ($i = 0; $i < $len; $i++) { $in = \ord($str[$i]); if ($mState == 0) { // When mState is zero we expect either a US-ASCII character or a multi-octet sequence. if (0 == (0x80 & ($in))) { // US-ASCII, pass straight through. $out[] = $in; $mBytes = 1; } elseif (0xC0 == (0xE0 & ($in))) { // First octet of 2 octet sequence $mUcs4 = ($in); $mUcs4 = ($mUcs4 & 0x1F) << 6; $mState = 1; $mBytes = 2; } elseif (0xE0 == (0xF0 & ($in))) { // First octet of 3 octet sequence $mUcs4 = ($in); $mUcs4 = ($mUcs4 & 0x0F) << 12; $mState = 2; $mBytes = 3; } elseif (0xF0 == (0xF8 & ($in))) { // First octet of 4 octet sequence $mUcs4 = ($in); $mUcs4 = ($mUcs4 & 0x07) << 18; $mState = 3; $mBytes = 4; } elseif (0xF8 == (0xFC & ($in))) { /* First octet of 5 octet sequence. * * This is illegal because the encoded codepoint must be either * (a) not the shortest form or * (b) outside the Unicode range of 0-0x10FFFF. * Rather than trying to resynchronize, we will carry on until the end * of the sequence and let the later error handling code catch it. */ $mUcs4 = ($in); $mUcs4 = ($mUcs4 & 0x03) << 24; $mState = 4; $mBytes = 5; } elseif (0xFC == (0xFE & ($in))) { // First octet of 6 octet sequence, see comments for 5 octet sequence. $mUcs4 = ($in); $mUcs4 = ($mUcs4 & 1) << 30; $mState = 5; $mBytes = 6; } else { // Current octet is neither in the US-ASCII range nor a legal first octet of a multi-octet sequence trigger_error('utf8_to_unicode: Illegal sequence identifier in UTF-8 at byte ' . $i, E_USER_WARNING); return false; } } else { // When mState is non-zero, we expect a continuation of the multi-octet sequence if (0x80 == (0xC0 & ($in))) { // Legal continuation. $shift = ($mState - 1) * 6; $tmp = $in; $tmp = ($tmp & 0x0000003F) << $shift; $mUcs4 |= $tmp; /** * End of the multi-octet sequence. mUcs4 now contains the final * Unicode codepoint to be output */ if (0 == --$mState) { /* * Check for illegal sequences and codepoints. */ // From Unicode 3.1, non-shortest form is illegal if ( ((2 == $mBytes) && ($mUcs4 < 0x0080)) || ((3 == $mBytes) && ($mUcs4 < 0x0800)) || ((4 == $mBytes) && ($mUcs4 < 0x10000)) || (4 < $mBytes) || // From Unicode 3.2, surrogate characters are illegal (($mUcs4 & 0xFFFFF800) == 0xD800) || // Codepoints outside the Unicode range are illegal ($mUcs4 > 0x10FFFF) ) { trigger_error('utf8_to_unicode: Illegal sequence or codepoint in UTF-8 at byte ' . $i, E_USER_WARNING); return false; } // BOM is legal but we don't want to output it if (0xFEFF != $mUcs4) { $out[] = $mUcs4; } // Initialize UTF8 cache $mState = 0; $mUcs4 = 0; $mBytes = 1; } } else { /* ((0xC0 & (*in) != 0x80) && (mState != 0)) Incomplete multi-octet sequence. */ trigger_error('utf8_to_unicode: Incomplete multi-octet sequence in UTF-8 at byte ' . $i, E_USER_WARNING); return false; } } } return $out; } /** * Takes an array of ints representing the Unicode characters and returns a UTF-8 string. * Astral planes are supported ie. the ints in the input can be > 0xFFFF. * Occurrances of the BOM are ignored. Surrogates are not allowed. * Returns false if the input array contains ints that represent surrogates or are outside the Unicode range and raises a PHP error at level E_USER_WARNING * Note: this function has been modified slightly in this library to use output buffering to concatenate the UTF-8 string (faster) as well as reference the array by it's keys * * @see utf8_to_unicode * @see http://hsivonen.iki.fi/php-utf8/ * * @param array $arr Array of unicode code points representing a string * * @return mixed UTF-8 string or FALSE if array contains invalid code points * @author */ function from_unicode($arr) { ob_start(); foreach (array_keys($arr) as $k) { if (($arr[$k] >= 0) && ($arr[$k] <= 0x007f)) // ASCII range (including control chars) { echo chr($arr[$k]); } elseif ($arr[$k] <= 0x07ff) // 2 byte sequence { echo chr(0xc0 | ($arr[$k] >> 6)); echo chr(0x80 | ($arr[$k] & 0x003f)); } elseif ($arr[$k] == 0xFEFF) // Byte order mark (skip) { // Nop -- zap the BOM } elseif ($arr[$k] >= 0xD800 && $arr[$k] <= 0xDFFF) // Test for illegal surrogates { // Found a surrogate trigger_error('utf8_from_unicode: Illegal surrogate at index: ' . $k . ', value: ' . $arr[$k], E_USER_WARNING); return false; } elseif ($arr[$k] <= 0xffff) // 3 byte sequence { echo chr(0xe0 | ($arr[$k] >> 12)); echo chr(0x80 | (($arr[$k] >> 6) & 0x003f)); echo chr(0x80 | ($arr[$k] & 0x003f)); } elseif ($arr[$k] <= 0x10ffff) // 4 byte sequence { echo chr(0xf0 | ($arr[$k] >> 18)); echo chr(0x80 | (($arr[$k] >> 12) & 0x3f)); echo chr(0x80 | (($arr[$k] >> 6) & 0x3f)); echo chr(0x80 | ($arr[$k] & 0x3f)); } else { // Out of range trigger_error('utf8_from_unicode: Codepoint out of Unicode range at index: ' . $k . ', value: ' . $arr[$k], E_USER_WARNING); return false; } } $result = ob_get_contents(); ob_end_clean(); return $result; } php-utf-8-1.2.1/src/utils/validation.php000066400000000000000000000142561252061617700200540ustar00rootroot00000000000000 * @see http://hsivonen.iki.fi/php-utf8/ * @see utf8_compliant * * @param string $str UTF-8 encoded string * * @return boolean TRUE if valid */ function is_valid($str) { $mState = 0; // Cached expected number of octets after the current octet // until the beginning of the next UTF8 character sequence $mUcs4 = 0; // Cached Unicode character $mBytes = 1; // Cached expected number of octets in the current sequence $len = strlen($str); for ($i = 0; $i < $len; $i++) { $in = \ord($str{$i}); if ($mState == 0) { // When mState is zero we expect either a US-ASCII character or a multi-octet sequence. if (0 == (0x80 & ($in))) { $mBytes = 1; // US-ASCII, pass straight through } elseif (0xC0 == (0xE0 & ($in))) { // First octet of 2 octet sequence $mUcs4 = ($in); $mUcs4 = ($mUcs4 & 0x1F) << 6; $mState = 1; $mBytes = 2; } elseif (0xE0 == (0xF0 & ($in))) { // First octet of 3 octet sequence $mUcs4 = ($in); $mUcs4 = ($mUcs4 & 0x0F) << 12; $mState = 2; $mBytes = 3; } elseif (0xF0 == (0xF8 & ($in))) { // First octet of 4 octet sequence $mUcs4 = ($in); $mUcs4 = ($mUcs4 & 0x07) << 18; $mState = 3; $mBytes = 4; } elseif (0xF8 == (0xFC & ($in))) { /* First octet of 5 octet sequence. * * This is illegal because the encoded codepoint must be either * (a) not the shortest form or * (b) outside the Unicode range of 0-0x10FFFF. * Rather than trying to resynchronize, we will carry on until the end * of the sequence and let the later error handling code catch it. */ $mUcs4 = ($in); $mUcs4 = ($mUcs4 & 0x03) << 24; $mState = 4; $mBytes = 5; } elseif (0xFC == (0xFE & ($in))) { // First octet of 6 octet sequence, see comments for 5 octet sequence. $mUcs4 = ($in); $mUcs4 = ($mUcs4 & 1) << 30; $mState = 5; $mBytes = 6; } else { // Current octet is neither in the US-ASCII range nor a legal first octet of a multi-octet sequence. return false; } } else { // When mState is non-zero, we expect a continuation of the multi-octet sequence if (0x80 == (0xC0 & ($in))) { // Legal continuation. $shift = ($mState - 1) * 6; $tmp = $in; $tmp = ($tmp & 0x0000003F) << $shift; $mUcs4 |= $tmp; /** * End of the multi-octet sequence. mUcs4 now contains the final * Unicode codepoint to be output */ if (0 == --$mState) { /* * Check for illegal sequences and codepoints. */ // From Unicode 3.1, non-shortest form is illegal if ( ((2 == $mBytes) && ($mUcs4 < 0x0080)) || ((3 == $mBytes) && ($mUcs4 < 0x0800)) || ((4 == $mBytes) && ($mUcs4 < 0x10000)) || (4 < $mBytes) || // From Unicode 3.2, surrogate characters are illegal (($mUcs4 & 0xFFFFF800) == 0xD800) || // Codepoints outside the Unicode range are illegal ($mUcs4 > 0x10FFFF) ) { return false; } // Initialize UTF8 cache $mState = 0; $mUcs4 = 0; $mBytes = 1; } } else { /** * ((0xC0 & (*in) != 0x80) && (mState != 0)) * Incomplete multi-octet sequence. */ return false; } } } return true; } /** * Tests whether a string complies as UTF-8. This will be much faster than * utf8_is_valid, but will pass five and six octet UTF-8 sequences, * which are not supported by Unicode and so cannot be displayed correctly * in a browser. * In other words it is not as strict as utf8_is_valid but it's faster. * If you use is to validate user input, you place yourself at the risk * that attackers will be able to inject 5 and 6 byte sequences (which may * or may not be a significant risk, depending on what you are are doing) * Note: Does not pass five and six octet UTF-8 sequences anymore in the unit tests. * * @see utf8_is_valid * @see http://www.php.net/manual/en/reference.pcre.pattern.modifiers.php#54805 * * @param string $str UTF-8 string to check * * @return boolean TRUE if string is valid UTF-8 */ function compliant($str) { if (empty($str)) { return true; } // If even just the first character can be matched, when the /u // modifier is used, then it's valid UTF-8. If the UTF-8 is somehow // invalid, nothing at all will match, even if the string contains // some valid sequences return preg_match('/^.{1}/us', $str, $ar) == 1; } php-utf-8-1.2.1/tests/000077500000000000000000000000001252061617700144145ustar00rootroot00000000000000php-utf-8-1.2.1/tests/bootstrap.php000066400000000000000000000002101252061617700171330ustar00rootroot00000000000000assertEquals('', utf8\accents_to_ascii('')); } public function test_lowercase() { $str = 'ô'; $this->assertEquals('o', utf8\accents_to_ascii($str, 'lower')); } public function test_uppercase() { $str = 'Ô'; $this->assertEquals('O', utf8\accents_to_ascii($str, 'upper')); } public function test_both() { $str = 'ôÔ'; $this->assertEquals('oO', utf8\accents_to_ascii($str, 'both')); } } php-utf-8-1.2.1/tests/cases/Utf8BadCleanTest.php000066400000000000000000000170021252061617700212630ustar00rootroot00000000000000assertEquals($str, utf8\bad_clean($str)); } public function test_valid_utf8_ascii() { $str = 'testing'; $this->assertEquals($str, utf8\bad_clean($str)); } public function test_invalid_utf8() { $str = "Iñtërnâtiôn\xe9àlizætiøn"; $this->assertEquals('Iñtërnâtiônàlizætiøn', utf8\bad_clean($str)); } public function test_invalid_utf8_ascii() { $str = "this is an invalid char '\xe9' here"; $this->assertEquals("this is an invalid char '' here", utf8\bad_clean($str)); } public function test_invalid_utf8_multiple() { $str = "\xe9Iñtërnâtiôn\xe9àlizætiøn\xe9"; $this->assertEquals('Iñtërnâtiônàlizætiøn', utf8\bad_clean($str)); } public function test_valid_two_octet_id() { $str = "abc\xc3\xb1"; $this->assertEquals($str, utf8\bad_clean($str)); } public function test_invalid_two_octet_sequence() { $str = "Iñtërnâtiônàlizætiøn \xc3\x28 Iñtërnâtiônàlizætiøn"; $stripped = "Iñtërnâtiônàlizætiøn \x28 Iñtërnâtiônàlizætiøn"; $this->assertEquals($stripped, utf8\bad_clean($str)); } public function test_invalid_id_between_two_and_three() { $str = "Iñtërnâtiônàlizætiøn\xa0\xa1Iñtërnâtiônàlizætiøn"; $stripped = "IñtërnâtiônàlizætiønIñtërnâtiônàlizætiøn"; $this->assertEquals($stripped, utf8\bad_clean($str)); } public function test_valid_three_octet_id() { $str = "Iñtërnâtiônàlizætiøn\xe2\x82\xa1Iñtërnâtiônàlizætiøn"; $this->assertEquals($str, utf8\bad_clean($str)); } public function test_invalid_three_octet_sequence_second() { $str = "Iñtërnâtiônàlizætiøn\xe2\x28\xa1Iñtërnâtiônàlizætiøn"; $stripped = "Iñtërnâtiônàlizætiøn(Iñtërnâtiônàlizætiøn"; $this->assertEquals($stripped, utf8\bad_clean($str)); } public function test_invalid_three_octet_sequence_third() { $str = "Iñtërnâtiônàlizætiøn\xe2\x82\x28Iñtërnâtiônàlizætiøn"; $stripped = "Iñtërnâtiônàlizætiøn(Iñtërnâtiônàlizætiøn"; $this->assertEquals($stripped, utf8\bad_clean($str)); } public function test_valid_four_octet_id() { $str = "Iñtërnâtiônàlizætiøn\xf0\x90\x8c\xbcIñtërnâtiônàlizætiøn"; $this->assertEquals($str, utf8\bad_clean($str)); } public function test_invalid_four_octet_sequence() { $str = "Iñtërnâtiônàlizætiøn\xf0\x28\x8c\xbcIñtërnâtiônàlizætiøn"; $stripped = "Iñtërnâtiônàlizætiøn(Iñtërnâtiônàlizætiøn"; $this->assertEquals($stripped, utf8\bad_clean($str)); } public function test_invalid_five_octet_sequence() { $str = "Iñtërnâtiônàlizætiøn\xf8\xa1\xa1\xa1\xa1Iñtërnâtiônàlizætiøn"; $stripped = "IñtërnâtiônàlizætiønIñtërnâtiônàlizætiøn"; $this->assertEquals($stripped, utf8\bad_clean($str)); } public function test_invalid_six_octet_sequence() { $str = "Iñtërnâtiônàlizætiøn\xfc\xa1\xa1\xa1\xa1\xa1Iñtërnâtiônàlizætiøn"; $stripped = "IñtërnâtiônàlizætiønIñtërnâtiônàlizætiøn"; $this->assertEquals($stripped, utf8\bad_clean($str)); } public function test_valid_utf8_replace() { $str = 'Iñtërnâtiônàlizætiøn'; $this->assertEquals($str, utf8\bad_clean($str, '?')); } public function test_valid_utf8_ascii_replace() { $str = 'testing'; $this->assertEquals($str, utf8\bad_clean($str, '?')); } public function test_invalid_utf8_replace() { $str = "Iñtërnâtiôn\xe9àlizætiøn"; $this->assertEquals('Iñtërnâtiôn?àlizætiøn', utf8\bad_clean($str, '?')); } public function test_invalid_utf8_with_x_replace() { $str = "Iñtërnâtiôn\xe9àlizætiøn"; $this->assertEquals('IñtërnâtiônXàlizætiøn', utf8\bad_clean($str, 'X')); } public function test_invalid_utf8_ascii_replace() { $str = "this is an invalid char '\xe9' here"; $this->assertEquals("this is an invalid char '?' here", utf8\bad_clean($str, '?')); } public function test_invalid_utf8_multiple_replace() { $str = "\xe9Iñtërnâtiôn\xe9àlizætiøn\xe9"; $this->assertEquals('?Iñtërnâtiôn?àlizætiøn?', utf8\bad_clean($str, '?')); } public function test_valid_two_octet_id_replace() { $str = "abc\xc3\xb1"; $this->assertEquals($str, utf8\bad_clean($str, '?')); } public function test_invalid_two_octet_sequence_replace() { $str = "Iñtërnâtiônàlizætiøn \xc3\x28 Iñtërnâtiônàlizætiøn"; $replaced = "Iñtërnâtiônàlizætiøn ?( Iñtërnâtiônàlizætiøn"; $this->assertEquals($replaced, utf8\bad_clean($str, '?')); } public function test_invalid_id_between_two_and_three_replace() { $str = "Iñtërnâtiônàlizætiøn\xa0\xa1Iñtërnâtiônàlizætiøn"; $replaced = "Iñtërnâtiônàlizætiøn??Iñtërnâtiônàlizætiøn"; $this->assertEquals($replaced, utf8\bad_clean($str, '?')); } public function test_valid_three_octet_id_replace() { $str = "Iñtërnâtiônàlizætiøn\xe2\x82\xa1Iñtërnâtiônàlizætiøn"; $this->assertEquals($str, utf8\bad_clean($str, '?')); } public function test_invalid_three_octet_sequence_second_replace() { $str = "Iñtërnâtiônàlizætiøn\xe2\x28\xa1Iñtërnâtiônàlizætiøn"; $replaced = "Iñtërnâtiônàlizætiøn?(?Iñtërnâtiônàlizætiøn"; $this->assertEquals($replaced, utf8\bad_clean($str, '?')); } public function test_invalid_three_octet_sequence_third_replace() { $str = "Iñtërnâtiônàlizætiøn\xe2\x82\x28Iñtërnâtiônàlizætiøn"; $replaced = "Iñtërnâtiônàlizætiøn??(Iñtërnâtiônàlizætiøn"; $this->assertEquals($replaced, utf8\bad_clean($str, '?')); } public function test_valid_four_octet_id_replace() { $str = "Iñtërnâtiônàlizætiøn\xf0\x90\x8c\xbcIñtërnâtiônàlizætiøn"; $this->assertEquals($str, utf8\bad_clean($str, '?')); } public function test_invalid_four_octet_sequence_replace() { $str = "Iñtërnâtiônàlizætiøn\xf0\x28\x8c\xbcIñtërnâtiônàlizætiøn"; $replaced = "Iñtërnâtiônàlizætiøn?(??Iñtërnâtiônàlizætiøn"; $this->assertEquals($replaced, utf8\bad_clean($str, '?')); } public function test_invalid_five_octet_sequence_replace() { $str = "Iñtërnâtiônàlizætiøn\xf8\xa1\xa1\xa1\xa1Iñtërnâtiônàlizætiøn"; $replaced = "Iñtërnâtiônàlizætiøn?????Iñtërnâtiônàlizætiøn"; $this->assertEquals($replaced, utf8\bad_clean($str, '?')); } public function test_invalid_six_octet_sequence_replace() { $str = "Iñtërnâtiônàlizætiøn\xfc\xa1\xa1\xa1\xa1\xa1Iñtërnâtiônàlizætiøn"; $replaced = "Iñtërnâtiônàlizætiøn??????Iñtërnâtiônàlizætiøn"; $this->assertEquals($replaced, utf8\bad_clean($str, '?')); } } php-utf-8-1.2.1/tests/cases/Utf8BadFindTest.php000066400000000000000000000141511252061617700211230ustar00rootroot00000000000000assertFalse(utf8\bad_find($str)); } public function test_valid_utf8_ascii() { $str = 'testing'; $this->assertFalse(utf8\bad_find($str)); } public function test_invalid_utf8() { $str = "Iñtërnâtiôn\xe9àlizætiøn"; $this->assertEquals(15, utf8\bad_find($str)); } public function test_invalid_utf8_ascii() { $str = "this is an invalid char '\xe9' here"; $this->assertEquals(25, utf8\bad_find($str)); } public function test_invalid_utf8_start() { $str = "\xe9Iñtërnâtiônàlizætiøn"; $this->assertEquals(0, utf8\bad_find($str)); } public function test_invalid_utf8_end() { $str = "Iñtërnâtiônàlizætiøn\xe9"; $this->assertEquals(27, utf8\bad_find($str)); } public function test_valid_two_octet_id() { $str = "abc\xc3\xb1"; $this->assertFalse(utf8\bad_find($str)); } public function test_invalid_two_octet_sequence() { $str = "Iñtërnâtiônàlizætiøn \xc3\x28 Iñtërnâtiônàlizætiøn"; $this->assertEquals(28, utf8\bad_find($str)); } public function test_invalid_id_between_two_and_three() { $str = "Iñtërnâtiônàlizætiøn\xa0\xa1Iñtërnâtiônàlizætiøn"; $this->assertEquals(27, utf8\bad_find($str)); } public function test_valid_three_octet_id() { $str = "Iñtërnâtiônàlizætiøn\xe2\x82\xa1Iñtërnâtiônàlizætiøn"; $this->assertFalse(utf8\bad_find($str)); } public function test_invalid_three_octet_sequence_second() { $str = "Iñtërnâtiônàlizætiøn\xe2\x28\xa1Iñtërnâtiônàlizætiøn"; $this->assertEquals(27, utf8\bad_find($str)); } public function test_invalid_three_octet_sequence_third() { $str = "Iñtërnâtiônàlizætiøn\xe2\x82\x28Iñtërnâtiônàlizætiøn"; $this->assertEquals(27, utf8\bad_find($str)); } public function test_valid_four_octet_id() { $str = "Iñtërnâtiônàlizætiøn\xf0\x90\x8c\xbcIñtërnâtiônàlizætiøn"; $this->assertFalse(utf8\bad_find($str)); } public function test_invalid_four_octet_sequence() { $str = "Iñtërnâtiônàlizætiøn\xf0\x28\x8c\xbcIñtërnâtiônàlizætiøn"; $this->assertEquals(27, utf8\bad_find($str)); } public function test_invalid_five_octet_sequence() { $str = "Iñtërnâtiônàlizætiøn\xf8\xa1\xa1\xa1\xa1Iñtërnâtiônàlizætiøn"; $this->assertEquals(27, utf8\bad_find($str)); } public function test_invalid_six_octet_sequence() { $str = "Iñtërnâtiônàlizætiøn\xfc\xa1\xa1\xa1\xa1\xa1Iñtërnâtiônàlizætiøn"; $this->assertEquals(27, utf8\bad_find($str)); } public function test_valid_utf8_all() { $str = 'Iñtërnâtiônàlizætiøn'; $this->assertFalse(utf8\bad_find($str, false)); } public function test_valid_utf8_ascii_all() { $str = 'testing'; $this->assertFalse(utf8\bad_find($str, false)); } public function test_invalid_utf8_all() { $str = "Iñtërnâtiôn\xe9àlizætiøn"; $test = array(15); $this->assertEquals($test, utf8\bad_find($str, false)); } public function test_invalid_utf8_ascii_all() { $str = "this is an invalid char '\xe9' here"; $test = array(25); $this->assertEquals($test, utf8\bad_find($str, false)); } public function test_invalid_utf8_multiple_all() { $str = "\xe9Iñtërnâtiôn\xe9àlizætiøn\xe9"; $test = array(0, 16, 29); $this->assertEquals($test, utf8\bad_find($str, false)); } public function test_valid_two_octet_id_all() { $str = "abc\xc3\xb1"; $this->assertFalse(utf8\bad_find($str, false)); } public function test_invalid_two_octet_sequence_all() { $str = "Iñtërnâtiônàlizætiøn \xc3\x28 Iñtërnâtiônàlizætiøn"; $this->assertEquals(array(28), utf8\bad_find($str, false)); } public function test_invalid_id_between_two_and_three_all() { $str = "Iñtërnâtiônàlizætiøn\xa0\xa1Iñtërnâtiônàlizætiøn"; $this->assertEquals(array(27, 28), utf8\bad_find($str, false)); } public function test_valid_three_octet_id_all() { $str = "Iñtërnâtiônàlizætiøn\xe2\x82\xa1Iñtërnâtiônàlizætiøn"; $this->assertFalse(utf8\bad_find($str, false)); } public function test_invalid_three_octet_sequence_second_all() { $str = "Iñtërnâtiônàlizætiøn\xe2\x28\xa1Iñtërnâtiônàlizætiøn"; $this->assertEquals(array(27, 29), utf8\bad_find($str, false)); } public function test_invalid_three_octet_sequence_third_all() { $str = "Iñtërnâtiônàlizætiøn\xe2\x82\x28Iñtërnâtiônàlizætiøn"; $this->assertEquals(27, utf8\bad_find($str)); } public function test_valid_four_octet_id_all() { $str = "Iñtërnâtiônàlizætiøn\xf0\x90\x8c\xbcIñtërnâtiônàlizætiøn"; $this->assertFalse(utf8\bad_find($str, false)); } public function test_invalid_four_octet_sequence_all() { $str = "Iñtërnâtiônàlizætiøn\xf0\x28\x8c\xbcIñtërnâtiônàlizætiøn"; $this->assertEquals(array(27, 29, 30), utf8\bad_find($str, false)); } public function test_invalid_five_octet_sequence_all() { $str = "Iñtërnâtiônàlizætiøn\xf8\xa1\xa1\xa1\xa1Iñtërnâtiônàlizætiøn"; $this->assertEquals(range(27, 31), utf8\bad_find($str, false)); } public function test_invalid_six_octet_sequence_all() { $str = "Iñtërnâtiônàlizætiøn\xfc\xa1\xa1\xa1\xa1\xa1Iñtërnâtiônàlizætiøn"; $this->assertEquals(range(27, 32), utf8\bad_find($str, false)); } } php-utf-8-1.2.1/tests/cases/Utf8BadIdentifyTest.php000066400000000000000000000076741252061617700220320ustar00rootroot00000000000000assertFalse(utf8\bad_identify($str, $i)); $this->assertNull($i); } public function test_valid_utf8_ascii() { $str = 'testing'; $this->assertFalse(utf8\bad_identify($str, $i)); $this->assertNull($i); } public function test_invalid_utf8() { $str = "Iñtërnâtiôn\xe9àlizætiøn"; $this->assertEquals(utf8\BAD_SEQINCOMPLETE, utf8\bad_identify($str, $i)); $this->assertEquals(15, $i); } public function test_invalid_utf8_ascii() { $str = "this is an invalid char '\xe9' here"; $this->assertEquals(utf8\BAD_SEQINCOMPLETE, utf8\bad_identify($str, $i)); $this->assertEquals(25, $i); } public function test_invalid_utf8_start() { $str = "\xe9Iñtërnâtiônàlizætiøn"; $this->assertEquals(utf8\BAD_SEQINCOMPLETE, utf8\bad_identify($str, $i)); $this->assertEquals(0, $i); } public function test_invalid_utf8_end() { $str = "Iñtërnâtiônàlizætiøn\xe9"; $this->assertEquals(utf8\BAD_SEQINCOMPLETE, utf8\bad_identify($str, $i)); $this->assertEquals(27, $i); } public function test_valid_two_octet_id() { $str = "abc\xc3\xb1"; $this->assertFalse(utf8\bad_identify($str, $i)); $this->assertNull($i); } public function test_invalid_two_octet_sequence() { $str = "Iñtërnâtiônàlizætiøn \xc3\x28 Iñtërnâtiônàlizætiøn"; $this->assertEquals(utf8\BAD_SEQINCOMPLETE, utf8\bad_identify($str, $i)); $this->assertEquals(28, $i); } public function test_invalid_id_between_two_and_three() { $str = "Iñtërnâtiônàlizætiøn\xa0\xa1Iñtërnâtiônàlizætiøn"; $this->assertEquals(utf8\BAD_SEQID, utf8\bad_identify($str, $i)); $this->assertEquals(27, $i); } public function test_valid_three_octet_id() { $str = "Iñtërnâtiônàlizætiøn\xe2\x82\xa1Iñtërnâtiônàlizætiøn"; $this->assertFalse(utf8\bad_identify($str, $i)); $this->assertNull($i); } public function test_invalid_three_octet_sequence_second() { $str = "Iñtërnâtiônàlizætiøn\xe2\x28\xa1Iñtërnâtiônàlizætiøn"; $this->assertEquals(utf8\BAD_SEQINCOMPLETE, utf8\bad_identify($str, $i)); $this->assertEquals(27, $i); } public function test_invalid_three_octet_sequence_third() { $str = "Iñtërnâtiônàlizætiøn\xe2\x82\x28Iñtërnâtiônàlizætiøn"; $this->assertEquals(utf8\BAD_SEQINCOMPLETE, utf8\bad_identify($str, $i)); $this->assertEquals(28, $i); } public function test_valid_four_octet_id() { $str = "Iñtërnâtiônàlizætiøn\xf0\x90\x8c\xbcIñtërnâtiônàlizætiøn"; $this->assertFalse(utf8\bad_identify($str, $i)); $this->assertNull($i); } public function test_invalid_four_octet_sequence() { $str = "Iñtërnâtiônàlizætiøn\xf0\x28\x8c\xbcIñtërnâtiônàlizætiøn"; $this->assertEquals(utf8\BAD_SEQINCOMPLETE, utf8\bad_identify($str, $i)); $this->assertEquals(27, $i); } public function test_invalid_five_octet_sequence() { $str = "Iñtërnâtiônàlizætiøn\xf8\xa1\xa1\xa1\xa1Iñtërnâtiônàlizætiøn"; $this->assertEquals(utf8\BAD_5OCTET, utf8\bad_identify($str, $i)); $this->assertEquals(27, $i); } public function test_invalid_six_octet_sequence() { $str = "Iñtërnâtiônàlizætiøn\xfc\xa1\xa1\xa1\xa1\xa1Iñtërnâtiônàlizætiøn"; $this->assertEquals(utf8\BAD_6OCTET, utf8\bad_identify($str, $i)); $this->assertEquals(27, $i); } } php-utf-8-1.2.1/tests/cases/Utf8CompliantTest.php000066400000000000000000000054071252061617700215660ustar00rootroot00000000000000assertTrue(utf8\compliant($str)); } public function test_valid_utf8_ascii() { $str = 'ABC 123'; $this->assertTrue(utf8\compliant($str)); } public function test_invalid_utf8() { $str = "Iñtërnâtiôn\xe9àlizætiøn"; $this->assertFalse(utf8\compliant($str)); } public function test_invalid_utf8_ascii() { $str = "this is an invalid char '\xe9' here"; $this->assertFalse(utf8\compliant($str)); } public function test_empty_string() { $str = ''; $this->assertTrue(utf8\compliant($str)); } public function test_valid_two_octet_id() { $str = "\xc3\xb1"; $this->assertTrue(utf8\compliant($str)); } public function test_invalid_two_octet_sequence() { $str = "Iñtërnâtiônàlizætiøn \xc3\x28 Iñtërnâtiônàlizætiøn"; $this->assertFalse(utf8\compliant($str)); } public function test_invalid_id_between_twoAnd_three() { $str = "Iñtërnâtiônàlizætiøn\xa0\xa1Iñtërnâtiônàlizætiøn"; $this->assertFalse(utf8\compliant($str)); } public function test_valid_three_octet_id() { $str = "Iñtërnâtiônàlizætiøn\xe2\x82\xa1Iñtërnâtiônàlizætiøn"; $this->assertTrue(utf8\compliant($str)); } public function test_invalid_three_octet_sequence_second() { $str = "Iñtërnâtiônàlizætiøn\xe2\x28\xa1Iñtërnâtiônàlizætiøn"; $this->assertFalse(utf8\compliant($str)); } public function test_invalid_three_octet_sequence_third() { $str = "Iñtërnâtiônàlizætiøn\xe2\x82\x28Iñtërnâtiônàlizætiøn"; $this->assertFalse(utf8\compliant($str)); } public function test_valid_four_octet_id() { $str = "Iñtërnâtiônàlizætiøn\xf0\x90\x8c\xbcIñtërnâtiônàlizætiøn"; $this->assertTrue(utf8\compliant($str)); } public function test_invalid_four_octet_sequence() { $str = "Iñtërnâtiônàlizætiøn\xf0\x28\x8c\xbcIñtërnâtiônàlizætiøn"; $this->assertFalse(utf8\compliant($str)); } public function test_invalid_five_octet_sequence() { $str = "Iñtërnâtiônàlizætiøn\xf8\xa1\xa1\xa1\xa1Iñtërnâtiônàlizætiøn"; $this->assertFalse(utf8\compliant($str)); } public function test_invalid_six_octet_sequence() { $str = "Iñtërnâtiônàlizætiøn\xfc\xa1\xa1\xa1\xa1\xa1Iñtërnâtiônàlizætiøn"; $this->assertFalse(utf8\compliant($str)); } } php-utf-8-1.2.1/tests/cases/Utf8FromUnicodeTest.php000066400000000000000000000016601252061617700220470ustar00rootroot00000000000000assertEmpty(utf8\from_unicode(array())); } public function test_array() { $unicode = array(); $unicode[0] = 73; $unicode[1] = 241; $unicode[2] = 116; $unicode[3] = 235; $unicode[4] = 114; $unicode[5] = 110; $unicode[6] = 226; $unicode[7] = 116; $unicode[8] = 105; $unicode[9] = 244; $unicode[10] = 110; $unicode[11] = 224; $unicode[12] = 108; $unicode[13] = 105; $unicode[14] = 122; $unicode[15] = 230; $unicode[16] = 116; $unicode[17] = 105; $unicode[18] = 248; $unicode[19] = 110; $this->assertEquals('Iñtërnâtiônàlizætiøn', utf8\from_unicode($unicode)); } } php-utf-8-1.2.1/tests/cases/Utf8IsAsciiTest.php000066400000000000000000000011371252061617700211600ustar00rootroot00000000000000assertFalse(utf8\is_ascii($str)); } public function test_ascii() { $str = 'testing'; $this->assertTrue(utf8\is_ascii($str)); } public function test_invalid_char() { $str = "tes\xe9ting"; $this->assertFalse(utf8\is_ascii($str)); } public function test_empty_str() { $str = ''; $this->assertTrue(utf8\is_ascii($str)); } } php-utf-8-1.2.1/tests/cases/Utf8IsValidTest.php000066400000000000000000000053661252061617700211770ustar00rootroot00000000000000assertTrue(utf8\is_valid($str)); } public function test_valid_utf8_ascii() { $str = 'ABC 123'; $this->assertTrue(utf8\is_valid($str)); } public function test_invalid_utf8() { $str = "Iñtërnâtiôn\xe9àlizætiøn"; $this->assertFalse(utf8\is_valid($str)); } public function test_invalid_utf8_ascii() { $str = "this is an invalid char '\xe9' here"; $this->assertFalse(utf8\is_valid($str)); } public function test_empty_string() { $str = ''; $this->assertTrue(utf8\is_valid($str)); } public function test_valid_two_octet_id() { $str = "\xc3\xb1"; $this->assertTrue(utf8\is_valid($str)); } public function test_invalid_two_octet_sequence() { $str = "Iñtërnâtiônàlizætiøn \xc3\x28 Iñtërnâtiônàlizætiøn"; $this->assertFalse(utf8\is_valid($str)); } public function test_invalid_id_between_twoAnd_three() { $str = "Iñtërnâtiônàlizætiøn\xa0\xa1Iñtërnâtiônàlizætiøn"; $this->assertFalse(utf8\is_valid($str)); } public function test_valid_three_octet_id() { $str = "Iñtërnâtiônàlizætiøn\xe2\x82\xa1Iñtërnâtiônàlizætiøn"; $this->assertTrue(utf8\is_valid($str)); } public function test_invalid_three_octet_sequence_second() { $str = "Iñtërnâtiônàlizætiøn\xe2\x28\xa1Iñtërnâtiônàlizætiøn"; $this->assertFalse(utf8\is_valid($str)); } public function test_invalid_three_octet_sequence_third() { $str = "Iñtërnâtiônàlizætiøn\xe2\x82\x28Iñtërnâtiônàlizætiøn"; $this->assertFalse(utf8\is_valid($str)); } public function test_valid_four_octet_id() { $str = "Iñtërnâtiônàlizætiøn\xf0\x90\x8c\xbcIñtërnâtiônàlizætiøn"; $this->assertTrue(utf8\is_valid($str)); } public function test_invalid_four_octet_sequence() { $str = "Iñtërnâtiônàlizætiøn\xf0\x28\x8c\xbcIñtërnâtiônàlizætiøn"; $this->assertFalse(utf8\is_valid($str)); } public function test_invalid_five_octet_sequence() { $str = "Iñtërnâtiônàlizætiøn\xf8\xa1\xa1\xa1\xa1Iñtërnâtiônàlizætiøn"; $this->assertFalse(utf8\is_valid($str)); } public function test_invalid_six_octet_sequence() { $str = "Iñtërnâtiônàlizætiøn\xfc\xa1\xa1\xa1\xa1\xa1Iñtërnâtiônàlizætiøn"; $this->assertFalse(utf8\is_valid($str)); } } php-utf-8-1.2.1/tests/cases/Utf8IsWordCharsTest.php000066400000000000000000000012531252061617700220230ustar00rootroot00000000000000assertTrue(utf8\is_word_chars('')); } public function test_all_word_chars() { $this->assertTrue(utf8\is_word_chars('HelloWorld')); } public function test_specials() { $str = 'Hello ' . chr(0xe0 | (0x2234 >> 12)) . chr(0x80 | ((0x2234 >> 6) & 0x003f)) . chr(0x80 | (0x2234 & 0x003f)) . ' World'; $this->assertFalse(utf8\is_word_chars($str)); } } php-utf-8-1.2.1/tests/cases/Utf8LtrimTest.php000066400000000000000000000030001252061617700207120ustar00rootroot00000000000000assertEquals($trimmed, utf8\ltrim($str, 'ñ')); } public function test_no_trim() { $str = ' Iñtërnâtiônàlizætiøn'; $trimmed = ' Iñtërnâtiônàlizætiøn'; $this->assertEquals($trimmed, utf8\ltrim($str, 'ñ')); } public function test_empty_string() { $str = ''; $trimmed = ''; $this->assertEquals($trimmed, utf8\ltrim($str)); } public function test_forward_slash() { $str = '/Iñtërnâtiônàlizætiøn'; $trimmed = 'Iñtërnâtiônàlizætiøn'; $this->assertEquals($trimmed, utf8\ltrim($str, '/')); } public function test_negate_char_class() { $str = 'Iñtërnâtiônàlizætiøn'; $trimmed = 'Iñtërnâtiônàlizætiøn'; $this->assertEquals($trimmed, utf8\ltrim($str, '^s')); } public function test_linefeed() { $str = "ñ\nñtërnâtiônàlizætiøn"; $trimmed = "\nñtërnâtiônàlizætiøn"; $this->assertEquals($trimmed, utf8\ltrim($str, 'ñ')); } public function test_linefeed_mask() { $str = "ñ\nñtërnâtiônàlizætiøn"; $trimmed = "tërnâtiônàlizætiøn"; $this->assertEquals($trimmed, utf8\ltrim($str, "ñ\n")); } } php-utf-8-1.2.1/tests/cases/Utf8OrdTest.php000066400000000000000000000013431252061617700203570ustar00rootroot00000000000000assertEquals(0, utf8\ord($str)); } public function test_ascii_char() { $str = 'a'; $this->assertEquals(97, utf8\ord($str)); } public function test_2_byte_char() { $str = 'ñ'; $this->assertEquals(241, utf8\ord($str)); } public function test_3_byte_char() { $str = '₧'; $this->assertEquals(8359, utf8\ord($str)); } public function test_4_byte_char() { $str = "\xf0\x90\x8c\xbc"; $this->assertEquals(66364, utf8\ord($str)); } } php-utf-8-1.2.1/tests/cases/Utf8PositionTest.php000066400000000000000000000075421252061617700214460ustar00rootroot00000000000000assertEquals(3, utf8\byte_position($str, 3)); $this->assertEquals(array(3, 4), utf8\byte_position($str, 3, 4)); $this->assertEquals(0, utf8\byte_position($str, -1)); $this->assertEquals(7, utf8\byte_position($str, 8)); } public function test_multibyte_char_to_byte() { $str = 'Iñtërnâtiônàlizætiøn'; $this->assertEquals(4, utf8\byte_position($str, 3)); $this->assertEquals(array(4, 7), utf8\byte_position($str, 3, 5)); $this->assertEquals(0, utf8\byte_position($str, -1)); $this->assertEquals(27, utf8\byte_position($str, 28)); } // Tests for utf8\locate_current_chr & utf8\locate_next_chr public function test_singlebyte() { $tests = array(); // Single byte, should return current index $tests[] = array('aaживπά우리をあöä', 0, 0); $tests[] = array('aaживπά우리をあöä', 1, 1); foreach ($tests as $test) { $this->assertEquals($test[2], utf8\locate_current_chr($test[0], $test[1])); } $tests = array(); $tests[] = array('aaживπά우리をあöä', 1, 1); foreach ($tests as $test) { $this->assertEquals($test[2], utf8\locate_next_chr($test[0], $test[1])); } } public function test_two_byte() { // Two byte, should move to boundary, expect even number $tests = array(); $tests[] = array('aaживπά우리をあöä', 2, 2); $tests[] = array('aaживπά우리をあöä', 3, 2); $tests[] = array('aaживπά우리をあöä', 4, 4); foreach ($tests as $test) { $this->assertEquals($test[2], utf8\locate_current_chr($test[0], $test[1])); } $tests = array(); $tests[] = array('aaживπά우리をあöä', 2, 2); $tests[] = array('aaживπά우리をあöä', 3, 4); $tests[] = array('aaживπά우리をあöä', 4, 4); foreach ($tests as $test) { $this->assertEquals($test[2], utf8\locate_next_chr($test[0], $test[1])); } } public function test_threebyte() { // Three byte, should move to boundary 10 or 13 $tests = array(); $tests[] = array('aaживπά우리をあöä', 10, 10); $tests[] = array('aaживπά우리をあöä', 11, 10); $tests[] = array('aaживπά우리をあöä', 12, 10); $tests[] = array('aaживπά우리をあöä', 13, 13); foreach ($tests as $test) { $this->assertEquals($test[2], utf8\locate_current_chr($test[0], $test[1])); } $tests = array(); $tests[] = array('aaживπά우리をあöä', 10, 10); $tests[] = array('aaживπά우리をあöä', 11, 13); $tests[] = array('aaживπά우리をあöä', 12, 13); $tests[] = array('aaживπά우리をあöä', 13, 13); foreach ($tests as $test) { $this->assertEquals($test[2], utf8\locate_next_chr($test[0], $test[1])); } } public function test_bounds() { // Bounds checking $tests = array(); $tests[] = array('aaживπά우리をあöä', -2, 0); $tests[] = array('aaживπά우리をあöä', 128, 29); foreach ($tests as $test) { $this->assertEquals($test[2], utf8\locate_current_chr($test[0], $test[1])); } $tests[] = array('aaживπά우리をあöä', -2, 0); $tests[] = array('aaживπά우리をあöä', 128, 29); foreach ($tests as $test) { $this->assertEquals($test[2], utf8\locate_next_chr($test[0], $test[1])); } } } php-utf-8-1.2.1/tests/cases/Utf8RtrimTest.php000066400000000000000000000021221252061617700207240ustar00rootroot00000000000000assertEquals($trimmed, utf8\rtrim($str, 'ø')); } public function test_no_trim() { $str = 'Iñtërnâtiônàlizætiøn '; $trimmed = 'Iñtërnâtiônàlizætiøn '; $this->assertEquals($trimmed, utf8\rtrim($str, 'ø')); } public function test_empty_string() { $str = ''; $trimmed = ''; $this->assertEquals($trimmed, utf8\rtrim($str)); } public function test_linefeed() { $str = "Iñtërnâtiônàlizætiø\nø"; $trimmed = "Iñtërnâtiônàlizætiø\n"; $this->assertEquals($trimmed, utf8\rtrim($str, 'ø')); } public function test_linefeed_mask() { $str = "Iñtërnâtiônàlizætiø\nø"; $trimmed = "Iñtërnâtiônàlizæti"; $this->assertEquals($trimmed, utf8\rtrim($str, "ø\n")); } } php-utf-8-1.2.1/tests/cases/Utf8StrIreplaceTest.php000066400000000000000000000062501252061617700220520ustar00rootroot00000000000000assertEquals($replaced, utf8\ireplace('lIzÆ', 'lise', $str)); } public function test_replace_no_match() { $str = 'Iñtërnâtiônàlizætiøn'; $replaced = 'Iñtërnâtiônàlizætiøn'; $this->assertEquals($replaced, utf8\ireplace('foo', 'bar', $str)); } public function test_empty_string() { $str = ''; $replaced = ''; $this->assertEquals($replaced, utf8\ireplace('foo', 'bar', $str)); } public function test_empty_search() { $str = 'Iñtërnâtiônàlizætiøn'; $replaced = 'Iñtërnâtiônàlizætiøn'; $this->assertEquals($replaced, utf8\ireplace('', 'x', $str)); } public function test_replace_count() { $str = 'Iñtërnâtiônàlizætiøn'; $replaced = 'IñtërXâtiôXàlizætiøn'; $this->assertEquals($replaced, utf8\ireplace('n', 'X', $str, 2)); } public function test_replace_different_search_replace_length() { $str = 'Iñtërnâtiônàlizætiøn'; $replaced = 'IñtërXXXâtiôXXXàlizætiøXXX'; $this->assertEquals($replaced, utf8\ireplace('n', 'XXX', $str)); } public function test_replace_array_ascii_search() { $str = 'Iñtërnâtiônàlizætiøn'; $replaced = 'Iñyërxâyiôxàlizæyiøx'; $this->assertEquals($replaced, utf8\ireplace(array('n', 't'), array('x', 'y'), $str)); } public function test_replace_array_utf8_search() { $str = 'Iñtërnâtiônàlizætiøn'; $replaced = 'I?tërnâti??nàliz????ti???n'; $this->assertEquals( utf8\ireplace( array('Ñ', 'ô', 'ø', 'Æ'), array('?', '??', '???', '????'), $str), $replaced); } public function test_replace_array_string_replace() { $str = 'Iñtërnâtiônàlizætiøn'; $replaced = 'I?tërnâti?nàliz?ti?n'; $this->assertEquals( $replaced, utf8\ireplace( array('Ñ', 'ô', 'ø', 'Æ'), '?', $str) ); } public function test_replace_array_single_array_replace() { $str = 'Iñtërnâtiônàlizætiøn'; $replaced = 'I?tërnâtinàliztin'; $this->assertEquals( utf8\ireplace( array('Ñ', 'ô', 'ø', 'Æ'), array('?'), $str), $replaced); } public function test_replace_linefeed() { $str = "Iñtërnâti\nônàlizætiøn"; $replaced = "Iñtërnâti\nônàlisetiøn"; $this->assertEquals($replaced, utf8\ireplace('lIzÆ', 'lise', $str)); } public function test_replace_linefeed_search() { $str = "Iñtërnâtiônàli\nzætiøn"; $replaced = "Iñtërnâtiônàlisetiøn"; $this->assertEquals($replaced, utf8\ireplace("lI\nzÆ", 'lise', $str)); } } php-utf-8-1.2.1/tests/cases/Utf8StrPadTest.php000066400000000000000000000020431252061617700210260ustar00rootroot00000000000000'; // 10 characters $padding = 'ø__'; // 4 characters $this->assertEquals($toPad . ' ', utf8\pad($toPad, 20)); $this->assertEquals(' ' . $toPad, utf8\pad($toPad, 20, ' ', STR_PAD_LEFT)); $this->assertEquals(' ' . $toPad . ' ', utf8\pad($toPad, 20, ' ', STR_PAD_BOTH)); $this->assertEquals($toPad, utf8\pad($toPad, 10)); $this->assertEquals('5char', str_pad('5char', 4)); // str_pos won't truncate input string $this->assertEquals($toPad, utf8\pad($toPad, 8)); $this->assertEquals($toPad . 'ø__ø__ø__ø', utf8\pad($toPad, 20, $padding, STR_PAD_RIGHT)); $this->assertEquals('ø__ø__ø__ø' . $toPad, utf8\pad($toPad, 20, $padding, STR_PAD_LEFT)); $this->assertEquals('ø__ø_' . $toPad . 'ø__ø_', utf8\pad($toPad, 20, $padding, STR_PAD_BOTH)); } } php-utf-8-1.2.1/tests/cases/Utf8StrSplitTest.php000066400000000000000000000040311252061617700214140ustar00rootroot00000000000000assertEquals($array, utf8\split($str)); } public function test_split_five_chars() { $str = 'Iñtërnâtiônàlizætiøn'; $array = array( 'Iñtër', 'nâtiô', 'nàliz', 'ætiøn', ); $this->assertEquals($array, utf8\split($str, 5)); } public function test_split_six_chars() { $str = 'Iñtërnâtiônàlizætiøn'; $array = array( 'Iñtërn', 'âtiônà', 'lizæti', 'øn', ); $this->assertEquals($array, utf8\split($str, 6)); } public function test_split_long() { $str = 'Iñtërnâtiônàlizætiøn'; $array = array( 'Iñtërnâtiônàlizætiøn', ); $this->assertEquals($array, utf8\split($str, 40)); } public function test_split_newline() { $str = "Iñtërn\nâtiônàl\nizætiøn\n"; $array = array( 'I', 'ñ', 't', 'ë', 'r', 'n', "\n", 'â', 't', 'i', 'ô', 'n', 'à', 'l', "\n", 'i', 'z', 'æ', 't', 'i', 'ø', 'n', "\n", ); $this->assertEquals($array, utf8\split($str)); } } php-utf-8-1.2.1/tests/cases/Utf8StrWordwrapTest.php000066400000000000000000000025201252061617700221270ustar00rootroot00000000000000assertEquals($wrapped, utf8\wordwrap($str)); } public function test_break_at_ten() { $str = 'Iñtërnâtiônàlizætiøn Iñtërnâtiônàlizætiøn'; $wrapped = "Iñtërnâtiônàlizætiøn\nIñtërnâtiônàlizætiøn"; $this->assertEquals($wrapped, utf8\wordwrap($str, 10)); } public function test_break_at_ten_cut() { $str = 'Iñtërnâtiônàlizætiøn'; $wrapped = "Iñtërnâtiô\nnàlizætiøn"; $this->assertEquals($wrapped, utf8\wordwrap($str, 10, "\n", true)); } public function test_break_at_ten_br() { $str = 'Iñtërnâtiônàlizætiøn Iñtërnâtiônàlizætiøn'; $wrapped = "Iñtërnâtiônàlizætiøn
Iñtërnâtiônàlizætiøn"; $this->assertEquals($wrapped, utf8\wordwrap($str, 12, '
')); } public function test_break_at_ten_int() { $str = 'Iñtërnâtiônàlizætiøn'; $wrapped = "Iñtërnâtiônà
lizætiøn"; $this->assertEquals($wrapped, utf8\wordwrap($str, 12, '
', true)); } } php-utf-8-1.2.1/tests/cases/Utf8StrcasecmpTest.php000066400000000000000000000026741252061617700217470ustar00rootroot00000000000000assertEquals(0, utf8\casecmp($str_x, $str_y)); } public function test_less() { $str_x = 'iñtërnâtiônàlizætiøn'; $str_y = 'IÑTËRNÂTIÔÀLIZÆTIØN'; $this->assertTrue(utf8\casecmp($str_x, $str_y) < 0); } public function test_greater() { $str_x = 'iñtërnâtiôàlizætiøn'; $str_y = 'IÑTËRNÂTIÔNÀLIZÆTIØN'; $this->assertTrue(utf8\casecmp($str_x, $str_y) > 0); } public function test_empty_x() { $str_x = ''; $str_y = 'IÑTËRNÂTIÔNÀLIZÆTIØN'; $this->assertTrue(utf8\casecmp($str_x, $str_y) < 0); } public function test_empty_y() { $str_x = 'iñtërnâtiôàlizætiøn'; $str_y = ''; $this->assertTrue(utf8\casecmp($str_x, $str_y) > 0); } public function test_empty_both() { $str_x = ''; $str_y = ''; $this->assertTrue(utf8\casecmp($str_x, $str_y) == 0); } public function test_linefeed() { $str_x = "iñtërnâtiôn\nàlizætiøn"; $str_y = "IÑTËRNÂTIÔN\nÀLIZÆTIØN"; $this->assertTrue(utf8\casecmp($str_x, $str_y) == 0); } } php-utf-8-1.2.1/tests/cases/Utf8StrcspnTest.php000066400000000000000000000034721252061617700212740ustar00rootroot00000000000000assertEquals(2, utf8\cspn($str, 't')); } protected function tes_no_match_multi_byte_search() { $str = 'iñtërnâtiônàlizætiøn'; $this->assertEquals(6, utf8\cspn($str, 'â')); } public function test_compare_strspn() { $str = 'aeioustr'; $this->assertEquals(strcspn($str, 'tr'), utf8\cspn($str, 'tr')); } public function test_match_ascii() { $str = 'internationalization'; $this->assertEquals(strcspn($str, 'a'), utf8\cspn($str, 'a')); } public function test_linefeed() { $str = "i\nñtërnâtiônàlizætiøn"; $this->assertEquals(3, utf8\cspn($str, 't')); } public function test_linefeed_mask() { $str = "i\nñtërnâtiônàlizætiøn"; $this->assertEquals(1, utf8\cspn($str, "\n")); } public function test_7() { $str = "abcdefghijklmnop"; $this->assertEquals(4, utf8\cspn($str, 'h', 3)); $this->assertEquals(0, utf8\cspn($str, 'd', 3)); } public function test_8() { $str = "A brief test.
"; $this->assertEquals(3, utf8\cspn($str, '/>', 21)); $this->assertEquals(1, utf8\cspn($str, '/>', 1)); } public function test_9() { $str = "A brief test.
現在、企業ユーザー向けに多岐にわたるサービスを提供しています。
"; $this->assertEquals(2, utf8\cspn($str, ">")); //! $this->assertEquals(3, utf8\cspn($str, '\/\>', 21)); $this->assertEquals(8, utf8\cspn($str, '向けに', 26)); } } php-utf-8-1.2.1/tests/cases/Utf8StripSpecialsTest.php000066400000000000000000000011161252061617700224160ustar00rootroot00000000000000assertEquals('', utf8\strip_specials('')); } public function test_strip() { $str = 'Hello ' . chr(0xe0 | (0x2234 >> 12)) . chr(0x80 | ((0x2234 >> 6) & 0x003f)) . chr(0x80 | (0x2234 & 0x003f)) . ' World'; $this->assertEquals('HelloWorld', utf8\strip_specials($str)); } } php-utf-8-1.2.1/tests/cases/Utf8StristrTest.php000066400000000000000000000026241252061617700213100ustar00rootroot00000000000000assertEquals('nâtiônàlizætiøn', utf8\ifind($str, $search)); } public function test_substr_no_match() { $str = 'iñtërnâtiônàlizætiøn'; $search = 'foo'; $this->assertFalse(utf8\ifind($str, $search)); } public function test_empty_search() { $str = 'iñtërnâtiônàlizætiøn'; $search = ''; $this->assertEquals('iñtërnâtiônàlizætiøn', utf8\ifind($str, $search)); } public function test_empty_str() { $str = ''; $search = 'NÂT'; $this->assertFalse(utf8\ifind($str, $search)); } public function test_empty_both() { $str = ''; $search = ''; $this->assertEmpty(utf8\ifind($str, $search)); } public function test_linefeed_str() { $str = "iñt\nërnâtiônàlizætiøn"; $search = 'NÂT'; $this->assertEquals('nâtiônàlizætiøn', utf8\ifind($str, $search)); } public function test_linefeed_both() { $str = "iñtërn\nâtiônàlizætiøn"; $search = "N\nÂT"; $this->assertEquals("n\nâtiônàlizætiøn", utf8\ifind($str, $search)); } } php-utf-8-1.2.1/tests/cases/Utf8StrlenTest.php000066400000000000000000000011231252061617700210760ustar00rootroot00000000000000assertEquals(20, utf8\len($str)); } public function test_utf8_invalid() { $str = "Iñtërnâtiôn\xe9àlizætiøn"; $this->assertEquals(20, utf8\len($str)); } public function test_ascii() { $str = 'ABC 123'; $this->assertEquals(7, utf8\len($str)); } public function test_empty_str() { $str = ''; $this->assertEquals(0, utf8\len($str)); } } php-utf-8-1.2.1/tests/cases/Utf8StrposTest.php000066400000000000000000000016331252061617700211270ustar00rootroot00000000000000assertEquals(6, utf8\pos($str, 'â')); } public function test_utf8_offset() { $str = 'Iñtërnâtiônàlizætiøn'; $this->assertEquals(19, utf8\pos($str, 'n', 11)); } public function test_utf8_invalid() { $str = "Iñtërnâtiôn\xe9àlizætiøn"; $this->assertEquals(15, utf8\pos($str, 'æ')); } public function test_ascii() { $str = 'ABC 123'; $this->assertEquals(1, utf8\pos($str, 'B')); } public function test_vs_strpos() { $str = 'ABC 123 ABC'; $this->assertEquals(strpos($str, 'B', 3), utf8\pos($str, 'B', 3)); } public function test_empty_str() { $str = ''; $this->assertFalse(utf8\pos($str, 'x')); } } php-utf-8-1.2.1/tests/cases/Utf8StrrevTest.php000066400000000000000000000012231252061617700211150ustar00rootroot00000000000000assertEquals($rev, utf8\reverse($str)); } public function test_empty_str() { $str = ''; $rev = ''; $this->assertEquals($rev, utf8\reverse($str)); } public function test_linefeed() { $str = "Iñtërnâtiôn\nàlizætiøn"; $rev = "nøitæzilà\nnôitânrëtñI"; $this->assertEquals($rev, utf8\reverse($str)); } } php-utf-8-1.2.1/tests/cases/Utf8StrrposTest.php000066400000000000000000000023251252061617700213100ustar00rootroot00000000000000assertEquals(17, utf8\rpos($str, 'i')); } public function test_utf8_offset() { $str = 'Iñtërnâtiônàlizætiøn'; $this->assertEquals(19, utf8\rpos($str, 'n', 11)); } public function test_utf8_invalid() { $str = "Iñtërnâtiôn\xe9àlizætiøn"; $this->assertEquals(15, utf8\rpos($str, 'æ')); } public function test_ascii() { $str = 'ABC ABC'; $this->assertEquals(5, utf8\rpos($str, 'B')); } public function test_vs_strpos() { $str = 'ABC 123 ABC'; $this->assertEquals(strrpos($str, 'B'), utf8\rpos($str, 'B')); } public function test_empty_str() { $str = ''; $this->assertFalse(utf8\rpos($str, 'x')); } public function test_linefeed() { $str = "Iñtërnâtiônàlizætiø\nn"; $this->assertEquals(17, utf8\rpos($str, 'i')); } public function test_linefeed_search() { $str = "Iñtërnâtiônàlizætiø\nn"; $this->assertEquals(19, utf8\rpos($str, "\n")); } } php-utf-8-1.2.1/tests/cases/Utf8StrspnTest.php000066400000000000000000000021151252061617700211220ustar00rootroot00000000000000assertEquals(11, utf8\span($str, 'âëiônñrt')); } public function test_match_two() { $str = 'iñtërnâtiônàlizætiøn'; $this->assertEquals(4, utf8\span($str, 'iñtë')); } public function test_compare_strspn() { $str = 'aeioustr'; $this->assertEquals(strspn($str, 'saeiou'), utf8\span($str, 'saeiou')); } public function test_match_ascii() { $str = 'internationalization'; $this->assertEquals(strspn($str, 'aeionrt'), utf8\span($str, 'aeionrt')); } public function test_linefeed() { $str = "iñtërnât\niônàlizætiøn"; $this->assertEquals(8, utf8\span($str, 'âëiônñrt')); } public function test_linefeed_mask() { $str = "iñtërnât\niônàlizætiøn"; $this->assertEquals(12, utf8\span($str, "âëiônñrt\n")); } } php-utf-8-1.2.1/tests/cases/Utf8StrtolowerTest.php000066400000000000000000000006431252061617700220210ustar00rootroot00000000000000assertEquals($lower, utf8\to_lower($str)); } public function test_empty_string() { $str = ''; $lower = ''; $this->assertEquals($lower, utf8\to_lower($str)); } } php-utf-8-1.2.1/tests/cases/Utf8StrtoupperTest.php000066400000000000000000000006431252061617700220240ustar00rootroot00000000000000assertEquals($upper, utf8\to_upper($str)); } public function test_empty_string() { $str = ''; $upper = ''; $this->assertEquals($upper, utf8\to_upper($str)); } } php-utf-8-1.2.1/tests/cases/Utf8SubstrReplaceTest.php000066400000000000000000000025131252061617700224110ustar00rootroot00000000000000assertEquals($replaced, utf8\sub_replace($str, 'X', 8)); } public function test_empty_string() { $str = ''; $replaced = 'X'; $this->assertEquals($replaced, utf8\sub_replace($str, 'X', 8)); } public function test_negative() { $str = 'testing'; $replaced = substr_replace($str, 'foo', -2, -2); $this->assertEquals($replaced, utf8\sub_replace($str, 'foo', -2, -2)); } public function test_zero() { $str = 'testing'; $replaced = substr_replace($str, 'foo', 0, 0); $this->assertEquals($replaced, utf8\sub_replace($str, 'foo', 0, 0)); } public function test_linefeed() { $str = "Iñ\ntërnâtiônàlizætiøn"; $replaced = "Iñ\ntërnâtX"; $this->assertEquals($replaced, utf8\sub_replace($str, 'X', 9)); } public function test_linefeed_replace() { $str = "Iñ\ntërnâtiônàlizætiøn"; $replaced = "Iñ\ntërnâtX\nY"; $this->assertEquals($replaced, utf8\sub_replace($str, "X\nY", 9)); } } php-utf-8-1.2.1/tests/cases/Utf8SubstrTest.php000066400000000000000000000041271252061617700211200ustar00rootroot00000000000000assertEquals('Iñ', utf8\sub($str, 0, 2)); } public function test_utf8_two() { $str = 'Iñtërnâtiônàlizætiøn'; $this->assertEquals('të', utf8\sub($str, 2, 2)); } public function test_utf8_zero() { $str = 'Iñtërnâtiônàlizætiøn'; $this->assertEquals('Iñtërnâtiônàlizætiøn', utf8\sub($str, 0)); } public function test_utf8_zero_zero() { $str = 'Iñtërnâtiônàlizætiøn'; $this->assertEquals('', utf8\sub($str, 0, 0)); } public function test_start_great_than_length() { $str = 'Iñt'; $this->assertEmpty(utf8\sub($str, 4)); } public function test_compare_start_great_than_length() { $str = 'abc'; $this->assertEquals(substr($str, 4), utf8\sub($str, 4)); } public function test_length_beyond_string() { $str = 'Iñt'; $this->assertEquals('ñt', utf8\sub($str, 1, 5)); } public function test_compare_length_beyond_string() { $str = 'abc'; $this->assertEquals(substr($str, 1, 5), utf8\sub($str, 1, 5)); } public function test_start_negative() { $str = 'Iñtërnâtiônàlizætiøn'; $this->assertEquals('tiøn', utf8\sub($str, -4)); } public function test_length_negative() { $str = 'Iñtërnâtiônàlizætiøn'; $this->assertEquals('nàlizæti', utf8\sub($str, 10, -2)); } public function test_start_length_negative() { $str = 'Iñtërnâtiônàlizætiøn'; $this->assertEquals('ti', utf8\sub($str, -4, -2)); } public function test_linefeed() { $str = "Iñ\ntërnâtiônàlizætiøn"; $this->assertEquals("ñ\ntër", utf8\sub($str, 1, 5)); } public function test_long_length() { $str = 'Iñtërnâtiônàlizætiøn'; $this->assertEquals('Iñtërnâtiônàlizætiøn', utf8\sub($str, 0, 15536)); } } php-utf-8-1.2.1/tests/cases/Utf8ToAsciiTest.php000066400000000000000000000016561252061617700211750ustar00rootroot00000000000000assertEquals('testig', utf8\to_ascii($str)); } public function test_ascii() { $str = 'testing'; $this->assertEquals('testing', utf8\to_ascii($str)); } public function test_invalid_char() { $str = "tes\xe9ting"; $this->assertEquals('testing', utf8\to_ascii($str)); } public function test_empty_str() { $str = ''; $this->assertEmpty(utf8\to_ascii($str)); } public function test_nul_and_non_7_bit() { $str = "a\x00ñ\x00c"; $this->assertEquals('ac', utf8\to_ascii($str, 'both')); } public function test_nul() { $str = "a\x00b\x00c"; $this->assertEquals('abc', utf8\to_ascii($str, 'ctrl_chars')); } } php-utf-8-1.2.1/tests/cases/Utf8ToUnicodeTest.php000066400000000000000000000016611252061617700215270ustar00rootroot00000000000000assertEquals(array(), utf8\to_unicode('')); } public function test_string() { $unicode = array(); $unicode[0] = 73; $unicode[1] = 241; $unicode[2] = 116; $unicode[3] = 235; $unicode[4] = 114; $unicode[5] = 110; $unicode[6] = 226; $unicode[7] = 116; $unicode[8] = 105; $unicode[9] = 244; $unicode[10] = 110; $unicode[11] = 224; $unicode[12] = 108; $unicode[13] = 105; $unicode[14] = 122; $unicode[15] = 230; $unicode[16] = 116; $unicode[17] = 105; $unicode[18] = 248; $unicode[19] = 110; $this->assertEquals($unicode, utf8\to_unicode('Iñtërnâtiônàlizætiøn')); } } php-utf-8-1.2.1/tests/cases/Utf8TrimTest.php000066400000000000000000000012451252061617700205470ustar00rootroot00000000000000assertEquals($trimmed, utf8\trim($str, 'ñø')); } public function test_no_trim() { $str = ' Iñtërnâtiônàlizætiøn '; $trimmed = ' Iñtërnâtiônàlizætiøn '; $this->assertEquals($trimmed, utf8\trim($str, 'ñø')); } public function test_empty_string() { $str = ''; $trimmed = ''; $this->assertEquals($trimmed, utf8\trim($str)); } } php-utf-8-1.2.1/tests/cases/Utf8UcfirstTest.php000066400000000000000000000023131252061617700212500ustar00rootroot00000000000000assertEquals($ucfirst, utf8\ucfirst($str)); } public function test_ucfirst_space() { $str = ' iñtërnâtiônàlizætiøn'; $ucfirst = ' iñtërnâtiônàlizætiøn'; $this->assertEquals($ucfirst, utf8\ucfirst($str)); } public function test_ucfirst_upper() { $str = 'Ñtërnâtiônàlizætiøn'; $ucfirst = 'Ñtërnâtiônàlizætiøn'; $this->assertEquals($ucfirst, utf8\ucfirst($str)); } public function test_empty_string() { $str = ''; $this->assertEquals('', utf8\ucfirst($str)); } public function test_one_char() { $str = 'ñ'; $ucfirst = "Ñ"; $this->assertEquals($ucfirst, utf8\ucfirst($str)); } public function test_linefeed() { $str = "ñtërn\nâtiônàlizætiøn"; $ucfirst = "Ñtërn\nâtiônàlizætiøn"; $this->assertEquals($ucfirst, utf8\ucfirst($str)); } } php-utf-8-1.2.1/tests/cases/Utf8UcwordsTest.php000066400000000000000000000023311252061617700212570ustar00rootroot00000000000000assertEquals($ucwords, utf8\ucwords($str)); } public function test_ucwords() { $str = 'iñt ërn âti ônà liz æti øn'; $ucwords = 'Iñt Ërn Âti Ônà Liz Æti Øn'; $this->assertEquals($ucwords, utf8\ucwords($str)); } public function test_ucwords_newline() { $str = "iñt ërn âti\n ônà liz æti øn"; $ucwords = "Iñt Ërn Âti\n Ônà Liz Æti Øn"; $this->assertEquals($ucwords, utf8\ucwords($str)); } public function test_empty_string() { $str = ''; $ucwords = ''; $this->assertEquals($ucwords, utf8\ucwords($str)); } public function test_one_char() { $str = 'ñ'; $ucwords = 'Ñ'; $this->assertEquals($ucwords, utf8\ucwords($str)); } public function test_linefeed() { $str = "iñt ërn âti\n ônà liz æti øn"; $ucwords = "Iñt Ërn Âti\n Ônà Liz Æti Øn"; $this->assertEquals($ucwords, utf8\ucwords($str)); } } php-utf-8-1.2.1/tests/data/000077500000000000000000000000001252061617700153255ustar00rootroot00000000000000php-utf-8-1.2.1/tests/data/utf8.html000066400000000000000000001233461252061617700171120ustar00rootroot00000000000000 UTF-8 SAMPLER ¥ · £ · € · $ · ¢ · ₡ · ₢ · ₣ · ₤ · ₥ · ₦ · ₧ · ₨ · ₩ · ₪ · ₫ · ₭ · ₮ · ₯ Frank da Cruz The Kermit Project - Columbia University New York City fdc@columbia.edu /Last update:/ Sun Jun 12 20:24:10 2005 ------------------------------------------------------------------------ [ PEACE ] [ Poetry <#poetry> ] [ I Can Eat Glass <#glass> ] [ The Quick Brown Fox <#quickbrownfox> ] [ HTML Features <#html> ] [ Credits, Tools, Commentary <#credits> ] UTF-8 is an ASCII-preserving encoding method for Unicode (ISO 10646), the Universal Character Set (UCS). The UCS encodes most of the world's writing systems in a single character set, allowing you to mix languages and scripts within a document without needing any tricks for switching character sets. This web page is encoded directly in UTF-8. As shown HERE , Columbia University's Kermit 95 terminal emulation software can display UTF-8 plain text in Windows 95, 98, ME, NT, XP, or 2000 when using a monospace Unicode font like Andale Mono WT J or Everson Mono Terminal , or the lesser populated Courier New, Lucida Console, or Andale Mono. C-Kermit can handle it too, if you have a Unicode display . As many languages as are representable in your font can be seen on the screen at the same time. This, however, is a Web page. Some Web browsers can handle UTF-8, some can't. And those that can might not have a sufficiently populated font to work with (some browsers might pick glyphs dynamically from multiple fonts; Netscape 6 seems to do this). CLICK HERE for a survey of Unicode fonts for Windows. The subtitle above shows currency symbols of many lands. If they don't appear as blobs, we're off to a good start! ------------------------------------------------------------------------ Poetry From the Anglo-Saxon Rune Poem (Rune version): ᚠᛇᚻ᛫ᛒᛦᚦ᛫ᚠᚱᚩᚠᚢᚱ᛫ᚠᛁᚱᚪ᛫ᚷᛖᚻᚹᛦᛚᚳᚢᛗ ᛋᚳᛖᚪᛚ᛫ᚦᛖᚪᚻ᛫ᛗᚪᚾᚾᚪ᛫ᚷᛖᚻᚹᛦᛚᚳ᛫ᛗᛁᚳᛚᚢᚾ᛫ᚻᛦᛏ᛫ᛞᚫᛚᚪᚾ ᚷᛁᚠ᛫ᚻᛖ᛫ᚹᛁᛚᛖ᛫ᚠᚩᚱ᛫ᛞᚱᛁᚻᛏᚾᛖ᛫ᛞᚩᛗᛖᛋ᛫ᚻᛚᛇᛏᚪᚾ᛬ From Laȝamon's/ Brut / (/The Chronicles of England/, Middle English, West Midlands): An preost wes on leoden, Laȝamon was ihoten He wes Leovenaðes sone -- liðe him be Drihten. He wonede at Ernleȝe at æðelen are chirechen, Uppen Sevarne staþe, sel þar him þuhte, Onfest Radestone, þer he bock radde. (The third letter in the author's name is Yogh, missing from many fonts; CLICK HERE for another Middle English sample with some explanation of letters and encoding). From the Tagelied of *Wolfram von Eschenbach* (Middle High German): Sîne klâwen durh die wolken sint geslagen, er stîget ûf mit grôzer kraft, ich sih in grâwen tägelîch als er wil tagen, den tac, der im geselleschaft erwenden wil, dem werden man, den ich mit sorgen în verliez. ich bringe in hinnen, ob ich kan. sîn vil manegiu tugent michz leisten hiez. Some lines of *Odysseus Elytis* (Greek): Τη γλώσσα μου έδωσαν ελληνική το σπίτι φτωχικό στις αμμουδιές του Ομήρου. Μονάχη έγνοια η γλώσσα μου στις αμμουδιές του Ομήρου. από το Άξιον Εστί του Οδυσσέα Ελύτη The first stanza of *Pushkin* 's Bronze Horseman (Russian): На берегу пустынных волн Стоял он, дум великих полн, И вдаль глядел. Пред ним широко Река неслася; бедный чёлн По ней стремился одиноко. По мшистым, топким берегам Чернели избы здесь и там, Приют убогого чухонца; И лес, неведомый лучам В тумане спрятанного солнца, Кругом шумел. *Šota Rustaveli* 's Veṗxis Ṭq̇aosani, ̣︡Th, The Knight in the Tiger's Skin (Georgian): ვეპხის ტყაოსანი შოთა რუსთაველი ღმერთსი შემვედრე, ნუთუ კვლა დამხსნას სოფლისა შრომასა, ცეცხლს, წყალსა და მიწასა, ჰაერთა თანა მრომასა; მომცნეს ფრთენი და აღვფრინდე, მივჰხვდე მას ჩემსა ნდომასა, დღისით და ღამით ვჰხედვიდე მზისა ელვათა კრთომაასა. Tamil poetry of Cupiramaniya Paarathiyar, சுப்ரமணிய பாரதியார் (1882-1921): யாமறிந்த மொழிகளிலே தமிழ்மொழி போல் இனிதாவது எங்கும் காணோம், பாமரராய் விலங்குகளாய், உலகனைத்தும் இகழ்ச்சிசொலப் பான்மை கெட்டு, நாமமது தமிழரெனக் கொண்டு இங்கு வாழ்ந்திடுதல் நன்றோ? சொல்லீர்! ------------------------------------------------------------------------ I Can Eat Glass And from the sublime to the ridiculous, here is a certain phrase¹ <#notes> in an assortment of languages: 1. *Sanskrit*: काचं शक्नोम्यत्तुम् । नोपहिनस्ति माम् ॥ 2. *Sanskrit* /(standard transcription):/ kācaṃ śaknomyattum; nopahinasti mām. 3. *Classical Greek*: ὕαλον ϕαγεῖν δύναμαι· τοῦτο οὔ με βλάπτει. 4. *Greek*: Μπορώ να φάω σπασμένα γυαλιά χωρίς να πάθω τίποτα. *Etruscan*: (NEEDED) 5. *Latin*: Vitrum edere possum; mihi non nocet. 6. *Old French*: Je puis mangier del voirre. Ne me nuit. 7. *French*: Je peux manger du verre, ça ne me fait pas de mal. 8. *Provençal / Occitan*: Pòdi manjar de veire, me nafrariá pas. 9. *Québécois*: J'peux manger d'la vitre, ça m'fa pas mal. 10. *Walloon*: Dji pou magnî do vêre, çoula m' freut nén må. *Champenois*: (NEEDED) *Lorrain*: (NEEDED) 11. *Picard*: Ch'peux mingi du verre, cha m'foé mie n'ma. *Corsican*: (NEEDED) 12. *Kreyòl Ayisyen*: Mwen kap manje vè, li pa blese'm. 13. *Basque*: Kristala jan dezaket, ez dit minik ematen. 14. *Catalan*: Puc menjar vidre que no em fa mal. 15. *Spanish*: Puedo comer vidrio, no me hace daño. 16. *Aragones*: Puedo minchar beire, no me'n fa mal . 17. *Galician*: Eu podo xantar cristais e non cortarme. 18. *Portuguese*: Posso comer vidro, não me faz mal. 19. *Brazilian Portuguese* (7 <#notes>): Posso comer vidro, não me machuca. 20. *Caboverdiano*: M' podê cumê vidru, ca ta maguâ-m'. 21. *Papiamentu*: Ami por kome glas anto e no ta hasimi daño. 22. *Italian*: Posso mangiare il vetro e non mi fa male. 23. *Milanese*: Sôn bôn de magnà el véder, el me fa minga mal. 24. *Roman*: Me posso magna' er vetro, e nun me fa male. 25. *Napoletano*: M' pozz magna' o'vetr, e nun m' fa mal. 26. *Sicilian*: Puotsu mangiari u vitru, nun mi fa mali. 27. *Venetian*: Mi posso magnare el vetro, no'l me fa mae. 28. *Zeneise* /(Genovese):/ Pòsso mangiâ o veddro e o no me fà mâ. *Rheto-Romance / Romansch*: (NEEDED) *Romany / Tsigane*: (NEEDED) 29. *Romanian*: Pot să mănânc sticlă și ea nu mă rănește. 30. *Esperanto*: Mi povas manĝi vitron, ĝi ne damaĝas min. *Pictish*: (NEEDED) *Breton*: (NEEDED) 31. *Cornish*: Mý a yl dybry gwéder hag éf ny wra ow ankenya. 32. *Welsh*: Dw i'n gallu bwyta gwydr, 'dyw e ddim yn gwneud dolur i mi. 33. *Manx Gaelic*: Foddym gee glonney agh cha jean eh gortaghey mee. 34. *Old Irish* /(Ogham):/ ᚛᚛ᚉᚑᚅᚔᚉᚉᚔᚋ ᚔᚈᚔ ᚍᚂᚐᚅᚑ ᚅᚔᚋᚌᚓᚅᚐ᚜ 35. *Old Irish* /(Latin):/ Con·iccim ithi nglano. Ním·géna. 36. *Irish*: Is féidir liom gloinne a ithe. Ní dhéanann sí dochar ar bith dom. 37. *Scottish Gaelic*: S urrainn dhomh gloinne ithe; cha ghoirtich i mi. 38. *Anglo-Saxon* /(Runes):/ ᛁᚳ᛫ᛗᚨᚷ᛫ᚷᛚᚨᛋ᛫ᛖᚩᛏᚪᚾ᛫ᚩᚾᛞ᛫ᚻᛁᛏ᛫ᚾᛖ᛫ᚻᛖᚪᚱᛗᛁᚪᚧ᛫ᛗᛖ᛬ 39. *Anglo-Saxon* /(Latin):/ Ic mæg glæs eotan ond hit ne hearmiað me. 40. *Middle English*: Ich canne glas eten and hit hirtiþ me nouȝt. 41. *English*: I can eat glass and it doesn't hurt me. 42. *English* /(IPA):/ [aɪ kæn iːt glɑːs ænd ɪt dɐz nɒt hɜːt miː] (Received Pronunciation) 43. *English* /(Braille):/ ⠊⠀⠉⠁⠝⠀⠑⠁⠞⠀⠛⠇⠁⠎⠎⠀⠁⠝⠙⠀⠊⠞⠀⠙⠕⠑⠎⠝⠞⠀⠓⠥⠗⠞⠀⠍⠑ 44. *Lalland Scots / Doric*: Ah can eat gless, it disnae hurt us. *Glaswegian*: (NEEDED) 45. *Gothic* (4 <#notes>): 𐌼𐌰𐌲 𐌲𐌻𐌴𐍃 𐌹̈𐍄𐌰𐌽, 𐌽𐌹 𐌼𐌹𐍃 𐍅𐌿 𐌽𐌳𐌰𐌽 𐌱𐍂𐌹𐌲𐌲𐌹𐌸. 46. *Old Norse* /(Runes):/ ᛖᚴ ᚷᛖᛏ ᛖᛏᛁ ᚧ ᚷᛚᛖᚱ ᛘᚾ ᚦᛖᛋᛋ ᚨᚧ ᚡᛖ ᚱᚧᚨ ᛋᚨᚱ 47. *Old Norse* /(Latin):/ Ek get etið gler án þess að verða sár. 48. *Norsk / Norwegian (Nynorsk):* Eg kan eta glas utan å skada meg. 49. *Norsk / Norwegian (Bokmål):* Jeg kan spise glass uten å skade meg. *Føroyskt / Faroese*: (NEEDED) 50. *Íslenska / Icelandic*: Ég get etið gler án þess að meiða mig. 51. *Svenska / Swedish*: Jag kan äta glas utan att skada mig. 52. *Dansk / Danish*: Jeg kan spise glas, det gør ikke ondt på mig. 53. *Soenderjysk*: Æ ka æe glass uhen at det go mæ naue. 54. *Frysk / Frisian*: Ik kin glês ite, it docht me net sear. 55. *Nederlands / Dutch*: Ik kan glas eten, het doet mij geen kwaad. 56. *Kirchröadsj/Bôchesserplat*: Iech ken glaas èèse, mer 't deet miech jing pieng. 57. *Afrikaans*: Ek kan glas eet, maar dit doen my nie skade nie. 58. *Lëtzebuergescht / Luxemburgish*: Ech kan Glas iessen, daat deet mir nët wei. 59. *Deutsch / German*: Ich kann Glas essen, ohne mir weh zu tun. 60. *Ruhrdeutsch*: Ich kann Glas verkasematuckeln, ohne dattet mich wat jucken tut. 61. *Lausitzer Mundart* ("Lusatian"): Ich koann Gloos assn und doas dudd merr ni wii. 62. *Odenwälderisch*: Iech konn glaasch voschbachteln ohne dass es mir ebbs daun doun dud. 63. *Sächsisch / Saxon*: 'sch kann Glos essn, ohne dass'sch mer wehtue. 64. *Pfälzisch*: Isch konn Glass fresse ohne dasses mer ebbes ausmache dud. 65. *Schwäbisch / Swabian*: I kå Glas frässa, ond des macht mr nix! 66. *Bayrisch / Bavarian*: I koh Glos esa, und es duard ma ned wei. 67. *Allemannisch*: I kaun Gloos essen, es tuat ma ned weh. 68. *Schwyzerdütsch*: Ich chan Glaas ässe, das tuet mir nöd weeh. 69. *Hungarian*: Meg tudom enni az üveget, nem lesz tőle bajom. 70. *Suomi / Finnish*: Voin syödä lasia, se ei vahingoita minua. 71. *Sami (Northern)*: Sáhtán borrat lása, dat ii leat bávččas. 72. *Erzian*: Мон ярсан суликадо, ды зыян эйстэнзэ а ули. *Karelian*: (NEEDED) *Vepsian*: (NEEDED) *Votian*: (NEEDED) *Livonian*: (NEEDED) 73. *Estonian*: Ma võin klaasi süüa, see ei tee mulle midagi. 74. *Latvian*: Es varu ēst stiklu, tas man nekaitē. 75. *Lithuanian*: Aš galiu valgyti stiklą ir jis manęs nežeidžia *Old Prussian*: (NEEDED) *Sorbian* (Wendish): (NEEDED) 76. *Czech*: Mohu jíst sklo, neublíží mi. 77. *Slovak*: Môžem jesť sklo. Nezraní ma. 78. *Polska / Polish*: Mogę jeść szkło i mi nie szkodzi. 79. *Slovenian:* Lahko jem steklo, ne da bi mi škodovalo. 80. *Croatian*: Ja mogu jesti staklo i ne boli me. 81. *Serbian* /(Latin):/ Mogu jesti staklo a da mi ne škodi. 82. *Serbian* /(Cyrillic):/ Могу јести стакло а да ми не шкоди. 83. *Macedonian:* Можам да јадам стакло, а не ме штета. 84. *Russian*: Я могу есть стекло, оно мне не вредит. 85. *Belarusian* /(Cyrillic):/ Я магу есці шкло, яно мне не шкодзіць. 86. *Belarusian* /(Lacinka):/ Ja mahu jeści škło, jano mne ne škodzić. 87. *Ukrainian*: Я можу їсти шкло, й воно мені не пошкодить. 88. *Bulgarian*: Мога да ям стъкло, то не ми вреди. 89. *Georgian*: მინას ვჭამ და არა მტკივა. 90. *Armenian*: Կրնամ ապակի ուտել և ինծի անհանգիստ չըներ։ 91. *Albanian*: Unë mund të ha qelq dhe nuk më gjen gjë. 92. *Turkish*: Cam yiyebilirim, bana zararı dokunmaz. 93. *Turkish* /(Ottoman):/ جام ييه بلورم بڭا ضررى طوقونمز 94. *Bangla / Bengali*: আমি কাঁচ খেতে পারি, তাতে আমার কোনো ক্ষতি হয় না। 95. *Marathi*: मी काच खाऊ शकतो, मला ते दुखत नाही. 96. *Hindi*: मैं काँच खा सकता हूँ, मुझे उस से कोई पीडा नहीं होती. 97. *Tamil*: நான் கண்ணாடி சாப்பிடுவேன், அதனால் எனக்கு ஒரு கேடும் வராது. 98. *Urdu*(2) <#notes>: میں کانچ کھا سکتا ہوں اور مجھے تکلیف نہیں ہوتی ۔ 99. *Pashto*(2) <#notes>: زه شيشه خوړلې شم، هغه ما نه خوږوي 100. *Farsi / Persian*: .من می توانم بدونِ احساس درد شيشه بخورم 101. *Arabic*(2) <#notes>: أنا قادر على أكل الزجاج و هذا لا يؤلمني. *Aramaic*: (NEEDED) 102. *Hebrew*(2) <#notes>: אני יכול לאכול זכוכית וזה לא מזיק לי. 103. *Yiddish*(2) <#notes>: איך קען עסן גלאָז און עס טוט מיר נישט װײ. *Judeo-Arabic*: (NEEDED) *Ladino*: (NEEDED) *Gǝʼǝz*: (NEEDED) *Amharic*: (NEEDED) 104. *Twi*: Metumi awe tumpan, ɜnyɜ me hwee. 105. *Hausa* (/Latin/): Inā iya taunar gilāshi kuma in gamā lāfiyā. 106. *Hausa* (/Ajami/) (2) <#notes>: إِنا إِىَ تَونَر غِلَاشِ كُمَ إِن غَمَا لَافِىَا 107. *Yoruba*(3) <#notes>: Mo lè je̩ dígí, kò ní pa mí lára. 108. *(Ki)Swahili*: Naweza kula bilauri na sikunyui. 109. *Malay*: Saya boleh makan kaca dan ia tidak mencederakan saya. 110. *Tagalog*: Kaya kong kumain nang bubog at hindi ako masaktan. 111. *Chamorro*: Siña yo' chumocho krestat, ti ha na'lalamen yo'. 112. *Javanese*: Aku isa mangan beling tanpa lara. *Burmese*: (NEEDED) 113. *Vietnamese (quốc ngữ)*: Tôi có thể ăn thủy tinh mà không hại gì. 114. *Vietnamese (nôm)* (4 <#notes>): 些 𣎏 世 咹 水 晶 𦓡 空 𣎏 害 咦 *Khmer*: (NEEDED) *Lao*: (NEEDED) 115. *Thai*: ฉันกินกระจกได้ แต่มันไม่ทำให้ฉันเจ็บ 116. *Mongolian* /(Cyrillic):/ Би шил идэй чадна, надад хортой биш 117. *Mongolian* /(Classic) (5 <#notes>):/ ᠪᠢ ᠰᠢᠯᠢ ᠢᠳᠡᠶᠦ ᠴᠢᠳᠠᠨᠠ ᠂ ᠨᠠᠳᠤᠷ ᠬᠣᠤᠷᠠᠳᠠᠢ ᠪᠢᠰᠢ *Dzongkha*: (NEEDED) *Nepali*: (NEEDED) 118. *Tibetan*: ཤེལ་སྒོ་ཟ་ནས་ང་ན་གི་མ་རེད། 119. *Chinese*: 我能吞下玻璃而不伤身体。 120. *Chinese* (Traditional): 我能吞下玻璃而不傷身體。 121. *Taiwanese*(6) <#notes>: Góa ē-tàng chia̍h po-lê, mā bē tio̍h-siong. 122. *Japanese*: 私はガラスを食べられます。それは私を傷つけません。 123. *Korean*: 나는 유리를 먹을 수 있어요. 그래도 아프지 않아요 124. *Bislama*: Mi save kakae glas, hemi no save katem mi. 125. *Hawaiian*: Hiki iaʻu ke ʻai i ke aniani; ʻaʻole nō lā au e ʻeha. 126. *Marquesan*: E koʻana e kai i te karahi, mea ʻā, ʻaʻe hauhau. 127. *Chinook Jargon:* Naika məkmək kakshət labutay, pi weyk ukuk munk-sik nay. 128. *Navajo*: Tsésǫʼ yishą́ągo bííníshghah dóó doo shił neezgai da. *Cherokee* /(and Cree, Ojibwa, Inuktitut, and other Native American languages):/ (NEEDED) *Garifuna*: (NEEDED) *Gullah*: (NEEDED) 129. *Lojban*: mi kakne le nu citka le blaci .iku'i le se go'i na xrani mi 130. *Nórdicg*: Ljœr ye caudran créneþ ý jor cẃran. /(Additions, corrections, completions,/ /gratefully accepted/ /.)/ For testing purposes, some of these are repeated in a *monospace font* . . . 1. Euro Symbol: €. 2. Greek: Μπορώ να φάω σπασμένα γυαλιά χωρίς να πάθω τίποτα. 3. Íslenska / Icelandic: Ég get etið gler án þess að meiða mig. 4. Polish: Mogę jeść szkło, i mi nie szkodzi. 5. Romanian: Pot să mănânc sticlă și ea nu mă rănește. 6. Ukrainian: Я можу їсти шкло, й воно мені не пошкодить. 7. Armenian: Կրնամ ապակի ուտել և ինծի անհանգիստ չըներ։ 8. Georgian: მინას ვჭამ და არა მტკივა. 9. Hindi: मैं काँच खा सकता हूँ, मुझे उस से कोई पीडा नहीं होती. 10. Hebrew(2) <#notes>: אני יכול לאכול זכוכית וזה לא מזיק לי. 11. Yiddish(2) <#notes>: איך קען עסן גלאָז און עס טוט מיר נישט װײ. 12. Arabic(2) <#notes>: أنا قادر على أكل الزجاج و هذا لا يؤلمني. 13. Japanese: 私はガラスを食べられます。それは私を傷つけません。 14. Thai: ฉันกินกระจกได้ แต่มันไม่ทำให้ฉันเจ็บ *Notes:* 1. The "I can eat glass" phrase and initial translations (about 30 of them) were borrowed from Ethan Mollick's I Can Eat Glass page (which disappeared on or about June 2004) and converted to UTF-8. Since Ethan's original page is gone, I should mention that his purpose was offer travelers a phrase they could use in any country that would command a certain kind of respect, or at least get attention. See Credits <#credits> for the many additional contributions since then. When submitting new entries, the word "hurt" (if you have a choice) is used in the sense of "cause harm", "do damage", or "bother", rather than "inflict pain" or "make sad". In this vein Otto Stolz comments (as do others further down; personally I think it's better for the purpose of this page to have extra entries and/or to show a greater repertoire of characters than it is to enforce a strict interpretation of the word "hurt"!): This is the meaning I have translated to the Swabian dialect. However, I just have noticed that most of the German variants translate the "inflict pain" meaning. The German example should rather read: "Ich kann Glas essen ohne mir zu schaden." (The comma fell victim to the 1996 orthographic reform, cf. http://www.ids-mannheim.de/reform/e3-1.html#P76. You may wish to contact the contributors of the following translations to correct them: * Lëtzebuergescht / Luxemburgish: Ech kan Glas iessen, daat deet mir nët wei. * Lausitzer Mundart ("Lusatian"): Ich koann Gloos assn und doas dudd merr ni wii. * Sächsisch / Saxon: 'sch kann Glos essn, ohne dass'sch mer wehtue. * Bayrisch / Bavarian: I koh Glos esa, und es duard ma ned wei. * Allemannisch: I kaun Gloos essen, es tuat ma ned weh. * Schwyzerdütsch: Ich chan Glaas ässe, das tuet mir nöd weeh. In contrast, I deem the following translations *alright*: * Ruhrdeutsch: Ich kann Glas verkasematuckeln, ohne dattet mich wat jucken tut. * Pfälzisch: Isch konn Glass fresse ohne dasses mer ebbes ausmache dud. * Schwäbisch / Swabian: I kå Glas frässa, ond des macht mr nix! (However, you could remove the commas, on account of http://www.ids-mannheim.de/reform/e3-1.html#P76 and http://www.ids-mannheim.de/reform/e3-1.html#P72, respectively.) I guess, also these examples translate the /wrong/ sense of "hurt", though I do not know these languages well enough to assert them definitely: * Nederlands / Dutch: Ik kan glas eten; het doet mij geen pijn. /(This one has been changed)/ * Kirchröadsj/Bôchesserplat: Iech ken glaas èèse, mer 't deet miech jing pieng. In the Romanic languages, the variations on "fa male" (it) are probably wrong, whilst the variations on "hace daño" (es) and "damaĝas" (Esperanto) are probably correct; "nocet" (la) is definitely right. The northern Germanic variants of "skada" are probably right, as are the Slavic variants of "škodi/шкоди" (se); however the Slavic variants of " boli" (hv) are probably wrong, as "bolena" means "pain/ache", IIRC. The numbering of the samples is arbitrary, done only to keep track of how many there are, and can change any time a new entry is added. The arrangement is also arbitrary but with some attempt to group related examples together. Note: All languages not listed are wanted, not just the ones that say (NEEDED). 2. Correct right-to-left display of these languages depends on the capabilities of your browser. The period should appear on the left. In the monospace Yiddish example, the Yiddish digraphs should occupy one character cell. 3. Yoruba: The third word is Latin letter small 'j' followed by small 'e' with U+0329, Combining Vertical Line Below. This displays correctly only if your Unicode font includes the U+0329 glyph and your browser supports combining diacritical marks. The Indic examples also include combining sequences. 4. Includes Unicode 3.1 (or later) characters beyond Plane 0. 5. The Classic Mongolian example should be vertical, top-to-bottom and left-to-right. But such display is almost impossible. Also no font yet exists which provides the proper ligatures and positional variants for the characters of this script, which works somewhat like Arabic. 6. Taiwanese is also known as Holo or Hoklo, and is related to Southern Min dialects such as Amoy. Contributed by Henry H. Tan-Tenn, who comments, "The above is the romanized version, in a script current among Taiwanese Christians since the mid-19th century. It was invented by British missionaries and saw use in hundreds of published works, mostly of a religious nature. Most Taiwanese did not know Chinese characters then, or at least not well enough to read. More to the point, though, a written standard using Chinese characters has never developed, so a significant minority of words are represented with different candidate characters, depending on one's personal preference or etymological theory. In this sentence, for example, "-tàng", "chia̍h", "mā" and "bē" are problematic using Chinese characters. "Góa" (I/me) and "po-lê" (glass) are as written in other Sinitic languages (e.g. Mandarin, Hakka)." 7. Wagner Amaral of Pinese & Amaral Associados notes that the Brazilian Portuguese sentence for "I can eat glass" should be identical to the Portuguese one, as the word "machuca" means "inflict pain", or rather "injuries". The words "faz mal" would more correctly translate as "cause harm". ------------------------------------------------------------------------ The Quick Brown Fox The "I can eat glass" sentences do not necessarily show off the orthography of each language to best advantage. In many alphabetic written languages it is possible to include all (or most) letters (or "special" characters) in a single (often nonsense) /pangram/. These were traditionally used in typewriter instruction; now they are useful for stress-testing computer fonts and keyboard input methods. Here are a few examples (SEND MORE): 1. *English:* The quick brown fox jumps over the lazy dog. 2. *Irish:* "An ḃfuil do ċroí ag bualaḋ ó ḟaitíos an ġrá a ṁeall lena ṗóg éada ó ṡlí do leasa ṫú?" "D'ḟuascail Íosa Úrṁac na hÓiġe Beannaiṫe pór Éava agus Áḋaiṁ." 3. *Dutch:* Pa's wijze lynx bezag vroom het fikse aquaduct. 4. *German: * Falsches Üben von Xylophonmusik quält jeden größeren Zwerg. (1) 5. *German: * Im finſteren Jagdſchloß am offenen Felsquellwaſſer patzte der affig-flatterhafte kauzig-höf‌liche Bäcker über ſeinem verſifften kniffligen C-Xylophon. (2) 6. *Swedish:* Flygande bäckasiner söka strax hwila på mjuka tuvor. 7. *Czech:* Příliš žluťoučký kůň úpěl ďábelské kódy. 8. *Slovak:* Starý kôň na hŕbe kníh žuje tíško povädnuté ruže, na stĺpe sa ďateľ učí kvákať novú ódu o živote. 9. *Russian:* В чащах юга жил-был цитрус? Да, но фальшивый экземпляр! ёъ. 10. *Bulgarian:* Жълтата дюля беше щастлива, че пухът, който цъфна, замръзна като гьон. 11. *Sami (Northern):* Vuol Ruoŧa geđggiid leat máŋga luosa ja čuovžža. 12. *Hungarian:* Árvíztűrő tükörfúrógép. 13. *Spanish:* El pingüino Wenceslao hizo kilómetros bajo exhaustiva lluvia y frío, añoraba a su querido cachorro. 14. *Portuguese:* O próximo vôo à noite sobre o Atlântico, põe freqüentemente o único médico. (3) 15. *French:* Les naïfs ægithales hâtifs pondant à Noël où il gèle sont sûrs d'être déçus et de voir leurs drôles d'œufs abîmés. 16. *Esperanto:* Eĥoŝanĝo ĉiuĵaŭde. 17. *Hebrew:* זה כיף סתם לשמוע איך תנצח קרפד עץ טוב בגן. 18. *Japanese* (Hiragana): いろはにほへど　ちりぬるを わがよたれぞ　つねならむ うゐのおくやま　けふこえて あさきゆめみじ　ゑひもせず (4) *Notes:* 1. Other phrases commonly used in Germany include: "Ein wackerer Bayer vertilgt ja bequem zwo Pfund Kalbshaxe" and, more recently, "Franz jagt im komplett verwahrlosten Taxi quer durch Bayern", but both lack umlauts and esszet. Previously, going for the shortest sentence that has all the umlauts and special characters, I had "Grüße aus Bärenhöfe (und Óechtringen)!" Acute accents are not used in native German words, so I was surprised to discover "Óechtringen" in the Deutsche Bundespost Postleitzahlenbuch (Vorsicht! 2.8MB JPG image). It's a small village in eastern Lower Saxony. The "oe" in this case turns out to be the Lower Saxon "lengthening e" (Dehnungs-e), which makes the previous vowel long (used in a number of Lower Saxon place names such as Soest and Itzehoe), not the "e" that indicates umlaut of the preceding vowel. Many thanks to the Óechtringen-Namenschreibungsuntersuchungskomitee (Alex Bochannek, Manfred Erren, Asmus Freytag, Christoph Päper, plus Werner Lemberg who serves as the Óechtringen-Namenschreibungsuntersuchungskomiteerechtschreibungsprüfer) for their relentless pursuit of the facts in this case. Conclusion: the accent almost certainly does not belong on this (or any other native German) word, but neither can it be dismissed as dirt on the page. To add to the mystery, it has been reported that other copies of the same edition of the PLZB do not show the accent! 2. From Karl Pentzlin (Kochel am See, Bavaria, Germany): "This German phrase is suited for display by a Fraktur (broken letter) font. It contains: all common three-letter ligatures: ffi ffl fft and all two-letter ligatures required by the Duden for Fraktur typesetting: ch ck ff fi fl ft ll ſch ſi ſſ ſt tz (all in a manner such they are not part of a three-letter ligature), one example of f-l where German typesetting rules prohibit ligating (marked by a ZWNJ), and all German letters a...z, ä,ö,ü,ß, ſ [long s] (all in a manner such that they are not part of a two-letter Fraktur ligature)." Otto Stolz notes that "'Schloß' is now spelled 'Schloss', in contrast to 'größer' (example 4) which has kept its 'ß'. Fraktur has been banned from general use, in 1942, and long-s (ſ) has ceased to be used with Antiqua (Roman) even earlier (the latest Antiqua-ſ I have seen is from 1913, but then I am no expert, so there may well be a later instance." Later Otto confirms the latter theory, "Now I've run across a book “Deutsche Rechtschreibung” (edited by Lutz Mackensen) from 1954 (my reprint is from 1956) that has kept the Antiqua-ſ in its dictionary part (but neither in the preface nor in the appendix)." 3. Diaeresis is not used in Iberian Portuguese. 4. From Yurio Miyazawa: "This poetry contains all the sounds in the Japanese language and used to be the first thing for children to learn in their Japanese class. The Hiragana version is particularly neat because it covers every character in the phonetic Hiragana character set." Yurio also sent the Kanji version: 色は匂へど 散りぬるを 我が世誰ぞ 常ならむ 有為の奥山 今日越えて 浅き夢見じ 酔ひもせず *Accented Cyrillic:* /(This section contributed by Vladimir Marinov.)/ In Bulgarian it is desirable, customary, or in some cases required to write accents over vowels. Unfortunately, no computer character sets contain the full repertoire of accented Cyrillic letters. With Unicode, however, it is possible to combine any Cyrillic letter with any combining accent. The appearance of the result depends on the font and the rendering engine. Here are two examples. 1. Той видя бялата коса́ по главата и́ и ко́са на рамото и́, и ре́че да и́ рече́: "Пара́та по́ па́ри от па́рата, не ща пари́!", но си поми́сли: "Хей, помисли́ си! А́ и́ река, а́ е скочила в тази река, която щеше да тече́, а не те́че." 2. По пъ́тя пъту́ват кю́рди и югославя́ни. ------------------------------------------------------------------------ HTML Features Here is the Russian alphabet (uppercase only) coded in three different ways, which should look identical: 1. АБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЫЬЭЮЯ /(Literal UTF-8)/ 2. АБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЫЬЭЮЯ /(Decimal numeric character reference)/ 3. АБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЫЬЭЮЯ /(Hexadecimal numeric character reference)/ In another test, we use HTML language tags to distinguish Bulgarian, Russian, and Serbian , which have different italic forms for lowercase б, г, д, п, and/or т: *Bulgarian*: [ бгдпт ] [ /бгдпт/ ] / Мога да ям стъкло и не ме боли./ *Russian*: [ бгдпт ] [ /бгдпт/ ] /Я могу есть стекло, это мне не вредит./ *Serbian*: [ бгдпт ] [ /бгдпт/ ] /Могу јести стакло а да ми не шкоди./ ------------------------------------------------------------------------ Credits, Tools, and Commentary *Credits:* The "I can eat glass" phrase and the initial collection of translations: Ethan Mollick . Transcription / conversion to UTF-8: Frank da Cruz. *Albanian:* Sindi Keesan. *Afrikaans:* Johan Fourie, Kevin Poalses. *Anglo Saxon:* Frank da Cruz. *Arabic:* Najib Tounsi. *Armenian:* Vaçe Kundakçı. *Belarusian:* Alexey Chernyak. *Bengali:* Somnath Purkayastha, Deepayan Sarkar. *Bislama:* Dan McGarry. *Braille:* Frank da Cruz. *Bulgarian:* Sindi Keesan, Guentcho Skordev, Vladimir Marinov. *Cabo Verde Creole:* Cláudio Alexandre Duarte. *Chinese:* Jack Soo, Wong Pui Lam. *Chinook Jargon:* David Robertson. *Cornish:* Chris Stephens. *Croatian:* Marjan Baće. *Czech:* Stanislav Pecha, Radovan Garabík. *Dutch:* Peter Gotink. Pim Blokland, Rob Daniel, Rob de Wit. *Erzian:* Jack Rueter. *Esperanto:* Franko Luin, Radovan Garabík. *Estonian:* Meelis Roos. *Farsi/Persian:* Payam Elahi. *Finnish:* Sampsa Toivanen. *French:* Luc Carissimo, Anne Colin du Terrail, Sean M. Burke. *Galician:* Laura Probaos. *Georgian:* Giorgi Lebanidze. *German:* Christoph Päper, Otto Stolz, Karl Pentzlin, Frank da Cruz. *Gothic:* Aurélien Coudurier. *Greek:* Ariel Glenn, Constantine Stathopoulos, Siva Nataraja. *Hebrew:* Jonathan Rosenne, Tal Barnea. *Hausa:* Malami Buba, Tom Gewecke. *Hawaiian:* na Hauʻoli Motta, Anela de Rego, Kaliko Trapp. *Hindi:* Shirish Kalele. *Hungarian:* András Rácz, Mark Holczhammer. *Icelandic:* Andrés Magnússon. *International Phonetic Alphabet (IPA):* Siva Nataraja / Vincent Ramos. *Irish:* Michael Everson, Marion Gunn, James Kass, Curtis Clark. *Italian:* Thomas De Bellis. *Japanese:* Makoto Takahashi, Yurio Miyazawa. *Kirchröadsj:* Roger Stoffers. *Kreyòl:* Sean M. Burke. *Korean:* Jungshik Shin. *Lëtzebuergescht:* Stefaan Eeckels. *Lithuanian:* Gediminas Grigas. *Lojban:* Edward Cherlin. *Lusatian:* Ronald Schaffhirt. *Macedonian:* Sindi Keesan. *Malay:* Zarina Mustapha. *Manx:* Éanna Ó Brádaigh. *Marathi:* Shirish Kalele. *Marquesan:* Kaliko Trapp. *Middle English:* Frank da Cruz. *Milanese:* Marco Cimarosti. *Mongolian:* Tom Gewecke. *Napoletano:* Diego Quintano. *Navajo:* Tom Gewecke. *Nórdicg* : Yẃlyan Rott. *Norwegian:* Herman Ranes. *Odenwälderisch:* Alexander Heß. *Old Irish:* Michael Everson. *Old Norse:* Andrés Magnússon. *Papiamentu:* Bianca and Denise Zanardi. *Pashto:* N.R. Liwal. *Pfälzisch:* Dr. Johannes Sander. *Picard:* Philippe Mennecier. *Polish:* Juliusz Chroboczek. *Portuguese:* "Cláudio" Alexandre Duarte, Bianca and Denise Zanardi, Pedro Palhoto Matos, Wagner Amaral. *Québécois:* Laurent Detillieux. *Roman:* Pierpaolo Bernardi. *Romanian:* Juliusz Chroboczek, Ionel Mugurel. *Ruhrdeutsch:* "Timwi". *Russian:* Alexey Chernyak, Serge Nesterovitch. *Sami:* Anne Colin du Terrail, Luc Carissimo. *Sanskrit:* Siva Nataraja / Vincent Ramos. *Sächsisch:* André Müller. *Schwäbisch:* Otto Stolz. *Scots:* Jonathan Riddell. *Serbian:* Sindi Keesan, Ranko Narancic, Boris Daljevic, Szilvia Csorba. *Slovak:* G. Adam Stanislav, Radovan Garabík. *Slovenian:* Albert Kolar. *Spanish:* Aleida Muñoz , Laura Probaos. *Swahili:* Ronald Schaffhirt. *Swedish:* Christian Rose, Bengt Larsson. *Taiwanese:* Henry H. Tan-Tenn. *Tagalog:* Jim Soliven. *Tamil:* Vasee Vaseeharan. *Tibetan:* D. Germano, Tom Gewecke. *Thai:* Alan Wood's wife. *Turkish:* Vaçe Kundakçı, Tom Gewecke, Merlign Olnon. *Ukrainian:* Michael Zajac. *Urdu:* Mustafa Ali. *Vietnamese* : Dixon Au, [James] Đỗ Bá Phước 杜 伯 福. *Walloon:* Pablo Saratxaga. *Welsh:* Geiriadur Prifysgol Cymru (Andrew). *Yiddish:* Mark David, *Zeneise:* Angelo Pavese. *Tools Used to Create This Web Page:* The UTF8-aware Kermit 95 terminal emulator on Windows, to a Unix host with the EMACS text editor. Kermit 95 displays UTF-8 and also allows keyboard entry of arbitrary Unicode BMP characters as 4 hex digits, as shown HERE . Hex codes for Unicode values can be found in The Unicode Standard (recommended) and the online code charts . When submissions arrive by email encoded in some other character set (Latin-1, Latin-2, KOI, various PC code pages, JEUC, etc), I use the TRANSLATE command of C-Kermit on the Unix host (where I read my mail ) to convert the character set to UTF-8 (I could also use Kermit 95 for this; it has the same TRANSLATE command). That's it -- no "Web authoring" tools, no locales, no "smart" anything. It's just plain text, nothing more. By the way, there's nothing special about EMACS -- any text editor will do, providing it allows entry of arbitrary 8-bit bytes as text, including the 0x80-0x9F "C1" range. EMACS 21.1 actually supports UTF-8; earlier versions don't know about it and display the octal codes; either way is OK for this purpose. *Commentary:* Date: Wed, 27 Feb 2002 13:21:59 +0100 From: "Bruno DEDOMINICIS" Subject: Je peux manger du verre, cela ne me fait pas mal. I just found out your website and it makes me feel like proposing an interpretation of the choice of this peculiar phrase. Glass is transparent and can hurt as everyone knows. The relation between people and civilisations is sometimes effusional and more often rude. The concept of breaking frontiers through globalization, in a way, is also an attempt to deny any difference. Isn't "transparency" the flag of modernity? Nothing should be hidden any more, authority is obsolete, and the new powers are supposed to reign through loving and smiling and no more through coercion... Eating glass without pain sounds like a very nice metaphor of this attempt. That is, frontiers should become glass transparent first, and be denied by incorporating them. On the reverse, it shows that through globalization, frontiers undergo a process of displacement, that is, when they are not any more speakable, they become repressed from the speech and are therefore incorporated and might become painful symptoms, as for example what happens when one tries to eat glass. The frontiers that used to separate bodies one from another tend to divide bodies from within and make them suffer.... The chosen phrase then appears as a denial of the symptom that might result from the destitution of traditional frontiers. Best, Bruno De Dominicis, Paris, France *Other Unicode pages onsite:* * Peace in All Languages * Frank's Compulsive Guide to Postal Addresses (especially the Index ) * Representing Middle English on the Web with UTF-8 * The Kermit Bibliography (in UTF-8) * Interchange of Non-English Computer Text (UTF-8 math and box-drawing) * Unicode Table (in UTF-8) *Unicode samplers offsite:* * Michael Everson's Bibliography of Typography and Scripts * Sample Unicode Test Pages and Script Links * I don't know, I only work here * Anyone can be provincial! * Transcriptions of "Unicode" * Example Unicode Usage for Business Applications * UTF-8 and Unicode FAQ for Unix/Linux *Unicode fonts:* * Unicode Fonts for Windows Computers (Alan Wood) * Unicode Fonts and Tools for X11 (Markus Kuhn) * Everson Mono (Michael Everson) * Agfa Monotype [ Kermit 95 ] [ K95 Screen Shots ] [ C-Kermit ] [ Kermit Home ] [ Display Problems? ] [ The Unicode Consortium ] ------------------------------------------------------------------------ UTF-8 Sampler / The Kermit Project / Columbia University / kermit@columbia.edu