Wala shell

Advanced PHP File Manager

Server IP: 127.0.0.1 | PHP Version: 8.3.30 | Domains Hosted: 54

Name	Size	Last Modified	Actions
📁 ..	-	2025-06-25 08:19
📄 .git-blame-ignore-revs # Reformat whole codebase with Python Black f776988f39bbaffa2b6d7a09c92e24623d5fc881	84 B	2023-08-01 19:12
📄 .gitattributes * text=auto	14 B	2023-08-01 19:12
📁 .github	-	2023-08-01 19:12
📄 .gitignore .pyc .egg-info .swp PKG-INFO /dist /build .hypothesis .cache .eggs wiki_.txt	81 B	2023-08-01 19:12
📄 .pre-commit-config.yaml repos: - repo: https://github.com/pre-commit/pre-commit-hooks rev: v4.3.0 hooks: - id: check-case-conflict - id: check-executables-have-shebangs - id: check-merge-conflict - repo: https://github.com/pycqa/isort rev: 5.10.1 hooks: - id: isort args: ["--profile", "black"] name: isort (python) - repo: https://github.com/psf/black rev: 22.6.0 hooks: - id: black args: ["--target-version", "py36"] - repo: https://github.com/pre-commit/mirrors-mypy rev: v0.961 hooks: - id: mypy files: ^chardet/ args: ["--strict", "--pretty", "--show-error-codes"] - repo: https://github.com/PyCQA/prospector rev: 1.7.7 # The version of Prospector to use, if not 'master' for latest hooks: - id: prospector	820 B	2023-08-01 19:12
📄 .prospector.yaml strictness: medium test-warnings: true pylint: disable: - line-too-long - too-many-branches - too-many-locals - too-many-arguments pycodestyle: disable: - E122 - E126 - E131 - E203 - E221 - E231 - E261 - E262 - E501 mccabe: run: false	296 B	2023-08-01 19:12
📄 LICENSE GNU LESSER GENERAL PUBLIC LICENSE Version 2.1, February 1999 Copyright (C) 1991, 1999 Free Software Foundation, Inc. 51 Franklin Street, 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. <one line to give the library's name and a brief idea of what it does.> Copyright (C) <year> <name of author> 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 Street, 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. <signature of Ty Coon>, 1 April 1990 Ty Coon, President of Vice That's all there is to it!	25.91 KB	2023-08-01 19:12
📄 MANIFEST.in include LICENSE include .rst include chardet/py.typed include requirements.txt include test.py recursive-include docs recursive-include tests * global-exclude *.pyc global-exclude __pycache__	195 B	2023-08-01 19:12
📄 NOTES.rst Class Hierarchy for chardet =========================== Universal Detector ------------------ Has a list of probers. CharSetProber ------------- Mostly abstract parent class. CharSetGroupProber ------------------ Runs a bunch of related probers at the same time and decides which is best. SBCSGroupProber --------------- SBCS = Single-ByteCharSet. Runs a bunch of SingleByteCharSetProbers. Always contains the same SingleByteCharSetProbers. SingleByteCharSetProber ----------------------- A CharSetProber that is used for detecting single-byte encodings by using a "precedence matrix" (i.e., a character bigram model). MBCSGroupProber --------------- Runs a bunch of MultiByteCharSetProbers. It also uses a UTF8Prober, which is essentially a MultiByteCharSetProber that only has a state machine. Always contains the same MultiByteCharSetProbers. MultiByteCharSetProber ---------------------- A CharSetProber that uses both a character unigram model (or "character distribution analysis") and an independent state machine for trying to detect and encoding. CodingStateMachine ------------------ Used for "coding scheme" detection, where we just look for either invalid byte sequences or sequences that only occur for that particular encoding. CharDistributionAnalysis ------------------------ Used for character unigram distribution encoding detection. Takes a mapping from characters to a "frequency order" (i.e., what frequency rank that byte has in the given encoding) and a "typical distribution ratio", which is the number of occurrences of the 512 most frequently used characters divided by the number of occurrences of the rest of the characters for a typical document. The "characters" in this case are 2-byte sequences and they are first converted to an "order" (name comes from ord() function, I believe). This "order" is used to index into the frequency order table to determine the frequency rank of that byte sequence. The reason this extra step is necessary is that the frequency rank table is language-specific (and not encoding-specific). What's where ============ Bigram files ------------ - ``hebrewprober.py`` - ``jpcntxprober.py`` - ``langbulgarianmodel.py`` - ``langcyrillicmodel.py`` - ``langgreekmodel.py`` - ``langhebrewmodel.py`` - ``langhungarianmodel.py`` - ``langthaimodel.py`` - ``latin1prober.py`` - ``sbcharsetprober.py`` - ``sbcsgroupprober.py`` Coding Scheme files ------------------- - ``escprober.py`` - ``escsm.py`` - ``utf8prober.py`` - ``codingstatemachine.py`` - ``mbcssmprober.py`` Unigram files ------------- - ``big5freqprober.py`` - ``chardistribution.py`` - ``euckrfreqprober.py`` - ``euctwfreqprober.py`` - ``gb2312freqprober.py`` - ``jisfreqprober.py`` Multibyte probers ----------------- - ``big5prober.py`` - ``cp949prober.py`` - ``eucjpprober.py`` - ``euckrprober.py`` - ``euctwprober.py`` - ``gb2312prober.py`` - ``mbcharsetprober.py`` - ``mbcsgroupprober.py`` - ``sjisprober.py`` Misc files ---------- - ``__init__.py`` (currently has ``detect`` function in it) - ``compat.py`` - ``enums.py`` - ``universaldetector.py`` - ``version.py`` Useful links ============ This is just a collection of information that I've found useful or thought might be useful in the future: - `BOM by Encoding`_ - `A Composite Approach to Language/Encoding Detection`_ - `What Every Programmer Absolutely...`_ - The actual `source`_ .. _BOM by Encoding: https://en.wikipedia.org/wiki/Byte_order_mark#Byte_order_marks_by_encoding .. _A Composite Approach to Language/Encoding Detection: http://www-archive.mozilla.org/projects/intl/UniversalCharsetDetection.html .. _What Every Programmer Absolutely...: http://kunststube.net/encoding/ .. _source: https://dxr.mozilla.org/mozilla/source/intl/chardet/	3.68 KB	2023-08-01 19:12
📄 README.rst Chardet: The Universal Character Encoding Detector -------------------------------------------------- .. image:: https://img.shields.io/travis/chardet/chardet/stable.svg :alt: Build status :target: https://travis-ci.org/chardet/chardet .. image:: https://img.shields.io/coveralls/chardet/chardet/stable.svg :target: https://coveralls.io/r/chardet/chardet .. image:: https://img.shields.io/pypi/v/chardet.svg :target: https://warehouse.python.org/project/chardet/ :alt: Latest version on PyPI .. image:: https://img.shields.io/pypi/l/chardet.svg :alt: License Detects - ASCII, UTF-8, UTF-16 (2 variants), UTF-32 (4 variants) - Big5, GB2312, EUC-TW, HZ-GB-2312, ISO-2022-CN (Traditional and Simplified Chinese) - EUC-JP, SHIFT_JIS, CP932, ISO-2022-JP (Japanese) - EUC-KR, ISO-2022-KR, Johab (Korean) - KOI8-R, MacCyrillic, IBM855, IBM866, ISO-8859-5, windows-1251 (Cyrillic) - ISO-8859-5, windows-1251 (Bulgarian) - ISO-8859-1, windows-1252, MacRoman (Western European languages) - ISO-8859-7, windows-1253 (Greek) - ISO-8859-8, windows-1255 (Visual and Logical Hebrew) - TIS-620 (Thai) .. note:: Our ISO-8859-2 and windows-1250 (Hungarian) probers have been temporarily disabled until we can retrain the models. Requires Python 3.7+. Installation ------------ Install from `PyPI <https://pypi.org/project/chardet/>`_:: pip install chardet Documentation ------------- For users, docs are now available at https://chardet.readthedocs.io/. Command-line Tool ----------------- chardet comes with a command-line script which reports on the encodings of one or more files:: % chardetect somefile someotherfile somefile: windows-1252 with confidence 0.5 someotherfile: ascii with confidence 1.0 About ----- This is a continuation of Mark Pilgrim's excellent original chardet port from C, and `Ian Cordasco <https://github.com/sigmavirus24>`_'s `charade <https://github.com/sigmavirus24/charade>`_ Python 3-compatible fork. :maintainer: Dan Blanchard	1.96 KB	2023-08-01 19:12
📄 bench.py """ Run chardet on a bunch of documents and see that we get the correct encodings. :author: Dan Blanchard :author: Ian Cordasco """ import argparse import sys import time from collections import defaultdict from os import listdir from os.path import dirname, isdir, join, realpath, relpath, splitext import chardet try: import cchardet # pylint: disable=import-error HAVE_CCHARDET = True except Exception: HAVE_CCHARDET = False # TODO: Restore Hungarian encodings (iso-8859-2 and windows-1250) after we # retrain model. MISSING_ENCODINGS = { "iso-8859-2", "iso-8859-6", "windows-1250", "windows-1254", "windows-1256", } EXPECTED_FAILURES = { "tests/iso-8859-7-greek/disabled.gr.xml", "tests/iso-8859-9-turkish/divxplanet.com.xml", "tests/iso-8859-9-turkish/subtitle.srt", "tests/iso-8859-9-turkish/wikitop_tr_ISO-8859-9.txt", } def get_py_impl(): """Return what kind of Python this is""" if hasattr(sys, "pypy_version_info"): pyimpl = "PyPy" elif sys.platform.startswith("java"): pyimpl = "Jython" elif sys.platform == "cli": pyimpl = "IronPython" else: pyimpl = "CPython" return pyimpl def get_test_files(): """Yields filenames to use for timing chardet.detect""" base_path = relpath(join(dirname(realpath(__file__)), "tests")) for encoding in listdir(base_path): path = join(base_path, encoding) # Skip files in tests directory if not isdir(path): continue # Remove language suffixes from encoding if present encoding = encoding.lower() for postfix in [ "-arabic", "-bulgarian", "-cyrillic", "-greek", "-hebrew", "-hungarian", "-turkish", ]: if encoding.endswith(postfix): encoding = encoding.rpartition(postfix)[0] break # Skip directories for encodings we don't handle yet. if encoding in MISSING_ENCODINGS: continue # Test encoding detection for each file we have of encoding for for file_name in listdir(path): ext = splitext(file_name)[1].lower() if ext not in [".html", ".txt", ".xml", ".srt"]: continue full_path = join(path, file_name) if full_path in EXPECTED_FAILURES: continue yield full_path, encoding def benchmark(chardet_mod=chardet, verbose=False, num_iters=10): print( f"Benchmarking {chardet_mod.__name__} {chardet_mod.__version__} " f"on {get_py_impl()} {sys.version}" ) print("-" * 80) total_time = 0 num_files = 0 encoding_times = defaultdict(float) encoding_num_files = defaultdict(int) for full_path, encoding in get_test_files(): num_files += 1 with open(full_path, "rb") as f: input_bytes = f.read() start = time.time() for _ in range(num_iters): chardet_mod.detect(input_bytes) bench_time = time.time() - start if verbose: print(f"Average time for {full_path}: {bench_time / num_iters}s") else: print(".", end="") sys.stdout.flush() total_time += bench_time encoding_times[encoding] += bench_time encoding_num_files[encoding] += 1 print("\nCalls per second for each encoding:") for encoding in sorted(encoding_times.keys()): calls_per_sec = ( num_iters * encoding_num_files[encoding] / encoding_times[encoding] ) print(f"{encoding}: {calls_per_sec}") calls_per_sec = num_iters * num_files / total_time print(f"\nTotal time: {total_time}s ({calls_per_sec} calls per second)") def main(): parser = argparse.ArgumentParser( description="Times how long it takes to process each file in test set " "multiple times.", formatter_class=argparse.ArgumentDefaultsHelpFormatter, ) parser.add_argument( "-c", "--cchardet", action="store_true", help="Run benchmarks for cChardet instead of chardet, if it is installed.", ) parser.add_argument( "-i", "--iterations", help="Number of times to process each file", type=int, default=10, ) parser.add_argument( "-v", "--verbose", help="Prints out the timing for each individual file.", action="store_true", ) args = parser.parse_args() if args.cchardet and not HAVE_CCHARDET: print("You must pip install cchardet if you want to benchmark it.") sys.exit(1) benchmark( chardet_mod=cchardet if args.cchardet else chardet, verbose=args.verbose, num_iters=args.iterations, ) if __name__ == "__main__": main()	4.79 KB	2023-08-01 19:12
📁 chardet	-	2025-06-25 08:26
📄 convert_language_model.py #!/usr/bin/env python ######################## BEGIN LICENSE BLOCK ######################## # Contributor(s): # 10.02.2015 - helour - first attempt # 08.08.2016 - Dan Blanchard - first usable release # # 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 # ######################### END LICENSE BLOCK ######################### """ Convert old style SBCS model to new """ import os import sys from argparse import ArgumentDefaultsHelpFormatter, ArgumentParser from string import ascii_letters import chardet from chardet import __version__ from chardet.metadata.languages import LANGUAGES from chardet.sbcharsetprober import SingleByteCharSetModel # Turn ascii_letters into a set to make other ops easier ascii_letters = set(ascii_letters) def normalize_name(charset_name): """Convert name to proper Python constant format""" # Title case to start charset_name = charset_name.upper() # Underscores instead of hyphens charset_name = charset_name.replace("-", "_") return charset_name def convert_sbcs_model(old_model, alphabet): """Create a SingleByteCharSetModel object representing the charset.""" # Setup tables necessary for computing transition frequencies for model char_to_order = dict(enumerate(old_model["char_to_order_map"])) pos_ratio = old_model["typical_positive_ratio"] keep_ascii_letters = old_model["keep_english_letter"] curr_model = SingleByteCharSetModel( charset_name=old_model["charset_name"], language=old_model["language"], char_to_order_map=char_to_order, # language_model is filled in later language_model=None, typical_positive_ratio=pos_ratio, keep_ascii_letters=keep_ascii_letters, alphabet=alphabet, ) return curr_model def print_char_to_order(var_name, order_map, charset_name, output_file): print(f"{var_name} = {{", file=output_file) for char, order in sorted(order_map.items()): char_bytes = bytes(bytearray((char,))) try: unicode_char = char_bytes.decode(charset_name) except UnicodeError: unicode_char = None print(f" {char!r}: {order!r}, # {unicode_char!r}", file=output_file) print("}\n", file=output_file) def print_language_model(var_name, language_model, output_file, char_ranks): print( "# 3: Positive\n# 2: Likely\n# 1: Unlikely\n# 0: Negative\n", file=output_file, ) print(f"{var_name} = {{", file=output_file) for first_char, sub_dict in sorted(language_model.items()): # Skip empty sub_dicts if not sub_dict or first_char not in char_ranks: continue print(f" {char_ranks[first_char]!r}: {{ # {first_char!r}", file=output_file) for second_char, likelihood in sorted(sub_dict.items()): if second_char not in char_ranks: continue print( f" {char_ranks[second_char]!r}: {likelihood!r}, # " f"{second_char!r}", file=output_file, ) print(" },", file=output_file) print("}\n", file=output_file) def convert_models_for_lang(language): """Convert old SingleByteCharSetModels for the given language""" # Validate language language = language.title() lang_metadata = LANGUAGES.get(language) if not lang_metadata: raise ValueError( f"Unknown language: {language}. If you are adding a model for a" " new language, you must first update metadata/" "languages.py" ) lang_mod_name = f"lang{language.lower()}model" if not os.path.exists(os.path.join("chardet", lang_mod_name + ".py")): print(f"Skipping {language} because it does not have an old model.") return lang_mod = getattr(chardet, lang_mod_name) print( f"\n{language}\n----------------------------------------------------------------" ) print(f"Keep ASCII Letters: {lang_metadata.use_ascii}") print(f"Alphabet: {lang_metadata.alphabet}") # Create char-to-order maps (aka char-to-rank dicts) charset_models = {} char_ranks = {} order_to_chars = {} for var_name in dir(lang_mod): if not ("Model" in var_name and "LangModel" not in var_name): continue old_model = getattr(lang_mod, var_name) charset_name = old_model["charset_name"] print(f"Converting charset model for {charset_name}") sys.stdout.flush() charset_models[charset_name] = convert_sbcs_model( old_model, lang_metadata.alphabet ) # Since we don't know which charsets have which characters, we have to # try to reconstruct char_ranks (for letters only, since that's all # the old language models contain) for byte_hex, order in charset_models[charset_name].char_to_order_map.items(): # order 64 was basically ignored before because of the off by one # error, but it's hard to know if training took that into account if order > 64: continue # Convert to bytes in Python 2 and 3 char = bytes(bytearray((byte_hex,))) try: unicode_char = char.decode(charset_name) except UnicodeDecodeError: continue if unicode_char not in char_ranks: char_ranks[unicode_char] = order order_to_chars[order] = unicode_char elif char_ranks[unicode_char] != order: raise ValueError(f"Unstable character ranking for {unicode_char}") old_lang_model = getattr(lang_mod, f"{language.title()}LangModel") language_model = {} # Preserve off-by-one error here by ignoring first column and row for i in range(1, 64): if i not in order_to_chars: continue lang_char = order_to_chars[i] language_model[lang_char] = {} for j in range(1, 64): if j not in order_to_chars: continue lang_char2 = order_to_chars[j] language_model[lang_char][lang_char2] = old_lang_model[(i * 64) + j] # Write output files print(f"Writing output file for {language}\n\n") sys.stdout.flush() with open(f"lang{language.lower()}model.py", "w", encoding="utf-8") as output_file: upper_lang = language.upper() # print header to set encoding print( "from chardet.sbcharsetprober import SingleByteCharSetModel\n\n", file=output_file, ) lm_name = f"{upper_lang}_LANG_MODEL" print_language_model(lm_name, language_model, output_file, char_ranks) print( "# 255: Undefined characters that did not exist in training text\n" "# 254: Carriage/Return\n" "# 253: symbol (punctuation) that does not belong to word\n" "# 252: 0 - 9\n" "# 251: Control characters\n\n" "# Character Mapping Table(s):", file=output_file, ) for charset_name, sbcs_model in charset_models.items(): normal_name = normalize_name(charset_name) char_to_order_name = f"{normal_name}_{upper_lang}_CHAR_TO_ORDER" print_char_to_order( char_to_order_name, sbcs_model.char_to_order_map, charset_name, output_file, ) sbcs_model_name = f"{normal_name}_{upper_lang}_MODEL" sbcs_model.char_to_order_map.clear() sbcs_model_repr = ( repr(sbcs_model) .replace("None", lm_name) .replace("{}", char_to_order_name) .replace(", ", (",\n" + " " * (len(sbcs_model_name) + 26))) ) print(f"{sbcs_model_name} = {sbcs_model_repr}\n", file=output_file) def main(): parser = ArgumentParser( description=__doc__, formatter_class=ArgumentDefaultsHelpFormatter ) parser.add_argument( "language", help="The name of the language the input documents are " "in. Also the name of the language the generated " "model will detect. If no language is specified, " "models for all languages known to chardet will be" " trained.", nargs="*", ) parser.add_argument("--version", action="version", version=__version__) args = parser.parse_args() if not args.language: args.language = list(sorted(LANGUAGES.keys())) for language in args.language: convert_models_for_lang(language) if __name__ == "__main__": main()	9.11 KB	2023-08-01 19:12
📁 docs	-	2023-08-01 19:12
📄 pyproject.toml [build-system] requires = ["setuptools"] build-backend = "setuptools.build_meta"	81 B	2023-08-01 19:12
📄 setup.cfg [metadata] name = chardet version = attr: chardet.version.__version__ description = Universal encoding detector for Python 3 long_description = file: README.rst author = Mark Pilgrim author_email = mark@diveintomark.org maintainer = Daniel Blanchard maintainer_email = dan.blanchard@gmail.com url = https://github.com/chardet/chardet license = LGPL keywords = encoding, i18n, xml project_urls = Documentation = https://chardet.readthedocs.io/ GitHub Project = https://github.com/chardet/chardet Issue Tracker = https://github.com/chardet/chardet/issues classifiers = Development Status :: 5 - Production/Stable Intended Audience :: Developers License :: OSI Approved :: GNU Lesser General Public License v2 or later (LGPLv2+) Operating System :: OS Independent Programming Language :: Python Programming Language :: Python :: 3 Programming Language :: Python :: 3.7 Programming Language :: Python :: 3.8 Programming Language :: Python :: 3.9 Programming Language :: Python :: 3.10 Programming Language :: Python :: 3.11 Programming Language :: Python :: Implementation :: CPython Programming Language :: Python :: Implementation :: PyPy Topic :: Software Development :: Libraries :: Python Modules Topic :: Text Processing :: Linguistic [options] include_package_data = true python_requires = >=3.7 packages = find: [options.package_data] chardet = py.typed [options.entry_points] console_scripts = chardetect = chardet.cli.chardetect:main [tool:pytest] addopts = -v python_files = test.py norecursedirs = *	1.55 KB	2023-08-01 19:12
📄 test.py """ Run chardet on a bunch of documents and see that we get the correct encodings. :author: Dan Blanchard :author: Ian Cordasco """ import textwrap from difflib import ndiff from os import listdir from os.path import dirname, isdir, join, realpath, relpath, splitext from pprint import pformat from unicodedata import normalize try: import hypothesis.strategies as st from hypothesis import Verbosity, assume, given, settings HAVE_HYPOTHESIS = True except ImportError: HAVE_HYPOTHESIS = False import pytest # pylint: disable=import-error import chardet from chardet.metadata.languages import LANGUAGES # TODO: Restore Hungarian encodings (iso-8859-2 and windows-1250) after we # retrain model. MISSING_ENCODINGS = { "iso-8859-2", "iso-8859-6", "windows-1250", "windows-1254", "windows-1256", } EXPECTED_FAILURES = { "tests/iso-8859-9-turkish/_ude_1.txt", "tests/iso-8859-9-turkish/_ude_2.txt", "tests/iso-8859-9-turkish/divxplanet.com.xml", "tests/iso-8859-9-turkish/subtitle.srt", "tests/iso-8859-9-turkish/wikitop_tr_ISO-8859-9.txt", } def gen_test_params(): """Yields tuples of paths and encodings to use for test_encoding_detection""" base_path = relpath(join(dirname(realpath(__file__)), "tests")) for encoding in listdir(base_path): path = join(base_path, encoding) # Skip files in tests directory if not isdir(path): continue # Remove language suffixes from encoding if present encoding = encoding.lower() for language in sorted(LANGUAGES.keys()): postfix = "-" + language.lower() if encoding.endswith(postfix): encoding = encoding.rpartition(postfix)[0] break # Skip directories for encodings we don't handle yet. if encoding in MISSING_ENCODINGS: continue # Test encoding detection for each file we have of encoding for for file_name in listdir(path): ext = splitext(file_name)[1].lower() if ext not in [".html", ".txt", ".xml", ".srt"]: continue full_path = join(path, file_name) test_case = full_path, encoding if full_path in EXPECTED_FAILURES: test_case = pytest.param(*test_case, marks=pytest.mark.xfail) yield test_case @pytest.mark.parametrize("file_name, encoding", gen_test_params()) def test_encoding_detection(file_name, encoding): with open(file_name, "rb") as f: input_bytes = f.read() result = chardet.detect(input_bytes) try: expected_unicode = input_bytes.decode(encoding) except LookupError: expected_unicode = "" try: detected_unicode = input_bytes.decode(result["encoding"]) except (LookupError, UnicodeDecodeError, TypeError): detected_unicode = "" if result: encoding_match = (result["encoding"] or "").lower() == encoding else: encoding_match = False # Only care about mismatches that would actually result in different # behavior when decoding expected_unicode = normalize("NFKC", expected_unicode) detected_unicode = normalize("NFKC", detected_unicode) if not encoding_match and expected_unicode != detected_unicode: wrapped_expected = "\n".join(textwrap.wrap(expected_unicode, 100)) + "\n" wrapped_detected = "\n".join(textwrap.wrap(detected_unicode, 100)) + "\n" diff = "".join( [ line for line in ndiff( wrapped_expected.splitlines(True), wrapped_detected.splitlines(True) ) if not line.startswith(" ") ][:20] ) all_encodings = chardet.detect_all(input_bytes, ignore_threshold=True) else: diff = "" encoding_match = True all_encodings = [result] assert encoding_match, ( f"Expected {encoding}, but got {result} for {file_name}. First 20 " f"lines with character differences: \n{diff}\n" f"All encodings: {pformat(all_encodings)}" ) @pytest.mark.parametrize("file_name, encoding", gen_test_params()) def test_encoding_detection_rename_legacy(file_name, encoding): with open(file_name, "rb") as f: input_bytes = f.read() result = chardet.detect(input_bytes, should_rename_legacy=True) try: expected_unicode = input_bytes.decode(encoding) except LookupError: expected_unicode = "" try: detected_unicode = input_bytes.decode(result["encoding"]) except (LookupError, UnicodeDecodeError, TypeError): detected_unicode = "" if result: encoding_match = (result["encoding"] or "").lower() == encoding else: encoding_match = False # Only care about mismatches that would actually result in different # behavior when decoding expected_unicode = normalize("NFKD", expected_unicode) detected_unicode = normalize("NFKD", detected_unicode) if not encoding_match and expected_unicode != detected_unicode: wrapped_expected = "\n".join(textwrap.wrap(expected_unicode, 100)) + "\n" wrapped_detected = "\n".join(textwrap.wrap(detected_unicode, 100)) + "\n" diff = "".join( [ line for line in ndiff( wrapped_expected.splitlines(True), wrapped_detected.splitlines(True) ) if not line.startswith(" ") ][:20] ) all_encodings = chardet.detect_all( input_bytes, ignore_threshold=True, should_rename_legacy=True ) else: diff = "" encoding_match = True all_encodings = [result] assert encoding_match, ( f"Expected {encoding}, but got {result} for {file_name}. First 20 " f"lines of character differences: \n{diff}\n" f"All encodings: {pformat(all_encodings)}" ) if HAVE_HYPOTHESIS: class JustALengthIssue(Exception): pass @pytest.mark.xfail @given( st.text(min_size=1), st.sampled_from( [ "ascii", "utf-8", "utf-16", "utf-32", "iso-8859-7", "iso-8859-8", "windows-1255", ] ), st.randoms(), ) @settings(max_examples=200) def test_never_fails_to_detect_if_there_is_a_valid_encoding(txt, enc, rnd): try: data = txt.encode(enc) except UnicodeEncodeError: assume(False) detected = chardet.detect(data)["encoding"] if detected is None: with pytest.raises(JustALengthIssue): @given(st.text(), random=rnd) @settings(verbosity=Verbosity.quiet, max_examples=50) def string_poisons_following_text(suffix): try: extended = (txt + suffix).encode(enc) except UnicodeEncodeError: assume(False) result = chardet.detect(extended) if result and result["encoding"] is not None: raise JustALengthIssue() @given( st.text(min_size=1), st.sampled_from( [ "ascii", "utf-8", "utf-16", "utf-32", "iso-8859-7", "iso-8859-8", "windows-1255", ] ), st.randoms(), ) @settings(max_examples=200) def test_detect_all_and_detect_one_should_agree(txt, enc, _): try: data = txt.encode(enc) except UnicodeEncodeError: assume(False) try: result = chardet.detect(data) results = chardet.detect_all(data) assert result["encoding"] == results[0]["encoding"] except Exception as exc: raise RuntimeError(f"{result} != {results}") from exc	7.95 KB	2023-08-01 19:12
📁 tests	-	2023-08-01 19:12

Terminal