pax_global_header00006660000000000000000000000064152012436610014512gustar00rootroot0000000000000052 comment=a814388f5a8a7b172ee2e2ca668fc33c7516e6bc pyzipper-0.4.0/000077500000000000000000000000001520124366100133755ustar00rootroot00000000000000pyzipper-0.4.0/.coveragerc000066400000000000000000000011541520124366100155170ustar00rootroot00000000000000[run] branch = True include = pyzipper/* # test/* # uncomment the above line if you want to see if all tests did run omit = setup.py pyzipper\__version__.py [report] # Regexes for lines to exclude from consideration exclude_lines = # Have to re-enable the standard pragma pragma: no cover # Don't complain about missing debug-only code: def __repr__ if self\.debug # Don't complain if tests don't hit defensive assertion code: raise AssertionError raise NotImplementedError # Don't complain if non-runnable code isn't run: if 0: if __name__ == .__main__.: pyzipper-0.4.0/.editorconfig000066400000000000000000000005221520124366100160510ustar00rootroot00000000000000# http://editorconfig.org root = true [*] indent_style = space indent_size = 4 trim_trailing_whitespace = true insert_final_newline = true charset = utf-8 end_of_line = lf [*.bat] indent_style = tab end_of_line = crlf [*.yml] indent_style = space indent_size = 2 [LICENSE] insert_final_newline = false [Makefile] indent_style = tab pyzipper-0.4.0/.github/000077500000000000000000000000001520124366100147355ustar00rootroot00000000000000pyzipper-0.4.0/.github/workflows/000077500000000000000000000000001520124366100167725ustar00rootroot00000000000000pyzipper-0.4.0/.github/workflows/tests.yml000066400000000000000000000017341520124366100206640ustar00rootroot00000000000000--- name: Tests on: push: branches: - master pull_request: permissions: {} jobs: tests: runs-on: ubuntu-latest strategy: fail-fast: false matrix: python-version: ['3.10', '3.11', '3.12', '3.13', '3.14'] steps: - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 with: persist-credentials: false - name: Set up Python ${{ matrix.python-version }} uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0 with: python-version: ${{ matrix.python-version }} - name: Install dependencies run: | python -m pip install pip==26.1.1 python -m pip install tox==4.53.1 - name: Run tox targets for ${{ matrix.python-version }} run: | PYVERSION=$(python -c "import sys; print(''.join([str(sys.version_info.major), str(sys.version_info.minor)]))") python -m tox -f "py${PYVERSION}" pyzipper-0.4.0/.gitignore000066400000000000000000000002461520124366100153670ustar00rootroot00000000000000build/ dist/ pyzipper.egg-info *.pyc *.swp *.egg .tox/ .coverage .coverage.* @test* # auto generated doc files docs/api/ docs/_build # Pycharm project files .idea/ pyzipper-0.4.0/AUTHORS.rst000066400000000000000000000002621520124366100152540ustar00rootroot00000000000000======= Credits ======= Development Lead ---------------- * Daniel Hillier Contributors ------------ * Sebastian Weigand pyzipper-0.4.0/CONTRIBUTING.rst000066400000000000000000000063121520124366100160400ustar00rootroot00000000000000.. highlight:: shell ============ Contributing ============ Contributions are welcome, and they are greatly appreciated! Every little bit helps, and credit will always be given. You can contribute in many ways: Types of Contributions ---------------------- Report Bugs ~~~~~~~~~~~ Report bugs at https://github.com/danifus/pyzipper/issues. If you are reporting a bug, please include: * Your operating system name and version. * Any details about your local setup that might be helpful in troubleshooting. * Detailed steps to reproduce the bug. Fix Bugs ~~~~~~~~ Look through the GitHub issues for bugs. Anything tagged with "bug" and "help wanted" is open to whoever wants to implement it. Implement Features ~~~~~~~~~~~~~~~~~~ Look through the GitHub issues for features. Anything tagged with "enhancement" and "help wanted" is open to whoever wants to implement it. Write Documentation ~~~~~~~~~~~~~~~~~~~ pyzipper could always use more documentation, whether as part of the official pyzipper docs, in docstrings, or even on the web in blog posts, articles, and such. Submit Feedback ~~~~~~~~~~~~~~~ The best way to send feedback is to file an issue at https://github.com/danifus/pyzipper/issues. If you are proposing a feature: * Explain in detail how it would work. * Keep the scope as narrow as possible, to make it easier to implement. * Remember that this is a volunteer-driven project, and that contributions are welcome :) Get Started! ------------ Ready to contribute? Here's how to set up `pyzipper` for local development. 1. Fork the `pyzipper` repo on GitHub. 2. Clone your fork locally:: $ git clone git@github.com:your_name_here/pyzipper.git 3. Install your local copy into a virtualenv. Assuming you have virtualenvwrapper installed, this is how you set up your fork for local development:: $ mkvirtualenv pyzipper $ cd pyzipper/ $ pip install -e . $ pip install -r requirements_dev.txt 4. Create a branch for local development:: $ git checkout -b name-of-your-bugfix-or-feature Now you can make your changes locally. 5. When you're done making changes, check that your changes pass flake8 and the tests, including testing other Python versions with tox:: $ tox To get flake8 and tox, just pip install them into your virtualenv. 6. Commit your changes and push your branch to GitHub:: $ git add . $ git commit -m "Your detailed description of your changes." $ git push origin name-of-your-bugfix-or-feature 7. Submit a pull request through the GitHub website. Pull Request Guidelines ----------------------- Before you submit a pull request, check that it meets these guidelines: 1. The pull request should include tests. 2. If the pull request adds functionality, the docs should be updated. Put your new functionality into a function with a docstring, and add the feature to the list in README.rst. Tips ---- To run a subset of tests:: $ py.test tests.test_pyzipper Deploying --------- A reminder for the maintainers on how to deploy. Make sure all your changes are committed (including an entry in HISTORY.rst). Then run:: $ bumpversion patch # possible: major / minor / patch $ git push $ git push --tags Travis will then deploy to PyPI if tests pass. pyzipper-0.4.0/HISTORY.rst000066400000000000000000000026601520124366100152740ustar00rootroot00000000000000======= History ======= 0.4.0 (2026-05-13) ------------------ * Update package to use pyproject.toml * Fix bug where CRC32 values were not removed for small files (CVE-2026-44722). pyzipper no longer writes any CRC32 values by default, regardless of file size. The CRC32 value could be used to brute-force candidate plaintexts by computing CRC32(candidate) and comparing against the stored value. In practice, this attack is feasible today only against small or low-entropy files, as CRC32 exhaustion across a large plaintext space is computationally prohibitive on current hardware. 0.3.6 (2022-07-31) ------------------ * Exclude test, not tests, from setup.py packaging 0.3.5 (2021-04-08) ------------------ * Update trove classifiers to include python 3.8 and 3.9 * Update tests to use github actions 0.3.4 (2020-12-24) ------------------ * Fix HMAC check when all filesize bytes have been decompressed but bytes remain in the lzma stream 0.3.3 (2020-06-18) ------------------ * Add extra exception message when user supplies non-bytes password * Fix reading zip64 extra when disk num entry is present * Add BadZipFile errors for invalid zip64 extra fields 0.3.1 (2018-11-17) ------------------ * Add support for Python 3.4, 3.5 * Add travis ci integration. * Fix bug in local file header record. 0.2.0 (2018-11-17) ------------------ * Second release on PyPI. 0.1.0 (2018-11-07) ------------------ * First release on PyPI. pyzipper-0.4.0/LICENSE000066400000000000000000000020571520124366100144060ustar00rootroot00000000000000MIT License Copyright (c) 2017 Daniel Hillier Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions: The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software. THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. pyzipper-0.4.0/LICENSE.python000066400000000000000000000336621520124366100157340ustar00rootroot00000000000000pyzipper is licensed under the MIT license; see the file LICENSE for details. pyzipper is forked from the Python standard library and its tests, which are licensed under the Python license, a permissive open source license. The copyright and license is included below for compliance with Python's terms. ---------------------------------------------------------------------- Copyright (c) 2001-present Python Software Foundation; All Rights Reserved A. HISTORY OF THE SOFTWARE ========================== Python was created in the early 1990s by Guido van Rossum at Stichting Mathematisch Centrum (CWI, see https://www.cwi.nl) in the Netherlands as a successor of a language called ABC. Guido remains Python's principal author, although it includes many contributions from others. In 1995, Guido continued his work on Python at the Corporation for National Research Initiatives (CNRI, see https://www.cnri.reston.va.us) in Reston, Virginia where he released several versions of the software. In May 2000, Guido and the Python core development team moved to BeOpen.com to form the BeOpen PythonLabs team. In October of the same year, the PythonLabs team moved to Digital Creations, which became Zope Corporation. In 2001, the Python Software Foundation (PSF, see https://www.python.org/psf/) was formed, a non-profit organization created specifically to own Python-related Intellectual Property. Zope Corporation was a sponsoring member of the PSF. All Python releases are Open Source (see https://opensource.org for the Open Source Definition). Historically, most, but not all, Python releases have also been GPL-compatible; the table below summarizes the various releases. Release Derived Year Owner GPL- from compatible? (1) 0.9.0 thru 1.2 1991-1995 CWI yes 1.3 thru 1.5.2 1.2 1995-1999 CNRI yes 1.6 1.5.2 2000 CNRI no 2.0 1.6 2000 BeOpen.com no 1.6.1 1.6 2001 CNRI yes (2) 2.1 2.0+1.6.1 2001 PSF no 2.0.1 2.0+1.6.1 2001 PSF yes 2.1.1 2.1+2.0.1 2001 PSF yes 2.1.2 2.1.1 2002 PSF yes 2.1.3 2.1.2 2002 PSF yes 2.2 and above 2.1.1 2001-now PSF yes Footnotes: (1) GPL-compatible doesn't mean that we're distributing Python under the GPL. All Python licenses, unlike the GPL, let you distribute a modified version without making your changes open source. The GPL-compatible licenses make it possible to combine Python with other software that is released under the GPL; the others don't. (2) According to Richard Stallman, 1.6.1 is not GPL-compatible, because its license has a choice of law clause. According to CNRI, however, Stallman's lawyer has told CNRI's lawyer that 1.6.1 is "not incompatible" with the GPL. Thanks to the many outside volunteers who have worked under Guido's direction to make these releases possible. B. TERMS AND CONDITIONS FOR ACCESSING OR OTHERWISE USING PYTHON =============================================================== Python software and documentation are licensed under the Python Software Foundation License Version 2. Starting with Python 3.8.6, examples, recipes, and other code in the documentation are dual licensed under the PSF License Version 2 and the Zero-Clause BSD license. Some software incorporated into Python is under different licenses. The licenses are listed with code falling under that license. PYTHON SOFTWARE FOUNDATION LICENSE VERSION 2 -------------------------------------------- 1. This LICENSE AGREEMENT is between the Python Software Foundation ("PSF"), and the Individual or Organization ("Licensee") accessing and otherwise using this software ("Python") in source or binary form and its associated documentation. 2. Subject to the terms and conditions of this License Agreement, PSF hereby grants Licensee a nonexclusive, royalty-free, world-wide license to reproduce, analyze, test, perform and/or display publicly, prepare derivative works, distribute, and otherwise use Python alone or in any derivative version, provided, however, that PSF's License Agreement and PSF's notice of copyright, i.e., "Copyright (c) 2001 Python Software Foundation; All Rights Reserved" are retained in Python alone or in any derivative version prepared by Licensee. 3. In the event Licensee prepares a derivative work that is based on or incorporates Python or any part thereof, and wants to make the derivative work available to others as provided herein, then Licensee hereby agrees to include in any such work a brief summary of the changes made to Python. 4. PSF is making Python available to Licensee on an "AS IS" basis. PSF MAKES NO REPRESENTATIONS OR WARRANTIES, EXPRESS OR IMPLIED. BY WAY OF EXAMPLE, BUT NOT LIMITATION, PSF MAKES NO AND DISCLAIMS ANY REPRESENTATION OR WARRANTY OF MERCHANTABILITY OR FITNESS FOR ANY PARTICULAR PURPOSE OR THAT THE USE OF PYTHON WILL NOT INFRINGE ANY THIRD PARTY RIGHTS. 5. PSF SHALL NOT BE LIABLE TO LICENSEE OR ANY OTHER USERS OF PYTHON FOR ANY INCIDENTAL, SPECIAL, OR CONSEQUENTIAL DAMAGES OR LOSS AS A RESULT OF MODIFYING, DISTRIBUTING, OR OTHERWISE USING PYTHON, OR ANY DERIVATIVE THEREOF, EVEN IF ADVISED OF THE POSSIBILITY THEREOF. 6. This License Agreement will automatically terminate upon a material breach of its terms and conditions. 7. Nothing in this License Agreement shall be deemed to create any relationship of agency, partnership, or joint venture between PSF and Licensee. This License Agreement does not grant permission to use PSF trademarks or trade name in a trademark sense to endorse or promote products or services of Licensee, or any third party. 8. By copying, installing or otherwise using Python, Licensee agrees to be bound by the terms and conditions of this License Agreement. BEOPEN.COM LICENSE AGREEMENT FOR PYTHON 2.0 ------------------------------------------- BEOPEN PYTHON OPEN SOURCE LICENSE AGREEMENT VERSION 1 1. This LICENSE AGREEMENT is between BeOpen.com ("BeOpen"), having an office at 160 Saratoga Avenue, Santa Clara, CA 95051, and the Individual or Organization ("Licensee") accessing and otherwise using this software in source or binary form and its associated documentation ("the Software"). 2. Subject to the terms and conditions of this BeOpen Python License Agreement, BeOpen hereby grants Licensee a non-exclusive, royalty-free, world-wide license to reproduce, analyze, test, perform and/or display publicly, prepare derivative works, distribute, and otherwise use the Software alone or in any derivative version, provided, however, that the BeOpen Python License is retained in the Software, alone or in any derivative version prepared by Licensee. 3. BeOpen is making the Software available to Licensee on an "AS IS" basis. BEOPEN MAKES NO REPRESENTATIONS OR WARRANTIES, EXPRESS OR IMPLIED. BY WAY OF EXAMPLE, BUT NOT LIMITATION, BEOPEN MAKES NO AND DISCLAIMS ANY REPRESENTATION OR WARRANTY OF MERCHANTABILITY OR FITNESS FOR ANY PARTICULAR PURPOSE OR THAT THE USE OF THE SOFTWARE WILL NOT INFRINGE ANY THIRD PARTY RIGHTS. 4. BEOPEN SHALL NOT BE LIABLE TO LICENSEE OR ANY OTHER USERS OF THE SOFTWARE FOR ANY INCIDENTAL, SPECIAL, OR CONSEQUENTIAL DAMAGES OR LOSS AS A RESULT OF USING, MODIFYING OR DISTRIBUTING THE SOFTWARE, OR ANY DERIVATIVE THEREOF, EVEN IF ADVISED OF THE POSSIBILITY THEREOF. 5. This License Agreement will automatically terminate upon a material breach of its terms and conditions. 6. This License Agreement shall be governed by and interpreted in all respects by the law of the State of California, excluding conflict of law provisions. Nothing in this License Agreement shall be deemed to create any relationship of agency, partnership, or joint venture between BeOpen and Licensee. This License Agreement does not grant permission to use BeOpen trademarks or trade names in a trademark sense to endorse or promote products or services of Licensee, or any third party. As an exception, the "BeOpen Python" logos available at http://www.pythonlabs.com/logos.html may be used according to the permissions granted on that web page. 7. By copying, installing or otherwise using the software, Licensee agrees to be bound by the terms and conditions of this License Agreement. CNRI LICENSE AGREEMENT FOR PYTHON 1.6.1 --------------------------------------- 1. This LICENSE AGREEMENT is between the Corporation for National Research Initiatives, having an office at 1895 Preston White Drive, Reston, VA 20191 ("CNRI"), and the Individual or Organization ("Licensee") accessing and otherwise using Python 1.6.1 software in source or binary form and its associated documentation. 2. Subject to the terms and conditions of this License Agreement, CNRI hereby grants Licensee a nonexclusive, royalty-free, world-wide license to reproduce, analyze, test, perform and/or display publicly, prepare derivative works, distribute, and otherwise use Python 1.6.1 alone or in any derivative version, provided, however, that CNRI's License Agreement and CNRI's notice of copyright, i.e., "Copyright (c) 1995-2001 Corporation for National Research Initiatives; All Rights Reserved" are retained in Python 1.6.1 alone or in any derivative version prepared by Licensee. Alternately, in lieu of CNRI's License Agreement, Licensee may substitute the following text (omitting the quotes): "Python 1.6.1 is made available subject to the terms and conditions in CNRI's License Agreement. This Agreement together with Python 1.6.1 may be located on the internet using the following unique, persistent identifier (known as a handle): 1895.22/1013. This Agreement may also be obtained from a proxy server on the internet using the following URL: http://hdl.handle.net/1895.22/1013". 3. In the event Licensee prepares a derivative work that is based on or incorporates Python 1.6.1 or any part thereof, and wants to make the derivative work available to others as provided herein, then Licensee hereby agrees to include in any such work a brief summary of the changes made to Python 1.6.1. 4. CNRI is making Python 1.6.1 available to Licensee on an "AS IS" basis. CNRI MAKES NO REPRESENTATIONS OR WARRANTIES, EXPRESS OR IMPLIED. BY WAY OF EXAMPLE, BUT NOT LIMITATION, CNRI MAKES NO AND DISCLAIMS ANY REPRESENTATION OR WARRANTY OF MERCHANTABILITY OR FITNESS FOR ANY PARTICULAR PURPOSE OR THAT THE USE OF PYTHON 1.6.1 WILL NOT INFRINGE ANY THIRD PARTY RIGHTS. 5. CNRI SHALL NOT BE LIABLE TO LICENSEE OR ANY OTHER USERS OF PYTHON 1.6.1 FOR ANY INCIDENTAL, SPECIAL, OR CONSEQUENTIAL DAMAGES OR LOSS AS A RESULT OF MODIFYING, DISTRIBUTING, OR OTHERWISE USING PYTHON 1.6.1, OR ANY DERIVATIVE THEREOF, EVEN IF ADVISED OF THE POSSIBILITY THEREOF. 6. This License Agreement will automatically terminate upon a material breach of its terms and conditions. 7. This License Agreement shall be governed by the federal intellectual property law of the United States, including without limitation the federal copyright law, and, to the extent such U.S. federal law does not apply, by the law of the Commonwealth of Virginia, excluding Virginia's conflict of law provisions. Notwithstanding the foregoing, with regard to derivative works based on Python 1.6.1 that incorporate non-separable material that was previously distributed under the GNU General Public License (GPL), the law of the Commonwealth of Virginia shall govern this License Agreement only as to issues arising under or with respect to Paragraphs 4, 5, and 7 of this License Agreement. Nothing in this License Agreement shall be deemed to create any relationship of agency, partnership, or joint venture between CNRI and Licensee. This License Agreement does not grant permission to use CNRI trademarks or trade name in a trademark sense to endorse or promote products or services of Licensee, or any third party. 8. By clicking on the "ACCEPT" button where indicated, or by copying, installing or otherwise using Python 1.6.1, Licensee agrees to be bound by the terms and conditions of this License Agreement. ACCEPT CWI LICENSE AGREEMENT FOR PYTHON 0.9.0 THROUGH 1.2 -------------------------------------------------- Copyright (c) 1991 - 1995, Stichting Mathematisch Centrum Amsterdam, The Netherlands. All rights reserved. Permission to use, copy, modify, and distribute this software and its documentation for any purpose and without fee is hereby granted, provided that the above copyright notice appear in all copies and that both that copyright notice and this permission notice appear in supporting documentation, and that the name of Stichting Mathematisch Centrum or CWI not be used in advertising or publicity pertaining to distribution of the software without specific, written prior permission. STICHTING MATHEMATISCH CENTRUM DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS, IN NO EVENT SHALL STICHTING MATHEMATISCH CENTRUM BE LIABLE FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. ZERO-CLAUSE BSD LICENSE FOR CODE IN THE PYTHON DOCUMENTATION ---------------------------------------------------------------------- Permission to use, copy, modify, and/or distribute this software for any purpose with or without fee is hereby granted. THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. pyzipper-0.4.0/MANIFEST.in000066400000000000000000000001311520124366100151260ustar00rootroot00000000000000include AUTHORS.rst include LICENSE include LICENSE.python include README.rst prune test pyzipper-0.4.0/README.rst000066400000000000000000000107121520124366100150650ustar00rootroot00000000000000pyzipper ======== A replacement for Python's ``zipfile`` that can read and write AES encrypted zip files. Forked from Python 3.7's ``zipfile`` module, it features the same ``zipfile`` API from that time (most notably, lacking support for ``pathlib``-compatible wrappers that were introduced in Python 3.8). Installation ------------ .. code-block:: bash pip install pyzipper Usage ----- .. code-block:: python import pyzipper secret_password = b'lost art of keeping a secret' with pyzipper.AESZipFile('new_test.zip', 'w', compression=pyzipper.ZIP_LZMA, encryption=pyzipper.WZ_AES) as zf: zf.setpassword(secret_password) zf.writestr('test.txt', "What ever you do, don't tell anyone!") with pyzipper.AESZipFile('new_test.zip') as zf: zf.setpassword(secret_password) my_secrets = zf.read('test.txt') CRC32 Values ------------ From pyzipper v0.4.0 onwards, no CRC32 values are included in the file headers by default. Prior to v0.4.0 (2026-05-13), a bug resulted in CRC32 values erroneously being included for small files (<20 uncompressed bytes). From the `WZ AES FAQ`_ about CRC values: Within the Zip format, the primary use of the CRC value is to detect accidental corruption of data that has been stored in the Zip file. With files encrypted according to the Zip 2.0 encryption specification, it also functions to some extent as a method of detecting deliberate attempts to modify the encrypted data, but not one that can be considered cryptographically strong. The CRC is not needed for these purposes with the WinZip AES encryption specification, where the HMAC-SHA1-based authentication code instead serves these roles. The CRC has a drawback in that for very small files, such as files with four or fewer bytes, the CRC can be used, independent of the encryption algorithm, to determine the unencrypted contents of the file. And, in general, it is preferable to store as little information as possible about the encrypted file in the unencrypted Zip headers. The CRC does serve one purpose that the authentication code does not. The CRC is computed based on the original uncompressed, unencrypted contents of the file, and it is checked after the file has been decrypted and decompressed. In contrast, the authentication code used with WinZip AES encryption is computed after compression/encryption and it is checked before decryption/decompression. In the very rare event of a hardware or software error that corrupts data during compression and encryption, or during decryption and decompression, the CRC will catch the error, but the authentication code will not. You can conditionally enable the inclusion of the CRC32 values for files with at least ``min_bytes_to_include_crc`` uncompressed bytes using the following code: .. code-block:: python with pyzipper.AESZipFile( 'new_test.zip', 'w', compression=pyzipper.ZIP_LZMA, ) as zf: zf.setencryption( pyzipper.WZ_AES, conditionally_include_crc=True, min_bytes_to_include_crc=, ) ... The lowest number of bytes ``min_bytes_to_include_crc`` may be set to is ``20``, as in `WZ AES FAQ`_. AES Strength ------------ The strength of the AES encryption can be configure to be 128, 192 or 256 bits. By default it is 256 bits. Use the ``setencryption()`` method to specify the encryption kwargs: .. code-block:: python import pyzipper secret_password = b'lost art of keeping a secret' with pyzipper.AESZipFile('new_test.zip', 'w', compression=pyzipper.ZIP_LZMA) as zf: zf.setpassword(secret_password) zf.setencryption(pyzipper.WZ_AES, nbits=256) zf.writestr('test.txt', "What ever you do, don't tell anyone!") with pyzipper.AESZipFile('new_test.zip') as zf: zf.setpassword(secret_password) my_secrets = zf.read('test.txt') Documentation ------------- Official Python ZipFile documentation is available here: https://docs.python.org/3/library/zipfile.html Credits ------- The docs skeleton was created with Cookiecutter_ and the `audreyr/cookiecutter-pypackage`_ project template. .. _Cookiecutter: https://github.com/audreyr/cookiecutter .. _`audreyr/cookiecutter-pypackage`: https://github.com/audreyr/cookiecutter-pypackage .. _`WZ AES FAQ`: https://www.winzip.com/en/support/aes-encryption/#crc-faq pyzipper-0.4.0/SECURITY.rst000066400000000000000000000007141520124366100154000ustar00rootroot00000000000000Security ======== If you have discovered a security vulnerability in this project, please report it privately. **Do not disclose it as a public issue.** This gives us time to work with you to fix the issue before public exposure. Please submit the report as a `Github draft security advisory`_. Please include a description of the impact and how to reproduce it. .. _`Github draft security advisory`: https://github.com/danifus/pyzipper/security/advisories pyzipper-0.4.0/pyproject.toml000066400000000000000000000027471520124366100163230ustar00rootroot00000000000000[build-system] requires = ["setuptools>=77.0.3"] build-backend = "setuptools.build_meta" [project] name = "pyzipper" dynamic = ["version"] requires-python = ">= 3.4" dependencies = [ 'pycryptodomex', ] authors = [ {name = "Daniel Hillier", email = "daniel.hillier@gmail.com"}, ] description = 'AES encryption for zipfile.' readme = "README.rst" license = "MIT" license-files = ["LICENSE", "LICENSE.python", "AUTHORS.rst"] classifiers = [ 'Development Status :: 4 - Beta', 'Topic :: System :: Archiving :: Compression', 'Intended Audience :: Developers', 'Operating System :: MacOS :: MacOS X', 'Operating System :: Microsoft :: Windows', 'Operating System :: POSIX :: Linux', 'Operating System :: POSIX', 'Operating System :: OS Independent', 'Programming Language :: Python', 'Programming Language :: Python :: 3', 'Programming Language :: Python :: 3.4', 'Programming Language :: Python :: 3.5', 'Programming Language :: Python :: 3.6', '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 :: 3.12', 'Programming Language :: Python :: 3.13', 'Programming Language :: Python :: 3.14', ] [project.urls] Homepage = "https://github.com/danifus/pyzipper" [tool.setuptools.dynamic] version = {attr = "pyzipper.__version__.__version__"} pyzipper-0.4.0/pyzipper/000077500000000000000000000000001520124366100152575ustar00rootroot00000000000000pyzipper-0.4.0/pyzipper/__init__.py000066400000000000000000000002301520124366100173630ustar00rootroot00000000000000from .zipfile import * # noqa: F401, F403 from .zipfile_aes import AESZipFile, WZ_AES # noqa: F401 from .__version__ import __version__ # noqa: F401 pyzipper-0.4.0/pyzipper/__version__.py000066400000000000000000000000771520124366100201160ustar00rootroot00000000000000VERSION = (0, 4, 0) __version__ = '.'.join(map(str, VERSION)) pyzipper-0.4.0/pyzipper/zipfile.py000066400000000000000000002726331520124366100173100ustar00rootroot00000000000000""" Read and write ZIP files. XXX references to utf-8 need further investigation. """ import io import os import importlib.util import sys import time import stat import shutil import struct import binascii import threading if sys.version_info[0:2] < (3, 6): import pathlib try: import zlib # We may need its compression method crc32 = zlib.crc32 except ImportError: zlib = None crc32 = binascii.crc32 try: import bz2 # We may need its compression method except ImportError: bz2 = None try: import lzma # We may need its compression method except ImportError: lzma = None __all__ = ["BadZipFile", "BadZipfile", "error", "ZIP_STORED", "ZIP_DEFLATED", "ZIP_BZIP2", "ZIP_LZMA", "is_zipfile", "ZipInfo", "ZipFile", "PyZipFile", "LargeZipFile"] class BadZipFile(Exception): pass class LargeZipFile(Exception): """ Raised when writing a zipfile, the zipfile requires ZIP64 extensions and those extensions are disabled. """ error = BadZipfile = BadZipFile # Pre-3.2 compatibility names ZIP64_LIMIT = (1 << 31) - 1 ZIP_FILECOUNT_LIMIT = (1 << 16) - 1 ZIP_MAX_COMMENT = (1 << 16) - 1 # constants for Zip file compression methods ZIP_STORED = 0 ZIP_DEFLATED = 8 ZIP_BZIP2 = 12 ZIP_LZMA = 14 # Other ZIP compression methods not supported DEFAULT_VERSION = 20 ZIP64_VERSION = 45 BZIP2_VERSION = 46 LZMA_VERSION = 63 # we recognize (but not necessarily support) all features up to that version MAX_EXTRACT_VERSION = 63 # Extensible data field codes: # Zip64 extended information extra field EXTRA_ZIP64 = 0x0001 # Below are some formats and associated data for reading/writing headers using # the struct module. The names and structures of headers/records are those used # in the PKWARE description of the ZIP file format: # http://www.pkware.com/documents/casestudies/APPNOTE.TXT # (URL valid as of January 2008) # The "end of central directory" structure, magic number, size, and indices # (section V.I in the format document) structEndArchive = b"<4s4H2LH" stringEndArchive = b"PK\005\006" sizeEndCentDir = struct.calcsize(structEndArchive) _ECD_SIGNATURE = 0 _ECD_DISK_NUMBER = 1 _ECD_DISK_START = 2 _ECD_ENTRIES_THIS_DISK = 3 _ECD_ENTRIES_TOTAL = 4 _ECD_SIZE = 5 _ECD_OFFSET = 6 _ECD_COMMENT_SIZE = 7 # These last two indices are not part of the structure as defined in the # spec, but they are used internally by this module as a convenience _ECD_COMMENT = 8 _ECD_LOCATION = 9 # The "central directory" structure, magic number, size, and indices # of entries in the structure (section V.F in the format document) structCentralDir = "<4s4B4HL2L5H2L" stringCentralDir = b"PK\001\002" sizeCentralDir = struct.calcsize(structCentralDir) # indexes of entries in the central directory structure _CD_SIGNATURE = 0 _CD_CREATE_VERSION = 1 _CD_CREATE_SYSTEM = 2 _CD_EXTRACT_VERSION = 3 _CD_EXTRACT_SYSTEM = 4 _CD_FLAG_BITS = 5 _CD_COMPRESS_TYPE = 6 _CD_TIME = 7 _CD_DATE = 8 _CD_CRC = 9 _CD_COMPRESSED_SIZE = 10 _CD_UNCOMPRESSED_SIZE = 11 _CD_FILENAME_LENGTH = 12 _CD_EXTRA_FIELD_LENGTH = 13 _CD_COMMENT_LENGTH = 14 _CD_DISK_NUMBER_START = 15 _CD_INTERNAL_FILE_ATTRIBUTES = 16 _CD_EXTERNAL_FILE_ATTRIBUTES = 17 _CD_LOCAL_HEADER_OFFSET = 18 _MASK_ENCRYPTED = 1 << 0 _MASK_COMPRESS_OPTION_1 = 1 << 1 _MASK_COMPRESS_OPTION_2 = 1 << 2 _MASK_USE_DATA_DESCRIPTOR = 1 << 3 # Bit 4: Reserved for use with compression method 8, for enhanced deflating. _MASK_RESERVED_BIT_4 = 1 << 4 _MASK_COMPRESSED_PATCH = 1 << 5 _MASK_STRONG_ENCRYPTION = 1 << 6 _MASK_UNUSED_BIT_7 = 1 << 7 _MASK_UNUSED_BIT_8 = 1 << 8 _MASK_UNUSED_BIT_9 = 1 << 9 _MASK_UNUSED_BIT_10 = 1 << 10 _MASK_UTF_FILENAME = 1 << 11 # Bit 12: Reserved by PKWARE for enhanced compression. _MASK_RESERVED_BIT_12 = 1 << 12 _MASK_ENCRYPTED_CENTRAL_DIR = 1 << 13 # Bit 14, 15: Reserved by PKWARE _MASK_RESERVED_BIT_14 = 1 << 14 _MASK_RESERVED_BIT_15 = 1 << 15 # The "local file header" structure, magic number, size, and indices # (section V.A in the format document) structFileHeader = "<4s2B4HL2L2H" stringFileHeader = b"PK\003\004" sizeFileHeader = struct.calcsize(structFileHeader) _FH_SIGNATURE = 0 _FH_EXTRACT_VERSION = 1 _FH_EXTRACT_SYSTEM = 2 _FH_GENERAL_PURPOSE_FLAG_BITS = 3 _FH_COMPRESSION_METHOD = 4 _FH_LAST_MOD_TIME = 5 _FH_LAST_MOD_DATE = 6 _FH_CRC = 7 _FH_COMPRESSED_SIZE = 8 _FH_UNCOMPRESSED_SIZE = 9 _FH_FILENAME_LENGTH = 10 _FH_EXTRA_FIELD_LENGTH = 11 # The "Zip64 end of central directory locator" structure, magic number, and size structEndArchive64Locator = "<4sLQL" stringEndArchive64Locator = b"PK\x06\x07" sizeEndCentDir64Locator = struct.calcsize(structEndArchive64Locator) # The "Zip64 end of central directory" record, magic number, size, and indices # (section V.G in the format document) structEndArchive64 = "<4sQ2H2L4Q" stringEndArchive64 = b"PK\x06\x06" sizeEndCentDir64 = struct.calcsize(structEndArchive64) _CD64_SIGNATURE = 0 _CD64_DIRECTORY_RECSIZE = 1 _CD64_CREATE_VERSION = 2 _CD64_EXTRACT_VERSION = 3 _CD64_DISK_NUMBER = 4 _CD64_DISK_NUMBER_START = 5 _CD64_NUMBER_ENTRIES_THIS_DISK = 6 _CD64_NUMBER_ENTRIES_TOTAL = 7 _CD64_DIRECTORY_SIZE = 8 _CD64_OFFSET_START_CENTDIR = 9 _DD_SIGNATURE = 0x08074b50 _EXTRA_FIELD_STRUCT = struct.Struct('= 0: # found the magic number; attempt to unpack and interpret recData = data[start:start+sizeEndCentDir] if len(recData) != sizeEndCentDir: # Zip file is corrupted. return None endrec = list(struct.unpack(structEndArchive, recData)) commentSize = endrec[_ECD_COMMENT_SIZE] # as claimed by the zip file comment = data[start+sizeEndCentDir:start+sizeEndCentDir+commentSize] endrec.append(comment) endrec.append(maxCommentStart + start) # Try to read the "Zip64 end of central directory" structure return _EndRecData64(fpin, maxCommentStart + start - filesize, endrec) # Unable to find a valid end of central directory structure return None class ZipInfo (object): """Class with attributes describing each file in the ZIP archive.""" __slots__ = ( 'orig_filename', 'filename', 'date_time', 'compress_type', '_compresslevel', 'comment', 'extra', 'create_system', 'create_version', 'extract_version', 'reserved', 'flag_bits', 'volume', 'internal_attr', 'external_attr', 'header_offset', 'CRC', 'compress_size', 'file_size', '_raw_time', ) def __init__(self, filename="NoName", date_time=(1980, 1, 1, 0, 0, 0)): self.orig_filename = filename # Original file name in archive # Terminate the file name at the first null byte. Null bytes in file # names are used as tricks by viruses in archives. null_byte = filename.find(chr(0)) if null_byte >= 0: filename = filename[0:null_byte] # This is used to ensure paths in generated ZIP files always use # forward slashes as the directory separator, as required by the # ZIP format specification. if os.sep != "/" and os.sep in filename: filename = filename.replace(os.sep, "/") self.filename = filename # Normalized file name self.date_time = date_time # year, month, day, hour, min, sec if date_time[0] < 1980: raise ValueError('ZIP does not support timestamps before 1980') # Standard values: self.compress_type = ZIP_STORED # Type of compression for the file self._compresslevel = None # Level for the compressor self.comment = b"" # Comment for each file self.extra = b"" # ZIP extra data if sys.platform == 'win32': self.create_system = 0 # System which created ZIP archive else: # Assume everything else is unix-y self.create_system = 3 # System which created ZIP archive self.create_version = DEFAULT_VERSION # Version which created ZIP archive self.extract_version = DEFAULT_VERSION # Version needed to extract archive self.reserved = 0 # Must be zero self.flag_bits = 0 # ZIP flag bits self.volume = 0 # Volume number of file header self.internal_attr = 0 # Internal attributes self.external_attr = 0 # External file attributes # Other attributes are set by class ZipFile: # header_offset Byte offset to the file header # CRC CRC-32 of the uncompressed file # compress_size Size of the compressed file # file_size Size of the uncompressed file def __repr__(self): result = ['<%s filename=%r' % (self.__class__.__name__, self.filename)] if self.compress_type != ZIP_STORED: result.append(' compress_type=%s' % compressor_names.get(self.compress_type, self.compress_type)) hi = self.external_attr >> 16 lo = self.external_attr & 0xFFFF if hi: result.append(' filemode=%r' % stat.filemode(hi)) if lo: result.append(' external_attr=%#x' % lo) isdir = self.is_dir() if not isdir or self.file_size: result.append(' file_size=%r' % self.file_size) if ((not isdir or self.compress_size) and (self.compress_type != ZIP_STORED or self.file_size != self.compress_size)): result.append(' compress_size=%r' % self.compress_size) result.append('>') return ''.join(result) @property def is_encrypted(self): return self.flag_bits & _MASK_ENCRYPTED @property def is_utf_filename(self): """Return True if filenames are encoded in UTF-8. Bit 11: Language encoding flag (EFS). If this bit is set, the filename and comment fields for this file MUST be encoded using UTF-8. """ return self.flag_bits & _MASK_UTF_FILENAME @property def is_compressed_patch_data(self): # Zip 2.7: compressed patched data return self.flag_bits & _MASK_COMPRESSED_PATCH @property def is_strong_encryption(self): return self.flag_bits & _MASK_STRONG_ENCRYPTION @property def use_datadescripter(self): """Returns True if datadescripter is in use. If bit 3 of flags is set, the data descripter is must exist. It is byte aligned and immediately follows the last byte of compressed data. crc-32 4 bytes compressed size 4 bytes uncompressed size 4 bytes """ return self.flag_bits & _MASK_USE_DATA_DESCRIPTOR def encode_datadescripter(self, zip64, crc, compress_size, file_size): fmt = ' ZIP64_LIMIT or compress_size > ZIP64_LIMIT if zip64 is None: zip64 = requires_zip64 if zip64: extra = struct.pack( ' ZIP64_LIMIT: zip64_fields.append(self.file_size) file_size = 0xffffffff else: file_size = self.file_size if self.compress_size > ZIP64_LIMIT: zip64_fields.append(self.compress_size) compress_size = 0xffffffff else: compress_size = self.compress_size if self.header_offset > ZIP64_LIMIT: zip64_fields.append(self.header_offset) header_offset = 0xffffffff else: header_offset = self.header_offset # For completeness - We don't support writing disks with multiple parts # so the number of disks is always going to be 0. Definitely not # more than 65,535. # ZIP64_DISK_LIMIT = (1 << 16) - 1 # if self.disk_start > ZIP64_DISK_LIMIT: # zip64_fields.append(self.disk_start) # disk_num = 0xffff # else: # header_offset = self.disk_start min_version = 0 if zip64_fields: extra = struct.pack( '= 4: tp, ln = struct.unpack(' len(extra): raise BadZipFile( "Corrupt extra field %04x (size=%d)" % (tp, ln) ) try: extra_decoders[tp](ln, extra) except KeyError: # We don't support this particular Extra Data field pass extra = extra[ln+4:] @classmethod def from_file(cls, filename, arcname=None, *, strict_timestamps=True): """Construct an appropriate ZipInfo for a file on the filesystem. filename should be the path to a file or directory on the filesystem. arcname is the name which it will have within the archive (by default, this will be the same as filename, but without a drive letter and with leading path separators removed). """ # os.PathLike and os.fspath were added in python 3.6 if sys.version_info[0:2] >= (3, 6): if isinstance(filename, os.PathLike): filename = os.fspath(filename) else: if isinstance(filename, pathlib.PurePath): filename = str(filename) st = os.stat(filename) isdir = stat.S_ISDIR(st.st_mode) mtime = time.localtime(st.st_mtime) date_time = mtime[0:6] if not strict_timestamps and date_time[0] < 1980: date_time = (1980, 1, 1, 0, 0, 0) elif not strict_timestamps and date_time[0] > 2107: date_time = (2107, 12, 31, 23, 59, 59) # Create ZipInfo instance to store file information if arcname is None: arcname = filename arcname = os.path.normpath(os.path.splitdrive(arcname)[1]) while arcname[0] in (os.sep, os.altsep): arcname = arcname[1:] if isdir: arcname += '/' zinfo = cls(arcname, date_time) zinfo.external_attr = (st.st_mode & 0xFFFF) << 16 # Unix attributes if isdir: zinfo.file_size = 0 zinfo.external_attr |= 0x10 # MS-DOS directory flag else: zinfo.file_size = st.st_size return zinfo def is_dir(self): """Return True if this archive member is a directory.""" return self.filename[-1] == '/' # ZIP encryption uses the CRC32 one-byte primitive for scrambling some # internal keys. We noticed that a direct implementation is faster than # relying on binascii.crc32(). _crctable = None def _gen_crc(crc): for j in range(8): if crc & 1: crc = (crc >> 1) ^ 0xEDB88320 else: crc >>= 1 return crc class BaseZipDecrypter: def decrypt(self, data): raise NotImplementedError( 'BaseZipDecrypter implementations must implement `decrypt`.' ) class CRCZipDecrypter(BaseZipDecrypter): """PKWARE Encryption Decrypter ZIP supports a password-based form of encryption. Even though known plaintext attacks have been found against it, it is still useful to be able to get data out of such a file. Usage: zd = CRCZipDecrypter(zinfo, mypwd, encryption_header) plain_bytes = zd.decrypt(cypher_bytes) """ encryption_header_length = 12 def __init__(self, zinfo, pwd, encryption_header): self.key0 = 305419896 self.key1 = 591751049 self.key2 = 878082192 global _crctable if _crctable is None: _crctable = list(map(_gen_crc, range(256))) self.crctable = _crctable for p in pwd: self.update_keys(p) # The first 12 bytes in the cypher stream is an encryption header # used to strengthen the algorithm. The first 11 bytes are # completely random, while the 12th contains the MSB of the CRC, # or the MSB of the file time depending on the header type # and is used to check the correctness of the password. h = self.decrypt(encryption_header[0:12]) if zinfo.use_datadescripter: # compare against the file type from extended local headers check_byte = (zinfo._raw_time >> 8) & 0xff else: # compare against the CRC otherwise check_byte = (zinfo.CRC >> 24) & 0xff if h[11] != check_byte: raise RuntimeError("Bad password for file %r" % zinfo.filename) def crc32(self, ch, crc): """Compute the CRC32 primitive on one byte.""" return (crc >> 8) ^ self.crctable[(crc ^ ch) & 0xFF] def update_keys(self, c): self.key0 = self.crc32(c, self.key0) self.key1 = (self.key1 + (self.key0 & 0xFF)) & 0xFFFFFFFF self.key1 = (self.key1 * 134775813 + 1) & 0xFFFFFFFF self.key2 = self.crc32(self.key1 >> 24, self.key2) def decrypt(self, data): """Decrypt a bytes object.""" result = bytearray() append = result.append for c in data: k = self.key2 | 2 c ^= ((k * (k ^ 1)) >> 8) & 0xFF self.update_keys(c) append(c) return bytes(result) class LZMACompressor: # The LZMA SDK version is not related to the XZ Util's liblzma version that # the python library links to. The LZMA SDK is associated with the 7-zip # project by Igor Pavlov. If there is a breaking change in how the # properties are packed or their contents, these version identifiers can be # used to specify the strategy for decompression. While the version of the # LZMA SDK changes with each new version of 7zip, I don't believe there has # been any breaking changes since the version supplied here (but I haven't # spent much time confirming if that is true). LZMA_SDK_MAJOR_VERSION = 9 LZMA_SDK_MINOR_VERSION = 4 def __init__(self): self._comp = None def _init(self): props = lzma._encode_filter_properties({'id': lzma.FILTER_LZMA1}) self._comp = lzma.LZMACompressor(lzma.FORMAT_RAW, filters=[ lzma._decode_filter_properties(lzma.FILTER_LZMA1, props) ]) header = struct.pack( '') return ''.join(result) def readline(self, limit=-1): """Read and return a line from the stream. If limit is specified, at most limit bytes will be read. """ if limit < 0: # Shortcut common case - newline found in buffer. i = self._readbuffer.find(b'\n', self._offset) + 1 if i > 0: line = self._readbuffer[self._offset: i] self._offset = i return line return io.BufferedIOBase.readline(self, limit) def peek(self, n=1): """Returns buffered bytes without advancing the position.""" if n > len(self._readbuffer) - self._offset: chunk = self.read(n) if len(chunk) > self._offset: self._readbuffer = chunk + self._readbuffer[self._offset:] self._offset = 0 else: self._offset -= len(chunk) # Return up to 512 bytes to reduce allocation overhead for tight loops. return self._readbuffer[self._offset: self._offset + 512] def readable(self): return True def read(self, n=-1): """Read and return up to n bytes. If the argument is omitted, None, or negative, data is read and returned until EOF is reached. """ if n is None or n < 0: buf = self._readbuffer[self._offset:] self._readbuffer = b'' self._offset = 0 while not self._eof: buf += self._read1(self.MAX_N) return buf end = n + self._offset if end < len(self._readbuffer): buf = self._readbuffer[self._offset:end] self._offset = end return buf n = end - len(self._readbuffer) buf = self._readbuffer[self._offset:] self._readbuffer = b'' self._offset = 0 while n > 0 and not self._eof: data = self._read1(n) if n < len(data): self._readbuffer = data self._offset = n buf += data[:n] break buf += data n -= len(data) return buf def _update_crc(self, newdata): # Update the CRC using the given data. if self._expected_crc is None: # No need to compute the CRC if we don't have a reference value return self._running_crc = crc32(newdata, self._running_crc) def check_crc(self): if self._expected_crc is None: # No need to compute the CRC if we don't have a reference value return # Check the CRC if we're at the end of the file if self._eof and self._running_crc != self._expected_crc: raise BadZipFile("Bad CRC-32 for file %r" % self.name) def check_integrity(self): self.check_crc() def read1(self, n): """Read up to n bytes with at most one read() system call.""" if n is None or n < 0: buf = self._readbuffer[self._offset:] self._readbuffer = b'' self._offset = 0 while not self._eof: data = self._read1(self.MAX_N) if data: buf += data break return buf end = n + self._offset if end < len(self._readbuffer): buf = self._readbuffer[self._offset:end] self._offset = end return buf n = end - len(self._readbuffer) buf = self._readbuffer[self._offset:] self._readbuffer = b'' self._offset = 0 if n > 0: while not self._eof: data = self._read1(n) if n < len(data): self._readbuffer = data self._offset = n buf += data[:n] break if data: buf += data break return buf def _read1(self, n): # Read up to n compressed bytes with at most one read() system call, # decrypt and decompress them. if self._eof or n <= 0: return b'' # Read from file. if self._compress_type == ZIP_DEFLATED: # Handle unconsumed data. data = self._decompressor.unconsumed_tail if n > len(data): data += self._read2(n - len(data)) else: data = self._read2(n) if self._compress_type == ZIP_STORED: self._eof = self._compress_left <= 0 elif self._compress_type == ZIP_DEFLATED: n = max(n, self.MIN_READ_SIZE) data = self._decompressor.decompress(data, n) self._eof = (self._decompressor.eof or self._compress_left <= 0 and not self._decompressor.unconsumed_tail) if self._eof: data += self._decompressor.flush() else: data = self._decompressor.decompress(data) self._eof = self._decompressor.eof or self._compress_left <= 0 data = data[:self._left] self._left -= len(data) if self._left <= 0: self._eof = True self._update_crc(data) if self._eof: self.check_integrity() return data def _read2(self, n): if self._compress_left <= 0: return b'' n = max(n, self.MIN_READ_SIZE) n = min(n, self._compress_left) data = self._fileobj.read(n) self._compress_left -= len(data) if not data: raise EOFError if self._decrypter is not None: data = self._decrypter.decrypt(data) return data def close(self): try: if self._close_fileobj: self._fileobj.close() finally: super().close() def seekable(self): return self._seekable def seek(self, offset, whence=0): if not self._seekable: raise io.UnsupportedOperation("underlying stream is not seekable") curr_pos = self.tell() if whence == 0: # Seek from start of file new_pos = offset elif whence == 1: # Seek from current position new_pos = curr_pos + offset elif whence == 2: # Seek from EOF new_pos = self._zinfo.file_size + offset else: raise ValueError("whence must be os.SEEK_SET (0), " "os.SEEK_CUR (1), or os.SEEK_END (2)") if new_pos > self._zinfo.file_size: new_pos = self._zinfo.file_size if new_pos < 0: new_pos = 0 read_offset = new_pos - curr_pos buff_offset = read_offset + self._offset if buff_offset >= 0 and buff_offset < len(self._readbuffer): # Just move the _offset index if the new position is in the # _readbuffer self._offset = buff_offset read_offset = 0 elif read_offset < 0: # Position is before the current position. Reset the ZipExtFile self._fileobj.seek(self._compress_start) self.read_init() read_offset = new_pos while read_offset > 0: read_len = min(self.MAX_SEEK_READ, read_offset) self.read(read_len) read_offset -= read_len return self.tell() def tell(self): if not self._seekable: raise io.UnsupportedOperation("underlying stream is not seekable") filepos = ( self._zinfo.file_size - self._left - len(self._readbuffer) + self._offset ) return filepos class _ZipWriteFile(io.BufferedIOBase): def __init__(self, zf, zinfo, zip64, encrypter=None): self._zinfo = zinfo self._zip64 = zip64 self._zipfile = zf self._compressor = _get_compressor(zinfo.compress_type, zinfo._compresslevel) self._encrypter = encrypter self._file_size = 0 self._compress_size = 0 self._crc = 0 self.write_local_header() if self._encrypter: self.write_encryption_header() @property def _fileobj(self): return self._zipfile.fp def writable(self): return True def write_local_header(self): header = self._zinfo.FileHeader(self._zip64) # From this point onwards, we have likely altered the contents of the # file. self._zipfile._didModify = True self._zipfile._writing = True self._fileobj.write(header) def write_encryption_header(self): buf = self._encrypter.encryption_header() self._compress_size += len(buf) self._fileobj.write(buf) def write(self, data): if self.closed: raise ValueError('I/O operation on closed file.') nbytes = len(data) self._file_size += nbytes self._crc = crc32(data, self._crc) if self._compressor: data = self._compressor.compress(data) if self._encrypter: data = self._encrypter.encrypt(data) self._compress_size += len(data) self._fileobj.write(data) return nbytes def close(self): if self.closed: return super().close() # Flush any data from the compressor, and update header info if self._compressor: buf = self._compressor.flush() else: buf = b'' if self._encrypter: buf = self._encrypter.encrypt(buf) buf += self._encrypter.flush() self._compress_size += len(buf) self._fileobj.write(buf) self._zinfo.compress_size = self._compress_size self._zinfo.CRC = self._crc self._zinfo.file_size = self._file_size if self._encrypter: self._encrypter.finalize_zipinfo(self._zinfo) if not self._zip64: if self._file_size > ZIP64_LIMIT: raise RuntimeError('File size unexpectedly exceeded ZIP64 ' 'limit') if self._compress_size > ZIP64_LIMIT: raise RuntimeError('Compressed size unexpectedly exceeded ' 'ZIP64 limit') # Write updated header info if self._zinfo.use_datadescripter: # Write CRC and file sizes after the file data self._fileobj.write(self._zinfo.datadescripter(self._zip64)) self._zipfile.start_dir = self._fileobj.tell() else: # Seek backwards and write file header (which will now include # correct CRC and file sizes) # Preserve current position in file self._zipfile.start_dir = self._fileobj.tell() self._fileobj.seek(self._zinfo.header_offset) self._fileobj.write(self._zinfo.FileHeader(self._zip64)) self._fileobj.seek(self._zipfile.start_dir) self._zipfile._writing = False # Successfully written: Add file to our caches self._zipfile.filelist.append(self._zinfo) self._zipfile.NameToInfo[self._zinfo.filename] = self._zinfo class ZipFile: """ Class with methods to open, read, write, close, list zip files. z = ZipFile(file, mode="r", compression=ZIP_STORED, allowZip64=True, compresslevel=None) file: Either the path to the file, or a file-like object. If it is a path, the file will be opened and closed by ZipFile. mode: The mode can be either read 'r', write 'w', exclusive create 'x', or append 'a'. compression: ZIP_STORED (no compression), ZIP_DEFLATED (requires zlib), ZIP_BZIP2 (requires bz2) or ZIP_LZMA (requires lzma). allowZip64: if True ZipFile will create files with ZIP64 extensions when needed, otherwise it will raise an exception when this would be necessary. compresslevel: None (default for the given compression type) or an integer specifying the level to pass to the compressor. When using ZIP_STORED or ZIP_LZMA this keyword has no effect. When using ZIP_DEFLATED integers 0 through 9 are accepted. When using ZIP_BZIP2 integers 1 through 9 are accepted. """ fp = None # Set here since __del__ checks it _windows_illegal_name_trans_table = None zipinfo_cls = ZipInfo zipextfile_cls = ZipExtFile zipwritefile_cls = _ZipWriteFile def __init__(self, file, mode="r", compression=ZIP_STORED, allowZip64=True, compresslevel=None, *, strict_timestamps=True): """Open the ZIP file with mode read 'r', write 'w', exclusive create 'x', or append 'a'.""" if mode not in ('r', 'w', 'x', 'a'): raise ValueError("ZipFile requires mode 'r', 'w', 'x', or 'a'") _check_compression(compression) self._allowZip64 = allowZip64 self._didModify = False self.debug = 0 # Level of printing: 0 through 3 self.NameToInfo = {} # Find file info given name self.filelist = [] # List of ZipInfo instances for archive self.compression = compression # Method of compression self.compresslevel = compresslevel self.mode = mode self.pwd = None self.encryption = None self.encryption_kwargs = None self._comment = b'' self._strict_timestamps = strict_timestamps # Check if we were passed a file-like object # os.PathLike and os.fspath were added in python 3.6 if sys.version_info[0:2] >= (3, 6): if isinstance(file, os.PathLike): file = os.fspath(file) else: if isinstance(file, pathlib.PurePath): file = str(file) if isinstance(file, str): # No, it's a filename self._filePassed = 0 self.filename = file modeDict = {'r': 'rb', 'w': 'w+b', 'x': 'x+b', 'a': 'r+b', 'r+b': 'w+b', 'w+b': 'wb', 'x+b': 'xb'} filemode = modeDict[mode] while True: try: self.fp = io.open(file, filemode) except OSError: if filemode in modeDict: filemode = modeDict[filemode] continue raise break else: self._filePassed = 1 self.fp = file self.filename = getattr(file, 'name', None) self._fileRefCnt = 1 self._lock = threading.RLock() self._seekable = True self._writing = False try: if mode == 'r': self._RealGetContents() elif mode in ('w', 'x'): # set the modified flag so central directory gets written # even if no files are added to the archive self._didModify = True try: self.start_dir = self.fp.tell() except (AttributeError, OSError): self.fp = _Tellable(self.fp) self.start_dir = 0 self._seekable = False else: # Some file-like objects can provide tell() but not seek() try: self.fp.seek(self.start_dir) except (AttributeError, OSError): self._seekable = False elif mode == 'a': try: # See if file is a zip file self._RealGetContents() # seek to start of directory and overwrite self.fp.seek(self.start_dir) except BadZipFile: # file is not a zip file, just append self.fp.seek(0, 2) # set the modified flag so central directory gets written # even if no files are added to the archive self._didModify = True self.start_dir = self.fp.tell() else: raise ValueError("Mode must be 'r', 'w', 'x', or 'a'") except Exception as e: fp = self.fp self.fp = None self._fpclose(fp) raise e def __enter__(self): return self def __exit__(self, type, value, traceback): self.close() def __repr__(self): result = ['<%s.%s' % (self.__class__.__module__, self.__class__.__qualname__)] if self.fp is not None: if self._filePassed: result.append(' file=%r' % self.fp) elif self.filename is not None: result.append(' filename=%r' % self.filename) result.append(' mode=%r' % self.mode) else: result.append(' [closed]') result.append('>') return ''.join(result) def _RealGetContents(self): """Read in the table of contents for the ZIP file.""" fp = self.fp try: endrec = _EndRecData(fp) except OSError: raise BadZipFile("File is not a zip file") if not endrec: raise BadZipFile("File is not a zip file") if self.debug > 1: print(endrec) size_cd = endrec[_ECD_SIZE] # bytes in central directory offset_cd = endrec[_ECD_OFFSET] # offset of central directory self._comment = endrec[_ECD_COMMENT] # archive comment # "concat" is zero, unless zip was concatenated to another file concat = endrec[_ECD_LOCATION] - size_cd - offset_cd if endrec[_ECD_SIGNATURE] == stringEndArchive64: # If Zip64 extension structures are present, account for them concat -= (sizeEndCentDir64 + sizeEndCentDir64Locator) if self.debug > 2: inferred = concat + offset_cd print("given, inferred, offset", offset_cd, inferred, concat) # self.start_dir: Position of start of central directory self.start_dir = offset_cd + concat fp.seek(self.start_dir, 0) data = fp.read(size_cd) fp = io.BytesIO(data) total = 0 while total < size_cd: centdir = fp.read(sizeCentralDir) if len(centdir) != sizeCentralDir: raise BadZipFile("Truncated central directory") centdir = struct.unpack(structCentralDir, centdir) if centdir[_CD_SIGNATURE] != stringCentralDir: raise BadZipFile("Bad magic number for central directory") if self.debug > 2: print(centdir) filename = fp.read(centdir[_CD_FILENAME_LENGTH]) flags = centdir[5] if flags & _MASK_UTF_FILENAME: # UTF-8 file names extension filename = filename.decode('utf-8') else: # Historical ZIP filename encoding filename = filename.decode('cp437') # Create ZipInfo instance to store file information x = self.zipinfo_cls(filename) x.extra = fp.read(centdir[_CD_EXTRA_FIELD_LENGTH]) x.comment = fp.read(centdir[_CD_COMMENT_LENGTH]) x.header_offset = centdir[_CD_LOCAL_HEADER_OFFSET] (x.create_version, x.create_system, x.extract_version, x.reserved, x.flag_bits, x.compress_type, t, d, x.CRC, x.compress_size, x.file_size) = centdir[1:12] if x.extract_version > MAX_EXTRACT_VERSION: raise NotImplementedError("zip file version %.1f" % (x.extract_version / 10)) x.volume, x.internal_attr, x.external_attr = centdir[15:18] # Convert date/time code to (year, month, day, hour, min, sec) x._raw_time = t x.date_time = ((d >> 9)+1980, (d >> 5) & 0xF, d & 0x1F, t >> 11, (t >> 5) & 0x3F, (t & 0x1F) * 2) x._decodeExtra() x.header_offset = x.header_offset + concat self.filelist.append(x) self.NameToInfo[x.filename] = x # update total bytes read from central directory total = (total + sizeCentralDir + centdir[_CD_FILENAME_LENGTH] + centdir[_CD_EXTRA_FIELD_LENGTH] + centdir[_CD_COMMENT_LENGTH]) if self.debug > 2: print("total", total) def namelist(self): """Return a list of file names in the archive.""" return [data.filename for data in self.filelist] def infolist(self): """Return a list of class ZipInfo instances for files in the archive.""" return self.filelist def printdir(self, file=None): """Print a table of contents for the zip file.""" print("%-46s %19s %12s" % ("File Name", "Modified ", "Size"), file=file) for zinfo in self.filelist: date = "%d-%02d-%02d %02d:%02d:%02d" % zinfo.date_time[:6] print("%-46s %s %12d" % (zinfo.filename, date, zinfo.file_size), file=file) def testzip(self): """Read all the files and check the CRC.""" chunk_size = 2 ** 20 for zinfo in self.filelist: try: # Read by chunks, to avoid an OverflowError or a # MemoryError with very large embedded files. with self.open(zinfo.filename, "r") as f: while f.read(chunk_size): # Check CRC-32 pass except BadZipFile: return zinfo.filename def getinfo(self, name): """Return the instance of ZipInfo given 'name'.""" info = self.NameToInfo.get(name) if info is None: raise KeyError( 'There is no item named %r in the archive' % name) return info def setpassword(self, pwd): """Set default password for encrypted files.""" if pwd and not isinstance(pwd, bytes): raise TypeError("pwd: expected bytes, got %s" % type(pwd).__name__) if pwd: self.pwd = pwd else: self.pwd = None def setencryption(self, encryption, **kwargs): self.encryption = encryption self.encryption_kwargs = kwargs def get_encrypter(self): raise NotImplementedError("That encryption method is not supported") @property def comment(self): """The comment text associated with the ZIP file.""" return self._comment @comment.setter def comment(self, comment): if not isinstance(comment, bytes): raise TypeError( "comment: expected bytes, got %s" % type(comment).__name__ ) # check for valid comment length if len(comment) > ZIP_MAX_COMMENT: import warnings warnings.warn('Archive comment is too long; truncating to %d bytes' % ZIP_MAX_COMMENT, stacklevel=2) comment = comment[:ZIP_MAX_COMMENT] self._comment = comment self._didModify = True def read(self, name, pwd=None): """Return file bytes (as a string) for name.""" with self.open(name, "r", pwd) as fp: return fp.read() def open(self, name, mode="r", pwd=None, *, force_zip64=False): """Return file-like object for 'name'. name is a string for the file name within the ZIP file, or a ZipInfo object. mode should be 'r' to read a file already in the ZIP file, or 'w' to write to a file newly added to the archive. pwd is the password to encrypt and decrypt files. When writing, if the file size is not known in advance but may exceed 2 GiB, pass force_zip64 to use the ZIP64 format, which can handle large files. If the size is known in advance, it is best to pass a ZipInfo instance for name, with zinfo.file_size set. """ if mode not in {"r", "w"}: raise ValueError('open() requires mode "r" or "w"') if not self.fp: raise ValueError( "Attempt to use ZIP archive that was already closed") if not pwd: pwd = self.pwd if pwd and not isinstance(pwd, bytes): raise TypeError("pwd: expected bytes, got %s" % type(pwd).__name__) # Make sure we have an info object if isinstance(name, self.zipinfo_cls): # 'name' is already an info object zinfo = name elif mode == 'w': zinfo = self.zipinfo_cls(name) zinfo.compress_type = self.compression zinfo._compresslevel = self.compresslevel else: # Get info object for name zinfo = self.getinfo(name) if mode == 'w': return self._open_to_write(zinfo, force_zip64=force_zip64, pwd=pwd) if self._writing: raise ValueError("Can't read from the ZIP file while there " "is an open writing handle on it. " "Close the writing handle before trying to read.") return self._open_to_read(mode, zinfo, pwd) def _open_to_read(self, mode, zinfo, pwd): # Open for reading: self._fileRefCnt += 1 zef_file = _SharedFile(self.fp, zinfo.header_offset, self._fpclose, self._lock, lambda: self._writing) try: return self.zipextfile_cls(zef_file, mode, zinfo, True, pwd) except Exception as e: zef_file.close() raise e def _open_to_write(self, zinfo, force_zip64=False, pwd=None): if force_zip64 and not self._allowZip64: raise ValueError( "force_zip64 is True, but allowZip64 was False when opening " "the ZIP file." ) if self._writing: raise ValueError("Can't write to the ZIP file while there is " "another write handle open on it. " "Close the first handle before opening another.") # Sizes and CRC are overwritten with correct data after processing the # file if not hasattr(zinfo, 'file_size'): zinfo.file_size = 0 zinfo.compress_size = 0 zinfo.CRC = 0 zinfo.flag_bits = 0x00 encrypter = None if pwd is not None or self.encryption is not None: zinfo.flag_bits |= _MASK_ENCRYPTED encrypter = self.get_encrypter() encrypter.update_zipinfo(zinfo) if zinfo.compress_type == ZIP_LZMA: # Compressed data includes an end-of-stream (EOS) marker zinfo.flag_bits |= _MASK_COMPRESS_OPTION_1 if not self._seekable: zinfo.flag_bits |= _MASK_USE_DATA_DESCRIPTOR if not zinfo.external_attr: zinfo.external_attr = 0o600 << 16 # permissions: ?rw------- # Compressed size can be larger than uncompressed size zip64 = self._allowZip64 and \ (force_zip64 or zinfo.file_size * 1.05 > ZIP64_LIMIT) # noqa: E127 if self._seekable: self.fp.seek(self.start_dir) zinfo.header_offset = self.fp.tell() self._writecheck(zinfo) return self.zipwritefile_cls(self, zinfo, zip64, encrypter) def extract(self, member, path=None, pwd=None): """Extract a member from the archive to the current working directory, using its full name. Its file information is extracted as accurately as possible. `member` may be a filename or a ZipInfo object. You can specify a different directory using `path`. """ if path is None: path = os.getcwd() else: # os.fspath were added in python 3.6 if sys.version_info[0:2] >= (3, 6): path = os.fspath(path) else: path = str(path) return self._extract_member(member, path, pwd) def extractall(self, path=None, members=None, pwd=None): """Extract all members from the archive to the current working directory. `path` specifies a different directory to extract to. `members` is optional and must be a subset of the list returned by namelist(). """ if members is None: members = self.namelist() if path is None: path = os.getcwd() else: # os.fspath were added in python 3.6 if sys.version_info[0:2] >= (3, 6): path = os.fspath(path) else: path = str(path) for zipinfo in members: self._extract_member(zipinfo, path, pwd) @classmethod def _sanitize_windows_name(cls, arcname, pathsep): """Replace bad characters and remove trailing dots from parts.""" table = cls._windows_illegal_name_trans_table if not table: illegal = ':<>|"?*' table = str.maketrans(illegal, '_' * len(illegal)) cls._windows_illegal_name_trans_table = table arcname = arcname.translate(table) # remove trailing dots arcname = (x.rstrip('.') for x in arcname.split(pathsep)) # rejoin, removing empty parts. arcname = pathsep.join(x for x in arcname if x) return arcname def _extract_member(self, member, targetpath, pwd): """Extract the ZipInfo object 'member' to a physical file on the path targetpath. """ if not isinstance(member, self.zipinfo_cls): member = self.getinfo(member) # build the destination pathname, replacing # forward slashes to platform specific separators. arcname = member.filename.replace('/', os.path.sep) if os.path.altsep: arcname = arcname.replace(os.path.altsep, os.path.sep) # interpret absolute pathname as relative, remove drive letter or # UNC path, redundant separators, "." and ".." components. arcname = os.path.splitdrive(arcname)[1] invalid_path_parts = ('', os.path.curdir, os.path.pardir) arcname = os.path.sep.join(x for x in arcname.split(os.path.sep) if x not in invalid_path_parts) if os.path.sep == '\\': # filter illegal characters on Windows arcname = self._sanitize_windows_name(arcname, os.path.sep) targetpath = os.path.join(targetpath, arcname) targetpath = os.path.normpath(targetpath) # Create all upper directories if necessary. upperdirs = os.path.dirname(targetpath) if upperdirs and not os.path.exists(upperdirs): os.makedirs(upperdirs) if member.is_dir(): if not os.path.isdir(targetpath): os.mkdir(targetpath) return targetpath with self.open(member, pwd=pwd) as source, \ open(targetpath, "wb") as target: shutil.copyfileobj(source, target) return targetpath def _writecheck(self, zinfo): """Check for errors before writing a file to the archive.""" if zinfo.filename in self.NameToInfo: import warnings warnings.warn('Duplicate name: %r' % zinfo.filename, stacklevel=3) if self.mode not in ('w', 'x', 'a'): raise ValueError("write() requires mode 'w', 'x', or 'a'") if not self.fp: raise ValueError( "Attempt to write ZIP archive that was already closed") _check_compression(zinfo.compress_type) if not self._allowZip64: requires_zip64 = None if len(self.filelist) >= ZIP_FILECOUNT_LIMIT: requires_zip64 = "Files count" elif zinfo.file_size > ZIP64_LIMIT: requires_zip64 = "Filesize" elif zinfo.header_offset > ZIP64_LIMIT: requires_zip64 = "Zipfile size" if requires_zip64: raise LargeZipFile(requires_zip64 + " would require ZIP64 extensions") def write(self, filename, arcname=None, compress_type=None, compresslevel=None): """Put the bytes from filename into the archive under the name arcname.""" if not self.fp: raise ValueError( "Attempt to write to ZIP archive that was already closed") if self._writing: raise ValueError( "Can't write to ZIP archive while an open writing handle exists" ) zinfo = self.zipinfo_cls.from_file( filename, arcname, strict_timestamps=self._strict_timestamps) if zinfo.is_dir(): zinfo.compress_size = 0 zinfo.CRC = 0 else: if compress_type is not None: zinfo.compress_type = compress_type else: zinfo.compress_type = self.compression if compresslevel is not None: zinfo._compresslevel = compresslevel else: zinfo._compresslevel = self.compresslevel if zinfo.is_dir(): with self._lock: if self._seekable: self.fp.seek(self.start_dir) zinfo.header_offset = self.fp.tell() # Start of header bytes if zinfo.compress_type == ZIP_LZMA: # Compressed data includes an end-of-stream (EOS) marker zinfo.flag_bits |= _MASK_COMPRESS_OPTION_1 self._writecheck(zinfo) self._didModify = True self.filelist.append(zinfo) self.NameToInfo[zinfo.filename] = zinfo self.fp.write(zinfo.FileHeader(False)) self.start_dir = self.fp.tell() else: with open(filename, "rb") as src, self.open(zinfo, 'w') as dest: shutil.copyfileobj(src, dest, 1024*8) def writestr(self, zinfo_or_arcname, data, compress_type=None, compresslevel=None): """Write a file into the archive. The contents is 'data', which may be either a 'str' or a 'bytes' instance; if it is a 'str', it is encoded as UTF-8 first. 'zinfo_or_arcname' is either a ZipInfo instance or the name of the file in the archive.""" if isinstance(data, str): data = data.encode("utf-8") if not isinstance(zinfo_or_arcname, self.zipinfo_cls): zinfo = self.zipinfo_cls( filename=zinfo_or_arcname, date_time=time.localtime(time.time())[:6]) zinfo.compress_type = self.compression zinfo._compresslevel = self.compresslevel if zinfo.filename[-1] == '/': zinfo.external_attr = 0o40775 << 16 # drwxrwxr-x zinfo.external_attr |= 0x10 # MS-DOS directory flag else: zinfo.external_attr = 0o600 << 16 # ?rw------- else: zinfo = zinfo_or_arcname if not self.fp: raise ValueError( "Attempt to write to ZIP archive that was already closed") if self._writing: raise ValueError( "Can't write to ZIP archive while an open writing handle exists." ) if compress_type is not None: zinfo.compress_type = compress_type if compresslevel is not None: zinfo._compresslevel = compresslevel zinfo.file_size = len(data) # Uncompressed size with self._lock: with self.open(zinfo, mode='w') as dest: dest.write(data) def __del__(self): """Call the "close()" method in case the user forgot.""" self.close() def close(self): """Close the file, and for mode 'w', 'x' and 'a' write the ending records.""" if self.fp is None: return if self._writing: raise ValueError("Can't close the ZIP file while there is " "an open writing handle on it. " "Close the writing handle before closing the zip.") try: if self.mode in ('w', 'x', 'a') and self._didModify: # write ending records with self._lock: if self._seekable: self.fp.seek(self.start_dir) self._write_end_record() finally: fp = self.fp self.fp = None self._fpclose(fp) def _write_end_record(self): for zinfo in self.filelist: # write central directory centdir, filename, extra_data = zinfo.central_directory() self.fp.write(centdir) self.fp.write(filename) self.fp.write(extra_data) self.fp.write(zinfo.comment) pos2 = self.fp.tell() # Write end-of-zip-archive record centDirCount = len(self.filelist) centDirSize = pos2 - self.start_dir centDirOffset = self.start_dir requires_zip64 = None if centDirCount > ZIP_FILECOUNT_LIMIT: requires_zip64 = "Files count" elif centDirOffset > ZIP64_LIMIT: requires_zip64 = "Central directory offset" elif centDirSize > ZIP64_LIMIT: requires_zip64 = "Central directory size" if requires_zip64: # Need to write the ZIP64 end-of-archive records if not self._allowZip64: raise LargeZipFile(requires_zip64 + " would require ZIP64 extensions") zip64endrec = struct.pack( structEndArchive64, stringEndArchive64, 44, 45, 45, 0, 0, centDirCount, centDirCount, centDirSize, centDirOffset) self.fp.write(zip64endrec) zip64locrec = struct.pack( structEndArchive64Locator, stringEndArchive64Locator, 0, pos2, 1) self.fp.write(zip64locrec) centDirCount = min(centDirCount, 0xFFFF) centDirSize = min(centDirSize, 0xFFFFFFFF) centDirOffset = min(centDirOffset, 0xFFFFFFFF) endrec = struct.pack(structEndArchive, stringEndArchive, 0, 0, centDirCount, centDirCount, centDirSize, centDirOffset, len(self._comment)) self.fp.write(endrec) self.fp.write(self._comment) self.fp.flush() def _fpclose(self, fp): assert self._fileRefCnt > 0 self._fileRefCnt -= 1 if not self._fileRefCnt and not self._filePassed: fp.close() class PyZipFile(ZipFile): """Class to create ZIP archives with Python library files and packages.""" def __init__(self, file, mode="r", compression=ZIP_STORED, allowZip64=True, optimize=-1): if sys.version_info[0:2] < (3, 5): raise NotImplementedError( "pyzipper.PyZipFile doesn't work for versions less than 3.5" ) ZipFile.__init__(self, file, mode=mode, compression=compression, allowZip64=allowZip64) self._optimize = optimize def writepy(self, pathname, basename="", filterfunc=None): """Add all files from "pathname" to the ZIP archive. If pathname is a package directory, search the directory and all package subdirectories recursively for all *.py and enter the modules into the archive. If pathname is a plain directory, listdir *.py and enter all modules. Else, pathname must be a Python *.py file and the module will be put into the archive. Added modules are always module.pyc. This method will compile the module.py into module.pyc if necessary. If filterfunc(pathname) is given, it is called with every argument. When it is False, the file or directory is skipped. """ # os.fspath were added in python 3.6 if sys.version_info[0:2] >= (3, 6): pathname = os.fspath(pathname) else: pathname = str(pathname) if filterfunc and not filterfunc(pathname): if self.debug: label = 'path' if os.path.isdir(pathname) else 'file' print('%s %r skipped by filterfunc' % (label, pathname)) return dir, name = os.path.split(pathname) if os.path.isdir(pathname): initname = os.path.join(pathname, "__init__.py") if os.path.isfile(initname): # This is a package directory, add it if basename: basename = "%s/%s" % (basename, name) else: basename = name if self.debug: print("Adding package in", pathname, "as", basename) fname, arcname = self._get_codename(initname[0:-3], basename) if self.debug: print("Adding", arcname) self.write(fname, arcname) dirlist = sorted(os.listdir(pathname)) dirlist.remove("__init__.py") # Add all *.py files and package subdirectories for filename in dirlist: path = os.path.join(pathname, filename) root, ext = os.path.splitext(filename) if os.path.isdir(path): if os.path.isfile(os.path.join(path, "__init__.py")): # This is a package directory, add it self.writepy(path, basename, filterfunc=filterfunc) # Recursive call elif ext == ".py": if filterfunc and not filterfunc(path): if self.debug: print('file %r skipped by filterfunc' % path) continue fname, arcname = self._get_codename(path[0:-3], basename) if self.debug: print("Adding", arcname) self.write(fname, arcname) else: # This is NOT a package directory, add its files at top level if self.debug: print("Adding files from directory", pathname) for filename in sorted(os.listdir(pathname)): path = os.path.join(pathname, filename) root, ext = os.path.splitext(filename) if ext == ".py": if filterfunc and not filterfunc(path): if self.debug: print('file %r skipped by filterfunc' % path) continue fname, arcname = self._get_codename(path[0:-3], basename) if self.debug: print("Adding", arcname) self.write(fname, arcname) else: if pathname[-3:] != ".py": raise RuntimeError( 'Files added with writepy() must end with ".py"') fname, arcname = self._get_codename(pathname[0:-3], basename) if self.debug: print("Adding file", arcname) self.write(fname, arcname) def _get_codename(self, pathname, basename): """Return (filename, archivename) for the path. Given a module name path, return the correct file path and archive name, compiling if necessary. For example, given /python/lib/string, return (/python/lib/string.pyc, string). """ def _compile(file, optimize=-1): import py_compile if self.debug: print("Compiling", file) try: py_compile.compile(file, doraise=True, optimize=optimize) except py_compile.PyCompileError as err: print(err.msg) return False return True file_py = pathname + ".py" file_pyc = pathname + ".pyc" pycache_opt0 = importlib.util.cache_from_source(file_py, optimization='') pycache_opt1 = importlib.util.cache_from_source(file_py, optimization=1) pycache_opt2 = importlib.util.cache_from_source(file_py, optimization=2) if self._optimize == -1: # legacy mode: use whatever file is present if (os.path.isfile(file_pyc) and os.stat(file_pyc).st_mtime >= os.stat(file_py).st_mtime): # Use .pyc file. arcname = fname = file_pyc elif (os.path.isfile(pycache_opt0) and os.stat(pycache_opt0).st_mtime >= os.stat(file_py).st_mtime): # Use the __pycache__/*.pyc file, but write it to the legacy pyc # file name in the archive. fname = pycache_opt0 arcname = file_pyc elif (os.path.isfile(pycache_opt1) and os.stat(pycache_opt1).st_mtime >= os.stat(file_py).st_mtime): # Use the __pycache__/*.pyc file, but write it to the legacy pyc # file name in the archive. fname = pycache_opt1 arcname = file_pyc elif (os.path.isfile(pycache_opt2) and os.stat(pycache_opt2).st_mtime >= os.stat(file_py).st_mtime): # Use the __pycache__/*.pyc file, but write it to the legacy pyc # file name in the archive. fname = pycache_opt2 arcname = file_pyc else: # Compile py into PEP 3147 pyc file. if _compile(file_py): if sys.flags.optimize == 0: fname = pycache_opt0 elif sys.flags.optimize == 1: fname = pycache_opt1 else: fname = pycache_opt2 arcname = file_pyc else: fname = arcname = file_py else: # new mode: use given optimization level if self._optimize == 0: fname = pycache_opt0 arcname = file_pyc else: arcname = file_pyc if self._optimize == 1: fname = pycache_opt1 elif self._optimize == 2: fname = pycache_opt2 else: msg = "invalid value for 'optimize': {!r}".format(self._optimize) raise ValueError(msg) if not (os.path.isfile(fname) and os.stat(fname).st_mtime >= os.stat(file_py).st_mtime): if not _compile(file_py, optimize=self._optimize): fname = arcname = file_py archivename = os.path.split(arcname)[1] if basename: archivename = "%s/%s" % (basename, archivename) return (fname, archivename) def main(args=None): import argparse description = 'A simple command-line interface for zipfile module.' parser = argparse.ArgumentParser(description=description) group = parser.add_mutually_exclusive_group(required=True) group.add_argument('-l', '--list', metavar='', help='Show listing of a zipfile') group.add_argument('-e', '--extract', nargs=2, metavar=('', ''), help='Extract zipfile into target dir') group.add_argument('-c', '--create', nargs='+', metavar=('', ''), help='Create zipfile from sources') group.add_argument('-t', '--test', metavar='', help='Test if a zipfile is valid') args = parser.parse_args(args) if args.test is not None: src = args.test with ZipFile(src, 'r') as zf: badfile = zf.testzip() if badfile: print("The following enclosed file is corrupted: {!r}".format(badfile)) print("Done testing") elif args.list is not None: src = args.list with ZipFile(src, 'r') as zf: zf.printdir() elif args.extract is not None: src, curdir = args.extract with ZipFile(src, 'r') as zf: zf.extractall(curdir) elif args.create is not None: zip_name = args.create.pop(0) files = args.create def addToZip(zf, path, zippath): if os.path.isfile(path): zf.write(path, zippath, ZIP_DEFLATED) elif os.path.isdir(path): if zippath: zf.write(path, zippath) for nm in sorted(os.listdir(path)): addToZip(zf, os.path.join(path, nm), os.path.join(zippath, nm)) # else: ignore with ZipFile(zip_name, 'w') as zf: for path in files: zippath = os.path.basename(path) if not zippath: zippath = os.path.basename(os.path.dirname(path)) if zippath in ('', os.curdir, os.pardir): zippath = '' addToZip(zf, path, zippath) if __name__ == "__main__": main() pyzipper-0.4.0/pyzipper/zipfile_aes.py000066400000000000000000000346041520124366100201320ustar00rootroot00000000000000import struct from Cryptodome.Protocol.KDF import PBKDF2 from Cryptodome.Cipher import AES from Cryptodome.Hash import HMAC from Cryptodome.Hash.SHA1 import SHA1Hash from Cryptodome.Util import Counter from Cryptodome import Random from .zipfile import ( ZIP_BZIP2, ZIP_LZMA, BadZipFile, BaseZipDecrypter, ZipFile, ZipInfo, ZipExtFile, ) WZ_AES = 'WZ_AES' WZ_AES_COMPRESS_TYPE = 99 WZ_AES_V1 = 0x0001 WZ_AES_V2 = 0x0002 WZ_AES_VENDOR_ID = b'AE' EXTRA_WZ_AES = 0x9901 WZ_SALT_LENGTHS = { 1: 8, # 128 bit 2: 12, # 192 bit 3: 16, # 256 bit } WZ_KEY_LENGTHS = { 1: 16, # 128 bit 2: 24, # 192 bit 3: 32, # 256 bit } class AESZipDecrypter(BaseZipDecrypter): hmac_size = 10 def __init__(self, zinfo, pwd, encryption_header): self.filename = zinfo.filename key_length = WZ_KEY_LENGTHS[zinfo.wz_aes_strength] salt_length = WZ_SALT_LENGTHS[zinfo.wz_aes_strength] salt = struct.unpack( "<{}s".format(salt_length), encryption_header[:salt_length] )[0] pwd_verify_length = 2 pwd_verify = encryption_header[salt_length:] dkLen = 2*key_length + pwd_verify_length keymaterial = PBKDF2(pwd, salt, count=1000, dkLen=dkLen) encpwdverify = keymaterial[2*key_length:] if encpwdverify != pwd_verify: raise RuntimeError("Bad password for file %r" % zinfo.filename) enckey = keymaterial[:key_length] self.decypter = AES.new( enckey, AES.MODE_CTR, counter=Counter.new(nbits=128, little_endian=True) ) encmac_key = keymaterial[key_length:2*key_length] self.hmac = HMAC.new(encmac_key, digestmod=SHA1Hash()) @staticmethod def encryption_header_length(zinfo): # salt_length + pwd_verify_length salt_length = WZ_SALT_LENGTHS[zinfo.wz_aes_strength] return salt_length + 2 def decrypt(self, data): self.hmac.update(data) return self.decypter.decrypt(data) def check_hmac(self, hmac_check): if self.hmac.digest()[:10] != hmac_check: raise BadZipFile("Bad HMAC check for file %r" % self.filename) class BaseZipEncrypter: def update_zipinfo(self, zipinfo): """Called when zip entry is opened for write and the encrypted is configured.""" raise NotImplementedError( 'BaseZipEncrypter implementations must implement `update_zipinfo`.' ) def finalize_zipinfo(self, zipinfo): """Updates the zipinfo instance when the zip entry is being closed. It may be possible to update some fields based on information that wasn't available when update_zipinfo was called. This function should not change properties that would need to be written to the local file header if the underlying zip is not seekable as it isn't possible to return to the local file header to rewrite the new values. """ raise NotImplementedError( 'BaseZipEncrypter implementations must implement `finalize_zipinfo`.' ) def encrypt(self, data): raise NotImplementedError( 'BaseZipEncrypter implementations must implement `encrypt`.' ) def encryption_header(self): raise NotImplementedError( 'BaseZipEncrypter implementations must implement ' '`encryption_header`.' ) def flush(self): return b'' class AESZipEncrypter(BaseZipEncrypter): hmac_size = 10 def __init__( self, pwd, nbits=256, force_wz_aes_version=None, conditionally_include_crc=None, min_bytes_to_include_crc=None, ): if not pwd: raise RuntimeError( '%s encryption requires a password.' % WZ_AES ) if nbits not in (128, 192, 256): raise RuntimeError( "`nbits` must be one of 128, 192, 256. Got '%s'" % nbits ) if conditionally_include_crc is not None: if ( conditionally_include_crc is not True and conditionally_include_crc is not False ): raise ValueError( "`conditionally_include_crc` must be True or False or None" ) if conditionally_include_crc: if min_bytes_to_include_crc is None: raise ValueError( "`min_bytes_to_include_crc` must be set if `conditionally_include_crc` is True" # noqa: E501 ) if min_bytes_to_include_crc < 20: raise ValueError( "`min_bytes_to_include_crc` must be 20 or greater" ) if min_bytes_to_include_crc is not None and not conditionally_include_crc: raise ValueError( "`conditionally_include_crc` must be True if `min_bytes_to_include_crc` is set" ) if force_wz_aes_version is not None: if force_wz_aes_version not in (WZ_AES_V1, WZ_AES_V2): raise ValueError( "`force_wz_aes_version` must be WZ_AES_V1 (1) or WZ_AES_V2 (2)" ) if conditionally_include_crc: raise ValueError( "`force_wz_aes_version` and `conditionally_include_crc` must not be specified at the same time." # noqa: E501 ) self.force_wz_aes_version = force_wz_aes_version self.conditionally_include_crc = conditionally_include_crc self.min_bytes_to_include_crc = min_bytes_to_include_crc salt_lengths = { 128: 8, 192: 12, 256: 16, } self.salt_length = salt_lengths[nbits] key_lengths = { 128: 16, 192: 24, 256: 32, } key_length = key_lengths[nbits] aes_strengths = { 128: 1, 192: 2, 256: 3, } self.aes_strength = aes_strengths[nbits] self.salt = Random.new().read(self.salt_length) pwd_verify_length = 2 dkLen = 2 * key_length + pwd_verify_length keymaterial = PBKDF2(pwd, self.salt, count=1000, dkLen=dkLen) self.encpwdverify = keymaterial[2*key_length:] enckey = keymaterial[:key_length] self.encrypter = AES.new( enckey, AES.MODE_CTR, counter=Counter.new(nbits=128, little_endian=True) ) encmac_key = keymaterial[key_length:2*key_length] self.hmac = HMAC.new(encmac_key, digestmod=SHA1Hash()) def compute_aes_version(self, zipinfo): # The only difference between version 1 and 2 is the # handling of the CRC values. For version 2 the CRC value # is not used and must be set to 0. # For small files, the CRC files can leak the contents of # the encrypted data. if self.force_wz_aes_version is not None: return self.force_wz_aes_version elif zipinfo.compress_type == ZIP_BZIP2: # For bzip2, the compression already has integrity checks # so CRC is not required. return WZ_AES_V2 elif ( self.conditionally_include_crc and zipinfo.file_size >= self.min_bytes_to_include_crc ): return WZ_AES_V1 return WZ_AES_V2 def update_zipinfo(self, zipinfo): zipinfo.wz_aes_vendor_id = WZ_AES_VENDOR_ID zipinfo.wz_aes_strength = self.aes_strength zipinfo.wz_aes_version = self.compute_aes_version(zipinfo) def finalize_zipinfo(self, zipinfo): # If we can't seek back, we have to keep the aes version we specified # when the local file header was written. If the file size is unknown, # this should be ae-2 if not zipinfo.use_datadescripter: # We can go back and change the aes version we specified earlier. zipinfo.wz_aes_version = self.compute_aes_version(zipinfo) def encryption_header(self): return self.salt + self.encpwdverify def encrypt(self, data): data = self.encrypter.encrypt(data) self.hmac.update(data) return data def flush(self): return struct.pack('<%ds' % self.hmac_size, self.hmac.digest()[:10]) class AESZipInfo(ZipInfo): """Class with attributes describing each file in the ZIP archive.""" # __slots__ on subclasses only need to contain the additional slots. __slots__ = ( 'wz_aes_version', 'wz_aes_vendor_id', 'wz_aes_strength', # 'wz_aes_actual_compression_type', ) def __init__(self, *args, **kwargs): super().__init__(*args, **kwargs) self.wz_aes_version = None self.wz_aes_vendor_id = None self.wz_aes_strength = None def decode_extra_wz_aes(self, ln, extra): if ln == 7: counts = struct.unpack(" 0: data = self._read2(self.MIN_READ_SIZE) # but we don't want to find any more data here. data = self._decompressor.decompress(data) if data: raise BadZipFile( "More data found than indicated by uncompressed size for " "'{}'".format(self.filename) ) hmac_check = self._fileobj.read(self._decrypter.hmac_size) self._decrypter.check_hmac(hmac_check) def check_integrity(self): if self._zinfo.wz_aes_version is not None: self.check_wz_aes() if self._expected_crc is not None and self._expected_crc != 0: # Not part of the spec but still check the CRC if it is # supplied when WZ_AES_V2 is specified (no CRC check and CRC # should be 0). self.check_crc() elif self._zinfo.wz_aes_version != WZ_AES_V2: # CRC value should be 0 for AES vendor version 2. self.check_crc() else: super().check_integrity() class AESZipFile(ZipFile): zipinfo_cls = AESZipInfo zipextfile_cls = AESZipExtFile def __init__(self, *args, **kwargs): encryption = kwargs.pop('encryption', None) encryption_kwargs = kwargs.pop('encryption_kwargs', None) super().__init__(*args, **kwargs) self.encryption = encryption self.encryption_kwargs = encryption_kwargs def get_encrypter(self): if self.encryption == WZ_AES: if self.encryption_kwargs is None: encryption_kwargs = {} else: encryption_kwargs = self.encryption_kwargs return AESZipEncrypter(pwd=self.pwd, **encryption_kwargs) pyzipper-0.4.0/requirements_build.txt000066400000000000000000000000461520124366100200400ustar00rootroot00000000000000pip==26.1.1 twine==6.2.0 build==1.5.0 pyzipper-0.4.0/requirements_dev.txt000066400000000000000000000002561520124366100175220ustar00rootroot00000000000000# fixed version of pycryptodomex so pyup bot can send PR's on updates pycryptodomex==3.23.0 # testing dependencies flake8==7.3.0 tox==4.53.1 pytest==9.0.3 pytest-cov==7.1.0 pyzipper-0.4.0/run_tests.py000066400000000000000000000007761520124366100160070ustar00rootroot00000000000000import sys import unittest names = [] if len(sys.argv) > 1: test_type = sys.argv[1] if test_type == 'extralargefile': names.append('test.test_zipfile64') elif test_type == 'aes': names.extend([ 'test.test_zipfile_aes', 'test.test_zipfile2' ]) else: names.append('test.test_zipfile') suite = unittest.TestLoader().loadTestsFromNames(names) runner = unittest.TextTestRunner(verbosity=2).run(suite) ret = not runner.wasSuccessful() sys.exit(ret) pyzipper-0.4.0/test/000077500000000000000000000000001520124366100143545ustar00rootroot00000000000000pyzipper-0.4.0/test/__init__.py000066400000000000000000000000001520124366100164530ustar00rootroot00000000000000pyzipper-0.4.0/test/badsyntax_3131.py000066400000000000000000000000401520124366100173640ustar00rootroot00000000000000# -*- coding: utf-8 -*- € = 2 pyzipper-0.4.0/test/badsyntax_future10.py000066400000000000000000000001371520124366100204570ustar00rootroot00000000000000from __future__ import absolute_import "spam, bar, blah" from __future__ import print_function pyzipper-0.4.0/test/badsyntax_future3.py000066400000000000000000000002541520124366100204010ustar00rootroot00000000000000"""This is a test""" from __future__ import nested_scopes from __future__ import rested_snopes def f(x): def g(y): return x + y return g result = f(2)(4) pyzipper-0.4.0/test/badsyntax_future4.py000066400000000000000000000002311520124366100203750ustar00rootroot00000000000000"""This is a test""" import __future__ from __future__ import nested_scopes def f(x): def g(y): return x + y return g result = f(2)(4) pyzipper-0.4.0/test/badsyntax_future5.py000066400000000000000000000002701520124366100204010ustar00rootroot00000000000000"""This is a test""" from __future__ import nested_scopes import foo from __future__ import nested_scopes def f(x): def g(y): return x + y return g result = f(2)(4) pyzipper-0.4.0/test/badsyntax_future6.py000066400000000000000000000002411520124366100204000ustar00rootroot00000000000000"""This is a test""" "this isn't a doc string" from __future__ import nested_scopes def f(x): def g(y): return x + y return g result = f(2)(4) pyzipper-0.4.0/test/badsyntax_future7.py000066400000000000000000000003041520124366100204010ustar00rootroot00000000000000"""This is a test""" from __future__ import nested_scopes; import string; from __future__ import \ nested_scopes def f(x): def g(y): return x + y return g result = f(2)(4) pyzipper-0.4.0/test/badsyntax_future8.py000066400000000000000000000001721520124366100204050ustar00rootroot00000000000000"""This is a test""" from __future__ import * def f(x): def g(y): return x + y return g print(f(2)(4)) pyzipper-0.4.0/test/badsyntax_future9.py000066400000000000000000000002161520124366100204050ustar00rootroot00000000000000"""This is a test""" from __future__ import nested_scopes, braces def f(x): def g(y): return x + y return g print(f(2)(4)) pyzipper-0.4.0/test/badsyntax_pep3120.py000066400000000000000000000000161520124366100200720ustar00rootroot00000000000000print("böse") pyzipper-0.4.0/test/support/000077500000000000000000000000001520124366100160705ustar00rootroot00000000000000pyzipper-0.4.0/test/support/__init__.py000066400000000000000000003103561520124366100202110ustar00rootroot00000000000000"""Supporting definitions for the Python regression tests.""" if __name__ != 'test.support': raise ImportError('support must be imported from the test package') import asyncio.events import collections.abc import contextlib import datetime import errno import faulthandler import fnmatch import functools import gc import importlib import importlib.util import io import logging.handlers import os import platform import re import shutil import socket import stat import struct import subprocess import sys import sysconfig import tempfile import _thread import threading import time import types import unittest import urllib.error import warnings from .testresult import get_test_runner try: import multiprocessing.process except ImportError: multiprocessing = None try: import zlib except ImportError: zlib = None try: import gzip except ImportError: gzip = None try: import bz2 except ImportError: bz2 = None try: import lzma except ImportError: lzma = None try: import resource except ImportError: resource = None __all__ = [ # globals "PIPE_MAX_SIZE", "verbose", "max_memuse", "use_resources", "failfast", # exceptions "Error", "TestFailed", "ResourceDenied", # imports "import_module", "import_fresh_module", "CleanImport", # modules "unload", "forget", # io "record_original_stdout", "get_original_stdout", "captured_stdout", "captured_stdin", "captured_stderr", # filesystem "TESTFN", "SAVEDCWD", "unlink", "rmtree", "temp_cwd", "findfile", "create_empty_file", "can_symlink", "fs_is_case_insensitive", # unittest "is_resource_enabled", "requires", "requires_freebsd_version", "requires_linux_version", "requires_mac_ver", "check_syntax_error", "TransientResource", "time_out", "socket_peer_reset", "ioerror_peer_reset", "transient_internet", "BasicTestRunner", "run_unittest", "run_doctest", "skip_unless_symlink", "requires_gzip", "requires_bz2", "requires_lzma", "bigmemtest", "bigaddrspacetest", "cpython_only", "get_attribute", "requires_IEEE_754", "skip_unless_xattr", "requires_zlib", "anticipate_failure", "load_package_tests", "detect_api_mismatch", "check__all__", "skip_unless_bind_unix_socket", "ignore_warnings", # sys "is_jython", "is_android", "check_impl_detail", "unix_shell", "setswitchinterval", # network "HOST", "IPV6_ENABLED", "find_unused_port", "bind_port", "open_urlresource", "bind_unix_socket", # processes 'temp_umask', "reap_children", # logging "TestHandler", # threads "threading_setup", "threading_cleanup", "reap_threads", "start_threads", # miscellaneous "check_warnings", "check_no_resource_warning", "check_no_warnings", "EnvironmentVarGuard", "run_with_locale", "swap_item", "swap_attr", "Matcher", "set_memlimit", "SuppressCrashReport", "sortdict", "run_with_tz", "PGO", "missing_compiler_executable", "fd_count", ] class Error(Exception): """Base class for regression test exceptions.""" class TestFailed(Error): """Test failed.""" class ResourceDenied(unittest.SkipTest): """Test skipped because it requested a disallowed resource. This is raised when a test calls requires() for a resource that has not be enabled. It is used to distinguish between expected and unexpected skips. """ @contextlib.contextmanager def _ignore_deprecated_imports(ignore=True): """Context manager to suppress package and module deprecation warnings when importing them. If ignore is False, this context manager has no effect. """ if ignore: with warnings.catch_warnings(): warnings.filterwarnings("ignore", ".+ (module|package)", DeprecationWarning) yield else: yield def ignore_warnings(*, category): """Decorator to suppress deprecation warnings. Use of context managers to hide warnings make diffs more noisy and tools like 'git blame' less useful. """ def decorator(test): @functools.wraps(test) def wrapper(self, *args, **kwargs): with warnings.catch_warnings(): warnings.simplefilter('ignore', category=category) return test(self, *args, **kwargs) return wrapper return decorator def import_module(name, deprecated=False, *, required_on=()): """Import and return the module to be tested, raising SkipTest if it is not available. If deprecated is True, any module or package deprecation messages will be suppressed. If a module is required on a platform but optional for others, set required_on to an iterable of platform prefixes which will be compared against sys.platform. """ with _ignore_deprecated_imports(deprecated): try: return importlib.import_module(name) except ImportError as msg: if sys.platform.startswith(tuple(required_on)): raise raise unittest.SkipTest(str(msg)) def _save_and_remove_module(name, orig_modules): """Helper function to save and remove a module from sys.modules Raise ImportError if the module can't be imported. """ # try to import the module and raise an error if it can't be imported if name not in sys.modules: __import__(name) del sys.modules[name] for modname in list(sys.modules): if modname == name or modname.startswith(name + '.'): orig_modules[modname] = sys.modules[modname] del sys.modules[modname] def _save_and_block_module(name, orig_modules): """Helper function to save and block a module in sys.modules Return True if the module was in sys.modules, False otherwise. """ saved = True try: orig_modules[name] = sys.modules[name] except KeyError: saved = False sys.modules[name] = None return saved def anticipate_failure(condition): """Decorator to mark a test that is known to be broken in some cases Any use of this decorator should have a comment identifying the associated tracker issue. """ if condition: return unittest.expectedFailure return lambda f: f def load_package_tests(pkg_dir, loader, standard_tests, pattern): """Generic load_tests implementation for simple test packages. Most packages can implement load_tests using this function as follows: def load_tests(*args): return load_package_tests(os.path.dirname(__file__), *args) """ if pattern is None: pattern = "test*" top_dir = os.path.dirname( # Lib os.path.dirname( # test os.path.dirname(__file__))) # support package_tests = loader.discover(start_dir=pkg_dir, top_level_dir=top_dir, pattern=pattern) standard_tests.addTests(package_tests) return standard_tests def import_fresh_module(name, fresh=(), blocked=(), deprecated=False): """Import and return a module, deliberately bypassing sys.modules. This function imports and returns a fresh copy of the named Python module by removing the named module from sys.modules before doing the import. Note that unlike reload, the original module is not affected by this operation. *fresh* is an iterable of additional module names that are also removed from the sys.modules cache before doing the import. *blocked* is an iterable of module names that are replaced with None in the module cache during the import to ensure that attempts to import them raise ImportError. The named module and any modules named in the *fresh* and *blocked* parameters are saved before starting the import and then reinserted into sys.modules when the fresh import is complete. Module and package deprecation messages are suppressed during this import if *deprecated* is True. This function will raise ImportError if the named module cannot be imported. """ # NOTE: test_heapq, test_json and test_warnings include extra sanity checks # to make sure that this utility function is working as expected with _ignore_deprecated_imports(deprecated): # Keep track of modules saved for later restoration as well # as those which just need a blocking entry removed orig_modules = {} names_to_remove = [] _save_and_remove_module(name, orig_modules) try: for fresh_name in fresh: _save_and_remove_module(fresh_name, orig_modules) for blocked_name in blocked: if not _save_and_block_module(blocked_name, orig_modules): names_to_remove.append(blocked_name) fresh_module = importlib.import_module(name) except ImportError: fresh_module = None finally: for orig_name, module in orig_modules.items(): sys.modules[orig_name] = module for name_to_remove in names_to_remove: del sys.modules[name_to_remove] return fresh_module def get_attribute(obj, name): """Get an attribute, raising SkipTest if AttributeError is raised.""" try: attribute = getattr(obj, name) except AttributeError: raise unittest.SkipTest("object %r has no attribute %r" % (obj, name)) else: return attribute verbose = 1 # Flag set to 0 by regrtest.py use_resources = None # Flag set to [] by regrtest.py max_memuse = 0 # Disable bigmem tests (they will still be run with # small sizes, to make sure they work.) real_max_memuse = 0 junit_xml_list = None # list of testsuite XML elements failfast = False # _original_stdout is meant to hold stdout at the time regrtest began. # This may be "the real" stdout, or IDLE's emulation of stdout, or whatever. # The point is to have some flavor of stdout the user can actually see. _original_stdout = None def record_original_stdout(stdout): global _original_stdout _original_stdout = stdout def get_original_stdout(): return _original_stdout or sys.stdout def unload(name): try: del sys.modules[name] except KeyError: pass def _force_run(path, func, *args): try: return func(*args) except OSError as err: if verbose >= 2: print('%s: %s' % (err.__class__.__name__, err)) print('re-run %s%r' % (func.__name__, args)) os.chmod(path, stat.S_IRWXU) return func(*args) if sys.platform.startswith("win"): def _waitfor(func, pathname, waitall=False): # Perform the operation func(pathname) # Now setup the wait loop if waitall: dirname = pathname else: dirname, name = os.path.split(pathname) dirname = dirname or '.' # Check for `pathname` to be removed from the filesystem. # The exponential backoff of the timeout amounts to a total # of ~1 second after which the deletion is probably an error # anyway. # Testing on an i7@4.3GHz shows that usually only 1 iteration is # required when contention occurs. timeout = 0.001 while timeout < 1.0: # Note we are only testing for the existence of the file(s) in # the contents of the directory regardless of any security or # access rights. If we have made it this far, we have sufficient # permissions to do that much using Python's equivalent of the # Windows API FindFirstFile. # Other Windows APIs can fail or give incorrect results when # dealing with files that are pending deletion. L = os.listdir(dirname) if not (L if waitall else name in L): return # Increase the timeout and try again time.sleep(timeout) timeout *= 2 warnings.warn('tests may fail, delete still pending for ' + pathname, RuntimeWarning, stacklevel=4) def _unlink(filename): _waitfor(os.unlink, filename) def _rmdir(dirname): _waitfor(os.rmdir, dirname) def _rmtree(path): def _rmtree_inner(path): for name in _force_run(path, os.listdir, path): fullname = os.path.join(path, name) try: mode = os.lstat(fullname).st_mode except OSError as exc: print("support.rmtree(): os.lstat({!r}) failed with {}".format(fullname, exc), file=sys.__stderr__) mode = 0 if stat.S_ISDIR(mode): _waitfor(_rmtree_inner, fullname, waitall=True) _force_run(fullname, os.rmdir, fullname) else: _force_run(fullname, os.unlink, fullname) _waitfor(_rmtree_inner, path, waitall=True) _waitfor(lambda p: _force_run(p, os.rmdir, p), path) def _longpath(path): try: import ctypes except ImportError: # No ctypes means we can't expands paths. pass else: buffer = ctypes.create_unicode_buffer(len(path) * 2) length = ctypes.windll.kernel32.GetLongPathNameW(path, buffer, len(buffer)) if length: return buffer[:length] return path else: _unlink = os.unlink _rmdir = os.rmdir def _rmtree(path): try: shutil.rmtree(path) return except OSError: pass def _rmtree_inner(path): for name in _force_run(path, os.listdir, path): fullname = os.path.join(path, name) try: mode = os.lstat(fullname).st_mode except OSError: mode = 0 if stat.S_ISDIR(mode): _rmtree_inner(fullname) _force_run(path, os.rmdir, fullname) else: _force_run(path, os.unlink, fullname) _rmtree_inner(path) os.rmdir(path) def _longpath(path): return path def unlink(filename): try: _unlink(filename) except (FileNotFoundError, NotADirectoryError): pass def rmdir(dirname): try: _rmdir(dirname) except FileNotFoundError: pass def rmtree(path): try: _rmtree(path) except FileNotFoundError: pass def make_legacy_pyc(source): """Move a PEP 3147/488 pyc file to its legacy pyc location. :param source: The file system path to the source file. The source file does not need to exist, however the PEP 3147/488 pyc file must exist. :return: The file system path to the legacy pyc file. """ pyc_file = importlib.util.cache_from_source(source) up_one = os.path.dirname(os.path.abspath(source)) legacy_pyc = os.path.join(up_one, source + 'c') os.rename(pyc_file, legacy_pyc) return legacy_pyc def forget(modname): """'Forget' a module was ever imported. This removes the module from sys.modules and deletes any PEP 3147/488 or legacy .pyc files. """ unload(modname) for dirname in sys.path: source = os.path.join(dirname, modname + '.py') # It doesn't matter if they exist or not, unlink all possible # combinations of PEP 3147/488 and legacy pyc files. unlink(source + 'c') for opt in ('', 1, 2): unlink(importlib.util.cache_from_source(source, optimization=opt)) # Check whether a gui is actually available def _is_gui_available(): if hasattr(_is_gui_available, 'result'): return _is_gui_available.result reason = None if sys.platform.startswith('win'): # if Python is running as a service (such as the buildbot service), # gui interaction may be disallowed import ctypes import ctypes.wintypes UOI_FLAGS = 1 WSF_VISIBLE = 0x0001 class USEROBJECTFLAGS(ctypes.Structure): _fields_ = [("fInherit", ctypes.wintypes.BOOL), ("fReserved", ctypes.wintypes.BOOL), ("dwFlags", ctypes.wintypes.DWORD)] dll = ctypes.windll.user32 h = dll.GetProcessWindowStation() if not h: raise ctypes.WinError() uof = USEROBJECTFLAGS() needed = ctypes.wintypes.DWORD() res = dll.GetUserObjectInformationW(h, UOI_FLAGS, ctypes.byref(uof), ctypes.sizeof(uof), ctypes.byref(needed)) if not res: raise ctypes.WinError() if not bool(uof.dwFlags & WSF_VISIBLE): reason = "gui not available (WSF_VISIBLE flag not set)" elif sys.platform == 'darwin': # The Aqua Tk implementations on OS X can abort the process if # being called in an environment where a window server connection # cannot be made, for instance when invoked by a buildbot or ssh # process not running under the same user id as the current console # user. To avoid that, raise an exception if the window manager # connection is not available. from ctypes import cdll, c_int, pointer, Structure from ctypes.util import find_library app_services = cdll.LoadLibrary(find_library("ApplicationServices")) if app_services.CGMainDisplayID() == 0: reason = "gui tests cannot run without OS X window manager" else: class ProcessSerialNumber(Structure): _fields_ = [("highLongOfPSN", c_int), ("lowLongOfPSN", c_int)] psn = ProcessSerialNumber() psn_p = pointer(psn) if ( (app_services.GetCurrentProcess(psn_p) < 0) or (app_services.SetFrontProcess(psn_p) < 0) ): reason = "cannot run without OS X gui process" # check on every platform whether tkinter can actually do anything if not reason: try: from tkinter import Tk root = Tk() root.withdraw() root.update() root.destroy() except Exception as e: err_string = str(e) if len(err_string) > 50: err_string = err_string[:50] + ' [...]' reason = 'Tk unavailable due to {}: {}'.format(type(e).__name__, err_string) _is_gui_available.reason = reason _is_gui_available.result = not reason return _is_gui_available.result def is_resource_enabled(resource): """Test whether a resource is enabled. Known resources are set by regrtest.py. If not running under regrtest.py, all resources are assumed enabled unless use_resources has been set. """ return use_resources is None or resource in use_resources def requires(resource, msg=None): """Raise ResourceDenied if the specified resource is not available.""" print(resource) if not is_resource_enabled(resource): if msg is None: msg = "Use of the %r resource not enabled" % resource raise ResourceDenied(msg) if resource == 'gui' and not _is_gui_available(): raise ResourceDenied(_is_gui_available.reason) def _requires_unix_version(sysname, min_version): """Decorator raising SkipTest if the OS is `sysname` and the version is less than `min_version`. For example, @_requires_unix_version('FreeBSD', (7, 2)) raises SkipTest if the FreeBSD version is less than 7.2. """ def decorator(func): @functools.wraps(func) def wrapper(*args, **kw): if platform.system() == sysname: version_txt = platform.release().split('-', 1)[0] try: version = tuple(map(int, version_txt.split('.'))) except ValueError: pass else: if version < min_version: min_version_txt = '.'.join(map(str, min_version)) raise unittest.SkipTest( "{} version {} or higher required, not {}".format(sysname, min_version_txt, version_txt)) return func(*args, **kw) wrapper.min_version = min_version return wrapper return decorator def requires_freebsd_version(*min_version): """Decorator raising SkipTest if the OS is FreeBSD and the FreeBSD version is less than `min_version`. For example, @requires_freebsd_version(7, 2) raises SkipTest if the FreeBSD version is less than 7.2. """ return _requires_unix_version('FreeBSD', min_version) def requires_linux_version(*min_version): """Decorator raising SkipTest if the OS is Linux and the Linux version is less than `min_version`. For example, @requires_linux_version(2, 6, 32) raises SkipTest if the Linux version is less than 2.6.32. """ return _requires_unix_version('Linux', min_version) def requires_mac_ver(*min_version): """Decorator raising SkipTest if the OS is Mac OS X and the OS X version if less than min_version. For example, @requires_mac_ver(10, 5) raises SkipTest if the OS X version is lesser than 10.5. """ def decorator(func): @functools.wraps(func) def wrapper(*args, **kw): if sys.platform == 'darwin': version_txt = platform.mac_ver()[0] try: version = tuple(map(int, version_txt.split('.'))) except ValueError: pass else: if version < min_version: min_version_txt = '.'.join(map(str, min_version)) raise unittest.SkipTest( "Mac OS X %s or higher required, not %s" % (min_version_txt, version_txt)) return func(*args, **kw) wrapper.min_version = min_version return wrapper return decorator HOST = "localhost" HOSTv4 = "127.0.0.1" HOSTv6 = "::1" def find_unused_port(family=socket.AF_INET, socktype=socket.SOCK_STREAM): """Returns an unused port that should be suitable for binding. This is achieved by creating a temporary socket with the same family and type as the 'sock' parameter (default is AF_INET, SOCK_STREAM), and binding it to the specified host address (defaults to 0.0.0.0) with the port set to 0, eliciting an unused ephemeral port from the OS. The temporary socket is then closed and deleted, and the ephemeral port is returned. Either this method or bind_port() should be used for any tests where a server socket needs to be bound to a particular port for the duration of the test. Which one to use depends on whether the calling code is creating a python socket, or if an unused port needs to be provided in a constructor or passed to an external program (i.e. the -accept argument to openssl's s_server mode). Always prefer bind_port() over find_unused_port() where possible. Hard coded ports should *NEVER* be used. As soon as a server socket is bound to a hard coded port, the ability to run multiple instances of the test simultaneously on the same host is compromised, which makes the test a ticking time bomb in a buildbot environment. On Unix buildbots, this may simply manifest as a failed test, which can be recovered from without intervention in most cases, but on Windows, the entire python process can completely and utterly wedge, requiring someone to log in to the buildbot and manually kill the affected process. (This is easy to reproduce on Windows, unfortunately, and can be traced to the SO_REUSEADDR socket option having different semantics on Windows versus Unix/Linux. On Unix, you can't have two AF_INET SOCK_STREAM sockets bind, listen and then accept connections on identical host/ports. An EADDRINUSE OSError will be raised at some point (depending on the platform and the order bind and listen were called on each socket). However, on Windows, if SO_REUSEADDR is set on the sockets, no EADDRINUSE will ever be raised when attempting to bind two identical host/ports. When accept() is called on each socket, the second caller's process will steal the port from the first caller, leaving them both in an awkwardly wedged state where they'll no longer respond to any signals or graceful kills, and must be forcibly killed via OpenProcess()/TerminateProcess(). The solution on Windows is to use the SO_EXCLUSIVEADDRUSE socket option instead of SO_REUSEADDR, which effectively affords the same semantics as SO_REUSEADDR on Unix. Given the propensity of Unix developers in the Open Source world compared to Windows ones, this is a common mistake. A quick look over OpenSSL's 0.9.8g source shows that they use SO_REUSEADDR when openssl.exe is called with the 's_server' option, for example. See http://bugs.python.org/issue2550 for more info. The following site also has a very thorough description about the implications of both REUSEADDR and EXCLUSIVEADDRUSE on Windows: http://msdn2.microsoft.com/en-us/library/ms740621(VS.85).aspx) XXX: although this approach is a vast improvement on previous attempts to elicit unused ports, it rests heavily on the assumption that the ephemeral port returned to us by the OS won't immediately be dished back out to some other process when we close and delete our temporary socket but before our calling code has a chance to bind the returned port. We can deal with this issue if/when we come across it. """ tempsock = socket.socket(family, socktype) port = bind_port(tempsock) tempsock.close() del tempsock return port def bind_port(sock, host=HOST): """Bind the socket to a free port and return the port number. Relies on ephemeral ports in order to ensure we are using an unbound port. This is important as many tests may be running simultaneously, especially in a buildbot environment. This method raises an exception if the sock.family is AF_INET and sock.type is SOCK_STREAM, *and* the socket has SO_REUSEADDR or SO_REUSEPORT set on it. Tests should *never* set these socket options for TCP/IP sockets. The only case for setting these options is testing multicasting via multiple UDP sockets. Additionally, if the SO_EXCLUSIVEADDRUSE socket option is available (i.e. on Windows), it will be set on the socket. This will prevent anyone else from bind()'ing to our host/port for the duration of the test. """ if sock.family == socket.AF_INET and sock.type == socket.SOCK_STREAM: if hasattr(socket, 'SO_REUSEADDR'): if sock.getsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR) == 1: raise TestFailed("tests should never set the SO_REUSEADDR " "socket option on TCP/IP sockets!") if hasattr(socket, 'SO_REUSEPORT'): try: if sock.getsockopt(socket.SOL_SOCKET, socket.SO_REUSEPORT) == 1: raise TestFailed("tests should never set the SO_REUSEPORT " "socket option on TCP/IP sockets!") except OSError: # Python's socket module was compiled using modern headers # thus defining SO_REUSEPORT but this process is running # under an older kernel that does not support SO_REUSEPORT. pass if hasattr(socket, 'SO_EXCLUSIVEADDRUSE'): sock.setsockopt(socket.SOL_SOCKET, socket.SO_EXCLUSIVEADDRUSE, 1) sock.bind((host, 0)) port = sock.getsockname()[1] return port def bind_unix_socket(sock, addr): """Bind a unix socket, raising SkipTest if PermissionError is raised.""" assert sock.family == socket.AF_UNIX try: sock.bind(addr) except PermissionError: sock.close() raise unittest.SkipTest('cannot bind AF_UNIX sockets') def _is_ipv6_enabled(): """Check whether IPv6 is enabled on this host.""" if socket.has_ipv6: sock = None try: sock = socket.socket(socket.AF_INET6, socket.SOCK_STREAM) sock.bind((HOSTv6, 0)) return True except OSError: pass finally: if sock: sock.close() return False IPV6_ENABLED = _is_ipv6_enabled() def system_must_validate_cert(f): """Skip the test on TLS certificate validation failures.""" @functools.wraps(f) def dec(*args, **kwargs): try: f(*args, **kwargs) except OSError as e: if "CERTIFICATE_VERIFY_FAILED" in str(e): raise unittest.SkipTest("system does not contain " "necessary certificates") raise return dec # A constant likely larger than the underlying OS pipe buffer size, to # make writes blocking. # Windows limit seems to be around 512 B, and many Unix kernels have a # 64 KiB pipe buffer size or 16 * PAGE_SIZE: take a few megs to be sure. # (see issue #17835 for a discussion of this number). PIPE_MAX_SIZE = 4 * 1024 * 1024 + 1 # A constant likely larger than the underlying OS socket buffer size, to make # writes blocking. # The socket buffer sizes can usually be tuned system-wide (e.g. through sysctl # on Linux), or on a per-socket basis (SO_SNDBUF/SO_RCVBUF). See issue #18643 # for a discussion of this number). SOCK_MAX_SIZE = 16 * 1024 * 1024 + 1 # decorator for skipping tests on non-IEEE 754 platforms requires_IEEE_754 = unittest.skipUnless( float.__getformat__("double").startswith("IEEE"), "test requires IEEE 754 doubles") requires_zlib = unittest.skipUnless(zlib, 'requires zlib') requires_gzip = unittest.skipUnless(gzip, 'requires gzip') requires_bz2 = unittest.skipUnless(bz2, 'requires bz2') requires_lzma = unittest.skipUnless(lzma, 'requires lzma') is_jython = sys.platform.startswith('java') is_android = hasattr(sys, 'getandroidapilevel') if sys.platform != 'win32': unix_shell = '/system/bin/sh' if is_android else '/bin/sh' else: unix_shell = None # Filename used for testing if os.name == 'java': # Jython disallows @ in module names TESTFN = '$test' else: TESTFN = '@test' # Disambiguate TESTFN for parallel testing, while letting it remain a valid # module name. TESTFN = "{}_{}_tmp".format(TESTFN, os.getpid()) # FS_NONASCII: non-ASCII character encodable by os.fsencode(), # or None if there is no such character. FS_NONASCII = None for character in ( # First try printable and common characters to have a readable filename. # For each character, the encoding list are just example of encodings able # to encode the character (the list is not exhaustive). # U+00E6 (Latin Small Letter Ae): cp1252, iso-8859-1 '\u00E6', # U+0130 (Latin Capital Letter I With Dot Above): cp1254, iso8859_3 '\u0130', # U+0141 (Latin Capital Letter L With Stroke): cp1250, cp1257 '\u0141', # U+03C6 (Greek Small Letter Phi): cp1253 '\u03C6', # U+041A (Cyrillic Capital Letter Ka): cp1251 '\u041A', # U+05D0 (Hebrew Letter Alef): Encodable to cp424 '\u05D0', # U+060C (Arabic Comma): cp864, cp1006, iso8859_6, mac_arabic '\u060C', # U+062A (Arabic Letter Teh): cp720 '\u062A', # U+0E01 (Thai Character Ko Kai): cp874 '\u0E01', # Then try more "special" characters. "special" because they may be # interpreted or displayed differently depending on the exact locale # encoding and the font. # U+00A0 (No-Break Space) '\u00A0', # U+20AC (Euro Sign) '\u20AC', ): try: os.fsdecode(os.fsencode(character)) except UnicodeError: pass else: FS_NONASCII = character break # TESTFN_UNICODE is a non-ascii filename TESTFN_UNICODE = TESTFN + "-\xe0\xf2\u0258\u0141\u011f" if sys.platform == 'darwin': # In Mac OS X's VFS API file names are, by definition, canonically # decomposed Unicode, encoded using UTF-8. See QA1173: # http://developer.apple.com/mac/library/qa/qa2001/qa1173.html import unicodedata TESTFN_UNICODE = unicodedata.normalize('NFD', TESTFN_UNICODE) TESTFN_ENCODING = sys.getfilesystemencoding() # TESTFN_UNENCODABLE is a filename (str type) that should *not* be able to be # encoded by the filesystem encoding (in strict mode). It can be None if we # cannot generate such filename. TESTFN_UNENCODABLE = None if os.name == 'nt': # skip win32s (0) or Windows 9x/ME (1) if sys.getwindowsversion().platform >= 2: # Different kinds of characters from various languages to minimize the # probability that the whole name is encodable to MBCS (issue #9819) TESTFN_UNENCODABLE = TESTFN + "-\u5171\u0141\u2661\u0363\uDC80" try: TESTFN_UNENCODABLE.encode(TESTFN_ENCODING) except UnicodeEncodeError: pass else: print('WARNING: The filename %r CAN be encoded by the filesystem encoding (%s). ' 'Unicode filename tests may not be effective' % (TESTFN_UNENCODABLE, TESTFN_ENCODING)) TESTFN_UNENCODABLE = None # Mac OS X denies unencodable filenames (invalid utf-8) elif sys.platform != 'darwin': try: # ascii and utf-8 cannot encode the byte 0xff b'\xff'.decode(TESTFN_ENCODING) except UnicodeDecodeError: # 0xff will be encoded using the surrogate character u+DCFF TESTFN_UNENCODABLE = TESTFN \ + b'-\xff'.decode(TESTFN_ENCODING, 'surrogateescape') else: # File system encoding (eg. ISO-8859-* encodings) can encode # the byte 0xff. Skip some unicode filename tests. pass # TESTFN_UNDECODABLE is a filename (bytes type) that should *not* be able to be # decoded from the filesystem encoding (in strict mode). It can be None if we # cannot generate such filename (ex: the latin1 encoding can decode any byte # sequence). On UNIX, TESTFN_UNDECODABLE can be decoded by os.fsdecode() thanks # to the surrogateescape error handler (PEP 383), but not from the filesystem # encoding in strict mode. TESTFN_UNDECODABLE = None for name in ( # b'\xff' is not decodable by os.fsdecode() with code page 932. Windows # accepts it to create a file or a directory, or don't accept to enter to # such directory (when the bytes name is used). So test b'\xe7' first: it is # not decodable from cp932. b'\xe7w\xf0', # undecodable from ASCII, UTF-8 b'\xff', # undecodable from iso8859-3, iso8859-6, iso8859-7, cp424, iso8859-8, cp856 # and cp857 b'\xae\xd5' # undecodable from UTF-8 (UNIX and Mac OS X) b'\xed\xb2\x80', b'\xed\xb4\x80', # undecodable from shift_jis, cp869, cp874, cp932, cp1250, cp1251, cp1252, # cp1253, cp1254, cp1255, cp1257, cp1258 b'\x81\x98', ): try: name.decode(TESTFN_ENCODING) except UnicodeDecodeError: TESTFN_UNDECODABLE = os.fsencode(TESTFN) + name break if FS_NONASCII: TESTFN_NONASCII = TESTFN + '-' + FS_NONASCII else: TESTFN_NONASCII = None # Save the initial cwd SAVEDCWD = os.getcwd() # Set by libregrtest/main.py so we can skip tests that are not # useful for PGO PGO = False @contextlib.contextmanager def temp_dir(path=None, quiet=False): """Return a context manager that creates a temporary directory. Arguments: path: the directory to create temporarily. If omitted or None, defaults to creating a temporary directory using tempfile.mkdtemp. quiet: if False (the default), the context manager raises an exception on error. Otherwise, if the path is specified and cannot be created, only a warning is issued. """ dir_created = False if path is None: path = tempfile.mkdtemp() dir_created = True path = os.path.realpath(path) else: try: os.mkdir(path) dir_created = True except OSError as exc: if not quiet: raise warnings.warn('tests may fail, unable to create ' 'temporary directory {!r}: {}'.format(path, exc), RuntimeWarning, stacklevel=3) if dir_created: pid = os.getpid() try: yield path finally: # In case the process forks, let only the parent remove the # directory. The child has a diffent process id. (bpo-30028) if dir_created and pid == os.getpid(): rmtree(path) @contextlib.contextmanager def change_cwd(path, quiet=False): """Return a context manager that changes the current working directory. Arguments: path: the directory to use as the temporary current working directory. quiet: if False (the default), the context manager raises an exception on error. Otherwise, it issues only a warning and keeps the current working directory the same. """ saved_dir = os.getcwd() try: os.chdir(path) except OSError as exc: if not quiet: raise warnings.warn('tests may fail, unable to change the current working ' 'directory to {!r}: {}'.format(path, exc), RuntimeWarning, stacklevel=3) try: yield os.getcwd() finally: os.chdir(saved_dir) @contextlib.contextmanager def temp_cwd(name='tempcwd', quiet=False): """ Context manager that temporarily creates and changes the CWD. The function temporarily changes the current working directory after creating a temporary directory in the current directory with name *name*. If *name* is None, the temporary directory is created using tempfile.mkdtemp. If *quiet* is False (default) and it is not possible to create or change the CWD, an error is raised. If *quiet* is True, only a warning is raised and the original CWD is used. """ with temp_dir(path=name, quiet=quiet) as temp_path: with change_cwd(temp_path, quiet=quiet) as cwd_dir: yield cwd_dir if hasattr(os, "umask"): @contextlib.contextmanager def temp_umask(umask): """Context manager that temporarily sets the process umask.""" oldmask = os.umask(umask) try: yield finally: os.umask(oldmask) # TEST_HOME_DIR refers to the top level directory of the "test" package # that contains Python's regression test suite TEST_SUPPORT_DIR = os.path.dirname(os.path.abspath(__file__)) TEST_HOME_DIR = os.path.dirname(TEST_SUPPORT_DIR) # TEST_DATA_DIR is used as a target download location for remote resources TEST_DATA_DIR = os.path.join(TEST_HOME_DIR, "data") def findfile(filename, subdir=None): """Try to find a file on sys.path or in the test directory. If it is not found the argument passed to the function is returned (this does not necessarily signal failure; could still be the legitimate path). Setting *subdir* indicates a relative path to use to find the file rather than looking directly in the path directories. """ if os.path.isabs(filename): return filename if subdir is not None: filename = os.path.join(subdir, filename) path = [TEST_HOME_DIR] + sys.path for dn in path: fn = os.path.join(dn, filename) if os.path.exists(fn): return fn return filename def create_empty_file(filename): """Create an empty file. If the file already exists, truncate it.""" fd = os.open(filename, os.O_WRONLY | os.O_CREAT | os.O_TRUNC) os.close(fd) def sortdict(dict): "Like repr(dict), but in sorted order." items = sorted(dict.items()) reprpairs = ["%r: %r" % pair for pair in items] withcommas = ", ".join(reprpairs) return "{%s}" % withcommas def make_bad_fd(): """ Create an invalid file descriptor by opening and closing a file and return its fd. """ file = open(TESTFN, "wb") try: return file.fileno() finally: file.close() unlink(TESTFN) def check_syntax_error(testcase, statement, errtext='', *, lineno=None, offset=None): with testcase.assertRaisesRegex(SyntaxError, errtext) as cm: compile(statement, '', 'exec') err = cm.exception testcase.assertIsNotNone(err.lineno) if lineno is not None: testcase.assertEqual(err.lineno, lineno) testcase.assertIsNotNone(err.offset) if offset is not None: testcase.assertEqual(err.offset, offset) def open_urlresource(url, *args, **kw): import urllib.request, urllib.parse check = kw.pop('check', None) filename = urllib.parse.urlparse(url)[2].split('/')[-1] # '/': it's URL! fn = os.path.join(TEST_DATA_DIR, filename) def check_valid_file(fn): f = open(fn, *args, **kw) if check is None: return f elif check(f): f.seek(0) return f f.close() if os.path.exists(fn): f = check_valid_file(fn) if f is not None: return f unlink(fn) # Verify the requirement before downloading the file requires('urlfetch') if verbose: print('\tfetching %s ...' % url, file=get_original_stdout()) opener = urllib.request.build_opener() if gzip: opener.addheaders.append(('Accept-Encoding', 'gzip')) f = opener.open(url, timeout=15) if gzip and f.headers.get('Content-Encoding') == 'gzip': f = gzip.GzipFile(fileobj=f) try: with open(fn, "wb") as out: s = f.read() while s: out.write(s) s = f.read() finally: f.close() f = check_valid_file(fn) if f is not None: return f raise TestFailed('invalid resource %r' % fn) class WarningsRecorder(object): """Convenience wrapper for the warnings list returned on entry to the warnings.catch_warnings() context manager. """ def __init__(self, warnings_list): self._warnings = warnings_list self._last = 0 def __getattr__(self, attr): if len(self._warnings) > self._last: return getattr(self._warnings[-1], attr) elif attr in warnings.WarningMessage._WARNING_DETAILS: return None raise AttributeError("%r has no attribute %r" % (self, attr)) @property def warnings(self): return self._warnings[self._last:] def reset(self): self._last = len(self._warnings) def _filterwarnings(filters, quiet=False): """Catch the warnings, then check if all the expected warnings have been raised and re-raise unexpected warnings. If 'quiet' is True, only re-raise the unexpected warnings. """ # Clear the warning registry of the calling module # in order to re-raise the warnings. frame = sys._getframe(2) registry = frame.f_globals.get('__warningregistry__') if registry: registry.clear() with warnings.catch_warnings(record=True) as w: # Set filter "always" to record all warnings. Because # test_warnings swap the module, we need to look up in # the sys.modules dictionary. sys.modules['warnings'].simplefilter("always") yield WarningsRecorder(w) # Filter the recorded warnings reraise = list(w) missing = [] for msg, cat in filters: seen = False for w in reraise[:]: warning = w.message # Filter out the matching messages if (re.match(msg, str(warning), re.I) and issubclass(warning.__class__, cat)): seen = True reraise.remove(w) if not seen and not quiet: # This filter caught nothing missing.append((msg, cat.__name__)) if reraise: raise AssertionError("unhandled warning %s" % reraise[0]) if missing: raise AssertionError("filter (%r, %s) did not catch any warning" % missing[0]) @contextlib.contextmanager def check_warnings(*filters, **kwargs): """Context manager to silence warnings. Accept 2-tuples as positional arguments: ("message regexp", WarningCategory) Optional argument: - if 'quiet' is True, it does not fail if a filter catches nothing (default True without argument, default False if some filters are defined) Without argument, it defaults to: check_warnings(("", Warning), quiet=True) """ quiet = kwargs.get('quiet') if not filters: filters = (("", Warning),) # Preserve backward compatibility if quiet is None: quiet = True return _filterwarnings(filters, quiet) @contextlib.contextmanager def check_no_warnings(testcase, message='', category=Warning, force_gc=False): """Context manager to check that no warnings are emitted. This context manager enables a given warning within its scope and checks that no warnings are emitted even with that warning enabled. If force_gc is True, a garbage collection is attempted before checking for warnings. This may help to catch warnings emitted when objects are deleted, such as ResourceWarning. Other keyword arguments are passed to warnings.filterwarnings(). """ with warnings.catch_warnings(record=True) as warns: warnings.filterwarnings('always', message=message, category=category) yield if force_gc: gc_collect() testcase.assertEqual(warns, []) @contextlib.contextmanager def check_no_resource_warning(testcase): """Context manager to check that no ResourceWarning is emitted. Usage: with check_no_resource_warning(self): f = open(...) ... del f You must remove the object which may emit ResourceWarning before the end of the context manager. """ with check_no_warnings(testcase, category=ResourceWarning, force_gc=True): yield class CleanImport(object): """Context manager to force import to return a new module reference. This is useful for testing module-level behaviours, such as the emission of a DeprecationWarning on import. Use like this: with CleanImport("foo"): importlib.import_module("foo") # new reference """ def __init__(self, *module_names): self.original_modules = sys.modules.copy() for module_name in module_names: if module_name in sys.modules: module = sys.modules[module_name] # It is possible that module_name is just an alias for # another module (e.g. stub for modules renamed in 3.x). # In that case, we also need delete the real module to clear # the import cache. if module.__name__ != module_name: del sys.modules[module.__name__] del sys.modules[module_name] def __enter__(self): return self def __exit__(self, *ignore_exc): sys.modules.update(self.original_modules) class EnvironmentVarGuard(collections.abc.MutableMapping): """Class to help protect the environment variable properly. Can be used as a context manager.""" def __init__(self): self._environ = os.environ self._changed = {} def __getitem__(self, envvar): return self._environ[envvar] def __setitem__(self, envvar, value): # Remember the initial value on the first access if envvar not in self._changed: self._changed[envvar] = self._environ.get(envvar) self._environ[envvar] = value def __delitem__(self, envvar): # Remember the initial value on the first access if envvar not in self._changed: self._changed[envvar] = self._environ.get(envvar) if envvar in self._environ: del self._environ[envvar] def keys(self): return self._environ.keys() def __iter__(self): return iter(self._environ) def __len__(self): return len(self._environ) def set(self, envvar, value): self[envvar] = value def unset(self, envvar): del self[envvar] def __enter__(self): return self def __exit__(self, *ignore_exc): for (k, v) in self._changed.items(): if v is None: if k in self._environ: del self._environ[k] else: self._environ[k] = v os.environ = self._environ class DirsOnSysPath(object): """Context manager to temporarily add directories to sys.path. This makes a copy of sys.path, appends any directories given as positional arguments, then reverts sys.path to the copied settings when the context ends. Note that *all* sys.path modifications in the body of the context manager, including replacement of the object, will be reverted at the end of the block. """ def __init__(self, *paths): self.original_value = sys.path[:] self.original_object = sys.path sys.path.extend(paths) def __enter__(self): return self def __exit__(self, *ignore_exc): sys.path = self.original_object sys.path[:] = self.original_value class TransientResource(object): """Raise ResourceDenied if an exception is raised while the context manager is in effect that matches the specified exception and attributes.""" def __init__(self, exc, **kwargs): self.exc = exc self.attrs = kwargs def __enter__(self): return self def __exit__(self, type_=None, value=None, traceback=None): """If type_ is a subclass of self.exc and value has attributes matching self.attrs, raise ResourceDenied. Otherwise let the exception propagate (if any).""" if type_ is not None and issubclass(self.exc, type_): for attr, attr_value in self.attrs.items(): if not hasattr(value, attr): break if getattr(value, attr) != attr_value: break else: raise ResourceDenied("an optional resource is not available") # Context managers that raise ResourceDenied when various issues # with the Internet connection manifest themselves as exceptions. # XXX deprecate these and use transient_internet() instead time_out = TransientResource(OSError, errno=errno.ETIMEDOUT) socket_peer_reset = TransientResource(OSError, errno=errno.ECONNRESET) ioerror_peer_reset = TransientResource(OSError, errno=errno.ECONNRESET) @contextlib.contextmanager def transient_internet(resource_name, *, timeout=30.0, errnos=()): """Return a context manager that raises ResourceDenied when various issues with the Internet connection manifest themselves as exceptions.""" default_errnos = [ ('ECONNREFUSED', 111), ('ECONNRESET', 104), ('EHOSTUNREACH', 113), ('ENETUNREACH', 101), ('ETIMEDOUT', 110), # socket.create_connection() fails randomly with # EADDRNOTAVAIL on Travis CI. ('EADDRNOTAVAIL', 99), ] default_gai_errnos = [ ('EAI_AGAIN', -3), ('EAI_FAIL', -4), ('EAI_NONAME', -2), ('EAI_NODATA', -5), # Encountered when trying to resolve IPv6-only hostnames ('WSANO_DATA', 11004), ] denied = ResourceDenied("Resource %r is not available" % resource_name) captured_errnos = errnos gai_errnos = [] if not captured_errnos: captured_errnos = [getattr(errno, name, num) for (name, num) in default_errnos] gai_errnos = [getattr(socket, name, num) for (name, num) in default_gai_errnos] def filter_error(err): n = getattr(err, 'errno', None) if (isinstance(err, socket.timeout) or (isinstance(err, socket.gaierror) and n in gai_errnos) or (isinstance(err, urllib.error.HTTPError) and 500 <= err.code <= 599) or (isinstance(err, urllib.error.URLError) and (("ConnectionRefusedError" in err.reason) or ("TimeoutError" in err.reason) or ("EOFError" in err.reason))) or n in captured_errnos): if not verbose: sys.stderr.write(denied.args[0] + "\n") raise denied from err old_timeout = socket.getdefaulttimeout() try: if timeout is not None: socket.setdefaulttimeout(timeout) yield except nntplib.NNTPTemporaryError as err: if verbose: sys.stderr.write(denied.args[0] + "\n") raise denied from err except OSError as err: # urllib can wrap original socket errors multiple times (!), we must # unwrap to get at the original error. while True: a = err.args if len(a) >= 1 and isinstance(a[0], OSError): err = a[0] # The error can also be wrapped as args[1]: # except socket.error as msg: # raise OSError('socket error', msg).with_traceback(sys.exc_info()[2]) elif len(a) >= 2 and isinstance(a[1], OSError): err = a[1] else: break filter_error(err) raise # XXX should we catch generic exceptions and look for their # __cause__ or __context__? finally: socket.setdefaulttimeout(old_timeout) @contextlib.contextmanager def captured_output(stream_name): """Return a context manager used by captured_stdout/stdin/stderr that temporarily replaces the sys stream *stream_name* with a StringIO.""" import io orig_stdout = getattr(sys, stream_name) setattr(sys, stream_name, io.StringIO()) try: yield getattr(sys, stream_name) finally: setattr(sys, stream_name, orig_stdout) def captured_stdout(): """Capture the output of sys.stdout: with captured_stdout() as stdout: print("hello") self.assertEqual(stdout.getvalue(), "hello\\n") """ return captured_output("stdout") def captured_stderr(): """Capture the output of sys.stderr: with captured_stderr() as stderr: print("hello", file=sys.stderr) self.assertEqual(stderr.getvalue(), "hello\\n") """ return captured_output("stderr") def captured_stdin(): """Capture the input to sys.stdin: with captured_stdin() as stdin: stdin.write('hello\\n') stdin.seek(0) # call test code that consumes from sys.stdin captured = input() self.assertEqual(captured, "hello") """ return captured_output("stdin") def gc_collect(): """Force as many objects as possible to be collected. In non-CPython implementations of Python, this is needed because timely deallocation is not guaranteed by the garbage collector. (Even in CPython this can be the case in case of reference cycles.) This means that __del__ methods may be called later than expected and weakrefs may remain alive for longer than expected. This function tries its best to force all garbage objects to disappear. """ gc.collect() if is_jython: time.sleep(0.1) gc.collect() gc.collect() @contextlib.contextmanager def disable_gc(): have_gc = gc.isenabled() gc.disable() try: yield finally: if have_gc: gc.enable() def python_is_optimized(): """Find if Python was built with optimizations.""" cflags = sysconfig.get_config_var('PY_CFLAGS') or '' final_opt = "" for opt in cflags.split(): if opt.startswith('-O'): final_opt = opt return final_opt not in ('', '-O0', '-Og') _header = 'nP' _align = '0n' if hasattr(sys, "gettotalrefcount"): _header = '2P' + _header _align = '0P' _vheader = _header + 'n' def calcobjsize(fmt): return struct.calcsize(_header + fmt + _align) def calcvobjsize(fmt): return struct.calcsize(_vheader + fmt + _align) _TPFLAGS_HAVE_GC = 1<<14 _TPFLAGS_HEAPTYPE = 1<<9 def check_sizeof(test, o, size): import _testcapi result = sys.getsizeof(o) # add GC header size if ((type(o) == type) and (o.__flags__ & _TPFLAGS_HEAPTYPE) or\ ((type(o) != type) and (type(o).__flags__ & _TPFLAGS_HAVE_GC))): size += _testcapi.SIZEOF_PYGC_HEAD msg = 'wrong size for %s: got %d, expected %d' \ % (type(o), result, size) test.assertEqual(result, size, msg) #======================================================================= # Decorator for running a function in a different locale, correctly resetting # it afterwards. def run_with_locale(catstr, *locales): def decorator(func): def inner(*args, **kwds): try: import locale category = getattr(locale, catstr) orig_locale = locale.setlocale(category) except AttributeError: # if the test author gives us an invalid category string raise except: # cannot retrieve original locale, so do nothing locale = orig_locale = None else: for loc in locales: try: locale.setlocale(category, loc) break except: pass # now run the function, resetting the locale on exceptions try: return func(*args, **kwds) finally: if locale and orig_locale: locale.setlocale(category, orig_locale) inner.__name__ = func.__name__ inner.__doc__ = func.__doc__ return inner return decorator #======================================================================= # Decorator for running a function in a specific timezone, correctly # resetting it afterwards. def run_with_tz(tz): def decorator(func): def inner(*args, **kwds): try: tzset = time.tzset except AttributeError: raise unittest.SkipTest("tzset required") if 'TZ' in os.environ: orig_tz = os.environ['TZ'] else: orig_tz = None os.environ['TZ'] = tz tzset() # now run the function, resetting the tz on exceptions try: return func(*args, **kwds) finally: if orig_tz is None: del os.environ['TZ'] else: os.environ['TZ'] = orig_tz time.tzset() inner.__name__ = func.__name__ inner.__doc__ = func.__doc__ return inner return decorator #======================================================================= # Big-memory-test support. Separate from 'resources' because memory use # should be configurable. # Some handy shorthands. Note that these are used for byte-limits as well # as size-limits, in the various bigmem tests _1M = 1024*1024 _1G = 1024 * _1M _2G = 2 * _1G _4G = 4 * _1G MAX_Py_ssize_t = sys.maxsize def set_memlimit(limit): global max_memuse global real_max_memuse sizes = { 'k': 1024, 'm': _1M, 'g': _1G, 't': 1024*_1G, } m = re.match(r'(\d+(\.\d+)?) (K|M|G|T)b?$', limit, re.IGNORECASE | re.VERBOSE) if m is None: raise ValueError('Invalid memory limit %r' % (limit,)) memlimit = int(float(m.group(1)) * sizes[m.group(3).lower()]) real_max_memuse = memlimit if memlimit > MAX_Py_ssize_t: memlimit = MAX_Py_ssize_t if memlimit < _2G - 1: raise ValueError('Memory limit %r too low to be useful' % (limit,)) max_memuse = memlimit class _MemoryWatchdog: """An object which periodically watches the process' memory consumption and prints it out. """ def __init__(self): self.procfile = '/proc/{pid}/statm'.format(pid=os.getpid()) self.started = False def start(self): try: f = open(self.procfile, 'r') except OSError as e: warnings.warn('/proc not available for stats: {}'.format(e), RuntimeWarning) sys.stderr.flush() return watchdog_script = findfile("memory_watchdog.py") self.mem_watchdog = subprocess.Popen([sys.executable, watchdog_script], stdin=f, stderr=subprocess.DEVNULL) f.close() self.started = True def stop(self): if self.started: self.mem_watchdog.terminate() self.mem_watchdog.wait() def bigmemtest(size, memuse, dry_run=True): """Decorator for bigmem tests. 'size' is a requested size for the test (in arbitrary, test-interpreted units.) 'memuse' is the number of bytes per unit for the test, or a good estimate of it. For example, a test that needs two byte buffers, of 4 GiB each, could be decorated with @bigmemtest(size=_4G, memuse=2). The 'size' argument is normally passed to the decorated test method as an extra argument. If 'dry_run' is true, the value passed to the test method may be less than the requested value. If 'dry_run' is false, it means the test doesn't support dummy runs when -M is not specified. """ def decorator(f): def wrapper(self): size = wrapper.size memuse = wrapper.memuse if not real_max_memuse: maxsize = 5147 else: maxsize = size if ((real_max_memuse or not dry_run) and real_max_memuse < maxsize * memuse): raise unittest.SkipTest( "not enough memory: %.1fG minimum needed" % (size * memuse / (1024 ** 3))) if real_max_memuse and verbose: print() print(" ... expected peak memory use: {peak:.1f}G" .format(peak=size * memuse / (1024 ** 3))) watchdog = _MemoryWatchdog() watchdog.start() else: watchdog = None try: return f(self, maxsize) finally: if watchdog: watchdog.stop() wrapper.size = size wrapper.memuse = memuse return wrapper return decorator def bigaddrspacetest(f): """Decorator for tests that fill the address space.""" def wrapper(self): if max_memuse < MAX_Py_ssize_t: if MAX_Py_ssize_t >= 2**63 - 1 and max_memuse >= 2**31: raise unittest.SkipTest( "not enough memory: try a 32-bit build instead") else: raise unittest.SkipTest( "not enough memory: %.1fG minimum needed" % (MAX_Py_ssize_t / (1024 ** 3))) else: return f(self) return wrapper #======================================================================= # unittest integration. class BasicTestRunner: def run(self, test): result = unittest.TestResult() test(result) return result def _id(obj): return obj def requires_resource(resource): if resource == 'gui' and not _is_gui_available(): return unittest.skip(_is_gui_available.reason) if is_resource_enabled(resource): return _id else: return unittest.skip("resource {0!r} is not enabled".format(resource)) def cpython_only(test): """ Decorator for tests only applicable on CPython. """ return impl_detail(cpython=True)(test) def impl_detail(msg=None, **guards): if check_impl_detail(**guards): return _id if msg is None: guardnames, default = _parse_guards(guards) if default: msg = "implementation detail not available on {0}" else: msg = "implementation detail specific to {0}" guardnames = sorted(guardnames.keys()) msg = msg.format(' or '.join(guardnames)) return unittest.skip(msg) def _parse_guards(guards): # Returns a tuple ({platform_name: run_me}, default_value) if not guards: return ({'cpython': True}, False) is_true = list(guards.values())[0] assert list(guards.values()) == [is_true] * len(guards) # all True or all False return (guards, not is_true) # Use the following check to guard CPython's implementation-specific tests -- # or to run them only on the implementation(s) guarded by the arguments. def check_impl_detail(**guards): """This function returns True or False depending on the host platform. Examples: if check_impl_detail(): # only on CPython (default) if check_impl_detail(jython=True): # only on Jython if check_impl_detail(cpython=False): # everywhere except on CPython """ guards, default = _parse_guards(guards) return guards.get(platform.python_implementation().lower(), default) def no_tracing(func): """Decorator to temporarily turn off tracing for the duration of a test.""" if not hasattr(sys, 'gettrace'): return func else: @functools.wraps(func) def wrapper(*args, **kwargs): original_trace = sys.gettrace() try: sys.settrace(None) return func(*args, **kwargs) finally: sys.settrace(original_trace) return wrapper def refcount_test(test): """Decorator for tests which involve reference counting. To start, the decorator does not run the test if is not run by CPython. After that, any trace function is unset during the test to prevent unexpected refcounts caused by the trace function. """ return no_tracing(cpython_only(test)) def _filter_suite(suite, pred): """Recursively filter test cases in a suite based on a predicate.""" newtests = [] for test in suite._tests: if isinstance(test, unittest.TestSuite): _filter_suite(test, pred) newtests.append(test) else: if pred(test): newtests.append(test) suite._tests = newtests def _run_suite(suite): """Run tests from a unittest.TestSuite-derived class.""" runner = get_test_runner(sys.stdout, verbosity=verbose) # TODO: Remove this before merging (here for easy comparison with old impl) #runner = unittest.TextTestRunner(sys.stdout, verbosity=2, failfast=failfast) result = runner.run(suite) if junit_xml_list is not None: junit_xml_list.append(result.get_xml_element()) if not result.wasSuccessful(): if len(result.errors) == 1 and not result.failures: err = result.errors[0][1] elif len(result.failures) == 1 and not result.errors: err = result.failures[0][1] else: err = "multiple errors occurred" if not verbose: err += "; run in verbose mode for details" raise TestFailed(err) # By default, don't filter tests _match_test_func = None _match_test_patterns = None def match_test(test): # Function used by support.run_unittest() and regrtest --list-cases if _match_test_func is None: return True else: return _match_test_func(test.id()) def _is_full_match_test(pattern): # If a pattern contains at least one dot, it's considered # as a full test identifier. # Example: 'test.test_os.FileTests.test_access'. # # Reject patterns which contain fnmatch patterns: '*', '?', '[...]' # or '[!...]'. For example, reject 'test_access*'. return ('.' in pattern) and (not re.search(r'[?*\[\]]', pattern)) def set_match_tests(patterns): global _match_test_func, _match_test_patterns if patterns == _match_test_patterns: # No change: no need to recompile patterns. return if not patterns: func = None # set_match_tests(None) behaves as set_match_tests(()) patterns = () elif all(map(_is_full_match_test, patterns)): # Simple case: all patterns are full test identifier. # The test.bisect utility only uses such full test identifiers. func = set(patterns).__contains__ else: regex = '|'.join(map(fnmatch.translate, patterns)) # The search *is* case sensitive on purpose: # don't use flags=re.IGNORECASE regex_match = re.compile(regex).match def match_test_regex(test_id): if regex_match(test_id): # The regex matches the whole identifier, for example # 'test.test_os.FileTests.test_access'. return True else: # Try to match parts of the test identifier. # For example, split 'test.test_os.FileTests.test_access' # into: 'test', 'test_os', 'FileTests' and 'test_access'. return any(map(regex_match, test_id.split("."))) func = match_test_regex # Create a copy since patterns can be mutable and so modified later _match_test_patterns = tuple(patterns) _match_test_func = func def run_unittest(*classes): """Run tests from unittest.TestCase-derived classes.""" valid_types = (unittest.TestSuite, unittest.TestCase) suite = unittest.TestSuite() for cls in classes: if isinstance(cls, str): if cls in sys.modules: suite.addTest(unittest.findTestCases(sys.modules[cls])) else: raise ValueError("str arguments must be keys in sys.modules") elif isinstance(cls, valid_types): suite.addTest(cls) else: suite.addTest(unittest.makeSuite(cls)) _filter_suite(suite, match_test) _run_suite(suite) #======================================================================= # Check for the presence of docstrings. # Rather than trying to enumerate all the cases where docstrings may be # disabled, we just check for that directly def _check_docstrings(): """Just used to check if docstrings are enabled""" MISSING_C_DOCSTRINGS = (check_impl_detail() and sys.platform != 'win32' and not sysconfig.get_config_var('WITH_DOC_STRINGS')) HAVE_DOCSTRINGS = (_check_docstrings.__doc__ is not None and not MISSING_C_DOCSTRINGS) requires_docstrings = unittest.skipUnless(HAVE_DOCSTRINGS, "test requires docstrings") #======================================================================= # doctest driver. def run_doctest(module, verbosity=None, optionflags=0): """Run doctest on the given module. Return (#failures, #tests). If optional argument verbosity is not specified (or is None), pass support's belief about verbosity on to doctest. Else doctest's usual behavior is used (it searches sys.argv for -v). """ import doctest if verbosity is None: verbosity = verbose else: verbosity = None f, t = doctest.testmod(module, verbose=verbosity, optionflags=optionflags) if f: raise TestFailed("%d of %d doctests failed" % (f, t)) if verbose: print('doctest (%s) ... %d tests with zero failures' % (module.__name__, t)) return f, t #======================================================================= # Support for saving and restoring the imported modules. def modules_setup(): return sys.modules.copy(), def modules_cleanup(oldmodules): # Encoders/decoders are registered permanently within the internal # codec cache. If we destroy the corresponding modules their # globals will be set to None which will trip up the cached functions. encodings = [(k, v) for k, v in sys.modules.items() if k.startswith('encodings.')] sys.modules.clear() sys.modules.update(encodings) # XXX: This kind of problem can affect more than just encodings. In particular # extension modules (such as _ssl) don't cope with reloading properly. # Really, test modules should be cleaning out the test specific modules they # know they added (ala test_runpy) rather than relying on this function (as # test_importhooks and test_pkg do currently). # Implicitly imported *real* modules should be left alone (see issue 10556). sys.modules.update(oldmodules) #======================================================================= # Threading support to prevent reporting refleaks when running regrtest.py -R # Flag used by saved_test_environment of test.libregrtest.save_env, # to check if a test modified the environment. The flag should be set to False # before running a new test. # # For example, threading_cleanup() sets the flag is the function fails # to cleanup threads. environment_altered = False # NOTE: we use thread._count() rather than threading.enumerate() (or the # moral equivalent thereof) because a threading.Thread object is still alive # until its __bootstrap() method has returned, even after it has been # unregistered from the threading module. # thread._count(), on the other hand, only gets decremented *after* the # __bootstrap() method has returned, which gives us reliable reference counts # at the end of a test run. def threading_setup(): return _thread._count(), threading._dangling.copy() def threading_cleanup(*original_values): global environment_altered _MAX_COUNT = 100 for count in range(_MAX_COUNT): values = _thread._count(), threading._dangling if values == original_values: break if not count: # Display a warning at the first iteration environment_altered = True dangling_threads = values[1] print("Warning -- threading_cleanup() failed to cleanup " "%s threads (count: %s, dangling: %s)" % (values[0] - original_values[0], values[0], len(dangling_threads)), file=sys.stderr) for thread in dangling_threads: print("Dangling thread: {!r}".format(thread), file=sys.stderr) sys.stderr.flush() # Don't hold references to threads dangling_threads = None values = None time.sleep(0.01) gc_collect() def reap_threads(func): """Use this function when threads are being used. This will ensure that the threads are cleaned up even when the test fails. """ @functools.wraps(func) def decorator(*args): key = threading_setup() try: return func(*args) finally: threading_cleanup(*key) return decorator @contextlib.contextmanager def wait_threads_exit(timeout=60.0): """ bpo-31234: Context manager to wait until all threads created in the with statement exit. Use _thread.count() to check if threads exited. Indirectly, wait until threads exit the internal t_bootstrap() C function of the _thread module. threading_setup() and threading_cleanup() are designed to emit a warning if a test leaves running threads in the background. This context manager is designed to cleanup threads started by the _thread.start_new_thread() which doesn't allow to wait for thread exit, whereas thread.Thread has a join() method. """ old_count = _thread._count() try: yield finally: start_time = time.monotonic() deadline = start_time + timeout while True: count = _thread._count() if count <= old_count: break if time.monotonic() > deadline: dt = time.monotonic() - start_time msg = ("wait_threads() failed to cleanup {} " "threads after {:.1f} seconds " "(count: {}, old count: {})".format(count - old_count, dt, count, old_count)) raise AssertionError(msg) time.sleep(0.010) gc_collect() def join_thread(thread, timeout=30.0): """Join a thread. Raise an AssertionError if the thread is still alive after timeout seconds. """ thread.join(timeout) if thread.is_alive(): msg = "failed to join the thread in {:.1f} seconds".format(timeout) raise AssertionError(msg) def reap_children(): """Use this function at the end of test_main() whenever sub-processes are started. This will help ensure that no extra children (zombies) stick around to hog resources and create problems when looking for refleaks. """ global environment_altered # Need os.waitpid(-1, os.WNOHANG): Windows is not supported if not (hasattr(os, 'waitpid') and hasattr(os, 'WNOHANG')): return # Reap all our dead child processes so we don't leave zombies around. # These hog resources and might be causing some of the buildbots to die. while True: try: # Read the exit status of any child process which already completed pid, status = os.waitpid(-1, os.WNOHANG) except OSError: break if pid == 0: break print("Warning -- reap_children() reaped child process %s" % pid, file=sys.stderr) environment_altered = True @contextlib.contextmanager def start_threads(threads, unlock=None): threads = list(threads) started = [] try: try: for t in threads: t.start() started.append(t) except: if verbose: print("Can't start %d threads, only %d threads started" % (len(threads), len(started))) raise yield finally: try: if unlock: unlock() endtime = starttime = time.time() for timeout in range(1, 16): endtime += 60 for t in started: t.join(max(endtime - time.time(), 0.01)) started = [t for t in started if t.isAlive()] if not started: break if verbose: print('Unable to join %d threads during a period of ' '%d minutes' % (len(started), timeout)) finally: started = [t for t in started if t.isAlive()] if started: faulthandler.dump_traceback(sys.stdout) raise AssertionError('Unable to join %d threads' % len(started)) @contextlib.contextmanager def swap_attr(obj, attr, new_val): """Temporary swap out an attribute with a new object. Usage: with swap_attr(obj, "attr", 5): ... This will set obj.attr to 5 for the duration of the with: block, restoring the old value at the end of the block. If `attr` doesn't exist on `obj`, it will be created and then deleted at the end of the block. The old value (or None if it doesn't exist) will be assigned to the target of the "as" clause, if there is one. """ if hasattr(obj, attr): real_val = getattr(obj, attr) setattr(obj, attr, new_val) try: yield real_val finally: setattr(obj, attr, real_val) else: setattr(obj, attr, new_val) try: yield finally: if hasattr(obj, attr): delattr(obj, attr) @contextlib.contextmanager def swap_item(obj, item, new_val): """Temporary swap out an item with a new object. Usage: with swap_item(obj, "item", 5): ... This will set obj["item"] to 5 for the duration of the with: block, restoring the old value at the end of the block. If `item` doesn't exist on `obj`, it will be created and then deleted at the end of the block. The old value (or None if it doesn't exist) will be assigned to the target of the "as" clause, if there is one. """ if item in obj: real_val = obj[item] obj[item] = new_val try: yield real_val finally: obj[item] = real_val else: obj[item] = new_val try: yield finally: if item in obj: del obj[item] def strip_python_stderr(stderr): """Strip the stderr of a Python process from potential debug output emitted by the interpreter. This will typically be run on the result of the communicate() method of a subprocess.Popen object. """ stderr = re.sub(br"\[\d+ refs, \d+ blocks\]\r?\n?", b"", stderr).strip() return stderr requires_type_collecting = unittest.skipIf(hasattr(sys, 'getcounts'), 'types are immortal if COUNT_ALLOCS is defined') def args_from_interpreter_flags(): """Return a list of command-line arguments reproducing the current settings in sys.flags and sys.warnoptions.""" return subprocess._args_from_interpreter_flags() def optim_args_from_interpreter_flags(): """Return a list of command-line arguments reproducing the current optimization settings in sys.flags.""" return subprocess._optim_args_from_interpreter_flags() #============================================================ # Support for assertions about logging. #============================================================ class TestHandler(logging.handlers.BufferingHandler): def __init__(self, matcher): # BufferingHandler takes a "capacity" argument # so as to know when to flush. As we're overriding # shouldFlush anyway, we can set a capacity of zero. # You can call flush() manually to clear out the # buffer. logging.handlers.BufferingHandler.__init__(self, 0) self.matcher = matcher def shouldFlush(self): return False def emit(self, record): self.format(record) self.buffer.append(record.__dict__) def matches(self, **kwargs): """ Look for a saved dict whose keys/values match the supplied arguments. """ result = False for d in self.buffer: if self.matcher.matches(d, **kwargs): result = True break return result class Matcher(object): _partial_matches = ('msg', 'message') def matches(self, d, **kwargs): """ Try to match a single dict with the supplied arguments. Keys whose values are strings and which are in self._partial_matches will be checked for partial (i.e. substring) matches. You can extend this scheme to (for example) do regular expression matching, etc. """ result = True for k in kwargs: v = kwargs[k] dv = d.get(k) if not self.match_value(k, dv, v): result = False break return result def match_value(self, k, dv, v): """ Try to match a single stored value (dv) with a supplied value (v). """ if type(v) != type(dv): result = False elif type(dv) is not str or k not in self._partial_matches: result = (v == dv) else: result = dv.find(v) >= 0 return result _can_symlink = None def can_symlink(): global _can_symlink if _can_symlink is not None: return _can_symlink symlink_path = TESTFN + "can_symlink" try: os.symlink(TESTFN, symlink_path) can = True except (OSError, NotImplementedError, AttributeError): can = False else: os.remove(symlink_path) _can_symlink = can return can def skip_unless_symlink(test): """Skip decorator for tests that require functional symlink""" ok = can_symlink() msg = "Requires functional symlink implementation" return test if ok else unittest.skip(msg)(test) _can_xattr = None def can_xattr(): global _can_xattr if _can_xattr is not None: return _can_xattr if not hasattr(os, "setxattr"): can = False else: tmp_dir = tempfile.mkdtemp() tmp_fp, tmp_name = tempfile.mkstemp(dir=tmp_dir) try: with open(TESTFN, "wb") as fp: try: # TESTFN & tempfile may use different file systems with # different capabilities os.setxattr(tmp_fp, b"user.test", b"") os.setxattr(tmp_name, b"trusted.foo", b"42") os.setxattr(fp.fileno(), b"user.test", b"") # Kernels < 2.6.39 don't respect setxattr flags. kernel_version = platform.release() m = re.match(r"2.6.(\d{1,2})", kernel_version) can = m is None or int(m.group(1)) >= 39 except OSError: can = False finally: unlink(TESTFN) unlink(tmp_name) rmdir(tmp_dir) _can_xattr = can return can def skip_unless_xattr(test): """Skip decorator for tests that require functional extended attributes""" ok = can_xattr() msg = "no non-broken extended attribute support" return test if ok else unittest.skip(msg)(test) _bind_nix_socket_error = None def skip_unless_bind_unix_socket(test): """Decorator for tests requiring a functional bind() for unix sockets.""" if not hasattr(socket, 'AF_UNIX'): return unittest.skip('No UNIX Sockets')(test) global _bind_nix_socket_error if _bind_nix_socket_error is None: path = TESTFN + "can_bind_unix_socket" with socket.socket(socket.AF_UNIX) as sock: try: sock.bind(path) _bind_nix_socket_error = False except OSError as e: _bind_nix_socket_error = e finally: unlink(path) if _bind_nix_socket_error: msg = 'Requires a functional unix bind(): %s' % _bind_nix_socket_error return unittest.skip(msg)(test) else: return test def fs_is_case_insensitive(directory): """Detects if the file system for the specified directory is case-insensitive.""" with tempfile.NamedTemporaryFile(dir=directory) as base: base_path = base.name case_path = base_path.upper() if case_path == base_path: case_path = base_path.lower() try: return os.path.samefile(base_path, case_path) except FileNotFoundError: return False def detect_api_mismatch(ref_api, other_api, *, ignore=()): """Returns the set of items in ref_api not in other_api, except for a defined list of items to be ignored in this check. By default this skips private attributes beginning with '_' but includes all magic methods, i.e. those starting and ending in '__'. """ missing_items = set(dir(ref_api)) - set(dir(other_api)) if ignore: missing_items -= set(ignore) missing_items = set(m for m in missing_items if not m.startswith('_') or m.endswith('__')) return missing_items def check__all__(test_case, module, name_of_module=None, extra=(), blacklist=()): """Assert that the __all__ variable of 'module' contains all public names. The module's public names (its API) are detected automatically based on whether they match the public name convention and were defined in 'module'. The 'name_of_module' argument can specify (as a string or tuple thereof) what module(s) an API could be defined in in order to be detected as a public API. One case for this is when 'module' imports part of its public API from other modules, possibly a C backend (like 'csv' and its '_csv'). The 'extra' argument can be a set of names that wouldn't otherwise be automatically detected as "public", like objects without a proper '__module__' attribute. If provided, it will be added to the automatically detected ones. The 'blacklist' argument can be a set of names that must not be treated as part of the public API even though their names indicate otherwise. Usage: import bar import foo import unittest from test import support class MiscTestCase(unittest.TestCase): def test__all__(self): support.check__all__(self, foo) class OtherTestCase(unittest.TestCase): def test__all__(self): extra = {'BAR_CONST', 'FOO_CONST'} blacklist = {'baz'} # Undocumented name. # bar imports part of its API from _bar. support.check__all__(self, bar, ('bar', '_bar'), extra=extra, blacklist=blacklist) """ if name_of_module is None: name_of_module = (module.__name__, ) elif isinstance(name_of_module, str): name_of_module = (name_of_module, ) expected = set(extra) for name in dir(module): if name.startswith('_') or name in blacklist: continue obj = getattr(module, name) if (getattr(obj, '__module__', None) in name_of_module or (not hasattr(obj, '__module__') and not isinstance(obj, types.ModuleType))): expected.add(name) test_case.assertCountEqual(module.__all__, expected) class SuppressCrashReport: """Try to prevent a crash report from popping up. On Windows, don't display the Windows Error Reporting dialog. On UNIX, disable the creation of coredump file. """ old_value = None old_modes = None def __enter__(self): """On Windows, disable Windows Error Reporting dialogs using SetErrorMode. On UNIX, try to save the previous core file size limit, then set soft limit to 0. """ if sys.platform.startswith('win'): # see http://msdn.microsoft.com/en-us/library/windows/desktop/ms680621.aspx # GetErrorMode is not available on Windows XP and Windows Server 2003, # but SetErrorMode returns the previous value, so we can use that import ctypes self._k32 = ctypes.windll.kernel32 SEM_NOGPFAULTERRORBOX = 0x02 self.old_value = self._k32.SetErrorMode(SEM_NOGPFAULTERRORBOX) self._k32.SetErrorMode(self.old_value | SEM_NOGPFAULTERRORBOX) # Suppress assert dialogs in debug builds # (see http://bugs.python.org/issue23314) try: import msvcrt msvcrt.CrtSetReportMode except (AttributeError, ImportError): # no msvcrt or a release build pass else: self.old_modes = {} for report_type in [msvcrt.CRT_WARN, msvcrt.CRT_ERROR, msvcrt.CRT_ASSERT]: old_mode = msvcrt.CrtSetReportMode(report_type, msvcrt.CRTDBG_MODE_FILE) old_file = msvcrt.CrtSetReportFile(report_type, msvcrt.CRTDBG_FILE_STDERR) self.old_modes[report_type] = old_mode, old_file else: if resource is not None: try: self.old_value = resource.getrlimit(resource.RLIMIT_CORE) resource.setrlimit(resource.RLIMIT_CORE, (0, self.old_value[1])) except (ValueError, OSError): pass if sys.platform == 'darwin': # Check if the 'Crash Reporter' on OSX was configured # in 'Developer' mode and warn that it will get triggered # when it is. # # This assumes that this context manager is used in tests # that might trigger the next manager. cmd = ['/usr/bin/defaults', 'read', 'com.apple.CrashReporter', 'DialogType'] proc = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE) with proc: stdout = proc.communicate()[0] if stdout.strip() == b'developer': print("this test triggers the Crash Reporter, " "that is intentional", end='', flush=True) return self def __exit__(self, *ignore_exc): """Restore Windows ErrorMode or core file behavior to initial value.""" if self.old_value is None: return if sys.platform.startswith('win'): self._k32.SetErrorMode(self.old_value) if self.old_modes: import msvcrt for report_type, (old_mode, old_file) in self.old_modes.items(): msvcrt.CrtSetReportMode(report_type, old_mode) msvcrt.CrtSetReportFile(report_type, old_file) else: if resource is not None: try: resource.setrlimit(resource.RLIMIT_CORE, self.old_value) except (ValueError, OSError): pass def patch(test_instance, object_to_patch, attr_name, new_value): """Override 'object_to_patch'.'attr_name' with 'new_value'. Also, add a cleanup procedure to 'test_instance' to restore 'object_to_patch' value for 'attr_name'. The 'attr_name' should be a valid attribute for 'object_to_patch'. """ # check that 'attr_name' is a real attribute for 'object_to_patch' # will raise AttributeError if it does not exist getattr(object_to_patch, attr_name) # keep a copy of the old value attr_is_local = False try: old_value = object_to_patch.__dict__[attr_name] except (AttributeError, KeyError): old_value = getattr(object_to_patch, attr_name, None) else: attr_is_local = True # restore the value when the test is done def cleanup(): if attr_is_local: setattr(object_to_patch, attr_name, old_value) else: delattr(object_to_patch, attr_name) test_instance.addCleanup(cleanup) # actually override the attribute setattr(object_to_patch, attr_name, new_value) def run_in_subinterp(code): """ Run code in a subinterpreter. Raise unittest.SkipTest if the tracemalloc module is enabled. """ # Issue #10915, #15751: PyGILState_*() functions don't work with # sub-interpreters, the tracemalloc module uses these functions internally try: import tracemalloc except ImportError: pass else: if tracemalloc.is_tracing(): raise unittest.SkipTest("run_in_subinterp() cannot be used " "if tracemalloc module is tracing " "memory allocations") import _testcapi return _testcapi.run_in_subinterp(code) def check_free_after_iterating(test, iter, cls, args=()): class A(cls): def __del__(self): nonlocal done done = True try: next(it) except StopIteration: pass done = False it = iter(A(*args)) # Issue 26494: Shouldn't crash test.assertRaises(StopIteration, next, it) # The sequence should be deallocated just after the end of iterating gc_collect() test.assertTrue(done) def missing_compiler_executable(cmd_names=[]): """Check if the compiler components used to build the interpreter exist. Check for the existence of the compiler executables whose names are listed in 'cmd_names' or all the compiler executables when 'cmd_names' is empty and return the first missing executable or None when none is found missing. """ from distutils import ccompiler, sysconfig, spawn compiler = ccompiler.new_compiler() sysconfig.customize_compiler(compiler) for name in compiler.executables: if cmd_names and name not in cmd_names: continue cmd = getattr(compiler, name) if cmd_names: assert cmd is not None, \ "the '%s' executable is not configured" % name elif cmd is None: continue if spawn.find_executable(cmd[0]) is None: return cmd[0] _is_android_emulator = None def setswitchinterval(interval): # Setting a very low gil interval on the Android emulator causes python # to hang (issue #26939). minimum_interval = 1e-5 if is_android and interval < minimum_interval: global _is_android_emulator if _is_android_emulator is None: _is_android_emulator = (subprocess.check_output( ['getprop', 'ro.kernel.qemu']).strip() == b'1') if _is_android_emulator: interval = minimum_interval return sys.setswitchinterval(interval) @contextlib.contextmanager def disable_faulthandler(): # use sys.__stderr__ instead of sys.stderr, since regrtest replaces # sys.stderr with a StringIO which has no file descriptor when a test # is run with -W/--verbose3. fd = sys.__stderr__.fileno() is_enabled = faulthandler.is_enabled() try: faulthandler.disable() yield finally: if is_enabled: faulthandler.enable(file=fd, all_threads=True) def fd_count(): """Count the number of open file descriptors. """ if sys.platform.startswith(('linux', 'freebsd')): try: names = os.listdir("/proc/self/fd") # Substract one because listdir() opens internally a file # descriptor to list the content of the /proc/self/fd/ directory. return len(names) - 1 except FileNotFoundError: pass MAXFD = 256 if hasattr(os, 'sysconf'): try: MAXFD = os.sysconf("SC_OPEN_MAX") except OSError: pass old_modes = None if sys.platform == 'win32': # bpo-25306, bpo-31009: Call CrtSetReportMode() to not kill the process # on invalid file descriptor if Python is compiled in debug mode try: import msvcrt msvcrt.CrtSetReportMode except (AttributeError, ImportError): # no msvcrt or a release build pass else: old_modes = {} for report_type in (msvcrt.CRT_WARN, msvcrt.CRT_ERROR, msvcrt.CRT_ASSERT): old_modes[report_type] = msvcrt.CrtSetReportMode(report_type, 0) try: count = 0 for fd in range(MAXFD): try: # Prefer dup() over fstat(). fstat() can require input/output # whereas dup() doesn't. fd2 = os.dup(fd) except OSError as e: if e.errno != errno.EBADF: raise else: os.close(fd2) count += 1 finally: if old_modes is not None: for report_type in (msvcrt.CRT_WARN, msvcrt.CRT_ERROR, msvcrt.CRT_ASSERT): msvcrt.CrtSetReportMode(report_type, old_modes[report_type]) return count class SaveSignals: """ Save and restore signal handlers. This class is only able to save/restore signal handlers registered by the Python signal module: see bpo-13285 for "external" signal handlers. """ def __init__(self): import signal self.signal = signal self.signals = signal.valid_signals() # SIGKILL and SIGSTOP signals cannot be ignored nor caught for signame in ('SIGKILL', 'SIGSTOP'): try: signum = getattr(signal, signame) except AttributeError: continue self.signals.remove(signum) self.handlers = {} def save(self): for signum in self.signals: handler = self.signal.getsignal(signum) if handler is None: # getsignal() returns None if a signal handler was not # registered by the Python signal module, # and the handler is not SIG_DFL nor SIG_IGN. # # Ignore the signal: we cannot restore the handler. continue self.handlers[signum] = handler def restore(self): for signum, handler in self.handlers.items(): self.signal.signal(signum, handler) def with_pymalloc(): import _testcapi return _testcapi.WITH_PYMALLOC class FakePath: """Simple implementing of the path protocol. """ def __init__(self, path): self.path = path def __repr__(self): return ''.format(self.path) def __fspath__(self): if (isinstance(self.path, BaseException) or isinstance(self.path, type) and issubclass(self.path, BaseException)): raise self.path else: return self.path def maybe_get_event_loop_policy(): """Return the global event loop policy if one is set, else return None.""" return asyncio.events._event_loop_policy pyzipper-0.4.0/test/support/script_helper.py000066400000000000000000000246071520124366100213160ustar00rootroot00000000000000# Common utility functions used by various script execution tests # e.g. test_cmd_line, test_cmd_line_script and test_runpy import collections import importlib import sys import os import os.path import subprocess import py_compile import zipfile from importlib.util import source_from_cache from test.support import make_legacy_pyc, strip_python_stderr # Cached result of the expensive test performed in the function below. __cached_interp_requires_environment = None def interpreter_requires_environment(): """ Returns True if our sys.executable interpreter requires environment variables in order to be able to run at all. This is designed to be used with @unittest.skipIf() to annotate tests that need to use an assert_python*() function to launch an isolated mode (-I) or no environment mode (-E) sub-interpreter process. A normal build & test does not run into this situation but it can happen when trying to run the standard library test suite from an interpreter that doesn't have an obvious home with Python's current home finding logic. Setting PYTHONHOME is one way to get most of the testsuite to run in that situation. PYTHONPATH or PYTHONUSERSITE are other common environment variables that might impact whether or not the interpreter can start. """ global __cached_interp_requires_environment if __cached_interp_requires_environment is None: # If PYTHONHOME is set, assume that we need it if 'PYTHONHOME' in os.environ: __cached_interp_requires_environment = True return True # Try running an interpreter with -E to see if it works or not. try: subprocess.check_call([sys.executable, '-E', '-c', 'import sys; sys.exit(0)']) except subprocess.CalledProcessError: __cached_interp_requires_environment = True else: __cached_interp_requires_environment = False return __cached_interp_requires_environment class _PythonRunResult(collections.namedtuple("_PythonRunResult", ("rc", "out", "err"))): """Helper for reporting Python subprocess run results""" def fail(self, cmd_line): """Provide helpful details about failed subcommand runs""" # Limit to 80 lines to ASCII characters maxlen = 80 * 100 out, err = self.out, self.err if len(out) > maxlen: out = b'(... truncated stdout ...)' + out[-maxlen:] if len(err) > maxlen: err = b'(... truncated stderr ...)' + err[-maxlen:] out = out.decode('ascii', 'replace').rstrip() err = err.decode('ascii', 'replace').rstrip() raise AssertionError("Process return code is %d\n" "command line: %r\n" "\n" "stdout:\n" "---\n" "%s\n" "---\n" "\n" "stderr:\n" "---\n" "%s\n" "---" % (self.rc, cmd_line, out, err)) # Executing the interpreter in a subprocess def run_python_until_end(*args, **env_vars): env_required = interpreter_requires_environment() cwd = env_vars.pop('__cwd', None) if '__isolated' in env_vars: isolated = env_vars.pop('__isolated') else: isolated = not env_vars and not env_required cmd_line = [sys.executable, '-X', 'faulthandler'] if isolated: # isolated mode: ignore Python environment variables, ignore user # site-packages, and don't add the current directory to sys.path cmd_line.append('-I') elif not env_vars and not env_required: # ignore Python environment variables cmd_line.append('-E') # But a special flag that can be set to override -- in this case, the # caller is responsible to pass the full environment. if env_vars.pop('__cleanenv', None): env = {} if sys.platform == 'win32': # Windows requires at least the SYSTEMROOT environment variable to # start Python. env['SYSTEMROOT'] = os.environ['SYSTEMROOT'] # Other interesting environment variables, not copied currently: # COMSPEC, HOME, PATH, TEMP, TMPDIR, TMP. else: # Need to preserve the original environment, for in-place testing of # shared library builds. env = os.environ.copy() # set TERM='' unless the TERM environment variable is passed explicitly # see issues #11390 and #18300 if 'TERM' not in env_vars: env['TERM'] = '' env.update(env_vars) cmd_line.extend(args) proc = subprocess.Popen(cmd_line, stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE, env=env, cwd=cwd) with proc: try: out, err = proc.communicate() finally: proc.kill() subprocess._cleanup() rc = proc.returncode err = strip_python_stderr(err) return _PythonRunResult(rc, out, err), cmd_line def _assert_python(expected_success, *args, **env_vars): res, cmd_line = run_python_until_end(*args, **env_vars) if (res.rc and expected_success) or (not res.rc and not expected_success): res.fail(cmd_line) return res def assert_python_ok(*args, **env_vars): """ Assert that running the interpreter with `args` and optional environment variables `env_vars` succeeds (rc == 0) and return a (return code, stdout, stderr) tuple. If the __cleanenv keyword is set, env_vars is used as a fresh environment. Python is started in isolated mode (command line option -I), except if the __isolated keyword is set to False. """ return _assert_python(True, *args, **env_vars) def assert_python_failure(*args, **env_vars): """ Assert that running the interpreter with `args` and optional environment variables `env_vars` fails (rc != 0) and return a (return code, stdout, stderr) tuple. See assert_python_ok() for more options. """ return _assert_python(False, *args, **env_vars) def spawn_python(*args, stdout=subprocess.PIPE, stderr=subprocess.STDOUT, **kw): """Run a Python subprocess with the given arguments. kw is extra keyword args to pass to subprocess.Popen. Returns a Popen object. """ cmd_line = [sys.executable] if not interpreter_requires_environment(): cmd_line.append('-E') cmd_line.extend(args) # Under Fedora (?), GNU readline can output junk on stderr when initialized, # depending on the TERM setting. Setting TERM=vt100 is supposed to disable # that. References: # - http://reinout.vanrees.org/weblog/2009/08/14/readline-invisible-character-hack.html # - http://stackoverflow.com/questions/15760712/python-readline-module-prints-escape-character-during-import # - http://lists.gnu.org/archive/html/bug-readline/2007-08/msg00004.html env = kw.setdefault('env', dict(os.environ)) env['TERM'] = 'vt100' return subprocess.Popen(cmd_line, stdin=subprocess.PIPE, stdout=stdout, stderr=stderr, **kw) def kill_python(p): """Run the given Popen process until completion and return stdout.""" p.stdin.close() data = p.stdout.read() p.stdout.close() # try to cleanup the child so we don't appear to leak when running # with regrtest -R. p.wait() subprocess._cleanup() return data def make_script(script_dir, script_basename, source, omit_suffix=False): script_filename = script_basename if not omit_suffix: script_filename += os.extsep + 'py' script_name = os.path.join(script_dir, script_filename) # The script should be encoded to UTF-8, the default string encoding script_file = open(script_name, 'w', encoding='utf-8') script_file.write(source) script_file.close() importlib.invalidate_caches() return script_name def make_zip_script(zip_dir, zip_basename, script_name, name_in_zip=None): zip_filename = zip_basename+os.extsep+'zip' zip_name = os.path.join(zip_dir, zip_filename) zip_file = zipfile.ZipFile(zip_name, 'w') if name_in_zip is None: parts = script_name.split(os.sep) if len(parts) >= 2 and parts[-2] == '__pycache__': legacy_pyc = make_legacy_pyc(source_from_cache(script_name)) name_in_zip = os.path.basename(legacy_pyc) script_name = legacy_pyc else: name_in_zip = os.path.basename(script_name) zip_file.write(script_name, name_in_zip) zip_file.close() #if test.support.verbose: # zip_file = zipfile.ZipFile(zip_name, 'r') # print 'Contents of %r:' % zip_name # zip_file.printdir() # zip_file.close() return zip_name, os.path.join(zip_name, name_in_zip) def make_pkg(pkg_dir, init_source=''): os.mkdir(pkg_dir) make_script(pkg_dir, '__init__', init_source) def make_zip_pkg(zip_dir, zip_basename, pkg_name, script_basename, source, depth=1, compiled=False): unlink = [] init_name = make_script(zip_dir, '__init__', '') unlink.append(init_name) init_basename = os.path.basename(init_name) script_name = make_script(zip_dir, script_basename, source) unlink.append(script_name) if compiled: init_name = py_compile.compile(init_name, doraise=True) script_name = py_compile.compile(script_name, doraise=True) unlink.extend((init_name, script_name)) pkg_names = [os.sep.join([pkg_name]*i) for i in range(1, depth+1)] script_name_in_zip = os.path.join(pkg_names[-1], os.path.basename(script_name)) zip_filename = zip_basename+os.extsep+'zip' zip_name = os.path.join(zip_dir, zip_filename) zip_file = zipfile.ZipFile(zip_name, 'w') for name in pkg_names: init_name_in_zip = os.path.join(name, init_basename) zip_file.write(init_name, init_name_in_zip) zip_file.write(script_name, script_name_in_zip) zip_file.close() for name in unlink: os.unlink(name) #if test.support.verbose: # zip_file = zipfile.ZipFile(zip_name, 'r') # print 'Contents of %r:' % zip_name # zip_file.printdir() # zip_file.close() return zip_name, os.path.join(zip_name, script_name_in_zip) pyzipper-0.4.0/test/support/testresult.py000066400000000000000000000145151520124366100206660ustar00rootroot00000000000000'''Test runner and result class for the regression test suite. ''' import functools import io import sys import time import traceback import unittest import xml.etree.ElementTree as ET from datetime import datetime class RegressionTestResult(unittest.TextTestResult): separator1 = '=' * 70 + '\n' separator2 = '-' * 70 + '\n' def __init__(self, stream, descriptions, verbosity): super().__init__(stream=stream, descriptions=descriptions, verbosity=0) self.buffer = True self.__suite = ET.Element('testsuite') self.__suite.set('start', datetime.utcnow().isoformat(' ')) self.__e = None self.__start_time = None self.__results = [] self.__verbose = bool(verbosity) @classmethod def __getId(cls, test): try: test_id = test.id except AttributeError: return str(test) try: return test_id() except TypeError: return str(test_id) return repr(test) def startTest(self, test): super().startTest(test) self.__e = e = ET.SubElement(self.__suite, 'testcase') self.__start_time = time.perf_counter() if self.__verbose: self.stream.write('{} ... '.format(self.getDescription(test))) self.stream.flush() def _add_result(self, test, capture=False, **args): e = self.__e self.__e = None if e is None: return e.set('name', args.pop('name', self.__getId(test))) e.set('status', args.pop('status', 'run')) e.set('result', args.pop('result', 'completed')) if self.__start_time: e.set('time', '{:0.6f}'.format(time.perf_counter() - self.__start_time)) if capture: stdout = self._stdout_buffer.getvalue().rstrip() ET.SubElement(e, 'system-out').text = stdout stderr = self._stderr_buffer.getvalue().rstrip() ET.SubElement(e, 'system-err').text = stderr for k, v in args.items(): if not k or not v: continue e2 = ET.SubElement(e, k) if hasattr(v, 'items'): for k2, v2 in v.items(): if k2: e2.set(k2, str(v2)) else: e2.text = str(v2) else: e2.text = str(v) def __write(self, c, word): if self.__verbose: self.stream.write('{}\n'.format(word)) @classmethod def __makeErrorDict(cls, err_type, err_value, err_tb): if isinstance(err_type, type): if err_type.__module__ == 'builtins': typename = err_type.__name__ else: typename = '{}.{}'.format(err_type.__module__, err_type.__name__) else: typename = repr(err_type) msg = traceback.format_exception(err_type, err_value, None) tb = traceback.format_exception(err_type, err_value, err_tb) return { 'type': typename, 'message': ''.join(msg), '': ''.join(tb), } def addError(self, test, err): self._add_result(test, True, error=self.__makeErrorDict(*err)) super().addError(test, err) self.__write('E', 'ERROR') def addExpectedFailure(self, test, err): self._add_result(test, True, output=self.__makeErrorDict(*err)) super().addExpectedFailure(test, err) self.__write('x', 'expected failure') def addFailure(self, test, err): self._add_result(test, True, failure=self.__makeErrorDict(*err)) super().addFailure(test, err) self.__write('F', 'FAIL') def addSkip(self, test, reason): self._add_result(test, skipped=reason) super().addSkip(test, reason) self.__write('S', 'skipped {!r}'.format(reason)) def addSuccess(self, test): self._add_result(test) super().addSuccess(test) self.__write('.', 'ok') def addUnexpectedSuccess(self, test): self._add_result(test, outcome='UNEXPECTED_SUCCESS') super().addUnexpectedSuccess(test) self.__write('u', 'unexpected success') def printErrors(self): if self.__verbose: self.stream.write('\n') self.printErrorList('ERROR', self.errors) self.printErrorList('FAIL', self.failures) def printErrorList(self, flavor, errors): for test, err in errors: self.stream.write(self.separator1) self.stream.write('{}: {}\n'.format(flavor, self.getDescription(test))) self.stream.write(self.separator2) self.stream.write('{}\n'.format(err)) def get_xml_element(self): e = self.__suite e.set('tests', str(self.testsRun)) e.set('errors', str(len(self.errors))) e.set('failures', str(len(self.failures))) return e class QuietRegressionTestRunner: def __init__(self, stream): self.result = RegressionTestResult(stream, None, 0) def run(self, test): test(self.result) return self.result def get_test_runner_class(verbosity): if verbosity: return functools.partial(unittest.TextTestRunner, resultclass=RegressionTestResult, buffer=True, verbosity=verbosity) return QuietRegressionTestRunner def get_test_runner(stream, verbosity): return get_test_runner_class(verbosity)(stream) if __name__ == '__main__': class TestTests(unittest.TestCase): def test_pass(self): pass def test_pass_slow(self): time.sleep(1.0) def test_fail(self): print('stdout', file=sys.stdout) print('stderr', file=sys.stderr) self.fail('failure message') def test_error(self): print('stdout', file=sys.stdout) print('stderr', file=sys.stderr) raise RuntimeError('error message') suite = unittest.TestSuite() suite.addTest(unittest.makeSuite(TestTests)) stream = io.StringIO() runner_cls = get_test_runner_class(sum(a == '-v' for a in sys.argv)) runner = runner_cls(sys.stdout) result = runner.run(suite) print('Output:', stream.getvalue()) print('XML: ', end='') for s in ET.tostringlist(result.get_xml_element()): print(s.decode(), end='') print() pyzipper-0.4.0/test/test_support.py000066400000000000000000000522101520124366100175010ustar00rootroot00000000000000import contextlib import errno import importlib import io import os import shutil import socket import stat import subprocess import sys import tempfile import textwrap import time import unittest from test import support from test.support import script_helper TESTFN = support.TESTFN class TestSupport(unittest.TestCase): def test_import_module(self): support.import_module("ftplib") self.assertRaises(unittest.SkipTest, support.import_module, "foo") def test_import_fresh_module(self): support.import_fresh_module("ftplib") def test_get_attribute(self): self.assertEqual(support.get_attribute(self, "test_get_attribute"), self.test_get_attribute) self.assertRaises(unittest.SkipTest, support.get_attribute, self, "foo") @unittest.skip("failing buildbots") def test_get_original_stdout(self): self.assertEqual(support.get_original_stdout(), sys.stdout) def test_unload(self): import sched self.assertIn("sched", sys.modules) support.unload("sched") self.assertNotIn("sched", sys.modules) def test_unlink(self): with open(TESTFN, "w") as f: pass support.unlink(TESTFN) self.assertFalse(os.path.exists(TESTFN)) support.unlink(TESTFN) def test_rmtree(self): dirpath = support.TESTFN + 'd' subdirpath = os.path.join(dirpath, 'subdir') os.mkdir(dirpath) os.mkdir(subdirpath) support.rmtree(dirpath) self.assertFalse(os.path.exists(dirpath)) with support.swap_attr(support, 'verbose', 0): support.rmtree(dirpath) os.mkdir(dirpath) os.mkdir(subdirpath) os.chmod(dirpath, stat.S_IRUSR|stat.S_IXUSR) with support.swap_attr(support, 'verbose', 0): support.rmtree(dirpath) self.assertFalse(os.path.exists(dirpath)) os.mkdir(dirpath) os.mkdir(subdirpath) os.chmod(dirpath, 0) with support.swap_attr(support, 'verbose', 0): support.rmtree(dirpath) self.assertFalse(os.path.exists(dirpath)) def test_forget(self): mod_filename = TESTFN + '.py' with open(mod_filename, 'w') as f: print('foo = 1', file=f) sys.path.insert(0, os.curdir) importlib.invalidate_caches() try: mod = __import__(TESTFN) self.assertIn(TESTFN, sys.modules) support.forget(TESTFN) self.assertNotIn(TESTFN, sys.modules) finally: del sys.path[0] support.unlink(mod_filename) support.rmtree('__pycache__') def test_HOST(self): s = socket.socket() s.bind((support.HOST, 0)) s.close() def test_find_unused_port(self): port = support.find_unused_port() s = socket.socket() s.bind((support.HOST, port)) s.close() def test_bind_port(self): s = socket.socket() support.bind_port(s) s.listen() s.close() # Tests for temp_dir() def test_temp_dir(self): """Test that temp_dir() creates and destroys its directory.""" parent_dir = tempfile.mkdtemp() parent_dir = os.path.realpath(parent_dir) try: path = os.path.join(parent_dir, 'temp') self.assertFalse(os.path.isdir(path)) with support.temp_dir(path) as temp_path: self.assertEqual(temp_path, path) self.assertTrue(os.path.isdir(path)) self.assertFalse(os.path.isdir(path)) finally: support.rmtree(parent_dir) def test_temp_dir__path_none(self): """Test passing no path.""" with support.temp_dir() as temp_path: self.assertTrue(os.path.isdir(temp_path)) self.assertFalse(os.path.isdir(temp_path)) def test_temp_dir__existing_dir__quiet_default(self): """Test passing a directory that already exists.""" def call_temp_dir(path): with support.temp_dir(path) as temp_path: raise Exception("should not get here") path = tempfile.mkdtemp() path = os.path.realpath(path) try: self.assertTrue(os.path.isdir(path)) self.assertRaises(FileExistsError, call_temp_dir, path) # Make sure temp_dir did not delete the original directory. self.assertTrue(os.path.isdir(path)) finally: shutil.rmtree(path) def test_temp_dir__existing_dir__quiet_true(self): """Test passing a directory that already exists with quiet=True.""" path = tempfile.mkdtemp() path = os.path.realpath(path) try: with support.check_warnings() as recorder: with support.temp_dir(path, quiet=True) as temp_path: self.assertEqual(path, temp_path) warnings = [str(w.message) for w in recorder.warnings] # Make sure temp_dir did not delete the original directory. self.assertTrue(os.path.isdir(path)) finally: shutil.rmtree(path) self.assertEqual(len(warnings), 1, warnings) warn = warnings[0] self.assertTrue(warn.startswith('tests may fail, unable to create ' 'temporary directory {!r}: '.format(path)), warn) @unittest.skipUnless(hasattr(os, "fork"), "test requires os.fork") def test_temp_dir__forked_child(self): """Test that a forked child process does not remove the directory.""" # See bpo-30028 for details. # Run the test as an external script, because it uses fork. script_helper.assert_python_ok("-c", textwrap.dedent(""" import os from test import support with support.temp_cwd() as temp_path: pid = os.fork() if pid != 0: # parent process (child has pid == 0) # wait for the child to terminate (pid, status) = os.waitpid(pid, 0) if status != 0: raise AssertionError(f"Child process failed with exit " f"status indication 0x{status:x}.") # Make sure that temp_path is still present. When the child # process leaves the 'temp_cwd'-context, the __exit__()- # method of the context must not remove the temporary # directory. if not os.path.isdir(temp_path): raise AssertionError("Child removed temp_path.") """)) # Tests for change_cwd() def test_change_cwd(self): original_cwd = os.getcwd() with support.temp_dir() as temp_path: with support.change_cwd(temp_path) as new_cwd: self.assertEqual(new_cwd, temp_path) self.assertEqual(os.getcwd(), new_cwd) self.assertEqual(os.getcwd(), original_cwd) def test_change_cwd__non_existent_dir(self): """Test passing a non-existent directory.""" original_cwd = os.getcwd() def call_change_cwd(path): with support.change_cwd(path) as new_cwd: raise Exception("should not get here") with support.temp_dir() as parent_dir: non_existent_dir = os.path.join(parent_dir, 'does_not_exist') self.assertRaises(FileNotFoundError, call_change_cwd, non_existent_dir) self.assertEqual(os.getcwd(), original_cwd) def test_change_cwd__non_existent_dir__quiet_true(self): """Test passing a non-existent directory with quiet=True.""" original_cwd = os.getcwd() with support.temp_dir() as parent_dir: bad_dir = os.path.join(parent_dir, 'does_not_exist') with support.check_warnings() as recorder: with support.change_cwd(bad_dir, quiet=True) as new_cwd: self.assertEqual(new_cwd, original_cwd) self.assertEqual(os.getcwd(), new_cwd) warnings = [str(w.message) for w in recorder.warnings] self.assertEqual(len(warnings), 1, warnings) warn = warnings[0] self.assertTrue(warn.startswith('tests may fail, unable to change ' 'the current working directory ' 'to {!r}: '.format(bad_dir)), warn) # Tests for change_cwd() def test_change_cwd__chdir_warning(self): """Check the warning message when os.chdir() fails.""" path = TESTFN + '_does_not_exist' with support.check_warnings() as recorder: with support.change_cwd(path=path, quiet=True): pass messages = [str(w.message) for w in recorder.warnings] self.assertEqual(len(messages), 1, messages) msg = messages[0] self.assertTrue(msg.startswith('tests may fail, unable to change ' 'the current working directory ' 'to {!r}: '.format(path)), msg) # Tests for temp_cwd() def test_temp_cwd(self): here = os.getcwd() with support.temp_cwd(name=TESTFN): self.assertEqual(os.path.basename(os.getcwd()), TESTFN) self.assertFalse(os.path.exists(TESTFN)) self.assertEqual(os.getcwd(), here) def test_temp_cwd__name_none(self): """Test passing None to temp_cwd().""" original_cwd = os.getcwd() with support.temp_cwd(name=None) as new_cwd: self.assertNotEqual(new_cwd, original_cwd) self.assertTrue(os.path.isdir(new_cwd)) self.assertEqual(os.getcwd(), new_cwd) self.assertEqual(os.getcwd(), original_cwd) def test_sortdict(self): self.assertEqual(support.sortdict({3:3, 2:2, 1:1}), "{1: 1, 2: 2, 3: 3}") def test_make_bad_fd(self): fd = support.make_bad_fd() with self.assertRaises(OSError) as cm: os.write(fd, b"foo") self.assertEqual(cm.exception.errno, errno.EBADF) def test_check_syntax_error(self): support.check_syntax_error(self, "def class", lineno=1, offset=5) with self.assertRaises(AssertionError): support.check_syntax_error(self, "x=1") def test_CleanImport(self): import importlib with support.CleanImport("asyncore"): importlib.import_module("asyncore") def test_DirsOnSysPath(self): with support.DirsOnSysPath('foo', 'bar'): self.assertIn("foo", sys.path) self.assertIn("bar", sys.path) self.assertNotIn("foo", sys.path) self.assertNotIn("bar", sys.path) def test_captured_stdout(self): with support.captured_stdout() as stdout: print("hello") self.assertEqual(stdout.getvalue(), "hello\n") def test_captured_stderr(self): with support.captured_stderr() as stderr: print("hello", file=sys.stderr) self.assertEqual(stderr.getvalue(), "hello\n") def test_captured_stdin(self): with support.captured_stdin() as stdin: stdin.write('hello\n') stdin.seek(0) # call test code that consumes from sys.stdin captured = input() self.assertEqual(captured, "hello") def test_gc_collect(self): support.gc_collect() def test_python_is_optimized(self): self.assertIsInstance(support.python_is_optimized(), bool) def test_swap_attr(self): class Obj: pass obj = Obj() obj.x = 1 with support.swap_attr(obj, "x", 5) as x: self.assertEqual(obj.x, 5) self.assertEqual(x, 1) self.assertEqual(obj.x, 1) with support.swap_attr(obj, "y", 5) as y: self.assertEqual(obj.y, 5) self.assertIsNone(y) self.assertFalse(hasattr(obj, 'y')) with support.swap_attr(obj, "y", 5): del obj.y self.assertFalse(hasattr(obj, 'y')) def test_swap_item(self): D = {"x":1} with support.swap_item(D, "x", 5) as x: self.assertEqual(D["x"], 5) self.assertEqual(x, 1) self.assertEqual(D["x"], 1) with support.swap_item(D, "y", 5) as y: self.assertEqual(D["y"], 5) self.assertIsNone(y) self.assertNotIn("y", D) with support.swap_item(D, "y", 5): del D["y"] self.assertNotIn("y", D) class RefClass: attribute1 = None attribute2 = None _hidden_attribute1 = None __magic_1__ = None class OtherClass: attribute2 = None attribute3 = None __magic_1__ = None __magic_2__ = None def test_detect_api_mismatch(self): missing_items = support.detect_api_mismatch(self.RefClass, self.OtherClass) self.assertEqual({'attribute1'}, missing_items) missing_items = support.detect_api_mismatch(self.OtherClass, self.RefClass) self.assertEqual({'attribute3', '__magic_2__'}, missing_items) def test_detect_api_mismatch__ignore(self): ignore = ['attribute1', 'attribute3', '__magic_2__', 'not_in_either'] missing_items = support.detect_api_mismatch( self.RefClass, self.OtherClass, ignore=ignore) self.assertEqual(set(), missing_items) missing_items = support.detect_api_mismatch( self.OtherClass, self.RefClass, ignore=ignore) self.assertEqual(set(), missing_items) def test_check__all__(self): extra = {'tempdir'} blacklist = {'template'} support.check__all__(self, tempfile, extra=extra, blacklist=blacklist) extra = {'TextTestResult', 'installHandler'} blacklist = {'load_tests', "TestProgram", "BaseTestSuite"} support.check__all__(self, unittest, ("unittest.result", "unittest.case", "unittest.suite", "unittest.loader", "unittest.main", "unittest.runner", "unittest.signals"), extra=extra, blacklist=blacklist) self.assertRaises(AssertionError, support.check__all__, self, unittest) @unittest.skipUnless(hasattr(os, 'waitpid') and hasattr(os, 'WNOHANG'), 'need os.waitpid() and os.WNOHANG') def test_reap_children(self): # Make sure that there is no other pending child process support.reap_children() # Create a child process pid = os.fork() if pid == 0: # child process: do nothing, just exit os._exit(0) t0 = time.monotonic() deadline = time.monotonic() + 60.0 was_altered = support.environment_altered try: support.environment_altered = False stderr = io.StringIO() while True: if time.monotonic() > deadline: self.fail("timeout") with contextlib.redirect_stderr(stderr): support.reap_children() # Use environment_altered to check if reap_children() found # the child process if support.environment_altered: break # loop until the child process completed time.sleep(0.100) msg = "Warning -- reap_children() reaped child process %s" % pid self.assertIn(msg, stderr.getvalue()) self.assertTrue(support.environment_altered) finally: support.environment_altered = was_altered # Just in case, check again that there is no other # pending child process support.reap_children() def check_options(self, args, func): code = 'from test.support import {}; print(repr({}()))'.format(func, func) cmd = [sys.executable, *args, '-c', code] env = {key: value for key, value in os.environ.items() if not key.startswith('PYTHON')} proc = subprocess.run(cmd, stdout=subprocess.PIPE, stderr=subprocess.DEVNULL, universal_newlines=True, env=env) self.assertEqual(proc.stdout.rstrip(), repr(args)) self.assertEqual(proc.returncode, 0) def test_args_from_interpreter_flags(self): # Test test.support.args_from_interpreter_flags() for opts in ( # no option [], # single option ['-B'], ['-s'], ['-S'], ['-E'], ['-v'], ['-b'], ['-q'], # same option multiple times ['-bb'], ['-vvv'], # -W options ['-Wignore'], # -X options ['-X', 'dev'], ['-Wignore', '-X', 'dev'], ['-X', 'faulthandler'], ['-X', 'importtime'], ['-X', 'showalloccount'], ['-X', 'showrefcount'], ['-X', 'tracemalloc'], ['-X', 'tracemalloc=3'], ): with self.subTest(opts=opts): self.check_options(opts, 'args_from_interpreter_flags') def test_optim_args_from_interpreter_flags(self): # Test test.support.optim_args_from_interpreter_flags() for opts in ( # no option [], ['-O'], ['-OO'], ['-OOOO'], ): with self.subTest(opts=opts): self.check_options(opts, 'optim_args_from_interpreter_flags') def test_match_test(self): class Test: def __init__(self, test_id): self.test_id = test_id def id(self): return self.test_id test_access = Test('test.test_os.FileTests.test_access') test_chdir = Test('test.test_os.Win32ErrorTests.test_chdir') with support.swap_attr(support, '_match_test_func', None): # match all support.set_match_tests([]) self.assertTrue(support.match_test(test_access)) self.assertTrue(support.match_test(test_chdir)) # match all using None support.set_match_tests(None) self.assertTrue(support.match_test(test_access)) self.assertTrue(support.match_test(test_chdir)) # match the full test identifier support.set_match_tests([test_access.id()]) self.assertTrue(support.match_test(test_access)) self.assertFalse(support.match_test(test_chdir)) # match the module name support.set_match_tests(['test_os']) self.assertTrue(support.match_test(test_access)) self.assertTrue(support.match_test(test_chdir)) # Test '*' pattern support.set_match_tests(['test_*']) self.assertTrue(support.match_test(test_access)) self.assertTrue(support.match_test(test_chdir)) # Test case sensitivity support.set_match_tests(['filetests']) self.assertFalse(support.match_test(test_access)) support.set_match_tests(['FileTests']) self.assertTrue(support.match_test(test_access)) # Test pattern containing '.' and a '*' metacharacter support.set_match_tests(['*test_os.*.test_*']) self.assertTrue(support.match_test(test_access)) self.assertTrue(support.match_test(test_chdir)) # Multiple patterns support.set_match_tests([test_access.id(), test_chdir.id()]) self.assertTrue(support.match_test(test_access)) self.assertTrue(support.match_test(test_chdir)) support.set_match_tests(['test_access', 'DONTMATCH']) self.assertTrue(support.match_test(test_access)) self.assertFalse(support.match_test(test_chdir)) def test_fd_count(self): # We cannot test the absolute value of fd_count(): on old Linux # kernel or glibc versions, os.urandom() keeps a FD open on # /dev/urandom device and Python has 4 FD opens instead of 3. start = support.fd_count() fd = os.open(__file__, os.O_RDONLY) try: more = support.fd_count() finally: os.close(fd) self.assertEqual(more - start, 1) # XXX -follows a list of untested API # make_legacy_pyc # is_resource_enabled # requires # fcmp # umaks # findfile # check_warnings # EnvironmentVarGuard # TransientResource # transient_internet # run_with_locale # set_memlimit # bigmemtest # precisionbigmemtest # bigaddrspacetest # requires_resource # run_doctest # threading_cleanup # reap_threads # strip_python_stderr # can_symlink # skip_unless_symlink # SuppressCrashReport def test_main(): tests = [TestSupport] support.run_unittest(*tests) if __name__ == '__main__': test_main() pyzipper-0.4.0/test/test_zipfile.py000066400000000000000000003275611520124366100174450ustar00rootroot00000000000000import contextlib import io import itertools import os import sys import importlib.util import pathlib import posixpath import time import struct from pyzipper import zipfile import unittest from tempfile import TemporaryFile from random import randint, random, getrandbits from test.support import script_helper from test.support import (TESTFN, findfile, unlink, rmtree, temp_dir, temp_cwd, requires_zlib, requires_bz2, requires_lzma, captured_stdout) TESTFN2 = TESTFN + "2" TESTFNDIR = TESTFN + "d" FIXEDTEST_SIZE = 1000 DATAFILES_DIR = 'zipfile_datafiles' SMALL_TEST_DATA = [('_ziptest1', '1q2w3e4r5t'), ('ziptest2dir/_ziptest2', 'qawsedrftg'), ('ziptest2dir/ziptest3dir/_ziptest3', 'azsxdcfvgb'), ('ziptest2dir/ziptest3dir/ziptest4dir/_ziptest3', '6y7u8i9o0p')] def getrandbytes(size): return getrandbits(8 * size).to_bytes(size, 'little') def get_files(test): yield TESTFN2 with TemporaryFile() as f: yield f test.assertFalse(f.closed) with io.BytesIO() as f: yield f test.assertFalse(f.closed) class AbstractTestsWithSourceFile: @classmethod def setUpClass(cls): cls.line_gen = [bytes("Zipfile test line %d. random float: %f\n" % (i, random()), "ascii") for i in range(FIXEDTEST_SIZE)] cls.data = b''.join(cls.line_gen) def setUp(self): # Make a source file with some lines with open(TESTFN, "wb") as fp: fp.write(self.data) def make_test_archive(self, f, compression, compresslevel=None): kwargs = {'compression': compression, 'compresslevel': compresslevel} # Create the ZIP archive with zipfile.ZipFile(f, "w", **kwargs) as zipfp: zipfp.write(TESTFN, "another.name") zipfp.write(TESTFN, TESTFN) zipfp.writestr("strfile", self.data) with zipfp.open('written-open-w', mode='w') as f: for line in self.line_gen: f.write(line) def zip_test(self, f, compression, compresslevel=None): self.make_test_archive(f, compression, compresslevel) # Read the ZIP archive with zipfile.ZipFile(f, "r", compression) as zipfp: self.assertEqual(zipfp.read(TESTFN), self.data) self.assertEqual(zipfp.read("another.name"), self.data) self.assertEqual(zipfp.read("strfile"), self.data) # Print the ZIP directory fp = io.StringIO() zipfp.printdir(file=fp) directory = fp.getvalue() lines = directory.splitlines() self.assertEqual(len(lines), 5) # Number of files + header self.assertIn('File Name', lines[0]) self.assertIn('Modified', lines[0]) self.assertIn('Size', lines[0]) fn, date, time_, size = lines[1].split() self.assertEqual(fn, 'another.name') self.assertTrue(time.strptime(date, '%Y-%m-%d')) self.assertTrue(time.strptime(time_, '%H:%M:%S')) self.assertEqual(size, str(len(self.data))) # Check the namelist names = zipfp.namelist() self.assertEqual(len(names), 4) self.assertIn(TESTFN, names) self.assertIn("another.name", names) self.assertIn("strfile", names) self.assertIn("written-open-w", names) # Check infolist infos = zipfp.infolist() names = [i.filename for i in infos] self.assertEqual(len(names), 4) self.assertIn(TESTFN, names) self.assertIn("another.name", names) self.assertIn("strfile", names) self.assertIn("written-open-w", names) for i in infos: self.assertEqual(i.file_size, len(self.data)) # check getinfo for nm in (TESTFN, "another.name", "strfile", "written-open-w"): info = zipfp.getinfo(nm) self.assertEqual(info.filename, nm) self.assertEqual(info.file_size, len(self.data)) # Check that testzip doesn't raise an exception zipfp.testzip() def test_basic(self): for f in get_files(self): self.zip_test(f, self.compression) def zip_open_test(self, f, compression): self.make_test_archive(f, compression) # Read the ZIP archive with zipfile.ZipFile(f, "r", compression) as zipfp: zipdata1 = [] with zipfp.open(TESTFN) as zipopen1: while True: read_data = zipopen1.read(256) if not read_data: break zipdata1.append(read_data) zipdata2 = [] with zipfp.open("another.name") as zipopen2: while True: read_data = zipopen2.read(256) if not read_data: break zipdata2.append(read_data) self.assertEqual(b''.join(zipdata1), self.data) self.assertEqual(b''.join(zipdata2), self.data) def test_open(self): for f in get_files(self): self.zip_open_test(f, self.compression) def test_open_with_pathlike(self): path = pathlib.Path(TESTFN2) self.zip_open_test(path, self.compression) with zipfile.ZipFile(path, "r", self.compression) as zipfp: self.assertIsInstance(zipfp.filename, str) def zip_random_open_test(self, f, compression): self.make_test_archive(f, compression) # Read the ZIP archive with zipfile.ZipFile(f, "r", compression) as zipfp: zipdata1 = [] with zipfp.open(TESTFN) as zipopen1: while True: read_data = zipopen1.read(randint(1, 1024)) if not read_data: break zipdata1.append(read_data) self.assertEqual(b''.join(zipdata1), self.data) def test_random_open(self): for f in get_files(self): self.zip_random_open_test(f, self.compression) def zip_read1_test(self, f, compression): self.make_test_archive(f, compression) # Read the ZIP archive with zipfile.ZipFile(f, "r") as zipfp, \ zipfp.open(TESTFN) as zipopen: zipdata = [] while True: read_data = zipopen.read1(-1) if not read_data: break zipdata.append(read_data) self.assertEqual(b''.join(zipdata), self.data) def test_read1(self): for f in get_files(self): self.zip_read1_test(f, self.compression) def zip_read1_10_test(self, f, compression): self.make_test_archive(f, compression) # Read the ZIP archive with zipfile.ZipFile(f, "r") as zipfp, \ zipfp.open(TESTFN) as zipopen: zipdata = [] while True: read_data = zipopen.read1(10) self.assertLessEqual(len(read_data), 10) if not read_data: break zipdata.append(read_data) self.assertEqual(b''.join(zipdata), self.data) def test_read1_10(self): for f in get_files(self): self.zip_read1_10_test(f, self.compression) def zip_readline_read_test(self, f, compression): self.make_test_archive(f, compression) # Read the ZIP archive with zipfile.ZipFile(f, "r") as zipfp, \ zipfp.open(TESTFN) as zipopen: data = b'' while True: read = zipopen.readline() if not read: break data += read read = zipopen.read(100) if not read: break data += read self.assertEqual(data, self.data) def test_readline_read(self): # Issue #7610: calls to readline() interleaved with calls to read(). for f in get_files(self): self.zip_readline_read_test(f, self.compression) def zip_readline_test(self, f, compression): self.make_test_archive(f, compression) # Read the ZIP archive with zipfile.ZipFile(f, "r") as zipfp: with zipfp.open(TESTFN) as zipopen: for line in self.line_gen: linedata = zipopen.readline() self.assertEqual(linedata, line) def test_readline(self): for f in get_files(self): self.zip_readline_test(f, self.compression) def zip_readlines_test(self, f, compression): self.make_test_archive(f, compression) # Read the ZIP archive with zipfile.ZipFile(f, "r") as zipfp: with zipfp.open(TESTFN) as zipopen: ziplines = zipopen.readlines() for line, zipline in zip(self.line_gen, ziplines): self.assertEqual(zipline, line) def test_readlines(self): for f in get_files(self): self.zip_readlines_test(f, self.compression) def zip_iterlines_test(self, f, compression): self.make_test_archive(f, compression) # Read the ZIP archive with zipfile.ZipFile(f, "r") as zipfp: with zipfp.open(TESTFN) as zipopen: for line, zipline in zip(self.line_gen, zipopen): self.assertEqual(zipline, line) def test_iterlines(self): for f in get_files(self): self.zip_iterlines_test(f, self.compression) def test_low_compression(self): """Check for cases where compressed data is larger than original.""" # Create the ZIP archive with zipfile.ZipFile(TESTFN2, "w", self.compression) as zipfp: zipfp.writestr("strfile", '12') # Get an open object for strfile with zipfile.ZipFile(TESTFN2, "r", self.compression) as zipfp: with zipfp.open("strfile") as openobj: self.assertEqual(openobj.read(1), b'1') self.assertEqual(openobj.read(1), b'2') def test_writestr_compression(self): zipfp = zipfile.ZipFile(TESTFN2, "w") zipfp.writestr("b.txt", "hello world", compress_type=self.compression) info = zipfp.getinfo('b.txt') self.assertEqual(info.compress_type, self.compression) def test_writestr_compresslevel(self): zipfp = zipfile.ZipFile(TESTFN2, "w", compresslevel=1) zipfp.writestr("a.txt", "hello world", compress_type=self.compression) zipfp.writestr("b.txt", "hello world", compress_type=self.compression, compresslevel=2) # Compression level follows the constructor. a_info = zipfp.getinfo('a.txt') self.assertEqual(a_info.compress_type, self.compression) self.assertEqual(a_info._compresslevel, 1) # Compression level is overridden. b_info = zipfp.getinfo('b.txt') self.assertEqual(b_info.compress_type, self.compression) self.assertEqual(b_info._compresslevel, 2) def test_read_return_size(self): # Issue #9837: ZipExtFile.read() shouldn't return more bytes # than requested. for test_size in (1, 4095, 4096, 4097, 16384): file_size = test_size + 1 junk = getrandbytes(file_size) with zipfile.ZipFile(io.BytesIO(), "w", self.compression) as zipf: zipf.writestr('foo', junk) with zipf.open('foo', 'r') as fp: buf = fp.read(test_size) self.assertEqual(len(buf), test_size) def test_truncated_zipfile(self): fp = io.BytesIO() with zipfile.ZipFile(fp, mode='w') as zipf: zipf.writestr('strfile', self.data, compress_type=self.compression) end_offset = fp.tell() zipfiledata = fp.getvalue() fp = io.BytesIO(zipfiledata) with zipfile.ZipFile(fp) as zipf: with zipf.open('strfile') as zipopen: fp.truncate(end_offset - 20) with self.assertRaises(EOFError): zipopen.read() fp = io.BytesIO(zipfiledata) with zipfile.ZipFile(fp) as zipf: with zipf.open('strfile') as zipopen: fp.truncate(end_offset - 20) with self.assertRaises(EOFError): while zipopen.read(100): pass fp = io.BytesIO(zipfiledata) with zipfile.ZipFile(fp) as zipf: with zipf.open('strfile') as zipopen: fp.truncate(end_offset - 20) with self.assertRaises(EOFError): while zipopen.read1(100): pass def test_repr(self): fname = 'file.name' for f in get_files(self): with zipfile.ZipFile(f, 'w', self.compression) as zipfp: zipfp.write(TESTFN, fname) r = repr(zipfp) self.assertIn("mode='w'", r) with zipfile.ZipFile(f, 'r') as zipfp: r = repr(zipfp) if isinstance(f, str): self.assertIn('filename=%r' % f, r) else: self.assertIn('file=%r' % f, r) self.assertIn("mode='r'", r) r = repr(zipfp.getinfo(fname)) self.assertIn('filename=%r' % fname, r) self.assertIn('filemode=', r) self.assertIn('file_size=', r) if self.compression != zipfile.ZIP_STORED: self.assertIn('compress_type=', r) self.assertIn('compress_size=', r) with zipfp.open(fname) as zipopen: r = repr(zipopen) self.assertIn('name=%r' % fname, r) self.assertIn("mode='r'", r) if self.compression != zipfile.ZIP_STORED: self.assertIn('compress_type=', r) self.assertIn('[closed]', repr(zipopen)) self.assertIn('[closed]', repr(zipfp)) def test_compresslevel_basic(self): for f in get_files(self): self.zip_test(f, self.compression, compresslevel=9) def test_per_file_compresslevel(self): """Check that files within a Zip archive can have different compression levels.""" with zipfile.ZipFile(TESTFN2, "w", compresslevel=1) as zipfp: zipfp.write(TESTFN, 'compress_1') zipfp.write(TESTFN, 'compress_9', compresslevel=9) one_info = zipfp.getinfo('compress_1') nine_info = zipfp.getinfo('compress_9') self.assertEqual(one_info._compresslevel, 1) self.assertEqual(nine_info._compresslevel, 9) def tearDown(self): unlink(TESTFN) unlink(TESTFN2) class StoredTestsWithSourceFile(AbstractTestsWithSourceFile, unittest.TestCase): compression = zipfile.ZIP_STORED test_low_compression = None def zip_test_writestr_permissions(self, f, compression): # Make sure that writestr and open(... mode='w') create files with # mode 0600, when they are passed a name rather than a ZipInfo # instance. self.make_test_archive(f, compression) with zipfile.ZipFile(f, "r") as zipfp: zinfo = zipfp.getinfo('strfile') self.assertEqual(zinfo.external_attr, 0o600 << 16) zinfo2 = zipfp.getinfo('written-open-w') self.assertEqual(zinfo2.external_attr, 0o600 << 16) def test_writestr_permissions(self): for f in get_files(self): self.zip_test_writestr_permissions(f, zipfile.ZIP_STORED) def test_absolute_arcnames(self): with zipfile.ZipFile(TESTFN2, "w", zipfile.ZIP_STORED) as zipfp: zipfp.write(TESTFN, "/absolute") with zipfile.ZipFile(TESTFN2, "r", zipfile.ZIP_STORED) as zipfp: self.assertEqual(zipfp.namelist(), ["absolute"]) def test_append_to_zip_file(self): """Test appending to an existing zipfile.""" with zipfile.ZipFile(TESTFN2, "w", zipfile.ZIP_STORED) as zipfp: zipfp.write(TESTFN, TESTFN) with zipfile.ZipFile(TESTFN2, "a", zipfile.ZIP_STORED) as zipfp: zipfp.writestr("strfile", self.data) self.assertEqual(zipfp.namelist(), [TESTFN, "strfile"]) def test_append_to_non_zip_file(self): """Test appending to an existing file that is not a zipfile.""" # NOTE: this test fails if len(d) < 22 because of the first # line "fpin.seek(-22, 2)" in _EndRecData data = b'I am not a ZipFile!'*10 with open(TESTFN2, 'wb') as f: f.write(data) with zipfile.ZipFile(TESTFN2, "a", zipfile.ZIP_STORED) as zipfp: zipfp.write(TESTFN, TESTFN) with open(TESTFN2, 'rb') as f: f.seek(len(data)) with zipfile.ZipFile(f, "r") as zipfp: self.assertEqual(zipfp.namelist(), [TESTFN]) self.assertEqual(zipfp.read(TESTFN), self.data) with open(TESTFN2, 'rb') as f: self.assertEqual(f.read(len(data)), data) zipfiledata = f.read() with io.BytesIO(zipfiledata) as bio, zipfile.ZipFile(bio) as zipfp: self.assertEqual(zipfp.namelist(), [TESTFN]) self.assertEqual(zipfp.read(TESTFN), self.data) def test_read_concatenated_zip_file(self): with io.BytesIO() as bio: with zipfile.ZipFile(bio, 'w', zipfile.ZIP_STORED) as zipfp: zipfp.write(TESTFN, TESTFN) zipfiledata = bio.getvalue() data = b'I am not a ZipFile!'*10 with open(TESTFN2, 'wb') as f: f.write(data) f.write(zipfiledata) with zipfile.ZipFile(TESTFN2) as zipfp: self.assertEqual(zipfp.namelist(), [TESTFN]) self.assertEqual(zipfp.read(TESTFN), self.data) def test_append_to_concatenated_zip_file(self): with io.BytesIO() as bio: with zipfile.ZipFile(bio, 'w', zipfile.ZIP_STORED) as zipfp: zipfp.write(TESTFN, TESTFN) zipfiledata = bio.getvalue() data = b'I am not a ZipFile!'*1000000 with open(TESTFN2, 'wb') as f: f.write(data) f.write(zipfiledata) with zipfile.ZipFile(TESTFN2, 'a') as zipfp: self.assertEqual(zipfp.namelist(), [TESTFN]) zipfp.writestr('strfile', self.data) with open(TESTFN2, 'rb') as f: self.assertEqual(f.read(len(data)), data) zipfiledata = f.read() with io.BytesIO(zipfiledata) as bio, zipfile.ZipFile(bio) as zipfp: self.assertEqual(zipfp.namelist(), [TESTFN, 'strfile']) self.assertEqual(zipfp.read(TESTFN), self.data) self.assertEqual(zipfp.read('strfile'), self.data) def test_ignores_newline_at_end(self): with zipfile.ZipFile(TESTFN2, "w", zipfile.ZIP_STORED) as zipfp: zipfp.write(TESTFN, TESTFN) with open(TESTFN2, 'a') as f: f.write("\r\n\00\00\00") with zipfile.ZipFile(TESTFN2, "r") as zipfp: self.assertIsInstance(zipfp, zipfile.ZipFile) def test_ignores_stuff_appended_past_comments(self): with zipfile.ZipFile(TESTFN2, "w", zipfile.ZIP_STORED) as zipfp: zipfp.comment = b"this is a comment" zipfp.write(TESTFN, TESTFN) with open(TESTFN2, 'a') as f: f.write("abcdef\r\n") with zipfile.ZipFile(TESTFN2, "r") as zipfp: self.assertIsInstance(zipfp, zipfile.ZipFile) self.assertEqual(zipfp.comment, b"this is a comment") def test_write_default_name(self): """Check that calling ZipFile.write without arcname specified produces the expected result.""" with zipfile.ZipFile(TESTFN2, "w") as zipfp: zipfp.write(TESTFN) with open(TESTFN, "rb") as f: self.assertEqual(zipfp.read(TESTFN), f.read()) def test_write_to_readonly(self): """Check that trying to call write() on a readonly ZipFile object raises a ValueError.""" with zipfile.ZipFile(TESTFN2, mode="w") as zipfp: zipfp.writestr("somefile.txt", "bogus") with zipfile.ZipFile(TESTFN2, mode="r") as zipfp: self.assertRaises(ValueError, zipfp.write, TESTFN) with zipfile.ZipFile(TESTFN2, mode="r") as zipfp: with self.assertRaises(ValueError): zipfp.open(TESTFN, mode='w') def test_add_file_before_1980(self): # Set atime and mtime to 1970-01-01 os.utime(TESTFN, (0, 0)) with zipfile.ZipFile(TESTFN2, "w") as zipfp: self.assertRaises(ValueError, zipfp.write, TESTFN) with zipfile.ZipFile(TESTFN2, "w", strict_timestamps=False) as zipfp: zipfp.write(TESTFN) zinfo = zipfp.getinfo(TESTFN) self.assertEqual(zinfo.date_time, (1980, 1, 1, 0, 0, 0)) def test_add_file_after_2107(self): # Set atime and mtime to 2108-12-30 try: os.utime(TESTFN, (4386268800, 4386268800)) except OverflowError: self.skipTest('Host fs cannot set timestamp to required value.') with zipfile.ZipFile(TESTFN2, "w") as zipfp: self.assertRaises(struct.error, zipfp.write, TESTFN) with zipfile.ZipFile(TESTFN2, "w", strict_timestamps=False) as zipfp: zipfp.write(TESTFN) zinfo = zipfp.getinfo(TESTFN) self.assertEqual(zinfo.date_time, (2107, 12, 31, 23, 59, 59)) @requires_zlib class DeflateTestsWithSourceFile(AbstractTestsWithSourceFile, unittest.TestCase): compression = zipfile.ZIP_DEFLATED def test_per_file_compression(self): """Check that files within a Zip archive can have different compression options.""" with zipfile.ZipFile(TESTFN2, "w") as zipfp: zipfp.write(TESTFN, 'storeme', zipfile.ZIP_STORED) zipfp.write(TESTFN, 'deflateme', zipfile.ZIP_DEFLATED) sinfo = zipfp.getinfo('storeme') dinfo = zipfp.getinfo('deflateme') self.assertEqual(sinfo.compress_type, zipfile.ZIP_STORED) self.assertEqual(dinfo.compress_type, zipfile.ZIP_DEFLATED) @requires_bz2 class Bzip2TestsWithSourceFile(AbstractTestsWithSourceFile, unittest.TestCase): compression = zipfile.ZIP_BZIP2 @requires_lzma class LzmaTestsWithSourceFile(AbstractTestsWithSourceFile, unittest.TestCase): compression = zipfile.ZIP_LZMA class AbstractTestZip64InSmallFiles: # These tests test the ZIP64 functionality without using large files, # see test_zipfile64 for proper tests. @classmethod def setUpClass(cls): line_gen = (bytes("Test of zipfile line %d." % i, "ascii") for i in range(0, FIXEDTEST_SIZE)) cls.data = b'\n'.join(line_gen) def setUp(self): self._limit = zipfile.ZIP64_LIMIT self._filecount_limit = zipfile.ZIP_FILECOUNT_LIMIT zipfile.ZIP64_LIMIT = 1000 zipfile.ZIP_FILECOUNT_LIMIT = 9 # Make a source file with some lines with open(TESTFN, "wb") as fp: fp.write(self.data) def zip_test(self, f, compression): # Create the ZIP archive with zipfile.ZipFile(f, "w", compression, allowZip64=True) as zipfp: zipfp.write(TESTFN, "another.name") zipfp.write(TESTFN, TESTFN) zipfp.writestr("strfile", self.data) # Read the ZIP archive with zipfile.ZipFile(f, "r", compression) as zipfp: self.assertEqual(zipfp.read(TESTFN), self.data) self.assertEqual(zipfp.read("another.name"), self.data) self.assertEqual(zipfp.read("strfile"), self.data) # Print the ZIP directory fp = io.StringIO() zipfp.printdir(fp) directory = fp.getvalue() lines = directory.splitlines() self.assertEqual(len(lines), 4) # Number of files + header self.assertIn('File Name', lines[0]) self.assertIn('Modified', lines[0]) self.assertIn('Size', lines[0]) fn, date, time_, size = lines[1].split() self.assertEqual(fn, 'another.name') self.assertTrue(time.strptime(date, '%Y-%m-%d')) self.assertTrue(time.strptime(time_, '%H:%M:%S')) self.assertEqual(size, str(len(self.data))) # Check the namelist names = zipfp.namelist() self.assertEqual(len(names), 3) self.assertIn(TESTFN, names) self.assertIn("another.name", names) self.assertIn("strfile", names) # Check infolist infos = zipfp.infolist() names = [i.filename for i in infos] self.assertEqual(len(names), 3) self.assertIn(TESTFN, names) self.assertIn("another.name", names) self.assertIn("strfile", names) for i in infos: self.assertEqual(i.file_size, len(self.data)) # check getinfo for nm in (TESTFN, "another.name", "strfile"): info = zipfp.getinfo(nm) self.assertEqual(info.filename, nm) self.assertEqual(info.file_size, len(self.data)) # Check that testzip doesn't raise an exception zipfp.testzip() def test_basic(self): for f in get_files(self): self.zip_test(f, self.compression) def test_too_many_files(self): # This test checks that more than 64k files can be added to an archive, # and that the resulting archive can be read properly by ZipFile zipf = zipfile.ZipFile(TESTFN, "w", self.compression, allowZip64=True) zipf.debug = 100 numfiles = 15 for i in range(numfiles): zipf.writestr("foo%08d" % i, "%d" % (i**3 % 57)) self.assertEqual(len(zipf.namelist()), numfiles) zipf.close() zipf2 = zipfile.ZipFile(TESTFN, "r", self.compression) self.assertEqual(len(zipf2.namelist()), numfiles) for i in range(numfiles): content = zipf2.read("foo%08d" % i).decode('ascii') self.assertEqual(content, "%d" % (i**3 % 57)) zipf2.close() def test_too_many_files_append(self): zipf = zipfile.ZipFile(TESTFN, "w", self.compression, allowZip64=False) zipf.debug = 100 numfiles = 9 for i in range(numfiles): zipf.writestr("foo%08d" % i, "%d" % (i**3 % 57)) self.assertEqual(len(zipf.namelist()), numfiles) with self.assertRaises(zipfile.LargeZipFile): zipf.writestr("foo%08d" % numfiles, b'') self.assertEqual(len(zipf.namelist()), numfiles) zipf.close() zipf = zipfile.ZipFile(TESTFN, "a", self.compression, allowZip64=False) zipf.debug = 100 self.assertEqual(len(zipf.namelist()), numfiles) with self.assertRaises(zipfile.LargeZipFile): zipf.writestr("foo%08d" % numfiles, b'') self.assertEqual(len(zipf.namelist()), numfiles) zipf.close() zipf = zipfile.ZipFile(TESTFN, "a", self.compression, allowZip64=True) zipf.debug = 100 self.assertEqual(len(zipf.namelist()), numfiles) numfiles2 = 15 for i in range(numfiles, numfiles2): zipf.writestr("foo%08d" % i, "%d" % (i**3 % 57)) self.assertEqual(len(zipf.namelist()), numfiles2) zipf.close() zipf2 = zipfile.ZipFile(TESTFN, "r", self.compression) self.assertEqual(len(zipf2.namelist()), numfiles2) for i in range(numfiles2): content = zipf2.read("foo%08d" % i).decode('ascii') self.assertEqual(content, "%d" % (i**3 % 57)) zipf2.close() def tearDown(self): zipfile.ZIP64_LIMIT = self._limit zipfile.ZIP_FILECOUNT_LIMIT = self._filecount_limit unlink(TESTFN) unlink(TESTFN2) class StoredTestZip64InSmallFiles(AbstractTestZip64InSmallFiles, unittest.TestCase): compression = zipfile.ZIP_STORED def large_file_exception_test(self, f, compression): with zipfile.ZipFile(f, "w", compression, allowZip64=False) as zipfp: self.assertRaises(zipfile.LargeZipFile, zipfp.write, TESTFN, "another.name") def large_file_exception_test2(self, f, compression): with zipfile.ZipFile(f, "w", compression, allowZip64=False) as zipfp: self.assertRaises(zipfile.LargeZipFile, zipfp.writestr, "another.name", self.data) def test_large_file_exception(self): for f in get_files(self): self.large_file_exception_test(f, zipfile.ZIP_STORED) self.large_file_exception_test2(f, zipfile.ZIP_STORED) def test_absolute_arcnames(self): with zipfile.ZipFile(TESTFN2, "w", zipfile.ZIP_STORED, allowZip64=True) as zipfp: zipfp.write(TESTFN, "/absolute") with zipfile.ZipFile(TESTFN2, "r", zipfile.ZIP_STORED) as zipfp: self.assertEqual(zipfp.namelist(), ["absolute"]) def test_append(self): # Test that appending to the Zip64 archive doesn't change # extra fields of existing entries. with zipfile.ZipFile(TESTFN2, "w", allowZip64=True) as zipfp: zipfp.writestr("strfile", self.data) with zipfile.ZipFile(TESTFN2, "r", allowZip64=True) as zipfp: zinfo = zipfp.getinfo("strfile") extra = zinfo.extra with zipfile.ZipFile(TESTFN2, "a", allowZip64=True) as zipfp: zipfp.writestr("strfile2", self.data) with zipfile.ZipFile(TESTFN2, "r", allowZip64=True) as zipfp: zinfo = zipfp.getinfo("strfile") self.assertEqual(zinfo.extra, extra) def make_zip64_file( self, file_size_64_set=False, file_size_extra=False, compress_size_64_set=False, compress_size_extra=False, header_offset_64_set=False, header_offset_extra=False, disk_num_64_set=False, disk_num_extra=False, ): """Generate bytes sequence for a zip with (incomplete) zip64 data. The actual values (not the zip 64 0xffffffff values) stored in the file are: file_size: 8 compress_size: 8 header_offset: 0 disk_num: 0 """ actual_size = 8 actual_header_offset = 0 actual_disk_num = 0 local_zip64_q_fields = [] local_zip64_i_fields = [] central_zip64_q_fields = [] central_zip64_i_fields = [] file_size = actual_size if file_size_64_set: file_size = 0xffffffff if file_size_extra: local_zip64_q_fields.append(actual_size) central_zip64_q_fields.append(actual_size) file_size = struct.pack("= 3.5') class PyZipFileTests(unittest.TestCase): def assertCompiledIn(self, name, namelist): if name + 'o' not in namelist: self.assertIn(name + 'c', namelist) def requiresWriteAccess(self, path): # effective_ids unavailable on windows if not os.access(path, os.W_OK, effective_ids=os.access in os.supports_effective_ids): self.skipTest('requires write access to the installed location') filename = os.path.join(path, 'test_zipfile.try') try: fd = os.open(filename, os.O_WRONLY | os.O_CREAT) os.close(fd) except Exception: self.skipTest('requires write access to the installed location') unlink(filename) def test_write_pyfile(self): self.requiresWriteAccess(os.path.dirname(__file__)) with TemporaryFile() as t, zipfile.PyZipFile(t, "w") as zipfp: fn = __file__ if fn.endswith('.pyc'): path_split = fn.split(os.sep) if os.altsep is not None: path_split.extend(fn.split(os.altsep)) if '__pycache__' in path_split: fn = importlib.util.source_from_cache(fn) else: fn = fn[:-1] zipfp.writepy(fn) bn = os.path.basename(fn) self.assertNotIn(bn, zipfp.namelist()) self.assertCompiledIn(bn, zipfp.namelist()) with TemporaryFile() as t, zipfile.PyZipFile(t, "w") as zipfp: fn = __file__ if fn.endswith('.pyc'): fn = fn[:-1] zipfp.writepy(fn, "testpackage") bn = "%s/%s" % ("testpackage", os.path.basename(fn)) self.assertNotIn(bn, zipfp.namelist()) self.assertCompiledIn(bn, zipfp.namelist()) def test_write_python_package(self): import email packagedir = os.path.dirname(email.__file__) self.requiresWriteAccess(packagedir) with TemporaryFile() as t, zipfile.PyZipFile(t, "w") as zipfp: zipfp.writepy(packagedir) # Check for a couple of modules at different levels of the # hierarchy names = zipfp.namelist() self.assertCompiledIn('email/__init__.py', names) self.assertCompiledIn('email/mime/text.py', names) def test_write_filtered_python_package(self): import test packagedir = os.path.dirname(test.__file__) self.requiresWriteAccess(packagedir) with TemporaryFile() as t, zipfile.PyZipFile(t, "w") as zipfp: # first make sure that the test folder gives error messages # (on the badsyntax_... files) with captured_stdout() as reportSIO: zipfp.writepy(packagedir) reportStr = reportSIO.getvalue() self.assertTrue('SyntaxError' in reportStr) # then check that the filter works on the whole package with captured_stdout() as reportSIO: zipfp.writepy(packagedir, filterfunc=lambda whatever: False) reportStr = reportSIO.getvalue() self.assertTrue('SyntaxError' not in reportStr) # then check that the filter works on individual files def filter(path): return not os.path.basename(path).startswith("bad") with captured_stdout() as reportSIO, self.assertWarns(UserWarning): zipfp.writepy(packagedir, filterfunc=filter) reportStr = reportSIO.getvalue() if reportStr: print(reportStr) self.assertTrue('SyntaxError' not in reportStr) def test_write_with_optimization(self): import email packagedir = os.path.dirname(email.__file__) self.requiresWriteAccess(packagedir) optlevel = 1 if __debug__ else 0 ext = '.pyc' with TemporaryFile() as t, \ zipfile.PyZipFile(t, "w", optimize=optlevel) as zipfp: zipfp.writepy(packagedir) names = zipfp.namelist() self.assertIn('email/__init__' + ext, names) self.assertIn('email/mime/text' + ext, names) def test_write_python_directory(self): os.mkdir(TESTFN2) try: with open(os.path.join(TESTFN2, "mod1.py"), "w") as fp: fp.write("print(42)\n") with open(os.path.join(TESTFN2, "mod2.py"), "w") as fp: fp.write("print(42 * 42)\n") with open(os.path.join(TESTFN2, "mod2.txt"), "w") as fp: fp.write("bla bla bla\n") with TemporaryFile() as t, zipfile.PyZipFile(t, "w") as zipfp: zipfp.writepy(TESTFN2) names = zipfp.namelist() self.assertCompiledIn('mod1.py', names) self.assertCompiledIn('mod2.py', names) self.assertNotIn('mod2.txt', names) finally: rmtree(TESTFN2) def test_write_python_directory_filtered(self): os.mkdir(TESTFN2) try: with open(os.path.join(TESTFN2, "mod1.py"), "w") as fp: fp.write("print(42)\n") with open(os.path.join(TESTFN2, "mod2.py"), "w") as fp: fp.write("print(42 * 42)\n") with TemporaryFile() as t, zipfile.PyZipFile(t, "w") as zipfp: zipfp.writepy(TESTFN2, filterfunc=lambda fn: not fn.endswith('mod2.py')) names = zipfp.namelist() self.assertCompiledIn('mod1.py', names) self.assertNotIn('mod2.py', names) finally: rmtree(TESTFN2) def test_write_non_pyfile(self): with TemporaryFile() as t, zipfile.PyZipFile(t, "w") as zipfp: with open(TESTFN, 'w') as f: f.write('most definitely not a python file') self.assertRaises(RuntimeError, zipfp.writepy, TESTFN) unlink(TESTFN) def test_write_pyfile_bad_syntax(self): os.mkdir(TESTFN2) try: with open(os.path.join(TESTFN2, "mod1.py"), "w") as fp: fp.write("Bad syntax in python file\n") with TemporaryFile() as t, zipfile.PyZipFile(t, "w") as zipfp: # syntax errors are printed to stdout with captured_stdout() as s: zipfp.writepy(os.path.join(TESTFN2, "mod1.py")) self.assertIn("SyntaxError", s.getvalue()) # as it will not have compiled the python file, it will # include the .py file not .pyc names = zipfp.namelist() self.assertIn('mod1.py', names) self.assertNotIn('mod1.pyc', names) finally: rmtree(TESTFN2) def test_write_pathlike(self): os.mkdir(TESTFN2) try: with open(os.path.join(TESTFN2, "mod1.py"), "w") as fp: fp.write("print(42)\n") with TemporaryFile() as t, zipfile.PyZipFile(t, "w") as zipfp: zipfp.writepy(pathlib.Path(TESTFN2) / "mod1.py") names = zipfp.namelist() self.assertCompiledIn('mod1.py', names) finally: rmtree(TESTFN2) class ExtractTests(unittest.TestCase): def make_test_file(self): with zipfile.ZipFile(TESTFN2, "w", zipfile.ZIP_STORED) as zipfp: for fpath, fdata in SMALL_TEST_DATA: zipfp.writestr(fpath, fdata) def test_extract(self): with temp_cwd(): self.make_test_file() with zipfile.ZipFile(TESTFN2, "r") as zipfp: for fpath, fdata in SMALL_TEST_DATA: writtenfile = zipfp.extract(fpath) # make sure it was written to the right place correctfile = os.path.join(os.getcwd(), fpath) correctfile = os.path.normpath(correctfile) self.assertEqual(writtenfile, correctfile) # make sure correct data is in correct file with open(writtenfile, "rb") as f: self.assertEqual(fdata.encode(), f.read()) unlink(writtenfile) def _test_extract_with_target(self, target): self.make_test_file() with zipfile.ZipFile(TESTFN2, "r") as zipfp: for fpath, fdata in SMALL_TEST_DATA: writtenfile = zipfp.extract(fpath, target) # compat with Path objects were added in python 3.6 if sys.version_info[0:2] < (3, 6): target = str(target) # make sure it was written to the right place correctfile = os.path.join(target, fpath) correctfile = os.path.normpath(correctfile) self.assertTrue(os.path.samefile(writtenfile, correctfile), (writtenfile, target)) # make sure correct data is in correct file with open(writtenfile, "rb") as f: self.assertEqual(fdata.encode(), f.read()) unlink(writtenfile) unlink(TESTFN2) def test_extract_with_target(self): with temp_dir() as extdir: self._test_extract_with_target(extdir) def test_extract_with_target_pathlike(self): with temp_dir() as extdir: self._test_extract_with_target(pathlib.Path(extdir)) def test_extract_all(self): with temp_cwd(): self.make_test_file() with zipfile.ZipFile(TESTFN2, "r") as zipfp: zipfp.extractall() for fpath, fdata in SMALL_TEST_DATA: outfile = os.path.join(os.getcwd(), fpath) with open(outfile, "rb") as f: self.assertEqual(fdata.encode(), f.read()) unlink(outfile) def _test_extract_all_with_target(self, target): self.make_test_file() with zipfile.ZipFile(TESTFN2, "r") as zipfp: zipfp.extractall(target) for fpath, fdata in SMALL_TEST_DATA: # compat with Path objects were added in python 3.6 if sys.version_info[0:2] < (3, 6): target = str(target) outfile = os.path.join(str(target), fpath) with open(outfile, "rb") as f: self.assertEqual(fdata.encode(), f.read()) unlink(outfile) unlink(TESTFN2) def test_extract_all_with_target(self): with temp_dir() as extdir: self._test_extract_all_with_target(extdir) def test_extract_all_with_target_pathlike(self): with temp_dir() as extdir: self._test_extract_all_with_target(pathlib.Path(extdir)) def check_file(self, filename, content): self.assertTrue(os.path.isfile(filename)) with open(filename, 'rb') as f: self.assertEqual(f.read(), content) def test_sanitize_windows_name(self): san = zipfile.ZipFile._sanitize_windows_name # Passing pathsep in allows this test to work regardless of platform. self.assertEqual(san(r',,?,C:,foo,bar/z', ','), r'_,C_,foo,bar/z') self.assertEqual(san(r'a\b,ce|f"g?h*i', ','), r'a\b,c_d_e_f_g_h_i') self.assertEqual(san('../../foo../../ba..r', '/'), r'foo/ba..r') def test_extract_hackers_arcnames_common_cases(self): common_hacknames = [ ('../foo/bar', 'foo/bar'), ('foo/../bar', 'foo/bar'), ('foo/../../bar', 'foo/bar'), ('foo/bar/..', 'foo/bar'), ('./../foo/bar', 'foo/bar'), ('/foo/bar', 'foo/bar'), ('/foo/../bar', 'foo/bar'), ('/foo/../../bar', 'foo/bar'), ] self._test_extract_hackers_arcnames(common_hacknames) @unittest.skipIf(os.path.sep != '\\', 'Requires \\ as path separator.') def test_extract_hackers_arcnames_windows_only(self): """Test combination of path fixing and windows name sanitization.""" windows_hacknames = [ (r'..\foo\bar', 'foo/bar'), (r'..\/foo\/bar', 'foo/bar'), (r'foo/\..\/bar', 'foo/bar'), (r'foo\/../\bar', 'foo/bar'), (r'C:foo/bar', 'foo/bar'), (r'C:/foo/bar', 'foo/bar'), (r'C://foo/bar', 'foo/bar'), (r'C:\foo\bar', 'foo/bar'), (r'//conky/mountpoint/foo/bar', 'foo/bar'), (r'\\conky\mountpoint\foo\bar', 'foo/bar'), (r'///conky/mountpoint/foo/bar', 'conky/mountpoint/foo/bar'), (r'\\\conky\mountpoint\foo\bar', 'conky/mountpoint/foo/bar'), (r'//conky//mountpoint/foo/bar', 'conky/mountpoint/foo/bar'), (r'\\conky\\mountpoint\foo\bar', 'conky/mountpoint/foo/bar'), (r'//?/C:/foo/bar', 'foo/bar'), (r'\\?\C:\foo\bar', 'foo/bar'), (r'C:/../C:/foo/bar', 'C_/foo/bar'), (r'a:b\ce|f"g?h*i', 'b/c_d_e_f_g_h_i'), ('../../foo../../ba..r', 'foo/ba..r'), ] self._test_extract_hackers_arcnames(windows_hacknames) @unittest.skipIf(os.path.sep != '/', r'Requires / as path separator.') def test_extract_hackers_arcnames_posix_only(self): posix_hacknames = [ ('//foo/bar', 'foo/bar'), ('../../foo../../ba..r', 'foo../ba..r'), (r'foo/..\bar', r'foo/..\bar'), ] self._test_extract_hackers_arcnames(posix_hacknames) def _test_extract_hackers_arcnames(self, hacknames): for arcname, fixedname in hacknames: content = b'foobar' + arcname.encode() with zipfile.ZipFile(TESTFN2, 'w', zipfile.ZIP_STORED) as zipfp: zinfo = zipfile.ZipInfo() # preserve backslashes zinfo.filename = arcname zinfo.external_attr = 0o600 << 16 zipfp.writestr(zinfo, content) arcname = arcname.replace(os.sep, "/") targetpath = os.path.join('target', 'subdir', 'subsub') correctfile = os.path.join(targetpath, *fixedname.split('/')) with zipfile.ZipFile(TESTFN2, 'r') as zipfp: writtenfile = zipfp.extract(arcname, targetpath) self.assertEqual(writtenfile, correctfile, msg='extract %r: %r != %r' % (arcname, writtenfile, correctfile)) self.check_file(correctfile, content) rmtree('target') with zipfile.ZipFile(TESTFN2, 'r') as zipfp: zipfp.extractall(targetpath) self.check_file(correctfile, content) rmtree('target') correctfile = os.path.join(os.getcwd(), *fixedname.split('/')) with zipfile.ZipFile(TESTFN2, 'r') as zipfp: writtenfile = zipfp.extract(arcname) self.assertEqual(writtenfile, correctfile, msg="extract %r" % arcname) self.check_file(correctfile, content) rmtree(fixedname.split('/')[0]) with zipfile.ZipFile(TESTFN2, 'r') as zipfp: zipfp.extractall() self.check_file(correctfile, content) rmtree(fixedname.split('/')[0]) unlink(TESTFN2) class OtherTests(unittest.TestCase): def test_open_via_zip_info(self): # Create the ZIP archive with zipfile.ZipFile(TESTFN2, "w", zipfile.ZIP_STORED) as zipfp: zipfp.writestr("name", "foo") with self.assertWarns(UserWarning): zipfp.writestr("name", "bar") self.assertEqual(zipfp.namelist(), ["name"] * 2) with zipfile.ZipFile(TESTFN2, "r") as zipfp: infos = zipfp.infolist() data = b"" for info in infos: with zipfp.open(info) as zipopen: data += zipopen.read() self.assertIn(data, {b"foobar", b"barfoo"}) data = b"" for info in infos: data += zipfp.read(info) self.assertIn(data, {b"foobar", b"barfoo"}) def test_writestr_extended_local_header_issue1202(self): with zipfile.ZipFile(TESTFN2, 'w') as orig_zip: for data in 'abcdefghijklmnop': zinfo = zipfile.ZipInfo(data) zinfo.flag_bits |= 0x08 # Include an extended local header. orig_zip.writestr(zinfo, data) def test_close(self): """Check that the zipfile is closed after the 'with' block.""" with zipfile.ZipFile(TESTFN2, "w") as zipfp: for fpath, fdata in SMALL_TEST_DATA: zipfp.writestr(fpath, fdata) self.assertIsNotNone(zipfp.fp, 'zipfp is not open') self.assertIsNone(zipfp.fp, 'zipfp is not closed') with zipfile.ZipFile(TESTFN2, "r") as zipfp: self.assertIsNotNone(zipfp.fp, 'zipfp is not open') self.assertIsNone(zipfp.fp, 'zipfp is not closed') def test_close_on_exception(self): """Check that the zipfile is closed if an exception is raised in the 'with' block.""" with zipfile.ZipFile(TESTFN2, "w") as zipfp: for fpath, fdata in SMALL_TEST_DATA: zipfp.writestr(fpath, fdata) try: with zipfile.ZipFile(TESTFN2, "r") as zipfp2: raise zipfile.BadZipFile() except zipfile.BadZipFile: self.assertIsNone(zipfp2.fp, 'zipfp is not closed') def test_unsupported_version(self): # File has an extract_version of 120 data = (b'PK\x03\x04x\x00\x00\x00\x00\x00!p\xa1@\x00\x00\x00\x00\x00\x00' b'\x00\x00\x00\x00\x00\x00\x01\x00\x00\x00xPK\x01\x02x\x03x\x00\x00\x00\x00' b'\x00!p\xa1@\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x01\x00\x00' b'\x00\x00\x00\x00\x00\x00\x00\x00\x00\x80\x01\x00\x00\x00\x00xPK\x05\x06' b'\x00\x00\x00\x00\x01\x00\x01\x00/\x00\x00\x00\x1f\x00\x00\x00\x00\x00') self.assertRaises(NotImplementedError, zipfile.ZipFile, io.BytesIO(data), 'r') @requires_zlib def test_read_unicode_filenames(self): # bug #10801 fname = findfile('zip_cp437_header.zip') with zipfile.ZipFile(fname) as zipfp: for name in zipfp.namelist(): zipfp.open(name).close() def test_write_unicode_filenames(self): with zipfile.ZipFile(TESTFN, "w") as zf: zf.writestr("foo.txt", "Test for unicode filename") zf.writestr("\xf6.txt", "Test for unicode filename") self.assertIsInstance(zf.infolist()[0].filename, str) with zipfile.ZipFile(TESTFN, "r") as zf: self.assertEqual(zf.filelist[0].filename, "foo.txt") self.assertEqual(zf.filelist[1].filename, "\xf6.txt") def test_exclusive_create_zip_file(self): """Test exclusive creating a new zipfile.""" unlink(TESTFN2) filename = 'testfile.txt' content = b'hello, world. this is some content.' with zipfile.ZipFile(TESTFN2, "x", zipfile.ZIP_STORED) as zipfp: zipfp.writestr(filename, content) with self.assertRaises(FileExistsError): zipfile.ZipFile(TESTFN2, "x", zipfile.ZIP_STORED) with zipfile.ZipFile(TESTFN2, "r") as zipfp: self.assertEqual(zipfp.namelist(), [filename]) self.assertEqual(zipfp.read(filename), content) def test_create_non_existent_file_for_append(self): if os.path.exists(TESTFN): os.unlink(TESTFN) filename = 'testfile.txt' content = b'hello, world. this is some content.' try: with zipfile.ZipFile(TESTFN, 'a') as zf: zf.writestr(filename, content) except OSError: self.fail('Could not append data to a non-existent zip file.') self.assertTrue(os.path.exists(TESTFN)) with zipfile.ZipFile(TESTFN, 'r') as zf: self.assertEqual(zf.read(filename), content) def test_close_erroneous_file(self): # This test checks that the ZipFile constructor closes the file object # it opens if there's an error in the file. If it doesn't, the # traceback holds a reference to the ZipFile object and, indirectly, # the file object. # On Windows, this causes the os.unlink() call to fail because the # underlying file is still open. This is SF bug #412214. # with open(TESTFN, "w") as fp: fp.write("this is not a legal zip file\n") try: zf = zipfile.ZipFile(TESTFN) except zipfile.BadZipFile: pass def test_is_zip_erroneous_file(self): """Check that is_zipfile() correctly identifies non-zip files.""" # - passing a filename with open(TESTFN, "w") as fp: fp.write("this is not a legal zip file\n") self.assertFalse(zipfile.is_zipfile(TESTFN)) # - passing a path-like object self.assertFalse(zipfile.is_zipfile(pathlib.Path(TESTFN))) # - passing a file object with open(TESTFN, "rb") as fp: self.assertFalse(zipfile.is_zipfile(fp)) # - passing a file-like object fp = io.BytesIO() fp.write(b"this is not a legal zip file\n") self.assertFalse(zipfile.is_zipfile(fp)) fp.seek(0, 0) self.assertFalse(zipfile.is_zipfile(fp)) def test_damaged_zipfile(self): """Check that zipfiles with missing bytes at the end raise BadZipFile.""" # - Create a valid zip file fp = io.BytesIO() with zipfile.ZipFile(fp, mode="w") as zipf: zipf.writestr("foo.txt", b"O, for a Muse of Fire!") zipfiledata = fp.getvalue() # - Now create copies of it missing the last N bytes and make sure # a BadZipFile exception is raised when we try to open it for N in range(len(zipfiledata)): fp = io.BytesIO(zipfiledata[:N]) self.assertRaises(zipfile.BadZipFile, zipfile.ZipFile, fp) def test_is_zip_valid_file(self): """Check that is_zipfile() correctly identifies zip files.""" # - passing a filename with zipfile.ZipFile(TESTFN, mode="w") as zipf: zipf.writestr("foo.txt", b"O, for a Muse of Fire!") self.assertTrue(zipfile.is_zipfile(TESTFN)) # - passing a file object with open(TESTFN, "rb") as fp: self.assertTrue(zipfile.is_zipfile(fp)) fp.seek(0, 0) zip_contents = fp.read() # - passing a file-like object fp = io.BytesIO() fp.write(zip_contents) self.assertTrue(zipfile.is_zipfile(fp)) fp.seek(0, 0) self.assertTrue(zipfile.is_zipfile(fp)) def test_non_existent_file_raises_OSError(self): # make sure we don't raise an AttributeError when a partially-constructed # ZipFile instance is finalized; this tests for regression on SF tracker # bug #403871. # The bug we're testing for caused an AttributeError to be raised # when a ZipFile instance was created for a file that did not # exist; the .fp member was not initialized but was needed by the # __del__() method. Since the AttributeError is in the __del__(), # it is ignored, but the user should be sufficiently annoyed by # the message on the output that regression will be noticed # quickly. self.assertRaises(OSError, zipfile.ZipFile, TESTFN) def test_empty_file_raises_BadZipFile(self): f = open(TESTFN, 'w') f.close() self.assertRaises(zipfile.BadZipFile, zipfile.ZipFile, TESTFN) with open(TESTFN, 'w') as fp: fp.write("short file") self.assertRaises(zipfile.BadZipFile, zipfile.ZipFile, TESTFN) def test_closed_zip_raises_ValueError(self): """Verify that testzip() doesn't swallow inappropriate exceptions.""" data = io.BytesIO() with zipfile.ZipFile(data, mode="w") as zipf: zipf.writestr("foo.txt", "O, for a Muse of Fire!") # This is correct; calling .read on a closed ZipFile should raise # a ValueError, and so should calling .testzip. An earlier # version of .testzip would swallow this exception (and any other) # and report that the first file in the archive was corrupt. self.assertRaises(ValueError, zipf.read, "foo.txt") self.assertRaises(ValueError, zipf.open, "foo.txt") self.assertRaises(ValueError, zipf.testzip) self.assertRaises(ValueError, zipf.writestr, "bogus.txt", "bogus") with open(TESTFN, 'w') as f: f.write('zipfile test data') self.assertRaises(ValueError, zipf.write, TESTFN) def test_bad_constructor_mode(self): """Check that bad modes passed to ZipFile constructor are caught.""" self.assertRaises(ValueError, zipfile.ZipFile, TESTFN, "q") def test_bad_open_mode(self): """Check that bad modes passed to ZipFile.open are caught.""" with zipfile.ZipFile(TESTFN, mode="w") as zipf: zipf.writestr("foo.txt", "O, for a Muse of Fire!") with zipfile.ZipFile(TESTFN, mode="r") as zipf: # read the data to make sure the file is there zipf.read("foo.txt") self.assertRaises(ValueError, zipf.open, "foo.txt", "q") # universal newlines support is removed self.assertRaises(ValueError, zipf.open, "foo.txt", "U") self.assertRaises(ValueError, zipf.open, "foo.txt", "rU") def test_read0(self): """Check that calling read(0) on a ZipExtFile object returns an empty string and doesn't advance file pointer.""" with zipfile.ZipFile(TESTFN, mode="w") as zipf: zipf.writestr("foo.txt", "O, for a Muse of Fire!") # read the data to make sure the file is there with zipf.open("foo.txt") as f: for i in range(FIXEDTEST_SIZE): self.assertEqual(f.read(0), b'') self.assertEqual(f.read(), b"O, for a Muse of Fire!") def test_open_non_existent_item(self): """Check that attempting to call open() for an item that doesn't exist in the archive raises a RuntimeError.""" with zipfile.ZipFile(TESTFN, mode="w") as zipf: self.assertRaises(KeyError, zipf.open, "foo.txt", "r") def test_bad_compression_mode(self): """Check that bad compression methods passed to ZipFile.open are caught.""" self.assertRaises(NotImplementedError, zipfile.ZipFile, TESTFN, "w", -1) def test_unsupported_compression(self): # data is declared as shrunk, but actually deflated data = (b'PK\x03\x04.\x00\x00\x00\x01\x00\xe4C\xa1@\x00\x00\x00' b'\x00\x02\x00\x00\x00\x00\x00\x00\x00\x01\x00\x00\x00x\x03\x00PK\x01' b'\x02.\x03.\x00\x00\x00\x01\x00\xe4C\xa1@\x00\x00\x00\x00\x02\x00\x00' b'\x00\x00\x00\x00\x00\x01\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00' b'\x80\x01\x00\x00\x00\x00xPK\x05\x06\x00\x00\x00\x00\x01\x00\x01\x00' b'/\x00\x00\x00!\x00\x00\x00\x00\x00') with zipfile.ZipFile(io.BytesIO(data), 'r') as zipf: self.assertRaises(NotImplementedError, zipf.open, 'x') def test_null_byte_in_filename(self): """Check that a filename containing a null byte is properly terminated.""" with zipfile.ZipFile(TESTFN, mode="w") as zipf: zipf.writestr("foo.txt\x00qqq", b"O, for a Muse of Fire!") self.assertEqual(zipf.namelist(), ['foo.txt']) def test_struct_sizes(self): """Check that ZIP internal structure sizes are calculated correctly.""" self.assertEqual(zipfile.sizeEndCentDir, 22) self.assertEqual(zipfile.sizeCentralDir, 46) self.assertEqual(zipfile.sizeEndCentDir64, 56) self.assertEqual(zipfile.sizeEndCentDir64Locator, 20) def test_comments(self): """Check that comments on the archive are handled properly.""" # check default comment is empty with zipfile.ZipFile(TESTFN, mode="w") as zipf: self.assertEqual(zipf.comment, b'') zipf.writestr("foo.txt", "O, for a Muse of Fire!") with zipfile.ZipFile(TESTFN, mode="r") as zipfr: self.assertEqual(zipfr.comment, b'') # check a simple short comment comment = b'Bravely taking to his feet, he beat a very brave retreat.' with zipfile.ZipFile(TESTFN, mode="w") as zipf: zipf.comment = comment zipf.writestr("foo.txt", "O, for a Muse of Fire!") with zipfile.ZipFile(TESTFN, mode="r") as zipfr: self.assertEqual(zipf.comment, comment) # check a comment of max length comment2 = ''.join(['%d' % (i**3 % 10) for i in range((1 << 16)-1)]) comment2 = comment2.encode("ascii") with zipfile.ZipFile(TESTFN, mode="w") as zipf: zipf.comment = comment2 zipf.writestr("foo.txt", "O, for a Muse of Fire!") with zipfile.ZipFile(TESTFN, mode="r") as zipfr: self.assertEqual(zipfr.comment, comment2) # check a comment that is too long is truncated with zipfile.ZipFile(TESTFN, mode="w") as zipf: with self.assertWarns(UserWarning): zipf.comment = comment2 + b'oops' zipf.writestr("foo.txt", "O, for a Muse of Fire!") with zipfile.ZipFile(TESTFN, mode="r") as zipfr: self.assertEqual(zipfr.comment, comment2) # check that comments are correctly modified in append mode with zipfile.ZipFile(TESTFN,mode="w") as zipf: zipf.comment = b"original comment" zipf.writestr("foo.txt", "O, for a Muse of Fire!") with zipfile.ZipFile(TESTFN,mode="a") as zipf: zipf.comment = b"an updated comment" with zipfile.ZipFile(TESTFN,mode="r") as zipf: self.assertEqual(zipf.comment, b"an updated comment") # check that comments are correctly shortened in append mode with zipfile.ZipFile(TESTFN,mode="w") as zipf: zipf.comment = b"original comment that's longer" zipf.writestr("foo.txt", "O, for a Muse of Fire!") with zipfile.ZipFile(TESTFN,mode="a") as zipf: zipf.comment = b"shorter comment" with zipfile.ZipFile(TESTFN,mode="r") as zipf: self.assertEqual(zipf.comment, b"shorter comment") def test_unicode_comment(self): with zipfile.ZipFile(TESTFN, "w", zipfile.ZIP_STORED) as zipf: zipf.writestr("foo.txt", "O, for a Muse of Fire!") with self.assertRaises(TypeError): zipf.comment = "this is an error" def test_change_comment_in_empty_archive(self): with zipfile.ZipFile(TESTFN, "a", zipfile.ZIP_STORED) as zipf: self.assertFalse(zipf.filelist) zipf.comment = b"this is a comment" with zipfile.ZipFile(TESTFN, "r") as zipf: self.assertEqual(zipf.comment, b"this is a comment") def test_change_comment_in_nonempty_archive(self): with zipfile.ZipFile(TESTFN, "w", zipfile.ZIP_STORED) as zipf: zipf.writestr("foo.txt", "O, for a Muse of Fire!") with zipfile.ZipFile(TESTFN, "a", zipfile.ZIP_STORED) as zipf: self.assertTrue(zipf.filelist) zipf.comment = b"this is a comment" with zipfile.ZipFile(TESTFN, "r") as zipf: self.assertEqual(zipf.comment, b"this is a comment") def test_empty_zipfile(self): # Check that creating a file in 'w' or 'a' mode and closing without # adding any files to the archives creates a valid empty ZIP file zipf = zipfile.ZipFile(TESTFN, mode="w") zipf.close() try: zipf = zipfile.ZipFile(TESTFN, mode="r") except zipfile.BadZipFile: self.fail("Unable to create empty ZIP file in 'w' mode") zipf = zipfile.ZipFile(TESTFN, mode="a") zipf.close() try: zipf = zipfile.ZipFile(TESTFN, mode="r") except: self.fail("Unable to create empty ZIP file in 'a' mode") def test_open_empty_file(self): # Issue 1710703: Check that opening a file with less than 22 bytes # raises a BadZipFile exception (rather than the previously unhelpful # OSError) f = open(TESTFN, 'w') f.close() self.assertRaises(zipfile.BadZipFile, zipfile.ZipFile, TESTFN, 'r') def test_create_zipinfo_before_1980(self): self.assertRaises(ValueError, zipfile.ZipInfo, 'seventies', (1979, 1, 1, 0, 0, 0)) def test_zipfile_with_short_extra_field(self): """If an extra field in the header is less than 4 bytes, skip it.""" zipdata = ( b'PK\x03\x04\x14\x00\x00\x00\x00\x00\x93\x9b\xad@\x8b\x9e' b'\xd9\xd3\x01\x00\x00\x00\x01\x00\x00\x00\x03\x00\x03\x00ab' b'c\x00\x00\x00APK\x01\x02\x14\x03\x14\x00\x00\x00\x00' b'\x00\x93\x9b\xad@\x8b\x9e\xd9\xd3\x01\x00\x00\x00\x01\x00\x00' b'\x00\x03\x00\x02\x00\x00\x00\x00\x00\x00\x00\x00\x00\xa4\x81\x00' b'\x00\x00\x00abc\x00\x00PK\x05\x06\x00\x00\x00\x00' b'\x01\x00\x01\x003\x00\x00\x00%\x00\x00\x00\x00\x00' ) with zipfile.ZipFile(io.BytesIO(zipdata), 'r') as zipf: # testzip returns the name of the first corrupt file, or None self.assertIsNone(zipf.testzip()) def test_open_conflicting_handles(self): # It's only possible to open one writable file handle at a time msg1 = b"It's fun to charter an accountant!" msg2 = b"And sail the wide accountant sea" msg3 = b"To find, explore the funds offshore" with zipfile.ZipFile(TESTFN2, 'w', zipfile.ZIP_STORED) as zipf: with zipf.open('foo', mode='w') as w2: w2.write(msg1) with zipf.open('bar', mode='w') as w1: with self.assertRaises(ValueError): zipf.open('handle', mode='w') with self.assertRaises(ValueError): zipf.open('foo', mode='r') with self.assertRaises(ValueError): zipf.writestr('str', 'abcde') with self.assertRaises(ValueError): zipf.write(__file__, 'file') with self.assertRaises(ValueError): zipf.close() w1.write(msg2) with zipf.open('baz', mode='w') as w2: w2.write(msg3) with zipfile.ZipFile(TESTFN2, 'r') as zipf: self.assertEqual(zipf.read('foo'), msg1) self.assertEqual(zipf.read('bar'), msg2) self.assertEqual(zipf.read('baz'), msg3) self.assertEqual(zipf.namelist(), ['foo', 'bar', 'baz']) def test_seek_tell(self): # Test seek functionality txt = b"Where's Bruce?" bloc = txt.find(b"Bruce") # Check seek on a file with zipfile.ZipFile(TESTFN, "w") as zipf: zipf.writestr("foo.txt", txt) with zipfile.ZipFile(TESTFN, "r") as zipf: with zipf.open("foo.txt", "r") as fp: fp.seek(bloc, os.SEEK_SET) self.assertEqual(fp.tell(), bloc) fp.seek(-bloc, os.SEEK_CUR) self.assertEqual(fp.tell(), 0) fp.seek(bloc, os.SEEK_CUR) self.assertEqual(fp.tell(), bloc) self.assertEqual(fp.read(5), txt[bloc:bloc+5]) # Make sure that the second read after seeking back beyond # _readbuffer returns the same content (ie. rewind to the start of # the file to read forward to the required position). old_read_size = fp.MIN_READ_SIZE fp.MIN_READ_SIZE = 1 fp._readbuffer = b'' fp._offset = 0 fp.seek(0, os.SEEK_SET) self.assertEqual(fp.tell(), 0) fp.seek(bloc, os.SEEK_CUR) self.assertEqual(fp.read(5), txt[bloc:bloc+5]) fp.MIN_READ_SIZE = old_read_size fp.seek(0, os.SEEK_END) self.assertEqual(fp.tell(), len(txt)) fp.seek(0, os.SEEK_SET) self.assertEqual(fp.tell(), 0) # Read the file completely to definitely call any eof integrity # checks (crc) and make sure they still pass. fp.read() # Check seek on memory file data = io.BytesIO() with zipfile.ZipFile(data, mode="w") as zipf: zipf.writestr("foo.txt", txt) with zipfile.ZipFile(data, mode="r") as zipf: with zipf.open("foo.txt", "r") as fp: fp.seek(bloc, os.SEEK_SET) self.assertEqual(fp.tell(), bloc) fp.seek(-bloc, os.SEEK_CUR) self.assertEqual(fp.tell(), 0) fp.seek(bloc, os.SEEK_CUR) self.assertEqual(fp.tell(), bloc) self.assertEqual(fp.read(5), txt[bloc:bloc+5]) # Make sure that the second read after seeking back beyond # _readbuffer returns the same content (ie. rewind to the start of # the file to read forward to the required position). old_read_size = fp.MIN_READ_SIZE fp.MIN_READ_SIZE = 1 fp._readbuffer = b'' fp._offset = 0 fp.seek(0, os.SEEK_SET) self.assertEqual(fp.tell(), 0) fp.seek(bloc, os.SEEK_CUR) self.assertEqual(fp.read(5), txt[bloc:bloc+5]) fp.MIN_READ_SIZE = old_read_size fp.seek(0, os.SEEK_END) self.assertEqual(fp.tell(), len(txt)) fp.seek(0, os.SEEK_SET) self.assertEqual(fp.tell(), 0) # Read the file completely to definitely call any eof integrity # checks (crc) and make sure they still pass. fp.read() def tearDown(self): unlink(TESTFN) unlink(TESTFN2) class AbstractBadCrcTests: def test_testzip_with_bad_crc(self): """Tests that files with bad CRCs return their name from testzip.""" zipdata = self.zip_with_bad_crc with zipfile.ZipFile(io.BytesIO(zipdata), mode="r") as zipf: # testzip returns the name of the first corrupt file, or None self.assertEqual('afile', zipf.testzip()) def test_read_with_bad_crc(self): """Tests that files with bad CRCs raise a BadZipFile exception when read.""" zipdata = self.zip_with_bad_crc # Using ZipFile.read() with zipfile.ZipFile(io.BytesIO(zipdata), mode="r") as zipf: self.assertRaises(zipfile.BadZipFile, zipf.read, 'afile') # Using ZipExtFile.read() with zipfile.ZipFile(io.BytesIO(zipdata), mode="r") as zipf: with zipf.open('afile', 'r') as corrupt_file: self.assertRaises(zipfile.BadZipFile, corrupt_file.read) # Same with small reads (in order to exercise the buffering logic) with zipfile.ZipFile(io.BytesIO(zipdata), mode="r") as zipf: with zipf.open('afile', 'r') as corrupt_file: corrupt_file.MIN_READ_SIZE = 2 with self.assertRaises(zipfile.BadZipFile): while corrupt_file.read(2): pass class StoredBadCrcTests(AbstractBadCrcTests, unittest.TestCase): compression = zipfile.ZIP_STORED zip_with_bad_crc = ( b'PK\003\004\024\0\0\0\0\0 \213\212;:r' b'\253\377\f\0\0\0\f\0\0\0\005\0\0\000af' b'ilehello,AworldP' b'K\001\002\024\003\024\0\0\0\0\0 \213\212;:' b'r\253\377\f\0\0\0\f\0\0\0\005\0\0\0\0' b'\0\0\0\0\0\0\0\200\001\0\0\0\000afi' b'lePK\005\006\0\0\0\0\001\0\001\0003\000' b'\0\0/\0\0\0\0\0') @requires_zlib class DeflateBadCrcTests(AbstractBadCrcTests, unittest.TestCase): compression = zipfile.ZIP_DEFLATED zip_with_bad_crc = ( b'PK\x03\x04\x14\x00\x00\x00\x08\x00n}\x0c=FA' b'KE\x10\x00\x00\x00n\x00\x00\x00\x05\x00\x00\x00af' b'ile\xcbH\xcd\xc9\xc9W(\xcf/\xcaI\xc9\xa0' b'=\x13\x00PK\x01\x02\x14\x03\x14\x00\x00\x00\x08\x00n' b'}\x0c=FAKE\x10\x00\x00\x00n\x00\x00\x00\x05' b'\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x80\x01\x00\x00\x00' b'\x00afilePK\x05\x06\x00\x00\x00\x00\x01\x00' b'\x01\x003\x00\x00\x003\x00\x00\x00\x00\x00') @requires_bz2 class Bzip2BadCrcTests(AbstractBadCrcTests, unittest.TestCase): compression = zipfile.ZIP_BZIP2 zip_with_bad_crc = ( b'PK\x03\x04\x14\x03\x00\x00\x0c\x00nu\x0c=FA' b'KE8\x00\x00\x00n\x00\x00\x00\x05\x00\x00\x00af' b'ileBZh91AY&SY\xd4\xa8\xca' b'\x7f\x00\x00\x0f\x11\x80@\x00\x06D\x90\x80 \x00 \xa5' b'P\xd9!\x03\x03\x13\x13\x13\x89\xa9\xa9\xc2u5:\x9f' b'\x8b\xb9"\x9c(HjTe?\x80PK\x01\x02\x14' b'\x03\x14\x03\x00\x00\x0c\x00nu\x0c=FAKE8' b'\x00\x00\x00n\x00\x00\x00\x05\x00\x00\x00\x00\x00\x00\x00\x00' b'\x00 \x80\x80\x81\x00\x00\x00\x00afilePK' b'\x05\x06\x00\x00\x00\x00\x01\x00\x01\x003\x00\x00\x00[\x00' b'\x00\x00\x00\x00') @requires_lzma class LzmaBadCrcTests(AbstractBadCrcTests, unittest.TestCase): compression = zipfile.ZIP_LZMA zip_with_bad_crc = ( b'PK\x03\x04\x14\x03\x00\x00\x0e\x00nu\x0c=FA' b'KE\x1b\x00\x00\x00n\x00\x00\x00\x05\x00\x00\x00af' b'ile\t\x04\x05\x00]\x00\x00\x00\x04\x004\x19I' b'\xee\x8d\xe9\x17\x89:3`\tq!.8\x00PK' b'\x01\x02\x14\x03\x14\x03\x00\x00\x0e\x00nu\x0c=FA' b'KE\x1b\x00\x00\x00n\x00\x00\x00\x05\x00\x00\x00\x00\x00' b'\x00\x00\x00\x00 \x80\x80\x81\x00\x00\x00\x00afil' b'ePK\x05\x06\x00\x00\x00\x00\x01\x00\x01\x003\x00\x00' b'\x00>\x00\x00\x00\x00\x00') class DecryptionTests(unittest.TestCase): """Check that ZIP decryption works. Since the library does not support encryption at the moment, we use a pre-generated encrypted ZIP file.""" data = ( b'PK\x03\x04\x14\x00\x01\x00\x00\x00n\x92i.#y\xef?&\x00\x00\x00\x1a\x00' b'\x00\x00\x08\x00\x00\x00test.txt\xfa\x10\xa0gly|\xfa-\xc5\xc0=\xf9y' b'\x18\xe0\xa8r\xb3Z}Lg\xbc\xae\xf9|\x9b\x19\xe4\x8b\xba\xbb)\x8c\xb0\xdbl' b'PK\x01\x02\x14\x00\x14\x00\x01\x00\x00\x00n\x92i.#y\xef?&\x00\x00\x00' b'\x1a\x00\x00\x00\x08\x00\x00\x00\x00\x00\x00\x00\x01\x00 \x00\xb6\x81' b'\x00\x00\x00\x00test.txtPK\x05\x06\x00\x00\x00\x00\x01\x00\x01\x006\x00' b'\x00\x00L\x00\x00\x00\x00\x00' ) data2 = ( b'PK\x03\x04\x14\x00\t\x00\x08\x00\xcf}38xu\xaa\xb2\x14\x00\x00\x00\x00\x02' b'\x00\x00\x04\x00\x15\x00zeroUT\t\x00\x03\xd6\x8b\x92G\xda\x8b\x92GUx\x04' b'\x00\xe8\x03\xe8\x03\xc7= 3.2') def test_unicode_password(self): expected_msg = "pwd: expected bytes, got str" with self.assertRaisesRegex(TypeError, expected_msg): self.zip.setpassword("unicode") with self.assertRaisesRegex(TypeError, expected_msg): self.zip.read("test.txt", "python") with self.assertRaisesRegex(TypeError, expected_msg): self.zip.open("test.txt", pwd="python") with self.assertRaisesRegex(TypeError, expected_msg): self.zip.extract("test.txt", pwd="python") with self.assertRaisesRegex(TypeError, expected_msg): self.zip.pwd = "python" self.zip.open("test.txt") def test_seek_tell(self): self.zip.setpassword(b"python") txt = self.plain test_word = b'encryption' bloc = txt.find(test_word) bloc_len = len(test_word) with self.zip.open("test.txt", "r") as fp: fp.seek(bloc, os.SEEK_SET) self.assertEqual(fp.tell(), bloc) fp.seek(-bloc, os.SEEK_CUR) self.assertEqual(fp.tell(), 0) fp.seek(bloc, os.SEEK_CUR) self.assertEqual(fp.tell(), bloc) self.assertEqual(fp.read(bloc_len), txt[bloc:bloc+bloc_len]) # Make sure that the second read after seeking back beyond # _readbuffer returns the same content (ie. rewind to the start of # the file to read forward to the required position). old_read_size = fp.MIN_READ_SIZE fp.MIN_READ_SIZE = 1 fp._readbuffer = b'' fp._offset = 0 fp.seek(0, os.SEEK_SET) self.assertEqual(fp.tell(), 0) fp.seek(bloc, os.SEEK_CUR) self.assertEqual(fp.read(bloc_len), txt[bloc:bloc+bloc_len]) fp.MIN_READ_SIZE = old_read_size fp.seek(0, os.SEEK_END) self.assertEqual(fp.tell(), len(txt)) fp.seek(0, os.SEEK_SET) self.assertEqual(fp.tell(), 0) # Read the file completely to definitely call any eof integrity # checks (crc) and make sure they still pass. fp.read() class AbstractTestsWithRandomBinaryFiles: @classmethod def setUpClass(cls): datacount = randint(16, 64)*1024 + randint(1, 1024) cls.data = b''.join(struct.pack('e|f"g?h*i', ','), r'a\b,c_d_e_f_g_h_i') self.assertEqual(san('../../foo../../ba..r', '/'), r'foo/ba..r') def test_extract_hackers_arcnames_common_cases(self): common_hacknames = [ ('../foo/bar', 'foo/bar'), ('foo/../bar', 'foo/bar'), ('foo/../../bar', 'foo/bar'), ('foo/bar/..', 'foo/bar'), ('./../foo/bar', 'foo/bar'), ('/foo/bar', 'foo/bar'), ('/foo/../bar', 'foo/bar'), ('/foo/../../bar', 'foo/bar'), ] self._test_extract_hackers_arcnames(common_hacknames) @unittest.skipIf(os.path.sep != '\\', 'Requires \\ as path separator.') def test_extract_hackers_arcnames_windows_only(self): """Test combination of path fixing and windows name sanitization.""" windows_hacknames = [ (r'..\foo\bar', 'foo/bar'), (r'..\/foo\/bar', 'foo/bar'), (r'foo/\..\/bar', 'foo/bar'), (r'foo\/../\bar', 'foo/bar'), (r'C:foo/bar', 'foo/bar'), (r'C:/foo/bar', 'foo/bar'), (r'C://foo/bar', 'foo/bar'), (r'C:\foo\bar', 'foo/bar'), (r'//conky/mountpoint/foo/bar', 'foo/bar'), (r'\\conky\mountpoint\foo\bar', 'foo/bar'), (r'///conky/mountpoint/foo/bar', 'conky/mountpoint/foo/bar'), (r'\\\conky\mountpoint\foo\bar', 'conky/mountpoint/foo/bar'), (r'//conky//mountpoint/foo/bar', 'conky/mountpoint/foo/bar'), (r'\\conky\\mountpoint\foo\bar', 'conky/mountpoint/foo/bar'), (r'//?/C:/foo/bar', 'foo/bar'), (r'\\?\C:\foo\bar', 'foo/bar'), (r'C:/../C:/foo/bar', 'C_/foo/bar'), (r'a:b\ce|f"g?h*i', 'b/c_d_e_f_g_h_i'), ('../../foo../../ba..r', 'foo/ba..r'), ] self._test_extract_hackers_arcnames(windows_hacknames) @unittest.skipIf(os.path.sep != '/', r'Requires / as path separator.') def test_extract_hackers_arcnames_posix_only(self): posix_hacknames = [ ('//foo/bar', 'foo/bar'), ('../../foo../../ba..r', 'foo../ba..r'), (r'foo/..\bar', r'foo/..\bar'), ] self._test_extract_hackers_arcnames(posix_hacknames) def _test_extract_hackers_arcnames(self, hacknames): for arcname, fixedname in hacknames: content = b'foobar' + arcname.encode() with zipfile.ZipFile(TESTFN2, 'w', zipfile.ZIP_STORED) as zipfp: zinfo = zipfile.ZipInfo() # preserve backslashes zinfo.filename = arcname zinfo.external_attr = 0o600 << 16 zipfp.writestr(zinfo, content) arcname = arcname.replace(os.sep, "/") targetpath = os.path.join('target', 'subdir', 'subsub') correctfile = os.path.join(targetpath, *fixedname.split('/')) with zipfile.ZipFile(TESTFN2, 'r') as zipfp: writtenfile = zipfp.extract(arcname, targetpath) self.assertEqual(writtenfile, correctfile, msg='extract %r: %r != %r' % (arcname, writtenfile, correctfile)) self.check_file(correctfile, content) rmtree('target') with zipfile.ZipFile(TESTFN2, 'r') as zipfp: zipfp.extractall(targetpath) self.check_file(correctfile, content) rmtree('target') correctfile = os.path.join(os.getcwd(), *fixedname.split('/')) with zipfile.ZipFile(TESTFN2, 'r') as zipfp: writtenfile = zipfp.extract(arcname) self.assertEqual(writtenfile, correctfile, msg="extract %r" % arcname) self.check_file(correctfile, content) rmtree(fixedname.split('/')[0]) with zipfile.ZipFile(TESTFN2, 'r') as zipfp: zipfp.extractall() self.check_file(correctfile, content) rmtree(fixedname.split('/')[0]) unlink(TESTFN2) class OtherTests(unittest.TestCase): def test_open_via_zip_info(self): # Create the ZIP archive with zipfile.ZipFile(TESTFN2, "w", zipfile.ZIP_STORED) as zipfp: zipfp.writestr("name", "foo") with self.assertWarns(UserWarning): zipfp.writestr("name", "bar") self.assertEqual(zipfp.namelist(), ["name"] * 2) with zipfile.ZipFile(TESTFN2, "r") as zipfp: infos = zipfp.infolist() data = b"" for info in infos: with zipfp.open(info) as zipopen: data += zipopen.read() self.assertIn(data, {b"foobar", b"barfoo"}) data = b"" for info in infos: data += zipfp.read(info) self.assertIn(data, {b"foobar", b"barfoo"}) def test_writestr_extended_local_header_issue1202(self): with zipfile.ZipFile(TESTFN2, 'w') as orig_zip: for data in 'abcdefghijklmnop': zinfo = zipfile.ZipInfo(data) zinfo.flag_bits |= 0x08 # Include an extended local header. orig_zip.writestr(zinfo, data) def test_close(self): """Check that the zipfile is closed after the 'with' block.""" with zipfile.ZipFile(TESTFN2, "w") as zipfp: for fpath, fdata in SMALL_TEST_DATA: zipfp.writestr(fpath, fdata) self.assertIsNotNone(zipfp.fp, 'zipfp is not open') self.assertIsNone(zipfp.fp, 'zipfp is not closed') with zipfile.ZipFile(TESTFN2, "r") as zipfp: self.assertIsNotNone(zipfp.fp, 'zipfp is not open') self.assertIsNone(zipfp.fp, 'zipfp is not closed') def test_close_on_exception(self): """Check that the zipfile is closed if an exception is raised in the 'with' block.""" with zipfile.ZipFile(TESTFN2, "w") as zipfp: for fpath, fdata in SMALL_TEST_DATA: zipfp.writestr(fpath, fdata) try: with zipfile.ZipFile(TESTFN2, "r") as zipfp2: raise zipfile.BadZipFile() except zipfile.BadZipFile: self.assertIsNone(zipfp2.fp, 'zipfp is not closed') def test_unsupported_version(self): # File has an extract_version of 120 data = (b'PK\x03\x04x\x00\x00\x00\x00\x00!p\xa1@\x00\x00\x00\x00\x00\x00' b'\x00\x00\x00\x00\x00\x00\x01\x00\x00\x00xPK\x01\x02x\x03x\x00\x00\x00\x00' b'\x00!p\xa1@\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x01\x00\x00' b'\x00\x00\x00\x00\x00\x00\x00\x00\x00\x80\x01\x00\x00\x00\x00xPK\x05\x06' b'\x00\x00\x00\x00\x01\x00\x01\x00/\x00\x00\x00\x1f\x00\x00\x00\x00\x00') self.assertRaises(NotImplementedError, zipfile.ZipFile, io.BytesIO(data), 'r') @requires_zlib def test_read_unicode_filenames(self): # bug #10801 fname = findfile('zip_cp437_header.zip') with zipfile.ZipFile(fname) as zipfp: for name in zipfp.namelist(): zipfp.open(name).close() def test_write_unicode_filenames(self): with zipfile.ZipFile(TESTFN, "w") as zf: zf.writestr("foo.txt", "Test for unicode filename") zf.writestr("\xf6.txt", "Test for unicode filename") self.assertIsInstance(zf.infolist()[0].filename, str) with zipfile.ZipFile(TESTFN, "r") as zf: self.assertEqual(zf.filelist[0].filename, "foo.txt") self.assertEqual(zf.filelist[1].filename, "\xf6.txt") def test_exclusive_create_zip_file(self): """Test exclusive creating a new zipfile.""" unlink(TESTFN2) filename = 'testfile.txt' content = b'hello, world. this is some content.' with zipfile.ZipFile(TESTFN2, "x", zipfile.ZIP_STORED) as zipfp: zipfp.writestr(filename, content) with self.assertRaises(FileExistsError): zipfile.ZipFile(TESTFN2, "x", zipfile.ZIP_STORED) with zipfile.ZipFile(TESTFN2, "r") as zipfp: self.assertEqual(zipfp.namelist(), [filename]) self.assertEqual(zipfp.read(filename), content) def test_create_non_existent_file_for_append(self): if os.path.exists(TESTFN): os.unlink(TESTFN) filename = 'testfile.txt' content = b'hello, world. this is some content.' try: with zipfile.ZipFile(TESTFN, 'a') as zf: zf.writestr(filename, content) except OSError: self.fail('Could not append data to a non-existent zip file.') self.assertTrue(os.path.exists(TESTFN)) with zipfile.ZipFile(TESTFN, 'r') as zf: self.assertEqual(zf.read(filename), content) def test_close_erroneous_file(self): # This test checks that the ZipFile constructor closes the file object # it opens if there's an error in the file. If it doesn't, the # traceback holds a reference to the ZipFile object and, indirectly, # the file object. # On Windows, this causes the os.unlink() call to fail because the # underlying file is still open. This is SF bug #412214. # with open(TESTFN, "w") as fp: fp.write("this is not a legal zip file\n") try: zf = zipfile.ZipFile(TESTFN) except zipfile.BadZipFile: pass def test_is_zip_erroneous_file(self): """Check that is_zipfile() correctly identifies non-zip files.""" # - passing a filename with open(TESTFN, "w") as fp: fp.write("this is not a legal zip file\n") self.assertFalse(zipfile.is_zipfile(TESTFN)) # - passing a path-like object self.assertFalse(zipfile.is_zipfile(pathlib.Path(TESTFN))) # - passing a file object with open(TESTFN, "rb") as fp: self.assertFalse(zipfile.is_zipfile(fp)) # - passing a file-like object fp = io.BytesIO() fp.write(b"this is not a legal zip file\n") self.assertFalse(zipfile.is_zipfile(fp)) fp.seek(0, 0) self.assertFalse(zipfile.is_zipfile(fp)) def test_damaged_zipfile(self): """Check that zipfiles with missing bytes at the end raise BadZipFile.""" # - Create a valid zip file fp = io.BytesIO() with zipfile.ZipFile(fp, mode="w") as zipf: zipf.writestr("foo.txt", b"O, for a Muse of Fire!") zipfiledata = fp.getvalue() # - Now create copies of it missing the last N bytes and make sure # a BadZipFile exception is raised when we try to open it for N in range(len(zipfiledata)): fp = io.BytesIO(zipfiledata[:N]) self.assertRaises(zipfile.BadZipFile, zipfile.ZipFile, fp) def test_is_zip_valid_file(self): """Check that is_zipfile() correctly identifies zip files.""" # - passing a filename with zipfile.ZipFile(TESTFN, mode="w") as zipf: zipf.writestr("foo.txt", b"O, for a Muse of Fire!") self.assertTrue(zipfile.is_zipfile(TESTFN)) # - passing a file object with open(TESTFN, "rb") as fp: self.assertTrue(zipfile.is_zipfile(fp)) fp.seek(0, 0) zip_contents = fp.read() # - passing a file-like object fp = io.BytesIO() fp.write(zip_contents) self.assertTrue(zipfile.is_zipfile(fp)) fp.seek(0, 0) self.assertTrue(zipfile.is_zipfile(fp)) def test_non_existent_file_raises_OSError(self): # make sure we don't raise an AttributeError when a partially-constructed # ZipFile instance is finalized; this tests for regression on SF tracker # bug #403871. # The bug we're testing for caused an AttributeError to be raised # when a ZipFile instance was created for a file that did not # exist; the .fp member was not initialized but was needed by the # __del__() method. Since the AttributeError is in the __del__(), # it is ignored, but the user should be sufficiently annoyed by # the message on the output that regression will be noticed # quickly. self.assertRaises(OSError, zipfile.ZipFile, TESTFN) def test_empty_file_raises_BadZipFile(self): f = open(TESTFN, 'w') f.close() self.assertRaises(zipfile.BadZipFile, zipfile.ZipFile, TESTFN) with open(TESTFN, 'w') as fp: fp.write("short file") self.assertRaises(zipfile.BadZipFile, zipfile.ZipFile, TESTFN) def test_closed_zip_raises_ValueError(self): """Verify that testzip() doesn't swallow inappropriate exceptions.""" data = io.BytesIO() with zipfile.ZipFile(data, mode="w") as zipf: zipf.writestr("foo.txt", "O, for a Muse of Fire!") # This is correct; calling .read on a closed ZipFile should raise # a ValueError, and so should calling .testzip. An earlier # version of .testzip would swallow this exception (and any other) # and report that the first file in the archive was corrupt. self.assertRaises(ValueError, zipf.read, "foo.txt") self.assertRaises(ValueError, zipf.open, "foo.txt") self.assertRaises(ValueError, zipf.testzip) self.assertRaises(ValueError, zipf.writestr, "bogus.txt", "bogus") with open(TESTFN, 'w') as f: f.write('zipfile test data') self.assertRaises(ValueError, zipf.write, TESTFN) def test_bad_constructor_mode(self): """Check that bad modes passed to ZipFile constructor are caught.""" self.assertRaises(ValueError, zipfile.ZipFile, TESTFN, "q") def test_bad_open_mode(self): """Check that bad modes passed to ZipFile.open are caught.""" with zipfile.ZipFile(TESTFN, mode="w") as zipf: zipf.writestr("foo.txt", "O, for a Muse of Fire!") with zipfile.ZipFile(TESTFN, mode="r") as zipf: # read the data to make sure the file is there zipf.read("foo.txt") self.assertRaises(ValueError, zipf.open, "foo.txt", "q") # universal newlines support is removed self.assertRaises(ValueError, zipf.open, "foo.txt", "U") self.assertRaises(ValueError, zipf.open, "foo.txt", "rU") def test_read0(self): """Check that calling read(0) on a ZipExtFile object returns an empty string and doesn't advance file pointer.""" with zipfile.ZipFile(TESTFN, mode="w") as zipf: zipf.writestr("foo.txt", "O, for a Muse of Fire!") # read the data to make sure the file is there with zipf.open("foo.txt") as f: for i in range(FIXEDTEST_SIZE): self.assertEqual(f.read(0), b'') self.assertEqual(f.read(), b"O, for a Muse of Fire!") def test_open_non_existent_item(self): """Check that attempting to call open() for an item that doesn't exist in the archive raises a RuntimeError.""" with zipfile.ZipFile(TESTFN, mode="w") as zipf: self.assertRaises(KeyError, zipf.open, "foo.txt", "r") def test_bad_compression_mode(self): """Check that bad compression methods passed to ZipFile.open are caught.""" self.assertRaises(NotImplementedError, zipfile.ZipFile, TESTFN, "w", -1) def test_unsupported_compression(self): # data is declared as shrunk, but actually deflated data = (b'PK\x03\x04.\x00\x00\x00\x01\x00\xe4C\xa1@\x00\x00\x00' b'\x00\x02\x00\x00\x00\x00\x00\x00\x00\x01\x00\x00\x00x\x03\x00PK\x01' b'\x02.\x03.\x00\x00\x00\x01\x00\xe4C\xa1@\x00\x00\x00\x00\x02\x00\x00' b'\x00\x00\x00\x00\x00\x01\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00' b'\x80\x01\x00\x00\x00\x00xPK\x05\x06\x00\x00\x00\x00\x01\x00\x01\x00' b'/\x00\x00\x00!\x00\x00\x00\x00\x00') with zipfile.ZipFile(io.BytesIO(data), 'r') as zipf: self.assertRaises(NotImplementedError, zipf.open, 'x') def test_null_byte_in_filename(self): """Check that a filename containing a null byte is properly terminated.""" with zipfile.ZipFile(TESTFN, mode="w") as zipf: zipf.writestr("foo.txt\x00qqq", b"O, for a Muse of Fire!") self.assertEqual(zipf.namelist(), ['foo.txt']) def test_struct_sizes(self): """Check that ZIP internal structure sizes are calculated correctly.""" self.assertEqual(zipfile.sizeEndCentDir, 22) self.assertEqual(zipfile.sizeCentralDir, 46) self.assertEqual(zipfile.sizeEndCentDir64, 56) self.assertEqual(zipfile.sizeEndCentDir64Locator, 20) def test_comments(self): """Check that comments on the archive are handled properly.""" # check default comment is empty with zipfile.ZipFile(TESTFN, mode="w") as zipf: self.assertEqual(zipf.comment, b'') zipf.writestr("foo.txt", "O, for a Muse of Fire!") with zipfile.ZipFile(TESTFN, mode="r") as zipfr: self.assertEqual(zipfr.comment, b'') # check a simple short comment comment = b'Bravely taking to his feet, he beat a very brave retreat.' with zipfile.ZipFile(TESTFN, mode="w") as zipf: zipf.comment = comment zipf.writestr("foo.txt", "O, for a Muse of Fire!") with zipfile.ZipFile(TESTFN, mode="r") as zipfr: self.assertEqual(zipf.comment, comment) # check a comment of max length comment2 = ''.join(['%d' % (i**3 % 10) for i in range((1 << 16)-1)]) comment2 = comment2.encode("ascii") with zipfile.ZipFile(TESTFN, mode="w") as zipf: zipf.comment = comment2 zipf.writestr("foo.txt", "O, for a Muse of Fire!") with zipfile.ZipFile(TESTFN, mode="r") as zipfr: self.assertEqual(zipfr.comment, comment2) # check a comment that is too long is truncated with zipfile.ZipFile(TESTFN, mode="w") as zipf: with self.assertWarns(UserWarning): zipf.comment = comment2 + b'oops' zipf.writestr("foo.txt", "O, for a Muse of Fire!") with zipfile.ZipFile(TESTFN, mode="r") as zipfr: self.assertEqual(zipfr.comment, comment2) # check that comments are correctly modified in append mode with zipfile.ZipFile(TESTFN,mode="w") as zipf: zipf.comment = b"original comment" zipf.writestr("foo.txt", "O, for a Muse of Fire!") with zipfile.ZipFile(TESTFN,mode="a") as zipf: zipf.comment = b"an updated comment" with zipfile.ZipFile(TESTFN,mode="r") as zipf: self.assertEqual(zipf.comment, b"an updated comment") # check that comments are correctly shortened in append mode with zipfile.ZipFile(TESTFN,mode="w") as zipf: zipf.comment = b"original comment that's longer" zipf.writestr("foo.txt", "O, for a Muse of Fire!") with zipfile.ZipFile(TESTFN,mode="a") as zipf: zipf.comment = b"shorter comment" with zipfile.ZipFile(TESTFN,mode="r") as zipf: self.assertEqual(zipf.comment, b"shorter comment") def test_unicode_comment(self): with zipfile.ZipFile(TESTFN, "w", zipfile.ZIP_STORED) as zipf: zipf.writestr("foo.txt", "O, for a Muse of Fire!") with self.assertRaises(TypeError): zipf.comment = "this is an error" def test_change_comment_in_empty_archive(self): with zipfile.ZipFile(TESTFN, "a", zipfile.ZIP_STORED) as zipf: self.assertFalse(zipf.filelist) zipf.comment = b"this is a comment" with zipfile.ZipFile(TESTFN, "r") as zipf: self.assertEqual(zipf.comment, b"this is a comment") def test_change_comment_in_nonempty_archive(self): with zipfile.ZipFile(TESTFN, "w", zipfile.ZIP_STORED) as zipf: zipf.writestr("foo.txt", "O, for a Muse of Fire!") with zipfile.ZipFile(TESTFN, "a", zipfile.ZIP_STORED) as zipf: self.assertTrue(zipf.filelist) zipf.comment = b"this is a comment" with zipfile.ZipFile(TESTFN, "r") as zipf: self.assertEqual(zipf.comment, b"this is a comment") def test_empty_zipfile(self): # Check that creating a file in 'w' or 'a' mode and closing without # adding any files to the archives creates a valid empty ZIP file zipf = zipfile.ZipFile(TESTFN, mode="w") zipf.close() try: zipf = zipfile.ZipFile(TESTFN, mode="r") except zipfile.BadZipFile: self.fail("Unable to create empty ZIP file in 'w' mode") zipf = zipfile.ZipFile(TESTFN, mode="a") zipf.close() try: zipf = zipfile.ZipFile(TESTFN, mode="r") except: self.fail("Unable to create empty ZIP file in 'a' mode") def test_open_empty_file(self): # Issue 1710703: Check that opening a file with less than 22 bytes # raises a BadZipFile exception (rather than the previously unhelpful # OSError) f = open(TESTFN, 'w') f.close() self.assertRaises(zipfile.BadZipFile, zipfile.ZipFile, TESTFN, 'r') def test_create_zipinfo_before_1980(self): self.assertRaises(ValueError, zipfile.ZipInfo, 'seventies', (1979, 1, 1, 0, 0, 0)) def test_zipfile_with_short_extra_field(self): """If an extra field in the header is less than 4 bytes, skip it.""" zipdata = ( b'PK\x03\x04\x14\x00\x00\x00\x00\x00\x93\x9b\xad@\x8b\x9e' b'\xd9\xd3\x01\x00\x00\x00\x01\x00\x00\x00\x03\x00\x03\x00ab' b'c\x00\x00\x00APK\x01\x02\x14\x03\x14\x00\x00\x00\x00' b'\x00\x93\x9b\xad@\x8b\x9e\xd9\xd3\x01\x00\x00\x00\x01\x00\x00' b'\x00\x03\x00\x02\x00\x00\x00\x00\x00\x00\x00\x00\x00\xa4\x81\x00' b'\x00\x00\x00abc\x00\x00PK\x05\x06\x00\x00\x00\x00' b'\x01\x00\x01\x003\x00\x00\x00%\x00\x00\x00\x00\x00' ) with zipfile.ZipFile(io.BytesIO(zipdata), 'r') as zipf: # testzip returns the name of the first corrupt file, or None self.assertIsNone(zipf.testzip()) def test_open_conflicting_handles(self): # It's only possible to open one writable file handle at a time msg1 = b"It's fun to charter an accountant!" msg2 = b"And sail the wide accountant sea" msg3 = b"To find, explore the funds offshore" with zipfile.ZipFile(TESTFN2, 'w', zipfile.ZIP_STORED) as zipf: with zipf.open('foo', mode='w') as w2: w2.write(msg1) with zipf.open('bar', mode='w') as w1: with self.assertRaises(ValueError): zipf.open('handle', mode='w') with self.assertRaises(ValueError): zipf.open('foo', mode='r') with self.assertRaises(ValueError): zipf.writestr('str', 'abcde') with self.assertRaises(ValueError): zipf.write(__file__, 'file') with self.assertRaises(ValueError): zipf.close() w1.write(msg2) with zipf.open('baz', mode='w') as w2: w2.write(msg3) with zipfile.ZipFile(TESTFN2, 'r') as zipf: self.assertEqual(zipf.read('foo'), msg1) self.assertEqual(zipf.read('bar'), msg2) self.assertEqual(zipf.read('baz'), msg3) self.assertEqual(zipf.namelist(), ['foo', 'bar', 'baz']) def test_seek_tell(self): # Test seek functionality txt = b"Where's Bruce?" bloc = txt.find(b"Bruce") # Check seek on a file with zipfile.ZipFile(TESTFN, "w") as zipf: zipf.writestr("foo.txt", txt) with zipfile.ZipFile(TESTFN, "r") as zipf: with zipf.open("foo.txt", "r") as fp: fp.seek(bloc, os.SEEK_SET) self.assertEqual(fp.tell(), bloc) fp.seek(-bloc, os.SEEK_CUR) self.assertEqual(fp.tell(), 0) fp.seek(bloc, os.SEEK_CUR) self.assertEqual(fp.tell(), bloc) self.assertEqual(fp.read(5), txt[bloc:bloc+5]) fp.seek(0, os.SEEK_END) self.assertEqual(fp.tell(), len(txt)) fp.seek(0, os.SEEK_SET) self.assertEqual(fp.tell(), 0) # Check seek on memory file data = io.BytesIO() with zipfile.ZipFile(data, mode="w") as zipf: zipf.writestr("foo.txt", txt) with zipfile.ZipFile(data, mode="r") as zipf: with zipf.open("foo.txt", "r") as fp: fp.seek(bloc, os.SEEK_SET) self.assertEqual(fp.tell(), bloc) fp.seek(-bloc, os.SEEK_CUR) self.assertEqual(fp.tell(), 0) fp.seek(bloc, os.SEEK_CUR) self.assertEqual(fp.tell(), bloc) self.assertEqual(fp.read(5), txt[bloc:bloc+5]) fp.seek(0, os.SEEK_END) self.assertEqual(fp.tell(), len(txt)) fp.seek(0, os.SEEK_SET) self.assertEqual(fp.tell(), 0) def tearDown(self): unlink(TESTFN) unlink(TESTFN2) class AbstractBadCrcTests: def test_testzip_with_bad_crc(self): """Tests that files with bad CRCs return their name from testzip.""" zipdata = self.zip_with_bad_crc with zipfile.ZipFile(io.BytesIO(zipdata), mode="r") as zipf: # testzip returns the name of the first corrupt file, or None self.assertEqual('afile', zipf.testzip()) def test_read_with_bad_crc(self): """Tests that files with bad CRCs raise a BadZipFile exception when read.""" zipdata = self.zip_with_bad_crc # Using ZipFile.read() with zipfile.ZipFile(io.BytesIO(zipdata), mode="r") as zipf: self.assertRaises(zipfile.BadZipFile, zipf.read, 'afile') # Using ZipExtFile.read() with zipfile.ZipFile(io.BytesIO(zipdata), mode="r") as zipf: with zipf.open('afile', 'r') as corrupt_file: self.assertRaises(zipfile.BadZipFile, corrupt_file.read) # Same with small reads (in order to exercise the buffering logic) with zipfile.ZipFile(io.BytesIO(zipdata), mode="r") as zipf: with zipf.open('afile', 'r') as corrupt_file: corrupt_file.MIN_READ_SIZE = 2 with self.assertRaises(zipfile.BadZipFile): while corrupt_file.read(2): pass class StoredBadCrcTests(AbstractBadCrcTests, unittest.TestCase): compression = zipfile.ZIP_STORED zip_with_bad_crc = ( b'PK\003\004\024\0\0\0\0\0 \213\212;:r' b'\253\377\f\0\0\0\f\0\0\0\005\0\0\000af' b'ilehello,AworldP' b'K\001\002\024\003\024\0\0\0\0\0 \213\212;:' b'r\253\377\f\0\0\0\f\0\0\0\005\0\0\0\0' b'\0\0\0\0\0\0\0\200\001\0\0\0\000afi' b'lePK\005\006\0\0\0\0\001\0\001\0003\000' b'\0\0/\0\0\0\0\0') @requires_zlib class DeflateBadCrcTests(AbstractBadCrcTests, unittest.TestCase): compression = zipfile.ZIP_DEFLATED zip_with_bad_crc = ( b'PK\x03\x04\x14\x00\x00\x00\x08\x00n}\x0c=FA' b'KE\x10\x00\x00\x00n\x00\x00\x00\x05\x00\x00\x00af' b'ile\xcbH\xcd\xc9\xc9W(\xcf/\xcaI\xc9\xa0' b'=\x13\x00PK\x01\x02\x14\x03\x14\x00\x00\x00\x08\x00n' b'}\x0c=FAKE\x10\x00\x00\x00n\x00\x00\x00\x05' b'\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x80\x01\x00\x00\x00' b'\x00afilePK\x05\x06\x00\x00\x00\x00\x01\x00' b'\x01\x003\x00\x00\x003\x00\x00\x00\x00\x00') @requires_bz2 class Bzip2BadCrcTests(AbstractBadCrcTests, unittest.TestCase): compression = zipfile.ZIP_BZIP2 zip_with_bad_crc = ( b'PK\x03\x04\x14\x03\x00\x00\x0c\x00nu\x0c=FA' b'KE8\x00\x00\x00n\x00\x00\x00\x05\x00\x00\x00af' b'ileBZh91AY&SY\xd4\xa8\xca' b'\x7f\x00\x00\x0f\x11\x80@\x00\x06D\x90\x80 \x00 \xa5' b'P\xd9!\x03\x03\x13\x13\x13\x89\xa9\xa9\xc2u5:\x9f' b'\x8b\xb9"\x9c(HjTe?\x80PK\x01\x02\x14' b'\x03\x14\x03\x00\x00\x0c\x00nu\x0c=FAKE8' b'\x00\x00\x00n\x00\x00\x00\x05\x00\x00\x00\x00\x00\x00\x00\x00' b'\x00 \x80\x80\x81\x00\x00\x00\x00afilePK' b'\x05\x06\x00\x00\x00\x00\x01\x00\x01\x003\x00\x00\x00[\x00' b'\x00\x00\x00\x00') @requires_lzma class LzmaBadCrcTests(AbstractBadCrcTests, unittest.TestCase): compression = zipfile.ZIP_LZMA zip_with_bad_crc = ( b'PK\x03\x04\x14\x03\x00\x00\x0e\x00nu\x0c=FA' b'KE\x1b\x00\x00\x00n\x00\x00\x00\x05\x00\x00\x00af' b'ile\t\x04\x05\x00]\x00\x00\x00\x04\x004\x19I' b'\xee\x8d\xe9\x17\x89:3`\tq!.8\x00PK' b'\x01\x02\x14\x03\x14\x03\x00\x00\x0e\x00nu\x0c=FA' b'KE\x1b\x00\x00\x00n\x00\x00\x00\x05\x00\x00\x00\x00\x00' b'\x00\x00\x00\x00 \x80\x80\x81\x00\x00\x00\x00afil' b'ePK\x05\x06\x00\x00\x00\x00\x01\x00\x01\x003\x00\x00' b'\x00>\x00\x00\x00\x00\x00') class DecryptionTests(unittest.TestCase): """Check that ZIP decryption works. Since the library does not support encryption at the moment, we use a pre-generated encrypted ZIP file.""" data = ( b'PK\x03\x04\x14\x00\x01\x00\x00\x00n\x92i.#y\xef?&\x00\x00\x00\x1a\x00' b'\x00\x00\x08\x00\x00\x00test.txt\xfa\x10\xa0gly|\xfa-\xc5\xc0=\xf9y' b'\x18\xe0\xa8r\xb3Z}Lg\xbc\xae\xf9|\x9b\x19\xe4\x8b\xba\xbb)\x8c\xb0\xdbl' b'PK\x01\x02\x14\x00\x14\x00\x01\x00\x00\x00n\x92i.#y\xef?&\x00\x00\x00' b'\x1a\x00\x00\x00\x08\x00\x00\x00\x00\x00\x00\x00\x01\x00 \x00\xb6\x81' b'\x00\x00\x00\x00test.txtPK\x05\x06\x00\x00\x00\x00\x01\x00\x01\x006\x00' b'\x00\x00L\x00\x00\x00\x00\x00' ) data2 = ( b'PK\x03\x04\x14\x00\t\x00\x08\x00\xcf}38xu\xaa\xb2\x14\x00\x00\x00\x00\x02' b'\x00\x00\x04\x00\x15\x00zeroUT\t\x00\x03\xd6\x8b\x92G\xda\x8b\x92GUx\x04' b'\x00\xe8\x03\xe8\x03\xc7= 3.5') class PyZipFileTests(unittest.TestCase): def assertCompiledIn(self, name, namelist): if name + 'o' not in namelist: self.assertIn(name + 'c', namelist) def requiresWriteAccess(self, path): # effective_ids unavailable on windows if not os.access(path, os.W_OK, effective_ids=os.access in os.supports_effective_ids): self.skipTest('requires write access to the installed location') filename = os.path.join(path, 'test_zipfile.try') try: fd = os.open(filename, os.O_WRONLY | os.O_CREAT) os.close(fd) except Exception: self.skipTest('requires write access to the installed location') unlink(filename) def test_write_pyfile(self): self.requiresWriteAccess(os.path.dirname(__file__)) with TemporaryFile() as t, zipfile.PyZipFile(t, "w") as zipfp: fn = __file__ if fn.endswith('.pyc'): path_split = fn.split(os.sep) if os.altsep is not None: path_split.extend(fn.split(os.altsep)) if '__pycache__' in path_split: fn = importlib.util.source_from_cache(fn) else: fn = fn[:-1] zipfp.writepy(fn) bn = os.path.basename(fn) self.assertNotIn(bn, zipfp.namelist()) self.assertCompiledIn(bn, zipfp.namelist()) with TemporaryFile() as t, zipfile.PyZipFile(t, "w") as zipfp: fn = __file__ if fn.endswith('.pyc'): fn = fn[:-1] zipfp.writepy(fn, "testpackage") bn = "%s/%s" % ("testpackage", os.path.basename(fn)) self.assertNotIn(bn, zipfp.namelist()) self.assertCompiledIn(bn, zipfp.namelist()) def test_write_python_package(self): import email packagedir = os.path.dirname(email.__file__) self.requiresWriteAccess(packagedir) with TemporaryFile() as t, zipfile.PyZipFile(t, "w") as zipfp: zipfp.writepy(packagedir) # Check for a couple of modules at different levels of the # hierarchy names = zipfp.namelist() self.assertCompiledIn('email/__init__.py', names) self.assertCompiledIn('email/mime/text.py', names) def test_write_filtered_python_package(self): import test packagedir = os.path.dirname(test.__file__) self.requiresWriteAccess(packagedir) with TemporaryFile() as t, zipfile.PyZipFile(t, "w") as zipfp: # first make sure that the test folder gives error messages # (on the badsyntax_... files) with captured_stdout() as reportSIO: zipfp.writepy(packagedir) reportStr = reportSIO.getvalue() self.assertTrue('SyntaxError' in reportStr) # then check that the filter works on the whole package with captured_stdout() as reportSIO: zipfp.writepy(packagedir, filterfunc=lambda whatever: False) reportStr = reportSIO.getvalue() self.assertTrue('SyntaxError' not in reportStr) # then check that the filter works on individual files def filter(path): return not os.path.basename(path).startswith("bad") with captured_stdout() as reportSIO, self.assertWarns(UserWarning): zipfp.writepy(packagedir, filterfunc=filter) reportStr = reportSIO.getvalue() if reportStr: print(reportStr) self.assertTrue('SyntaxError' not in reportStr) def test_write_with_optimization(self): import email packagedir = os.path.dirname(email.__file__) self.requiresWriteAccess(packagedir) optlevel = 1 if __debug__ else 0 ext = '.pyc' with TemporaryFile() as t, \ zipfile.PyZipFile(t, "w", optimize=optlevel) as zipfp: zipfp.writepy(packagedir) names = zipfp.namelist() self.assertIn('email/__init__' + ext, names) self.assertIn('email/mime/text' + ext, names) def test_write_python_directory(self): os.mkdir(TESTFN2) try: with open(os.path.join(TESTFN2, "mod1.py"), "w") as fp: fp.write("print(42)\n") with open(os.path.join(TESTFN2, "mod2.py"), "w") as fp: fp.write("print(42 * 42)\n") with open(os.path.join(TESTFN2, "mod2.txt"), "w") as fp: fp.write("bla bla bla\n") with TemporaryFile() as t, zipfile.PyZipFile(t, "w") as zipfp: zipfp.writepy(TESTFN2) names = zipfp.namelist() self.assertCompiledIn('mod1.py', names) self.assertCompiledIn('mod2.py', names) self.assertNotIn('mod2.txt', names) finally: rmtree(TESTFN2) def test_write_python_directory_filtered(self): os.mkdir(TESTFN2) try: with open(os.path.join(TESTFN2, "mod1.py"), "w") as fp: fp.write("print(42)\n") with open(os.path.join(TESTFN2, "mod2.py"), "w") as fp: fp.write("print(42 * 42)\n") with TemporaryFile() as t, zipfile.PyZipFile(t, "w") as zipfp: zipfp.writepy(TESTFN2, filterfunc=lambda fn: not fn.endswith('mod2.py')) names = zipfp.namelist() self.assertCompiledIn('mod1.py', names) self.assertNotIn('mod2.py', names) finally: rmtree(TESTFN2) def test_write_non_pyfile(self): with TemporaryFile() as t, zipfile.PyZipFile(t, "w") as zipfp: with open(TESTFN, 'w') as f: f.write('most definitely not a python file') self.assertRaises(RuntimeError, zipfp.writepy, TESTFN) unlink(TESTFN) def test_write_pyfile_bad_syntax(self): os.mkdir(TESTFN2) try: with open(os.path.join(TESTFN2, "mod1.py"), "w") as fp: fp.write("Bad syntax in python file\n") with TemporaryFile() as t, zipfile.PyZipFile(t, "w") as zipfp: # syntax errors are printed to stdout with captured_stdout() as s: zipfp.writepy(os.path.join(TESTFN2, "mod1.py")) self.assertIn("SyntaxError", s.getvalue()) # as it will not have compiled the python file, it will # include the .py file not .pyc names = zipfp.namelist() self.assertIn('mod1.py', names) self.assertNotIn('mod1.pyc', names) finally: rmtree(TESTFN2) def test_write_pathlike(self): os.mkdir(TESTFN2) try: with open(os.path.join(TESTFN2, "mod1.py"), "w") as fp: fp.write("print(42)\n") with TemporaryFile() as t, zipfile.PyZipFile(t, "w") as zipfp: zipfp.writepy(pathlib.Path(TESTFN2) / "mod1.py") names = zipfp.namelist() self.assertCompiledIn('mod1.py', names) finally: rmtree(TESTFN2) class ExtractTests(unittest.TestCase): def make_test_file(self): with zipfile_aes.AESZipFile(TESTFN2, "w", zipfile.ZIP_STORED) as zipfp: for fpath, fdata in SMALL_TEST_DATA: zipfp.writestr(fpath, fdata) def test_extract(self): with temp_cwd(): self.make_test_file() with zipfile_aes.AESZipFile(TESTFN2, "r") as zipfp: for fpath, fdata in SMALL_TEST_DATA: writtenfile = zipfp.extract(fpath) # make sure it was written to the right place correctfile = os.path.join(os.getcwd(), fpath) correctfile = os.path.normpath(correctfile) self.assertEqual(writtenfile, correctfile) # make sure correct data is in correct file with open(writtenfile, "rb") as f: self.assertEqual(fdata.encode(), f.read()) unlink(writtenfile) def _test_extract_with_target(self, target): self.make_test_file() with zipfile_aes.AESZipFile(TESTFN2, "r") as zipfp: for fpath, fdata in SMALL_TEST_DATA: writtenfile = zipfp.extract(fpath, target) # compat with Path objects were added in python 3.6 if sys.version_info[0:2] < (3, 6): target = str(target) # make sure it was written to the right place correctfile = os.path.join(target, fpath) correctfile = os.path.normpath(correctfile) self.assertTrue(os.path.samefile(writtenfile, correctfile), (writtenfile, target)) # make sure correct data is in correct file with open(writtenfile, "rb") as f: self.assertEqual(fdata.encode(), f.read()) unlink(writtenfile) unlink(TESTFN2) def test_extract_with_target(self): with temp_dir() as extdir: self._test_extract_with_target(extdir) def test_extract_with_target_pathlike(self): with temp_dir() as extdir: self._test_extract_with_target(pathlib.Path(extdir)) def test_extract_all(self): with temp_cwd(): self.make_test_file() with zipfile_aes.AESZipFile(TESTFN2, "r") as zipfp: zipfp.extractall() for fpath, fdata in SMALL_TEST_DATA: outfile = os.path.join(os.getcwd(), fpath) with open(outfile, "rb") as f: self.assertEqual(fdata.encode(), f.read()) unlink(outfile) def _test_extract_all_with_target(self, target): self.make_test_file() with zipfile_aes.AESZipFile(TESTFN2, "r") as zipfp: zipfp.extractall(target) for fpath, fdata in SMALL_TEST_DATA: # compat with Path objects were added in python 3.6 if sys.version_info[0:2] < (3, 6): target = str(target) outfile = os.path.join(str(target), fpath) with open(outfile, "rb") as f: self.assertEqual(fdata.encode(), f.read()) unlink(outfile) unlink(TESTFN2) def test_extract_all_with_target(self): with temp_dir() as extdir: self._test_extract_all_with_target(extdir) def test_extract_all_with_target_pathlike(self): with temp_dir() as extdir: self._test_extract_all_with_target(pathlib.Path(extdir)) def check_file(self, filename, content): self.assertTrue(os.path.isfile(filename)) with open(filename, 'rb') as f: self.assertEqual(f.read(), content) def test_sanitize_windows_name(self): san = zipfile_aes.AESZipFile._sanitize_windows_name # Passing pathsep in allows this test to work regardless of platform. self.assertEqual(san(r',,?,C:,foo,bar/z', ','), r'_,C_,foo,bar/z') self.assertEqual(san(r'a\b,ce|f"g?h*i', ','), r'a\b,c_d_e_f_g_h_i') self.assertEqual(san('../../foo../../ba..r', '/'), r'foo/ba..r') def test_extract_hackers_arcnames_common_cases(self): common_hacknames = [ ('../foo/bar', 'foo/bar'), ('foo/../bar', 'foo/bar'), ('foo/../../bar', 'foo/bar'), ('foo/bar/..', 'foo/bar'), ('./../foo/bar', 'foo/bar'), ('/foo/bar', 'foo/bar'), ('/foo/../bar', 'foo/bar'), ('/foo/../../bar', 'foo/bar'), ] self._test_extract_hackers_arcnames(common_hacknames) @unittest.skipIf(os.path.sep != '\\', 'Requires \\ as path separator.') def test_extract_hackers_arcnames_windows_only(self): """Test combination of path fixing and windows name sanitization.""" windows_hacknames = [ (r'..\foo\bar', 'foo/bar'), (r'..\/foo\/bar', 'foo/bar'), (r'foo/\..\/bar', 'foo/bar'), (r'foo\/../\bar', 'foo/bar'), (r'C:foo/bar', 'foo/bar'), (r'C:/foo/bar', 'foo/bar'), (r'C://foo/bar', 'foo/bar'), (r'C:\foo\bar', 'foo/bar'), (r'//conky/mountpoint/foo/bar', 'foo/bar'), (r'\\conky\mountpoint\foo\bar', 'foo/bar'), (r'///conky/mountpoint/foo/bar', 'conky/mountpoint/foo/bar'), (r'\\\conky\mountpoint\foo\bar', 'conky/mountpoint/foo/bar'), (r'//conky//mountpoint/foo/bar', 'conky/mountpoint/foo/bar'), (r'\\conky\\mountpoint\foo\bar', 'conky/mountpoint/foo/bar'), (r'//?/C:/foo/bar', 'foo/bar'), (r'\\?\C:\foo\bar', 'foo/bar'), (r'C:/../C:/foo/bar', 'C_/foo/bar'), (r'a:b\ce|f"g?h*i', 'b/c_d_e_f_g_h_i'), ('../../foo../../ba..r', 'foo/ba..r'), ] self._test_extract_hackers_arcnames(windows_hacknames) @unittest.skipIf(os.path.sep != '/', r'Requires / as path separator.') def test_extract_hackers_arcnames_posix_only(self): posix_hacknames = [ ('//foo/bar', 'foo/bar'), ('../../foo../../ba..r', 'foo../ba..r'), (r'foo/..\bar', r'foo/..\bar'), ] self._test_extract_hackers_arcnames(posix_hacknames) def _test_extract_hackers_arcnames(self, hacknames): for arcname, fixedname in hacknames: content = b'foobar' + arcname.encode() with zipfile_aes.AESZipFile(TESTFN2, 'w', zipfile.ZIP_STORED) as zipfp: zinfo = zipfile_aes.AESZipInfo() # preserve backslashes zinfo.filename = arcname zinfo.external_attr = 0o600 << 16 zipfp.writestr(zinfo, content) arcname = arcname.replace(os.sep, "/") targetpath = os.path.join('target', 'subdir', 'subsub') correctfile = os.path.join(targetpath, *fixedname.split('/')) with zipfile_aes.AESZipFile(TESTFN2, 'r') as zipfp: writtenfile = zipfp.extract(arcname, targetpath) self.assertEqual(writtenfile, correctfile, msg='extract %r: %r != %r' % (arcname, writtenfile, correctfile)) self.check_file(correctfile, content) rmtree('target') with zipfile_aes.AESZipFile(TESTFN2, 'r') as zipfp: zipfp.extractall(targetpath) self.check_file(correctfile, content) rmtree('target') correctfile = os.path.join(os.getcwd(), *fixedname.split('/')) with zipfile_aes.AESZipFile(TESTFN2, 'r') as zipfp: writtenfile = zipfp.extract(arcname) self.assertEqual(writtenfile, correctfile, msg="extract %r" % arcname) self.check_file(correctfile, content) rmtree(fixedname.split('/')[0]) with zipfile_aes.AESZipFile(TESTFN2, 'r') as zipfp: zipfp.extractall() self.check_file(correctfile, content) rmtree(fixedname.split('/')[0]) unlink(TESTFN2) class OtherTests(unittest.TestCase): def test_open_via_zip_info(self): # Create the ZIP archive with zipfile_aes.AESZipFile(TESTFN2, "w", zipfile.ZIP_STORED) as zipfp: zipfp.writestr("name", "foo") with self.assertWarns(UserWarning): zipfp.writestr("name", "bar") self.assertEqual(zipfp.namelist(), ["name"] * 2) with zipfile_aes.AESZipFile(TESTFN2, "r") as zipfp: infos = zipfp.infolist() data = b"" for info in infos: with zipfp.open(info) as zipopen: data += zipopen.read() self.assertIn(data, {b"foobar", b"barfoo"}) data = b"" for info in infos: data += zipfp.read(info) self.assertIn(data, {b"foobar", b"barfoo"}) def test_writestr_extended_local_header_issue1202(self): with zipfile_aes.AESZipFile(TESTFN2, 'w') as orig_zip: for data in 'abcdefghijklmnop': zinfo = zipfile_aes.AESZipInfo(data) zinfo.flag_bits |= 0x08 # Include an extended local header. orig_zip.writestr(zinfo, data) def test_close(self): """Check that the zipfile is closed after the 'with' block.""" with zipfile_aes.AESZipFile(TESTFN2, "w") as zipfp: for fpath, fdata in SMALL_TEST_DATA: zipfp.writestr(fpath, fdata) self.assertIsNotNone(zipfp.fp, 'zipfp is not open') self.assertIsNone(zipfp.fp, 'zipfp is not closed') with zipfile_aes.AESZipFile(TESTFN2, "r") as zipfp: self.assertIsNotNone(zipfp.fp, 'zipfp is not open') self.assertIsNone(zipfp.fp, 'zipfp is not closed') def test_close_on_exception(self): """Check that the zipfile is closed if an exception is raised in the 'with' block.""" with zipfile_aes.AESZipFile(TESTFN2, "w") as zipfp: for fpath, fdata in SMALL_TEST_DATA: zipfp.writestr(fpath, fdata) try: with zipfile_aes.AESZipFile(TESTFN2, "r") as zipfp2: raise zipfile.BadZipFile() except zipfile.BadZipFile: self.assertIsNone(zipfp2.fp, 'zipfp is not closed') def test_unsupported_version(self): # File has an extract_version of 120 data = (b'PK\x03\x04x\x00\x00\x00\x00\x00!p\xa1@\x00\x00\x00\x00\x00\x00' b'\x00\x00\x00\x00\x00\x00\x01\x00\x00\x00xPK\x01\x02x\x03x\x00\x00\x00\x00' b'\x00!p\xa1@\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x01\x00\x00' b'\x00\x00\x00\x00\x00\x00\x00\x00\x00\x80\x01\x00\x00\x00\x00xPK\x05\x06' b'\x00\x00\x00\x00\x01\x00\x01\x00/\x00\x00\x00\x1f\x00\x00\x00\x00\x00') self.assertRaises(NotImplementedError, zipfile_aes.AESZipFile, io.BytesIO(data), 'r') @requires_zlib def test_read_unicode_filenames(self): # bug #10801 fname = findfile('zip_cp437_header.zip') with zipfile_aes.AESZipFile(fname) as zipfp: for name in zipfp.namelist(): zipfp.open(name).close() def test_write_unicode_filenames(self): with zipfile_aes.AESZipFile(TESTFN, "w") as zf: zf.writestr("foo.txt", "Test for unicode filename") zf.writestr("\xf6.txt", "Test for unicode filename") self.assertIsInstance(zf.infolist()[0].filename, str) with zipfile_aes.AESZipFile(TESTFN, "r") as zf: self.assertEqual(zf.filelist[0].filename, "foo.txt") self.assertEqual(zf.filelist[1].filename, "\xf6.txt") def test_exclusive_create_zip_file(self): """Test exclusive creating a new zipfile.""" unlink(TESTFN2) filename = 'testfile.txt' content = b'hello, world. this is some content.' with zipfile_aes.AESZipFile(TESTFN2, "x", zipfile.ZIP_STORED) as zipfp: zipfp.writestr(filename, content) with self.assertRaises(FileExistsError): zipfile_aes.AESZipFile(TESTFN2, "x", zipfile.ZIP_STORED) with zipfile_aes.AESZipFile(TESTFN2, "r") as zipfp: self.assertEqual(zipfp.namelist(), [filename]) self.assertEqual(zipfp.read(filename), content) def test_create_non_existent_file_for_append(self): if os.path.exists(TESTFN): os.unlink(TESTFN) filename = 'testfile.txt' content = b'hello, world. this is some content.' try: with zipfile_aes.AESZipFile(TESTFN, 'a') as zf: zf.writestr(filename, content) except OSError: self.fail('Could not append data to a non-existent zip file.') self.assertTrue(os.path.exists(TESTFN)) with zipfile_aes.AESZipFile(TESTFN, 'r') as zf: self.assertEqual(zf.read(filename), content) def test_close_erroneous_file(self): # This test checks that the ZipFile constructor closes the file object # it opens if there's an error in the file. If it doesn't, the # traceback holds a reference to the ZipFile object and, indirectly, # the file object. # On Windows, this causes the os.unlink() call to fail because the # underlying file is still open. This is SF bug #412214. # with open(TESTFN, "w") as fp: fp.write("this is not a legal zip file\n") try: zf = zipfile_aes.AESZipFile(TESTFN) except zipfile.BadZipFile: pass def test_is_zip_erroneous_file(self): """Check that is_zipfile() correctly identifies non-zip files.""" # - passing a filename with open(TESTFN, "w") as fp: fp.write("this is not a legal zip file\n") self.assertFalse(zipfile.is_zipfile(TESTFN)) # - passing a path-like object self.assertFalse(zipfile.is_zipfile(pathlib.Path(TESTFN))) # - passing a file object with open(TESTFN, "rb") as fp: self.assertFalse(zipfile.is_zipfile(fp)) # - passing a file-like object fp = io.BytesIO() fp.write(b"this is not a legal zip file\n") self.assertFalse(zipfile.is_zipfile(fp)) fp.seek(0, 0) self.assertFalse(zipfile.is_zipfile(fp)) def test_damaged_zipfile(self): """Check that zipfiles with missing bytes at the end raise BadZipFile.""" # - Create a valid zip file fp = io.BytesIO() with zipfile_aes.AESZipFile(fp, mode="w") as zipf: zipf.writestr("foo.txt", b"O, for a Muse of Fire!") zipfiledata = fp.getvalue() # - Now create copies of it missing the last N bytes and make sure # a BadZipFile exception is raised when we try to open it for N in range(len(zipfiledata)): fp = io.BytesIO(zipfiledata[:N]) self.assertRaises(zipfile.BadZipFile, zipfile_aes.AESZipFile, fp) def test_is_zip_valid_file(self): """Check that is_zipfile() correctly identifies zip files.""" # - passing a filename with zipfile_aes.AESZipFile(TESTFN, mode="w") as zipf: zipf.writestr("foo.txt", b"O, for a Muse of Fire!") self.assertTrue(zipfile.is_zipfile(TESTFN)) # - passing a file object with open(TESTFN, "rb") as fp: self.assertTrue(zipfile.is_zipfile(fp)) fp.seek(0, 0) zip_contents = fp.read() # - passing a file-like object fp = io.BytesIO() fp.write(zip_contents) self.assertTrue(zipfile.is_zipfile(fp)) fp.seek(0, 0) self.assertTrue(zipfile.is_zipfile(fp)) def test_non_existent_file_raises_OSError(self): # make sure we don't raise an AttributeError when a partially-constructed # ZipFile instance is finalized; this tests for regression on SF tracker # bug #403871. # The bug we're testing for caused an AttributeError to be raised # when a ZipFile instance was created for a file that did not # exist; the .fp member was not initialized but was needed by the # __del__() method. Since the AttributeError is in the __del__(), # it is ignored, but the user should be sufficiently annoyed by # the message on the output that regression will be noticed # quickly. self.assertRaises(OSError, zipfile_aes.AESZipFile, TESTFN) def test_empty_file_raises_BadZipFile(self): f = open(TESTFN, 'w') f.close() self.assertRaises(zipfile.BadZipFile, zipfile_aes.AESZipFile, TESTFN) with open(TESTFN, 'w') as fp: fp.write("short file") self.assertRaises(zipfile.BadZipFile, zipfile_aes.AESZipFile, TESTFN) def test_closed_zip_raises_ValueError(self): """Verify that testzip() doesn't swallow inappropriate exceptions.""" data = io.BytesIO() with zipfile_aes.AESZipFile(data, mode="w") as zipf: zipf.writestr("foo.txt", "O, for a Muse of Fire!") # This is correct; calling .read on a closed ZipFile should raise # a ValueError, and so should calling .testzip. An earlier # version of .testzip would swallow this exception (and any other) # and report that the first file in the archive was corrupt. self.assertRaises(ValueError, zipf.read, "foo.txt") self.assertRaises(ValueError, zipf.open, "foo.txt") self.assertRaises(ValueError, zipf.testzip) self.assertRaises(ValueError, zipf.writestr, "bogus.txt", "bogus") with open(TESTFN, 'w') as f: f.write('zipfile test data') self.assertRaises(ValueError, zipf.write, TESTFN) def test_bad_constructor_mode(self): """Check that bad modes passed to ZipFile constructor are caught.""" self.assertRaises(ValueError, zipfile_aes.AESZipFile, TESTFN, "q") def test_bad_open_mode(self): """Check that bad modes passed to ZipFile.open are caught.""" with zipfile_aes.AESZipFile(TESTFN, mode="w") as zipf: zipf.writestr("foo.txt", "O, for a Muse of Fire!") with zipfile_aes.AESZipFile(TESTFN, mode="r") as zipf: # read the data to make sure the file is there zipf.read("foo.txt") self.assertRaises(ValueError, zipf.open, "foo.txt", "q") # universal newlines support is removed self.assertRaises(ValueError, zipf.open, "foo.txt", "U") self.assertRaises(ValueError, zipf.open, "foo.txt", "rU") def test_read0(self): """Check that calling read(0) on a ZipExtFile object returns an empty string and doesn't advance file pointer.""" with zipfile_aes.AESZipFile(TESTFN, mode="w") as zipf: zipf.writestr("foo.txt", "O, for a Muse of Fire!") # read the data to make sure the file is there with zipf.open("foo.txt") as f: for i in range(FIXEDTEST_SIZE): self.assertEqual(f.read(0), b'') self.assertEqual(f.read(), b"O, for a Muse of Fire!") def test_open_non_existent_item(self): """Check that attempting to call open() for an item that doesn't exist in the archive raises a RuntimeError.""" with zipfile_aes.AESZipFile(TESTFN, mode="w") as zipf: self.assertRaises(KeyError, zipf.open, "foo.txt", "r") def test_bad_compression_mode(self): """Check that bad compression methods passed to ZipFile.open are caught.""" self.assertRaises(NotImplementedError, zipfile_aes.AESZipFile, TESTFN, "w", -1) def test_unsupported_compression(self): # data is declared as shrunk, but actually deflated data = (b'PK\x03\x04.\x00\x00\x00\x01\x00\xe4C\xa1@\x00\x00\x00' b'\x00\x02\x00\x00\x00\x00\x00\x00\x00\x01\x00\x00\x00x\x03\x00PK\x01' b'\x02.\x03.\x00\x00\x00\x01\x00\xe4C\xa1@\x00\x00\x00\x00\x02\x00\x00' b'\x00\x00\x00\x00\x00\x01\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00' b'\x80\x01\x00\x00\x00\x00xPK\x05\x06\x00\x00\x00\x00\x01\x00\x01\x00' b'/\x00\x00\x00!\x00\x00\x00\x00\x00') with zipfile_aes.AESZipFile(io.BytesIO(data), 'r') as zipf: self.assertRaises(NotImplementedError, zipf.open, 'x') def test_null_byte_in_filename(self): """Check that a filename containing a null byte is properly terminated.""" with zipfile_aes.AESZipFile(TESTFN, mode="w") as zipf: zipf.writestr("foo.txt\x00qqq", b"O, for a Muse of Fire!") self.assertEqual(zipf.namelist(), ['foo.txt']) def test_struct_sizes(self): """Check that ZIP internal structure sizes are calculated correctly.""" self.assertEqual(zipfile.sizeEndCentDir, 22) self.assertEqual(zipfile.sizeCentralDir, 46) self.assertEqual(zipfile.sizeEndCentDir64, 56) self.assertEqual(zipfile.sizeEndCentDir64Locator, 20) def test_comments(self): """Check that comments on the archive are handled properly.""" # check default comment is empty with zipfile_aes.AESZipFile(TESTFN, mode="w") as zipf: self.assertEqual(zipf.comment, b'') zipf.writestr("foo.txt", "O, for a Muse of Fire!") with zipfile_aes.AESZipFile(TESTFN, mode="r") as zipfr: self.assertEqual(zipfr.comment, b'') # check a simple short comment comment = b'Bravely taking to his feet, he beat a very brave retreat.' with zipfile_aes.AESZipFile(TESTFN, mode="w") as zipf: zipf.comment = comment zipf.writestr("foo.txt", "O, for a Muse of Fire!") with zipfile_aes.AESZipFile(TESTFN, mode="r") as zipfr: self.assertEqual(zipf.comment, comment) # check a comment of max length comment2 = ''.join(['%d' % (i**3 % 10) for i in range((1 << 16)-1)]) comment2 = comment2.encode("ascii") with zipfile_aes.AESZipFile(TESTFN, mode="w") as zipf: zipf.comment = comment2 zipf.writestr("foo.txt", "O, for a Muse of Fire!") with zipfile_aes.AESZipFile(TESTFN, mode="r") as zipfr: self.assertEqual(zipfr.comment, comment2) # check a comment that is too long is truncated with zipfile_aes.AESZipFile(TESTFN, mode="w") as zipf: with self.assertWarns(UserWarning): zipf.comment = comment2 + b'oops' zipf.writestr("foo.txt", "O, for a Muse of Fire!") with zipfile_aes.AESZipFile(TESTFN, mode="r") as zipfr: self.assertEqual(zipfr.comment, comment2) # check that comments are correctly modified in append mode with zipfile_aes.AESZipFile(TESTFN,mode="w") as zipf: zipf.comment = b"original comment" zipf.writestr("foo.txt", "O, for a Muse of Fire!") with zipfile_aes.AESZipFile(TESTFN,mode="a") as zipf: zipf.comment = b"an updated comment" with zipfile_aes.AESZipFile(TESTFN,mode="r") as zipf: self.assertEqual(zipf.comment, b"an updated comment") # check that comments are correctly shortened in append mode with zipfile_aes.AESZipFile(TESTFN,mode="w") as zipf: zipf.comment = b"original comment that's longer" zipf.writestr("foo.txt", "O, for a Muse of Fire!") with zipfile_aes.AESZipFile(TESTFN,mode="a") as zipf: zipf.comment = b"shorter comment" with zipfile_aes.AESZipFile(TESTFN,mode="r") as zipf: self.assertEqual(zipf.comment, b"shorter comment") def test_unicode_comment(self): with zipfile_aes.AESZipFile(TESTFN, "w", zipfile.ZIP_STORED) as zipf: zipf.writestr("foo.txt", "O, for a Muse of Fire!") with self.assertRaises(TypeError): zipf.comment = "this is an error" def test_change_comment_in_empty_archive(self): with zipfile_aes.AESZipFile(TESTFN, "a", zipfile.ZIP_STORED) as zipf: self.assertFalse(zipf.filelist) zipf.comment = b"this is a comment" with zipfile_aes.AESZipFile(TESTFN, "r") as zipf: self.assertEqual(zipf.comment, b"this is a comment") def test_change_comment_in_nonempty_archive(self): with zipfile_aes.AESZipFile(TESTFN, "w", zipfile.ZIP_STORED) as zipf: zipf.writestr("foo.txt", "O, for a Muse of Fire!") with zipfile_aes.AESZipFile(TESTFN, "a", zipfile.ZIP_STORED) as zipf: self.assertTrue(zipf.filelist) zipf.comment = b"this is a comment" with zipfile_aes.AESZipFile(TESTFN, "r") as zipf: self.assertEqual(zipf.comment, b"this is a comment") def test_empty_zipfile(self): # Check that creating a file in 'w' or 'a' mode and closing without # adding any files to the archives creates a valid empty ZIP file zipf = zipfile_aes.AESZipFile(TESTFN, mode="w") zipf.close() try: zipf = zipfile_aes.AESZipFile(TESTFN, mode="r") except zipfile.BadZipFile: self.fail("Unable to create empty ZIP file in 'w' mode") zipf = zipfile_aes.AESZipFile(TESTFN, mode="a") zipf.close() try: zipf = zipfile_aes.AESZipFile(TESTFN, mode="r") except: self.fail("Unable to create empty ZIP file in 'a' mode") def test_open_empty_file(self): # Issue 1710703: Check that opening a file with less than 22 bytes # raises a BadZipFile exception (rather than the previously unhelpful # OSError) f = open(TESTFN, 'w') f.close() self.assertRaises(zipfile.BadZipFile, zipfile_aes.AESZipFile, TESTFN, 'r') def test_create_zipinfo_before_1980(self): self.assertRaises(ValueError, zipfile_aes.AESZipInfo, 'seventies', (1979, 1, 1, 0, 0, 0)) def test_zipfile_with_short_extra_field(self): """If an extra field in the header is less than 4 bytes, skip it.""" zipdata = ( b'PK\x03\x04\x14\x00\x00\x00\x00\x00\x93\x9b\xad@\x8b\x9e' b'\xd9\xd3\x01\x00\x00\x00\x01\x00\x00\x00\x03\x00\x03\x00ab' b'c\x00\x00\x00APK\x01\x02\x14\x03\x14\x00\x00\x00\x00' b'\x00\x93\x9b\xad@\x8b\x9e\xd9\xd3\x01\x00\x00\x00\x01\x00\x00' b'\x00\x03\x00\x02\x00\x00\x00\x00\x00\x00\x00\x00\x00\xa4\x81\x00' b'\x00\x00\x00abc\x00\x00PK\x05\x06\x00\x00\x00\x00' b'\x01\x00\x01\x003\x00\x00\x00%\x00\x00\x00\x00\x00' ) with zipfile_aes.AESZipFile(io.BytesIO(zipdata), 'r') as zipf: # testzip returns the name of the first corrupt file, or None self.assertIsNone(zipf.testzip()) def test_open_conflicting_handles(self): # It's only possible to open one writable file handle at a time msg1 = b"It's fun to charter an accountant!" msg2 = b"And sail the wide accountant sea" msg3 = b"To find, explore the funds offshore" with zipfile_aes.AESZipFile(TESTFN2, 'w', zipfile.ZIP_STORED) as zipf: with zipf.open('foo', mode='w') as w2: w2.write(msg1) with zipf.open('bar', mode='w') as w1: with self.assertRaises(ValueError): zipf.open('handle', mode='w') with self.assertRaises(ValueError): zipf.open('foo', mode='r') with self.assertRaises(ValueError): zipf.writestr('str', 'abcde') with self.assertRaises(ValueError): zipf.write(__file__, 'file') with self.assertRaises(ValueError): zipf.close() w1.write(msg2) with zipf.open('baz', mode='w') as w2: w2.write(msg3) with zipfile_aes.AESZipFile(TESTFN2, 'r') as zipf: self.assertEqual(zipf.read('foo'), msg1) self.assertEqual(zipf.read('bar'), msg2) self.assertEqual(zipf.read('baz'), msg3) self.assertEqual(zipf.namelist(), ['foo', 'bar', 'baz']) def test_seek_tell(self): # Test seek functionality txt = b"Where's Bruce?" bloc = txt.find(b"Bruce") # Check seek on a file with zipfile_aes.AESZipFile(TESTFN, "w") as zipf: zipf.writestr("foo.txt", txt) with zipfile_aes.AESZipFile(TESTFN, "r") as zipf: with zipf.open("foo.txt", "r") as fp: fp.seek(bloc, os.SEEK_SET) self.assertEqual(fp.tell(), bloc) fp.seek(-bloc, os.SEEK_CUR) self.assertEqual(fp.tell(), 0) fp.seek(bloc, os.SEEK_CUR) self.assertEqual(fp.tell(), bloc) self.assertEqual(fp.read(5), txt[bloc:bloc+5]) fp.seek(0, os.SEEK_END) self.assertEqual(fp.tell(), len(txt)) fp.seek(0, os.SEEK_SET) self.assertEqual(fp.tell(), 0) # Check seek on memory file data = io.BytesIO() with zipfile_aes.AESZipFile(data, mode="w") as zipf: zipf.writestr("foo.txt", txt) with zipfile_aes.AESZipFile(data, mode="r") as zipf: with zipf.open("foo.txt", "r") as fp: fp.seek(bloc, os.SEEK_SET) self.assertEqual(fp.tell(), bloc) fp.seek(-bloc, os.SEEK_CUR) self.assertEqual(fp.tell(), 0) fp.seek(bloc, os.SEEK_CUR) self.assertEqual(fp.tell(), bloc) self.assertEqual(fp.read(5), txt[bloc:bloc+5]) fp.seek(0, os.SEEK_END) self.assertEqual(fp.tell(), len(txt)) fp.seek(0, os.SEEK_SET) self.assertEqual(fp.tell(), 0) def tearDown(self): unlink(TESTFN) unlink(TESTFN2) class AbstractBadCrcTests: def test_testzip_with_bad_crc(self): """Tests that files with bad CRCs return their name from testzip.""" zipdata = self.zip_with_bad_crc with zipfile_aes.AESZipFile(io.BytesIO(zipdata), mode="r") as zipf: # testzip returns the name of the first corrupt file, or None self.assertEqual('afile', zipf.testzip()) def test_read_with_bad_crc(self): """Tests that files with bad CRCs raise a BadZipFile exception when read.""" zipdata = self.zip_with_bad_crc # Using ZipFile.read() with zipfile_aes.AESZipFile(io.BytesIO(zipdata), mode="r") as zipf: self.assertRaises(zipfile.BadZipFile, zipf.read, 'afile') # Using ZipExtFile.read() with zipfile_aes.AESZipFile(io.BytesIO(zipdata), mode="r") as zipf: with zipf.open('afile', 'r') as corrupt_file: self.assertRaises(zipfile.BadZipFile, corrupt_file.read) # Same with small reads (in order to exercise the buffering logic) with zipfile_aes.AESZipFile(io.BytesIO(zipdata), mode="r") as zipf: with zipf.open('afile', 'r') as corrupt_file: corrupt_file.MIN_READ_SIZE = 2 with self.assertRaises(zipfile.BadZipFile): while corrupt_file.read(2): pass class StoredBadCrcTests(AbstractBadCrcTests, unittest.TestCase): compression = zipfile.ZIP_STORED zip_with_bad_crc = ( b'PK\003\004\024\0\0\0\0\0 \213\212;:r' b'\253\377\f\0\0\0\f\0\0\0\005\0\0\000af' b'ilehello,AworldP' b'K\001\002\024\003\024\0\0\0\0\0 \213\212;:' b'r\253\377\f\0\0\0\f\0\0\0\005\0\0\0\0' b'\0\0\0\0\0\0\0\200\001\0\0\0\000afi' b'lePK\005\006\0\0\0\0\001\0\001\0003\000' b'\0\0/\0\0\0\0\0') @requires_zlib class DeflateBadCrcTests(AbstractBadCrcTests, unittest.TestCase): compression = zipfile.ZIP_DEFLATED zip_with_bad_crc = ( b'PK\x03\x04\x14\x00\x00\x00\x08\x00n}\x0c=FA' b'KE\x10\x00\x00\x00n\x00\x00\x00\x05\x00\x00\x00af' b'ile\xcbH\xcd\xc9\xc9W(\xcf/\xcaI\xc9\xa0' b'=\x13\x00PK\x01\x02\x14\x03\x14\x00\x00\x00\x08\x00n' b'}\x0c=FAKE\x10\x00\x00\x00n\x00\x00\x00\x05' b'\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x80\x01\x00\x00\x00' b'\x00afilePK\x05\x06\x00\x00\x00\x00\x01\x00' b'\x01\x003\x00\x00\x003\x00\x00\x00\x00\x00') @requires_bz2 class Bzip2BadCrcTests(AbstractBadCrcTests, unittest.TestCase): compression = zipfile.ZIP_BZIP2 zip_with_bad_crc = ( b'PK\x03\x04\x14\x03\x00\x00\x0c\x00nu\x0c=FA' b'KE8\x00\x00\x00n\x00\x00\x00\x05\x00\x00\x00af' b'ileBZh91AY&SY\xd4\xa8\xca' b'\x7f\x00\x00\x0f\x11\x80@\x00\x06D\x90\x80 \x00 \xa5' b'P\xd9!\x03\x03\x13\x13\x13\x89\xa9\xa9\xc2u5:\x9f' b'\x8b\xb9"\x9c(HjTe?\x80PK\x01\x02\x14' b'\x03\x14\x03\x00\x00\x0c\x00nu\x0c=FAKE8' b'\x00\x00\x00n\x00\x00\x00\x05\x00\x00\x00\x00\x00\x00\x00\x00' b'\x00 \x80\x80\x81\x00\x00\x00\x00afilePK' b'\x05\x06\x00\x00\x00\x00\x01\x00\x01\x003\x00\x00\x00[\x00' b'\x00\x00\x00\x00') @requires_lzma class LzmaBadCrcTests(AbstractBadCrcTests, unittest.TestCase): compression = zipfile.ZIP_LZMA zip_with_bad_crc = ( b'PK\x03\x04\x14\x03\x00\x00\x0e\x00nu\x0c=FA' b'KE\x1b\x00\x00\x00n\x00\x00\x00\x05\x00\x00\x00af' b'ile\t\x04\x05\x00]\x00\x00\x00\x04\x004\x19I' b'\xee\x8d\xe9\x17\x89:3`\tq!.8\x00PK' b'\x01\x02\x14\x03\x14\x03\x00\x00\x0e\x00nu\x0c=FA' b'KE\x1b\x00\x00\x00n\x00\x00\x00\x05\x00\x00\x00\x00\x00' b'\x00\x00\x00\x00 \x80\x80\x81\x00\x00\x00\x00afil' b'ePK\x05\x06\x00\x00\x00\x00\x01\x00\x01\x003\x00\x00' b'\x00>\x00\x00\x00\x00\x00') class DecryptionTests(unittest.TestCase): """Check that ZIP decryption works. Since the library does not support encryption at the moment, we use a pre-generated encrypted ZIP file.""" data = ( b'PK\x03\x04\x14\x00\x01\x00\x00\x00n\x92i.#y\xef?&\x00\x00\x00\x1a\x00' b'\x00\x00\x08\x00\x00\x00test.txt\xfa\x10\xa0gly|\xfa-\xc5\xc0=\xf9y' b'\x18\xe0\xa8r\xb3Z}Lg\xbc\xae\xf9|\x9b\x19\xe4\x8b\xba\xbb)\x8c\xb0\xdbl' b'PK\x01\x02\x14\x00\x14\x00\x01\x00\x00\x00n\x92i.#y\xef?&\x00\x00\x00' b'\x1a\x00\x00\x00\x08\x00\x00\x00\x00\x00\x00\x00\x01\x00 \x00\xb6\x81' b'\x00\x00\x00\x00test.txtPK\x05\x06\x00\x00\x00\x00\x01\x00\x01\x006\x00' b'\x00\x00L\x00\x00\x00\x00\x00' ) data2 = ( b'PK\x03\x04\x14\x00\t\x00\x08\x00\xcf}38xu\xaa\xb2\x14\x00\x00\x00\x00\x02' b'\x00\x00\x04\x00\x15\x00zeroUT\t\x00\x03\xd6\x8b\x92G\xda\x8b\x92GUx\x04' b'\x00\xe8\x03\xe8\x03\xc7= 4: tp, ln = struct.unpack('