diff --git a/.coveragerc b/.coveragerc new file mode 100644 index 00000000..c5619672 --- /dev/null +++ b/.coveragerc @@ -0,0 +1,7 @@ +[run] +branch = True +source = dulwich + +[report] +exclude_lines = + raise NotImplementedError diff --git a/.gitignore b/.gitignore new file mode 100644 index 00000000..1229de30 --- /dev/null +++ b/.gitignore @@ -0,0 +1,24 @@ +_trial_temp +build +build-pypy +MANIFEST +dist +apidocs +*,cover +.testrepository +*.pyc +*.pyd +*.pyo +*.so +*~ +*.swp +*.swh +*.swn +*.swo +docs/tutorial/index.html +dulwich.egg-info/ +.tox/ +.idea/ +.coverage +htmlcov/ +docs/api/*.txt diff --git a/.mailmap b/.mailmap new file mode 100644 index 00000000..41a70c12 --- /dev/null +++ b/.mailmap @@ -0,0 +1,23 @@ +Jelmer Vernooij +Jelmer Vernooij +Jelmer Vernooij +Jelmer Vernooij +Jelmer Vernooij +Jelmer Vernooij +Martin +Dave Borowitz +Dave Borowitz +John Carr +Mark Mikofski +Mark Mikofski +David Carr +Jon Bain +James Westby +David Keijser +Benoît HERVIER +Ryan Faulkner +David Bennett +Risto Kankkunen +Augie Fackler +Damien Tournoud +Marcin Kuźmiński diff --git a/.travis.yml b/.travis.yml index 662f3cac..c346113b 100644 --- a/.travis.yml +++ b/.travis.yml @@ -1,51 +1,47 @@ language: python sudo: false cache: pip python: - 2.7 - 3.4 - 3.5 - - 3.5-dev - 3.6 - 3.6-dev - - pypy3.3-5.2-alpha1 - pypy3.5 env: - PYTHONHASHSEED=random TEST_REQUIRE="gevent greenlet geventhttpclient fastimport" matrix: include: - python: pypy env: TEST_REQUIRE=fastimport - - python: 3.3 - env: TEST_REQUIRE=fastimport - python: 3.7 env: TEST_REQUIRE=fastimport dist: xenial sudo: true - - python: 3.8-dev - env: TEST_REQUIRE=fastimport - dist: xenial - sudo: true - + # flakes checker fails on python 3.8-dev: + #- python: 3.8-dev + # env: TEST_REQUIRE=fastimport + # dist: xenial + # sudo: true install: - travis_retry pip install -U pip coverage codecov flake8 $TEST_REQUIRE script: # Test without c extensions - python -m coverage run -p -m unittest dulwich.tests.test_suite # Test with c extensions - python setup.py build_ext -i - python -m coverage run -p -m unittest dulwich.tests.test_suite # Style - make style after_success: - python -m coverage combine - codecov diff --git a/AUTHORS b/AUTHORS index 9518fdfc..efaa3dfb 100644 --- a/AUTHORS +++ b/AUTHORS @@ -1,148 +1,150 @@ Jelmer Vernooij Dave Borowitz John Carr Gary van der Merwe milki Augie Fackler Tay Ray Chuan Risto Kankkunen Jonas Haag Fabien Boucher James Westby Mike Edgar Koen Martens Abderrahim Kitouni William Grant Marcin Kuzminski Ryan Faulkner Julian Berman Mark Mikofski Michael K Ali Sabil Damien Tournoud Hannu Valtonen Mika Mäenpää Paul Hummer Lele Gaifax Lukasz Balcerzak Tommy Yu anatoly techtonik bmcorser Brendan Cully Chow Loong Jin Chris Eberle Dmitriy Hervé Cauwelier Hugo Osvaldo Barrera Jameson Nash Marc Brinkmann Nicolas Dandrimont Robert Brown Siddharth Agarwal Stefan Zimmermann Takeshi Kanemoto Yifan Zhang Aaron O'Mullan Adam "Cezar" Jenkins Alberto Ruiz Alexander Belchenko Andreas Kloeckner André Roth Benjamin Pollack Benoit HERVIER Dan Callaghan David Keijser David Ostrovsky David Pursehouse Dmitrij D. Czarkoff Doug Hellmann Dov Feldstern Félix Mattrat Hwee Miin Koh Jason R. Coombs Jeremy Whitlock John Arbash Meinel Laurent Rineau Martin Packman Max Shawabkeh Michael Hudson Nick Stenning Nick Ward Paul Chen Roland Mas Ronald Blaschke Ronny Pfannschmidt Ross Light Ryan McKern Ted Horst Thomas Liebetraut Timo Schmid Víðir Valberg Guðmundsson dak180 Akbar Gumbira Alex Holmes Andi McClure Andres Lowrie Artem Tikhomirov Brian Visel Bruce Duncan Bruno Renié Chaiwat Suttipongsakul Chris Bunney Chris Reid Daniele Sluijters David Bennett David Blewett David Carr Dirk Elan Ruusamäe Forrest Hopkins Hal Wine Hans Kolek Jakub Wilk JonChu Kostis Anagnostopoulos Kyle Kelly Lionel Flandrin Max Bowsher <_@maxb.eu> Mike Williams Mikhail Terekhov Nix OnMaster Pascal Quantin Ricardo Salveti Rod Cloutier Sam Vilain Stefano Rivera Steven Myint Søren Løvborg Travis Cline Victor Stinner Volodymyr Holovko Yuval Langer codingtony jon bain kwatters max Segev Finer fviolette dzhuang Antoine Pietri Taras Postument Earl Chew Daniel Andersson Fabian Grünbichler Kenneth Lareau Antoine R. Dumont (@ardumont) Alistair Broomhead Marcel Schnirring Adam Bradley Filipp Frizzy Romain Keramitas semyon-slepov Daniel M. Capella grun Sylvia van Os Boris Feld +KS Chan +egor If you contributed but are missing from this list, please send me an e-mail. diff --git a/CONTRIBUTING.md b/CONTRIBUTING.rst similarity index 99% rename from CONTRIBUTING.md rename to CONTRIBUTING.rst index 14a271ea..d9da2334 100644 --- a/CONTRIBUTING.md +++ b/CONTRIBUTING.rst @@ -1,55 +1,56 @@ All functionality should be available in pure Python. Optional C implementations may be written for performance reasons, but should never replace the Python implementation. The C implementations should follow the kernel/git coding style. Where possible include updates to NEWS along with your improvements. New functionality and bug fixes should be accompanied by matching unit tests. Coding style ------------ Where possible, please follow PEP8 with regard to coding style. Furthermore, triple-quotes should always be """, single quotes are ' unless using " would result in less escaping within the string. Public methods, functions and classes should all have doc strings. Please use epydoc style docstrings to document parameters and return values. You can generate the documentation by running "make doc". Running the tests ----------------- To run the testsuite, you should be able to simply run "make check". This will run the tests using unittest. - $ make check +:: + $ make check Tox configuration is also present as well as a Travis configuration file. String Types ------------ Like Linux, Git treats filenames as arbitrary bytestrings. There is no prescribed encoding for these strings, and although it is fairly common to use UTF-8, any raw byte strings are supported. For this reason, Dulwich internally treats git-based filenames as bytestrings. It is up to the Dulwich API user to encode and decode them if necessary. In the future, the porcelain may accept unicode strings and convert them to bytestrings as necessary on the fly (using sys.getfilesystemencoding()). * git-repository related filenames: bytes * object sha1 digests (20 bytes long): bytes * object sha1 hexdigests (40 bytes long): str (bytestrings on python2, strings on python3) Merge requests -------------- Please either send pull requests to the maintainer (jelmer@jelmer.uk) or create new pull requests on GitHub. Licensing --------- All contributions should be made under the same license that Dulwich itself comes under: both Apache License, version 2.0 or later and GNU General Public License, version 2.0 or later. diff --git a/MANIFEST.in b/MANIFEST.in index bd727e2c..067dc2ad 100644 --- a/MANIFEST.in +++ b/MANIFEST.in @@ -1,18 +1,18 @@ include NEWS include AUTHORS -include README.md -include README.swift.md +include README.rst +include README.swift.rst include Makefile include COPYING -include CONTRIBUTING.md +include CONTRIBUTING.rst include TODO include setup.cfg include dulwich/stdint.h recursive-include docs conf.py *.txt Makefile make.bat recursive-include examples *.py graft dulwich/tests/data include tox.ini include dulwich.cfg include appveyor.yml include .testr.conf include .travis.yml diff --git a/Makefile b/Makefile index 8054ee2c..d0bdb3d2 100644 --- a/Makefile +++ b/Makefile @@ -1,71 +1,66 @@ PYTHON = python -Werror PYFLAKES = pyflakes PEP8 = pep8 FLAKE8 ?= flake8 SETUP = $(PYTHON) setup.py -PYDOCTOR ?= pydoctor TESTRUNNER ?= unittest RUNTEST = PYTHONHASHSEED=random PYTHONPATH=$(shell pwd)$(if $(PYTHONPATH),:$(PYTHONPATH),) $(PYTHON) -m $(TESTRUNNER) $(TEST_OPTIONS) COVERAGE = python3-coverage DESTDIR=/ all: build -doc:: pydoctor doc:: sphinx sphinx:: $(MAKE) -C docs html -pydoctor:: - $(PYDOCTOR) --make-html -c dulwich.cfg - build:: $(SETUP) build $(SETUP) build_ext -i install:: $(SETUP) install --root="$(DESTDIR)" check:: build $(RUNTEST) dulwich.tests.test_suite check-tutorial:: build $(RUNTEST) dulwich.tests.tutorial_test_suite check-nocompat:: build $(RUNTEST) dulwich.tests.nocompat_test_suite check-compat:: build $(RUNTEST) dulwich.tests.compat_test_suite check-pypy:: clean $(MAKE) check-noextensions PYTHON=pypy check-noextensions:: clean $(RUNTEST) dulwich.tests.test_suite check-all: check check-pypy check-noextensions clean:: $(SETUP) clean --all rm -f dulwich/*.so flakes: $(PYFLAKES) dulwich pep8: $(PEP8) dulwich style: - $(FLAKE8) --exclude=build,.git,build-pypy,.tox + $(FLAKE8) before-push: check git diff origin/master | $(PEP8) --diff coverage: $(COVERAGE) run -m unittest dulwich.tests.test_suite dulwich.contrib.test_suite coverage-html: coverage $(COVERAGE) html diff --git a/NEWS b/NEWS index 983a1786..64f84217 100644 --- a/NEWS +++ b/NEWS @@ -1,1825 +1,1910 @@ +0.19.10 2018-01-15 + + IMPROVEMENTS + + * Add `dulwich.porcelain.write_tree`. + (Jelmer Vernooij) + + * Support reading ``MERGE_HEADS`` in ``Repo.do_commit``. + (Jelmer Vernooij) + + * Import from ``collections.abc`` rather than ``collections`` where + applicable. Required for 3.8 compatibility. + (Jelmer Vernooij) + + * Support plain strings as refspec arguments to + ``dulwich.porcelain.push``. (Jelmer Vernooij) + + * Add support for creating signed tags. + (Jelmer Vernooij, #542) + + BUG FIXES + + * Handle invalid ref that pretends to be a sub-folder under a valid ref. + (KS Chan) + +0.19.9 2018-11-17 + + BUG FIXES + + * Avoid fetching ghosts in ``Repo.fetch``. + (Jelmer Vernooij) + + * Preserve port and username in parsed HTTP URLs. + (Jelmer Vernooij) + + * Add basic server side implementation of ``git-upload-archive``. + (Jelmer Vernooij) + +0.19.8 2018-11-06 + + * Fix encoding when reading README file in setup.py. + (egor , #668) + +0.19.7 2018-11-05 + + CHANGES + + * Drop support for Python 3 < 3.4. This is because + pkg_resources (which get used by setuptools and mock) + no longer supports 3.3 and earlier. (Jelmer Vernooij) + + IMPROVEMENTS + + * Support ``depth`` argument to ``GitClient.fetch_pack`` and support + fetching and updating shallow metadata. (Jelmer Vernooij, #240) + + BUG FIXES + + * Don't write to stdout and stderr when they are not available + (such as is the case for pythonw). (Sylvia van Os, #652) + + * Fix compatibility with newer versions of git, which expect CONTENT_LENGTH + to be set to 0 for empty body requests. (Jelmer Vernooij, #657) + + * Raise an exception client-side when a caller tries to request + SHAs that are not directly referenced the servers' refs. + (Jelmer Vernooij) + + * Raise more informative errors when unable to connect to repository + over SSH or subprocess. (Jelmer Vernooij) + + * Handle commit identity fields with multiple ">" characters. + (Nicolas Dandrimont) + + IMPROVEMENTS + + * ``dulwich.porcelain.get_object_by_path`` method for easily + accessing a path in another tree. (Jelmer Vernooij) + + * Support the ``i18n.commitEncoding`` setting in config. + (Jelmer Vernooij) + 0.19.6 2018-08-11 BUG FIXES * Fix support for custom transport arguments in ``dulwich.porcelain.clone``. (Semyon Slepov) * Fix compatibility with Python 3.8 (Jelmer Vernooij, Daniel M. Capella) * Fix some corner cases in ``path_to_tree_path``. (Romain Keramitas) * Support paths as bytestrings in various places in ``dulwich.index`` (Jelmer Vernooij) + * Avoid setup.cfg for now, since it seems to break pypi metadata. + (Jelmer Vernooij, #658) + 0.19.5 2018-07-08 IMPROVEMENTS * Add ``porcelain.describe``. (Sylvia van Os) BUG FIXES * Fix regression in ``dulwich.porcelain.clone`` that prevented cloning of remote repositories. (Jelmer Vernooij, #639) * Don't leave around empty parent directories for removed refs. (Damien Tournoud, #640) 0.19.4 2018-06-24 IMPROVEMENTS * Add ``porcelain.ls_files``. (Jelmer Vernooij) * Add ``Index.items``. (Jelmer Vernooij) BUG FIXES * Avoid unicode characters (e.g. the digraph ij in my surname) in setup.cfg, since setuptools doesn't deal well with them. See https://github.com/pypa/setuptools/issues/1062. (Jelmer Vernooij, #637) 0.19.3 2018-06-17 IMPROVEMENTS * Add really basic `dulwich.porcelain.fsck` implementation. (Jelmer Vernooij) * When the `DULWICH_PDB` environment variable is set, make SIGQUIT open pdb in the 'dulwich' command. * Add `checkout` argument to `Repo.clone`. (Jelmer Vernooij, #503) * Add `Repo.get_shallow` method. (Jelmer Vernooij) * Add basic `dulwich.stash` module. (Jelmer Vernooij) * Support a `prefix` argument to `dulwich.archive.tar_stream`. (Jelmer Vernooij) BUG FIXES * Fix handling of encoding for tags. (Jelmer Vernooij, #608) * Fix tutorial tests on Python 3. (Jelmer Vernooij, #573) * Fix remote refs created by `porcelain.fetch`. (Daniel Andersson, #623) * More robust pack creation on Windows. (Daniel Andersson) * Fix recursive option for `porcelain.ls_tree`. (Romain Keramitas) TESTS * Some improvements to paramiko tests. (Filipp Frizzy) 0.19.2 2018-04-07 BUG FIXES * Fix deprecated Index.iterblobs method. (Jelmer Vernooij) 0.19.1 2018-04-05 IMPROVEMENTS * Add 'dulwich.mailmap' file for reading mailmap files. (Jelmer Vernooij) * Dulwich no longer depends on urllib3[secure]. Instead, "dulwich[https]" can be used to pull in the necessary dependencies for HTTPS support. (Jelmer Vernooij, #616) * Support the `http.sslVerify` and `http.sslCAInfo` configuration options. (Jelmer Vernooij) * Factor out `dulwich.client.parse_rsync_url` function. (Jelmer Vernooij) * Fix repeat HTTP requests using the same smart HTTP client. (Jelmer Vernooij) * New 'client.PLinkSSHVendor' for creating connections using PuTTY's plink.exe. (Adam Bradley, Filipp Frizzy) * Only pass in `key_filename` and `password` to SSHVendor implementations if those parameters are set. (This helps with older SSHVendor implementations) (Jelmer Vernooij) API CHANGES * Index.iterblobs has been renamed to Index.iterobjects. (Jelmer Vernooij) 0.19.0 2018-03-10 BUG FIXES * Make `dulwich.archive` set the gzip header file modification time so that archives created from the same Git tree are always identical. (#577, Jonas Haag) * Allow comment characters (#, ;) within configuration file strings (Daniel Andersson, #579) * Raise exception when passing in invalid author/committer values to Repo.do_commit(). (Jelmer Vernooij, #602) IMPROVEMENTS * Add a fastimport ``extra``. (Jelmer Vernooij) * Start writing reflog entries. (Jelmer Vernooij) * Add ability to use password and keyfile ssh options with SSHVendor. (Filipp Kucheryavy) * Add ``change_type_same`` flag to ``tree_changes``. (Jelmer Vernooij) API CHANGES * ``GitClient.send_pack`` now accepts a ``generate_pack_data`` rather than a ``generate_pack_contents`` function for performance reasons. (Jelmer Vernooij) * Dulwich now uses urllib3 internally for HTTP requests. The `opener` argument to `dulwich.client.HttpGitClient` that took a `urllib2` opener instance has been replaced by a `pool_manager` argument that takes a `urllib3` pool manager instance. (Daniel Andersson) 0.18.6 2017-11-11 BUG FIXES * Fix handling of empty repositories in ``porcelain.clone``. (#570, Jelmer Vernooij) * Raise an error when attempting to add paths that are not under the repository. (Jelmer Vernooij) * Fix error message for missing trailing ]. (Daniel Andersson) * Raise EmptyFileException when corruption (in the form of an empty file) is detected. (Antoine R. Dumont, #582) IMPROVEMENTS * Enforce date field parsing consistency. This also add checks on those date fields for potential overflow. (Antoine R. Dumont, #567) 0.18.5 2017-10-29 BUG FIXES * Fix cwd for hooks. (Fabian Grünbichler) * Fix setting of origin in config when non-standard origin is passed into ``Repo.clone``. (Kenneth Lareau, #565) * Prevent setting SSH arguments from SSH URLs when using SSH through a subprocess. Note that Dulwich doesn't support cloning submodules. (CVE-2017-16228) (Jelmer Vernooij) IMPROVEMENTS * Silently ignored directories in ``Repo.stage``. (Jelmer Vernooij, #564) API CHANGES * GitFile now raises ``FileLocked`` when encountering a lock rather than OSError(EEXIST). (Jelmer Vernooij) 0.18.4 2017-10-01 BUG FIXES * Make default User-Agent start with "git/" because GitHub won't response to HTTP smart server requests otherwise (and reply with a 404). (Jelmer vernooij, #562) 0.18.3 2017-09-03 BUG FIXES * Read config during porcelain operations that involve remotes. (Jelmer Vernooij, #545) * Fix headers of empty chunks in unified diffs. (Taras Postument, #543) * Properly follow redirects over HTTP. (Jelmer Vernooij, #117) IMPROVEMENTS * Add ``dulwich.porcelain.update_head``. (Jelmer Vernooij, #439) * ``GitClient.fetch_pack`` now returns symrefs. (Jelmer Vernooij, #485) * The server now supports providing symrefs. (Jelmer Vernooij, #485) * Add ``dulwich.object_store.commit_tree_changes`` to incrementally commit changes to a tree structure. (Jelmer Vernooij) * Add basic ``PackBasedObjectStore.repack`` method. (Jelmer Vernooij, Earl Chew, #296, #549, #552) 0.18.2 2017-08-01 TEST FIXES * Use constant timestamp so tests pass in all timezones, not just BST. (Jelmer Vernooij) 0.18.1 2017-07-31 BUG FIXES * Fix syntax error in dulwich.contrib.test_swift_smoke. (Jelmer Vernooij) 0.18.0 2017-07-31 BUG FIXES * Fix remaining tests on Windows. (Jelmer Vernooij, #493) * Fix build of C extensions with Python 3 on Windows. (Jelmer Vernooij) * Pass 'mkdir' argument onto Repo.init_bare in Repo.clone. (Jelmer Vernooij, #504) * In ``dulwich.porcelain.add``, if no files are specified, add from current working directory rather than repository root. (Jelmer Vernooij, #521) * Properly deal with submodules in 'porcelain.status'. (Jelmer Vernooij, #517) * ``dulwich.porcelain.remove`` now actually removes files from disk, not just from the index. (Jelmer Vernooij, #488) * Fix handling of "reset" command with markers and without "from". (Antoine Pietri) * Fix handling of "merge" command with markers. (Antoine Pietri) * Support treeish argument to porcelain.reset(), rather than requiring a ref/commit id. (Jelmer Vernooij) * Handle race condition when mtime doesn't change between writes/reads. (Jelmer Vernooij, #541) * Fix ``dulwich.porcelain.show`` on commits with Python 3. (Jelmer Vernooij, #532) IMPROVEMENTS * Add basic support for reading ignore files in ``dulwich.ignore``. ``dulwich.porcelain.add`` and ``dulwich.porcelain.status`` now honor ignores. (Jelmer Vernooij, Segev Finer, #524, #526) * New ``dulwich.porcelain.check_ignore`` command. (Jelmer Vernooij) * ``dulwich.porcelain.status`` now supports a ``ignored`` argument. (Jelmer Vernooij) DOCUMENTATION * Clarified docstrings for Client.{send_pack,fetch_pack} implementations. (Jelmer Vernooij, #523) 0.17.3 2017-03-20 PLATFORM SUPPORT * List Python 3.3 as supported. (Jelmer Vernooij, #513) BUG FIXES * Fix compatibility with pypy 3. (Jelmer Vernooij) 0.17.2 2017-03-19 BUG FIXES * Add workaround for https://bitbucket.org/pypy/pypy/issues/2499/cpyext-pystring_asstring-doesnt-work, fixing Dulwich when used with C extensions on pypy < 5.6. (Victor Stinner) * Properly quote config values with a '#' character in them. (Jelmer Vernooij, #511) 0.17.1 2017-03-01 IMPROVEMENTS * Add basic 'dulwich pull' command. (Jelmer Vernooij) BUG FIXES * Cope with existing submodules during pull. (Jelmer Vernooij, #505) 0.17.0 2017-03-01 TEST FIXES * Skip test that requires sync to synchronize filesystems if os.sync is not available. (Koen Martens) IMPROVEMENTS * Implement MemoryRepo.{set_description,get_description}. (Jelmer Vernooij) * Raise exception in Repo.stage() when absolute paths are passed in. Allow passing in relative paths to porcelain.add().(Jelmer Vernooij) BUG FIXES * Handle multi-line quoted values in config files. (Jelmer Vernooij, #495) * Allow porcelain.clone of repository without HEAD. (Jelmer Vernooij, #501) * Support passing tag ids to Walker()'s include argument. (Jelmer Vernooij) * Don't strip trailing newlines from extra headers. (Nicolas Dandrimont) * Set bufsize=0 for subprocess interaction with SSH client. Fixes hangs on Python 3. (René Stern, #434) * Don't drop first slash for SSH paths, except for those starting with "~". (Jelmer Vernooij, René Stern, #463) * Properly log off after retrieving just refs. (Jelmer Vernooij) 0.16.3 2016-01-14 TEST FIXES * Remove racy check that relies on clock time changing between writes. (Jelmer Vernooij) IMPROVEMENTS * Add porcelain.remote_add. (Jelmer Vernooij) 0.16.2 2016-01-14 IMPROVEMENTS * Fixed failing test-cases on windows. (Koen Martens) API CHANGES * Repo is now a context manager, so that it can be easily closed using a ``with`` statement. (Søren Løvborg) TEST FIXES * Only run worktree list compat tests against git 2.7.0, when 'git worktree list' was introduced. (Jelmer Vernooij) BUG FIXES * Ignore filemode when building index when core.filemode is false. (Koen Martens) * Initialize core.filemode configuration setting by probing the filesystem for trustable permissions. (Koen Martens) * Fix ``porcelain.reset`` to respect the comittish argument. (Koen Martens) * Fix dulwich.porcelain.ls_remote() on Python 3. (#471, Jelmer Vernooij) * Allow both unicode and byte strings for host paths in dulwich.client. (#435, Jelmer Vernooij) * Add remote from porcelain.clone. (#466, Jelmer Vernooij) * Fix unquoting of credentials before passing to urllib2. (#475, Volodymyr Holovko) * Cope with submodules in `build_index_from_tree`. (#477, Jelmer Vernooij) * Handle deleted files in `get_unstaged_changes`. (#483, Doug Hellmann) * Don't overwrite files when they haven't changed in `build_file_from_blob`. (#479, Benoît HERVIER) * Check for existence of index file before opening pack. Fixes a race when new packs are being added. (#482, wme) 0.16.1 2016-12-25 BUG FIXES * Fix python3 compatibility for dulwich.contrib.release_robot. (Jelmer Vernooij) 0.16.0 2016-12-24 IMPROVEMENTS * Add support for worktrees. See `git-worktree(1)` and `gitrepository-layout(5)`. (Laurent Rineau) * Add support for `commondir` file in Git control directories. (Laurent Rineau) * Add support for passwords in HTTP URLs. (Jon Bain, Mika Mäenpää) * Add `release_robot` script to contrib, allowing easy finding of current version based on Git tags. (Mark Mikofski) * Add ``Blob.splitlines`` method. (Jelmer Vernooij) BUG FIXES * Fix handling of ``Commit.tree`` being set to an actual tree object rather than a tree id. (Jelmer Vernooij) * Return remote refs from LocalGitClient.fetch_pack(), consistent with the documentation for that method. (#461, Jelmer Vernooij) * Fix handling of unknown URL schemes in get_transport_and_path. (#465, Jelmer Vernooij) 0.15.0 2016-10-09 BUG FIXES * Allow missing trailing LF when reading service name from HTTP servers. (Jelmer Vernooij, Andrew Shadura, #442) * Fix dulwich.porcelain.pull() on Python3. (Jelmer Vernooij, #451) * Properly pull in tags during dulwich.porcelain.clone. (Jelmer Vernooij, #408) CHANGES * Changed license from "GNU General Public License, version 2.0 or later" to "Apache License, version 2.0 or later or GNU General Public License, version 2.0 or later". (#153) IMPROVEMENTS * Add ``dulwich.porcelain.ls_tree`` implementation. (Jelmer Vernooij) 0.14.1 2016-07-05 BUG FIXES * Fix regression removing untouched refs when pushing over SSH. (Jelmer Vernooij #441) * Skip Python3 tests for SWIFT contrib module, as it has not yet been ported. 0.14.0 2016-07-03 BUG FIXES * Fix ShaFile.id after modification of a copied ShaFile. (Félix Mattrat, Jelmer Vernooij) * Support removing refs from porcelain.push. (Jelmer Vernooij, #437) * Stop magic protocol ref `capabilities^{}` from leaking out to clients. (Jelmer Vernooij, #254) IMPROVEMENTS * Add `dulwich.config.parse_submodules` function. * Add `RefsContainer.follow` method. (#438) 0.13.0 2016-04-24 IMPROVEMENTS * Support `ssh://` URLs in get_transport_and_path_from_url(). (Jelmer Vernooij, #402) * Support missing empty line after headers in Git commits and tags. (Nicolas Dandrimont, #413) * Fix `dulwich.porcelain.status` when used in empty trees. (Jelmer Vernooij, #415) * Return copies of objects in MemoryObjectStore rather than references, making the behaviour more consistent with that of DiskObjectStore. (Félix Mattrat, Jelmer Vernooij) * Fix ``dulwich.web`` on Python3. (#295, Jonas Haag) CHANGES * Drop support for Python 2.6. * Fix python3 client web support. (Jelmer Vernooij) BUG FIXES * Fix hang on Gzip decompression. (Jonas Haag) * Don't rely on working tell() and seek() methods on wsgi.input. (Jonas Haag) * Support fastexport/fastimport functionality on python3 with newer versions of fastimport (>= 0.9.5). (Jelmer Vernooij, Félix Mattrat) 0.12.0 2015-12-13 IMPROVEMENTS * Add a `dulwich.archive` module that can create tarballs. Based on code from Jonas Haag in klaus. * Add a `dulwich.reflog` module for reading and writing reflogs. (Jelmer Vernooij) * Fix handling of ambiguous refs in `parse_ref` to make it match the behaviour described in https://git-scm.com/docs/gitrevisions. (Chris Bunney) * Support Python3 in C modules. (Lele Gaifax) BUG FIXES * Simplify handling of SSH command invocation. Fixes quoting of paths. Thanks, Thomas Liebetraut. (#384) * Fix inconsistent handling of trailing slashes for DictRefsContainer. (#383) * Add hack to support thin packs duing fetch(), albeit while requiring the entire pack file to be loaded into memory. (jsbain) CHANGES * This will be the last release to support Python 2.6. 0.11.2 2015-09-18 IMPROVEMENTS * Add support for agent= capability. (Jelmer Vernooij, #298) * Add support for quiet capability. (Jelmer Vernooij) CHANGES * The ParamikoSSHVendor class has been moved to * dulwich.contrib.paramiko_vendor, as it's currently untested. (Jelmer Vernooij, #364) 0.11.1 2015-09-13 Fix-up release to exclude broken blame.py file. 0.11.0 2015-09-13 IMPROVEMENTS * Extended Python3 support to most of the codebase. (Gary van der Merwe, Jelmer Vernooij) * The `Repo` object has a new `close` method that can be called to close any open resources. (Gary van der Merwe) * Support 'git.bat' in SubprocessGitClient on Windows. (Stefan Zimmermann) * Advertise 'ofs-delta' capability in receive-pack server side capabilities. (Jelmer Vernooij) * Switched `default_local_git_client_cls` to `LocalGitClient`. (Gary van der Merwe) * Add `porcelain.ls_remote` and `GitClient.get_refs`. (Michael Edgar) * Add `Repo.discover` method. (B. M. Corser) * Add `dulwich.objectspec.parse_refspec`. (Jelmer Vernooij) * Add `porcelain.pack_objects` and `porcelain.repack`. (Jelmer Vernooij) BUG FIXES * Fix handling of 'done' in graph walker and implement the 'no-done' capability. (Tommy Yu, #88) * Avoid recursion limit issues resolving deltas. (William Grant, #81) * Allow arguments in local client binary path overrides. (Jelmer Vernooij) * Fix handling of commands with arguments in paramiko SSH client. (Andreas Klöckner, Jelmer Vernooij, #363) * Fix parsing of quoted strings in configs. (Jelmer Vernooij, #305) 0.10.1 2015-03-25 BUG FIXES * Return `ApplyDeltaError` when encountering delta errors in both C extensions and native delta application code. (Jelmer Vernooij, #259) 0.10.0 2015-03-22 BUG FIXES * In dulwich.index.build_index_from_tree, by default refuse to create entries that start with .git/. * Fix running of testsuite when installed. (Jelmer Vernooij, #223) * Use a block cache in _find_content_rename_candidates(), improving performance. (Mike Williams) * Add support for ``core.protectNTFS`` setting. (Jelmer Vernooij) * Fix TypeError when fetching empty updates. (Hwee Miin Koh) * Resolve delta refs when pulling into a MemoryRepo. (Max Shawabkeh, #256) * Fix handling of tags of non-commits in missing object finder. (Augie Fackler, #211) * Explicitly disable mmap on plan9 where it doesn't work. (Jeff Sickel) IMPROVEMENTS * New public method `Repo.reset_index`. (Jelmer Vernooij) * Prevent duplicate parsing of loose files in objects directory when reading. Thanks to David Keijser for the report. (Jelmer Vernooij, #231) 0.9.9 2015-03-20 SECURITY BUG FIXES * Fix buffer overflow in C implementation of pack apply_delta(). (CVE-2015-0838) Thanks to Ivan Fratric of the Google Security Team for reporting this issue. (Jelmer Vernooij) 0.9.8 2014-11-30 BUG FIXES * Various fixes to improve test suite running on Windows. (Gary van der Merwe) * Limit delta copy length to 64K in v2 pack files. (Robert Brown) * Strip newline from final ACKed SHA while fetching packs. (Michael Edgar) * Remove assignment to PyList_SIZE() that was causing segfaults on pypy. (Jelmer Vernooij, #196) IMPROVEMENTS * Add porcelain 'receive-pack' and 'upload-pack'. (Jelmer Vernooij) * Handle SIGINT signals in bin/dulwich. (Jelmer Vernooij) * Add 'status' support to bin/dulwich. (Jelmer Vernooij) * Add 'branch_create', 'branch_list', 'branch_delete' porcelain. (Jelmer Vernooij) * Add 'fetch' porcelain. (Jelmer Vernooij) * Add 'tag_delete' porcelain. (Jelmer Vernooij) * Add support for serializing/deserializing 'gpgsig' attributes in Commit. (Jelmer Vernooij) CHANGES * dul-web is now available as 'dulwich web-daemon'. (Jelmer Vernooij) * dulwich.porcelain.tag has been renamed to tag_create. dulwich.porcelain.list_tags has been renamed to tag_list. (Jelmer Vernooij) API CHANGES * Restore support for Python 2.6. (Jelmer Vernooij, Gary van der Merwe) 0.9.7 2014-06-08 BUG FIXES * Fix tests dependent on hash ordering. (Michael Edgar) * Support staging symbolic links in Repo.stage. (Robert Brown) * Ensure that all files object are closed when running the test suite. (Gary van der Merwe) * When writing OFS_DELTA pack entries, write correct offset. (Augie Fackler) * Fix handler of larger copy operations in packs. (Augie Fackler) * Various fixes to improve test suite running on Windows. (Gary van der Merwe) * Fix logic for extra adds of identical files in rename detector. (Robert Brown) IMPROVEMENTS * Add porcelain 'status'. (Ryan Faulkner) * Add porcelain 'daemon'. (Jelmer Vernooij) * Add `dulwich.greenthreads` module which provides support for concurrency of some object store operations. (Fabien Boucher) * Various changes to improve compatibility with Python 3. (Gary van der Merwe, Hannu Valtonen, michael-k) * Add OpenStack Swift backed repository implementation in dulwich.contrib. See README.swift for details. (Fabien Boucher) API CHANGES * An optional close function can be passed to the Protocol class. This will be called by its close method. (Gary van der Merwe) * All classes with close methods are now context managers, so that they can be easily closed using a `with` statement. (Gary van der Merwe) * Remove deprecated `num_objects` argument to `write_pack` methods. (Jelmer Vernooij) OTHER CHANGES * The 'dul-daemon' script has been removed. The same functionality is now available as 'dulwich daemon'. (Jelmer Vernooij) 0.9.6 2014-04-23 IMPROVEMENTS * Add support for recursive add in 'git add'. (Ryan Faulkner, Jelmer Vernooij) * Add porcelain 'list_tags'. (Ryan Faulkner) * Add porcelain 'push'. (Ryan Faulkner) * Add porcelain 'pull'. (Ryan Faulkner) * Support 'http.proxy' in HttpGitClient. (Jelmer Vernooij, #1096030) * Support 'http.useragent' in HttpGitClient. (Jelmer Vernooij) * In server, wait for clients to send empty list of wants when talking to empty repository. (Damien Tournoud) * Various changes to improve compatibility with Python 3. (Gary van der Merwe) BUG FIXES * Support unseekable 'wsgi.input' streams. (Jonas Haag) * Raise TypeError when passing unicode() object to Repo.__getitem__. (Jonas Haag) * Fix handling of `reset` command in dulwich.fastexport. (Jelmer Vernooij, #1249029) * In client, don't wait for server to close connection first. Fixes hang when used against GitHub server implementation. (Siddharth Agarwal) * DeltaChainIterator: fix a corner case where an object is inflated as an object already in the repository. (Damien Tournoud, #135) * Stop leaking file handles during pack reload. (Damien Tournoud) * Avoid reopening packs during pack cache reload. (Jelmer Vernooij) API CHANGES * Drop support for Python 2.6. (Jelmer Vernooij) 0.9.5 2014-02-23 IMPROVEMENTS * Add porcelain 'tag'. (Ryan Faulkner) * New module `dulwich.objectspec` for parsing strings referencing objects and commit ranges. (Jelmer Vernooij) * Add shallow branch support. (milki) * Allow passing urllib2 `opener` into HttpGitClient. (Dov Feldstern, #909037) CHANGES * Drop support for Python 2.4 and 2.5. (Jelmer Vernooij) API CHANGES * Remove long deprecated ``Repo.commit``, ``Repo.get_blob``, ``Repo.tree`` and ``Repo.tag``. (Jelmer Vernooij) * Remove long deprecated ``Repo.revision_history`` and ``Repo.ref``. (Jelmer Vernooij) * Remove long deprecated ``Tree.entries``. (Jelmer Vernooij) BUG FIXES * Raise KeyError rather than TypeError when passing in unicode object of length 20 or 40 to Repo.__getitem__. (Jelmer Vernooij) * Use 'rm' rather than 'unlink' in tests, since the latter does not exist on OpenBSD and other platforms. (Dmitrij D. Czarkoff) 0.9.4 2013-11-30 IMPROVEMENTS * Add ssh_kwargs attribute to ParamikoSSHVendor. (milki) * Add Repo.set_description(). (Víðir Valberg Guðmundsson) * Add a basic `dulwich.porcelain` module. (Jelmer Vernooij, Marcin Kuzminski) * Various performance improvements for object access. (Jelmer Vernooij) * New function `get_transport_and_path_from_url`, similar to `get_transport_and_path` but only supports URLs. (Jelmer Vernooij) * Add support for file:// URLs in `get_transport_and_path_from_url`. (Jelmer Vernooij) * Add LocalGitClient implementation. (Jelmer Vernooij) BUG FIXES * Support filesystems with 64bit inode and device numbers. (André Roth) CHANGES * Ref handling has been moved to dulwich.refs. (Jelmer Vernooij) API CHANGES * Remove long deprecated RefsContainer.set_ref(). (Jelmer Vernooij) * Repo.ref() is now deprecated in favour of Repo.refs[]. (Jelmer Vernooij) FEATURES * Add support for graftpoints. (milki) 0.9.3 2013-09-27 BUG FIXES * Fix path for stdint.h in MANIFEST.in. (Jelmer Vernooij) 0.9.2 2013-09-26 BUG FIXES * Include stdint.h in MANIFEST.in (Mark Mikofski) 0.9.1 2013-09-22 BUG FIXES * Support lookups of 40-character refs in BaseRepo.__getitem__. (Chow Loong Jin, Jelmer Vernooij) * Fix fetching packs with side-band-64k capability disabled. (David Keijser, Jelmer Vernooij) * Several fixes in send-pack protocol behaviour - handling of empty pack files and deletes. (milki, #1063087) * Fix capability negotiation when fetching packs over HTTP. (#1072461, William Grant) * Enforce determine_wants returning an empty list rather than None. (Fabien Boucher, Jelmer Vernooij) * In the server, support pushes just removing refs. (Fabien Boucher, Jelmer Vernooij) IMPROVEMENTS * Support passing a single revision to BaseRepo.get_walker() rather than a list of revisions. (Alberto Ruiz) * Add `Repo.get_description` method. (Jelmer Vernooij) * Support thin packs in Pack.iterobjects() and Pack.get_raw(). (William Grant) * Add `MemoryObjectStore.add_pack` and `MemoryObjectStore.add_thin_pack` methods. (David Bennett) * Add paramiko-based SSH vendor. (Aaron O'Mullan) * Support running 'dulwich.server' and 'dulwich.web' using 'python -m'. (Jelmer Vernooij) * Add ObjectStore.close(). (Jelmer Vernooij) * Raise appropriate NotImplementedError when encountering dumb HTTP servers. (Jelmer Vernooij) API CHANGES * SSHVendor.connect_ssh has been renamed to SSHVendor.run_command. (Jelmer Vernooij) * ObjectStore.add_pack() now returns a 3-tuple. The last element will be an abort() method that can be used to cancel the pack operation. (Jelmer Vernooij) 0.9.0 2013-05-31 BUG FIXES * Push efficiency - report missing objects only. (#562676, Artem Tikhomirov) * Use indentation consistent with C Git in config files. (#1031356, Curt Moore, Jelmer Vernooij) * Recognize and skip binary files in diff function. (Takeshi Kanemoto) * Fix handling of relative paths in dulwich.client.get_transport_and_path. (Brian Visel, #1169368) * Preserve ordering of entries in configuration. (Benjamin Pollack) * Support ~ expansion in SSH client paths. (milki, #1083439) * Support relative paths in alternate paths. (milki, Michel Lespinasse, #1175007) * Log all error messages from wsgiref server to the logging module. This makes the test suit quiet again. (Gary van der Merwe) * Support passing None for empty tree in changes_from_tree. (Kevin Watters) * Support fetching empty repository in client. (milki, #1060462) IMPROVEMENTS: * Add optional honor_filemode flag to build_index_from_tree. (Mark Mikofski) * Support core/filemode setting when building trees. (Jelmer Vernooij) * Add chapter on tags in tutorial. (Ryan Faulkner) FEATURES * Add support for mergetags. (milki, #963525) * Add support for posix shell hooks. (milki) 0.8.7 2012-11-27 BUG FIXES * Fix use of alternates in ``DiskObjectStore``.{__contains__,__iter__}. (Dmitriy) * Fix compatibility with Python 2.4. (David Carr) 0.8.6 2012-11-09 API CHANGES * dulwich.__init__ no longer imports client, protocol, repo and server modules. (Jelmer Vernooij) FEATURES * ConfigDict now behaves more like a dictionary. (Adam 'Cezar' Jenkins, issue #58) * HTTPGitApplication now takes an optional `fallback_app` argument. (Jonas Haag, issue #67) * Support for large pack index files. (Jameson Nash) TESTING * Make index entry tests a little bit less strict, to cope with slightly different behaviour on various platforms. (Jelmer Vernooij) * ``setup.py test`` (available when setuptools is installed) now runs all tests, not just the basic unit tests. (Jelmer Vernooij) BUG FIXES * Commit._deserialize now actually deserializes the current state rather than the previous one. (Yifan Zhang, issue #59) * Handle None elements in lists of TreeChange objects. (Alex Holmes) * Support cloning repositories without HEAD set. (D-Key, Jelmer Vernooij, issue #69) * Support ``MemoryRepo.get_config``. (Jelmer Vernooij) * In ``get_transport_and_path``, pass extra keyword arguments on to HttpGitClient. (Jelmer Vernooij) 0.8.5 2012-03-29 BUG FIXES * Avoid use of 'with' in dulwich.index. (Jelmer Vernooij) * Be a little bit strict about OS behaviour in index tests. Should fix the tests on Debian GNU/kFreeBSD. (Jelmer Vernooij) 0.8.4 2012-03-28 BUG FIXES * Options on the same line as sections in config files are now supported. (Jelmer Vernooij, #920553) * Only negotiate capabilities that are also supported by the server. (Rod Cloutier, Risto Kankkunen) * Fix parsing of invalid timezone offsets with two minus signs. (Jason R. Coombs, #697828) * Reset environment variables during tests, to avoid test isolation leaks reading ~/.gitconfig. (Risto Kankkunen) TESTS * $HOME is now explicitly specified for tests that use it to read ``~/.gitconfig``, to prevent test isolation issues. (Jelmer Vernooij, #920330) FEATURES * Additional arguments to get_transport_and_path are now passed on to the constructor of the transport. (Sam Vilain) * The WSGI server now transparently handles when a git client submits data using Content-Encoding: gzip. (David Blewett, Jelmer Vernooij) * Add dulwich.index.build_index_from_tree(). (milki) 0.8.3 2012-01-21 FEATURES * The config parser now supports the git-config file format as described in git-config(1) and can write git config files. (Jelmer Vernooij, #531092, #768687) * ``Repo.do_commit`` will now use the user identity from .git/config or ~/.gitconfig if none was explicitly specified. (Jelmer Vernooij) BUG FIXES * Allow ``determine_wants`` methods to include the zero sha in their return value. (Jelmer Vernooij) 0.8.2 2011-12-18 BUG FIXES * Cope with different zlib buffer sizes in sha1 file parser. (Jelmer Vernooij) * Fix get_transport_and_path for HTTP/HTTPS URLs. (Bruno Renié) * Avoid calling free_objects() on NULL in error cases. (Chris Eberle) * Fix use --bare argument to 'dulwich init'. (Chris Eberle) * Properly abort connections when the determine_wants function raises an exception. (Jelmer Vernooij, #856769) * Tweak xcodebuild hack to deal with more error output. (Jelmer Vernooij, #903840) FEATURES * Add support for retrieving tarballs from remote servers. (Jelmer Vernooij, #379087) * New method ``update_server_info`` which generates data for dumb server access. (Jelmer Vernooij, #731235) 0.8.1 2011-10-31 FEATURES * Repo.do_commit has a new argument 'ref'. * Repo.do_commit has a new argument 'merge_heads'. (Jelmer Vernooij) * New ``Repo.get_walker`` method. (Jelmer Vernooij) * New ``Repo.clone`` method. (Jelmer Vernooij, #725369) * ``GitClient.send_pack`` now supports the 'side-band-64k' capability. (Jelmer Vernooij) * ``HttpGitClient`` which supports the smart server protocol over HTTP. "dumb" access is not yet supported. (Jelmer Vernooij, #373688) * Add basic support for alternates. (Jelmer Vernooij, #810429) CHANGES * unittest2 or python >= 2.7 is now required for the testsuite. testtools is no longer supported. (Jelmer Vernooij, #830713) BUG FIXES * Fix compilation with older versions of MSVC. (Martin gz) * Special case 'refs/stash' as a valid ref. (Jelmer Vernooij, #695577) * Smart protocol clients can now change refs even if they are not uploading new data. (Jelmer Vernooij, #855993) * Don't compile C extensions when running in pypy. (Ronny Pfannschmidt, #881546) * Use different name for strnlen replacement function to avoid clashing with system strnlen. (Jelmer Vernooij, #880362) API CHANGES * ``Repo.revision_history`` is now deprecated in favor of ``Repo.get_walker``. (Jelmer Vernooij) 0.8.0 2011-08-07 FEATURES * New DeltaChainIterator abstract class for quickly iterating all objects in a pack, with implementations for pack indexing and inflation. (Dave Borowitz) * New walk module with a Walker class for customizable commit walking. (Dave Borowitz) * New tree_changes_for_merge function in diff_tree. (Dave Borowitz) * Easy rename detection in RenameDetector even without find_copies_harder. (Dave Borowitz) BUG FIXES * Avoid storing all objects in memory when writing pack. (Jelmer Vernooij, #813268) * Support IPv6 for git:// connections. (Jelmer Vernooij, #801543) * Improve performance of Repo.revision_history(). (Timo Schmid, #535118) * Fix use of SubprocessWrapper on Windows. (Paulo Madeira, #670035) * Fix compilation on newer versions of Mac OS X (Lion and up). (Ryan McKern, #794543) * Prevent raising ValueError for correct refs in RefContainer.__delitem__. * Correctly return a tuple from MemoryObjectStore.get_raw. (Dave Borowitz) * Fix a bug in reading the pack checksum when there are fewer than 20 bytes left in the buffer. (Dave Borowitz) * Support ~ in git:// URL paths. (Jelmer Vernooij, #813555) * Make ShaFile.__eq__ work when other is not a ShaFile. (Dave Borowitz) * ObjectStore.get_graph_walker() now no longer yields the same revision more than once. This has a significant improvement for performance when wide revision graphs are involved. (Jelmer Vernooij, #818168) * Teach ReceivePackHandler how to read empty packs. (Dave Borowitz) * Don't send a pack with duplicates of the same object. (Dave Borowitz) * Teach the server how to serve a clone of an empty repo. (Dave Borowitz) * Correctly advertise capabilities during receive-pack. (Dave Borowitz) * Fix add/add and add/rename conflicts in tree_changes_for_merge. (Dave Borowitz) * Use correct MIME types in web server. (Dave Borowitz) API CHANGES * write_pack no longer takes the num_objects argument and requires an object to be passed in that is iterable (rather than an iterator) and that provides __len__. (Jelmer Vernooij) * write_pack_data has been renamed to write_pack_objects and no longer takes a num_objects argument. (Jelmer Vernooij) * take_msb_bytes, read_zlib_chunks, unpack_objects, and PackStreamReader.read_objects now take an additional argument indicating a crc32 to compute. (Dave Borowitz) * PackObjectIterator was removed; its functionality is still exposed by PackData.iterobjects. (Dave Borowitz) * Add a sha arg to write_pack_object to incrementally compute a SHA. (Dave Borowitz) * Include offset in PackStreamReader results. (Dave Borowitz) * Move PackStreamReader from server to pack. (Dave Borowitz) * Extract a check_length_and_checksum, compute_file_sha, and pack_object_header pack helper functions. (Dave Borowitz) * Extract a compute_file_sha function. (Dave Borowitz) * Remove move_in_thin_pack as a separate method; add_thin_pack now completes the thin pack and moves it in in one step. Remove ThinPackData as well. (Dave Borowitz) * Custom buffer size in read_zlib_chunks. (Dave Borowitz) * New UnpackedObject data class that replaces ad-hoc tuples in the return value of unpack_object and various DeltaChainIterator methods. (Dave Borowitz) * Add a lookup_path convenience method to Tree. (Dave Borowitz) * Optionally create RenameDetectors without passing in tree SHAs. (Dave Borowitz) * Optionally include unchanged entries in RenameDetectors. (Dave Borowitz) * Optionally pass a RenameDetector to tree_changes. (Dave Borowitz) * Optionally pass a request object through to server handlers. (Dave Borowitz) TEST CHANGES * If setuptools is installed, "python setup.py test" will now run the testsuite. (Jelmer Vernooij) * Add a new build_pack test utility for building packs from a simple spec. (Dave Borowitz) * Add a new build_commit_graph test utility for building commits from a simple spec. (Dave Borowitz) 0.7.1 2011-04-12 BUG FIXES * Fix double decref in _diff_tree.c. (Ted Horst, #715528) * Fix the build on Windows. (Pascal Quantin) * Fix get_transport_and_path compatibility with pre-2.6.5 versions of Python. (Max Bowsher, #707438) * BaseObjectStore.determine_wants_all no longer breaks on zero SHAs. (Jelmer Vernooij) * write_tree_diff() now supports submodules. (Jelmer Vernooij) * Fix compilation for XCode 4 and older versions of distutils.sysconfig. (Daniele Sluijters) IMPROVEMENTS * Sphinxified documentation. (Lukasz Balcerzak) * Add Pack.keep.(Marc Brinkmann) API CHANGES * The order of the parameters to Tree.add(name, mode, sha) has changed, and is now consistent with the rest of Dulwich. Existing code will still work but print a DeprecationWarning. (Jelmer Vernooij, #663550) * Tree.entries() is now deprecated in favour of Tree.items() and Tree.iteritems(). (Jelmer Vernooij) 0.7.0 2011-01-21 FEATURES * New `dulwich.diff_tree` module for simple content-based rename detection. (Dave Borowitz) * Add Tree.items(). (Jelmer Vernooij) * Add eof() and unread_pkt_line() methods to Protocol. (Dave Borowitz) * Add write_tree_diff(). (Jelmer Vernooij) * Add `serve_command` function for git server commands as executables. (Jelmer Vernooij) * dulwich.client.get_transport_and_path now supports rsync-style repository URLs. (Dave Borowitz, #568493) BUG FIXES * Correct short-circuiting operation for no-op fetches in the server. (Dave Borowitz) * Support parsing git mbox patches without a version tail, as generated by Mercurial. (Jelmer Vernooij) * Fix dul-receive-pack and dul-upload-pack. (Jelmer Vernooij) * Zero-padded file modes in Tree objects no longer trigger an exception but the check code warns about them. (Augie Fackler, #581064) * Repo.init() now honors the mkdir flag. (#671159) * The ref format is now checked when setting a ref rather than when reading it back. (Dave Borowitz, #653527) * Make sure pack files are closed correctly. (Tay Ray Chuan) DOCUMENTATION * Run the tutorial inside the test suite. (Jelmer Vernooij) * Reorganized and updated the tutorial. (Jelmer Vernooij, Dave Borowitz, #610550, #610540) 0.6.2 2010-10-16 BUG FIXES * HTTP server correctly handles empty CONTENT_LENGTH. (Dave Borowitz) * Don't error when creating GitFiles with the default mode. (Dave Borowitz) * ThinPackData.from_file now works with resolve_ext_ref callback. (Dave Borowitz) * Provide strnlen() on mingw32 which doesn't have it. (Hans Kolek) * Set bare=true in the configuratin for bare repositories. (Dirk Neumann) FEATURES * Use slots for core objects to save up on memory. (Jelmer Vernooij) * Web server supports streaming progress/pack output. (Dave Borowitz) * New public function dulwich.pack.write_pack_header. (Dave Borowitz) * Distinguish between missing files and read errors in HTTP server. (Dave Borowitz) * Initial work on support for fastimport using python-fastimport. (Jelmer Vernooij) * New dulwich.pack.MemoryPackIndex class. (Jelmer Vernooij) * Delegate SHA peeling to the object store. (Dave Borowitz) TESTS * Use GitFile when modifying packed-refs in tests. (Dave Borowitz) * New tests in test_web with better coverage and fewer ad-hoc mocks. (Dave Borowitz) * Standardize quote delimiters in test_protocol. (Dave Borowitz) * Fix use when testtools is installed. (Jelmer Vernooij) * Add trivial test for write_pack_header. (Jelmer Vernooij) * Refactor some of dulwich.tests.compat.server_utils. (Dave Borowitz) * Allow overwriting id property of objects in test utils. (Dave Borowitz) * Use real in-memory objects rather than stubs for server tests. (Dave Borowitz) * Clean up MissingObjectFinder. (Dave Borowitz) API CHANGES * ObjectStore.iter_tree_contents now walks contents in depth-first, sorted order. (Dave Borowitz) * ObjectStore.iter_tree_contents can optionally yield tree objects as well. (Dave Borowitz). * Add side-band-64k support to ReceivePackHandler. (Dave Borowitz) * Change server capabilities methods to classmethods. (Dave Borowitz) * Tweak server handler injection. (Dave Borowitz) * PackIndex1 and PackIndex2 now subclass FilePackIndex, which is itself a subclass of PackIndex. (Jelmer Vernooij) DOCUMENTATION * Add docstrings for various functions in dulwich.objects. (Jelmer Vernooij) * Clean up docstrings in dulwich.protocol. (Dave Borowitz) * Explicitly specify allowed protocol commands to ProtocolGraphWalker.read_proto_line. (Dave Borowitz) * Add utility functions to DictRefsContainer. (Dave Borowitz) 0.6.1 2010-07-22 BUG FIXES * Fix memory leak in C implementation of sorted_tree_items. (Dave Borowitz) * Use correct path separators for named repo files. (Dave Borowitz) * python > 2.7 and testtools-based test runners will now also pick up skipped tests correctly. (Jelmer Vernooij) FEATURES * Move named file initilization to BaseRepo. (Dave Borowitz) * Add logging utilities and git/HTTP server logging. (Dave Borowitz) * The GitClient interface has been cleaned up and instances are now reusable. (Augie Fackler) * Allow overriding paths to executables in GitSSHClient. (Ross Light, Jelmer Vernooij, #585204) * Add PackBasedObjectStore.pack_loose_objects(). (Jelmer Vernooij) TESTS * Add tests for sorted_tree_items and C implementation. (Dave Borowitz) * Add a MemoryRepo that stores everything in memory. (Dave Borowitz) * Quiet logging output from web tests. (Dave Borowitz) * More flexible version checking for compat tests. (Dave Borowitz) * Compat tests for servers with and without side-band-64k. (Dave Borowitz) CLEANUP * Clean up file headers. (Dave Borowitz) TESTS * Use GitFile when modifying packed-refs in tests. (Dave Borowitz) API CHANGES * dulwich.pack.write_pack_index_v{1,2} now take a file-like object rather than a filename. (Jelmer Vernooij) * Make dul-daemon/dul-web trivial wrappers around server functionality. (Dave Borowitz) * Move reference WSGI handler to web.py. (Dave Borowitz) * Factor out _report_status in ReceivePackHandler. (Dave Borowitz) * Factor out a function to convert a line to a pkt-line. (Dave Borowitz) 0.6.0 2010-05-22 note: This list is most likely incomplete for 0.6.0. BUG FIXES * Fix ReceivePackHandler to disallow removing refs without delete-refs. (Dave Borowitz) * Deal with capabilities required by the client, even if they can not be disabled in the server. (Dave Borowitz) * Fix trailing newlines in generated patch files. (Jelmer Vernooij) * Implement RefsContainer.__contains__. (Jelmer Vernooij) * Cope with \r in ref files on Windows. ( http://github.com/jelmer/dulwich/issues/#issue/13, Jelmer Vernooij) * Fix GitFile breakage on Windows. (Anatoly Techtonik, #557585) * Support packed ref deletion with no peeled refs. (Augie Fackler) * Fix send pack when there is nothing to fetch. (Augie Fackler) * Fix fetch if no progress function is specified. (Augie Fackler) * Allow double-staging of files that are deleted in the index. (Dave Borowitz) * Fix RefsContainer.add_if_new to support dangling symrefs. (Dave Borowitz) * Non-existant index files in non-bare repositories are now treated as empty. (Dave Borowitz) * Always update ShaFile.id when the contents of the object get changed. (Jelmer Vernooij) * Various Python2.4-compatibility fixes. (Dave Borowitz) * Fix thin pack handling. (Dave Borowitz) FEATURES * Add include-tag capability to server. (Dave Borowitz) * New dulwich.fastexport module that can generate fastexport streams. (Jelmer Vernooij) * Implemented BaseRepo.__contains__. (Jelmer Vernooij) * Add __setitem__ to DictRefsContainer. (Dave Borowitz) * Overall improvements checking Git objects. (Dave Borowitz) * Packs are now verified while they are received. (Dave Borowitz) TESTS * Add framework for testing compatibility with C Git. (Dave Borowitz) * Add various tests for the use of non-bare repositories. (Dave Borowitz) * Cope with diffstat not being available on all platforms. (Tay Ray Chuan, Jelmer Vernooij) * Add make_object and make_commit convenience functions to test utils. (Dave Borowitz) API BREAKAGES * The 'committer' and 'message' arguments to Repo.do_commit() have been swapped. 'committer' is now optional. (Jelmer Vernooij) * Repo.get_blob, Repo.commit, Repo.tag and Repo.tree are now deprecated. (Jelmer Vernooij) * RefsContainer.set_ref() was renamed to RefsContainer.set_symbolic_ref(), for clarity. (Jelmer Vernooij) API CHANGES * The primary serialization APIs in dulwich.objects now work with chunks of strings rather than with full-text strings. (Jelmer Vernooij) 0.5.02010-03-03 BUG FIXES * Support custom fields in commits (readonly). (Jelmer Vernooij) * Improved ref handling. (Dave Borowitz) * Rework server protocol to be smarter and interoperate with cgit client. (Dave Borowitz) * Add a GitFile class that uses the same locking protocol for writes as cgit. (Dave Borowitz) * Cope with forward slashes correctly in the index on Windows. (Jelmer Vernooij, #526793) FEATURES * --pure option to setup.py to allow building/installing without the C extensions. (Hal Wine, Anatoly Techtonik, Jelmer Vernooij, #434326) * Implement Repo.get_config(). (Jelmer Vernooij, Augie Fackler) * HTTP dumb and smart server. (Dave Borowitz) * Add abstract baseclass for Repo that does not require file system operations. (Dave Borowitz) 0.4.1 2010-01-03 FEATURES * Add ObjectStore.iter_tree_contents(). (Jelmer Vernooij) * Add Index.changes_from_tree(). (Jelmer Vernooij) * Add ObjectStore.tree_changes(). (Jelmer Vernooij) * Add functionality for writing patches in dulwich.patch. (Jelmer Vernooij) 0.4.0 2009-10-07 DOCUMENTATION * Added tutorial. API CHANGES * dulwich.object_store.tree_lookup_path will now return the mode and sha of the object found rather than the object itself. BUG FIXES * Use binascii.hexlify / binascii.unhexlify for better performance. * Cope with extra unknown data in index files by ignoring it (for now). * Add proper error message when server unexpectedly hangs up. (#415843) * Correctly write opcode for equal in create_delta. 0.3.3 2009-07-23 FEATURES * Implement ShaFile.__hash__(). * Implement Tree.__len__() BUG FIXES * Check for 'objects' and 'refs' directories when looking for a Git repository. (#380818) 0.3.2 2009-05-20 BUG FIXES * Support the encoding field in Commits. * Some Windows compatibility fixes. * Fixed several issues in commit support. FEATURES * Basic support for handling submodules. 0.3.1 2009-05-13 FEATURES * Implemented Repo.__getitem__, Repo.__setitem__ and Repo.__delitem__ to access content. API CHANGES * Removed Repo.set_ref, Repo.remove_ref, Repo.tags, Repo.get_refs and Repo.heads in favor of Repo.refs, a dictionary-like object for accessing refs. BUG FIXES * Removed import of 'sha' module in objects.py, which was causing deprecation warnings on Python 2.6. 0.3.0 2009-05-10 FEATURES * A new function 'commit_tree' has been added that can commit a tree based on an index. BUG FIXES * The memory usage when generating indexes has been significantly reduced. * A memory leak in the C implementation of parse_tree has been fixed. * The send-pack smart server command now works. (Thanks Scott Chacon) * The handling of short timestamps (less than 10 digits) has been fixed. * The handling of timezones has been fixed. 0.2.1 2009-04-30 BUG FIXES * Fix compatibility with Python2.4. 0.2.0 2009-04-30 FEATURES * Support for activity reporting in smart protocol client. * Optional C extensions for better performance in a couple of places that are performance-critical. 0.1.1 2009-03-13 BUG FIXES * Fixed regression in Repo.find_missing_objects() * Don't fetch ^{} objects from remote hosts, as requesting them causes a hangup. * Always write pack to disk completely before calculating checksum. FEATURES * Allow disabling thin packs when talking to remote hosts. 0.1.0 2009-01-24 * Initial release. diff --git a/PKG-INFO b/PKG-INFO index 53932d42..6b9c95fc 100644 --- a/PKG-INFO +++ b/PKG-INFO @@ -1,119 +1,126 @@ Metadata-Version: 2.1 Name: dulwich -Version: 0.19.6 -Summary: [![Build Status](https://travis-ci.org/dulwich/dulwich.png?branch=master)](https://travis-ci.org/dulwich/dulwich) -[![Windows Build status](https://ci.appveyor.com/api/projects/status/mob7g4vnrfvvoweb?svg=true)](https://ci.appveyor.com/project/jelmer/dulwich/branch/master) - -This is the Dulwich project. - -It aims to provide an interface to git repos (both local and remote) that -doesn't call out to git directly but instead uses pure Python. - -**Main website**: [www.dulwich.io](https://www.dulwich.io/) - -**License**: Apache License, version 2 or GNU General Public License, version 2 or later. - -The project is named after the part of London that Mr. and Mrs. Git live in -in the particular Monty Python sketch. - -Installation ------------- - -By default, Dulwich' setup.py will attempt to build and install the optional C -extensions. The reason for this is that they significantly improve the performance -since some low-level operations that are executed often are much slower in CPython. - -If you don't want to install the C bindings, specify the --pure argument to setup.py:: - - $ python setup.py --pure install - -or if you are installing from pip:: - - $ pip install dulwich --global-option="--pure" - -Note that you can also specify --global-option in a -[requirements.txt](https://pip.pypa.io/en/stable/reference/pip_install/#requirement-specifiers) -file, e.g. like this:: - - dulwich --global-option=--pure - -Getting started ---------------- - -Dulwich comes with both a lower-level API and higher-level plumbing ("porcelain"). - -For example, to use the lower level API to access the commit message of the -last commit: - - >>> from dulwich.repo import Repo - >>> r = Repo('.') - >>> r.head() - '57fbe010446356833a6ad1600059d80b1e731e15' - >>> c = r[r.head()] - >>> c - - >>> c.message - 'Add note about encoding.\n' - -And to print it using porcelain: - - >>> from dulwich import porcelain - >>> porcelain.log('.', max_entries=1) - -------------------------------------------------- - commit: 57fbe010446356833a6ad1600059d80b1e731e15 - Author: Jelmer Vernooij - Date: Sat Apr 29 2017 23:57:34 +0000 - - Add note about encoding. - -Further documentation ---------------------- - -The dulwich documentation can be found in docs/ and -[on the web](https://www.dulwich.io/docs/). - -The API reference can be generated using pydoctor, by running "make pydoctor", -or [on the web](https://www.dulwich.io/apidocs). - -Help ----- - -There is a *#dulwich* IRC channel on the [Freenode](https://www.freenode.net/), and -[dulwich-announce](https://groups.google.com/forum/#!forum/dulwich-announce) -and [dulwich-discuss](https://groups.google.com/forum/#!forum/dulwich-discuss) -mailing lists. - -Contributing ------------- - -For a full list of contributors, see the git logs or [AUTHORS](AUTHORS). - -If you'd like to contribute to Dulwich, see the [CONTRIBUTING](CONTRIBUTING.md) -file and [list of open issues](https://github.com/dulwich/dulwich/issues). - -Supported versions of Python ----------------------------- - -At the moment, Dulwich supports (and is tested on) CPython 2.7, 3.3, 3.4, 3.5, 3.6 and Pypy. - +Version: 0.19.10 +Summary: Python Git Library Home-page: https://www.dulwich.io/ Author: Jelmer Vernooij Author-email: jelmer@jelmer.uk License: Apachev2 or later or GPLv2 Project-URL: Bug Tracker, https://github.com/dulwich/dulwich/issues -Description: UNKNOWN +Project-URL: GitHub, https://github.com/dulwich/dulwich +Project-URL: Repository, https://www.dulwich.io/code/ +Description: .. image:: https://travis-ci.org/dulwich/dulwich.png?branch=master + :alt: Build Status + :target: https://travis-ci.org/dulwich/dulwich + + .. image:: https://ci.appveyor.com/api/projects/status/mob7g4vnrfvvoweb?svg=true + :alt: Windows Build Status + :target: https://ci.appveyor.com/project/jelmer/dulwich/branch/master + + This is the Dulwich project. + + It aims to provide an interface to git repos (both local and remote) that + doesn't call out to git directly but instead uses pure Python. + + **Main website**: + + **License**: Apache License, version 2 or GNU General Public License, version 2 or later. + + The project is named after the part of London that Mr. and Mrs. Git live in + in the particular Monty Python sketch. + + Installation + ------------ + + By default, Dulwich' setup.py will attempt to build and install the optional C + extensions. The reason for this is that they significantly improve the performance + since some low-level operations that are executed often are much slower in CPython. + + If you don't want to install the C bindings, specify the --pure argument to setup.py:: + + $ python setup.py --pure install + + or if you are installing from pip:: + + $ pip install dulwich --global-option="--pure" + + Note that you can also specify --global-option in a + `requirements.txt `_ + file, e.g. like this:: + + dulwich --global-option=--pure + + Getting started + --------------- + + Dulwich comes with both a lower-level API and higher-level plumbing ("porcelain"). + + For example, to use the lower level API to access the commit message of the + last commit:: + + >>> from dulwich.repo import Repo + >>> r = Repo('.') + >>> r.head() + '57fbe010446356833a6ad1600059d80b1e731e15' + >>> c = r[r.head()] + >>> c + + >>> c.message + 'Add note about encoding.\n' + + And to print it using porcelain:: + + >>> from dulwich import porcelain + >>> porcelain.log('.', max_entries=1) + -------------------------------------------------- + commit: 57fbe010446356833a6ad1600059d80b1e731e15 + Author: Jelmer Vernooij + Date: Sat Apr 29 2017 23:57:34 +0000 + + Add note about encoding. + + Further documentation + --------------------- + + The dulwich documentation can be found in docs/ and + `on the web `_. + + The API reference can be generated using pydoctor, by running "make pydoctor", + or `on the web `_. + + Help + ---- + + There is a *#dulwich* IRC channel on the `Freenode `_, and + `dulwich-announce `_ + and `dulwich-discuss `_ + mailing lists. + + Contributing + ------------ + + For a full list of contributors, see the git logs or `AUTHORS `_. + + If you'd like to contribute to Dulwich, see the `CONTRIBUTING `_ + file and `list of open issues `_. + + Supported versions of Python + ---------------------------- + + At the moment, Dulwich supports (and is tested on) CPython 2.7, 3.4, 3.5, 3.6 and Pypy. + +Keywords: git vcs Platform: UNKNOWN Classifier: Development Status :: 4 - Beta Classifier: License :: OSI Approved :: Apache Software License Classifier: Programming Language :: Python :: 2.7 -Classifier: Programming Language :: Python :: 3.3 Classifier: Programming Language :: Python :: 3.4 Classifier: Programming Language :: Python :: 3.5 Classifier: Programming Language :: Python :: 3.6 Classifier: Programming Language :: Python :: Implementation :: CPython Classifier: Programming Language :: Python :: Implementation :: PyPy Classifier: Operating System :: POSIX Classifier: Operating System :: Microsoft :: Windows Classifier: Topic :: Software Development :: Version Control Provides-Extra: fastimport Provides-Extra: https diff --git a/README.md b/README.rst similarity index 65% rename from README.md rename to README.rst index 568b8387..701e2abc 100644 --- a/README.md +++ b/README.rst @@ -1,94 +1,99 @@ -[![Build Status](https://travis-ci.org/dulwich/dulwich.png?branch=master)](https://travis-ci.org/dulwich/dulwich) -[![Windows Build status](https://ci.appveyor.com/api/projects/status/mob7g4vnrfvvoweb?svg=true)](https://ci.appveyor.com/project/jelmer/dulwich/branch/master) +.. image:: https://travis-ci.org/dulwich/dulwich.png?branch=master + :alt: Build Status + :target: https://travis-ci.org/dulwich/dulwich + +.. image:: https://ci.appveyor.com/api/projects/status/mob7g4vnrfvvoweb?svg=true + :alt: Windows Build Status + :target: https://ci.appveyor.com/project/jelmer/dulwich/branch/master This is the Dulwich project. It aims to provide an interface to git repos (both local and remote) that doesn't call out to git directly but instead uses pure Python. -**Main website**: [www.dulwich.io](https://www.dulwich.io/) +**Main website**: **License**: Apache License, version 2 or GNU General Public License, version 2 or later. The project is named after the part of London that Mr. and Mrs. Git live in in the particular Monty Python sketch. Installation ------------ By default, Dulwich' setup.py will attempt to build and install the optional C extensions. The reason for this is that they significantly improve the performance since some low-level operations that are executed often are much slower in CPython. If you don't want to install the C bindings, specify the --pure argument to setup.py:: $ python setup.py --pure install or if you are installing from pip:: $ pip install dulwich --global-option="--pure" Note that you can also specify --global-option in a -[requirements.txt](https://pip.pypa.io/en/stable/reference/pip_install/#requirement-specifiers) +`requirements.txt `_ file, e.g. like this:: dulwich --global-option=--pure Getting started --------------- Dulwich comes with both a lower-level API and higher-level plumbing ("porcelain"). For example, to use the lower level API to access the commit message of the -last commit: +last commit:: >>> from dulwich.repo import Repo >>> r = Repo('.') >>> r.head() '57fbe010446356833a6ad1600059d80b1e731e15' >>> c = r[r.head()] >>> c >>> c.message 'Add note about encoding.\n' -And to print it using porcelain: +And to print it using porcelain:: >>> from dulwich import porcelain >>> porcelain.log('.', max_entries=1) -------------------------------------------------- commit: 57fbe010446356833a6ad1600059d80b1e731e15 Author: Jelmer Vernooij Date: Sat Apr 29 2017 23:57:34 +0000 Add note about encoding. Further documentation --------------------- The dulwich documentation can be found in docs/ and -[on the web](https://www.dulwich.io/docs/). +`on the web `_. The API reference can be generated using pydoctor, by running "make pydoctor", -or [on the web](https://www.dulwich.io/apidocs). +or `on the web `_. Help ---- -There is a *#dulwich* IRC channel on the [Freenode](https://www.freenode.net/), and -[dulwich-announce](https://groups.google.com/forum/#!forum/dulwich-announce) -and [dulwich-discuss](https://groups.google.com/forum/#!forum/dulwich-discuss) +There is a *#dulwich* IRC channel on the `Freenode `_, and +`dulwich-announce `_ +and `dulwich-discuss `_ mailing lists. Contributing ------------ -For a full list of contributors, see the git logs or [AUTHORS](AUTHORS). +For a full list of contributors, see the git logs or `AUTHORS `_. -If you'd like to contribute to Dulwich, see the [CONTRIBUTING](CONTRIBUTING.md) -file and [list of open issues](https://github.com/dulwich/dulwich/issues). +If you'd like to contribute to Dulwich, see the `CONTRIBUTING `_ +file and `list of open issues `_. Supported versions of Python ---------------------------- -At the moment, Dulwich supports (and is tested on) CPython 2.7, 3.3, 3.4, 3.5, 3.6 and Pypy. +At the moment, Dulwich supports (and is tested on) CPython 2.7, 3.4, 3.5, 3.6 and Pypy. diff --git a/README.swift.md b/README.swift.rst similarity index 93% rename from README.swift.md rename to README.swift.rst index 2c82c4a0..7fefafc2 100644 --- a/README.swift.md +++ b/README.swift.rst @@ -1,133 +1,133 @@ Openstack Swift as backend for Dulwich ====================================== Fabien Boucher The module dulwich/contrib/swift.py implements dulwich.repo.BaseRepo in order to being compatible with Openstack Swift. We can then use Dulwich as server (Git server) and instead of using a regular POSIX file system to store repository objects we use the object storage Swift via its own API. c Git client <---> Dulwich server <---> Openstack Swift API This implementation is still a work in progress and we can say that is a Beta version so you need to be prepared to find bugs. Configuration file ------------------ We need to provide some configuration values in order to let Dulwich talk and authenticate against Swift. The following config file must -be used as template: +be used as template:: [swift] # Authentication URL (Keystone or Swift) auth_url = http://127.0.0.1:5000/v2.0 # Authentication version to use auth_ver = 2 # The tenant and username separated by a semicolon username = admin;admin # The user password password = pass # The Object storage region to use (auth v2) (Default RegionOne) region_name = RegionOne # The Object storage endpoint URL to use (auth v2) (Default internalURL) endpoint_type = internalURL # Concurrency to use for parallel tasks (Default 10) concurrency = 10 # Size of the HTTP pool (Default 10) http_pool_length = 10 # Timeout delay for HTTP connections (Default 20) http_timeout = 20 # Chunk size to read from pack (Bytes) (Default 12228) chunk_length = 12228 # Cache size (MBytes) (Default 20) cache_length = 20 Note that for now we use the same tenant to perform the requests against Swift. Therefor there is only one Swift account used for storing repositories. Each repository will be contained in a Swift container. How to start unittest --------------------- There is no need to have a Swift cluster running to run the unitests. -Just run the following command in the Dulwich source directory: +Just run the following command in the Dulwich source directory:: $ PYTHONPATH=. python -m dulwich.contrib.test_swift How to start functional tests ----------------------------- We provide some basic tests to perform smoke tests against a real Swift cluster. To run those functional tests you need a properly configured -configuration file. The tests can be run as follow: +configuration file. The tests can be run as follow:: $ DULWICH_SWIFT_CFG=/etc/swift-dul.conf PYTHONPATH=. python -m dulwich.contrib.test_swift_smoke How to install -------------- Install the Dulwich library via the setup.py. The dependencies will be -automatically retrieved from pypi: +automatically retrieved from pypi:: $ python ./setup.py install How to run the server --------------------- -Start the server using the following command: +Start the server using the following command:: $ python -m dulwich.contrib.swift daemon -c /etc/swift-dul.conf -l 127.0.0.1 Note that a lot of request will be performed against the Swift cluster so it is better to start the Dulwich server as close as possible of the Swift proxy. The best solution is to run the server on the Swift proxy node to reduce the latency. How to use ---------- Once you have validated that the functional tests is working as expected and the server is running we can init a bare repository. Run this -command with the name of the repository to create: +command with the name of the repository to create:: $ python -m dulwich.contrib.swift init -c /etc/swift-dul.conf edeploy The repository name will be the container that will contain all the Git objects for the repository. Then standard c Git client can be used to perform operations against this repository. -As an example we can clone the previously empty bare repository: +As an example we can clone the previously empty bare repository:: $ git clone git://localhost/edeploy -Then push an existing project in it: +Then push an existing project in it:: $ git clone https://github.com/enovance/edeploy.git edeployclone $ cd edeployclone $ git remote add alt git://localhost/edeploy $ git push alt master $ git ls-remote alt 9dc50a9a9bff1e232a74e365707f22a62492183e HEAD 9dc50a9a9bff1e232a74e365707f22a62492183e refs/heads/master The other Git commands can be used the way you do usually against a regular repository. Note the daemon subcommands starts a Git server listening for the Git protocol. Therefor there is no authentication or encryption at all between the cGIT client and the GIT server (Dulwich). Note on the .info file for pack object -------------------------------------- The Swift interface of Dulwich relies only on the pack format to store Git objects. Instead of using only an index (pack-sha.idx) along with the pack, we add a second file (pack-sha.info). This file is automatically created when a client pushes some references on the repository. The purpose of this file is to speed up pack creation server side when a client fetches some references. Currently this .info format is not optimized and may change in future. diff --git a/appveyor.yml b/appveyor.yml index c401fb86..ed11d9f7 100644 --- a/appveyor.yml +++ b/appveyor.yml @@ -1,96 +1,88 @@ environment: matrix: - PYTHON: "C:\\Python27" PYTHON_VERSION: "2.7.x" PYTHON_ARCH: "32" - PYTHON: "C:\\Python27-x64" PYTHON_VERSION: "2.7.x" PYTHON_ARCH: "64" - - PYTHON: "C:\\Python33" - PYTHON_VERSION: "3.3.x" - PYTHON_ARCH: "32" - - - PYTHON: "C:\\Python33-x64" - PYTHON_VERSION: "3.3.x" - PYTHON_ARCH: "64" - DISTUTILS_USE_SDK: "1" - - PYTHON: "C:\\Python34" PYTHON_VERSION: "3.4.x" PYTHON_ARCH: "32" - PYTHON: "C:\\Python34-x64" PYTHON_VERSION: "3.4.x" PYTHON_ARCH: "64" DISTUTILS_USE_SDK: "1" - PYTHON: "C:\\Python35" PYTHON_VERSION: "3.5.x" PYTHON_ARCH: "32" - PYTHON: "C:\\Python35-x64" PYTHON_VERSION: "3.5.x" PYTHON_ARCH: "64" - PYTHON: "C:\\Python36" PYTHON_VERSION: "3.6.x" PYTHON_ARCH: "32" - PYTHON: "C:\\Python36-x64" PYTHON_VERSION: "3.6.x" PYTHON_ARCH: "64" install: # If there is a newer build queued for the same PR, cancel this one. # The AppVeyor 'rollout builds' option is supposed to serve the same # purpose but it is problematic because it tends to cancel builds pushed # directly to master instead of just PR builds (or the converse). # credits: JuliaLang developers. - ps: if ($env:APPVEYOR_PULL_REQUEST_NUMBER -and $env:APPVEYOR_BUILD_NUMBER -ne ((Invoke-RestMethod ` https://ci.appveyor.com/api/projects/$env:APPVEYOR_ACCOUNT_NAME/$env:APPVEYOR_PROJECT_SLUG/history?recordsNumber=50).builds | ` Where-Object pullRequestId -eq $env:APPVEYOR_PULL_REQUEST_NUMBER)[0].buildNumber) { ` throw "There are newer queued builds for this pull request, failing early." } - ECHO "Filesystem root:" - ps: "ls \"C:/\"" - ECHO "Installed SDKs:" - ps: "ls \"C:/Program Files/Microsoft SDKs/Windows\"" # Install Python (from the official .msi of http://python.org) and pip when # not already installed. - ps: if (-not(Test-Path($env:PYTHON))) { & appveyor\install.ps1 } # Prepend newly installed Python to the PATH of this build (this cannot be # done from inside the powershell script as it would require to restart # the parent CMD process). - "SET PATH=%PYTHON%;%PYTHON%\\Scripts;%PATH%" # Check that we have the expected version and architecture for Python - "build.cmd %PYTHON%\\python.exe --version" - "build.cmd %PYTHON%\\python.exe -c \"import struct; print(struct.calcsize('P') * 8)\"" # Install setuptools/wheel so that we can e.g. use bdist_wheel - "pip install setuptools wheel" - "build.cmd %PYTHON%\\python.exe setup.py develop" build_script: # Build the compiled extension - "build.cmd %PYTHON%\\python.exe setup.py build" test_script: - "build.cmd %PYTHON%\\python.exe setup.py test" + - "build.cmd %PYTHON%\\pythonw.exe setup.py test" after_test: - "build.cmd %PYTHON%\\python.exe setup.py bdist_wheel" # http://stackoverflow.com/questions/43255455/unicode-character-causing-error-with-bdist-wininst-on-python-3-but-not-python-2 # - "python setup.py bdist_wininst" - "build.cmd %PYTHON%\\python.exe setup.py bdist_msi" - ps: "ls dist" artifacts: - path: dist\* diff --git a/bin/dulwich b/bin/dulwich index 1626b56b..eeaee124 100755 --- a/bin/dulwich +++ b/bin/dulwich @@ -1,700 +1,716 @@ #!/usr/bin/python -u # # dulwich - Simple command-line interface to Dulwich # Copyright (C) 2008-2011 Jelmer Vernooij # vim: expandtab # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """Simple command-line interface to Dulwich> This is a very simple command-line wrapper for Dulwich. It is by no means intended to be a full-blown Git command-line interface but just a way to test Dulwich. """ import os import sys from getopt import getopt import optparse import signal def signal_int(signal, frame): sys.exit(1) def signal_quit(signal, frame): import pdb pdb.set_trace() if 'DULWICH_PDB' in os.environ: signal.signal(signal.SIGQUIT, signal_quit) signal.signal(signal.SIGINT, signal_int) from dulwich import porcelain from dulwich.client import get_transport_and_path from dulwich.errors import ApplyDeltaError from dulwich.index import Index from dulwich.pack import Pack, sha_to_hex from dulwich.patch import write_tree_diff from dulwich.repo import Repo class Command(object): """A Dulwich subcommand.""" def run(self, args): """Run the command.""" raise NotImplementedError(self.run) class cmd_archive(Command): def run(self, args): parser = optparse.OptionParser() parser.add_option("--remote", type=str, help="Retrieve archive from specified remote repo") options, args = parser.parse_args(args) committish = args.pop(0) if options.remote: client, path = get_transport_and_path(options.remote) client.archive(path, committish, sys.stdout.write, write_error=sys.stderr.write) else: porcelain.archive('.', committish, outstream=sys.stdout, errstream=sys.stderr) class cmd_add(Command): def run(self, args): opts, args = getopt(args, "", []) porcelain.add(".", paths=args) class cmd_rm(Command): def run(self, args): opts, args = getopt(args, "", []) porcelain.rm(".", paths=args) class cmd_fetch_pack(Command): def run(self, args): opts, args = getopt(args, "", ["all"]) opts = dict(opts) client, path = get_transport_and_path(args.pop(0)) r = Repo(".") if "--all" in opts: determine_wants = r.object_store.determine_wants_all else: determine_wants = lambda x: [y for y in args if not y in r.object_store] client.fetch(path, r, determine_wants) class cmd_fetch(Command): def run(self, args): opts, args = getopt(args, "", []) opts = dict(opts) client, path = get_transport_and_path(args.pop(0)) r = Repo(".") if "--all" in opts: determine_wants = r.object_store.determine_wants_all refs = client.fetch(path, r, progress=sys.stdout.write) print("Remote refs:") for item in refs.items(): print("%s -> %s" % item) class cmd_fsck(Command): def run(self, args): opts, args = getopt(args, "", []) opts = dict(opts) for (obj, msg) in porcelain.fsck('.'): print("%s: %s" % (obj, msg)) class cmd_log(Command): def run(self, args): parser = optparse.OptionParser() parser.add_option("--reverse", dest="reverse", action="store_true", help="Reverse order in which entries are printed") parser.add_option("--name-status", dest="name_status", action="store_true", help="Print name/status for each changed file") options, args = parser.parse_args(args) porcelain.log(".", paths=args, reverse=options.reverse, name_status=options.name_status, outstream=sys.stdout) class cmd_diff(Command): def run(self, args): opts, args = getopt(args, "", []) if args == []: print("Usage: dulwich diff COMMITID") sys.exit(1) r = Repo(".") commit_id = args[0] commit = r[commit_id] parent_commit = r[commit.parents[0]] write_tree_diff(sys.stdout, r.object_store, parent_commit.tree, commit.tree) class cmd_dump_pack(Command): def run(self, args): opts, args = getopt(args, "", []) if args == []: print("Usage: dulwich dump-pack FILENAME") sys.exit(1) basename, _ = os.path.splitext(args[0]) x = Pack(basename) print("Object names checksum: %s" % x.name()) print("Checksum: %s" % sha_to_hex(x.get_stored_checksum())) if not x.check(): print("CHECKSUM DOES NOT MATCH") print("Length: %d" % len(x)) for name in x: try: print("\t%s" % x[name]) except KeyError as k: print("\t%s: Unable to resolve base %s" % (name, k)) except ApplyDeltaError as e: print("\t%s: Unable to apply delta: %r" % (name, e)) class cmd_dump_index(Command): def run(self, args): opts, args = getopt(args, "", []) if args == []: print("Usage: dulwich dump-index FILENAME") sys.exit(1) filename = args[0] idx = Index(filename) for o in idx: print(o, idx[o]) class cmd_init(Command): def run(self, args): opts, args = getopt(args, "", ["bare"]) opts = dict(opts) if args == []: path = os.getcwd() else: path = args[0] porcelain.init(path, bare=("--bare" in opts)) class cmd_clone(Command): def run(self, args): - opts, args = getopt(args, "", ["bare"]) - opts = dict(opts) + parser = optparse.OptionParser() + parser.add_option("--bare", dest="bare", + help="Whether to create a bare repository.", + action="store_true") + parser.add_option("--depth", dest="depth", + type=int, help="Depth at which to fetch") + options, args = parser.parse_args(args) if args == []: print("usage: dulwich clone host:path [PATH]") sys.exit(1) source = args.pop(0) if len(args) > 0: target = args.pop(0) else: target = None - porcelain.clone(source, target, bare=("--bare" in opts)) + porcelain.clone(source, target, bare=options.bare, depth=options.depth) class cmd_commit(Command): def run(self, args): opts, args = getopt(args, "", ["message"]) opts = dict(opts) porcelain.commit(".", message=opts["--message"]) class cmd_commit_tree(Command): def run(self, args): opts, args = getopt(args, "", ["message"]) if args == []: print("usage: dulwich commit-tree tree") sys.exit(1) opts = dict(opts) porcelain.commit_tree(".", tree=args[0], message=opts["--message"]) class cmd_update_server_info(Command): def run(self, args): porcelain.update_server_info(".") class cmd_symbolic_ref(Command): def run(self, args): opts, args = getopt(args, "", ["ref-name", "force"]) if not args: print("Usage: dulwich symbolic-ref REF_NAME [--force]") sys.exit(1) ref_name = args.pop(0) porcelain.symbolic_ref(".", ref_name=ref_name, force='--force' in args) class cmd_show(Command): def run(self, args): opts, args = getopt(args, "", []) porcelain.show(".", args) class cmd_diff_tree(Command): def run(self, args): opts, args = getopt(args, "", []) if len(args) < 2: print("Usage: dulwich diff-tree OLD-TREE NEW-TREE") sys.exit(1) porcelain.diff_tree(".", args[0], args[1]) class cmd_rev_list(Command): def run(self, args): opts, args = getopt(args, "", []) if len(args) < 1: print('Usage: dulwich rev-list COMMITID...') sys.exit(1) porcelain.rev_list('.', args) class cmd_tag(Command): def run(self, args): - opts, args = getopt(args, '', []) - if len(args) < 2: - print('Usage: dulwich tag NAME') - sys.exit(1) - porcelain.tag('.', args[0]) + parser = optparse.OptionParser() + parser.add_option("-a", "--annotated", help="Create an annotated tag.", action="store_true") + parser.add_option("-s", "--sign", help="Sign the annotated tag.", action="store_true") + options, args = parser.parse_args(args) + porcelain.tag_create( + '.', args[0], annotated=options.annotated, + sign=options.sign) class cmd_repack(Command): def run(self, args): opts, args = getopt(args, "", []) opts = dict(opts) porcelain.repack('.') class cmd_reset(Command): def run(self, args): opts, args = getopt(args, "", ["hard", "soft", "mixed"]) opts = dict(opts) mode = "" if "--hard" in opts: mode = "hard" elif "--soft" in opts: mode = "soft" elif "--mixed" in opts: mode = "mixed" porcelain.reset('.', mode=mode, *args) class cmd_daemon(Command): def run(self, args): from dulwich import log_utils from dulwich.protocol import TCP_GIT_PORT parser = optparse.OptionParser() parser.add_option("-l", "--listen_address", dest="listen_address", default="localhost", help="Binding IP address.") parser.add_option("-p", "--port", dest="port", type=int, default=TCP_GIT_PORT, help="Binding TCP port.") options, args = parser.parse_args(args) log_utils.default_logging_config() if len(args) >= 1: gitdir = args[0] else: gitdir = '.' from dulwich import porcelain porcelain.daemon(gitdir, address=options.listen_address, port=options.port) class cmd_web_daemon(Command): def run(self, args): from dulwich import log_utils parser = optparse.OptionParser() parser.add_option("-l", "--listen_address", dest="listen_address", default="", help="Binding IP address.") parser.add_option("-p", "--port", dest="port", type=int, default=8000, help="Binding TCP port.") options, args = parser.parse_args(args) log_utils.default_logging_config() if len(args) >= 1: gitdir = args[0] else: gitdir = '.' from dulwich import porcelain porcelain.web_daemon(gitdir, address=options.listen_address, port=options.port) +class cmd_write_tree(Command): + + def run(self, args): + parser = optparse.OptionParser() + options, args = parser.parse_args(args) + sys.stdout.write('%s\n' % porcelain.write_tree('.')) + + class cmd_receive_pack(Command): def run(self, args): parser = optparse.OptionParser() options, args = parser.parse_args(args) if len(args) >= 1: gitdir = args[0] else: gitdir = '.' porcelain.receive_pack(gitdir) class cmd_upload_pack(Command): def run(self, args): parser = optparse.OptionParser() options, args = parser.parse_args(args) if len(args) >= 1: gitdir = args[0] else: gitdir = '.' porcelain.upload_pack(gitdir) class cmd_status(Command): def run(self, args): parser = optparse.OptionParser() options, args = parser.parse_args(args) if len(args) >= 1: gitdir = args[0] else: gitdir = '.' status = porcelain.status(gitdir) if any(names for (kind, names) in status.staged.items()): sys.stdout.write("Changes to be committed:\n\n") for kind, names in status.staged.items(): for name in names: sys.stdout.write("\t%s: %s\n" % ( kind, name.decode(sys.getfilesystemencoding()))) sys.stdout.write("\n") if status.unstaged: sys.stdout.write("Changes not staged for commit:\n\n") for name in status.unstaged: sys.stdout.write("\t%s\n" % name.decode(sys.getfilesystemencoding())) sys.stdout.write("\n") if status.untracked: sys.stdout.write("Untracked files:\n\n") for name in status.untracked: sys.stdout.write("\t%s\n" % name) sys.stdout.write("\n") class cmd_ls_remote(Command): def run(self, args): opts, args = getopt(args, '', []) if len(args) < 1: print('Usage: dulwich ls-remote URL') sys.exit(1) refs = porcelain.ls_remote(args[0]) for ref in sorted(refs): sys.stdout.write("%s\t%s\n" % (ref, refs[ref])) class cmd_ls_tree(Command): def run(self, args): parser = optparse.OptionParser() parser.add_option("-r", "--recursive", action="store_true", help="Recusively list tree contents.") parser.add_option("--name-only", action="store_true", help="Only display name.") options, args = parser.parse_args(args) try: treeish = args.pop(0) except IndexError: treeish = None porcelain.ls_tree( '.', treeish, outstream=sys.stdout, recursive=options.recursive, name_only=options.name_only) class cmd_pack_objects(Command): def run(self, args): opts, args = getopt(args, '', ['stdout']) opts = dict(opts) if len(args) < 1 and not '--stdout' in args: print('Usage: dulwich pack-objects basename') sys.exit(1) object_ids = [l.strip() for l in sys.stdin.readlines()] basename = args[0] if '--stdout' in opts: packf = getattr(sys.stdout, 'buffer', sys.stdout) idxf = None close = [] else: packf = open(basename + '.pack', 'w') idxf = open(basename + '.idx', 'w') close = [packf, idxf] porcelain.pack_objects('.', object_ids, packf, idxf) for f in close: f.close() class cmd_pull(Command): def run(self, args): parser = optparse.OptionParser() options, args = parser.parse_args(args) try: from_location = args[0] except IndexError: from_location = None porcelain.pull('.', from_location) class cmd_push(Command): def run(self, args): parser = optparse.OptionParser() options, args = parser.parse_args(args) if len(args) < 2: print("Usage: dulwich push TO-LOCATION REFSPEC..") sys.exit(1) to_location = args[0] refspecs = args[1:] porcelain.push('.', to_location, refspecs) class cmd_remote_add(Command): def run(self, args): parser = optparse.OptionParser() options, args = parser.parse_args(args) porcelain.remote_add('.', args[0], args[1]) class SuperCommand(Command): subcommands = {} def run(self, args): if not args: print("Supported subcommands: %s" % ', '.join(self.subcommands.keys())) return False cmd = args[0] try: cmd_kls = self.subcommands[cmd] except KeyError: print('No such subcommand: %s' % args[0]) return False return cmd_kls().run(args[1:]) class cmd_remote(SuperCommand): subcommands = { "add": cmd_remote_add, } class cmd_check_ignore(Command): def run(self, args): parser = optparse.OptionParser() options, args = parser.parse_args(args) ret = 1 for path in porcelain.check_ignore('.', args): print(path) ret = 0 return ret class cmd_check_mailmap(Command): def run(self, args): parser = optparse.OptionParser() options, args = parser.parse_args(args) for arg in args: canonical_identity = porcelain.check_mailmap('.', arg) print(canonical_identity) class cmd_stash_list(Command): def run(self, args): parser = optparse.OptionParser() options, args = parser.parse_args(args) for i, entry in porcelain.stash_list('.'): print("stash@{%d}: %s" % (i, entry.message.rstrip('\n'))) class cmd_stash_push(Command): def run(self, args): parser = optparse.OptionParser() options, args = parser.parse_args(args) porcelain.stash_push('.') print("Saved working directory and index state") class cmd_stash_pop(Command): def run(self, args): parser = optparse.OptionParser() options, args = parser.parse_args(args) porcelain.stash_pop('.') print("Restrored working directory and index state") class cmd_stash(SuperCommand): subcommands = { "list": cmd_stash_list, "pop": cmd_stash_pop, "push": cmd_stash_push, } class cmd_ls_files(Command): def run(self, args): parser = optparse.OptionParser() options, args = parser.parse_args(args) for name in porcelain.ls_files('.'): print(name) class cmd_describe(Command): def run(self, args): parser = optparse.OptionParser() options, args = parser.parse_args(args) print(porcelain.describe('.')) class cmd_help(Command): def run(self, args): parser = optparse.OptionParser() parser.add_option("-a", "--all", dest="all", action="store_true", help="List all commands.") options, args = parser.parse_args(args) if options.all: print('Available commands:') for cmd in sorted(commands): print(' %s' % cmd) else: print("""\ The dulwich command line tool is currently a very basic frontend for the Dulwich python module. For full functionality, please see the API reference. For a list of supported commands, see 'dulwich help -a'. """) commands = { "add": cmd_add, "archive": cmd_archive, "check-ignore": cmd_check_ignore, "check-mailmap": cmd_check_mailmap, "clone": cmd_clone, "commit": cmd_commit, "commit-tree": cmd_commit_tree, "describe": cmd_describe, "daemon": cmd_daemon, "diff": cmd_diff, "diff-tree": cmd_diff_tree, "dump-pack": cmd_dump_pack, "dump-index": cmd_dump_index, "fetch-pack": cmd_fetch_pack, "fetch": cmd_fetch, "fsck": cmd_fsck, "help": cmd_help, "init": cmd_init, "log": cmd_log, "ls-files": cmd_ls_files, "ls-remote": cmd_ls_remote, "ls-tree": cmd_ls_tree, "pack-objects": cmd_pack_objects, "pull": cmd_pull, "push": cmd_push, "receive-pack": cmd_receive_pack, "remote": cmd_remote, "repack": cmd_repack, "reset": cmd_reset, "rev-list": cmd_rev_list, "rm": cmd_rm, "show": cmd_show, "stash": cmd_stash, "status": cmd_status, "symbolic-ref": cmd_symbolic_ref, "tag": cmd_tag, "update-server-info": cmd_update_server_info, "upload-pack": cmd_upload_pack, "web-daemon": cmd_web_daemon, + "write-tree": cmd_write_tree, } if len(sys.argv) < 2: print("Usage: %s <%s> [OPTIONS...]" % (sys.argv[0], "|".join(commands.keys()))) sys.exit(1) cmd = sys.argv[1] try: cmd_kls = commands[cmd] except KeyError: print("No such subcommand: %s" % cmd) sys.exit(1) # TODO(jelmer): Return non-0 on errors cmd_kls().run(sys.argv[2:]) diff --git a/build.cmd b/build.cmd new file mode 100644 index 00000000..23df2b69 --- /dev/null +++ b/build.cmd @@ -0,0 +1,21 @@ +@echo off +:: To build extensions for 64 bit Python 3, we need to configure environment +:: variables to use the MSVC 2010 C++ compilers from GRMSDKX_EN_DVD.iso of: +:: MS Windows SDK for Windows 7 and .NET Framework 4 +:: +:: More details at: +:: https://github.com/cython/cython/wiki/CythonExtensionsOnWindows + +IF "%DISTUTILS_USE_SDK%"=="1" ( + ECHO Configuring environment to build with MSVC on a 64bit architecture + ECHO Using Windows SDK 7.1 + "C:\Program Files\Microsoft SDKs\Windows\v7.1\Setup\WindowsSdkVer.exe" -q -version:v7.1 + CALL "C:\Program Files\Microsoft SDKs\Windows\v7.1\Bin\SetEnv.cmd" /x64 /release + SET MSSdk=1 + REM Need the following to allow tox to see the SDK compiler + SET TOX_TESTENV_PASSENV=DISTUTILS_USE_SDK MSSdk INCLUDE LIB +) ELSE ( + ECHO Using default MSVC build environment +) + +CALL %* diff --git a/devscripts/PREAMBLE.c b/devscripts/PREAMBLE.c new file mode 100644 index 00000000..90c1d306 --- /dev/null +++ b/devscripts/PREAMBLE.c @@ -0,0 +1,15 @@ + * Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU + * General Public License as public by the Free Software Foundation; version 2.0 + * or (at your option) any later version. You can redistribute it and/or + * modify it under the terms of either of these two licenses. + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + * + * You should have received a copy of the licenses; if not, see + * for a copy of the GNU General Public License + * and for a copy of the Apache + * License, Version 2.0. diff --git a/dulwich/__init__.py b/devscripts/PREAMBLE.py similarity index 76% copy from dulwich/__init__.py copy to devscripts/PREAMBLE.py index 6602928c..f7027871 100644 --- a/dulwich/__init__.py +++ b/devscripts/PREAMBLE.py @@ -1,25 +1,16 @@ -# __init__.py -- The git module of dulwich -# Copyright (C) 2007 James Westby -# Copyright (C) 2008 Jelmer Vernooij -# # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # - - -"""Python implementation of the Git file formats and protocols.""" - -__version__ = (0, 19, 6) diff --git a/devscripts/replace-preamble.sh b/devscripts/replace-preamble.sh new file mode 100755 index 00000000..72a75943 --- /dev/null +++ b/devscripts/replace-preamble.sh @@ -0,0 +1,3 @@ +#!/usr/bin/zsh +perl -i -p0e "s{\Q$(cat PREAMBLE.py.old)\E}{$(cat devscripts/PREAMBLE.py)}g" dulwich/**/*.py bin/dul* +perl -i -p0e "s{\Q$(cat PREAMBLE.c.old)\E}{$(cat devscripts/PREAMBLE.c)}g" dulwich/*.c diff --git a/docs/Makefile b/docs/Makefile index 6a27ce67..f78d2767 100644 --- a/docs/Makefile +++ b/docs/Makefile @@ -1,96 +1,99 @@ # Makefile for Sphinx documentation # # You can set these variables from the command line. SPHINXOPTS = SPHINXBUILD = sphinx-build PAPER = BUILDDIR = build # Internal variables. PAPEROPT_a4 = -D latex_paper_size=a4 PAPEROPT_letter = -D latex_paper_size=letter ALLSPHINXOPTS = -d $(BUILDDIR)/doctrees $(PAPEROPT_$(PAPER)) $(SPHINXOPTS) . .PHONY: help clean html dirhtml pickle json htmlhelp qthelp latex changes linkcheck doctest help: @echo "Please use \`make ' where is one of" @echo " html to make standalone HTML files" @echo " pdf to make PDF document" @echo " dirhtml to make HTML files named index.html in directories" @echo " pickle to make pickle files" @echo " json to make JSON files" @echo " htmlhelp to make HTML files and a HTML help project" @echo " qthelp to make HTML files and a qthelp project" @echo " latex to make LaTeX files, you can set PAPER=a4 or PAPER=letter" @echo " changes to make an overview of all changed/added/deprecated items" @echo " linkcheck to check all external links for integrity" @echo " doctest to run all doctests embedded in the documentation (if enabled)" clean: -rm -rf $(BUILDDIR)/* -html: +apidocs: + sphinx-apidoc -feM -s txt -o api ../dulwich + +html: apidocs $(SPHINXBUILD) -b html $(ALLSPHINXOPTS) $(BUILDDIR)/html @echo @echo "Build finished. The HTML pages are in $(BUILDDIR)/html." -dirhtml: +dirhtml: apidocs $(SPHINXBUILD) -b dirhtml $(ALLSPHINXOPTS) $(BUILDDIR)/dirhtml @echo @echo "Build finished. The HTML pages are in $(BUILDDIR)/dirhtml." -pickle: +pickle: apidocs $(SPHINXBUILD) -b pickle $(ALLSPHINXOPTS) $(BUILDDIR)/pickle @echo @echo "Build finished; now you can process the pickle files." -json: +json: apidocs $(SPHINXBUILD) -b json $(ALLSPHINXOPTS) $(BUILDDIR)/json @echo @echo "Build finished; now you can process the JSON files." -htmlhelp: +htmlhelp: apidocs $(SPHINXBUILD) -b htmlhelp $(ALLSPHINXOPTS) $(BUILDDIR)/htmlhelp @echo @echo "Build finished; now you can run HTML Help Workshop with the" \ ".hhp project file in $(BUILDDIR)/htmlhelp." -qthelp: +qthelp: apidocs $(SPHINXBUILD) -b qthelp $(ALLSPHINXOPTS) $(BUILDDIR)/qthelp @echo @echo "Build finished; now you can run "qcollectiongenerator" with the" \ ".qhcp project file in $(BUILDDIR)/qthelp, like this:" @echo "# qcollectiongenerator $(BUILDDIR)/qthelp/dulwich.qhcp" @echo "To view the help file:" @echo "# assistant -collectionFile $(BUILDDIR)/qthelp/dulwich.qhc" -latex: +latex: apidocs $(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex @echo @echo "Build finished; the LaTeX files are in $(BUILDDIR)/latex." @echo "Run \`make all-pdf' or \`make all-ps' in that directory to" \ "run these through (pdf)latex." -changes: +changes: apidocs $(SPHINXBUILD) -b changes $(ALLSPHINXOPTS) $(BUILDDIR)/changes @echo @echo "The overview file is in $(BUILDDIR)/changes." linkcheck: $(SPHINXBUILD) -b linkcheck $(ALLSPHINXOPTS) $(BUILDDIR)/linkcheck @echo @echo "Link check complete; look for any errors in the above output " \ "or in $(BUILDDIR)/linkcheck/output.txt." doctest: $(SPHINXBUILD) -b doctest $(ALLSPHINXOPTS) $(BUILDDIR)/doctest @echo "Testing of doctests in the sources finished, look at the " \ "results in $(BUILDDIR)/doctest/output.txt." pdf: $(SPHINXBUILD) -b pdf $(ALLSPHINXOPTS) $(BUILDDIR)/pdf @echo @echo "Build finished. The PDF files are in $(BUILDDIR)/pdf." diff --git a/docs/api/index.txt b/docs/api/index.txt new file mode 100644 index 00000000..355c3a1a --- /dev/null +++ b/docs/api/index.txt @@ -0,0 +1,14 @@ +This is the API documentation for Dulwich. + +Module reference +---------------- + +.. toctree:: + :maxdepth: 3 + + modules + +Indices: + +* :ref:`modindex` +* :ref:`search` diff --git a/docs/conf.py b/docs/conf.py index 9fef29e5..0374178e 100644 --- a/docs/conf.py +++ b/docs/conf.py @@ -1,218 +1,223 @@ # -*- coding: utf-8 -*- # # dulwich documentation build configuration file, created by # sphinx-quickstart on Thu Feb 18 23:18:28 2010. # # This file is execfile()d with the current directory set to its containing # dir. # # Note that not all possible configuration values are present in this # autogenerated file. # # All configuration values have a default; values that are commented out # serve to show the default. import os import sys # If extensions (or modules to document with autodoc) are in another directory, # add these directories to sys.path here. If the directory is relative to the # documentation root, use os.path.abspath to make it absolute, like shown here. sys.path.insert(0, os.path.abspath('..')) sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__)))) dulwich = __import__('dulwich') # -- General configuration ---------------------------------------------------- # Add any Sphinx extension module names here, as strings. They can be # extensions coming with Sphinx (named 'sphinx.ext.*') or your custom ones. -extensions = ['sphinx.ext.autodoc'] +extensions = [ + 'sphinx.ext.autodoc', + 'sphinx.ext.ifconfig', + 'sphinx.ext.intersphinx', + 'sphinx_epytext', + ] try: import rst2pdf if rst2pdf.version >= '0.16': extensions.append('rst2pdf.pdfbuilder') except ImportError: print("[NOTE] In order to build PDF you need rst2pdf with version >=0.16") autoclass_content = "both" # Add any paths that contain templates here, relative to this directory. templates_path = ['templates'] # The suffix of source filenames. source_suffix = '.txt' # The encoding of source files. # source_encoding = 'utf-8' # The master toctree document. master_doc = 'index' # General information about the project. project = u'dulwich' -copyright = u'2011, Jelmer Vernooij' +copyright = u'2011-2018 Jelmer Vernooij' # The version info for the project you're documenting, acts as replacement for # |version| and |release|, also used in various other places throughout the # built documents. # # The short X.Y version. version = '.'.join(map(str, dulwich.__version__[:2])) # The full version, including alpha/beta/rc tags. release = '.'.join(map(str, dulwich.__version__)) # The language for content autogenerated by Sphinx. Refer to documentation # for a list of supported languages. # language = None # There are two options for replacing |today|: either, you set today to some # non-false value, then it is used: # today = '' # Else, today_fmt is used as the format for a strftime call. # today_fmt = '%B %d, %Y' # List of documents that shouldn't be included in the build. # unused_docs = [] # List of directories, relative to source directory, that shouldn't be searched # for source files. exclude_trees = ['build'] # The reST default role (used for this markup: `text`) to use for all # documents. # default_role = None # If true, '()' will be appended to :func: etc. cross-reference text. # add_function_parentheses = True # If true, the current module name will be prepended to all description # unit titles (such as .. function::). # add_module_names = True # If true, sectionauthor and moduleauthor directives will be shown in the # output. They are ignored by default. # show_authors = False # The name of the Pygments (syntax highlighting) style to use. pygments_style = 'sphinx' # A list of ignored prefixes for module index sorting. # modindex_common_prefix = [] # -- Options for HTML output ------------------------------------------------- # The theme to use for HTML and HTML Help pages. Major themes that come with # Sphinx are currently 'default' and 'sphinxdoc'. # html_theme = 'default' -html_theme = 'nature' +html_theme = 'agogo' # Theme options are theme-specific and customize the look and feel of a theme # further. For a list of options available for each theme, see the # documentation. # html_theme_options = {} # Add any paths that contain custom themes here, relative to this directory. html_theme_path = ['theme'] # The name for this set of Sphinx documents. If None, it defaults to # " v documentation". # html_title = None # A shorter title for the navigation bar. Default is the same as html_title. # html_short_title = None # The name of an image file (relative to this directory) to place at the top # of the sidebar. # html_logo = None # The name of an image file (within the static path) to use as favicon of the # docs. This file should be a Windows icon file (.ico) being 16x16 or 32x32 # pixels large. # html_favicon = None # Add any paths that contain custom static files (such as style sheets) here, # relative to this directory. They are copied after the builtin static files, # so a file named "default.css" will overwrite the builtin "default.css". html_static_path = [] # If not '', a 'Last updated on:' timestamp is inserted at every page bottom, # using the given strftime format. # html_last_updated_fmt = '%b %d, %Y' # If true, SmartyPants will be used to convert quotes and dashes to # typographically correct entities. # html_use_smartypants = True # Custom sidebar templates, maps document names to template names. # html_sidebars = {} # Additional templates that should be rendered to pages, maps page names to # template names. # html_additional_pages = {} # If false, no module index is generated. # html_use_modindex = True # If false, no index is generated. # html_use_index = True # If true, the index is split into individual pages for each letter. # html_split_index = False # If true, links to the reST sources are added to the pages. # html_show_sourcelink = True # If true, an OpenSearch description file will be output, and all pages will # contain a tag referring to it. The value of this option must be the # base URL from which the finished HTML is served. # html_use_opensearch = '' # If nonempty, this is the file name suffix for HTML files (e.g. ".xhtml"). # html_file_suffix = '' # Output file base name for HTML help builder. htmlhelp_basename = 'dulwichdoc' # -- Options for LaTeX output ------------------------------------------------ # The paper size ('letter' or 'a4'). # latex_paper_size = 'letter' # The font size ('10pt', '11pt' or '12pt'). # latex_font_size = '10pt' # Grouping the document tree into LaTeX files. List of tuples # (source start file, target name, title, author, documentclass # [howto/manual]). latex_documents = [ ('index', 'dulwich.tex', u'dulwich Documentation', u'Jelmer Vernooij', 'manual'), ] # The name of an image file (relative to this directory) to place at the top of # the title page. # latex_logo = None # For "manual" documents, if this is true, then toplevel headings are parts, # not chapters. # latex_use_parts = False # Additional stuff for the LaTeX preamble. # latex_preamble = '' # Documents to append as an appendix to all manuals. # latex_appendices = [] # If false, no module index is generated. # latex_use_modindex = True pdf_documents = [ ('index', u'dulwich', u'Documentation for dulwich', u'Jelmer Vernooij'), ] pdf_stylesheets = ['sphinx', 'kerning', 'a4'] pdf_break_level = 2 pdf_inline_footnotes = True diff --git a/docs/index.txt b/docs/index.txt index 113fba3a..78585c8e 100644 --- a/docs/index.txt +++ b/docs/index.txt @@ -1,36 +1,37 @@ .. _index: ====================================== dulwich - Python implementation of Git ====================================== Overview ======== -.. include:: ../README.md +.. include:: ../README.rst Documentation ============= - .. toctree:: :maxdepth: 2 performance protocol tutorial/index + api/index + Changelog ========= .. include:: ../NEWS Indices and tables ================== * :ref:`genindex` * :ref:`modindex` * :ref:`search` diff --git a/docs/tutorial/.gitignore b/docs/tutorial/.gitignore new file mode 100644 index 00000000..6b71f091 --- /dev/null +++ b/docs/tutorial/.gitignore @@ -0,0 +1,2 @@ +*.html +myrepo diff --git a/dulwich.egg-info/PKG-INFO b/dulwich.egg-info/PKG-INFO index 53932d42..6b9c95fc 100644 --- a/dulwich.egg-info/PKG-INFO +++ b/dulwich.egg-info/PKG-INFO @@ -1,119 +1,126 @@ Metadata-Version: 2.1 Name: dulwich -Version: 0.19.6 -Summary: [![Build Status](https://travis-ci.org/dulwich/dulwich.png?branch=master)](https://travis-ci.org/dulwich/dulwich) -[![Windows Build status](https://ci.appveyor.com/api/projects/status/mob7g4vnrfvvoweb?svg=true)](https://ci.appveyor.com/project/jelmer/dulwich/branch/master) - -This is the Dulwich project. - -It aims to provide an interface to git repos (both local and remote) that -doesn't call out to git directly but instead uses pure Python. - -**Main website**: [www.dulwich.io](https://www.dulwich.io/) - -**License**: Apache License, version 2 or GNU General Public License, version 2 or later. - -The project is named after the part of London that Mr. and Mrs. Git live in -in the particular Monty Python sketch. - -Installation ------------- - -By default, Dulwich' setup.py will attempt to build and install the optional C -extensions. The reason for this is that they significantly improve the performance -since some low-level operations that are executed often are much slower in CPython. - -If you don't want to install the C bindings, specify the --pure argument to setup.py:: - - $ python setup.py --pure install - -or if you are installing from pip:: - - $ pip install dulwich --global-option="--pure" - -Note that you can also specify --global-option in a -[requirements.txt](https://pip.pypa.io/en/stable/reference/pip_install/#requirement-specifiers) -file, e.g. like this:: - - dulwich --global-option=--pure - -Getting started ---------------- - -Dulwich comes with both a lower-level API and higher-level plumbing ("porcelain"). - -For example, to use the lower level API to access the commit message of the -last commit: - - >>> from dulwich.repo import Repo - >>> r = Repo('.') - >>> r.head() - '57fbe010446356833a6ad1600059d80b1e731e15' - >>> c = r[r.head()] - >>> c - - >>> c.message - 'Add note about encoding.\n' - -And to print it using porcelain: - - >>> from dulwich import porcelain - >>> porcelain.log('.', max_entries=1) - -------------------------------------------------- - commit: 57fbe010446356833a6ad1600059d80b1e731e15 - Author: Jelmer Vernooij - Date: Sat Apr 29 2017 23:57:34 +0000 - - Add note about encoding. - -Further documentation ---------------------- - -The dulwich documentation can be found in docs/ and -[on the web](https://www.dulwich.io/docs/). - -The API reference can be generated using pydoctor, by running "make pydoctor", -or [on the web](https://www.dulwich.io/apidocs). - -Help ----- - -There is a *#dulwich* IRC channel on the [Freenode](https://www.freenode.net/), and -[dulwich-announce](https://groups.google.com/forum/#!forum/dulwich-announce) -and [dulwich-discuss](https://groups.google.com/forum/#!forum/dulwich-discuss) -mailing lists. - -Contributing ------------- - -For a full list of contributors, see the git logs or [AUTHORS](AUTHORS). - -If you'd like to contribute to Dulwich, see the [CONTRIBUTING](CONTRIBUTING.md) -file and [list of open issues](https://github.com/dulwich/dulwich/issues). - -Supported versions of Python ----------------------------- - -At the moment, Dulwich supports (and is tested on) CPython 2.7, 3.3, 3.4, 3.5, 3.6 and Pypy. - +Version: 0.19.10 +Summary: Python Git Library Home-page: https://www.dulwich.io/ Author: Jelmer Vernooij Author-email: jelmer@jelmer.uk License: Apachev2 or later or GPLv2 Project-URL: Bug Tracker, https://github.com/dulwich/dulwich/issues -Description: UNKNOWN +Project-URL: GitHub, https://github.com/dulwich/dulwich +Project-URL: Repository, https://www.dulwich.io/code/ +Description: .. image:: https://travis-ci.org/dulwich/dulwich.png?branch=master + :alt: Build Status + :target: https://travis-ci.org/dulwich/dulwich + + .. image:: https://ci.appveyor.com/api/projects/status/mob7g4vnrfvvoweb?svg=true + :alt: Windows Build Status + :target: https://ci.appveyor.com/project/jelmer/dulwich/branch/master + + This is the Dulwich project. + + It aims to provide an interface to git repos (both local and remote) that + doesn't call out to git directly but instead uses pure Python. + + **Main website**: + + **License**: Apache License, version 2 or GNU General Public License, version 2 or later. + + The project is named after the part of London that Mr. and Mrs. Git live in + in the particular Monty Python sketch. + + Installation + ------------ + + By default, Dulwich' setup.py will attempt to build and install the optional C + extensions. The reason for this is that they significantly improve the performance + since some low-level operations that are executed often are much slower in CPython. + + If you don't want to install the C bindings, specify the --pure argument to setup.py:: + + $ python setup.py --pure install + + or if you are installing from pip:: + + $ pip install dulwich --global-option="--pure" + + Note that you can also specify --global-option in a + `requirements.txt `_ + file, e.g. like this:: + + dulwich --global-option=--pure + + Getting started + --------------- + + Dulwich comes with both a lower-level API and higher-level plumbing ("porcelain"). + + For example, to use the lower level API to access the commit message of the + last commit:: + + >>> from dulwich.repo import Repo + >>> r = Repo('.') + >>> r.head() + '57fbe010446356833a6ad1600059d80b1e731e15' + >>> c = r[r.head()] + >>> c + + >>> c.message + 'Add note about encoding.\n' + + And to print it using porcelain:: + + >>> from dulwich import porcelain + >>> porcelain.log('.', max_entries=1) + -------------------------------------------------- + commit: 57fbe010446356833a6ad1600059d80b1e731e15 + Author: Jelmer Vernooij + Date: Sat Apr 29 2017 23:57:34 +0000 + + Add note about encoding. + + Further documentation + --------------------- + + The dulwich documentation can be found in docs/ and + `on the web `_. + + The API reference can be generated using pydoctor, by running "make pydoctor", + or `on the web `_. + + Help + ---- + + There is a *#dulwich* IRC channel on the `Freenode `_, and + `dulwich-announce `_ + and `dulwich-discuss `_ + mailing lists. + + Contributing + ------------ + + For a full list of contributors, see the git logs or `AUTHORS `_. + + If you'd like to contribute to Dulwich, see the `CONTRIBUTING `_ + file and `list of open issues `_. + + Supported versions of Python + ---------------------------- + + At the moment, Dulwich supports (and is tested on) CPython 2.7, 3.4, 3.5, 3.6 and Pypy. + +Keywords: git vcs Platform: UNKNOWN Classifier: Development Status :: 4 - Beta Classifier: License :: OSI Approved :: Apache Software License Classifier: Programming Language :: Python :: 2.7 -Classifier: Programming Language :: Python :: 3.3 Classifier: Programming Language :: Python :: 3.4 Classifier: Programming Language :: Python :: 3.5 Classifier: Programming Language :: Python :: 3.6 Classifier: Programming Language :: Python :: Implementation :: CPython Classifier: Programming Language :: Python :: Implementation :: PyPy Classifier: Operating System :: POSIX Classifier: Operating System :: Microsoft :: Windows Classifier: Topic :: Software Development :: Version Control Provides-Extra: fastimport Provides-Extra: https diff --git a/dulwich.egg-info/SOURCES.txt b/dulwich.egg-info/SOURCES.txt index 0e23b94c..0a49f5d5 100644 --- a/dulwich.egg-info/SOURCES.txt +++ b/dulwich.egg-info/SOURCES.txt @@ -1,206 +1,219 @@ +.coveragerc +.gitignore +.mailmap .testr.conf .travis.yml AUTHORS -CONTRIBUTING.md +CONTRIBUTING.rst COPYING MANIFEST.in Makefile NEWS -README.md -README.swift.md +README.rst +README.swift.rst TODO appveyor.yml +build.cmd dulwich.cfg +requirements.txt setup.cfg setup.py tox.ini bin/dul-receive-pack bin/dul-upload-pack bin/dulwich +devscripts/PREAMBLE.c +devscripts/PREAMBLE.py +devscripts/replace-preamble.sh docs/Makefile docs/conf.py docs/index.txt docs/make.bat docs/performance.txt docs/protocol.txt +docs/api/index.txt +docs/tutorial/.gitignore docs/tutorial/Makefile docs/tutorial/conclusion.txt docs/tutorial/encoding.txt docs/tutorial/file-format.txt docs/tutorial/index.txt docs/tutorial/introduction.txt docs/tutorial/object-store.txt docs/tutorial/porcelain.txt docs/tutorial/remote.txt docs/tutorial/repo.txt docs/tutorial/tag.txt dulwich/__init__.py dulwich/_diff_tree.c dulwich/_objects.c dulwich/_pack.c dulwich/archive.py dulwich/client.py dulwich/config.py dulwich/diff_tree.py dulwich/errors.py dulwich/fastexport.py dulwich/file.py dulwich/greenthreads.py dulwich/hooks.py dulwich/ignore.py dulwich/index.py +dulwich/line_ending.py dulwich/log_utils.py dulwich/lru_cache.py dulwich/mailmap.py dulwich/object_store.py dulwich/objects.py dulwich/objectspec.py dulwich/pack.py dulwich/patch.py dulwich/porcelain.py dulwich/protocol.py dulwich/reflog.py dulwich/refs.py dulwich/repo.py dulwich/server.py dulwich/stash.py dulwich/stdint.h dulwich/walk.py dulwich/web.py dulwich.egg-info/PKG-INFO dulwich.egg-info/SOURCES.txt dulwich.egg-info/dependency_links.txt dulwich.egg-info/requires.txt dulwich.egg-info/top_level.txt +dulwich/contrib/README.md dulwich/contrib/__init__.py dulwich/contrib/paramiko_vendor.py dulwich/contrib/release_robot.py dulwich/contrib/swift.py dulwich/contrib/test_release_robot.py dulwich/contrib/test_swift.py dulwich/contrib/test_swift_smoke.py dulwich/tests/__init__.py dulwich/tests/test_archive.py dulwich/tests/test_blackbox.py dulwich/tests/test_client.py dulwich/tests/test_config.py dulwich/tests/test_diff_tree.py dulwich/tests/test_fastexport.py dulwich/tests/test_file.py dulwich/tests/test_grafts.py dulwich/tests/test_greenthreads.py dulwich/tests/test_hooks.py dulwich/tests/test_ignore.py dulwich/tests/test_index.py +dulwich/tests/test_line_ending.py dulwich/tests/test_lru_cache.py dulwich/tests/test_mailmap.py dulwich/tests/test_missing_obj_finder.py dulwich/tests/test_object_store.py dulwich/tests/test_objects.py dulwich/tests/test_objectspec.py dulwich/tests/test_pack.py dulwich/tests/test_patch.py dulwich/tests/test_porcelain.py dulwich/tests/test_protocol.py dulwich/tests/test_reflog.py dulwich/tests/test_refs.py dulwich/tests/test_repository.py dulwich/tests/test_server.py dulwich/tests/test_stash.py dulwich/tests/test_utils.py dulwich/tests/test_walk.py dulwich/tests/test_web.py dulwich/tests/utils.py dulwich/tests/compat/__init__.py dulwich/tests/compat/server_utils.py dulwich/tests/compat/test_client.py dulwich/tests/compat/test_pack.py dulwich/tests/compat/test_repository.py dulwich/tests/compat/test_server.py dulwich/tests/compat/test_utils.py dulwich/tests/compat/test_web.py dulwich/tests/compat/utils.py dulwich/tests/data/blobs/11/11111111111111111111111111111111111111 dulwich/tests/data/blobs/6f/670c0fb53f9463760b7295fbb814e965fb20c8 dulwich/tests/data/blobs/95/4a536f7819d40e6f637f849ee187dd10066349 dulwich/tests/data/blobs/e6/9de29bb2d1d6434b8b29ae775ad8c2e48c5391 dulwich/tests/data/commits/0d/89f20333fbb1d2f3a94da77f4981373d8f4310 dulwich/tests/data/commits/5d/ac377bdded4c9aeb8dff595f0faeebcc8498cc dulwich/tests/data/commits/60/dacdc733de308bb77bb76ce0fb0f9b44c9769e dulwich/tests/data/indexes/index dulwich/tests/data/packs/pack-bc63ddad95e7321ee734ea11a7a62d314e0d7481.idx dulwich/tests/data/packs/pack-bc63ddad95e7321ee734ea11a7a62d314e0d7481.pack dulwich/tests/data/repos/.gitattributes dulwich/tests/data/repos/issue88_expect_ack_nak_client.export dulwich/tests/data/repos/issue88_expect_ack_nak_other.export dulwich/tests/data/repos/issue88_expect_ack_nak_server.export dulwich/tests/data/repos/server_new.export dulwich/tests/data/repos/server_old.export dulwich/tests/data/repos/a.git/HEAD dulwich/tests/data/repos/a.git/packed-refs dulwich/tests/data/repos/a.git/objects/28/237f4dc30d0d462658d6b937b08a0f0b6ef55a dulwich/tests/data/repos/a.git/objects/2a/72d929692c41d8554c07f6301757ba18a65d91 dulwich/tests/data/repos/a.git/objects/4e/f30bbfe26431a69c3820d3a683df54d688f2ec dulwich/tests/data/repos/a.git/objects/4f/2e6529203aa6d44b5af6e3292c837ceda003f9 dulwich/tests/data/repos/a.git/objects/7d/9a07d797595ef11344549b8d08198e48c15364 dulwich/tests/data/repos/a.git/objects/a2/96d0bb611188cabb256919f36bc30117cca005 dulwich/tests/data/repos/a.git/objects/a9/0fa2d900a17e99b433217e988c4eb4a2e9a097 dulwich/tests/data/repos/a.git/objects/b0/931cadc54336e78a1d980420e3268903b57a50 dulwich/tests/data/repos/a.git/objects/ff/d47d45845a8f6576491e1edb97e3fe6a850e7f dulwich/tests/data/repos/a.git/refs/heads/master dulwich/tests/data/repos/a.git/refs/tags/mytag dulwich/tests/data/repos/empty.git/HEAD dulwich/tests/data/repos/empty.git/config dulwich/tests/data/repos/empty.git/objects/info/.gitignore dulwich/tests/data/repos/empty.git/objects/pack/.gitignore dulwich/tests/data/repos/empty.git/refs/heads/.gitignore dulwich/tests/data/repos/empty.git/refs/tags/.gitignore dulwich/tests/data/repos/ooo_merge.git/HEAD dulwich/tests/data/repos/ooo_merge.git/objects/29/69be3e8ee1c0222396a5611407e4769f14e54b dulwich/tests/data/repos/ooo_merge.git/objects/38/74e9c60a6d149c44c928140f250d81e6381520 dulwich/tests/data/repos/ooo_merge.git/objects/6f/670c0fb53f9463760b7295fbb814e965fb20c8 dulwich/tests/data/repos/ooo_merge.git/objects/70/c190eb48fa8bbb50ddc692a17b44cb781af7f6 dulwich/tests/data/repos/ooo_merge.git/objects/76/01d7f6231db6a57f7bbb79ee52e4d462fd44d1 dulwich/tests/data/repos/ooo_merge.git/objects/90/182552c4a85a45ec2a835cadc3451bebdfe870 dulwich/tests/data/repos/ooo_merge.git/objects/95/4a536f7819d40e6f637f849ee187dd10066349 dulwich/tests/data/repos/ooo_merge.git/objects/b2/a2766a2879c209ab1176e7e778b81ae422eeaa dulwich/tests/data/repos/ooo_merge.git/objects/f5/07291b64138b875c28e03469025b1ea20bc614 dulwich/tests/data/repos/ooo_merge.git/objects/f9/e39b120c68182a4ba35349f832d0e4e61f485c dulwich/tests/data/repos/ooo_merge.git/objects/fb/5b0425c7ce46959bec94d54b9a157645e114f5 dulwich/tests/data/repos/ooo_merge.git/refs/heads/master dulwich/tests/data/repos/refs.git/HEAD dulwich/tests/data/repos/refs.git/packed-refs dulwich/tests/data/repos/refs.git/objects/3b/9e5457140e738c2dcd39bf6d7acf88379b90d1 dulwich/tests/data/repos/refs.git/objects/3e/c9c43c84ff242e3ef4a9fc5bc111fd780a76a8 dulwich/tests/data/repos/refs.git/objects/42/d06bd4b77fed026b154d16493e5deab78f02ec dulwich/tests/data/repos/refs.git/objects/a1/8114c31713746a33a2e70d9914d1ef3e781425 dulwich/tests/data/repos/refs.git/objects/cd/a609072918d7b70057b6bef9f4c2537843fcfe dulwich/tests/data/repos/refs.git/objects/df/6800012397fb85c56e7418dd4eb9405dee075c dulwich/tests/data/repos/refs.git/refs/heads/40-char-ref-aaaaaaaaaaaaaaaaaa dulwich/tests/data/repos/refs.git/refs/heads/loop dulwich/tests/data/repos/refs.git/refs/heads/master dulwich/tests/data/repos/refs.git/refs/tags/refs-0.2 dulwich/tests/data/repos/simple_merge.git/HEAD dulwich/tests/data/repos/simple_merge.git/objects/0d/89f20333fbb1d2f3a94da77f4981373d8f4310 dulwich/tests/data/repos/simple_merge.git/objects/1b/6318f651a534b38f9c7aedeebbd56c1e896853 dulwich/tests/data/repos/simple_merge.git/objects/29/69be3e8ee1c0222396a5611407e4769f14e54b dulwich/tests/data/repos/simple_merge.git/objects/4c/ffe90e0a41ad3f5190079d7c8f036bde29cbe6 dulwich/tests/data/repos/simple_merge.git/objects/5d/ac377bdded4c9aeb8dff595f0faeebcc8498cc dulwich/tests/data/repos/simple_merge.git/objects/60/dacdc733de308bb77bb76ce0fb0f9b44c9769e dulwich/tests/data/repos/simple_merge.git/objects/6f/670c0fb53f9463760b7295fbb814e965fb20c8 dulwich/tests/data/repos/simple_merge.git/objects/70/c190eb48fa8bbb50ddc692a17b44cb781af7f6 dulwich/tests/data/repos/simple_merge.git/objects/90/182552c4a85a45ec2a835cadc3451bebdfe870 dulwich/tests/data/repos/simple_merge.git/objects/95/4a536f7819d40e6f637f849ee187dd10066349 dulwich/tests/data/repos/simple_merge.git/objects/ab/64bbdcc51b170d21588e5c5d391ee5c0c96dfd dulwich/tests/data/repos/simple_merge.git/objects/d4/bdad6549dfedf25d3b89d21f506aff575b28a7 dulwich/tests/data/repos/simple_merge.git/objects/d8/0c186a03f423a81b39df39dc87fd269736ca86 dulwich/tests/data/repos/simple_merge.git/objects/e6/9de29bb2d1d6434b8b29ae775ad8c2e48c5391 dulwich/tests/data/repos/simple_merge.git/refs/heads/master dulwich/tests/data/repos/submodule/dotgit dulwich/tests/data/tags/71/033db03a03c6a36721efcf1968dd8f8e0cf023 dulwich/tests/data/trees/70/c190eb48fa8bbb50ddc692a17b44cb781af7f6 examples/clone.py examples/config.py examples/diff.py examples/latest_change.py examples/memoryrepo.py \ No newline at end of file diff --git a/dulwich.egg-info/requires.txt b/dulwich.egg-info/requires.txt index aad86d41..8f56c2ff 100644 --- a/dulwich.egg-info/requires.txt +++ b/dulwich.egg-info/requires.txt @@ -1,8 +1,8 @@ certifi -urllib3>=1.21 +urllib3>=1.23 [fastimport] fastimport [https] -urllib3[secure]>=1.21 +urllib3[secure]>=1.23 diff --git a/dulwich/__init__.py b/dulwich/__init__.py index 6602928c..6fe2a50f 100644 --- a/dulwich/__init__.py +++ b/dulwich/__init__.py @@ -1,25 +1,25 @@ # __init__.py -- The git module of dulwich # Copyright (C) 2007 James Westby # Copyright (C) 2008 Jelmer Vernooij # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """Python implementation of the Git file formats and protocols.""" -__version__ = (0, 19, 6) +__version__ = (0, 19, 10) diff --git a/dulwich/client.py b/dulwich/client.py index e1af49e3..66428ac2 100644 --- a/dulwich/client.py +++ b/dulwich/client.py @@ -1,1651 +1,1755 @@ # client.py -- Implementation of the client side git protocols # Copyright (C) 2008-2013 Jelmer Vernooij # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """Client side support for the Git protocol. The Dulwich client supports the following capabilities: * thin-pack * multi_ack_detailed * multi_ack * side-band-64k * ofs-delta * quiet * report-status * delete-refs Known capabilities that are not supported: * shallow * no-progress * include-tag """ from contextlib import closing from io import BytesIO, BufferedReader -import gzip import select import socket import subprocess import sys try: from urllib import quote as urlquote from urllib import unquote as urlunquote except ImportError: from urllib.parse import quote as urlquote from urllib.parse import unquote as urlunquote try: import urlparse except ImportError: import urllib.parse as urlparse import dulwich from dulwich.errors import ( GitProtocolError, NotGitRepository, SendPackError, UpdateRefsError, ) from dulwich.protocol import ( + HangupException, _RBUFSIZE, agent_string, capability_agent, extract_capability_names, CAPABILITY_AGENT, CAPABILITY_DELETE_REFS, CAPABILITY_MULTI_ACK, CAPABILITY_MULTI_ACK_DETAILED, CAPABILITY_OFS_DELTA, CAPABILITY_QUIET, CAPABILITY_REPORT_STATUS, + CAPABILITY_SHALLOW, CAPABILITY_SYMREF, CAPABILITY_SIDE_BAND_64K, CAPABILITY_THIN_PACK, CAPABILITIES_REF, KNOWN_RECEIVE_CAPABILITIES, KNOWN_UPLOAD_CAPABILITIES, + COMMAND_DEEPEN, + COMMAND_SHALLOW, + COMMAND_UNSHALLOW, COMMAND_DONE, COMMAND_HAVE, COMMAND_WANT, SIDE_BAND_CHANNEL_DATA, SIDE_BAND_CHANNEL_PROGRESS, SIDE_BAND_CHANNEL_FATAL, PktLineParser, Protocol, ProtocolFile, TCP_GIT_PORT, ZERO_SHA, extract_capabilities, parse_capability, ) from dulwich.pack import ( write_pack_data, write_pack_objects, ) from dulwich.refs import ( read_info_refs, + ANNOTATED_TAG_SUFFIX, ) +class InvalidWants(Exception): + """Invalid wants.""" + + def __init__(self, wants): + Exception.__init__( + self, + "requested wants not in server provided refs: %r" % wants) + + def _fileno_can_read(fileno): """Check if a file descriptor is readable.""" return len(select.select([fileno], [], [], 0)[0]) > 0 def _win32_peek_avail(handle): """Wrapper around PeekNamedPipe to check how many bytes are available.""" from ctypes import byref, wintypes, windll c_avail = wintypes.DWORD() c_message = wintypes.DWORD() success = windll.kernel32.PeekNamedPipe( handle, None, 0, None, byref(c_avail), byref(c_message)) if not success: raise OSError(wintypes.GetLastError()) return c_avail.value COMMON_CAPABILITIES = [CAPABILITY_OFS_DELTA, CAPABILITY_SIDE_BAND_64K] UPLOAD_CAPABILITIES = ([CAPABILITY_THIN_PACK, CAPABILITY_MULTI_ACK, - CAPABILITY_MULTI_ACK_DETAILED] + COMMON_CAPABILITIES) + CAPABILITY_MULTI_ACK_DETAILED, CAPABILITY_SHALLOW] + + COMMON_CAPABILITIES) RECEIVE_CAPABILITIES = [CAPABILITY_REPORT_STATUS] + COMMON_CAPABILITIES class ReportStatusParser(object): """Handle status as reported by servers with 'report-status' capability. """ def __init__(self): self._done = False self._pack_status = None self._ref_status_ok = True self._ref_statuses = [] def check(self): """Check if there were any errors and, if so, raise exceptions. :raise SendPackError: Raised when the server could not unpack :raise UpdateRefsError: Raised when refs could not be updated """ if self._pack_status not in (b'unpack ok', None): raise SendPackError(self._pack_status) if not self._ref_status_ok: ref_status = {} ok = set() for status in self._ref_statuses: if b' ' not in status: # malformed response, move on to the next one continue status, ref = status.split(b' ', 1) if status == b'ng': if b' ' in ref: ref, status = ref.split(b' ', 1) else: ok.add(ref) ref_status[ref] = status # TODO(jelmer): don't assume encoding of refs is ascii. raise UpdateRefsError(', '.join([ refname.decode('ascii') for refname in ref_status if refname not in ok]) + ' failed to update', ref_status=ref_status) def handle_packet(self, pkt): """Handle a packet. :raise GitProtocolError: Raised when packets are received after a flush packet. """ if self._done: raise GitProtocolError("received more data after status report") if pkt is None: self._done = True return if self._pack_status is None: self._pack_status = pkt.strip() else: ref_status = pkt.strip() self._ref_statuses.append(ref_status) if not ref_status.startswith(b'ok '): self._ref_status_ok = False def read_pkt_refs(proto): server_capabilities = None refs = {} # Receive refs from server for pkt in proto.read_pkt_seq(): (sha, ref) = pkt.rstrip(b'\n').split(None, 1) if sha == b'ERR': - raise GitProtocolError(ref) + raise GitProtocolError(ref.decode('utf-8', 'replace')) if server_capabilities is None: (ref, server_capabilities) = extract_capabilities(ref) refs[ref] = sha if len(refs) == 0: return {}, set([]) if refs == {CAPABILITIES_REF: ZERO_SHA}: refs = {} return refs, set(server_capabilities) class FetchPackResult(object): """Result of a fetch-pack operation. :var refs: Dictionary with all remote refs :var symrefs: Dictionary with remote symrefs :var agent: User agent string """ _FORWARDED_ATTRS = [ 'clear', 'copy', 'fromkeys', 'get', 'has_key', 'items', 'iteritems', 'iterkeys', 'itervalues', 'keys', 'pop', 'popitem', 'setdefault', 'update', 'values', 'viewitems', 'viewkeys', 'viewvalues'] - def __init__(self, refs, symrefs, agent): + def __init__(self, refs, symrefs, agent, new_shallow=None, + new_unshallow=None): self.refs = refs self.symrefs = symrefs self.agent = agent + self.new_shallow = new_shallow + self.new_unshallow = new_unshallow def _warn_deprecated(self): import warnings warnings.warn( "Use FetchPackResult.refs instead.", DeprecationWarning, stacklevel=3) def __eq__(self, other): if isinstance(other, dict): self._warn_deprecated() return (self.refs == other) return (self.refs == other.refs and self.symrefs == other.symrefs and self.agent == other.agent) def __contains__(self, name): self._warn_deprecated() return name in self.refs def __getitem__(self, name): self._warn_deprecated() return self.refs[name] def __len__(self): self._warn_deprecated() return len(self.refs) def __iter__(self): self._warn_deprecated() return iter(self.refs) def __getattribute__(self, name): if name in type(self)._FORWARDED_ATTRS: self._warn_deprecated() return getattr(self.refs, name) return super(FetchPackResult, self).__getattribute__(name) def __repr__(self): return "%s(%r, %r, %r)" % ( self.__class__.__name__, self.refs, self.symrefs, self.agent) +def _read_shallow_updates(proto): + new_shallow = set() + new_unshallow = set() + for pkt in proto.read_pkt_seq(): + cmd, sha = pkt.split(b' ', 1) + if cmd == COMMAND_SHALLOW: + new_shallow.add(sha.strip()) + elif cmd == COMMAND_UNSHALLOW: + new_unshallow.add(sha.strip()) + else: + raise GitProtocolError('unknown command %s' % pkt) + return (new_shallow, new_unshallow) + + # TODO(durin42): this doesn't correctly degrade if the server doesn't # support some capabilities. This should work properly with servers # that don't support multi_ack. class GitClient(object): """Git smart server client. """ def __init__(self, thin_packs=True, report_activity=None, quiet=False): """Create a new GitClient instance. :param thin_packs: Whether or not thin packs should be retrieved :param report_activity: Optional callback for reporting transport activity. """ self._report_activity = report_activity self._report_status_parser = None self._fetch_capabilities = set(UPLOAD_CAPABILITIES) self._fetch_capabilities.add(capability_agent()) self._send_capabilities = set(RECEIVE_CAPABILITIES) self._send_capabilities.add(capability_agent()) if quiet: self._send_capabilities.add(CAPABILITY_QUIET) if not thin_packs: self._fetch_capabilities.remove(CAPABILITY_THIN_PACK) def get_url(self, path): """Retrieves full url to given path. :param path: Repository path (as string) :return: Url to path (as string) """ raise NotImplementedError(self.get_url) @classmethod def from_parsedurl(cls, parsedurl, **kwargs): """Create an instance of this client from a urlparse.parsed object. :param parsedurl: Result of urlparse.urlparse() :return: A `GitClient` object """ raise NotImplementedError(cls.from_parsedurl) def send_pack(self, path, update_refs, generate_pack_data, progress=None): """Upload a pack to a remote repository. :param path: Repository path (as bytestring) :param update_refs: Function to determine changes to remote refs. Receive dict with existing remote refs, returns dict with changed refs (name -> sha, where sha=ZERO_SHA for deletions) :param generate_pack_data: Function that can return a tuple with number of objects and list of pack data to include :param progress: Optional progress function :raises SendPackError: if server rejects the pack data :raises UpdateRefsError: if the server supports report-status and rejects ref updates :return: new_refs dictionary containing the changes that were made {refname: new_ref}, including deleted refs. """ raise NotImplementedError(self.send_pack) - def fetch(self, path, target, determine_wants=None, progress=None): + def fetch(self, path, target, determine_wants=None, progress=None, + depth=None): """Fetch into a target repository. :param path: Path to fetch from (as bytestring) :param target: Target repository to fetch into :param determine_wants: Optional function to determine what refs to fetch. Receives dictionary of name->sha, should return list of shas to fetch. Defaults to all shas. :param progress: Optional progress function + :param depth: Depth to fetch at :return: Dictionary with all remote refs (not just those fetched) """ if determine_wants is None: determine_wants = target.object_store.determine_wants_all if CAPABILITY_THIN_PACK in self._fetch_capabilities: # TODO(jelmer): Avoid reading entire file into memory and # only processing it after the whole file has been fetched. f = BytesIO() def commit(): if f.tell(): f.seek(0) target.object_store.add_thin_pack(f.read, None) def abort(): pass else: f, commit, abort = target.object_store.add_pack() try: result = self.fetch_pack( path, determine_wants, target.get_graph_walker(), f.write, - progress) + progress=progress, depth=depth) except BaseException: abort() raise else: commit() + target.update_shallow(result.new_shallow, result.new_unshallow) return result def fetch_pack(self, path, determine_wants, graph_walker, pack_data, - progress=None): + progress=None, depth=None): """Retrieve a pack from a git smart server. :param path: Remote path to fetch from :param determine_wants: Function determine what refs to fetch. Receives dictionary of name->sha, should return list of shas to fetch. :param graph_walker: Object with next() and ack(). :param pack_data: Callback called for each bit of data in the pack :param progress: Callback for progress reports (strings) + :param depth: Shallow fetch depth :return: FetchPackResult object """ raise NotImplementedError(self.fetch_pack) def get_refs(self, path): """Retrieve the current refs from a git smart server. :param path: Path to the repo to fetch from. (as bytestring) """ raise NotImplementedError(self.get_refs) def _parse_status_report(self, proto): unpack = proto.read_pkt_line().strip() if unpack != b'unpack ok': st = True # flush remaining error data while st is not None: st = proto.read_pkt_line() raise SendPackError(unpack) statuses = [] errs = False ref_status = proto.read_pkt_line() while ref_status: ref_status = ref_status.strip() statuses.append(ref_status) if not ref_status.startswith(b'ok '): errs = True ref_status = proto.read_pkt_line() if errs: ref_status = {} ok = set() for status in statuses: if b' ' not in status: # malformed response, move on to the next one continue status, ref = status.split(b' ', 1) if status == b'ng': if b' ' in ref: ref, status = ref.split(b' ', 1) else: ok.add(ref) ref_status[ref] = status raise UpdateRefsError(', '.join([ refname for refname in ref_status if refname not in ok]) + b' failed to update', ref_status=ref_status) def _read_side_band64k_data(self, proto, channel_callbacks): """Read per-channel data. This requires the side-band-64k capability. :param proto: Protocol object to read from :param channel_callbacks: Dictionary mapping channels to packet handlers to use. None for a callback discards channel data. """ for pkt in proto.read_pkt_seq(): channel = ord(pkt[:1]) pkt = pkt[1:] try: cb = channel_callbacks[channel] except KeyError: raise AssertionError('Invalid sideband channel %d' % channel) else: if cb is not None: cb(pkt) def _handle_receive_pack_head(self, proto, capabilities, old_refs, new_refs): """Handle the head of a 'git-receive-pack' request. :param proto: Protocol object to read from :param capabilities: List of negotiated capabilities :param old_refs: Old refs, as received from the server :param new_refs: Refs to change :return: (have, want) tuple """ want = [] have = [x for x in old_refs.values() if not x == ZERO_SHA] sent_capabilities = False for refname in new_refs: if not isinstance(refname, bytes): raise TypeError('refname is not a bytestring: %r' % refname) old_sha1 = old_refs.get(refname, ZERO_SHA) if not isinstance(old_sha1, bytes): raise TypeError('old sha1 for %s is not a bytestring: %r' % (refname, old_sha1)) new_sha1 = new_refs.get(refname, ZERO_SHA) if not isinstance(new_sha1, bytes): raise TypeError('old sha1 for %s is not a bytestring %r' % (refname, new_sha1)) if old_sha1 != new_sha1: if sent_capabilities: proto.write_pkt_line(old_sha1 + b' ' + new_sha1 + b' ' + refname) else: proto.write_pkt_line( old_sha1 + b' ' + new_sha1 + b' ' + refname + b'\0' + b' '.join(capabilities)) sent_capabilities = True if new_sha1 not in have and new_sha1 != ZERO_SHA: want.append(new_sha1) proto.write_pkt_line(None) return (have, want) def _negotiate_receive_pack_capabilities(self, server_capabilities): negotiated_capabilities = ( self._send_capabilities & server_capabilities) unknown_capabilities = ( # noqa: F841 extract_capability_names(server_capabilities) - KNOWN_RECEIVE_CAPABILITIES) # TODO(jelmer): warn about unknown capabilities return negotiated_capabilities def _handle_receive_pack_tail(self, proto, capabilities, progress=None): """Handle the tail of a 'git-receive-pack' request. :param proto: Protocol object to read from :param capabilities: List of negotiated capabilities :param progress: Optional progress reporting function """ if CAPABILITY_SIDE_BAND_64K in capabilities: if progress is None: def progress(x): pass channel_callbacks = {2: progress} if CAPABILITY_REPORT_STATUS in capabilities: channel_callbacks[1] = PktLineParser( self._report_status_parser.handle_packet).parse self._read_side_band64k_data(proto, channel_callbacks) else: if CAPABILITY_REPORT_STATUS in capabilities: for pkt in proto.read_pkt_seq(): self._report_status_parser.handle_packet(pkt) if self._report_status_parser is not None: self._report_status_parser.check() def _negotiate_upload_pack_capabilities(self, server_capabilities): unknown_capabilities = ( # noqa: F841 extract_capability_names(server_capabilities) - KNOWN_UPLOAD_CAPABILITIES) # TODO(jelmer): warn about unknown capabilities symrefs = {} agent = None for capability in server_capabilities: k, v = parse_capability(capability) if k == CAPABILITY_SYMREF: (src, dst) = v.split(b':', 1) symrefs[src] = dst if k == CAPABILITY_AGENT: agent = v negotiated_capabilities = ( self._fetch_capabilities & server_capabilities) return (negotiated_capabilities, symrefs, agent) def _handle_upload_pack_head(self, proto, capabilities, graph_walker, - wants, can_read): + wants, can_read, depth): """Handle the head of a 'git-upload-pack' request. :param proto: Protocol object to read from :param capabilities: List of negotiated capabilities :param graph_walker: GraphWalker instance to call .ack() on :param wants: List of commits to fetch :param can_read: function that returns a boolean that indicates whether there is extra graph data to read on proto + :param depth: Depth for request """ assert isinstance(wants, list) and isinstance(wants[0], bytes) proto.write_pkt_line(COMMAND_WANT + b' ' + wants[0] + b' ' + b' '.join(capabilities) + b'\n') for want in wants[1:]: proto.write_pkt_line(COMMAND_WANT + b' ' + want + b'\n') - proto.write_pkt_line(None) + if depth not in (0, None) or getattr(graph_walker, 'shallow', None): + if CAPABILITY_SHALLOW not in capabilities: + raise GitProtocolError( + "server does not support shallow capability required for " + "depth") + for sha in graph_walker.shallow: + proto.write_pkt_line(COMMAND_SHALLOW + b' ' + sha + b'\n') + proto.write_pkt_line(COMMAND_DEEPEN + b' ' + + str(depth).encode('ascii') + b'\n') + proto.write_pkt_line(None) + if can_read is not None: + (new_shallow, new_unshallow) = _read_shallow_updates(proto) + else: + new_shallow = new_unshallow = None + else: + new_shallow = new_unshallow = set() + proto.write_pkt_line(None) have = next(graph_walker) while have: proto.write_pkt_line(COMMAND_HAVE + b' ' + have + b'\n') - if can_read(): + if can_read is not None and can_read(): pkt = proto.read_pkt_line() parts = pkt.rstrip(b'\n').split(b' ') if parts[0] == b'ACK': graph_walker.ack(parts[1]) if parts[2] in (b'continue', b'common'): pass elif parts[2] == b'ready': break else: raise AssertionError( "%s not in ('continue', 'ready', 'common)" % parts[2]) have = next(graph_walker) proto.write_pkt_line(COMMAND_DONE + b'\n') + return (new_shallow, new_unshallow) def _handle_upload_pack_tail(self, proto, capabilities, graph_walker, pack_data, progress=None, rbufsize=_RBUFSIZE): """Handle the tail of a 'git-upload-pack' request. :param proto: Protocol object to read from :param capabilities: List of negotiated capabilities :param graph_walker: GraphWalker instance to call .ack() on :param pack_data: Function to call with pack data :param progress: Optional progress reporting function :param rbufsize: Read buffer size """ pkt = proto.read_pkt_line() while pkt: parts = pkt.rstrip(b'\n').split(b' ') if parts[0] == b'ACK': graph_walker.ack(parts[1]) if len(parts) < 3 or parts[2] not in ( b'ready', b'continue', b'common'): break pkt = proto.read_pkt_line() if CAPABILITY_SIDE_BAND_64K in capabilities: if progress is None: # Just ignore progress data def progress(x): pass self._read_side_band64k_data(proto, { SIDE_BAND_CHANNEL_DATA: pack_data, SIDE_BAND_CHANNEL_PROGRESS: progress} ) else: while True: data = proto.read(rbufsize) if data == b"": break pack_data(data) +def check_wants(wants, refs): + """Check that a set of wants is valid. + + :param wants: Set of object SHAs to fetch + :param refs: Refs dictionary to check against + """ + missing = set(wants) - { + v for (k, v) in refs.items() + if not k.endswith(ANNOTATED_TAG_SUFFIX)} + if missing: + raise InvalidWants(missing) + + +def remote_error_from_stderr(stderr): + """Return an appropriate exception based on stderr output. """ + if stderr is None: + return HangupException() + for l in stderr.readlines(): + if l.startswith(b'ERROR: '): + return GitProtocolError( + l[len(b'ERROR: '):].decode('utf-8', 'replace')) + return GitProtocolError(l.decode('utf-8', 'replace')) + return HangupException() + + class TraditionalGitClient(GitClient): """Traditional Git client.""" DEFAULT_ENCODING = 'utf-8' def __init__(self, path_encoding=DEFAULT_ENCODING, **kwargs): self._remote_path_encoding = path_encoding super(TraditionalGitClient, self).__init__(**kwargs) def _connect(self, cmd, path): """Create a connection to the server. This method is abstract - concrete implementations should implement their own variant which connects to the server and returns an initialized Protocol object with the service ready for use and a can_read function which may be used to see if reads would block. :param cmd: The git service name to which we should connect. :param path: The path we should pass to the service. (as bytestirng) """ raise NotImplementedError() def send_pack(self, path, update_refs, generate_pack_data, progress=None): """Upload a pack to a remote repository. :param path: Repository path (as bytestring) :param update_refs: Function to determine changes to remote refs. Receive dict with existing remote refs, returns dict with changed refs (name -> sha, where sha=ZERO_SHA for deletions) :param generate_pack_data: Function that can return a tuple with number of objects and pack data to upload. :param progress: Optional callback called with progress updates :raises SendPackError: if server rejects the pack data :raises UpdateRefsError: if the server supports report-status and rejects ref updates :return: new_refs dictionary containing the changes that were made {refname: new_ref}, including deleted refs. """ - proto, unused_can_read = self._connect(b'receive-pack', path) + proto, unused_can_read, stderr = self._connect(b'receive-pack', path) with proto: - old_refs, server_capabilities = read_pkt_refs(proto) + try: + old_refs, server_capabilities = read_pkt_refs(proto) + except HangupException: + raise remote_error_from_stderr(stderr) negotiated_capabilities = \ self._negotiate_receive_pack_capabilities(server_capabilities) if CAPABILITY_REPORT_STATUS in negotiated_capabilities: self._report_status_parser = ReportStatusParser() report_status_parser = self._report_status_parser try: new_refs = orig_new_refs = update_refs(dict(old_refs)) except BaseException: proto.write_pkt_line(None) raise if CAPABILITY_DELETE_REFS not in server_capabilities: # Server does not support deletions. Fail later. new_refs = dict(orig_new_refs) for ref, sha in orig_new_refs.items(): if sha == ZERO_SHA: if CAPABILITY_REPORT_STATUS in negotiated_capabilities: report_status_parser._ref_statuses.append( b'ng ' + sha + b' remote does not support deleting refs') report_status_parser._ref_status_ok = False del new_refs[ref] if new_refs is None: proto.write_pkt_line(None) return old_refs if len(new_refs) == 0 and len(orig_new_refs): # NOOP - Original new refs filtered out by policy proto.write_pkt_line(None) if report_status_parser is not None: report_status_parser.check() return old_refs (have, want) = self._handle_receive_pack_head( proto, negotiated_capabilities, old_refs, new_refs) if (not want and set(new_refs.items()).issubset(set(old_refs.items()))): return new_refs pack_data_count, pack_data = generate_pack_data( have, want, ofs_delta=(CAPABILITY_OFS_DELTA in negotiated_capabilities)) dowrite = bool(pack_data_count) dowrite = dowrite or any(old_refs.get(ref) != sha for (ref, sha) in new_refs.items() if sha != ZERO_SHA) if dowrite: write_pack_data(proto.write_file(), pack_data_count, pack_data) self._handle_receive_pack_tail( proto, negotiated_capabilities, progress) return new_refs def fetch_pack(self, path, determine_wants, graph_walker, pack_data, - progress=None): + progress=None, depth=None): """Retrieve a pack from a git smart server. :param path: Remote path to fetch from :param determine_wants: Function determine what refs to fetch. Receives dictionary of name->sha, should return list of shas to fetch. :param graph_walker: Object with next() and ack(). :param pack_data: Callback called for each bit of data in the pack :param progress: Callback for progress reports (strings) + :param depth: Shallow fetch depth :return: FetchPackResult object """ - proto, can_read = self._connect(b'upload-pack', path) + proto, can_read, stderr = self._connect(b'upload-pack', path) with proto: - refs, server_capabilities = read_pkt_refs(proto) + try: + refs, server_capabilities = read_pkt_refs(proto) + except HangupException: + raise remote_error_from_stderr(stderr) negotiated_capabilities, symrefs, agent = ( self._negotiate_upload_pack_capabilities( server_capabilities)) if refs is None: proto.write_pkt_line(None) return FetchPackResult(refs, symrefs, agent) try: wants = determine_wants(refs) except BaseException: proto.write_pkt_line(None) raise if wants is not None: wants = [cid for cid in wants if cid != ZERO_SHA] if not wants: proto.write_pkt_line(None) return FetchPackResult(refs, symrefs, agent) - self._handle_upload_pack_head( - proto, negotiated_capabilities, graph_walker, wants, can_read) + check_wants(wants, refs) + (new_shallow, new_unshallow) = self._handle_upload_pack_head( + proto, negotiated_capabilities, graph_walker, wants, can_read, + depth=depth) self._handle_upload_pack_tail( proto, negotiated_capabilities, graph_walker, pack_data, progress) - return FetchPackResult(refs, symrefs, agent) + return FetchPackResult( + refs, symrefs, agent, new_shallow, new_unshallow) def get_refs(self, path): """Retrieve the current refs from a git smart server.""" # stock `git ls-remote` uses upload-pack - proto, _ = self._connect(b'upload-pack', path) + proto, _, stderr = self._connect(b'upload-pack', path) with proto: - refs, _ = read_pkt_refs(proto) + try: + refs, _ = read_pkt_refs(proto) + except HangupException: + raise remote_error_from_stderr(stderr) proto.write_pkt_line(None) return refs def archive(self, path, committish, write_data, progress=None, write_error=None, format=None, subdirs=None, prefix=None): - proto, can_read = self._connect(b'upload-archive', path) + proto, can_read, stderr = self._connect(b'upload-archive', path) with proto: if format is not None: proto.write_pkt_line(b"argument --format=" + format) proto.write_pkt_line(b"argument " + committish) if subdirs is not None: for subdir in subdirs: proto.write_pkt_line(b"argument " + subdir) if prefix is not None: proto.write_pkt_line(b"argument --prefix=" + prefix) proto.write_pkt_line(None) - pkt = proto.read_pkt_line() + try: + pkt = proto.read_pkt_line() + except HangupException: + raise remote_error_from_stderr(stderr) if pkt == b"NACK\n": return elif pkt == b"ACK\n": pass elif pkt.startswith(b"ERR "): - raise GitProtocolError(pkt[4:].rstrip(b"\n")) + raise GitProtocolError( + pkt[4:].rstrip(b"\n").decode('utf-8', 'replace')) else: raise AssertionError("invalid response %r" % pkt) ret = proto.read_pkt_line() if ret is not None: raise AssertionError("expected pkt tail") self._read_side_band64k_data(proto, { SIDE_BAND_CHANNEL_DATA: write_data, SIDE_BAND_CHANNEL_PROGRESS: progress, SIDE_BAND_CHANNEL_FATAL: write_error}) class TCPGitClient(TraditionalGitClient): """A Git Client that works over TCP directly (i.e. git://).""" def __init__(self, host, port=None, **kwargs): if port is None: port = TCP_GIT_PORT self._host = host self._port = port super(TCPGitClient, self).__init__(**kwargs) @classmethod def from_parsedurl(cls, parsedurl, **kwargs): return cls(parsedurl.hostname, port=parsedurl.port, **kwargs) def get_url(self, path): netloc = self._host if self._port is not None and self._port != TCP_GIT_PORT: netloc += ":%d" % self._port return urlparse.urlunsplit(("git", netloc, path, '', '')) def _connect(self, cmd, path): if not isinstance(cmd, bytes): raise TypeError(cmd) if not isinstance(path, bytes): path = path.encode(self._remote_path_encoding) sockaddrs = socket.getaddrinfo( self._host, self._port, socket.AF_UNSPEC, socket.SOCK_STREAM) s = None err = socket.error("no address found for %s" % self._host) for (family, socktype, proto, canonname, sockaddr) in sockaddrs: s = socket.socket(family, socktype, proto) s.setsockopt(socket.IPPROTO_TCP, socket.TCP_NODELAY, 1) try: s.connect(sockaddr) break - except socket.error as err: + except socket.error as e: + err = e if s is not None: s.close() s = None if s is None: raise err # -1 means system default buffering rfile = s.makefile('rb', -1) # 0 means unbuffered wfile = s.makefile('wb', 0) def close(): rfile.close() wfile.close() s.close() proto = Protocol(rfile.read, wfile.write, close, report_activity=self._report_activity) if path.startswith(b"/~"): path = path[1:] # TODO(jelmer): Alternative to ascii? proto.send_cmd( b'git-' + cmd, path, b'host=' + self._host.encode('ascii')) - return proto, lambda: _fileno_can_read(s) + return proto, lambda: _fileno_can_read(s), None class SubprocessWrapper(object): """A socket-like object that talks to a subprocess via pipes.""" def __init__(self, proc): self.proc = proc if sys.version_info[0] == 2: self.read = proc.stdout.read else: self.read = BufferedReader(proc.stdout).read self.write = proc.stdin.write + @property + def stderr(self): + return self.proc.stderr + def can_read(self): if sys.platform == 'win32': from msvcrt import get_osfhandle handle = get_osfhandle(self.proc.stdout.fileno()) return _win32_peek_avail(handle) != 0 else: return _fileno_can_read(self.proc.stdout.fileno()) def close(self): self.proc.stdin.close() self.proc.stdout.close() if self.proc.stderr: self.proc.stderr.close() self.proc.wait() def find_git_command(): """Find command to run for system Git (usually C Git). """ if sys.platform == 'win32': # support .exe, .bat and .cmd try: # to avoid overhead import win32api except ImportError: # run through cmd.exe with some overhead return ['cmd', '/c', 'git'] else: status, git = win32api.FindExecutable('git') return [git] else: return ['git'] class SubprocessGitClient(TraditionalGitClient): """Git client that talks to a server using a subprocess.""" - def __init__(self, **kwargs): - self._connection = None - self._stderr = None - self._stderr = kwargs.get('stderr') - if 'stderr' in kwargs: - del kwargs['stderr'] - super(SubprocessGitClient, self).__init__(**kwargs) - @classmethod def from_parsedurl(cls, parsedurl, **kwargs): return cls(**kwargs) git_command = None def _connect(self, service, path): if not isinstance(service, bytes): raise TypeError(service) if isinstance(path, bytes): path = path.decode(self._remote_path_encoding) if self.git_command is None: git_command = find_git_command() argv = git_command + [service.decode('ascii'), path] - p = SubprocessWrapper( - subprocess.Popen(argv, bufsize=0, stdin=subprocess.PIPE, + p = subprocess.Popen(argv, bufsize=0, stdin=subprocess.PIPE, stdout=subprocess.PIPE, - stderr=self._stderr)) - return Protocol(p.read, p.write, p.close, - report_activity=self._report_activity), p.can_read + stderr=subprocess.PIPE) + pw = SubprocessWrapper(p) + return (Protocol(pw.read, pw.write, pw.close, + report_activity=self._report_activity), + pw.can_read, p.stderr) class LocalGitClient(GitClient): """Git Client that just uses a local Repo.""" def __init__(self, thin_packs=True, report_activity=None, config=None): """Create a new LocalGitClient instance. :param thin_packs: Whether or not thin packs should be retrieved :param report_activity: Optional callback for reporting transport activity. """ self._report_activity = report_activity # Ignore the thin_packs argument def get_url(self, path): return urlparse.urlunsplit(('file', '', path, '', '')) @classmethod def from_parsedurl(cls, parsedurl, **kwargs): return cls(**kwargs) @classmethod def _open_repo(cls, path): from dulwich.repo import Repo if not isinstance(path, str): path = path.decode(sys.getfilesystemencoding()) return closing(Repo(path)) def send_pack(self, path, update_refs, generate_pack_data, progress=None): """Upload a pack to a remote repository. :param path: Repository path (as bytestring) :param update_refs: Function to determine changes to remote refs. Receive dict with existing remote refs, returns dict with changed refs (name -> sha, where sha=ZERO_SHA for deletions) :param generate_pack_data: Function that can return a tuple with number of items and pack data to upload. :param progress: Optional progress function :raises SendPackError: if server rejects the pack data :raises UpdateRefsError: if the server supports report-status and rejects ref updates :return: new_refs dictionary containing the changes that were made {refname: new_ref}, including deleted refs. """ if not progress: def progress(x): pass with self._open_repo(path) as target: old_refs = target.get_refs() new_refs = update_refs(dict(old_refs)) have = [sha1 for sha1 in old_refs.values() if sha1 != ZERO_SHA] want = [] for refname, new_sha1 in new_refs.items(): if (new_sha1 not in have and new_sha1 not in want and new_sha1 != ZERO_SHA): want.append(new_sha1) if (not want and set(new_refs.items()).issubset(set(old_refs.items()))): return new_refs target.object_store.add_pack_data( *generate_pack_data(have, want, ofs_delta=True)) for refname, new_sha1 in new_refs.items(): old_sha1 = old_refs.get(refname, ZERO_SHA) if new_sha1 != ZERO_SHA: if not target.refs.set_if_equals( refname, old_sha1, new_sha1): progress('unable to set %s to %s' % (refname, new_sha1)) else: if not target.refs.remove_if_equals(refname, old_sha1): progress('unable to remove %s' % refname) return new_refs - def fetch(self, path, target, determine_wants=None, progress=None): + def fetch(self, path, target, determine_wants=None, progress=None, + depth=None): """Fetch into a target repository. :param path: Path to fetch from (as bytestring) :param target: Target repository to fetch into :param determine_wants: Optional function determine what refs to fetch. Receives dictionary of name->sha, should return list of shas to fetch. Defaults to all shas. :param progress: Optional progress function + :param depth: Shallow fetch depth :return: FetchPackResult object """ with self._open_repo(path) as r: refs = r.fetch(target, determine_wants=determine_wants, - progress=progress) + progress=progress, depth=depth) return FetchPackResult(refs, r.refs.get_symrefs(), agent_string()) def fetch_pack(self, path, determine_wants, graph_walker, pack_data, - progress=None): + progress=None, depth=None): """Retrieve a pack from a git smart server. :param path: Remote path to fetch from :param determine_wants: Function determine what refs to fetch. Receives dictionary of name->sha, should return list of shas to fetch. :param graph_walker: Object with next() and ack(). :param pack_data: Callback called for each bit of data in the pack :param progress: Callback for progress reports (strings) + :param depth: Shallow fetch depth :return: FetchPackResult object """ with self._open_repo(path) as r: objects_iter = r.fetch_objects( - determine_wants, graph_walker, progress) + determine_wants, graph_walker, progress=progress, depth=depth) symrefs = r.refs.get_symrefs() agent = agent_string() # Did the process short-circuit (e.g. in a stateless RPC call)? # Note that the client still expects a 0-object pack in most cases. if objects_iter is None: return FetchPackResult(None, symrefs, agent) protocol = ProtocolFile(None, pack_data) write_pack_objects(protocol, objects_iter) return FetchPackResult(r.get_refs(), symrefs, agent) def get_refs(self, path): """Retrieve the current refs from a git smart server.""" with self._open_repo(path) as target: return target.get_refs() # What Git client to use for local access default_local_git_client_cls = LocalGitClient class SSHVendor(object): """A client side SSH implementation.""" def connect_ssh(self, host, command, username=None, port=None, password=None, key_filename=None): # This function was deprecated in 0.9.1 import warnings warnings.warn( "SSHVendor.connect_ssh has been renamed to SSHVendor.run_command", DeprecationWarning) return self.run_command(host, command, username=username, port=port, password=password, key_filename=key_filename) def run_command(self, host, command, username=None, port=None, password=None, key_filename=None): """Connect to an SSH server. Run a command remotely and return a file-like object for interaction with the remote command. :param host: Host name :param command: Command to run (as argv array) :param username: Optional ame of user to log in as :param port: Optional SSH port to use :param password: Optional ssh password for login or private key :param key_filename: Optional path to private keyfile """ raise NotImplementedError(self.run_command) class StrangeHostname(Exception): """Refusing to connect to strange SSH hostname.""" def __init__(self, hostname): super(StrangeHostname, self).__init__(hostname) class SubprocessSSHVendor(SSHVendor): """SSH vendor that shells out to the local 'ssh' command.""" def run_command(self, host, command, username=None, port=None, password=None, key_filename=None): if password is not None: raise NotImplementedError( "Setting password not supported by SubprocessSSHVendor.") args = ['ssh', '-x'] if port: args.extend(['-p', str(port)]) if key_filename: args.extend(['-i', str(key_filename)]) if username: host = '%s@%s' % (username, host) if host.startswith('-'): raise StrangeHostname(hostname=host) args.append(host) proc = subprocess.Popen(args + [command], bufsize=0, stdin=subprocess.PIPE, - stdout=subprocess.PIPE) + stdout=subprocess.PIPE, + stderr=subprocess.PIPE) return SubprocessWrapper(proc) class PLinkSSHVendor(SSHVendor): """SSH vendor that shells out to the local 'plink' command.""" def run_command(self, host, command, username=None, port=None, password=None, key_filename=None): if sys.platform == 'win32': args = ['plink.exe', '-ssh'] else: args = ['plink', '-ssh'] if password is not None: import warnings warnings.warn( "Invoking PLink with a password exposes the password in the " "process list.") args.extend(['-pw', str(password)]) if port: args.extend(['-P', str(port)]) if key_filename: args.extend(['-i', str(key_filename)]) if username: host = '%s@%s' % (username, host) if host.startswith('-'): raise StrangeHostname(hostname=host) args.append(host) proc = subprocess.Popen(args + [command], bufsize=0, stdin=subprocess.PIPE, - stdout=subprocess.PIPE) + stdout=subprocess.PIPE, + stderr=subprocess.PIPE) return SubprocessWrapper(proc) def ParamikoSSHVendor(**kwargs): import warnings warnings.warn( "ParamikoSSHVendor has been moved to dulwich.contrib.paramiko_vendor.", DeprecationWarning) from dulwich.contrib.paramiko_vendor import ParamikoSSHVendor return ParamikoSSHVendor(**kwargs) # Can be overridden by users get_ssh_vendor = SubprocessSSHVendor class SSHGitClient(TraditionalGitClient): def __init__(self, host, port=None, username=None, vendor=None, config=None, password=None, key_filename=None, **kwargs): self.host = host self.port = port self.username = username self.password = password self.key_filename = key_filename super(SSHGitClient, self).__init__(**kwargs) self.alternative_paths = {} if vendor is not None: self.ssh_vendor = vendor else: self.ssh_vendor = get_ssh_vendor() def get_url(self, path): netloc = self.host if self.port is not None: netloc += ":%d" % self.port if self.username is not None: netloc = urlquote(self.username, '@/:') + "@" + netloc return urlparse.urlunsplit(('ssh', netloc, path, '', '')) @classmethod def from_parsedurl(cls, parsedurl, **kwargs): return cls(host=parsedurl.hostname, port=parsedurl.port, username=parsedurl.username, **kwargs) def _get_cmd_path(self, cmd): cmd = self.alternative_paths.get(cmd, b'git-' + cmd) assert isinstance(cmd, bytes) return cmd def _connect(self, cmd, path): if not isinstance(cmd, bytes): raise TypeError(cmd) if isinstance(path, bytes): path = path.decode(self._remote_path_encoding) if path.startswith("/~"): path = path[1:] argv = (self._get_cmd_path(cmd).decode(self._remote_path_encoding) + " '" + path + "'") kwargs = {} if self.password is not None: kwargs['password'] = self.password if self.key_filename is not None: kwargs['key_filename'] = self.key_filename con = self.ssh_vendor.run_command( self.host, argv, port=self.port, username=self.username, **kwargs) return (Protocol(con.read, con.write, con.close, report_activity=self._report_activity), - con.can_read) + con.can_read, getattr(con, 'stderr', None)) def default_user_agent_string(): # Start user agent with "git/", because GitHub requires this. :-( See # https://github.com/jelmer/dulwich/issues/562 for details. return "git/dulwich/%s" % ".".join([str(x) for x in dulwich.__version__]) def default_urllib3_manager(config, **override_kwargs): """Return `urllib3` connection pool manager. Honour detected proxy configurations. :param config: `dulwich.config.ConfigDict` instance with Git configuration. :param kwargs: Additional arguments for urllib3.ProxyManager :return: `urllib3.ProxyManager` instance for proxy configurations, `urllib3.PoolManager` otherwise. """ proxy_server = user_agent = None ca_certs = ssl_verify = None if config is not None: try: proxy_server = config.get(b"http", b"proxy") except KeyError: pass try: user_agent = config.get(b"http", b"useragent") except KeyError: pass # TODO(jelmer): Support per-host settings try: ssl_verify = config.get_boolean(b"http", b"sslVerify") except KeyError: ssl_verify = True try: ca_certs = config.get_boolean(b"http", b"sslCAInfo") except KeyError: ca_certs = None if user_agent is None: user_agent = default_user_agent_string() headers = {"User-agent": user_agent} kwargs = {} if ssl_verify is True: kwargs['cert_reqs'] = "CERT_REQUIRED" elif ssl_verify is False: kwargs['cert_reqs'] = 'CERT_NONE' else: # Default to SSL verification kwargs['cert_reqs'] = "CERT_REQUIRED" if ca_certs is not None: kwargs['ca_certs'] = ca_certs kwargs.update(override_kwargs) # Try really hard to find a SSL certificate path if 'ca_certs' not in kwargs and kwargs.get('cert_reqs') != 'CERT_NONE': try: import certifi except ImportError: pass else: kwargs['ca_certs'] = certifi.where() import urllib3 if proxy_server is not None: # `urllib3` requires a `str` object in both Python 2 and 3, while # `ConfigDict` coerces entries to `bytes` on Python 3. Compensate. if not isinstance(proxy_server, str): proxy_server = proxy_server.decode() manager = urllib3.ProxyManager(proxy_server, headers=headers, **kwargs) else: manager = urllib3.PoolManager(headers=headers, **kwargs) return manager class HttpGitClient(GitClient): def __init__(self, base_url, dumb=None, pool_manager=None, config=None, username=None, password=None, **kwargs): self._base_url = base_url.rstrip("/") + "/" self._username = username self._password = password self.dumb = dumb - self.headers = {} if pool_manager is None: self.pool_manager = default_urllib3_manager(config) else: self.pool_manager = pool_manager if username is not None: # No escaping needed: ":" is not allowed in username: # https://tools.ietf.org/html/rfc2617#section-2 credentials = "%s:%s" % (username, password) import urllib3.util basic_auth = urllib3.util.make_headers(basic_auth=credentials) self.pool_manager.headers.update(basic_auth) GitClient.__init__(self, **kwargs) def get_url(self, path): return self._get_url(path).rstrip("/") @classmethod def from_parsedurl(cls, parsedurl, **kwargs): password = parsedurl.password if password is not None: - password = urlunquote(password) + kwargs['password'] = urlunquote(password) username = parsedurl.username if username is not None: - username = urlunquote(username) - # TODO(jelmer): This also strips the username - parsedurl = parsedurl._replace(netloc=parsedurl.hostname) - return cls(urlparse.urlunparse(parsedurl), - password=password, username=username, **kwargs) + kwargs['username'] = urlunquote(username) + netloc = parsedurl.hostname + if parsedurl.port: + netloc = "%s:%s" % (netloc, parsedurl.port) + if parsedurl.username: + netloc = "%s@%s" % (parsedurl.username, netloc) + parsedurl = parsedurl._replace(netloc=netloc) + return cls(urlparse.urlunparse(parsedurl), **kwargs) def __repr__(self): return "%s(%r, dumb=%r)" % ( type(self).__name__, self._base_url, self.dumb) def _get_url(self, path): if not isinstance(path, str): # TODO(jelmer): this is unrelated to the local filesystem; # This is not necessarily the right encoding to decode the path # with. path = path.decode(sys.getfilesystemencoding()) return urlparse.urljoin(self._base_url, path).rstrip("/") + "/" def _http_request(self, url, headers=None, data=None, allow_compression=False): """Perform HTTP request. :param url: Request URL. :param headers: Optional custom headers to override defaults. :param data: Request data. :param allow_compression: Allow GZipped communication. :return: Tuple (`response`, `read`), where response is an `urllib3` response object with additional `content_type` and `redirect_location` properties, and `read` is a consumable read method for the response data. """ req_headers = self.pool_manager.headers.copy() if headers is not None: req_headers.update(headers) req_headers["Pragma"] = "no-cache" if allow_compression: req_headers["Accept-Encoding"] = "gzip" else: req_headers["Accept-Encoding"] = "identity" if data is None: resp = self.pool_manager.request("GET", url, headers=req_headers) else: resp = self.pool_manager.request("POST", url, headers=req_headers, body=data) if resp.status == 404: raise NotGitRepository() elif resp.status != 200: raise GitProtocolError("unexpected http resp %d for %s" % (resp.status, url)) # TODO: Optimization available by adding `preload_content=False` to the # request and just passing the `read` method on instead of going via # `BytesIO`, if we can guarantee that the entire response is consumed # before issuing the next to still allow for connection reuse from the # pool. - if resp.getheader("Content-Encoding") == "gzip": - read = gzip.GzipFile(fileobj=BytesIO(resp.data)).read - else: - read = BytesIO(resp.data).read + read = BytesIO(resp.data).read resp.content_type = resp.getheader("Content-Type") resp.redirect_location = resp.get_redirect_location() return resp, read def _discover_references(self, service, base_url): assert base_url[-1] == "/" tail = "info/refs" headers = {"Accept": "*/*"} if self.dumb is not True: tail += "?service=%s" % service.decode('ascii') url = urlparse.urljoin(base_url, tail) resp, read = self._http_request(url, headers, allow_compression=True) if resp.redirect_location: # Something changed (redirect!), so let's update the base URL if not resp.redirect_location.endswith(tail): raise GitProtocolError( "Redirected from URL %s to URL %s without %s" % ( url, resp.redirect_location, tail)) base_url = resp.redirect_location[:-len(tail)] try: self.dumb = not resp.content_type.startswith("application/x-git-") if not self.dumb: proto = Protocol(read, None) # The first line should mention the service try: [pkt] = list(proto.read_pkt_seq()) except ValueError: raise GitProtocolError( "unexpected number of packets received") if pkt.rstrip(b'\n') != (b'# service=' + service): raise GitProtocolError( "unexpected first line %r from smart server" % pkt) return read_pkt_refs(proto) + (base_url, ) else: return read_info_refs(resp), set(), base_url finally: resp.close() def _smart_request(self, service, url, data): assert url[-1] == "/" url = urlparse.urljoin(url, service) result_content_type = "application/x-%s-result" % service headers = { "Content-Type": "application/x-%s-request" % service, "Accept": result_content_type, "Content-Length": str(len(data)), } resp, read = self._http_request(url, headers, data) if resp.content_type != result_content_type: raise GitProtocolError("Invalid content-type from server: %s" % resp.content_type) return resp, read def send_pack(self, path, update_refs, generate_pack_data, progress=None): """Upload a pack to a remote repository. :param path: Repository path (as bytestring) :param update_refs: Function to determine changes to remote refs. Receive dict with existing remote refs, returns dict with changed refs (name -> sha, where sha=ZERO_SHA for deletions) :param generate_pack_data: Function that can return a tuple with number of elements and pack data to upload. :param progress: Optional progress function :raises SendPackError: if server rejects the pack data :raises UpdateRefsError: if the server supports report-status and rejects ref updates :return: new_refs dictionary containing the changes that were made {refname: new_ref}, including deleted refs. """ url = self._get_url(path) old_refs, server_capabilities, url = self._discover_references( b"git-receive-pack", url) negotiated_capabilities = self._negotiate_receive_pack_capabilities( server_capabilities) negotiated_capabilities.add(capability_agent()) if CAPABILITY_REPORT_STATUS in negotiated_capabilities: self._report_status_parser = ReportStatusParser() new_refs = update_refs(dict(old_refs)) if new_refs is None: # Determine wants function is aborting the push. return old_refs if self.dumb: raise NotImplementedError(self.fetch_pack) req_data = BytesIO() req_proto = Protocol(None, req_data.write) (have, want) = self._handle_receive_pack_head( req_proto, negotiated_capabilities, old_refs, new_refs) if not want and set(new_refs.items()).issubset(set(old_refs.items())): return new_refs pack_data_count, pack_data = generate_pack_data( have, want, ofs_delta=(CAPABILITY_OFS_DELTA in negotiated_capabilities)) if pack_data_count: write_pack_data(req_proto.write_file(), pack_data_count, pack_data) resp, read = self._smart_request("git-receive-pack", url, data=req_data.getvalue()) try: resp_proto = Protocol(read, None) self._handle_receive_pack_tail( resp_proto, negotiated_capabilities, progress) return new_refs finally: resp.close() def fetch_pack(self, path, determine_wants, graph_walker, pack_data, - progress=None): + progress=None, depth=None): """Retrieve a pack from a git smart server. :param determine_wants: Callback that returns list of commits to fetch :param graph_walker: Object with next() and ack(). :param pack_data: Callback called for each bit of data in the pack :param progress: Callback for progress reports (strings) + :param depth: Depth for request :return: FetchPackResult object """ url = self._get_url(path) refs, server_capabilities, url = self._discover_references( b"git-upload-pack", url) negotiated_capabilities, symrefs, agent = ( self._negotiate_upload_pack_capabilities( server_capabilities)) wants = determine_wants(refs) if wants is not None: wants = [cid for cid in wants if cid != ZERO_SHA] if not wants: return FetchPackResult(refs, symrefs, agent) if self.dumb: raise NotImplementedError(self.send_pack) + check_wants(wants, refs) req_data = BytesIO() req_proto = Protocol(None, req_data.write) - self._handle_upload_pack_head( + (new_shallow, new_unshallow) = self._handle_upload_pack_head( req_proto, negotiated_capabilities, graph_walker, wants, - lambda: False) + can_read=None, depth=depth) resp, read = self._smart_request( "git-upload-pack", url, data=req_data.getvalue()) try: resp_proto = Protocol(read, None) + if new_shallow is None and new_unshallow is None: + (new_shallow, new_unshallow) = _read_shallow_updates( + resp_proto) self._handle_upload_pack_tail( resp_proto, negotiated_capabilities, graph_walker, pack_data, progress) - return FetchPackResult(refs, symrefs, agent) + return FetchPackResult( + refs, symrefs, agent, new_shallow, new_unshallow) finally: resp.close() def get_refs(self, path): """Retrieve the current refs from a git smart server.""" url = self._get_url(path) refs, _, _ = self._discover_references( b"git-upload-pack", url) return refs def get_transport_and_path_from_url(url, config=None, **kwargs): """Obtain a git client from a URL. :param url: URL to open (a unicode string) :param config: Optional config object :param thin_packs: Whether or not thin packs should be retrieved :param report_activity: Optional callback for reporting transport activity. :return: Tuple with client instance and relative path. """ parsed = urlparse.urlparse(url) if parsed.scheme == 'git': return (TCPGitClient.from_parsedurl(parsed, **kwargs), parsed.path) elif parsed.scheme in ('git+ssh', 'ssh'): return SSHGitClient.from_parsedurl(parsed, **kwargs), parsed.path elif parsed.scheme in ('http', 'https'): return HttpGitClient.from_parsedurl( parsed, config=config, **kwargs), parsed.path elif parsed.scheme == 'file': return default_local_git_client_cls.from_parsedurl( parsed, **kwargs), parsed.path raise ValueError("unknown scheme '%s'" % parsed.scheme) def parse_rsync_url(location): """Parse a rsync-style URL.""" if ':' in location and '@' not in location: # SSH with no user@, zero or one leading slash. (host, path) = location.split(':', 1) user = None elif ':' in location: # SSH with user@host:foo. user_host, path = location.split(':', 1) if '@' in user_host: user, host = user_host.rsplit('@', 1) else: user = None host = user_host else: raise ValueError('not a valid rsync-style URL') return (user, host, path) def get_transport_and_path(location, **kwargs): """Obtain a git client from a URL. :param location: URL or path (a string) :param config: Optional config object :param thin_packs: Whether or not thin packs should be retrieved :param report_activity: Optional callback for reporting transport activity. :return: Tuple with client instance and relative path. """ # First, try to parse it as a URL try: return get_transport_and_path_from_url(location, **kwargs) except ValueError: pass if (sys.platform == 'win32' and location[0].isalpha() and location[1:3] == ':\\'): # Windows local path return default_local_git_client_cls(**kwargs), location try: (username, hostname, path) = parse_rsync_url(location) except ValueError: # Otherwise, assume it's a local path. return default_local_git_client_cls(**kwargs), location else: return SSHGitClient(hostname, username=username, **kwargs), path diff --git a/dulwich/config.py b/dulwich/config.py index cc818e4e..416d5524 100644 --- a/dulwich/config.py +++ b/dulwich/config.py @@ -1,543 +1,550 @@ # config.py - Reading and writing Git config files # Copyright (C) 2011-2013 Jelmer Vernooij # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """Reading and writing Git configuration files. TODO: * preserve formatting when updating configuration files * treat subsection names as case-insensitive for [branch.foo] style subsections """ import errno import os import sys from collections import ( - Iterable, OrderedDict, - MutableMapping, ) - +try: + from collections.abc import ( + Iterable, + MutableMapping, + ) +except ImportError: # python < 3.7 + from collections import ( + Iterable, + MutableMapping, + ) from dulwich.file import GitFile SENTINAL = object() def lower_key(key): if isinstance(key, (bytes, str)): return key.lower() if isinstance(key, Iterable): return type(key)( map(lower_key, key) ) return key class CaseInsensitiveDict(OrderedDict): @classmethod def make(cls, dict_in=None): if isinstance(dict_in, cls): return dict_in out = cls() if dict_in is None: return out if not isinstance(dict_in, MutableMapping): raise TypeError for key, value in dict_in.items(): out[key] = value return out def __setitem__(self, key, value, **kwargs): key = lower_key(key) super(CaseInsensitiveDict, self).__setitem__(key, value, **kwargs) def __getitem__(self, item): key = lower_key(item) return super(CaseInsensitiveDict, self).__getitem__(key) def get(self, key, default=SENTINAL): try: return self[key] except KeyError: pass if default is SENTINAL: return type(self)() return default def setdefault(self, key, default=SENTINAL): try: return self[key] except KeyError: self[key] = self.get(key, default) return self[key] class Config(object): """A Git configuration.""" def get(self, section, name): """Retrieve the contents of a configuration setting. :param section: Tuple with section name and optional subsection namee :param subsection: Subsection name :return: Contents of the setting :raise KeyError: if the value is not set """ raise NotImplementedError(self.get) def get_boolean(self, section, name, default=None): """Retrieve a configuration setting as boolean. :param section: Tuple with section name and optional subsection namee :param name: Name of the setting, including section and possible subsection. :return: Contents of the setting :raise KeyError: if the value is not set """ try: value = self.get(section, name) except KeyError: return default if value.lower() == b"true": return True elif value.lower() == b"false": return False raise ValueError("not a valid boolean string: %r" % value) def set(self, section, name, value): """Set a configuration value. :param section: Tuple with section name and optional subsection namee :param name: Name of the configuration value, including section and optional subsection :param: Value of the setting """ raise NotImplementedError(self.set) def iteritems(self, section): """Iterate over the configuration pairs for a specific section. :param section: Tuple with section name and optional subsection namee :return: Iterator over (name, value) pairs """ raise NotImplementedError(self.iteritems) def itersections(self): """Iterate over the sections. :return: Iterator over section tuples """ raise NotImplementedError(self.itersections) def has_section(self, name): """Check if a specified section exists. :param name: Name of section to check for :return: boolean indicating whether the section exists """ return (name in self.itersections()) class ConfigDict(Config, MutableMapping): """Git configuration stored in a dictionary.""" def __init__(self, values=None, encoding=None): """Create a new ConfigDict.""" if encoding is None: encoding = sys.getdefaultencoding() self.encoding = encoding self._values = CaseInsensitiveDict.make(values) def __repr__(self): return "%s(%r)" % (self.__class__.__name__, self._values) def __eq__(self, other): return ( isinstance(other, self.__class__) and other._values == self._values) def __getitem__(self, key): return self._values.__getitem__(key) def __setitem__(self, key, value): return self._values.__setitem__(key, value) def __delitem__(self, key): return self._values.__delitem__(key) def __iter__(self): return self._values.__iter__() def __len__(self): return self._values.__len__() @classmethod def _parse_setting(cls, name): parts = name.split(".") if len(parts) == 3: return (parts[0], parts[1], parts[2]) else: return (parts[0], None, parts[1]) def _check_section_and_name(self, section, name): if not isinstance(section, tuple): section = (section, ) section = tuple([ subsection.encode(self.encoding) if not isinstance(subsection, bytes) else subsection for subsection in section ]) if not isinstance(name, bytes): name = name.encode(self.encoding) return section, name def get(self, section, name): section, name = self._check_section_and_name(section, name) if len(section) > 1: try: return self._values[section][name] except KeyError: pass return self._values[(section[0],)][name] def set(self, section, name, value): section, name = self._check_section_and_name(section, name) if type(value) not in (bool, bytes): value = value.encode(self.encoding) self._values.setdefault(section)[name] = value def iteritems(self, section): return self._values.get(section).items() def itersections(self): return self._values.keys() def _format_string(value): if (value.startswith(b" ") or value.startswith(b"\t") or value.endswith(b" ") or b'#' in value or value.endswith(b"\t")): return b'"' + _escape_value(value) + b'"' else: return _escape_value(value) _ESCAPE_TABLE = { ord(b"\\"): ord(b"\\"), ord(b"\""): ord(b"\""), ord(b"n"): ord(b"\n"), ord(b"t"): ord(b"\t"), ord(b"b"): ord(b"\b"), } _COMMENT_CHARS = [ord(b"#"), ord(b";")] _WHITESPACE_CHARS = [ord(b"\t"), ord(b" ")] def _parse_string(value): value = bytearray(value.strip()) ret = bytearray() whitespace = bytearray() in_quotes = False i = 0 while i < len(value): c = value[i] if c == ord(b"\\"): i += 1 try: v = _ESCAPE_TABLE[value[i]] except IndexError: raise ValueError( "escape character in %r at %d before end of string" % (value, i)) except KeyError: raise ValueError( "escape character followed by unknown character " "%s at %d in %r" % (value[i], i, value)) if whitespace: ret.extend(whitespace) whitespace = bytearray() ret.append(v) elif c == ord(b"\""): in_quotes = (not in_quotes) elif c in _COMMENT_CHARS and not in_quotes: # the rest of the line is a comment break elif c in _WHITESPACE_CHARS: whitespace.append(c) else: if whitespace: ret.extend(whitespace) whitespace = bytearray() ret.append(c) i += 1 if in_quotes: raise ValueError("missing end quote") return bytes(ret) def _escape_value(value): """Escape a value.""" value = value.replace(b"\\", b"\\\\") value = value.replace(b"\n", b"\\n") value = value.replace(b"\t", b"\\t") value = value.replace(b"\"", b"\\\"") return value def _check_variable_name(name): for i in range(len(name)): c = name[i:i+1] if not c.isalnum() and c != b'-': return False return True def _check_section_name(name): for i in range(len(name)): c = name[i:i+1] if not c.isalnum() and c not in (b'-', b'.'): return False return True def _strip_comments(line): comment_bytes = {ord(b"#"), ord(b";")} quote = ord(b'"') string_open = False # Normalize line to bytearray for simple 2/3 compatibility for i, character in enumerate(bytearray(line)): # Comment characters outside balanced quotes denote comment start if character == quote: string_open = not string_open elif not string_open and character in comment_bytes: return line[:i] return line class ConfigFile(ConfigDict): """A Git configuration file, like .git/config or ~/.gitconfig. """ @classmethod def from_file(cls, f): """Read configuration from a file-like object.""" ret = cls() section = None setting = None for lineno, line in enumerate(f.readlines()): line = line.lstrip() if setting is None: # Parse section header ("[bla]") if len(line) > 0 and line[:1] == b"[": line = _strip_comments(line).rstrip() try: last = line.index(b"]") except ValueError: raise ValueError("expected trailing ]") pts = line[1:last].split(b" ", 1) line = line[last+1:] if len(pts) == 2: if pts[1][:1] != b"\"" or pts[1][-1:] != b"\"": raise ValueError( "Invalid subsection %r" % pts[1]) else: pts[1] = pts[1][1:-1] if not _check_section_name(pts[0]): raise ValueError("invalid section name %r" % pts[0]) section = (pts[0], pts[1]) else: if not _check_section_name(pts[0]): raise ValueError( "invalid section name %r" % pts[0]) pts = pts[0].split(b".", 1) if len(pts) == 2: section = (pts[0], pts[1]) else: section = (pts[0], ) ret._values.setdefault(section) if _strip_comments(line).strip() == b"": continue if section is None: raise ValueError("setting %r without section" % line) try: setting, value = line.split(b"=", 1) except ValueError: setting = line value = b"true" setting = setting.strip() if not _check_variable_name(setting): raise ValueError("invalid variable name %s" % setting) if value.endswith(b"\\\n"): continuation = value[:-2] else: continuation = None value = _parse_string(value) ret._values[section][setting] = value setting = None else: # continuation line if line.endswith(b"\\\n"): continuation += line[:-2] else: continuation += line value = _parse_string(continuation) ret._values[section][setting] = value continuation = None setting = None return ret @classmethod def from_path(cls, path): """Read configuration from a file on disk.""" with GitFile(path, 'rb') as f: ret = cls.from_file(f) ret.path = path return ret def write_to_path(self, path=None): """Write configuration to a file on disk.""" if path is None: path = self.path with GitFile(path, 'wb') as f: self.write_to_file(f) def write_to_file(self, f): """Write configuration to a file-like object.""" for section, values in self._values.items(): try: section_name, subsection_name = section except ValueError: (section_name, ) = section subsection_name = None if subsection_name is None: f.write(b"[" + section_name + b"]\n") else: f.write(b"[" + section_name + b" \"" + subsection_name + b"\"]\n") for key, value in values.items(): if value is True: value = b"true" elif value is False: value = b"false" else: value = _format_string(value) f.write(b"\t" + key + b" = " + value + b"\n") class StackedConfig(Config): """Configuration which reads from multiple config files..""" def __init__(self, backends, writable=None): self.backends = backends self.writable = writable def __repr__(self): return "<%s for %r>" % (self.__class__.__name__, self.backends) @classmethod def default(cls): return cls(cls.default_backends()) @classmethod def default_backends(cls): """Retrieve the default configuration. See git-config(1) for details on the files searched. """ paths = [] paths.append(os.path.expanduser("~/.gitconfig")) xdg_config_home = os.environ.get( "XDG_CONFIG_HOME", os.path.expanduser("~/.config/"), ) paths.append(os.path.join(xdg_config_home, "git", "config")) if "GIT_CONFIG_NOSYSTEM" not in os.environ: paths.append("/etc/gitconfig") backends = [] for path in paths: try: cf = ConfigFile.from_path(path) except (IOError, OSError) as e: if e.errno != errno.ENOENT: raise else: continue backends.append(cf) return backends def get(self, section, name): if not isinstance(section, tuple): section = (section, ) for backend in self.backends: try: return backend.get(section, name) except KeyError: pass raise KeyError(name) def set(self, section, name, value): if self.writable is None: raise NotImplementedError(self.set) return self.writable.set(section, name, value) def parse_submodules(config): """Parse a gitmodules GitConfig file, returning submodules. :param config: A `ConfigFile` :return: list of tuples (submodule path, url, name), where name is quoted part of the section's name. """ for section in config.keys(): section_kind, section_name = section if section_kind == b'submodule': sm_path = config.get(section, b'path') sm_url = config.get(section, b'url') yield (sm_path, sm_url, section_name) diff --git a/dulwich/contrib/README.md b/dulwich/contrib/README.md new file mode 100644 index 00000000..3e65c012 --- /dev/null +++ b/dulwich/contrib/README.md @@ -0,0 +1,3 @@ +This directory contains code that some may find useful. Code here is not an official +part of Dulwich, and may no longer work. Unlike the rest of Dulwich, it is not regularly +tested. diff --git a/dulwich/contrib/paramiko_vendor.py b/dulwich/contrib/paramiko_vendor.py index 9cb748fe..bfd1715b 100644 --- a/dulwich/contrib/paramiko_vendor.py +++ b/dulwich/contrib/paramiko_vendor.py @@ -1,152 +1,111 @@ # paramiko_vendor.py -- paramiko implementation of the SSHVendor interface # Copyright (C) 2013 Aaron O'Mullan # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """Paramiko SSH support for Dulwich. To use this implementation as the SSH implementation in Dulwich, override the dulwich.client.get_ssh_vendor attribute: >>> from dulwich import client as _mod_client >>> from dulwich.contrib.paramiko_vendor import ParamikoSSHVendor >>> _mod_client.get_ssh_vendor = ParamikoSSHVendor This implementation is experimental and does not have any tests. """ import paramiko import paramiko.client -import threading class _ParamikoWrapper(object): - STDERR_READ_N = 2048 # 2k - def __init__(self, client, channel, progress_stderr=None): + def __init__(self, client, channel): self.client = client self.channel = channel - self.progress_stderr = progress_stderr - self.should_monitor = bool(progress_stderr) or True - self.monitor_thread = None - self.stderr = b'' # Channel must block self.channel.setblocking(True) - # Start - if self.should_monitor: - self.monitor_thread = threading.Thread( - target=self.monitor_stderr) - self.monitor_thread.start() - - def monitor_stderr(self): - while self.should_monitor: - # Block and read - data = self.read_stderr(self.STDERR_READ_N) - - # Socket closed - if not data: - self.should_monitor = False - break - - # Emit data - if self.progress_stderr: - self.progress_stderr(data) - - # Append to buffer - self.stderr += data - - def stop_monitoring(self): - # Stop StdErr thread - if self.should_monitor: - self.should_monitor = False - self.monitor_thread.join() - - # Get left over data - data = self.channel.in_stderr_buffer.empty() - self.stderr += data + @property + def stderr(self): + return self.channel.makefile_stderr() def can_read(self): return self.channel.recv_ready() def write(self, data): return self.channel.sendall(data) - def read_stderr(self, n): - return self.channel.recv_stderr(n) - def read(self, n=None): data = self.channel.recv(n) data_len = len(data) # Closed socket if not data: return b'' # Read more if needed if n and data_len < n: diff_len = n - data_len return data + self.read(diff_len) return data def close(self): self.channel.close() - self.stop_monitoring() class ParamikoSSHVendor(object): # http://docs.paramiko.org/en/2.4/api/client.html def __init__(self, **kwargs): self.kwargs = kwargs def run_command(self, host, command, username=None, port=None, - progress_stderr=None, password=None, pkey=None, key_filename=None, **kwargs): client = paramiko.SSHClient() connection_kwargs = {'hostname': host} connection_kwargs.update(self.kwargs) if username: connection_kwargs['username'] = username if port: connection_kwargs['port'] = port if password: connection_kwargs['password'] = password if pkey: connection_kwargs['pkey'] = pkey if key_filename: connection_kwargs['key_filename'] = key_filename connection_kwargs.update(kwargs) policy = paramiko.client.MissingHostKeyPolicy() client.set_missing_host_key_policy(policy) client.connect(**connection_kwargs) # Open SSH session channel = client.get_transport().open_session() # Run commands channel.exec_command(command) - return _ParamikoWrapper( - client, channel, progress_stderr=progress_stderr) + return _ParamikoWrapper(client, channel) diff --git a/dulwich/ignore.py b/dulwich/ignore.py index b3878938..ab0e92a0 100644 --- a/dulwich/ignore.py +++ b/dulwich/ignore.py @@ -1,358 +1,358 @@ # Copyright (C) 2017 Jelmer Vernooij # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """Parsing of gitignore files. For details for the matching rules, see https://git-scm.com/docs/gitignore """ import os.path import re import sys def _translate_segment(segment): if segment == b"*": return b'[^/]+' res = b"" i, n = 0, len(segment) while i < n: c = segment[i:i+1] i = i+1 if c == b'*': res += b'[^/]*' elif c == b'?': res += b'.' elif c == b'[': j = i if j < n and segment[j:j+1] == b'!': j = j+1 if j < n and segment[j:j+1] == b']': j = j+1 while j < n and segment[j:j+1] != b']': j = j+1 if j >= n: res += b'\\[' else: stuff = segment[i:j].replace(b'\\', b'\\\\') i = j+1 if stuff.startswith(b'!'): stuff = b'^' + stuff[1:] elif stuff.startswith(b'^'): stuff = b'\\' + stuff res += b'[' + stuff + b']' else: res += re.escape(c) return res def translate(pat): """Translate a shell PATTERN to a regular expression. There is no way to quote meta-characters. Originally copied from fnmatch in Python 2.7, but modified for Dulwich to cope with features in Git ignore patterns. """ res = b'(?ms)' if b'/' not in pat[:-1]: # If there's no slash, this is a filename-based match res += b'(.*/)?' if pat.startswith(b'**/'): # Leading **/ pat = pat[2:] res += b'(.*/)?' if pat.startswith(b'/'): pat = pat[1:] for i, segment in enumerate(pat.split(b'/')): if segment == b'**': res += b'(/.*)?' continue else: res += ((re.escape(b'/') if i > 0 else b'') + _translate_segment(segment)) if not pat.endswith(b'/'): res += b'/?' - return res + b'\Z' + return res + b'\\Z' def read_ignore_patterns(f): """Read a git ignore file. :param f: File-like object to read from :return: List of patterns """ for line in f: line = line.rstrip(b"\r\n") # Ignore blank lines, they're used for readability. if not line: continue if line.startswith(b'#'): # Comment continue # Trailing spaces are ignored unless they are quoted with a backslash. while line.endswith(b' ') and not line.endswith(b'\\ '): line = line[:-1] line = line.replace(b'\\ ', b' ') yield line def match_pattern(path, pattern, ignorecase=False): """Match a gitignore-style pattern against a path. :param path: Path to match :param pattern: Pattern to match :param ignorecase: Whether to do case-sensitive matching :return: bool indicating whether the pattern matched """ return Pattern(pattern, ignorecase).match(path) class Pattern(object): """A single ignore pattern.""" def __init__(self, pattern, ignorecase=False): self.pattern = pattern self.ignorecase = ignorecase if pattern[0:1] == b'!': self.is_exclude = False pattern = pattern[1:] else: if pattern[0:1] == b'\\': pattern = pattern[1:] self.is_exclude = True flags = 0 if self.ignorecase: flags = re.IGNORECASE self._re = re.compile(translate(pattern), flags) def __bytes__(self): return self.pattern def __str__(self): return self.pattern.decode(sys.getfilesystemencoding()) def __eq__(self, other): return (type(self) == type(other) and self.pattern == other.pattern and self.ignorecase == other.ignorecase) def __repr__(self): return "%s(%s, %r)" % ( type(self).__name__, self.pattern, self.ignorecase) def match(self, path): """Try to match a path against this ignore pattern. :param path: Path to match (relative to ignore location) :return: boolean """ return bool(self._re.match(path)) class IgnoreFilter(object): def __init__(self, patterns, ignorecase=False): self._patterns = [] self._ignorecase = ignorecase for pattern in patterns: self.append_pattern(pattern) def append_pattern(self, pattern): """Add a pattern to the set.""" self._patterns.append(Pattern(pattern, self._ignorecase)) def find_matching(self, path): """Yield all matching patterns for path. :param path: Path to match :return: Iterator over iterators """ if not isinstance(path, bytes): path = path.encode(sys.getfilesystemencoding()) for pattern in self._patterns: if pattern.match(path): yield pattern def is_ignored(self, path): """Check whether a path is ignored. For directories, include a trailing slash. :return: status is None if file is not mentioned, True if it is included, False if it is explicitly excluded. """ status = None for pattern in self.find_matching(path): status = pattern.is_exclude return status @classmethod def from_path(cls, path, ignorecase=False): with open(path, 'rb') as f: ret = cls(read_ignore_patterns(f), ignorecase) ret._path = path return ret def __repr__(self): if getattr(self, '_path', None) is None: return "<%s>" % (type(self).__name__) else: return "%s.from_path(%r)" % (type(self).__name__, self._path) class IgnoreFilterStack(object): """Check for ignore status in multiple filters.""" def __init__(self, filters): self._filters = filters def is_ignored(self, path): """Check whether a path is explicitly included or excluded in ignores. :param path: Path to check :return: None if the file is not mentioned, True if it is included, False if it is explicitly excluded. """ status = None for filter in self._filters: status = filter.is_ignored(path) if status is not None: return status return status def default_user_ignore_filter_path(config): """Return default user ignore filter path. :param config: A Config object :return: Path to a global ignore file """ try: return config.get((b'core', ), b'excludesFile') except KeyError: pass xdg_config_home = os.environ.get( "XDG_CONFIG_HOME", os.path.expanduser("~/.config/"), ) return os.path.join(xdg_config_home, 'git', 'ignore') class IgnoreFilterManager(object): """Ignore file manager.""" def __init__(self, top_path, global_filters, ignorecase): self._path_filters = {} self._top_path = top_path self._global_filters = global_filters self._ignorecase = ignorecase def __repr__(self): return "%s(%s, %r, %r)" % ( type(self).__name__, self._top_path, self._global_filters, self._ignorecase) def _load_path(self, path): try: return self._path_filters[path] except KeyError: pass p = os.path.join(self._top_path, path, '.gitignore') try: self._path_filters[path] = IgnoreFilter.from_path( p, self._ignorecase) except IOError: self._path_filters[path] = None return self._path_filters[path] def find_matching(self, path): """Find matching patterns for path. Stops after the first ignore file with matches. :param path: Path to check :return: Iterator over Pattern instances """ if os.path.isabs(path): raise ValueError('%s is an absolute path' % path) filters = [(0, f) for f in self._global_filters] if os.path.sep != '/': path = path.replace(os.path.sep, '/') parts = path.split('/') for i in range(len(parts)+1): dirname = '/'.join(parts[:i]) for s, f in filters: relpath = '/'.join(parts[s:i]) if i < len(parts): # Paths leading up to the final part are all directories, # so need a trailing slash. relpath += '/' matches = list(f.find_matching(relpath)) if matches: return iter(matches) ignore_filter = self._load_path(dirname) if ignore_filter is not None: filters.insert(0, (i, ignore_filter)) return iter([]) def is_ignored(self, path): """Check whether a path is explicitly included or excluded in ignores. :param path: Path to check :return: None if the file is not mentioned, True if it is included, False if it is explicitly excluded. """ matches = list(self.find_matching(path)) if matches: return matches[-1].is_exclude return None @classmethod def from_repo(cls, repo): """Create a IgnoreFilterManager from a repository. :param repo: Repository object :return: A `IgnoreFilterManager` object """ global_filters = [] for p in [ os.path.join(repo.controldir(), 'info', 'exclude'), default_user_ignore_filter_path(repo.get_config_stack())]: try: global_filters.append(IgnoreFilter.from_path(p)) except IOError: pass config = repo.get_config_stack() ignorecase = config.get_boolean((b'core'), (b'ignorecase'), False) return cls(repo.path, global_filters, ignorecase) diff --git a/dulwich/line_ending.py b/dulwich/line_ending.py new file mode 100644 index 00000000..c2a79f4f --- /dev/null +++ b/dulwich/line_ending.py @@ -0,0 +1,181 @@ +# line_ending.py -- Line ending conversion functions +# Copyright (C) 2018-2018 Boris Feld +# +# Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU +# General Public License as public by the Free Software Foundation; version 2.0 +# or (at your option) any later version. You can redistribute it and/or +# modify it under the terms of either of these two licenses. +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# +# You should have received a copy of the licenses; if not, see +# for a copy of the GNU General Public License +# and for a copy of the Apache +# License, Version 2.0. +# +""" All line-ending related functions, from conversions to config processing + +Line-ending normalization is a complex beast. Here is some notes and details +about how it seems to work. + +The normalization is a two-fold process that happens at two moments: + +- When reading a file from the index and to the working directory. For example + when doing a `git clone` or `git checkout` call. We call this process the + read filter in this module. +- When writing a file to the index from the working directory. For example + when doing a `git add` call. We call this process the write filter in this + module. + +One thing to know is that Git does line-ending normalization only on text +files. How does Git know that a file is text? We can either mark a file as a +text file, a binary file or ask Git to automatically decides. Git has an +heuristic to detect if a file is a text file or a binary file. It seems based +on the percentage of non-printable characters in files. + +The code for this heuristic is here: +https://git.kernel.org/pub/scm/git/git.git/tree/convert.c#n46 + +Dulwich have an implementation with a slightly different heuristic, the +`is_binary` function in `dulwich.patch`. + +The binary detection heuristic implementation is close to the one in JGit: +https://github.com/eclipse/jgit/blob/f6873ffe522bbc3536969a3a3546bf9a819b92bf/org.eclipse.jgit/src/org/eclipse/jgit/diff/RawText.java#L300 + +There is multiple variables that impact the normalization. + +First, a repository can contains a `.gitattributes` file (or more than one...) +that can further customize the operation on some file patterns, for example: + + *.txt text + +Force all `.txt` files to be treated as text files and to have their lines +endings normalized. + + *.jpg -text + +Force all `.jpg` files to be treated as binary files and to not have their +lines endings converted. + + *.vcproj text eol=crlf + +Force all `.vcproj` files to be treated as text files and to have their lines +endings converted into `CRLF` in working directory no matter the native EOL of +the platform. + + *.sh text eol=lf + +Force all `.sh` files to be treated as text files and to have their lines +endings converted into `LF` in working directory no matter the native EOL of +the platform. + +If the `eol` attribute is not defined, Git uses the `core.eol` configuration +value described later. + + * text=auto + +Force all files to be scanned by the text file heuristic detection and to have +their line endings normalized in case they are detected as text files. + +Git also have a obsolete attribute named `crlf` that can be translated to the +corresponding text attribute value. + +Then there are some configuration option (that can be defined at the +repository or user level): + +- core.autocrlf +- core.eol + +`core.autocrlf` is taken into account for all files that doesn't have a `text` +attribute defined in `.gitattributes`; it takes three possible values: + + - `true`: This forces all files on the working directory to have CRLF + line-endings in the working directory and convert line-endings to LF + when writing to the index. When autocrlf is set to true, eol value is + ignored. + - `input`: Quite similar to the `true` value but only force the write + filter, ie line-ending of new files added to the index will get their + line-endings converted to LF. + - `false` (default): No normalization is done. + +`core.eol` is the top-level configuration to define the line-ending to use +when applying the read_filer. It takes three possible values: + + - `lf`: When normalization is done, force line-endings to be `LF` in the + working directory. + - `crlf`: When normalization is done, force line-endings to be `CRLF` in + the working directory. + - `native` (default): When normalization is done, force line-endings to be + the platform's native line ending. + +One thing to remember is when line-ending normalization is done on a file, Git +always normalize line-ending to `LF` when writing to the index. + +There are sources that seems to indicate that Git won't do line-ending +normalization when a file contains mixed line-endings. I think this logic +might be in text / binary detection heuristic but couldn't find it yet. + +Sources: +- https://git-scm.com/docs/git-config#git-config-coreeol +- https://git-scm.com/docs/git-config#git-config-coreautocrlf +- https://git-scm.com/docs/gitattributes#_checking_out_and_checking_in +- https://adaptivepatchwork.com/2012/03/01/mind-the-end-of-your-line/ +""" + +CRLF = b"\r\n" +LF = b"\n" + + +def convert_crlf_to_lf(text_hunk): + """Convert CRLF in text hunk into LF + + :param text_hunk: A bytes string representing a text hunk + :return: The text hunk with the same type, with CRLF replaced into LF + """ + return text_hunk.replace(CRLF, LF) + + +def convert_lf_to_crlf(text_hunk): + """Convert LF in text hunk into CRLF + + :param text_hunk: A bytes string representing a text hunk + :return: The text hunk with the same type, with LF replaced into CRLF + """ + # TODO find a more efficient way of doing it + intermediary = text_hunk.replace(CRLF, LF) + return intermediary.replace(LF, CRLF) + + +def get_checkout_filter_autocrlf(core_autocrlf): + """ Returns the correct checkout filter base on autocrlf value + + :param core_autocrlf: The bytes configuration value of core.autocrlf. + Valid values are: b'true', b'false' or b'input'. + :return: Either None if no filter has to be applied or a function + accepting a single argument, a binary text hunk + """ + + if core_autocrlf == b"true": + return convert_lf_to_crlf + + return None + + +def get_checkin_filter_autocrlf(core_autocrlf): + """ Returns the correct checkin filter base on autocrlf value + + :param core_autocrlf: The bytes configuration value of core.autocrlf. + Valid values are: b'true', b'false' or b'input'. + :return: Either None if no filter has to be applied or a function + accepting a single argument, a binary text hunk + """ + + if core_autocrlf == b"true" or core_autocrlf == b"input": + return convert_crlf_to_lf + + # Checking filter should never be `convert_lf_to_crlf` + return None diff --git a/dulwich/object_store.py b/dulwich/object_store.py index 0da3b52c..8534d621 100644 --- a/dulwich/object_store.py +++ b/dulwich/object_store.py @@ -1,1317 +1,1334 @@ # object_store.py -- Object store for git objects # Copyright (C) 2008-2013 Jelmer Vernooij # and others # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """Git object store interfaces and implementation.""" from io import BytesIO import errno from itertools import chain import os import stat import sys import tempfile import time from dulwich.diff_tree import ( tree_changes, walk_trees, ) from dulwich.errors import ( NotTreeError, ) from dulwich.file import GitFile from dulwich.objects import ( Commit, ShaFile, Tag, Tree, ZERO_SHA, hex_to_sha, sha_to_hex, hex_to_filename, S_ISGITLINK, object_class, ) from dulwich.pack import ( Pack, PackData, PackInflater, iter_sha1, pack_objects_to_data, write_pack_header, write_pack_index_v2, write_pack_data, write_pack_object, compute_file_sha, PackIndexer, PackStreamCopier, ) +from dulwich.refs import ANNOTATED_TAG_SUFFIX INFODIR = 'info' PACKDIR = 'pack' class BaseObjectStore(object): """Object store interface.""" def determine_wants_all(self, refs): return [sha for (ref, sha) in refs.items() - if sha not in self and not ref.endswith(b"^{}") and + if sha not in self and + not ref.endswith(ANNOTATED_TAG_SUFFIX) and not sha == ZERO_SHA] def iter_shas(self, shas): """Iterate over the objects for the specified shas. :param shas: Iterable object with SHAs :return: Object iterator """ return ObjectStoreIterator(self, shas) def contains_loose(self, sha): """Check if a particular object is present by SHA1 and is loose.""" raise NotImplementedError(self.contains_loose) def contains_packed(self, sha): """Check if a particular object is present by SHA1 and is packed.""" raise NotImplementedError(self.contains_packed) def __contains__(self, sha): """Check if a particular object is present by SHA1. This method makes no distinction between loose and packed objects. """ return self.contains_packed(sha) or self.contains_loose(sha) @property def packs(self): """Iterable of pack objects.""" raise NotImplementedError def get_raw(self, name): """Obtain the raw text for an object. :param name: sha for the object. :return: tuple with numeric type and object contents. """ raise NotImplementedError(self.get_raw) def __getitem__(self, sha): """Obtain an object by SHA1.""" type_num, uncomp = self.get_raw(sha) return ShaFile.from_raw_string(type_num, uncomp, sha=sha) def __iter__(self): """Iterate over the SHAs that are present in this store.""" raise NotImplementedError(self.__iter__) def add_object(self, obj): """Add a single object to this object store. """ raise NotImplementedError(self.add_object) def add_objects(self, objects, progress=None): """Add a set of objects to this object store. :param objects: Iterable over a list of (object, path) tuples """ raise NotImplementedError(self.add_objects) def add_pack_data(self, count, pack_data, progress=None): """Add pack data to this object store. :param num_items: Number of items to add :param pack_data: Iterator over pack data tuples """ if count == 0: # Don't bother writing an empty pack file return f, commit, abort = self.add_pack() try: write_pack_data(f, count, pack_data, progress) except BaseException: abort() raise else: return commit() def tree_changes(self, source, target, want_unchanged=False, include_trees=False, change_type_same=False): """Find the differences between the contents of two trees :param source: SHA1 of the source tree :param target: SHA1 of the target tree :param want_unchanged: Whether unchanged files should be reported :param include_trees: Whether to include trees :param change_type_same: Whether to report files changing type in the same entry. :return: Iterator over tuples with (oldpath, newpath), (oldmode, newmode), (oldsha, newsha) """ for change in tree_changes(self, source, target, want_unchanged=want_unchanged, include_trees=include_trees, change_type_same=change_type_same): yield ((change.old.path, change.new.path), (change.old.mode, change.new.mode), (change.old.sha, change.new.sha)) def iter_tree_contents(self, tree_id, include_trees=False): """Iterate the contents of a tree and all subtrees. Iteration is depth-first pre-order, as in e.g. os.walk. :param tree_id: SHA1 of the tree. :param include_trees: If True, include tree objects in the iteration. :return: Iterator over TreeEntry namedtuples for all the objects in a tree. """ for entry, _ in walk_trees(self, tree_id, None): if ((entry.mode is not None and not stat.S_ISDIR(entry.mode)) or include_trees): yield entry def find_missing_objects(self, haves, wants, progress=None, get_tagged=None, - get_parents=lambda commit: commit.parents): + get_parents=lambda commit: commit.parents, + depth=None): """Find the missing objects required for a set of revisions. :param haves: Iterable over SHAs already in common. :param wants: Iterable over SHAs of objects to fetch. :param progress: Simple progress function that will be called with updated progress strings. :param get_tagged: Function that returns a dict of pointed-to sha -> tag sha for including tags. :param get_parents: Optional function for getting the parents of a commit. :return: Iterator over (sha, path) pairs. """ finder = MissingObjectFinder(self, haves, wants, progress, get_tagged, get_parents=get_parents) return iter(finder.next, None) def find_common_revisions(self, graphwalker): """Find which revisions this store has in common using graphwalker. :param graphwalker: A graphwalker object. :return: List of SHAs that are in common """ haves = [] sha = next(graphwalker) while sha: if sha in self: haves.append(sha) graphwalker.ack(sha) sha = next(graphwalker) return haves def generate_pack_contents(self, have, want, progress=None): """Iterate over the contents of a pack file. :param have: List of SHA1s of objects that should not be sent :param want: List of SHA1s of objects that should be sent :param progress: Optional progress reporting method """ return self.iter_shas(self.find_missing_objects(have, want, progress)) def generate_pack_data(self, have, want, progress=None, ofs_delta=True): """Generate pack data objects for a set of wants/haves. :param have: List of SHA1s of objects that should not be sent :param want: List of SHA1s of objects that should be sent :param ofs_delta: Whether OFS deltas can be included :param progress: Optional progress reporting method """ # TODO(jelmer): More efficient implementation return pack_objects_to_data( self.generate_pack_contents(have, want, progress)) def peel_sha(self, sha): """Peel all tags from a SHA. :param sha: The object SHA to peel. :return: The fully-peeled SHA1 of a tag object, after peeling all intermediate tags; if the original ref does not point to a tag, this will equal the original SHA1. """ obj = self[sha] obj_class = object_class(obj.type_name) while obj_class is Tag: obj_class, sha = obj.object obj = self[sha] return obj def _collect_ancestors(self, heads, common=set(), get_parents=lambda commit: commit.parents): """Collect all ancestors of heads up to (excluding) those in common. :param heads: commits to start from :param common: commits to end at, or empty set to walk repository completely :param get_parents: Optional function for getting the parents of a commit. :return: a tuple (A, B) where A - all commits reachable from heads but not present in common, B - common (shared) elements that are directly reachable from heads """ bases = set() commits = set() queue = [] queue.extend(heads) while queue: e = queue.pop(0) if e in common: bases.add(e) elif e not in commits: commits.add(e) cmt = self[e] queue.extend(get_parents(cmt)) return (commits, bases) def close(self): """Close any files opened by this object store.""" # Default implementation is a NO-OP class PackBasedObjectStore(BaseObjectStore): def __init__(self): self._pack_cache = {} @property def alternates(self): return [] def contains_packed(self, sha): """Check if a particular object is present by SHA1 and is packed. This does not check alternates. """ for pack in self.packs: if sha in pack: return True return False def __contains__(self, sha): """Check if a particular object is present by SHA1. This method makes no distinction between loose and packed objects. """ if self.contains_packed(sha) or self.contains_loose(sha): return True for alternate in self.alternates: if sha in alternate: return True return False def _pack_cache_stale(self): """Check whether the pack cache is stale.""" raise NotImplementedError(self._pack_cache_stale) def _add_known_pack(self, base_name, pack): """Add a newly appeared pack to the cache by path. """ prev_pack = self._pack_cache.get(base_name) if prev_pack is not pack: self._pack_cache[base_name] = pack if prev_pack: prev_pack.close() def _flush_pack_cache(self): pack_cache = self._pack_cache self._pack_cache = {} while pack_cache: (name, pack) = pack_cache.popitem() pack.close() def close(self): self._flush_pack_cache() @property def packs(self): """List with pack objects.""" if self._pack_cache is None or self._pack_cache_stale(): self._update_pack_cache() return self._pack_cache.values() def _iter_alternate_objects(self): """Iterate over the SHAs of all the objects in alternate stores.""" for alternate in self.alternates: for alternate_object in alternate: yield alternate_object def _iter_loose_objects(self): """Iterate over the SHAs of all loose objects.""" raise NotImplementedError(self._iter_loose_objects) def _get_loose_object(self, sha): raise NotImplementedError(self._get_loose_object) def _remove_loose_object(self, sha): raise NotImplementedError(self._remove_loose_object) def _remove_pack(self, name): raise NotImplementedError(self._remove_pack) def pack_loose_objects(self): """Pack loose objects. :return: Number of objects packed """ objects = set() for sha in self._iter_loose_objects(): objects.add((self._get_loose_object(sha), None)) self.add_objects(list(objects)) for obj, path in objects: self._remove_loose_object(obj.id) return len(objects) def repack(self): """Repack the packs in this repository. Note that this implementation is fairly naive and currently keeps all objects in memory while it repacks. """ loose_objects = set() for sha in self._iter_loose_objects(): loose_objects.add(self._get_loose_object(sha)) objects = {(obj, None) for obj in loose_objects} old_packs = {p.name(): p for p in self.packs} for name, pack in old_packs.items(): objects.update((obj, None) for obj in pack.iterobjects()) self._flush_pack_cache() # The name of the consolidated pack might match the name of a # pre-existing pack. Take care not to remove the newly created # consolidated pack. consolidated = self.add_objects(objects) old_packs.pop(consolidated.name(), None) for obj in loose_objects: self._remove_loose_object(obj.id) for name, pack in old_packs.items(): self._remove_pack(pack) self._update_pack_cache() return len(objects) def __iter__(self): """Iterate over the SHAs that are present in this store.""" iterables = (list(self.packs) + [self._iter_loose_objects()] + [self._iter_alternate_objects()]) return chain(*iterables) def contains_loose(self, sha): """Check if a particular object is present by SHA1 and is loose. This does not check alternates. """ return self._get_loose_object(sha) is not None def get_raw(self, name): """Obtain the raw fulltext for an object. :param name: sha for the object. :return: tuple with numeric type and object contents. """ if len(name) == 40: sha = hex_to_sha(name) hexsha = name elif len(name) == 20: sha = name hexsha = None else: raise AssertionError("Invalid object name %r" % name) for pack in self.packs: try: return pack.get_raw(sha) except KeyError: pass if hexsha is None: hexsha = sha_to_hex(name) ret = self._get_loose_object(hexsha) if ret is not None: return ret.type_num, ret.as_raw_string() for alternate in self.alternates: try: return alternate.get_raw(hexsha) except KeyError: pass raise KeyError(hexsha) def add_objects(self, objects, progress=None): """Add a set of objects to this object store. :param objects: Iterable over (object, path) tuples, should support __len__. :return: Pack object of the objects written. """ return self.add_pack_data( *pack_objects_to_data(objects), progress=progress) class DiskObjectStore(PackBasedObjectStore): """Git-style object store that exists on disk.""" def __init__(self, path): """Open an object store. :param path: Path of the object store. """ super(DiskObjectStore, self).__init__() self.path = path self.pack_dir = os.path.join(self.path, PACKDIR) self._pack_cache_time = 0 self._pack_cache = {} self._alternates = None def __repr__(self): return "<%s(%r)>" % (self.__class__.__name__, self.path) @property def alternates(self): if self._alternates is not None: return self._alternates self._alternates = [] for path in self._read_alternate_paths(): self._alternates.append(DiskObjectStore(path)) return self._alternates def _read_alternate_paths(self): try: f = GitFile(os.path.join(self.path, INFODIR, "alternates"), 'rb') except (OSError, IOError) as e: if e.errno == errno.ENOENT: return raise with f: for line in f.readlines(): line = line.rstrip(b"\n") if line[0] == b"#": continue if os.path.isabs(line): yield line.decode(sys.getfilesystemencoding()) else: yield os.path.join(self.path, line).decode( sys.getfilesystemencoding()) def add_alternate_path(self, path): """Add an alternate path to this object store. """ try: os.mkdir(os.path.join(self.path, INFODIR)) except OSError as e: if e.errno != errno.EEXIST: raise alternates_path = os.path.join(self.path, INFODIR, "alternates") with GitFile(alternates_path, 'wb') as f: try: orig_f = open(alternates_path, 'rb') except (OSError, IOError) as e: if e.errno != errno.ENOENT: raise else: with orig_f: f.write(orig_f.read()) f.write(path.encode(sys.getfilesystemencoding()) + b"\n") if not os.path.isabs(path): path = os.path.join(self.path, path) self.alternates.append(DiskObjectStore(path)) def _update_pack_cache(self): try: pack_dir_contents = os.listdir(self.pack_dir) except OSError as e: if e.errno == errno.ENOENT: self._pack_cache_time = 0 self.close() return raise self._pack_cache_time = max( os.stat(self.pack_dir).st_mtime, time.time()) pack_files = set() for name in pack_dir_contents: if name.startswith("pack-") and name.endswith(".pack"): # verify that idx exists first (otherwise the pack was not yet # fully written) idx_name = os.path.splitext(name)[0] + ".idx" if idx_name in pack_dir_contents: pack_name = name[:-len(".pack")] pack_files.add(pack_name) # Open newly appeared pack files for f in pack_files: if f not in self._pack_cache: self._pack_cache[f] = Pack(os.path.join(self.pack_dir, f)) # Remove disappeared pack files for f in set(self._pack_cache) - pack_files: self._pack_cache.pop(f).close() def _pack_cache_stale(self): try: return os.stat(self.pack_dir).st_mtime >= self._pack_cache_time except OSError as e: if e.errno == errno.ENOENT: return True raise def _get_shafile_path(self, sha): # Check from object dir return hex_to_filename(self.path, sha) def _iter_loose_objects(self): for base in os.listdir(self.path): if len(base) != 2: continue for rest in os.listdir(os.path.join(self.path, base)): yield (base+rest).encode(sys.getfilesystemencoding()) def _get_loose_object(self, sha): path = self._get_shafile_path(sha) try: return ShaFile.from_path(path) except (OSError, IOError) as e: if e.errno == errno.ENOENT: return None raise def _remove_loose_object(self, sha): os.remove(self._get_shafile_path(sha)) def _remove_pack(self, pack): os.remove(pack.data.path) os.remove(pack.index.path) def _get_pack_basepath(self, entries): suffix = iter_sha1(entry[0] for entry in entries) # TODO: Handle self.pack_dir being bytes suffix = suffix.decode('ascii') return os.path.join(self.pack_dir, "pack-" + suffix) def _complete_thin_pack(self, f, path, copier, indexer): """Move a specific file containing a pack into the pack directory. :note: The file should be on the same file system as the packs directory. :param f: Open file object for the pack. :param path: Path to the pack file. :param copier: A PackStreamCopier to use for writing pack data. :param indexer: A PackIndexer for indexing the pack. """ entries = list(indexer) # Update the header with the new number of objects. f.seek(0) write_pack_header(f, len(entries) + len(indexer.ext_refs())) # Must flush before reading (http://bugs.python.org/issue3207) f.flush() # Rescan the rest of the pack, computing the SHA with the new header. new_sha = compute_file_sha(f, end_ofs=-20) # Must reposition before writing (http://bugs.python.org/issue3207) f.seek(0, os.SEEK_CUR) # Complete the pack. for ext_sha in indexer.ext_refs(): assert len(ext_sha) == 20 type_num, data = self.get_raw(ext_sha) offset = f.tell() crc32 = write_pack_object(f, type_num, data, sha=new_sha) entries.append((ext_sha, offset, crc32)) pack_sha = new_sha.digest() f.write(pack_sha) f.close() # Move the pack in. entries.sort() pack_base_name = self._get_pack_basepath(entries) target_pack = pack_base_name + '.pack' if sys.platform == 'win32': # Windows might have the target pack file lingering. Attempt # removal, silently passing if the target does not exist. try: os.remove(target_pack) except (IOError, OSError) as e: if e.errno != errno.ENOENT: raise os.rename(path, target_pack) # Write the index. index_file = GitFile(pack_base_name + '.idx', 'wb') try: write_pack_index_v2(index_file, entries, pack_sha) index_file.close() finally: index_file.abort() # Add the pack to the store and return it. final_pack = Pack(pack_base_name) final_pack.check_length_and_checksum() self._add_known_pack(pack_base_name, final_pack) return final_pack def add_thin_pack(self, read_all, read_some): """Add a new thin pack to this object store. Thin packs are packs that contain deltas with parents that exist outside the pack. They should never be placed in the object store directly, and always indexed and completed as they are copied. :param read_all: Read function that blocks until the number of requested bytes are read. :param read_some: Read function that returns at least one byte, but may not return the number of bytes requested. :return: A Pack object pointing at the now-completed thin pack in the objects/pack directory. """ fd, path = tempfile.mkstemp(dir=self.path, prefix='tmp_pack_') with os.fdopen(fd, 'w+b') as f: indexer = PackIndexer(f, resolve_ext_ref=self.get_raw) copier = PackStreamCopier(read_all, read_some, f, delta_iter=indexer) copier.verify() return self._complete_thin_pack(f, path, copier, indexer) def move_in_pack(self, path): """Move a specific file containing a pack into the pack directory. :note: The file should be on the same file system as the packs directory. :param path: Path to the pack file. """ with PackData(path) as p: entries = p.sorted_entries() basename = self._get_pack_basepath(entries) with GitFile(basename+".idx", "wb") as f: write_pack_index_v2(f, entries, p.get_stored_checksum()) if self._pack_cache is None or self._pack_cache_stale(): self._update_pack_cache() try: return self._pack_cache[basename] except KeyError: pass target_pack = basename + '.pack' if sys.platform == 'win32': # Windows might have the target pack file lingering. Attempt # removal, silently passing if the target does not exist. try: os.remove(target_pack) except (IOError, OSError) as e: if e.errno != errno.ENOENT: raise os.rename(path, target_pack) final_pack = Pack(basename) self._add_known_pack(basename, final_pack) return final_pack def add_pack(self): """Add a new pack to this object store. :return: Fileobject to write to, a commit function to call when the pack is finished and an abort function. """ fd, path = tempfile.mkstemp(dir=self.pack_dir, suffix=".pack") f = os.fdopen(fd, 'wb') def commit(): f.flush() os.fsync(fd) f.close() if os.path.getsize(path) > 0: return self.move_in_pack(path) else: os.remove(path) return None def abort(): f.close() os.remove(path) return f, commit, abort def add_object(self, obj): """Add a single object to this object store. :param obj: Object to add """ path = self._get_shafile_path(obj.id) dir = os.path.dirname(path) try: os.mkdir(dir) except OSError as e: if e.errno != errno.EEXIST: raise if os.path.exists(path): return # Already there, no need to write again with GitFile(path, 'wb') as f: f.write(obj.as_legacy_object()) @classmethod def init(cls, path): try: os.mkdir(path) except OSError as e: if e.errno != errno.EEXIST: raise os.mkdir(os.path.join(path, "info")) os.mkdir(os.path.join(path, PACKDIR)) return cls(path) class MemoryObjectStore(BaseObjectStore): """Object store that keeps all objects in memory.""" def __init__(self): super(MemoryObjectStore, self).__init__() self._data = {} def _to_hexsha(self, sha): if len(sha) == 40: return sha elif len(sha) == 20: return sha_to_hex(sha) else: raise ValueError("Invalid sha %r" % (sha,)) def contains_loose(self, sha): """Check if a particular object is present by SHA1 and is loose.""" return self._to_hexsha(sha) in self._data def contains_packed(self, sha): """Check if a particular object is present by SHA1 and is packed.""" return False def __iter__(self): """Iterate over the SHAs that are present in this store.""" return iter(self._data.keys()) @property def packs(self): """List with pack objects.""" return [] def get_raw(self, name): """Obtain the raw text for an object. :param name: sha for the object. :return: tuple with numeric type and object contents. """ obj = self[self._to_hexsha(name)] return obj.type_num, obj.as_raw_string() def __getitem__(self, name): return self._data[self._to_hexsha(name)].copy() def __delitem__(self, name): """Delete an object from this store, for testing only.""" del self._data[self._to_hexsha(name)] def add_object(self, obj): """Add a single object to this object store. """ self._data[obj.id] = obj.copy() def add_objects(self, objects, progress=None): """Add a set of objects to this object store. :param objects: Iterable over a list of (object, path) tuples """ for obj, path in objects: self.add_object(obj) def add_pack(self): """Add a new pack to this object store. Because this object store doesn't support packs, we extract and add the individual objects. :return: Fileobject to write to and a commit function to call when the pack is finished. """ f = BytesIO() def commit(): p = PackData.from_file(BytesIO(f.getvalue()), f.tell()) f.close() for obj in PackInflater.for_pack_data(p, self.get_raw): self.add_object(obj) def abort(): pass return f, commit, abort def _complete_thin_pack(self, f, indexer): """Complete a thin pack by adding external references. :param f: Open file object for the pack. :param indexer: A PackIndexer for indexing the pack. """ entries = list(indexer) # Update the header with the new number of objects. f.seek(0) write_pack_header(f, len(entries) + len(indexer.ext_refs())) # Rescan the rest of the pack, computing the SHA with the new header. new_sha = compute_file_sha(f, end_ofs=-20) # Complete the pack. for ext_sha in indexer.ext_refs(): assert len(ext_sha) == 20 type_num, data = self.get_raw(ext_sha) write_pack_object(f, type_num, data, sha=new_sha) pack_sha = new_sha.digest() f.write(pack_sha) def add_thin_pack(self, read_all, read_some): """Add a new thin pack to this object store. Thin packs are packs that contain deltas with parents that exist outside the pack. Because this object store doesn't support packs, we extract and add the individual objects. :param read_all: Read function that blocks until the number of requested bytes are read. :param read_some: Read function that returns at least one byte, but may not return the number of bytes requested. """ f, commit, abort = self.add_pack() try: indexer = PackIndexer(f, resolve_ext_ref=self.get_raw) copier = PackStreamCopier(read_all, read_some, f, delta_iter=indexer) copier.verify() self._complete_thin_pack(f, indexer) except BaseException: abort() raise else: commit() class ObjectIterator(object): """Interface for iterating over objects.""" def iterobjects(self): raise NotImplementedError(self.iterobjects) class ObjectStoreIterator(ObjectIterator): """ObjectIterator that works on top of an ObjectStore.""" def __init__(self, store, sha_iter): """Create a new ObjectIterator. :param store: Object store to retrieve from :param sha_iter: Iterator over (sha, path) tuples """ self.store = store self.sha_iter = sha_iter self._shas = [] def __iter__(self): """Yield tuple with next object and path.""" for sha, path in self.itershas(): yield self.store[sha], path def iterobjects(self): """Iterate over just the objects.""" for o, path in self: yield o def itershas(self): """Iterate over the SHAs.""" for sha in self._shas: yield sha for sha in self.sha_iter: self._shas.append(sha) yield sha def __contains__(self, needle): """Check if an object is present. :note: This checks if the object is present in the underlying object store, not if it would be yielded by the iterator. :param needle: SHA1 of the object to check for """ return needle in self.store def __getitem__(self, key): """Find an object by SHA1. :note: This retrieves the object from the underlying object store. It will also succeed if the object would not be returned by the iterator. """ return self.store[key] def __len__(self): """Return the number of objects.""" return len(list(self.itershas())) def empty(self): iter = self.itershas() try: iter() except StopIteration: return True else: return False def __bool__(self): """Indicate whether this object has contents.""" return not self.empty() def tree_lookup_path(lookup_obj, root_sha, path): """Look up an object in a Git tree. :param lookup_obj: Callback for retrieving object by SHA1 :param root_sha: SHA1 of the root tree :param path: Path to lookup :return: A tuple of (mode, SHA) of the resulting path. """ tree = lookup_obj(root_sha) if not isinstance(tree, Tree): raise NotTreeError(root_sha) return tree.lookup_path(lookup_obj, path) def _collect_filetree_revs(obj_store, tree_sha, kset): """Collect SHA1s of files and directories for specified tree. :param obj_store: Object store to get objects by SHA from :param tree_sha: tree reference to walk :param kset: set to fill with references to files and directories """ filetree = obj_store[tree_sha] for name, mode, sha in filetree.iteritems(): if not S_ISGITLINK(mode) and sha not in kset: kset.add(sha) if stat.S_ISDIR(mode): _collect_filetree_revs(obj_store, sha, kset) def _split_commits_and_tags(obj_store, lst, ignore_unknown=False): """Split object id list into three lists with commit, tag, and other SHAs. Commits referenced by tags are included into commits list as well. Only SHA1s known in this repository will get through, and unless ignore_unknown argument is True, KeyError is thrown for SHA1 missing in the repository :param obj_store: Object store to get objects by SHA1 from :param lst: Collection of commit and tag SHAs :param ignore_unknown: True to skip SHA1 missing in the repository silently. :return: A tuple of (commits, tags, others) SHA1s """ commits = set() tags = set() others = set() for e in lst: try: o = obj_store[e] except KeyError: if not ignore_unknown: raise else: if isinstance(o, Commit): commits.add(e) elif isinstance(o, Tag): tags.add(e) tagged = o.object[1] c, t, o = _split_commits_and_tags( obj_store, [tagged], ignore_unknown=ignore_unknown) commits |= c tags |= t others |= o else: others.add(e) return (commits, tags, others) class MissingObjectFinder(object): """Find the objects missing from another object store. :param object_store: Object store containing at least all objects to be sent :param haves: SHA1s of commits not to send (already present in target) :param wants: SHA1s of commits to send :param progress: Optional function to report progress to. :param get_tagged: Function that returns a dict of pointed-to sha -> tag sha for including tags. :param get_parents: Optional function for getting the parents of a commit. :param tagged: dict of pointed-to sha -> tag sha for including tags """ def __init__(self, object_store, haves, wants, progress=None, get_tagged=None, get_parents=lambda commit: commit.parents): self.object_store = object_store self._get_parents = get_parents # process Commits and Tags differently # Note, while haves may list commits/tags not available locally, # and such SHAs would get filtered out by _split_commits_and_tags, # wants shall list only known SHAs, and otherwise # _split_commits_and_tags fails with KeyError have_commits, have_tags, have_others = ( _split_commits_and_tags(object_store, haves, True)) want_commits, want_tags, want_others = ( _split_commits_and_tags(object_store, wants, False)) # all_ancestors is a set of commits that shall not be sent # (complete repository up to 'haves') all_ancestors = object_store._collect_ancestors( have_commits, get_parents=self._get_parents)[0] # all_missing - complete set of commits between haves and wants # common - commits from all_ancestors we hit into while # traversing parent hierarchy of wants missing_commits, common_commits = object_store._collect_ancestors( want_commits, all_ancestors, get_parents=self._get_parents) self.sha_done = set() # Now, fill sha_done with commits and revisions of # files and directories known to be both locally # and on target. Thus these commits and files # won't get selected for fetch for h in common_commits: self.sha_done.add(h) cmt = object_store[h] _collect_filetree_revs(object_store, cmt.tree, self.sha_done) # record tags we have as visited, too for t in have_tags: self.sha_done.add(t) missing_tags = want_tags.difference(have_tags) missing_others = want_others.difference(have_others) # in fact, what we 'want' is commits, tags, and others # we've found missing wants = missing_commits.union(missing_tags) wants = wants.union(missing_others) self.objects_to_send = set([(w, None, False) for w in wants]) if progress is None: self.progress = lambda x: None else: self.progress = progress self._tagged = get_tagged and get_tagged() or {} def add_todo(self, entries): self.objects_to_send.update([e for e in entries if not e[0] in self.sha_done]) def next(self): while True: if not self.objects_to_send: return None (sha, name, leaf) = self.objects_to_send.pop() if sha not in self.sha_done: break if not leaf: o = self.object_store[sha] if isinstance(o, Commit): self.add_todo([(o.tree, "", False)]) elif isinstance(o, Tree): self.add_todo([(s, n, not stat.S_ISDIR(m)) for n, m, s in o.iteritems() if not S_ISGITLINK(m)]) elif isinstance(o, Tag): self.add_todo([(o.object[1], None, False)]) if sha in self._tagged: self.add_todo([(self._tagged[sha], None, True)]) self.sha_done.add(sha) self.progress(("counting objects: %d\r" % len(self.sha_done)).encode('ascii')) return (sha, name) __next__ = next class ObjectStoreGraphWalker(object): """Graph walker that finds what commits are missing from an object store. :ivar heads: Revisions without descendants in the local repo :ivar get_parents: Function to retrieve parents in the local repo """ - def __init__(self, local_heads, get_parents): + def __init__(self, local_heads, get_parents, shallow=None): """Create a new instance. :param local_heads: Heads to start search with :param get_parents: Function for finding the parents of a SHA1. """ self.heads = set(local_heads) self.get_parents = get_parents self.parents = {} + if shallow is None: + shallow = set() + self.shallow = shallow def ack(self, sha): """Ack that a revision and its ancestors are present in the source.""" if len(sha) != 40: raise ValueError("unexpected sha %r received" % sha) ancestors = set([sha]) # stop if we run out of heads to remove while self.heads: for a in ancestors: if a in self.heads: self.heads.remove(a) # collect all ancestors new_ancestors = set() for a in ancestors: ps = self.parents.get(a) if ps is not None: new_ancestors.update(ps) self.parents[a] = None # no more ancestors; stop if not new_ancestors: break ancestors = new_ancestors def next(self): """Iterate over ancestors of heads in the target.""" if self.heads: ret = self.heads.pop() ps = self.get_parents(ret) self.parents[ret] = ps self.heads.update( [p for p in ps if p not in self.parents]) return ret return None __next__ = next def commit_tree_changes(object_store, tree, changes): """Commit a specified set of changes to a tree structure. This will apply a set of changes on top of an existing tree, storing new objects in object_store. changes are a list of tuples with (path, mode, object_sha). Paths can be both blobs and trees. See the mode and object sha to None deletes the path. This method works especially well if there are only a small number of changes to a big tree. For a large number of changes to a large tree, use e.g. commit_tree. :param object_store: Object store to store new objects in and retrieve old ones from. :param tree: Original tree root :param changes: changes to apply :return: New tree root object """ # TODO(jelmer): Save up the objects and add them using .add_objects # rather than with individual calls to .add_object. nested_changes = {} for (path, new_mode, new_sha) in changes: try: (dirname, subpath) = path.split(b'/', 1) except ValueError: if new_sha is None: del tree[path] else: tree[path] = (new_mode, new_sha) else: nested_changes.setdefault(dirname, []).append( (subpath, new_mode, new_sha)) for name, subchanges in nested_changes.items(): try: orig_subtree = object_store[tree[name][1]] except KeyError: orig_subtree = Tree() subtree = commit_tree_changes(object_store, orig_subtree, subchanges) if len(subtree) == 0: del tree[name] else: tree[name] = (stat.S_IFDIR, subtree.id) object_store.add_object(tree) return tree class OverlayObjectStore(BaseObjectStore): """Object store that can overlay multiple object stores.""" def __init__(self, bases, add_store=None): self.bases = bases self.add_store = add_store def add_object(self, object): if self.add_store is None: raise NotImplementedError(self.add_object) return self.add_store.add_object(object) def add_objects(self, objects, progress=None): if self.add_store is None: raise NotImplementedError(self.add_object) return self.add_store.add_objects(objects, progress) @property def packs(self): ret = [] for b in self.bases: ret.extend(b.packs) return ret def __iter__(self): done = set() for b in self.bases: for o_id in b: if o_id not in done: yield o_id done.add(o_id) def get_raw(self, sha_id): for b in self.bases: try: return b.get_raw(sha_id) except KeyError: pass else: raise KeyError(sha_id) def contains_packed(self, sha): for b in self.bases: if b.contains_packed(sha): return True else: return False def contains_loose(self, sha): for b in self.bases: if b.contains_loose(sha): return True else: return False + + +def read_packs_file(f): + """Yield the packs listed in a packs file.""" + for line in f.read().splitlines(): + if not line: + continue + (kind, name) = line.split(b" ", 1) + if kind != b"P": + continue + yield name.decode(sys.getfilesystemencoding()) diff --git a/dulwich/objects.py b/dulwich/objects.py index f79643cf..a56fdec9 100644 --- a/dulwich/objects.py +++ b/dulwich/objects.py @@ -1,1377 +1,1400 @@ # objects.py -- Access to base git objects # Copyright (C) 2007 James Westby # Copyright (C) 2008-2013 Jelmer Vernooij # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """Access to base git objects.""" import binascii from io import BytesIO from collections import namedtuple import os import posixpath import stat import sys import warnings import zlib from hashlib import sha1 from dulwich.errors import ( ChecksumMismatch, NotBlobError, NotCommitError, NotTagError, NotTreeError, ObjectFormatException, EmptyFileException, ) from dulwich.file import GitFile ZERO_SHA = b'0' * 40 # Header fields for commits _TREE_HEADER = b'tree' _PARENT_HEADER = b'parent' _AUTHOR_HEADER = b'author' _COMMITTER_HEADER = b'committer' _ENCODING_HEADER = b'encoding' _MERGETAG_HEADER = b'mergetag' _GPGSIG_HEADER = b'gpgsig' # Header fields for objects _OBJECT_HEADER = b'object' _TYPE_HEADER = b'type' _TAG_HEADER = b'tag' _TAGGER_HEADER = b'tagger' S_IFGITLINK = 0o160000 MAX_TIME = 9223372036854775807 # (2**63) - 1 - signed long int max +BEGIN_PGP_SIGNATURE = b"-----BEGIN PGP SIGNATURE-----" + def S_ISGITLINK(m): """Check if a mode indicates a submodule. :param m: Mode to check :return: a ``boolean`` """ return (stat.S_IFMT(m) == S_IFGITLINK) def _decompress(string): dcomp = zlib.decompressobj() dcomped = dcomp.decompress(string) dcomped += dcomp.flush() return dcomped def sha_to_hex(sha): """Takes a string and returns the hex of the sha within""" hexsha = binascii.hexlify(sha) assert len(hexsha) == 40, "Incorrect length of sha1 string: %d" % hexsha return hexsha def hex_to_sha(hex): """Takes a hex sha and returns a binary sha""" assert len(hex) == 40, "Incorrect length of hexsha: %s" % hex try: return binascii.unhexlify(hex) except TypeError as exc: if not isinstance(hex, bytes): raise raise ValueError(exc.args[0]) def valid_hexsha(hex): if len(hex) != 40: return False try: binascii.unhexlify(hex) except (TypeError, binascii.Error): return False else: return True def hex_to_filename(path, hex): """Takes a hex sha and returns its filename relative to the given path.""" # os.path.join accepts bytes or unicode, but all args must be of the same # type. Make sure that hex which is expected to be bytes, is the same type # as path. if getattr(path, 'encode', None) is not None: hex = hex.decode('ascii') dir = hex[:2] file = hex[2:] # Check from object dir return os.path.join(path, dir, file) def filename_to_hex(filename): """Takes an object filename and returns its corresponding hex sha.""" # grab the last (up to) two path components names = filename.rsplit(os.path.sep, 2)[-2:] errmsg = "Invalid object filename: %s" % filename assert len(names) == 2, errmsg base, rest = names assert len(base) == 2 and len(rest) == 38, errmsg hex = (base + rest).encode('ascii') hex_to_sha(hex) return hex def object_header(num_type, length): """Return an object header for the given numeric type and text length.""" return (object_class(num_type).type_name + b' ' + str(length).encode('ascii') + b'\0') def serializable_property(name, docstring=None): """A property that helps tracking whether serialization is necessary. """ def set(obj, value): setattr(obj, "_"+name, value) obj._needs_serialization = True def get(obj): return getattr(obj, "_"+name) return property(get, set, doc=docstring) def object_class(type): """Get the object class corresponding to the given type. :param type: Either a type name string or a numeric type. :return: The ShaFile subclass corresponding to the given type, or None if type is not a valid type name/number. """ return _TYPE_MAP.get(type, None) def check_hexsha(hex, error_msg): """Check if a string is a valid hex sha string. :param hex: Hex string to check :param error_msg: Error message to use in exception :raise ObjectFormatException: Raised when the string is not valid """ if not valid_hexsha(hex): raise ObjectFormatException("%s %s" % (error_msg, hex)) def check_identity(identity, error_msg): """Check if the specified identity is valid. This will raise an exception if the identity is not valid. :param identity: Identity string :param error_msg: Error message to use in exception """ email_start = identity.find(b'<') email_end = identity.find(b'>') if (email_start < 0 or email_end < 0 or email_end <= email_start or identity.find(b'<', email_start + 1) >= 0 or identity.find(b'>', email_end + 1) >= 0 or not identity.endswith(b'>')): raise ObjectFormatException(error_msg) def check_time(time_seconds): """Check if the specified time is not prone to overflow error. This will raise an exception if the time is not valid. :param time_info: author/committer/tagger info """ # Prevent overflow error if time_seconds > MAX_TIME: raise ObjectFormatException( 'Date field should not exceed %s' % MAX_TIME) def git_line(*items): """Formats items into a space separated line.""" return b' '.join(items) + b'\n' class FixedSha(object): """SHA object that behaves like hashlib's but is given a fixed value.""" __slots__ = ('_hexsha', '_sha') def __init__(self, hexsha): if getattr(hexsha, 'encode', None) is not None: hexsha = hexsha.encode('ascii') if not isinstance(hexsha, bytes): raise TypeError('Expected bytes for hexsha, got %r' % hexsha) self._hexsha = hexsha self._sha = hex_to_sha(hexsha) def digest(self): """Return the raw SHA digest.""" return self._sha def hexdigest(self): """Return the hex SHA digest.""" return self._hexsha.decode('ascii') class ShaFile(object): """A git SHA file.""" __slots__ = ('_chunked_text', '_sha', '_needs_serialization') @staticmethod def _parse_legacy_object_header(magic, f): """Parse a legacy object, creating it but not reading the file.""" bufsize = 1024 decomp = zlib.decompressobj() header = decomp.decompress(magic) start = 0 end = -1 while end < 0: extra = f.read(bufsize) header += decomp.decompress(extra) magic += extra end = header.find(b'\0', start) start = len(header) header = header[:end] type_name, size = header.split(b' ', 1) size = int(size) # sanity check obj_class = object_class(type_name) if not obj_class: raise ObjectFormatException("Not a known type: %s" % type_name) return obj_class() def _parse_legacy_object(self, map): """Parse a legacy object, setting the raw string.""" text = _decompress(map) header_end = text.find(b'\0') if header_end < 0: raise ObjectFormatException("Invalid object header, no \\0") self.set_raw_string(text[header_end+1:]) def as_legacy_object_chunks(self): """Return chunks representing the object in the experimental format. :return: List of strings """ compobj = zlib.compressobj() yield compobj.compress(self._header()) for chunk in self.as_raw_chunks(): yield compobj.compress(chunk) yield compobj.flush() def as_legacy_object(self): """Return string representing the object in the experimental format. """ return b''.join(self.as_legacy_object_chunks()) def as_raw_chunks(self): """Return chunks with serialization of the object. :return: List of strings, not necessarily one per line """ if self._needs_serialization: self._sha = None self._chunked_text = self._serialize() self._needs_serialization = False return self._chunked_text def as_raw_string(self): """Return raw string with serialization of the object. :return: String object """ return b''.join(self.as_raw_chunks()) if sys.version_info[0] >= 3: def __bytes__(self): """Return raw string serialization of this object.""" return self.as_raw_string() else: def __str__(self): """Return raw string serialization of this object.""" return self.as_raw_string() def __hash__(self): """Return unique hash for this object.""" return hash(self.id) def as_pretty_string(self): """Return a string representing this object, fit for display.""" return self.as_raw_string() def set_raw_string(self, text, sha=None): """Set the contents of this object from a serialized string.""" if not isinstance(text, bytes): raise TypeError('Expected bytes for text, got %r' % text) self.set_raw_chunks([text], sha) def set_raw_chunks(self, chunks, sha=None): """Set the contents of this object from a list of chunks.""" self._chunked_text = chunks self._deserialize(chunks) if sha is None: self._sha = None else: self._sha = FixedSha(sha) self._needs_serialization = False @staticmethod def _parse_object_header(magic, f): """Parse a new style object, creating it but not reading the file.""" num_type = (ord(magic[0:1]) >> 4) & 7 obj_class = object_class(num_type) if not obj_class: raise ObjectFormatException("Not a known type %d" % num_type) return obj_class() def _parse_object(self, map): """Parse a new style object, setting self._text.""" # skip type and size; type must have already been determined, and # we trust zlib to fail if it's otherwise corrupted byte = ord(map[0:1]) used = 1 while (byte & 0x80) != 0: byte = ord(map[used:used+1]) used += 1 raw = map[used:] self.set_raw_string(_decompress(raw)) @classmethod def _is_legacy_object(cls, magic): b0 = ord(magic[0:1]) b1 = ord(magic[1:2]) word = (b0 << 8) + b1 return (b0 & 0x8F) == 0x08 and (word % 31) == 0 @classmethod def _parse_file(cls, f): map = f.read() if not map: raise EmptyFileException('Corrupted empty file detected') if cls._is_legacy_object(map): obj = cls._parse_legacy_object_header(map, f) obj._parse_legacy_object(map) else: obj = cls._parse_object_header(map, f) obj._parse_object(map) return obj def __init__(self): """Don't call this directly""" self._sha = None self._chunked_text = [] self._needs_serialization = True def _deserialize(self, chunks): raise NotImplementedError(self._deserialize) def _serialize(self): raise NotImplementedError(self._serialize) @classmethod def from_path(cls, path): """Open a SHA file from disk.""" with GitFile(path, 'rb') as f: return cls.from_file(f) @classmethod def from_file(cls, f): """Get the contents of a SHA file on disk.""" try: obj = cls._parse_file(f) obj._sha = None return obj except (IndexError, ValueError): raise ObjectFormatException("invalid object header") @staticmethod def from_raw_string(type_num, string, sha=None): """Creates an object of the indicated type from the raw string given. :param type_num: The numeric type of the object. :param string: The raw uncompressed contents. :param sha: Optional known sha for the object """ obj = object_class(type_num)() obj.set_raw_string(string, sha) return obj @staticmethod def from_raw_chunks(type_num, chunks, sha=None): """Creates an object of the indicated type from the raw chunks given. :param type_num: The numeric type of the object. :param chunks: An iterable of the raw uncompressed contents. :param sha: Optional known sha for the object """ obj = object_class(type_num)() obj.set_raw_chunks(chunks, sha) return obj @classmethod def from_string(cls, string): """Create a ShaFile from a string.""" obj = cls() obj.set_raw_string(string) return obj def _check_has_member(self, member, error_msg): """Check that the object has a given member variable. :param member: the member variable to check for :param error_msg: the message for an error if the member is missing :raise ObjectFormatException: with the given error_msg if member is missing or is None """ if getattr(self, member, None) is None: raise ObjectFormatException(error_msg) def check(self): """Check this object for internal consistency. :raise ObjectFormatException: if the object is malformed in some way :raise ChecksumMismatch: if the object was created with a SHA that does not match its contents """ # TODO: if we find that error-checking during object parsing is a # performance bottleneck, those checks should be moved to the class's # check() method during optimization so we can still check the object # when necessary. old_sha = self.id try: self._deserialize(self.as_raw_chunks()) self._sha = None new_sha = self.id except Exception as e: raise ObjectFormatException(e) if old_sha != new_sha: raise ChecksumMismatch(new_sha, old_sha) def _header(self): return object_header(self.type, self.raw_length()) def raw_length(self): """Returns the length of the raw string of this object.""" ret = 0 for chunk in self.as_raw_chunks(): ret += len(chunk) return ret def sha(self): """The SHA1 object that is the name of this object.""" if self._sha is None or self._needs_serialization: # this is a local because as_raw_chunks() overwrites self._sha new_sha = sha1() new_sha.update(self._header()) for chunk in self.as_raw_chunks(): new_sha.update(chunk) self._sha = new_sha return self._sha def copy(self): """Create a new copy of this SHA1 object from its raw string""" obj_class = object_class(self.get_type()) return obj_class.from_raw_string( self.get_type(), self.as_raw_string(), self.id) @property def id(self): """The hex SHA of this object.""" return self.sha().hexdigest().encode('ascii') def get_type(self): """Return the type number for this object class.""" return self.type_num def set_type(self, type): """Set the type number for this object class.""" self.type_num = type # DEPRECATED: use type_num or type_name as needed. type = property(get_type, set_type) def __repr__(self): return "<%s %s>" % (self.__class__.__name__, self.id) def __ne__(self, other): + """Check whether this object does not match the other.""" return not isinstance(other, ShaFile) or self.id != other.id def __eq__(self, other): """Return True if the SHAs of the two objects match. - - It doesn't make sense to talk about an order on ShaFiles, so we don't - override the rich comparison methods (__le__, etc.). """ return isinstance(other, ShaFile) and self.id == other.id def __lt__(self, other): + """Return whether SHA of this object is less than the other. + """ if not isinstance(other, ShaFile): raise TypeError return self.id < other.id def __le__(self, other): + """Check whether SHA of this object is less than or equal to the other. + """ if not isinstance(other, ShaFile): raise TypeError return self.id <= other.id def __cmp__(self, other): + """Compare the SHA of this object with that of the other object. + """ if not isinstance(other, ShaFile): raise TypeError return cmp(self.id, other.id) # noqa: F821 class Blob(ShaFile): """A Git Blob object.""" __slots__ = () type_name = b'blob' type_num = 3 def __init__(self): super(Blob, self).__init__() self._chunked_text = [] self._needs_serialization = False def _get_data(self): return self.as_raw_string() def _set_data(self, data): self.set_raw_string(data) data = property(_get_data, _set_data, "The text contained within the blob object.") def _get_chunked(self): return self._chunked_text def _set_chunked(self, chunks): self._chunked_text = chunks def _serialize(self): return self._chunked_text def _deserialize(self, chunks): self._chunked_text = chunks chunked = property( _get_chunked, _set_chunked, "The text within the blob object, as chunks (not necessarily lines).") @classmethod def from_path(cls, path): blob = ShaFile.from_path(path) if not isinstance(blob, cls): raise NotBlobError(path) return blob def check(self): """Check this object for internal consistency. :raise ObjectFormatException: if the object is malformed in some way """ super(Blob, self).check() def splitlines(self): """Return list of lines in this blob. This preserves the original line endings. """ chunks = self.chunked if not chunks: return [] if len(chunks) == 1: return chunks[0].splitlines(True) remaining = None ret = [] for chunk in chunks: lines = chunk.splitlines(True) if len(lines) > 1: ret.append((remaining or b"") + lines[0]) ret.extend(lines[1:-1]) remaining = lines[-1] elif len(lines) == 1: if remaining is None: remaining = lines.pop() else: remaining += lines.pop() if remaining is not None: ret.append(remaining) return ret def _parse_message(chunks): """Parse a message with a list of fields and a body. :param chunks: the raw chunks of the tag or commit object. :return: iterator of tuples of (field, value), one per header line, in the order read from the text, possibly including duplicates. Includes a field named None for the freeform tag/commit text. """ f = BytesIO(b''.join(chunks)) k = None v = "" eof = False def _strip_last_newline(value): """Strip the last newline from value""" if value and value.endswith(b'\n'): return value[:-1] return value # Parse the headers # # Headers can contain newlines. The next line is indented with a space. # We store the latest key as 'k', and the accumulated value as 'v'. for line in f: if line.startswith(b' '): # Indented continuation of the previous line v += line[1:] else: if k is not None: # We parsed a new header, return its value yield (k, _strip_last_newline(v)) if line == b'\n': # Empty line indicates end of headers break (k, v) = line.split(b' ', 1) else: # We reached end of file before the headers ended. We still need to # return the previous header, then we need to return a None field for # the text. eof = True if k is not None: yield (k, _strip_last_newline(v)) yield (None, None) if not eof: # We didn't reach the end of file while parsing headers. We can return # the rest of the file as a message. yield (None, f.read()) f.close() class Tag(ShaFile): """A Git Tag object.""" type_name = b'tag' type_num = 4 __slots__ = ('_tag_timezone_neg_utc', '_name', '_object_sha', '_object_class', '_tag_time', '_tag_timezone', - '_tagger', '_message') + '_tagger', '_message', '_signature') def __init__(self): super(Tag, self).__init__() self._tagger = None self._tag_time = None self._tag_timezone = None self._tag_timezone_neg_utc = False + self._signature = None @classmethod def from_path(cls, filename): tag = ShaFile.from_path(filename) if not isinstance(tag, cls): raise NotTagError(filename) return tag def check(self): """Check this object for internal consistency. :raise ObjectFormatException: if the object is malformed in some way """ super(Tag, self).check() self._check_has_member("_object_sha", "missing object sha") self._check_has_member("_object_class", "missing object type") self._check_has_member("_name", "missing tag name") if not self._name: raise ObjectFormatException("empty tag name") check_hexsha(self._object_sha, "invalid object sha") if getattr(self, "_tagger", None): check_identity(self._tagger, "invalid tagger") self._check_has_member("_tag_time", "missing tag time") check_time(self._tag_time) last = None for field, _ in _parse_message(self._chunked_text): if field == _OBJECT_HEADER and last is not None: raise ObjectFormatException("unexpected object") elif field == _TYPE_HEADER and last != _OBJECT_HEADER: raise ObjectFormatException("unexpected type") elif field == _TAG_HEADER and last != _TYPE_HEADER: raise ObjectFormatException("unexpected tag name") elif field == _TAGGER_HEADER and last != _TAG_HEADER: raise ObjectFormatException("unexpected tagger") last = field def _serialize(self): chunks = [] chunks.append(git_line(_OBJECT_HEADER, self._object_sha)) chunks.append(git_line(_TYPE_HEADER, self._object_class.type_name)) chunks.append(git_line(_TAG_HEADER, self._name)) if self._tagger: if self._tag_time is None: chunks.append(git_line(_TAGGER_HEADER, self._tagger)) else: chunks.append(git_line( _TAGGER_HEADER, self._tagger, str(self._tag_time).encode('ascii'), format_timezone( self._tag_timezone, self._tag_timezone_neg_utc))) if self._message is not None: chunks.append(b'\n') # To close headers chunks.append(self._message) + if self._signature is not None: + chunks.append(self._signature) return chunks def _deserialize(self, chunks): """Grab the metadata attached to the tag""" self._tagger = None self._tag_time = None self._tag_timezone = None self._tag_timezone_neg_utc = False for field, value in _parse_message(chunks): if field == _OBJECT_HEADER: self._object_sha = value elif field == _TYPE_HEADER: obj_class = object_class(value) if not obj_class: raise ObjectFormatException("Not a known type: %s" % value) self._object_class = obj_class elif field == _TAG_HEADER: self._name = value elif field == _TAGGER_HEADER: (self._tagger, self._tag_time, (self._tag_timezone, self._tag_timezone_neg_utc)) = parse_time_entry(value) elif field is None: - self._message = value + if value is None: + self._message = None + self._signature = None + else: + try: + sig_idx = value.index(BEGIN_PGP_SIGNATURE) + except ValueError: + self._message = value + self._signature = None + else: + self._message = value[:sig_idx] + self._signature = value[sig_idx:] else: raise ObjectFormatException("Unknown field %s" % field) def _get_object(self): """Get the object pointed to by this tag. :return: tuple of (object class, sha). """ return (self._object_class, self._object_sha) def _set_object(self, value): (self._object_class, self._object_sha) = value self._needs_serialization = True object = property(_get_object, _set_object) name = serializable_property("name", "The name of this tag") tagger = serializable_property( "tagger", "Returns the name of the person who created this tag") tag_time = serializable_property( "tag_time", "The creation timestamp of the tag. As the number of seconds " "since the epoch") tag_timezone = serializable_property( "tag_timezone", "The timezone that tag_time is in.") message = serializable_property( - "message", "The message attached to this tag") + "message", "the message attached to this tag") + + signature = serializable_property( + "signature", "Optional detached GPG signature") class TreeEntry(namedtuple('TreeEntry', ['path', 'mode', 'sha'])): """Named tuple encapsulating a single tree entry.""" def in_path(self, path): """Return a copy of this entry with the given path prepended.""" if not isinstance(self.path, bytes): raise TypeError('Expected bytes for path, got %r' % path) return TreeEntry(posixpath.join(path, self.path), self.mode, self.sha) def parse_tree(text, strict=False): """Parse a tree text. :param text: Serialized text to parse :return: iterator of tuples of (name, mode, sha) :raise ObjectFormatException: if the object was malformed in some way """ count = 0 length = len(text) while count < length: mode_end = text.index(b' ', count) mode_text = text[count:mode_end] if strict and mode_text.startswith(b'0'): raise ObjectFormatException("Invalid mode '%s'" % mode_text) try: mode = int(mode_text, 8) except ValueError: raise ObjectFormatException("Invalid mode '%s'" % mode_text) name_end = text.index(b'\0', mode_end) name = text[mode_end+1:name_end] count = name_end+21 sha = text[name_end+1:count] if len(sha) != 20: raise ObjectFormatException("Sha has invalid length") hexsha = sha_to_hex(sha) yield (name, mode, hexsha) def serialize_tree(items): """Serialize the items in a tree to a text. :param items: Sorted iterable over (name, mode, sha) tuples :return: Serialized tree text as chunks """ for name, mode, hexsha in items: yield (("%04o" % mode).encode('ascii') + b' ' + name + b'\0' + hex_to_sha(hexsha)) def sorted_tree_items(entries, name_order): """Iterate over a tree entries dictionary. :param name_order: If True, iterate entries in order of their name. If False, iterate entries in tree order, that is, treat subtree entries as having '/' appended. :param entries: Dictionary mapping names to (mode, sha) tuples :return: Iterator over (name, mode, hexsha) """ key_func = name_order and key_entry_name_order or key_entry for name, entry in sorted(entries.items(), key=key_func): mode, hexsha = entry # Stricter type checks than normal to mirror checks in the C version. mode = int(mode) if not isinstance(hexsha, bytes): raise TypeError('Expected bytes for SHA, got %r' % hexsha) yield TreeEntry(name, mode, hexsha) def key_entry(entry): """Sort key for tree entry. :param entry: (name, value) tuplee """ (name, value) = entry if stat.S_ISDIR(value[0]): name += b'/' return name def key_entry_name_order(entry): """Sort key for tree entry in name order.""" return entry[0] def pretty_format_tree_entry(name, mode, hexsha, encoding="utf-8"): """Pretty format tree entry. :param name: Name of the directory entry :param mode: Mode of entry :param hexsha: Hexsha of the referenced object :return: string describing the tree entry """ if mode & stat.S_IFDIR: kind = "tree" else: kind = "blob" return "%04o %s %s\t%s\n" % ( mode, kind, hexsha.decode('ascii'), name.decode(encoding, 'replace')) class Tree(ShaFile): """A Git tree object""" type_name = b'tree' type_num = 2 __slots__ = ('_entries') def __init__(self): super(Tree, self).__init__() self._entries = {} @classmethod def from_path(cls, filename): tree = ShaFile.from_path(filename) if not isinstance(tree, cls): raise NotTreeError(filename) return tree def __contains__(self, name): return name in self._entries def __getitem__(self, name): return self._entries[name] def __setitem__(self, name, value): """Set a tree entry by name. :param name: The name of the entry, as a string. :param value: A tuple of (mode, hexsha), where mode is the mode of the entry as an integral type and hexsha is the hex SHA of the entry as a string. """ mode, hexsha = value self._entries[name] = (mode, hexsha) self._needs_serialization = True def __delitem__(self, name): del self._entries[name] self._needs_serialization = True def __len__(self): return len(self._entries) def __iter__(self): return iter(self._entries) def add(self, name, mode, hexsha): """Add an entry to the tree. :param mode: The mode of the entry as an integral type. Not all possible modes are supported by git; see check() for details. :param name: The name of the entry, as a string. :param hexsha: The hex SHA of the entry as a string. """ if isinstance(name, int) and isinstance(mode, bytes): (name, mode) = (mode, name) warnings.warn( "Please use Tree.add(name, mode, hexsha)", category=DeprecationWarning, stacklevel=2) self._entries[name] = mode, hexsha self._needs_serialization = True def iteritems(self, name_order=False): """Iterate over entries. :param name_order: If True, iterate in name order instead of tree order. :return: Iterator over (name, mode, sha) tuples """ return sorted_tree_items(self._entries, name_order) def items(self): """Return the sorted entries in this tree. :return: List with (name, mode, sha) tuples """ return list(self.iteritems()) def _deserialize(self, chunks): """Grab the entries in the tree""" try: parsed_entries = parse_tree(b''.join(chunks)) except ValueError as e: raise ObjectFormatException(e) # TODO: list comprehension is for efficiency in the common (small) # case; if memory efficiency in the large case is a concern, use a # genexp. self._entries = dict([(n, (m, s)) for n, m, s in parsed_entries]) def check(self): """Check this object for internal consistency. :raise ObjectFormatException: if the object is malformed in some way """ super(Tree, self).check() last = None allowed_modes = (stat.S_IFREG | 0o755, stat.S_IFREG | 0o644, stat.S_IFLNK, stat.S_IFDIR, S_IFGITLINK, # TODO: optionally exclude as in git fsck --strict stat.S_IFREG | 0o664) for name, mode, sha in parse_tree(b''.join(self._chunked_text), True): check_hexsha(sha, 'invalid sha %s' % sha) if b'/' in name or name in (b'', b'.', b'..', b'.git'): raise ObjectFormatException( 'invalid name %s' % name.decode('utf-8', 'replace')) if mode not in allowed_modes: raise ObjectFormatException('invalid mode %06o' % mode) entry = (name, (mode, sha)) if last: if key_entry(last) > key_entry(entry): raise ObjectFormatException('entries not sorted') if name == last[0]: raise ObjectFormatException('duplicate entry %s' % name) last = entry def _serialize(self): return list(serialize_tree(self.iteritems())) def as_pretty_string(self): text = [] for name, mode, hexsha in self.iteritems(): text.append(pretty_format_tree_entry(name, mode, hexsha)) return "".join(text) def lookup_path(self, lookup_obj, path): """Look up an object in a Git tree. :param lookup_obj: Callback for retrieving object by SHA1 :param path: Path to lookup :return: A tuple of (mode, SHA) of the resulting path. """ parts = path.split(b'/') sha = self.id mode = None for p in parts: if not p: continue obj = lookup_obj(sha) if not isinstance(obj, Tree): raise NotTreeError(sha) mode, sha = obj[p] return mode, sha def parse_timezone(text): """Parse a timezone text fragment (e.g. '+0100'). :param text: Text to parse. :return: Tuple with timezone as seconds difference to UTC and a boolean indicating whether this was a UTC timezone prefixed with a negative sign (-0000). """ # cgit parses the first character as the sign, and the rest # as an integer (using strtol), which could also be negative. # We do the same for compatibility. See #697828. if not text[0] in b'+-': raise ValueError("Timezone must start with + or - (%(text)s)" % vars()) sign = text[:1] offset = int(text[1:]) if sign == b'-': offset = -offset unnecessary_negative_timezone = (offset >= 0 and sign == b'-') signum = (offset < 0) and -1 or 1 offset = abs(offset) hours = int(offset / 100) minutes = (offset % 100) return (signum * (hours * 3600 + minutes * 60), unnecessary_negative_timezone) def format_timezone(offset, unnecessary_negative_timezone=False): """Format a timezone for Git serialization. :param offset: Timezone offset as seconds difference to UTC :param unnecessary_negative_timezone: Whether to use a minus sign for UTC or positive timezones (-0000 and --700 rather than +0000 / +0700). """ if offset % 60 != 0: raise ValueError("Unable to handle non-minute offset.") if offset < 0 or unnecessary_negative_timezone: sign = '-' offset = -offset else: sign = '+' return ('%c%02d%02d' % (sign, offset / 3600, (offset / 60) % 60)).encode('ascii') def parse_time_entry(value): """Parse time entry behavior :param value: Bytes representing a git commit/tag line :raise: ObjectFormatException in case of parsing error (malformed field date) :return: Tuple of (author, time, (timezone, timezone_neg_utc)) """ try: - sep = value.index(b'> ') + sep = value.rindex(b'> ') except ValueError: return (value, None, (None, False)) try: person = value[0:sep+1] rest = value[sep+2:] timetext, timezonetext = rest.rsplit(b' ', 1) time = int(timetext) timezone, timezone_neg_utc = parse_timezone(timezonetext) except ValueError as e: raise ObjectFormatException(e) return person, time, (timezone, timezone_neg_utc) def parse_commit(chunks): """Parse a commit object from chunks. :param chunks: Chunks to parse :return: Tuple of (tree, parents, author_info, commit_info, encoding, mergetag, gpgsig, message, extra) """ parents = [] extra = [] tree = None author_info = (None, None, (None, None)) commit_info = (None, None, (None, None)) encoding = None mergetag = [] message = None gpgsig = None for field, value in _parse_message(chunks): # TODO(jelmer): Enforce ordering if field == _TREE_HEADER: tree = value elif field == _PARENT_HEADER: parents.append(value) elif field == _AUTHOR_HEADER: author_info = parse_time_entry(value) elif field == _COMMITTER_HEADER: commit_info = parse_time_entry(value) elif field == _ENCODING_HEADER: encoding = value elif field == _MERGETAG_HEADER: mergetag.append(Tag.from_string(value + b'\n')) elif field == _GPGSIG_HEADER: gpgsig = value elif field is None: message = value else: extra.append((field, value)) return (tree, parents, author_info, commit_info, encoding, mergetag, gpgsig, message, extra) class Commit(ShaFile): """A git commit object""" type_name = b'commit' type_num = 1 __slots__ = ('_parents', '_encoding', '_extra', '_author_timezone_neg_utc', '_commit_timezone_neg_utc', '_commit_time', '_author_time', '_author_timezone', '_commit_timezone', '_author', '_committer', '_tree', '_message', '_mergetag', '_gpgsig') def __init__(self): super(Commit, self).__init__() self._parents = [] self._encoding = None self._mergetag = [] self._gpgsig = None self._extra = [] self._author_timezone_neg_utc = False self._commit_timezone_neg_utc = False @classmethod def from_path(cls, path): commit = ShaFile.from_path(path) if not isinstance(commit, cls): raise NotCommitError(path) return commit def _deserialize(self, chunks): (self._tree, self._parents, author_info, commit_info, self._encoding, self._mergetag, self._gpgsig, self._message, self._extra) = ( parse_commit(chunks)) (self._author, self._author_time, (self._author_timezone, self._author_timezone_neg_utc)) = author_info (self._committer, self._commit_time, (self._commit_timezone, self._commit_timezone_neg_utc)) = commit_info def check(self): """Check this object for internal consistency. :raise ObjectFormatException: if the object is malformed in some way """ super(Commit, self).check() self._check_has_member("_tree", "missing tree") self._check_has_member("_author", "missing author") self._check_has_member("_committer", "missing committer") self._check_has_member("_author_time", "missing author time") self._check_has_member("_commit_time", "missing commit time") for parent in self._parents: check_hexsha(parent, "invalid parent sha") check_hexsha(self._tree, "invalid tree sha") check_identity(self._author, "invalid author") check_identity(self._committer, "invalid committer") check_time(self._author_time) check_time(self._commit_time) last = None for field, _ in _parse_message(self._chunked_text): if field == _TREE_HEADER and last is not None: raise ObjectFormatException("unexpected tree") elif field == _PARENT_HEADER and last not in (_PARENT_HEADER, _TREE_HEADER): raise ObjectFormatException("unexpected parent") elif field == _AUTHOR_HEADER and last not in (_TREE_HEADER, _PARENT_HEADER): raise ObjectFormatException("unexpected author") elif field == _COMMITTER_HEADER and last != _AUTHOR_HEADER: raise ObjectFormatException("unexpected committer") elif field == _ENCODING_HEADER and last != _COMMITTER_HEADER: raise ObjectFormatException("unexpected encoding") last = field # TODO: optionally check for duplicate parents def _serialize(self): chunks = [] tree_bytes = ( self._tree.id if isinstance(self._tree, Tree) else self._tree) chunks.append(git_line(_TREE_HEADER, tree_bytes)) for p in self._parents: chunks.append(git_line(_PARENT_HEADER, p)) chunks.append(git_line( _AUTHOR_HEADER, self._author, str(self._author_time).encode('ascii'), format_timezone( self._author_timezone, self._author_timezone_neg_utc))) chunks.append(git_line( _COMMITTER_HEADER, self._committer, str(self._commit_time).encode('ascii'), format_timezone(self._commit_timezone, self._commit_timezone_neg_utc))) if self.encoding: chunks.append(git_line(_ENCODING_HEADER, self.encoding)) for mergetag in self.mergetag: mergetag_chunks = mergetag.as_raw_string().split(b'\n') chunks.append(git_line(_MERGETAG_HEADER, mergetag_chunks[0])) # Embedded extra header needs leading space for chunk in mergetag_chunks[1:]: chunks.append(b' ' + chunk + b'\n') # No trailing empty line if chunks[-1].endswith(b' \n'): chunks[-1] = chunks[-1][:-2] for k, v in self.extra: if b'\n' in k or b'\n' in v: raise AssertionError( "newline in extra data: %r -> %r" % (k, v)) chunks.append(git_line(k, v)) if self.gpgsig: sig_chunks = self.gpgsig.split(b'\n') chunks.append(git_line(_GPGSIG_HEADER, sig_chunks[0])) for chunk in sig_chunks[1:]: chunks.append(git_line(b'', chunk)) chunks.append(b'\n') # There must be a new line after the headers chunks.append(self._message) return chunks tree = serializable_property( "tree", "Tree that is the state of this commit") def _get_parents(self): """Return a list of parents of this commit.""" return self._parents def _set_parents(self, value): """Set a list of parents of this commit.""" self._needs_serialization = True self._parents = value parents = property(_get_parents, _set_parents, doc="Parents of this commit, by their SHA1.") def _get_extra(self): """Return extra settings of this commit.""" return self._extra extra = property( _get_extra, doc="Extra header fields not understood (presumably added in a " "newer version of git). Kept verbatim so the object can " "be correctly reserialized. For private commit metadata, use " "pseudo-headers in Commit.message, rather than this field.") author = serializable_property( "author", "The name of the author of the commit") committer = serializable_property( "committer", "The name of the committer of the commit") message = serializable_property( "message", "The commit message") commit_time = serializable_property( "commit_time", "The timestamp of the commit. As the number of seconds since the " "epoch.") commit_timezone = serializable_property( "commit_timezone", "The zone the commit time is in") author_time = serializable_property( "author_time", "The timestamp the commit was written. As the number of " "seconds since the epoch.") author_timezone = serializable_property( "author_timezone", "Returns the zone the author time is in.") encoding = serializable_property( "encoding", "Encoding of the commit message.") mergetag = serializable_property( "mergetag", "Associated signed tag.") gpgsig = serializable_property( "gpgsig", "GPG Signature.") OBJECT_CLASSES = ( Commit, Tree, Blob, Tag, ) _TYPE_MAP = {} for cls in OBJECT_CLASSES: _TYPE_MAP[cls.type_name] = cls _TYPE_MAP[cls.type_num] = cls # Hold on to the pure-python implementations for testing _parse_tree_py = parse_tree _sorted_tree_items_py = sorted_tree_items try: # Try to import C versions from dulwich._objects import parse_tree, sorted_tree_items except ImportError: pass diff --git a/dulwich/objectspec.py b/dulwich/objectspec.py index 8edf7da2..1e6fb93c 100644 --- a/dulwich/objectspec.py +++ b/dulwich/objectspec.py @@ -1,186 +1,186 @@ # objectspec.py -- Object specification # Copyright (C) 2014 Jelmer Vernooij # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """Object specification.""" def to_bytes(text): if getattr(text, "encode", None) is not None: text = text.encode('ascii') return text def parse_object(repo, objectish): """Parse a string referring to an object. :param repo: A `Repo` object :param objectish: A string referring to an object :return: A git object :raise KeyError: If the object can not be found """ objectish = to_bytes(objectish) return repo[objectish] def parse_tree(repo, treeish): """Parse a string referring to a tree. :param repo: A `Repo` object :param treeish: A string referring to a tree :return: A git object :raise KeyError: If the object can not be found """ treeish = to_bytes(treeish) o = repo[treeish] if o.type_name == b"commit": return repo[o.tree] return o def parse_ref(container, refspec): """Parse a string referring to a reference. :param container: A RefsContainer object :param refspec: A string referring to a ref :return: A ref :raise KeyError: If the ref can not be found """ refspec = to_bytes(refspec) possible_refs = [ refspec, b"refs/" + refspec, b"refs/tags/" + refspec, b"refs/heads/" + refspec, b"refs/remotes/" + refspec, b"refs/remotes/" + refspec + b"/HEAD" ] for ref in possible_refs: if ref in container: return ref else: raise KeyError(refspec) def parse_reftuple(lh_container, rh_container, refspec): """Parse a reftuple spec. :param lh_container: A RefsContainer object :param hh_container: A RefsContainer object :param refspec: A string :return: A tuple with left and right ref :raise KeyError: If one of the refs can not be found """ + refspec = to_bytes(refspec) if refspec.startswith(b"+"): force = True refspec = refspec[1:] else: force = False - refspec = to_bytes(refspec) if b":" in refspec: (lh, rh) = refspec.split(b":") else: lh = rh = refspec if lh == b"": lh = None else: lh = parse_ref(lh_container, lh) if rh == b"": rh = None else: try: rh = parse_ref(rh_container, rh) except KeyError: # TODO: check force? if b"/" not in rh: rh = b"refs/heads/" + rh return (lh, rh, force) def parse_reftuples(lh_container, rh_container, refspecs): """Parse a list of reftuple specs to a list of reftuples. :param lh_container: A RefsContainer object :param hh_container: A RefsContainer object :param refspecs: A list of refspecs or a string :return: A list of refs :raise KeyError: If one of the refs can not be found """ if not isinstance(refspecs, list): refspecs = [refspecs] ret = [] # TODO: Support * in refspecs for refspec in refspecs: ret.append(parse_reftuple(lh_container, rh_container, refspec)) return ret def parse_refs(container, refspecs): """Parse a list of refspecs to a list of refs. :param container: A RefsContainer object :param refspecs: A list of refspecs or a string :return: A list of refs :raise KeyError: If one of the refs can not be found """ # TODO: Support * in refspecs if not isinstance(refspecs, list): refspecs = [refspecs] ret = [] for refspec in refspecs: ret.append(parse_ref(container, refspec)) return ret def parse_commit_range(repo, committishs): """Parse a string referring to a range of commits. :param repo: A `Repo` object :param committishs: A string referring to a range of commits. :return: An iterator over `Commit` objects :raise KeyError: When the reference commits can not be found :raise ValueError: If the range can not be parsed """ committishs = to_bytes(committishs) # TODO(jelmer): Support more than a single commit.. return iter([parse_commit(repo, committishs)]) def parse_commit(repo, committish): """Parse a string referring to a single commit. :param repo: A` Repo` object :param commitish: A string referring to a single commit. :return: A Commit object :raise KeyError: When the reference commits can not be found :raise ValueError: If the range can not be parsed """ committish = to_bytes(committish) try: return repo[committish] except KeyError: pass try: return repo[parse_ref(repo, committish)] except KeyError: pass raise KeyError(committish) # TODO: parse_path_in_tree(), which handles e.g. v1.0:Documentation diff --git a/dulwich/porcelain.py b/dulwich/porcelain.py index f6b0db40..228a664f 100644 --- a/dulwich/porcelain.py +++ b/dulwich/porcelain.py @@ -1,1366 +1,1429 @@ # porcelain.py -- Porcelain-like layer on top of Dulwich # Copyright (C) 2013 Jelmer Vernooij # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """Simple wrapper that provides porcelain-like functions on top of Dulwich. Currently implemented: * archive * add * branch{_create,_delete,_list} * check-ignore * checkout * clone * commit * commit-tree * daemon * describe * diff-tree * fetch * init * ls-files * ls-remote * ls-tree * pull * push * rm * remote{_add} * receive-pack * reset * rev-list * tag{_create,_delete,_list} * upload-pack * update-server-info * status * symbolic-ref These functions are meant to behave similarly to the git subcommands. Differences in behaviour are considered bugs. Functions should generally accept both unicode strings and bytestrings """ from collections import namedtuple from contextlib import ( closing, contextmanager, ) -from io import BytesIO +from io import BytesIO, RawIOBase import datetime import os import posixpath import stat import sys import time from dulwich.archive import ( tar_stream, ) from dulwich.client import ( get_transport_and_path, ) from dulwich.config import ( StackedConfig, ) from dulwich.diff_tree import ( CHANGE_ADD, CHANGE_DELETE, CHANGE_MODIFY, CHANGE_RENAME, CHANGE_COPY, RENAME_CHANGE_TYPES, ) from dulwich.errors import ( SendPackError, UpdateRefsError, ) from dulwich.ignore import IgnoreFilterManager from dulwich.index import ( blob_from_path_and_stat, get_unstaged_changes, ) from dulwich.object_store import ( tree_lookup_path, ) from dulwich.objects import ( Commit, Tag, format_timezone, parse_timezone, pretty_format_tree_entry, ) from dulwich.objectspec import ( parse_commit, parse_object, parse_ref, parse_reftuples, parse_tree, ) from dulwich.pack import ( write_pack_index, write_pack_objects, ) from dulwich.patch import write_tree_diff from dulwich.protocol import ( Protocol, ZERO_SHA, ) from dulwich.refs import ( ANNOTATED_TAG_SUFFIX, strip_peeled_refs, ) from dulwich.repo import (BaseRepo, Repo) from dulwich.server import ( FileSystemBackend, TCPGitServer, ReceivePackHandler, UploadPackHandler, update_server_info as server_update_server_info, ) # Module level tuple definition for status output GitStatus = namedtuple('GitStatus', 'staged unstaged untracked') -default_bytes_out_stream = getattr(sys.stdout, 'buffer', sys.stdout) -default_bytes_err_stream = getattr(sys.stderr, 'buffer', sys.stderr) +class NoneStream(RawIOBase): + """Fallback if stdout or stderr are unavailable, does nothing.""" + def read(self, size=-1): + return None + + def readall(self): + return None + + def readinto(self, b): + return None + + def write(self, b): + return None + + +default_bytes_out_stream = getattr( + sys.stdout, 'buffer', sys.stdout + ) or NoneStream() +default_bytes_err_stream = getattr( + sys.stderr, 'buffer', sys.stderr + ) or NoneStream() DEFAULT_ENCODING = 'utf-8' class RemoteExists(Exception): """Raised when the remote already exists.""" def open_repo(path_or_repo): """Open an argument that can be a repository or a path for a repository.""" if isinstance(path_or_repo, BaseRepo): return path_or_repo return Repo(path_or_repo) @contextmanager def _noop_context_manager(obj): """Context manager that has the same api as closing but does nothing.""" yield obj def open_repo_closing(path_or_repo): """Open an argument that can be a repository or a path for a repository. returns a context manager that will close the repo on exit if the argument is a path, else does nothing if the argument is a repo. """ if isinstance(path_or_repo, BaseRepo): return _noop_context_manager(path_or_repo) return closing(Repo(path_or_repo)) def path_to_tree_path(repopath, path): """Convert a path to a path usable in an index, e.g. bytes and relative to the repository root. :param repopath: Repository path, absolute or relative to the cwd :param path: A path, absolute or relative to the cwd :return: A path formatted for use in e.g. an index """ if not isinstance(path, bytes): path = path.encode(sys.getfilesystemencoding()) if not isinstance(repopath, bytes): repopath = repopath.encode(sys.getfilesystemencoding()) treepath = os.path.relpath(path, repopath) if treepath.startswith(b'..'): raise ValueError('Path not in repo') + if os.path.sep != '/': + treepath = treepath.replace(os.path.sep.encode('ascii'), b'/') return treepath def archive(repo, committish=None, outstream=default_bytes_out_stream, errstream=default_bytes_err_stream): """Create an archive. :param repo: Path of repository for which to generate an archive. :param committish: Commit SHA1 or ref to use :param outstream: Output stream (defaults to stdout) :param errstream: Error stream (defaults to stderr) """ if committish is None: committish = "HEAD" with open_repo_closing(repo) as repo_obj: c = repo_obj[committish] for chunk in tar_stream( repo_obj.object_store, repo_obj.object_store[c.tree], c.commit_time): outstream.write(chunk) def update_server_info(repo="."): """Update server info files for a repository. :param repo: path to the repository """ with open_repo_closing(repo) as r: server_update_server_info(r) def symbolic_ref(repo, ref_name, force=False): """Set git symbolic ref into HEAD. :param repo: path to the repository :param ref_name: short name of the new ref :param force: force settings without checking if it exists in refs/heads """ with open_repo_closing(repo) as repo_obj: ref_path = _make_branch_ref(ref_name) if not force and ref_path not in repo_obj.refs.keys(): raise ValueError('fatal: ref `%s` is not a ref' % ref_name) repo_obj.refs.set_symbolic_ref(b'HEAD', ref_path) def commit(repo=".", message=None, author=None, committer=None, encoding=None): """Create a new commit. :param repo: Path to repository :param message: Optional commit message :param author: Optional author name and email :param committer: Optional committer name and email :return: SHA1 of the new commit """ # FIXME: Support --all argument # FIXME: Support --signoff argument if getattr(message, 'encode', None): message = message.encode(encoding or DEFAULT_ENCODING) if getattr(author, 'encode', None): author = author.encode(encoding or DEFAULT_ENCODING) if getattr(committer, 'encode', None): committer = committer.encode(encoding or DEFAULT_ENCODING) with open_repo_closing(repo) as r: return r.do_commit( message=message, author=author, committer=committer, encoding=encoding) def commit_tree(repo, tree, message=None, author=None, committer=None): """Create a new commit object. :param repo: Path to repository :param tree: An existing tree object :param author: Optional author name and email :param committer: Optional committer name and email """ with open_repo_closing(repo) as r: return r.do_commit( message=message, tree=tree, committer=committer, author=author) def init(path=".", bare=False): """Create a new git repository. :param path: Path to repository. :param bare: Whether to create a bare repository. :return: A Repo instance """ if not os.path.exists(path): os.mkdir(path) if bare: return Repo.init_bare(path) else: return Repo.init(path) def clone(source, target=None, bare=False, checkout=None, errstream=default_bytes_err_stream, outstream=None, - origin=b"origin", **kwargs): + origin=b"origin", depth=None, **kwargs): """Clone a local or remote git repository. :param source: Path or URL for source repository :param target: Path to target repository (optional) :param bare: Whether or not to create a bare repository :param checkout: Whether or not to check-out HEAD after cloning :param errstream: Optional stream to write progress to :param outstream: Optional stream to write progress to (deprecated) :param origin: Name of remote from the repository used to clone + :param depth: Depth to fetch at :return: The new repository """ # TODO(jelmer): This code overlaps quite a bit with Repo.clone if outstream is not None: import warnings warnings.warn( "outstream= has been deprecated in favour of errstream=.", DeprecationWarning, stacklevel=3) errstream = outstream if checkout is None: checkout = (not bare) if checkout and bare: raise ValueError("checkout and bare are incompatible") if target is None: target = source.split("/")[-1] if not os.path.exists(target): os.mkdir(target) if bare: r = Repo.init_bare(target) else: r = Repo.init(target) reflog_message = b'clone: from ' + source.encode('utf-8') try: fetch_result = fetch( r, source, origin, errstream=errstream, message=reflog_message, - **kwargs) + depth=depth, **kwargs) target_config = r.get_config() if not isinstance(source, bytes): source = source.encode(DEFAULT_ENCODING) target_config.set((b'remote', origin), b'url', source) target_config.set( (b'remote', origin), b'fetch', b'+refs/heads/*:refs/remotes/' + origin + b'/*') target_config.write_to_path() # TODO(jelmer): Support symref capability, # https://github.com/jelmer/dulwich/issues/485 try: head = r[fetch_result[b'HEAD']] except KeyError: head = None else: r[b'HEAD'] = head.id if checkout and not bare and head is not None: errstream.write(b'Checking out ' + head.id + b'\n') r.reset_index(head.tree) except BaseException: r.close() raise return r def add(repo=".", paths=None): """Add files to the staging area. :param repo: Repository for the files :param paths: Paths to add. No value passed stages all modified files. :return: Tuple with set of added files and ignored files """ ignored = set() with open_repo_closing(repo) as r: ignore_manager = IgnoreFilterManager.from_repo(r) if not paths: paths = list( get_untracked_paths(os.getcwd(), r.path, r.open_index())) relpaths = [] if not isinstance(paths, list): paths = [paths] for p in paths: relpath = os.path.relpath(p, r.path) if relpath.startswith('..' + os.path.sep): raise ValueError('path %r is not in repo' % relpath) # FIXME: Support patterns, directories. if ignore_manager.is_ignored(relpath): ignored.add(relpath) continue relpaths.append(relpath) r.stage(relpaths) return (relpaths, ignored) def remove(repo=".", paths=None, cached=False): """Remove files from the staging area. :param repo: Repository for the files :param paths: Paths to remove """ with open_repo_closing(repo) as r: index = r.open_index() for p in paths: full_path = os.path.abspath(p).encode(sys.getfilesystemencoding()) tree_path = path_to_tree_path(r.path, p) try: index_sha = index[tree_path].sha except KeyError: raise Exception('%s did not match any files' % p) if not cached: try: st = os.lstat(full_path) except OSError: pass else: try: blob = blob_from_path_and_stat(full_path, st) except IOError: pass else: try: committed_sha = tree_lookup_path( r.__getitem__, r[r.head()].tree, tree_path)[1] except KeyError: committed_sha = None if blob.id != index_sha and index_sha != committed_sha: raise Exception( 'file has staged content differing ' 'from both the file and head: %s' % p) if index_sha != committed_sha: raise Exception( 'file has staged changes: %s' % p) os.remove(full_path) del index[tree_path] index.write() rm = remove def commit_decode(commit, contents, default_encoding=DEFAULT_ENCODING): if commit.encoding is not None: return contents.decode(commit.encoding, "replace") return contents.decode(default_encoding, "replace") def print_commit(commit, decode, outstream=sys.stdout): """Write a human-readable commit log entry. :param commit: A `Commit` object :param outstream: A stream file to write to """ outstream.write("-" * 50 + "\n") outstream.write("commit: " + commit.id.decode('ascii') + "\n") if len(commit.parents) > 1: outstream.write( "merge: " + "...".join([c.decode('ascii') for c in commit.parents[1:]]) + "\n") outstream.write("Author: " + decode(commit.author) + "\n") if commit.author != commit.committer: outstream.write("Committer: " + decode(commit.committer) + "\n") time_tuple = time.gmtime(commit.author_time + commit.author_timezone) time_str = time.strftime("%a %b %d %Y %H:%M:%S", time_tuple) timezone_str = format_timezone(commit.author_timezone).decode('ascii') outstream.write("Date: " + time_str + " " + timezone_str + "\n") outstream.write("\n") outstream.write(decode(commit.message) + "\n") outstream.write("\n") def print_tag(tag, decode, outstream=sys.stdout): """Write a human-readable tag. :param tag: A `Tag` object :param decode: Function for decoding bytes to unicode string :param outstream: A stream to write to """ outstream.write("Tagger: " + decode(tag.tagger) + "\n") outstream.write("Date: " + decode(tag.tag_time) + "\n") outstream.write("\n") outstream.write(decode(tag.message) + "\n") outstream.write("\n") def show_blob(repo, blob, decode, outstream=sys.stdout): """Write a blob to a stream. :param repo: A `Repo` object :param blob: A `Blob` object :param decode: Function for decoding bytes to unicode string :param outstream: A stream file to write to """ outstream.write(decode(blob.data)) def show_commit(repo, commit, decode, outstream=sys.stdout): """Show a commit to a stream. :param repo: A `Repo` object :param commit: A `Commit` object :param decode: Function for decoding bytes to unicode string :param outstream: Stream to write to """ print_commit(commit, decode=decode, outstream=outstream) if commit.parents: parent_commit = repo[commit.parents[0]] base_tree = parent_commit.tree else: base_tree = None diffstream = BytesIO() write_tree_diff( diffstream, repo.object_store, base_tree, commit.tree) diffstream.seek(0) outstream.write( diffstream.getvalue().decode( commit.encoding or DEFAULT_ENCODING, 'replace')) def show_tree(repo, tree, decode, outstream=sys.stdout): """Print a tree to a stream. :param repo: A `Repo` object :param tree: A `Tree` object :param decode: Function for decoding bytes to unicode string :param outstream: Stream to write to """ for n in tree: outstream.write(decode(n) + "\n") def show_tag(repo, tag, decode, outstream=sys.stdout): """Print a tag to a stream. :param repo: A `Repo` object :param tag: A `Tag` object :param decode: Function for decoding bytes to unicode string :param outstream: Stream to write to """ print_tag(tag, decode, outstream) show_object(repo, repo[tag.object[1]], outstream) def show_object(repo, obj, decode, outstream): return { b"tree": show_tree, b"blob": show_blob, b"commit": show_commit, b"tag": show_tag, }[obj.type_name](repo, obj, decode, outstream) def print_name_status(changes): """Print a simple status summary, listing changed files. """ for change in changes: if not change: continue if isinstance(change, list): change = change[0] if change.type == CHANGE_ADD: path1 = change.new.path path2 = '' kind = 'A' elif change.type == CHANGE_DELETE: path1 = change.old.path path2 = '' kind = 'D' elif change.type == CHANGE_MODIFY: path1 = change.new.path path2 = '' kind = 'M' elif change.type in RENAME_CHANGE_TYPES: path1 = change.old.path path2 = change.new.path if change.type == CHANGE_RENAME: kind = 'R' elif change.type == CHANGE_COPY: kind = 'C' yield '%-8s%-20s%-20s' % (kind, path1, path2) def log(repo=".", paths=None, outstream=sys.stdout, max_entries=None, reverse=False, name_status=False): """Write commit logs. :param repo: Path to repository :param paths: Optional set of specific paths to print entries for :param outstream: Stream to write log output to :param reverse: Reverse order in which entries are printed :param name_status: Print name status :param max_entries: Optional maximum number of entries to display """ with open_repo_closing(repo) as r: walker = r.get_walker( max_entries=max_entries, paths=paths, reverse=reverse) for entry in walker: def decode(x): return commit_decode(entry.commit, x) print_commit(entry.commit, decode, outstream) if name_status: outstream.writelines( [l+'\n' for l in print_name_status(entry.changes())]) # TODO(jelmer): better default for encoding? def show(repo=".", objects=None, outstream=sys.stdout, default_encoding=DEFAULT_ENCODING): """Print the changes in a commit. :param repo: Path to repository :param objects: Objects to show (defaults to [HEAD]) :param outstream: Stream to write to :param default_encoding: Default encoding to use if none is set in the commit """ if objects is None: objects = ["HEAD"] if not isinstance(objects, list): objects = [objects] with open_repo_closing(repo) as r: for objectish in objects: o = parse_object(r, objectish) if isinstance(o, Commit): def decode(x): return commit_decode(o, x, default_encoding) else: def decode(x): return x.decode(default_encoding) show_object(r, o, decode, outstream) def diff_tree(repo, old_tree, new_tree, outstream=sys.stdout): """Compares the content and mode of blobs found via two tree objects. :param repo: Path to repository :param old_tree: Id of old tree :param new_tree: Id of new tree :param outstream: Stream to write to """ with open_repo_closing(repo) as r: write_tree_diff(outstream, r.object_store, old_tree, new_tree) def rev_list(repo, commits, outstream=sys.stdout): """Lists commit objects in reverse chronological order. :param repo: Path to repository :param commits: Commits over which to iterate :param outstream: Stream to write to """ with open_repo_closing(repo) as r: for entry in r.get_walker(include=[r[c].id for c in commits]): outstream.write(entry.commit.id + b"\n") def tag(*args, **kwargs): import warnings warnings.warn("tag has been deprecated in favour of tag_create.", DeprecationWarning) return tag_create(*args, **kwargs) def tag_create( repo, tag, author=None, message=None, annotated=False, - objectish="HEAD", tag_time=None, tag_timezone=None): + objectish="HEAD", tag_time=None, tag_timezone=None, + sign=False): """Creates a tag in git via dulwich calls: :param repo: Path to repository :param tag: tag string :param author: tag author (optional, if annotated is set) :param message: tag message (optional) :param annotated: whether to create an annotated tag :param objectish: object the tag should point at, defaults to HEAD :param tag_time: Optional time for annotated tag :param tag_timezone: Optional timezone for annotated tag + :param sign: GPG Sign the tag """ with open_repo_closing(repo) as r: object = parse_object(r, objectish) if annotated: # Create the tag object tag_obj = Tag() if author is None: # TODO(jelmer): Don't use repo private method. - author = r._get_user_identity() + author = r._get_user_identity(r.get_config_stack()) tag_obj.tagger = author tag_obj.message = message tag_obj.name = tag tag_obj.object = (type(object), object.id) if tag_time is None: tag_time = int(time.time()) tag_obj.tag_time = tag_time if tag_timezone is None: # TODO(jelmer) Use current user timezone rather than UTC tag_timezone = 0 elif isinstance(tag_timezone, str): tag_timezone = parse_timezone(tag_timezone) tag_obj.tag_timezone = tag_timezone + if sign: + import gpg + with gpg.Context(armor=True) as c: + tag_obj.signature, result = c.sign(tag_obj.as_raw_string()) r.object_store.add_object(tag_obj) tag_id = tag_obj.id else: tag_id = object.id r.refs[_make_tag_ref(tag)] = tag_id def list_tags(*args, **kwargs): import warnings warnings.warn("list_tags has been deprecated in favour of tag_list.", DeprecationWarning) return tag_list(*args, **kwargs) def tag_list(repo, outstream=sys.stdout): """List all tags. :param repo: Path to repository :param outstream: Stream to write tags to """ with open_repo_closing(repo) as r: tags = sorted(r.refs.as_dict(b"refs/tags")) return tags def tag_delete(repo, name): """Remove a tag. :param repo: Path to repository :param name: Name of tag to remove """ with open_repo_closing(repo) as r: if isinstance(name, bytes): names = [name] elif isinstance(name, list): names = name else: raise TypeError("Unexpected tag name type %r" % name) for name in names: del r.refs[_make_tag_ref(name)] def reset(repo, mode, treeish="HEAD"): """Reset current HEAD to the specified state. :param repo: Path to repository :param mode: Mode ("hard", "soft", "mixed") :param treeish: Treeish to reset to """ if mode != "hard": raise ValueError("hard is the only mode currently supported") with open_repo_closing(repo) as r: tree = parse_tree(r, treeish) r.reset_index(tree.id) def push(repo, remote_location, refspecs, outstream=default_bytes_out_stream, errstream=default_bytes_err_stream, **kwargs): """Remote push with dulwich via dulwich.client :param repo: Path to repository :param remote_location: Location of the remote :param refspecs: Refs to push to remote :param outstream: A stream file to write output :param errstream: A stream file to write errors """ # Open the repo with open_repo_closing(repo) as r: # Get the client and path client, path = get_transport_and_path( remote_location, config=r.get_config_stack(), **kwargs) selected_refs = [] def update_refs(refs): selected_refs.extend(parse_reftuples(r.refs, refs, refspecs)) new_refs = {} # TODO: Handle selected_refs == {None: None} for (lh, rh, force) in selected_refs: if lh is None: new_refs[rh] = ZERO_SHA else: new_refs[rh] = r.refs[lh] return new_refs err_encoding = getattr(errstream, 'encoding', None) or DEFAULT_ENCODING remote_location_bytes = client.get_url(path).encode(err_encoding) try: client.send_pack( path, update_refs, generate_pack_data=r.object_store.generate_pack_data, progress=errstream.write) errstream.write( b"Push to " + remote_location_bytes + b" successful.\n") except (UpdateRefsError, SendPackError) as e: errstream.write(b"Push to " + remote_location_bytes + b" failed -> " + e.message.encode(err_encoding) + b"\n") def pull(repo, remote_location=None, refspecs=None, outstream=default_bytes_out_stream, errstream=default_bytes_err_stream, **kwargs): """Pull from remote via dulwich.client :param repo: Path to repository :param remote_location: Location of the remote :param refspec: refspecs to fetch :param outstream: A stream file to write to output :param errstream: A stream file to write to errors """ # Open the repo with open_repo_closing(repo) as r: if remote_location is None: # TODO(jelmer): Lookup 'remote' for current branch in config raise NotImplementedError( "looking up remote from branch config not supported yet") if refspecs is None: refspecs = [b"HEAD"] selected_refs = [] def determine_wants(remote_refs): selected_refs.extend( parse_reftuples(remote_refs, r.refs, refspecs)) return [remote_refs[lh] for (lh, rh, force) in selected_refs] client, path = get_transport_and_path( remote_location, config=r.get_config_stack(), **kwargs) fetch_result = client.fetch( path, r, progress=errstream.write, determine_wants=determine_wants) for (lh, rh, force) in selected_refs: r.refs[rh] = fetch_result.refs[lh] if selected_refs: r[b'HEAD'] = fetch_result.refs[selected_refs[0][1]] # Perform 'git checkout .' - syncs staged changes tree = r[b"HEAD"].tree r.reset_index(tree=tree) def status(repo=".", ignored=False): """Returns staged, unstaged, and untracked changes relative to the HEAD. :param repo: Path to repository or repository object :param ignored: Whether to include ignored files in `untracked` :return: GitStatus tuple, staged - list of staged paths (diff index/HEAD) unstaged - list of unstaged paths (diff index/working-tree) untracked - list of untracked, un-ignored & non-.git paths """ with open_repo_closing(repo) as r: # 1. Get status of staged tracked_changes = get_tree_changes(r) # 2. Get status of unstaged index = r.open_index() unstaged_changes = list(get_unstaged_changes(index, r.path)) ignore_manager = IgnoreFilterManager.from_repo(r) untracked_paths = get_untracked_paths(r.path, r.path, index) if ignored: untracked_changes = list(untracked_paths) else: untracked_changes = [ p for p in untracked_paths if not ignore_manager.is_ignored(p)] return GitStatus(tracked_changes, unstaged_changes, untracked_changes) def get_untracked_paths(frompath, basepath, index): """Get untracked paths. ;param frompath: Path to walk :param basepath: Path to compare to :param index: Index to check against """ # If nothing is specified, add all non-ignored files. for dirpath, dirnames, filenames in os.walk(frompath): # Skip .git and below. if '.git' in dirnames: dirnames.remove('.git') if dirpath != basepath: continue if '.git' in filenames: filenames.remove('.git') if dirpath != basepath: continue for filename in filenames: ap = os.path.join(dirpath, filename) ip = path_to_tree_path(basepath, ap) if ip not in index: yield os.path.relpath(ap, frompath) def get_tree_changes(repo): """Return add/delete/modify changes to tree by comparing index to HEAD. :param repo: repo path or object :return: dict with lists for each type of change """ with open_repo_closing(repo) as r: index = r.open_index() # Compares the Index to the HEAD & determines changes # Iterate through the changes and report add/delete/modify # TODO: call out to dulwich.diff_tree somehow. tracked_changes = { 'add': [], 'delete': [], 'modify': [], } try: tree_id = r[b'HEAD'].tree except KeyError: tree_id = None for change in index.changes_from_tree(r.object_store, tree_id): if not change[0][0]: tracked_changes['add'].append(change[0][1]) elif not change[0][1]: tracked_changes['delete'].append(change[0][0]) elif change[0][0] == change[0][1]: tracked_changes['modify'].append(change[0][0]) else: raise AssertionError('git mv ops not yet supported') return tracked_changes def daemon(path=".", address=None, port=None): """Run a daemon serving Git requests over TCP/IP. :param path: Path to the directory to serve. :param address: Optional address to listen on (defaults to ::) :param port: Optional port to listen on (defaults to TCP_GIT_PORT) """ # TODO(jelmer): Support git-daemon-export-ok and --export-all. backend = FileSystemBackend(path) server = TCPGitServer(backend, address, port) server.serve_forever() def web_daemon(path=".", address=None, port=None): """Run a daemon serving Git requests over HTTP. :param path: Path to the directory to serve :param address: Optional address to listen on (defaults to ::) :param port: Optional port to listen on (defaults to 80) """ from dulwich.web import ( make_wsgi_chain, make_server, WSGIRequestHandlerLogger, WSGIServerLogger) backend = FileSystemBackend(path) app = make_wsgi_chain(backend) server = make_server(address, port, app, handler_class=WSGIRequestHandlerLogger, server_class=WSGIServerLogger) server.serve_forever() def upload_pack(path=".", inf=None, outf=None): """Upload a pack file after negotiating its contents using smart protocol. :param path: Path to the repository :param inf: Input stream to communicate with client :param outf: Output stream to communicate with client """ if outf is None: outf = getattr(sys.stdout, 'buffer', sys.stdout) if inf is None: inf = getattr(sys.stdin, 'buffer', sys.stdin) path = os.path.expanduser(path) backend = FileSystemBackend(path) def send_fn(data): outf.write(data) outf.flush() proto = Protocol(inf.read, send_fn) handler = UploadPackHandler(backend, [path], proto) # FIXME: Catch exceptions and write a single-line summary to outf. handler.handle() return 0 def receive_pack(path=".", inf=None, outf=None): """Receive a pack file after negotiating its contents using smart protocol. :param path: Path to the repository :param inf: Input stream to communicate with client :param outf: Output stream to communicate with client """ if outf is None: outf = getattr(sys.stdout, 'buffer', sys.stdout) if inf is None: inf = getattr(sys.stdin, 'buffer', sys.stdin) path = os.path.expanduser(path) backend = FileSystemBackend(path) def send_fn(data): outf.write(data) outf.flush() proto = Protocol(inf.read, send_fn) handler = ReceivePackHandler(backend, [path], proto) # FIXME: Catch exceptions and write a single-line summary to outf. handler.handle() return 0 def _make_branch_ref(name): if getattr(name, 'encode', None): name = name.encode(DEFAULT_ENCODING) return b"refs/heads/" + name def _make_tag_ref(name): if getattr(name, 'encode', None): name = name.encode(DEFAULT_ENCODING) return b"refs/tags/" + name def branch_delete(repo, name): """Delete a branch. :param repo: Path to the repository :param name: Name of the branch """ with open_repo_closing(repo) as r: if isinstance(name, list): names = name else: names = [name] for name in names: del r.refs[_make_branch_ref(name)] def branch_create(repo, name, objectish=None, force=False): """Create a branch. :param repo: Path to the repository :param name: Name of the new branch :param objectish: Target object to point new branch at (defaults to HEAD) :param force: Force creation of branch, even if it already exists """ with open_repo_closing(repo) as r: if objectish is None: objectish = "HEAD" object = parse_object(r, objectish) refname = _make_branch_ref(name) ref_message = b"branch: Created from " + objectish.encode('utf-8') if force: r.refs.set_if_equals(refname, None, object.id, message=ref_message) else: if not r.refs.add_if_new(refname, object.id, message=ref_message): raise KeyError("Branch with name %s already exists." % name) def branch_list(repo): """List all branches. :param repo: Path to the repository """ with open_repo_closing(repo) as r: return r.refs.keys(base=b"refs/heads/") def fetch(repo, remote_location, remote_name=b'origin', outstream=sys.stdout, - errstream=default_bytes_err_stream, message=None, **kwargs): + errstream=default_bytes_err_stream, message=None, depth=None, + **kwargs): """Fetch objects from a remote server. :param repo: Path to the repository :param remote_location: String identifying a remote server :param remote_name: Name for remote server :param outstream: Output stream (defaults to stdout) :param errstream: Error stream (defaults to stderr) :param message: Reflog message (defaults to b"fetch: from ") + :param depth: Depth to fetch at :return: Dictionary with refs on the remote """ if message is None: message = b'fetch: from ' + remote_location.encode("utf-8") with open_repo_closing(repo) as r: client, path = get_transport_and_path( remote_location, config=r.get_config_stack(), **kwargs) - fetch_result = client.fetch(path, r, progress=errstream.write) + fetch_result = client.fetch(path, r, progress=errstream.write, + depth=depth) stripped_refs = strip_peeled_refs(fetch_result.refs) branches = { n[len(b'refs/heads/'):]: v for (n, v) in stripped_refs.items() if n.startswith(b'refs/heads/')} r.refs.import_refs( b'refs/remotes/' + remote_name, branches, message=message) tags = { n[len(b'refs/tags/'):]: v for (n, v) in stripped_refs.items() if n.startswith(b'refs/tags/') and not n.endswith(ANNOTATED_TAG_SUFFIX)} r.refs.import_refs(b'refs/tags', tags, message=message) return fetch_result.refs def ls_remote(remote, config=None, **kwargs): """List the refs in a remote. :param remote: Remote repository location :param config: Configuration to use :return: Dictionary with remote refs """ if config is None: config = StackedConfig.default() client, host_path = get_transport_and_path(remote, config=config, **kwargs) return client.get_refs(host_path) def repack(repo): """Repack loose files in a repository. Currently this only packs loose objects. :param repo: Path to the repository """ with open_repo_closing(repo) as r: r.object_store.pack_loose_objects() def pack_objects(repo, object_ids, packf, idxf, delta_window_size=None): """Pack objects into a file. :param repo: Path to the repository :param object_ids: List of object ids to write :param packf: File-like object to write to :param idxf: File-like object to write to (can be None) """ with open_repo_closing(repo) as r: entries, data_sum = write_pack_objects( packf, r.object_store.iter_shas((oid, None) for oid in object_ids), delta_window_size=delta_window_size) if idxf is not None: entries = sorted([(k, v[0], v[1]) for (k, v) in entries.items()]) write_pack_index(idxf, entries, data_sum) def ls_tree(repo, treeish=b"HEAD", outstream=sys.stdout, recursive=False, name_only=False): """List contents of a tree. :param repo: Path to the repository :param tree_ish: Tree id to list :param outstream: Output stream (defaults to stdout) :param recursive: Whether to recursively list files :param name_only: Only print item name """ def list_tree(store, treeid, base): for (name, mode, sha) in store[treeid].iteritems(): if base: name = posixpath.join(base, name) if name_only: outstream.write(name + b"\n") else: outstream.write(pretty_format_tree_entry(name, mode, sha)) if stat.S_ISDIR(mode) and recursive: list_tree(store, sha, name) with open_repo_closing(repo) as r: tree = parse_tree(r, treeish) list_tree(r.object_store, tree.id, "") def remote_add(repo, name, url): """Add a remote. :param repo: Path to the repository :param name: Remote name :param url: Remote URL """ if not isinstance(name, bytes): name = name.encode(DEFAULT_ENCODING) if not isinstance(url, bytes): url = url.encode(DEFAULT_ENCODING) with open_repo_closing(repo) as r: c = r.get_config() section = (b'remote', name) if c.has_section(section): raise RemoteExists(section) c.set(section, b"url", url) c.write_to_path() def check_ignore(repo, paths, no_index=False): """Debug gitignore files. :param repo: Path to the repository :param paths: List of paths to check for :param no_index: Don't check index :return: List of ignored files """ with open_repo_closing(repo) as r: index = r.open_index() ignore_manager = IgnoreFilterManager.from_repo(r) for path in paths: if not no_index and path_to_tree_path(r.path, path) in index: continue if os.path.isabs(path): path = os.path.relpath(path, r.path) if ignore_manager.is_ignored(path): yield path def update_head(repo, target, detached=False, new_branch=None): """Update HEAD to point at a new branch/commit. Note that this does not actually update the working tree. :param repo: Path to the repository :param detach: Create a detached head :param target: Branch or committish to switch to :param new_branch: New branch to create """ with open_repo_closing(repo) as r: if new_branch is not None: to_set = _make_branch_ref(new_branch) else: to_set = b"HEAD" if detached: # TODO(jelmer): Provide some way so that the actual ref gets # updated rather than what it points to, so the delete isn't # necessary. del r.refs[to_set] r.refs[to_set] = parse_commit(r, target).id else: r.refs.set_symbolic_ref(to_set, parse_ref(r, target)) if new_branch is not None: r.refs.set_symbolic_ref(b"HEAD", to_set) def check_mailmap(repo, contact): """Check canonical name and email of contact. :param repo: Path to the repository :param contact: Contact name and/or email :return: Canonical contact data """ with open_repo_closing(repo) as r: from dulwich.mailmap import Mailmap import errno try: mailmap = Mailmap.from_path(os.path.join(r.path, '.mailmap')) except IOError as e: if e.errno != errno.ENOENT: raise mailmap = Mailmap() return mailmap.lookup(contact) def fsck(repo): """Check a repository. :param repo: A path to the repository :return: Iterator over errors/warnings """ with open_repo_closing(repo) as r: # TODO(jelmer): check pack files # TODO(jelmer): check graph # TODO(jelmer): check refs for sha in r.object_store: o = r.object_store[sha] try: o.check() except Exception as e: yield (sha, e) def stash_list(repo): """List all stashes in a repository.""" with open_repo_closing(repo) as r: from dulwich.stash import Stash stash = Stash.from_repo(r) return enumerate(list(stash.stashes())) def stash_push(repo): """Push a new stash onto the stack.""" with open_repo_closing(repo) as r: from dulwich.stash import Stash stash = Stash.from_repo(r) stash.push() def stash_pop(repo): """Pop a new stash from the stack.""" with open_repo_closing(repo) as r: from dulwich.stash import Stash stash = Stash.from_repo(r) stash.pop() def ls_files(repo): """List all files in an index.""" with open_repo_closing(repo) as r: return sorted(r.open_index()) def describe(repo): """Describe the repository version. :param projdir: git repository root :returns: a string description of the current git revision Examples: "gabcdefh", "v0.1" or "v0.1-5-gabcdefh". """ # Get the repository with open_repo_closing(repo) as r: # Get a list of all tags refs = r.get_refs() tags = {} for key, value in refs.items(): key = key.decode() obj = r.get_object(value) if u'tags' not in key: continue _, tag = key.rsplit(u'/', 1) try: commit = obj.object except AttributeError: continue else: commit = r.get_object(commit[1]) tags[tag] = [ datetime.datetime(*time.gmtime(commit.commit_time)[:6]), commit.id.decode('ascii'), ] sorted_tags = sorted(tags.items(), key=lambda tag: tag[1][0], reverse=True) # If there are no tags, return the current commit if len(sorted_tags) == 0: return 'g{}'.format(r[r.head()].id.decode('ascii')[:7]) # We're now 0 commits from the top commit_count = 0 # Get the latest commit latest_commit = r[r.head()] # Walk through all commits walker = r.get_walker() for entry in walker: # Check if tag commit_id = entry.commit.id.decode('ascii') for tag in sorted_tags: tag_name = tag[0] tag_commit = tag[1][1] if commit_id == tag_commit: if commit_count == 0: return tag_name else: return '{}-{}-g{}'.format( tag_name, commit_count, latest_commit.id.decode('ascii')[:7]) commit_count += 1 # Return plain commit if no parent tag can be found return 'g{}'.format(latest_commit.id.decode('ascii')[:7]) + + +def get_object_by_path(repo, path, committish=None): + """Get an object by path. + + :param repo: A path to the repository + :param path: Path to look up + :param committish: Commit to look up path in + :return: A `ShaFile` object + """ + if committish is None: + committish = "HEAD" + # Get the repository + with open_repo_closing(repo) as r: + commit = parse_commit(repo, committish) + base_tree = commit.tree + if not isinstance(path, bytes): + path = path.encode(commit.encoding or DEFAULT_ENCODING) + (mode, sha) = tree_lookup_path( + r.object_store.__getitem__, + base_tree, path) + return r[sha] + + +def write_tree(repo): + """Write a tree object from the index. + + :param repo: Repository for which to write tree + :return: tree id for the tree that was written + """ + with open_repo_closing(repo) as r: + return r.open_index().commit(r.object_store) diff --git a/dulwich/refs.py b/dulwich/refs.py index 89c4cfdb..88dea193 100644 --- a/dulwich/refs.py +++ b/dulwich/refs.py @@ -1,922 +1,932 @@ # refs.py -- For dealing with git refs # Copyright (C) 2008-2013 Jelmer Vernooij # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """Ref handling. """ import errno import os import sys from dulwich.errors import ( PackedRefsException, RefFormatError, ) from dulwich.objects import ( git_line, valid_hexsha, ZERO_SHA, ) from dulwich.file import ( GitFile, ensure_dir_exists, ) SYMREF = b'ref: ' LOCAL_BRANCH_PREFIX = b'refs/heads/' LOCAL_TAG_PREFIX = b'refs/tags/' BAD_REF_CHARS = set(b'\177 ~^:?*[') ANNOTATED_TAG_SUFFIX = b'^{}' def parse_symref_value(contents): """Parse a symref value. :param contents: Contents to parse :return: Destination """ if contents.startswith(SYMREF): return contents[len(SYMREF):].rstrip(b'\r\n') raise ValueError(contents) def check_ref_format(refname): """Check if a refname is correctly formatted. Implements all the same rules as git-check-ref-format[1]. [1] http://www.kernel.org/pub/software/scm/git/docs/git-check-ref-format.html :param refname: The refname to check :return: True if refname is valid, False otherwise """ # These could be combined into one big expression, but are listed # separately to parallel [1]. if b'/.' in refname or refname.startswith(b'.'): return False if b'/' not in refname: return False if b'..' in refname: return False for i, c in enumerate(refname): if ord(refname[i:i+1]) < 0o40 or c in BAD_REF_CHARS: return False if refname[-1] in b'/.': return False if refname.endswith(b'.lock'): return False if b'@{' in refname: return False if b'\\' in refname: return False return True class RefsContainer(object): """A container for refs.""" def __init__(self, logger=None): self._logger = logger def _log(self, ref, old_sha, new_sha, committer=None, timestamp=None, timezone=None, message=None): if self._logger is None: return if message is None: return self._logger(ref, old_sha, new_sha, committer, timestamp, timezone, message) def set_symbolic_ref(self, name, other, committer=None, timestamp=None, timezone=None, message=None): """Make a ref point at another ref. :param name: Name of the ref to set :param other: Name of the ref to point at :param message: Optional message """ raise NotImplementedError(self.set_symbolic_ref) def get_packed_refs(self): """Get contents of the packed-refs file. :return: Dictionary mapping ref names to SHA1s :note: Will return an empty dictionary when no packed-refs file is present. """ raise NotImplementedError(self.get_packed_refs) def get_peeled(self, name): """Return the cached peeled value of a ref, if available. :param name: Name of the ref to peel :return: The peeled value of the ref. If the ref is known not point to a tag, this will be the SHA the ref refers to. If the ref may point to a tag, but no cached information is available, None is returned. """ return None def import_refs(self, base, other, committer=None, timestamp=None, timezone=None, message=None): for name, value in other.items(): self.set_if_equals(b'/'.join((base, name)), None, value, message=message) def allkeys(self): """All refs present in this container.""" raise NotImplementedError(self.allkeys) def keys(self, base=None): """Refs present in this container. :param base: An optional base to return refs under. :return: An unsorted set of valid refs in this container, including packed refs. """ if base is not None: return self.subkeys(base) else: return self.allkeys() def subkeys(self, base): """Refs present in this container under a base. :param base: The base to return refs under. :return: A set of valid refs in this container under the base; the base prefix is stripped from the ref names returned. """ keys = set() base_len = len(base) + 1 for refname in self.allkeys(): if refname.startswith(base): keys.add(refname[base_len:]) return keys def as_dict(self, base=None): """Return the contents of this container as a dictionary. """ ret = {} keys = self.keys(base) if base is None: base = b'' else: base = base.rstrip(b'/') for key in keys: try: ret[key] = self[(base + b'/' + key).strip(b'/')] except KeyError: continue # Unable to resolve return ret def _check_refname(self, name): """Ensure a refname is valid and lives in refs or is HEAD. HEAD is not a valid refname according to git-check-ref-format, but this class needs to be able to touch HEAD. Also, check_ref_format expects refnames without the leading 'refs/', but this class requires that so it cannot touch anything outside the refs dir (or HEAD). :param name: The name of the reference. :raises KeyError: if a refname is not HEAD or is otherwise not valid. """ if name in (b'HEAD', b'refs/stash'): return if not name.startswith(b'refs/') or not check_ref_format(name[5:]): raise RefFormatError(name) def read_ref(self, refname): """Read a reference without following any references. :param refname: The name of the reference :return: The contents of the ref file, or None if it does not exist. """ contents = self.read_loose_ref(refname) if not contents: contents = self.get_packed_refs().get(refname, None) return contents def read_loose_ref(self, name): """Read a loose reference and return its contents. :param name: the refname to read :return: The contents of the ref file, or None if it does not exist. """ raise NotImplementedError(self.read_loose_ref) def follow(self, name): """Follow a reference name. :return: a tuple of (refnames, sha), wheres refnames are the names of references in the chain """ contents = SYMREF + name depth = 0 refnames = [] while contents.startswith(SYMREF): refname = contents[len(SYMREF):] refnames.append(refname) contents = self.read_ref(refname) if not contents: break depth += 1 if depth > 5: raise KeyError(name) return refnames, contents def _follow(self, name): import warnings warnings.warn( "RefsContainer._follow is deprecated. Use RefsContainer.follow " "instead.", DeprecationWarning) refnames, contents = self.follow(name) if not refnames: return (None, contents) return (refnames[-1], contents) def __contains__(self, refname): if self.read_ref(refname): return True return False def __getitem__(self, name): """Get the SHA1 for a reference name. This method follows all symbolic references. """ _, sha = self.follow(name) if sha is None: raise KeyError(name) return sha def set_if_equals(self, name, old_ref, new_ref, committer=None, timestamp=None, timezone=None, message=None): """Set a refname to new_ref only if it currently equals old_ref. This method follows all symbolic references if applicable for the subclass, and can be used to perform an atomic compare-and-swap operation. :param name: The refname to set. :param old_ref: The old sha the refname must refer to, or None to set unconditionally. :param new_ref: The new sha the refname will refer to. :param message: Message for reflog :return: True if the set was successful, False otherwise. """ raise NotImplementedError(self.set_if_equals) def add_if_new(self, name, ref): """Add a new reference only if it does not already exist. :param name: Ref name :param ref: Ref value :param message: Message for reflog """ raise NotImplementedError(self.add_if_new) def __setitem__(self, name, ref): """Set a reference name to point to the given SHA1. This method follows all symbolic references if applicable for the subclass. :note: This method unconditionally overwrites the contents of a reference. To update atomically only if the reference has not changed, use set_if_equals(). :param name: The refname to set. :param ref: The new sha the refname will refer to. """ self.set_if_equals(name, None, ref) def remove_if_equals(self, name, old_ref, committer=None, timestamp=None, timezone=None, message=None): """Remove a refname only if it currently equals old_ref. This method does not follow symbolic references, even if applicable for the subclass. It can be used to perform an atomic compare-and-delete operation. :param name: The refname to delete. :param old_ref: The old sha the refname must refer to, or None to delete unconditionally. :param message: Message for reflog :return: True if the delete was successful, False otherwise. """ raise NotImplementedError(self.remove_if_equals) def __delitem__(self, name): """Remove a refname. This method does not follow symbolic references, even if applicable for the subclass. :note: This method unconditionally deletes the contents of a reference. To delete atomically only if the reference has not changed, use remove_if_equals(). :param name: The refname to delete. """ self.remove_if_equals(name, None) def get_symrefs(self): """Get a dict with all symrefs in this container. :return: Dictionary mapping source ref to target ref """ ret = {} for src in self.allkeys(): try: dst = parse_symref_value(self.read_ref(src)) except ValueError: pass else: ret[src] = dst return ret class DictRefsContainer(RefsContainer): """RefsContainer backed by a simple dict. This container does not support symbolic or packed references and is not threadsafe. """ def __init__(self, refs, logger=None): super(DictRefsContainer, self).__init__(logger=logger) self._refs = refs self._peeled = {} def allkeys(self): return self._refs.keys() def read_loose_ref(self, name): return self._refs.get(name, None) def get_packed_refs(self): return {} def set_symbolic_ref(self, name, other, committer=None, timestamp=None, timezone=None, message=None): old = self.follow(name)[-1] self._refs[name] = SYMREF + other self._log(name, old, old, committer=committer, timestamp=timestamp, timezone=timezone, message=message) def set_if_equals(self, name, old_ref, new_ref, committer=None, timestamp=None, timezone=None, message=None): if old_ref is not None and self._refs.get(name, ZERO_SHA) != old_ref: return False realnames, _ = self.follow(name) for realname in realnames: self._check_refname(realname) old = self._refs.get(realname) self._refs[realname] = new_ref self._log(realname, old, new_ref, committer=committer, timestamp=timestamp, timezone=timezone, message=message) return True def add_if_new(self, name, ref, committer=None, timestamp=None, timezone=None, message=None): if name in self._refs: return False self._refs[name] = ref self._log(name, None, ref, committer=committer, timestamp=timestamp, timezone=timezone, message=message) return True def remove_if_equals(self, name, old_ref, committer=None, timestamp=None, timezone=None, message=None): if old_ref is not None and self._refs.get(name, ZERO_SHA) != old_ref: return False try: old = self._refs.pop(name) except KeyError: pass else: self._log(name, old, None, committer=committer, timestamp=timestamp, timezone=timezone, message=message) return True def get_peeled(self, name): return self._peeled.get(name) def _update(self, refs): """Update multiple refs; intended only for testing.""" # TODO(dborowitz): replace this with a public function that uses # set_if_equal. self._refs.update(refs) def _update_peeled(self, peeled): """Update cached peeled refs; intended only for testing.""" self._peeled.update(peeled) class InfoRefsContainer(RefsContainer): """Refs container that reads refs from a info/refs file.""" def __init__(self, f): self._refs = {} self._peeled = {} for l in f.readlines(): sha, name = l.rstrip(b'\n').split(b'\t') if name.endswith(ANNOTATED_TAG_SUFFIX): name = name[:-3] if not check_ref_format(name): raise ValueError("invalid ref name %r" % name) self._peeled[name] = sha else: if not check_ref_format(name): raise ValueError("invalid ref name %r" % name) self._refs[name] = sha def allkeys(self): return self._refs.keys() def read_loose_ref(self, name): return self._refs.get(name, None) def get_packed_refs(self): return {} def get_peeled(self, name): try: return self._peeled[name] except KeyError: return self._refs[name] class DiskRefsContainer(RefsContainer): """Refs container that reads refs from disk.""" def __init__(self, path, worktree_path=None, logger=None): super(DiskRefsContainer, self).__init__(logger=logger) if getattr(path, 'encode', None) is not None: path = path.encode(sys.getfilesystemencoding()) self.path = path if worktree_path is None: worktree_path = path if getattr(worktree_path, 'encode', None) is not None: worktree_path = worktree_path.encode(sys.getfilesystemencoding()) self.worktree_path = worktree_path self._packed_refs = None self._peeled_refs = None def __repr__(self): return "%s(%r)" % (self.__class__.__name__, self.path) def subkeys(self, base): subkeys = set() path = self.refpath(base) for root, unused_dirs, files in os.walk(path): dir = root[len(path):] if os.path.sep != '/': dir = dir.replace(os.path.sep.encode( sys.getfilesystemencoding()), b"/") dir = dir.strip(b'/') for filename in files: refname = b"/".join(([dir] if dir else []) + [filename]) # check_ref_format requires at least one /, so we prepend the # base before calling it. if check_ref_format(base + b'/' + refname): subkeys.add(refname) for key in self.get_packed_refs(): if key.startswith(base): subkeys.add(key[len(base):].strip(b'/')) return subkeys def allkeys(self): allkeys = set() if os.path.exists(self.refpath(b'HEAD')): allkeys.add(b'HEAD') path = self.refpath(b'') refspath = self.refpath(b'refs') for root, unused_dirs, files in os.walk(refspath): dir = root[len(path):] if os.path.sep != '/': dir = dir.replace( os.path.sep.encode(sys.getfilesystemencoding()), b"/") for filename in files: refname = b"/".join([dir, filename]) if check_ref_format(refname): allkeys.add(refname) allkeys.update(self.get_packed_refs()) return allkeys def refpath(self, name): """Return the disk path of a ref. """ if os.path.sep != "/": name = name.replace( b"/", os.path.sep.encode(sys.getfilesystemencoding())) # TODO: as the 'HEAD' reference is working tree specific, it # should actually not be a part of RefsContainer if name == b'HEAD': return os.path.join(self.worktree_path, name) else: return os.path.join(self.path, name) def get_packed_refs(self): """Get contents of the packed-refs file. :return: Dictionary mapping ref names to SHA1s :note: Will return an empty dictionary when no packed-refs file is present. """ # TODO: invalidate the cache on repacking if self._packed_refs is None: # set both to empty because we want _peeled_refs to be # None if and only if _packed_refs is also None. self._packed_refs = {} self._peeled_refs = {} path = os.path.join(self.path, b'packed-refs') try: f = GitFile(path, 'rb') except IOError as e: if e.errno == errno.ENOENT: return {} raise with f: first_line = next(iter(f)).rstrip() if (first_line.startswith(b'# pack-refs') and b' peeled' in first_line): for sha, name, peeled in read_packed_refs_with_peeled(f): self._packed_refs[name] = sha if peeled: self._peeled_refs[name] = peeled else: f.seek(0) for sha, name in read_packed_refs(f): self._packed_refs[name] = sha return self._packed_refs def get_peeled(self, name): """Return the cached peeled value of a ref, if available. :param name: Name of the ref to peel :return: The peeled value of the ref. If the ref is known not point to a tag, this will be the SHA the ref refers to. If the ref may point to a tag, but no cached information is available, None is returned. """ self.get_packed_refs() if self._peeled_refs is None or name not in self._packed_refs: # No cache: no peeled refs were read, or this ref is loose return None if name in self._peeled_refs: return self._peeled_refs[name] else: # Known not peelable return self[name] def read_loose_ref(self, name): """Read a reference file and return its contents. If the reference file a symbolic reference, only read the first line of the file. Otherwise, only read the first 40 bytes. :param name: the refname to read, relative to refpath :return: The contents of the ref file, or None if the file does not exist. :raises IOError: if any other error occurs """ filename = self.refpath(name) try: with GitFile(filename, 'rb') as f: header = f.read(len(SYMREF)) if header == SYMREF: # Read only the first line return header + next(iter(f)).rstrip(b'\r\n') else: # Read only the first 40 bytes return header + f.read(40 - len(SYMREF)) except IOError as e: - if e.errno in (errno.ENOENT, errno.EISDIR): + if e.errno in (errno.ENOENT, errno.EISDIR, errno.ENOTDIR): return None raise def _remove_packed_ref(self, name): if self._packed_refs is None: return filename = os.path.join(self.path, b'packed-refs') # reread cached refs from disk, while holding the lock f = GitFile(filename, 'wb') try: self._packed_refs = None self.get_packed_refs() if name not in self._packed_refs: return del self._packed_refs[name] if name in self._peeled_refs: del self._peeled_refs[name] write_packed_refs(f, self._packed_refs, self._peeled_refs) f.close() finally: f.abort() def set_symbolic_ref(self, name, other, committer=None, timestamp=None, timezone=None, message=None): """Make a ref point at another ref. :param name: Name of the ref to set :param other: Name of the ref to point at :param message: Optional message to describe the change """ self._check_refname(name) self._check_refname(other) filename = self.refpath(name) f = GitFile(filename, 'wb') try: f.write(SYMREF + other + b'\n') sha = self.follow(name)[-1] self._log(name, sha, sha, committer=committer, timestamp=timestamp, timezone=timezone, message=message) except BaseException: f.abort() raise else: f.close() def set_if_equals(self, name, old_ref, new_ref, committer=None, timestamp=None, timezone=None, message=None): """Set a refname to new_ref only if it currently equals old_ref. This method follows all symbolic references, and can be used to perform an atomic compare-and-swap operation. :param name: The refname to set. :param old_ref: The old sha the refname must refer to, or None to set unconditionally. :param new_ref: The new sha the refname will refer to. :param message: Set message for reflog :return: True if the set was successful, False otherwise. """ self._check_refname(name) try: realnames, _ = self.follow(name) realname = realnames[-1] except (KeyError, IndexError): realname = name filename = self.refpath(realname) + + # make sure none of the ancestor folders is in packed refs + probe_ref = os.path.dirname(realname) + packed_refs = self.get_packed_refs() + while probe_ref: + if packed_refs.get(probe_ref, None) is not None: + raise OSError(errno.ENOTDIR, + 'Not a directory: {}'.format(filename)) + probe_ref = os.path.dirname(probe_ref) + ensure_dir_exists(os.path.dirname(filename)) with GitFile(filename, 'wb') as f: if old_ref is not None: try: # read again while holding the lock orig_ref = self.read_loose_ref(realname) if orig_ref is None: orig_ref = self.get_packed_refs().get( realname, ZERO_SHA) if orig_ref != old_ref: f.abort() return False except (OSError, IOError): f.abort() raise try: f.write(new_ref + b'\n') except (OSError, IOError): f.abort() raise self._log(realname, old_ref, new_ref, committer=committer, timestamp=timestamp, timezone=timezone, message=message) return True def add_if_new(self, name, ref, committer=None, timestamp=None, timezone=None, message=None): """Add a new reference only if it does not already exist. This method follows symrefs, and only ensures that the last ref in the chain does not exist. :param name: The refname to set. :param ref: The new sha the refname will refer to. :param message: Optional message for reflog :return: True if the add was successful, False otherwise. """ try: realnames, contents = self.follow(name) if contents is not None: return False realname = realnames[-1] except (KeyError, IndexError): realname = name self._check_refname(realname) filename = self.refpath(realname) ensure_dir_exists(os.path.dirname(filename)) with GitFile(filename, 'wb') as f: if os.path.exists(filename) or name in self.get_packed_refs(): f.abort() return False try: f.write(ref + b'\n') except (OSError, IOError): f.abort() raise else: self._log(name, None, ref, committer=committer, timestamp=timestamp, timezone=timezone, message=message) return True def remove_if_equals(self, name, old_ref, committer=None, timestamp=None, timezone=None, message=None): """Remove a refname only if it currently equals old_ref. This method does not follow symbolic references. It can be used to perform an atomic compare-and-delete operation. :param name: The refname to delete. :param old_ref: The old sha the refname must refer to, or None to delete unconditionally. :param message: Optional message :return: True if the delete was successful, False otherwise. """ self._check_refname(name) filename = self.refpath(name) ensure_dir_exists(os.path.dirname(filename)) f = GitFile(filename, 'wb') try: if old_ref is not None: orig_ref = self.read_loose_ref(name) if orig_ref is None: orig_ref = self.get_packed_refs().get(name, ZERO_SHA) if orig_ref != old_ref: return False # remove the reference file itself try: os.remove(filename) except OSError as e: if e.errno != errno.ENOENT: # may only be packed raise self._remove_packed_ref(name) self._log(name, old_ref, None, committer=committer, timestamp=timestamp, timezone=timezone, message=message) finally: # never write, we just wanted the lock f.abort() # outside of the lock, clean-up any parent directory that might now # be empty. this ensures that re-creating a reference of the same # name of what was previously a directory works as expected parent = name while True: try: parent, _ = parent.rsplit(b'/', 1) except ValueError: break parent_filename = self.refpath(parent) try: os.rmdir(parent_filename) - except OSError as e: + except OSError: # this can be caused by the parent directory being # removed by another process, being not empty, etc. # in any case, this is non fatal because we already # removed the reference, just ignore it break return True def _split_ref_line(line): """Split a single ref line into a tuple of SHA1 and name.""" fields = line.rstrip(b'\n\r').split(b' ') if len(fields) != 2: raise PackedRefsException("invalid ref line %r" % line) sha, name = fields if not valid_hexsha(sha): raise PackedRefsException("Invalid hex sha %r" % sha) if not check_ref_format(name): raise PackedRefsException("invalid ref name %r" % name) return (sha, name) def read_packed_refs(f): """Read a packed refs file. :param f: file-like object to read from :return: Iterator over tuples with SHA1s and ref names. """ for l in f: if l.startswith(b'#'): # Comment continue if l.startswith(b'^'): raise PackedRefsException( "found peeled ref in packed-refs without peeled") yield _split_ref_line(l) def read_packed_refs_with_peeled(f): """Read a packed refs file including peeled refs. Assumes the "# pack-refs with: peeled" line was already read. Yields tuples with ref names, SHA1s, and peeled SHA1s (or None). :param f: file-like object to read from, seek'ed to the second line """ last = None for line in f: if line[0] == b'#': continue line = line.rstrip(b'\r\n') if line.startswith(b'^'): if not last: raise PackedRefsException("unexpected peeled ref line") if not valid_hexsha(line[1:]): raise PackedRefsException("Invalid hex sha %r" % line[1:]) sha, name = _split_ref_line(last) last = None yield (sha, name, line[1:]) else: if last: sha, name = _split_ref_line(last) yield (sha, name, None) last = line if last: sha, name = _split_ref_line(last) yield (sha, name, None) def write_packed_refs(f, packed_refs, peeled_refs=None): """Write a packed refs file. :param f: empty file-like object to write to :param packed_refs: dict of refname to sha of packed refs to write :param peeled_refs: dict of refname to peeled value of sha """ if peeled_refs is None: peeled_refs = {} else: f.write(b'# pack-refs with: peeled\n') for refname in sorted(packed_refs.keys()): f.write(git_line(packed_refs[refname], refname)) if refname in peeled_refs: f.write(b'^' + peeled_refs[refname] + b'\n') def read_info_refs(f): ret = {} for l in f.readlines(): (sha, name) = l.rstrip(b"\r\n").split(b"\t", 1) ret[name] = sha return ret def write_info_refs(refs, store): """Generate info refs.""" for name, sha in sorted(refs.items()): # get_refs() includes HEAD as a special case, but we don't want to # advertise it if name == b'HEAD': continue try: o = store[sha] except KeyError: continue peeled = store.peel_sha(sha) yield o.id + b'\t' + name + b'\n' if o.id != peeled.id: yield peeled.id + b'\t' + name + ANNOTATED_TAG_SUFFIX + b'\n' def is_local_branch(x): return x.startswith(LOCAL_BRANCH_PREFIX) def strip_peeled_refs(refs): """Remove all peeled refs""" return {ref: sha for (ref, sha) in refs.items() if not ref.endswith(ANNOTATED_TAG_SUFFIX)} diff --git a/dulwich/repo.py b/dulwich/repo.py index 0ae1ff83..e6f2f214 100644 --- a/dulwich/repo.py +++ b/dulwich/repo.py @@ -1,1288 +1,1356 @@ # repo.py -- For dealing with git repositories. # Copyright (C) 2007 James Westby # Copyright (C) 2008-2013 Jelmer Vernooij # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """Repository access. This module contains the base class for git repositories (BaseRepo) and an implementation which uses a repository on local disk (Repo). """ from io import BytesIO import errno import os import sys import stat import time from dulwich.errors import ( NoIndexPresent, NotBlobError, NotCommitError, NotGitRepository, NotTreeError, NotTagError, CommitError, RefFormatError, HookError, ) from dulwich.file import ( GitFile, ) from dulwich.object_store import ( DiskObjectStore, MemoryObjectStore, ObjectStoreGraphWalker, ) from dulwich.objects import ( check_hexsha, Blob, Commit, ShaFile, Tag, Tree, ) from dulwich.pack import ( pack_objects_to_data, ) from dulwich.hooks import ( PreCommitShellHook, PostCommitShellHook, CommitMsgShellHook, ) from dulwich.refs import ( # noqa: F401 + ANNOTATED_TAG_SUFFIX, check_ref_format, RefsContainer, DictRefsContainer, InfoRefsContainer, DiskRefsContainer, read_packed_refs, read_packed_refs_with_peeled, write_packed_refs, SYMREF, ) import warnings CONTROLDIR = '.git' OBJECTDIR = 'objects' REFSDIR = 'refs' REFSDIR_TAGS = 'tags' REFSDIR_HEADS = 'heads' INDEX_FILENAME = "index" COMMONDIR = 'commondir' GITDIR = 'gitdir' WORKTREES = 'worktrees' BASE_DIRECTORIES = [ ["branches"], [REFSDIR], [REFSDIR, REFSDIR_TAGS], [REFSDIR, REFSDIR_HEADS], ["hooks"], ["info"] ] DEFAULT_REF = b'refs/heads/master' class InvalidUserIdentity(Exception): """User identity is not of the format 'user '""" def __init__(self, identity): self.identity = identity def check_user_identity(identity): """Verify that a user identity is formatted correctly. :param identity: User identity bytestring :raise InvalidUserIdentity: Raised when identity is invalid """ try: fst, snd = identity.split(b' <', 1) except ValueError: raise InvalidUserIdentity(identity) if b'>' not in snd: raise InvalidUserIdentity(identity) def parse_graftpoints(graftpoints): """Convert a list of graftpoints into a dict :param graftpoints: Iterator of graftpoint lines Each line is formatted as: []* Resulting dictionary is: : [*] https://git.wiki.kernel.org/index.php/GraftPoint """ grafts = {} for l in graftpoints: raw_graft = l.split(None, 1) commit = raw_graft[0] if len(raw_graft) == 2: parents = raw_graft[1].split() else: parents = [] for sha in [commit] + parents: check_hexsha(sha, 'Invalid graftpoint') grafts[commit] = parents return grafts def serialize_graftpoints(graftpoints): """Convert a dictionary of grafts into string The graft dictionary is: : [*] Each line is formatted as: []* https://git.wiki.kernel.org/index.php/GraftPoint """ graft_lines = [] for commit, parents in graftpoints.items(): if parents: graft_lines.append(commit + b' ' + b' '.join(parents)) else: graft_lines.append(commit) return b'\n'.join(graft_lines) class BaseRepo(object): """Base class for a git repository. :ivar object_store: Dictionary-like object for accessing the objects :ivar refs: Dictionary-like object with the refs in this repository """ def __init__(self, object_store, refs): """Open a repository. This shouldn't be called directly, but rather through one of the base classes, such as MemoryRepo or Repo. :param object_store: Object store to use :param refs: Refs container to use """ self.object_store = object_store self.refs = refs self._graftpoints = {} self.hooks = {} def _determine_file_mode(self): """Probe the file-system to determine whether permissions can be trusted. :return: True if permissions can be trusted, False otherwise. """ raise NotImplementedError(self._determine_file_mode) def _init_files(self, bare): """Initialize a default set of named files.""" from dulwich.config import ConfigFile self._put_named_file('description', b"Unnamed repository") f = BytesIO() cf = ConfigFile() cf.set("core", "repositoryformatversion", "0") if self._determine_file_mode(): cf.set("core", "filemode", True) else: cf.set("core", "filemode", False) cf.set("core", "bare", bare) cf.set("core", "logallrefupdates", True) cf.write_to_file(f) self._put_named_file('config', f.getvalue()) self._put_named_file(os.path.join('info', 'exclude'), b'') def get_named_file(self, path): """Get a file from the control dir with a specific name. Although the filename should be interpreted as a filename relative to the control dir in a disk-based Repo, the object returned need not be pointing to a file in that location. :param path: The path to the file, relative to the control dir. :return: An open file object, or None if the file does not exist. """ raise NotImplementedError(self.get_named_file) def _put_named_file(self, path, contents): """Write a file to the control dir with the given name and contents. :param path: The path to the file, relative to the control dir. :param contents: A string to write to the file. """ raise NotImplementedError(self._put_named_file) + def _del_named_file(self, path): + """Delete a file in the contrl directory with the given name.""" + raise NotImplementedError(self._del_named_file) + def open_index(self): """Open the index for this repository. :raise NoIndexPresent: If no index is present :return: The matching `Index` """ raise NotImplementedError(self.open_index) - def fetch(self, target, determine_wants=None, progress=None): + def fetch(self, target, determine_wants=None, progress=None, depth=None): """Fetch objects into another repository. :param target: The target repository :param determine_wants: Optional function to determine what refs to fetch. :param progress: Optional progress function + :param depth: Optional shallow fetch depth :return: The local refs """ if determine_wants is None: determine_wants = target.object_store.determine_wants_all count, pack_data = self.fetch_pack_data( - determine_wants, target.get_graph_walker(), progress) + determine_wants, target.get_graph_walker(), progress=progress, + depth=depth) target.object_store.add_pack_data(count, pack_data, progress) return self.get_refs() def fetch_pack_data(self, determine_wants, graph_walker, progress, - get_tagged=None): + get_tagged=None, depth=None): """Fetch the pack data required for a set of revisions. :param determine_wants: Function that takes a dictionary with heads and returns the list of heads to fetch. :param graph_walker: Object that can iterate over the list of revisions to fetch and has an "ack" method that will be called to acknowledge that a revision is present. :param progress: Simple progress function that will be called with updated progress strings. :param get_tagged: Function that returns a dict of pointed-to sha -> tag sha for including tags. + :param depth: Shallow fetch depth :return: count and iterator over pack data """ # TODO(jelmer): Fetch pack data directly, don't create objects first. objects = self.fetch_objects(determine_wants, graph_walker, progress, - get_tagged) + get_tagged, depth=depth) return pack_objects_to_data(objects) def fetch_objects(self, determine_wants, graph_walker, progress, - get_tagged=None): + get_tagged=None, depth=None): """Fetch the missing objects required for a set of revisions. :param determine_wants: Function that takes a dictionary with heads and returns the list of heads to fetch. :param graph_walker: Object that can iterate over the list of revisions to fetch and has an "ack" method that will be called to acknowledge that a revision is present. :param progress: Simple progress function that will be called with updated progress strings. :param get_tagged: Function that returns a dict of pointed-to sha -> tag sha for including tags. + :param depth: Shallow fetch depth :return: iterator over objects, with __len__ implemented """ - wants = determine_wants(self.get_refs()) + if depth not in (None, 0): + raise NotImplementedError("depth not supported yet") + + refs = {} + for ref, sha in self.get_refs().items(): + try: + obj = self.object_store[sha] + except KeyError: + warnings.warn( + 'ref %s points at non-present sha %s' % ( + ref.decode('utf-8', 'replace'), sha.decode('ascii')), + UserWarning) + continue + else: + if isinstance(obj, Tag): + refs[ref + ANNOTATED_TAG_SUFFIX] = obj.object[1] + refs[ref] = sha + + wants = determine_wants(refs) if not isinstance(wants, list): raise TypeError("determine_wants() did not return a list") shallows = getattr(graph_walker, 'shallow', frozenset()) unshallows = getattr(graph_walker, 'unshallow', frozenset()) if wants == []: # TODO(dborowitz): find a way to short-circuit that doesn't change # this interface. if shallows or unshallows: # Do not send a pack in shallow short-circuit path return None return [] # If the graph walker is set up with an implementation that can # ACK/NAK to the wire, it will write data to the client through # this call as a side-effect. haves = self.object_store.find_common_revisions(graph_walker) # Deal with shallow requests separately because the haves do # not reflect what objects are missing if shallows or unshallows: # TODO: filter the haves commits from iter_shas. the specific # commits aren't missing. haves = [] def get_parents(commit): if commit.id in shallows: return [] return self.get_parents(commit.id, commit) return self.object_store.iter_shas( self.object_store.find_missing_objects( haves, wants, progress, get_tagged, get_parents=get_parents)) def get_graph_walker(self, heads=None): """Retrieve a graph walker. A graph walker is used by a remote repository (or proxy) to find out which objects are present in this repository. :param heads: Repository heads to use (optional) :return: A graph walker object """ if heads is None: heads = self.refs.as_dict(b'refs/heads').values() - return ObjectStoreGraphWalker(heads, self.get_parents) + return ObjectStoreGraphWalker( + heads, self.get_parents, shallow=self.get_shallow()) def get_refs(self): """Get dictionary with all refs. :return: A ``dict`` mapping ref names to SHA1s """ return self.refs.as_dict() def head(self): """Return the SHA1 pointed at by HEAD.""" return self.refs[b'HEAD'] def _get_object(self, sha, cls): assert len(sha) in (20, 40) ret = self.get_object(sha) if not isinstance(ret, cls): if cls is Commit: raise NotCommitError(ret) elif cls is Blob: raise NotBlobError(ret) elif cls is Tree: raise NotTreeError(ret) elif cls is Tag: raise NotTagError(ret) else: raise Exception("Type invalid: %r != %r" % ( ret.type_name, cls.type_name)) return ret def get_object(self, sha): """Retrieve the object with the specified SHA. :param sha: SHA to retrieve :return: A ShaFile object :raise KeyError: when the object can not be found """ return self.object_store[sha] def get_parents(self, sha, commit=None): """Retrieve the parents of a specific commit. If the specific commit is a graftpoint, the graft parents will be returned instead. :param sha: SHA of the commit for which to retrieve the parents :param commit: Optional commit matching the sha :return: List of parents """ try: return self._graftpoints[sha] except KeyError: if commit is None: commit = self[sha] return commit.parents def get_config(self): """Retrieve the config object. :return: `ConfigFile` object for the ``.git/config`` file. """ raise NotImplementedError(self.get_config) def get_description(self): """Retrieve the description for this repository. :return: String with the description of the repository as set by the user. """ raise NotImplementedError(self.get_description) def set_description(self, description): """Set the description for this repository. :param description: Text to set as description for this repository. """ raise NotImplementedError(self.set_description) def get_config_stack(self): """Return a config stack for this repository. This stack accesses the configuration for both this repository itself (.git/config) and the global configuration, which usually lives in ~/.gitconfig. :return: `Config` instance for this repository """ from dulwich.config import StackedConfig backends = [self.get_config()] + StackedConfig.default_backends() return StackedConfig(backends, writable=backends[0]) def get_shallow(self): """Get the set of shallow commits. :return: Set of shallow commits. """ - return set() + f = self.get_named_file('shallow') + if f is None: + return set() + with f: + return set(l.strip() for l in f) + + def update_shallow(self, new_shallow, new_unshallow): + """Update the list of shallow objects. + + :param new_shallow: Newly shallow objects + :param new_unshallow: Newly no longer shallow objects + """ + shallow = self.get_shallow() + if new_shallow: + shallow.update(new_shallow) + if new_unshallow: + shallow.difference_update(new_unshallow) + self._put_named_file( + 'shallow', + b''.join([sha + b'\n' for sha in shallow])) def get_peeled(self, ref): """Get the peeled value of a ref. :param ref: The refname to peel. :return: The fully-peeled SHA1 of a tag object, after peeling all intermediate tags; if the original ref does not point to a tag, this will equal the original SHA1. """ cached = self.refs.get_peeled(ref) if cached is not None: return cached return self.object_store.peel_sha(self.refs[ref]).id def get_walker(self, include=None, *args, **kwargs): """Obtain a walker for this repository. :param include: Iterable of SHAs of commits to include along with their ancestors. Defaults to [HEAD] :param exclude: Iterable of SHAs of commits to exclude along with their ancestors, overriding includes. :param order: ORDER_* constant specifying the order of results. Anything other than ORDER_DATE may result in O(n) memory usage. :param reverse: If True, reverse the order of output, requiring O(n) memory. :param max_entries: The maximum number of entries to yield, or None for no limit. :param paths: Iterable of file or subtree paths to show entries for. :param rename_detector: diff.RenameDetector object for detecting renames. :param follow: If True, follow path across renames/copies. Forces a default rename_detector. :param since: Timestamp to list commits after. :param until: Timestamp to list commits before. :param queue_cls: A class to use for a queue of commits, supporting the iterator protocol. The constructor takes a single argument, the Walker. :return: A `Walker` object """ from dulwich.walk import Walker if include is None: include = [self.head()] if isinstance(include, str): include = [include] kwargs['get_parents'] = lambda commit: self.get_parents( commit.id, commit) return Walker(self.object_store, include, *args, **kwargs) def __getitem__(self, name): """Retrieve a Git object by SHA1 or ref. :param name: A Git object SHA1 or a ref name :return: A `ShaFile` object, such as a Commit or Blob :raise KeyError: when the specified ref or object does not exist """ if not isinstance(name, bytes): raise TypeError("'name' must be bytestring, not %.80s" % type(name).__name__) if len(name) in (20, 40): try: return self.object_store[name] except (KeyError, ValueError): pass try: return self.object_store[self.refs[name]] except RefFormatError: raise KeyError(name) def __contains__(self, name): """Check if a specific Git object or ref is present. :param name: Git object SHA1 or ref name """ if len(name) in (20, 40): return name in self.object_store or name in self.refs else: return name in self.refs def __setitem__(self, name, value): """Set a ref. :param name: ref name :param value: Ref value - either a ShaFile object, or a hex sha """ if name.startswith(b"refs/") or name == b'HEAD': if isinstance(value, ShaFile): self.refs[name] = value.id elif isinstance(value, bytes): self.refs[name] = value else: raise TypeError(value) else: raise ValueError(name) def __delitem__(self, name): """Remove a ref. :param name: Name of the ref to remove """ if name.startswith(b"refs/") or name == b"HEAD": del self.refs[name] else: raise ValueError(name) - def _get_user_identity(self): + def _get_user_identity(self, config): """Determine the identity to use for new commits. """ user = os.environ.get("GIT_COMMITTER_NAME") email = os.environ.get("GIT_COMMITTER_EMAIL") - config = self.get_config_stack() if user is None: try: user = config.get(("user", ), "name") except KeyError: user = None if email is None: try: email = config.get(("user", ), "email") except KeyError: email = None if user is None: import getpass user = getpass.getuser().encode(sys.getdefaultencoding()) if email is None: import getpass import socket email = ("{}@{}".format(getpass.getuser(), socket.gethostname()) .encode(sys.getdefaultencoding())) return (user + b" <" + email + b">") def _add_graftpoints(self, updated_graftpoints): """Add or modify graftpoints :param updated_graftpoints: Dict of commit shas to list of parent shas """ # Simple validation for commit, parents in updated_graftpoints.items(): for sha in [commit] + parents: check_hexsha(sha, 'Invalid graftpoint') self._graftpoints.update(updated_graftpoints) def _remove_graftpoints(self, to_remove=[]): """Remove graftpoints :param to_remove: List of commit shas """ for sha in to_remove: del self._graftpoints[sha] + def _read_heads(self, name): + f = self.get_named_file(name) + if f is None: + return [] + with f: + return [l.strip() for l in f.readlines() if l.strip()] + def do_commit(self, message=None, committer=None, author=None, commit_timestamp=None, commit_timezone=None, author_timestamp=None, author_timezone=None, tree=None, encoding=None, ref=b'HEAD', merge_heads=None): """Create a new commit. :param message: Commit message :param committer: Committer fullname :param author: Author fullname (defaults to committer) :param commit_timestamp: Commit timestamp (defaults to now) :param commit_timezone: Commit timestamp timezone (defaults to GMT) :param author_timestamp: Author timestamp (defaults to commit timestamp) :param author_timezone: Author timestamp timezone (defaults to commit timestamp timezone) :param tree: SHA1 of the tree root to use (if not specified the current index will be committed). :param encoding: Encoding :param ref: Optional ref to commit to (defaults to current branch) :param merge_heads: Merge heads (defaults to .git/MERGE_HEADS) :return: New commit SHA1 """ import time c = Commit() if tree is None: index = self.open_index() c.tree = index.commit(self.object_store) else: if len(tree) != 40: raise ValueError("tree must be a 40-byte hex sha string") c.tree = tree try: self.hooks['pre-commit'].execute() except HookError as e: raise CommitError(e) except KeyError: # no hook defined, silent fallthrough pass + config = self.get_config_stack() if merge_heads is None: - # FIXME: Read merge heads from .git/MERGE_HEADS - merge_heads = [] + merge_heads = self._read_heads('MERGE_HEADS') if committer is None: - committer = self._get_user_identity() + committer = self._get_user_identity(config) check_user_identity(committer) c.committer = committer if commit_timestamp is None: # FIXME: Support GIT_COMMITTER_DATE environment variable commit_timestamp = time.time() c.commit_time = int(commit_timestamp) if commit_timezone is None: # FIXME: Use current user timezone rather than UTC commit_timezone = 0 c.commit_timezone = commit_timezone if author is None: # FIXME: Support GIT_AUTHOR_NAME/GIT_AUTHOR_EMAIL environment # variables author = committer c.author = author check_user_identity(author) if author_timestamp is None: # FIXME: Support GIT_AUTHOR_DATE environment variable author_timestamp = commit_timestamp c.author_time = int(author_timestamp) if author_timezone is None: author_timezone = commit_timezone c.author_timezone = author_timezone + if encoding is None: + try: + encoding = config.get(('i18n', ), 'commitEncoding') + except KeyError: + pass # No dice if encoding is not None: c.encoding = encoding if message is None: # FIXME: Try to read commit message from .git/MERGE_MSG raise ValueError("No commit message specified") try: c.message = self.hooks['commit-msg'].execute(message) if c.message is None: c.message = message except HookError as e: raise CommitError(e) except KeyError: # no hook defined, message not modified c.message = message if ref is None: # Create a dangling commit c.parents = merge_heads self.object_store.add_object(c) else: try: old_head = self.refs[ref] c.parents = [old_head] + merge_heads self.object_store.add_object(c) ok = self.refs.set_if_equals( ref, old_head, c.id, message=b"commit: " + message, committer=committer, timestamp=commit_timestamp, timezone=commit_timezone) except KeyError: c.parents = merge_heads self.object_store.add_object(c) ok = self.refs.add_if_new( ref, c.id, message=b"commit: " + message, committer=committer, timestamp=commit_timestamp, timezone=commit_timezone) if not ok: # Fail if the atomic compare-and-swap failed, leaving the # commit and all its objects as garbage. raise CommitError("%s changed during commit" % (ref,)) + self._del_named_file('MERGE_HEADS') + try: self.hooks['post-commit'].execute() except HookError as e: # silent failure warnings.warn("post-commit hook failed: %s" % e, UserWarning) except KeyError: # no hook defined, silent fallthrough pass return c.id def read_gitfile(f): """Read a ``.git`` file. The first line of the file should start with "gitdir: " :param f: File-like object to read from :return: A path """ cs = f.read() if not cs.startswith("gitdir: "): raise ValueError("Expected file to start with 'gitdir: '") return cs[len("gitdir: "):].rstrip("\n") class Repo(BaseRepo): """A git repository backed by local disk. To open an existing repository, call the contructor with the path of the repository. To create a new repository, use the Repo.init class method. """ def __init__(self, root): hidden_path = os.path.join(root, CONTROLDIR) if os.path.isdir(os.path.join(hidden_path, OBJECTDIR)): self.bare = False self._controldir = hidden_path elif (os.path.isdir(os.path.join(root, OBJECTDIR)) and os.path.isdir(os.path.join(root, REFSDIR))): self.bare = True self._controldir = root elif os.path.isfile(hidden_path): self.bare = False with open(hidden_path, 'r') as f: path = read_gitfile(f) self.bare = False self._controldir = os.path.join(root, path) else: raise NotGitRepository( "No git repository was found at %(path)s" % dict(path=root) ) commondir = self.get_named_file(COMMONDIR) if commondir is not None: with commondir: self._commondir = os.path.join( self.controldir(), commondir.read().rstrip(b"\r\n").decode( sys.getfilesystemencoding())) else: self._commondir = self._controldir self.path = root object_store = DiskObjectStore( os.path.join(self.commondir(), OBJECTDIR)) refs = DiskRefsContainer(self.commondir(), self._controldir, logger=self._write_reflog) BaseRepo.__init__(self, object_store, refs) self._graftpoints = {} graft_file = self.get_named_file(os.path.join("info", "grafts"), basedir=self.commondir()) if graft_file: with graft_file: self._graftpoints.update(parse_graftpoints(graft_file)) graft_file = self.get_named_file("shallow", basedir=self.commondir()) if graft_file: with graft_file: self._graftpoints.update(parse_graftpoints(graft_file)) self.hooks['pre-commit'] = PreCommitShellHook(self.controldir()) self.hooks['commit-msg'] = CommitMsgShellHook(self.controldir()) self.hooks['post-commit'] = PostCommitShellHook(self.controldir()) def _write_reflog(self, ref, old_sha, new_sha, committer, timestamp, timezone, message): from .reflog import format_reflog_line path = os.path.join( self.controldir(), 'logs', ref.decode(sys.getfilesystemencoding())) try: os.makedirs(os.path.dirname(path)) except OSError as e: if e.errno != errno.EEXIST: raise if committer is None: - committer = self._get_user_identity() + config = self.get_config_stack() + committer = self._get_user_identity(config) check_user_identity(committer) if timestamp is None: timestamp = int(time.time()) if timezone is None: timezone = 0 # FIXME with open(path, 'ab') as f: f.write(format_reflog_line(old_sha, new_sha, committer, timestamp, timezone, message) + b'\n') @classmethod def discover(cls, start='.'): """Iterate parent directories to discover a repository Return a Repo object for the first parent directory that looks like a Git repository. :param start: The directory to start discovery from (defaults to '.') """ remaining = True path = os.path.abspath(start) while remaining: try: return cls(path) except NotGitRepository: path, remaining = os.path.split(path) raise NotGitRepository( "No git repository was found at %(path)s" % dict(path=start) ) def controldir(self): """Return the path of the control directory.""" return self._controldir def commondir(self): """Return the path of the common directory. For a main working tree, it is identical to controldir(). For a linked working tree, it is the control directory of the main working tree.""" return self._commondir def _determine_file_mode(self): """Probe the file-system to determine whether permissions can be trusted. :return: True if permissions can be trusted, False otherwise. """ fname = os.path.join(self.path, '.probe-permissions') with open(fname, 'w') as f: f.write('') st1 = os.lstat(fname) os.chmod(fname, st1.st_mode ^ stat.S_IXUSR) st2 = os.lstat(fname) os.unlink(fname) mode_differs = st1.st_mode != st2.st_mode st2_has_exec = (st2.st_mode & stat.S_IXUSR) != 0 return mode_differs and st2_has_exec def _put_named_file(self, path, contents): """Write a file to the control dir with the given name and contents. :param path: The path to the file, relative to the control dir. :param contents: A string to write to the file. """ path = path.lstrip(os.path.sep) with GitFile(os.path.join(self.controldir(), path), 'wb') as f: f.write(contents) + def _del_named_file(self, path): + try: + os.unlink(os.path.join(self.controldir(), path)) + except (IOError, OSError) as e: + if e.errno == errno.ENOENT: + return + raise + def get_named_file(self, path, basedir=None): """Get a file from the control dir with a specific name. Although the filename should be interpreted as a filename relative to the control dir in a disk-based Repo, the object returned need not be pointing to a file in that location. :param path: The path to the file, relative to the control dir. :param basedir: Optional argument that specifies an alternative to the control dir. :return: An open file object, or None if the file does not exist. """ # TODO(dborowitz): sanitize filenames, since this is used directly by # the dumb web serving code. if basedir is None: basedir = self.controldir() path = path.lstrip(os.path.sep) try: return open(os.path.join(basedir, path), 'rb') except (IOError, OSError) as e: if e.errno == errno.ENOENT: return None raise - def get_shallow(self): - f = self.get_named_file('shallow') - if f is None: - return set() - with f: - return set(l.strip() for l in f) - def index_path(self): """Return path to the index file.""" return os.path.join(self.controldir(), INDEX_FILENAME) def open_index(self): """Open the index for this repository. :raise NoIndexPresent: If no index is present :return: The matching `Index` """ from dulwich.index import Index if not self.has_index(): raise NoIndexPresent() return Index(self.index_path()) def has_index(self): """Check if an index is present.""" # Bare repos must never have index files; non-bare repos may have a # missing index file, which is treated as empty. return not self.bare def stage(self, fs_paths): """Stage a set of paths. :param fs_paths: List of paths, relative to the repository path """ root_path_bytes = self.path.encode(sys.getfilesystemencoding()) if not isinstance(fs_paths, list): fs_paths = [fs_paths] from dulwich.index import ( blob_from_path_and_stat, index_entry_from_stat, _fs_to_tree_path, ) index = self.open_index() for fs_path in fs_paths: if not isinstance(fs_path, bytes): fs_path = fs_path.encode(sys.getfilesystemencoding()) if os.path.isabs(fs_path): raise ValueError( "path %r should be relative to " "repository root, not absolute" % fs_path) tree_path = _fs_to_tree_path(fs_path) full_path = os.path.join(root_path_bytes, fs_path) try: st = os.lstat(full_path) except OSError: # File no longer exists try: del index[tree_path] except KeyError: pass # already removed else: if not stat.S_ISDIR(st.st_mode): blob = blob_from_path_and_stat(full_path, st) self.object_store.add_object(blob) index[tree_path] = index_entry_from_stat(st, blob.id, 0) else: try: del index[tree_path] except KeyError: pass index.write() def clone(self, target_path, mkdir=True, bare=False, origin=b"origin", checkout=None): """Clone this repository. :param target_path: Target path :param mkdir: Create the target directory :param bare: Whether to create a bare repository :param origin: Base name for refs in target repository cloned from this repository :return: Created repository as `Repo` """ if not bare: target = self.init(target_path, mkdir=mkdir) else: if checkout: raise ValueError("checkout and bare are incompatible") target = self.init_bare(target_path, mkdir=mkdir) self.fetch(target) encoded_path = self.path if not isinstance(encoded_path, bytes): encoded_path = encoded_path.encode(sys.getfilesystemencoding()) ref_message = b"clone: from " + encoded_path target.refs.import_refs( b'refs/remotes/' + origin, self.refs.as_dict(b'refs/heads'), message=ref_message) target.refs.import_refs( b'refs/tags', self.refs.as_dict(b'refs/tags'), message=ref_message) try: target.refs.add_if_new( DEFAULT_REF, self.refs[DEFAULT_REF], message=ref_message) except KeyError: pass target_config = target.get_config() target_config.set(('remote', 'origin'), 'url', encoded_path) target_config.set(('remote', 'origin'), 'fetch', '+refs/heads/*:refs/remotes/origin/*') target_config.write_to_path() # Update target head head_chain, head_sha = self.refs.follow(b'HEAD') if head_chain and head_sha is not None: target.refs.set_symbolic_ref(b'HEAD', head_chain[-1], message=ref_message) target[b'HEAD'] = head_sha if checkout is None: checkout = (not bare) if checkout: # Checkout HEAD to target dir target.reset_index() return target def reset_index(self, tree=None): """Reset the index back to a specific tree. :param tree: Tree SHA to reset to, None for current HEAD tree. """ from dulwich.index import ( build_index_from_tree, validate_path_element_default, validate_path_element_ntfs, ) if tree is None: tree = self[b'HEAD'].tree config = self.get_config() honor_filemode = config.get_boolean( b'core', b'filemode', os.name != "nt") if config.get_boolean(b'core', b'core.protectNTFS', os.name == "nt"): validate_path_element = validate_path_element_ntfs else: validate_path_element = validate_path_element_default return build_index_from_tree( self.path, self.index_path(), self.object_store, tree, honor_filemode=honor_filemode, validate_path_element=validate_path_element) def get_config(self): """Retrieve the config object. :return: `ConfigFile` object for the ``.git/config`` file. """ from dulwich.config import ConfigFile path = os.path.join(self._controldir, 'config') try: return ConfigFile.from_path(path) except (IOError, OSError) as e: if e.errno != errno.ENOENT: raise ret = ConfigFile() ret.path = path return ret def get_description(self): """Retrieve the description of this repository. :return: A string describing the repository or None. """ path = os.path.join(self._controldir, 'description') try: with GitFile(path, 'rb') as f: return f.read() except (IOError, OSError) as e: if e.errno != errno.ENOENT: raise return None def __repr__(self): return "" % self.path def set_description(self, description): """Set the description for this repository. :param description: Text to set as description for this repository. """ self._put_named_file('description', description) @classmethod def _init_maybe_bare(cls, path, bare): for d in BASE_DIRECTORIES: os.mkdir(os.path.join(path, *d)) DiskObjectStore.init(os.path.join(path, OBJECTDIR)) ret = cls(path) ret.refs.set_symbolic_ref(b'HEAD', DEFAULT_REF) ret._init_files(bare) return ret @classmethod def init(cls, path, mkdir=False): """Create a new repository. :param path: Path in which to create the repository :param mkdir: Whether to create the directory :return: `Repo` instance """ if mkdir: os.mkdir(path) controldir = os.path.join(path, CONTROLDIR) os.mkdir(controldir) cls._init_maybe_bare(controldir, False) return cls(path) @classmethod def _init_new_working_directory(cls, path, main_repo, identifier=None, mkdir=False): """Create a new working directory linked to a repository. :param path: Path in which to create the working tree. :param main_repo: Main repository to reference :param identifier: Worktree identifier :param mkdir: Whether to create the directory :return: `Repo` instance """ if mkdir: os.mkdir(path) if identifier is None: identifier = os.path.basename(path) main_worktreesdir = os.path.join(main_repo.controldir(), WORKTREES) worktree_controldir = os.path.join(main_worktreesdir, identifier) gitdirfile = os.path.join(path, CONTROLDIR) with open(gitdirfile, 'wb') as f: f.write(b'gitdir: ' + worktree_controldir.encode(sys.getfilesystemencoding()) + b'\n') try: os.mkdir(main_worktreesdir) except OSError as e: if e.errno != errno.EEXIST: raise try: os.mkdir(worktree_controldir) except OSError as e: if e.errno != errno.EEXIST: raise with open(os.path.join(worktree_controldir, GITDIR), 'wb') as f: f.write(gitdirfile.encode(sys.getfilesystemencoding()) + b'\n') with open(os.path.join(worktree_controldir, COMMONDIR), 'wb') as f: f.write(b'../..\n') with open(os.path.join(worktree_controldir, 'HEAD'), 'wb') as f: f.write(main_repo.head() + b'\n') r = cls(path) r.reset_index() return r @classmethod def init_bare(cls, path, mkdir=False): """Create a new bare repository. ``path`` should already exist and be an empty directory. :param path: Path to create bare repository in :return: a `Repo` instance """ if mkdir: os.mkdir(path) return cls._init_maybe_bare(path, True) create = init_bare def close(self): """Close any files opened by this repository.""" self.object_store.close() def __enter__(self): return self def __exit__(self, exc_type, exc_val, exc_tb): self.close() class MemoryRepo(BaseRepo): """Repo that stores refs, objects, and named files in memory. MemoryRepos are always bare: they have no working tree and no index, since those have a stronger dependency on the filesystem. """ def __init__(self): from dulwich.config import ConfigFile self._reflog = [] refs_container = DictRefsContainer({}, logger=self._append_reflog) BaseRepo.__init__(self, MemoryObjectStore(), refs_container) self._named_files = {} self.bare = True self._config = ConfigFile() self._description = None def _append_reflog(self, *args): self._reflog.append(args) def set_description(self, description): self._description = description def get_description(self): return self._description def _determine_file_mode(self): """Probe the file-system to determine whether permissions can be trusted. :return: True if permissions can be trusted, False otherwise. """ return sys.platform != 'win32' def _put_named_file(self, path, contents): """Write a file to the control dir with the given name and contents. :param path: The path to the file, relative to the control dir. :param contents: A string to write to the file. """ self._named_files[path] = contents + def _del_named_file(self, path): + try: + del self._named_files[path] + except KeyError: + pass + def get_named_file(self, path): """Get a file from the control dir with a specific name. Although the filename should be interpreted as a filename relative to the control dir in a disk-baked Repo, the object returned need not be pointing to a file in that location. :param path: The path to the file, relative to the control dir. :return: An open file object, or None if the file does not exist. """ contents = self._named_files.get(path, None) if contents is None: return None return BytesIO(contents) def open_index(self): """Fail to open index for this repo, since it is bare. :raise NoIndexPresent: Raised when no index is present """ raise NoIndexPresent() def get_config(self): """Retrieve the config object. :return: `ConfigFile` object. """ return self._config @classmethod def init_bare(cls, objects, refs): """Create a new bare repository in memory. :param objects: Objects for the new repository, as iterable :param refs: Refs as dictionary, mapping names to object SHA1s """ ret = cls() for obj in objects: ret.object_store.add_object(obj) for refname, sha in refs.items(): ret.refs.add_if_new(refname, sha) ret._init_files(bare=True) return ret diff --git a/dulwich/server.py b/dulwich/server.py index 1d3cc7e3..db6ebb7f 100644 --- a/dulwich/server.py +++ b/dulwich/server.py @@ -1,1149 +1,1186 @@ # server.py -- Implementation of the server side git protocols # Copyright (C) 2008 John Carr # Coprygith (C) 2011-2012 Jelmer Vernooij # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """Git smart network protocol server implementation. For more detailed implementation on the network protocol, see the Documentation/technical directory in the cgit distribution, and in particular: * Documentation/technical/protocol-capabilities.txt * Documentation/technical/pack-protocol.txt Currently supported capabilities: * include-tag * thin-pack * multi_ack_detailed * multi_ack * side-band-64k * ofs-delta * no-progress * report-status * delete-refs * shallow * symref """ import collections import os import socket import sys +import time import zlib try: import SocketServer except ImportError: import socketserver as SocketServer +from dulwich.archive import tar_stream from dulwich.errors import ( ApplyDeltaError, ChecksumMismatch, GitProtocolError, NotGitRepository, UnexpectedCommandError, ObjectFormatException, ) from dulwich import log_utils from dulwich.objects import ( Commit, valid_hexsha, ) from dulwich.pack import ( write_pack_objects, ) from dulwich.protocol import ( # noqa: F401 BufferedPktLineWriter, capability_agent, CAPABILITIES_REF, CAPABILITY_DELETE_REFS, CAPABILITY_INCLUDE_TAG, CAPABILITY_MULTI_ACK_DETAILED, CAPABILITY_MULTI_ACK, CAPABILITY_NO_DONE, CAPABILITY_NO_PROGRESS, CAPABILITY_OFS_DELTA, CAPABILITY_QUIET, CAPABILITY_REPORT_STATUS, CAPABILITY_SHALLOW, CAPABILITY_SIDE_BAND_64K, CAPABILITY_THIN_PACK, COMMAND_DEEPEN, COMMAND_DONE, COMMAND_HAVE, COMMAND_SHALLOW, COMMAND_UNSHALLOW, COMMAND_WANT, MULTI_ACK, MULTI_ACK_DETAILED, Protocol, ProtocolFile, ReceivableProtocol, SIDE_BAND_CHANNEL_DATA, SIDE_BAND_CHANNEL_PROGRESS, SIDE_BAND_CHANNEL_FATAL, SINGLE_ACK, TCP_GIT_PORT, ZERO_SHA, ack_type, extract_capabilities, extract_want_line_capabilities, symref_capabilities, ) from dulwich.refs import ( ANNOTATED_TAG_SUFFIX, write_info_refs, ) from dulwich.repo import ( Repo, ) logger = log_utils.getLogger(__name__) class Backend(object): """A backend for the Git smart server implementation.""" def open_repository(self, path): """Open the repository at a path. :param path: Path to the repository :raise NotGitRepository: no git repository was found at path :return: Instance of BackendRepo """ raise NotImplementedError(self.open_repository) class BackendRepo(object): """Repository abstraction used by the Git server. The methods required here are a subset of those provided by dulwich.repo.Repo. """ object_store = None refs = None def get_refs(self): """ Get all the refs in the repository :return: dict of name -> sha """ raise NotImplementedError def get_peeled(self, name): """Return the cached peeled value of a ref, if available. :param name: Name of the ref to peel :return: The peeled value of the ref. If the ref is known not point to a tag, this will be the SHA the ref refers to. If no cached information about a tag is available, this method may return None, but it should attempt to peel the tag if possible. """ return None def fetch_objects(self, determine_wants, graph_walker, progress, get_tagged=None): """ Yield the objects required for a list of commits. :param progress: is a callback to send progress messages to the client :param get_tagged: Function that returns a dict of pointed-to sha -> tag sha for including tags. """ raise NotImplementedError class DictBackend(Backend): """Trivial backend that looks up Git repositories in a dictionary.""" def __init__(self, repos): self.repos = repos def open_repository(self, path): logger.debug('Opening repository at %s', path) try: return self.repos[path] except KeyError: raise NotGitRepository( "No git repository was found at %(path)s" % dict(path=path) ) class FileSystemBackend(Backend): """Simple backend looking up Git repositories in the local file system.""" def __init__(self, root=os.sep): super(FileSystemBackend, self).__init__() self.root = (os.path.abspath(root) + os.sep).replace( os.sep * 2, os.sep) def open_repository(self, path): logger.debug('opening repository at %s', path) abspath = os.path.abspath(os.path.join(self.root, path)) + os.sep normcase_abspath = os.path.normcase(abspath) normcase_root = os.path.normcase(self.root) if not normcase_abspath.startswith(normcase_root): raise NotGitRepository( "Path %r not inside root %r" % (path, self.root)) return Repo(abspath) class Handler(object): """Smart protocol command handler base class.""" def __init__(self, backend, proto, http_req=None): self.backend = backend self.proto = proto self.http_req = http_req def handle(self): raise NotImplementedError(self.handle) class PackHandler(Handler): """Protocol handler for packs.""" def __init__(self, backend, proto, http_req=None): super(PackHandler, self).__init__(backend, proto, http_req) self._client_capabilities = None # Flags needed for the no-done capability self._done_received = False @classmethod def capability_line(cls, capabilities): logger.info('Sending capabilities: %s', capabilities) return b"".join([b" " + c for c in capabilities]) @classmethod def capabilities(cls): raise NotImplementedError(cls.capabilities) @classmethod def innocuous_capabilities(cls): return [CAPABILITY_INCLUDE_TAG, CAPABILITY_THIN_PACK, CAPABILITY_NO_PROGRESS, CAPABILITY_OFS_DELTA, capability_agent()] @classmethod def required_capabilities(cls): """Return a list of capabilities that we require the client to have.""" return [] def set_client_capabilities(self, caps): allowable_caps = set(self.innocuous_capabilities()) allowable_caps.update(self.capabilities()) for cap in caps: if cap not in allowable_caps: raise GitProtocolError('Client asked for capability %s that ' 'was not advertised.' % cap) for cap in self.required_capabilities(): if cap not in caps: raise GitProtocolError('Client does not support required ' 'capability %s.' % cap) self._client_capabilities = set(caps) logger.info('Client capabilities: %s', caps) def has_capability(self, cap): if self._client_capabilities is None: raise GitProtocolError('Server attempted to access capability %s ' 'before asking client' % cap) return cap in self._client_capabilities def notify_done(self): self._done_received = True class UploadPackHandler(PackHandler): """Protocol handler for uploading a pack to the client.""" def __init__(self, backend, args, proto, http_req=None, advertise_refs=False): super(UploadPackHandler, self).__init__( backend, proto, http_req=http_req) self.repo = backend.open_repository(args[0]) self._graph_walker = None self.advertise_refs = advertise_refs # A state variable for denoting that the have list is still # being processed, and the client is not accepting any other # data (such as side-band, see the progress method here). self._processing_have_lines = False @classmethod def capabilities(cls): return [CAPABILITY_MULTI_ACK_DETAILED, CAPABILITY_MULTI_ACK, CAPABILITY_SIDE_BAND_64K, CAPABILITY_THIN_PACK, CAPABILITY_OFS_DELTA, CAPABILITY_NO_PROGRESS, CAPABILITY_INCLUDE_TAG, CAPABILITY_SHALLOW, CAPABILITY_NO_DONE] @classmethod def required_capabilities(cls): return (CAPABILITY_SIDE_BAND_64K, CAPABILITY_THIN_PACK, CAPABILITY_OFS_DELTA) def progress(self, message): if (self.has_capability(CAPABILITY_NO_PROGRESS) or self._processing_have_lines): return self.proto.write_sideband(SIDE_BAND_CHANNEL_PROGRESS, message) def get_tagged(self, refs=None, repo=None): """Get a dict of peeled values of tags to their original tag shas. :param refs: dict of refname -> sha of possible tags; defaults to all of the backend's refs. :param repo: optional Repo instance for getting peeled refs; defaults to the backend's repo, if available :return: dict of peeled_sha -> tag_sha, where tag_sha is the sha of a tag whose peeled value is peeled_sha. """ if not self.has_capability(CAPABILITY_INCLUDE_TAG): return {} if refs is None: refs = self.repo.get_refs() if repo is None: repo = getattr(self.repo, "repo", None) if repo is None: # Bail if we don't have a Repo available; this is ok since # clients must be able to handle if the server doesn't include # all relevant tags. # TODO: fix behavior when missing return {} + # TODO(jelmer): Integrate this with the refs logic in + # Repo.fetch_objects tagged = {} for name, sha in refs.items(): peeled_sha = repo.get_peeled(name) if peeled_sha != sha: tagged[peeled_sha] = sha return tagged def handle(self): def write(x): return self.proto.write_sideband(SIDE_BAND_CHANNEL_DATA, x) graph_walker = _ProtocolGraphWalker( self, self.repo.object_store, self.repo.get_peeled, self.repo.refs.get_symrefs) objects_iter = self.repo.fetch_objects( graph_walker.determine_wants, graph_walker, self.progress, get_tagged=self.get_tagged) # Note the fact that client is only processing responses related # to the have lines it sent, and any other data (including side- # band) will be be considered a fatal error. self._processing_have_lines = True # Did the process short-circuit (e.g. in a stateless RPC call)? Note # that the client still expects a 0-object pack in most cases. # Also, if it also happens that the object_iter is instantiated # with a graph walker with an implementation that talks over the # wire (which is this instance of this class) this will actually # iterate through everything and write things out to the wire. if len(objects_iter) == 0: return # The provided haves are processed, and it is safe to send side- # band data now. self._processing_have_lines = False if not graph_walker.handle_done( not self.has_capability(CAPABILITY_NO_DONE), self._done_received): return - self.progress(b"dul-daemon says what\n") self.progress( ("counting objects: %d, done.\n" % len(objects_iter)).encode( 'ascii')) write_pack_objects(ProtocolFile(None, write), objects_iter) - self.progress(b"how was that, then?\n") # we are done self.proto.write_pkt_line(None) def _split_proto_line(line, allowed): """Split a line read from the wire. :param line: The line read from the wire. :param allowed: An iterable of command names that should be allowed. Command names not listed below as possible return values will be ignored. If None, any commands from the possible return values are allowed. :return: a tuple having one of the following forms: ('want', obj_id) ('have', obj_id) ('done', None) (None, None) (for a flush-pkt) :raise UnexpectedCommandError: if the line cannot be parsed into one of the allowed return values. """ if not line: fields = [None] else: fields = line.rstrip(b'\n').split(b' ', 1) command = fields[0] if allowed is not None and command not in allowed: raise UnexpectedCommandError(command) if len(fields) == 1 and command in (COMMAND_DONE, None): return (command, None) elif len(fields) == 2: if command in (COMMAND_WANT, COMMAND_HAVE, COMMAND_SHALLOW, COMMAND_UNSHALLOW): if not valid_hexsha(fields[1]): raise GitProtocolError("Invalid sha") return tuple(fields) elif command == COMMAND_DEEPEN: return command, int(fields[1]) raise GitProtocolError('Received invalid line from client: %r' % line) def _find_shallow(store, heads, depth): """Find shallow commits according to a given depth. :param store: An ObjectStore for looking up objects. :param heads: Iterable of head SHAs to start walking from. :param depth: The depth of ancestors to include. A depth of one includes only the heads themselves. :return: A tuple of (shallow, not_shallow), sets of SHAs that should be considered shallow and unshallow according to the arguments. Note that these sets may overlap if a commit is reachable along multiple paths. """ parents = {} def get_parents(sha): result = parents.get(sha, None) if not result: result = store[sha].parents parents[sha] = result return result todo = [] # stack of (sha, depth) for head_sha in heads: obj = store.peel_sha(head_sha) if isinstance(obj, Commit): todo.append((obj.id, 1)) not_shallow = set() shallow = set() while todo: sha, cur_depth = todo.pop() if cur_depth < depth: not_shallow.add(sha) new_depth = cur_depth + 1 todo.extend((p, new_depth) for p in get_parents(sha)) else: shallow.add(sha) return shallow, not_shallow def _want_satisfied(store, haves, want, earliest): o = store[want] pending = collections.deque([o]) known = set([want]) while pending: commit = pending.popleft() if commit.id in haves: return True if commit.type_name != b"commit": # non-commit wants are assumed to be satisfied continue for parent in commit.parents: if parent in known: continue known.add(parent) parent_obj = store[parent] # TODO: handle parents with later commit times than children if parent_obj.commit_time >= earliest: pending.append(parent_obj) return False def _all_wants_satisfied(store, haves, wants): """Check whether all the current wants are satisfied by a set of haves. :param store: Object store to retrieve objects from :param haves: A set of commits we know the client has. :param wants: A set of commits the client wants :note: Wants are specified with set_wants rather than passed in since in the current interface they are determined outside this class. """ haves = set(haves) if haves: earliest = min([store[h].commit_time for h in haves]) else: earliest = 0 for want in wants: if not _want_satisfied(store, haves, want, earliest): return False return True class _ProtocolGraphWalker(object): """A graph walker that knows the git protocol. As a graph walker, this class implements ack(), next(), and reset(). It also contains some base methods for interacting with the wire and walking the commit tree. The work of determining which acks to send is passed on to the implementation instance stored in _impl. The reason for this is that we do not know at object creation time what ack level the protocol requires. A call to set_ack_type() is required to set up the implementation, before any calls to next() or ack() are made. """ def __init__(self, handler, object_store, get_peeled, get_symrefs): self.handler = handler self.store = object_store self.get_peeled = get_peeled self.get_symrefs = get_symrefs self.proto = handler.proto self.http_req = handler.http_req self.advertise_refs = handler.advertise_refs self._wants = [] self.shallow = set() self.client_shallow = set() self.unshallow = set() self._cached = False self._cache = [] self._cache_index = 0 self._impl = None def determine_wants(self, heads): """Determine the wants for a set of heads. The given heads are advertised to the client, who then specifies which refs he wants using 'want' lines. This portion of the protocol is the same regardless of ack type, and in fact is used to set the ack type of the ProtocolGraphWalker. If the client has the 'shallow' capability, this method also reads and responds to the 'shallow' and 'deepen' lines from the client. These are not part of the wants per se, but they set up necessary state for walking the graph. Additionally, later code depends on this method consuming everything up to the first 'have' line. :param heads: a dict of refname->SHA1 to advertise :return: a list of SHA1s requested by the client """ symrefs = self.get_symrefs() values = set(heads.values()) if self.advertise_refs or not self.http_req: for i, (ref, sha) in enumerate(sorted(heads.items())): + try: + peeled_sha = self.get_peeled(ref) + except KeyError: + # Skip refs that are inaccessible + # TODO(jelmer): Integrate with Repo.fetch_objects refs + # logic. + continue line = sha + b' ' + ref if not i: line += (b'\x00' + self.handler.capability_line( self.handler.capabilities() + symref_capabilities(symrefs.items()))) self.proto.write_pkt_line(line + b'\n') - peeled_sha = self.get_peeled(ref) if peeled_sha != sha: self.proto.write_pkt_line( peeled_sha + b' ' + ref + ANNOTATED_TAG_SUFFIX + b'\n') # i'm done.. self.proto.write_pkt_line(None) if self.advertise_refs: return [] # Now client will sending want want want commands want = self.proto.read_pkt_line() if not want: return [] line, caps = extract_want_line_capabilities(want) self.handler.set_client_capabilities(caps) self.set_ack_type(ack_type(caps)) allowed = (COMMAND_WANT, COMMAND_SHALLOW, COMMAND_DEEPEN, None) command, sha = _split_proto_line(line, allowed) want_revs = [] while command == COMMAND_WANT: if sha not in values: raise GitProtocolError( 'Client wants invalid object %s' % sha) want_revs.append(sha) command, sha = self.read_proto_line(allowed) self.set_wants(want_revs) if command in (COMMAND_SHALLOW, COMMAND_DEEPEN): self.unread_proto_line(command, sha) self._handle_shallow_request(want_revs) if self.http_req and self.proto.eof(): # The client may close the socket at this point, expecting a # flush-pkt from the server. We might be ready to send a packfile # at this point, so we need to explicitly short-circuit in this # case. return [] return want_revs def unread_proto_line(self, command, value): if isinstance(value, int): value = str(value).encode('ascii') self.proto.unread_pkt_line(command + b' ' + value) def ack(self, have_ref): if len(have_ref) != 40: raise ValueError("invalid sha %r" % have_ref) return self._impl.ack(have_ref) def reset(self): self._cached = True self._cache_index = 0 def next(self): if not self._cached: if not self._impl and self.http_req: return None return next(self._impl) self._cache_index += 1 if self._cache_index > len(self._cache): return None return self._cache[self._cache_index] __next__ = next def read_proto_line(self, allowed): """Read a line from the wire. :param allowed: An iterable of command names that should be allowed. :return: A tuple of (command, value); see _split_proto_line. :raise UnexpectedCommandError: If an error occurred reading the line. """ return _split_proto_line(self.proto.read_pkt_line(), allowed) def _handle_shallow_request(self, wants): while True: command, val = self.read_proto_line( (COMMAND_DEEPEN, COMMAND_SHALLOW)) if command == COMMAND_DEEPEN: depth = val break self.client_shallow.add(val) self.read_proto_line((None,)) # consume client's flush-pkt shallow, not_shallow = _find_shallow(self.store, wants, depth) # Update self.shallow instead of reassigning it since we passed a # reference to it before this method was called. self.shallow.update(shallow - not_shallow) new_shallow = self.shallow - self.client_shallow unshallow = self.unshallow = not_shallow & self.client_shallow for sha in sorted(new_shallow): self.proto.write_pkt_line(COMMAND_SHALLOW + b' ' + sha) for sha in sorted(unshallow): self.proto.write_pkt_line(COMMAND_UNSHALLOW + b' ' + sha) self.proto.write_pkt_line(None) def notify_done(self): # relay the message down to the handler. self.handler.notify_done() def send_ack(self, sha, ack_type=b''): if ack_type: ack_type = b' ' + ack_type self.proto.write_pkt_line(b'ACK ' + sha + ack_type + b'\n') def send_nak(self): self.proto.write_pkt_line(b'NAK\n') def handle_done(self, done_required, done_received): # Delegate this to the implementation. return self._impl.handle_done(done_required, done_received) def set_wants(self, wants): self._wants = wants def all_wants_satisfied(self, haves): """Check whether all the current wants are satisfied by a set of haves. :param haves: A set of commits we know the client has. :note: Wants are specified with set_wants rather than passed in since in the current interface they are determined outside this class. """ return _all_wants_satisfied(self.store, haves, self._wants) def set_ack_type(self, ack_type): impl_classes = { MULTI_ACK: MultiAckGraphWalkerImpl, MULTI_ACK_DETAILED: MultiAckDetailedGraphWalkerImpl, SINGLE_ACK: SingleAckGraphWalkerImpl, } self._impl = impl_classes[ack_type](self) _GRAPH_WALKER_COMMANDS = (COMMAND_HAVE, COMMAND_DONE, None) class SingleAckGraphWalkerImpl(object): """Graph walker implementation that speaks the single-ack protocol.""" def __init__(self, walker): self.walker = walker self._common = [] def ack(self, have_ref): if not self._common: self.walker.send_ack(have_ref) self._common.append(have_ref) def next(self): command, sha = self.walker.read_proto_line(_GRAPH_WALKER_COMMANDS) if command in (None, COMMAND_DONE): # defer the handling of done self.walker.notify_done() return None elif command == COMMAND_HAVE: return sha __next__ = next def handle_done(self, done_required, done_received): if not self._common: self.walker.send_nak() if done_required and not done_received: # we are not done, especially when done is required; skip # the pack for this request and especially do not handle # the done. return False if not done_received and not self._common: # Okay we are not actually done then since the walker picked # up no haves. This is usually triggered when client attempts # to pull from a source that has no common base_commit. # See: test_server.MultiAckDetailedGraphWalkerImplTestCase.\ # test_multi_ack_stateless_nodone return False return True class MultiAckGraphWalkerImpl(object): """Graph walker implementation that speaks the multi-ack protocol.""" def __init__(self, walker): self.walker = walker self._found_base = False self._common = [] def ack(self, have_ref): self._common.append(have_ref) if not self._found_base: self.walker.send_ack(have_ref, b'continue') if self.walker.all_wants_satisfied(self._common): self._found_base = True # else we blind ack within next def next(self): while True: command, sha = self.walker.read_proto_line(_GRAPH_WALKER_COMMANDS) if command is None: self.walker.send_nak() # in multi-ack mode, a flush-pkt indicates the client wants to # flush but more have lines are still coming continue elif command == COMMAND_DONE: self.walker.notify_done() return None elif command == COMMAND_HAVE: if self._found_base: # blind ack self.walker.send_ack(sha, b'continue') return sha __next__ = next def handle_done(self, done_required, done_received): if done_required and not done_received: # we are not done, especially when done is required; skip # the pack for this request and especially do not handle # the done. return False if not done_received and not self._common: # Okay we are not actually done then since the walker picked # up no haves. This is usually triggered when client attempts # to pull from a source that has no common base_commit. # See: test_server.MultiAckDetailedGraphWalkerImplTestCase.\ # test_multi_ack_stateless_nodone return False # don't nak unless no common commits were found, even if not # everything is satisfied if self._common: self.walker.send_ack(self._common[-1]) else: self.walker.send_nak() return True class MultiAckDetailedGraphWalkerImpl(object): """Graph walker implementation speaking the multi-ack-detailed protocol.""" def __init__(self, walker): self.walker = walker self._common = [] def ack(self, have_ref): # Should only be called iff have_ref is common self._common.append(have_ref) self.walker.send_ack(have_ref, b'common') def next(self): while True: command, sha = self.walker.read_proto_line(_GRAPH_WALKER_COMMANDS) if command is None: if self.walker.all_wants_satisfied(self._common): self.walker.send_ack(self._common[-1], b'ready') self.walker.send_nak() if self.walker.http_req: # The HTTP version of this request a flush-pkt always # signifies an end of request, so we also return # nothing here as if we are done (but not really, as # it depends on whether no-done capability was # specified and that's handled in handle_done which # may or may not call post_nodone_check depending on # that). return None elif command == COMMAND_DONE: # Let the walker know that we got a done. self.walker.notify_done() break elif command == COMMAND_HAVE: # return the sha and let the caller ACK it with the # above ack method. return sha # don't nak unless no common commits were found, even if not # everything is satisfied __next__ = next def handle_done(self, done_required, done_received): if done_required and not done_received: # we are not done, especially when done is required; skip # the pack for this request and especially do not handle # the done. return False if not done_received and not self._common: # Okay we are not actually done then since the walker picked # up no haves. This is usually triggered when client attempts # to pull from a source that has no common base_commit. # See: test_server.MultiAckDetailedGraphWalkerImplTestCase.\ # test_multi_ack_stateless_nodone return False # don't nak unless no common commits were found, even if not # everything is satisfied if self._common: self.walker.send_ack(self._common[-1]) else: self.walker.send_nak() return True class ReceivePackHandler(PackHandler): """Protocol handler for downloading a pack from the client.""" def __init__(self, backend, args, proto, http_req=None, advertise_refs=False): super(ReceivePackHandler, self).__init__( backend, proto, http_req=http_req) self.repo = backend.open_repository(args[0]) self.advertise_refs = advertise_refs @classmethod def capabilities(cls): return [CAPABILITY_REPORT_STATUS, CAPABILITY_DELETE_REFS, CAPABILITY_QUIET, CAPABILITY_OFS_DELTA, CAPABILITY_SIDE_BAND_64K, CAPABILITY_NO_DONE] def _apply_pack(self, refs): all_exceptions = (IOError, OSError, ChecksumMismatch, ApplyDeltaError, AssertionError, socket.error, zlib.error, ObjectFormatException) status = [] will_send_pack = False for command in refs: if command[1] != ZERO_SHA: will_send_pack = True if will_send_pack: # TODO: more informative error messages than just the exception # string try: recv = getattr(self.proto, "recv", None) self.repo.object_store.add_thin_pack(self.proto.read, recv) status.append((b'unpack', b'ok')) except all_exceptions as e: status.append((b'unpack', str(e).replace('\n', ''))) # The pack may still have been moved in, but it may contain # broken objects. We trust a later GC to clean it up. else: # The git protocol want to find a status entry related to unpack # process even if no pack data has been sent. status.append((b'unpack', b'ok')) for oldsha, sha, ref in refs: ref_status = b'ok' try: if sha == ZERO_SHA: if CAPABILITY_DELETE_REFS not in self.capabilities(): raise GitProtocolError( 'Attempted to delete refs without delete-refs ' 'capability.') try: self.repo.refs.remove_if_equals(ref, oldsha) except all_exceptions: ref_status = b'failed to delete' else: try: self.repo.refs.set_if_equals(ref, oldsha, sha) except all_exceptions: ref_status = b'failed to write' - except KeyError as e: + except KeyError: ref_status = b'bad ref' status.append((ref, ref_status)) return status def _report_status(self, status): if self.has_capability(CAPABILITY_SIDE_BAND_64K): writer = BufferedPktLineWriter( lambda d: self.proto.write_sideband(SIDE_BAND_CHANNEL_DATA, d)) write = writer.write def flush(): writer.flush() self.proto.write_pkt_line(None) else: write = self.proto.write_pkt_line def flush(): pass for name, msg in status: if name == b'unpack': write(b'unpack ' + msg + b'\n') elif msg == b'ok': write(b'ok ' + name + b'\n') else: write(b'ng ' + name + b' ' + msg + b'\n') write(None) flush() def handle(self): if self.advertise_refs or not self.http_req: refs = sorted(self.repo.get_refs().items()) symrefs = sorted(self.repo.refs.get_symrefs().items()) if not refs: refs = [(CAPABILITIES_REF, ZERO_SHA)] self.proto.write_pkt_line( refs[0][1] + b' ' + refs[0][0] + b'\0' + self.capability_line( self.capabilities() + symref_capabilities(symrefs)) + b'\n') for i in range(1, len(refs)): ref = refs[i] self.proto.write_pkt_line(ref[1] + b' ' + ref[0] + b'\n') self.proto.write_pkt_line(None) if self.advertise_refs: return client_refs = [] ref = self.proto.read_pkt_line() # if ref is none then client doesnt want to send us anything.. if ref is None: return ref, caps = extract_capabilities(ref) self.set_client_capabilities(caps) # client will now send us a list of (oldsha, newsha, ref) while ref: client_refs.append(ref.split()) ref = self.proto.read_pkt_line() # backend can now deal with this refs and read a pack using self.read status = self._apply_pack(client_refs) # when we have read all the pack from the client, send a status report # if the client asked for it if self.has_capability(CAPABILITY_REPORT_STATUS): self._report_status(status) class UploadArchiveHandler(Handler): - def __init__(self, backend, proto, http_req=None): + def __init__(self, backend, args, proto, http_req=None): super(UploadArchiveHandler, self).__init__(backend, proto, http_req) + self.repo = backend.open_repository(args[0]) def handle(self): - # TODO(jelmer) - raise NotImplementedError(self.handle) + def write(x): + return self.proto.write_sideband(SIDE_BAND_CHANNEL_DATA, x) + arguments = [] + for pkt in self.proto.read_pkt_seq(): + (key, value) = pkt.split(b' ', 1) + if key != b'argument': + raise GitProtocolError('unknown command %s' % key) + arguments.append(value.rstrip(b'\n')) + prefix = b'' + format = 'tar' + i = 0 + store = self.repo.object_store + while i < len(arguments): + argument = arguments[i] + if argument == b'--prefix': + i += 1 + prefix = arguments[i] + elif argument == b'--format': + i += 1 + format = arguments[i].decode('ascii') + else: + commit_sha = self.repo.refs[argument] + tree = store[store[commit_sha].tree] + i += 1 + self.proto.write_pkt_line(b'ACK\n') + self.proto.write_pkt_line(None) + for chunk in tar_stream( + store, tree, mtime=time.time(), prefix=prefix, format=format): + write(chunk) + self.proto.write_pkt_line(None) # Default handler classes for git services. DEFAULT_HANDLERS = { b'git-upload-pack': UploadPackHandler, b'git-receive-pack': ReceivePackHandler, - # b'git-upload-archive': UploadArchiveHandler, + b'git-upload-archive': UploadArchiveHandler, } class TCPGitRequestHandler(SocketServer.StreamRequestHandler): def __init__(self, handlers, *args, **kwargs): self.handlers = handlers SocketServer.StreamRequestHandler.__init__(self, *args, **kwargs) def handle(self): proto = ReceivableProtocol(self.connection.recv, self.wfile.write) command, args = proto.read_cmd() logger.info('Handling %s request, args=%s', command, args) cls = self.handlers.get(command, None) if not callable(cls): raise GitProtocolError('Invalid service %s' % command) h = cls(self.server.backend, args, proto) h.handle() class TCPGitServer(SocketServer.TCPServer): allow_reuse_address = True serve = SocketServer.TCPServer.serve_forever def _make_handler(self, *args, **kwargs): return TCPGitRequestHandler(self.handlers, *args, **kwargs) def __init__(self, backend, listen_addr, port=TCP_GIT_PORT, handlers=None): self.handlers = dict(DEFAULT_HANDLERS) if handlers is not None: self.handlers.update(handlers) self.backend = backend logger.info('Listening for TCP connections on %s:%d', listen_addr, port) SocketServer.TCPServer.__init__(self, (listen_addr, port), self._make_handler) def verify_request(self, request, client_address): logger.info('Handling request from %s', client_address) return True def handle_error(self, request, client_address): logger.exception('Exception happened during processing of request ' 'from %s', client_address) def main(argv=sys.argv): """Entry point for starting a TCP git server.""" import optparse parser = optparse.OptionParser() parser.add_option("-l", "--listen_address", dest="listen_address", default="localhost", help="Binding IP address.") parser.add_option("-p", "--port", dest="port", type=int, default=TCP_GIT_PORT, help="Binding TCP port.") options, args = parser.parse_args(argv) log_utils.default_logging_config() if len(args) > 1: gitdir = args[1] else: gitdir = '.' # TODO(jelmer): Support git-daemon-export-ok and --export-all. backend = FileSystemBackend(gitdir) server = TCPGitServer(backend, options.listen_address, options.port) server.serve_forever() def serve_command(handler_cls, argv=sys.argv, backend=None, inf=sys.stdin, outf=sys.stdout): """Serve a single command. This is mostly useful for the implementation of commands used by e.g. git+ssh. :param handler_cls: `Handler` class to use for the request :param argv: execv-style command-line arguments. Defaults to sys.argv. :param backend: `Backend` to use :param inf: File-like object to read from, defaults to standard input. :param outf: File-like object to write to, defaults to standard output. :return: Exit code for use with sys.exit. 0 on success, 1 on failure. """ if backend is None: backend = FileSystemBackend() def send_fn(data): outf.write(data) outf.flush() proto = Protocol(inf.read, send_fn) handler = handler_cls(backend, argv[1:], proto) # FIXME: Catch exceptions and write a single-line summary to outf. handler.handle() return 0 def generate_info_refs(repo): """Generate an info refs file.""" refs = repo.get_refs() return write_info_refs(refs, repo.object_store) def generate_objects_info_packs(repo): """Generate an index for for packs.""" for pack in repo.object_store.packs: yield ( b'P ' + pack.data.filename.encode(sys.getfilesystemencoding()) + b'\n') def update_server_info(repo): """Generate server info for dumb file access. This generates info/refs and objects/info/packs, similar to "git update-server-info". """ repo._put_named_file( os.path.join('info', 'refs'), b"".join(generate_info_refs(repo))) repo._put_named_file( os.path.join('objects', 'info', 'packs'), b"".join(generate_objects_info_packs(repo))) if __name__ == '__main__': main() diff --git a/dulwich/tests/__init__.py b/dulwich/tests/__init__.py index a533b176..2984efc9 100644 --- a/dulwich/tests/__init__.py +++ b/dulwich/tests/__init__.py @@ -1,194 +1,195 @@ # __init__.py -- The tests for dulwich # Copyright (C) 2007 James Westby # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """Tests for Dulwich.""" import doctest import os import shutil import subprocess import sys import tempfile # If Python itself provides an exception, use that import unittest from unittest import ( # noqa: F401 SkipTest, TestCase as _TestCase, skipIf, expectedFailure, ) class TestCase(_TestCase): def setUp(self): super(TestCase, self).setUp() self._old_home = os.environ.get("HOME") os.environ["HOME"] = "/nonexistant" def tearDown(self): super(TestCase, self).tearDown() if self._old_home: os.environ["HOME"] = self._old_home else: del os.environ["HOME"] class BlackboxTestCase(TestCase): """Blackbox testing.""" # TODO(jelmer): Include more possible binary paths. bin_directories = [os.path.abspath(os.path.join( os.path.dirname(__file__), "..", "..", "bin")), '/usr/bin', '/usr/local/bin'] def bin_path(self, name): """Determine the full path of a binary. :param name: Name of the script :return: Full path """ for d in self.bin_directories: p = os.path.join(d, name) if os.path.isfile(p): return p else: raise SkipTest("Unable to find binary %s" % name) def run_command(self, name, args): """Run a Dulwich command. :param name: Name of the command, as it exists in bin/ :param args: Arguments to the command """ env = dict(os.environ) env["PYTHONPATH"] = os.pathsep.join(sys.path) # Since they don't have any extensions, Windows can't recognize # executablility of the Python files in /bin. Even then, we'd have to # expect the user to set up file associations for .py files. # # Save us from all that headache and call python with the bin script. argv = [sys.executable, self.bin_path(name)] + args return subprocess.Popen( argv, stdout=subprocess.PIPE, stdin=subprocess.PIPE, stderr=subprocess.PIPE, env=env) def self_test_suite(): names = [ 'archive', 'blackbox', 'client', 'config', 'diff_tree', 'fastexport', 'file', 'grafts', 'greenthreads', 'hooks', 'ignore', 'index', + 'line_ending', 'lru_cache', 'mailmap', 'objects', 'objectspec', 'object_store', 'missing_obj_finder', 'pack', 'patch', 'porcelain', 'protocol', 'reflog', 'refs', 'repository', 'server', 'stash', 'utils', 'walk', 'web', ] module_names = ['dulwich.tests.test_' + name for name in names] loader = unittest.TestLoader() return loader.loadTestsFromNames(module_names) def tutorial_test_suite(): import dulwich.client # noqa: F401 import dulwich.config # noqa: F401 import dulwich.index # noqa: F401 import dulwich.reflog # noqa: F401 import dulwich.repo # noqa: F401 import dulwich.server # noqa: F401 import dulwich.patch # noqa: F401 tutorial = [ 'introduction', 'file-format', 'repo', 'object-store', 'remote', 'conclusion', ] tutorial_files = ["../../docs/tutorial/%s.txt" % name for name in tutorial] def setup(test): test.__old_cwd = os.getcwd() test.tempdir = tempfile.mkdtemp() test.globs.update({'tempdir': test.tempdir}) os.chdir(test.tempdir) def teardown(test): os.chdir(test.__old_cwd) shutil.rmtree(test.tempdir) return doctest.DocFileSuite( module_relative=True, package='dulwich.tests', setUp=setup, tearDown=teardown, *tutorial_files) def nocompat_test_suite(): result = unittest.TestSuite() result.addTests(self_test_suite()) result.addTests(tutorial_test_suite()) from dulwich.contrib import test_suite as contrib_test_suite result.addTests(contrib_test_suite()) return result def compat_test_suite(): result = unittest.TestSuite() from dulwich.tests.compat import test_suite as compat_test_suite result.addTests(compat_test_suite()) return result def test_suite(): result = unittest.TestSuite() result.addTests(self_test_suite()) if sys.platform != 'win32': result.addTests(tutorial_test_suite()) from dulwich.tests.compat import test_suite as compat_test_suite result.addTests(compat_test_suite()) from dulwich.contrib import test_suite as contrib_test_suite result.addTests(contrib_test_suite()) return result diff --git a/dulwich/tests/compat/test_client.py b/dulwich/tests/compat/test_client.py index f7c3930e..90e26056 100644 --- a/dulwich/tests/compat/test_client.py +++ b/dulwich/tests/compat/test_client.py @@ -1,557 +1,570 @@ # test_client.py -- Compatibilty tests for git client. # Copyright (C) 2010 Google, Inc. # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """Compatibilty tests between the Dulwich client and the cgit server.""" import copy from io import BytesIO import os import select import signal import subprocess import sys import tarfile import tempfile import threading try: from urlparse import unquote except ImportError: from urllib.parse import unquote try: import BaseHTTPServer import SimpleHTTPServer except ImportError: import http.server BaseHTTPServer = http.server SimpleHTTPServer = http.server from dulwich import ( client, errors, file, index, protocol, objects, repo, ) from dulwich.tests import ( SkipTest, expectedFailure, ) from dulwich.tests.compat.utils import ( CompatTestCase, check_for_daemon, import_repo_to_dir, rmtree_ro, run_git_or_fail, _DEFAULT_GIT, ) if sys.platform == 'win32': import ctypes class DulwichClientTestBase(object): """Tests for client/server compatibility.""" def setUp(self): self.gitroot = os.path.dirname( import_repo_to_dir('server_new.export').rstrip(os.sep)) self.dest = os.path.join(self.gitroot, 'dest') file.ensure_dir_exists(self.dest) run_git_or_fail(['init', '--quiet', '--bare'], cwd=self.dest) def tearDown(self): rmtree_ro(self.gitroot) def assertDestEqualsSrc(self): repo_dir = os.path.join(self.gitroot, 'server_new.export') dest_repo_dir = os.path.join(self.gitroot, 'dest') with repo.Repo(repo_dir) as src: with repo.Repo(dest_repo_dir) as dest: self.assertReposEqual(src, dest) def _client(self): raise NotImplementedError() def _build_path(self): raise NotImplementedError() def _do_send_pack(self): c = self._client() srcpath = os.path.join(self.gitroot, 'server_new.export') with repo.Repo(srcpath) as src: sendrefs = dict(src.get_refs()) del sendrefs[b'HEAD'] c.send_pack(self._build_path('/dest'), lambda _: sendrefs, src.object_store.generate_pack_data) def test_send_pack(self): self._do_send_pack() self.assertDestEqualsSrc() def test_send_pack_nothing_to_send(self): self._do_send_pack() self.assertDestEqualsSrc() # nothing to send, but shouldn't raise either. self._do_send_pack() def test_send_without_report_status(self): c = self._client() c._send_capabilities.remove(b'report-status') srcpath = os.path.join(self.gitroot, 'server_new.export') with repo.Repo(srcpath) as src: sendrefs = dict(src.get_refs()) del sendrefs[b'HEAD'] c.send_pack(self._build_path('/dest'), lambda _: sendrefs, src.object_store.generate_pack_data) self.assertDestEqualsSrc() def make_dummy_commit(self, dest): b = objects.Blob.from_string(b'hi') dest.object_store.add_object(b) t = index.commit_tree(dest.object_store, [(b'hi', b.id, 0o100644)]) c = objects.Commit() c.author = c.committer = b'Foo Bar ' c.author_time = c.commit_time = 0 c.author_timezone = c.commit_timezone = 0 c.message = b'hi' c.tree = t dest.object_store.add_object(c) return c.id def disable_ff_and_make_dummy_commit(self): # disable non-fast-forward pushes to the server dest = repo.Repo(os.path.join(self.gitroot, 'dest')) run_git_or_fail(['config', 'receive.denyNonFastForwards', 'true'], cwd=dest.path) commit_id = self.make_dummy_commit(dest) return dest, commit_id def compute_send(self, src): sendrefs = dict(src.get_refs()) del sendrefs[b'HEAD'] return sendrefs, src.object_store.generate_pack_data def test_send_pack_one_error(self): dest, dummy_commit = self.disable_ff_and_make_dummy_commit() dest.refs[b'refs/heads/master'] = dummy_commit repo_dir = os.path.join(self.gitroot, 'server_new.export') with repo.Repo(repo_dir) as src: sendrefs, gen_pack = self.compute_send(src) c = self._client() try: c.send_pack(self._build_path('/dest'), lambda _: sendrefs, gen_pack) except errors.UpdateRefsError as e: self.assertEqual('refs/heads/master failed to update', e.args[0]) self.assertEqual({b'refs/heads/branch': b'ok', b'refs/heads/master': b'non-fast-forward'}, e.ref_status) def test_send_pack_multiple_errors(self): dest, dummy = self.disable_ff_and_make_dummy_commit() # set up for two non-ff errors branch, master = b'refs/heads/branch', b'refs/heads/master' dest.refs[branch] = dest.refs[master] = dummy repo_dir = os.path.join(self.gitroot, 'server_new.export') with repo.Repo(repo_dir) as src: sendrefs, gen_pack = self.compute_send(src) c = self._client() try: c.send_pack(self._build_path('/dest'), lambda _: sendrefs, gen_pack) except errors.UpdateRefsError as e: self.assertIn( str(e), ['{0}, {1} failed to update'.format( branch.decode('ascii'), master.decode('ascii')), '{1}, {0} failed to update'.format( branch.decode('ascii'), master.decode('ascii'))]) self.assertEqual({branch: b'non-fast-forward', master: b'non-fast-forward'}, e.ref_status) def test_archive(self): c = self._client() f = BytesIO() c.archive(self._build_path('/server_new.export'), b'HEAD', f.write) f.seek(0) tf = tarfile.open(fileobj=f) self.assertEqual(['baz', 'foo'], tf.getnames()) def test_fetch_pack(self): c = self._client() with repo.Repo(os.path.join(self.gitroot, 'dest')) as dest: result = c.fetch(self._build_path('/server_new.export'), dest) for r in result.refs.items(): dest.refs.set_if_equals(r[0], None, r[1]) self.assertDestEqualsSrc() + def test_fetch_pack_depth(self): + c = self._client() + with repo.Repo(os.path.join(self.gitroot, 'dest')) as dest: + result = c.fetch(self._build_path('/server_new.export'), dest, + depth=1) + for r in result.refs.items(): + dest.refs.set_if_equals(r[0], None, r[1]) + self.assertEqual( + dest.get_shallow(), + set([b'35e0b59e187dd72a0af294aedffc213eaa4d03ff', + b'514dc6d3fbfe77361bcaef320c4d21b72bc10be9'])) + def test_repeat(self): c = self._client() with repo.Repo(os.path.join(self.gitroot, 'dest')) as dest: result = c.fetch(self._build_path('/server_new.export'), dest) for r in result.refs.items(): dest.refs.set_if_equals(r[0], None, r[1]) self.assertDestEqualsSrc() result = c.fetch(self._build_path('/server_new.export'), dest) for r in result.refs.items(): dest.refs.set_if_equals(r[0], None, r[1]) self.assertDestEqualsSrc() def test_incremental_fetch_pack(self): self.test_fetch_pack() dest, dummy = self.disable_ff_and_make_dummy_commit() dest.refs[b'refs/heads/master'] = dummy c = self._client() repo_dir = os.path.join(self.gitroot, 'server_new.export') with repo.Repo(repo_dir) as dest: result = c.fetch(self._build_path('/dest'), dest) for r in result.refs.items(): dest.refs.set_if_equals(r[0], None, r[1]) self.assertDestEqualsSrc() def test_fetch_pack_no_side_band_64k(self): c = self._client() c._fetch_capabilities.remove(b'side-band-64k') with repo.Repo(os.path.join(self.gitroot, 'dest')) as dest: result = c.fetch(self._build_path('/server_new.export'), dest) for r in result.refs.items(): dest.refs.set_if_equals(r[0], None, r[1]) self.assertDestEqualsSrc() def test_fetch_pack_zero_sha(self): # zero sha1s are already present on the client, and should # be ignored c = self._client() with repo.Repo(os.path.join(self.gitroot, 'dest')) as dest: result = c.fetch( self._build_path('/server_new.export'), dest, lambda refs: [protocol.ZERO_SHA]) for r in result.refs.items(): dest.refs.set_if_equals(r[0], None, r[1]) def test_send_remove_branch(self): with repo.Repo(os.path.join(self.gitroot, 'dest')) as dest: dummy_commit = self.make_dummy_commit(dest) dest.refs[b'refs/heads/master'] = dummy_commit dest.refs[b'refs/heads/abranch'] = dummy_commit sendrefs = dict(dest.refs) sendrefs[b'refs/heads/abranch'] = b"00" * 20 del sendrefs[b'HEAD'] def gen_pack(have, want, ofs_delta=False): return 0, [] c = self._client() self.assertEqual(dest.refs[b"refs/heads/abranch"], dummy_commit) c.send_pack( self._build_path('/dest'), lambda _: sendrefs, gen_pack) self.assertFalse(b"refs/heads/abranch" in dest.refs) def test_get_refs(self): c = self._client() refs = c.get_refs(self._build_path('/server_new.export')) repo_dir = os.path.join(self.gitroot, 'server_new.export') with repo.Repo(repo_dir) as dest: self.assertDictEqual(dest.refs.as_dict(), refs) class DulwichTCPClientTest(CompatTestCase, DulwichClientTestBase): def setUp(self): CompatTestCase.setUp(self) DulwichClientTestBase.setUp(self) if check_for_daemon(limit=1): raise SkipTest('git-daemon was already running on port %s' % protocol.TCP_GIT_PORT) fd, self.pidfile = tempfile.mkstemp(prefix='dulwich-test-git-client', suffix=".pid") os.fdopen(fd).close() args = [_DEFAULT_GIT, 'daemon', '--verbose', '--export-all', '--pid-file=%s' % self.pidfile, '--base-path=%s' % self.gitroot, '--enable=receive-pack', '--enable=upload-archive', '--listen=localhost', '--reuseaddr', self.gitroot] self.process = subprocess.Popen( args, cwd=self.gitroot, stdout=subprocess.PIPE, stderr=subprocess.PIPE) if not check_for_daemon(): raise SkipTest('git-daemon failed to start') def tearDown(self): with open(self.pidfile) as f: pid = int(f.read().strip()) if sys.platform == 'win32': PROCESS_TERMINATE = 1 handle = ctypes.windll.kernel32.OpenProcess( PROCESS_TERMINATE, False, pid) ctypes.windll.kernel32.TerminateProcess(handle, -1) ctypes.windll.kernel32.CloseHandle(handle) else: try: os.kill(pid, signal.SIGKILL) os.unlink(self.pidfile) except (OSError, IOError): pass self.process.wait() self.process.stdout.close() self.process.stderr.close() DulwichClientTestBase.tearDown(self) CompatTestCase.tearDown(self) def _client(self): return client.TCPGitClient('localhost') def _build_path(self, path): return path if sys.platform == 'win32': @expectedFailure def test_fetch_pack_no_side_band_64k(self): DulwichClientTestBase.test_fetch_pack_no_side_band_64k(self) class TestSSHVendor(object): @staticmethod def run_command(host, command, username=None, port=None, password=None, key_filename=None): cmd, path = command.split(' ') cmd = cmd.split('-', 1) path = path.replace("'", "") p = subprocess.Popen(cmd + [path], bufsize=0, stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE) return client.SubprocessWrapper(p) class DulwichMockSSHClientTest(CompatTestCase, DulwichClientTestBase): def setUp(self): CompatTestCase.setUp(self) DulwichClientTestBase.setUp(self) self.real_vendor = client.get_ssh_vendor client.get_ssh_vendor = TestSSHVendor def tearDown(self): DulwichClientTestBase.tearDown(self) CompatTestCase.tearDown(self) client.get_ssh_vendor = self.real_vendor def _client(self): return client.SSHGitClient('localhost') def _build_path(self, path): return self.gitroot + path class DulwichSubprocessClientTest(CompatTestCase, DulwichClientTestBase): def setUp(self): CompatTestCase.setUp(self) DulwichClientTestBase.setUp(self) def tearDown(self): DulwichClientTestBase.tearDown(self) CompatTestCase.tearDown(self) def _client(self): - return client.SubprocessGitClient(stderr=subprocess.PIPE) + return client.SubprocessGitClient() def _build_path(self, path): return self.gitroot + path class GitHTTPRequestHandler(SimpleHTTPServer.SimpleHTTPRequestHandler): """HTTP Request handler that calls out to 'git http-backend'.""" # Make rfile unbuffered -- we need to read one line and then pass # the rest to a subprocess, so we can't use buffered input. rbufsize = 0 def do_POST(self): self.run_backend() def do_GET(self): self.run_backend() def send_head(self): return self.run_backend() def log_request(self, code='-', size='-'): # Let's be quiet, the test suite is noisy enough already pass def run_backend(self): """Call out to git http-backend.""" # Based on CGIHTTPServer.CGIHTTPRequestHandler.run_cgi: # Copyright (c) 2001-2010 Python Software Foundation; # All Rights Reserved # Licensed under the Python Software Foundation License. rest = self.path # find an explicit query string, if present. i = rest.rfind('?') if i >= 0: rest, query = rest[:i], rest[i+1:] else: query = '' env = copy.deepcopy(os.environ) env['SERVER_SOFTWARE'] = self.version_string() env['SERVER_NAME'] = self.server.server_name env['GATEWAY_INTERFACE'] = 'CGI/1.1' env['SERVER_PROTOCOL'] = self.protocol_version env['SERVER_PORT'] = str(self.server.server_port) env['GIT_PROJECT_ROOT'] = self.server.root_path env["GIT_HTTP_EXPORT_ALL"] = "1" env['REQUEST_METHOD'] = self.command uqrest = unquote(rest) env['PATH_INFO'] = uqrest env['SCRIPT_NAME'] = "/" if query: env['QUERY_STRING'] = query host = self.address_string() if host != self.client_address[0]: env['REMOTE_HOST'] = host env['REMOTE_ADDR'] = self.client_address[0] authorization = self.headers.get("authorization") if authorization: authorization = authorization.split() if len(authorization) == 2: import base64 import binascii env['AUTH_TYPE'] = authorization[0] if authorization[0].lower() == "basic": try: authorization = base64.decodestring(authorization[1]) except binascii.Error: pass else: authorization = authorization.split(':') if len(authorization) == 2: env['REMOTE_USER'] = authorization[0] # XXX REMOTE_IDENT content_type = self.headers.get('content-type') if content_type: env['CONTENT_TYPE'] = content_type length = self.headers.get('content-length') if length: env['CONTENT_LENGTH'] = length referer = self.headers.get('referer') if referer: env['HTTP_REFERER'] = referer accept = [] for line in self.headers.getallmatchingheaders('accept'): if line[:1] in "\t\n\r ": accept.append(line.strip()) else: accept = accept + line[7:].split(',') env['HTTP_ACCEPT'] = ','.join(accept) ua = self.headers.get('user-agent') if ua: env['HTTP_USER_AGENT'] = ua co = self.headers.get('cookie') if co: env['HTTP_COOKIE'] = co # XXX Other HTTP_* headers # Since we're setting the env in the parent, provide empty # values to override previously set values for k in ('QUERY_STRING', 'REMOTE_HOST', 'CONTENT_LENGTH', 'HTTP_USER_AGENT', 'HTTP_COOKIE', 'HTTP_REFERER'): env.setdefault(k, "") self.wfile.write(b"HTTP/1.1 200 Script output follows\r\n") self.wfile.write( ("Server: %s\r\n" % self.server.server_name).encode('ascii')) self.wfile.write( ("Date: %s\r\n" % self.date_time_string()).encode('ascii')) decoded_query = query.replace('+', ' ') try: nbytes = int(length) except (TypeError, ValueError): nbytes = 0 if self.command.lower() == "post" and nbytes > 0: data = self.rfile.read(nbytes) else: data = None + env['CONTENT_LENGTH'] = '0' # throw away additional data [see bug #427345] while select.select([self.rfile._sock], [], [], 0)[0]: if not self.rfile._sock.recv(1): break args = ['http-backend'] if '=' not in decoded_query: args.append(decoded_query) stdout = run_git_or_fail( args, input=data, env=env, stderr=subprocess.PIPE) self.wfile.write(stdout) class HTTPGitServer(BaseHTTPServer.HTTPServer): allow_reuse_address = True def __init__(self, server_address, root_path): BaseHTTPServer.HTTPServer.__init__( self, server_address, GitHTTPRequestHandler) self.root_path = root_path self.server_name = "localhost" def get_url(self): return 'http://%s:%s/' % (self.server_name, self.server_port) class DulwichHttpClientTest(CompatTestCase, DulwichClientTestBase): min_git_version = (1, 7, 0, 2) def setUp(self): CompatTestCase.setUp(self) DulwichClientTestBase.setUp(self) self._httpd = HTTPGitServer(("localhost", 0), self.gitroot) self.addCleanup(self._httpd.shutdown) threading.Thread(target=self._httpd.serve_forever).start() run_git_or_fail(['config', 'http.uploadpack', 'true'], cwd=self.dest) run_git_or_fail(['config', 'http.receivepack', 'true'], cwd=self.dest) def tearDown(self): DulwichClientTestBase.tearDown(self) CompatTestCase.tearDown(self) self._httpd.shutdown() self._httpd.socket.close() def _client(self): return client.HttpGitClient(self._httpd.get_url()) def _build_path(self, path): return path def test_archive(self): raise SkipTest("exporting archives not supported over http") diff --git a/dulwich/tests/compat/test_pack.py b/dulwich/tests/compat/test_pack.py index ea75f8cf..46daa68a 100644 --- a/dulwich/tests/compat/test_pack.py +++ b/dulwich/tests/compat/test_pack.py @@ -1,156 +1,156 @@ # test_pack.py -- Compatibility tests for git packs. # Copyright (C) 2010 Google, Inc. # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """Compatibility tests for git packs.""" import binascii import os import re import shutil import tempfile from dulwich.pack import ( write_pack, ) from dulwich.objects import ( Blob, ) from dulwich.tests import ( SkipTest, ) from dulwich.tests.test_pack import ( a_sha, pack1_sha, PackTests, ) from dulwich.tests.compat.utils import ( require_git_version, run_git_or_fail, ) -_NON_DELTA_RE = re.compile(b'non delta: (?P\d+) objects') +_NON_DELTA_RE = re.compile(b'non delta: (?P\\d+) objects') def _git_verify_pack_object_list(output): pack_shas = set() for line in output.splitlines(): sha = line[:40] try: binascii.unhexlify(sha) except (TypeError, binascii.Error): continue # non-sha line pack_shas.add(sha) return pack_shas class TestPack(PackTests): """Compatibility tests for reading and writing pack files.""" def setUp(self): require_git_version((1, 5, 0)) super(TestPack, self).setUp() self._tempdir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, self._tempdir) def test_copy(self): with self.get_pack(pack1_sha) as origpack: self.assertSucceeds(origpack.index.check) pack_path = os.path.join(self._tempdir, "Elch") write_pack(pack_path, origpack.pack_tuples()) output = run_git_or_fail(['verify-pack', '-v', pack_path]) orig_shas = set(o.id for o in origpack.iterobjects()) self.assertEqual(orig_shas, _git_verify_pack_object_list(output)) def test_deltas_work(self): with self.get_pack(pack1_sha) as orig_pack: orig_blob = orig_pack[a_sha] new_blob = Blob() new_blob.data = orig_blob.data + b'x' all_to_pack = list(orig_pack.pack_tuples()) + [(new_blob, None)] pack_path = os.path.join(self._tempdir, 'pack_with_deltas') write_pack(pack_path, all_to_pack, deltify=True) output = run_git_or_fail(['verify-pack', '-v', pack_path]) self.assertEqual(set(x[0].id for x in all_to_pack), _git_verify_pack_object_list(output)) # We specifically made a new blob that should be a delta # against the blob a_sha, so make sure we really got only 3 # non-delta objects: got_non_delta = int(_NON_DELTA_RE.search(output).group('non_delta')) self.assertEqual( 3, got_non_delta, 'Expected 3 non-delta objects, got %d' % got_non_delta) def test_delta_medium_object(self): # This tests an object set that will have a copy operation # 2**20 in size. with self.get_pack(pack1_sha) as orig_pack: orig_blob = orig_pack[a_sha] new_blob = Blob() new_blob.data = orig_blob.data + (b'x' * 2 ** 20) new_blob_2 = Blob() new_blob_2.data = new_blob.data + b'y' all_to_pack = list(orig_pack.pack_tuples()) + [(new_blob, None), (new_blob_2, None)] pack_path = os.path.join(self._tempdir, 'pack_with_deltas') write_pack(pack_path, all_to_pack, deltify=True) output = run_git_or_fail(['verify-pack', '-v', pack_path]) self.assertEqual(set(x[0].id for x in all_to_pack), _git_verify_pack_object_list(output)) # We specifically made a new blob that should be a delta # against the blob a_sha, so make sure we really got only 3 # non-delta objects: got_non_delta = int(_NON_DELTA_RE.search(output).group('non_delta')) self.assertEqual( 3, got_non_delta, 'Expected 3 non-delta objects, got %d' % got_non_delta) # We expect one object to have a delta chain length of two # (new_blob_2), so let's verify that actually happens: self.assertIn(b'chain length = 2', output) # This test is SUPER slow: over 80 seconds on a 2012-era # laptop. This is because SequenceMatcher is worst-case quadratic # on the input size. It's impractical to produce deltas for # objects this large, but it's still worth doing the right thing # when it happens. def test_delta_large_object(self): # This tests an object set that will have a copy operation # 2**25 in size. This is a copy large enough that it requires # two copy operations in git's binary delta format. raise SkipTest('skipping slow, large test') with self.get_pack(pack1_sha) as orig_pack: new_blob = Blob() new_blob.data = 'big blob' + ('x' * 2 ** 25) new_blob_2 = Blob() new_blob_2.data = new_blob.data + 'y' all_to_pack = list(orig_pack.pack_tuples()) + [(new_blob, None), (new_blob_2, None)] pack_path = os.path.join(self._tempdir, "pack_with_deltas") write_pack(pack_path, all_to_pack, deltify=True) output = run_git_or_fail(['verify-pack', '-v', pack_path]) self.assertEqual(set(x[0].id for x in all_to_pack), _git_verify_pack_object_list(output)) # We specifically made a new blob that should be a delta # against the blob a_sha, so make sure we really got only 4 # non-delta objects: got_non_delta = int(_NON_DELTA_RE.search(output).group('non_delta')) self.assertEqual( 4, got_non_delta, 'Expected 4 non-delta objects, got %d' % got_non_delta) diff --git a/dulwich/tests/test_client.py b/dulwich/tests/test_client.py index d49428a5..5ea6b480 100644 --- a/dulwich/tests/test_client.py +++ b/dulwich/tests/test_client.py @@ -1,1158 +1,1226 @@ # test_client.py -- Tests for the git protocol, client side # Copyright (C) 2009 Jelmer Vernooij # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # from io import BytesIO import base64 import sys import shutil import tempfile import warnings try: from urllib import quote as urlquote except ImportError: from urllib.parse import quote as urlquote try: import urlparse except ImportError: import urllib.parse as urlparse import urllib3 import dulwich from dulwich import ( client, ) from dulwich.client import ( + InvalidWants, LocalGitClient, TraditionalGitClient, TCPGitClient, SSHGitClient, HttpGitClient, ReportStatusParser, SendPackError, StrangeHostname, SubprocessSSHVendor, PLinkSSHVendor, UpdateRefsError, + check_wants, default_urllib3_manager, get_transport_and_path, get_transport_and_path_from_url, parse_rsync_url, ) from dulwich.config import ( ConfigDict, ) from dulwich.tests import ( TestCase, ) from dulwich.protocol import ( TCP_GIT_PORT, Protocol, ) from dulwich.pack import ( pack_objects_to_data, write_pack_data, write_pack_objects, ) from dulwich.objects import ( Commit, Tree ) from dulwich.repo import ( MemoryRepo, Repo, ) from dulwich.tests import skipIf from dulwich.tests.utils import ( open_repo, tear_down_repo, setup_warning_catcher, ) class DummyClient(TraditionalGitClient): def __init__(self, can_read, read, write): self.can_read = can_read self.read = read self.write = write TraditionalGitClient.__init__(self) def _connect(self, service, path): - return Protocol(self.read, self.write), self.can_read + return Protocol(self.read, self.write), self.can_read, None class DummyPopen(): def __init__(self, *args, **kwards): self.stdin = BytesIO(b"stdin") self.stdout = BytesIO(b"stdout") self.stderr = BytesIO(b"stderr") self.returncode = 0 self.args = args self.kwargs = kwards def communicate(self, *args, **kwards): return ('Running', '') def wait(self, *args, **kwards): return False # TODO(durin42): add unit-level tests of GitClient class GitClientTests(TestCase): def setUp(self): super(GitClientTests, self).setUp() self.rout = BytesIO() self.rin = BytesIO() self.client = DummyClient(lambda x: True, self.rin.read, self.rout.write) def test_caps(self): agent_cap = ( 'agent=dulwich/%d.%d.%d' % dulwich.__version__).encode('ascii') self.assertEqual(set([b'multi_ack', b'side-band-64k', b'ofs-delta', - b'thin-pack', b'multi_ack_detailed', + b'thin-pack', b'multi_ack_detailed', b'shallow', agent_cap]), set(self.client._fetch_capabilities)) self.assertEqual(set([b'ofs-delta', b'report-status', b'side-band-64k', agent_cap]), set(self.client._send_capabilities)) def test_archive_ack(self): self.rin.write( b'0009NACK\n' b'0000') self.rin.seek(0) self.client.archive(b'bla', b'HEAD', None, None) self.assertEqual(self.rout.getvalue(), b'0011argument HEAD0000') def test_fetch_empty(self): self.rin.write(b'0000') self.rin.seek(0) def check_heads(heads): self.assertEqual(heads, {}) return [] ret = self.client.fetch_pack(b'/', check_heads, None, None) self.assertEqual({}, ret.refs) self.assertEqual({}, ret.symrefs) def test_fetch_pack_ignores_magic_ref(self): self.rin.write( b'00000000000000000000000000000000000000000000 capabilities^{}' b'\x00 multi_ack ' b'thin-pack side-band side-band-64k ofs-delta shallow no-progress ' b'include-tag\n' b'0000') self.rin.seek(0) def check_heads(heads): self.assertEqual({}, heads) return [] ret = self.client.fetch_pack(b'bla', check_heads, None, None, None) self.assertEqual({}, ret.refs) self.assertEqual({}, ret.symrefs) self.assertEqual(self.rout.getvalue(), b'0000') def test_fetch_pack_none(self): self.rin.write( b'008855dcc6bf963f922e1ed5c4bbaaefcfacef57b1d7 HEAD\x00multi_ack ' b'thin-pack side-band side-band-64k ofs-delta shallow no-progress ' b'include-tag\n' b'0000') self.rin.seek(0) ret = self.client.fetch_pack( b'bla', lambda heads: [], None, None, None) self.assertEqual( {b'HEAD': b'55dcc6bf963f922e1ed5c4bbaaefcfacef57b1d7'}, ret.refs) self.assertEqual({}, ret.symrefs) self.assertEqual(self.rout.getvalue(), b'0000') + def test_fetch_pack_sha_not_in_ref(self): + self.rin.write( + b'008855dcc6bf963f922e1ed5c4bbaaefcfacef57b1d7 HEAD\x00multi_ack ' + b'thin-pack side-band side-band-64k ofs-delta shallow no-progress ' + b'include-tag\n' + b'0000') + self.rin.seek(0) + self.assertRaises( + InvalidWants, self.client.fetch_pack, + b'bla', + lambda heads: ['aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa'], + None, None, + None) + def test_send_pack_no_sideband64k_with_update_ref_error(self): # No side-bank-64k reported by server shouldn't try to parse # side band data pkts = [b'55dcc6bf963f922e1ed5c4bbaaefcfacef57b1d7 capabilities^{}' b'\x00 report-status delete-refs ofs-delta\n', b'', b"unpack ok", b"ng refs/foo/bar pre-receive hook declined", b''] for pkt in pkts: if pkt == b'': self.rin.write(b"0000") else: self.rin.write(("%04x" % (len(pkt)+4)).encode('ascii') + pkt) self.rin.seek(0) tree = Tree() commit = Commit() commit.tree = tree commit.parents = [] commit.author = commit.committer = b'test user' commit.commit_time = commit.author_time = 1174773719 commit.commit_timezone = commit.author_timezone = 0 commit.encoding = b'UTF-8' commit.message = b'test message' - def determine_wants(refs): + def update_refs(refs): return {b'refs/foo/bar': commit.id, } def generate_pack_data(have, want, ofs_delta=False): return pack_objects_to_data([(commit, None), (tree, ''), ]) self.assertRaises(UpdateRefsError, self.client.send_pack, "blah", - determine_wants, generate_pack_data) + update_refs, generate_pack_data) def test_send_pack_none(self): self.rin.write( b'0078310ca9477129b8586fa2afc779c1f57cf64bba6c ' b'refs/heads/master\x00 report-status delete-refs ' b'side-band-64k quiet ofs-delta\n' b'0000') self.rin.seek(0) - def determine_wants(refs): + def update_refs(refs): return { b'refs/heads/master': b'310ca9477129b8586fa2afc779c1f57cf64bba6c' } def generate_pack_data(have, want, ofs_delta=False): return 0, [] - self.client.send_pack(b'/', determine_wants, generate_pack_data) + self.client.send_pack(b'/', update_refs, generate_pack_data) self.assertEqual(self.rout.getvalue(), b'0000') def test_send_pack_keep_and_delete(self): self.rin.write( b'0063310ca9477129b8586fa2afc779c1f57cf64bba6c ' b'refs/heads/master\x00report-status delete-refs ofs-delta\n' b'003f310ca9477129b8586fa2afc779c1f57cf64bba6c refs/heads/keepme\n' b'0000000eunpack ok\n' b'0019ok refs/heads/master\n' b'0000') self.rin.seek(0) - def determine_wants(refs): + def update_refs(refs): return {b'refs/heads/master': b'0' * 40} def generate_pack_data(have, want, ofs_delta=False): return 0, [] - self.client.send_pack(b'/', determine_wants, generate_pack_data) + self.client.send_pack(b'/', update_refs, generate_pack_data) self.assertIn( self.rout.getvalue(), [b'007f310ca9477129b8586fa2afc779c1f57cf64bba6c ' b'0000000000000000000000000000000000000000 ' b'refs/heads/master\x00report-status ofs-delta0000', b'007f310ca9477129b8586fa2afc779c1f57cf64bba6c ' b'0000000000000000000000000000000000000000 ' b'refs/heads/master\x00ofs-delta report-status0000']) def test_send_pack_delete_only(self): self.rin.write( b'0063310ca9477129b8586fa2afc779c1f57cf64bba6c ' b'refs/heads/master\x00report-status delete-refs ofs-delta\n' b'0000000eunpack ok\n' b'0019ok refs/heads/master\n' b'0000') self.rin.seek(0) - def determine_wants(refs): + def update_refs(refs): return {b'refs/heads/master': b'0' * 40} def generate_pack_data(have, want, ofs_delta=False): return 0, [] - self.client.send_pack(b'/', determine_wants, generate_pack_data) + self.client.send_pack(b'/', update_refs, generate_pack_data) self.assertIn( self.rout.getvalue(), [b'007f310ca9477129b8586fa2afc779c1f57cf64bba6c ' b'0000000000000000000000000000000000000000 ' b'refs/heads/master\x00report-status ofs-delta0000', b'007f310ca9477129b8586fa2afc779c1f57cf64bba6c ' b'0000000000000000000000000000000000000000 ' b'refs/heads/master\x00ofs-delta report-status0000']) def test_send_pack_new_ref_only(self): self.rin.write( b'0063310ca9477129b8586fa2afc779c1f57cf64bba6c ' b'refs/heads/master\x00report-status delete-refs ofs-delta\n' b'0000000eunpack ok\n' b'0019ok refs/heads/blah12\n' b'0000') self.rin.seek(0) - def determine_wants(refs): + def update_refs(refs): return { b'refs/heads/blah12': b'310ca9477129b8586fa2afc779c1f57cf64bba6c', b'refs/heads/master': b'310ca9477129b8586fa2afc779c1f57cf64bba6c' } def generate_pack_data(have, want, ofs_delta=False): return 0, [] f = BytesIO() write_pack_objects(f, {}) - self.client.send_pack('/', determine_wants, generate_pack_data) + self.client.send_pack('/', update_refs, generate_pack_data) self.assertIn( self.rout.getvalue(), [b'007f0000000000000000000000000000000000000000 ' b'310ca9477129b8586fa2afc779c1f57cf64bba6c ' b'refs/heads/blah12\x00report-status ofs-delta0000' + f.getvalue(), b'007f0000000000000000000000000000000000000000 ' b'310ca9477129b8586fa2afc779c1f57cf64bba6c ' b'refs/heads/blah12\x00ofs-delta report-status0000' + f.getvalue()]) def test_send_pack_new_ref(self): self.rin.write( b'0064310ca9477129b8586fa2afc779c1f57cf64bba6c ' b'refs/heads/master\x00 report-status delete-refs ofs-delta\n' b'0000000eunpack ok\n' b'0019ok refs/heads/blah12\n' b'0000') self.rin.seek(0) tree = Tree() commit = Commit() commit.tree = tree commit.parents = [] commit.author = commit.committer = b'test user' commit.commit_time = commit.author_time = 1174773719 commit.commit_timezone = commit.author_timezone = 0 commit.encoding = b'UTF-8' commit.message = b'test message' - def determine_wants(refs): + def update_refs(refs): return { b'refs/heads/blah12': commit.id, b'refs/heads/master': b'310ca9477129b8586fa2afc779c1f57cf64bba6c' } def generate_pack_data(have, want, ofs_delta=False): return pack_objects_to_data([(commit, None), (tree, b''), ]) f = BytesIO() write_pack_data(f, *generate_pack_data(None, None)) - self.client.send_pack(b'/', determine_wants, generate_pack_data) + self.client.send_pack(b'/', update_refs, generate_pack_data) self.assertIn( self.rout.getvalue(), [b'007f0000000000000000000000000000000000000000 ' + commit.id + b' refs/heads/blah12\x00report-status ofs-delta0000' + f.getvalue(), b'007f0000000000000000000000000000000000000000 ' + commit.id + b' refs/heads/blah12\x00ofs-delta report-status0000' + f.getvalue()]) def test_send_pack_no_deleteref_delete_only(self): pkts = [b'310ca9477129b8586fa2afc779c1f57cf64bba6c refs/heads/master' b'\x00 report-status ofs-delta\n', b'', b''] for pkt in pkts: if pkt == b'': self.rin.write(b"0000") else: self.rin.write(("%04x" % (len(pkt)+4)).encode('ascii') + pkt) self.rin.seek(0) - def determine_wants(refs): + def update_refs(refs): return {b'refs/heads/master': b'0' * 40} def generate_pack_data(have, want, ofs_delta=False): return 0, [] self.assertRaises(UpdateRefsError, self.client.send_pack, b"/", - determine_wants, generate_pack_data) + update_refs, generate_pack_data) self.assertEqual(self.rout.getvalue(), b'0000') class TestGetTransportAndPath(TestCase): def test_tcp(self): c, path = get_transport_and_path('git://foo.com/bar/baz') self.assertTrue(isinstance(c, TCPGitClient)) self.assertEqual('foo.com', c._host) self.assertEqual(TCP_GIT_PORT, c._port) self.assertEqual('/bar/baz', path) def test_tcp_port(self): c, path = get_transport_and_path('git://foo.com:1234/bar/baz') self.assertTrue(isinstance(c, TCPGitClient)) self.assertEqual('foo.com', c._host) self.assertEqual(1234, c._port) self.assertEqual('/bar/baz', path) def test_git_ssh_explicit(self): c, path = get_transport_and_path('git+ssh://foo.com/bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo.com', c.host) self.assertEqual(None, c.port) self.assertEqual(None, c.username) self.assertEqual('/bar/baz', path) def test_ssh_explicit(self): c, path = get_transport_and_path('ssh://foo.com/bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo.com', c.host) self.assertEqual(None, c.port) self.assertEqual(None, c.username) self.assertEqual('/bar/baz', path) def test_ssh_port_explicit(self): c, path = get_transport_and_path( 'git+ssh://foo.com:1234/bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo.com', c.host) self.assertEqual(1234, c.port) self.assertEqual('/bar/baz', path) def test_username_and_port_explicit_unknown_scheme(self): c, path = get_transport_and_path( 'unknown://git@server:7999/dply/stuff.git') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('unknown', c.host) self.assertEqual('//git@server:7999/dply/stuff.git', path) def test_username_and_port_explicit(self): c, path = get_transport_and_path( 'ssh://git@server:7999/dply/stuff.git') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('git', c.username) self.assertEqual('server', c.host) self.assertEqual(7999, c.port) self.assertEqual('/dply/stuff.git', path) def test_ssh_abspath_doubleslash(self): c, path = get_transport_and_path('git+ssh://foo.com//bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo.com', c.host) self.assertEqual(None, c.port) self.assertEqual(None, c.username) self.assertEqual('//bar/baz', path) def test_ssh_port(self): c, path = get_transport_and_path( 'git+ssh://foo.com:1234/bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo.com', c.host) self.assertEqual(1234, c.port) self.assertEqual('/bar/baz', path) def test_ssh_implicit(self): c, path = get_transport_and_path('foo:/bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo', c.host) self.assertEqual(None, c.port) self.assertEqual(None, c.username) self.assertEqual('/bar/baz', path) def test_ssh_host(self): c, path = get_transport_and_path('foo.com:/bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo.com', c.host) self.assertEqual(None, c.port) self.assertEqual(None, c.username) self.assertEqual('/bar/baz', path) def test_ssh_user_host(self): c, path = get_transport_and_path('user@foo.com:/bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo.com', c.host) self.assertEqual(None, c.port) self.assertEqual('user', c.username) self.assertEqual('/bar/baz', path) def test_ssh_relpath(self): c, path = get_transport_and_path('foo:bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo', c.host) self.assertEqual(None, c.port) self.assertEqual(None, c.username) self.assertEqual('bar/baz', path) def test_ssh_host_relpath(self): c, path = get_transport_and_path('foo.com:bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo.com', c.host) self.assertEqual(None, c.port) self.assertEqual(None, c.username) self.assertEqual('bar/baz', path) def test_ssh_user_host_relpath(self): c, path = get_transport_and_path('user@foo.com:bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo.com', c.host) self.assertEqual(None, c.port) self.assertEqual('user', c.username) self.assertEqual('bar/baz', path) def test_local(self): c, path = get_transport_and_path('foo.bar/baz') self.assertTrue(isinstance(c, LocalGitClient)) self.assertEqual('foo.bar/baz', path) @skipIf(sys.platform != 'win32', 'Behaviour only happens on windows.') def test_local_abs_windows_path(self): c, path = get_transport_and_path('C:\\foo.bar\\baz') self.assertTrue(isinstance(c, LocalGitClient)) self.assertEqual('C:\\foo.bar\\baz', path) def test_error(self): # Need to use a known urlparse.uses_netloc URL scheme to get the # expected parsing of the URL on Python versions less than 2.6.5 c, path = get_transport_and_path('prospero://bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) def test_http(self): url = 'https://github.com/jelmer/dulwich' c, path = get_transport_and_path(url) self.assertTrue(isinstance(c, HttpGitClient)) self.assertEqual('/jelmer/dulwich', path) def test_http_auth(self): url = 'https://user:passwd@github.com/jelmer/dulwich' c, path = get_transport_and_path(url) self.assertTrue(isinstance(c, HttpGitClient)) self.assertEqual('/jelmer/dulwich', path) self.assertEqual('user', c._username) self.assertEqual('passwd', c._password) + def test_http_auth_with_username(self): + url = 'https://github.com/jelmer/dulwich' + + c, path = get_transport_and_path( + url, username='user2', password='blah') + + self.assertTrue(isinstance(c, HttpGitClient)) + self.assertEqual('/jelmer/dulwich', path) + self.assertEqual('user2', c._username) + self.assertEqual('blah', c._password) + + def test_http_auth_with_username_and_in_url(self): + url = 'https://user:passwd@github.com/jelmer/dulwich' + + c, path = get_transport_and_path( + url, username='user2', password='blah') + + self.assertTrue(isinstance(c, HttpGitClient)) + self.assertEqual('/jelmer/dulwich', path) + self.assertEqual('user', c._username) + self.assertEqual('passwd', c._password) + def test_http_no_auth(self): url = 'https://github.com/jelmer/dulwich' c, path = get_transport_and_path(url) self.assertTrue(isinstance(c, HttpGitClient)) self.assertEqual('/jelmer/dulwich', path) self.assertIs(None, c._username) self.assertIs(None, c._password) class TestGetTransportAndPathFromUrl(TestCase): def test_tcp(self): c, path = get_transport_and_path_from_url('git://foo.com/bar/baz') self.assertTrue(isinstance(c, TCPGitClient)) self.assertEqual('foo.com', c._host) self.assertEqual(TCP_GIT_PORT, c._port) self.assertEqual('/bar/baz', path) def test_tcp_port(self): c, path = get_transport_and_path_from_url('git://foo.com:1234/bar/baz') self.assertTrue(isinstance(c, TCPGitClient)) self.assertEqual('foo.com', c._host) self.assertEqual(1234, c._port) self.assertEqual('/bar/baz', path) def test_ssh_explicit(self): c, path = get_transport_and_path_from_url('git+ssh://foo.com/bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo.com', c.host) self.assertEqual(None, c.port) self.assertEqual(None, c.username) self.assertEqual('/bar/baz', path) def test_ssh_port_explicit(self): c, path = get_transport_and_path_from_url( 'git+ssh://foo.com:1234/bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo.com', c.host) self.assertEqual(1234, c.port) self.assertEqual('/bar/baz', path) def test_ssh_homepath(self): c, path = get_transport_and_path_from_url( 'git+ssh://foo.com/~/bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo.com', c.host) self.assertEqual(None, c.port) self.assertEqual(None, c.username) self.assertEqual('/~/bar/baz', path) def test_ssh_port_homepath(self): c, path = get_transport_and_path_from_url( 'git+ssh://foo.com:1234/~/bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo.com', c.host) self.assertEqual(1234, c.port) self.assertEqual('/~/bar/baz', path) def test_ssh_host_relpath(self): self.assertRaises( ValueError, get_transport_and_path_from_url, 'foo.com:bar/baz') def test_ssh_user_host_relpath(self): self.assertRaises( ValueError, get_transport_and_path_from_url, 'user@foo.com:bar/baz') def test_local_path(self): self.assertRaises( ValueError, get_transport_and_path_from_url, 'foo.bar/baz') def test_error(self): # Need to use a known urlparse.uses_netloc URL scheme to get the # expected parsing of the URL on Python versions less than 2.6.5 self.assertRaises( ValueError, get_transport_and_path_from_url, 'prospero://bar/baz') def test_http(self): url = 'https://github.com/jelmer/dulwich' c, path = get_transport_and_path_from_url(url) self.assertTrue(isinstance(c, HttpGitClient)) + self.assertEqual('https://github.com', c.get_url(b'/')) + self.assertEqual('/jelmer/dulwich', path) + + def test_http_port(self): + url = 'https://github.com:9090/jelmer/dulwich' + c, path = get_transport_and_path_from_url(url) + self.assertEqual('https://github.com:9090', c.get_url(b'/')) + self.assertTrue(isinstance(c, HttpGitClient)) self.assertEqual('/jelmer/dulwich', path) def test_file(self): c, path = get_transport_and_path_from_url('file:///home/jelmer/foo') self.assertTrue(isinstance(c, LocalGitClient)) self.assertEqual('/home/jelmer/foo', path) class TestSSHVendor(object): def __init__(self): self.host = None self.command = "" self.username = None self.port = None self.password = None self.key_filename = None def run_command(self, host, command, username=None, port=None, password=None, key_filename=None): self.host = host self.command = command self.username = username self.port = port self.password = password self.key_filename = key_filename class Subprocess: pass setattr(Subprocess, 'read', lambda: None) setattr(Subprocess, 'write', lambda: None) setattr(Subprocess, 'close', lambda: None) setattr(Subprocess, 'can_read', lambda: None) return Subprocess() class SSHGitClientTests(TestCase): def setUp(self): super(SSHGitClientTests, self).setUp() self.server = TestSSHVendor() self.real_vendor = client.get_ssh_vendor client.get_ssh_vendor = lambda: self.server self.client = SSHGitClient('git.samba.org') def tearDown(self): super(SSHGitClientTests, self).tearDown() client.get_ssh_vendor = self.real_vendor def test_get_url(self): path = '/tmp/repo.git' c = SSHGitClient('git.samba.org') url = c.get_url(path) self.assertEqual('ssh://git.samba.org/tmp/repo.git', url) def test_get_url_with_username_and_port(self): path = '/tmp/repo.git' c = SSHGitClient('git.samba.org', port=2222, username='user') url = c.get_url(path) self.assertEqual('ssh://user@git.samba.org:2222/tmp/repo.git', url) def test_default_command(self): self.assertEqual( b'git-upload-pack', self.client._get_cmd_path(b'upload-pack')) def test_alternative_command_path(self): self.client.alternative_paths[b'upload-pack'] = ( b'/usr/lib/git/git-upload-pack') self.assertEqual( b'/usr/lib/git/git-upload-pack', self.client._get_cmd_path(b'upload-pack')) def test_alternative_command_path_spaces(self): self.client.alternative_paths[b'upload-pack'] = ( b'/usr/lib/git/git-upload-pack -ibla') self.assertEqual(b"/usr/lib/git/git-upload-pack -ibla", self.client._get_cmd_path(b'upload-pack')) def test_connect(self): server = self.server client = self.client client.username = b"username" client.port = 1337 client._connect(b"command", b"/path/to/repo") self.assertEqual(b"username", server.username) self.assertEqual(1337, server.port) self.assertEqual("git-command '/path/to/repo'", server.command) client._connect(b"relative-command", b"/~/path/to/repo") self.assertEqual("git-relative-command '~/path/to/repo'", server.command) class ReportStatusParserTests(TestCase): def test_invalid_pack(self): parser = ReportStatusParser() parser.handle_packet(b"unpack error - foo bar") parser.handle_packet(b"ok refs/foo/bar") parser.handle_packet(None) self.assertRaises(SendPackError, parser.check) def test_update_refs_error(self): parser = ReportStatusParser() parser.handle_packet(b"unpack ok") parser.handle_packet(b"ng refs/foo/bar need to pull") parser.handle_packet(None) self.assertRaises(UpdateRefsError, parser.check) def test_ok(self): parser = ReportStatusParser() parser.handle_packet(b"unpack ok") parser.handle_packet(b"ok refs/foo/bar") parser.handle_packet(None) parser.check() class LocalGitClientTests(TestCase): def test_get_url(self): path = "/tmp/repo.git" c = LocalGitClient() url = c.get_url(path) self.assertEqual('file:///tmp/repo.git', url) def test_fetch_into_empty(self): c = LocalGitClient() t = MemoryRepo() s = open_repo('a.git') self.addCleanup(tear_down_repo, s) self.assertEqual(s.get_refs(), c.fetch(s.path, t).refs) def test_fetch_empty(self): c = LocalGitClient() s = open_repo('a.git') self.addCleanup(tear_down_repo, s) out = BytesIO() walker = {} ret = c.fetch_pack( s.path, lambda heads: [], graph_walker=walker, pack_data=out.write) self.assertEqual({ b'HEAD': b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', b'refs/heads/master': b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', b'refs/tags/mytag': b'28237f4dc30d0d462658d6b937b08a0f0b6ef55a', b'refs/tags/mytag-packed': b'b0931cadc54336e78a1d980420e3268903b57a50' }, ret.refs) self.assertEqual( {b'HEAD': b'refs/heads/master'}, ret.symrefs) self.assertEqual( b"PACK\x00\x00\x00\x02\x00\x00\x00\x00\x02\x9d\x08" b"\x82;\xd8\xa8\xea\xb5\x10\xadj\xc7\\\x82<\xfd>\xd3\x1e", out.getvalue()) def test_fetch_pack_none(self): c = LocalGitClient() s = open_repo('a.git') self.addCleanup(tear_down_repo, s) out = BytesIO() walker = MemoryRepo().get_graph_walker() ret = c.fetch_pack( s.path, lambda heads: [b"a90fa2d900a17e99b433217e988c4eb4a2e9a097"], graph_walker=walker, pack_data=out.write) self.assertEqual({b'HEAD': b'refs/heads/master'}, ret.symrefs) self.assertEqual({ b'HEAD': b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', b'refs/heads/master': b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', b'refs/tags/mytag': b'28237f4dc30d0d462658d6b937b08a0f0b6ef55a', b'refs/tags/mytag-packed': b'b0931cadc54336e78a1d980420e3268903b57a50' }, ret.refs) # Hardcoding is not ideal, but we'll fix that some other day.. self.assertTrue(out.getvalue().startswith( b'PACK\x00\x00\x00\x02\x00\x00\x00\x07')) def test_send_pack_without_changes(self): local = open_repo('a.git') self.addCleanup(tear_down_repo, local) target = open_repo('a.git') self.addCleanup(tear_down_repo, target) self.send_and_verify(b"master", local, target) def test_send_pack_with_changes(self): local = open_repo('a.git') self.addCleanup(tear_down_repo, local) target_path = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, target_path) with Repo.init_bare(target_path) as target: self.send_and_verify(b"master", local, target) def test_get_refs(self): local = open_repo('refs.git') self.addCleanup(tear_down_repo, local) client = LocalGitClient() refs = client.get_refs(local.path) self.assertDictEqual(local.refs.as_dict(), refs) def send_and_verify(self, branch, local, target): """Send branch from local to remote repository and verify it worked.""" client = LocalGitClient() ref_name = b"refs/heads/" + branch new_refs = client.send_pack(target.path, lambda _: {ref_name: local.refs[ref_name]}, local.object_store.generate_pack_data) self.assertEqual(local.refs[ref_name], new_refs[ref_name]) obj_local = local.get_object(new_refs[ref_name]) obj_target = target.get_object(new_refs[ref_name]) self.assertEqual(obj_local, obj_target) class HttpGitClientTests(TestCase): @staticmethod def b64encode(s): """Python 2/3 compatible Base64 encoder. Returns string.""" try: return base64.b64encode(s) except TypeError: return base64.b64encode(s.encode('latin1')).decode('ascii') def test_get_url(self): base_url = 'https://github.com/jelmer/dulwich' path = '/jelmer/dulwich' c = HttpGitClient(base_url) url = c.get_url(path) self.assertEqual('https://github.com/jelmer/dulwich', url) def test_get_url_bytes_path(self): base_url = 'https://github.com/jelmer/dulwich' path_bytes = b'/jelmer/dulwich' c = HttpGitClient(base_url) url = c.get_url(path_bytes) self.assertEqual('https://github.com/jelmer/dulwich', url) def test_get_url_with_username_and_passwd(self): base_url = 'https://github.com/jelmer/dulwich' path = '/jelmer/dulwich' c = HttpGitClient(base_url, username='USERNAME', password='PASSWD') url = c.get_url(path) self.assertEqual('https://github.com/jelmer/dulwich', url) def test_init_username_passwd_set(self): url = 'https://github.com/jelmer/dulwich' c = HttpGitClient(url, config=None, username='user', password='passwd') self.assertEqual('user', c._username) self.assertEqual('passwd', c._password) basic_auth = c.pool_manager.headers['authorization'] auth_string = '%s:%s' % ('user', 'passwd') b64_credentials = self.b64encode(auth_string) expected_basic_auth = 'Basic %s' % b64_credentials self.assertEqual(basic_auth, expected_basic_auth) def test_init_no_username_passwd(self): url = 'https://github.com/jelmer/dulwich' c = HttpGitClient(url, config=None) self.assertIs(None, c._username) self.assertIs(None, c._password) self.assertNotIn('authorization', c.pool_manager.headers) def test_from_parsedurl_on_url_with_quoted_credentials(self): original_username = 'john|the|first' quoted_username = urlquote(original_username) original_password = 'Ya#1$2%3' quoted_password = urlquote(original_password) url = 'https://{username}:{password}@github.com/jelmer/dulwich'.format( username=quoted_username, password=quoted_password ) c = HttpGitClient.from_parsedurl(urlparse.urlparse(url)) self.assertEqual(original_username, c._username) self.assertEqual(original_password, c._password) basic_auth = c.pool_manager.headers['authorization'] auth_string = '%s:%s' % (original_username, original_password) b64_credentials = self.b64encode(auth_string) expected_basic_auth = 'Basic %s' % str(b64_credentials) self.assertEqual(basic_auth, expected_basic_auth) class TCPGitClientTests(TestCase): def test_get_url(self): host = 'github.com' path = '/jelmer/dulwich' c = TCPGitClient(host) url = c.get_url(path) self.assertEqual('git://github.com/jelmer/dulwich', url) def test_get_url_with_port(self): host = 'github.com' path = '/jelmer/dulwich' port = 9090 c = TCPGitClient(host, port=port) url = c.get_url(path) self.assertEqual('git://github.com:9090/jelmer/dulwich', url) class DefaultUrllib3ManagerTest(TestCase): def test_no_config(self): manager = default_urllib3_manager(config=None) self.assertEqual(manager.connection_pool_kw['cert_reqs'], 'CERT_REQUIRED') def test_config_no_proxy(self): manager = default_urllib3_manager(config=ConfigDict()) self.assertNotIsInstance(manager, urllib3.ProxyManager) def test_config_ssl(self): config = ConfigDict() config.set(b'http', b'sslVerify', b'true') manager = default_urllib3_manager(config=config) self.assertEqual(manager.connection_pool_kw['cert_reqs'], 'CERT_REQUIRED') def test_config_no_ssl(self): config = ConfigDict() config.set(b'http', b'sslVerify', b'false') manager = default_urllib3_manager(config=config) self.assertEqual(manager.connection_pool_kw['cert_reqs'], 'CERT_NONE') def test_config_proxy(self): config = ConfigDict() config.set(b'http', b'proxy', b'http://localhost:3128/') manager = default_urllib3_manager(config=config) self.assertIsInstance(manager, urllib3.ProxyManager) self.assertTrue(hasattr(manager, 'proxy')) self.assertEqual(manager.proxy.scheme, 'http') self.assertEqual(manager.proxy.host, 'localhost') self.assertEqual(manager.proxy.port, 3128) def test_config_no_verify_ssl(self): manager = default_urllib3_manager(config=None, cert_reqs="CERT_NONE") self.assertEqual(manager.connection_pool_kw['cert_reqs'], 'CERT_NONE') class SubprocessSSHVendorTests(TestCase): def setUp(self): # Monkey Patch client subprocess popen self._orig_popen = dulwich.client.subprocess.Popen dulwich.client.subprocess.Popen = DummyPopen def tearDown(self): dulwich.client.subprocess.Popen = self._orig_popen def test_run_command_dashes(self): vendor = SubprocessSSHVendor() self.assertRaises(StrangeHostname, vendor.run_command, '--weird-host', 'git-clone-url') def test_run_command_password(self): vendor = SubprocessSSHVendor() self.assertRaises(NotImplementedError, vendor.run_command, 'host', 'git-clone-url', password='12345') def test_run_command_password_and_privkey(self): vendor = SubprocessSSHVendor() self.assertRaises(NotImplementedError, vendor.run_command, 'host', 'git-clone-url', password='12345', key_filename='/tmp/id_rsa') def test_run_command_with_port_username_and_privkey(self): expected = ['ssh', '-x', '-p', '2200', '-i', '/tmp/id_rsa', 'user@host', 'git-clone-url'] vendor = SubprocessSSHVendor() command = vendor.run_command( 'host', 'git-clone-url', username='user', port='2200', key_filename='/tmp/id_rsa') args = command.proc.args self.assertListEqual(expected, args[0]) class PLinkSSHVendorTests(TestCase): def setUp(self): # Monkey Patch client subprocess popen self._orig_popen = dulwich.client.subprocess.Popen dulwich.client.subprocess.Popen = DummyPopen def tearDown(self): dulwich.client.subprocess.Popen = self._orig_popen def test_run_command_dashes(self): vendor = PLinkSSHVendor() self.assertRaises(StrangeHostname, vendor.run_command, '--weird-host', 'git-clone-url') def test_run_command_password_and_privkey(self): vendor = PLinkSSHVendor() warnings.simplefilter("always", UserWarning) self.addCleanup(warnings.resetwarnings) warnings_list, restore_warnings = setup_warning_catcher() self.addCleanup(restore_warnings) command = vendor.run_command( 'host', 'git-clone-url', password='12345', key_filename='/tmp/id_rsa') expected_warning = UserWarning( 'Invoking PLink with a password exposes the password in the ' 'process list.') for w in warnings_list: if (type(w) == type(expected_warning) and w.args == expected_warning.args): break else: raise AssertionError( 'Expected warning %r not in %r' % (expected_warning, warnings_list)) args = command.proc.args if sys.platform == 'win32': binary = ['plink.exe', '-ssh'] else: binary = ['plink', '-ssh'] expected = binary + [ '-pw', '12345', '-i', '/tmp/id_rsa', 'host', 'git-clone-url'] self.assertListEqual(expected, args[0]) def test_run_command_password(self): if sys.platform == 'win32': binary = ['plink.exe', '-ssh'] else: binary = ['plink', '-ssh'] expected = binary + ['-pw', '12345', 'host', 'git-clone-url'] vendor = PLinkSSHVendor() warnings.simplefilter("always", UserWarning) self.addCleanup(warnings.resetwarnings) warnings_list, restore_warnings = setup_warning_catcher() self.addCleanup(restore_warnings) command = vendor.run_command('host', 'git-clone-url', password='12345') expected_warning = UserWarning( 'Invoking PLink with a password exposes the password in the ' 'process list.') for w in warnings_list: if (type(w) == type(expected_warning) and w.args == expected_warning.args): break else: raise AssertionError( 'Expected warning %r not in %r' % (expected_warning, warnings_list)) args = command.proc.args self.assertListEqual(expected, args[0]) def test_run_command_with_port_username_and_privkey(self): if sys.platform == 'win32': binary = ['plink.exe', '-ssh'] else: binary = ['plink', '-ssh'] expected = binary + [ '-P', '2200', '-i', '/tmp/id_rsa', 'user@host', 'git-clone-url'] vendor = PLinkSSHVendor() command = vendor.run_command( 'host', 'git-clone-url', username='user', port='2200', key_filename='/tmp/id_rsa') args = command.proc.args self.assertListEqual(expected, args[0]) class RsyncUrlTests(TestCase): def test_simple(self): self.assertEqual( parse_rsync_url('foo:bar/path'), (None, 'foo', 'bar/path')) self.assertEqual( parse_rsync_url('user@foo:bar/path'), ('user', 'foo', 'bar/path')) def test_path(self): self.assertRaises(ValueError, parse_rsync_url, '/path') + + +class CheckWantsTests(TestCase): + + def test_fine(self): + check_wants( + [b'2f3dc7a53fb752a6961d3a56683df46d4d3bf262'], + {b'refs/heads/blah': b'2f3dc7a53fb752a6961d3a56683df46d4d3bf262'}) + + def test_missing(self): + self.assertRaises( + InvalidWants, check_wants, + [b'2f3dc7a53fb752a6961d3a56683df46d4d3bf262'], + {b'refs/heads/blah': b'3f3dc7a53fb752a6961d3a56683df46d4d3bf262'}) + + def test_annotated(self): + self.assertRaises( + InvalidWants, check_wants, + [b'2f3dc7a53fb752a6961d3a56683df46d4d3bf262'], + {b'refs/heads/blah': b'3f3dc7a53fb752a6961d3a56683df46d4d3bf262', + b'refs/heads/blah^{}': + b'2f3dc7a53fb752a6961d3a56683df46d4d3bf262'}) diff --git a/dulwich/tests/test_diff_tree.py b/dulwich/tests/test_diff_tree.py index cc5fbbeb..8498a290 100644 --- a/dulwich/tests/test_diff_tree.py +++ b/dulwich/tests/test_diff_tree.py @@ -1,948 +1,954 @@ # test_diff_tree.py -- Tests for file and tree diff utilities. # Copyright (C) 2010 Google, Inc. # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """Tests for file and tree diff utilities.""" from itertools import permutations from dulwich.diff_tree import ( CHANGE_MODIFY, CHANGE_RENAME, CHANGE_COPY, CHANGE_UNCHANGED, TreeChange, _merge_entries, _merge_entries_py, tree_changes, tree_changes_for_merge, _count_blocks, _count_blocks_py, _similarity_score, _tree_change_key, RenameDetector, _is_tree, _is_tree_py ) from dulwich.index import ( commit_tree, ) from dulwich.object_store import ( MemoryObjectStore, ) from dulwich.objects import ( ShaFile, Blob, TreeEntry, Tree, ) from dulwich.tests import ( TestCase, ) from dulwich.tests.utils import ( F, make_object, functest_builder, ext_functest_builder, ) class DiffTestCase(TestCase): def setUp(self): super(DiffTestCase, self).setUp() self.store = MemoryObjectStore() self.empty_tree = self.commit_tree([]) def commit_tree(self, entries): commit_blobs = [] for entry in entries: if len(entry) == 2: path, obj = entry mode = F else: path, obj, mode = entry if isinstance(obj, Blob): self.store.add_object(obj) sha = obj.id else: sha = obj commit_blobs.append((path, sha, mode)) return self.store[commit_tree(self.store, commit_blobs)] class TreeChangesTest(DiffTestCase): def setUp(self): super(TreeChangesTest, self).setUp() self.detector = RenameDetector(self.store) def assertMergeFails(self, merge_entries, name, mode, sha): t = Tree() t[name] = (mode, sha) self.assertRaises((TypeError, ValueError), merge_entries, '', t, t) def _do_test_merge_entries(self, merge_entries): blob_a1 = make_object(Blob, data=b'a1') blob_a2 = make_object(Blob, data=b'a2') blob_b1 = make_object(Blob, data=b'b1') blob_c2 = make_object(Blob, data=b'c2') tree1 = self.commit_tree([(b'a', blob_a1, 0o100644), (b'b', blob_b1, 0o100755)]) tree2 = self.commit_tree([(b'a', blob_a2, 0o100644), (b'c', blob_c2, 0o100755)]) self.assertEqual([], merge_entries(b'', self.empty_tree, self.empty_tree)) self.assertEqual( [((None, None, None), (b'a', 0o100644, blob_a1.id)), ((None, None, None), (b'b', 0o100755, blob_b1.id)), ], merge_entries(b'', self.empty_tree, tree1)) self.assertEqual( [((None, None, None), (b'x/a', 0o100644, blob_a1.id)), ((None, None, None), (b'x/b', 0o100755, blob_b1.id)), ], merge_entries(b'x', self.empty_tree, tree1)) self.assertEqual( [((b'a', 0o100644, blob_a2.id), (None, None, None)), ((b'c', 0o100755, blob_c2.id), (None, None, None)), ], merge_entries(b'', tree2, self.empty_tree)) self.assertEqual( [((b'a', 0o100644, blob_a1.id), (b'a', 0o100644, blob_a2.id)), ((b'b', 0o100755, blob_b1.id), (None, None, None)), ((None, None, None), (b'c', 0o100755, blob_c2.id)), ], merge_entries(b'', tree1, tree2)) self.assertEqual( [((b'a', 0o100644, blob_a2.id), (b'a', 0o100644, blob_a1.id)), ((None, None, None), (b'b', 0o100755, blob_b1.id)), ((b'c', 0o100755, blob_c2.id), (None, None, None)), ], merge_entries(b'', tree2, tree1)) self.assertMergeFails(merge_entries, 0xdeadbeef, 0o100644, '1' * 40) self.assertMergeFails(merge_entries, b'a', b'deadbeef', '1' * 40) self.assertMergeFails(merge_entries, b'a', 0o100644, 0xdeadbeef) test_merge_entries = functest_builder(_do_test_merge_entries, _merge_entries_py) test_merge_entries_extension = ext_functest_builder(_do_test_merge_entries, _merge_entries) def _do_test_is_tree(self, is_tree): self.assertFalse(is_tree(TreeEntry(None, None, None))) self.assertFalse(is_tree(TreeEntry(b'a', 0o100644, b'a' * 40))) self.assertFalse(is_tree(TreeEntry(b'a', 0o100755, b'a' * 40))) self.assertFalse(is_tree(TreeEntry(b'a', 0o120000, b'a' * 40))) self.assertTrue(is_tree(TreeEntry(b'a', 0o040000, b'a' * 40))) self.assertRaises(TypeError, is_tree, TreeEntry(b'a', b'x', b'a' * 40)) self.assertRaises(AttributeError, is_tree, 1234) test_is_tree = functest_builder(_do_test_is_tree, _is_tree_py) test_is_tree_extension = ext_functest_builder(_do_test_is_tree, _is_tree) def assertChangesEqual(self, expected, tree1, tree2, **kwargs): actual = list(tree_changes(self.store, tree1.id, tree2.id, **kwargs)) self.assertEqual(expected, actual) # For brevity, the following tests use tuples instead of TreeEntry objects. def test_tree_changes_empty(self): self.assertChangesEqual([], self.empty_tree, self.empty_tree) def test_tree_changes_no_changes(self): blob = make_object(Blob, data=b'blob') tree = self.commit_tree([(b'a', blob), (b'b/c', blob)]) self.assertChangesEqual([], self.empty_tree, self.empty_tree) self.assertChangesEqual([], tree, tree) self.assertChangesEqual( [TreeChange(CHANGE_UNCHANGED, (b'a', F, blob.id), (b'a', F, blob.id)), TreeChange(CHANGE_UNCHANGED, (b'b/c', F, blob.id), (b'b/c', F, blob.id))], tree, tree, want_unchanged=True) def test_tree_changes_add_delete(self): blob_a = make_object(Blob, data=b'a') blob_b = make_object(Blob, data=b'b') tree = self.commit_tree([(b'a', blob_a, 0o100644), (b'x/b', blob_b, 0o100755)]) self.assertChangesEqual( [TreeChange.add((b'a', 0o100644, blob_a.id)), TreeChange.add((b'x/b', 0o100755, blob_b.id))], self.empty_tree, tree) self.assertChangesEqual( [TreeChange.delete((b'a', 0o100644, blob_a.id)), TreeChange.delete((b'x/b', 0o100755, blob_b.id))], tree, self.empty_tree) def test_tree_changes_modify_contents(self): blob_a1 = make_object(Blob, data=b'a1') blob_a2 = make_object(Blob, data=b'a2') tree1 = self.commit_tree([(b'a', blob_a1)]) tree2 = self.commit_tree([(b'a', blob_a2)]) self.assertChangesEqual( [TreeChange(CHANGE_MODIFY, (b'a', F, blob_a1.id), (b'a', F, blob_a2.id))], tree1, tree2) def test_tree_changes_modify_mode(self): blob_a = make_object(Blob, data=b'a') tree1 = self.commit_tree([(b'a', blob_a, 0o100644)]) tree2 = self.commit_tree([(b'a', blob_a, 0o100755)]) self.assertChangesEqual( [TreeChange(CHANGE_MODIFY, (b'a', 0o100644, blob_a.id), (b'a', 0o100755, blob_a.id))], tree1, tree2) def test_tree_changes_change_type(self): blob_a1 = make_object(Blob, data=b'a') blob_a2 = make_object(Blob, data=b'/foo/bar') tree1 = self.commit_tree([(b'a', blob_a1, 0o100644)]) tree2 = self.commit_tree([(b'a', blob_a2, 0o120000)]) self.assertChangesEqual( [TreeChange.delete((b'a', 0o100644, blob_a1.id)), TreeChange.add((b'a', 0o120000, blob_a2.id))], tree1, tree2) def test_tree_changes_change_type_same(self): blob_a1 = make_object(Blob, data=b'a') blob_a2 = make_object(Blob, data=b'/foo/bar') tree1 = self.commit_tree([(b'a', blob_a1, 0o100644)]) tree2 = self.commit_tree([(b'a', blob_a2, 0o120000)]) self.assertChangesEqual( [TreeChange(CHANGE_MODIFY, (b'a', 0o100644, blob_a1.id), (b'a', 0o120000, blob_a2.id))], tree1, tree2, change_type_same=True) def test_tree_changes_to_tree(self): blob_a = make_object(Blob, data=b'a') blob_x = make_object(Blob, data=b'x') tree1 = self.commit_tree([(b'a', blob_a)]) tree2 = self.commit_tree([(b'a/x', blob_x)]) self.assertChangesEqual( [TreeChange.delete((b'a', F, blob_a.id)), TreeChange.add((b'a/x', F, blob_x.id))], tree1, tree2) def test_tree_changes_complex(self): blob_a_1 = make_object(Blob, data=b'a1_1') blob_bx1_1 = make_object(Blob, data=b'bx1_1') blob_bx2_1 = make_object(Blob, data=b'bx2_1') blob_by1_1 = make_object(Blob, data=b'by1_1') blob_by2_1 = make_object(Blob, data=b'by2_1') tree1 = self.commit_tree([ (b'a', blob_a_1), (b'b/x/1', blob_bx1_1), (b'b/x/2', blob_bx2_1), (b'b/y/1', blob_by1_1), (b'b/y/2', blob_by2_1), ]) blob_a_2 = make_object(Blob, data=b'a1_2') blob_bx1_2 = blob_bx1_1 blob_by_2 = make_object(Blob, data=b'by_2') blob_c_2 = make_object(Blob, data=b'c_2') tree2 = self.commit_tree([ (b'a', blob_a_2), (b'b/x/1', blob_bx1_2), (b'b/y', blob_by_2), (b'c', blob_c_2), ]) self.assertChangesEqual( [TreeChange(CHANGE_MODIFY, (b'a', F, blob_a_1.id), (b'a', F, blob_a_2.id)), TreeChange.delete((b'b/x/2', F, blob_bx2_1.id)), TreeChange.add((b'b/y', F, blob_by_2.id)), TreeChange.delete((b'b/y/1', F, blob_by1_1.id)), TreeChange.delete((b'b/y/2', F, blob_by2_1.id)), TreeChange.add((b'c', F, blob_c_2.id))], tree1, tree2) def test_tree_changes_name_order(self): blob = make_object(Blob, data=b'a') tree1 = self.commit_tree([(b'a', blob), (b'a.', blob), (b'a..', blob)]) # Tree order is the reverse of this, so if we used tree order, 'a..' # would not be merged. tree2 = self.commit_tree( [(b'a/x', blob), (b'a./x', blob), (b'a..', blob)]) self.assertChangesEqual( [TreeChange.delete((b'a', F, blob.id)), TreeChange.add((b'a/x', F, blob.id)), TreeChange.delete((b'a.', F, blob.id)), TreeChange.add((b'a./x', F, blob.id))], tree1, tree2) def test_tree_changes_prune(self): blob_a1 = make_object(Blob, data=b'a1') blob_a2 = make_object(Blob, data=b'a2') blob_x = make_object(Blob, data=b'x') tree1 = self.commit_tree([(b'a', blob_a1), (b'b/x', blob_x)]) tree2 = self.commit_tree([(b'a', blob_a2), (b'b/x', blob_x)]) # Remove identical items so lookups will fail unless we prune. subtree = self.store[tree1[b'b'][1]] for entry in subtree.items(): del self.store[entry.sha] del self.store[subtree.id] self.assertChangesEqual( [TreeChange(CHANGE_MODIFY, (b'a', F, blob_a1.id), (b'a', F, blob_a2.id))], tree1, tree2) def test_tree_changes_rename_detector(self): blob_a1 = make_object(Blob, data=b'a\nb\nc\nd\n') blob_a2 = make_object(Blob, data=b'a\nb\nc\ne\n') blob_b = make_object(Blob, data=b'b') tree1 = self.commit_tree([(b'a', blob_a1), (b'b', blob_b)]) tree2 = self.commit_tree([(b'c', blob_a2), (b'b', blob_b)]) detector = RenameDetector(self.store) self.assertChangesEqual( [TreeChange.delete((b'a', F, blob_a1.id)), TreeChange.add((b'c', F, blob_a2.id))], tree1, tree2) self.assertChangesEqual( [TreeChange.delete((b'a', F, blob_a1.id)), TreeChange(CHANGE_UNCHANGED, (b'b', F, blob_b.id), (b'b', F, blob_b.id)), TreeChange.add((b'c', F, blob_a2.id))], tree1, tree2, want_unchanged=True) self.assertChangesEqual( [TreeChange(CHANGE_RENAME, (b'a', F, blob_a1.id), (b'c', F, blob_a2.id))], tree1, tree2, rename_detector=detector) self.assertChangesEqual( [TreeChange(CHANGE_RENAME, (b'a', F, blob_a1.id), (b'c', F, blob_a2.id)), TreeChange(CHANGE_UNCHANGED, (b'b', F, blob_b.id), (b'b', F, blob_b.id))], tree1, tree2, rename_detector=detector, want_unchanged=True) def assertChangesForMergeEqual(self, expected, parent_trees, merge_tree, **kwargs): parent_tree_ids = [t.id for t in parent_trees] actual = list(tree_changes_for_merge( self.store, parent_tree_ids, merge_tree.id, **kwargs)) self.assertEqual(expected, actual) parent_tree_ids.reverse() expected = [list(reversed(cs)) for cs in expected] actual = list(tree_changes_for_merge( self.store, parent_tree_ids, merge_tree.id, **kwargs)) self.assertEqual(expected, actual) def test_tree_changes_for_merge_add_no_conflict(self): blob = make_object(Blob, data=b'blob') parent1 = self.commit_tree([]) parent2 = merge = self.commit_tree([(b'a', blob)]) self.assertChangesForMergeEqual([], [parent1, parent2], merge) self.assertChangesForMergeEqual([], [parent2, parent2], merge) def test_tree_changes_for_merge_add_modify_conflict(self): blob1 = make_object(Blob, data=b'1') blob2 = make_object(Blob, data=b'2') parent1 = self.commit_tree([]) parent2 = self.commit_tree([(b'a', blob1)]) merge = self.commit_tree([(b'a', blob2)]) self.assertChangesForMergeEqual( [[TreeChange.add((b'a', F, blob2.id)), TreeChange(CHANGE_MODIFY, (b'a', F, blob1.id), (b'a', F, blob2.id))]], [parent1, parent2], merge) def test_tree_changes_for_merge_modify_modify_conflict(self): blob1 = make_object(Blob, data=b'1') blob2 = make_object(Blob, data=b'2') blob3 = make_object(Blob, data=b'3') parent1 = self.commit_tree([(b'a', blob1)]) parent2 = self.commit_tree([(b'a', blob2)]) merge = self.commit_tree([(b'a', blob3)]) self.assertChangesForMergeEqual( [[TreeChange(CHANGE_MODIFY, (b'a', F, blob1.id), (b'a', F, blob3.id)), TreeChange(CHANGE_MODIFY, (b'a', F, blob2.id), (b'a', F, blob3.id))]], [parent1, parent2], merge) def test_tree_changes_for_merge_modify_no_conflict(self): blob1 = make_object(Blob, data=b'1') blob2 = make_object(Blob, data=b'2') parent1 = self.commit_tree([(b'a', blob1)]) parent2 = merge = self.commit_tree([(b'a', blob2)]) self.assertChangesForMergeEqual([], [parent1, parent2], merge) def test_tree_changes_for_merge_delete_delete_conflict(self): blob1 = make_object(Blob, data=b'1') blob2 = make_object(Blob, data=b'2') parent1 = self.commit_tree([(b'a', blob1)]) parent2 = self.commit_tree([(b'a', blob2)]) merge = self.commit_tree([]) self.assertChangesForMergeEqual( [[TreeChange.delete((b'a', F, blob1.id)), TreeChange.delete((b'a', F, blob2.id))]], [parent1, parent2], merge) def test_tree_changes_for_merge_delete_no_conflict(self): blob = make_object(Blob, data=b'blob') has = self.commit_tree([(b'a', blob)]) doesnt_have = self.commit_tree([]) self.assertChangesForMergeEqual([], [has, has], doesnt_have) self.assertChangesForMergeEqual([], [has, doesnt_have], doesnt_have) def test_tree_changes_for_merge_octopus_no_conflict(self): r = list(range(5)) blobs = [make_object(Blob, data=bytes(i)) for i in r] parents = [self.commit_tree([(b'a', blobs[i])]) for i in r] for i in r: # Take the SHA from each of the parents. self.assertChangesForMergeEqual([], parents, parents[i]) def test_tree_changes_for_merge_octopus_modify_conflict(self): # Because the octopus merge strategy is limited, I doubt it's possible # to create this with the git command line. But the output is well- # defined, so test it anyway. r = list(range(5)) parent_blobs = [make_object(Blob, data=bytes(i)) for i in r] merge_blob = make_object(Blob, data=b'merge') parents = [self.commit_tree([(b'a', parent_blobs[i])]) for i in r] merge = self.commit_tree([(b'a', merge_blob)]) expected = [[TreeChange(CHANGE_MODIFY, (b'a', F, parent_blobs[i].id), (b'a', F, merge_blob.id)) for i in r]] self.assertChangesForMergeEqual(expected, parents, merge) def test_tree_changes_for_merge_octopus_delete(self): blob1 = make_object(Blob, data=b'1') blob2 = make_object(Blob, data=b'3') parent1 = self.commit_tree([(b'a', blob1)]) parent2 = self.commit_tree([(b'a', blob2)]) parent3 = merge = self.commit_tree([]) self.assertChangesForMergeEqual([], [parent1, parent1, parent1], merge) self.assertChangesForMergeEqual([], [parent1, parent1, parent3], merge) self.assertChangesForMergeEqual([], [parent1, parent3, parent3], merge) self.assertChangesForMergeEqual( [[TreeChange.delete((b'a', F, blob1.id)), TreeChange.delete((b'a', F, blob2.id)), None]], [parent1, parent2, parent3], merge) def test_tree_changes_for_merge_add_add_same_conflict(self): blob = make_object(Blob, data=b'a\nb\nc\nd\n') parent1 = self.commit_tree([(b'a', blob)]) parent2 = self.commit_tree([]) merge = self.commit_tree([(b'b', blob)]) add = TreeChange.add((b'b', F, blob.id)) self.assertChangesForMergeEqual( [[add, add]], [parent1, parent2], merge) def test_tree_changes_for_merge_add_exact_rename_conflict(self): blob = make_object(Blob, data=b'a\nb\nc\nd\n') parent1 = self.commit_tree([(b'a', blob)]) parent2 = self.commit_tree([]) merge = self.commit_tree([(b'b', blob)]) self.assertChangesForMergeEqual( [[TreeChange(CHANGE_RENAME, (b'a', F, blob.id), (b'b', F, blob.id)), TreeChange.add((b'b', F, blob.id))]], [parent1, parent2], merge, rename_detector=self.detector) def test_tree_changes_for_merge_add_content_rename_conflict(self): blob1 = make_object(Blob, data=b'a\nb\nc\nd\n') blob2 = make_object(Blob, data=b'a\nb\nc\ne\n') parent1 = self.commit_tree([(b'a', blob1)]) parent2 = self.commit_tree([]) merge = self.commit_tree([(b'b', blob2)]) self.assertChangesForMergeEqual( [[TreeChange(CHANGE_RENAME, (b'a', F, blob1.id), (b'b', F, blob2.id)), TreeChange.add((b'b', F, blob2.id))]], [parent1, parent2], merge, rename_detector=self.detector) def test_tree_changes_for_merge_modify_rename_conflict(self): blob1 = make_object(Blob, data=b'a\nb\nc\nd\n') blob2 = make_object(Blob, data=b'a\nb\nc\ne\n') parent1 = self.commit_tree([(b'a', blob1)]) parent2 = self.commit_tree([(b'b', blob1)]) merge = self.commit_tree([(b'b', blob2)]) self.assertChangesForMergeEqual( [[TreeChange(CHANGE_RENAME, (b'a', F, blob1.id), (b'b', F, blob2.id)), TreeChange(CHANGE_MODIFY, (b'b', F, blob1.id), (b'b', F, blob2.id))]], [parent1, parent2], merge, rename_detector=self.detector) class RenameDetectionTest(DiffTestCase): def _do_test_count_blocks(self, count_blocks): blob = make_object(Blob, data=b'a\nb\na\n') - self.assertEqual({hash(b'a\n'): 4, hash(b'b\n'): 2}, - count_blocks(blob)) + self.assertBlockCountEqual({b'a\n': 4, b'b\n': 2}, count_blocks(blob)) test_count_blocks = functest_builder(_do_test_count_blocks, _count_blocks_py) test_count_blocks_extension = ext_functest_builder(_do_test_count_blocks, _count_blocks) def _do_test_count_blocks_no_newline(self, count_blocks): blob = make_object(Blob, data=b'a\na') - self.assertEqual({hash(b'a\n'): 2, hash(b'a'): 1}, _count_blocks(blob)) + self.assertBlockCountEqual({b'a\n': 2, b'a': 1}, _count_blocks(blob)) test_count_blocks_no_newline = functest_builder( _do_test_count_blocks_no_newline, _count_blocks_py) test_count_blocks_no_newline_extension = ext_functest_builder( _do_test_count_blocks_no_newline, _count_blocks) + def assertBlockCountEqual(self, expected, got): + self.assertEqual( + {(hash(l) & 0xffffffff): c for (l, c) in expected.items()}, + {(h & 0xffffffff): c for (h, c) in got.items()}) + def _do_test_count_blocks_chunks(self, count_blocks): blob = ShaFile.from_raw_chunks(Blob.type_num, [b'a\nb', b'\na\n']) - self.assertEqual({hash(b'a\n'): 4, hash(b'b\n'): 2}, - _count_blocks(blob)) + self.assertBlockCountEqual({b'a\n': 4, b'b\n': 2}, _count_blocks(blob)) test_count_blocks_chunks = functest_builder(_do_test_count_blocks_chunks, _count_blocks_py) test_count_blocks_chunks_extension = ext_functest_builder( _do_test_count_blocks_chunks, _count_blocks) def _do_test_count_blocks_long_lines(self, count_blocks): a = b'a' * 64 data = a + b'xxx\ny\n' + a + b'zzz\n' blob = make_object(Blob, data=data) - self.assertEqual({hash(b'a' * 64): 128, hash(b'xxx\n'): 4, - hash(b'y\n'): 2, hash(b'zzz\n'): 4}, - _count_blocks(blob)) + self.assertBlockCountEqual( + {b'a' * 64: 128, + b'xxx\n': 4, + b'y\n': 2, + b'zzz\n': 4}, + _count_blocks(blob)) test_count_blocks_long_lines = functest_builder( _do_test_count_blocks_long_lines, _count_blocks_py) test_count_blocks_long_lines_extension = ext_functest_builder( _do_test_count_blocks_long_lines, _count_blocks) def assertSimilar(self, expected_score, blob1, blob2): self.assertEqual(expected_score, _similarity_score(blob1, blob2)) self.assertEqual(expected_score, _similarity_score(blob2, blob1)) def test_similarity_score(self): blob0 = make_object(Blob, data=b'') blob1 = make_object(Blob, data=b'ab\ncd\ncd\n') blob2 = make_object(Blob, data=b'ab\n') blob3 = make_object(Blob, data=b'cd\n') blob4 = make_object(Blob, data=b'cd\ncd\n') self.assertSimilar(100, blob0, blob0) self.assertSimilar(0, blob0, blob1) self.assertSimilar(33, blob1, blob2) self.assertSimilar(33, blob1, blob3) self.assertSimilar(66, blob1, blob4) self.assertSimilar(0, blob2, blob3) self.assertSimilar(50, blob3, blob4) def test_similarity_score_cache(self): blob1 = make_object(Blob, data=b'ab\ncd\n') blob2 = make_object(Blob, data=b'ab\n') block_cache = {} self.assertEqual( 50, _similarity_score(blob1, blob2, block_cache=block_cache)) self.assertEqual(set([blob1.id, blob2.id]), set(block_cache)) def fail_chunks(): self.fail('Unexpected call to as_raw_chunks()') blob1.as_raw_chunks = blob2.as_raw_chunks = fail_chunks blob1.raw_length = lambda: 6 blob2.raw_length = lambda: 3 self.assertEqual( 50, _similarity_score(blob1, blob2, block_cache=block_cache)) def test_tree_entry_sort(self): sha = 'abcd' * 10 expected_entries = [ TreeChange.add(TreeEntry(b'aaa', F, sha)), TreeChange(CHANGE_COPY, TreeEntry(b'bbb', F, sha), TreeEntry(b'aab', F, sha)), TreeChange(CHANGE_MODIFY, TreeEntry(b'bbb', F, sha), TreeEntry(b'bbb', F, b'dabc' * 10)), TreeChange(CHANGE_RENAME, TreeEntry(b'bbc', F, sha), TreeEntry(b'ddd', F, sha)), TreeChange.delete(TreeEntry(b'ccc', F, sha)), ] for perm in permutations(expected_entries): self.assertEqual(expected_entries, sorted(perm, key=_tree_change_key)) def detect_renames(self, tree1, tree2, want_unchanged=False, **kwargs): detector = RenameDetector(self.store, **kwargs) return detector.changes_with_renames(tree1.id, tree2.id, want_unchanged=want_unchanged) def test_no_renames(self): blob1 = make_object(Blob, data=b'a\nb\nc\nd\n') blob2 = make_object(Blob, data=b'a\nb\ne\nf\n') blob3 = make_object(Blob, data=b'a\nb\ng\nh\n') tree1 = self.commit_tree([(b'a', blob1), (b'b', blob2)]) tree2 = self.commit_tree([(b'a', blob1), (b'b', blob3)]) self.assertEqual( [TreeChange(CHANGE_MODIFY, (b'b', F, blob2.id), (b'b', F, blob3.id))], self.detect_renames(tree1, tree2)) def test_exact_rename_one_to_one(self): blob1 = make_object(Blob, data=b'1') blob2 = make_object(Blob, data=b'2') tree1 = self.commit_tree([(b'a', blob1), (b'b', blob2)]) tree2 = self.commit_tree([(b'c', blob1), (b'd', blob2)]) self.assertEqual( [TreeChange(CHANGE_RENAME, (b'a', F, blob1.id), (b'c', F, blob1.id)), TreeChange(CHANGE_RENAME, (b'b', F, blob2.id), (b'd', F, blob2.id))], self.detect_renames(tree1, tree2)) def test_exact_rename_split_different_type(self): blob = make_object(Blob, data=b'/foo') tree1 = self.commit_tree([(b'a', blob, 0o100644)]) tree2 = self.commit_tree([(b'a', blob, 0o120000)]) self.assertEqual( [TreeChange.add((b'a', 0o120000, blob.id)), TreeChange.delete((b'a', 0o100644, blob.id))], self.detect_renames(tree1, tree2)) def test_exact_rename_and_different_type(self): blob1 = make_object(Blob, data=b'1') blob2 = make_object(Blob, data=b'2') tree1 = self.commit_tree([(b'a', blob1)]) tree2 = self.commit_tree([(b'a', blob2, 0o120000), (b'b', blob1)]) self.assertEqual( [TreeChange.add((b'a', 0o120000, blob2.id)), TreeChange(CHANGE_RENAME, (b'a', F, blob1.id), (b'b', F, blob1.id))], self.detect_renames(tree1, tree2)) def test_exact_rename_one_to_many(self): blob = make_object(Blob, data=b'1') tree1 = self.commit_tree([(b'a', blob)]) tree2 = self.commit_tree([(b'b', blob), (b'c', blob)]) self.assertEqual( [TreeChange(CHANGE_RENAME, (b'a', F, blob.id), (b'b', F, blob.id)), TreeChange(CHANGE_COPY, (b'a', F, blob.id), (b'c', F, blob.id))], self.detect_renames(tree1, tree2)) def test_exact_rename_many_to_one(self): blob = make_object(Blob, data=b'1') tree1 = self.commit_tree([(b'a', blob), (b'b', blob)]) tree2 = self.commit_tree([(b'c', blob)]) self.assertEqual( [TreeChange(CHANGE_RENAME, (b'a', F, blob.id), (b'c', F, blob.id)), TreeChange.delete((b'b', F, blob.id))], self.detect_renames(tree1, tree2)) def test_exact_rename_many_to_many(self): blob = make_object(Blob, data=b'1') tree1 = self.commit_tree([(b'a', blob), (b'b', blob)]) tree2 = self.commit_tree([(b'c', blob), (b'd', blob), (b'e', blob)]) self.assertEqual( [TreeChange(CHANGE_RENAME, (b'a', F, blob.id), (b'c', F, blob.id)), TreeChange(CHANGE_COPY, (b'a', F, blob.id), (b'e', F, blob.id)), TreeChange(CHANGE_RENAME, (b'b', F, blob.id), (b'd', F, blob.id))], self.detect_renames(tree1, tree2)) def test_exact_copy_modify(self): blob1 = make_object(Blob, data=b'a\nb\nc\nd\n') blob2 = make_object(Blob, data=b'a\nb\nc\ne\n') tree1 = self.commit_tree([(b'a', blob1)]) tree2 = self.commit_tree([(b'a', blob2), (b'b', blob1)]) self.assertEqual( [TreeChange(CHANGE_MODIFY, (b'a', F, blob1.id), (b'a', F, blob2.id)), TreeChange(CHANGE_COPY, (b'a', F, blob1.id), (b'b', F, blob1.id))], self.detect_renames(tree1, tree2)) def test_exact_copy_change_mode(self): blob = make_object(Blob, data=b'a\nb\nc\nd\n') tree1 = self.commit_tree([(b'a', blob)]) tree2 = self.commit_tree([(b'a', blob, 0o100755), (b'b', blob)]) self.assertEqual( [TreeChange(CHANGE_MODIFY, (b'a', F, blob.id), (b'a', 0o100755, blob.id)), TreeChange(CHANGE_COPY, (b'a', F, blob.id), (b'b', F, blob.id))], self.detect_renames(tree1, tree2)) def test_rename_threshold(self): blob1 = make_object(Blob, data=b'a\nb\nc\n') blob2 = make_object(Blob, data=b'a\nb\nd\n') tree1 = self.commit_tree([(b'a', blob1)]) tree2 = self.commit_tree([(b'b', blob2)]) self.assertEqual( [TreeChange(CHANGE_RENAME, (b'a', F, blob1.id), (b'b', F, blob2.id))], self.detect_renames(tree1, tree2, rename_threshold=50)) self.assertEqual( [TreeChange.delete((b'a', F, blob1.id)), TreeChange.add((b'b', F, blob2.id))], self.detect_renames(tree1, tree2, rename_threshold=75)) def test_content_rename_max_files(self): blob1 = make_object(Blob, data=b'a\nb\nc\nd') blob4 = make_object(Blob, data=b'a\nb\nc\ne\n') blob2 = make_object(Blob, data=b'e\nf\ng\nh\n') blob3 = make_object(Blob, data=b'e\nf\ng\ni\n') tree1 = self.commit_tree([(b'a', blob1), (b'b', blob2)]) tree2 = self.commit_tree([(b'c', blob3), (b'd', blob4)]) self.assertEqual( [TreeChange(CHANGE_RENAME, (b'a', F, blob1.id), (b'd', F, blob4.id)), TreeChange(CHANGE_RENAME, (b'b', F, blob2.id), (b'c', F, blob3.id))], self.detect_renames(tree1, tree2)) self.assertEqual( [TreeChange.delete((b'a', F, blob1.id)), TreeChange.delete((b'b', F, blob2.id)), TreeChange.add((b'c', F, blob3.id)), TreeChange.add((b'd', F, blob4.id))], self.detect_renames(tree1, tree2, max_files=1)) def test_content_rename_one_to_one(self): b11 = make_object(Blob, data=b'a\nb\nc\nd\n') b12 = make_object(Blob, data=b'a\nb\nc\ne\n') - b21 = make_object(Blob, data=b'e\nf\ng\n\h') - b22 = make_object(Blob, data=b'e\nf\ng\n\i') + b21 = make_object(Blob, data=b'e\nf\ng\n\nh') + b22 = make_object(Blob, data=b'e\nf\ng\n\ni') tree1 = self.commit_tree([(b'a', b11), (b'b', b21)]) tree2 = self.commit_tree([(b'c', b12), (b'd', b22)]) self.assertEqual( [TreeChange(CHANGE_RENAME, (b'a', F, b11.id), (b'c', F, b12.id)), TreeChange(CHANGE_RENAME, (b'b', F, b21.id), (b'd', F, b22.id))], self.detect_renames(tree1, tree2)) def test_content_rename_one_to_one_ordering(self): blob1 = make_object(Blob, data=b'a\nb\nc\nd\ne\nf\n') blob2 = make_object(Blob, data=b'a\nb\nc\nd\ng\nh\n') # 6/10 match to blob1, 8/10 match to blob2 blob3 = make_object(Blob, data=b'a\nb\nc\nd\ng\ni\n') tree1 = self.commit_tree([(b'a', blob1), (b'b', blob2)]) tree2 = self.commit_tree([(b'c', blob3)]) self.assertEqual( [TreeChange.delete((b'a', F, blob1.id)), TreeChange(CHANGE_RENAME, (b'b', F, blob2.id), (b'c', F, blob3.id))], self.detect_renames(tree1, tree2)) tree3 = self.commit_tree([(b'a', blob2), (b'b', blob1)]) tree4 = self.commit_tree([(b'c', blob3)]) self.assertEqual( [TreeChange(CHANGE_RENAME, (b'a', F, blob2.id), (b'c', F, blob3.id)), TreeChange.delete((b'b', F, blob1.id))], self.detect_renames(tree3, tree4)) def test_content_rename_one_to_many(self): blob1 = make_object(Blob, data=b'aa\nb\nc\nd\ne\n') blob2 = make_object(Blob, data=b'ab\nb\nc\nd\ne\n') # 8/11 match blob3 = make_object(Blob, data=b'aa\nb\nc\nd\nf\n') # 9/11 match tree1 = self.commit_tree([(b'a', blob1)]) tree2 = self.commit_tree([(b'b', blob2), (b'c', blob3)]) self.assertEqual( [TreeChange(CHANGE_COPY, (b'a', F, blob1.id), (b'b', F, blob2.id)), TreeChange(CHANGE_RENAME, (b'a', F, blob1.id), (b'c', F, blob3.id))], self.detect_renames(tree1, tree2)) def test_content_rename_many_to_one(self): blob1 = make_object(Blob, data=b'a\nb\nc\nd\n') blob2 = make_object(Blob, data=b'a\nb\nc\ne\n') blob3 = make_object(Blob, data=b'a\nb\nc\nf\n') tree1 = self.commit_tree([(b'a', blob1), (b'b', blob2)]) tree2 = self.commit_tree([(b'c', blob3)]) self.assertEqual( [TreeChange(CHANGE_RENAME, (b'a', F, blob1.id), (b'c', F, blob3.id)), TreeChange.delete((b'b', F, blob2.id))], self.detect_renames(tree1, tree2)) def test_content_rename_many_to_many(self): blob1 = make_object(Blob, data=b'a\nb\nc\nd\n') blob2 = make_object(Blob, data=b'a\nb\nc\ne\n') blob3 = make_object(Blob, data=b'a\nb\nc\nf\n') blob4 = make_object(Blob, data=b'a\nb\nc\ng\n') tree1 = self.commit_tree([(b'a', blob1), (b'b', blob2)]) tree2 = self.commit_tree([(b'c', blob3), (b'd', blob4)]) # TODO(dborowitz): Distribute renames rather than greedily choosing # copies. self.assertEqual( [TreeChange(CHANGE_RENAME, (b'a', F, blob1.id), (b'c', F, blob3.id)), TreeChange(CHANGE_COPY, (b'a', F, blob1.id), (b'd', F, blob4.id)), TreeChange.delete((b'b', F, blob2.id))], self.detect_renames(tree1, tree2)) def test_content_rename_with_more_deletions(self): blob1 = make_object(Blob, data=b'') tree1 = self.commit_tree([(b'a', blob1), (b'b', blob1), (b'c', blob1), (b'd', blob1)]) tree2 = self.commit_tree([(b'e', blob1), (b'f', blob1), (b'g', blob1)]) self.maxDiff = None self.assertEqual( [TreeChange(CHANGE_RENAME, (b'a', F, blob1.id), (b'e', F, blob1.id)), TreeChange(CHANGE_RENAME, (b'b', F, blob1.id), (b'f', F, blob1.id)), TreeChange(CHANGE_RENAME, (b'c', F, blob1.id), (b'g', F, blob1.id)), TreeChange.delete((b'd', F, blob1.id))], self.detect_renames(tree1, tree2)) def test_content_rename_gitlink(self): blob1 = make_object(Blob, data=b'blob1') blob2 = make_object(Blob, data=b'blob2') link1 = b'1' * 40 link2 = b'2' * 40 tree1 = self.commit_tree([(b'a', blob1), (b'b', link1, 0o160000)]) tree2 = self.commit_tree([(b'c', blob2), (b'd', link2, 0o160000)]) self.assertEqual( [TreeChange.delete((b'a', 0o100644, blob1.id)), TreeChange.delete((b'b', 0o160000, link1)), TreeChange.add((b'c', 0o100644, blob2.id)), TreeChange.add((b'd', 0o160000, link2))], self.detect_renames(tree1, tree2)) def test_exact_rename_swap(self): blob1 = make_object(Blob, data=b'1') blob2 = make_object(Blob, data=b'2') tree1 = self.commit_tree([(b'a', blob1), (b'b', blob2)]) tree2 = self.commit_tree([(b'a', blob2), (b'b', blob1)]) self.assertEqual( [TreeChange(CHANGE_MODIFY, (b'a', F, blob1.id), (b'a', F, blob2.id)), TreeChange(CHANGE_MODIFY, (b'b', F, blob2.id), (b'b', F, blob1.id))], self.detect_renames(tree1, tree2)) self.assertEqual( [TreeChange(CHANGE_RENAME, (b'a', F, blob1.id), (b'b', F, blob1.id)), TreeChange(CHANGE_RENAME, (b'b', F, blob2.id), (b'a', F, blob2.id))], self.detect_renames(tree1, tree2, rewrite_threshold=50)) def test_content_rename_swap(self): blob1 = make_object(Blob, data=b'a\nb\nc\nd\n') blob2 = make_object(Blob, data=b'e\nf\ng\nh\n') blob3 = make_object(Blob, data=b'a\nb\nc\ne\n') blob4 = make_object(Blob, data=b'e\nf\ng\ni\n') tree1 = self.commit_tree([(b'a', blob1), (b'b', blob2)]) tree2 = self.commit_tree([(b'a', blob4), (b'b', blob3)]) self.assertEqual( [TreeChange(CHANGE_RENAME, (b'a', F, blob1.id), (b'b', F, blob3.id)), TreeChange(CHANGE_RENAME, (b'b', F, blob2.id), (b'a', F, blob4.id))], self.detect_renames(tree1, tree2, rewrite_threshold=60)) def test_rewrite_threshold(self): blob1 = make_object(Blob, data=b'a\nb\nc\nd\n') blob2 = make_object(Blob, data=b'a\nb\nc\ne\n') blob3 = make_object(Blob, data=b'a\nb\nf\ng\n') tree1 = self.commit_tree([(b'a', blob1)]) tree2 = self.commit_tree([(b'a', blob3), (b'b', blob2)]) no_renames = [ TreeChange(CHANGE_MODIFY, (b'a', F, blob1.id), (b'a', F, blob3.id)), TreeChange(CHANGE_COPY, (b'a', F, blob1.id), (b'b', F, blob2.id))] self.assertEqual( no_renames, self.detect_renames(tree1, tree2)) self.assertEqual( no_renames, self.detect_renames( tree1, tree2, rewrite_threshold=40)) self.assertEqual( [TreeChange.add((b'a', F, blob3.id)), TreeChange(CHANGE_RENAME, (b'a', F, blob1.id), (b'b', F, blob2.id))], self.detect_renames(tree1, tree2, rewrite_threshold=80)) def test_find_copies_harder_exact(self): blob = make_object(Blob, data=b'blob') tree1 = self.commit_tree([(b'a', blob)]) tree2 = self.commit_tree([(b'a', blob), (b'b', blob)]) self.assertEqual([TreeChange.add((b'b', F, blob.id))], self.detect_renames(tree1, tree2)) self.assertEqual( [TreeChange(CHANGE_COPY, (b'a', F, blob.id), (b'b', F, blob.id))], self.detect_renames(tree1, tree2, find_copies_harder=True)) def test_find_copies_harder_content(self): blob1 = make_object(Blob, data=b'a\nb\nc\nd\n') blob2 = make_object(Blob, data=b'a\nb\nc\ne\n') tree1 = self.commit_tree([(b'a', blob1)]) tree2 = self.commit_tree([(b'a', blob1), (b'b', blob2)]) self.assertEqual([TreeChange.add((b'b', F, blob2.id))], self.detect_renames(tree1, tree2)) self.assertEqual( [TreeChange(CHANGE_COPY, (b'a', F, blob1.id), (b'b', F, blob2.id))], self.detect_renames(tree1, tree2, find_copies_harder=True)) def test_find_copies_harder_with_rewrites(self): blob_a1 = make_object(Blob, data=b'a\nb\nc\nd\n') blob_a2 = make_object(Blob, data=b'f\ng\nh\ni\n') blob_b2 = make_object(Blob, data=b'a\nb\nc\ne\n') tree1 = self.commit_tree([(b'a', blob_a1)]) tree2 = self.commit_tree([(b'a', blob_a2), (b'b', blob_b2)]) self.assertEqual( [TreeChange(CHANGE_MODIFY, (b'a', F, blob_a1.id), (b'a', F, blob_a2.id)), TreeChange(CHANGE_COPY, (b'a', F, blob_a1.id), (b'b', F, blob_b2.id))], self.detect_renames(tree1, tree2, find_copies_harder=True)) self.assertEqual( [TreeChange.add((b'a', F, blob_a2.id)), TreeChange(CHANGE_RENAME, (b'a', F, blob_a1.id), (b'b', F, blob_b2.id))], self.detect_renames(tree1, tree2, rewrite_threshold=50, find_copies_harder=True)) def test_reuse_detector(self): blob = make_object(Blob, data=b'blob') tree1 = self.commit_tree([(b'a', blob)]) tree2 = self.commit_tree([(b'b', blob)]) detector = RenameDetector(self.store) changes = [TreeChange(CHANGE_RENAME, (b'a', F, blob.id), (b'b', F, blob.id))] self.assertEqual(changes, detector.changes_with_renames(tree1.id, tree2.id)) self.assertEqual(changes, detector.changes_with_renames(tree1.id, tree2.id)) def test_want_unchanged(self): blob_a1 = make_object(Blob, data=b'a\nb\nc\nd\n') blob_b = make_object(Blob, data=b'b') blob_c2 = make_object(Blob, data=b'a\nb\nc\ne\n') tree1 = self.commit_tree([(b'a', blob_a1), (b'b', blob_b)]) tree2 = self.commit_tree([(b'c', blob_c2), (b'b', blob_b)]) self.assertEqual( [TreeChange(CHANGE_RENAME, (b'a', F, blob_a1.id), (b'c', F, blob_c2.id))], self.detect_renames(tree1, tree2)) self.assertEqual( [TreeChange(CHANGE_RENAME, (b'a', F, blob_a1.id), (b'c', F, blob_c2.id)), TreeChange(CHANGE_UNCHANGED, (b'b', F, blob_b.id), (b'b', F, blob_b.id))], self.detect_renames(tree1, tree2, want_unchanged=True)) diff --git a/dulwich/tests/test_ignore.py b/dulwich/tests/test_ignore.py index 339e8ad1..ade0e8a1 100644 --- a/dulwich/tests/test_ignore.py +++ b/dulwich/tests/test_ignore.py @@ -1,260 +1,260 @@ # test_ignore.py -- Tests for ignore files. # Copyright (C) 2017 Jelmer Vernooij # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """Tests for ignore files.""" from io import BytesIO import os import re import shutil import tempfile from dulwich.tests import TestCase from dulwich.ignore import ( IgnoreFilter, IgnoreFilterManager, IgnoreFilterStack, Pattern, match_pattern, read_ignore_patterns, translate, ) from dulwich.repo import Repo POSITIVE_MATCH_TESTS = [ (b"foo.c", b"*.c"), (b".c", b"*.c"), (b"foo/foo.c", b"*.c"), (b"foo/foo.c", b"foo.c"), (b"foo.c", b"/*.c"), (b"foo.c", b"/foo.c"), (b"foo.c", b"foo.c"), (b"foo.c", b"foo.[ch]"), (b"foo/bar/bla.c", b"foo/**"), (b"foo/bar/bla/blie.c", b"foo/**/blie.c"), (b"foo/bar/bla.c", b"**/bla.c"), (b"bla.c", b"**/bla.c"), (b"foo/bar", b"foo/**/bar"), (b"foo/bla/bar", b"foo/**/bar"), (b"foo/bar/", b"bar/"), (b"foo/bar/", b"bar"), (b"foo/bar/something", b"foo/bar/*"), ] NEGATIVE_MATCH_TESTS = [ (b"foo.c", b"foo.[dh]"), (b"foo/foo.c", b"/foo.c"), (b"foo/foo.c", b"/*.c"), (b"foo/bar/", b"/bar/"), (b"foo/bar/", b"foo/bar/*"), ] TRANSLATE_TESTS = [ (b"*.c", b'(?ms)(.*/)?[^/]*\\.c/?\\Z'), (b"foo.c", b'(?ms)(.*/)?foo\\.c/?\\Z'), (b"/*.c", b'(?ms)[^/]*\\.c/?\\Z'), (b"/foo.c", b'(?ms)foo\\.c/?\\Z'), (b"foo.c", b'(?ms)(.*/)?foo\\.c/?\\Z'), (b"foo.[ch]", b'(?ms)(.*/)?foo\\.[ch]/?\\Z'), (b"bar/", b'(?ms)(.*/)?bar\\/\\Z'), (b"foo/**", b'(?ms)foo(/.*)?/?\\Z'), (b"foo/**/blie.c", b'(?ms)foo(/.*)?\\/blie\\.c/?\\Z'), (b"**/bla.c", b'(?ms)(.*/)?bla\\.c/?\\Z'), (b"foo/**/bar", b'(?ms)foo(/.*)?\\/bar/?\\Z'), (b"foo/bar/*", b'(?ms)foo\\/bar\\/[^/]+/?\\Z'), ] class TranslateTests(TestCase): def test_translate(self): for (pattern, regex) in TRANSLATE_TESTS: if re.escape(b'/') == b'/': # Slash is no longer escaped in Python3.7, so undo the escaping # in the expected return value.. regex = regex.replace(b'\\/', b'/') self.assertEqual( regex, translate(pattern), "orig pattern: %r, regex: %r, expected: %r" % (pattern, translate(pattern), regex)) class ReadIgnorePatterns(TestCase): def test_read_file(self): f = BytesIO(b""" # a comment # and an empty line: -\#not a comment +\\#not a comment !negative with trailing whitespace -with escaped trailing whitespace\ +with escaped trailing whitespace\\ """) # noqa: W291 self.assertEqual(list(read_ignore_patterns(f)), [ b'\\#not a comment', b'!negative', b'with trailing whitespace', b'with escaped trailing whitespace ' ]) class MatchPatternTests(TestCase): def test_matches(self): for (path, pattern) in POSITIVE_MATCH_TESTS: self.assertTrue( match_pattern(path, pattern), "path: %r, pattern: %r" % (path, pattern)) def test_no_matches(self): for (path, pattern) in NEGATIVE_MATCH_TESTS: self.assertFalse( match_pattern(path, pattern), "path: %r, pattern: %r" % (path, pattern)) class IgnoreFilterTests(TestCase): def test_included(self): filter = IgnoreFilter([b'a.c', b'b.c']) self.assertTrue(filter.is_ignored(b'a.c')) self.assertIs(None, filter.is_ignored(b'c.c')) self.assertEqual( [Pattern(b'a.c')], list(filter.find_matching(b'a.c'))) self.assertEqual( [], list(filter.find_matching(b'c.c'))) def test_included_ignorecase(self): filter = IgnoreFilter([b'a.c', b'b.c'], ignorecase=False) self.assertTrue(filter.is_ignored(b'a.c')) self.assertFalse(filter.is_ignored(b'A.c')) filter = IgnoreFilter([b'a.c', b'b.c'], ignorecase=True) self.assertTrue(filter.is_ignored(b'a.c')) self.assertTrue(filter.is_ignored(b'A.c')) self.assertTrue(filter.is_ignored(b'A.C')) def test_excluded(self): filter = IgnoreFilter([b'a.c', b'b.c', b'!c.c']) self.assertFalse(filter.is_ignored(b'c.c')) self.assertIs(None, filter.is_ignored(b'd.c')) self.assertEqual( [Pattern(b'!c.c')], list(filter.find_matching(b'c.c'))) self.assertEqual([], list(filter.find_matching(b'd.c'))) def test_include_exclude_include(self): filter = IgnoreFilter([b'a.c', b'!a.c', b'a.c']) self.assertTrue(filter.is_ignored(b'a.c')) self.assertEqual( [Pattern(b'a.c'), Pattern(b'!a.c'), Pattern(b'a.c')], list(filter.find_matching(b'a.c'))) def test_manpage(self): # A specific example from the gitignore manpage filter = IgnoreFilter([ b'/*', b'!/foo', b'/foo/*', b'!/foo/bar']) self.assertTrue(filter.is_ignored(b'a.c')) self.assertTrue(filter.is_ignored(b'foo/blie')) self.assertFalse(filter.is_ignored(b'foo')) self.assertFalse(filter.is_ignored(b'foo/bar')) self.assertFalse(filter.is_ignored(b'foo/bar/')) self.assertFalse(filter.is_ignored(b'foo/bar/bloe')) class IgnoreFilterStackTests(TestCase): def test_stack_first(self): filter1 = IgnoreFilter([b'[a].c', b'[b].c', b'![d].c']) filter2 = IgnoreFilter([b'[a].c', b'![b],c', b'[c].c', b'[d].c']) stack = IgnoreFilterStack([filter1, filter2]) self.assertIs(True, stack.is_ignored(b'a.c')) self.assertIs(True, stack.is_ignored(b'b.c')) self.assertIs(True, stack.is_ignored(b'c.c')) self.assertIs(False, stack.is_ignored(b'd.c')) self.assertIs(None, stack.is_ignored(b'e.c')) class IgnoreFilterManagerTests(TestCase): def test_load_ignore(self): tmp_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, tmp_dir) repo = Repo.init(tmp_dir) with open(os.path.join(repo.path, '.gitignore'), 'wb') as f: f.write(b'/foo/bar\n') f.write(b'/dir2\n') f.write(b'/dir3/\n') os.mkdir(os.path.join(repo.path, 'dir')) with open(os.path.join(repo.path, 'dir', '.gitignore'), 'wb') as f: f.write(b'/blie\n') with open(os.path.join(repo.path, 'dir', 'blie'), 'wb') as f: f.write(b'IGNORED') p = os.path.join(repo.controldir(), 'info', 'exclude') with open(p, 'wb') as f: f.write(b'/excluded\n') m = IgnoreFilterManager.from_repo(repo) self.assertTrue(m.is_ignored('dir/blie')) self.assertIs(None, m.is_ignored(os.path.join('dir', 'bloe'))) self.assertIs(None, m.is_ignored('dir')) self.assertTrue(m.is_ignored(os.path.join('foo', 'bar'))) self.assertTrue(m.is_ignored(os.path.join('excluded'))) self.assertTrue(m.is_ignored(os.path.join( 'dir2', 'fileinignoreddir'))) self.assertFalse(m.is_ignored('dir3')) self.assertTrue(m.is_ignored('dir3/')) self.assertTrue(m.is_ignored('dir3/bla')) def test_load_ignore_ignorecase(self): tmp_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, tmp_dir) repo = Repo.init(tmp_dir) config = repo.get_config() config.set(b'core', b'ignorecase', True) config.write_to_path() with open(os.path.join(repo.path, '.gitignore'), 'wb') as f: f.write(b'/foo/bar\n') f.write(b'/dir\n') m = IgnoreFilterManager.from_repo(repo) self.assertTrue(m.is_ignored(os.path.join('dir', 'blie'))) self.assertTrue(m.is_ignored(os.path.join('DIR', 'blie'))) def test_ignored_contents(self): tmp_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, tmp_dir) repo = Repo.init(tmp_dir) with open(os.path.join(repo.path, '.gitignore'), 'wb') as f: f.write(b'a/*\n') f.write(b'!a/*.txt\n') m = IgnoreFilterManager.from_repo(repo) os.mkdir(os.path.join(repo.path, 'a')) self.assertIs(None, m.is_ignored('a')) self.assertIs(None, m.is_ignored('a/')) self.assertFalse(m.is_ignored('a/b.txt')) self.assertTrue(m.is_ignored('a/c.dat')) diff --git a/dulwich/tests/test_line_ending.py b/dulwich/tests/test_line_ending.py new file mode 100644 index 00000000..5e519a94 --- /dev/null +++ b/dulwich/tests/test_line_ending.py @@ -0,0 +1,94 @@ +# -*- coding: utf-8 -*- +# test_line_ending.py -- Tests for the line ending functions +# encoding: utf-8 +# Copyright (C) 2018-2019 Boris Feld +# +# Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU +# General Public License as public by the Free Software Foundation; version 2.0 +# or (at your option) any later version. You can redistribute it and/or +# modify it under the terms of either of these two licenses. +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# +# You should have received a copy of the licenses; if not, see +# for a copy of the GNU General Public License +# and for a copy of the Apache +# License, Version 2.0. +# + +"""Tests for the line ending conversion.""" + +from dulwich.line_ending import ( + convert_crlf_to_lf, + convert_lf_to_crlf, + get_checkin_filter_autocrlf, + get_checkout_filter_autocrlf, +) +from dulwich.tests import TestCase + + +class LineEndingConversion(TestCase): + """Test the line ending conversion functions in various cases""" + + def test_convert_crlf_to_lf_no_op(self): + self.assertEqual(convert_crlf_to_lf(b"foobar"), b"foobar") + + def test_convert_crlf_to_lf(self): + self.assertEqual( + convert_crlf_to_lf(b"line1\r\nline2"), b"line1\nline2" + ) + + def test_convert_crlf_to_lf_mixed(self): + self.assertEqual( + convert_crlf_to_lf(b"line1\r\n\nline2"), b"line1\n\nline2" + ) + + def test_convert_lf_to_crlf_no_op(self): + self.assertEqual(convert_lf_to_crlf(b"foobar"), b"foobar") + + def test_convert_lf_to_crlf(self): + self.assertEqual( + convert_lf_to_crlf(b"line1\nline2"), b"line1\r\nline2" + ) + + def test_convert_lf_to_crlf_mixed(self): + self.assertEqual( + convert_lf_to_crlf(b"line1\r\n\nline2"), b"line1\r\n\r\nline2" + ) + + +class GetLineEndingAutocrlfFilters(TestCase): + + def test_get_checkin_filter_autocrlf_default(self): + checkin_filter = get_checkin_filter_autocrlf(b"false") + + self.assertEqual(checkin_filter, None) + + def test_get_checkin_filter_autocrlf_true(self): + checkin_filter = get_checkin_filter_autocrlf(b"true") + + self.assertEqual(checkin_filter, convert_crlf_to_lf) + + def test_get_checkin_filter_autocrlf_input(self): + checkin_filter = get_checkin_filter_autocrlf(b"input") + + self.assertEqual(checkin_filter, convert_crlf_to_lf) + + def test_get_checkout_filter_autocrlf_default(self): + checkout_filter = get_checkout_filter_autocrlf(b"false") + + self.assertEqual(checkout_filter, None) + + def test_get_checkout_filter_autocrlf_true(self): + checkout_filter = get_checkout_filter_autocrlf(b"true") + + self.assertEqual(checkout_filter, convert_lf_to_crlf) + + def test_get_checkout_filter_autocrlf_input(self): + checkout_filter = get_checkout_filter_autocrlf(b"input") + + self.assertEqual(checkout_filter, None) diff --git a/dulwich/tests/test_object_store.py b/dulwich/tests/test_object_store.py index ab868b7f..8667b71e 100644 --- a/dulwich/tests/test_object_store.py +++ b/dulwich/tests/test_object_store.py @@ -1,647 +1,655 @@ # test_object_store.py -- tests for object_store.py # Copyright (C) 2008 Jelmer Vernooij # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """Tests for the object store interface.""" from contextlib import closing from io import BytesIO import os import shutil import stat import tempfile from dulwich.index import ( commit_tree, ) from dulwich.errors import ( NotTreeError, EmptyFileException, ) from dulwich.objects import ( sha_to_hex, Blob, Tree, TreeEntry, ) from dulwich.object_store import ( DiskObjectStore, MemoryObjectStore, OverlayObjectStore, ObjectStoreGraphWalker, commit_tree_changes, + read_packs_file, tree_lookup_path, ) from dulwich.pack import ( REF_DELTA, write_pack_objects, ) from dulwich.tests import ( TestCase, ) from dulwich.tests.utils import ( make_object, make_tag, build_pack, ) testobject = make_object(Blob, data=b"yummy data") class ObjectStoreTests(object): def test_determine_wants_all(self): self.assertEqual( [b"1" * 40], self.store.determine_wants_all({b"refs/heads/foo": b"1" * 40})) def test_determine_wants_all_zero(self): self.assertEqual( [], self.store.determine_wants_all({b"refs/heads/foo": b"0" * 40})) def test_iter(self): self.assertEqual([], list(self.store)) def test_get_nonexistant(self): self.assertRaises(KeyError, lambda: self.store[b"a" * 40]) def test_contains_nonexistant(self): self.assertFalse((b"a" * 40) in self.store) def test_add_objects_empty(self): self.store.add_objects([]) def test_add_commit(self): # TODO: Argh, no way to construct Git commit objects without # access to a serialized form. self.store.add_objects([]) def test_store_resilience(self): """Test if updating an existing stored object doesn't erase the object from the store. """ test_object = make_object(Blob, data=b'data') self.store.add_object(test_object) test_object_id = test_object.id test_object.data = test_object.data + b'update' stored_test_object = self.store[test_object_id] self.assertNotEqual(test_object.id, stored_test_object.id) self.assertEqual(stored_test_object.id, test_object_id) def test_add_object(self): self.store.add_object(testobject) self.assertEqual(set([testobject.id]), set(self.store)) self.assertTrue(testobject.id in self.store) r = self.store[testobject.id] self.assertEqual(r, testobject) def test_add_objects(self): data = [(testobject, "mypath")] self.store.add_objects(data) self.assertEqual(set([testobject.id]), set(self.store)) self.assertTrue(testobject.id in self.store) r = self.store[testobject.id] self.assertEqual(r, testobject) def test_tree_changes(self): blob_a1 = make_object(Blob, data=b'a1') blob_a2 = make_object(Blob, data=b'a2') blob_b = make_object(Blob, data=b'b') for blob in [blob_a1, blob_a2, blob_b]: self.store.add_object(blob) blobs_1 = [(b'a', blob_a1.id, 0o100644), (b'b', blob_b.id, 0o100644)] tree1_id = commit_tree(self.store, blobs_1) blobs_2 = [(b'a', blob_a2.id, 0o100644), (b'b', blob_b.id, 0o100644)] tree2_id = commit_tree(self.store, blobs_2) change_a = ((b'a', b'a'), (0o100644, 0o100644), (blob_a1.id, blob_a2.id)) self.assertEqual([change_a], list(self.store.tree_changes(tree1_id, tree2_id))) self.assertEqual( [change_a, ((b'b', b'b'), (0o100644, 0o100644), (blob_b.id, blob_b.id))], list(self.store.tree_changes(tree1_id, tree2_id, want_unchanged=True))) def test_iter_tree_contents(self): blob_a = make_object(Blob, data=b'a') blob_b = make_object(Blob, data=b'b') blob_c = make_object(Blob, data=b'c') for blob in [blob_a, blob_b, blob_c]: self.store.add_object(blob) blobs = [ (b'a', blob_a.id, 0o100644), (b'ad/b', blob_b.id, 0o100644), (b'ad/bd/c', blob_c.id, 0o100755), (b'ad/c', blob_c.id, 0o100644), (b'c', blob_c.id, 0o100644), ] tree_id = commit_tree(self.store, blobs) self.assertEqual([TreeEntry(p, m, h) for (p, h, m) in blobs], list(self.store.iter_tree_contents(tree_id))) def test_iter_tree_contents_include_trees(self): blob_a = make_object(Blob, data=b'a') blob_b = make_object(Blob, data=b'b') blob_c = make_object(Blob, data=b'c') for blob in [blob_a, blob_b, blob_c]: self.store.add_object(blob) blobs = [ (b'a', blob_a.id, 0o100644), (b'ad/b', blob_b.id, 0o100644), (b'ad/bd/c', blob_c.id, 0o100755), ] tree_id = commit_tree(self.store, blobs) tree = self.store[tree_id] tree_ad = self.store[tree[b'ad'][1]] tree_bd = self.store[tree_ad[b'bd'][1]] expected = [ TreeEntry(b'', 0o040000, tree_id), TreeEntry(b'a', 0o100644, blob_a.id), TreeEntry(b'ad', 0o040000, tree_ad.id), TreeEntry(b'ad/b', 0o100644, blob_b.id), TreeEntry(b'ad/bd', 0o040000, tree_bd.id), TreeEntry(b'ad/bd/c', 0o100755, blob_c.id), ] actual = self.store.iter_tree_contents(tree_id, include_trees=True) self.assertEqual(expected, list(actual)) def make_tag(self, name, obj): tag = make_tag(obj, name=name) self.store.add_object(tag) return tag def test_peel_sha(self): self.store.add_object(testobject) tag1 = self.make_tag(b'1', testobject) tag2 = self.make_tag(b'2', testobject) tag3 = self.make_tag(b'3', testobject) for obj in [testobject, tag1, tag2, tag3]: self.assertEqual(testobject, self.store.peel_sha(obj.id)) def test_get_raw(self): self.store.add_object(testobject) self.assertEqual((Blob.type_num, b'yummy data'), self.store.get_raw(testobject.id)) def test_close(self): # For now, just check that close doesn't barf. self.store.add_object(testobject) self.store.close() class OverlayObjectStoreTests(ObjectStoreTests, TestCase): def setUp(self): TestCase.setUp(self) self.bases = [MemoryObjectStore(), MemoryObjectStore()] self.store = OverlayObjectStore(self.bases, self.bases[0]) class MemoryObjectStoreTests(ObjectStoreTests, TestCase): def setUp(self): TestCase.setUp(self) self.store = MemoryObjectStore() def test_add_pack(self): o = MemoryObjectStore() f, commit, abort = o.add_pack() try: b = make_object(Blob, data=b"more yummy data") write_pack_objects(f, [(b, None)]) except BaseException: abort() raise else: commit() def test_add_pack_emtpy(self): o = MemoryObjectStore() f, commit, abort = o.add_pack() commit() def test_add_thin_pack(self): o = MemoryObjectStore() blob = make_object(Blob, data=b'yummy data') o.add_object(blob) f = BytesIO() entries = build_pack(f, [ (REF_DELTA, (blob.id, b'more yummy data')), ], store=o) o.add_thin_pack(f.read, None) packed_blob_sha = sha_to_hex(entries[0][3]) self.assertEqual((Blob.type_num, b'more yummy data'), o.get_raw(packed_blob_sha)) def test_add_thin_pack_empty(self): o = MemoryObjectStore() f = BytesIO() entries = build_pack(f, [], store=o) self.assertEqual([], entries) o.add_thin_pack(f.read, None) class PackBasedObjectStoreTests(ObjectStoreTests): def tearDown(self): for pack in self.store.packs: pack.close() def test_empty_packs(self): self.assertEqual([], list(self.store.packs)) def test_pack_loose_objects(self): b1 = make_object(Blob, data=b"yummy data") self.store.add_object(b1) b2 = make_object(Blob, data=b"more yummy data") self.store.add_object(b2) b3 = make_object(Blob, data=b"even more yummy data") b4 = make_object(Blob, data=b"and more yummy data") self.store.add_objects([(b3, None), (b4, None)]) self.assertEqual({b1.id, b2.id, b3.id, b4.id}, set(self.store)) self.assertEqual(1, len(self.store.packs)) self.assertEqual(2, self.store.pack_loose_objects()) self.assertNotEqual([], list(self.store.packs)) self.assertEqual(0, self.store.pack_loose_objects()) def test_repack(self): b1 = make_object(Blob, data=b"yummy data") self.store.add_object(b1) b2 = make_object(Blob, data=b"more yummy data") self.store.add_object(b2) b3 = make_object(Blob, data=b"even more yummy data") b4 = make_object(Blob, data=b"and more yummy data") self.store.add_objects([(b3, None), (b4, None)]) b5 = make_object(Blob, data=b"and more data") b6 = make_object(Blob, data=b"and some more data") self.store.add_objects([(b5, None), (b6, None)]) self.assertEqual({b1.id, b2.id, b3.id, b4.id, b5.id, b6.id}, set(self.store)) self.assertEqual(2, len(self.store.packs)) self.assertEqual(6, self.store.repack()) self.assertEqual(1, len(self.store.packs)) self.assertEqual(0, self.store.pack_loose_objects()) def test_repack_existing(self): b1 = make_object(Blob, data=b"yummy data") self.store.add_object(b1) b2 = make_object(Blob, data=b"more yummy data") self.store.add_object(b2) self.store.add_objects([(b1, None), (b2, None)]) self.store.add_objects([(b2, None)]) self.assertEqual({b1.id, b2.id}, set(self.store)) self.assertEqual(2, len(self.store.packs)) self.assertEqual(2, self.store.repack()) self.assertEqual(1, len(self.store.packs)) self.assertEqual(0, self.store.pack_loose_objects()) self.assertEqual({b1.id, b2.id}, set(self.store)) self.assertEqual(1, len(self.store.packs)) self.assertEqual(2, self.store.repack()) self.assertEqual(1, len(self.store.packs)) self.assertEqual(0, self.store.pack_loose_objects()) class DiskObjectStoreTests(PackBasedObjectStoreTests, TestCase): def setUp(self): TestCase.setUp(self) self.store_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, self.store_dir) self.store = DiskObjectStore.init(self.store_dir) def tearDown(self): TestCase.tearDown(self) PackBasedObjectStoreTests.tearDown(self) def test_alternates(self): alternate_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, alternate_dir) alternate_store = DiskObjectStore(alternate_dir) b2 = make_object(Blob, data=b"yummy data") alternate_store.add_object(b2) store = DiskObjectStore(self.store_dir) self.assertRaises(KeyError, store.__getitem__, b2.id) store.add_alternate_path(alternate_dir) self.assertIn(b2.id, store) self.assertEqual(b2, store[b2.id]) def test_corrupted_object_raise_exception(self): """Corrupted sha1 disk file should raise specific exception""" self.store.add_object(testobject) self.assertEqual((Blob.type_num, b'yummy data'), self.store.get_raw(testobject.id)) self.assertTrue(self.store.contains_loose(testobject.id)) self.assertIsNotNone(self.store._get_loose_object(testobject.id)) path = self.store._get_shafile_path(testobject.id) with open(path, 'wb') as f: # corrupt the file f.write(b'') expected_error_msg = 'Corrupted empty file detected' try: self.store.contains_loose(testobject.id) except EmptyFileException as e: self.assertEqual(str(e), expected_error_msg) try: self.store._get_loose_object(testobject.id) except EmptyFileException as e: self.assertEqual(str(e), expected_error_msg) # this does not change iteration on loose objects though self.assertEqual([testobject.id], list(self.store._iter_loose_objects())) def test_add_alternate_path(self): store = DiskObjectStore(self.store_dir) self.assertEqual([], list(store._read_alternate_paths())) store.add_alternate_path("/foo/path") self.assertEqual(["/foo/path"], list(store._read_alternate_paths())) store.add_alternate_path("/bar/path") self.assertEqual( ["/foo/path", "/bar/path"], list(store._read_alternate_paths())) def test_rel_alternative_path(self): alternate_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, alternate_dir) alternate_store = DiskObjectStore(alternate_dir) b2 = make_object(Blob, data=b"yummy data") alternate_store.add_object(b2) store = DiskObjectStore(self.store_dir) self.assertRaises(KeyError, store.__getitem__, b2.id) store.add_alternate_path( os.path.relpath(alternate_dir, self.store_dir)) self.assertEqual(list(alternate_store), list(store.alternates[0])) self.assertIn(b2.id, store) self.assertEqual(b2, store[b2.id]) def test_pack_dir(self): o = DiskObjectStore(self.store_dir) self.assertEqual(os.path.join(self.store_dir, "pack"), o.pack_dir) def test_add_pack(self): o = DiskObjectStore(self.store_dir) f, commit, abort = o.add_pack() try: b = make_object(Blob, data=b"more yummy data") write_pack_objects(f, [(b, None)]) except BaseException: abort() raise else: commit() def test_add_thin_pack(self): o = DiskObjectStore(self.store_dir) try: blob = make_object(Blob, data=b'yummy data') o.add_object(blob) f = BytesIO() entries = build_pack(f, [ (REF_DELTA, (blob.id, b'more yummy data')), ], store=o) with o.add_thin_pack(f.read, None) as pack: packed_blob_sha = sha_to_hex(entries[0][3]) pack.check_length_and_checksum() self.assertEqual( sorted([blob.id, packed_blob_sha]), list(pack)) self.assertTrue(o.contains_packed(packed_blob_sha)) self.assertTrue(o.contains_packed(blob.id)) self.assertEqual((Blob.type_num, b'more yummy data'), o.get_raw(packed_blob_sha)) finally: o.close() def test_add_thin_pack_empty(self): with closing(DiskObjectStore(self.store_dir)) as o: f = BytesIO() entries = build_pack(f, [], store=o) self.assertEqual([], entries) o.add_thin_pack(f.read, None) class TreeLookupPathTests(TestCase): def setUp(self): TestCase.setUp(self) self.store = MemoryObjectStore() blob_a = make_object(Blob, data=b'a') blob_b = make_object(Blob, data=b'b') blob_c = make_object(Blob, data=b'c') for blob in [blob_a, blob_b, blob_c]: self.store.add_object(blob) blobs = [ (b'a', blob_a.id, 0o100644), (b'ad/b', blob_b.id, 0o100644), (b'ad/bd/c', blob_c.id, 0o100755), (b'ad/c', blob_c.id, 0o100644), (b'c', blob_c.id, 0o100644), ] self.tree_id = commit_tree(self.store, blobs) def get_object(self, sha): return self.store[sha] def test_lookup_blob(self): o_id = tree_lookup_path(self.get_object, self.tree_id, b'a')[1] self.assertTrue(isinstance(self.store[o_id], Blob)) def test_lookup_tree(self): o_id = tree_lookup_path(self.get_object, self.tree_id, b'ad')[1] self.assertTrue(isinstance(self.store[o_id], Tree)) o_id = tree_lookup_path(self.get_object, self.tree_id, b'ad/bd')[1] self.assertTrue(isinstance(self.store[o_id], Tree)) o_id = tree_lookup_path(self.get_object, self.tree_id, b'ad/bd/')[1] self.assertTrue(isinstance(self.store[o_id], Tree)) def test_lookup_nonexistent(self): self.assertRaises( KeyError, tree_lookup_path, self.get_object, self.tree_id, b'j') def test_lookup_not_tree(self): self.assertRaises( NotTreeError, tree_lookup_path, self.get_object, self.tree_id, b'ad/b/j') class ObjectStoreGraphWalkerTests(TestCase): def get_walker(self, heads, parent_map): new_parent_map = dict( [(k * 40, [(p * 40) for p in ps]) for (k, ps) in parent_map.items()]) return ObjectStoreGraphWalker([x * 40 for x in heads], new_parent_map.__getitem__) def test_ack_invalid_value(self): gw = self.get_walker([], {}) self.assertRaises(ValueError, gw.ack, "tooshort") def test_empty(self): gw = self.get_walker([], {}) self.assertIs(None, next(gw)) gw.ack(b"a" * 40) self.assertIs(None, next(gw)) def test_descends(self): gw = self.get_walker([b"a"], {b"a": [b"b"], b"b": []}) self.assertEqual(b"a" * 40, next(gw)) self.assertEqual(b"b" * 40, next(gw)) def test_present(self): gw = self.get_walker([b"a"], {b"a": [b"b"], b"b": []}) gw.ack(b"a" * 40) self.assertIs(None, next(gw)) def test_parent_present(self): gw = self.get_walker([b"a"], {b"a": [b"b"], b"b": []}) self.assertEqual(b"a" * 40, next(gw)) gw.ack(b"a" * 40) self.assertIs(None, next(gw)) def test_child_ack_later(self): gw = self.get_walker([b"a"], {b"a": [b"b"], b"b": [b"c"], b"c": []}) self.assertEqual(b"a" * 40, next(gw)) self.assertEqual(b"b" * 40, next(gw)) gw.ack(b"a" * 40) self.assertIs(None, next(gw)) def test_only_once(self): # a b # | | # c d # \ / # e gw = self.get_walker([b"a", b"b"], { b"a": [b"c"], b"b": [b"d"], b"c": [b"e"], b"d": [b"e"], b"e": [], }) walk = [] acked = False walk.append(next(gw)) walk.append(next(gw)) # A branch (a, c) or (b, d) may be done after 2 steps or 3 depending on # the order walked: 3-step walks include (a, b, c) and (b, a, d), etc. if walk == [b"a" * 40, b"c" * 40] or walk == [b"b" * 40, b"d" * 40]: gw.ack(walk[0]) acked = True walk.append(next(gw)) if not acked and walk[2] == b"c" * 40: gw.ack(b"a" * 40) elif not acked and walk[2] == b"d" * 40: gw.ack(b"b" * 40) walk.append(next(gw)) self.assertIs(None, next(gw)) self.assertEqual([b"a" * 40, b"b" * 40, b"c" * 40, b"d" * 40], sorted(walk)) self.assertLess(walk.index(b"a" * 40), walk.index(b"c" * 40)) self.assertLess(walk.index(b"b" * 40), walk.index(b"d" * 40)) class CommitTreeChangesTests(TestCase): def setUp(self): super(CommitTreeChangesTests, self).setUp() self.store = MemoryObjectStore() self.blob_a = make_object(Blob, data=b'a') self.blob_b = make_object(Blob, data=b'b') self.blob_c = make_object(Blob, data=b'c') for blob in [self.blob_a, self.blob_b, self.blob_c]: self.store.add_object(blob) blobs = [ (b'a', self.blob_a.id, 0o100644), (b'ad/b', self.blob_b.id, 0o100644), (b'ad/bd/c', self.blob_c.id, 0o100755), (b'ad/c', self.blob_c.id, 0o100644), (b'c', self.blob_c.id, 0o100644), ] self.tree_id = commit_tree(self.store, blobs) def test_no_changes(self): self.assertEqual( self.store[self.tree_id], commit_tree_changes(self.store, self.store[self.tree_id], [])) def test_add_blob(self): blob_d = make_object(Blob, data=b'd') new_tree = commit_tree_changes( self.store, self.store[self.tree_id], [ (b'd', 0o100644, blob_d.id)]) self.assertEqual( new_tree[b'd'], (33188, b'c59d9b6344f1af00e504ba698129f07a34bbed8d')) def test_add_blob_in_dir(self): blob_d = make_object(Blob, data=b'd') new_tree = commit_tree_changes( self.store, self.store[self.tree_id], [ (b'e/f/d', 0o100644, blob_d.id)]) self.assertEqual( new_tree.items(), [ TreeEntry(path=b'a', mode=stat.S_IFREG | 0o100644, sha=self.blob_a.id), TreeEntry(path=b'ad', mode=stat.S_IFDIR, sha=b'0e2ce2cd7725ff4817791be31ccd6e627e801f4a'), TreeEntry(path=b'c', mode=stat.S_IFREG | 0o100644, sha=self.blob_c.id), TreeEntry(path=b'e', mode=stat.S_IFDIR, sha=b'6ab344e288724ac2fb38704728b8896e367ed108') ]) e_tree = self.store[new_tree[b'e'][1]] self.assertEqual( e_tree.items(), [ TreeEntry(path=b'f', mode=stat.S_IFDIR, sha=b'24d2c94d8af232b15a0978c006bf61ef4479a0a5') ]) f_tree = self.store[e_tree[b'f'][1]] self.assertEqual( f_tree.items(), [ TreeEntry(path=b'd', mode=stat.S_IFREG | 0o100644, sha=blob_d.id) ]) def test_delete_blob(self): new_tree = commit_tree_changes( self.store, self.store[self.tree_id], [ (b'ad/bd/c', None, None)]) self.assertEqual(set(new_tree), {b'a', b'ad', b'c'}) ad_tree = self.store[new_tree[b'ad'][1]] self.assertEqual(set(ad_tree), {b'b', b'c'}) + + +class TestReadPacksFile(TestCase): + + def test_read_packs(self): + self.assertEqual(["pack-1.pack"], list(read_packs_file(BytesIO(b"""P pack-1.pack +""")))) diff --git a/dulwich/tests/test_objects.py b/dulwich/tests/test_objects.py index 05708270..c6556fac 100644 --- a/dulwich/tests/test_objects.py +++ b/dulwich/tests/test_objects.py @@ -1,1289 +1,1313 @@ # test_objects.py -- tests for objects.py # Copyright (C) 2007 James Westby # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """Tests for git base objects.""" # TODO: Round-trip parse-serialize-parse and serialize-parse-serialize tests. from io import BytesIO import datetime from itertools import ( permutations, ) import os import stat import warnings from contextlib import contextmanager from dulwich.errors import ( ObjectFormatException, ) from dulwich.objects import ( Blob, Tree, Commit, ShaFile, Tag, TreeEntry, format_timezone, hex_to_sha, sha_to_hex, hex_to_filename, check_hexsha, check_identity, object_class, parse_timezone, pretty_format_tree_entry, parse_tree, _parse_tree_py, sorted_tree_items, _sorted_tree_items_py, MAX_TIME ) from dulwich.tests import ( TestCase, ) from dulwich.tests.utils import ( make_commit, make_object, functest_builder, ext_functest_builder, ) a_sha = b'6f670c0fb53f9463760b7295fbb814e965fb20c8' b_sha = b'2969be3e8ee1c0222396a5611407e4769f14e54b' c_sha = b'954a536f7819d40e6f637f849ee187dd10066349' tree_sha = b'70c190eb48fa8bbb50ddc692a17b44cb781af7f6' tag_sha = b'71033db03a03c6a36721efcf1968dd8f8e0cf023' class TestHexToSha(TestCase): def test_simple(self): self.assertEqual(b'\xab\xcd' * 10, hex_to_sha(b'abcd' * 10)) def test_reverse(self): self.assertEqual(b'abcd' * 10, sha_to_hex(b'\xab\xcd' * 10)) class BlobReadTests(TestCase): """Test decompression of blobs""" def get_sha_file(self, cls, base, sha): dir = os.path.join(os.path.dirname(__file__), 'data', base) return cls.from_path(hex_to_filename(dir, sha)) def get_blob(self, sha): """Return the blob named sha from the test data dir""" return self.get_sha_file(Blob, 'blobs', sha) def get_tree(self, sha): return self.get_sha_file(Tree, 'trees', sha) def get_tag(self, sha): return self.get_sha_file(Tag, 'tags', sha) def commit(self, sha): return self.get_sha_file(Commit, 'commits', sha) def test_decompress_simple_blob(self): b = self.get_blob(a_sha) self.assertEqual(b.data, b'test 1\n') self.assertEqual(b.sha().hexdigest().encode('ascii'), a_sha) def test_hash(self): b = self.get_blob(a_sha) self.assertEqual(hash(b.id), hash(b)) def test_parse_empty_blob_object(self): sha = b'e69de29bb2d1d6434b8b29ae775ad8c2e48c5391' b = self.get_blob(sha) self.assertEqual(b.data, b'') self.assertEqual(b.id, sha) self.assertEqual(b.sha().hexdigest().encode('ascii'), sha) def test_create_blob_from_string(self): string = b'test 2\n' b = Blob.from_string(string) self.assertEqual(b.data, string) self.assertEqual(b.sha().hexdigest().encode('ascii'), b_sha) def test_legacy_from_file(self): b1 = Blob.from_string(b'foo') b_raw = b1.as_legacy_object() b2 = b1.from_file(BytesIO(b_raw)) self.assertEqual(b1, b2) def test_chunks(self): string = b'test 5\n' b = Blob.from_string(string) self.assertEqual([string], b.chunked) def test_splitlines(self): for case in [ [], [b'foo\nbar\n'], [b'bl\na', b'blie'], [b'bl\na', b'blie', b'bloe\n'], [b'', b'bl\na', b'blie', b'bloe\n'], [b'', b'', b'', b'bla\n'], [b'', b'', b'', b'bla\n', b''], [b'bl', b'', b'a\naaa'], [b'a\naaa', b'a'], ]: b = Blob() b.chunked = case self.assertEqual(b.data.splitlines(True), b.splitlines()) def test_set_chunks(self): b = Blob() b.chunked = [b'te', b'st', b' 5\n'] self.assertEqual(b'test 5\n', b.data) b.chunked = [b'te', b'st', b' 6\n'] self.assertEqual(b'test 6\n', b.as_raw_string()) self.assertEqual(b'test 6\n', bytes(b)) def test_parse_legacy_blob(self): string = b'test 3\n' b = self.get_blob(c_sha) self.assertEqual(b.data, string) self.assertEqual(b.sha().hexdigest().encode('ascii'), c_sha) def test_eq(self): blob1 = self.get_blob(a_sha) blob2 = self.get_blob(a_sha) self.assertEqual(blob1, blob2) def test_read_tree_from_file(self): t = self.get_tree(tree_sha) self.assertEqual(t.items()[0], (b'a', 33188, a_sha)) self.assertEqual(t.items()[1], (b'b', 33188, b_sha)) def test_read_tree_from_file_parse_count(self): old_deserialize = Tree._deserialize def reset_deserialize(): Tree._deserialize = old_deserialize self.addCleanup(reset_deserialize) self.deserialize_count = 0 def counting_deserialize(*args, **kwargs): self.deserialize_count += 1 return old_deserialize(*args, **kwargs) Tree._deserialize = counting_deserialize t = self.get_tree(tree_sha) self.assertEqual(t.items()[0], (b'a', 33188, a_sha)) self.assertEqual(t.items()[1], (b'b', 33188, b_sha)) self.assertEqual(self.deserialize_count, 1) def test_read_tag_from_file(self): t = self.get_tag(tag_sha) self.assertEqual(t.object, (Commit, b'51b668fd5bf7061b7d6fa525f88803e6cfadaa51')) self.assertEqual(t.name, b'signed') self.assertEqual(t.tagger, b'Ali Sabil ') self.assertEqual(t.tag_time, 1231203091) self.assertEqual( t.message, b'This is a signed tag\n' + ) + self.assertEqual( + t.signature, b'-----BEGIN PGP SIGNATURE-----\n' b'Version: GnuPG v1.4.9 (GNU/Linux)\n' b'\n' b'iEYEABECAAYFAkliqx8ACgkQqSMmLy9u/' b'kcx5ACfakZ9NnPl02tOyYP6pkBoEkU1\n' b'5EcAn0UFgokaSvS371Ym/4W9iJj6vh3h\n' b'=ql7y\n' b'-----END PGP SIGNATURE-----\n') def test_read_commit_from_file(self): sha = b'60dacdc733de308bb77bb76ce0fb0f9b44c9769e' c = self.commit(sha) self.assertEqual(c.tree, tree_sha) self.assertEqual(c.parents, [b'0d89f20333fbb1d2f3a94da77f4981373d8f4310']) self.assertEqual(c.author, b'James Westby ') self.assertEqual(c.committer, b'James Westby ') self.assertEqual(c.commit_time, 1174759230) self.assertEqual(c.commit_timezone, 0) self.assertEqual(c.author_timezone, 0) self.assertEqual(c.message, b'Test commit\n') def test_read_commit_no_parents(self): sha = b'0d89f20333fbb1d2f3a94da77f4981373d8f4310' c = self.commit(sha) self.assertEqual(c.tree, b'90182552c4a85a45ec2a835cadc3451bebdfe870') self.assertEqual(c.parents, []) self.assertEqual(c.author, b'James Westby ') self.assertEqual(c.committer, b'James Westby ') self.assertEqual(c.commit_time, 1174758034) self.assertEqual(c.commit_timezone, 0) self.assertEqual(c.author_timezone, 0) self.assertEqual(c.message, b'Test commit\n') def test_read_commit_two_parents(self): sha = b'5dac377bdded4c9aeb8dff595f0faeebcc8498cc' c = self.commit(sha) self.assertEqual(c.tree, b'd80c186a03f423a81b39df39dc87fd269736ca86') self.assertEqual(c.parents, [b'ab64bbdcc51b170d21588e5c5d391ee5c0c96dfd', b'4cffe90e0a41ad3f5190079d7c8f036bde29cbe6']) self.assertEqual(c.author, b'James Westby ') self.assertEqual(c.committer, b'James Westby ') self.assertEqual(c.commit_time, 1174773719) self.assertEqual(c.commit_timezone, 0) self.assertEqual(c.author_timezone, 0) self.assertEqual(c.message, b'Merge ../b\n') def test_stub_sha(self): sha = b'5' * 40 c = make_commit(id=sha, message=b'foo') self.assertTrue(isinstance(c, Commit)) self.assertEqual(sha, c.id) self.assertNotEqual(sha, c.sha()) class ShaFileCheckTests(TestCase): def assertCheckFails(self, cls, data): obj = cls() def do_check(): obj.set_raw_string(data) obj.check() self.assertRaises(ObjectFormatException, do_check) def assertCheckSucceeds(self, cls, data): obj = cls() obj.set_raw_string(data) self.assertEqual(None, obj.check()) small_buffer_zlib_object = ( b'\x48\x89\x15\xcc\x31\x0e\xc2\x30\x0c\x40\x51\xe6' b'\x9c\xc2\x3b\xaa\x64\x37\xc4\xc1\x12\x42\x5c\xc5' b'\x49\xac\x52\xd4\x92\xaa\x78\xe1\xf6\x94\xed\xeb' b'\x0d\xdf\x75\x02\xa2\x7c\xea\xe5\x65\xd5\x81\x8b' b'\x9a\x61\xba\xa0\xa9\x08\x36\xc9\x4c\x1a\xad\x88' b'\x16\xba\x46\xc4\xa8\x99\x6a\x64\xe1\xe0\xdf\xcd' b'\xa0\xf6\x75\x9d\x3d\xf8\xf1\xd0\x77\xdb\xfb\xdc' b'\x86\xa3\x87\xf1\x2f\x93\xed\x00\xb7\xc7\xd2\xab' b'\x2e\xcf\xfe\xf1\x3b\x50\xa4\x91\x53\x12\x24\x38' b'\x23\x21\x86\xf0\x03\x2f\x91\x24\x52' ) class ShaFileTests(TestCase): def test_deflated_smaller_window_buffer(self): # zlib on some systems uses smaller buffers, # resulting in a different header. # See https://github.com/libgit2/libgit2/pull/464 sf = ShaFile.from_file(BytesIO(small_buffer_zlib_object)) self.assertEqual(sf.type_name, b'tag') self.assertEqual(sf.tagger, b' <@localhost>') class CommitSerializationTests(TestCase): def make_commit(self, **kwargs): attrs = {'tree': b'd80c186a03f423a81b39df39dc87fd269736ca86', 'parents': [b'ab64bbdcc51b170d21588e5c5d391ee5c0c96dfd', b'4cffe90e0a41ad3f5190079d7c8f036bde29cbe6'], 'author': b'James Westby ', 'committer': b'James Westby ', 'commit_time': 1174773719, 'author_time': 1174773719, 'commit_timezone': 0, 'author_timezone': 0, 'message': b'Merge ../b\n'} attrs.update(kwargs) return make_commit(**attrs) def test_encoding(self): c = self.make_commit(encoding=b'iso8859-1') self.assertTrue(b'encoding iso8859-1\n' in c.as_raw_string()) def test_short_timestamp(self): c = self.make_commit(commit_time=30) c1 = Commit() c1.set_raw_string(c.as_raw_string()) self.assertEqual(30, c1.commit_time) def test_full_tree(self): c = self.make_commit(commit_time=30) t = Tree() t.add(b'data-x', 0o644, Blob().id) c.tree = t c1 = Commit() c1.set_raw_string(c.as_raw_string()) self.assertEqual(t.id, c1.tree) self.assertEqual(c.as_raw_string(), c1.as_raw_string()) def test_raw_length(self): c = self.make_commit() self.assertEqual(len(c.as_raw_string()), c.raw_length()) def test_simple(self): c = self.make_commit() self.assertEqual(c.id, b'5dac377bdded4c9aeb8dff595f0faeebcc8498cc') self.assertEqual( b'tree d80c186a03f423a81b39df39dc87fd269736ca86\n' b'parent ab64bbdcc51b170d21588e5c5d391ee5c0c96dfd\n' b'parent 4cffe90e0a41ad3f5190079d7c8f036bde29cbe6\n' b'author James Westby ' b'1174773719 +0000\n' b'committer James Westby ' b'1174773719 +0000\n' b'\n' b'Merge ../b\n', c.as_raw_string()) def test_timezone(self): c = self.make_commit(commit_timezone=(5 * 60)) self.assertTrue(b' +0005\n' in c.as_raw_string()) def test_neg_timezone(self): c = self.make_commit(commit_timezone=(-1 * 3600)) self.assertTrue(b' -0100\n' in c.as_raw_string()) def test_deserialize(self): c = self.make_commit() d = Commit() d._deserialize(c.as_raw_chunks()) self.assertEqual(c, d) def test_serialize_gpgsig(self): commit = self.make_commit(gpgsig=b"""-----BEGIN PGP SIGNATURE----- Version: GnuPG v1 iQIcBAABCgAGBQJULCdfAAoJEACAbyvXKaRXuKwP/RyP9PA49uAvu8tQVCC/uBa8 vi975+xvO14R8Pp8k2nps7lSxCdtCd+xVT1VRHs0wNhOZo2YCVoU1HATkPejqSeV NScTHcxnk4/+bxyfk14xvJkNp7FlQ3npmBkA+lbV0Ubr33rvtIE5jiJPyz+SgWAg xdBG2TojV0squj00GoH/euK6aX7GgZtwdtpTv44haCQdSuPGDcI4TORqR6YSqvy3 GPE+3ZqXPFFb+KILtimkxitdwB7CpwmNse2vE3rONSwTvi8nq3ZoQYNY73CQGkUy qoFU0pDtw87U3niFin1ZccDgH0bB6624sLViqrjcbYJeg815Htsu4rmzVaZADEVC XhIO4MThebusdk0AcNGjgpf3HRHk0DPMDDlIjm+Oao0cqovvF6VyYmcb0C+RmhJj dodLXMNmbqErwTk3zEkW0yZvNIYXH7m9SokPCZa4eeIM7be62X6h1mbt0/IU6Th+ v18fS0iTMP/Viug5und+05C/v04kgDo0CPphAbXwWMnkE4B6Tl9sdyUYXtvQsL7x 0+WP1gL27ANqNZiI07Kz/BhbBAQI/+2TFT7oGr0AnFPQ5jHp+3GpUf6OKuT1wT3H ND189UFuRuubxb42vZhpcXRbqJVWnbECTKVUPsGZqat3enQUB63uM4i6/RdONDZA fDeF1m4qYs+cUXKNUZ03 =X6RT -----END PGP SIGNATURE-----""") self.maxDiff = None self.assertEqual(b"""\ tree d80c186a03f423a81b39df39dc87fd269736ca86 parent ab64bbdcc51b170d21588e5c5d391ee5c0c96dfd parent 4cffe90e0a41ad3f5190079d7c8f036bde29cbe6 author James Westby 1174773719 +0000 committer James Westby 1174773719 +0000 gpgsig -----BEGIN PGP SIGNATURE----- Version: GnuPG v1 iQIcBAABCgAGBQJULCdfAAoJEACAbyvXKaRXuKwP/RyP9PA49uAvu8tQVCC/uBa8 vi975+xvO14R8Pp8k2nps7lSxCdtCd+xVT1VRHs0wNhOZo2YCVoU1HATkPejqSeV NScTHcxnk4/+bxyfk14xvJkNp7FlQ3npmBkA+lbV0Ubr33rvtIE5jiJPyz+SgWAg xdBG2TojV0squj00GoH/euK6aX7GgZtwdtpTv44haCQdSuPGDcI4TORqR6YSqvy3 GPE+3ZqXPFFb+KILtimkxitdwB7CpwmNse2vE3rONSwTvi8nq3ZoQYNY73CQGkUy qoFU0pDtw87U3niFin1ZccDgH0bB6624sLViqrjcbYJeg815Htsu4rmzVaZADEVC XhIO4MThebusdk0AcNGjgpf3HRHk0DPMDDlIjm+Oao0cqovvF6VyYmcb0C+RmhJj dodLXMNmbqErwTk3zEkW0yZvNIYXH7m9SokPCZa4eeIM7be62X6h1mbt0/IU6Th+ v18fS0iTMP/Viug5und+05C/v04kgDo0CPphAbXwWMnkE4B6Tl9sdyUYXtvQsL7x 0+WP1gL27ANqNZiI07Kz/BhbBAQI/+2TFT7oGr0AnFPQ5jHp+3GpUf6OKuT1wT3H ND189UFuRuubxb42vZhpcXRbqJVWnbECTKVUPsGZqat3enQUB63uM4i6/RdONDZA fDeF1m4qYs+cUXKNUZ03 =X6RT -----END PGP SIGNATURE----- Merge ../b """, commit.as_raw_string()) # noqa: W291,W293 def test_serialize_mergetag(self): tag = make_object( Tag, object=(Commit, b'a38d6181ff27824c79fc7df825164a212eff6a3f'), object_type_name=b'commit', name=b'v2.6.22-rc7', tag_time=1183319674, tag_timezone=0, tagger=b'Linus Torvalds ', message=default_message) commit = self.make_commit(mergetag=[tag]) self.assertEqual(b"""tree d80c186a03f423a81b39df39dc87fd269736ca86 parent ab64bbdcc51b170d21588e5c5d391ee5c0c96dfd parent 4cffe90e0a41ad3f5190079d7c8f036bde29cbe6 author James Westby 1174773719 +0000 committer James Westby 1174773719 +0000 mergetag object a38d6181ff27824c79fc7df825164a212eff6a3f type commit tag v2.6.22-rc7 tagger Linus Torvalds 1183319674 +0000 Linux 2.6.22-rc7 -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.7 (GNU/Linux) iD8DBQBGiAaAF3YsRnbiHLsRAitMAKCiLboJkQECM/jpYsY3WPfvUgLXkACgg3ql OK2XeQOiEeXtT76rV4t2WR4= =ivrA -----END PGP SIGNATURE----- Merge ../b """, commit.as_raw_string()) # noqa: W291,W293 def test_serialize_mergetags(self): tag = make_object( Tag, object=(Commit, b'a38d6181ff27824c79fc7df825164a212eff6a3f'), object_type_name=b'commit', name=b'v2.6.22-rc7', tag_time=1183319674, tag_timezone=0, tagger=b'Linus Torvalds ', message=default_message) commit = self.make_commit(mergetag=[tag, tag]) self.assertEqual(b"""tree d80c186a03f423a81b39df39dc87fd269736ca86 parent ab64bbdcc51b170d21588e5c5d391ee5c0c96dfd parent 4cffe90e0a41ad3f5190079d7c8f036bde29cbe6 author James Westby 1174773719 +0000 committer James Westby 1174773719 +0000 mergetag object a38d6181ff27824c79fc7df825164a212eff6a3f type commit tag v2.6.22-rc7 tagger Linus Torvalds 1183319674 +0000 Linux 2.6.22-rc7 -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.7 (GNU/Linux) iD8DBQBGiAaAF3YsRnbiHLsRAitMAKCiLboJkQECM/jpYsY3WPfvUgLXkACgg3ql OK2XeQOiEeXtT76rV4t2WR4= =ivrA -----END PGP SIGNATURE----- mergetag object a38d6181ff27824c79fc7df825164a212eff6a3f type commit tag v2.6.22-rc7 tagger Linus Torvalds 1183319674 +0000 Linux 2.6.22-rc7 -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.7 (GNU/Linux) iD8DBQBGiAaAF3YsRnbiHLsRAitMAKCiLboJkQECM/jpYsY3WPfvUgLXkACgg3ql OK2XeQOiEeXtT76rV4t2WR4= =ivrA -----END PGP SIGNATURE----- Merge ../b """, commit.as_raw_string()) # noqa: W291,W293 def test_deserialize_mergetag(self): tag = make_object( Tag, object=(Commit, b'a38d6181ff27824c79fc7df825164a212eff6a3f'), object_type_name=b'commit', name=b'v2.6.22-rc7', tag_time=1183319674, tag_timezone=0, tagger=b'Linus Torvalds ', message=default_message) commit = self.make_commit(mergetag=[tag]) d = Commit() d._deserialize(commit.as_raw_chunks()) self.assertEqual(commit, d) def test_deserialize_mergetags(self): tag = make_object( Tag, object=(Commit, b'a38d6181ff27824c79fc7df825164a212eff6a3f'), object_type_name=b'commit', name=b'v2.6.22-rc7', tag_time=1183319674, tag_timezone=0, tagger=b'Linus Torvalds ', message=default_message) commit = self.make_commit(mergetag=[tag, tag]) d = Commit() d._deserialize(commit.as_raw_chunks()) self.assertEqual(commit, d) default_committer = ( b'James Westby 1174773719 +0000') class CommitParseTests(ShaFileCheckTests): def make_commit_lines(self, tree=b'd80c186a03f423a81b39df39dc87fd269736ca86', parents=[ b'ab64bbdcc51b170d21588e5c5d391ee5c0c96dfd', b'4cffe90e0a41ad3f5190079d7c8f036bde29cbe6'], author=default_committer, committer=default_committer, encoding=None, message=b'Merge ../b\n', extra=None): lines = [] if tree is not None: lines.append(b'tree ' + tree) if parents is not None: lines.extend(b'parent ' + p for p in parents) if author is not None: lines.append(b'author ' + author) if committer is not None: lines.append(b'committer ' + committer) if encoding is not None: lines.append(b'encoding ' + encoding) if extra is not None: for name, value in sorted(extra.items()): lines.append(name + b' ' + value) lines.append(b'') if message is not None: lines.append(message) return lines def make_commit_text(self, **kwargs): return b'\n'.join(self.make_commit_lines(**kwargs)) def test_simple(self): c = Commit.from_string(self.make_commit_text()) self.assertEqual(b'Merge ../b\n', c.message) self.assertEqual(b'James Westby ', c.author) self.assertEqual(b'James Westby ', c.committer) self.assertEqual(b'd80c186a03f423a81b39df39dc87fd269736ca86', c.tree) self.assertEqual([b'ab64bbdcc51b170d21588e5c5d391ee5c0c96dfd', b'4cffe90e0a41ad3f5190079d7c8f036bde29cbe6'], c.parents) expected_time = datetime.datetime(2007, 3, 24, 22, 1, 59) self.assertEqual(expected_time, datetime.datetime.utcfromtimestamp(c.commit_time)) self.assertEqual(0, c.commit_timezone) self.assertEqual(expected_time, datetime.datetime.utcfromtimestamp(c.author_time)) self.assertEqual(0, c.author_timezone) self.assertEqual(None, c.encoding) def test_custom(self): c = Commit.from_string(self.make_commit_text( extra={b'extra-field': b'data'})) self.assertEqual([(b'extra-field', b'data')], c.extra) def test_encoding(self): c = Commit.from_string(self.make_commit_text(encoding=b'UTF-8')) self.assertEqual(b'UTF-8', c.encoding) def test_check(self): self.assertCheckSucceeds(Commit, self.make_commit_text()) self.assertCheckSucceeds(Commit, self.make_commit_text(parents=None)) self.assertCheckSucceeds(Commit, self.make_commit_text(encoding=b'UTF-8')) self.assertCheckFails(Commit, self.make_commit_text(tree=b'xxx')) self.assertCheckFails(Commit, self.make_commit_text( parents=[a_sha, b'xxx'])) bad_committer = b'some guy without an email address 1174773719 +0000' self.assertCheckFails(Commit, self.make_commit_text(committer=bad_committer)) self.assertCheckFails(Commit, self.make_commit_text(author=bad_committer)) self.assertCheckFails(Commit, self.make_commit_text(author=None)) self.assertCheckFails(Commit, self.make_commit_text(committer=None)) self.assertCheckFails(Commit, self.make_commit_text( author=None, committer=None)) def test_check_duplicates(self): # duplicate each of the header fields for i in range(5): lines = self.make_commit_lines(parents=[a_sha], encoding=b'UTF-8') lines.insert(i, lines[i]) text = b'\n'.join(lines) if lines[i].startswith(b'parent'): # duplicate parents are ok for now self.assertCheckSucceeds(Commit, text) else: self.assertCheckFails(Commit, text) def test_check_order(self): lines = self.make_commit_lines(parents=[a_sha], encoding=b'UTF-8') headers = lines[:5] rest = lines[5:] # of all possible permutations, ensure only the original succeeds for perm in permutations(headers): perm = list(perm) text = b'\n'.join(perm + rest) if perm == headers: self.assertCheckSucceeds(Commit, text) else: self.assertCheckFails(Commit, text) def test_check_commit_with_unparseable_time(self): identity_with_wrong_time = ( b'Igor Sysoev 18446743887488505614+42707004') # Those fail at reading time self.assertCheckFails( Commit, self.make_commit_text(author=default_committer, committer=identity_with_wrong_time)) self.assertCheckFails( Commit, self.make_commit_text(author=identity_with_wrong_time, committer=default_committer)) def test_check_commit_with_overflow_date(self): """Date with overflow should raise an ObjectFormatException when checked """ identity_with_wrong_time = ( b'Igor Sysoev 18446743887488505614 +42707004') commit0 = Commit.from_string(self.make_commit_text( author=identity_with_wrong_time, committer=default_committer)) commit1 = Commit.from_string(self.make_commit_text( author=default_committer, committer=identity_with_wrong_time)) # Those fails when triggering the check() method for commit in [commit0, commit1]: with self.assertRaises(ObjectFormatException): commit.check() + def test_mangled_author_line(self): + """Mangled author line should successfully parse""" + author_line = ( + b'Karl MacMillan <"Karl MacMillan ' + b'"> 1197475547 -0500' + ) + expected_identity = ( + b'Karl MacMillan <"Karl MacMillan ' + b'">' + ) + commit = Commit.from_string( + self.make_commit_text(author=author_line) + ) + + # The commit parses properly + self.assertEqual(commit.author, expected_identity) + + # But the check fails because the author identity is bogus + with self.assertRaises(ObjectFormatException): + commit.check() + def test_parse_gpgsig(self): c = Commit.from_string(b"""tree aaff74984cccd156a469afa7d9ab10e4777beb24 author Jelmer Vernooij 1412179807 +0200 committer Jelmer Vernooij 1412179807 +0200 gpgsig -----BEGIN PGP SIGNATURE----- Version: GnuPG v1 iQIcBAABCgAGBQJULCdfAAoJEACAbyvXKaRXuKwP/RyP9PA49uAvu8tQVCC/uBa8 vi975+xvO14R8Pp8k2nps7lSxCdtCd+xVT1VRHs0wNhOZo2YCVoU1HATkPejqSeV NScTHcxnk4/+bxyfk14xvJkNp7FlQ3npmBkA+lbV0Ubr33rvtIE5jiJPyz+SgWAg xdBG2TojV0squj00GoH/euK6aX7GgZtwdtpTv44haCQdSuPGDcI4TORqR6YSqvy3 GPE+3ZqXPFFb+KILtimkxitdwB7CpwmNse2vE3rONSwTvi8nq3ZoQYNY73CQGkUy qoFU0pDtw87U3niFin1ZccDgH0bB6624sLViqrjcbYJeg815Htsu4rmzVaZADEVC XhIO4MThebusdk0AcNGjgpf3HRHk0DPMDDlIjm+Oao0cqovvF6VyYmcb0C+RmhJj dodLXMNmbqErwTk3zEkW0yZvNIYXH7m9SokPCZa4eeIM7be62X6h1mbt0/IU6Th+ v18fS0iTMP/Viug5und+05C/v04kgDo0CPphAbXwWMnkE4B6Tl9sdyUYXtvQsL7x 0+WP1gL27ANqNZiI07Kz/BhbBAQI/+2TFT7oGr0AnFPQ5jHp+3GpUf6OKuT1wT3H ND189UFuRuubxb42vZhpcXRbqJVWnbECTKVUPsGZqat3enQUB63uM4i6/RdONDZA fDeF1m4qYs+cUXKNUZ03 =X6RT -----END PGP SIGNATURE----- foo """) # noqa: W291,W293 self.assertEqual(b'foo\n', c.message) self.assertEqual([], c.extra) self.assertEqual(b"""-----BEGIN PGP SIGNATURE----- Version: GnuPG v1 iQIcBAABCgAGBQJULCdfAAoJEACAbyvXKaRXuKwP/RyP9PA49uAvu8tQVCC/uBa8 vi975+xvO14R8Pp8k2nps7lSxCdtCd+xVT1VRHs0wNhOZo2YCVoU1HATkPejqSeV NScTHcxnk4/+bxyfk14xvJkNp7FlQ3npmBkA+lbV0Ubr33rvtIE5jiJPyz+SgWAg xdBG2TojV0squj00GoH/euK6aX7GgZtwdtpTv44haCQdSuPGDcI4TORqR6YSqvy3 GPE+3ZqXPFFb+KILtimkxitdwB7CpwmNse2vE3rONSwTvi8nq3ZoQYNY73CQGkUy qoFU0pDtw87U3niFin1ZccDgH0bB6624sLViqrjcbYJeg815Htsu4rmzVaZADEVC XhIO4MThebusdk0AcNGjgpf3HRHk0DPMDDlIjm+Oao0cqovvF6VyYmcb0C+RmhJj dodLXMNmbqErwTk3zEkW0yZvNIYXH7m9SokPCZa4eeIM7be62X6h1mbt0/IU6Th+ v18fS0iTMP/Viug5und+05C/v04kgDo0CPphAbXwWMnkE4B6Tl9sdyUYXtvQsL7x 0+WP1gL27ANqNZiI07Kz/BhbBAQI/+2TFT7oGr0AnFPQ5jHp+3GpUf6OKuT1wT3H ND189UFuRuubxb42vZhpcXRbqJVWnbECTKVUPsGZqat3enQUB63uM4i6/RdONDZA fDeF1m4qYs+cUXKNUZ03 =X6RT -----END PGP SIGNATURE-----""", c.gpgsig) def test_parse_header_trailing_newline(self): c = Commit.from_string(b'''\ tree a7d6277f78d3ecd0230a1a5df6db00b1d9c521ac parent c09b6dec7a73760fbdb478383a3c926b18db8bbe author Neil Matatall 1461964057 -1000 committer Neil Matatall 1461964057 -1000 gpgsig -----BEGIN PGP SIGNATURE----- wsBcBAABCAAQBQJXI80ZCRA6pcNDcVZ70gAAarcIABs72xRX3FWeox349nh6ucJK CtwmBTusez2Zwmq895fQEbZK7jpaGO5TRO4OvjFxlRo0E08UFx3pxZHSpj6bsFeL hHsDXnCaotphLkbgKKRdGZo7tDqM84wuEDlh4MwNe7qlFC7bYLDyysc81ZX5lpMm 2MFF1TvjLAzSvkT7H1LPkuR3hSvfCYhikbPOUNnKOo0sYjeJeAJ/JdAVQ4mdJIM0 gl3REp9+A+qBEpNQI7z94Pg5Bc5xenwuDh3SJgHvJV6zBWupWcdB3fAkVd4TPnEZ nHxksHfeNln9RKseIDcy4b2ATjhDNIJZARHNfr6oy4u3XPW4svRqtBsLoMiIeuI= =ms6q -----END PGP SIGNATURE----- 3.3.0 version bump and docs ''') # noqa: W291,W293 self.assertEqual([], c.extra) self.assertEqual(b'''\ -----BEGIN PGP SIGNATURE----- wsBcBAABCAAQBQJXI80ZCRA6pcNDcVZ70gAAarcIABs72xRX3FWeox349nh6ucJK CtwmBTusez2Zwmq895fQEbZK7jpaGO5TRO4OvjFxlRo0E08UFx3pxZHSpj6bsFeL hHsDXnCaotphLkbgKKRdGZo7tDqM84wuEDlh4MwNe7qlFC7bYLDyysc81ZX5lpMm 2MFF1TvjLAzSvkT7H1LPkuR3hSvfCYhikbPOUNnKOo0sYjeJeAJ/JdAVQ4mdJIM0 gl3REp9+A+qBEpNQI7z94Pg5Bc5xenwuDh3SJgHvJV6zBWupWcdB3fAkVd4TPnEZ nHxksHfeNln9RKseIDcy4b2ATjhDNIJZARHNfr6oy4u3XPW4svRqtBsLoMiIeuI= =ms6q -----END PGP SIGNATURE-----\n''', c.gpgsig) _TREE_ITEMS = { b'a.c': (0o100755, b'd80c186a03f423a81b39df39dc87fd269736ca86'), b'a': (stat.S_IFDIR, b'd80c186a03f423a81b39df39dc87fd269736ca86'), b'a/c': (stat.S_IFDIR, b'd80c186a03f423a81b39df39dc87fd269736ca86'), } _SORTED_TREE_ITEMS = [ TreeEntry(b'a.c', 0o100755, b'd80c186a03f423a81b39df39dc87fd269736ca86'), TreeEntry(b'a', stat.S_IFDIR, b'd80c186a03f423a81b39df39dc87fd269736ca86'), TreeEntry(b'a/c', stat.S_IFDIR, b'd80c186a03f423a81b39df39dc87fd269736ca86'), ] class TreeTests(ShaFileCheckTests): def test_add(self): myhexsha = b'd80c186a03f423a81b39df39dc87fd269736ca86' x = Tree() x.add(b'myname', 0o100755, myhexsha) self.assertEqual(x[b'myname'], (0o100755, myhexsha)) self.assertEqual( b'100755 myname\0' + hex_to_sha(myhexsha), x.as_raw_string()) def test_add_old_order(self): myhexsha = b'd80c186a03f423a81b39df39dc87fd269736ca86' x = Tree() warnings.simplefilter("ignore", DeprecationWarning) try: x.add(0o100755, b'myname', myhexsha) finally: warnings.resetwarnings() self.assertEqual(x[b'myname'], (0o100755, myhexsha)) self.assertEqual(b'100755 myname\0' + hex_to_sha(myhexsha), x.as_raw_string()) def test_simple(self): myhexsha = b'd80c186a03f423a81b39df39dc87fd269736ca86' x = Tree() x[b'myname'] = (0o100755, myhexsha) self.assertEqual(b'100755 myname\0' + hex_to_sha(myhexsha), x.as_raw_string()) self.assertEqual(b'100755 myname\0' + hex_to_sha(myhexsha), bytes(x)) def test_tree_update_id(self): x = Tree() x[b'a.c'] = (0o100755, b'd80c186a03f423a81b39df39dc87fd269736ca86') self.assertEqual(b'0c5c6bc2c081accfbc250331b19e43b904ab9cdd', x.id) x[b'a.b'] = (stat.S_IFDIR, b'd80c186a03f423a81b39df39dc87fd269736ca86') self.assertEqual(b'07bfcb5f3ada15bbebdfa3bbb8fd858a363925c8', x.id) def test_tree_iteritems_dir_sort(self): x = Tree() for name, item in _TREE_ITEMS.items(): x[name] = item self.assertEqual(_SORTED_TREE_ITEMS, x.items()) def test_tree_items_dir_sort(self): x = Tree() for name, item in _TREE_ITEMS.items(): x[name] = item self.assertEqual(_SORTED_TREE_ITEMS, x.items()) def _do_test_parse_tree(self, parse_tree): dir = os.path.join(os.path.dirname(__file__), 'data', 'trees') o = Tree.from_path(hex_to_filename(dir, tree_sha)) self.assertEqual([(b'a', 0o100644, a_sha), (b'b', 0o100644, b_sha)], list(parse_tree(o.as_raw_string()))) # test a broken tree that has a leading 0 on the file mode broken_tree = b'0100644 foo\0' + hex_to_sha(a_sha) def eval_parse_tree(*args, **kwargs): return list(parse_tree(*args, **kwargs)) self.assertEqual([(b'foo', 0o100644, a_sha)], eval_parse_tree(broken_tree)) self.assertRaises(ObjectFormatException, eval_parse_tree, broken_tree, strict=True) test_parse_tree = functest_builder(_do_test_parse_tree, _parse_tree_py) test_parse_tree_extension = ext_functest_builder(_do_test_parse_tree, parse_tree) def _do_test_sorted_tree_items(self, sorted_tree_items): def do_sort(entries): return list(sorted_tree_items(entries, False)) actual = do_sort(_TREE_ITEMS) self.assertEqual(_SORTED_TREE_ITEMS, actual) self.assertTrue(isinstance(actual[0], TreeEntry)) # C/Python implementations may differ in specific error types, but # should all error on invalid inputs. # For example, the C implementation has stricter type checks, so may # raise TypeError where the Python implementation raises # AttributeError. errors = (TypeError, ValueError, AttributeError) self.assertRaises(errors, do_sort, b'foo') self.assertRaises(errors, do_sort, {b'foo': (1, 2, 3)}) myhexsha = b'd80c186a03f423a81b39df39dc87fd269736ca86' self.assertRaises(errors, do_sort, {b'foo': (b'xxx', myhexsha)}) self.assertRaises(errors, do_sort, {b'foo': (0o100755, 12345)}) test_sorted_tree_items = functest_builder(_do_test_sorted_tree_items, _sorted_tree_items_py) test_sorted_tree_items_extension = ext_functest_builder( _do_test_sorted_tree_items, sorted_tree_items) def _do_test_sorted_tree_items_name_order(self, sorted_tree_items): self.assertEqual([ TreeEntry(b'a', stat.S_IFDIR, b'd80c186a03f423a81b39df39dc87fd269736ca86'), TreeEntry(b'a.c', 0o100755, b'd80c186a03f423a81b39df39dc87fd269736ca86'), TreeEntry(b'a/c', stat.S_IFDIR, b'd80c186a03f423a81b39df39dc87fd269736ca86'), ], list(sorted_tree_items(_TREE_ITEMS, True))) test_sorted_tree_items_name_order = functest_builder( _do_test_sorted_tree_items_name_order, _sorted_tree_items_py) test_sorted_tree_items_name_order_extension = ext_functest_builder( _do_test_sorted_tree_items_name_order, sorted_tree_items) def test_check(self): t = Tree sha = hex_to_sha(a_sha) # filenames self.assertCheckSucceeds(t, b'100644 .a\0' + sha) self.assertCheckFails(t, b'100644 \0' + sha) self.assertCheckFails(t, b'100644 .\0' + sha) self.assertCheckFails(t, b'100644 a/a\0' + sha) self.assertCheckFails(t, b'100644 ..\0' + sha) self.assertCheckFails(t, b'100644 .git\0' + sha) # modes self.assertCheckSucceeds(t, b'100644 a\0' + sha) self.assertCheckSucceeds(t, b'100755 a\0' + sha) self.assertCheckSucceeds(t, b'160000 a\0' + sha) # TODO more whitelisted modes self.assertCheckFails(t, b'123456 a\0' + sha) self.assertCheckFails(t, b'123abc a\0' + sha) # should fail check, but parses ok self.assertCheckFails(t, b'0100644 foo\0' + sha) # shas self.assertCheckFails(t, b'100644 a\0' + (b'x' * 5)) self.assertCheckFails(t, b'100644 a\0' + (b'x' * 18) + b'\0') self.assertCheckFails( t, b'100644 a\0' + (b'x' * 21) + b'\n100644 b\0' + sha) # ordering sha2 = hex_to_sha(b_sha) self.assertCheckSucceeds( t, b'100644 a\0' + sha + b'\n100644 b\0' + sha) self.assertCheckSucceeds( t, b'100644 a\0' + sha + b'\n100644 b\0' + sha2) self.assertCheckFails(t, b'100644 a\0' + sha + b'\n100755 a\0' + sha2) self.assertCheckFails(t, b'100644 b\0' + sha2 + b'\n100644 a\0' + sha) def test_iter(self): t = Tree() t[b'foo'] = (0o100644, a_sha) self.assertEqual(set([b'foo']), set(t)) class TagSerializeTests(TestCase): def test_serialize_simple(self): x = make_object( Tag, tagger=b'Jelmer Vernooij ', name=b'0.1', message=b'Tag 0.1', object=(Blob, b'd80c186a03f423a81b39df39dc87fd269736ca86'), tag_time=423423423, tag_timezone=0) self.assertEqual((b'object d80c186a03f423a81b39df39dc87fd269736ca86\n' b'type blob\n' b'tag 0.1\n' b'tagger Jelmer Vernooij ' b'423423423 +0000\n' b'\n' b'Tag 0.1'), x.as_raw_string()) def test_serialize_none_message(self): x = make_object( Tag, tagger=b'Jelmer Vernooij ', name=b'0.1', message=None, object=(Blob, b'd80c186a03f423a81b39df39dc87fd269736ca86'), tag_time=423423423, tag_timezone=0) self.assertEqual((b'object d80c186a03f423a81b39df39dc87fd269736ca86\n' b'type blob\n' b'tag 0.1\n' b'tagger Jelmer Vernooij ' b'423423423 +0000\n'), x.as_raw_string()) default_tagger = (b'Linus Torvalds ' b'1183319674 -0700') default_message = b"""Linux 2.6.22-rc7 -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.7 (GNU/Linux) iD8DBQBGiAaAF3YsRnbiHLsRAitMAKCiLboJkQECM/jpYsY3WPfvUgLXkACgg3ql OK2XeQOiEeXtT76rV4t2WR4= =ivrA -----END PGP SIGNATURE----- """ class TagParseTests(ShaFileCheckTests): def make_tag_lines(self, object_sha=b'a38d6181ff27824c79fc7df825164a212eff6a3f', object_type_name=b'commit', name=b'v2.6.22-rc7', tagger=default_tagger, message=default_message): lines = [] if object_sha is not None: lines.append(b'object ' + object_sha) if object_type_name is not None: lines.append(b'type ' + object_type_name) if name is not None: lines.append(b'tag ' + name) if tagger is not None: lines.append(b'tagger ' + tagger) if message is not None: lines.append(b'') lines.append(message) return lines def make_tag_text(self, **kwargs): return b'\n'.join(self.make_tag_lines(**kwargs)) def test_parse(self): x = Tag() x.set_raw_string(self.make_tag_text()) self.assertEqual( b'Linus Torvalds ', x.tagger) self.assertEqual(b'v2.6.22-rc7', x.name) object_type, object_sha = x.object self.assertEqual(b'a38d6181ff27824c79fc7df825164a212eff6a3f', object_sha) self.assertEqual(Commit, object_type) self.assertEqual(datetime.datetime.utcfromtimestamp(x.tag_time), datetime.datetime(2007, 7, 1, 19, 54, 34)) self.assertEqual(-25200, x.tag_timezone) def test_parse_no_tagger(self): x = Tag() x.set_raw_string(self.make_tag_text(tagger=None)) self.assertEqual(None, x.tagger) self.assertEqual(b'v2.6.22-rc7', x.name) self.assertEqual(None, x.tag_time) def test_parse_no_message(self): x = Tag() x.set_raw_string(self.make_tag_text(message=None)) self.assertEqual(None, x.message) self.assertEqual( b'Linus Torvalds ', x.tagger) self.assertEqual(datetime.datetime.utcfromtimestamp(x.tag_time), datetime.datetime(2007, 7, 1, 19, 54, 34)) self.assertEqual(-25200, x.tag_timezone) self.assertEqual(b'v2.6.22-rc7', x.name) def test_check(self): self.assertCheckSucceeds(Tag, self.make_tag_text()) self.assertCheckFails(Tag, self.make_tag_text(object_sha=None)) self.assertCheckFails(Tag, self.make_tag_text(object_type_name=None)) self.assertCheckFails(Tag, self.make_tag_text(name=None)) self.assertCheckFails(Tag, self.make_tag_text(name=b'')) self.assertCheckFails(Tag, self.make_tag_text( object_type_name=b'foobar')) self.assertCheckFails(Tag, self.make_tag_text( tagger=b'some guy without an email address 1183319674 -0700')) self.assertCheckFails(Tag, self.make_tag_text( tagger=(b'Linus Torvalds ' b'Sun 7 Jul 2007 12:54:34 +0700'))) self.assertCheckFails(Tag, self.make_tag_text(object_sha=b'xxx')) def test_check_tag_with_unparseable_field(self): self.assertCheckFails(Tag, self.make_tag_text( tagger=(b'Linus Torvalds ' b'423423+0000'))) def test_check_tag_with_overflow_time(self): """Date with overflow should raise an ObjectFormatException when checked """ author = 'Some Dude %s +0000' % (MAX_TIME+1, ) tag = Tag.from_string(self.make_tag_text( tagger=(author.encode()))) with self.assertRaises(ObjectFormatException): tag.check() def test_check_duplicates(self): # duplicate each of the header fields for i in range(4): lines = self.make_tag_lines() lines.insert(i, lines[i]) self.assertCheckFails(Tag, b'\n'.join(lines)) def test_check_order(self): lines = self.make_tag_lines() headers = lines[:4] rest = lines[4:] # of all possible permutations, ensure only the original succeeds for perm in permutations(headers): perm = list(perm) text = b'\n'.join(perm + rest) if perm == headers: self.assertCheckSucceeds(Tag, text) else: self.assertCheckFails(Tag, text) def test_tree_copy_after_update(self): """Check Tree.id is correctly updated when the tree is copied after updated. """ shas = [] tree = Tree() shas.append(tree.id) tree.add(b'data', 0o644, Blob().id) copied = tree.copy() shas.append(tree.id) shas.append(copied.id) self.assertNotIn(shas[0], shas[1:]) self.assertEqual(shas[1], shas[2]) class CheckTests(TestCase): def test_check_hexsha(self): check_hexsha(a_sha, "failed to check good sha") self.assertRaises(ObjectFormatException, check_hexsha, b'1' * 39, 'sha too short') self.assertRaises(ObjectFormatException, check_hexsha, b'1' * 41, 'sha too long') self.assertRaises(ObjectFormatException, check_hexsha, b'x' * 40, 'invalid characters') def test_check_identity(self): check_identity(b'Dave Borowitz ', "failed to check good identity") check_identity(b'', "failed to check good identity") self.assertRaises(ObjectFormatException, check_identity, b'Dave Borowitz', "no email") self.assertRaises(ObjectFormatException, check_identity, b'Dave Borowitz ', "incomplete email") self.assertRaises(ObjectFormatException, check_identity, b'Dave Borowitz <', "typo") self.assertRaises(ObjectFormatException, check_identity, b'Dave Borowitz >', "typo") self.assertRaises(ObjectFormatException, check_identity, b'Dave Borowitz xxx', "trailing characters") class TimezoneTests(TestCase): def test_parse_timezone_utc(self): self.assertEqual((0, False), parse_timezone(b'+0000')) def test_parse_timezone_utc_negative(self): self.assertEqual((0, True), parse_timezone(b'-0000')) def test_generate_timezone_utc(self): self.assertEqual(b'+0000', format_timezone(0)) def test_generate_timezone_utc_negative(self): self.assertEqual(b'-0000', format_timezone(0, True)) def test_parse_timezone_cet(self): self.assertEqual((60 * 60, False), parse_timezone(b'+0100')) def test_format_timezone_cet(self): self.assertEqual(b'+0100', format_timezone(60 * 60)) def test_format_timezone_pdt(self): self.assertEqual(b'-0400', format_timezone(-4 * 60 * 60)) def test_parse_timezone_pdt(self): self.assertEqual((-4 * 60 * 60, False), parse_timezone(b'-0400')) def test_format_timezone_pdt_half(self): self.assertEqual(b'-0440', format_timezone(int(((-4 * 60) - 40) * 60))) def test_format_timezone_double_negative(self): self.assertEqual(b'--700', format_timezone(int(((7 * 60)) * 60), True)) def test_parse_timezone_pdt_half(self): self.assertEqual((((-4 * 60) - 40) * 60, False), parse_timezone(b'-0440')) def test_parse_timezone_double_negative(self): self.assertEqual( (int(((7 * 60)) * 60), False), parse_timezone(b'+700')) self.assertEqual( (int(((7 * 60)) * 60), True), parse_timezone(b'--700')) class ShaFileCopyTests(TestCase): def assert_copy(self, orig): oclass = object_class(orig.type_num) copy = orig.copy() self.assertTrue(isinstance(copy, oclass)) self.assertEqual(copy, orig) self.assertTrue(copy is not orig) def test_commit_copy(self): attrs = {'tree': b'd80c186a03f423a81b39df39dc87fd269736ca86', 'parents': [b'ab64bbdcc51b170d21588e5c5d391ee5c0c96dfd', b'4cffe90e0a41ad3f5190079d7c8f036bde29cbe6'], 'author': b'James Westby ', 'committer': b'James Westby ', 'commit_time': 1174773719, 'author_time': 1174773719, 'commit_timezone': 0, 'author_timezone': 0, 'message': b'Merge ../b\n'} commit = make_commit(**attrs) self.assert_copy(commit) def test_blob_copy(self): blob = make_object(Blob, data=b'i am a blob') self.assert_copy(blob) def test_tree_copy(self): blob = make_object(Blob, data=b'i am a blob') tree = Tree() tree[b'blob'] = (stat.S_IFREG, blob.id) self.assert_copy(tree) def test_tag_copy(self): tag = make_object( Tag, name=b'tag', message=b'', tagger=b'Tagger ', tag_time=12345, tag_timezone=0, object=(Commit, b'0' * 40)) self.assert_copy(tag) class ShaFileSerializeTests(TestCase): """`ShaFile` objects only gets serialized once if they haven't changed. """ @contextmanager def assert_serialization_on_change( self, obj, needs_serialization_after_change=True): old_id = obj.id self.assertFalse(obj._needs_serialization) yield obj if needs_serialization_after_change: self.assertTrue(obj._needs_serialization) else: self.assertFalse(obj._needs_serialization) new_id = obj.id self.assertFalse(obj._needs_serialization) self.assertNotEqual(old_id, new_id) def test_commit_serialize(self): attrs = {'tree': b'd80c186a03f423a81b39df39dc87fd269736ca86', 'parents': [b'ab64bbdcc51b170d21588e5c5d391ee5c0c96dfd', b'4cffe90e0a41ad3f5190079d7c8f036bde29cbe6'], 'author': b'James Westby ', 'committer': b'James Westby ', 'commit_time': 1174773719, 'author_time': 1174773719, 'commit_timezone': 0, 'author_timezone': 0, 'message': b'Merge ../b\n'} commit = make_commit(**attrs) with self.assert_serialization_on_change(commit): commit.parents = [b'ab64bbdcc51b170d21588e5c5d391ee5c0c96dfd'] def test_blob_serialize(self): blob = make_object(Blob, data=b'i am a blob') with self.assert_serialization_on_change( blob, needs_serialization_after_change=False): blob.data = b'i am another blob' def test_tree_serialize(self): blob = make_object(Blob, data=b'i am a blob') tree = Tree() tree[b'blob'] = (stat.S_IFREG, blob.id) with self.assert_serialization_on_change(tree): tree[b'blob2'] = (stat.S_IFREG, blob.id) def test_tag_serialize(self): tag = make_object( Tag, name=b'tag', message=b'', tagger=b'Tagger ', tag_time=12345, tag_timezone=0, object=(Commit, b'0' * 40)) with self.assert_serialization_on_change(tag): tag.message = b'new message' def test_tag_serialize_time_error(self): with self.assertRaises(ObjectFormatException): tag = make_object( Tag, name=b'tag', message=b'some message', tagger=b'Tagger 1174773719+0000', object=(Commit, b'0' * 40)) tag._deserialize(tag._serialize()) class PrettyFormatTreeEntryTests(TestCase): def test_format(self): self.assertEqual( '40000 tree 40820c38cfb182ce6c8b261555410d8382a5918b\tfoo\n', pretty_format_tree_entry( b"foo", 0o40000, b"40820c38cfb182ce6c8b261555410d8382a5918b")) diff --git a/dulwich/tests/test_objectspec.py b/dulwich/tests/test_objectspec.py index ce7e1301..baedc61b 100644 --- a/dulwich/tests/test_objectspec.py +++ b/dulwich/tests/test_objectspec.py @@ -1,208 +1,213 @@ # test_objectspec.py -- tests for objectspec.py # Copyright (C) 2014 Jelmer Vernooij # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """Tests for revision spec parsing.""" # TODO: Round-trip parse-serialize-parse and serialize-parse-serialize tests. from dulwich.objects import ( Blob, ) from dulwich.objectspec import ( parse_object, parse_commit_range, parse_ref, parse_refs, parse_reftuple, parse_reftuples, parse_tree, ) from dulwich.repo import MemoryRepo from dulwich.tests import ( TestCase, ) from dulwich.tests.utils import ( build_commit_graph, ) class ParseObjectTests(TestCase): """Test parse_object.""" def test_nonexistent(self): r = MemoryRepo() self.assertRaises(KeyError, parse_object, r, "thisdoesnotexist") def test_blob_by_sha(self): r = MemoryRepo() b = Blob.from_string(b"Blah") r.object_store.add_object(b) self.assertEqual(b, parse_object(r, b.id)) class ParseCommitRangeTests(TestCase): """Test parse_commit_range.""" def test_nonexistent(self): r = MemoryRepo() self.assertRaises(KeyError, parse_commit_range, r, "thisdoesnotexist") def test_commit_by_sha(self): r = MemoryRepo() c1, c2, c3 = build_commit_graph( r.object_store, [[1], [2, 1], [3, 1, 2]]) self.assertEqual([c1], list(parse_commit_range(r, c1.id))) class ParseRefTests(TestCase): def test_nonexistent(self): r = {} self.assertRaises(KeyError, parse_ref, r, b"thisdoesnotexist") def test_ambiguous_ref(self): r = {b"ambig1": 'bla', b"refs/ambig1": 'bla', b"refs/tags/ambig1": 'bla', b"refs/heads/ambig1": 'bla', b"refs/remotes/ambig1": 'bla', b"refs/remotes/ambig1/HEAD": "bla"} self.assertEqual(b"ambig1", parse_ref(r, b"ambig1")) def test_ambiguous_ref2(self): r = {b"refs/ambig2": 'bla', b"refs/tags/ambig2": 'bla', b"refs/heads/ambig2": 'bla', b"refs/remotes/ambig2": 'bla', b"refs/remotes/ambig2/HEAD": "bla"} self.assertEqual(b"refs/ambig2", parse_ref(r, b"ambig2")) def test_ambiguous_tag(self): r = {b"refs/tags/ambig3": 'bla', b"refs/heads/ambig3": 'bla', b"refs/remotes/ambig3": 'bla', b"refs/remotes/ambig3/HEAD": "bla"} self.assertEqual(b"refs/tags/ambig3", parse_ref(r, b"ambig3")) def test_ambiguous_head(self): r = {b"refs/heads/ambig4": 'bla', b"refs/remotes/ambig4": 'bla', b"refs/remotes/ambig4/HEAD": "bla"} self.assertEqual(b"refs/heads/ambig4", parse_ref(r, b"ambig4")) def test_ambiguous_remote(self): r = {b"refs/remotes/ambig5": 'bla', b"refs/remotes/ambig5/HEAD": "bla"} self.assertEqual(b"refs/remotes/ambig5", parse_ref(r, b"ambig5")) def test_ambiguous_remote_head(self): r = {b"refs/remotes/ambig6/HEAD": "bla"} self.assertEqual(b"refs/remotes/ambig6/HEAD", parse_ref(r, b"ambig6")) def test_heads_full(self): r = {b"refs/heads/foo": "bla"} self.assertEqual(b"refs/heads/foo", parse_ref(r, b"refs/heads/foo")) def test_heads_partial(self): r = {b"refs/heads/foo": "bla"} self.assertEqual(b"refs/heads/foo", parse_ref(r, b"heads/foo")) def test_tags_partial(self): r = {b"refs/tags/foo": "bla"} self.assertEqual(b"refs/tags/foo", parse_ref(r, b"tags/foo")) class ParseRefsTests(TestCase): def test_nonexistent(self): r = {} self.assertRaises(KeyError, parse_refs, r, [b"thisdoesnotexist"]) def test_head(self): r = {b"refs/heads/foo": "bla"} self.assertEqual([b"refs/heads/foo"], parse_refs(r, [b"foo"])) def test_full(self): r = {b"refs/heads/foo": "bla"} self.assertEqual([b"refs/heads/foo"], parse_refs(r, b"refs/heads/foo")) class ParseReftupleTests(TestCase): def test_nonexistent(self): r = {} self.assertRaises(KeyError, parse_reftuple, r, r, b"thisdoesnotexist") def test_head(self): r = {b"refs/heads/foo": "bla"} self.assertEqual((b"refs/heads/foo", b"refs/heads/foo", False), parse_reftuple(r, r, b"foo")) self.assertEqual((b"refs/heads/foo", b"refs/heads/foo", True), parse_reftuple(r, r, b"+foo")) self.assertEqual((b"refs/heads/foo", b"refs/heads/foo", True), parse_reftuple(r, {}, b"+foo")) def test_full(self): r = {b"refs/heads/foo": "bla"} self.assertEqual((b"refs/heads/foo", b"refs/heads/foo", False), parse_reftuple(r, r, b"refs/heads/foo")) def test_no_left_ref(self): r = {b"refs/heads/foo": "bla"} self.assertEqual((None, b"refs/heads/foo", False), parse_reftuple(r, r, b":refs/heads/foo")) def test_no_right_ref(self): r = {b"refs/heads/foo": "bla"} self.assertEqual((b"refs/heads/foo", None, False), parse_reftuple(r, r, b"refs/heads/foo:")) + def test_default_with_string(self): + r = {b"refs/heads/foo": "bla"} + self.assertEqual((b"refs/heads/foo", b"refs/heads/foo", False), + parse_reftuple(r, r, "foo")) + class ParseReftuplesTests(TestCase): def test_nonexistent(self): r = {} self.assertRaises(KeyError, parse_reftuples, r, r, [b"thisdoesnotexist"]) def test_head(self): r = {b"refs/heads/foo": "bla"} self.assertEqual([(b"refs/heads/foo", b"refs/heads/foo", False)], parse_reftuples(r, r, [b"foo"])) def test_full(self): r = {b"refs/heads/foo": "bla"} self.assertEqual([(b"refs/heads/foo", b"refs/heads/foo", False)], parse_reftuples(r, r, b"refs/heads/foo")) class ParseTreeTests(TestCase): """Test parse_tree.""" def test_nonexistent(self): r = MemoryRepo() self.assertRaises(KeyError, parse_tree, r, "thisdoesnotexist") def test_from_commit(self): r = MemoryRepo() c1, c2, c3 = build_commit_graph( r.object_store, [[1], [2, 1], [3, 1, 2]]) self.assertEqual(r[c1.tree], parse_tree(r, c1.id)) self.assertEqual(r[c1.tree], parse_tree(r, c1.tree)) diff --git a/dulwich/tests/test_porcelain.py b/dulwich/tests/test_porcelain.py index 49cf1d76..feed11f7 100644 --- a/dulwich/tests/test_porcelain.py +++ b/dulwich/tests/test_porcelain.py @@ -1,1528 +1,1576 @@ # test_porcelain.py -- porcelain tests # Copyright (C) 2013 Jelmer Vernooij # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """Tests for dulwich.porcelain.""" from io import BytesIO try: from StringIO import StringIO except ImportError: from io import StringIO import os import shutil import tarfile import tempfile import time from dulwich import porcelain from dulwich.diff_tree import tree_changes from dulwich.objects import ( Blob, Tag, Tree, ZERO_SHA, ) from dulwich.repo import ( NoIndexPresent, Repo, ) from dulwich.tests import ( TestCase, ) from dulwich.tests.utils import ( build_commit_graph, make_commit, make_object, ) class PorcelainTestCase(TestCase): def setUp(self): super(PorcelainTestCase, self).setUp() self.test_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, self.test_dir) self.repo = Repo.init(os.path.join(self.test_dir, 'repo'), mkdir=True) self.addCleanup(self.repo.close) class ArchiveTests(PorcelainTestCase): """Tests for the archive command.""" def test_simple(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]]) self.repo.refs[b"refs/heads/master"] = c3.id out = BytesIO() err = BytesIO() porcelain.archive(self.repo.path, b"refs/heads/master", outstream=out, errstream=err) self.assertEqual(b"", err.getvalue()) tf = tarfile.TarFile(fileobj=out) self.addCleanup(tf.close) self.assertEqual([], tf.getnames()) class UpdateServerInfoTests(PorcelainTestCase): def test_simple(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]]) self.repo.refs[b"refs/heads/foo"] = c3.id porcelain.update_server_info(self.repo.path) self.assertTrue(os.path.exists( os.path.join(self.repo.controldir(), 'info', 'refs'))) class CommitTests(PorcelainTestCase): def test_custom_author(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]]) self.repo.refs[b"refs/heads/foo"] = c3.id sha = porcelain.commit( self.repo.path, message=b"Some message", author=b"Joe ", committer=b"Bob ") self.assertTrue(isinstance(sha, bytes)) self.assertEqual(len(sha), 40) def test_unicode(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]]) self.repo.refs[b"refs/heads/foo"] = c3.id sha = porcelain.commit( self.repo.path, message="Some message", author="Joe ", committer="Bob ") self.assertTrue(isinstance(sha, bytes)) self.assertEqual(len(sha), 40) class CloneTests(PorcelainTestCase): def test_simple_local(self): f1_1 = make_object(Blob, data=b'f1') commit_spec = [[1], [2, 1], [3, 1, 2]] trees = {1: [(b'f1', f1_1), (b'f2', f1_1)], 2: [(b'f1', f1_1), (b'f2', f1_1)], 3: [(b'f1', f1_1), (b'f2', f1_1)], } c1, c2, c3 = build_commit_graph(self.repo.object_store, commit_spec, trees) self.repo.refs[b"refs/heads/master"] = c3.id self.repo.refs[b"refs/tags/foo"] = c3.id target_path = tempfile.mkdtemp() errstream = BytesIO() self.addCleanup(shutil.rmtree, target_path) r = porcelain.clone(self.repo.path, target_path, checkout=False, errstream=errstream) self.addCleanup(r.close) self.assertEqual(r.path, target_path) target_repo = Repo(target_path) self.assertEqual(0, len(target_repo.open_index())) self.assertEqual(c3.id, target_repo.refs[b'refs/tags/foo']) self.assertTrue(b'f1' not in os.listdir(target_path)) self.assertTrue(b'f2' not in os.listdir(target_path)) c = r.get_config() encoded_path = self.repo.path if not isinstance(encoded_path, bytes): encoded_path = encoded_path.encode('utf-8') self.assertEqual(encoded_path, c.get((b'remote', b'origin'), b'url')) self.assertEqual( b'+refs/heads/*:refs/remotes/origin/*', c.get((b'remote', b'origin'), b'fetch')) def test_simple_local_with_checkout(self): f1_1 = make_object(Blob, data=b'f1') commit_spec = [[1], [2, 1], [3, 1, 2]] trees = {1: [(b'f1', f1_1), (b'f2', f1_1)], 2: [(b'f1', f1_1), (b'f2', f1_1)], 3: [(b'f1', f1_1), (b'f2', f1_1)], } c1, c2, c3 = build_commit_graph(self.repo.object_store, commit_spec, trees) self.repo.refs[b"refs/heads/master"] = c3.id target_path = tempfile.mkdtemp() errstream = BytesIO() self.addCleanup(shutil.rmtree, target_path) with porcelain.clone(self.repo.path, target_path, checkout=True, errstream=errstream) as r: self.assertEqual(r.path, target_path) with Repo(target_path) as r: self.assertEqual(r.head(), c3.id) self.assertTrue('f1' in os.listdir(target_path)) self.assertTrue('f2' in os.listdir(target_path)) def test_bare_local_with_checkout(self): f1_1 = make_object(Blob, data=b'f1') commit_spec = [[1], [2, 1], [3, 1, 2]] trees = {1: [(b'f1', f1_1), (b'f2', f1_1)], 2: [(b'f1', f1_1), (b'f2', f1_1)], 3: [(b'f1', f1_1), (b'f2', f1_1)], } c1, c2, c3 = build_commit_graph(self.repo.object_store, commit_spec, trees) self.repo.refs[b"refs/heads/master"] = c3.id target_path = tempfile.mkdtemp() errstream = BytesIO() self.addCleanup(shutil.rmtree, target_path) with porcelain.clone( self.repo.path, target_path, bare=True, errstream=errstream) as r: self.assertEqual(r.path, target_path) with Repo(target_path) as r: r.head() self.assertRaises(NoIndexPresent, r.open_index) self.assertFalse(b'f1' in os.listdir(target_path)) self.assertFalse(b'f2' in os.listdir(target_path)) def test_no_checkout_with_bare(self): f1_1 = make_object(Blob, data=b'f1') commit_spec = [[1]] trees = {1: [(b'f1', f1_1), (b'f2', f1_1)]} (c1, ) = build_commit_graph(self.repo.object_store, commit_spec, trees) self.repo.refs[b"refs/heads/master"] = c1.id self.repo.refs[b"HEAD"] = c1.id target_path = tempfile.mkdtemp() errstream = BytesIO() self.addCleanup(shutil.rmtree, target_path) self.assertRaises( ValueError, porcelain.clone, self.repo.path, target_path, checkout=True, bare=True, errstream=errstream) def test_no_head_no_checkout(self): f1_1 = make_object(Blob, data=b'f1') commit_spec = [[1]] trees = {1: [(b'f1', f1_1), (b'f2', f1_1)]} (c1, ) = build_commit_graph(self.repo.object_store, commit_spec, trees) self.repo.refs[b"refs/heads/master"] = c1.id target_path = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, target_path) errstream = BytesIO() r = porcelain.clone( self.repo.path, target_path, checkout=True, errstream=errstream) r.close() + def test_no_head_no_checkout_outstream_errstream_autofallback(self): + f1_1 = make_object(Blob, data=b'f1') + commit_spec = [[1]] + trees = {1: [(b'f1', f1_1), (b'f2', f1_1)]} + + (c1, ) = build_commit_graph(self.repo.object_store, commit_spec, trees) + self.repo.refs[b"refs/heads/master"] = c1.id + target_path = tempfile.mkdtemp() + self.addCleanup(shutil.rmtree, target_path) + errstream = porcelain.NoneStream() + r = porcelain.clone( + self.repo.path, target_path, checkout=True, errstream=errstream) + r.close() + class InitTests(TestCase): def test_non_bare(self): repo_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, repo_dir) porcelain.init(repo_dir) def test_bare(self): repo_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, repo_dir) porcelain.init(repo_dir, bare=True) class AddTests(PorcelainTestCase): def test_add_default_paths(self): # create a file for initial commit fullpath = os.path.join(self.repo.path, 'blah') with open(fullpath, 'w') as f: f.write("\n") porcelain.add(repo=self.repo.path, paths=[fullpath]) porcelain.commit(repo=self.repo.path, message=b'test', author=b'test ', committer=b'test ') # Add a second test file and a file in a directory with open(os.path.join(self.repo.path, 'foo'), 'w') as f: f.write("\n") os.mkdir(os.path.join(self.repo.path, 'adir')) with open(os.path.join(self.repo.path, 'adir', 'afile'), 'w') as f: f.write("\n") cwd = os.getcwd() try: os.chdir(self.repo.path) porcelain.add(self.repo.path) finally: os.chdir(cwd) # Check that foo was added and nothing in .git was modified index = self.repo.open_index() self.assertEqual(sorted(index), [b'adir/afile', b'blah', b'foo']) def test_add_default_paths_subdir(self): os.mkdir(os.path.join(self.repo.path, 'foo')) with open(os.path.join(self.repo.path, 'blah'), 'w') as f: f.write("\n") with open(os.path.join(self.repo.path, 'foo', 'blie'), 'w') as f: f.write("\n") cwd = os.getcwd() try: os.chdir(os.path.join(self.repo.path, 'foo')) porcelain.add(repo=self.repo.path) porcelain.commit(repo=self.repo.path, message=b'test', author=b'test ', committer=b'test ') finally: os.chdir(cwd) index = self.repo.open_index() self.assertEqual(sorted(index), [b'foo/blie']) def test_add_file(self): fullpath = os.path.join(self.repo.path, 'foo') with open(fullpath, 'w') as f: f.write("BAR") porcelain.add(self.repo.path, paths=[fullpath]) self.assertIn(b"foo", self.repo.open_index()) def test_add_ignored(self): with open(os.path.join(self.repo.path, '.gitignore'), 'w') as f: f.write("foo") with open(os.path.join(self.repo.path, 'foo'), 'w') as f: f.write("BAR") with open(os.path.join(self.repo.path, 'bar'), 'w') as f: f.write("BAR") (added, ignored) = porcelain.add(self.repo.path, paths=[ os.path.join(self.repo.path, "foo"), os.path.join(self.repo.path, "bar")]) self.assertIn(b"bar", self.repo.open_index()) self.assertEqual(set(['bar']), set(added)) self.assertEqual(set(['foo']), ignored) def test_add_file_absolute_path(self): # Absolute paths are (not yet) supported with open(os.path.join(self.repo.path, 'foo'), 'w') as f: f.write("BAR") porcelain.add(self.repo, paths=[os.path.join(self.repo.path, "foo")]) self.assertIn(b"foo", self.repo.open_index()) def test_add_not_in_repo(self): with open(os.path.join(self.test_dir, 'foo'), 'w') as f: f.write("BAR") self.assertRaises( ValueError, porcelain.add, self.repo, paths=[os.path.join(self.test_dir, "foo")]) self.assertRaises( ValueError, porcelain.add, self.repo, paths=["../foo"]) self.assertEqual([], list(self.repo.open_index())) class RemoveTests(PorcelainTestCase): def test_remove_file(self): fullpath = os.path.join(self.repo.path, 'foo') with open(fullpath, 'w') as f: f.write("BAR") porcelain.add(self.repo.path, paths=[fullpath]) porcelain.commit(repo=self.repo, message=b'test', author=b'test ', committer=b'test ') self.assertTrue(os.path.exists(os.path.join(self.repo.path, 'foo'))) cwd = os.getcwd() try: os.chdir(self.repo.path) porcelain.remove(self.repo.path, paths=["foo"]) finally: os.chdir(cwd) self.assertFalse(os.path.exists(os.path.join(self.repo.path, 'foo'))) def test_remove_file_staged(self): fullpath = os.path.join(self.repo.path, 'foo') with open(fullpath, 'w') as f: f.write("BAR") cwd = os.getcwd() try: os.chdir(self.repo.path) porcelain.add(self.repo.path, paths=[fullpath]) self.assertRaises(Exception, porcelain.rm, self.repo.path, paths=["foo"]) finally: os.chdir(cwd) class LogTests(PorcelainTestCase): def test_simple(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]]) self.repo.refs[b"HEAD"] = c3.id outstream = StringIO() porcelain.log(self.repo.path, outstream=outstream) self.assertEqual(3, outstream.getvalue().count("-" * 50)) def test_max_entries(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]]) self.repo.refs[b"HEAD"] = c3.id outstream = StringIO() porcelain.log(self.repo.path, outstream=outstream, max_entries=1) self.assertEqual(1, outstream.getvalue().count("-" * 50)) class ShowTests(PorcelainTestCase): def test_nolist(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]]) self.repo.refs[b"HEAD"] = c3.id outstream = StringIO() porcelain.show(self.repo.path, objects=c3.id, outstream=outstream) self.assertTrue(outstream.getvalue().startswith("-" * 50)) def test_simple(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]]) self.repo.refs[b"HEAD"] = c3.id outstream = StringIO() porcelain.show(self.repo.path, objects=[c3.id], outstream=outstream) self.assertTrue(outstream.getvalue().startswith("-" * 50)) def test_blob(self): b = Blob.from_string(b"The Foo\n") self.repo.object_store.add_object(b) outstream = StringIO() porcelain.show(self.repo.path, objects=[b.id], outstream=outstream) self.assertEqual(outstream.getvalue(), "The Foo\n") def test_commit_no_parent(self): a = Blob.from_string(b"The Foo\n") ta = Tree() ta.add(b"somename", 0o100644, a.id) ca = make_commit(tree=ta.id) self.repo.object_store.add_objects([(a, None), (ta, None), (ca, None)]) outstream = StringIO() porcelain.show(self.repo.path, objects=[ca.id], outstream=outstream) self.assertMultiLineEqual(outstream.getvalue(), """\ -------------------------------------------------- commit: 344da06c1bb85901270b3e8875c988a027ec087d Author: Test Author Committer: Test Committer Date: Fri Jan 01 2010 00:00:00 +0000 Test message. diff --git /dev/null b/somename new mode 100644 index 0000000..ea5c7bf 100644 --- /dev/null +++ b/somename @@ -0,0 +1 @@ +The Foo """) def test_commit_with_change(self): a = Blob.from_string(b"The Foo\n") ta = Tree() ta.add(b"somename", 0o100644, a.id) ca = make_commit(tree=ta.id) b = Blob.from_string(b"The Bar\n") tb = Tree() tb.add(b"somename", 0o100644, b.id) cb = make_commit(tree=tb.id, parents=[ca.id]) self.repo.object_store.add_objects( [(a, None), (b, None), (ta, None), (tb, None), (ca, None), (cb, None)]) outstream = StringIO() porcelain.show(self.repo.path, objects=[cb.id], outstream=outstream) self.assertMultiLineEqual(outstream.getvalue(), """\ -------------------------------------------------- commit: 2c6b6c9cb72c130956657e1fdae58e5b103744fa Author: Test Author Committer: Test Committer Date: Fri Jan 01 2010 00:00:00 +0000 Test message. diff --git a/somename b/somename index ea5c7bf..fd38bcb 100644 --- a/somename +++ b/somename @@ -1 +1 @@ -The Foo +The Bar """) class SymbolicRefTests(PorcelainTestCase): def test_set_wrong_symbolic_ref(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]]) self.repo.refs[b"HEAD"] = c3.id self.assertRaises(ValueError, porcelain.symbolic_ref, self.repo.path, b'foobar') def test_set_force_wrong_symbolic_ref(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]]) self.repo.refs[b"HEAD"] = c3.id porcelain.symbolic_ref(self.repo.path, b'force_foobar', force=True) # test if we actually changed the file with self.repo.get_named_file('HEAD') as f: new_ref = f.read() self.assertEqual(new_ref, b'ref: refs/heads/force_foobar\n') def test_set_symbolic_ref(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]]) self.repo.refs[b"HEAD"] = c3.id porcelain.symbolic_ref(self.repo.path, b'master') def test_set_symbolic_ref_other_than_master(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]], attrs=dict(refs='develop')) self.repo.refs[b"HEAD"] = c3.id self.repo.refs[b"refs/heads/develop"] = c3.id porcelain.symbolic_ref(self.repo.path, b'develop') # test if we actually changed the file with self.repo.get_named_file('HEAD') as f: new_ref = f.read() self.assertEqual(new_ref, b'ref: refs/heads/develop\n') class DiffTreeTests(PorcelainTestCase): def test_empty(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]]) self.repo.refs[b"HEAD"] = c3.id outstream = BytesIO() porcelain.diff_tree(self.repo.path, c2.tree, c3.tree, outstream=outstream) self.assertEqual(outstream.getvalue(), b"") class CommitTreeTests(PorcelainTestCase): def test_simple(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]]) b = Blob() b.data = b"foo the bar" t = Tree() t.add(b"somename", 0o100644, b.id) self.repo.object_store.add_object(t) self.repo.object_store.add_object(b) sha = porcelain.commit_tree( self.repo.path, t.id, message=b"Withcommit.", author=b"Joe ", committer=b"Jane ") self.assertTrue(isinstance(sha, bytes)) self.assertEqual(len(sha), 40) class RevListTests(PorcelainTestCase): def test_simple(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]]) outstream = BytesIO() porcelain.rev_list( self.repo.path, [c3.id], outstream=outstream) self.assertEqual( c3.id + b"\n" + c2.id + b"\n" + c1.id + b"\n", outstream.getvalue()) class TagCreateTests(PorcelainTestCase): def test_annotated(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]]) self.repo.refs[b"HEAD"] = c3.id porcelain.tag_create(self.repo.path, b"tryme", b'foo ', b'bar', annotated=True) tags = self.repo.refs.as_dict(b"refs/tags") self.assertEqual(list(tags.keys()), [b"tryme"]) tag = self.repo[b'refs/tags/tryme'] self.assertTrue(isinstance(tag, Tag)) self.assertEqual(b"foo ", tag.tagger) self.assertEqual(b"bar", tag.message) self.assertLess(time.time() - tag.tag_time, 5) def test_unannotated(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]]) self.repo.refs[b"HEAD"] = c3.id porcelain.tag_create(self.repo.path, b"tryme", annotated=False) tags = self.repo.refs.as_dict(b"refs/tags") self.assertEqual(list(tags.keys()), [b"tryme"]) self.repo[b'refs/tags/tryme'] self.assertEqual(list(tags.values()), [self.repo.head()]) def test_unannotated_unicode(self): c1, c2, c3 = build_commit_graph( self.repo.object_store, [[1], [2, 1], [3, 1, 2]]) self.repo.refs[b"HEAD"] = c3.id porcelain.tag_create(self.repo.path, "tryme", annotated=False) tags = self.repo.refs.as_dict(b"refs/tags") self.assertEqual(list(tags.keys()), [b"tryme"]) self.repo[b'refs/tags/tryme'] self.assertEqual(list(tags.values()), [self.repo.head()]) class TagListTests(PorcelainTestCase): def test_empty(self): tags = porcelain.tag_list(self.repo.path) self.assertEqual([], tags) def test_simple(self): self.repo.refs[b"refs/tags/foo"] = b"aa" * 20 self.repo.refs[b"refs/tags/bar/bla"] = b"bb" * 20 tags = porcelain.tag_list(self.repo.path) self.assertEqual([b"bar/bla", b"foo"], tags) class TagDeleteTests(PorcelainTestCase): def test_simple(self): [c1] = build_commit_graph(self.repo.object_store, [[1]]) self.repo[b"HEAD"] = c1.id porcelain.tag_create(self.repo, b'foo') self.assertTrue(b"foo" in porcelain.tag_list(self.repo)) porcelain.tag_delete(self.repo, b'foo') self.assertFalse(b"foo" in porcelain.tag_list(self.repo)) class ResetTests(PorcelainTestCase): def test_hard_head(self): fullpath = os.path.join(self.repo.path, 'foo') with open(fullpath, 'w') as f: f.write("BAR") porcelain.add(self.repo.path, paths=[fullpath]) porcelain.commit(self.repo.path, message=b"Some message", committer=b"Jane ", author=b"John ") with open(os.path.join(self.repo.path, 'foo'), 'wb') as f: f.write(b"OOH") porcelain.reset(self.repo, "hard", b"HEAD") index = self.repo.open_index() changes = list(tree_changes(self.repo, index.commit(self.repo.object_store), self.repo[b'HEAD'].tree)) self.assertEqual([], changes) def test_hard_commit(self): fullpath = os.path.join(self.repo.path, 'foo') with open(fullpath, 'w') as f: f.write("BAR") porcelain.add(self.repo.path, paths=[fullpath]) sha = porcelain.commit(self.repo.path, message=b"Some message", committer=b"Jane ", author=b"John ") with open(fullpath, 'wb') as f: f.write(b"BAZ") porcelain.add(self.repo.path, paths=[fullpath]) porcelain.commit(self.repo.path, message=b"Some other message", committer=b"Jane ", author=b"John ") porcelain.reset(self.repo, "hard", sha) index = self.repo.open_index() changes = list(tree_changes(self.repo, index.commit(self.repo.object_store), self.repo[sha].tree)) self.assertEqual([], changes) class PushTests(PorcelainTestCase): def test_simple(self): """ Basic test of porcelain push where self.repo is the remote. First clone the remote, commit a file to the clone, then push the changes back to the remote. """ outstream = BytesIO() errstream = BytesIO() porcelain.commit(repo=self.repo.path, message=b'init', author=b'author ', committer=b'committer ') # Setup target repo cloned from temp test repo clone_path = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, clone_path) target_repo = porcelain.clone(self.repo.path, target=clone_path, errstream=errstream) try: self.assertEqual(target_repo[b'HEAD'], self.repo[b'HEAD']) finally: target_repo.close() # create a second file to be pushed back to origin handle, fullpath = tempfile.mkstemp(dir=clone_path) os.close(handle) porcelain.add(repo=clone_path, paths=[fullpath]) porcelain.commit(repo=clone_path, message=b'push', author=b'author ', committer=b'committer ') # Setup a non-checked out branch in the remote refs_path = b"refs/heads/foo" new_id = self.repo[b'HEAD'].id self.assertNotEqual(new_id, ZERO_SHA) self.repo.refs[refs_path] = new_id # Push to the remote porcelain.push(clone_path, self.repo.path, b"HEAD:" + refs_path, outstream=outstream, errstream=errstream) # Check that the target and source with Repo(clone_path) as r_clone: self.assertEqual({ b'HEAD': new_id, b'refs/heads/foo': r_clone[b'HEAD'].id, b'refs/heads/master': new_id, }, self.repo.get_refs()) self.assertEqual(r_clone[b'HEAD'].id, self.repo[refs_path].id) # Get the change in the target repo corresponding to the add # this will be in the foo branch. change = list(tree_changes(self.repo, self.repo[b'HEAD'].tree, self.repo[b'refs/heads/foo'].tree))[0] self.assertEqual(os.path.basename(fullpath), change.new.path.decode('ascii')) def test_delete(self): """Basic test of porcelain push, removing a branch. """ outstream = BytesIO() errstream = BytesIO() porcelain.commit(repo=self.repo.path, message=b'init', author=b'author ', committer=b'committer ') # Setup target repo cloned from temp test repo clone_path = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, clone_path) target_repo = porcelain.clone(self.repo.path, target=clone_path, errstream=errstream) target_repo.close() # Setup a non-checked out branch in the remote refs_path = b"refs/heads/foo" new_id = self.repo[b'HEAD'].id self.assertNotEqual(new_id, ZERO_SHA) self.repo.refs[refs_path] = new_id # Push to the remote porcelain.push(clone_path, self.repo.path, b":" + refs_path, outstream=outstream, errstream=errstream) self.assertEqual({ b'HEAD': new_id, b'refs/heads/master': new_id, }, self.repo.get_refs()) class PullTests(PorcelainTestCase): def setUp(self): super(PullTests, self).setUp() # create a file for initial commit handle, fullpath = tempfile.mkstemp(dir=self.repo.path) os.close(handle) porcelain.add(repo=self.repo.path, paths=fullpath) porcelain.commit(repo=self.repo.path, message=b'test', author=b'test ', committer=b'test ') # Setup target repo self.target_path = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, self.target_path) target_repo = porcelain.clone(self.repo.path, target=self.target_path, errstream=BytesIO()) target_repo.close() # create a second file to be pushed handle, fullpath = tempfile.mkstemp(dir=self.repo.path) os.close(handle) porcelain.add(repo=self.repo.path, paths=fullpath) porcelain.commit(repo=self.repo.path, message=b'test2', author=b'test2 ', committer=b'test2 ') self.assertTrue(b'refs/heads/master' in self.repo.refs) self.assertTrue(b'refs/heads/master' in target_repo.refs) def test_simple(self): outstream = BytesIO() errstream = BytesIO() # Pull changes into the cloned repo porcelain.pull(self.target_path, self.repo.path, b'refs/heads/master', outstream=outstream, errstream=errstream) # Check the target repo for pushed changes with Repo(self.target_path) as r: self.assertEqual(r[b'HEAD'].id, self.repo[b'HEAD'].id) def test_no_refspec(self): outstream = BytesIO() errstream = BytesIO() # Pull changes into the cloned repo porcelain.pull(self.target_path, self.repo.path, outstream=outstream, errstream=errstream) # Check the target repo for pushed changes with Repo(self.target_path) as r: self.assertEqual(r[b'HEAD'].id, self.repo[b'HEAD'].id) class StatusTests(PorcelainTestCase): def test_empty(self): results = porcelain.status(self.repo) self.assertEqual( {'add': [], 'delete': [], 'modify': []}, results.staged) self.assertEqual([], results.unstaged) def test_status_base(self): """Integration test for `status` functionality.""" # Commit a dummy file then modify it fullpath = os.path.join(self.repo.path, 'foo') with open(fullpath, 'w') as f: f.write('origstuff') porcelain.add(repo=self.repo.path, paths=[fullpath]) porcelain.commit(repo=self.repo.path, message=b'test status', author=b'author ', committer=b'committer ') # modify access and modify time of path os.utime(fullpath, (0, 0)) with open(fullpath, 'wb') as f: f.write(b'stuff') # Make a dummy file and stage it filename_add = 'bar' fullpath = os.path.join(self.repo.path, filename_add) with open(fullpath, 'w') as f: f.write('stuff') porcelain.add(repo=self.repo.path, paths=fullpath) results = porcelain.status(self.repo) self.assertEqual(results.staged['add'][0], filename_add.encode('ascii')) self.assertEqual(results.unstaged, [b'foo']) def test_status_all(self): del_path = os.path.join(self.repo.path, 'foo') mod_path = os.path.join(self.repo.path, 'bar') add_path = os.path.join(self.repo.path, 'baz') us_path = os.path.join(self.repo.path, 'blye') ut_path = os.path.join(self.repo.path, 'blyat') with open(del_path, 'w') as f: f.write('origstuff') with open(mod_path, 'w') as f: f.write('origstuff') with open(us_path, 'w') as f: f.write('origstuff') porcelain.add(repo=self.repo.path, paths=[del_path, mod_path, us_path]) porcelain.commit(repo=self.repo.path, message=b'test status', author=b'author ', committer=b'committer ') porcelain.remove(self.repo.path, [del_path]) with open(add_path, 'w') as f: f.write('origstuff') with open(mod_path, 'w') as f: f.write('more_origstuff') with open(us_path, 'w') as f: f.write('more_origstuff') porcelain.add(repo=self.repo.path, paths=[add_path, mod_path]) with open(us_path, 'w') as f: f.write('\norigstuff') with open(ut_path, 'w') as f: f.write('origstuff') results = porcelain.status(self.repo.path) self.assertDictEqual( {'add': [b'baz'], 'delete': [b'foo'], 'modify': [b'bar']}, results.staged) self.assertListEqual(results.unstaged, [b'blye']) self.assertListEqual(results.untracked, ['blyat']) def test_get_tree_changes_add(self): """Unit test for get_tree_changes add.""" # Make a dummy file, stage filename = 'bar' fullpath = os.path.join(self.repo.path, filename) with open(fullpath, 'w') as f: f.write('stuff') porcelain.add(repo=self.repo.path, paths=fullpath) porcelain.commit(repo=self.repo.path, message=b'test status', author=b'author ', committer=b'committer ') filename = 'foo' fullpath = os.path.join(self.repo.path, filename) with open(fullpath, 'w') as f: f.write('stuff') porcelain.add(repo=self.repo.path, paths=fullpath) changes = porcelain.get_tree_changes(self.repo.path) self.assertEqual(changes['add'][0], filename.encode('ascii')) self.assertEqual(len(changes['add']), 1) self.assertEqual(len(changes['modify']), 0) self.assertEqual(len(changes['delete']), 0) def test_get_tree_changes_modify(self): """Unit test for get_tree_changes modify.""" # Make a dummy file, stage, commit, modify filename = 'foo' fullpath = os.path.join(self.repo.path, filename) with open(fullpath, 'w') as f: f.write('stuff') porcelain.add(repo=self.repo.path, paths=fullpath) porcelain.commit(repo=self.repo.path, message=b'test status', author=b'author ', committer=b'committer ') with open(fullpath, 'w') as f: f.write('otherstuff') porcelain.add(repo=self.repo.path, paths=fullpath) changes = porcelain.get_tree_changes(self.repo.path) self.assertEqual(changes['modify'][0], filename.encode('ascii')) self.assertEqual(len(changes['add']), 0) self.assertEqual(len(changes['modify']), 1) self.assertEqual(len(changes['delete']), 0) def test_get_tree_changes_delete(self): """Unit test for get_tree_changes delete.""" # Make a dummy file, stage, commit, remove filename = 'foo' fullpath = os.path.join(self.repo.path, filename) with open(fullpath, 'w') as f: f.write('stuff') porcelain.add(repo=self.repo.path, paths=fullpath) porcelain.commit(repo=self.repo.path, message=b'test status', author=b'author ', committer=b'committer ') cwd = os.getcwd() try: os.chdir(self.repo.path) porcelain.remove(repo=self.repo.path, paths=[filename]) finally: os.chdir(cwd) changes = porcelain.get_tree_changes(self.repo.path) self.assertEqual(changes['delete'][0], filename.encode('ascii')) self.assertEqual(len(changes['add']), 0) self.assertEqual(len(changes['modify']), 0) self.assertEqual(len(changes['delete']), 1) def test_get_untracked_paths(self): with open(os.path.join(self.repo.path, '.gitignore'), 'w') as f: f.write('ignored\n') with open(os.path.join(self.repo.path, 'ignored'), 'w') as f: f.write('blah\n') with open(os.path.join(self.repo.path, 'notignored'), 'w') as f: f.write('blah\n') self.assertEqual( set(['ignored', 'notignored', '.gitignore']), set(porcelain.get_untracked_paths(self.repo.path, self.repo.path, self.repo.open_index()))) self.assertEqual(set(['.gitignore', 'notignored']), set(porcelain.status(self.repo).untracked)) self.assertEqual(set(['.gitignore', 'notignored', 'ignored']), set(porcelain.status(self.repo, ignored=True) .untracked)) def test_get_untracked_paths_nested(self): with open(os.path.join(self.repo.path, 'notignored'), 'w') as f: f.write('blah\n') subrepo = Repo.init(os.path.join(self.repo.path, 'nested'), mkdir=True) with open(os.path.join(subrepo.path, 'another'), 'w') as f: f.write('foo\n') self.assertEqual( set(['notignored']), set(porcelain.get_untracked_paths(self.repo.path, self.repo.path, self.repo.open_index()))) self.assertEqual( set(['another']), set(porcelain.get_untracked_paths(subrepo.path, subrepo.path, subrepo.open_index()))) # TODO(jelmer): Add test for dulwich.porcelain.daemon class UploadPackTests(PorcelainTestCase): """Tests for upload_pack.""" def test_upload_pack(self): outf = BytesIO() exitcode = porcelain.upload_pack( self.repo.path, BytesIO(b"0000"), outf) outlines = outf.getvalue().splitlines() self.assertEqual([b"0000"], outlines) self.assertEqual(0, exitcode) class ReceivePackTests(PorcelainTestCase): """Tests for receive_pack.""" def test_receive_pack(self): filename = 'foo' fullpath = os.path.join(self.repo.path, filename) with open(fullpath, 'w') as f: f.write('stuff') porcelain.add(repo=self.repo.path, paths=fullpath) self.repo.do_commit(message=b'test status', author=b'author ', committer=b'committer ', author_timestamp=1402354300, commit_timestamp=1402354300, author_timezone=0, commit_timezone=0) outf = BytesIO() exitcode = porcelain.receive_pack( self.repo.path, BytesIO(b"0000"), outf) outlines = outf.getvalue().splitlines() self.assertEqual([ b'0091319b56ce3aee2d489f759736a79cc552c9bb86d9 HEAD\x00 report-status ' # noqa: E501 b'delete-refs quiet ofs-delta side-band-64k ' b'no-done symref=HEAD:refs/heads/master', b'003f319b56ce3aee2d489f759736a79cc552c9bb86d9 refs/heads/master', b'0000'], outlines) self.assertEqual(0, exitcode) class BranchListTests(PorcelainTestCase): def test_standard(self): self.assertEqual(set([]), set(porcelain.branch_list(self.repo))) def test_new_branch(self): [c1] = build_commit_graph(self.repo.object_store, [[1]]) self.repo[b"HEAD"] = c1.id porcelain.branch_create(self.repo, b"foo") self.assertEqual( set([b"master", b"foo"]), set(porcelain.branch_list(self.repo))) class BranchCreateTests(PorcelainTestCase): def test_branch_exists(self): [c1] = build_commit_graph(self.repo.object_store, [[1]]) self.repo[b"HEAD"] = c1.id porcelain.branch_create(self.repo, b"foo") self.assertRaises(KeyError, porcelain.branch_create, self.repo, b"foo") porcelain.branch_create(self.repo, b"foo", force=True) def test_new_branch(self): [c1] = build_commit_graph(self.repo.object_store, [[1]]) self.repo[b"HEAD"] = c1.id porcelain.branch_create(self.repo, b"foo") self.assertEqual( set([b"master", b"foo"]), set(porcelain.branch_list(self.repo))) class BranchDeleteTests(PorcelainTestCase): def test_simple(self): [c1] = build_commit_graph(self.repo.object_store, [[1]]) self.repo[b"HEAD"] = c1.id porcelain.branch_create(self.repo, b'foo') self.assertTrue(b"foo" in porcelain.branch_list(self.repo)) porcelain.branch_delete(self.repo, b'foo') self.assertFalse(b"foo" in porcelain.branch_list(self.repo)) def test_simple_unicode(self): [c1] = build_commit_graph(self.repo.object_store, [[1]]) self.repo[b"HEAD"] = c1.id porcelain.branch_create(self.repo, 'foo') self.assertTrue(b"foo" in porcelain.branch_list(self.repo)) porcelain.branch_delete(self.repo, 'foo') self.assertFalse(b"foo" in porcelain.branch_list(self.repo)) class FetchTests(PorcelainTestCase): def test_simple(self): outstream = BytesIO() errstream = BytesIO() # create a file for initial commit handle, fullpath = tempfile.mkstemp(dir=self.repo.path) os.close(handle) porcelain.add(repo=self.repo.path, paths=fullpath) porcelain.commit(repo=self.repo.path, message=b'test', author=b'test ', committer=b'test ') # Setup target repo target_path = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, target_path) target_repo = porcelain.clone(self.repo.path, target=target_path, errstream=errstream) # create a second file to be pushed handle, fullpath = tempfile.mkstemp(dir=self.repo.path) os.close(handle) porcelain.add(repo=self.repo.path, paths=fullpath) porcelain.commit(repo=self.repo.path, message=b'test2', author=b'test2 ', committer=b'test2 ') self.assertFalse(self.repo[b'HEAD'].id in target_repo) target_repo.close() # Fetch changes into the cloned repo porcelain.fetch(target_path, self.repo.path, outstream=outstream, errstream=errstream) # Assert that fetch updated the local image of the remote self.assert_correct_remote_refs( target_repo.get_refs(), self.repo.get_refs()) # Check the target repo for pushed changes with Repo(target_path) as r: self.assertTrue(self.repo[b'HEAD'].id in r) def test_with_remote_name(self): remote_name = b'origin' outstream = BytesIO() errstream = BytesIO() # create a file for initial commit handle, fullpath = tempfile.mkstemp(dir=self.repo.path) os.close(handle) porcelain.add(repo=self.repo.path, paths=fullpath) porcelain.commit(repo=self.repo.path, message=b'test', author=b'test ', committer=b'test ') # Setup target repo target_path = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, target_path) target_repo = porcelain.clone(self.repo.path, target=target_path, errstream=errstream) # Capture current refs target_refs = target_repo.get_refs() # create a second file to be pushed handle, fullpath = tempfile.mkstemp(dir=self.repo.path) os.close(handle) porcelain.add(repo=self.repo.path, paths=fullpath) porcelain.commit(repo=self.repo.path, message=b'test2', author=b'test2 ', committer=b'test2 ') self.assertFalse(self.repo[b'HEAD'].id in target_repo) target_repo.close() # Fetch changes into the cloned repo porcelain.fetch(target_path, self.repo.path, remote_name=remote_name, outstream=outstream, errstream=errstream) # Assert that fetch updated the local image of the remote self.assert_correct_remote_refs( target_repo.get_refs(), self.repo.get_refs()) # Check the target repo for pushed changes, as well as updates # for the refs with Repo(target_path) as r: self.assertTrue(self.repo[b'HEAD'].id in r) self.assertNotEqual(self.repo.get_refs(), target_refs) def assert_correct_remote_refs( self, local_refs, remote_refs, remote_name=b'origin'): """Assert that known remote refs corresponds to actual remote refs.""" local_ref_prefix = b'refs/heads' remote_ref_prefix = b'refs/remotes/' + remote_name locally_known_remote_refs = { k[len(remote_ref_prefix) + 1:]: v for k, v in local_refs.items() if k.startswith(remote_ref_prefix)} normalized_remote_refs = { k[len(local_ref_prefix) + 1:]: v for k, v in remote_refs.items() if k.startswith(local_ref_prefix)} self.assertEqual(locally_known_remote_refs, normalized_remote_refs) class RepackTests(PorcelainTestCase): def test_empty(self): porcelain.repack(self.repo) def test_simple(self): handle, fullpath = tempfile.mkstemp(dir=self.repo.path) os.close(handle) porcelain.add(repo=self.repo.path, paths=fullpath) porcelain.repack(self.repo) class LsTreeTests(PorcelainTestCase): def test_empty(self): porcelain.commit(repo=self.repo.path, message=b'test status', author=b'author ', committer=b'committer ') f = StringIO() porcelain.ls_tree(self.repo, b"HEAD", outstream=f) self.assertEqual(f.getvalue(), "") def test_simple(self): # Commit a dummy file then modify it fullpath = os.path.join(self.repo.path, 'foo') with open(fullpath, 'w') as f: f.write('origstuff') porcelain.add(repo=self.repo.path, paths=[fullpath]) porcelain.commit(repo=self.repo.path, message=b'test status', author=b'author ', committer=b'committer ') f = StringIO() porcelain.ls_tree(self.repo, b"HEAD", outstream=f) self.assertEqual( f.getvalue(), '100644 blob 8b82634d7eae019850bb883f06abf428c58bc9aa\tfoo\n') def test_recursive(self): # Create a directory then write a dummy file in it dirpath = os.path.join(self.repo.path, 'adir') filepath = os.path.join(dirpath, 'afile') os.mkdir(dirpath) with open(filepath, 'w') as f: f.write('origstuff') porcelain.add(repo=self.repo.path, paths=[filepath]) porcelain.commit(repo=self.repo.path, message=b'test status', author=b'author ', committer=b'committer ') f = StringIO() porcelain.ls_tree(self.repo, b"HEAD", outstream=f) self.assertEqual( f.getvalue(), '40000 tree b145cc69a5e17693e24d8a7be0016ed8075de66d\tadir\n') f = StringIO() porcelain.ls_tree(self.repo, b"HEAD", outstream=f, recursive=True) self.assertEqual( f.getvalue(), '40000 tree b145cc69a5e17693e24d8a7be0016ed8075de66d\tadir\n' '100644 blob 8b82634d7eae019850bb883f06abf428c58bc9aa\tadir' '/afile\n') class LsRemoteTests(PorcelainTestCase): def test_empty(self): self.assertEqual({}, porcelain.ls_remote(self.repo.path)) def test_some(self): cid = porcelain.commit(repo=self.repo.path, message=b'test status', author=b'author ', committer=b'committer ') self.assertEqual({ b'refs/heads/master': cid, b'HEAD': cid}, porcelain.ls_remote(self.repo.path)) class LsFilesTests(PorcelainTestCase): def test_empty(self): self.assertEqual([], list(porcelain.ls_files(self.repo))) def test_simple(self): # Commit a dummy file then modify it fullpath = os.path.join(self.repo.path, 'foo') with open(fullpath, 'w') as f: f.write('origstuff') porcelain.add(repo=self.repo.path, paths=[fullpath]) self.assertEqual([b'foo'], list(porcelain.ls_files(self.repo))) class RemoteAddTests(PorcelainTestCase): def test_new(self): porcelain.remote_add( self.repo, 'jelmer', 'git://jelmer.uk/code/dulwich') c = self.repo.get_config() self.assertEqual( c.get((b'remote', b'jelmer'), b'url'), b'git://jelmer.uk/code/dulwich') def test_exists(self): porcelain.remote_add( self.repo, 'jelmer', 'git://jelmer.uk/code/dulwich') self.assertRaises(porcelain.RemoteExists, porcelain.remote_add, self.repo, 'jelmer', 'git://jelmer.uk/code/dulwich') class CheckIgnoreTests(PorcelainTestCase): def test_check_ignored(self): with open(os.path.join(self.repo.path, '.gitignore'), 'w') as f: f.write('foo') foo_path = os.path.join(self.repo.path, 'foo') with open(foo_path, 'w') as f: f.write('BAR') bar_path = os.path.join(self.repo.path, 'bar') with open(bar_path, 'w') as f: f.write('BAR') self.assertEqual( ['foo'], list(porcelain.check_ignore(self.repo, [foo_path]))) self.assertEqual( [], list(porcelain.check_ignore(self.repo, [bar_path]))) def test_check_added_abs(self): path = os.path.join(self.repo.path, 'foo') with open(path, 'w') as f: f.write('BAR') self.repo.stage(['foo']) with open(os.path.join(self.repo.path, '.gitignore'), 'w') as f: f.write('foo\n') self.assertEqual( [], list(porcelain.check_ignore(self.repo, [path]))) self.assertEqual( ['foo'], list(porcelain.check_ignore(self.repo, [path], no_index=True))) def test_check_added_rel(self): with open(os.path.join(self.repo.path, 'foo'), 'w') as f: f.write('BAR') self.repo.stage(['foo']) with open(os.path.join(self.repo.path, '.gitignore'), 'w') as f: f.write('foo\n') cwd = os.getcwd() os.mkdir(os.path.join(self.repo.path, 'bar')) os.chdir(os.path.join(self.repo.path, 'bar')) try: self.assertEqual( list(porcelain.check_ignore(self.repo, ['../foo'])), []) self.assertEqual(['../foo'], list( porcelain.check_ignore(self.repo, ['../foo'], no_index=True))) finally: os.chdir(cwd) class UpdateHeadTests(PorcelainTestCase): def test_set_to_branch(self): [c1] = build_commit_graph(self.repo.object_store, [[1]]) self.repo.refs[b"refs/heads/blah"] = c1.id porcelain.update_head(self.repo, "blah") self.assertEqual(c1.id, self.repo.head()) self.assertEqual(b'ref: refs/heads/blah', self.repo.refs.read_ref(b'HEAD')) def test_set_to_branch_detached(self): [c1] = build_commit_graph(self.repo.object_store, [[1]]) self.repo.refs[b"refs/heads/blah"] = c1.id porcelain.update_head(self.repo, "blah", detached=True) self.assertEqual(c1.id, self.repo.head()) self.assertEqual(c1.id, self.repo.refs.read_ref(b'HEAD')) def test_set_to_commit_detached(self): [c1] = build_commit_graph(self.repo.object_store, [[1]]) self.repo.refs[b"refs/heads/blah"] = c1.id porcelain.update_head(self.repo, c1.id, detached=True) self.assertEqual(c1.id, self.repo.head()) self.assertEqual(c1.id, self.repo.refs.read_ref(b'HEAD')) def test_set_new_branch(self): [c1] = build_commit_graph(self.repo.object_store, [[1]]) self.repo.refs[b"refs/heads/blah"] = c1.id porcelain.update_head(self.repo, "blah", new_branch="bar") self.assertEqual(c1.id, self.repo.head()) self.assertEqual(b'ref: refs/heads/bar', self.repo.refs.read_ref(b'HEAD')) class MailmapTests(PorcelainTestCase): def test_no_mailmap(self): self.assertEqual( b'Jelmer Vernooij ', porcelain.check_mailmap( self.repo, b'Jelmer Vernooij ')) def test_mailmap_lookup(self): with open(os.path.join(self.repo.path, '.mailmap'), 'wb') as f: f.write(b"""\ Jelmer Vernooij """) self.assertEqual( b'Jelmer Vernooij ', porcelain.check_mailmap( self.repo, b'Jelmer Vernooij ')) class FsckTests(PorcelainTestCase): def test_none(self): self.assertEqual( [], list(porcelain.fsck(self.repo))) def test_git_dir(self): obj = Tree() a = Blob() a.data = b"foo" obj.add(b".git", 0o100644, a.id) self.repo.object_store.add_objects( [(a, None), (obj, None)]) self.assertEqual( [(obj.id, 'invalid name .git')], [(sha, str(e)) for (sha, e) in porcelain.fsck(self.repo)]) class DescribeTests(PorcelainTestCase): def test_no_commits(self): self.assertRaises(KeyError, porcelain.describe, self.repo.path) def test_single_commit(self): fullpath = os.path.join(self.repo.path, 'foo') with open(fullpath, 'w') as f: f.write("BAR") porcelain.add(repo=self.repo.path, paths=[fullpath]) sha = porcelain.commit( self.repo.path, message=b"Some message", author=b"Joe ", committer=b"Bob ") self.assertEqual( 'g{}'.format(sha[:7].decode('ascii')), porcelain.describe(self.repo.path)) def test_tag(self): fullpath = os.path.join(self.repo.path, 'foo') with open(fullpath, 'w') as f: f.write("BAR") porcelain.add(repo=self.repo.path, paths=[fullpath]) porcelain.commit( self.repo.path, message=b"Some message", author=b"Joe ", committer=b"Bob ") porcelain.tag_create(self.repo.path, b"tryme", b'foo ', b'bar', annotated=True) self.assertEqual( "tryme", porcelain.describe(self.repo.path)) def test_tag_and_commit(self): fullpath = os.path.join(self.repo.path, 'foo') with open(fullpath, 'w') as f: f.write("BAR") porcelain.add(repo=self.repo.path, paths=[fullpath]) porcelain.commit( self.repo.path, message=b"Some message", author=b"Joe ", committer=b"Bob ") porcelain.tag_create(self.repo.path, b"tryme", b'foo ', b'bar', annotated=True) with open(fullpath, 'w') as f: f.write("BAR2") porcelain.add(repo=self.repo.path, paths=[fullpath]) sha = porcelain.commit( self.repo.path, message=b"Some message", author=b"Joe ", committer=b"Bob ") self.assertEqual( 'tryme-1-g{}'.format(sha[:7].decode('ascii')), porcelain.describe(self.repo.path)) class HelperTests(PorcelainTestCase): + def test_path_to_tree_path_base(self): self.assertEqual( b'bar', porcelain.path_to_tree_path('/home/foo', '/home/foo/bar')) self.assertEqual(b'bar', porcelain.path_to_tree_path('.', './bar')) self.assertEqual(b'bar', porcelain.path_to_tree_path('.', 'bar')) cwd = os.getcwd() self.assertEqual( b'bar', porcelain.path_to_tree_path('.', os.path.join(cwd, 'bar'))) self.assertEqual(b'bar', porcelain.path_to_tree_path(cwd, 'bar')) def test_path_to_tree_path_syntax(self): self.assertEqual(b'bar', porcelain.path_to_tree_path(b'.', './bar')) self.assertEqual(b'bar', porcelain.path_to_tree_path('.', b'./bar')) self.assertEqual(b'bar', porcelain.path_to_tree_path(b'.', b'./bar')) def test_path_to_tree_path_error(self): with self.assertRaises(ValueError): porcelain.path_to_tree_path('/home/foo/', '/home/bar/baz') def test_path_to_tree_path_rel(self): cwd = os.getcwd() os.mkdir(os.path.join(self.repo.path, 'foo')) os.mkdir(os.path.join(self.repo.path, 'foo/bar')) try: os.chdir(os.path.join(self.repo.path, 'foo/bar')) self.assertEqual(b'bar/baz', porcelain.path_to_tree_path( '..', 'baz')) self.assertEqual(b'bar/baz', porcelain.path_to_tree_path( os.path.join(os.getcwd(), '..'), os.path.join(os.getcwd(), 'baz'))) self.assertEqual(b'bar/baz', porcelain.path_to_tree_path( '..', os.path.join(os.getcwd(), 'baz'))) self.assertEqual(b'bar/baz', porcelain.path_to_tree_path( os.path.join(os.getcwd(), '..'), 'baz')) finally: os.chdir(cwd) + + +class GetObjectBypathTests(PorcelainTestCase): + + def test_simple(self): + fullpath = os.path.join(self.repo.path, 'foo') + with open(fullpath, 'w') as f: + f.write("BAR") + porcelain.add(repo=self.repo.path, paths=[fullpath]) + porcelain.commit( + self.repo.path, message=b"Some message", + author=b"Joe ", + committer=b"Bob ") + self.assertEqual( + b"BAR", + porcelain.get_object_by_path(self.repo, 'foo').data) + + def test_missing(self): + self.assertRaises( + KeyError, + porcelain.get_object_by_path, self.repo, 'foo') + + +class WriteTreeTests(PorcelainTestCase): + + def test_simple(self): + fullpath = os.path.join(self.repo.path, 'foo') + with open(fullpath, 'w') as f: + f.write("BAR") + porcelain.add(repo=self.repo.path, paths=[fullpath]) + self.assertEqual( + b'd2092c8a9f311f0311083bf8d177f2ca0ab5b241', + porcelain.write_tree(self.repo)) diff --git a/dulwich/tests/test_refs.py b/dulwich/tests/test_refs.py index ee9611f7..cc31a0aa 100644 --- a/dulwich/tests/test_refs.py +++ b/dulwich/tests/test_refs.py @@ -1,621 +1,658 @@ # test_refs.py -- tests for refs.py # encoding: utf-8 # Copyright (C) 2013 Jelmer Vernooij # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """Tests for dulwich.refs.""" from io import BytesIO import os import sys import tempfile from dulwich import errors from dulwich.file import ( GitFile, ) from dulwich.objects import ZERO_SHA from dulwich.refs import ( DictRefsContainer, InfoRefsContainer, check_ref_format, _split_ref_line, parse_symref_value, read_packed_refs_with_peeled, read_packed_refs, strip_peeled_refs, write_packed_refs, ) from dulwich.repo import Repo from dulwich.tests import ( SkipTest, TestCase, ) from dulwich.tests.utils import ( open_repo, tear_down_repo, ) class CheckRefFormatTests(TestCase): """Tests for the check_ref_format function. These are the same tests as in the git test suite. """ def test_valid(self): self.assertTrue(check_ref_format(b'heads/foo')) self.assertTrue(check_ref_format(b'foo/bar/baz')) self.assertTrue(check_ref_format(b'refs///heads/foo')) self.assertTrue(check_ref_format(b'foo./bar')) self.assertTrue(check_ref_format(b'heads/foo@bar')) self.assertTrue(check_ref_format(b'heads/fix.lock.error')) def test_invalid(self): self.assertFalse(check_ref_format(b'foo')) self.assertFalse(check_ref_format(b'heads/foo/')) self.assertFalse(check_ref_format(b'./foo')) self.assertFalse(check_ref_format(b'.refs/foo')) self.assertFalse(check_ref_format(b'heads/foo..bar')) self.assertFalse(check_ref_format(b'heads/foo?bar')) self.assertFalse(check_ref_format(b'heads/foo.lock')) self.assertFalse(check_ref_format(b'heads/v@{ation')) self.assertFalse(check_ref_format(b'heads/foo\bar')) ONES = b'1' * 40 TWOS = b'2' * 40 THREES = b'3' * 40 FOURS = b'4' * 40 class PackedRefsFileTests(TestCase): def test_split_ref_line_errors(self): self.assertRaises(errors.PackedRefsException, _split_ref_line, b'singlefield') self.assertRaises(errors.PackedRefsException, _split_ref_line, b'badsha name') self.assertRaises(errors.PackedRefsException, _split_ref_line, ONES + b' bad/../refname') def test_read_without_peeled(self): f = BytesIO(b'\n'.join([ b'# comment', ONES + b' ref/1', TWOS + b' ref/2'])) self.assertEqual([(ONES, b'ref/1'), (TWOS, b'ref/2')], list(read_packed_refs(f))) def test_read_without_peeled_errors(self): f = BytesIO(b'\n'.join([ ONES + b' ref/1', b'^' + TWOS])) self.assertRaises(errors.PackedRefsException, list, read_packed_refs(f)) def test_read_with_peeled(self): f = BytesIO(b'\n'.join([ ONES + b' ref/1', TWOS + b' ref/2', b'^' + THREES, FOURS + b' ref/4'])) self.assertEqual([ (ONES, b'ref/1', None), (TWOS, b'ref/2', THREES), (FOURS, b'ref/4', None), ], list(read_packed_refs_with_peeled(f))) def test_read_with_peeled_errors(self): f = BytesIO(b'\n'.join([ b'^' + TWOS, ONES + b' ref/1'])) self.assertRaises(errors.PackedRefsException, list, read_packed_refs(f)) f = BytesIO(b'\n'.join([ ONES + b' ref/1', b'^' + TWOS, b'^' + THREES])) self.assertRaises(errors.PackedRefsException, list, read_packed_refs(f)) def test_write_with_peeled(self): f = BytesIO() write_packed_refs(f, {b'ref/1': ONES, b'ref/2': TWOS}, {b'ref/1': THREES}) self.assertEqual( b'\n'.join([b'# pack-refs with: peeled', ONES + b' ref/1', b'^' + THREES, TWOS + b' ref/2']) + b'\n', f.getvalue()) def test_write_without_peeled(self): f = BytesIO() write_packed_refs(f, {b'ref/1': ONES, b'ref/2': TWOS}) self.assertEqual(b'\n'.join([ONES + b' ref/1', TWOS + b' ref/2']) + b'\n', f.getvalue()) # Dict of refs that we expect all RefsContainerTests subclasses to define. _TEST_REFS = { b'HEAD': b'42d06bd4b77fed026b154d16493e5deab78f02ec', b'refs/heads/40-char-ref-aaaaaaaaaaaaaaaaaa': b'42d06bd4b77fed026b154d16493e5deab78f02ec', b'refs/heads/master': b'42d06bd4b77fed026b154d16493e5deab78f02ec', b'refs/heads/packed': b'42d06bd4b77fed026b154d16493e5deab78f02ec', b'refs/tags/refs-0.1': b'df6800012397fb85c56e7418dd4eb9405dee075c', b'refs/tags/refs-0.2': b'3ec9c43c84ff242e3ef4a9fc5bc111fd780a76a8', b'refs/heads/loop': b'ref: refs/heads/loop', } class RefsContainerTests(object): def test_keys(self): actual_keys = set(self._refs.keys()) self.assertEqual(set(self._refs.allkeys()), actual_keys) self.assertEqual(set(_TEST_REFS.keys()), actual_keys) actual_keys = self._refs.keys(b'refs/heads') actual_keys.discard(b'loop') self.assertEqual( [b'40-char-ref-aaaaaaaaaaaaaaaaaa', b'master', b'packed'], sorted(actual_keys)) self.assertEqual([b'refs-0.1', b'refs-0.2'], sorted(self._refs.keys(b'refs/tags'))) def test_as_dict(self): # refs/heads/loop does not show up even if it exists expected_refs = dict(_TEST_REFS) del expected_refs[b'refs/heads/loop'] self.assertEqual(expected_refs, self._refs.as_dict()) def test_get_symrefs(self): self._refs.set_symbolic_ref(b'refs/heads/src', b'refs/heads/dst') symrefs = self._refs.get_symrefs() if b'HEAD' in symrefs: symrefs.pop(b'HEAD') self.assertEqual({b'refs/heads/src': b'refs/heads/dst', b'refs/heads/loop': b'refs/heads/loop'}, symrefs) def test_setitem(self): self._refs[b'refs/some/ref'] = ( b'42d06bd4b77fed026b154d16493e5deab78f02ec') self.assertEqual(b'42d06bd4b77fed026b154d16493e5deab78f02ec', self._refs[b'refs/some/ref']) self.assertRaises( errors.RefFormatError, self._refs.__setitem__, b'notrefs/foo', b'42d06bd4b77fed026b154d16493e5deab78f02ec') def test_set_if_equals(self): nines = b'9' * 40 self.assertFalse(self._refs.set_if_equals(b'HEAD', b'c0ffee', nines)) self.assertEqual(b'42d06bd4b77fed026b154d16493e5deab78f02ec', self._refs[b'HEAD']) self.assertTrue(self._refs.set_if_equals( b'HEAD', b'42d06bd4b77fed026b154d16493e5deab78f02ec', nines)) self.assertEqual(nines, self._refs[b'HEAD']) self.assertTrue(self._refs.set_if_equals(b'refs/heads/master', None, nines)) self.assertEqual(nines, self._refs[b'refs/heads/master']) self.assertTrue(self._refs.set_if_equals( b'refs/heads/nonexistant', ZERO_SHA, nines)) self.assertEqual(nines, self._refs[b'refs/heads/nonexistant']) def test_add_if_new(self): nines = b'9' * 40 self.assertFalse(self._refs.add_if_new(b'refs/heads/master', nines)) self.assertEqual(b'42d06bd4b77fed026b154d16493e5deab78f02ec', self._refs[b'refs/heads/master']) self.assertTrue(self._refs.add_if_new(b'refs/some/ref', nines)) self.assertEqual(nines, self._refs[b'refs/some/ref']) def test_set_symbolic_ref(self): self._refs.set_symbolic_ref(b'refs/heads/symbolic', b'refs/heads/master') self.assertEqual(b'ref: refs/heads/master', self._refs.read_loose_ref(b'refs/heads/symbolic')) self.assertEqual(b'42d06bd4b77fed026b154d16493e5deab78f02ec', self._refs[b'refs/heads/symbolic']) def test_set_symbolic_ref_overwrite(self): nines = b'9' * 40 self.assertFalse(b'refs/heads/symbolic' in self._refs) self._refs[b'refs/heads/symbolic'] = nines self.assertEqual(nines, self._refs.read_loose_ref(b'refs/heads/symbolic')) self._refs.set_symbolic_ref(b'refs/heads/symbolic', b'refs/heads/master') self.assertEqual(b'ref: refs/heads/master', self._refs.read_loose_ref(b'refs/heads/symbolic')) self.assertEqual(b'42d06bd4b77fed026b154d16493e5deab78f02ec', self._refs[b'refs/heads/symbolic']) def test_check_refname(self): self._refs._check_refname(b'HEAD') self._refs._check_refname(b'refs/stash') self._refs._check_refname(b'refs/heads/foo') self.assertRaises(errors.RefFormatError, self._refs._check_refname, b'refs') self.assertRaises(errors.RefFormatError, self._refs._check_refname, b'notrefs/foo') def test_contains(self): self.assertTrue(b'refs/heads/master' in self._refs) self.assertFalse(b'refs/heads/bar' in self._refs) def test_delitem(self): self.assertEqual(b'42d06bd4b77fed026b154d16493e5deab78f02ec', self._refs[b'refs/heads/master']) del self._refs[b'refs/heads/master'] self.assertRaises(KeyError, lambda: self._refs[b'refs/heads/master']) def test_remove_if_equals(self): self.assertFalse(self._refs.remove_if_equals(b'HEAD', b'c0ffee')) self.assertEqual(b'42d06bd4b77fed026b154d16493e5deab78f02ec', self._refs[b'HEAD']) self.assertTrue(self._refs.remove_if_equals( b'refs/tags/refs-0.2', b'3ec9c43c84ff242e3ef4a9fc5bc111fd780a76a8')) self.assertTrue(self._refs.remove_if_equals( b'refs/tags/refs-0.2', ZERO_SHA)) self.assertFalse(b'refs/tags/refs-0.2' in self._refs) class DictRefsContainerTests(RefsContainerTests, TestCase): def setUp(self): TestCase.setUp(self) self._refs = DictRefsContainer(dict(_TEST_REFS)) def test_invalid_refname(self): # FIXME: Move this test into RefsContainerTests, but requires # some way of injecting invalid refs. self._refs._refs[b'refs/stash'] = b'00' * 20 expected_refs = dict(_TEST_REFS) del expected_refs[b'refs/heads/loop'] expected_refs[b'refs/stash'] = b'00' * 20 self.assertEqual(expected_refs, self._refs.as_dict()) class DiskRefsContainerTests(RefsContainerTests, TestCase): def setUp(self): TestCase.setUp(self) self._repo = open_repo('refs.git') self.addCleanup(tear_down_repo, self._repo) self._refs = self._repo.refs def test_get_packed_refs(self): self.assertEqual({ b'refs/heads/packed': b'42d06bd4b77fed026b154d16493e5deab78f02ec', b'refs/tags/refs-0.1': b'df6800012397fb85c56e7418dd4eb9405dee075c', }, self._refs.get_packed_refs()) def test_get_peeled_not_packed(self): # not packed self.assertEqual(None, self._refs.get_peeled(b'refs/tags/refs-0.2')) self.assertEqual(b'3ec9c43c84ff242e3ef4a9fc5bc111fd780a76a8', self._refs[b'refs/tags/refs-0.2']) # packed, known not peelable self.assertEqual(self._refs[b'refs/heads/packed'], self._refs.get_peeled(b'refs/heads/packed')) # packed, peeled self.assertEqual(b'42d06bd4b77fed026b154d16493e5deab78f02ec', self._refs.get_peeled(b'refs/tags/refs-0.1')) def test_setitem(self): RefsContainerTests.test_setitem(self) - f = open(os.path.join(self._refs.path, b'refs', b'some', b'ref'), 'rb') - self.assertEqual(b'42d06bd4b77fed026b154d16493e5deab78f02ec', - f.read()[:40]) - f.close() + path = os.path.join(self._refs.path, b'refs', b'some', b'ref') + with open(path, 'rb') as f: + self.assertEqual(b'42d06bd4b77fed026b154d16493e5deab78f02ec', + f.read()[:40]) + + self.assertRaises( + OSError, self._refs.__setitem__, + b'refs/some/ref/sub', b'42d06bd4b77fed026b154d16493e5deab78f02ec') + + def test_setitem_packed(self): + with open(os.path.join(self._refs.path, b'packed-refs'), 'w') as f: + f.write('# pack-refs with: peeled fully-peeled sorted \n') + f.write( + '42d06bd4b77fed026b154d16493e5deab78f02ec refs/heads/packed\n') + + # It's allowed to set a new ref on a packed ref, the new ref will be + # placed outside on refs/ + self._refs[b'refs/heads/packed'] = ( + b'3ec9c43c84ff242e3ef4a9fc5bc111fd780a76a8' + ) + packed_ref_path = os.path.join( + self._refs.path, b'refs', b'heads', b'packed') + with open(packed_ref_path, 'rb') as f: + self.assertEqual( + b'3ec9c43c84ff242e3ef4a9fc5bc111fd780a76a8', + f.read()[:40]) + + self.assertRaises( + OSError, self._refs.__setitem__, + b'refs/heads/packed/sub', + b'42d06bd4b77fed026b154d16493e5deab78f02ec') def test_setitem_symbolic(self): ones = b'1' * 40 self._refs[b'HEAD'] = ones self.assertEqual(ones, self._refs[b'HEAD']) # ensure HEAD was not modified f = open(os.path.join(self._refs.path, b'HEAD'), 'rb') v = next(iter(f)).rstrip(b'\n\r') f.close() self.assertEqual(b'ref: refs/heads/master', v) # ensure the symbolic link was written through f = open(os.path.join(self._refs.path, b'refs', b'heads', b'master'), 'rb') self.assertEqual(ones, f.read()[:40]) f.close() def test_set_if_equals(self): RefsContainerTests.test_set_if_equals(self) # ensure symref was followed self.assertEqual(b'9' * 40, self._refs[b'refs/heads/master']) # ensure lockfile was deleted self.assertFalse(os.path.exists( os.path.join(self._refs.path, b'refs', b'heads', b'master.lock'))) self.assertFalse(os.path.exists( os.path.join(self._refs.path, b'HEAD.lock'))) def test_add_if_new_packed(self): # don't overwrite packed ref self.assertFalse(self._refs.add_if_new(b'refs/tags/refs-0.1', b'9' * 40)) self.assertEqual(b'df6800012397fb85c56e7418dd4eb9405dee075c', self._refs[b'refs/tags/refs-0.1']) def test_add_if_new_symbolic(self): # Use an empty repo instead of the default. repo_dir = os.path.join(tempfile.mkdtemp(), 'test') os.makedirs(repo_dir) repo = Repo.init(repo_dir) self.addCleanup(tear_down_repo, repo) refs = repo.refs nines = b'9' * 40 self.assertEqual(b'ref: refs/heads/master', refs.read_ref(b'HEAD')) self.assertFalse(b'refs/heads/master' in refs) self.assertTrue(refs.add_if_new(b'HEAD', nines)) self.assertEqual(b'ref: refs/heads/master', refs.read_ref(b'HEAD')) self.assertEqual(nines, refs[b'HEAD']) self.assertEqual(nines, refs[b'refs/heads/master']) self.assertFalse(refs.add_if_new(b'HEAD', b'1' * 40)) self.assertEqual(nines, refs[b'HEAD']) self.assertEqual(nines, refs[b'refs/heads/master']) def test_follow(self): self.assertEqual(([b'HEAD', b'refs/heads/master'], b'42d06bd4b77fed026b154d16493e5deab78f02ec'), self._refs.follow(b'HEAD')) self.assertEqual(([b'refs/heads/master'], b'42d06bd4b77fed026b154d16493e5deab78f02ec'), self._refs.follow(b'refs/heads/master')) self.assertRaises(KeyError, self._refs.follow, b'refs/heads/loop') def test_delitem(self): RefsContainerTests.test_delitem(self) ref_file = os.path.join(self._refs.path, b'refs', b'heads', b'master') self.assertFalse(os.path.exists(ref_file)) self.assertFalse(b'refs/heads/master' in self._refs.get_packed_refs()) def test_delitem_symbolic(self): self.assertEqual(b'ref: refs/heads/master', self._refs.read_loose_ref(b'HEAD')) del self._refs[b'HEAD'] self.assertRaises(KeyError, lambda: self._refs[b'HEAD']) self.assertEqual(b'42d06bd4b77fed026b154d16493e5deab78f02ec', self._refs[b'refs/heads/master']) self.assertFalse( os.path.exists(os.path.join(self._refs.path, b'HEAD'))) def test_remove_if_equals_symref(self): # HEAD is a symref, so shouldn't equal its dereferenced value self.assertFalse(self._refs.remove_if_equals( b'HEAD', b'42d06bd4b77fed026b154d16493e5deab78f02ec')) self.assertTrue(self._refs.remove_if_equals( b'refs/heads/master', b'42d06bd4b77fed026b154d16493e5deab78f02ec')) self.assertRaises(KeyError, lambda: self._refs[b'refs/heads/master']) # HEAD is now a broken symref self.assertRaises(KeyError, lambda: self._refs[b'HEAD']) self.assertEqual(b'ref: refs/heads/master', self._refs.read_loose_ref(b'HEAD')) self.assertFalse(os.path.exists( os.path.join(self._refs.path, b'refs', b'heads', b'master.lock'))) self.assertFalse(os.path.exists( os.path.join(self._refs.path, b'HEAD.lock'))) def test_remove_packed_without_peeled(self): refs_file = os.path.join(self._repo.path, 'packed-refs') f = GitFile(refs_file) refs_data = f.read() f.close() f = GitFile(refs_file, 'wb') f.write(b'\n'.join(l for l in refs_data.split(b'\n') if not l or l[0] not in b'#^')) f.close() self._repo = Repo(self._repo.path) refs = self._repo.refs self.assertTrue(refs.remove_if_equals( b'refs/heads/packed', b'42d06bd4b77fed026b154d16493e5deab78f02ec')) def test_remove_if_equals_packed(self): # test removing ref that is only packed self.assertEqual(b'df6800012397fb85c56e7418dd4eb9405dee075c', self._refs[b'refs/tags/refs-0.1']) self.assertTrue( self._refs.remove_if_equals( b'refs/tags/refs-0.1', b'df6800012397fb85c56e7418dd4eb9405dee075c')) self.assertRaises(KeyError, lambda: self._refs[b'refs/tags/refs-0.1']) def test_remove_parent(self): self._refs[b'refs/heads/foo/bar'] = ( b'df6800012397fb85c56e7418dd4eb9405dee075c' ) del self._refs[b'refs/heads/foo/bar'] ref_file = os.path.join( self._refs.path, b'refs', b'heads', b'foo', b'bar', ) self.assertFalse(os.path.exists(ref_file)) ref_file = os.path.join(self._refs.path, b'refs', b'heads', b'foo') self.assertFalse(os.path.exists(ref_file)) ref_file = os.path.join(self._refs.path, b'refs', b'heads') self.assertTrue(os.path.exists(ref_file)) self._refs[b'refs/heads/foo'] = ( b'df6800012397fb85c56e7418dd4eb9405dee075c' ) def test_read_ref(self): self.assertEqual(b'ref: refs/heads/master', self._refs.read_ref(b'HEAD')) self.assertEqual(b'42d06bd4b77fed026b154d16493e5deab78f02ec', self._refs.read_ref(b'refs/heads/packed')) self.assertEqual(None, self._refs.read_ref(b'nonexistant')) + def test_read_loose_ref(self): + self._refs[b'refs/heads/foo'] = ( + b'df6800012397fb85c56e7418dd4eb9405dee075c' + ) + + self.assertEqual(None, self._refs.read_ref(b'refs/heads/foo/bar')) + def test_non_ascii(self): try: encoded_ref = u'refs/tags/schön'.encode( sys.getfilesystemencoding()) except UnicodeEncodeError: raise SkipTest( "filesystem encoding doesn't support special character") p = os.path.join( self._repo.path.encode(sys.getfilesystemencoding()), encoded_ref) with open(p, 'w') as f: f.write('00' * 20) expected_refs = dict(_TEST_REFS) expected_refs[encoded_ref] = b'00' * 20 del expected_refs[b'refs/heads/loop'] self.assertEqual(expected_refs, self._repo.get_refs()) def test_cyrillic(self): + if sys.platform == 'win32': + raise SkipTest( + "filesystem encoding doesn't support arbitrary bytes") # reported in https://github.com/dulwich/dulwich/issues/608 name = b'\xcd\xee\xe2\xe0\xff\xe2\xe5\xf2\xea\xe01' encoded_ref = b'refs/heads/' + name with open(os.path.join( self._repo.path.encode( sys.getfilesystemencoding()), encoded_ref), 'w') as f: f.write('00' * 20) expected_refs = set(_TEST_REFS.keys()) expected_refs.add(encoded_ref) self.assertEqual(expected_refs, set(self._repo.refs.allkeys())) self.assertEqual({r[len(b'refs/'):] for r in expected_refs if r.startswith(b'refs/')}, set(self._repo.refs.subkeys(b'refs/'))) expected_refs.remove(b'refs/heads/loop') expected_refs.add(b'HEAD') self.assertEqual(expected_refs, set(self._repo.get_refs().keys())) _TEST_REFS_SERIALIZED = ( b'42d06bd4b77fed026b154d16493e5deab78f02ec\t' b'refs/heads/40-char-ref-aaaaaaaaaaaaaaaaaa\n' b'42d06bd4b77fed026b154d16493e5deab78f02ec\trefs/heads/master\n' b'42d06bd4b77fed026b154d16493e5deab78f02ec\trefs/heads/packed\n' b'df6800012397fb85c56e7418dd4eb9405dee075c\trefs/tags/refs-0.1\n' b'3ec9c43c84ff242e3ef4a9fc5bc111fd780a76a8\trefs/tags/refs-0.2\n') class InfoRefsContainerTests(TestCase): def test_invalid_refname(self): text = _TEST_REFS_SERIALIZED + b'00' * 20 + b'\trefs/stash\n' refs = InfoRefsContainer(BytesIO(text)) expected_refs = dict(_TEST_REFS) del expected_refs[b'HEAD'] expected_refs[b'refs/stash'] = b'00' * 20 del expected_refs[b'refs/heads/loop'] self.assertEqual(expected_refs, refs.as_dict()) def test_keys(self): refs = InfoRefsContainer(BytesIO(_TEST_REFS_SERIALIZED)) actual_keys = set(refs.keys()) self.assertEqual(set(refs.allkeys()), actual_keys) expected_refs = dict(_TEST_REFS) del expected_refs[b'HEAD'] del expected_refs[b'refs/heads/loop'] self.assertEqual(set(expected_refs.keys()), actual_keys) actual_keys = refs.keys(b'refs/heads') actual_keys.discard(b'loop') self.assertEqual( [b'40-char-ref-aaaaaaaaaaaaaaaaaa', b'master', b'packed'], sorted(actual_keys)) self.assertEqual([b'refs-0.1', b'refs-0.2'], sorted(refs.keys(b'refs/tags'))) def test_as_dict(self): refs = InfoRefsContainer(BytesIO(_TEST_REFS_SERIALIZED)) # refs/heads/loop does not show up even if it exists expected_refs = dict(_TEST_REFS) del expected_refs[b'HEAD'] del expected_refs[b'refs/heads/loop'] self.assertEqual(expected_refs, refs.as_dict()) def test_contains(self): refs = InfoRefsContainer(BytesIO(_TEST_REFS_SERIALIZED)) self.assertTrue(b'refs/heads/master' in refs) self.assertFalse(b'refs/heads/bar' in refs) def test_get_peeled(self): refs = InfoRefsContainer(BytesIO(_TEST_REFS_SERIALIZED)) # refs/heads/loop does not show up even if it exists self.assertEqual( _TEST_REFS[b'refs/heads/master'], refs.get_peeled(b'refs/heads/master')) class ParseSymrefValueTests(TestCase): def test_valid(self): self.assertEqual( b'refs/heads/foo', parse_symref_value(b'ref: refs/heads/foo')) def test_invalid(self): self.assertRaises(ValueError, parse_symref_value, b'foobar') class StripPeeledRefsTests(TestCase): all_refs = { b'refs/heads/master': b'8843d7f92416211de9ebb963ff4ce28125932878', b'refs/heads/testing': b'186a005b134d8639a58b6731c7c1ea821a6eedba', b'refs/tags/1.0.0': b'a93db4b0360cc635a2b93675010bac8d101f73f0', b'refs/tags/1.0.0^{}': b'a93db4b0360cc635a2b93675010bac8d101f73f0', b'refs/tags/2.0.0': b'0749936d0956c661ac8f8d3483774509c165f89e', b'refs/tags/2.0.0^{}': b'0749936d0956c661ac8f8d3483774509c165f89e', } non_peeled_refs = { b'refs/heads/master': b'8843d7f92416211de9ebb963ff4ce28125932878', b'refs/heads/testing': b'186a005b134d8639a58b6731c7c1ea821a6eedba', b'refs/tags/1.0.0': b'a93db4b0360cc635a2b93675010bac8d101f73f0', b'refs/tags/2.0.0': b'0749936d0956c661ac8f8d3483774509c165f89e', } def test_strip_peeled_refs(self): # Simple check of two dicts self.assertEqual( strip_peeled_refs(self.all_refs), self.non_peeled_refs) diff --git a/dulwich/tests/test_repository.py b/dulwich/tests/test_repository.py index f19141f0..2b2bc674 100644 --- a/dulwich/tests/test_repository.py +++ b/dulwich/tests/test_repository.py @@ -1,968 +1,1053 @@ # -*- coding: utf-8 -*- # test_repository.py -- tests for repository.py # Copyright (C) 2007 James Westby # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """Tests for the repository.""" import locale import os import stat import shutil import sys import tempfile import warnings from dulwich import errors from dulwich.object_store import ( tree_lookup_path, ) from dulwich import objects from dulwich.config import Config from dulwich.errors import NotGitRepository from dulwich.repo import ( InvalidUserIdentity, Repo, MemoryRepo, check_user_identity, ) from dulwich.tests import ( TestCase, skipIf, ) from dulwich.tests.utils import ( open_repo, tear_down_repo, setup_warning_catcher, ) missing_sha = b'b91fa4d900e17e99b433218e988c4eb4a3e9a097' class CreateRepositoryTests(TestCase): def assertFileContentsEqual(self, expected, repo, path): f = repo.get_named_file(path) if not f: self.assertEqual(expected, None) else: with f: self.assertEqual(expected, f.read()) def _check_repo_contents(self, repo, expect_bare): self.assertEqual(expect_bare, repo.bare) self.assertFileContentsEqual( b'Unnamed repository', repo, 'description') self.assertFileContentsEqual( b'', repo, os.path.join('info', 'exclude')) self.assertFileContentsEqual(None, repo, 'nonexistent file') barestr = b'bare = ' + str(expect_bare).lower().encode('ascii') with repo.get_named_file('config') as f: config_text = f.read() self.assertTrue(barestr in config_text, "%r" % config_text) expect_filemode = sys.platform != 'win32' barestr = b'filemode = ' + str(expect_filemode).lower().encode('ascii') with repo.get_named_file('config') as f: config_text = f.read() self.assertTrue(barestr in config_text, "%r" % config_text) def test_create_memory(self): repo = MemoryRepo.init_bare([], {}) self._check_repo_contents(repo, True) def test_create_disk_bare(self): tmp_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, tmp_dir) repo = Repo.init_bare(tmp_dir) self.assertEqual(tmp_dir, repo._controldir) self._check_repo_contents(repo, True) def test_create_disk_non_bare(self): tmp_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, tmp_dir) repo = Repo.init(tmp_dir) self.assertEqual(os.path.join(tmp_dir, '.git'), repo._controldir) self._check_repo_contents(repo, False) def test_create_disk_non_bare_mkdir(self): tmp_dir = tempfile.mkdtemp() target_dir = os.path.join(tmp_dir, "target") self.addCleanup(shutil.rmtree, tmp_dir) repo = Repo.init(target_dir, mkdir=True) self.assertEqual(os.path.join(target_dir, '.git'), repo._controldir) self._check_repo_contents(repo, False) def test_create_disk_bare_mkdir(self): tmp_dir = tempfile.mkdtemp() target_dir = os.path.join(tmp_dir, "target") self.addCleanup(shutil.rmtree, tmp_dir) repo = Repo.init_bare(target_dir, mkdir=True) self.assertEqual(target_dir, repo._controldir) self._check_repo_contents(repo, True) class MemoryRepoTests(TestCase): def test_set_description(self): r = MemoryRepo.init_bare([], {}) description = b"Some description" r.set_description(description) self.assertEqual(description, r.get_description()) class RepositoryRootTests(TestCase): def mkdtemp(self): return tempfile.mkdtemp() def open_repo(self, name): temp_dir = self.mkdtemp() repo = open_repo(name, temp_dir) self.addCleanup(tear_down_repo, repo) return repo def test_simple_props(self): r = self.open_repo('a.git') self.assertEqual(r.controldir(), r.path) def test_setitem(self): r = self.open_repo('a.git') r[b"refs/tags/foo"] = b'a90fa2d900a17e99b433217e988c4eb4a2e9a097' self.assertEqual(b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', r[b"refs/tags/foo"].id) def test_getitem_unicode(self): r = self.open_repo('a.git') test_keys = [ (b'refs/heads/master', True), (b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', True), (b'11' * 19 + b'--', False), ] for k, contained in test_keys: self.assertEqual(k in r, contained) # Avoid deprecation warning under Py3.2+ if getattr(self, 'assertRaisesRegex', None): assertRaisesRegexp = self.assertRaisesRegex else: assertRaisesRegexp = self.assertRaisesRegexp for k, _ in test_keys: assertRaisesRegexp( TypeError, "'name' must be bytestring, not int", r.__getitem__, 12 ) def test_delitem(self): r = self.open_repo('a.git') del r[b'refs/heads/master'] self.assertRaises(KeyError, lambda: r[b'refs/heads/master']) del r[b'HEAD'] self.assertRaises(KeyError, lambda: r[b'HEAD']) self.assertRaises(ValueError, r.__delitem__, b'notrefs/foo') def test_get_refs(self): r = self.open_repo('a.git') self.assertEqual({ b'HEAD': b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', b'refs/heads/master': b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', b'refs/tags/mytag': b'28237f4dc30d0d462658d6b937b08a0f0b6ef55a', b'refs/tags/mytag-packed': b'b0931cadc54336e78a1d980420e3268903b57a50', }, r.get_refs()) def test_head(self): r = self.open_repo('a.git') self.assertEqual(r.head(), b'a90fa2d900a17e99b433217e988c4eb4a2e9a097') def test_get_object(self): r = self.open_repo('a.git') obj = r.get_object(r.head()) self.assertEqual(obj.type_name, b'commit') def test_get_object_non_existant(self): r = self.open_repo('a.git') self.assertRaises(KeyError, r.get_object, missing_sha) def test_contains_object(self): r = self.open_repo('a.git') self.assertTrue(r.head() in r) def test_contains_ref(self): r = self.open_repo('a.git') self.assertTrue(b"HEAD" in r) def test_get_no_description(self): r = self.open_repo('a.git') self.assertIs(None, r.get_description()) def test_get_description(self): r = self.open_repo('a.git') with open(os.path.join(r.path, 'description'), 'wb') as f: f.write(b"Some description") self.assertEqual(b"Some description", r.get_description()) def test_set_description(self): r = self.open_repo('a.git') description = b"Some description" r.set_description(description) self.assertEqual(description, r.get_description()) def test_contains_missing(self): r = self.open_repo('a.git') self.assertFalse(b"bar" in r) def test_get_peeled(self): # unpacked ref r = self.open_repo('a.git') tag_sha = b'28237f4dc30d0d462658d6b937b08a0f0b6ef55a' self.assertNotEqual(r[tag_sha].sha().hexdigest(), r.head()) self.assertEqual(r.get_peeled(b'refs/tags/mytag'), r.head()) # packed ref with cached peeled value packed_tag_sha = b'b0931cadc54336e78a1d980420e3268903b57a50' parent_sha = r[r.head()].parents[0] self.assertNotEqual(r[packed_tag_sha].sha().hexdigest(), parent_sha) self.assertEqual(r.get_peeled(b'refs/tags/mytag-packed'), parent_sha) # TODO: add more corner cases to test repo def test_get_peeled_not_tag(self): r = self.open_repo('a.git') self.assertEqual(r.get_peeled(b'HEAD'), r.head()) def test_get_walker(self): r = self.open_repo('a.git') # include defaults to [r.head()] self.assertEqual( [e.commit.id for e in r.get_walker()], [r.head(), b'2a72d929692c41d8554c07f6301757ba18a65d91']) self.assertEqual( [e.commit.id for e in r.get_walker([b'2a72d929692c41d8554c07f6301757ba18a65d91'])], [b'2a72d929692c41d8554c07f6301757ba18a65d91']) self.assertEqual( [e.commit.id for e in r.get_walker(b'2a72d929692c41d8554c07f6301757ba18a65d91')], [b'2a72d929692c41d8554c07f6301757ba18a65d91']) + def test_fetch(self): + r = self.open_repo('a.git') + tmp_dir = self.mkdtemp() + self.addCleanup(shutil.rmtree, tmp_dir) + t = Repo.init(tmp_dir) + self.addCleanup(t.close) + r.fetch(t) + self.assertIn(b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', t) + self.assertIn(b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', t) + self.assertIn(b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', t) + self.assertIn(b'28237f4dc30d0d462658d6b937b08a0f0b6ef55a', t) + self.assertIn(b'b0931cadc54336e78a1d980420e3268903b57a50', t) + + def test_fetch_ignores_missing_refs(self): + r = self.open_repo('a.git') + missing = b'1234566789123456789123567891234657373833' + r.refs[b'refs/heads/blah'] = missing + tmp_dir = self.mkdtemp() + self.addCleanup(shutil.rmtree, tmp_dir) + t = Repo.init(tmp_dir) + self.addCleanup(t.close) + r.fetch(t) + self.assertIn(b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', t) + self.assertIn(b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', t) + self.assertIn(b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', t) + self.assertIn(b'28237f4dc30d0d462658d6b937b08a0f0b6ef55a', t) + self.assertIn(b'b0931cadc54336e78a1d980420e3268903b57a50', t) + self.assertNotIn(missing, t) + def test_clone(self): r = self.open_repo('a.git') tmp_dir = self.mkdtemp() self.addCleanup(shutil.rmtree, tmp_dir) with r.clone(tmp_dir, mkdir=False) as t: self.assertEqual({ b'HEAD': b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', b'refs/remotes/origin/master': b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', b'refs/heads/master': b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', b'refs/tags/mytag': b'28237f4dc30d0d462658d6b937b08a0f0b6ef55a', b'refs/tags/mytag-packed': b'b0931cadc54336e78a1d980420e3268903b57a50', }, t.refs.as_dict()) shas = [e.commit.id for e in r.get_walker()] self.assertEqual(shas, [t.head(), b'2a72d929692c41d8554c07f6301757ba18a65d91']) c = t.get_config() encoded_path = r.path if not isinstance(encoded_path, bytes): encoded_path = encoded_path.encode(sys.getfilesystemencoding()) self.assertEqual(encoded_path, c.get((b'remote', b'origin'), b'url')) self.assertEqual( b'+refs/heads/*:refs/remotes/origin/*', c.get((b'remote', b'origin'), b'fetch')) def test_clone_no_head(self): temp_dir = self.mkdtemp() self.addCleanup(shutil.rmtree, temp_dir) repo_dir = os.path.join(os.path.dirname(__file__), 'data', 'repos') dest_dir = os.path.join(temp_dir, 'a.git') shutil.copytree(os.path.join(repo_dir, 'a.git'), dest_dir, symlinks=True) r = Repo(dest_dir) del r.refs[b"refs/heads/master"] del r.refs[b"HEAD"] t = r.clone(os.path.join(temp_dir, 'b.git'), mkdir=True) self.assertEqual({ b'refs/tags/mytag': b'28237f4dc30d0d462658d6b937b08a0f0b6ef55a', b'refs/tags/mytag-packed': b'b0931cadc54336e78a1d980420e3268903b57a50', }, t.refs.as_dict()) def test_clone_empty(self): """Test clone() doesn't crash if HEAD points to a non-existing ref. This simulates cloning server-side bare repository either when it is still empty or if user renames master branch and pushes private repo to the server. Non-bare repo HEAD always points to an existing ref. """ r = self.open_repo('empty.git') tmp_dir = self.mkdtemp() self.addCleanup(shutil.rmtree, tmp_dir) r.clone(tmp_dir, mkdir=False, bare=True) def test_clone_bare(self): r = self.open_repo('a.git') tmp_dir = self.mkdtemp() self.addCleanup(shutil.rmtree, tmp_dir) t = r.clone(tmp_dir, mkdir=False) t.close() def test_clone_checkout_and_bare(self): r = self.open_repo('a.git') tmp_dir = self.mkdtemp() self.addCleanup(shutil.rmtree, tmp_dir) self.assertRaises(ValueError, r.clone, tmp_dir, mkdir=False, checkout=True, bare=True) def test_merge_history(self): r = self.open_repo('simple_merge.git') shas = [e.commit.id for e in r.get_walker()] self.assertEqual(shas, [b'5dac377bdded4c9aeb8dff595f0faeebcc8498cc', b'ab64bbdcc51b170d21588e5c5d391ee5c0c96dfd', b'4cffe90e0a41ad3f5190079d7c8f036bde29cbe6', b'60dacdc733de308bb77bb76ce0fb0f9b44c9769e', b'0d89f20333fbb1d2f3a94da77f4981373d8f4310']) def test_out_of_order_merge(self): """Test that revision history is ordered by date, not parent order.""" r = self.open_repo('ooo_merge.git') shas = [e.commit.id for e in r.get_walker()] self.assertEqual(shas, [b'7601d7f6231db6a57f7bbb79ee52e4d462fd44d1', b'f507291b64138b875c28e03469025b1ea20bc614', b'fb5b0425c7ce46959bec94d54b9a157645e114f5', b'f9e39b120c68182a4ba35349f832d0e4e61f485c']) def test_get_tags_empty(self): r = self.open_repo('ooo_merge.git') self.assertEqual({}, r.refs.as_dict(b'refs/tags')) def test_get_config(self): r = self.open_repo('ooo_merge.git') self.assertIsInstance(r.get_config(), Config) def test_get_config_stack(self): r = self.open_repo('ooo_merge.git') self.assertIsInstance(r.get_config_stack(), Config) @skipIf(not getattr(os, 'symlink', None), 'Requires symlink support') def test_submodule(self): temp_dir = self.mkdtemp() self.addCleanup(shutil.rmtree, temp_dir) repo_dir = os.path.join(os.path.dirname(__file__), 'data', 'repos') shutil.copytree(os.path.join(repo_dir, 'a.git'), os.path.join(temp_dir, 'a.git'), symlinks=True) rel = os.path.relpath(os.path.join(repo_dir, 'submodule'), temp_dir) os.symlink(os.path.join(rel, 'dotgit'), os.path.join(temp_dir, '.git')) with Repo(temp_dir) as r: self.assertEqual(r.head(), b'a90fa2d900a17e99b433217e988c4eb4a2e9a097') def test_common_revisions(self): """ This test demonstrates that ``find_common_revisions()`` actually returns common heads, not revisions; dulwich already uses ``find_common_revisions()`` in such a manner (see ``Repo.fetch_objects()``). """ expected_shas = set([b'60dacdc733de308bb77bb76ce0fb0f9b44c9769e']) # Source for objects. r_base = self.open_repo('simple_merge.git') # Re-create each-side of the merge in simple_merge.git. # # Since the trees and blobs are missing, the repository created is # corrupted, but we're only checking for commits for the purpose of # this test, so it's immaterial. r1_dir = self.mkdtemp() self.addCleanup(shutil.rmtree, r1_dir) r1_commits = [b'ab64bbdcc51b170d21588e5c5d391ee5c0c96dfd', # HEAD b'60dacdc733de308bb77bb76ce0fb0f9b44c9769e', b'0d89f20333fbb1d2f3a94da77f4981373d8f4310'] r2_dir = self.mkdtemp() self.addCleanup(shutil.rmtree, r2_dir) r2_commits = [b'4cffe90e0a41ad3f5190079d7c8f036bde29cbe6', # HEAD b'60dacdc733de308bb77bb76ce0fb0f9b44c9769e', b'0d89f20333fbb1d2f3a94da77f4981373d8f4310'] r1 = Repo.init_bare(r1_dir) for c in r1_commits: r1.object_store.add_object(r_base.get_object(c)) r1.refs[b'HEAD'] = r1_commits[0] r2 = Repo.init_bare(r2_dir) for c in r2_commits: r2.object_store.add_object(r_base.get_object(c)) r2.refs[b'HEAD'] = r2_commits[0] # Finally, the 'real' testing! shas = r2.object_store.find_common_revisions(r1.get_graph_walker()) self.assertEqual(set(shas), expected_shas) shas = r1.object_store.find_common_revisions(r2.get_graph_walker()) self.assertEqual(set(shas), expected_shas) def test_shell_hook_pre_commit(self): if os.name != 'posix': self.skipTest('shell hook tests requires POSIX shell') pre_commit_fail = """#!/bin/sh exit 1 """ pre_commit_success = """#!/bin/sh exit 0 """ repo_dir = os.path.join(self.mkdtemp()) self.addCleanup(shutil.rmtree, repo_dir) r = Repo.init(repo_dir) self.addCleanup(r.close) pre_commit = os.path.join(r.controldir(), 'hooks', 'pre-commit') with open(pre_commit, 'w') as f: f.write(pre_commit_fail) os.chmod(pre_commit, stat.S_IREAD | stat.S_IWRITE | stat.S_IEXEC) self.assertRaises(errors.CommitError, r.do_commit, 'failed commit', committer='Test Committer ', author='Test Author ', commit_timestamp=12345, commit_timezone=0, author_timestamp=12345, author_timezone=0) with open(pre_commit, 'w') as f: f.write(pre_commit_success) os.chmod(pre_commit, stat.S_IREAD | stat.S_IWRITE | stat.S_IEXEC) commit_sha = r.do_commit( b'empty commit', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12395, commit_timezone=0, author_timestamp=12395, author_timezone=0) self.assertEqual([], r[commit_sha].parents) def test_shell_hook_commit_msg(self): if os.name != 'posix': self.skipTest('shell hook tests requires POSIX shell') commit_msg_fail = """#!/bin/sh exit 1 """ commit_msg_success = """#!/bin/sh exit 0 """ repo_dir = self.mkdtemp() self.addCleanup(shutil.rmtree, repo_dir) r = Repo.init(repo_dir) self.addCleanup(r.close) commit_msg = os.path.join(r.controldir(), 'hooks', 'commit-msg') with open(commit_msg, 'w') as f: f.write(commit_msg_fail) os.chmod(commit_msg, stat.S_IREAD | stat.S_IWRITE | stat.S_IEXEC) self.assertRaises(errors.CommitError, r.do_commit, b'failed commit', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12345, commit_timezone=0, author_timestamp=12345, author_timezone=0) with open(commit_msg, 'w') as f: f.write(commit_msg_success) os.chmod(commit_msg, stat.S_IREAD | stat.S_IWRITE | stat.S_IEXEC) commit_sha = r.do_commit( b'empty commit', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12395, commit_timezone=0, author_timestamp=12395, author_timezone=0) self.assertEqual([], r[commit_sha].parents) def test_shell_hook_post_commit(self): if os.name != 'posix': self.skipTest('shell hook tests requires POSIX shell') repo_dir = self.mkdtemp() self.addCleanup(shutil.rmtree, repo_dir) r = Repo.init(repo_dir) self.addCleanup(r.close) (fd, path) = tempfile.mkstemp(dir=repo_dir) os.close(fd) post_commit_msg = """#!/bin/sh rm """ + path + """ """ root_sha = r.do_commit( b'empty commit', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12345, commit_timezone=0, author_timestamp=12345, author_timezone=0) self.assertEqual([], r[root_sha].parents) post_commit = os.path.join(r.controldir(), 'hooks', 'post-commit') with open(post_commit, 'wb') as f: f.write(post_commit_msg.encode(locale.getpreferredencoding())) os.chmod(post_commit, stat.S_IREAD | stat.S_IWRITE | stat.S_IEXEC) commit_sha = r.do_commit( b'empty commit', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12345, commit_timezone=0, author_timestamp=12345, author_timezone=0) self.assertEqual([root_sha], r[commit_sha].parents) self.assertFalse(os.path.exists(path)) post_commit_msg_fail = """#!/bin/sh exit 1 """ with open(post_commit, 'w') as f: f.write(post_commit_msg_fail) os.chmod(post_commit, stat.S_IREAD | stat.S_IWRITE | stat.S_IEXEC) warnings.simplefilter("always", UserWarning) self.addCleanup(warnings.resetwarnings) warnings_list, restore_warnings = setup_warning_catcher() self.addCleanup(restore_warnings) commit_sha2 = r.do_commit( b'empty commit', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12345, commit_timezone=0, author_timestamp=12345, author_timezone=0) expected_warning = UserWarning( 'post-commit hook failed: Hook post-commit exited with ' 'non-zero status',) for w in warnings_list: if (type(w) == type(expected_warning) and w.args == expected_warning.args): break else: raise AssertionError( 'Expected warning %r not in %r' % (expected_warning, warnings_list)) self.assertEqual([commit_sha], r[commit_sha2].parents) def test_as_dict(self): def check(repo): self.assertEqual( repo.refs.subkeys(b'refs/tags'), repo.refs.subkeys(b'refs/tags/')) self.assertEqual( repo.refs.as_dict(b'refs/tags'), repo.refs.as_dict(b'refs/tags/')) self.assertEqual( repo.refs.as_dict(b'refs/heads'), repo.refs.as_dict(b'refs/heads/')) bare = self.open_repo('a.git') tmp_dir = self.mkdtemp() self.addCleanup(shutil.rmtree, tmp_dir) with bare.clone(tmp_dir, mkdir=False) as nonbare: check(nonbare) check(bare) def test_working_tree(self): temp_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, temp_dir) worktree_temp_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, worktree_temp_dir) r = Repo.init(temp_dir) self.addCleanup(r.close) root_sha = r.do_commit( b'empty commit', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12345, commit_timezone=0, author_timestamp=12345, author_timezone=0) r.refs[b'refs/heads/master'] = root_sha w = Repo._init_new_working_directory(worktree_temp_dir, r) self.addCleanup(w.close) new_sha = w.do_commit( b'new commit', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12345, commit_timezone=0, author_timestamp=12345, author_timezone=0) w.refs[b'HEAD'] = new_sha self.assertEqual(os.path.abspath(r.controldir()), os.path.abspath(w.commondir())) self.assertEqual(r.refs.keys(), w.refs.keys()) self.assertNotEqual(r.head(), w.head()) class BuildRepoRootTests(TestCase): """Tests that build on-disk repos from scratch. Repos live in a temp dir and are torn down after each test. They start with a single commit in master having single file named 'a'. """ def get_repo_dir(self): return os.path.join(tempfile.mkdtemp(), 'test') def setUp(self): super(BuildRepoRootTests, self).setUp() self._repo_dir = self.get_repo_dir() os.makedirs(self._repo_dir) r = self._repo = Repo.init(self._repo_dir) self.addCleanup(tear_down_repo, r) self.assertFalse(r.bare) self.assertEqual(b'ref: refs/heads/master', r.refs.read_ref(b'HEAD')) self.assertRaises(KeyError, lambda: r.refs[b'refs/heads/master']) with open(os.path.join(r.path, 'a'), 'wb') as f: f.write(b'file contents') r.stage(['a']) commit_sha = r.do_commit( b'msg', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12345, commit_timezone=0, author_timestamp=12345, author_timezone=0) self.assertEqual([], r[commit_sha].parents) self._root_commit = commit_sha - def test_shallow(self): + def test_get_shallow(self): self.assertEqual(set(), self._repo.get_shallow()) with open(os.path.join(self._repo.path, '.git', 'shallow'), 'wb') as f: f.write(b'a90fa2d900a17e99b433217e988c4eb4a2e9a097\n') self.assertEqual({b'a90fa2d900a17e99b433217e988c4eb4a2e9a097'}, self._repo.get_shallow()) + def test_update_shallow(self): + self._repo.update_shallow(None, None) # no op + self.assertEqual(set(), self._repo.get_shallow()) + self._repo.update_shallow( + [b'a90fa2d900a17e99b433217e988c4eb4a2e9a097'], + None) + self.assertEqual( + {b'a90fa2d900a17e99b433217e988c4eb4a2e9a097'}, + self._repo.get_shallow()) + self._repo.update_shallow( + [b'a90fa2d900a17e99b433217e988c4eb4a2e9a097'], + [b'f9e39b120c68182a4ba35349f832d0e4e61f485c']) + self.assertEqual({b'a90fa2d900a17e99b433217e988c4eb4a2e9a097'}, + self._repo.get_shallow()) + def test_build_repo(self): r = self._repo self.assertEqual(b'ref: refs/heads/master', r.refs.read_ref(b'HEAD')) self.assertEqual(self._root_commit, r.refs[b'refs/heads/master']) expected_blob = objects.Blob.from_string(b'file contents') self.assertEqual(expected_blob.data, r[expected_blob.id].data) actual_commit = r[self._root_commit] self.assertEqual(b'msg', actual_commit.message) def test_commit_modified(self): r = self._repo with open(os.path.join(r.path, 'a'), 'wb') as f: f.write(b'new contents') r.stage(['a']) commit_sha = r.do_commit( b'modified a', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12395, commit_timezone=0, author_timestamp=12395, author_timezone=0) self.assertEqual([self._root_commit], r[commit_sha].parents) a_mode, a_id = tree_lookup_path(r.get_object, r[commit_sha].tree, b'a') self.assertEqual(stat.S_IFREG | 0o644, a_mode) self.assertEqual(b'new contents', r[a_id].data) @skipIf(not getattr(os, 'symlink', None), 'Requires symlink support') def test_commit_symlink(self): r = self._repo os.symlink('a', os.path.join(r.path, 'b')) r.stage(['a', 'b']) commit_sha = r.do_commit( b'Symlink b', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12395, commit_timezone=0, author_timestamp=12395, author_timezone=0) self.assertEqual([self._root_commit], r[commit_sha].parents) b_mode, b_id = tree_lookup_path(r.get_object, r[commit_sha].tree, b'b') self.assertTrue(stat.S_ISLNK(b_mode)) self.assertEqual(b'a', r[b_id].data) + def test_commit_merge_heads_file(self): + tmp_dir = tempfile.mkdtemp() + self.addCleanup(shutil.rmtree, tmp_dir) + r = Repo.init(tmp_dir) + with open(os.path.join(r.path, 'a'), 'w') as f: + f.write('initial text') + c1 = r.do_commit( + b'initial commit', + committer=b'Test Committer ', + author=b'Test Author ', + commit_timestamp=12395, commit_timezone=0, + author_timestamp=12395, author_timezone=0) + with open(os.path.join(r.path, 'a'), 'w') as f: + f.write('merged text') + with open(os.path.join(r.path, '.git', 'MERGE_HEADS'), 'w') as f: + f.write('c27a2d21dd136312d7fa9e8baabb82561a1727d0\n') + r.stage(['a']) + commit_sha = r.do_commit( + b'deleted a', + committer=b'Test Committer ', + author=b'Test Author ', + commit_timestamp=12395, commit_timezone=0, + author_timestamp=12395, author_timezone=0) + self.assertEqual([ + c1, + b'c27a2d21dd136312d7fa9e8baabb82561a1727d0'], + r[commit_sha].parents) + def test_commit_deleted(self): r = self._repo os.remove(os.path.join(r.path, 'a')) r.stage(['a']) commit_sha = r.do_commit( b'deleted a', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12395, commit_timezone=0, author_timestamp=12395, author_timezone=0) self.assertEqual([self._root_commit], r[commit_sha].parents) self.assertEqual([], list(r.open_index())) tree = r[r[commit_sha].tree] self.assertEqual([], list(tree.iteritems())) def test_commit_follows(self): r = self._repo r.refs.set_symbolic_ref(b'HEAD', b'refs/heads/bla') commit_sha = r.do_commit( b'commit with strange character', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12395, commit_timezone=0, author_timestamp=12395, author_timezone=0, ref=b'HEAD') self.assertEqual(commit_sha, r[b'refs/heads/bla'].id) def test_commit_encoding(self): r = self._repo commit_sha = r.do_commit( b'commit with strange character \xee', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12395, commit_timezone=0, author_timestamp=12395, author_timezone=0, encoding=b"iso8859-1") self.assertEqual(b"iso8859-1", r[commit_sha].encoding) + def test_commit_encoding_from_config(self): + r = self._repo + c = r.get_config() + c.set(('i18n',), 'commitEncoding', 'iso8859-1') + c.write_to_path() + commit_sha = r.do_commit( + b'commit with strange character \xee', + committer=b'Test Committer ', + author=b'Test Author ', + commit_timestamp=12395, commit_timezone=0, + author_timestamp=12395, author_timezone=0) + self.assertEqual(b"iso8859-1", r[commit_sha].encoding) + def test_commit_config_identity(self): # commit falls back to the users' identity if it wasn't specified r = self._repo c = r.get_config() c.set((b"user", ), b"name", b"Jelmer") c.set((b"user", ), b"email", b"jelmer@apache.org") c.write_to_path() commit_sha = r.do_commit(b'message') self.assertEqual( b"Jelmer ", r[commit_sha].author) self.assertEqual( b"Jelmer ", r[commit_sha].committer) def test_commit_config_identity_in_memoryrepo(self): # commit falls back to the users' identity if it wasn't specified r = MemoryRepo.init_bare([], {}) c = r.get_config() c.set((b"user", ), b"name", b"Jelmer") c.set((b"user", ), b"email", b"jelmer@apache.org") commit_sha = r.do_commit(b'message', tree=objects.Tree().id) self.assertEqual( b"Jelmer ", r[commit_sha].author) self.assertEqual( b"Jelmer ", r[commit_sha].committer) def test_commit_fail_ref(self): r = self._repo def set_if_equals(name, old_ref, new_ref, **kwargs): return False r.refs.set_if_equals = set_if_equals def add_if_new(name, new_ref, **kwargs): self.fail('Unexpected call to add_if_new') r.refs.add_if_new = add_if_new old_shas = set(r.object_store) self.assertRaises(errors.CommitError, r.do_commit, b'failed commit', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12345, commit_timezone=0, author_timestamp=12345, author_timezone=0) new_shas = set(r.object_store) - old_shas self.assertEqual(1, len(new_shas)) # Check that the new commit (now garbage) was added. new_commit = r[new_shas.pop()] self.assertEqual(r[self._root_commit].tree, new_commit.tree) self.assertEqual(b'failed commit', new_commit.message) def test_commit_branch(self): r = self._repo commit_sha = r.do_commit( b'commit to branch', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12395, commit_timezone=0, author_timestamp=12395, author_timezone=0, ref=b"refs/heads/new_branch") self.assertEqual(self._root_commit, r[b"HEAD"].id) self.assertEqual(commit_sha, r[b"refs/heads/new_branch"].id) self.assertEqual([], r[commit_sha].parents) self.assertTrue(b"refs/heads/new_branch" in r) new_branch_head = commit_sha commit_sha = r.do_commit( b'commit to branch 2', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12395, commit_timezone=0, author_timestamp=12395, author_timezone=0, ref=b"refs/heads/new_branch") self.assertEqual(self._root_commit, r[b"HEAD"].id) self.assertEqual(commit_sha, r[b"refs/heads/new_branch"].id) self.assertEqual([new_branch_head], r[commit_sha].parents) def test_commit_merge_heads(self): r = self._repo merge_1 = r.do_commit( b'commit to branch 2', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12395, commit_timezone=0, author_timestamp=12395, author_timezone=0, ref=b"refs/heads/new_branch") commit_sha = r.do_commit( b'commit with merge', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12395, commit_timezone=0, author_timestamp=12395, author_timezone=0, merge_heads=[merge_1]) self.assertEqual( [self._root_commit, merge_1], r[commit_sha].parents) def test_commit_dangling_commit(self): r = self._repo old_shas = set(r.object_store) old_refs = r.get_refs() commit_sha = r.do_commit( b'commit with no ref', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12395, commit_timezone=0, author_timestamp=12395, author_timezone=0, ref=None) new_shas = set(r.object_store) - old_shas # New sha is added, but no new refs self.assertEqual(1, len(new_shas)) new_commit = r[new_shas.pop()] self.assertEqual(r[self._root_commit].tree, new_commit.tree) self.assertEqual([], r[commit_sha].parents) self.assertEqual(old_refs, r.get_refs()) def test_commit_dangling_commit_with_parents(self): r = self._repo old_shas = set(r.object_store) old_refs = r.get_refs() commit_sha = r.do_commit( b'commit with no ref', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12395, commit_timezone=0, author_timestamp=12395, author_timezone=0, ref=None, merge_heads=[self._root_commit]) new_shas = set(r.object_store) - old_shas # New sha is added, but no new refs self.assertEqual(1, len(new_shas)) new_commit = r[new_shas.pop()] self.assertEqual(r[self._root_commit].tree, new_commit.tree) self.assertEqual([self._root_commit], r[commit_sha].parents) self.assertEqual(old_refs, r.get_refs()) def test_stage_absolute(self): r = self._repo os.remove(os.path.join(r.path, 'a')) self.assertRaises(ValueError, r.stage, [os.path.join(r.path, 'a')]) def test_stage_deleted(self): r = self._repo os.remove(os.path.join(r.path, 'a')) r.stage(['a']) r.stage(['a']) # double-stage a deleted path def test_stage_directory(self): r = self._repo os.mkdir(os.path.join(r.path, 'c')) r.stage(['c']) self.assertEqual([b'a'], list(r.open_index())) @skipIf(sys.platform == 'win32' and sys.version_info[:2] >= (3, 6), 'tries to implicitly decode as utf8') def test_commit_no_encode_decode(self): r = self._repo repo_path_bytes = r.path.encode(sys.getfilesystemencoding()) encodings = ('utf8', 'latin1') names = [u'À'.encode(encoding) for encoding in encodings] for name, encoding in zip(names, encodings): full_path = os.path.join(repo_path_bytes, name) with open(full_path, 'wb') as f: f.write(encoding.encode('ascii')) # These files are break tear_down_repo, so cleanup these files # ourselves. self.addCleanup(os.remove, full_path) r.stage(names) commit_sha = r.do_commit( b'Files with different encodings', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12395, commit_timezone=0, author_timestamp=12395, author_timezone=0, ref=None, merge_heads=[self._root_commit]) for name, encoding in zip(names, encodings): mode, id = tree_lookup_path(r.get_object, r[commit_sha].tree, name) self.assertEqual(stat.S_IFREG | 0o644, mode) self.assertEqual(encoding.encode('ascii'), r[id].data) def test_discover_intended(self): path = os.path.join(self._repo_dir, 'b/c') r = Repo.discover(path) self.assertEqual(r.head(), self._repo.head()) def test_discover_isrepo(self): r = Repo.discover(self._repo_dir) self.assertEqual(r.head(), self._repo.head()) def test_discover_notrepo(self): with self.assertRaises(NotGitRepository): Repo.discover('/') class CheckUserIdentityTests(TestCase): def test_valid(self): check_user_identity(b'Me ') def test_invalid(self): self.assertRaises(InvalidUserIdentity, check_user_identity, b'No Email') self.assertRaises(InvalidUserIdentity, check_user_identity, b'Fullname ') self.assertRaises(InvalidUserIdentity, check_user_identity, b'Fullname >order<>') diff --git a/requirements.txt b/requirements.txt new file mode 100644 index 00000000..cff1307d --- /dev/null +++ b/requirements.txt @@ -0,0 +1 @@ +urllib3[secure]>=1.23 diff --git a/setup.cfg b/setup.cfg index 561aa948..ca1b10d6 100644 --- a/setup.cfg +++ b/setup.cfg @@ -1,30 +1,7 @@ -[metadata] -name = dulwich -author = Jelmer Vernooij -author_email = jelmer@jelmer.uk -home-page = https://www.dulwich.io/ -description = file:README.md -summary = Python Git Library -classifiers = - Development Status :: 4 - Beta - License :: OSI Approved :: Apache Software License - Programming Language :: Python :: 2.7 - Programming Language :: Python :: 3.3 - Programming Language :: Python :: 3.4 - Programming Language :: Python :: 3.5 - Programming Language :: Python :: 3.6 - Programming Language :: Python :: Implementation :: CPython - Programming Language :: Python :: Implementation :: PyPy - Operating System :: POSIX - Operating System :: Microsoft :: Windows - Topic :: Software Development :: Version Control -keyword = git, vcs -project_urls = - Bug Tracker = https://github.com/dulwich/dulwich/issues - -[build_ext] +[flake8] +exclude = build,.git,build-pypy,.tox [egg_info] tag_build = tag_date = 0 diff --git a/setup.py b/setup.py index 2d5cc5c3..684f78db 100755 --- a/setup.py +++ b/setup.py @@ -1,97 +1,125 @@ #!/usr/bin/python # encoding: utf-8 # Setup file for dulwich # Copyright (C) 2008-2016 Jelmer Vernooij try: from setuptools import setup, Extension except ImportError: from distutils.core import setup, Extension has_setuptools = False else: has_setuptools = True from distutils.core import Distribution +import io import os import sys -dulwich_version_string = '0.19.6' +dulwich_version_string = '0.19.10' include_dirs = [] # Windows MSVC support if sys.platform == 'win32' and sys.version_info[:2] < (3, 6): # Include dulwich/ for fallback stdint.h include_dirs.append('dulwich') class DulwichDistribution(Distribution): def is_pure(self): if self.pure: return True def has_ext_modules(self): return not self.pure global_options = Distribution.global_options + [ ('pure', None, "use pure Python code instead of C " "extensions (slower on CPython)")] pure = False if sys.platform == 'darwin' and os.path.exists('/usr/bin/xcodebuild'): # XCode 4.0 dropped support for ppc architecture, which is hardcoded in # distutils.sysconfig import subprocess p = subprocess.Popen( ['/usr/bin/xcodebuild', '-version'], stdout=subprocess.PIPE, stderr=subprocess.PIPE, env={}) out, err = p.communicate() for line in out.splitlines(): line = line.decode("utf8") # Also parse only first digit, because 3.2.1 can't be parsed nicely if (line.startswith('Xcode') and int(line.split()[1].split('.')[0]) >= 4): os.environ['ARCHFLAGS'] = '' tests_require = ['fastimport'] if '__pypy__' not in sys.modules and not sys.platform == 'win32': tests_require.extend([ 'gevent', 'geventhttpclient', 'mock', 'setuptools>=17.1']) ext_modules = [ Extension('dulwich._objects', ['dulwich/_objects.c'], include_dirs=include_dirs), Extension('dulwich._pack', ['dulwich/_pack.c'], include_dirs=include_dirs), Extension('dulwich._diff_tree', ['dulwich/_diff_tree.c'], include_dirs=include_dirs), ] setup_kwargs = {} if has_setuptools: setup_kwargs['extras_require'] = { 'fastimport': ['fastimport'], - 'https': ['urllib3[secure]>=1.21'], + 'https': ['urllib3[secure]>=1.23'], } - setup_kwargs['install_requires'] = ['urllib3>=1.21', 'certifi'] + setup_kwargs['install_requires'] = ['urllib3>=1.23', 'certifi'] setup_kwargs['include_package_data'] = True setup_kwargs['test_suite'] = 'dulwich.tests.test_suite' setup_kwargs['tests_require'] = tests_require +with io.open(os.path.join(os.path.dirname(__file__), "README.rst"), + encoding="utf-8") as f: + description = f.read() setup(name='dulwich', + author="Jelmer Vernooij", + author_email="jelmer@jelmer.uk", + url="https://www.dulwich.io/", + long_description=description, + description="Python Git Library", version=dulwich_version_string, license='Apachev2 or later or GPLv2', + project_urls={ + "Bug Tracker": "https://github.com/dulwich/dulwich/issues", + "Repository": "https://www.dulwich.io/code/", + "GitHub": "https://github.com/dulwich/dulwich", + }, + keywords="git vcs", packages=['dulwich', 'dulwich.tests', 'dulwich.tests.compat', 'dulwich.contrib'], package_data={'': ['../docs/tutorial/*.txt']}, scripts=['bin/dulwich', 'bin/dul-receive-pack', 'bin/dul-upload-pack'], ext_modules=ext_modules, distclass=DulwichDistribution, + classifiers=[ + 'Development Status :: 4 - Beta', + 'License :: OSI Approved :: Apache Software License', + 'Programming Language :: Python :: 2.7', + 'Programming Language :: Python :: 3.4', + 'Programming Language :: Python :: 3.5', + 'Programming Language :: Python :: 3.6', + 'Programming Language :: Python :: Implementation :: CPython', + 'Programming Language :: Python :: Implementation :: PyPy', + 'Operating System :: POSIX', + 'Operating System :: Microsoft :: Windows', + 'Topic :: Software Development :: Version Control', + ], **setup_kwargs )