diff --git a/.travis.yml b/.travis.yml index 2753c292..8ad8dff4 100644 --- a/.travis.yml +++ b/.travis.yml @@ -1,41 +1,40 @@ language: python sudo: false cache: pip python: - 2.7 - 3.3 - 3.4 - 3.5 - 3.5-dev - 3.6 - 3.6-dev - - 3.7-dev - pypy3.3-5.2-alpha1 env: - PYTHONHASHSEED=random TEST_REQUIRE="gevent greenlet geventhttpclient fastimport" matrix: include: - python: pypy env: TEST_REQUIRE=fastimport install: - travis_retry pip install -U pip coverage codecov flake8 $TEST_REQUIRE script: # Test without c extensions - python -m coverage run -p --source=dulwich -m unittest dulwich.tests.test_suite # Test with c extensions - python setup.py build_ext -i - python -m coverage run -p --source=dulwich -m unittest dulwich.tests.test_suite # Style - make style after_success: - python -m coverage combine - codecov diff --git a/AUTHORS b/AUTHORS index e60008b5..a3dd58ad 100644 --- a/AUTHORS +++ b/AUTHORS @@ -1,134 +1,140 @@ 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 If you contributed but are missing from this list, please send me an e-mail. diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md index 46c0f930..14a271ea 100644 --- a/CONTRIBUTING.md +++ b/CONTRIBUTING.md @@ -1,51 +1,55 @@ 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 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. +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) +* 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. +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. +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 deleted file mode 100644 index bd727e2c..00000000 --- a/MANIFEST.in +++ /dev/null @@ -1,18 +0,0 @@ -include NEWS -include AUTHORS -include README.md -include README.swift.md -include Makefile -include COPYING -include CONTRIBUTING.md -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 d8783cb1..39886c22 100644 --- a/Makefile +++ b/Makefile @@ -1,71 +1,71 @@ -PYTHON = python +PYTHON = python -Werror PYFLAKES = pyflakes PEP8 = pep8 FLAKE8 ?= flake8 SETUP = $(PYTHON) setup.py PYDOCTOR ?= pydoctor TESTRUNNER ?= unittest RUNTEST = PYTHONHASHSEED=random PYTHONPATH=.:$(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 before-push: check git diff origin/master | $(PEP8) --diff coverage: $(COVERAGE) run --source=dulwich -m unittest dulwich.tests.test_suite dulwich.contrib.test_suite coverage-html: coverage $(COVERAGE) html diff --git a/NEWS b/NEWS index 78030d94..cac6bedf 100644 --- a/NEWS +++ b/NEWS @@ -1,1649 +1,1707 @@ +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 2017-1000117) (Jelmer Vernooij) + (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 f39240d7..7646f5d9 100644 --- a/PKG-INFO +++ b/PKG-INFO @@ -1,32 +1,32 @@ Metadata-Version: 1.1 Name: dulwich -Version: 0.18.5 +Version: 0.19.0 Summary: Python Git Library Home-page: https://www.dulwich.io/ Author: UNKNOWN Author-email: jelmer@jelmer.uk License: Apachev2 or later or GPLv2 Description: Python implementation of the Git file formats and protocols, without the need to have git installed. All functionality is available in pure Python. Optional C extensions can be built for improved performance. The project is named after the part of London that Mr. and Mrs. Git live in in the particular Monty Python sketch. Keywords: git 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 diff --git a/README.md b/README.md index f3761f04..5ec53fc0 100644 --- a/README.md +++ b/README.md @@ -1,88 +1,94 @@ -[![Build Status](https://travis-ci.org/jelmer/dulwich.png?branch=master)](https://travis-ci.org/jelmer/dulwich) -[![Windows Build status](https://ci.appveyor.com/api/projects/status/mob7g4vnrfvvoweb?svg=true)](https://ci.appveyor.com/project/jelmer/dulwich/branch/master) +[![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/dulwich/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/jelmer/dulwich/issues). +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. diff --git a/TODO b/TODO index 618f5d15..9d2a6e7b 100644 --- a/TODO +++ b/TODO @@ -1,2 +1,6 @@ - 'git annotate' equivalent -- repacking +- reflog handling + +Performance: + - more efficient pack iteration + - more efficient delta generation diff --git a/dulwich.egg-info/PKG-INFO b/dulwich.egg-info/PKG-INFO deleted file mode 100644 index f39240d7..00000000 --- a/dulwich.egg-info/PKG-INFO +++ /dev/null @@ -1,32 +0,0 @@ -Metadata-Version: 1.1 -Name: dulwich -Version: 0.18.5 -Summary: Python Git Library -Home-page: https://www.dulwich.io/ -Author: UNKNOWN -Author-email: jelmer@jelmer.uk -License: Apachev2 or later or GPLv2 -Description: - Python implementation of the Git file formats and protocols, - without the need to have git installed. - - All functionality is available in pure Python. Optional - C extensions can be built for improved performance. - - The project is named after the part of London that Mr. and Mrs. Git live - in in the particular Monty Python sketch. - -Keywords: git -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 diff --git a/dulwich.egg-info/SOURCES.txt b/dulwich.egg-info/SOURCES.txt deleted file mode 100644 index ce25214f..00000000 --- a/dulwich.egg-info/SOURCES.txt +++ /dev/null @@ -1,200 +0,0 @@ -.testr.conf -.travis.yml -AUTHORS -CONTRIBUTING.md -COPYING -MANIFEST.in -Makefile -NEWS -README.md -README.swift.md -TODO -appveyor.yml -dulwich.cfg -setup.cfg -setup.py -tox.ini -bin/dul-receive-pack -bin/dul-upload-pack -bin/dulwich -docs/Makefile -docs/conf.py -docs/index.txt -docs/make.bat -docs/performance.txt -docs/protocol.txt -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/log_utils.py -dulwich/lru_cache.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/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/top_level.txt -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_lru_cache.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_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 \ No newline at end of file diff --git a/dulwich.egg-info/dependency_links.txt b/dulwich.egg-info/dependency_links.txt deleted file mode 100644 index 8b137891..00000000 --- a/dulwich.egg-info/dependency_links.txt +++ /dev/null @@ -1 +0,0 @@ - diff --git a/dulwich.egg-info/top_level.txt b/dulwich.egg-info/top_level.txt deleted file mode 100644 index e8413a49..00000000 --- a/dulwich.egg-info/top_level.txt +++ /dev/null @@ -1 +0,0 @@ -dulwich diff --git a/dulwich/__init__.py b/dulwich/__init__.py index 4cf6f134..9da35114 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, 18, 5) +__version__ = (0, 19, 0) diff --git a/dulwich/archive.py b/dulwich/archive.py index 46d4ccaa..a6370d83 100644 --- a/dulwich/archive.py +++ b/dulwich/archive.py @@ -1,118 +1,132 @@ # archive.py -- Creating an archive from a tarball # Copyright (C) 2015 Jonas Haag # Copyright (C) 2015 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. # """Generates tarballs for Git trees. """ import posixpath import stat import tarfile +import struct +from os import SEEK_END from io import BytesIO from contextlib import closing class ChunkedBytesIO(object): """Turn a list of bytestrings into a file-like object. This is similar to creating a `BytesIO` from a concatenation of the bytestring list, but saves memory by NOT creating one giant bytestring first:: BytesIO(b''.join(list_of_bytestrings)) =~= ChunkedBytesIO( list_of_bytestrings) """ def __init__(self, contents): self.contents = contents self.pos = (0, 0) def read(self, maxbytes=None): if maxbytes < 0: maxbytes = float('inf') buf = [] chunk, cursor = self.pos while chunk < len(self.contents): if maxbytes < len(self.contents[chunk]) - cursor: buf.append(self.contents[chunk][cursor:cursor+maxbytes]) cursor += maxbytes self.pos = (chunk, cursor) break else: buf.append(self.contents[chunk][cursor:]) maxbytes -= len(self.contents[chunk]) - cursor chunk += 1 cursor = 0 self.pos = (chunk, cursor) return b''.join(buf) def tar_stream(store, tree, mtime, format=''): """Generate a tar stream for the contents of a Git tree. Returns a generator that lazily assembles a .tar.gz archive, yielding it in pieces (bytestrings). To obtain the complete .tar.gz binary file, simply concatenate these chunks. :param store: Object store to retrieve objects from :param tree: Tree object for the tree root :param mtime: UNIX timestamp that is assigned as the modification time for - all files + all files, and the gzip header modification time if format='gz' :param format: Optional compression format for tarball :return: Bytestrings """ buf = BytesIO() with closing(tarfile.open(None, "w:%s" % format, buf)) as tar: + if format == 'gz': + # Manually correct the gzip header file modification time so that + # archives created from the same Git tree are always identical. + # The gzip header file modification time is not currenctly + # accessible from the tarfile API, see: + # https://bugs.python.org/issue31526 + buf.seek(0) + assert buf.read(2) == b'\x1f\x8b', 'Invalid gzip header' + buf.seek(4) + buf.write(struct.pack(' # # 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 urllib2 import urlparse except ImportError: import urllib.request as urllib2 import urllib.parse as urlparse +import certifi +import urllib3 +import urllib3.util + import dulwich from dulwich.errors import ( GitProtocolError, NotGitRepository, SendPackError, UpdateRefsError, ) from dulwich.protocol import ( _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_SYMREF, CAPABILITY_SIDE_BAND_64K, CAPABILITY_THIN_PACK, CAPABILITIES_REF, KNOWN_RECEIVE_CAPABILITIES, KNOWN_UPLOAD_CAPABILITIES, 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, ) +if sys.version_info < (2, 7, 9): + # Before Python 2.7.9 the `ssl` module lacks SNI support and lags behind in + # security updates. Use pyOpenSSL instead. + import urllib3.contrib.pyopenssl + urllib3.contrib.pyopenssl.inject_into_urllib3() + + 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) 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) if server_capabilities is None: (ref, server_capabilities) = extract_capabilities(ref) refs[ref] = sha if len(refs) == 0: - return None, set([]) + 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): self.refs = refs self.symrefs = symrefs self.agent = agent 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) # 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_contents, - progress=None, write_pack=write_pack_objects): + 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_contents: Function that can return a sequence of - the shas of the objects to upload. + :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 - :param write_pack: Function called with (file, iterable of objects) to - write the objects returned by generate_pack_contents to the server. :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): """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 :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) - except: + except BaseException: abort() raise else: commit() return result def fetch_pack(self, path, determine_wants, graph_walker, pack_data, progress=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) :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): """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 """ 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) have = next(graph_walker) while have: proto.write_pkt_line(COMMAND_HAVE + b' ' + have + b'\n') if 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') 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) 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_contents, - progress=None, write_pack=write_pack_objects): + 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_contents: Function that can return a sequence of - the shas of the objects to upload. + :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 - :param write_pack: Function called with (file, iterable of objects) to - write the objects returned by generate_pack_contents to the server. :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) with proto: old_refs, server_capabilities = read_pkt_refs(proto) 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: + 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 - objects = generate_pack_contents(have, want) + pack_data_count, pack_data = generate_pack_data( + have, want, + ofs_delta=(CAPABILITY_OFS_DELTA in negotiated_capabilities)) - dowrite = len(objects) > 0 + 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(proto.write_file(), objects) + 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): """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) :return: FetchPackResult object """ proto, can_read = self._connect(b'upload-pack', path) with proto: refs, server_capabilities = read_pkt_refs(proto) 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: + 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) self._handle_upload_pack_tail( proto, negotiated_capabilities, graph_walker, pack_data, progress) return FetchPackResult(refs, symrefs, agent) 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) with proto: refs, _ = read_pkt_refs(proto) proto.write_pkt_line(None) return refs def archive(self, path, committish, write_data, progress=None, write_error=None): proto, can_read = self._connect(b'upload-archive', path) with proto: proto.write_pkt_line(b"argument " + committish) proto.write_pkt_line(None) pkt = proto.read_pkt_line() if pkt == b"NACK\n": return elif pkt == b"ACK\n": pass elif pkt.startswith(b"ERR "): raise GitProtocolError(pkt[4:].rstrip(b"\n")) 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: 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) 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 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, stdout=subprocess.PIPE, stderr=self._stderr)) return Protocol(p.read, p.write, p.close, report_activity=self._report_activity), p.can_read 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_contents, - progress=None, write_pack=write_pack_objects): + 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_contents: Function that can return a sequence of - the shas of the objects to upload. + :param generate_pack_data: Function that can return a tuple + with number of items and pack data to upload. :param progress: Optional progress function - :param write_pack: Function called with (file, iterable of objects) to - write the objects returned by generate_pack_contents to the server. :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_objects(generate_pack_contents(have, want)) + 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): """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 - :return: Dictionary with all remote refs (not just those fetched) + :return: FetchPackResult object """ with self._open_repo(path) as r: - return r.fetch(target, determine_wants=determine_wants, + refs = r.fetch(target, determine_wants=determine_wants, progress=progress) + return FetchPackResult(refs, r.refs.get_symrefs(), + agent_string()) def fetch_pack(self, path, determine_wants, graph_walker, pack_data, progress=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) :return: FetchPackResult object """ with self._open_repo(path) as r: objects_iter = r.fetch_objects( determine_wants, graph_walker, progress) 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) - write_pack_objects(ProtocolFile(None, pack_data), objects_iter) + 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): + 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) + 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): + 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): - # FIXME: This has no way to deal with passwords.. + def run_command(self, host, command, username=None, port=None, + password=None, key_filename=None): + + if password: + raise NotImplementedError( + "You can't set password or passphrase for ssh key " + "with SubprocessSSHVendor, use ParamikoSSHVendor instead" + ) + args = ['ssh', '-x'] - if port is not None: + + if port: args.extend(['-p', str(port)]) - if username is not None: + + 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) + return SubprocessWrapper(proc) + + +class PuttySSHVendor(SSHVendor): + """SSH vendor that shells out to the local 'putty' command.""" + + def run_command(self, host, command, username=None, port=None, + password=None, key_filename=None): + + if password and key_filename: + raise NotImplementedError( + "You can't set passphrase for ssh key " + "with PuttySSHVendor, use ParamikoSSHVendor instead" + ) + + if sys.platform == 'win32': + args = ['putty.exe', '-ssh'] + else: + args = ['putty', '-ssh'] + + if password: + import warnings + warnings.warn( + "Invoking Putty 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) 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, **kwargs): + 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 + "'") con = self.ssh_vendor.run_command( - self.host, argv, port=self.port, username=self.username) + self.host, argv, port=self.port, username=self.username, + password=self.password, key_filename=self.key_filename) return (Protocol(con.read, con.write, con.close, report_activity=self._report_activity), con.can_read) 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_urllib2_opener(config): +def default_urllib3_manager(config, verify_ssl=True): + """Return `urllib3` connection pool manager. + + Honour detected proxy configurations. + + :param config: `dulwich.config.ConfigDict` instance with Git configuration. + :param verify_ssl: Whether SSL verification is enabled. + :return: `urllib3.ProxyManager` instance for proxy configurations, + `urllib3.PoolManager` otherwise. + """ + proxy_server = user_agent = None + if config is not None: try: proxy_server = config.get(b"http", b"proxy") except KeyError: - proxy_server = None - else: - proxy_server = None - handlers = [] - if proxy_server is not None: - handlers.append(urllib2.ProxyHandler({"http": proxy_server})) - opener = urllib2.build_opener(*handlers) - if config is not None: + pass try: user_agent = config.get(b"http", b"useragent") except KeyError: - user_agent = None - else: - user_agent = None + pass + + ssl_kwargs = {} + if verify_ssl: + ssl_kwargs.update(cert_reqs="CERT_REQUIRED", ca_certs=certifi.where()) + if user_agent is None: user_agent = default_user_agent_string() - opener.addheaders = [('User-agent', user_agent)] - return opener + + headers = {"User-agent": user_agent} + + 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, + **ssl_kwargs) + else: + manager = urllib3.PoolManager(headers=headers, **ssl_kwargs) + + return manager class HttpGitClient(GitClient): - def __init__(self, base_url, dumb=None, opener=None, config=None, + 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 - if opener is None: - self.opener = default_urllib2_opener(config) + self.headers = {} + + if pool_manager is None: + self.pool_manager = default_urllib3_manager(config) else: - self.opener = opener + self.pool_manager = pool_manager + if username is not None: - pass_man = urllib2.HTTPPasswordMgrWithDefaultRealm() - pass_man.add_password(None, base_url, username, password) - self.opener.add_handler(urllib2.HTTPBasicAuthHandler(pass_man)) + # No escaping needed: ":" is not allowed in username: + # https://tools.ietf.org/html/rfc2617#section-2 + credentials = "%s:%s" % (username, password) + 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): auth, host = urllib2.splituser(parsedurl.netloc) password = parsedurl.password if password is not None: 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=host) return cls(urlparse.urlunparse(parsedurl), password=password, username=username, **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={}, data=None, + def _http_request(self, url, headers=None, data=None, allow_compression=False): - if headers is None: - headers = dict(headers.items()) - headers["Pragma"] = "no-cache" + """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: - headers["Accept-Encoding"] = "gzip" + req_headers["Accept-Encoding"] = "gzip" else: - headers["Accept-Encoding"] = "identity" - req = urllib2.Request(url, headers=headers, data=data) - try: - resp = self.opener.open(req) - except urllib2.HTTPError as e: - if e.code == 404: - raise NotGitRepository() - if e.code != 200: - raise GitProtocolError("unexpected http response %d for %s" % - (e.code, url)) - if resp.info().get('Content-Encoding') == 'gzip': - read = gzip.GzipFile(fileobj=BytesIO(resp.read())).read + req_headers["Accept-Encoding"] = "identity" + + if data is None: + resp = self.pool_manager.request("GET", url, headers=req_headers) else: - read = resp.read + 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 + + 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 False: tail += "?service=%s" % service.decode('ascii') url = urlparse.urljoin(base_url, tail) resp, read = self._http_request(url, headers, allow_compression=True) - if url != resp.geturl(): + if resp.redirect_location: # Something changed (redirect!), so let's update the base URL - if not resp.geturl().endswith(tail): + if not resp.redirect_location.endswith(tail): raise GitProtocolError( "Redirected from URL %s to URL %s without %s" % ( - url, resp.geturl(), tail)) - base_url = resp.geturl()[:-len(tail)] + url, resp.redirect_location, tail)) + base_url = resp.redirect_location[:-len(tail)] try: - content_type = resp.info().gettype() - except AttributeError: - content_type = resp.info().get_content_type() - try: - self.dumb = (not content_type.startswith("application/x-git-")) + 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 + "Content-Type": "application/x-%s-request" % service, + "Accept": result_content_type, + "Content-Length": str(len(data)), } resp, read = self._http_request(url, headers, data) - try: - content_type = resp.info().gettype() - except AttributeError: - content_type = resp.info().get_content_type() - if content_type != ( - "application/x-%s-result" % service): + if resp.content_type != result_content_type: raise GitProtocolError("Invalid content-type from server: %s" - % content_type) + % resp.content_type) return resp, read - def send_pack(self, path, update_refs, generate_pack_contents, - progress=None, write_pack=write_pack_objects): + 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_contents: Function that can return a sequence of - the shas of the objects to upload. + :param generate_pack_data: Function that can return a tuple + with number of elements and pack data to upload. :param progress: Optional progress function - :param write_pack: Function called with (file, iterable of objects) to - write the objects returned by generate_pack_contents to the server. :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 - objects = generate_pack_contents(have, want) - if len(objects) > 0: - write_pack(req_proto.write_file(), objects) + 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(resp.read, None) + 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): """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) :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) req_data = BytesIO() req_proto = Protocol(None, req_data.write) self._handle_upload_pack_head( req_proto, negotiated_capabilities, graph_walker, wants, lambda: False) resp, read = self._smart_request( "git-upload-pack", url, data=req_data.getvalue()) try: resp_proto = Protocol(read, None) self._handle_upload_pack_tail( resp_proto, negotiated_capabilities, graph_walker, pack_data, progress) return FetchPackResult(refs, symrefs, agent) 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 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 if ':' in location and '@' not in location: # SSH with no user@, zero or one leading slash. (hostname, path) = location.split(':', 1) return SSHGitClient(hostname, **kwargs), path 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 return SSHGitClient(host, username=user, **kwargs), path # Otherwise, assume it's a local path. return default_local_git_client_cls(**kwargs), location diff --git a/dulwich/config.py b/dulwich/config.py index f11cf3da..08ab0704 100644 --- a/dulwich/config.py +++ b/dulwich/config.py @@ -1,449 +1,543 @@ # 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, ) 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): + def __init__(self, values=None, encoding=None): """Create a new ConfigDict.""" - if values is None: - values = OrderedDict() - self._values = values + 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 get(self, section, name): + 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): - if not isinstance(section, tuple): - section = (section, ) - if not isinstance(name, bytes): - raise TypeError(name) + section, name = self._check_section_and_name(section, name) + if type(value) not in (bool, bytes): - raise TypeError(value) - self._values.setdefault(section, OrderedDict())[name] = value + value = value.encode(self.encoding) + + self._values.setdefault(section)[name] = value def iteritems(self, section): - return self._values.get(section, OrderedDict()).items() + 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): - line = line.split(b"#")[0] - line = line.split(b";")[0] + 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() - last = line.index(b"]") - if last == -1: + try: + last = line.index(b"]") + except ValueError: raise ValueError("expected trailing ]") pts = line[1:last].split(b" ", 1) line = line[last+1:] - pts[0] = pts[0].lower() 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[section] = OrderedDict() + 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().lower() + 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/paramiko_vendor.py b/dulwich/contrib/paramiko_vendor.py index 13c0162a..00d7f215 100644 --- a/dulwich/contrib/paramiko_vendor.py +++ b/dulwich/contrib/paramiko_vendor.py @@ -1,138 +1,152 @@ # 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): 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 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 # 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): - self.ssh_kwargs = {} + def __init__(self, **kwargs): + self.kwargs = kwargs - def run_command(self, host, command, username=None, port=None, - progress_stderr=None): - # Paramiko needs an explicit port. None is not valid - if port is None: - port = 22 + 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(host, username=username, port=port, - **self.ssh_kwargs) + 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) diff --git a/dulwich/contrib/swift.py b/dulwich/contrib/swift.py index 2e792e4f..a106bb18 100644 --- a/dulwich/contrib/swift.py +++ b/dulwich/contrib/swift.py @@ -1,1052 +1,1052 @@ # swift.py -- Repo implementation atop OpenStack SWIFT # Copyright (C) 2013 eNovance SAS # # Author: Fabien Boucher # # 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. # """Repo implementation atop OpenStack SWIFT.""" # TODO: Refactor to share more code with dulwich/repo.py. # TODO(fbo): Second attempt to _send() must be notified via real log # TODO(fbo): More logs for operations import os import stat import zlib import tempfile import posixpath try: import urlparse except ImportError: import urllib.parse as urlparse from io import BytesIO try: from ConfigParser import ConfigParser except ImportError: from configparser import ConfigParser from geventhttpclient import HTTPClient from dulwich.greenthreads import ( GreenThreadsMissingObjectFinder, GreenThreadsObjectStoreIterator, ) from dulwich.lru_cache import LRUSizeCache from dulwich.objects import ( Blob, Commit, Tree, Tag, S_ISGITLINK, ) from dulwich.object_store import ( PackBasedObjectStore, PACKDIR, INFODIR, ) from dulwich.pack import ( PackData, Pack, PackIndexer, PackStreamCopier, write_pack_header, compute_file_sha, iter_sha1, write_pack_index_v2, load_pack_index_file, read_pack_header, _compute_object_size, unpack_object, write_pack_object, ) from dulwich.protocol import TCP_GIT_PORT from dulwich.refs import ( InfoRefsContainer, read_info_refs, write_info_refs, ) from dulwich.repo import ( BaseRepo, OBJECTDIR, ) from dulwich.server import ( Backend, TCPGitServer, ) try: from simplejson import loads as json_loads from simplejson import dumps as json_dumps except ImportError: from json import loads as json_loads from json import dumps as json_dumps import sys """ # Configuration file sample [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 """ class PackInfoObjectStoreIterator(GreenThreadsObjectStoreIterator): def __len__(self): while len(self.finder.objects_to_send): for _ in range(0, len(self.finder.objects_to_send)): sha = self.finder.next() self._shas.append(sha) return len(self._shas) class PackInfoMissingObjectFinder(GreenThreadsMissingObjectFinder): 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: info = self.object_store.pack_info_get(sha) if info[0] == Commit.type_num: self.add_todo([(info[2], "", False)]) elif info[0] == Tree.type_num: self.add_todo([tuple(i) for i in info[1]]) elif info[0] == Tag.type_num: self.add_todo([(info[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)) return (sha, name) def load_conf(path=None, file=None): """Load configuration in global var CONF :param path: The path to the configuration file :param file: If provided read instead the file like object """ conf = ConfigParser() if file: try: conf.read_file(file, path) except AttributeError: # read_file only exists in Python3 conf.readfp(file) return conf confpath = None if not path: try: confpath = os.environ['DULWICH_SWIFT_CFG'] except KeyError: raise Exception("You need to specify a configuration file") else: confpath = path if not os.path.isfile(confpath): raise Exception("Unable to read configuration file %s" % confpath) conf.read(confpath) return conf def swift_load_pack_index(scon, filename): """Read a pack index file from Swift :param scon: a `SwiftConnector` instance :param filename: Path to the index file objectise :return: a `PackIndexer` instance """ f = scon.get_object(filename) try: return load_pack_index_file(filename, f) finally: f.close() def pack_info_create(pack_data, pack_index): pack = Pack.from_objects(pack_data, pack_index) info = {} for obj in pack.iterobjects(): # Commit if obj.type_num == Commit.type_num: info[obj.id] = (obj.type_num, obj.parents, obj.tree) # Tree elif obj.type_num == Tree.type_num: shas = [(s, n, not stat.S_ISDIR(m)) for n, m, s in obj.items() if not S_ISGITLINK(m)] info[obj.id] = (obj.type_num, shas) # Blob elif obj.type_num == Blob.type_num: info[obj.id] = None # Tag elif obj.type_num == Tag.type_num: info[obj.id] = (obj.type_num, obj.object[1]) return zlib.compress(json_dumps(info)) def load_pack_info(filename, scon=None, file=None): if not file: f = scon.get_object(filename) else: f = file if not f: return None try: return json_loads(zlib.decompress(f.read())) finally: f.close() class SwiftException(Exception): pass class SwiftConnector(object): """A Connector to swift that manage authentication and errors catching """ def __init__(self, root, conf): """ Initialize a SwiftConnector :param root: The swift container that will act as Git bare repository :param conf: A ConfigParser Object """ self.conf = conf self.auth_ver = self.conf.get("swift", "auth_ver") if self.auth_ver not in ["1", "2"]: raise NotImplementedError( "Wrong authentication version use either 1 or 2") self.auth_url = self.conf.get("swift", "auth_url") self.user = self.conf.get("swift", "username") self.password = self.conf.get("swift", "password") self.concurrency = self.conf.getint('swift', 'concurrency') or 10 self.http_timeout = self.conf.getint('swift', 'http_timeout') or 20 self.http_pool_length = \ self.conf.getint('swift', 'http_pool_length') or 10 self.region_name = self.conf.get("swift", "region_name") or "RegionOne" self.endpoint_type = \ self.conf.get("swift", "endpoint_type") or "internalURL" self.cache_length = self.conf.getint("swift", "cache_length") or 20 self.chunk_length = self.conf.getint("swift", "chunk_length") or 12228 self.root = root block_size = 1024 * 12 # 12KB if self.auth_ver == "1": self.storage_url, self.token = self.swift_auth_v1() else: self.storage_url, self.token = self.swift_auth_v2() token_header = {'X-Auth-Token': str(self.token)} self.httpclient = \ HTTPClient.from_url(str(self.storage_url), concurrency=self.http_pool_length, block_size=block_size, connection_timeout=self.http_timeout, network_timeout=self.http_timeout, headers=token_header) self.base_path = str(posixpath.join( urlparse.urlparse(self.storage_url).path, self.root)) def swift_auth_v1(self): self.user = self.user.replace(";", ":") auth_httpclient = HTTPClient.from_url( self.auth_url, connection_timeout=self.http_timeout, network_timeout=self.http_timeout, ) headers = {'X-Auth-User': self.user, 'X-Auth-Key': self.password} path = urlparse.urlparse(self.auth_url).path ret = auth_httpclient.request('GET', path, headers=headers) # Should do something with redirections (301 in my case) if ret.status_code < 200 or ret.status_code >= 300: raise SwiftException('AUTH v1.0 request failed on ' + '%s with error code %s (%s)' % (str(auth_httpclient.get_base_url()) + path, ret.status_code, str(ret.items()))) storage_url = ret['X-Storage-Url'] token = ret['X-Auth-Token'] return storage_url, token def swift_auth_v2(self): self.tenant, self.user = self.user.split(';') auth_dict = {} auth_dict['auth'] = {'passwordCredentials': { 'username': self.user, 'password': self.password, }, 'tenantName': self.tenant} auth_json = json_dumps(auth_dict) headers = {'Content-Type': 'application/json'} auth_httpclient = HTTPClient.from_url( self.auth_url, connection_timeout=self.http_timeout, network_timeout=self.http_timeout, ) path = urlparse.urlparse(self.auth_url).path if not path.endswith('tokens'): path = posixpath.join(path, 'tokens') ret = auth_httpclient.request('POST', path, body=auth_json, headers=headers) if ret.status_code < 200 or ret.status_code >= 300: raise SwiftException('AUTH v2.0 request failed on ' + '%s with error code %s (%s)' % (str(auth_httpclient.get_base_url()) + path, ret.status_code, str(ret.items()))) auth_ret_json = json_loads(ret.read()) token = auth_ret_json['access']['token']['id'] catalogs = auth_ret_json['access']['serviceCatalog'] object_store = [o_store for o_store in catalogs if o_store['type'] == 'object-store'][0] endpoints = object_store['endpoints'] endpoint = [endp for endp in endpoints if endp["region"] == self.region_name][0] return endpoint[self.endpoint_type], token def test_root_exists(self): """Check that Swift container exist :return: True if exist or None it not """ ret = self.httpclient.request('HEAD', self.base_path) if ret.status_code == 404: return None if ret.status_code < 200 or ret.status_code > 300: raise SwiftException('HEAD request failed with error code %s' % ret.status_code) return True def create_root(self): """Create the Swift container :raise: `SwiftException` if unable to create """ if not self.test_root_exists(): ret = self.httpclient.request('PUT', self.base_path) if ret.status_code < 200 or ret.status_code > 300: raise SwiftException('PUT request failed with error code %s' % ret.status_code) def get_container_objects(self): """Retrieve objects list in a container :return: A list of dict that describe objects or None if container does not exist """ qs = '?format=json' path = self.base_path + qs ret = self.httpclient.request('GET', path) if ret.status_code == 404: return None if ret.status_code < 200 or ret.status_code > 300: raise SwiftException('GET request failed with error code %s' % ret.status_code) content = ret.read() return json_loads(content) def get_object_stat(self, name): """Retrieve object stat :param name: The object name :return: A dict that describe the object or None if object does not exist """ path = self.base_path + '/' + name ret = self.httpclient.request('HEAD', path) if ret.status_code == 404: return None if ret.status_code < 200 or ret.status_code > 300: raise SwiftException('HEAD request failed with error code %s' % ret.status_code) resp_headers = {} for header, value in ret.items(): resp_headers[header.lower()] = value return resp_headers def put_object(self, name, content): """Put an object :param name: The object name :param content: A file object :raise: `SwiftException` if unable to create """ content.seek(0) data = content.read() path = self.base_path + '/' + name headers = {'Content-Length': str(len(data))} def _send(): ret = self.httpclient.request('PUT', path, body=data, headers=headers) return ret try: # Sometime got Broken Pipe - Dirty workaround ret = _send() except Exception: # Second attempt work ret = _send() if ret.status_code < 200 or ret.status_code > 300: raise SwiftException('PUT request failed with error code %s' % ret.status_code) def get_object(self, name, range=None): """Retrieve an object :param name: The object name :param range: A string range like "0-10" to retrieve specified bytes in object content :return: A file like instance or bytestring if range is specified """ headers = {} if range: headers['Range'] = 'bytes=%s' % range path = self.base_path + '/' + name ret = self.httpclient.request('GET', path, headers=headers) if ret.status_code == 404: return None if ret.status_code < 200 or ret.status_code > 300: raise SwiftException('GET request failed with error code %s' % ret.status_code) content = ret.read() if range: return content return BytesIO(content) def del_object(self, name): """Delete an object :param name: The object name :raise: `SwiftException` if unable to delete """ path = self.base_path + '/' + name ret = self.httpclient.request('DELETE', path) if ret.status_code < 200 or ret.status_code > 300: raise SwiftException('DELETE request failed with error code %s' % ret.status_code) def del_root(self): """Delete the root container by removing container content :raise: `SwiftException` if unable to delete """ for obj in self.get_container_objects(): self.del_object(obj['name']) ret = self.httpclient.request('DELETE', self.base_path) if ret.status_code < 200 or ret.status_code > 300: raise SwiftException('DELETE request failed with error code %s' % ret.status_code) class SwiftPackReader(object): """A SwiftPackReader that mimic read and sync method The reader allows to read a specified amount of bytes from a given offset of a Swift object. A read offset is kept internaly. The reader will read from Swift a specified amount of data to complete its internal buffer. chunk_length specifiy the amount of data to read from Swift. """ def __init__(self, scon, filename, pack_length): """Initialize a SwiftPackReader :param scon: a `SwiftConnector` instance :param filename: the pack filename :param pack_length: The size of the pack object """ self.scon = scon self.filename = filename self.pack_length = pack_length self.offset = 0 self.base_offset = 0 self.buff = b'' self.buff_length = self.scon.chunk_length def _read(self, more=False): if more: self.buff_length = self.buff_length * 2 - l = self.base_offset + offset = self.base_offset r = min(self.base_offset + self.buff_length, self.pack_length) - ret = self.scon.get_object(self.filename, range="%s-%s" % (l, r)) + ret = self.scon.get_object(self.filename, range="%s-%s" % (offset, r)) self.buff = ret def read(self, length): """Read a specified amount of Bytes form the pack object :param length: amount of bytes to read :return: bytestring """ end = self.offset+length if self.base_offset + end > self.pack_length: data = self.buff[self.offset:] self.offset = end return data if end > len(self.buff): # Need to read more from swift self._read(more=True) return self.read(length) data = self.buff[self.offset:end] self.offset = end return data def seek(self, offset): """Seek to a specified offset :param offset: the offset to seek to """ self.base_offset = offset self._read() self.offset = 0 def read_checksum(self): """Read the checksum from the pack :return: the checksum bytestring """ return self.scon.get_object(self.filename, range="-20") class SwiftPackData(PackData): """The data contained in a packfile. We use the SwiftPackReader to read bytes from packs stored in Swift using the Range header feature of Swift. """ def __init__(self, scon, filename): """ Initialize a SwiftPackReader :param scon: a `SwiftConnector` instance :param filename: the pack filename """ self.scon = scon self._filename = filename self._header_size = 12 headers = self.scon.get_object_stat(self._filename) self.pack_length = int(headers['content-length']) pack_reader = SwiftPackReader(self.scon, self._filename, self.pack_length) (version, self._num_objects) = read_pack_header(pack_reader.read) self._offset_cache = LRUSizeCache(1024*1024*self.scon.cache_length, compute_size=_compute_object_size) self.pack = None def get_object_at(self, offset): if offset in self._offset_cache: return self._offset_cache[offset] assert offset >= self._header_size pack_reader = SwiftPackReader(self.scon, self._filename, self.pack_length) pack_reader.seek(offset) unpacked, _ = unpack_object(pack_reader.read) return (unpacked.pack_type_num, unpacked._obj()) def get_stored_checksum(self): pack_reader = SwiftPackReader(self.scon, self._filename, self.pack_length) return pack_reader.read_checksum() def close(self): pass class SwiftPack(Pack): """A Git pack object. Same implementation as pack.Pack except that _idx_load and _data_load are bounded to Swift version of load_pack_index and PackData. """ def __init__(self, *args, **kwargs): self.scon = kwargs['scon'] del kwargs['scon'] super(SwiftPack, self).__init__(*args, **kwargs) self._pack_info_path = self._basename + '.info' self._pack_info = None self._pack_info_load = lambda: load_pack_info(self._pack_info_path, self.scon) self._idx_load = lambda: swift_load_pack_index(self.scon, self._idx_path) self._data_load = lambda: SwiftPackData(self.scon, self._data_path) @property def pack_info(self): """The pack data object being used.""" if self._pack_info is None: self._pack_info = self._pack_info_load() return self._pack_info class SwiftObjectStore(PackBasedObjectStore): """A Swift Object Store Allow to manage a bare Git repository from Openstack Swift. This object store only supports pack files and not loose objects. """ def __init__(self, scon): """Open a Swift object store. :param scon: A `SwiftConnector` instance """ super(SwiftObjectStore, self).__init__() self.scon = scon self.root = self.scon.root self.pack_dir = posixpath.join(OBJECTDIR, PACKDIR) self._alternates = None @property def packs(self): """List with pack objects.""" if not self._pack_cache: self._update_pack_cache() return self._pack_cache.values() def _update_pack_cache(self): for pack in self._load_packs(): self._pack_cache[pack._basename] = pack def _iter_loose_objects(self): """Loose objects are not supported by this repository """ return [] def iter_shas(self, finder): """An iterator over pack's ObjectStore. :return: a `ObjectStoreIterator` or `GreenThreadsObjectStoreIterator` instance if gevent is enabled """ shas = iter(finder.next, None) return PackInfoObjectStoreIterator( self, shas, finder, self.scon.concurrency) def find_missing_objects(self, *args, **kwargs): kwargs['concurrency'] = self.scon.concurrency return PackInfoMissingObjectFinder(self, *args, **kwargs) def _load_packs(self): """Load all packs from Swift :return: a list of `SwiftPack` instances """ objects = self.scon.get_container_objects() pack_files = [o['name'].replace(".pack", "") for o in objects if o['name'].endswith(".pack")] return [SwiftPack(pack, scon=self.scon) for pack in pack_files] def pack_info_get(self, sha): for pack in self.packs: if sha in pack: return pack.pack_info[sha] def _collect_ancestors(self, heads, common=set()): def _find_parents(commit): for pack in self.packs: if commit in pack: try: parents = pack.pack_info[commit][1] except KeyError: # Seems to have no parents return [] return parents 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) parents = _find_parents(e) queue.extend(parents) return (commits, bases) def add_pack(self): """Add a new pack to this object store. :return: Fileobject to write to and a commit function to call when the pack is finished. """ f = BytesIO() def commit(): f.seek(0) pack = PackData(file=f, filename="") entries = pack.sorted_entries() if len(entries): basename = posixpath.join(self.pack_dir, "pack-%s" % iter_sha1(entry[0] for entry in entries)) index = BytesIO() write_pack_index_v2(index, entries, pack.get_stored_checksum()) self.scon.put_object(basename + ".pack", f) f.close() self.scon.put_object(basename + ".idx", index) index.close() final_pack = SwiftPack(basename, scon=self.scon) final_pack.check_length_and_checksum() self._add_known_pack(basename, final_pack) return final_pack else: return None def abort(): pass return f, commit, abort def add_object(self, obj): self.add_objects([(obj, None), ]) def _pack_cache_stale(self): return False def _get_loose_object(self, sha): return None def add_thin_pack(self, read_all, read_some): """Read a thin pack Read it from a stream and complete it in a temporary file. Then the pack and the corresponding index file are uploaded to Swift. """ fd, path = tempfile.mkstemp(prefix='tmp_pack_') f = os.fdopen(fd, 'w+b') try: 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) finally: f.close() os.unlink(path) def _complete_thin_pack(self, f, path, copier, indexer): 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.flush() # Move the pack in. entries.sort() pack_base_name = posixpath.join( self.pack_dir, 'pack-' + iter_sha1(e[0] for e in entries).decode( sys.getfilesystemencoding())) self.scon.put_object(pack_base_name + '.pack', f) # Write the index. filename = pack_base_name + '.idx' index_file = BytesIO() write_pack_index_v2(index_file, entries, pack_sha) self.scon.put_object(filename, index_file) # Write pack info. f.seek(0) pack_data = PackData(filename="", file=f) index_file.seek(0) pack_index = load_pack_index_file('', index_file) serialized_pack_info = pack_info_create(pack_data, pack_index) f.close() index_file.close() pack_info_file = BytesIO(serialized_pack_info) filename = pack_base_name + '.info' self.scon.put_object(filename, pack_info_file) pack_info_file.close() # Add the pack to the store and return it. final_pack = SwiftPack(pack_base_name, scon=self.scon) final_pack.check_length_and_checksum() self._add_known_pack(pack_base_name, final_pack) return final_pack class SwiftInfoRefsContainer(InfoRefsContainer): """Manage references in info/refs object. """ def __init__(self, scon, store): self.scon = scon self.filename = 'info/refs' self.store = store f = self.scon.get_object(self.filename) if not f: f = BytesIO(b'') super(SwiftInfoRefsContainer, self).__init__(f) def _load_check_ref(self, name, old_ref): self._check_refname(name) f = self.scon.get_object(self.filename) if not f: return {} refs = read_info_refs(f) if old_ref is not None: if refs[name] != old_ref: return False return refs def _write_refs(self, refs): f = BytesIO() f.writelines(write_info_refs(refs, self.store)) self.scon.put_object(self.filename, f) def set_if_equals(self, name, old_ref, new_ref): """Set a refname to new_ref only if it currently equals old_ref. """ if name == 'HEAD': return True refs = self._load_check_ref(name, old_ref) if not isinstance(refs, dict): return False refs[name] = new_ref self._write_refs(refs) self._refs[name] = new_ref return True def remove_if_equals(self, name, old_ref): """Remove a refname only if it currently equals old_ref. """ if name == 'HEAD': return True refs = self._load_check_ref(name, old_ref) if not isinstance(refs, dict): return False del refs[name] self._write_refs(refs) del self._refs[name] return True def allkeys(self): try: self._refs['HEAD'] = self._refs['refs/heads/master'] except KeyError: pass return self._refs.keys() class SwiftRepo(BaseRepo): def __init__(self, root, conf): """Init a Git bare Repository on top of a Swift container. References are managed in info/refs objects by `SwiftInfoRefsContainer`. The root attribute is the Swift container that contain the Git bare repository. :param root: The container which contains the bare repo :param conf: A ConfigParser object """ self.root = root.lstrip('/') self.conf = conf self.scon = SwiftConnector(self.root, self.conf) objects = self.scon.get_container_objects() if not objects: raise Exception('There is not any GIT repo here : %s' % self.root) objects = [o['name'].split('/')[0] for o in objects] if OBJECTDIR not in objects: raise Exception('This repository (%s) is not bare.' % self.root) self.bare = True self._controldir = self.root object_store = SwiftObjectStore(self.scon) refs = SwiftInfoRefsContainer(self.scon, object_store) BaseRepo.__init__(self, object_store, refs) 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 False def _put_named_file(self, filename, contents): """Put an object in a Swift container :param filename: the path to the object to put on Swift :param contents: the content as bytestring """ f = BytesIO() f.write(contents) self.scon.put_object(filename, f) f.close() @classmethod def init_bare(cls, scon, conf): """Create a new bare repository. :param scon: a `SwiftConnector` instance :param conf: a ConfigParser object :return: a `SwiftRepo` instance """ scon.create_root() for obj in [posixpath.join(OBJECTDIR, PACKDIR), posixpath.join(INFODIR, 'refs')]: scon.put_object(obj, BytesIO(b'')) ret = cls(scon.root, conf) ret._init_files(True) return ret class SwiftSystemBackend(Backend): def __init__(self, logger, conf): self.conf = conf self.logger = logger def open_repository(self, path): self.logger.info('opening repository at %s', path) return SwiftRepo(path, self.conf) def cmd_daemon(args): """Entry point for starting a TCP git server.""" import optparse parser = optparse.OptionParser() parser.add_option("-l", "--listen_address", dest="listen_address", default="127.0.0.1", help="Binding IP address.") parser.add_option("-p", "--port", dest="port", type=int, default=TCP_GIT_PORT, help="Binding TCP port.") parser.add_option("-c", "--swift_config", dest="swift_config", default="", help="Path to the configuration file for Swift backend.") options, args = parser.parse_args(args) try: import gevent import geventhttpclient # noqa: F401 except ImportError: print("gevent and geventhttpclient libraries are mandatory " " for use the Swift backend.") sys.exit(1) import gevent.monkey gevent.monkey.patch_socket() from dulwich.contrib.swift import load_conf from dulwich import log_utils logger = log_utils.getLogger(__name__) conf = load_conf(options.swift_config) backend = SwiftSystemBackend(logger, conf) log_utils.default_logging_config() server = TCPGitServer(backend, options.listen_address, port=options.port) server.serve_forever() def cmd_init(args): import optparse parser = optparse.OptionParser() parser.add_option("-c", "--swift_config", dest="swift_config", default="", help="Path to the configuration file for Swift backend.") options, args = parser.parse_args(args) conf = load_conf(options.swift_config) if args == []: parser.error("missing repository name") repo = args[0] scon = SwiftConnector(repo, conf) SwiftRepo.init_bare(scon, conf) def main(argv=sys.argv): commands = { "init": cmd_init, "daemon": cmd_daemon, } if len(sys.argv) < 2: print("Usage: %s <%s> [OPTIONS...]" % ( sys.argv[0], "|".join(commands.keys()))) sys.exit(1) cmd = sys.argv[1] if cmd not in commands: print("No such subcommand: %s" % cmd) sys.exit(1) commands[cmd](sys.argv[2:]) if __name__ == '__main__': main() diff --git a/dulwich/contrib/test_swift_smoke.py b/dulwich/contrib/test_swift_smoke.py index 71d29deb..2ab960c3 100644 --- a/dulwich/contrib/test_swift_smoke.py +++ b/dulwich/contrib/test_swift_smoke.py @@ -1,317 +1,317 @@ # test_smoke.py -- Functional tests for the Swift backend. # Copyright (C) 2013 eNovance SAS # # Author: Fabien Boucher # # 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. # """Start functional tests A Swift installation must be available before starting those tests. The account and authentication method used during this functional tests must be changed in the configuration file passed as environment variable. The container used to create a fake repository is defined in cls.fakerepo and will be deleted after the tests. DULWICH_SWIFT_CFG=/tmp/conf.cfg PYTHONPATH=. python -m unittest \ dulwich.tests_swift.test_smoke """ import os import unittest import tempfile import shutil import gevent from gevent import monkey monkey.patch_all() from dulwich import ( # noqa:E402 server, repo, index, client, objects, ) from dulwich.contrib import swift # noqa:E402 class DulwichServer(): """Start the TCPGitServer with Swift backend """ def __init__(self, backend, port): self.port = port self.backend = backend def run(self): self.server = server.TCPGitServer(self.backend, 'localhost', port=self.port) self.job = gevent.spawn(self.server.serve_forever) def stop(self): self.server.shutdown() gevent.joinall((self.job,)) class SwiftSystemBackend(server.Backend): def open_repository(self, path): return swift.SwiftRepo(path, conf=swift.load_conf()) class SwiftRepoSmokeTest(unittest.TestCase): @classmethod def setUpClass(cls): cls.backend = SwiftSystemBackend() cls.port = 9148 cls.server_address = 'localhost' cls.fakerepo = 'fakerepo' cls.th_server = DulwichServer(cls.backend, cls.port) cls.th_server.run() cls.conf = swift.load_conf() @classmethod def tearDownClass(cls): cls.th_server.stop() def setUp(self): self.scon = swift.SwiftConnector(self.fakerepo, self.conf) if self.scon.test_root_exists(): try: self.scon.del_root() except swift.SwiftException: pass self.temp_d = tempfile.mkdtemp() if os.path.isdir(self.temp_d): shutil.rmtree(self.temp_d) def tearDown(self): if self.scon.test_root_exists(): try: self.scon.del_root() except swift.SwiftException: pass if os.path.isdir(self.temp_d): shutil.rmtree(self.temp_d) def test_init_bare(self): swift.SwiftRepo.init_bare(self.scon, self.conf) self.assertTrue(self.scon.test_root_exists()) obj = self.scon.get_container_objects() filtered = [o for o in obj if o['name'] == 'info/refs' or o['name'] == 'objects/pack'] self.assertEqual(len(filtered), 2) def test_clone_bare(self): local_repo = repo.Repo.init(self.temp_d, mkdir=True) swift.SwiftRepo.init_bare(self.scon, self.conf) tcp_client = client.TCPGitClient(self.server_address, port=self.port) remote_refs = tcp_client.fetch(self.fakerepo, local_repo) # The remote repo is empty (no refs retreived) self.assertEqual(remote_refs, None) def test_push_commit(self): def determine_wants(*args): return {"refs/heads/master": local_repo.refs["HEAD"]} local_repo = repo.Repo.init(self.temp_d, mkdir=True) # Nothing in the staging area local_repo.do_commit('Test commit', 'fbo@localhost') sha = local_repo.refs.read_loose_ref('refs/heads/master') swift.SwiftRepo.init_bare(self.scon, self.conf) tcp_client = client.TCPGitClient(self.server_address, port=self.port) tcp_client.send_pack(self.fakerepo, determine_wants, - local_repo.object_store.generate_pack_contents) + local_repo.object_store.generate_pack_data) swift_repo = swift.SwiftRepo("fakerepo", self.conf) remote_sha = swift_repo.refs.read_loose_ref('refs/heads/master') self.assertEqual(sha, remote_sha) def test_push_branch(self): def determine_wants(*args): return {"refs/heads/mybranch": local_repo.refs["refs/heads/mybranch"]} local_repo = repo.Repo.init(self.temp_d, mkdir=True) # Nothing in the staging area local_repo.do_commit('Test commit', 'fbo@localhost', ref='refs/heads/mybranch') sha = local_repo.refs.read_loose_ref('refs/heads/mybranch') swift.SwiftRepo.init_bare(self.scon, self.conf) tcp_client = client.TCPGitClient(self.server_address, port=self.port) tcp_client.send_pack("/fakerepo", determine_wants, - local_repo.object_store.generate_pack_contents) + local_repo.object_store.generate_pack_data) swift_repo = swift.SwiftRepo(self.fakerepo, self.conf) remote_sha = swift_repo.refs.read_loose_ref('refs/heads/mybranch') self.assertEqual(sha, remote_sha) def test_push_multiple_branch(self): def determine_wants(*args): return {"refs/heads/mybranch": local_repo.refs["refs/heads/mybranch"], "refs/heads/master": local_repo.refs["refs/heads/master"], "refs/heads/pullr-108": local_repo.refs["refs/heads/pullr-108"]} local_repo = repo.Repo.init(self.temp_d, mkdir=True) # Nothing in the staging area local_shas = {} remote_shas = {} for branch in ('master', 'mybranch', 'pullr-108'): local_shas[branch] = local_repo.do_commit( 'Test commit %s' % branch, 'fbo@localhost', ref='refs/heads/%s' % branch) swift.SwiftRepo.init_bare(self.scon, self.conf) tcp_client = client.TCPGitClient(self.server_address, port=self.port) tcp_client.send_pack(self.fakerepo, determine_wants, - local_repo.object_store.generate_pack_contents) + local_repo.object_store.generate_pack_data) swift_repo = swift.SwiftRepo("fakerepo", self.conf) for branch in ('master', 'mybranch', 'pullr-108'): remote_shas[branch] = swift_repo.refs.read_loose_ref( 'refs/heads/%s' % branch) self.assertDictEqual(local_shas, remote_shas) def test_push_data_branch(self): def determine_wants(*args): return {"refs/heads/master": local_repo.refs["HEAD"]} local_repo = repo.Repo.init(self.temp_d, mkdir=True) os.mkdir(os.path.join(self.temp_d, "dir")) files = ('testfile', 'testfile2', 'dir/testfile3') i = 0 for f in files: open(os.path.join(self.temp_d, f), 'w').write("DATA %s" % i) i += 1 local_repo.stage(files) local_repo.do_commit('Test commit', 'fbo@localhost', ref='refs/heads/master') swift.SwiftRepo.init_bare(self.scon, self.conf) tcp_client = client.TCPGitClient(self.server_address, port=self.port) tcp_client.send_pack(self.fakerepo, determine_wants, - local_repo.object_store.generate_pack_contents) + local_repo.object_store.generate_pack_data) swift_repo = swift.SwiftRepo("fakerepo", self.conf) commit_sha = swift_repo.refs.read_loose_ref('refs/heads/master') otype, data = swift_repo.object_store.get_raw(commit_sha) commit = objects.ShaFile.from_raw_string(otype, data) otype, data = swift_repo.object_store.get_raw(commit._tree) tree = objects.ShaFile.from_raw_string(otype, data) objs = tree.items() objs_ = [] for tree_entry in objs: objs_.append(swift_repo.object_store.get_raw(tree_entry.sha)) # Blob self.assertEqual(objs_[1][1], 'DATA 0') self.assertEqual(objs_[2][1], 'DATA 1') # Tree self.assertEqual(objs_[0][0], 2) def test_clone_then_push_data(self): self.test_push_data_branch() shutil.rmtree(self.temp_d) local_repo = repo.Repo.init(self.temp_d, mkdir=True) tcp_client = client.TCPGitClient(self.server_address, port=self.port) remote_refs = tcp_client.fetch(self.fakerepo, local_repo) files = (os.path.join(self.temp_d, 'testfile'), os.path.join(self.temp_d, 'testfile2')) local_repo["HEAD"] = remote_refs["refs/heads/master"] indexfile = local_repo.index_path() tree = local_repo["HEAD"].tree index.build_index_from_tree(local_repo.path, indexfile, local_repo.object_store, tree) for f in files: self.assertEqual(os.path.isfile(f), True) def determine_wants(*args): return {"refs/heads/master": local_repo.refs["HEAD"]} os.mkdir(os.path.join(self.temp_d, "test")) files = ('testfile11', 'testfile22', 'test/testfile33') i = 0 for f in files: open(os.path.join(self.temp_d, f), 'w').write("DATA %s" % i) i += 1 local_repo.stage(files) local_repo.do_commit('Test commit', 'fbo@localhost', ref='refs/heads/master') tcp_client.send_pack("/fakerepo", determine_wants, - local_repo.object_store.generate_pack_contents) + local_repo.object_store.generate_pack_data) def test_push_remove_branch(self): def determine_wants(*args): return {"refs/heads/pullr-108": objects.ZERO_SHA, "refs/heads/master": local_repo.refs['refs/heads/master'], "refs/heads/mybranch": local_repo.refs['refs/heads/mybranch'], } self.test_push_multiple_branch() local_repo = repo.Repo(self.temp_d) tcp_client = client.TCPGitClient(self.server_address, port=self.port) tcp_client.send_pack(self.fakerepo, determine_wants, - local_repo.object_store.generate_pack_contents) + local_repo.object_store.generate_pack_data) swift_repo = swift.SwiftRepo("fakerepo", self.conf) self.assertNotIn('refs/heads/pullr-108', swift_repo.refs.allkeys()) def test_push_annotated_tag(self): def determine_wants(*args): return {"refs/heads/master": local_repo.refs["HEAD"], "refs/tags/v1.0": local_repo.refs["refs/tags/v1.0"]} local_repo = repo.Repo.init(self.temp_d, mkdir=True) # Nothing in the staging area sha = local_repo.do_commit('Test commit', 'fbo@localhost') otype, data = local_repo.object_store.get_raw(sha) commit = objects.ShaFile.from_raw_string(otype, data) tag = objects.Tag() tag.tagger = "fbo@localhost" tag.message = "Annotated tag" tag.tag_timezone = objects.parse_timezone('-0200')[0] tag.tag_time = commit.author_time tag.object = (objects.Commit, commit.id) tag.name = "v0.1" local_repo.object_store.add_object(tag) local_repo.refs['refs/tags/v1.0'] = tag.id swift.SwiftRepo.init_bare(self.scon, self.conf) tcp_client = client.TCPGitClient(self.server_address, port=self.port) tcp_client.send_pack(self.fakerepo, determine_wants, - local_repo.object_store.generate_pack_contents) + local_repo.object_store.generate_pack_data) swift_repo = swift.SwiftRepo(self.fakerepo, self.conf) tag_sha = swift_repo.refs.read_loose_ref('refs/tags/v1.0') otype, data = swift_repo.object_store.get_raw(tag_sha) rtag = objects.ShaFile.from_raw_string(otype, data) self.assertEqual(rtag.object[1], commit.id) self.assertEqual(rtag.id, tag.id) if __name__ == '__main__': unittest.main() diff --git a/dulwich/diff_tree.py b/dulwich/diff_tree.py index 1cdc9890..167cb28e 100644 --- a/dulwich/diff_tree.py +++ b/dulwich/diff_tree.py @@ -1,600 +1,608 @@ # diff_tree.py -- Utilities for diffing files and trees. # 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. # """Utilities for diffing files and trees.""" import sys from collections import ( defaultdict, namedtuple, ) from io import BytesIO from itertools import chain import stat from dulwich.objects import ( S_ISGITLINK, TreeEntry, ) # TreeChange type constants. CHANGE_ADD = 'add' CHANGE_MODIFY = 'modify' CHANGE_DELETE = 'delete' CHANGE_RENAME = 'rename' CHANGE_COPY = 'copy' CHANGE_UNCHANGED = 'unchanged' RENAME_CHANGE_TYPES = (CHANGE_RENAME, CHANGE_COPY) _NULL_ENTRY = TreeEntry(None, None, None) _MAX_SCORE = 100 RENAME_THRESHOLD = 60 MAX_FILES = 200 REWRITE_THRESHOLD = None class TreeChange(namedtuple('TreeChange', ['type', 'old', 'new'])): """Named tuple a single change between two trees.""" @classmethod def add(cls, new): return cls(CHANGE_ADD, _NULL_ENTRY, new) @classmethod def delete(cls, old): return cls(CHANGE_DELETE, old, _NULL_ENTRY) def _tree_entries(path, tree): result = [] if not tree: return result for entry in tree.iteritems(name_order=True): result.append(entry.in_path(path)) return result def _merge_entries(path, tree1, tree2): """Merge the entries of two trees. :param path: A path to prepend to all tree entry names. :param tree1: The first Tree object to iterate, or None. :param tree2: The second Tree object to iterate, or None. :return: A list of pairs of TreeEntry objects for each pair of entries in the trees. If an entry exists in one tree but not the other, the other entry will have all attributes set to None. If neither entry's path is None, they are guaranteed to match. """ entries1 = _tree_entries(path, tree1) entries2 = _tree_entries(path, tree2) i1 = i2 = 0 len1 = len(entries1) len2 = len(entries2) result = [] while i1 < len1 and i2 < len2: entry1 = entries1[i1] entry2 = entries2[i2] if entry1.path < entry2.path: result.append((entry1, _NULL_ENTRY)) i1 += 1 elif entry1.path > entry2.path: result.append((_NULL_ENTRY, entry2)) i2 += 1 else: result.append((entry1, entry2)) i1 += 1 i2 += 1 for i in range(i1, len1): result.append((entries1[i], _NULL_ENTRY)) for i in range(i2, len2): result.append((_NULL_ENTRY, entries2[i])) return result def _is_tree(entry): mode = entry.mode if mode is None: return False return stat.S_ISDIR(mode) def walk_trees(store, tree1_id, tree2_id, prune_identical=False): """Recursively walk all the entries of two trees. Iteration is depth-first pre-order, as in e.g. os.walk. :param store: An ObjectStore for looking up objects. :param tree1_id: The SHA of the first Tree object to iterate, or None. :param tree2_id: The SHA of the second Tree object to iterate, or None. :param prune_identical: If True, identical subtrees will not be walked. :return: Iterator over Pairs of TreeEntry objects for each pair of entries in the trees and their subtrees recursively. If an entry exists in one tree but not the other, the other entry will have all attributes set to None. If neither entry's path is None, they are guaranteed to match. """ # This could be fairly easily generalized to >2 trees if we find a use # case. mode1 = tree1_id and stat.S_IFDIR or None mode2 = tree2_id and stat.S_IFDIR or None todo = [(TreeEntry(b'', mode1, tree1_id), TreeEntry(b'', mode2, tree2_id))] while todo: entry1, entry2 = todo.pop() is_tree1 = _is_tree(entry1) is_tree2 = _is_tree(entry2) if prune_identical and is_tree1 and is_tree2 and entry1 == entry2: continue tree1 = is_tree1 and store[entry1.sha] or None tree2 = is_tree2 and store[entry2.sha] or None path = entry1.path or entry2.path todo.extend(reversed(_merge_entries(path, tree1, tree2))) yield entry1, entry2 -def _skip_tree(entry): - if entry.mode is None or stat.S_ISDIR(entry.mode): +def _skip_tree(entry, include_trees): + if entry.mode is None or (not include_trees and stat.S_ISDIR(entry.mode)): return _NULL_ENTRY return entry def tree_changes(store, tree1_id, tree2_id, want_unchanged=False, - rename_detector=None): + rename_detector=None, include_trees=False, + change_type_same=False): """Find the differences between the contents of two trees. :param store: An ObjectStore for looking up objects. :param tree1_id: The SHA of the source tree. :param tree2_id: The SHA of the target tree. :param want_unchanged: If True, include TreeChanges for unmodified entries as well. + :param include_trees: Whether to include trees :param rename_detector: RenameDetector object for detecting renames. + :param change_type_same: Whether to report change types in the same + entry or as delete+add. :return: Iterator over TreeChange instances for each change between the source and target tree. """ + if include_trees and rename_detector is not None: + raise NotImplementedError( + 'rename_detector and include_trees are mutually exclusive') if (rename_detector is not None and tree1_id is not None and tree2_id is not None): for change in rename_detector.changes_with_renames( tree1_id, tree2_id, want_unchanged=want_unchanged): yield change return entries = walk_trees(store, tree1_id, tree2_id, prune_identical=(not want_unchanged)) for entry1, entry2 in entries: if entry1 == entry2 and not want_unchanged: continue # Treat entries for trees as missing. - entry1 = _skip_tree(entry1) - entry2 = _skip_tree(entry2) + entry1 = _skip_tree(entry1, include_trees) + entry2 = _skip_tree(entry2, include_trees) if entry1 != _NULL_ENTRY and entry2 != _NULL_ENTRY: - if stat.S_IFMT(entry1.mode) != stat.S_IFMT(entry2.mode): + if (stat.S_IFMT(entry1.mode) != stat.S_IFMT(entry2.mode) + and not change_type_same): # File type changed: report as delete/add. yield TreeChange.delete(entry1) entry1 = _NULL_ENTRY change_type = CHANGE_ADD elif entry1 == entry2: change_type = CHANGE_UNCHANGED else: change_type = CHANGE_MODIFY elif entry1 != _NULL_ENTRY: change_type = CHANGE_DELETE elif entry2 != _NULL_ENTRY: change_type = CHANGE_ADD else: # Both were None because at least one was a tree. continue yield TreeChange(change_type, entry1, entry2) def _all_eq(seq, key, value): for e in seq: if key(e) != value: return False return True def _all_same(seq, key): return _all_eq(seq[1:], key, key(seq[0])) def tree_changes_for_merge(store, parent_tree_ids, tree_id, rename_detector=None): """Get the tree changes for a merge tree relative to all its parents. :param store: An ObjectStore for looking up objects. :param parent_tree_ids: An iterable of the SHAs of the parent trees. :param tree_id: The SHA of the merge tree. :param rename_detector: RenameDetector object for detecting renames. :return: Iterator over lists of TreeChange objects, one per conflicted path in the merge. Each list contains one element per parent, with the TreeChange for that path relative to that parent. An element may be None if it never existed in one parent and was deleted in two others. A path is only included in the output if it is a conflict, i.e. its SHA in the merge tree is not found in any of the parents, or in the case of deletes, if not all of the old SHAs match. """ all_parent_changes = [tree_changes(store, t, tree_id, rename_detector=rename_detector) for t in parent_tree_ids] num_parents = len(parent_tree_ids) changes_by_path = defaultdict(lambda: [None] * num_parents) # Organize by path. for i, parent_changes in enumerate(all_parent_changes): for change in parent_changes: if change.type == CHANGE_DELETE: path = change.old.path else: path = change.new.path changes_by_path[path][i] = change def old_sha(c): return c.old.sha def change_type(c): return c.type # Yield only conflicting changes. for _, changes in sorted(changes_by_path.items()): assert len(changes) == num_parents have = [c for c in changes if c is not None] if _all_eq(have, change_type, CHANGE_DELETE): if not _all_same(have, old_sha): yield changes elif not _all_same(have, change_type): yield changes elif None not in changes: # If no change was found relative to one parent, that means the SHA # must have matched the SHA in that parent, so it is not a # conflict. yield changes _BLOCK_SIZE = 64 def _count_blocks(obj): """Count the blocks in an object. Splits the data into blocks either on lines or <=64-byte chunks of lines. :param obj: The object to count blocks for. :return: A dict of block hashcode -> total bytes occurring. """ block_counts = defaultdict(int) block = BytesIO() n = 0 # Cache attrs as locals to avoid expensive lookups in the inner loop. block_write = block.write block_seek = block.seek block_truncate = block.truncate block_getvalue = block.getvalue for c in chain(*obj.as_raw_chunks()): if sys.version_info[0] == 3: c = c.to_bytes(1, 'big') block_write(c) n += 1 if c == b'\n' or n == _BLOCK_SIZE: value = block_getvalue() block_counts[hash(value)] += len(value) block_seek(0) block_truncate() n = 0 if n > 0: last_block = block_getvalue() block_counts[hash(last_block)] += len(last_block) return block_counts def _common_bytes(blocks1, blocks2): """Count the number of common bytes in two block count dicts. :param block1: The first dict of block hashcode -> total bytes. :param block2: The second dict of block hashcode -> total bytes. :return: The number of bytes in common between blocks1 and blocks2. This is only approximate due to possible hash collisions. """ # Iterate over the smaller of the two dicts, since this is symmetrical. if len(blocks1) > len(blocks2): blocks1, blocks2 = blocks2, blocks1 score = 0 for block, count1 in blocks1.items(): count2 = blocks2.get(block) if count2: score += min(count1, count2) return score def _similarity_score(obj1, obj2, block_cache=None): """Compute a similarity score for two objects. :param obj1: The first object to score. :param obj2: The second object to score. :param block_cache: An optional dict of SHA to block counts to cache results between calls. :return: The similarity score between the two objects, defined as the number of bytes in common between the two objects divided by the maximum size, scaled to the range 0-100. """ if block_cache is None: block_cache = {} if obj1.id not in block_cache: block_cache[obj1.id] = _count_blocks(obj1) if obj2.id not in block_cache: block_cache[obj2.id] = _count_blocks(obj2) common_bytes = _common_bytes(block_cache[obj1.id], block_cache[obj2.id]) max_size = max(obj1.raw_length(), obj2.raw_length()) if not max_size: return _MAX_SCORE return int(float(common_bytes) * _MAX_SCORE / max_size) def _tree_change_key(entry): # Sort by old path then new path. If only one exists, use it for both keys. path1 = entry.old.path path2 = entry.new.path if path1 is None: path1 = path2 if path2 is None: path2 = path1 return (path1, path2) class RenameDetector(object): """Object for handling rename detection between two trees.""" def __init__(self, store, rename_threshold=RENAME_THRESHOLD, max_files=MAX_FILES, rewrite_threshold=REWRITE_THRESHOLD, find_copies_harder=False): """Initialize the rename detector. :param store: An ObjectStore for looking up objects. :param rename_threshold: The threshold similarity score for considering an add/delete pair to be a rename/copy; see _similarity_score. :param max_files: The maximum number of adds and deletes to consider, or None for no limit. The detector is guaranteed to compare no more than max_files ** 2 add/delete pairs. This limit is provided because rename detection can be quadratic in the project size. If the limit is exceeded, no content rename detection is attempted. :param rewrite_threshold: The threshold similarity score below which a modify should be considered a delete/add, or None to not break modifies; see _similarity_score. :param find_copies_harder: If True, consider unmodified files when detecting copies. """ self._store = store self._rename_threshold = rename_threshold self._rewrite_threshold = rewrite_threshold self._max_files = max_files self._find_copies_harder = find_copies_harder self._want_unchanged = False def _reset(self): self._adds = [] self._deletes = [] self._changes = [] def _should_split(self, change): if (self._rewrite_threshold is None or change.type != CHANGE_MODIFY or change.old.sha == change.new.sha): return False old_obj = self._store[change.old.sha] new_obj = self._store[change.new.sha] return _similarity_score(old_obj, new_obj) < self._rewrite_threshold def _add_change(self, change): if change.type == CHANGE_ADD: self._adds.append(change) elif change.type == CHANGE_DELETE: self._deletes.append(change) elif self._should_split(change): self._deletes.append(TreeChange.delete(change.old)) self._adds.append(TreeChange.add(change.new)) elif ((self._find_copies_harder and change.type == CHANGE_UNCHANGED) or change.type == CHANGE_MODIFY): # Treat all modifies as potential deletes for rename detection, # but don't split them (to avoid spurious renames). Setting # find_copies_harder means we treat unchanged the same as # modified. self._deletes.append(change) else: self._changes.append(change) def _collect_changes(self, tree1_id, tree2_id): want_unchanged = self._find_copies_harder or self._want_unchanged for change in tree_changes(self._store, tree1_id, tree2_id, want_unchanged=want_unchanged): self._add_change(change) def _prune(self, add_paths, delete_paths): self._adds = [a for a in self._adds if a.new.path not in add_paths] self._deletes = [d for d in self._deletes if d.old.path not in delete_paths] def _find_exact_renames(self): add_map = defaultdict(list) for add in self._adds: add_map[add.new.sha].append(add.new) delete_map = defaultdict(list) for delete in self._deletes: # Keep track of whether the delete was actually marked as a delete. # If not, it needs to be marked as a copy. is_delete = delete.type == CHANGE_DELETE delete_map[delete.old.sha].append((delete.old, is_delete)) add_paths = set() delete_paths = set() for sha, sha_deletes in delete_map.items(): sha_adds = add_map[sha] for (old, is_delete), new in zip(sha_deletes, sha_adds): if stat.S_IFMT(old.mode) != stat.S_IFMT(new.mode): continue if is_delete: delete_paths.add(old.path) add_paths.add(new.path) new_type = is_delete and CHANGE_RENAME or CHANGE_COPY self._changes.append(TreeChange(new_type, old, new)) num_extra_adds = len(sha_adds) - len(sha_deletes) # TODO(dborowitz): Less arbitrary way of dealing with extra copies. old = sha_deletes[0][0] if num_extra_adds > 0: for new in sha_adds[-num_extra_adds:]: add_paths.add(new.path) self._changes.append(TreeChange(CHANGE_COPY, old, new)) self._prune(add_paths, delete_paths) def _should_find_content_renames(self): return len(self._adds) * len(self._deletes) <= self._max_files ** 2 def _rename_type(self, check_paths, delete, add): if check_paths and delete.old.path == add.new.path: # If the paths match, this must be a split modify, so make sure it # comes out as a modify. return CHANGE_MODIFY elif delete.type != CHANGE_DELETE: # If it's in deletes but not marked as a delete, it must have been # added due to find_copies_harder, and needs to be marked as a # copy. return CHANGE_COPY return CHANGE_RENAME def _find_content_rename_candidates(self): candidates = self._candidates = [] # TODO: Optimizations: # - Compare object sizes before counting blocks. # - Skip if delete's S_IFMT differs from all adds. # - Skip if adds or deletes is empty. # Match C git's behavior of not attempting to find content renames if # the matrix size exceeds the threshold. if not self._should_find_content_renames(): return block_cache = {} check_paths = self._rename_threshold is not None for delete in self._deletes: if S_ISGITLINK(delete.old.mode): continue # Git links don't exist in this repo. old_sha = delete.old.sha old_obj = self._store[old_sha] block_cache[old_sha] = _count_blocks(old_obj) for add in self._adds: if stat.S_IFMT(delete.old.mode) != stat.S_IFMT(add.new.mode): continue new_obj = self._store[add.new.sha] score = _similarity_score(old_obj, new_obj, block_cache=block_cache) if score > self._rename_threshold: new_type = self._rename_type(check_paths, delete, add) rename = TreeChange(new_type, delete.old, add.new) candidates.append((-score, rename)) def _choose_content_renames(self): # Sort scores from highest to lowest, but keep names in ascending # order. self._candidates.sort() delete_paths = set() add_paths = set() for _, change in self._candidates: new_path = change.new.path if new_path in add_paths: continue old_path = change.old.path orig_type = change.type if old_path in delete_paths: change = TreeChange(CHANGE_COPY, change.old, change.new) # If the candidate was originally a copy, that means it came from a # modified or unchanged path, so we don't want to prune it. if orig_type != CHANGE_COPY: delete_paths.add(old_path) add_paths.add(new_path) self._changes.append(change) self._prune(add_paths, delete_paths) def _join_modifies(self): if self._rewrite_threshold is None: return modifies = {} delete_map = dict((d.old.path, d) for d in self._deletes) for add in self._adds: path = add.new.path delete = delete_map.get(path) if (delete is not None and stat.S_IFMT(delete.old.mode) == stat.S_IFMT(add.new.mode)): modifies[path] = TreeChange(CHANGE_MODIFY, delete.old, add.new) self._adds = [a for a in self._adds if a.new.path not in modifies] self._deletes = [a for a in self._deletes if a.new.path not in modifies] self._changes += modifies.values() def _sorted_changes(self): result = [] result.extend(self._adds) result.extend(self._deletes) result.extend(self._changes) result.sort(key=_tree_change_key) return result def _prune_unchanged(self): if self._want_unchanged: return self._deletes = [ d for d in self._deletes if d.type != CHANGE_UNCHANGED] def changes_with_renames(self, tree1_id, tree2_id, want_unchanged=False): """Iterate TreeChanges between two tree SHAs, with rename detection.""" self._reset() self._want_unchanged = want_unchanged self._collect_changes(tree1_id, tree2_id) self._find_exact_renames() self._find_content_rename_candidates() self._choose_content_renames() self._join_modifies() self._prune_unchanged() return self._sorted_changes() # Hold on to the pure-python implementations for testing. _is_tree_py = _is_tree _merge_entries_py = _merge_entries _count_blocks_py = _count_blocks try: # Try to import C versions from dulwich._diff_tree import _is_tree, _merge_entries, _count_blocks except ImportError: pass diff --git a/dulwich/errors.py b/dulwich/errors.py index 2f5ddf73..3d2b20b4 100644 --- a/dulwich/errors.py +++ b/dulwich/errors.py @@ -1,180 +1,187 @@ # errors.py -- errors for dulwich # Copyright (C) 2007 James Westby # Copyright (C) 2009-2012 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. # """Dulwich-related exception classes and utility functions.""" import binascii class ChecksumMismatch(Exception): """A checksum didn't match the expected contents.""" def __init__(self, expected, got, extra=None): if len(expected) == 20: expected = binascii.hexlify(expected) if len(got) == 20: got = binascii.hexlify(got) self.expected = expected self.got = got self.extra = extra if self.extra is None: Exception.__init__( self, "Checksum mismatch: Expected %s, got %s" % (expected, got)) else: Exception.__init__( self, "Checksum mismatch: Expected %s, got %s; %s" % (expected, got, extra)) class WrongObjectException(Exception): """Baseclass for all the _ is not a _ exceptions on objects. Do not instantiate directly. Subclasses should define a type_name attribute that indicates what was expected if they were raised. """ def __init__(self, sha, *args, **kwargs): Exception.__init__(self, "%s is not a %s" % (sha, self.type_name)) class NotCommitError(WrongObjectException): """Indicates that the sha requested does not point to a commit.""" type_name = 'commit' class NotTreeError(WrongObjectException): """Indicates that the sha requested does not point to a tree.""" type_name = 'tree' class NotTagError(WrongObjectException): """Indicates that the sha requested does not point to a tag.""" type_name = 'tag' class NotBlobError(WrongObjectException): """Indicates that the sha requested does not point to a blob.""" type_name = 'blob' class MissingCommitError(Exception): """Indicates that a commit was not found in the repository""" def __init__(self, sha, *args, **kwargs): self.sha = sha Exception.__init__(self, "%s is not in the revision store" % sha) class ObjectMissing(Exception): """Indicates that a requested object is missing.""" def __init__(self, sha, *args, **kwargs): Exception.__init__(self, "%s is not in the pack" % sha) class ApplyDeltaError(Exception): """Indicates that applying a delta failed.""" def __init__(self, *args, **kwargs): Exception.__init__(self, *args, **kwargs) class NotGitRepository(Exception): """Indicates that no Git repository was found.""" def __init__(self, *args, **kwargs): Exception.__init__(self, *args, **kwargs) class GitProtocolError(Exception): """Git protocol exception.""" def __init__(self, *args, **kwargs): Exception.__init__(self, *args, **kwargs) class SendPackError(GitProtocolError): """An error occurred during send_pack.""" def __init__(self, *args, **kwargs): Exception.__init__(self, *args, **kwargs) class UpdateRefsError(GitProtocolError): """The server reported errors updating refs.""" def __init__(self, *args, **kwargs): self.ref_status = kwargs.pop('ref_status') Exception.__init__(self, *args, **kwargs) class HangupException(GitProtocolError): """Hangup exception.""" def __init__(self): Exception.__init__( self, "The remote server unexpectedly closed the connection.") class UnexpectedCommandError(GitProtocolError): """Unexpected command received in a proto line.""" def __init__(self, command): if command is None: command = 'flush-pkt' else: command = 'command %s' % command GitProtocolError.__init__(self, 'Protocol got unexpected %s' % command) class FileFormatException(Exception): """Base class for exceptions relating to reading git file formats.""" class PackedRefsException(FileFormatException): """Indicates an error parsing a packed-refs file.""" class ObjectFormatException(FileFormatException): """Indicates an error parsing an object.""" +class EmptyFileException(FileFormatException): + """Indicates an empty file instead of the object's disk + representation. + + """ + + class NoIndexPresent(Exception): """No index is present.""" class CommitError(Exception): """An error occurred while performing a commit.""" class RefFormatError(Exception): """Indicates an invalid ref name.""" class HookError(Exception): """An error occurred while executing a hook.""" diff --git a/dulwich/fastexport.py b/dulwich/fastexport.py index 28178c82..18b8716b 100644 --- a/dulwich/fastexport.py +++ b/dulwich/fastexport.py @@ -1,250 +1,249 @@ # __init__.py -- Fast export/import functionality # Copyright (C) 2010-2013 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. # """Fast export/import functionality.""" import sys from dulwich.index import ( commit_tree, ) from dulwich.objects import ( Blob, Commit, Tag, ZERO_SHA, ) from fastimport import __version__ as fastimport_version if (fastimport_version <= (0, 9, 5) and sys.version_info[0] == 3 and sys.version_info[1] < 5): raise ImportError("Older versions of fastimport don't support python3<3.5") from fastimport import ( # noqa: E402 commands, errors as fastimport_errors, parser, processor, ) import stat # noqa: E402 def split_email(text): (name, email) = text.rsplit(b" <", 1) return (name, email.rstrip(b">")) class GitFastExporter(object): """Generate a fast-export output stream for Git objects.""" def __init__(self, outf, store): self.outf = outf self.store = store self.markers = {} self._marker_idx = 0 def print_cmd(self, cmd): self.outf.write(getattr(cmd, "__bytes__", cmd.__repr__)() + b"\n") def _allocate_marker(self): self._marker_idx += 1 return ("%d" % (self._marker_idx,)).encode('ascii') def _export_blob(self, blob): marker = self._allocate_marker() self.markers[marker] = blob.id return (commands.BlobCommand(marker, blob.data), marker) def emit_blob(self, blob): (cmd, marker) = self._export_blob(blob) self.print_cmd(cmd) return marker def _iter_files(self, base_tree, new_tree): for ((old_path, new_path), (old_mode, new_mode), (old_hexsha, new_hexsha)) in \ self.store.tree_changes(base_tree, new_tree): if new_path is None: yield commands.FileDeleteCommand(old_path) continue if not stat.S_ISDIR(new_mode): blob = self.store[new_hexsha] marker = self.emit_blob(blob) if old_path != new_path and old_path is not None: yield commands.FileRenameCommand(old_path, new_path) if old_mode != new_mode or old_hexsha != new_hexsha: prefixed_marker = b':' + marker yield commands.FileModifyCommand( new_path, new_mode, prefixed_marker, None ) def _export_commit(self, commit, ref, base_tree=None): file_cmds = list(self._iter_files(base_tree, commit.tree)) marker = self._allocate_marker() if commit.parents: from_ = commit.parents[0] merges = commit.parents[1:] else: from_ = None merges = [] author, author_email = split_email(commit.author) committer, committer_email = split_email(commit.committer) cmd = commands.CommitCommand( ref, marker, (author, author_email, commit.author_time, commit.author_timezone), (committer, committer_email, commit.commit_time, commit.commit_timezone), commit.message, from_, merges, file_cmds) return (cmd, marker) def emit_commit(self, commit, ref, base_tree=None): cmd, marker = self._export_commit(commit, ref, base_tree) self.print_cmd(cmd) return marker class GitImportProcessor(processor.ImportProcessor): """An import processor that imports into a Git repository using Dulwich. """ # FIXME: Batch creation of objects? def __init__(self, repo, params=None, verbose=False, outf=None): processor.ImportProcessor.__init__(self, params, verbose) self.repo = repo self.last_commit = ZERO_SHA self.markers = {} self._contents = {} + def lookup_object(self, objectish): + if objectish.startswith(b":"): + return self.markers[objectish[1:]] + return objectish + def import_stream(self, stream): p = parser.ImportParser(stream) self.process(p.iter_commands) return self.markers def blob_handler(self, cmd): """Process a BlobCommand.""" blob = Blob.from_string(cmd.data) self.repo.object_store.add_object(blob) if cmd.mark: self.markers[cmd.mark] = blob.id def checkpoint_handler(self, cmd): """Process a CheckpointCommand.""" pass def commit_handler(self, cmd): """Process a CommitCommand.""" commit = Commit() if cmd.author is not None: author = cmd.author else: author = cmd.committer (author_name, author_email, author_timestamp, author_timezone) = author (committer_name, committer_email, commit_timestamp, commit_timezone) = cmd.committer commit.author = author_name + b" <" + author_email + b">" commit.author_timezone = author_timezone commit.author_time = int(author_timestamp) commit.committer = committer_name + b" <" + committer_email + b">" commit.commit_timezone = commit_timezone commit.commit_time = int(commit_timestamp) commit.message = cmd.message commit.parents = [] if cmd.from_: + cmd.from_ = self.lookup_object(cmd.from_) self._reset_base(cmd.from_) for filecmd in cmd.iter_files(): if filecmd.name == b"filemodify": if filecmd.data is not None: blob = Blob.from_string(filecmd.data) self.repo.object_store.add(blob) blob_id = blob.id else: - assert filecmd.dataref.startswith(b":"), \ - ("non-marker refs not supported yet (%r)" % - filecmd.dataref) - blob_id = self.markers[filecmd.dataref[1:]] + blob_id = self.lookup_object(filecmd.dataref) self._contents[filecmd.path] = (filecmd.mode, blob_id) elif filecmd.name == b"filedelete": del self._contents[filecmd.path] elif filecmd.name == b"filecopy": self._contents[filecmd.dest_path] = self._contents[ filecmd.src_path] elif filecmd.name == b"filerename": self._contents[filecmd.new_path] = self._contents[ filecmd.old_path] del self._contents[filecmd.old_path] elif filecmd.name == b"filedeleteall": self._contents = {} else: raise Exception("Command %s not supported" % filecmd.name) commit.tree = commit_tree( self.repo.object_store, ((path, hexsha, mode) for (path, (mode, hexsha)) in self._contents.items())) if self.last_commit != ZERO_SHA: commit.parents.append(self.last_commit) for merge in cmd.merges: - if merge.startswith(b':'): - merge = self.markers[merge[1:]] - commit.parents.append(merge) + commit.parents.append(self.lookup_object(merge)) self.repo.object_store.add_object(commit) self.repo[cmd.ref] = commit.id self.last_commit = commit.id if cmd.mark: self.markers[cmd.mark] = commit.id def progress_handler(self, cmd): """Process a ProgressCommand.""" pass def _reset_base(self, commit_id): if self.last_commit == commit_id: return self._contents = {} self.last_commit = commit_id if commit_id != ZERO_SHA: tree_id = self.repo[commit_id].tree for (path, mode, hexsha) in ( self.repo.object_store.iter_tree_contents(tree_id)): self._contents[path] = (mode, hexsha) def reset_handler(self, cmd): """Process a ResetCommand.""" if cmd.from_ is None: from_ = ZERO_SHA else: - from_ = cmd.from_ - if from_.startswith(b":"): - from_ = self.markers[from_[1:]] + from_ = self.lookup_object(cmd.from_) self._reset_base(from_) self.repo.refs[cmd.ref] = from_ def tag_handler(self, cmd): """Process a TagCommand.""" tag = Tag() tag.tagger = cmd.tagger tag.message = cmd.message tag.name = cmd.tag self.repo.add_object(tag) self.repo.refs["refs/tags/" + tag.name] = tag.id def feature_handler(self, cmd): """Process a FeatureCommand.""" raise fastimport_errors.UnknownFeature(cmd.feature_name) diff --git a/dulwich/ignore.py b/dulwich/ignore.py index 089f2caa..b3878938 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' def read_ignore_patterns(f): """Read a git ignore file. :param f: File-like object to read from :return: List of patterns """ - for l in f: - l = l.rstrip(b"\r\n") + for line in f: + line = line.rstrip(b"\r\n") # Ignore blank lines, they're used for readability. - if not l: + if not line: continue - if l.startswith(b'#'): + if line.startswith(b'#'): # Comment continue # Trailing spaces are ignored unless they are quoted with a backslash. - while l.endswith(b' ') and not l.endswith(b'\\ '): - l = l[:-1] - l = l.replace(b'\\ ', b' ') + while line.endswith(b' ') and not line.endswith(b'\\ '): + line = line[:-1] + line = line.replace(b'\\ ', b' ') - yield l + 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(('core', ), 'excludesFile') + 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/index.py b/dulwich/index.py index 7e0b79df..c910e1e6 100644 --- a/dulwich/index.py +++ b/dulwich/index.py @@ -1,648 +1,704 @@ # index.py -- File parser/writer for the git index file # 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. # """Parser for the git index file format.""" import collections import errno import os import stat import struct import sys from dulwich.file import GitFile from dulwich.objects import ( Blob, S_IFGITLINK, S_ISGITLINK, Tree, hex_to_sha, sha_to_hex, ) from dulwich.pack import ( SHA1Reader, SHA1Writer, ) IndexEntry = collections.namedtuple( 'IndexEntry', [ 'ctime', 'mtime', 'dev', 'ino', 'mode', 'uid', 'gid', 'size', 'sha', 'flags']) +FLAG_STAGEMASK = 0x3000 +FLAG_VALID = 0x8000 +FLAG_EXTENDED = 0x4000 + + def pathsplit(path): """Split a /-delimited path into a directory part and a basename. :param path: The path to split. :return: Tuple with directory name and basename """ try: (dirname, basename) = path.rsplit(b"/", 1) except ValueError: return (b"", path) else: return (dirname, basename) def pathjoin(*args): """Join a /-delimited path. """ return b"/".join([p for p in args if p]) def read_cache_time(f): """Read a cache time. :param f: File-like object to read from :return: Tuple with seconds and nanoseconds """ return struct.unpack(">LL", f.read(8)) def write_cache_time(f, t): """Write a cache time. :param f: File-like object to write to :param t: Time to write (as int, float or tuple with secs and nsecs) """ if isinstance(t, int): t = (t, 0) elif isinstance(t, float): (secs, nsecs) = divmod(t, 1.0) t = (int(secs), int(nsecs * 1000000000)) elif not isinstance(t, tuple): raise TypeError(t) f.write(struct.pack(">LL", *t)) def read_cache_entry(f): """Read an entry from a cache file. :param f: File-like object to read from :return: tuple with: device, inode, mode, uid, gid, size, sha, flags """ beginoffset = f.tell() ctime = read_cache_time(f) mtime = read_cache_time(f) (dev, ino, mode, uid, gid, size, sha, flags, ) = \ struct.unpack(">LLLLLL20sH", f.read(20 + 4 * 6 + 2)) name = f.read((flags & 0x0fff)) # Padding: real_size = ((f.tell() - beginoffset + 8) & ~7) f.read((beginoffset + real_size) - f.tell()) return (name, ctime, mtime, dev, ino, mode, uid, gid, size, sha_to_hex(sha), flags & ~0x0fff) def write_cache_entry(f, entry): """Write an index entry to a file. :param f: File object :param entry: Entry to write, tuple with: (name, ctime, mtime, dev, ino, mode, uid, gid, size, sha, flags) """ beginoffset = f.tell() (name, ctime, mtime, dev, ino, mode, uid, gid, size, sha, flags) = entry write_cache_time(f, ctime) write_cache_time(f, mtime) flags = len(name) | (flags & ~0x0fff) f.write(struct.pack( b'>LLLLLL20sH', dev & 0xFFFFFFFF, ino & 0xFFFFFFFF, mode, uid, gid, size, hex_to_sha(sha), flags)) f.write(name) real_size = ((f.tell() - beginoffset + 8) & ~7) f.write(b'\0' * ((beginoffset + real_size) - f.tell())) def read_index(f): """Read an index file, yielding the individual entries.""" header = f.read(4) if header != b'DIRC': raise AssertionError("Invalid index file header: %r" % header) (version, num_entries) = struct.unpack(b'>LL', f.read(4 * 2)) assert version in (1, 2) for i in range(num_entries): yield read_cache_entry(f) def read_index_dict(f): """Read an index file and return it as a dictionary. :param f: File object to read from """ ret = {} for x in read_index(f): ret[x[0]] = IndexEntry(*x[1:]) return ret def write_index(f, entries): """Write an index file. :param f: File-like object to write to :param entries: Iterable over the entries to write """ f.write(b'DIRC') f.write(struct.pack(b'>LL', 2, len(entries))) for x in entries: write_cache_entry(f, x) def write_index_dict(f, entries): """Write an index file based on the contents of a dictionary. """ entries_list = [] for name in sorted(entries): entries_list.append((name,) + tuple(entries[name])) write_index(f, entries_list) def cleanup_mode(mode): """Cleanup a mode value. This will return a mode that can be stored in a tree object. :param mode: Mode to clean up. """ if stat.S_ISLNK(mode): return stat.S_IFLNK elif stat.S_ISDIR(mode): return stat.S_IFDIR elif S_ISGITLINK(mode): return S_IFGITLINK ret = stat.S_IFREG | 0o644 ret |= (mode & 0o111) return ret class Index(object): """A Git Index file.""" def __init__(self, filename): """Open an index file. :param filename: Path to the index file """ self._filename = filename self.clear() self.read() @property def path(self): return self._filename def __repr__(self): return "%s(%r)" % (self.__class__.__name__, self._filename) def write(self): """Write current contents of index to disk.""" f = GitFile(self._filename, 'wb') try: f = SHA1Writer(f) write_index_dict(f, self._byname) finally: f.close() def read(self): """Read current contents of index from disk.""" if not os.path.exists(self._filename): return f = GitFile(self._filename, 'rb') try: f = SHA1Reader(f) for x in read_index(f): self[x[0]] = IndexEntry(*x[1:]) # FIXME: Additional data? f.read(os.path.getsize(self._filename)-f.tell()-20) f.check_sha() finally: f.close() def __len__(self): """Number of entries in this index file.""" return len(self._byname) def __getitem__(self, name): """Retrieve entry by relative path. :return: tuple with (ctime, mtime, dev, ino, mode, uid, gid, size, sha, flags) """ return self._byname[name] def __iter__(self): """Iterate over the paths in this index.""" return iter(self._byname) def get_sha1(self, path): """Return the (git object) SHA1 for the object at a path.""" return self[path].sha def get_mode(self, path): """Return the POSIX file mode for the object at a path.""" return self[path].mode def iterblobs(self): """Iterate over path, sha, mode tuples for use with commit_tree.""" for path in self: entry = self[path] yield path, entry.sha, cleanup_mode(entry.mode) def clear(self): """Remove all contents from this index.""" self._byname = {} def __setitem__(self, name, x): assert isinstance(name, bytes) assert len(x) == 10 # Remove the old entry if any self._byname[name] = IndexEntry(*x) def __delitem__(self, name): assert isinstance(name, bytes) del self._byname[name] def iteritems(self): return self._byname.items() def update(self, entries): for name, value in entries.items(): self[name] = value def changes_from_tree(self, object_store, tree, want_unchanged=False): """Find the differences between the contents of this index and a tree. :param object_store: Object store to use for retrieving tree contents :param tree: SHA1 of the root tree :param want_unchanged: Whether unchanged files should be reported :return: Iterator over tuples with (oldpath, newpath), (oldmode, newmode), (oldsha, newsha) """ def lookup_entry(path): entry = self[path] return entry.sha, entry.mode for (name, mode, sha) in changes_from_tree( self._byname.keys(), lookup_entry, object_store, tree, want_unchanged=want_unchanged): yield (name, mode, sha) def commit(self, object_store): """Create a new tree from an index. :param object_store: Object store to save the tree in :return: Root tree SHA """ return commit_tree(object_store, self.iterblobs()) def commit_tree(object_store, blobs): """Commit a new tree. :param object_store: Object store to add trees to :param blobs: Iterable over blob path, sha, mode entries :return: SHA1 of the created tree. """ trees = {b'': {}} def add_tree(path): if path in trees: return trees[path] dirname, basename = pathsplit(path) t = add_tree(dirname) assert isinstance(basename, bytes) newtree = {} t[basename] = newtree trees[path] = newtree return newtree for path, sha, mode in blobs: tree_path, basename = pathsplit(path) tree = add_tree(tree_path) tree[basename] = (mode, sha) def build_tree(path): tree = Tree() for basename, entry in trees[path].items(): if isinstance(entry, dict): mode = stat.S_IFDIR sha = build_tree(pathjoin(path, basename)) else: (mode, sha) = entry tree.add(basename, mode, sha) object_store.add_object(tree) return tree.id return build_tree(b'') def commit_index(object_store, index): """Create a new tree from an index. :param object_store: Object store to save the tree in :param index: Index file :note: This function is deprecated, use index.commit() instead. :return: Root tree sha. """ return commit_tree(object_store, index.iterblobs()) def changes_from_tree(names, lookup_entry, object_store, tree, want_unchanged=False): """Find the differences between the contents of a tree and a working copy. :param names: Iterable of names in the working copy :param lookup_entry: Function to lookup an entry in the working copy :param object_store: Object store to use for retrieving tree contents :param tree: SHA1 of the root tree, or None for an empty tree :param want_unchanged: Whether unchanged files should be reported :return: Iterator over tuples with (oldpath, newpath), (oldmode, newmode), (oldsha, newsha) """ + # TODO(jelmer): Support a include_trees option other_names = set(names) if tree is not None: for (name, mode, sha) in object_store.iter_tree_contents(tree): try: (other_sha, other_mode) = lookup_entry(name) except KeyError: # Was removed yield ((name, None), (mode, None), (sha, None)) else: other_names.remove(name) if (want_unchanged or other_sha != sha or other_mode != mode): yield ((name, name), (mode, other_mode), (sha, other_sha)) # Mention added files for name in other_names: try: (other_sha, other_mode) = lookup_entry(name) except KeyError: pass else: yield ((None, name), (None, other_mode), (None, other_sha)) def index_entry_from_stat(stat_val, hex_sha, flags, mode=None): """Create a new index entry from a stat value. :param stat_val: POSIX stat_result instance :param hex_sha: Hex sha of the object :param flags: Index flags """ if mode is None: mode = cleanup_mode(stat_val.st_mode) return (stat_val.st_ctime, stat_val.st_mtime, stat_val.st_dev, stat_val.st_ino, mode, stat_val.st_uid, stat_val.st_gid, stat_val.st_size, hex_sha, flags) def build_file_from_blob(blob, mode, target_path, honor_filemode=True): """Build a file or symlink on disk based on a Git object. :param obj: The git object :param mode: File mode :param target_path: Path to write to :param honor_filemode: An optional flag to honor core.filemode setting in config file, default is core.filemode=True, change executable bit :return: stat object for the file """ try: oldstat = os.lstat(target_path) except OSError as e: if e.errno == errno.ENOENT: oldstat = None else: raise contents = blob.as_raw_string() if stat.S_ISLNK(mode): # FIXME: This will fail on Windows. What should we do instead? if oldstat: os.unlink(target_path) if sys.platform == 'win32' and sys.version_info[0] == 3: # os.readlink on Python3 on Windows requires a unicode string. # TODO(jelmer): Don't assume tree_encoding == fs_encoding tree_encoding = sys.getfilesystemencoding() contents = contents.decode(tree_encoding) target_path = target_path.decode(tree_encoding) os.symlink(contents, target_path) else: if oldstat is not None and oldstat.st_size == len(contents): with open(target_path, 'rb') as f: if f.read() == contents: return oldstat with open(target_path, 'wb') as f: # Write out file f.write(contents) if honor_filemode: os.chmod(target_path, mode) return os.lstat(target_path) INVALID_DOTNAMES = (b".git", b".", b"..", b"") def validate_path_element_default(element): return element.lower() not in INVALID_DOTNAMES def validate_path_element_ntfs(element): stripped = element.rstrip(b". ").lower() if stripped in INVALID_DOTNAMES: return False if stripped == b"git~1": return False return True def validate_path(path, element_validator=validate_path_element_default): """Default path validator that just checks for .git/.""" parts = path.split(b"/") for p in parts: if not element_validator(p): return False else: return True def build_index_from_tree(root_path, index_path, object_store, tree_id, honor_filemode=True, validate_path_element=validate_path_element_default): """Generate and materialize index from a tree :param tree_id: Tree to materialize :param root_path: Target dir for materialized index files :param index_path: Target path for generated index :param object_store: Non-empty object store holding tree contents :param honor_filemode: An optional flag to honor core.filemode setting in config file, default is core.filemode=True, change executable bit :param validate_path_element: Function to validate path elements to check out; default just refuses .git and .. directories. :note:: existing index is wiped and contents are not merged in a working dir. Suitable only for fresh clones. """ index = Index(index_path) if not isinstance(root_path, bytes): root_path = root_path.encode(sys.getfilesystemencoding()) for entry in object_store.iter_tree_contents(tree_id): if not validate_path(entry.path, validate_path_element): continue full_path = _tree_to_fs_path(root_path, entry.path) if not os.path.exists(os.path.dirname(full_path)): os.makedirs(os.path.dirname(full_path)) # TODO(jelmer): Merge new index into working tree if S_ISGITLINK(entry.mode): if not os.path.isdir(full_path): os.mkdir(full_path) st = os.lstat(full_path) # TODO(jelmer): record and return submodule paths else: obj = object_store[entry.sha] st = build_file_from_blob( obj, entry.mode, full_path, honor_filemode=honor_filemode) # Add file to index if not honor_filemode or S_ISGITLINK(entry.mode): # we can not use tuple slicing to build a new tuple, # because on windows that will convert the times to # longs, which causes errors further along st_tuple = (entry.mode, st.st_ino, st.st_dev, st.st_nlink, st.st_uid, st.st_gid, st.st_size, st.st_atime, st.st_mtime, st.st_ctime) st = st.__class__(st_tuple) index[entry.path] = index_entry_from_stat(st, entry.sha, 0) index.write() def blob_from_path_and_stat(fs_path, st): """Create a blob from a path and a stat object. :param fs_path: Full file system path to file :param st: A stat object :return: A `Blob` object """ assert isinstance(fs_path, bytes) blob = Blob() if not stat.S_ISLNK(st.st_mode): with open(fs_path, 'rb') as f: blob.data = f.read() else: if sys.platform == 'win32' and sys.version_info[0] == 3: # os.readlink on Python3 on Windows requires a unicode string. # TODO(jelmer): Don't assume tree_encoding == fs_encoding tree_encoding = sys.getfilesystemencoding() fs_path = fs_path.decode(tree_encoding) blob.data = os.readlink(fs_path).encode(tree_encoding) else: blob.data = os.readlink(fs_path) return blob def get_unstaged_changes(index, root_path): """Walk through an index and check for differences against working tree. :param index: index to check :param root_path: path in which to find files :return: iterator over paths with unstaged changes """ # For each entry in the index check the sha1 & ensure not staged if not isinstance(root_path, bytes): root_path = root_path.encode(sys.getfilesystemencoding()) for tree_path, entry in index.iteritems(): full_path = _tree_to_fs_path(root_path, tree_path) try: blob = blob_from_path_and_stat(full_path, os.lstat(full_path)) except OSError as e: if e.errno != errno.ENOENT: raise # The file was removed, so we assume that counts as # different from whatever file used to exist. yield tree_path except IOError as e: if e.errno != errno.EISDIR: raise # This is actually a directory if os.path.exists(os.path.join(tree_path, '.git')): # Submodule from dulwich.errors import NotGitRepository from dulwich.repo import Repo try: if entry.sha != Repo(tree_path).head(): yield tree_path except NotGitRepository: yield tree_path else: # The file was changed to a directory, so consider it removed. yield tree_path else: if blob.id != entry.sha: yield tree_path os_sep_bytes = os.sep.encode('ascii') def _tree_to_fs_path(root_path, tree_path): """Convert a git tree path to a file system path. :param root_path: Root filesystem path :param tree_path: Git tree path as bytes :return: File system path. """ assert isinstance(tree_path, bytes) if os_sep_bytes != b'/': sep_corrected_path = tree_path.replace(b'/', os_sep_bytes) else: sep_corrected_path = tree_path return os.path.join(root_path, sep_corrected_path) def _fs_to_tree_path(fs_path, fs_encoding=None): """Convert a file system path to a git tree path. :param fs_path: File system path. :param fs_encoding: File system encoding :return: Git tree path as bytes """ if fs_encoding is None: fs_encoding = sys.getfilesystemencoding() if not isinstance(fs_path, bytes): fs_path_bytes = fs_path.encode(fs_encoding) else: fs_path_bytes = fs_path if os_sep_bytes != b'/': tree_path = fs_path_bytes.replace(os_sep_bytes, b'/') else: tree_path = fs_path_bytes return tree_path + + +def iter_fresh_entries(index, root_path): + """Iterate over current versions of index entries on disk. + + :param index: Index file + :param root_path: Root path to access from + :return: Iterator over path, index_entry + """ + for path in set(index): + p = _tree_to_fs_path(root_path, path) + try: + st = os.lstat(p) + blob = blob_from_path_and_stat(p, st) + except OSError as e: + if e.errno == errno.ENOENT: + del index[path] + else: + raise + except IOError as e: + if e.errno == errno.EISDIR: + del index[path] + else: + raise + else: + yield path, index_entry_from_stat(st, blob.id, 0) + + +def iter_fresh_blobs(index, root_path): + """Iterate over versions of blobs on disk referenced by index. + + :param index: Index file + :param root_path: Root path to access from + :return: Iterator over path, sha, mode + """ + for path, entry in iter_fresh_entries(index, root_path): + entry = IndexEntry(*entry) + yield path, entry.sha, cleanup_mode(entry.mode) + + +def refresh_index(index, root_path): + """Refresh the contents of an index. + + This is the equivalent to running 'git commit -a'. + + :param index: Index to update + :param root_path: Root filesystem path + """ + for path, entry in iter_fresh_entries(index, root_path): + index[path] = path diff --git a/dulwich/object_store.py b/dulwich/object_store.py index a73c6817..fac3e291 100644 --- a/dulwich/object_store.py +++ b/dulwich/object_store.py @@ -1,1220 +1,1306 @@ # 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, - write_pack_objects, compute_file_sha, PackIndexer, PackStreamCopier, ) 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 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): """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 tree_changes(self, source, target, want_unchanged=False): + def add_pack_data(self, count, pack_data): + """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) + 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): + 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 not stat.S_ISDIR(entry.mode) or include_trees: + 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): """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 text for an object. + """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): """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. """ - if len(objects) == 0: - # Don't bother writing an empty pack file - return - f, commit, abort = self.add_pack() - try: - write_pack_objects(f, objects) - except: - abort() - raise - else: - return commit() + return self.add_pack_data(*pack_objects_to_data(objects)) 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 l in f.readlines(): - l = l.rstrip(b"\n") - if l[0] == b"#": + for line in f.readlines(): + line = line.rstrip(b"\n") + if line[0] == b"#": continue - if os.path.isabs(l): - yield l.decode(sys.getfilesystemencoding()) + if os.path.isabs(line): + yield line.decode(sys.getfilesystemencoding()) else: - yield os.path.join(self.path, l).decode( + 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) if sys.platform == 'win32': try: os.rename(path, pack_base_name + '.pack') except WindowsError: os.remove(pack_base_name + '.pack') os.rename(path, pack_base_name + '.pack') else: os.rename(path, pack_base_name + '.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 + else: + os.unlink(path) os.rename(path, basename + ".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): """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: + except BaseException: abort() raise else: commit() -class ObjectImporter(object): - """Interface for importing objects.""" - - def __init__(self, count): - """Create a new ObjectImporter. - - :param count: Number of objects that's going to be imported. - """ - self.count = count - - def add_object(self, object): - """Add an object.""" - raise NotImplementedError(self.add_object) - - def finish(self, object): - """Finish the import and write objects to disk.""" - raise NotImplementedError(self.finish) - - 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): """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 = {} 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): + if self.add_store is None: + raise NotImplementedError(self.add_object) + return self.add_store.add_objects(objects) + + @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 diff --git a/dulwich/objects.py b/dulwich/objects.py index e659e41f..c4ed024d 100644 --- a/dulwich/objects.py +++ b/dulwich/objects.py @@ -1,1336 +1,1375 @@ # 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 + + 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 sepreated line.""" + """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()) - def __str__(self): - """Return raw string serialization of this object.""" - return self.as_raw_string() + 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): 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): if not isinstance(other, ShaFile): raise TypeError return self.id < other.id def __le__(self, other): if not isinstance(other, ShaFile): raise TypeError return self.id <= other.id def __cmp__(self, other): 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 l in f: - if l.startswith(b' '): + for line in f: + if line.startswith(b' '): # Indented continuation of the previous line - v += l[1:] + v += line[1:] else: if k is not None: # We parsed a new header, return its value yield (k, _strip_last_newline(v)) - if l == b'\n': + if line == b'\n': # Empty line indicates end of headers break - (k, v) = l.split(b' ', 1) + (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') def __init__(self): super(Tag, self).__init__() self._tagger = None self._tag_time = None self._tag_timezone = None self._tag_timezone_neg_utc = False @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) 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: - try: - sep = value.index(b'> ') - except ValueError: - self._tagger = value - self._tag_time = None - self._tag_timezone = None - self._tag_timezone_neg_utc = False - else: - self._tagger = value[0:sep+1] - try: - (timetext, timezonetext) = ( - value[sep+2:].rsplit(b' ', 1)) - self._tag_time = int(timetext) - self._tag_timezone, self._tag_timezone_neg_utc = ( - parse_timezone(timezonetext)) - except ValueError as e: - raise ObjectFormatException(e) + (self._tagger, + self._tag_time, + (self._tag_timezone, + self._tag_timezone_neg_utc)) = parse_time_entry(value) elif field is None: self._message = value 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") 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 - l = len(text) - while count < l: + 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'..'): raise ObjectFormatException('invalid name %s' % name) 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'> ') + 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, timetext, timezonetext = value.rsplit(b' ', 2) - author_time = int(timetext) - author_info = (author, author_time, parse_timezone(timezonetext)) + author_info = parse_time_entry(value) elif field == _COMMITTER_HEADER: - committer, timetext, timezonetext = value.rsplit(b' ', 2) - commit_time = int(timetext) - commit_info = ( - committer, commit_time, parse_timezone(timezonetext)) + 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") - # times are currently checked when set + 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/pack.py b/dulwich/pack.py index 9919607f..96f3b9bc 100644 --- a/dulwich/pack.py +++ b/dulwich/pack.py @@ -1,1975 +1,2035 @@ # pack.py -- For dealing with packed 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. # """Classes for dealing with packed git objects. A pack is a compact representation of a bunch of objects, stored using deltas where possible. They have two parts, the pack file, which stores the data, and an index that tells you where the data is. To find an object you look in all of the index files 'til you find a match for the object name. You then use the pointer got from this as a pointer in to the corresponding packfile. """ from collections import defaultdict import binascii from io import BytesIO, UnsupportedOperation from collections import ( deque, ) import difflib import struct from itertools import chain try: from itertools import imap, izip except ImportError: # Python3 imap = map izip = zip import os import sys from hashlib import sha1 from os import ( SEEK_CUR, SEEK_END, ) from struct import unpack_from import zlib try: import mmap except ImportError: has_mmap = False else: has_mmap = True # For some reason the above try, except fails to set has_mmap = False for plan9 if sys.platform == 'Plan9': has_mmap = False from dulwich.errors import ( # noqa: E402 ApplyDeltaError, ChecksumMismatch, ) from dulwich.file import GitFile # noqa: E402 from dulwich.lru_cache import ( # noqa: E402 LRUSizeCache, ) from dulwich.objects import ( # noqa: E402 ShaFile, hex_to_sha, sha_to_hex, object_header, ) OFS_DELTA = 6 REF_DELTA = 7 DELTA_TYPES = (OFS_DELTA, REF_DELTA) DEFAULT_PACK_DELTA_WINDOW_SIZE = 10 def take_msb_bytes(read, crc32=None): """Read bytes marked with most significant bit. :param read: Read function """ ret = [] while len(ret) == 0 or ret[-1] & 0x80: b = read(1) if crc32 is not None: crc32 = binascii.crc32(b, crc32) ret.append(ord(b[:1])) return ret, crc32 class UnpackedObject(object): """Class encapsulating an object unpacked from a pack file. These objects should only be created from within unpack_object. Most members start out as empty and are filled in at various points by read_zlib_chunks, unpack_object, DeltaChainIterator, etc. End users of this object should take care that the function they're getting this object from is guaranteed to set the members they need. """ __slots__ = [ 'offset', # Offset in its pack. '_sha', # Cached binary SHA. 'obj_type_num', # Type of this object. 'obj_chunks', # Decompressed and delta-resolved chunks. 'pack_type_num', # Type of this object in the pack (may be a delta). 'delta_base', # Delta base offset or SHA. 'comp_chunks', # Compressed object chunks. 'decomp_chunks', # Decompressed object chunks. 'decomp_len', # Decompressed length of this object. 'crc32', # CRC32. ] # TODO(dborowitz): read_zlib_chunks and unpack_object could very well be # methods of this object. def __init__(self, pack_type_num, delta_base, decomp_len, crc32): self.offset = None self._sha = None self.pack_type_num = pack_type_num self.delta_base = delta_base self.comp_chunks = None self.decomp_chunks = [] self.decomp_len = decomp_len self.crc32 = crc32 if pack_type_num in DELTA_TYPES: self.obj_type_num = None self.obj_chunks = None else: self.obj_type_num = pack_type_num self.obj_chunks = self.decomp_chunks self.delta_base = delta_base def sha(self): """Return the binary SHA of this object.""" if self._sha is None: self._sha = obj_sha(self.obj_type_num, self.obj_chunks) return self._sha def sha_file(self): """Return a ShaFile from this object.""" return ShaFile.from_raw_chunks(self.obj_type_num, self.obj_chunks) # Only provided for backwards compatibility with code that expects either # chunks or a delta tuple. def _obj(self): """Return the decompressed chunks, or (delta base, delta chunks).""" if self.pack_type_num in DELTA_TYPES: return (self.delta_base, self.decomp_chunks) else: return self.decomp_chunks def __eq__(self, other): if not isinstance(other, UnpackedObject): return False for slot in self.__slots__: if getattr(self, slot) != getattr(other, slot): return False return True def __ne__(self, other): return not (self == other) def __repr__(self): data = ['%s=%r' % (s, getattr(self, s)) for s in self.__slots__] return '%s(%s)' % (self.__class__.__name__, ', '.join(data)) _ZLIB_BUFSIZE = 4096 def read_zlib_chunks(read_some, unpacked, include_comp=False, buffer_size=_ZLIB_BUFSIZE): """Read zlib data from a buffer. This function requires that the buffer have additional data following the compressed data, which is guaranteed to be the case for git pack files. :param read_some: Read function that returns at least one byte, but may return less than the requested size. :param unpacked: An UnpackedObject to write result data to. If its crc32 attr is not None, the CRC32 of the compressed bytes will be computed using this starting CRC32. After this function, will have the following attrs set: * comp_chunks (if include_comp is True) * decomp_chunks * decomp_len * crc32 :param include_comp: If True, include compressed data in the result. :param buffer_size: Size of the read buffer. :return: Leftover unused data from the decompression. :raise zlib.error: if a decompression error occurred. """ if unpacked.decomp_len <= -1: raise ValueError('non-negative zlib data stream size expected') decomp_obj = zlib.decompressobj() comp_chunks = [] decomp_chunks = unpacked.decomp_chunks decomp_len = 0 crc32 = unpacked.crc32 while True: add = read_some(buffer_size) if not add: raise zlib.error('EOF before end of zlib stream') comp_chunks.append(add) decomp = decomp_obj.decompress(add) decomp_len += len(decomp) decomp_chunks.append(decomp) unused = decomp_obj.unused_data if unused: left = len(unused) if crc32 is not None: crc32 = binascii.crc32(add[:-left], crc32) if include_comp: comp_chunks[-1] = add[:-left] break elif crc32 is not None: crc32 = binascii.crc32(add, crc32) if crc32 is not None: crc32 &= 0xffffffff if decomp_len != unpacked.decomp_len: raise zlib.error('decompressed data does not match expected size') unpacked.crc32 = crc32 if include_comp: unpacked.comp_chunks = comp_chunks return unused def iter_sha1(iter): """Return the hexdigest of the SHA1 over a set of names. :param iter: Iterator over string objects :return: 40-byte hex sha1 digest """ sha = sha1() for name in iter: sha.update(name) return sha.hexdigest().encode('ascii') def load_pack_index(path): """Load an index file by path. :param filename: Path to the index file :return: A PackIndex loaded from the given path """ with GitFile(path, 'rb') as f: return load_pack_index_file(path, f) def _load_file_contents(f, size=None): try: fd = f.fileno() except (UnsupportedOperation, AttributeError): fd = None # Attempt to use mmap if possible if fd is not None: if size is None: size = os.fstat(fd).st_size if has_mmap: try: contents = mmap.mmap(fd, size, access=mmap.ACCESS_READ) except mmap.error: # Perhaps a socket? pass else: return contents, size contents = f.read() size = len(contents) return contents, size def load_pack_index_file(path, f): """Load an index file from a file-like object. :param path: Path for the index file :param f: File-like object :return: A PackIndex loaded from the given file """ contents, size = _load_file_contents(f) if contents[:4] == b'\377tOc': version = struct.unpack(b'>L', contents[4:8])[0] if version == 2: return PackIndex2( path, file=f, contents=contents, size=size) else: raise KeyError('Unknown pack index format %d' % version) else: return PackIndex1(path, file=f, contents=contents, size=size) def bisect_find_sha(start, end, sha, unpack_name): """Find a SHA in a data blob with sorted SHAs. :param start: Start index of range to search :param end: End index of range to search :param sha: Sha to find :param unpack_name: Callback to retrieve SHA by index :return: Index of the SHA, or None if it wasn't found """ assert start <= end while start <= end: i = (start + end) // 2 file_sha = unpack_name(i) if file_sha < sha: start = i + 1 elif file_sha > sha: end = i - 1 else: return i return None class PackIndex(object): """An index in to a packfile. Given a sha id of an object a pack index can tell you the location in the packfile of that object if it has it. """ def __eq__(self, other): if not isinstance(other, PackIndex): return False for (name1, _, _), (name2, _, _) in izip(self.iterentries(), other.iterentries()): if name1 != name2: return False return True def __ne__(self, other): return not self.__eq__(other) def __len__(self): """Return the number of entries in this pack index.""" raise NotImplementedError(self.__len__) def __iter__(self): """Iterate over the SHAs in this pack.""" return imap(sha_to_hex, self._itersha()) def iterentries(self): """Iterate over the entries in this pack index. :return: iterator over tuples with object name, offset in packfile and crc32 checksum. """ raise NotImplementedError(self.iterentries) def get_pack_checksum(self): """Return the SHA1 checksum stored for the corresponding packfile. :return: 20-byte binary digest """ raise NotImplementedError(self.get_pack_checksum) def object_index(self, sha): """Return the index in to the corresponding packfile for the object. Given the name of an object it will return the offset that object lives at within the corresponding pack file. If the pack file doesn't have the object then None will be returned. """ if len(sha) == 40: sha = hex_to_sha(sha) return self._object_index(sha) + def object_sha1(self, index): + """Return the SHA1 corresponding to the index in the pack file. + """ + # PERFORMANCE/TODO(jelmer): Avoid scanning entire index + for (name, offset, crc32) in self.iterentries(): + if offset == index: + return name + else: + raise KeyError(index) + def _object_index(self, sha): """See object_index. :param sha: A *binary* SHA string. (20 characters long)_ """ raise NotImplementedError(self._object_index) def objects_sha1(self): """Return the hex SHA1 over all the shas of all objects in this pack. :note: This is used for the filename of the pack. """ return iter_sha1(self._itersha()) def _itersha(self): """Yield all the SHA1's of the objects in the index, sorted.""" raise NotImplementedError(self._itersha) class MemoryPackIndex(PackIndex): """Pack index that is stored entirely in memory.""" def __init__(self, entries, pack_checksum=None): """Create a new MemoryPackIndex. :param entries: Sequence of name, idx, crc32 (sorted) :param pack_checksum: Optional pack checksum """ self._by_sha = {} + self._by_index = {} for name, idx, crc32 in entries: self._by_sha[name] = idx + self._by_index[idx] = name self._entries = entries self._pack_checksum = pack_checksum def get_pack_checksum(self): return self._pack_checksum def __len__(self): return len(self._entries) def _object_index(self, sha): return self._by_sha[sha][0] + def object_sha1(self, index): + return self._by_index[index] + def _itersha(self): return iter(self._by_sha) def iterentries(self): return iter(self._entries) class FilePackIndex(PackIndex): """Pack index that is based on a file. To do the loop it opens the file, and indexes first 256 4 byte groups with the first byte of the sha id. The value in the four byte group indexed is the end of the group that shares the same starting byte. Subtract one from the starting byte and index again to find the start of the group. The values are sorted by sha id within the group, so do the math to find the start and end offset and then bisect in to find if the value is present. """ def __init__(self, filename, file=None, contents=None, size=None): """Create a pack index object. Provide it with the name of the index file to consider, and it will map it whenever required. """ self._filename = filename # Take the size now, so it can be checked each time we map the file to # ensure that it hasn't changed. if file is None: self._file = GitFile(filename, 'rb') else: self._file = file if contents is None: self._contents, self._size = _load_file_contents(self._file, size) else: self._contents, self._size = (contents, size) @property def path(self): return self._filename def __eq__(self, other): # Quick optimization: if (isinstance(other, FilePackIndex) and self._fan_out_table != other._fan_out_table): return False return super(FilePackIndex, self).__eq__(other) def close(self): self._file.close() if getattr(self._contents, "close", None) is not None: self._contents.close() def __len__(self): """Return the number of entries in this pack index.""" return self._fan_out_table[-1] def _unpack_entry(self, i): """Unpack the i-th entry in the index file. :return: Tuple with object name (SHA), offset in pack file and CRC32 checksum (if known). """ raise NotImplementedError(self._unpack_entry) def _unpack_name(self, i): """Unpack the i-th name from the index file.""" raise NotImplementedError(self._unpack_name) def _unpack_offset(self, i): """Unpack the i-th object offset from the index file.""" raise NotImplementedError(self._unpack_offset) def _unpack_crc32_checksum(self, i): """Unpack the crc32 checksum for the ith object from the index file. """ raise NotImplementedError(self._unpack_crc32_checksum) def _itersha(self): for i in range(len(self)): yield self._unpack_name(i) def iterentries(self): """Iterate over the entries in this pack index. :return: iterator over tuples with object name, offset in packfile and crc32 checksum. """ for i in range(len(self)): yield self._unpack_entry(i) def _read_fan_out_table(self, start_offset): ret = [] for i in range(0x100): fanout_entry = self._contents[ start_offset+i*4:start_offset+(i+1)*4] ret.append(struct.unpack('>L', fanout_entry)[0]) return ret def check(self): """Check that the stored checksum matches the actual checksum.""" actual = self.calculate_checksum() stored = self.get_stored_checksum() if actual != stored: raise ChecksumMismatch(stored, actual) def calculate_checksum(self): """Calculate the SHA1 checksum over this pack index. :return: This is a 20-byte binary digest """ return sha1(self._contents[:-20]).digest() def get_pack_checksum(self): """Return the SHA1 checksum stored for the corresponding packfile. :return: 20-byte binary digest """ return bytes(self._contents[-40:-20]) def get_stored_checksum(self): """Return the SHA1 checksum stored for this index. :return: 20-byte binary digest """ return bytes(self._contents[-20:]) def _object_index(self, sha): """See object_index. :param sha: A *binary* SHA string. (20 characters long)_ """ assert len(sha) == 20 idx = ord(sha[:1]) if idx == 0: start = 0 else: start = self._fan_out_table[idx-1] end = self._fan_out_table[idx] i = bisect_find_sha(start, end, sha, self._unpack_name) if i is None: raise KeyError(sha) return self._unpack_offset(i) class PackIndex1(FilePackIndex): """Version 1 Pack Index file.""" def __init__(self, filename, file=None, contents=None, size=None): super(PackIndex1, self).__init__(filename, file, contents, size) self.version = 1 self._fan_out_table = self._read_fan_out_table(0) def _unpack_entry(self, i): (offset, name) = unpack_from('>L20s', self._contents, (0x100 * 4) + (i * 24)) return (name, offset, None) def _unpack_name(self, i): offset = (0x100 * 4) + (i * 24) + 4 return self._contents[offset:offset+20] def _unpack_offset(self, i): offset = (0x100 * 4) + (i * 24) return unpack_from('>L', self._contents, offset)[0] def _unpack_crc32_checksum(self, i): # Not stored in v1 index files return None class PackIndex2(FilePackIndex): """Version 2 Pack Index file.""" def __init__(self, filename, file=None, contents=None, size=None): super(PackIndex2, self).__init__(filename, file, contents, size) if self._contents[:4] != b'\377tOc': raise AssertionError('Not a v2 pack index file') (self.version, ) = unpack_from(b'>L', self._contents, 4) if self.version != 2: raise AssertionError('Version was %d' % self.version) self._fan_out_table = self._read_fan_out_table(8) self._name_table_offset = 8 + 0x100 * 4 self._crc32_table_offset = self._name_table_offset + 20 * len(self) self._pack_offset_table_offset = (self._crc32_table_offset + 4 * len(self)) self._pack_offset_largetable_offset = ( self._pack_offset_table_offset + 4 * len(self)) def _unpack_entry(self, i): return (self._unpack_name(i), self._unpack_offset(i), self._unpack_crc32_checksum(i)) def _unpack_name(self, i): offset = self._name_table_offset + i * 20 return self._contents[offset:offset+20] def _unpack_offset(self, i): offset = self._pack_offset_table_offset + i * 4 offset = unpack_from('>L', self._contents, offset)[0] if offset & (2**31): offset = ( self._pack_offset_largetable_offset + (offset & (2 ** 31 - 1)) * 8) offset = unpack_from('>Q', self._contents, offset)[0] return offset def _unpack_crc32_checksum(self, i): return unpack_from('>L', self._contents, self._crc32_table_offset + i * 4)[0] def read_pack_header(read): """Read the header of a pack file. :param read: Read function :return: Tuple of (pack version, number of objects). If no data is available to read, returns (None, None). """ header = read(12) if not header: return None, None if header[:4] != b'PACK': raise AssertionError('Invalid pack header %r' % header) (version,) = unpack_from(b'>L', header, 4) if version not in (2, 3): raise AssertionError('Version was %d' % version) (num_objects,) = unpack_from(b'>L', header, 8) return (version, num_objects) def chunks_length(chunks): if isinstance(chunks, bytes): return len(chunks) else: return sum(imap(len, chunks)) def unpack_object(read_all, read_some=None, compute_crc32=False, include_comp=False, zlib_bufsize=_ZLIB_BUFSIZE): """Unpack a Git object. :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. :param compute_crc32: If True, compute the CRC32 of the compressed data. If False, the returned CRC32 will be None. :param include_comp: If True, include compressed data in the result. :param zlib_bufsize: An optional buffer size for zlib operations. :return: A tuple of (unpacked, unused), where unused is the unused data leftover from decompression, and unpacked in an UnpackedObject with the following attrs set: * obj_chunks (for non-delta types) * pack_type_num * delta_base (for delta types) * comp_chunks (if include_comp is True) * decomp_chunks * decomp_len * crc32 (if compute_crc32 is True) """ if read_some is None: read_some = read_all if compute_crc32: crc32 = 0 else: crc32 = None bytes, crc32 = take_msb_bytes(read_all, crc32=crc32) type_num = (bytes[0] >> 4) & 0x07 size = bytes[0] & 0x0f for i, byte in enumerate(bytes[1:]): size += (byte & 0x7f) << ((i * 7) + 4) raw_base = len(bytes) if type_num == OFS_DELTA: bytes, crc32 = take_msb_bytes(read_all, crc32=crc32) raw_base += len(bytes) if bytes[-1] & 0x80: raise AssertionError delta_base_offset = bytes[0] & 0x7f for byte in bytes[1:]: delta_base_offset += 1 delta_base_offset <<= 7 delta_base_offset += (byte & 0x7f) delta_base = delta_base_offset elif type_num == REF_DELTA: delta_base = read_all(20) if compute_crc32: crc32 = binascii.crc32(delta_base, crc32) raw_base += 20 else: delta_base = None unpacked = UnpackedObject(type_num, delta_base, size, crc32) unused = read_zlib_chunks(read_some, unpacked, buffer_size=zlib_bufsize, include_comp=include_comp) return unpacked, unused def _compute_object_size(value): """Compute the size of a unresolved object for use with LRUSizeCache.""" (num, obj) = value if num in DELTA_TYPES: return chunks_length(obj[1]) return chunks_length(obj) class PackStreamReader(object): """Class to read a pack stream. The pack is read from a ReceivableProtocol using read() or recv() as appropriate. """ def __init__(self, read_all, read_some=None, zlib_bufsize=_ZLIB_BUFSIZE): self.read_all = read_all if read_some is None: self.read_some = read_all else: self.read_some = read_some self.sha = sha1() self._offset = 0 self._rbuf = BytesIO() # trailer is a deque to avoid memory allocation on small reads self._trailer = deque() self._zlib_bufsize = zlib_bufsize def _read(self, read, size): """Read up to size bytes using the given callback. As a side effect, update the verifier's hash (excluding the last 20 bytes read). :param read: The read callback to read from. :param size: The maximum number of bytes to read; the particular behavior is callback-specific. """ data = read(size) # maintain a trailer of the last 20 bytes we've read n = len(data) self._offset += n tn = len(self._trailer) if n >= 20: to_pop = tn to_add = 20 else: to_pop = max(n + tn - 20, 0) to_add = n self.sha.update( bytes(bytearray([self._trailer.popleft() for _ in range(to_pop)]))) self._trailer.extend(data[-to_add:]) # hash everything but the trailer self.sha.update(data[:-to_add]) return data def _buf_len(self): buf = self._rbuf start = buf.tell() buf.seek(0, SEEK_END) end = buf.tell() buf.seek(start) return end - start @property def offset(self): return self._offset - self._buf_len() def read(self, size): """Read, blocking until size bytes are read.""" buf_len = self._buf_len() if buf_len >= size: return self._rbuf.read(size) buf_data = self._rbuf.read() self._rbuf = BytesIO() return buf_data + self._read(self.read_all, size - buf_len) def recv(self, size): """Read up to size bytes, blocking until one byte is read.""" buf_len = self._buf_len() if buf_len: data = self._rbuf.read(size) if size >= buf_len: self._rbuf = BytesIO() return data return self._read(self.read_some, size) def __len__(self): return self._num_objects def read_objects(self, compute_crc32=False): """Read the objects in this pack file. :param compute_crc32: If True, compute the CRC32 of the compressed data. If False, the returned CRC32 will be None. :return: Iterator over UnpackedObjects with the following members set: offset obj_type_num obj_chunks (for non-delta types) delta_base (for delta types) decomp_chunks decomp_len crc32 (if compute_crc32 is True) :raise ChecksumMismatch: if the checksum of the pack contents does not match the checksum in the pack trailer. :raise zlib.error: if an error occurred during zlib decompression. :raise IOError: if an error occurred writing to the output file. """ pack_version, self._num_objects = read_pack_header(self.read) if pack_version is None: return for i in range(self._num_objects): offset = self.offset unpacked, unused = unpack_object( self.read, read_some=self.recv, compute_crc32=compute_crc32, zlib_bufsize=self._zlib_bufsize) unpacked.offset = offset # prepend any unused data to current read buffer buf = BytesIO() buf.write(unused) buf.write(self._rbuf.read()) buf.seek(0) self._rbuf = buf yield unpacked if self._buf_len() < 20: # If the read buffer is full, then the last read() got the whole # trailer off the wire. If not, it means there is still some of the # trailer to read. We need to read() all 20 bytes; N come from the # read buffer and (20 - N) come from the wire. self.read(20) pack_sha = bytearray(self._trailer) if pack_sha != self.sha.digest(): raise ChecksumMismatch(sha_to_hex(pack_sha), self.sha.hexdigest()) class PackStreamCopier(PackStreamReader): """Class to verify a pack stream as it is being read. The pack is read from a ReceivableProtocol using read() or recv() as appropriate and written out to the given file-like object. """ def __init__(self, read_all, read_some, outfile, delta_iter=None): """Initialize the copier. :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. :param outfile: File-like object to write output through. :param delta_iter: Optional DeltaChainIterator to record deltas as we read them. """ super(PackStreamCopier, self).__init__(read_all, read_some=read_some) self.outfile = outfile self._delta_iter = delta_iter def _read(self, read, size): """Read data from the read callback and write it to the file.""" data = super(PackStreamCopier, self)._read(read, size) self.outfile.write(data) return data def verify(self): """Verify a pack stream and write it to the output file. See PackStreamReader.iterobjects for a list of exceptions this may throw. """ if self._delta_iter: for unpacked in self.read_objects(): self._delta_iter.record(unpacked) else: for _ in self.read_objects(): pass def obj_sha(type, chunks): """Compute the SHA for a numeric type and object chunks.""" sha = sha1() sha.update(object_header(type, chunks_length(chunks))) if isinstance(chunks, bytes): sha.update(chunks) else: for chunk in chunks: sha.update(chunk) return sha.digest() def compute_file_sha(f, start_ofs=0, end_ofs=0, buffer_size=1 << 16): """Hash a portion of a file into a new SHA. :param f: A file-like object to read from that supports seek(). :param start_ofs: The offset in the file to start reading at. :param end_ofs: The offset in the file to end reading at, relative to the end of the file. :param buffer_size: A buffer size for reading. :return: A new SHA object updated with data read from the file. """ sha = sha1() f.seek(0, SEEK_END) length = f.tell() if (end_ofs < 0 and length + end_ofs < start_ofs) or end_ofs > length: raise AssertionError( "Attempt to read beyond file length. " "start_ofs: %d, end_ofs: %d, file length: %d" % ( start_ofs, end_ofs, length)) todo = length + end_ofs - start_ofs f.seek(start_ofs) while todo: data = f.read(min(todo, buffer_size)) sha.update(data) todo -= len(data) return sha class PackData(object): """The data contained in a packfile. Pack files can be accessed both sequentially for exploding a pack, and directly with the help of an index to retrieve a specific object. The objects within are either complete or a delta against another. The header is variable length. If the MSB of each byte is set then it indicates that the subsequent byte is still part of the header. For the first byte the next MS bits are the type, which tells you the type of object, and whether it is a delta. The LS byte is the lowest bits of the size. For each subsequent byte the LS 7 bits are the next MS bits of the size, i.e. the last byte of the header contains the MS bits of the size. For the complete objects the data is stored as zlib deflated data. The size in the header is the uncompressed object size, so to uncompress you need to just keep feeding data to zlib until you get an object back, or it errors on bad data. This is done here by just giving the complete buffer from the start of the deflated object on. This is bad, but until I get mmap sorted out it will have to do. Currently there are no integrity checks done. Also no attempt is made to try and detect the delta case, or a request for an object at the wrong position. It will all just throw a zlib or KeyError. """ def __init__(self, filename, file=None, size=None): """Create a PackData object representing the pack in the given filename. The file must exist and stay readable until the object is disposed of. It must also stay the same size. It will be mapped whenever needed. Currently there is a restriction on the size of the pack as the python mmap implementation is flawed. """ self._filename = filename self._size = size self._header_size = 12 if file is None: self._file = GitFile(self._filename, 'rb') else: self._file = file (version, self._num_objects) = read_pack_header(self._file.read) self._offset_cache = LRUSizeCache( 1024*1024*20, compute_size=_compute_object_size) self.pack = None @property def filename(self): return os.path.basename(self._filename) @property def path(self): return self._filename @classmethod def from_file(cls, file, size): return cls(str(file), file=file, size=size) @classmethod def from_path(cls, path): return cls(filename=path) def close(self): self._file.close() def __enter__(self): return self def __exit__(self, exc_type, exc_val, exc_tb): self.close() def _get_size(self): if self._size is not None: return self._size self._size = os.path.getsize(self._filename) if self._size < self._header_size: errmsg = ('%s is too small for a packfile (%d < %d)' % (self._filename, self._size, self._header_size)) raise AssertionError(errmsg) return self._size def __len__(self): """Returns the number of objects in this pack.""" return self._num_objects def calculate_checksum(self): """Calculate the checksum for this pack. :return: 20-byte binary SHA1 digest """ return compute_file_sha(self._file, end_ofs=-20).digest() def get_ref(self, sha): """Get the object for a ref SHA, only looking in this pack.""" # TODO: cache these results if self.pack is None: raise KeyError(sha) try: offset = self.pack.index.object_index(sha) except KeyError: offset = None if offset: type, obj = self.get_object_at(offset) elif self.pack is not None and self.pack.resolve_ext_ref: type, obj = self.pack.resolve_ext_ref(sha) else: raise KeyError(sha) return offset, type, obj def resolve_object(self, offset, type, obj, get_ref=None): """Resolve an object, possibly resolving deltas when necessary. :return: Tuple with object type and contents. """ # Walk down the delta chain, building a stack of deltas to reach # the requested object. base_offset = offset base_type = type base_obj = obj delta_stack = [] while base_type in DELTA_TYPES: prev_offset = base_offset if get_ref is None: get_ref = self.get_ref if base_type == OFS_DELTA: (delta_offset, delta) = base_obj # TODO: clean up asserts and replace with nicer error messages base_offset = base_offset - delta_offset base_type, base_obj = self.get_object_at(base_offset) assert isinstance(base_type, int) elif base_type == REF_DELTA: (basename, delta) = base_obj assert isinstance(basename, bytes) and len(basename) == 20 base_offset, base_type, base_obj = get_ref(basename) assert isinstance(base_type, int) delta_stack.append((prev_offset, base_type, delta)) # Now grab the base object (mustn't be a delta) and apply the # deltas all the way up the stack. chunks = base_obj for prev_offset, delta_type, delta in reversed(delta_stack): chunks = apply_delta(chunks, delta) # TODO(dborowitz): This can result in poor performance if # large base objects are separated from deltas in the pack. # We should reorganize so that we apply deltas to all # objects in a chain one after the other to optimize cache # performance. if prev_offset is not None: self._offset_cache[prev_offset] = base_type, chunks return base_type, chunks def iterobjects(self, progress=None, compute_crc32=True): self._file.seek(self._header_size) for i in range(1, self._num_objects + 1): offset = self._file.tell() unpacked, unused = unpack_object( self._file.read, compute_crc32=compute_crc32) if progress is not None: progress(i, self._num_objects) yield (offset, unpacked.pack_type_num, unpacked._obj(), unpacked.crc32) # Back up over unused data. self._file.seek(-len(unused), SEEK_CUR) def _iter_unpacked(self): # TODO(dborowitz): Merge this with iterobjects, if we can change its # return type. self._file.seek(self._header_size) if self._num_objects is None: return for _ in range(self._num_objects): offset = self._file.tell() unpacked, unused = unpack_object( self._file.read, compute_crc32=False) unpacked.offset = offset yield unpacked # Back up over unused data. self._file.seek(-len(unused), SEEK_CUR) def iterentries(self, progress=None): """Yield entries summarizing the contents of this pack. :param progress: Progress function, called with current and total object count. :return: iterator of tuples with (sha, offset, crc32) """ num_objects = self._num_objects resolve_ext_ref = ( self.pack.resolve_ext_ref if self.pack is not None else None) indexer = PackIndexer.for_pack_data( self, resolve_ext_ref=resolve_ext_ref) for i, result in enumerate(indexer): if progress is not None: progress(i, num_objects) yield result def sorted_entries(self, progress=None): """Return entries in this pack, sorted by SHA. :param progress: Progress function, called with current and total object count :return: List of tuples with (sha, offset, crc32) """ ret = sorted(self.iterentries(progress=progress)) return ret def create_index_v1(self, filename, progress=None): """Create a version 1 file for this data file. :param filename: Index filename. :param progress: Progress report function :return: Checksum of index file """ entries = self.sorted_entries(progress=progress) with GitFile(filename, 'wb') as f: return write_pack_index_v1(f, entries, self.calculate_checksum()) def create_index_v2(self, filename, progress=None): """Create a version 2 index file for this data file. :param filename: Index filename. :param progress: Progress report function :return: Checksum of index file """ entries = self.sorted_entries(progress=progress) with GitFile(filename, 'wb') as f: return write_pack_index_v2(f, entries, self.calculate_checksum()) def create_index(self, filename, progress=None, version=2): """Create an index file for this data file. :param filename: Index filename. :param progress: Progress report function :return: Checksum of index file """ if version == 1: return self.create_index_v1(filename, progress) elif version == 2: return self.create_index_v2(filename, progress) else: raise ValueError('unknown index format %d' % version) def get_stored_checksum(self): """Return the expected checksum stored in this pack.""" self._file.seek(-20, SEEK_END) return self._file.read(20) def check(self): """Check the consistency of this pack.""" actual = self.calculate_checksum() stored = self.get_stored_checksum() if actual != stored: raise ChecksumMismatch(stored, actual) + def get_compressed_data_at(self, offset): + """Given offset in the packfile return compressed data that is there. + + Using the associated index the location of an object can be looked up, + and then the packfile can be asked directly for that object using this + function. + """ + assert offset >= self._header_size + self._file.seek(offset) + unpacked, _ = unpack_object(self._file.read, include_comp=True) + return (unpacked.pack_type_num, unpacked.delta_base, + unpacked.comp_chunks) + def get_object_at(self, offset): """Given an offset in to the packfile return the object that is there. Using the associated index the location of an object can be looked up, and then the packfile can be asked directly for that object using this function. """ try: return self._offset_cache[offset] except KeyError: pass assert offset >= self._header_size self._file.seek(offset) unpacked, _ = unpack_object(self._file.read) return (unpacked.pack_type_num, unpacked._obj()) class DeltaChainIterator(object): """Abstract iterator over pack data based on delta chains. Each object in the pack is guaranteed to be inflated exactly once, regardless of how many objects reference it as a delta base. As a result, memory usage is proportional to the length of the longest delta chain. Subclasses can override _result to define the result type of the iterator. By default, results are UnpackedObjects with the following members set: * offset * obj_type_num * obj_chunks * pack_type_num * delta_base (for delta types) * comp_chunks (if _include_comp is True) * decomp_chunks * decomp_len * crc32 (if _compute_crc32 is True) """ _compute_crc32 = False _include_comp = False def __init__(self, file_obj, resolve_ext_ref=None): self._file = file_obj self._resolve_ext_ref = resolve_ext_ref self._pending_ofs = defaultdict(list) self._pending_ref = defaultdict(list) self._full_ofs = [] self._shas = {} self._ext_refs = [] @classmethod def for_pack_data(cls, pack_data, resolve_ext_ref=None): walker = cls(None, resolve_ext_ref=resolve_ext_ref) walker.set_pack_data(pack_data) for unpacked in pack_data._iter_unpacked(): walker.record(unpacked) return walker def record(self, unpacked): type_num = unpacked.pack_type_num offset = unpacked.offset if type_num == OFS_DELTA: base_offset = offset - unpacked.delta_base self._pending_ofs[base_offset].append(offset) elif type_num == REF_DELTA: self._pending_ref[unpacked.delta_base].append(offset) else: self._full_ofs.append((offset, type_num)) def set_pack_data(self, pack_data): self._file = pack_data._file def _walk_all_chains(self): for offset, type_num in self._full_ofs: for result in self._follow_chain(offset, type_num, None): yield result for result in self._walk_ref_chains(): yield result assert not self._pending_ofs def _ensure_no_pending(self): if self._pending_ref: raise KeyError([sha_to_hex(s) for s in self._pending_ref]) def _walk_ref_chains(self): if not self._resolve_ext_ref: self._ensure_no_pending() return for base_sha, pending in sorted(self._pending_ref.items()): if base_sha not in self._pending_ref: continue try: type_num, chunks = self._resolve_ext_ref(base_sha) except KeyError: # Not an external ref, but may depend on one. Either it will # get popped via a _follow_chain call, or we will raise an # error below. continue self._ext_refs.append(base_sha) self._pending_ref.pop(base_sha) for new_offset in pending: for result in self._follow_chain(new_offset, type_num, chunks): yield result self._ensure_no_pending() def _result(self, unpacked): return unpacked def _resolve_object(self, offset, obj_type_num, base_chunks): self._file.seek(offset) unpacked, _ = unpack_object( self._file.read, include_comp=self._include_comp, compute_crc32=self._compute_crc32) unpacked.offset = offset if base_chunks is None: assert unpacked.pack_type_num == obj_type_num else: assert unpacked.pack_type_num in DELTA_TYPES unpacked.obj_type_num = obj_type_num unpacked.obj_chunks = apply_delta(base_chunks, unpacked.decomp_chunks) return unpacked def _follow_chain(self, offset, obj_type_num, base_chunks): # Unlike PackData.get_object_at, there is no need to cache offsets as # this approach by design inflates each object exactly once. todo = [(offset, obj_type_num, base_chunks)] for offset, obj_type_num, base_chunks in todo: unpacked = self._resolve_object(offset, obj_type_num, base_chunks) yield self._result(unpacked) unblocked = chain(self._pending_ofs.pop(unpacked.offset, []), self._pending_ref.pop(unpacked.sha(), [])) todo.extend( (new_offset, unpacked.obj_type_num, unpacked.obj_chunks) for new_offset in unblocked) def __iter__(self): return self._walk_all_chains() def ext_refs(self): return self._ext_refs class PackIndexer(DeltaChainIterator): """Delta chain iterator that yields index entries.""" _compute_crc32 = True def _result(self, unpacked): return unpacked.sha(), unpacked.offset, unpacked.crc32 class PackInflater(DeltaChainIterator): """Delta chain iterator that yields ShaFile objects.""" def _result(self, unpacked): return unpacked.sha_file() class SHA1Reader(object): """Wrapper for file-like object that remembers the SHA1 of its data.""" def __init__(self, f): self.f = f self.sha1 = sha1(b'') def read(self, num=None): data = self.f.read(num) self.sha1.update(data) return data def check_sha(self): stored = self.f.read(20) if stored != self.sha1.digest(): raise ChecksumMismatch(self.sha1.hexdigest(), sha_to_hex(stored)) def close(self): return self.f.close() def tell(self): return self.f.tell() class SHA1Writer(object): """Wrapper for file-like object that remembers the SHA1 of its data.""" def __init__(self, f): self.f = f self.length = 0 self.sha1 = sha1(b'') def write(self, data): self.sha1.update(data) self.f.write(data) self.length += len(data) def write_sha(self): sha = self.sha1.digest() assert len(sha) == 20 self.f.write(sha) self.length += len(sha) return sha def close(self): sha = self.write_sha() self.f.close() return sha def offset(self): return self.length def tell(self): return self.f.tell() def pack_object_header(type_num, delta_base, size): """Create a pack object header for the given object info. :param type_num: Numeric type of the object. :param delta_base: Delta base offset or ref, or None for whole objects. :param size: Uncompressed object size. :return: A header for a packed object. """ header = [] c = (type_num << 4) | (size & 15) size >>= 4 while size: header.append(c | 0x80) c = size & 0x7f size >>= 7 header.append(c) if type_num == OFS_DELTA: ret = [delta_base & 0x7f] delta_base >>= 7 while delta_base: delta_base -= 1 ret.insert(0, 0x80 | (delta_base & 0x7f)) delta_base >>= 7 header.extend(ret) elif type_num == REF_DELTA: assert len(delta_base) == 20 header += delta_base return bytearray(header) def write_pack_object(f, type, object, sha=None): """Write pack object to a file. :param f: File to write to :param type: Numeric type of the object :param object: Object to write :return: Tuple with offset at which the object was written, and crc32 """ if type in DELTA_TYPES: delta_base, object = object else: delta_base = None header = bytes(pack_object_header(type, delta_base, len(object))) comp_data = zlib.compress(object) crc32 = 0 for data in (header, comp_data): f.write(data) if sha is not None: sha.update(data) crc32 = binascii.crc32(data, crc32) return crc32 & 0xffffffff def write_pack(filename, objects, deltify=None, delta_window_size=None): """Write a new pack data file. :param filename: Path to the new pack file (without .pack extension) :param objects: Iterable of (object, path) tuples to write. Should provide __len__ :param window_size: Delta window size :param deltify: Whether to deltify pack objects :return: Tuple with checksum of pack file and index file """ with GitFile(filename + '.pack', 'wb') as f: entries, data_sum = write_pack_objects( f, objects, delta_window_size=delta_window_size, deltify=deltify) entries = sorted([(k, v[0], v[1]) for (k, v) in entries.items()]) with GitFile(filename + '.idx', 'wb') as f: return data_sum, write_pack_index_v2(f, entries, data_sum) def write_pack_header(f, num_objects): """Write a pack header for the given number of objects.""" f.write(b'PACK') # Pack header f.write(struct.pack(b'>L', 2)) # Pack version f.write(struct.pack(b'>L', num_objects)) # Number of objects in pack def deltify_pack_objects(objects, window_size=None): """Generate deltas for pack objects. :param objects: An iterable of (object, path) tuples to deltify. :param window_size: Window size; None for default :return: Iterator over type_num, object id, delta_base, content delta_base is None for full text entries """ + # TODO(jelmer): Use threads if window_size is None: window_size = DEFAULT_PACK_DELTA_WINDOW_SIZE # Build a list of objects ordered by the magic Linus heuristic # This helps us find good objects to diff against us magic = [] for obj, path in objects: magic.append((obj.type_num, path, -obj.raw_length(), obj)) magic.sort() possible_bases = deque() for type_num, path, neg_length, o in magic: raw = o.as_raw_string() winner = raw winner_base = None for base in possible_bases: if base.type_num != type_num: continue delta = create_delta(base.as_raw_string(), raw) if len(delta) < len(winner): winner_base = base.sha().digest() winner = delta yield type_num, o.sha().digest(), winner_base, winner possible_bases.appendleft(o) while len(possible_bases) > window_size: possible_bases.pop() -def write_pack_objects(f, objects, delta_window_size=None, deltify=False): +def pack_objects_to_data(objects): + """Create pack data from objects + + :param objects: Pack objects + :return: Tuples with (type_num, hexdigest, delta base, object chunks) + """ + count = len(objects) + return (count, + ((o.type_num, o.sha().digest(), None, o.as_raw_string()) + for (o, path) in objects)) + + +def write_pack_objects(f, objects, delta_window_size=None, deltify=None): """Write a new pack data file. :param f: File to write to :param objects: Iterable of (object, path) tuples to write. Should provide __len__ :param window_size: Sliding window size for searching for deltas; Set to None for default window size. :param deltify: Whether to deltify objects :return: Dict mapping id -> (offset, crc32 checksum), pack checksum """ + if deltify is None: + # PERFORMANCE/TODO(jelmer): This should be enabled but is *much* too + # slow at the moment. + deltify = False if deltify: pack_contents = deltify_pack_objects(objects, delta_window_size) + pack_contents_count = len(objects) else: - pack_contents = ( - (o.type_num, o.sha().digest(), None, o.as_raw_string()) - for (o, path) in objects) + pack_contents_count, pack_contents = pack_objects_to_data(objects) - return write_pack_data(f, len(objects), pack_contents) + return write_pack_data(f, pack_contents_count, pack_contents) def write_pack_data(f, num_records, records): """Write a new pack data file. :param f: File to write to :param num_records: Number of records :param records: Iterator over type_num, object_id, delta_base, raw :return: Dict mapping id -> (offset, crc32 checksum), pack checksum """ # Write the pack entries = {} f = SHA1Writer(f) write_pack_header(f, num_records) for type_num, object_id, delta_base, raw in records: offset = f.offset() if delta_base is not None: try: base_offset, base_crc32 = entries[delta_base] except KeyError: type_num = REF_DELTA raw = (delta_base, raw) else: type_num = OFS_DELTA raw = (offset - base_offset, raw) crc32 = write_pack_object(f, type_num, raw) entries[object_id] = (offset, crc32) return entries, f.write_sha() def write_pack_index_v1(f, entries, pack_checksum): """Write a new pack index file. :param f: A file-like object to write to :param entries: List of tuples with object name (sha), offset_in_pack, and crc32_checksum. :param pack_checksum: Checksum of the pack file. :return: The SHA of the written index file """ f = SHA1Writer(f) fan_out_table = defaultdict(lambda: 0) for (name, offset, entry_checksum) in entries: fan_out_table[ord(name[:1])] += 1 # Fan-out table for i in range(0x100): f.write(struct.pack('>L', fan_out_table[i])) fan_out_table[i+1] += fan_out_table[i] for (name, offset, entry_checksum) in entries: if not (offset <= 0xffffffff): raise TypeError("pack format 1 only supports offsets < 2Gb") f.write(struct.pack('>L20s', offset, name)) assert len(pack_checksum) == 20 f.write(pack_checksum) return f.write_sha() def _delta_encode_size(size): ret = bytearray() c = size & 0x7f size >>= 7 while size: ret.append(c | 0x80) c = size & 0x7f size >>= 7 ret.append(c) return ret # The length of delta compression copy operations in version 2 packs is limited # to 64K. To copy more, we use several copy operations. Version 3 packs allow # 24-bit lengths in copy operations, but we always make version 2 packs. _MAX_COPY_LEN = 0xffff def _encode_copy_operation(start, length): scratch = [] op = 0x80 for i in range(4): if start & 0xff << i*8: scratch.append((start >> i*8) & 0xff) op |= 1 << i for i in range(2): if length & 0xff << i*8: scratch.append((length >> i*8) & 0xff) op |= 1 << (4+i) return bytearray([op] + scratch) def create_delta(base_buf, target_buf): """Use python difflib to work out how to transform base_buf to target_buf. :param base_buf: Base buffer :param target_buf: Target buffer """ assert isinstance(base_buf, bytes) assert isinstance(target_buf, bytes) out_buf = bytearray() # write delta header out_buf += _delta_encode_size(len(base_buf)) out_buf += _delta_encode_size(len(target_buf)) # write out delta opcodes seq = difflib.SequenceMatcher(a=base_buf, b=target_buf) for opcode, i1, i2, j1, j2 in seq.get_opcodes(): # Git patch opcodes don't care about deletes! # if opcode == 'replace' or opcode == 'delete': # pass if opcode == 'equal': # If they are equal, unpacker will use data from base_buf # Write out an opcode that says what range to use copy_start = i1 copy_len = i2 - i1 while copy_len > 0: to_copy = min(copy_len, _MAX_COPY_LEN) out_buf += _encode_copy_operation(copy_start, to_copy) copy_start += to_copy copy_len -= to_copy if opcode == 'replace' or opcode == 'insert': # If we are replacing a range or adding one, then we just # output it to the stream (prefixed by its size) s = j2 - j1 o = j1 while s > 127: out_buf.append(127) out_buf += bytearray(target_buf[o:o+127]) s -= 127 o += 127 out_buf.append(s) out_buf += bytearray(target_buf[o:o+s]) return bytes(out_buf) def apply_delta(src_buf, delta): """Based on the similar function in git's patch-delta.c. :param src_buf: Source buffer :param delta: Delta instructions """ if not isinstance(src_buf, bytes): src_buf = b''.join(src_buf) if not isinstance(delta, bytes): delta = b''.join(delta) out = [] index = 0 delta_length = len(delta) def get_delta_header_size(delta, index): size = 0 i = 0 while delta: cmd = ord(delta[index:index+1]) index += 1 size |= (cmd & ~0x80) << i i += 7 if not cmd & 0x80: break return size, index src_size, index = get_delta_header_size(delta, index) dest_size, index = get_delta_header_size(delta, index) assert src_size == len(src_buf), '%d vs %d' % (src_size, len(src_buf)) while index < delta_length: cmd = ord(delta[index:index+1]) index += 1 if cmd & 0x80: cp_off = 0 for i in range(4): if cmd & (1 << i): x = ord(delta[index:index+1]) index += 1 cp_off |= x << (i * 8) cp_size = 0 # Version 3 packs can contain copy sizes larger than 64K. for i in range(3): if cmd & (1 << (4+i)): x = ord(delta[index:index+1]) index += 1 cp_size |= x << (i * 8) if cp_size == 0: cp_size = 0x10000 if (cp_off + cp_size < cp_size or cp_off + cp_size > src_size or cp_size > dest_size): break out.append(src_buf[cp_off:cp_off+cp_size]) elif cmd != 0: out.append(delta[index:index+cmd]) index += cmd else: raise ApplyDeltaError('Invalid opcode 0') if index != delta_length: raise ApplyDeltaError('delta not empty: %r' % delta[index:]) if dest_size != chunks_length(out): raise ApplyDeltaError('dest size incorrect') return out def write_pack_index_v2(f, entries, pack_checksum): """Write a new pack index file. :param f: File-like object to write to :param entries: List of tuples with object name (sha), offset_in_pack, and crc32_checksum. :param pack_checksum: Checksum of the pack file. :return: The SHA of the index file written """ f = SHA1Writer(f) f.write(b'\377tOc') # Magic! f.write(struct.pack('>L', 2)) fan_out_table = defaultdict(lambda: 0) for (name, offset, entry_checksum) in entries: fan_out_table[ord(name[:1])] += 1 # Fan-out table largetable = [] for i in range(0x100): f.write(struct.pack(b'>L', fan_out_table[i])) fan_out_table[i+1] += fan_out_table[i] for (name, offset, entry_checksum) in entries: f.write(name) for (name, offset, entry_checksum) in entries: f.write(struct.pack(b'>L', entry_checksum)) for (name, offset, entry_checksum) in entries: if offset < 2**31: f.write(struct.pack(b'>L', offset)) else: f.write(struct.pack(b'>L', 2**31 + len(largetable))) largetable.append(offset) for offset in largetable: f.write(struct.pack(b'>Q', offset)) assert len(pack_checksum) == 20 f.write(pack_checksum) return f.write_sha() write_pack_index = write_pack_index_v2 class Pack(object): """A Git pack object.""" def __init__(self, basename, resolve_ext_ref=None): self._basename = basename self._data = None self._idx = None self._idx_path = self._basename + '.idx' self._data_path = self._basename + '.pack' self._data_load = lambda: PackData(self._data_path) self._idx_load = lambda: load_pack_index(self._idx_path) self.resolve_ext_ref = resolve_ext_ref @classmethod def from_lazy_objects(self, data_fn, idx_fn): """Create a new pack object from callables to load pack data and index objects.""" ret = Pack('') ret._data_load = data_fn ret._idx_load = idx_fn return ret @classmethod def from_objects(self, data, idx): """Create a new pack object from pack data and index objects.""" ret = Pack('') ret._data_load = lambda: data ret._idx_load = lambda: idx return ret def name(self): """The SHA over the SHAs of the objects in this pack.""" return self.index.objects_sha1() @property def data(self): """The pack data object being used.""" if self._data is None: self._data = self._data_load() self._data.pack = self self.check_length_and_checksum() return self._data @property def index(self): """The index being used. :note: This may be an in-memory index """ if self._idx is None: self._idx = self._idx_load() return self._idx def close(self): if self._data is not None: self._data.close() if self._idx is not None: self._idx.close() def __enter__(self): return self def __exit__(self, exc_type, exc_val, exc_tb): self.close() def __eq__(self, other): return isinstance(self, type(other)) and self.index == other.index def __len__(self): """Number of entries in this pack.""" return len(self.index) def __repr__(self): return '%s(%r)' % (self.__class__.__name__, self._basename) def __iter__(self): """Iterate over all the sha1s of the objects in this pack.""" return iter(self.index) def check_length_and_checksum(self): """Sanity check the length and checksum of the pack index and data.""" assert len(self.index) == len(self.data) idx_stored_checksum = self.index.get_pack_checksum() data_stored_checksum = self.data.get_stored_checksum() if idx_stored_checksum != data_stored_checksum: raise ChecksumMismatch(sha_to_hex(idx_stored_checksum), sha_to_hex(data_stored_checksum)) def check(self): """Check the integrity of this pack. :raise ChecksumMismatch: if a checksum for the index or data is wrong """ self.index.check() self.data.check() for obj in self.iterobjects(): obj.check() # TODO: object connectivity checks def get_stored_checksum(self): return self.data.get_stored_checksum() def __contains__(self, sha1): """Check whether this pack contains a particular SHA1.""" try: self.index.object_index(sha1) return True except KeyError: return False + def get_raw_unresolved(self, sha1): + """Get raw unresolved data for a SHA. + + :param sha1: SHA to return data for + :return: Tuple with pack object type, delta base (if applicable), + list of data chunks + """ + offset = self.index.object_index(sha1) + (obj_type, delta_base, chunks) = self.data.get_compressed_data_at( + offset) + if obj_type == OFS_DELTA: + delta_base = sha_to_hex( + self.index.object_sha1(offset - delta_base)) + obj_type = REF_DELTA + return (obj_type, delta_base, chunks) + def get_raw(self, sha1): offset = self.index.object_index(sha1) obj_type, obj = self.data.get_object_at(offset) type_num, chunks = self.data.resolve_object(offset, obj_type, obj) return type_num, b''.join(chunks) def __getitem__(self, sha1): """Retrieve the specified SHA1.""" type, uncomp = self.get_raw(sha1) return ShaFile.from_raw_string(type, uncomp, sha=sha1) def iterobjects(self): """Iterate over the objects in this pack.""" return iter(PackInflater.for_pack_data( self.data, resolve_ext_ref=self.resolve_ext_ref)) def pack_tuples(self): """Provide an iterable for use with write_pack_objects. :return: Object that can iterate over (object, path) tuples and provides __len__ """ class PackTupleIterable(object): def __init__(self, pack): self.pack = pack def __len__(self): return len(self.pack) def __iter__(self): return ((o, None) for o in self.pack.iterobjects()) return PackTupleIterable(self) def keep(self, msg=None): """Add a .keep file for the pack, preventing git from garbage collecting it. :param msg: A message written inside the .keep file; can be used later to determine whether or not a .keep file is obsolete. :return: The path of the .keep file, as a string. """ keepfile_name = '%s.keep' % self._basename with GitFile(keepfile_name, 'wb') as keepfile: if msg: keepfile.write(msg) keepfile.write(b'\n') return keepfile_name try: from dulwich._pack import apply_delta, bisect_find_sha # noqa: F811 except ImportError: pass diff --git a/dulwich/patch.py b/dulwich/patch.py index 24b06154..7ba5f87e 100644 --- a/dulwich/patch.py +++ b/dulwich/patch.py @@ -1,349 +1,350 @@ # patch.py -- For dealing with packed-style patches. # Copyright (C) 2009-2013 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. # """Classes for dealing with git am-style patches. These patches are basically unified diffs with some extra metadata tacked on. """ from difflib import SequenceMatcher import email.parser import time from dulwich.objects import ( Blob, Commit, S_ISGITLINK, ) FIRST_FEW_BYTES = 8000 def write_commit_patch(f, commit, contents, progress, version=None, encoding=None): """Write a individual file patch. :param commit: Commit object :param progress: Tuple with current patch number and total. :return: tuple with filename and contents """ encoding = encoding or getattr(f, "encoding", "ascii") if isinstance(contents, str): contents = contents.encode(encoding) (num, total) = progress f.write(b"From " + commit.id + b" " + time.ctime(commit.commit_time).encode(encoding) + b"\n") f.write(b"From: " + commit.author + b"\n") f.write(b"Date: " + time.strftime("%a, %d %b %Y %H:%M:%S %Z").encode(encoding) + b"\n") f.write(("Subject: [PATCH %d/%d] " % (num, total)).encode(encoding) + commit.message + b"\n") f.write(b"\n") f.write(b"---\n") try: import subprocess p = subprocess.Popen(["diffstat"], stdout=subprocess.PIPE, stdin=subprocess.PIPE) except (ImportError, OSError): pass # diffstat not available? else: (diffstat, _) = p.communicate(contents) f.write(diffstat) f.write(b"\n") f.write(contents) f.write(b"-- \n") if version is None: from dulwich import __version__ as dulwich_version f.write(b"Dulwich %d.%d.%d\n" % dulwich_version) else: f.write(version.encode(encoding) + b"\n") def get_summary(commit): """Determine the summary line for use in a filename. :param commit: Commit :return: Summary string """ return commit.message.splitlines()[0].replace(" ", "-") # Unified Diff def _format_range_unified(start, stop): 'Convert range to the "ed" format' # Per the diff spec at http://www.unix.org/single_unix_specification/ beginning = start + 1 # lines start numbering with one length = stop - start if length == 1: return '{}'.format(beginning) if not length: beginning -= 1 # empty ranges begin at line just before the range return '{},{}'.format(beginning, length) def unified_diff(a, b, fromfile='', tofile='', fromfiledate='', tofiledate='', n=3, lineterm='\n'): """difflib.unified_diff that can detect "No newline at end of file" as original "git diff" does. Based on the same function in Python2.7 difflib.py """ started = False for group in SequenceMatcher(None, a, b).get_grouped_opcodes(n): if not started: started = True fromdate = '\t{}'.format(fromfiledate) if fromfiledate else '' todate = '\t{}'.format(tofiledate) if tofiledate else '' yield '--- {}{}{}'.format( fromfile.decode("ascii"), fromdate, lineterm ).encode('ascii') yield '+++ {}{}{}'.format( tofile.decode("ascii"), todate, lineterm ).encode('ascii') first, last = group[0], group[-1] file1_range = _format_range_unified(first[1], last[2]) file2_range = _format_range_unified(first[3], last[4]) yield '@@ -{} +{} @@{}'.format( file1_range, file2_range, lineterm ).encode('ascii') for tag, i1, i2, j1, j2 in group: if tag == 'equal': for line in a[i1:i2]: yield b' ' + line continue if tag in ('replace', 'delete'): for line in a[i1:i2]: if not line[-1:] == b'\n': line += b'\n\\ No newline at end of file\n' yield b'-' + line if tag in ('replace', 'insert'): for line in b[j1:j2]: if not line[-1:] == b'\n': line += b'\n\\ No newline at end of file\n' yield b'+' + line def is_binary(content): """See if the first few bytes contain any null characters. :param content: Bytestring to check for binary content """ return b'\0' in content[:FIRST_FEW_BYTES] def shortid(hexsha): if hexsha is None: return b"0" * 7 else: return hexsha[:7] def patch_filename(p, root): if p is None: return b"/dev/null" else: return root + b"/" + p def write_object_diff(f, store, old_file, new_file, diff_binary=False): """Write the diff for an object. :param f: File-like object to write to :param store: Store to retrieve objects from, if necessary :param old_file: (path, mode, hexsha) tuple :param new_file: (path, mode, hexsha) tuple :param diff_binary: Whether to diff files even if they are considered binary files by is_binary(). :note: the tuple elements should be None for nonexistant files """ (old_path, old_mode, old_id) = old_file (new_path, new_mode, new_id) = new_file old_path = patch_filename(old_path, b"a") new_path = patch_filename(new_path, b"b") def content(mode, hexsha): if hexsha is None: return Blob.from_string(b'') elif S_ISGITLINK(mode): return Blob.from_string(b"Submodule commit " + hexsha + b"\n") else: return store[hexsha] def lines(content): if not content: return [] else: return content.splitlines() f.writelines(gen_diff_header( (old_path, new_path), (old_mode, new_mode), (old_id, new_id))) old_content = content(old_mode, old_id) new_content = content(new_mode, new_id) if not diff_binary and ( is_binary(old_content.data) or is_binary(new_content.data)): f.write(b"Binary files " + old_path + b" and " + new_path + b" differ\n") else: f.writelines(unified_diff(lines(old_content), lines(new_content), old_path, new_path)) # TODO(jelmer): Support writing unicode, rather than bytes. def gen_diff_header(paths, modes, shas): """Write a blob diff header. :param paths: Tuple with old and new path :param modes: Tuple with old and new modes :param shas: Tuple with old and new shas """ (old_path, new_path) = paths (old_mode, new_mode) = modes (old_sha, new_sha) = shas yield b"diff --git " + old_path + b" " + new_path + b"\n" if old_mode != new_mode: if new_mode is not None: if old_mode is not None: yield ("old mode %o\n" % old_mode).encode('ascii') yield ("new mode %o\n" % new_mode).encode('ascii') else: yield ("deleted mode %o\n" % old_mode).encode('ascii') yield b"index " + shortid(old_sha) + b".." + shortid(new_sha) if new_mode is not None: yield (" %o" % new_mode).encode('ascii') yield b"\n" # TODO(jelmer): Support writing unicode, rather than bytes. def write_blob_diff(f, old_file, new_file): """Write blob diff. :param f: File-like object to write to :param old_file: (path, mode, hexsha) tuple (None if nonexisting) :param new_file: (path, mode, hexsha) tuple (None if nonexisting) :note: The use of write_object_diff is recommended over this function. """ (old_path, old_mode, old_blob) = old_file (new_path, new_mode, new_blob) = new_file old_path = patch_filename(old_path, b"a") new_path = patch_filename(new_path, b"b") def lines(blob): if blob is not None: return blob.splitlines() else: return [] f.writelines(gen_diff_header( (old_path, new_path), (old_mode, new_mode), (getattr(old_blob, "id", None), getattr(new_blob, "id", None)))) old_contents = lines(old_blob) new_contents = lines(new_blob) f.writelines(unified_diff(old_contents, new_contents, old_path, new_path)) def write_tree_diff(f, store, old_tree, new_tree, diff_binary=False): """Write tree diff. :param f: File-like object to write to. :param old_tree: Old tree id :param new_tree: New tree id :param diff_binary: Whether to diff files even if they are considered binary files by is_binary(). """ changes = store.tree_changes(old_tree, new_tree) for (oldpath, newpath), (oldmode, newmode), (oldsha, newsha) in changes: write_object_diff(f, store, (oldpath, oldmode, oldsha), (newpath, newmode, newsha), diff_binary=diff_binary) def git_am_patch_split(f, encoding=None): """Parse a git-am-style patch and split it up into bits. :param f: File-like object to parse :param encoding: Encoding to use when creating Git objects :return: Tuple with commit object, diff contents and git version """ encoding = encoding or getattr(f, "encoding", "ascii") + encoding = encoding or "ascii" contents = f.read() if (isinstance(contents, bytes) and getattr(email.parser, "BytesParser", None)): parser = email.parser.BytesParser() msg = parser.parsebytes(contents) else: parser = email.parser.Parser() msg = parser.parsestr(contents) return parse_patch_message(msg, encoding) def parse_patch_message(msg, encoding=None): """Extract a Commit object and patch from an e-mail message. :param msg: An email message (email.message.Message) :param encoding: Encoding to use to encode Git commits :return: Tuple with commit object, diff contents and git version """ c = Commit() c.author = msg["from"].encode(encoding) c.committer = msg["from"].encode(encoding) try: patch_tag_start = msg["subject"].index("[PATCH") except ValueError: subject = msg["subject"] else: close = msg["subject"].index("] ", patch_tag_start) subject = msg["subject"][close+2:] c.message = (subject.replace("\n", "") + "\n").encode(encoding) first = True body = msg.get_payload(decode=True) lines = body.splitlines(True) line_iter = iter(lines) - for l in line_iter: - if l == b"---\n": + for line in line_iter: + if line == b"---\n": break if first: - if l.startswith(b"From: "): - c.author = l[len(b"From: "):].rstrip() + if line.startswith(b"From: "): + c.author = line[len(b"From: "):].rstrip() else: - c.message += b"\n" + l + c.message += b"\n" + line first = False else: - c.message += l + c.message += line diff = b"" - for l in line_iter: - if l == b"-- \n": + for line in line_iter: + if line == b"-- \n": break - diff += l + diff += line try: version = next(line_iter).rstrip(b"\n") except StopIteration: version = None return c, diff, version diff --git a/dulwich/porcelain.py b/dulwich/porcelain.py index 31682be2..0c055d46 100644 --- a/dulwich/porcelain.py +++ b/dulwich/porcelain.py @@ -1,1181 +1,1222 @@ # 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 * diff-tree * fetch * init * 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 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 +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) 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 e.g. an index. :param repo: Repository :param path: A path :return: A path formatted for use in e.g. an index """ os.path.relpath(path, repopath) if os.path.sep != '/': path = path.replace(os.path.sep, '/') return path.encode(sys.getfilesystemencoding()) 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 = b'refs/heads/' + ref_name + 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): +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) + 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"): + origin=b"origin", **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 :return: The new repository """ 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") config = StackedConfig.default() - client, host_path = get_transport_and_path(source, config=config) + client, host_path = get_transport_and_path(source, config=config, **kwargs) if target is None: target = host_path.split("/")[-1] if not os.path.exists(target): os.mkdir(target) if bare: r = Repo.init_bare(target) else: r = Repo.init(target) try: - remote_refs = client.fetch( + fetch_result = client.fetch( host_path, r, determine_wants=r.object_store.determine_wants_all, progress=errstream.write) + ref_message = b"clone: from " + source.encode('utf-8') r.refs.import_refs( b'refs/remotes/' + origin, - {n[len(b'refs/heads/'):]: v for (n, v) in remote_refs.items() - if n.startswith(b'refs/heads/')}) + {n[len(b'refs/heads/'):]: v for (n, v) in fetch_result.refs.items() + if n.startswith(b'refs/heads/')}, + message=ref_message) r.refs.import_refs( b'refs/tags', - {n[len(b'refs/tags/'):]: v for (n, v) in remote_refs.items() + {n[len(b'refs/tags/'):]: v for (n, v) in fetch_result.refs.items() if n.startswith(b'refs/tags/') and - not n.endswith(ANNOTATED_TAG_SUFFIX)}) - if b"HEAD" in remote_refs and not bare: - # TODO(jelmer): Support symref capability, - # https://github.com/jelmer/dulwich/issues/485 - r[b"HEAD"] = remote_refs[b"HEAD"] + not n.endswith(ANNOTATED_TAG_SUFFIX)}, + message=ref_message) 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() - if checkout and b"HEAD" in r.refs: - errstream.write(b'Checking out HEAD\n') - r.reset_index() - except: + # TODO(jelmer): Support symref capability, + # https://github.com/jelmer/dulwich/issues/485 + try: + head = r[fetch_result.refs[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('../'): + 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): """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 """ 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() 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 r.object_store.add_object(tag_obj) tag_id = tag_obj.id else: tag_id = object.id - r.refs[b'refs/tags/' + tag] = tag_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[b"refs/tags/" + name] + 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): + 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()) + 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, r.object_store.generate_pack_contents, + 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): + 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()) - remote_refs = client.fetch( + 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] = remote_refs[lh] + r.refs[rh] = fetch_result.refs[lh] if selected_refs: - r[b'HEAD'] = remote_refs[selected_refs[0][1]] + 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 ignoed 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, bytes): - names = [name] - elif isinstance(name, list): + if isinstance(name, list): names = name else: - raise TypeError("Unexpected branch name type %r" % name) + names = [name] for name in names: - del r.refs[b"refs/heads/" + name] + 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 = b"refs/heads/" + name - if refname in r.refs and not force: - raise KeyError("Branch with name %s already exists." % name) - r.refs[refname] = object.id + 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, outstream=sys.stdout, - errstream=default_bytes_err_stream): +def fetch(repo, remote_location, remote_name=b'origin', outstream=sys.stdout, + errstream=default_bytes_err_stream, **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) :return: Dictionary with refs on the remote """ with open_repo_closing(repo) as r: client, path = get_transport_and_path( - remote_location, config=r.get_config_stack()) - remote_refs = client.fetch(path, r, progress=errstream.write) - return remote_refs + remote_location, config=r.get_config_stack(), **kwargs) + fetch_result = client.fetch(path, r, progress=errstream.write) + ref_name = b'refs/remotes/' + remote_name + r.refs.import_refs(ref_name, strip_peeled_refs(fetch_result.refs)) + return fetch_result.refs -def ls_remote(remote): +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 """ - config = StackedConfig.default() - client, host_path = get_transport_and_path(remote, config=config) + 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): 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 os.path.isabs(path): path = os.path.relpath(path, r.path) if not no_index and path_to_tree_path(r.path, path) in index: continue 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 = b"refs/heads/" + new_branch.encode(DEFAULT_ENCODING) + 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) diff --git a/dulwich/reflog.py b/dulwich/reflog.py index 488a23ae..aec32e60 100644 --- a/dulwich/reflog.py +++ b/dulwich/reflog.py @@ -1,76 +1,76 @@ # reflog.py -- Parsing and writing reflog files # Copyright (C) 2015 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. # """Utilities for reading and generating reflogs. """ import collections from dulwich.objects import ( format_timezone, parse_timezone, ZERO_SHA, ) Entry = collections.namedtuple( 'Entry', ['old_sha', 'new_sha', 'committer', 'timestamp', 'timezone', 'message']) def format_reflog_line(old_sha, new_sha, committer, timestamp, timezone, message): """Generate a single reflog line. :param old_sha: Old Commit SHA :param new_sha: New Commit SHA :param committer: Committer name and e-mail :param timestamp: Timestamp :param timezone: Timezone :param message: Message """ if old_sha is None: old_sha = ZERO_SHA return (old_sha + b' ' + new_sha + b' ' + committer + b' ' + - str(timestamp).encode('ascii') + b' ' + + str(int(timestamp)).encode('ascii') + b' ' + format_timezone(timezone) + b'\t' + message) def parse_reflog_line(line): """Parse a reflog line. :param line: Line to parse :return: Tuple of (old_sha, new_sha, committer, timestamp, timezone, message) """ (begin, message) = line.split(b'\t', 1) (old_sha, new_sha, rest) = begin.split(b' ', 2) (committer, timestamp_str, timezone_str) = rest.rsplit(b' ', 2) return Entry(old_sha, new_sha, committer, int(timestamp_str), parse_timezone(timezone_str)[0], message) def read_reflog(f): """Read reflog. :param f: File-like object :returns: Iterator over Entry objects """ for l in f: yield parse_reflog_line(l) diff --git a/dulwich/refs.py b/dulwich/refs.py index 0a19a16c..4389031b 100644 --- a/dulwich/refs.py +++ b/dulwich/refs.py @@ -1,821 +1,890 @@ # 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/' 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 set_symbolic_ref(self, name, other): + 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): + def import_refs(self, base, other, committer=None, timestamp=None, + timezone=None, message=None): for name, value in other.items(): - self[b'/'.join((base, name))] = value + 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): + 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.""" + """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): + 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): + 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): + 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): + 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): + 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): + 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: - del self._refs[name] + 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): + def __init__(self, path, worktree_path=None, logger=None): + super(DiskRefsContainer, self).__init__(logger=logger) self.path = path self.worktree_path = worktree_path or 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, dirs, files in os.walk(path): dir = root[len(path):].strip(os.path.sep).replace(os.path.sep, "/") for filename in files: refname = (("%s/%s" % (dir, filename)) .strip("/").encode(sys.getfilesystemencoding())) # 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'') for root, dirs, files in os.walk(self.refpath(b'refs')): dir = root[len(path):].strip(os.path.sep).replace(os.path.sep, "/") for filename in files: refname = ( "%s/%s" % (dir, filename)).encode( sys.getfilesystemencoding()) 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 (getattr(self.path, "encode", None) and getattr(name, "decode", None)): name = name.decode(sys.getfilesystemencoding()) if os.path.sep != "/": name = name.replace("/", os.path.sep) # TODO: as the 'HEAD' reference is working tree specific, it # should actually not be a part of RefsContainer if name == '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, '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): return None raise def _remove_packed_ref(self, name): if self._packed_refs is None: return filename = os.path.join(self.path, '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): + 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) try: f = GitFile(filename, 'wb') try: f.write(SYMREF + other + b'\n') except (IOError, OSError): f.abort() raise + else: + sha = self.follow(name)[-1] + self._log(name, sha, sha, committer=committer, + timestamp=timestamp, timezone=timezone, + message=message) finally: f.close() - def set_if_equals(self, name, old_ref, new_ref): + 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) 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): + 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): + 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 # may only be packed try: os.remove(filename) except OSError as e: if e.errno != errno.ENOENT: 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() 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 l in f: - if l[0] == b'#': + for line in f: + if line[0] == b'#': continue - l = l.rstrip(b'\r\n') - if l.startswith(b'^'): + line = line.rstrip(b'\r\n') + if line.startswith(b'^'): if not last: raise PackedRefsException("unexpected peeled ref line") - if not valid_hexsha(l[1:]): - raise PackedRefsException("Invalid hex sha %r" % l[1:]) + 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, l[1:]) + yield (sha, name, line[1:]) else: if last: sha, name = _split_ref_line(last) yield (sha, name, None) - last = l + 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(b'refs/heads/') + + +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 2ca70f96..b3cc2cad 100644 --- a/dulwich/repo.py +++ b/dulwich/repo.py @@ -1,1166 +1,1247 @@ # 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.hooks import ( PreCommitShellHook, PostCommitShellHook, CommitMsgShellHook, ) from dulwich.refs import ( # noqa: F401 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(b"core", b"repositoryformatversion", b"0") + cf.set("core", "repositoryformatversion", "0") if self._determine_file_mode(): - cf.set(b"core", b"filemode", True) + cf.set("core", "filemode", True) else: - cf.set(b"core", b"filemode", False) + cf.set("core", "filemode", False) - cf.set(b"core", b"bare", bare) - cf.set(b"core", b"logallrefupdates", True) + 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 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): """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 :return: The local refs """ if determine_wants is None: determine_wants = target.object_store.determine_wants_all target.object_store.add_objects( self.fetch_objects(determine_wants, target.get_graph_walker(), progress)) return self.get_refs() def fetch_objects(self, determine_wants, graph_walker, progress, get_tagged=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. :return: iterator over objects, with __len__ implemented """ wants = determine_wants(self.get_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) 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_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): """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() - return (config.get((b"user", ), b"name") + b" <" + - config.get((b"user", ), b"email") + b">") + 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 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 if merge_heads is None: # FIXME: Read merge heads from .git/MERGE_HEADS merge_heads = [] if committer is None: - # FIXME: Support GIT_COMMITTER_NAME/GIT_COMMITTER_EMAIL environment - # variables committer = self._get_user_identity() + 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 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) + 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) + 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,)) 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) + 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() + 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 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 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"): """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: 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')) + 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')) + 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]) + target.refs.add_if_new( + DEFAULT_REF, self.refs[DEFAULT_REF], + message=ref_message) except KeyError: pass target_config = target.get_config() - encoded_path = self.path - if not isinstance(encoded_path, bytes): - encoded_path = encoded_path.encode(sys.getfilesystemencoding()) - target_config.set((b'remote', b'origin'), b'url', encoded_path) - target_config.set((b'remote', b'origin'), b'fetch', - b'+refs/heads/*:refs/remotes/origin/*') + 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]) + target.refs.set_symbolic_ref(b'HEAD', head_chain[-1], + message=ref_message) target[b'HEAD'] = head_sha if not bare: # 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( - 'core', 'filemode', os.name != "nt") - if config.get_boolean('core', 'core.protectNTFS', os.name == "nt"): + 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 - BaseRepo.__init__(self, MemoryObjectStore(), DictRefsContainer({})) + 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 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[refname] = sha + ret.refs.add_if_new(refname, sha) ret._init_files(bare=True) return ret diff --git a/dulwich/tests/compat/test_client.py b/dulwich/tests/compat/test_client.py index 4f6579e8..d60be1a3 100644 --- a/dulwich/tests/compat/test_client.py +++ b/dulwich/tests/compat/test_client.py @@ -1,544 +1,545 @@ # 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_contents) + 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_contents) + 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_contents + 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_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): - return [] + 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): + 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) 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 # 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/test_archive.py b/dulwich/tests/test_archive.py index 3735d028..8f67c4aa 100644 --- a/dulwich/tests/test_archive.py +++ b/dulwich/tests/test_archive.py @@ -1,65 +1,96 @@ # test_archive.py -- tests for archive # Copyright (C) 2015 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 archive support.""" from io import BytesIO import tarfile +import struct +from unittest import skipUnless from dulwich.archive import tar_stream from dulwich.object_store import ( MemoryObjectStore, ) from dulwich.objects import ( Blob, Tree, ) from dulwich.tests import ( TestCase, ) from dulwich.tests.utils import ( build_commit_graph, ) +try: + from mock import patch +except ImportError: + patch = None + class ArchiveTests(TestCase): def test_empty(self): store = MemoryObjectStore() c1, c2, c3 = build_commit_graph(store, [[1], [2, 1], [3, 1, 2]]) tree = store[c3.tree] stream = b''.join(tar_stream(store, tree, 10)) out = BytesIO(stream) tf = tarfile.TarFile(fileobj=out) self.addCleanup(tf.close) self.assertEqual([], tf.getnames()) - def test_simple(self): + def _get_example_tar_stream(self, *tar_stream_args, **tar_stream_kwargs): store = MemoryObjectStore() b1 = Blob.from_string(b"somedata") store.add_object(b1) t1 = Tree() t1.add(b"somename", 0o100644, b1.id) store.add_object(t1) - stream = b''.join(tar_stream(store, t1, 10)) - out = BytesIO(stream) - tf = tarfile.TarFile(fileobj=out) + stream = b''.join( + tar_stream(store, t1, *tar_stream_args, **tar_stream_kwargs)) + return BytesIO(stream) + + def test_simple(self): + stream = self._get_example_tar_stream(mtime=0) + tf = tarfile.TarFile(fileobj=stream) self.addCleanup(tf.close) self.assertEqual(["somename"], tf.getnames()) + + def test_gzip_mtime(self): + stream = self._get_example_tar_stream(mtime=1234, format='gz') + expected_mtime = struct.pack(' # # 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 - -try: - import urllib2 -except ImportError: - import urllib.request as urllib2 +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 certifi +import urllib3 + import dulwich from dulwich import ( client, ) from dulwich.client import ( LocalGitClient, TraditionalGitClient, TCPGitClient, SSHGitClient, HttpGitClient, ReportStatusParser, SendPackError, StrangeHostname, SubprocessSSHVendor, + PuttySSHVendor, UpdateRefsError, - default_urllib2_opener, + default_urllib3_manager, get_transport_and_path, get_transport_and_path_from_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 +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', 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.assertIs(heads, None) + self.assertEqual(heads, {}) return [] ret = self.client.fetch_pack(b'/', check_heads, None, None) - self.assertIs(None, ret.refs) + 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.assertEquals({}, heads) + self.assertEqual({}, heads) return [] ret = self.client.fetch_pack(b'bla', check_heads, None, None, None) - self.assertIs(None, ret.refs) + 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_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): return {b'refs/foo/bar': commit.id, } - def generate_pack_contents(have, want): - return [(commit, None), (tree, ''), ] + 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_contents) + determine_wants, 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): return { b'refs/heads/master': b'310ca9477129b8586fa2afc779c1f57cf64bba6c' } - def generate_pack_contents(have, want): - return {} + def generate_pack_data(have, want, ofs_delta=False): + return 0, [] - self.client.send_pack(b'/', determine_wants, generate_pack_contents) + self.client.send_pack(b'/', determine_wants, 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): return {b'refs/heads/master': b'0' * 40} - def generate_pack_contents(have, want): - return {} + def generate_pack_data(have, want, ofs_delta=False): + return 0, [] - self.client.send_pack(b'/', determine_wants, generate_pack_contents) + self.client.send_pack(b'/', determine_wants, 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): return {b'refs/heads/master': b'0' * 40} - def generate_pack_contents(have, want): - return {} + def generate_pack_data(have, want, ofs_delta=False): + return 0, [] - self.client.send_pack(b'/', determine_wants, generate_pack_contents) + self.client.send_pack(b'/', determine_wants, 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): return { b'refs/heads/blah12': b'310ca9477129b8586fa2afc779c1f57cf64bba6c', b'refs/heads/master': b'310ca9477129b8586fa2afc779c1f57cf64bba6c' } - def generate_pack_contents(have, want): - return {} + 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_contents) + self.client.send_pack('/', determine_wants, 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): return { b'refs/heads/blah12': commit.id, b'refs/heads/master': b'310ca9477129b8586fa2afc779c1f57cf64bba6c' } - def generate_pack_contents(have, want): - return [(commit, None), (tree, b''), ] + def generate_pack_data(have, want, ofs_delta=False): + return pack_objects_to_data([(commit, None), (tree, b''), ]) f = BytesIO() - write_pack_objects(f, generate_pack_contents(None, None)) - self.client.send_pack(b'/', determine_wants, generate_pack_contents) + write_pack_data(f, *generate_pack_data(None, None)) + self.client.send_pack(b'/', determine_wants, 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): return {b'refs/heads/master': b'0' * 40} - def generate_pack_contents(have, want): - return {} + def generate_pack_data(have, want, ofs_delta=False): + return 0, [] self.assertRaises(UpdateRefsError, self.client.send_pack, b"/", - determine_wants, generate_pack_contents) + determine_wants, 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_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('/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): + 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)) + 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_contents) + 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) - [pw_handler] = [ - h for h in c.opener.handlers - if getattr(h, 'passwd', None) is not None] - self.assertEqual( - ('user', 'passwd'), - pw_handler.passwd.find_user_password( - None, 'https://github.com/jelmer/dulwich')) + + 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) - pw_handler = [ - h for h in c.opener.handlers - if getattr(h, 'passwd', None) is not None] - self.assertEqual(0, len(pw_handler)) + 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) - [pw_handler] = [ - h for h in c.opener.handlers - if getattr(h, 'passwd', None) is not None] - self.assertEqual( - (original_username, original_password), - pw_handler.passwd.find_user_password( - None, 'https://github.com/jelmer/dulwich')) + + 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 DefaultUrllib2OpenerTest(TestCase): +class DefaultUrllib3ManagerTest(TestCase): + + def assert_verify_ssl(self, manager, assertion=True): + pool_keywords = tuple(manager.connection_pool_kw.items()) + assert_method = self.assertIn if assertion else self.assertNotIn + assert_method(('cert_reqs', 'CERT_REQUIRED'), pool_keywords) + assert_method(('ca_certs', certifi.where()), pool_keywords) def test_no_config(self): - default_urllib2_opener(config=None) + manager = default_urllib3_manager(config=None) + self.assert_verify_ssl(manager) def test_config_no_proxy(self): - default_urllib2_opener(config=ConfigDict()) + manager = default_urllib3_manager(config=ConfigDict()) + self.assert_verify_ssl(manager) def test_config_proxy(self): config = ConfigDict() config.set(b'http', b'proxy', b'http://localhost:3128/') - opener = default_urllib2_opener(config=config) - self.assertIn(urllib2.ProxyHandler, - list(map(lambda x: x.__class__, opener.handlers))) + 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) + self.assert_verify_ssl(manager) + + def test_config_no_verify_ssl(self): + manager = default_urllib3_manager(config=None, verify_ssl=False) + self.assert_verify_ssl(manager, assertion=False) 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 PuttySSHVendorTests(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 = PuttySSHVendor() + self.assertRaises(StrangeHostname, vendor.run_command, '--weird-host', + 'git-clone-url') + + def test_run_command_password_and_privkey(self): + vendor = PuttySSHVendor() + self.assertRaises(NotImplementedError, vendor.run_command, + 'host', 'git-clone-url', + password='12345', key_filename='/tmp/id_rsa') + + def test_run_command_password(self): + if sys.platform == 'win32': + binary = ['putty.exe', '-ssh'] + else: + binary = ['putty', '-ssh'] + expected = binary + ['-pw', '12345', 'host', 'git-clone-url'] + + vendor = PuttySSHVendor() + + 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 Putty 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 = ['putty.exe', '-ssh'] + else: + binary = ['putty', '-ssh'] + expected = binary + [ + '-P', '2200', '-i', '/tmp/id_rsa', + 'user@host', 'git-clone-url'] + + vendor = PuttySSHVendor() + 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]) diff --git a/dulwich/tests/test_config.py b/dulwich/tests/test_config.py index 38ef34c4..a4b58f5c 100644 --- a/dulwich/tests/test_config.py +++ b/dulwich/tests/test_config.py @@ -1,325 +1,343 @@ # test_config.py -- Tests for reading and writing configuration files # Copyright (C) 2011 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 reading and writing configuration files.""" from io import BytesIO from dulwich.config import ( ConfigDict, ConfigFile, StackedConfig, _check_section_name, _check_variable_name, _format_string, _escape_value, _parse_string, parse_submodules, ) from dulwich.tests import ( TestCase, ) class ConfigFileTests(TestCase): def from_file(self, text): return ConfigFile.from_file(BytesIO(text)) def test_empty(self): ConfigFile() def test_eq(self): self.assertEqual(ConfigFile(), ConfigFile()) def test_default_config(self): cf = self.from_file(b"""[core] \trepositoryformatversion = 0 \tfilemode = true \tbare = false \tlogallrefupdates = true """) self.assertEqual(ConfigFile({(b"core", ): { b"repositoryformatversion": b"0", b"filemode": b"true", b"bare": b"false", b"logallrefupdates": b"true"}}), cf) def test_from_file_empty(self): cf = self.from_file(b"") self.assertEqual(ConfigFile(), cf) def test_empty_line_before_section(self): cf = self.from_file(b"\n[section]\n") self.assertEqual(ConfigFile({(b"section", ): {}}), cf) def test_comment_before_section(self): cf = self.from_file(b"# foo\n[section]\n") self.assertEqual(ConfigFile({(b"section", ): {}}), cf) def test_comment_after_section(self): cf = self.from_file(b"[section] # foo\n") self.assertEqual(ConfigFile({(b"section", ): {}}), cf) def test_comment_after_variable(self): cf = self.from_file(b"[section]\nbar= foo # a comment\n") self.assertEqual(ConfigFile({(b"section", ): {b"bar": b"foo"}}), cf) + def test_comment_character_within_value_string(self): + cf = self.from_file(b"[section]\nbar= \"foo#bar\"\n") + self.assertEqual( + ConfigFile({(b"section", ): {b"bar": b"foo#bar"}}), cf) + + def test_comment_character_within_section_string(self): + cf = self.from_file(b"[branch \"foo#bar\"] # a comment\nbar= foo\n") + self.assertEqual( + ConfigFile({(b"branch", b"foo#bar"): {b"bar": b"foo"}}), cf) + def test_from_file_section(self): cf = self.from_file(b"[core]\nfoo = bar\n") self.assertEqual(b"bar", cf.get((b"core", ), b"foo")) self.assertEqual(b"bar", cf.get((b"core", b"foo"), b"foo")) - def test_from_file_section_case_insensitive(self): + def test_from_file_section_case_insensitive_lower(self): cf = self.from_file(b"[cOre]\nfOo = bar\n") self.assertEqual(b"bar", cf.get((b"core", ), b"foo")) self.assertEqual(b"bar", cf.get((b"core", b"foo"), b"foo")) + def test_from_file_section_case_insensitive_mixed(self): + cf = self.from_file(b"[cOre]\nfOo = bar\n") + self.assertEqual(b"bar", cf.get((b"core", ), b"fOo")) + self.assertEqual(b"bar", cf.get((b"cOre", b"fOo"), b"fOo")) + def test_from_file_with_mixed_quoted(self): cf = self.from_file(b"[core]\nfoo = \"bar\"la\n") self.assertEqual(b"barla", cf.get((b"core", ), b"foo")) - def test_from_file_with_open_quoted(self): + def test_from_file_section_with_open_brackets(self): + self.assertRaises(ValueError, self.from_file, b"[core\nfoo = bar\n") + + def test_from_file_value_with_open_quoted(self): self.assertRaises(ValueError, self.from_file, b"[core]\nfoo = \"bar\n") def test_from_file_with_quotes(self): cf = self.from_file( b"[core]\n" b'foo = " bar"\n') self.assertEqual(b" bar", cf.get((b"core", ), b"foo")) def test_from_file_with_interrupted_line(self): cf = self.from_file( b"[core]\n" b'foo = bar\\\n' b' la\n') self.assertEqual(b"barla", cf.get((b"core", ), b"foo")) def test_from_file_with_boolean_setting(self): cf = self.from_file( b"[core]\n" b'foo\n') self.assertEqual(b"true", cf.get((b"core", ), b"foo")) def test_from_file_subsection(self): cf = self.from_file(b"[branch \"foo\"]\nfoo = bar\n") self.assertEqual(b"bar", cf.get((b"branch", b"foo"), b"foo")) def test_from_file_subsection_invalid(self): self.assertRaises( ValueError, self.from_file, b"[branch \"foo]\nfoo = bar\n") def test_from_file_subsection_not_quoted(self): cf = self.from_file(b"[branch.foo]\nfoo = bar\n") self.assertEqual(b"bar", cf.get((b"branch", b"foo"), b"foo")) def test_write_to_file_empty(self): c = ConfigFile() f = BytesIO() c.write_to_file(f) self.assertEqual(b"", f.getvalue()) def test_write_to_file_section(self): c = ConfigFile() c.set((b"core", ), b"foo", b"bar") f = BytesIO() c.write_to_file(f) self.assertEqual(b"[core]\n\tfoo = bar\n", f.getvalue()) def test_write_to_file_subsection(self): c = ConfigFile() c.set((b"branch", b"blie"), b"foo", b"bar") f = BytesIO() c.write_to_file(f) self.assertEqual(b"[branch \"blie\"]\n\tfoo = bar\n", f.getvalue()) def test_same_line(self): cf = self.from_file(b"[branch.foo] foo = bar\n") self.assertEqual(b"bar", cf.get((b"branch", b"foo"), b"foo")) def test_quoted(self): cf = self.from_file(b"""[gui] \tfontdiff = -family \\\"Ubuntu Mono\\\" -size 11 -overstrike 0 """) self.assertEqual(ConfigFile({(b'gui', ): { b'fontdiff': b'-family "Ubuntu Mono" -size 11 -overstrike 0', }}), cf) def test_quoted_multiline(self): cf = self.from_file(b"""[alias] who = \"!who() {\\ git log --no-merges --pretty=format:'%an - %ae' $@ | uniq -c | sort -rn;\\ };\\ who\" """) self.assertEqual(ConfigFile({(b'alias', ): { b'who': (b"!who() {git log --no-merges --pretty=format:'%an - " b"%ae' $@ | uniq -c | sort -rn;};who") }}), cf) def test_set_hash_gets_quoted(self): c = ConfigFile() c.set(b"xandikos", b"color", b"#665544") f = BytesIO() c.write_to_file(f) self.assertEqual(b"[xandikos]\n\tcolor = \"#665544\"\n", f.getvalue()) class ConfigDictTests(TestCase): def test_get_set(self): cd = ConfigDict() self.assertRaises(KeyError, cd.get, b"foo", b"core") cd.set((b"core", ), b"foo", b"bla") self.assertEqual(b"bla", cd.get((b"core", ), b"foo")) cd.set((b"core", ), b"foo", b"bloe") self.assertEqual(b"bloe", cd.get((b"core", ), b"foo")) def test_get_boolean(self): cd = ConfigDict() cd.set((b"core", ), b"foo", b"true") self.assertTrue(cd.get_boolean((b"core", ), b"foo")) cd.set((b"core", ), b"foo", b"false") self.assertFalse(cd.get_boolean((b"core", ), b"foo")) cd.set((b"core", ), b"foo", b"invalid") self.assertRaises(ValueError, cd.get_boolean, (b"core", ), b"foo") def test_dict(self): cd = ConfigDict() cd.set((b"core", ), b"foo", b"bla") cd.set((b"core2", ), b"foo", b"bloe") self.assertEqual([(b"core", ), (b"core2", )], list(cd.keys())) self.assertEqual(cd[(b"core", )], {b'foo': b'bla'}) cd[b'a'] = b'b' self.assertEqual(cd[b'a'], b'b') def test_iteritems(self): cd = ConfigDict() cd.set((b"core", ), b"foo", b"bla") cd.set((b"core2", ), b"foo", b"bloe") self.assertEqual( [(b'foo', b'bla')], list(cd.iteritems((b"core", )))) def test_iteritems_nonexistant(self): cd = ConfigDict() cd.set((b"core2", ), b"foo", b"bloe") self.assertEqual([], list(cd.iteritems((b"core", )))) def test_itersections(self): cd = ConfigDict() cd.set((b"core2", ), b"foo", b"bloe") self.assertEqual([(b"core2", )], list(cd.itersections())) class StackedConfigTests(TestCase): def test_default_backends(self): StackedConfig.default_backends() class EscapeValueTests(TestCase): def test_nothing(self): self.assertEqual(b"foo", _escape_value(b"foo")) def test_backslash(self): self.assertEqual(b"foo\\\\", _escape_value(b"foo\\")) def test_newline(self): self.assertEqual(b"foo\\n", _escape_value(b"foo\n")) class FormatStringTests(TestCase): def test_quoted(self): self.assertEqual(b'" foo"', _format_string(b" foo")) self.assertEqual(b'"\\tfoo"', _format_string(b"\tfoo")) def test_not_quoted(self): self.assertEqual(b'foo', _format_string(b"foo")) self.assertEqual(b'foo bar', _format_string(b"foo bar")) class ParseStringTests(TestCase): def test_quoted(self): self.assertEqual(b' foo', _parse_string(b'" foo"')) self.assertEqual(b'\tfoo', _parse_string(b'"\\tfoo"')) def test_not_quoted(self): self.assertEqual(b'foo', _parse_string(b"foo")) self.assertEqual(b'foo bar', _parse_string(b"foo bar")) def test_nothing(self): self.assertEqual(b"", _parse_string(b'')) def test_tab(self): self.assertEqual(b"\tbar\t", _parse_string(b"\\tbar\\t")) def test_newline(self): self.assertEqual(b"\nbar\t", _parse_string(b"\\nbar\\t\t")) def test_quote(self): self.assertEqual(b"\"foo\"", _parse_string(b"\\\"foo\\\"")) class CheckVariableNameTests(TestCase): def test_invalid(self): self.assertFalse(_check_variable_name(b"foo ")) self.assertFalse(_check_variable_name(b"bar,bar")) self.assertFalse(_check_variable_name(b"bar.bar")) def test_valid(self): self.assertTrue(_check_variable_name(b"FOO")) self.assertTrue(_check_variable_name(b"foo")) self.assertTrue(_check_variable_name(b"foo-bar")) class CheckSectionNameTests(TestCase): def test_invalid(self): self.assertFalse(_check_section_name(b"foo ")) self.assertFalse(_check_section_name(b"bar,bar")) def test_valid(self): self.assertTrue(_check_section_name(b"FOO")) self.assertTrue(_check_section_name(b"foo")) self.assertTrue(_check_section_name(b"foo-bar")) self.assertTrue(_check_section_name(b"bar.bar")) class SubmodulesTests(TestCase): def testSubmodules(self): cf = ConfigFile.from_file(BytesIO(b"""\ [submodule "core/lib"] \tpath = core/lib \turl = https://github.com/phhusson/QuasselC.git """)) got = list(parse_submodules(cf)) self.assertEqual([ (b'core/lib', b'https://github.com/phhusson/QuasselC.git', b'core/lib')], got) diff --git a/dulwich/tests/test_diff_tree.py b/dulwich/tests/test_diff_tree.py index c53cf7a1..cc5fbbeb 100644 --- a/dulwich/tests/test_diff_tree.py +++ b/dulwich/tests/test_diff_tree.py @@ -1,938 +1,948 @@ # 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)) 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)) 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 _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)) 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)) 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') 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_fastexport.py b/dulwich/tests/test_fastexport.py index 09fbb986..d5340e08 100644 --- a/dulwich/tests/test_fastexport.py +++ b/dulwich/tests/test_fastexport.py @@ -1,242 +1,260 @@ # test_fastexport.py -- Fast export/import functionality # Copyright (C) 2010 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 stat from dulwich.object_store import ( MemoryObjectStore, ) from dulwich.objects import ( Blob, Commit, Tree, ZERO_SHA, ) from dulwich.repo import ( MemoryRepo, ) from dulwich.tests import ( SkipTest, TestCase, ) from dulwich.tests.utils import ( build_commit_graph, ) class GitFastExporterTests(TestCase): """Tests for the GitFastExporter tests.""" def setUp(self): super(GitFastExporterTests, self).setUp() self.store = MemoryObjectStore() self.stream = BytesIO() try: from dulwich.fastexport import GitFastExporter except ImportError: raise SkipTest("python-fastimport not available") self.fastexporter = GitFastExporter(self.stream, self.store) def test_emit_blob(self): b = Blob() b.data = b"fooBAR" self.fastexporter.emit_blob(b) self.assertEqual(b'blob\nmark :1\ndata 6\nfooBAR\n', self.stream.getvalue()) def test_emit_commit(self): b = Blob() b.data = b"FOO" t = Tree() t.add(b"foo", stat.S_IFREG | 0o644, b.id) c = Commit() c.committer = c.author = b"Jelmer " c.author_time = c.commit_time = 1271345553 c.author_timezone = c.commit_timezone = 0 c.message = b"msg" c.tree = t.id self.store.add_objects([(b, None), (t, None), (c, None)]) self.fastexporter.emit_commit(c, b"refs/heads/master") self.assertEqual(b"""blob mark :1 data 3 FOO commit refs/heads/master mark :2 author Jelmer 1271345553 +0000 committer Jelmer 1271345553 +0000 data 3 msg M 644 :1 foo """, self.stream.getvalue()) class GitImportProcessorTests(TestCase): """Tests for the GitImportProcessor tests.""" def setUp(self): super(GitImportProcessorTests, self).setUp() self.repo = MemoryRepo() try: from dulwich.fastexport import GitImportProcessor except ImportError: raise SkipTest("python-fastimport not available") self.processor = GitImportProcessor(self.repo) def test_reset_handler(self): from fastimport import commands [c1] = build_commit_graph(self.repo.object_store, [[1]]) cmd = commands.ResetCommand(b"refs/heads/foo", c1.id) self.processor.reset_handler(cmd) self.assertEqual(c1.id, self.repo.get_refs()[b"refs/heads/foo"]) self.assertEqual(c1.id, self.processor.last_commit) def test_reset_handler_marker(self): from fastimport import commands [c1, c2] = build_commit_graph(self.repo.object_store, [[1], [2]]) self.processor.markers[b'10'] = c1.id cmd = commands.ResetCommand(b"refs/heads/foo", b':10') self.processor.reset_handler(cmd) self.assertEqual(c1.id, self.repo.get_refs()[b"refs/heads/foo"]) def test_reset_handler_default(self): from fastimport import commands [c1, c2] = build_commit_graph(self.repo.object_store, [[1], [2]]) cmd = commands.ResetCommand(b"refs/heads/foo", None) self.processor.reset_handler(cmd) self.assertEqual(ZERO_SHA, self.repo.get_refs()[b"refs/heads/foo"]) def test_commit_handler(self): from fastimport import commands cmd = commands.CommitCommand( b"refs/heads/foo", b"mrkr", (b"Jelmer", b"jelmer@samba.org", 432432432.0, 3600), (b"Jelmer", b"jelmer@samba.org", 432432432.0, 3600), b"FOO", None, [], []) self.processor.commit_handler(cmd) commit = self.repo[self.processor.last_commit] self.assertEqual(b"Jelmer ", commit.author) self.assertEqual(b"Jelmer ", commit.committer) self.assertEqual(b"FOO", commit.message) self.assertEqual([], commit.parents) self.assertEqual(432432432.0, commit.commit_time) self.assertEqual(432432432.0, commit.author_time) self.assertEqual(3600, commit.commit_timezone) self.assertEqual(3600, commit.author_timezone) self.assertEqual(commit, self.repo[b"refs/heads/foo"]) + def test_commit_handler_markers(self): + from fastimport import commands + [c1, c2, c3] = build_commit_graph(self.repo.object_store, + [[1], [2], [3]]) + self.processor.markers[b'10'] = c1.id + self.processor.markers[b'42'] = c2.id + self.processor.markers[b'98'] = c3.id + cmd = commands.CommitCommand( + b"refs/heads/foo", b"mrkr", + (b"Jelmer", b"jelmer@samba.org", 432432432.0, 3600), + (b"Jelmer", b"jelmer@samba.org", 432432432.0, 3600), + b"FOO", b':10', [b':42', b':98'], []) + self.processor.commit_handler(cmd) + commit = self.repo[self.processor.last_commit] + self.assertEqual(c1.id, commit.parents[0]) + self.assertEqual(c2.id, commit.parents[1]) + self.assertEqual(c3.id, commit.parents[2]) + def test_import_stream(self): markers = self.processor.import_stream(BytesIO(b"""blob mark :1 data 11 text for a commit refs/heads/master mark :2 committer Joe Foo 1288287382 +0000 data 20 M 100644 :1 a """)) self.assertEqual(2, len(markers)) self.assertTrue(isinstance(self.repo[markers[b"1"]], Blob)) self.assertTrue(isinstance(self.repo[markers[b"2"]], Commit)) def test_file_add(self): from fastimport import commands cmd = commands.BlobCommand(b"23", b"data") self.processor.blob_handler(cmd) cmd = commands.CommitCommand( b"refs/heads/foo", b"mrkr", (b"Jelmer", b"jelmer@samba.org", 432432432.0, 3600), (b"Jelmer", b"jelmer@samba.org", 432432432.0, 3600), b"FOO", None, [], [commands.FileModifyCommand(b"path", 0o100644, b":23", None)]) self.processor.commit_handler(cmd) commit = self.repo[self.processor.last_commit] self.assertEqual([ (b'path', 0o100644, b'6320cd248dd8aeaab759d5871f8781b5c0505172')], self.repo[commit.tree].items()) def simple_commit(self): from fastimport import commands cmd = commands.BlobCommand(b"23", b"data") self.processor.blob_handler(cmd) cmd = commands.CommitCommand( b"refs/heads/foo", b"mrkr", (b"Jelmer", b"jelmer@samba.org", 432432432.0, 3600), (b"Jelmer", b"jelmer@samba.org", 432432432.0, 3600), b"FOO", None, [], [commands.FileModifyCommand(b"path", 0o100644, b":23", None)]) self.processor.commit_handler(cmd) commit = self.repo[self.processor.last_commit] return commit def make_file_commit(self, file_cmds): """Create a trivial commit with the specified file commands. :param file_cmds: File commands to run. :return: The created commit object """ from fastimport import commands cmd = commands.CommitCommand( b"refs/heads/foo", b"mrkr", (b"Jelmer", b"jelmer@samba.org", 432432432.0, 3600), (b"Jelmer", b"jelmer@samba.org", 432432432.0, 3600), b"FOO", None, [], file_cmds) self.processor.commit_handler(cmd) return self.repo[self.processor.last_commit] def test_file_copy(self): from fastimport import commands self.simple_commit() commit = self.make_file_commit( [commands.FileCopyCommand(b"path", b"new_path")]) self.assertEqual([ (b'new_path', 0o100644, b'6320cd248dd8aeaab759d5871f8781b5c0505172'), (b'path', 0o100644, b'6320cd248dd8aeaab759d5871f8781b5c0505172'), ], self.repo[commit.tree].items()) def test_file_move(self): from fastimport import commands self.simple_commit() commit = self.make_file_commit( [commands.FileRenameCommand(b"path", b"new_path")]) self.assertEqual([ (b'new_path', 0o100644, b'6320cd248dd8aeaab759d5871f8781b5c0505172'), ], self.repo[commit.tree].items()) def test_file_delete(self): from fastimport import commands self.simple_commit() commit = self.make_file_commit([commands.FileDeleteCommand(b"path")]) self.assertEqual([], self.repo[commit.tree].items()) def test_file_deleteall(self): from fastimport import commands self.simple_commit() commit = self.make_file_commit([commands.FileDeleteAllCommand()]) self.assertEqual([], self.repo[commit.tree].items()) diff --git a/dulwich/tests/test_index.py b/dulwich/tests/test_index.py index 2749ca79..fb036c1a 100644 --- a/dulwich/tests/test_index.py +++ b/dulwich/tests/test_index.py @@ -1,660 +1,662 @@ # -*- coding: utf-8 -*- # test_index.py -- Tests for the git index # encoding: utf-8 # Copyright (C) 2008-2009 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. # """Tests for the index.""" from io import BytesIO import os import shutil import stat import struct import sys import tempfile from dulwich.index import ( Index, build_index_from_tree, cleanup_mode, commit_tree, get_unstaged_changes, index_entry_from_stat, read_index, read_index_dict, validate_path_element_default, validate_path_element_ntfs, write_cache_time, write_index, write_index_dict, _tree_to_fs_path, _fs_to_tree_path, ) from dulwich.object_store import ( MemoryObjectStore, ) from dulwich.objects import ( Blob, Commit, Tree, S_IFGITLINK, ) from dulwich.repo import Repo from dulwich.tests import ( TestCase, skipIf, ) class IndexTestCase(TestCase): datadir = os.path.join(os.path.dirname(__file__), 'data/indexes') def get_simple_index(self, name): return Index(os.path.join(self.datadir, name)) class SimpleIndexTestCase(IndexTestCase): def test_len(self): self.assertEqual(1, len(self.get_simple_index("index"))) def test_iter(self): self.assertEqual([b'bla'], list(self.get_simple_index("index"))) def test_getitem(self): self.assertEqual( ((1230680220, 0), (1230680220, 0), 2050, 3761020, 33188, 1000, 1000, 0, b'e69de29bb2d1d6434b8b29ae775ad8c2e48c5391', 0), self.get_simple_index("index")[b"bla"]) def test_empty(self): i = self.get_simple_index("notanindex") self.assertEqual(0, len(i)) self.assertFalse(os.path.exists(i._filename)) def test_against_empty_tree(self): i = self.get_simple_index("index") changes = list(i.changes_from_tree(MemoryObjectStore(), None)) self.assertEqual(1, len(changes)) (oldname, newname), (oldmode, newmode), (oldsha, newsha) = changes[0] self.assertEqual(b'bla', newname) self.assertEqual(b'e69de29bb2d1d6434b8b29ae775ad8c2e48c5391', newsha) class SimpleIndexWriterTestCase(IndexTestCase): def setUp(self): IndexTestCase.setUp(self) self.tempdir = tempfile.mkdtemp() def tearDown(self): IndexTestCase.tearDown(self) shutil.rmtree(self.tempdir) def test_simple_write(self): entries = [(b'barbla', (1230680220, 0), (1230680220, 0), 2050, 3761020, 33188, 1000, 1000, 0, b'e69de29bb2d1d6434b8b29ae775ad8c2e48c5391', 0)] filename = os.path.join(self.tempdir, 'test-simple-write-index') with open(filename, 'wb+') as x: write_index(x, entries) with open(filename, 'rb') as x: self.assertEqual(entries, list(read_index(x))) class ReadIndexDictTests(IndexTestCase): def setUp(self): IndexTestCase.setUp(self) self.tempdir = tempfile.mkdtemp() def tearDown(self): IndexTestCase.tearDown(self) shutil.rmtree(self.tempdir) def test_simple_write(self): entries = { b'barbla': ((1230680220, 0), (1230680220, 0), 2050, 3761020, 33188, 1000, 1000, 0, b'e69de29bb2d1d6434b8b29ae775ad8c2e48c5391', 0)} filename = os.path.join(self.tempdir, 'test-simple-write-index') with open(filename, 'wb+') as x: write_index_dict(x, entries) with open(filename, 'rb') as x: self.assertEqual(entries, read_index_dict(x)) class CommitTreeTests(TestCase): def setUp(self): super(CommitTreeTests, self).setUp() self.store = MemoryObjectStore() def test_single_blob(self): blob = Blob() blob.data = b"foo" self.store.add_object(blob) blobs = [(b"bla", blob.id, stat.S_IFREG)] rootid = commit_tree(self.store, blobs) self.assertEqual(rootid, b"1a1e80437220f9312e855c37ac4398b68e5c1d50") self.assertEqual((stat.S_IFREG, blob.id), self.store[rootid][b"bla"]) self.assertEqual(set([rootid, blob.id]), set(self.store._data.keys())) def test_nested(self): blob = Blob() blob.data = b"foo" self.store.add_object(blob) blobs = [(b"bla/bar", blob.id, stat.S_IFREG)] rootid = commit_tree(self.store, blobs) self.assertEqual(rootid, b"d92b959b216ad0d044671981196781b3258fa537") dirid = self.store[rootid][b"bla"][1] self.assertEqual(dirid, b"c1a1deb9788150829579a8b4efa6311e7b638650") self.assertEqual((stat.S_IFDIR, dirid), self.store[rootid][b"bla"]) self.assertEqual((stat.S_IFREG, blob.id), self.store[dirid][b"bar"]) self.assertEqual(set([rootid, dirid, blob.id]), set(self.store._data.keys())) class CleanupModeTests(TestCase): def test_file(self): self.assertEqual(0o100644, cleanup_mode(0o100000)) def test_executable(self): self.assertEqual(0o100755, cleanup_mode(0o100711)) def test_symlink(self): self.assertEqual(0o120000, cleanup_mode(0o120711)) def test_dir(self): self.assertEqual(0o040000, cleanup_mode(0o40531)) def test_submodule(self): self.assertEqual(0o160000, cleanup_mode(0o160744)) class WriteCacheTimeTests(TestCase): def test_write_string(self): f = BytesIO() self.assertRaises(TypeError, write_cache_time, f, "foo") def test_write_int(self): f = BytesIO() write_cache_time(f, 434343) self.assertEqual(struct.pack(">LL", 434343, 0), f.getvalue()) def test_write_tuple(self): f = BytesIO() write_cache_time(f, (434343, 21)) self.assertEqual(struct.pack(">LL", 434343, 21), f.getvalue()) def test_write_float(self): f = BytesIO() write_cache_time(f, 434343.000000021) self.assertEqual(struct.pack(">LL", 434343, 21), f.getvalue()) class IndexEntryFromStatTests(TestCase): def test_simple(self): st = os.stat_result( (16877, 131078, 64769, 154, 1000, 1000, 12288, 1323629595, 1324180496, 1324180496)) entry = index_entry_from_stat(st, "22" * 20, 0) self.assertEqual(entry, ( 1324180496, 1324180496, 64769, 131078, 16384, 1000, 1000, 12288, '2222222222222222222222222222222222222222', 0)) def test_override_mode(self): st = os.stat_result( (stat.S_IFREG + 0o644, 131078, 64769, 154, 1000, 1000, 12288, 1323629595, 1324180496, 1324180496)) entry = index_entry_from_stat( st, "22" * 20, 0, mode=stat.S_IFREG + 0o755) self.assertEqual(entry, ( 1324180496, 1324180496, 64769, 131078, 33261, 1000, 1000, 12288, '2222222222222222222222222222222222222222', 0)) class BuildIndexTests(TestCase): def assertReasonableIndexEntry(self, index_entry, mode, filesize, sha): self.assertEqual(index_entry[4], mode) # mode self.assertEqual(index_entry[7], filesize) # filesize self.assertEqual(index_entry[8], sha) # sha def assertFileContents(self, path, contents, symlink=False): if symlink: self.assertEqual(os.readlink(path), contents) else: with open(path, 'rb') as f: self.assertEqual(f.read(), contents) def test_empty(self): repo_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, repo_dir) with Repo.init(repo_dir) as repo: tree = Tree() repo.object_store.add_object(tree) build_index_from_tree( repo.path, repo.index_path(), repo.object_store, tree.id) # Verify index entries index = repo.open_index() self.assertEqual(len(index), 0) # Verify no files self.assertEqual(['.git'], os.listdir(repo.path)) def test_git_dir(self): repo_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, repo_dir) with Repo.init(repo_dir) as repo: # Populate repo filea = Blob.from_string(b'file a') filee = Blob.from_string(b'd') tree = Tree() tree[b'.git/a'] = (stat.S_IFREG | 0o644, filea.id) tree[b'c/e'] = (stat.S_IFREG | 0o644, filee.id) repo.object_store.add_objects( [(o, None) for o in [filea, filee, tree]]) build_index_from_tree( repo.path, repo.index_path(), repo.object_store, tree.id) # Verify index entries index = repo.open_index() self.assertEqual(len(index), 1) # filea apath = os.path.join(repo.path, '.git', 'a') self.assertFalse(os.path.exists(apath)) # filee epath = os.path.join(repo.path, 'c', 'e') self.assertTrue(os.path.exists(epath)) self.assertReasonableIndexEntry( index[b'c/e'], stat.S_IFREG | 0o644, 1, filee.id) self.assertFileContents(epath, b'd') def test_nonempty(self): repo_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, repo_dir) with Repo.init(repo_dir) as repo: # Populate repo filea = Blob.from_string(b'file a') fileb = Blob.from_string(b'file b') filed = Blob.from_string(b'file d') tree = Tree() tree[b'a'] = (stat.S_IFREG | 0o644, filea.id) tree[b'b'] = (stat.S_IFREG | 0o644, fileb.id) tree[b'c/d'] = (stat.S_IFREG | 0o644, filed.id) repo.object_store.add_objects( [(o, None) for o in [filea, fileb, filed, tree]]) build_index_from_tree( repo.path, repo.index_path(), repo.object_store, tree.id) # Verify index entries index = repo.open_index() self.assertEqual(len(index), 3) # filea apath = os.path.join(repo.path, 'a') self.assertTrue(os.path.exists(apath)) self.assertReasonableIndexEntry( index[b'a'], stat.S_IFREG | 0o644, 6, filea.id) self.assertFileContents(apath, b'file a') # fileb bpath = os.path.join(repo.path, 'b') self.assertTrue(os.path.exists(bpath)) self.assertReasonableIndexEntry( index[b'b'], stat.S_IFREG | 0o644, 6, fileb.id) self.assertFileContents(bpath, b'file b') # filed dpath = os.path.join(repo.path, 'c', 'd') self.assertTrue(os.path.exists(dpath)) self.assertReasonableIndexEntry( index[b'c/d'], stat.S_IFREG | 0o644, 6, filed.id) self.assertFileContents(dpath, b'file d') # Verify no extra files self.assertEqual( ['.git', 'a', 'b', 'c'], sorted(os.listdir(repo.path))) self.assertEqual( ['d'], sorted(os.listdir(os.path.join(repo.path, 'c')))) @skipIf(not getattr(os, 'sync', None), 'Requires sync support') def test_norewrite(self): repo_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, repo_dir) with Repo.init(repo_dir) as repo: # Populate repo filea = Blob.from_string(b'file a') filea_path = os.path.join(repo_dir, 'a') tree = Tree() tree[b'a'] = (stat.S_IFREG | 0o644, filea.id) repo.object_store.add_objects([(o, None) for o in [filea, tree]]) # First Write build_index_from_tree(repo.path, repo.index_path(), repo.object_store, tree.id) # Use sync as metadata can be cached on some FS os.sync() mtime = os.stat(filea_path).st_mtime # Test Rewrite build_index_from_tree(repo.path, repo.index_path(), repo.object_store, tree.id) os.sync() self.assertEqual(mtime, os.stat(filea_path).st_mtime) # Modify content with open(filea_path, 'wb') as fh: fh.write(b'test a') os.sync() mtime = os.stat(filea_path).st_mtime # Test rewrite build_index_from_tree(repo.path, repo.index_path(), repo.object_store, tree.id) os.sync() with open(filea_path, 'rb') as fh: self.assertEqual(b'file a', fh.read()) @skipIf(not getattr(os, 'symlink', None), 'Requires symlink support') def test_symlink(self): repo_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, repo_dir) with Repo.init(repo_dir) as repo: # Populate repo filed = Blob.from_string(b'file d') filee = Blob.from_string(b'd') tree = Tree() tree[b'c/d'] = (stat.S_IFREG | 0o644, filed.id) tree[b'c/e'] = (stat.S_IFLNK, filee.id) # symlink repo.object_store.add_objects( [(o, None) for o in [filed, filee, tree]]) build_index_from_tree( repo.path, repo.index_path(), repo.object_store, tree.id) # Verify index entries index = repo.open_index() # symlink to d epath = os.path.join(repo.path, 'c', 'e') self.assertTrue(os.path.exists(epath)) self.assertReasonableIndexEntry( index[b'c/e'], stat.S_IFLNK, 0 if sys.platform == 'win32' else 1, filee.id) self.assertFileContents(epath, 'd', symlink=True) def test_no_decode_encode(self): repo_dir = tempfile.mkdtemp() repo_dir_bytes = repo_dir.encode(sys.getfilesystemencoding()) self.addCleanup(shutil.rmtree, repo_dir) with Repo.init(repo_dir) as repo: # Populate repo file = Blob.from_string(b'foo') tree = Tree() latin1_name = u'À'.encode('latin1') latin1_path = os.path.join(repo_dir_bytes, latin1_name) utf8_name = u'À'.encode('utf8') utf8_path = os.path.join(repo_dir_bytes, utf8_name) tree[latin1_name] = (stat.S_IFREG | 0o644, file.id) tree[utf8_name] = (stat.S_IFREG | 0o644, file.id) repo.object_store.add_objects( [(o, None) for o in [file, tree]]) try: os.path.exists(latin1_path) except UnicodeDecodeError: # This happens e.g. with python3.6 on Windows. # It implicitly decodes using utf8, which doesn't work. self.skipTest('can not implicitly convert as utf8') build_index_from_tree( repo.path, repo.index_path(), repo.object_store, tree.id) # Verify index entries index = repo.open_index() self.assertIn(latin1_name, index) self.assertIn(utf8_name, index) self.assertTrue(os.path.exists(latin1_path)) self.assertTrue(os.path.exists(utf8_path)) def test_git_submodule(self): repo_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, repo_dir) with Repo.init(repo_dir) as repo: filea = Blob.from_string(b'file alalala') subtree = Tree() subtree[b'a'] = (stat.S_IFREG | 0o644, filea.id) c = Commit() c.tree = subtree.id c.committer = c.author = b'Somebody ' c.commit_time = c.author_time = 42342 c.commit_timezone = c.author_timezone = 0 c.parents = [] c.message = b'Subcommit' tree = Tree() tree[b'c'] = (S_IFGITLINK, c.id) repo.object_store.add_objects( [(o, None) for o in [tree]]) build_index_from_tree( repo.path, repo.index_path(), repo.object_store, tree.id) # Verify index entries index = repo.open_index() self.assertEqual(len(index), 1) # filea apath = os.path.join(repo.path, 'c/a') self.assertFalse(os.path.exists(apath)) # dir c cpath = os.path.join(repo.path, 'c') self.assertTrue(os.path.isdir(cpath)) self.assertEqual(index[b'c'][4], S_IFGITLINK) # mode self.assertEqual(index[b'c'][8], c.id) # sha def test_git_submodule_exists(self): repo_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, repo_dir) with Repo.init(repo_dir) as repo: filea = Blob.from_string(b'file alalala') subtree = Tree() subtree[b'a'] = (stat.S_IFREG | 0o644, filea.id) c = Commit() c.tree = subtree.id c.committer = c.author = b'Somebody ' c.commit_time = c.author_time = 42342 c.commit_timezone = c.author_timezone = 0 c.parents = [] c.message = b'Subcommit' tree = Tree() tree[b'c'] = (S_IFGITLINK, c.id) os.mkdir(os.path.join(repo_dir, 'c')) repo.object_store.add_objects( [(o, None) for o in [tree]]) build_index_from_tree( repo.path, repo.index_path(), repo.object_store, tree.id) # Verify index entries index = repo.open_index() self.assertEqual(len(index), 1) # filea apath = os.path.join(repo.path, 'c/a') self.assertFalse(os.path.exists(apath)) # dir c cpath = os.path.join(repo.path, 'c') self.assertTrue(os.path.isdir(cpath)) self.assertEqual(index[b'c'][4], S_IFGITLINK) # mode self.assertEqual(index[b'c'][8], c.id) # sha class GetUnstagedChangesTests(TestCase): def test_get_unstaged_changes(self): """Unit test for get_unstaged_changes.""" repo_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, repo_dir) with Repo.init(repo_dir) as repo: # Commit a dummy file then modify it foo1_fullpath = os.path.join(repo_dir, 'foo1') with open(foo1_fullpath, 'wb') as f: f.write(b'origstuff') foo2_fullpath = os.path.join(repo_dir, 'foo2') with open(foo2_fullpath, 'wb') as f: f.write(b'origstuff') repo.stage(['foo1', 'foo2']) - repo.do_commit(b'test status', author=b'', committer=b'') + repo.do_commit(b'test status', author=b'author ', + committer=b'committer ') with open(foo1_fullpath, 'wb') as f: f.write(b'newstuff') # modify access and modify time of path os.utime(foo1_fullpath, (0, 0)) changes = get_unstaged_changes(repo.open_index(), repo_dir) self.assertEqual(list(changes), [b'foo1']) def test_get_unstaged_deleted_changes(self): """Unit test for get_unstaged_changes.""" repo_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, repo_dir) with Repo.init(repo_dir) as repo: # Commit a dummy file then remove it foo1_fullpath = os.path.join(repo_dir, 'foo1') with open(foo1_fullpath, 'wb') as f: f.write(b'origstuff') repo.stage(['foo1']) - repo.do_commit(b'test status', author=b'', committer=b'') + repo.do_commit(b'test status', author=b'author ', + committer=b'committer ') os.unlink(foo1_fullpath) changes = get_unstaged_changes(repo.open_index(), repo_dir) self.assertEqual(list(changes), [b'foo1']) class TestValidatePathElement(TestCase): def test_default(self): self.assertTrue(validate_path_element_default(b"bla")) self.assertTrue(validate_path_element_default(b".bla")) self.assertFalse(validate_path_element_default(b".git")) self.assertFalse(validate_path_element_default(b".giT")) self.assertFalse(validate_path_element_default(b"..")) self.assertTrue(validate_path_element_default(b"git~1")) def test_ntfs(self): self.assertTrue(validate_path_element_ntfs(b"bla")) self.assertTrue(validate_path_element_ntfs(b".bla")) self.assertFalse(validate_path_element_ntfs(b".git")) self.assertFalse(validate_path_element_ntfs(b".giT")) self.assertFalse(validate_path_element_ntfs(b"..")) self.assertFalse(validate_path_element_ntfs(b"git~1")) class TestTreeFSPathConversion(TestCase): def test_tree_to_fs_path(self): tree_path = u'délwíçh/foo'.encode('utf8') fs_path = _tree_to_fs_path(b'/prefix/path', tree_path) self.assertEqual( fs_path, os.path.join(u'/prefix/path', u'délwíçh', u'foo').encode('utf8')) def test_fs_to_tree_path_str(self): fs_path = os.path.join(os.path.join(u'délwíçh', u'foo')) tree_path = _fs_to_tree_path(fs_path, "utf-8") self.assertEqual(tree_path, u'délwíçh/foo'.encode("utf-8")) def test_fs_to_tree_path_bytes(self): fs_path = os.path.join(os.path.join(u'délwíçh', u'foo').encode('utf8')) tree_path = _fs_to_tree_path(fs_path, "utf-8") self.assertEqual(tree_path, u'délwíçh/foo'.encode('utf8')) diff --git a/dulwich/tests/test_object_store.py b/dulwich/tests/test_object_store.py index b42e3623..986bf3d6 100644 --- a/dulwich/tests/test_object_store.py +++ b/dulwich/tests/test_object_store.py @@ -1,610 +1,647 @@ # 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, 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: + 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: + 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'}) diff --git a/dulwich/tests/test_objects.py b/dulwich/tests/test_objects.py index c6cf9bbb..8c955804 100644 --- a/dulwich/tests/test_objects.py +++ b/dulwich/tests/test_objects.py @@ -1,1229 +1,1288 @@ # 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' 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_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) # 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_pack.py b/dulwich/tests/test_pack.py index a3d5c8a2..750eae71 100644 --- a/dulwich/tests/test_pack.py +++ b/dulwich/tests/test_pack.py @@ -1,1106 +1,1128 @@ # test_pack.py -- Tests for the handling of git packs. # 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. # """Tests for Dulwich packs.""" from io import BytesIO from hashlib import sha1 import os import shutil import tempfile import zlib from dulwich.errors import ( ApplyDeltaError, ChecksumMismatch, ) from dulwich.file import ( GitFile, ) from dulwich.object_store import ( MemoryObjectStore, ) from dulwich.objects import ( hex_to_sha, sha_to_hex, Commit, Tree, Blob, ) from dulwich.pack import ( OFS_DELTA, REF_DELTA, MemoryPackIndex, Pack, PackData, apply_delta, create_delta, deltify_pack_objects, load_pack_index, UnpackedObject, read_zlib_chunks, write_pack_header, write_pack_index_v1, write_pack_index_v2, write_pack_object, write_pack, unpack_object, compute_file_sha, PackStreamReader, DeltaChainIterator, _delta_encode_size, _encode_copy_operation, ) from dulwich.tests import ( TestCase, ) from dulwich.tests.utils import ( make_object, build_pack, ) pack1_sha = b'bc63ddad95e7321ee734ea11a7a62d314e0d7481' a_sha = b'6f670c0fb53f9463760b7295fbb814e965fb20c8' tree_sha = b'b2a2766a2879c209ab1176e7e778b81ae422eeaa' commit_sha = b'f18faa16531ac570a3fdc8c7ca16682548dafd12' class PackTests(TestCase): """Base class for testing packs""" def setUp(self): super(PackTests, self).setUp() self.tempdir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, self.tempdir) datadir = os.path.abspath( os.path.join(os.path.dirname(__file__), 'data/packs')) def get_pack_index(self, sha): """Returns a PackIndex from the datadir with the given sha""" return load_pack_index( os.path.join(self.datadir, 'pack-%s.idx' % sha.decode('ascii'))) def get_pack_data(self, sha): """Returns a PackData object from the datadir with the given sha""" return PackData( os.path.join( self.datadir, 'pack-%s.pack' % sha.decode('ascii'))) def get_pack(self, sha): return Pack( os.path.join(self.datadir, 'pack-%s' % sha.decode('ascii'))) def assertSucceeds(self, func, *args, **kwargs): try: func(*args, **kwargs) except ChecksumMismatch as e: self.fail(e) class PackIndexTests(PackTests): """Class that tests the index of packfiles""" def test_object_index(self): """Tests that the correct object offset is returned from the index.""" p = self.get_pack_index(pack1_sha) self.assertRaises(KeyError, p.object_index, pack1_sha) self.assertEqual(p.object_index(a_sha), 178) self.assertEqual(p.object_index(tree_sha), 138) self.assertEqual(p.object_index(commit_sha), 12) + def test_object_sha1(self): + """Tests that the correct object offset is returned from the index.""" + p = self.get_pack_index(pack1_sha) + self.assertRaises(KeyError, p.object_sha1, 876) + self.assertEqual(p.object_sha1(178), hex_to_sha(a_sha)) + self.assertEqual(p.object_sha1(138), hex_to_sha(tree_sha)) + self.assertEqual(p.object_sha1(12), hex_to_sha(commit_sha)) + def test_index_len(self): p = self.get_pack_index(pack1_sha) self.assertEqual(3, len(p)) def test_get_stored_checksum(self): p = self.get_pack_index(pack1_sha) self.assertEqual(b'f2848e2ad16f329ae1c92e3b95e91888daa5bd01', sha_to_hex(p.get_stored_checksum())) self.assertEqual(b'721980e866af9a5f93ad674144e1459b8ba3e7b7', sha_to_hex(p.get_pack_checksum())) def test_index_check(self): p = self.get_pack_index(pack1_sha) self.assertSucceeds(p.check) def test_iterentries(self): p = self.get_pack_index(pack1_sha) entries = [(sha_to_hex(s), o, c) for s, o, c in p.iterentries()] self.assertEqual([ (b'6f670c0fb53f9463760b7295fbb814e965fb20c8', 178, None), (b'b2a2766a2879c209ab1176e7e778b81ae422eeaa', 138, None), (b'f18faa16531ac570a3fdc8c7ca16682548dafd12', 12, None) ], entries) def test_iter(self): p = self.get_pack_index(pack1_sha) self.assertEqual(set([tree_sha, commit_sha, a_sha]), set(p)) class TestPackDeltas(TestCase): test_string1 = b'The answer was flailing in the wind' test_string2 = b'The answer was falling down the pipe' test_string3 = b'zzzzz' test_string_empty = b'' test_string_big = b'Z' * 8192 test_string_huge = b'Z' * 100000 def _test_roundtrip(self, base, target): self.assertEqual( target, b''.join(apply_delta(base, create_delta(base, target)))) def test_nochange(self): self._test_roundtrip(self.test_string1, self.test_string1) def test_nochange_huge(self): self._test_roundtrip(self.test_string_huge, self.test_string_huge) def test_change(self): self._test_roundtrip(self.test_string1, self.test_string2) def test_rewrite(self): self._test_roundtrip(self.test_string1, self.test_string3) def test_empty_to_big(self): self._test_roundtrip(self.test_string_empty, self.test_string_big) def test_empty_to_huge(self): self._test_roundtrip(self.test_string_empty, self.test_string_huge) def test_huge_copy(self): self._test_roundtrip(self.test_string_huge + self.test_string1, self.test_string_huge + self.test_string2) def test_dest_overflow(self): self.assertRaises(ApplyDeltaError, apply_delta, b'a'*0x10000, b'\x80\x80\x04\x80\x80\x04\x80' + b'a'*0x10000) self.assertRaises( ApplyDeltaError, apply_delta, b'', b'\x00\x80\x02\xb0\x11\x11') def test_pypy_issue(self): # Test for https://github.com/jelmer/dulwich/issues/509 / # https://bitbucket.org/pypy/pypy/issues/2499/cpyext-pystring_asstring-doesnt-work chunks = [ b'tree 03207ccf58880a748188836155ceed72f03d65d6\n' b'parent 408fbab530fd4abe49249a636a10f10f44d07a21\n' b'author Victor Stinner ' b'1421355207 +0100\n' b'committer Victor Stinner ' b'1421355207 +0100\n' b'\n' b'Backout changeset 3a06020af8cf\n' b'\nStreamWriter: close() now clears the reference to the ' b'transport\n' b'\nStreamWriter now raises an exception if it is closed: ' b'write(), writelines(),\n' b'write_eof(), can_write_eof(), get_extra_info(), drain().\n'] delta = [ b'\xcd\x03\xad\x03]tree ff3c181a393d5a7270cddc01ea863818a8621ca8\n' b'parent 20a103cc90135494162e819f98d0edfc1f1fba6b\x91]7\x0510738' b'\x91\x99@\x0b10738 +0100\x93\x04\x01\xc9'] res = apply_delta(chunks, delta) expected = [ b'tree ff3c181a393d5a7270cddc01ea863818a8621ca8\n' b'parent 20a103cc90135494162e819f98d0edfc1f1fba6b', b'\nauthor Victor Stinner 14213', b'10738', b' +0100\ncommitter Victor Stinner ' b'14213', b'10738 +0100', b'\n\nStreamWriter: close() now clears the reference to the ' b'transport\n\n' b'StreamWriter now raises an exception if it is closed: ' b'write(), writelines(),\n' b'write_eof(), can_write_eof(), get_extra_info(), drain().\n'] self.assertEqual(b''.join(expected), b''.join(res)) class TestPackData(PackTests): """Tests getting the data from the packfile.""" def test_create_pack(self): self.get_pack_data(pack1_sha).close() def test_from_file(self): path = os.path.join(self.datadir, 'pack-%s.pack' % pack1_sha.decode('ascii')) with open(path, 'rb') as f: PackData.from_file(f, os.path.getsize(path)) def test_pack_len(self): with self.get_pack_data(pack1_sha) as p: self.assertEqual(3, len(p)) def test_index_check(self): with self.get_pack_data(pack1_sha) as p: self.assertSucceeds(p.check) def test_iterobjects(self): with self.get_pack_data(pack1_sha) as p: commit_data = ( b'tree b2a2766a2879c209ab1176e7e778b81ae422eeaa\n' b'author James Westby ' b'1174945067 +0100\n' b'committer James Westby ' b'1174945067 +0100\n' b'\n' b'Test commit\n') blob_sha = b'6f670c0fb53f9463760b7295fbb814e965fb20c8' tree_data = b'100644 a\0' + hex_to_sha(blob_sha) actual = [] for offset, type_num, chunks, crc32 in p.iterobjects(): actual.append((offset, type_num, b''.join(chunks), crc32)) self.assertEqual([ (12, 1, commit_data, 3775879613), (138, 2, tree_data, 912998690), (178, 3, b'test 1\n', 1373561701) ], actual) def test_iterentries(self): with self.get_pack_data(pack1_sha) as p: entries = set((sha_to_hex(s), o, c) for s, o, c in p.iterentries()) self.assertEqual(set([ (b'6f670c0fb53f9463760b7295fbb814e965fb20c8', 178, 1373561701), (b'b2a2766a2879c209ab1176e7e778b81ae422eeaa', 138, 912998690), (b'f18faa16531ac570a3fdc8c7ca16682548dafd12', 12, 3775879613), ]), entries) def test_create_index_v1(self): with self.get_pack_data(pack1_sha) as p: filename = os.path.join(self.tempdir, 'v1test.idx') p.create_index_v1(filename) idx1 = load_pack_index(filename) idx2 = self.get_pack_index(pack1_sha) self.assertEqual(idx1, idx2) def test_create_index_v2(self): with self.get_pack_data(pack1_sha) as p: filename = os.path.join(self.tempdir, 'v2test.idx') p.create_index_v2(filename) idx1 = load_pack_index(filename) idx2 = self.get_pack_index(pack1_sha) self.assertEqual(idx1, idx2) def test_compute_file_sha(self): f = BytesIO(b'abcd1234wxyz') self.assertEqual(sha1(b'abcd1234wxyz').hexdigest(), compute_file_sha(f).hexdigest()) self.assertEqual(sha1(b'abcd1234wxyz').hexdigest(), compute_file_sha(f, buffer_size=5).hexdigest()) self.assertEqual(sha1(b'abcd1234').hexdigest(), compute_file_sha(f, end_ofs=-4).hexdigest()) self.assertEqual(sha1(b'1234wxyz').hexdigest(), compute_file_sha(f, start_ofs=4).hexdigest()) self.assertEqual( sha1(b'1234').hexdigest(), compute_file_sha(f, start_ofs=4, end_ofs=-4).hexdigest()) def test_compute_file_sha_short_file(self): f = BytesIO(b'abcd1234wxyz') self.assertRaises(AssertionError, compute_file_sha, f, end_ofs=-20) self.assertRaises(AssertionError, compute_file_sha, f, end_ofs=20) self.assertRaises(AssertionError, compute_file_sha, f, start_ofs=10, end_ofs=-12) class TestPack(PackTests): def test_len(self): with self.get_pack(pack1_sha) as p: self.assertEqual(3, len(p)) def test_contains(self): with self.get_pack(pack1_sha) as p: self.assertTrue(tree_sha in p) def test_get(self): with self.get_pack(pack1_sha) as p: self.assertEqual(type(p[tree_sha]), Tree) def test_iter(self): with self.get_pack(pack1_sha) as p: self.assertEqual(set([tree_sha, commit_sha, a_sha]), set(p)) def test_iterobjects(self): with self.get_pack(pack1_sha) as p: expected = set([p[s] for s in [commit_sha, tree_sha, a_sha]]) self.assertEqual(expected, set(list(p.iterobjects()))) def test_pack_tuples(self): with self.get_pack(pack1_sha) as p: tuples = p.pack_tuples() expected = set( [(p[s], None) for s in [commit_sha, tree_sha, a_sha]]) self.assertEqual(expected, set(list(tuples))) self.assertEqual(expected, set(list(tuples))) self.assertEqual(3, len(tuples)) def test_get_object_at(self): """Tests random access for non-delta objects""" with self.get_pack(pack1_sha) as p: obj = p[a_sha] self.assertEqual(obj.type_name, b'blob') self.assertEqual(obj.sha().hexdigest().encode('ascii'), a_sha) obj = p[tree_sha] self.assertEqual(obj.type_name, b'tree') self.assertEqual(obj.sha().hexdigest().encode('ascii'), tree_sha) obj = p[commit_sha] self.assertEqual(obj.type_name, b'commit') self.assertEqual(obj.sha().hexdigest().encode('ascii'), commit_sha) def test_copy(self): with self.get_pack(pack1_sha) as origpack: self.assertSucceeds(origpack.index.check) basename = os.path.join(self.tempdir, 'Elch') write_pack(basename, origpack.pack_tuples()) with Pack(basename) as newpack: self.assertEqual(origpack, newpack) self.assertSucceeds(newpack.index.check) self.assertEqual(origpack.name(), newpack.name()) self.assertEqual(origpack.index.get_pack_checksum(), newpack.index.get_pack_checksum()) wrong_version = origpack.index.version != newpack.index.version orig_checksum = origpack.index.get_stored_checksum() new_checksum = newpack.index.get_stored_checksum() self.assertTrue(wrong_version or orig_checksum == new_checksum) def test_commit_obj(self): with self.get_pack(pack1_sha) as p: commit = p[commit_sha] self.assertEqual(b'James Westby ', commit.author) self.assertEqual([], commit.parents) def _copy_pack(self, origpack): basename = os.path.join(self.tempdir, 'somepack') write_pack(basename, origpack.pack_tuples()) return Pack(basename) def test_keep_no_message(self): with self.get_pack(pack1_sha) as p: p = self._copy_pack(p) with p: keepfile_name = p.keep() # file should exist self.assertTrue(os.path.exists(keepfile_name)) with open(keepfile_name, 'r') as f: buf = f.read() self.assertEqual('', buf) def test_keep_message(self): with self.get_pack(pack1_sha) as p: p = self._copy_pack(p) msg = b'some message' with p: keepfile_name = p.keep(msg) # file should exist self.assertTrue(os.path.exists(keepfile_name)) # and contain the right message, with a linefeed with open(keepfile_name, 'rb') as f: buf = f.read() self.assertEqual(msg + b'\n', buf) def test_name(self): with self.get_pack(pack1_sha) as p: self.assertEqual(pack1_sha, p.name()) def test_length_mismatch(self): with self.get_pack_data(pack1_sha) as data: index = self.get_pack_index(pack1_sha) Pack.from_objects(data, index).check_length_and_checksum() data._file.seek(12) bad_file = BytesIO() write_pack_header(bad_file, 9999) bad_file.write(data._file.read()) bad_file = BytesIO(bad_file.getvalue()) bad_data = PackData('', file=bad_file) bad_pack = Pack.from_lazy_objects(lambda: bad_data, lambda: index) self.assertRaises(AssertionError, lambda: bad_pack.data) self.assertRaises(AssertionError, lambda: bad_pack.check_length_and_checksum()) def test_checksum_mismatch(self): with self.get_pack_data(pack1_sha) as data: index = self.get_pack_index(pack1_sha) Pack.from_objects(data, index).check_length_and_checksum() data._file.seek(0) bad_file = BytesIO(data._file.read()[:-20] + (b'\xff' * 20)) bad_data = PackData('', file=bad_file) bad_pack = Pack.from_lazy_objects(lambda: bad_data, lambda: index) self.assertRaises(ChecksumMismatch, lambda: bad_pack.data) self.assertRaises(ChecksumMismatch, lambda: bad_pack.check_length_and_checksum()) def test_iterobjects_2(self): with self.get_pack(pack1_sha) as p: objs = dict((o.id, o) for o in p.iterobjects()) self.assertEqual(3, len(objs)) self.assertEqual(sorted(objs), sorted(p.index)) self.assertTrue(isinstance(objs[a_sha], Blob)) self.assertTrue(isinstance(objs[tree_sha], Tree)) self.assertTrue(isinstance(objs[commit_sha], Commit)) class TestThinPack(PackTests): def setUp(self): super(TestThinPack, self).setUp() self.store = MemoryObjectStore() self.blobs = {} for blob in (b'foo', b'bar', b'foo1234', b'bar2468'): self.blobs[blob] = make_object(Blob, data=blob) self.store.add_object(self.blobs[b'foo']) self.store.add_object(self.blobs[b'bar']) # Build a thin pack. 'foo' is as an external reference, 'bar' an # internal reference. self.pack_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, self.pack_dir) self.pack_prefix = os.path.join(self.pack_dir, 'pack') with open(self.pack_prefix + '.pack', 'wb') as f: build_pack(f, [ (REF_DELTA, (self.blobs[b'foo'].id, b'foo1234')), (Blob.type_num, b'bar'), (REF_DELTA, (self.blobs[b'bar'].id, b'bar2468'))], store=self.store) # Index the new pack. with self.make_pack(True) as pack: with PackData(pack._data_path) as data: data.pack = pack data.create_index(self.pack_prefix + '.idx') del self.store[self.blobs[b'bar'].id] def make_pack(self, resolve_ext_ref): return Pack( self.pack_prefix, resolve_ext_ref=self.store.get_raw if resolve_ext_ref else None) def test_get_raw(self): with self.make_pack(False) as p: self.assertRaises( KeyError, p.get_raw, self.blobs[b'foo1234'].id) with self.make_pack(True) as p: self.assertEqual( (3, b'foo1234'), p.get_raw(self.blobs[b'foo1234'].id)) + def test_get_raw_unresolved(self): + with self.make_pack(False) as p: + self.assertEqual( + (7, + b'\x19\x10(\x15f=#\xf8\xb7ZG\xe7\xa0\x19e\xdc\xdc\x96F\x8c', + [b'x\x9ccf\x9f\xc0\xccbhdl\x02\x00\x06f\x01l']), + p.get_raw_unresolved(self.blobs[b'foo1234'].id)) + with self.make_pack(True) as p: + self.assertEqual( + (7, + b'\x19\x10(\x15f=#\xf8\xb7ZG\xe7\xa0\x19e\xdc\xdc\x96F\x8c', + [b'x\x9ccf\x9f\xc0\xccbhdl\x02\x00\x06f\x01l']), + p.get_raw_unresolved(self.blobs[b'foo1234'].id)) + def test_iterobjects(self): with self.make_pack(False) as p: self.assertRaises(KeyError, list, p.iterobjects()) with self.make_pack(True) as p: self.assertEqual( sorted([self.blobs[b'foo1234'].id, self.blobs[b'bar'].id, self.blobs[b'bar2468'].id]), sorted(o.id for o in p.iterobjects())) class WritePackTests(TestCase): def test_write_pack_header(self): f = BytesIO() write_pack_header(f, 42) self.assertEqual(b'PACK\x00\x00\x00\x02\x00\x00\x00*', f.getvalue()) def test_write_pack_object(self): f = BytesIO() f.write(b'header') offset = f.tell() crc32 = write_pack_object(f, Blob.type_num, b'blob') self.assertEqual(crc32, zlib.crc32(f.getvalue()[6:]) & 0xffffffff) f.write(b'x') # unpack_object needs extra trailing data. f.seek(offset) unpacked, unused = unpack_object(f.read, compute_crc32=True) self.assertEqual(Blob.type_num, unpacked.pack_type_num) self.assertEqual(Blob.type_num, unpacked.obj_type_num) self.assertEqual([b'blob'], unpacked.decomp_chunks) self.assertEqual(crc32, unpacked.crc32) self.assertEqual(b'x', unused) def test_write_pack_object_sha(self): f = BytesIO() f.write(b'header') offset = f.tell() sha_a = sha1(b'foo') sha_b = sha_a.copy() write_pack_object(f, Blob.type_num, b'blob', sha=sha_a) self.assertNotEqual(sha_a.digest(), sha_b.digest()) sha_b.update(f.getvalue()[offset:]) self.assertEqual(sha_a.digest(), sha_b.digest()) pack_checksum = hex_to_sha('721980e866af9a5f93ad674144e1459b8ba3e7b7') class BaseTestPackIndexWriting(object): def assertSucceeds(self, func, *args, **kwargs): try: func(*args, **kwargs) except ChecksumMismatch as e: self.fail(e) def index(self, filename, entries, pack_checksum): raise NotImplementedError(self.index) def test_empty(self): idx = self.index('empty.idx', [], pack_checksum) self.assertEqual(idx.get_pack_checksum(), pack_checksum) self.assertEqual(0, len(idx)) def test_large(self): entry1_sha = hex_to_sha('4e6388232ec39792661e2e75db8fb117fc869ce6') entry2_sha = hex_to_sha('e98f071751bd77f59967bfa671cd2caebdccc9a2') entries = [(entry1_sha, 0xf2972d0830529b87, 24), (entry2_sha, (~0xf2972d0830529b87) & (2 ** 64 - 1), 92)] if not self._supports_large: self.assertRaises(TypeError, self.index, 'single.idx', entries, pack_checksum) return idx = self.index('single.idx', entries, pack_checksum) self.assertEqual(idx.get_pack_checksum(), pack_checksum) self.assertEqual(2, len(idx)) actual_entries = list(idx.iterentries()) self.assertEqual(len(entries), len(actual_entries)) for mine, actual in zip(entries, actual_entries): my_sha, my_offset, my_crc = mine actual_sha, actual_offset, actual_crc = actual self.assertEqual(my_sha, actual_sha) self.assertEqual(my_offset, actual_offset) if self._has_crc32_checksum: self.assertEqual(my_crc, actual_crc) else: self.assertTrue(actual_crc is None) def test_single(self): entry_sha = hex_to_sha('6f670c0fb53f9463760b7295fbb814e965fb20c8') my_entries = [(entry_sha, 178, 42)] idx = self.index('single.idx', my_entries, pack_checksum) self.assertEqual(idx.get_pack_checksum(), pack_checksum) self.assertEqual(1, len(idx)) actual_entries = list(idx.iterentries()) self.assertEqual(len(my_entries), len(actual_entries)) for mine, actual in zip(my_entries, actual_entries): my_sha, my_offset, my_crc = mine actual_sha, actual_offset, actual_crc = actual self.assertEqual(my_sha, actual_sha) self.assertEqual(my_offset, actual_offset) if self._has_crc32_checksum: self.assertEqual(my_crc, actual_crc) else: self.assertTrue(actual_crc is None) class BaseTestFilePackIndexWriting(BaseTestPackIndexWriting): def setUp(self): self.tempdir = tempfile.mkdtemp() def tearDown(self): shutil.rmtree(self.tempdir) def index(self, filename, entries, pack_checksum): path = os.path.join(self.tempdir, filename) self.writeIndex(path, entries, pack_checksum) idx = load_pack_index(path) self.assertSucceeds(idx.check) self.assertEqual(idx.version, self._expected_version) return idx def writeIndex(self, filename, entries, pack_checksum): # FIXME: Write to BytesIO instead rather than hitting disk ? with GitFile(filename, "wb") as f: self._write_fn(f, entries, pack_checksum) class TestMemoryIndexWriting(TestCase, BaseTestPackIndexWriting): def setUp(self): TestCase.setUp(self) self._has_crc32_checksum = True self._supports_large = True def index(self, filename, entries, pack_checksum): return MemoryPackIndex(entries, pack_checksum) def tearDown(self): TestCase.tearDown(self) class TestPackIndexWritingv1(TestCase, BaseTestFilePackIndexWriting): def setUp(self): TestCase.setUp(self) BaseTestFilePackIndexWriting.setUp(self) self._has_crc32_checksum = False self._expected_version = 1 self._supports_large = False self._write_fn = write_pack_index_v1 def tearDown(self): TestCase.tearDown(self) BaseTestFilePackIndexWriting.tearDown(self) class TestPackIndexWritingv2(TestCase, BaseTestFilePackIndexWriting): def setUp(self): TestCase.setUp(self) BaseTestFilePackIndexWriting.setUp(self) self._has_crc32_checksum = True self._supports_large = True self._expected_version = 2 self._write_fn = write_pack_index_v2 def tearDown(self): TestCase.tearDown(self) BaseTestFilePackIndexWriting.tearDown(self) class ReadZlibTests(TestCase): decomp = ( b'tree 4ada885c9196b6b6fa08744b5862bf92896fc002\n' b'parent None\n' b'author Jelmer Vernooij 1228980214 +0000\n' b'committer Jelmer Vernooij 1228980214 +0000\n' b'\n' b"Provide replacement for mmap()'s offset argument.") comp = zlib.compress(decomp) extra = b'nextobject' def setUp(self): super(ReadZlibTests, self).setUp() self.read = BytesIO(self.comp + self.extra).read self.unpacked = UnpackedObject( Tree.type_num, None, len(self.decomp), 0) def test_decompress_size(self): good_decomp_len = len(self.decomp) self.unpacked.decomp_len = -1 self.assertRaises(ValueError, read_zlib_chunks, self.read, self.unpacked) self.unpacked.decomp_len = good_decomp_len - 1 self.assertRaises(zlib.error, read_zlib_chunks, self.read, self.unpacked) self.unpacked.decomp_len = good_decomp_len + 1 self.assertRaises(zlib.error, read_zlib_chunks, self.read, self.unpacked) def test_decompress_truncated(self): read = BytesIO(self.comp[:10]).read self.assertRaises(zlib.error, read_zlib_chunks, read, self.unpacked) read = BytesIO(self.comp).read self.assertRaises(zlib.error, read_zlib_chunks, read, self.unpacked) def test_decompress_empty(self): unpacked = UnpackedObject(Tree.type_num, None, 0, None) comp = zlib.compress(b'') read = BytesIO(comp + self.extra).read unused = read_zlib_chunks(read, unpacked) self.assertEqual(b'', b''.join(unpacked.decomp_chunks)) self.assertNotEqual(b'', unused) self.assertEqual(self.extra, unused + read()) def test_decompress_no_crc32(self): self.unpacked.crc32 = None read_zlib_chunks(self.read, self.unpacked) self.assertEqual(None, self.unpacked.crc32) def _do_decompress_test(self, buffer_size, **kwargs): unused = read_zlib_chunks(self.read, self.unpacked, buffer_size=buffer_size, **kwargs) self.assertEqual(self.decomp, b''.join(self.unpacked.decomp_chunks)) self.assertEqual(zlib.crc32(self.comp), self.unpacked.crc32) self.assertNotEqual(b'', unused) self.assertEqual(self.extra, unused + self.read()) def test_simple_decompress(self): self._do_decompress_test(4096) self.assertEqual(None, self.unpacked.comp_chunks) # These buffer sizes are not intended to be realistic, but rather simulate # larger buffer sizes that may end at various places. def test_decompress_buffer_size_1(self): self._do_decompress_test(1) def test_decompress_buffer_size_2(self): self._do_decompress_test(2) def test_decompress_buffer_size_3(self): self._do_decompress_test(3) def test_decompress_buffer_size_4(self): self._do_decompress_test(4) def test_decompress_include_comp(self): self._do_decompress_test(4096, include_comp=True) self.assertEqual(self.comp, b''.join(self.unpacked.comp_chunks)) class DeltifyTests(TestCase): def test_empty(self): self.assertEqual([], list(deltify_pack_objects([]))) def test_single(self): b = Blob.from_string(b"foo") self.assertEqual( [(b.type_num, b.sha().digest(), None, b.as_raw_string())], list(deltify_pack_objects([(b, b"")]))) def test_simple_delta(self): b1 = Blob.from_string(b"a" * 101) b2 = Blob.from_string(b"a" * 100) delta = create_delta(b1.as_raw_string(), b2.as_raw_string()) self.assertEqual([ (b1.type_num, b1.sha().digest(), None, b1.as_raw_string()), (b2.type_num, b2.sha().digest(), b1.sha().digest(), delta) ], list(deltify_pack_objects([(b1, b""), (b2, b"")]))) class TestPackStreamReader(TestCase): def test_read_objects_emtpy(self): f = BytesIO() build_pack(f, []) reader = PackStreamReader(f.read) self.assertEqual(0, len(list(reader.read_objects()))) def test_read_objects(self): f = BytesIO() entries = build_pack(f, [ (Blob.type_num, b'blob'), (OFS_DELTA, (0, b'blob1')), ]) reader = PackStreamReader(f.read) objects = list(reader.read_objects(compute_crc32=True)) self.assertEqual(2, len(objects)) unpacked_blob, unpacked_delta = objects self.assertEqual(entries[0][0], unpacked_blob.offset) self.assertEqual(Blob.type_num, unpacked_blob.pack_type_num) self.assertEqual(Blob.type_num, unpacked_blob.obj_type_num) self.assertEqual(None, unpacked_blob.delta_base) self.assertEqual(b'blob', b''.join(unpacked_blob.decomp_chunks)) self.assertEqual(entries[0][4], unpacked_blob.crc32) self.assertEqual(entries[1][0], unpacked_delta.offset) self.assertEqual(OFS_DELTA, unpacked_delta.pack_type_num) self.assertEqual(None, unpacked_delta.obj_type_num) self.assertEqual(unpacked_delta.offset - unpacked_blob.offset, unpacked_delta.delta_base) delta = create_delta(b'blob', b'blob1') self.assertEqual(delta, b''.join(unpacked_delta.decomp_chunks)) self.assertEqual(entries[1][4], unpacked_delta.crc32) def test_read_objects_buffered(self): f = BytesIO() build_pack(f, [ (Blob.type_num, b'blob'), (OFS_DELTA, (0, b'blob1')), ]) reader = PackStreamReader(f.read, zlib_bufsize=4) self.assertEqual(2, len(list(reader.read_objects()))) def test_read_objects_empty(self): reader = PackStreamReader(BytesIO().read) self.assertEqual([], list(reader.read_objects())) class TestPackIterator(DeltaChainIterator): _compute_crc32 = True def __init__(self, *args, **kwargs): super(TestPackIterator, self).__init__(*args, **kwargs) self._unpacked_offsets = set() def _result(self, unpacked): """Return entries in the same format as build_pack.""" return (unpacked.offset, unpacked.obj_type_num, b''.join(unpacked.obj_chunks), unpacked.sha(), unpacked.crc32) def _resolve_object(self, offset, pack_type_num, base_chunks): assert offset not in self._unpacked_offsets, ( 'Attempted to re-inflate offset %i' % offset) self._unpacked_offsets.add(offset) return super(TestPackIterator, self)._resolve_object( offset, pack_type_num, base_chunks) class DeltaChainIteratorTests(TestCase): def setUp(self): super(DeltaChainIteratorTests, self).setUp() self.store = MemoryObjectStore() self.fetched = set() def store_blobs(self, blobs_data): blobs = [] for data in blobs_data: blob = make_object(Blob, data=data) blobs.append(blob) self.store.add_object(blob) return blobs def get_raw_no_repeat(self, bin_sha): """Wrapper around store.get_raw that doesn't allow repeat lookups.""" hex_sha = sha_to_hex(bin_sha) self.assertFalse(hex_sha in self.fetched, 'Attempted to re-fetch object %s' % hex_sha) self.fetched.add(hex_sha) return self.store.get_raw(hex_sha) def make_pack_iter(self, f, thin=None): if thin is None: thin = bool(list(self.store)) resolve_ext_ref = thin and self.get_raw_no_repeat or None data = PackData('test.pack', file=f) return TestPackIterator.for_pack_data( data, resolve_ext_ref=resolve_ext_ref) def assertEntriesMatch(self, expected_indexes, entries, pack_iter): expected = [entries[i] for i in expected_indexes] self.assertEqual(expected, list(pack_iter._walk_all_chains())) def test_no_deltas(self): f = BytesIO() entries = build_pack(f, [ (Commit.type_num, b'commit'), (Blob.type_num, b'blob'), (Tree.type_num, b'tree'), ]) self.assertEntriesMatch([0, 1, 2], entries, self.make_pack_iter(f)) def test_ofs_deltas(self): f = BytesIO() entries = build_pack(f, [ (Blob.type_num, b'blob'), (OFS_DELTA, (0, b'blob1')), (OFS_DELTA, (0, b'blob2')), ]) self.assertEntriesMatch([0, 1, 2], entries, self.make_pack_iter(f)) def test_ofs_deltas_chain(self): f = BytesIO() entries = build_pack(f, [ (Blob.type_num, b'blob'), (OFS_DELTA, (0, b'blob1')), (OFS_DELTA, (1, b'blob2')), ]) self.assertEntriesMatch([0, 1, 2], entries, self.make_pack_iter(f)) def test_ref_deltas(self): f = BytesIO() entries = build_pack(f, [ (REF_DELTA, (1, b'blob1')), (Blob.type_num, (b'blob')), (REF_DELTA, (1, b'blob2')), ]) self.assertEntriesMatch([1, 0, 2], entries, self.make_pack_iter(f)) def test_ref_deltas_chain(self): f = BytesIO() entries = build_pack(f, [ (REF_DELTA, (2, b'blob1')), (Blob.type_num, (b'blob')), (REF_DELTA, (1, b'blob2')), ]) self.assertEntriesMatch([1, 2, 0], entries, self.make_pack_iter(f)) def test_ofs_and_ref_deltas(self): # Deltas pending on this offset are popped before deltas depending on # this ref. f = BytesIO() entries = build_pack(f, [ (REF_DELTA, (1, b'blob1')), (Blob.type_num, (b'blob')), (OFS_DELTA, (1, b'blob2')), ]) self.assertEntriesMatch([1, 2, 0], entries, self.make_pack_iter(f)) def test_mixed_chain(self): f = BytesIO() entries = build_pack(f, [ (Blob.type_num, b'blob'), (REF_DELTA, (2, b'blob2')), (OFS_DELTA, (0, b'blob1')), (OFS_DELTA, (1, b'blob3')), (OFS_DELTA, (0, b'bob')), ]) self.assertEntriesMatch([0, 2, 4, 1, 3], entries, self.make_pack_iter(f)) def test_long_chain(self): n = 100 objects_spec = [(Blob.type_num, b'blob')] for i in range(n): objects_spec.append( (OFS_DELTA, (i, b'blob' + str(i).encode('ascii')))) f = BytesIO() entries = build_pack(f, objects_spec) self.assertEntriesMatch(range(n + 1), entries, self.make_pack_iter(f)) def test_branchy_chain(self): n = 100 objects_spec = [(Blob.type_num, b'blob')] for i in range(n): objects_spec.append( (OFS_DELTA, (0, b'blob' + str(i).encode('ascii')))) f = BytesIO() entries = build_pack(f, objects_spec) self.assertEntriesMatch(range(n + 1), entries, self.make_pack_iter(f)) def test_ext_ref(self): blob, = self.store_blobs([b'blob']) f = BytesIO() entries = build_pack(f, [(REF_DELTA, (blob.id, b'blob1'))], store=self.store) pack_iter = self.make_pack_iter(f) self.assertEntriesMatch([0], entries, pack_iter) self.assertEqual([hex_to_sha(blob.id)], pack_iter.ext_refs()) def test_ext_ref_chain(self): blob, = self.store_blobs([b'blob']) f = BytesIO() entries = build_pack(f, [ (REF_DELTA, (1, b'blob2')), (REF_DELTA, (blob.id, b'blob1')), ], store=self.store) pack_iter = self.make_pack_iter(f) self.assertEntriesMatch([1, 0], entries, pack_iter) self.assertEqual([hex_to_sha(blob.id)], pack_iter.ext_refs()) def test_ext_ref_chain_degenerate(self): # Test a degenerate case where the sender is sending a REF_DELTA # object that expands to an object already in the repository. blob, = self.store_blobs([b'blob']) blob2, = self.store_blobs([b'blob2']) assert blob.id < blob2.id f = BytesIO() entries = build_pack(f, [ (REF_DELTA, (blob.id, b'blob2')), (REF_DELTA, (0, b'blob3')), ], store=self.store) pack_iter = self.make_pack_iter(f) self.assertEntriesMatch([0, 1], entries, pack_iter) self.assertEqual([hex_to_sha(blob.id)], pack_iter.ext_refs()) def test_ext_ref_multiple_times(self): blob, = self.store_blobs([b'blob']) f = BytesIO() entries = build_pack(f, [ (REF_DELTA, (blob.id, b'blob1')), (REF_DELTA, (blob.id, b'blob2')), ], store=self.store) pack_iter = self.make_pack_iter(f) self.assertEntriesMatch([0, 1], entries, pack_iter) self.assertEqual([hex_to_sha(blob.id)], pack_iter.ext_refs()) def test_multiple_ext_refs(self): b1, b2 = self.store_blobs([b'foo', b'bar']) f = BytesIO() entries = build_pack(f, [ (REF_DELTA, (b1.id, b'foo1')), (REF_DELTA, (b2.id, b'bar2')), ], store=self.store) pack_iter = self.make_pack_iter(f) self.assertEntriesMatch([0, 1], entries, pack_iter) self.assertEqual([hex_to_sha(b1.id), hex_to_sha(b2.id)], pack_iter.ext_refs()) def test_bad_ext_ref_non_thin_pack(self): blob, = self.store_blobs([b'blob']) f = BytesIO() build_pack(f, [(REF_DELTA, (blob.id, b'blob1'))], store=self.store) pack_iter = self.make_pack_iter(f, thin=False) try: list(pack_iter._walk_all_chains()) self.fail() except KeyError as e: self.assertEqual(([blob.id],), e.args) def test_bad_ext_ref_thin_pack(self): b1, b2, b3 = self.store_blobs([b'foo', b'bar', b'baz']) f = BytesIO() build_pack(f, [ (REF_DELTA, (1, b'foo99')), (REF_DELTA, (b1.id, b'foo1')), (REF_DELTA, (b2.id, b'bar2')), (REF_DELTA, (b3.id, b'baz3')), ], store=self.store) del self.store[b2.id] del self.store[b3.id] pack_iter = self.make_pack_iter(f) try: list(pack_iter._walk_all_chains()) self.fail() except KeyError as e: self.assertEqual((sorted([b2.id, b3.id]),), (sorted(e.args[0]),)) class DeltaEncodeSizeTests(TestCase): def test_basic(self): self.assertEqual(b'\x00', _delta_encode_size(0)) self.assertEqual(b'\x01', _delta_encode_size(1)) self.assertEqual(b'\xfa\x01', _delta_encode_size(250)) self.assertEqual(b'\xe8\x07', _delta_encode_size(1000)) self.assertEqual(b'\xa0\x8d\x06', _delta_encode_size(100000)) class EncodeCopyOperationTests(TestCase): def test_basic(self): self.assertEqual(b'\x80', _encode_copy_operation(0, 0)) self.assertEqual(b'\x91\x01\x0a', _encode_copy_operation(1, 10)) self.assertEqual(b'\xb1\x64\xe8\x03', _encode_copy_operation(100, 1000)) self.assertEqual(b'\x93\xe8\x03\x01', _encode_copy_operation(1000, 1)) diff --git a/dulwich/tests/test_patch.py b/dulwich/tests/test_patch.py index 2a4b0705..982623fd 100644 --- a/dulwich/tests/test_patch.py +++ b/dulwich/tests/test_patch.py @@ -1,539 +1,539 @@ # test_patch.py -- tests for patch.py # Copyright (C) 2010 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 patch.py.""" from io import BytesIO, StringIO from dulwich.objects import ( Blob, Commit, S_IFGITLINK, Tree, ) from dulwich.object_store import ( MemoryObjectStore, ) from dulwich.patch import ( git_am_patch_split, write_blob_diff, write_commit_patch, write_object_diff, write_tree_diff, ) from dulwich.tests import ( SkipTest, TestCase, ) class WriteCommitPatchTests(TestCase): def test_simple_bytesio(self): f = BytesIO() c = Commit() c.committer = c.author = b"Jelmer " c.commit_time = c.author_time = 1271350201 c.commit_timezone = c.author_timezone = 0 c.message = b"This is the first line\nAnd this is the second line.\n" c.tree = Tree().id write_commit_patch(f, c, b"CONTENTS", (1, 1), version="custom") f.seek(0) lines = f.readlines() self.assertTrue(lines[0].startswith( b"From 0b0d34d1b5b596c928adc9a727a4b9e03d025298")) self.assertEqual(lines[1], b"From: Jelmer \n") self.assertTrue(lines[2].startswith(b"Date: ")) self.assertEqual([ b"Subject: [PATCH 1/1] This is the first line\n", b"And this is the second line.\n", b"\n", b"\n", b"---\n"], lines[3:8]) self.assertEqual([ b"CONTENTS-- \n", b"custom\n"], lines[-2:]) if len(lines) >= 12: # diffstat may not be present self.assertEqual(lines[8], b" 0 files changed\n") class ReadGitAmPatch(TestCase): def test_extract_string(self): text = b"""\ From ff643aae102d8870cac88e8f007e70f58f3a7363 Mon Sep 17 00:00:00 2001 From: Jelmer Vernooij Date: Thu, 15 Apr 2010 15:40:28 +0200 Subject: [PATCH 1/2] Remove executable bit from prey.ico (triggers a warning). --- pixmaps/prey.ico | Bin 9662 -> 9662 bytes 1 files changed, 0 insertions(+), 0 deletions(-) mode change 100755 => 100644 pixmaps/prey.ico -- 1.7.0.4 """ # noqa: W291 c, diff, version = git_am_patch_split( StringIO(text.decode("utf-8")), "utf-8") self.assertEqual(b"Jelmer Vernooij ", c.committer) self.assertEqual(b"Jelmer Vernooij ", c.author) self.assertEqual(b"Remove executable bit from prey.ico " b"(triggers a warning).\n", c.message) self.assertEqual(b""" pixmaps/prey.ico | Bin 9662 -> 9662 bytes 1 files changed, 0 insertions(+), 0 deletions(-) mode change 100755 => 100644 pixmaps/prey.ico """, diff) self.assertEqual(b"1.7.0.4", version) def test_extract_bytes(self): text = b"""\ From ff643aae102d8870cac88e8f007e70f58f3a7363 Mon Sep 17 00:00:00 2001 From: Jelmer Vernooij Date: Thu, 15 Apr 2010 15:40:28 +0200 Subject: [PATCH 1/2] Remove executable bit from prey.ico (triggers a warning). --- pixmaps/prey.ico | Bin 9662 -> 9662 bytes 1 files changed, 0 insertions(+), 0 deletions(-) mode change 100755 => 100644 pixmaps/prey.ico -- 1.7.0.4 """ # noqa: W291 c, diff, version = git_am_patch_split(BytesIO(text)) self.assertEqual(b"Jelmer Vernooij ", c.committer) self.assertEqual(b"Jelmer Vernooij ", c.author) self.assertEqual(b"Remove executable bit from prey.ico " b"(triggers a warning).\n", c.message) self.assertEqual(b""" pixmaps/prey.ico | Bin 9662 -> 9662 bytes 1 files changed, 0 insertions(+), 0 deletions(-) mode change 100755 => 100644 pixmaps/prey.ico """, diff) self.assertEqual(b"1.7.0.4", version) def test_extract_spaces(self): text = b"""From ff643aae102d8870cac88e8f007e70f58f3a7363 Mon Sep 17 00:00:00 2001 From: Jelmer Vernooij Date: Thu, 15 Apr 2010 15:40:28 +0200 Subject: [Dulwich-users] [PATCH] Added unit tests for dulwich.object_store.tree_lookup_path. * dulwich/tests/test_object_store.py (TreeLookupPathTests): This test case contains a few tests that ensure the tree_lookup_path function works as expected. --- pixmaps/prey.ico | Bin 9662 -> 9662 bytes 1 files changed, 0 insertions(+), 0 deletions(-) mode change 100755 => 100644 pixmaps/prey.ico -- 1.7.0.4 """ # noqa: W291 c, diff, version = git_am_patch_split(BytesIO(text), "utf-8") self.assertEqual(b'''\ Added unit tests for dulwich.object_store.tree_lookup_path. * dulwich/tests/test_object_store.py (TreeLookupPathTests): This test case contains a few tests that ensure the tree_lookup_path function works as expected. ''', c.message) def test_extract_pseudo_from_header(self): text = b"""From ff643aae102d8870cac88e8f007e70f58f3a7363 Mon Sep 17 00:00:00 2001 From: Jelmer Vernooij Date: Thu, 15 Apr 2010 15:40:28 +0200 Subject: [Dulwich-users] [PATCH] Added unit tests for dulwich.object_store.tree_lookup_path. -From: Jelmer Vernooy +From: Jelmer Vernooij * dulwich/tests/test_object_store.py (TreeLookupPathTests): This test case contains a few tests that ensure the tree_lookup_path function works as expected. --- pixmaps/prey.ico | Bin 9662 -> 9662 bytes 1 files changed, 0 insertions(+), 0 deletions(-) mode change 100755 => 100644 pixmaps/prey.ico -- 1.7.0.4 """ # noqa: W291 c, diff, version = git_am_patch_split(BytesIO(text), "utf-8") - self.assertEqual(b"Jelmer Vernooy ", c.author) + self.assertEqual(b"Jelmer Vernooij ", c.author) self.assertEqual(b'''\ Added unit tests for dulwich.object_store.tree_lookup_path. * dulwich/tests/test_object_store.py (TreeLookupPathTests): This test case contains a few tests that ensure the tree_lookup_path function works as expected. ''', c.message) def test_extract_no_version_tail(self): text = b"""\ From ff643aae102d8870cac88e8f007e70f58f3a7363 Mon Sep 17 00:00:00 2001 From: Jelmer Vernooij Date: Thu, 15 Apr 2010 15:40:28 +0200 Subject: [Dulwich-users] [PATCH] Added unit tests for dulwich.object_store.tree_lookup_path. -From: Jelmer Vernooy +From: Jelmer Vernooij --- pixmaps/prey.ico | Bin 9662 -> 9662 bytes 1 files changed, 0 insertions(+), 0 deletions(-) mode change 100755 => 100644 pixmaps/prey.ico """ c, diff, version = git_am_patch_split(BytesIO(text), "utf-8") self.assertEqual(None, version) def test_extract_mercurial(self): raise SkipTest( "git_am_patch_split doesn't handle Mercurial patches " "properly yet") expected_diff = """\ diff --git a/dulwich/tests/test_patch.py b/dulwich/tests/test_patch.py --- a/dulwich/tests/test_patch.py +++ b/dulwich/tests/test_patch.py @@ -158,7 +158,7 @@ ''' c, diff, version = git_am_patch_split(BytesIO(text)) - self.assertIs(None, version) + self.assertEqual(None, version) class DiffTests(TestCase): """ # noqa: W291,W293 text = """\ From dulwich-users-bounces+jelmer=samba.org@lists.launchpad.net \ Mon Nov 29 00:58:18 2010 Date: Sun, 28 Nov 2010 17:57:27 -0600 From: Augie Fackler To: dulwich-users Subject: [Dulwich-users] [PATCH] test_patch: fix tests on Python 2.6 Content-Transfer-Encoding: 8bit Change-Id: I5e51313d4ae3a65c3f00c665002a7489121bb0d6 %s _______________________________________________ Mailing list: https://launchpad.net/~dulwich-users Post to : dulwich-users@lists.launchpad.net Unsubscribe : https://launchpad.net/~dulwich-users More help : https://help.launchpad.net/ListHelp """ % expected_diff # noqa: W291 c, diff, version = git_am_patch_split(BytesIO(text)) self.assertEqual(expected_diff, diff) self.assertEqual(None, version) class DiffTests(TestCase): """Tests for write_blob_diff and write_tree_diff.""" def test_blob_diff(self): f = BytesIO() write_blob_diff( f, (b"foo.txt", 0o644, Blob.from_string(b"old\nsame\n")), (b"bar.txt", 0o644, Blob.from_string(b"new\nsame\n"))) self.assertEqual([ b"diff --git a/foo.txt b/bar.txt", b"index 3b0f961..a116b51 644", b"--- a/foo.txt", b"+++ b/bar.txt", b"@@ -1,2 +1,2 @@", b"-old", b"+new", b" same" ], f.getvalue().splitlines()) def test_blob_add(self): f = BytesIO() write_blob_diff( f, (None, None, None), (b"bar.txt", 0o644, Blob.from_string(b"new\nsame\n"))) self.assertEqual([ b'diff --git /dev/null b/bar.txt', b'new mode 644', b'index 0000000..a116b51 644', b'--- /dev/null', b'+++ b/bar.txt', b'@@ -0,0 +1,2 @@', b'+new', b'+same' ], f.getvalue().splitlines()) def test_blob_remove(self): f = BytesIO() write_blob_diff( f, (b"bar.txt", 0o644, Blob.from_string(b"new\nsame\n")), (None, None, None)) self.assertEqual([ b'diff --git a/bar.txt /dev/null', b'deleted mode 644', b'index a116b51..0000000', b'--- a/bar.txt', b'+++ /dev/null', b'@@ -1,2 +0,0 @@', b'-new', b'-same' ], f.getvalue().splitlines()) def test_tree_diff(self): f = BytesIO() store = MemoryObjectStore() added = Blob.from_string(b"add\n") removed = Blob.from_string(b"removed\n") changed1 = Blob.from_string(b"unchanged\nremoved\n") changed2 = Blob.from_string(b"unchanged\nadded\n") unchanged = Blob.from_string(b"unchanged\n") tree1 = Tree() tree1.add(b"removed.txt", 0o644, removed.id) tree1.add(b"changed.txt", 0o644, changed1.id) tree1.add(b"unchanged.txt", 0o644, changed1.id) tree2 = Tree() tree2.add(b"added.txt", 0o644, added.id) tree2.add(b"changed.txt", 0o644, changed2.id) tree2.add(b"unchanged.txt", 0o644, changed1.id) store.add_objects([(o, None) for o in [ tree1, tree2, added, removed, changed1, changed2, unchanged]]) write_tree_diff(f, store, tree1.id, tree2.id) self.assertEqual([ b'diff --git /dev/null b/added.txt', b'new mode 644', b'index 0000000..76d4bb8 644', b'--- /dev/null', b'+++ b/added.txt', b'@@ -0,0 +1 @@', b'+add', b'diff --git a/changed.txt b/changed.txt', b'index bf84e48..1be2436 644', b'--- a/changed.txt', b'+++ b/changed.txt', b'@@ -1,2 +1,2 @@', b' unchanged', b'-removed', b'+added', b'diff --git a/removed.txt /dev/null', b'deleted mode 644', b'index 2c3f0b3..0000000', b'--- a/removed.txt', b'+++ /dev/null', b'@@ -1 +0,0 @@', b'-removed', ], f.getvalue().splitlines()) def test_tree_diff_submodule(self): f = BytesIO() store = MemoryObjectStore() tree1 = Tree() tree1.add(b"asubmodule", S_IFGITLINK, b"06d0bdd9e2e20377b3180e4986b14c8549b393e4") tree2 = Tree() tree2.add(b"asubmodule", S_IFGITLINK, b"cc975646af69f279396d4d5e1379ac6af80ee637") store.add_objects([(o, None) for o in [tree1, tree2]]) write_tree_diff(f, store, tree1.id, tree2.id) self.assertEqual([ b'diff --git a/asubmodule b/asubmodule', b'index 06d0bdd..cc97564 160000', b'--- a/asubmodule', b'+++ b/asubmodule', b'@@ -1 +1 @@', b'-Submodule commit 06d0bdd9e2e20377b3180e4986b14c8549b393e4', b'+Submodule commit cc975646af69f279396d4d5e1379ac6af80ee637', ], f.getvalue().splitlines()) def test_object_diff_blob(self): f = BytesIO() b1 = Blob.from_string(b"old\nsame\n") b2 = Blob.from_string(b"new\nsame\n") store = MemoryObjectStore() store.add_objects([(b1, None), (b2, None)]) write_object_diff(f, store, (b"foo.txt", 0o644, b1.id), (b"bar.txt", 0o644, b2.id)) self.assertEqual([ b"diff --git a/foo.txt b/bar.txt", b"index 3b0f961..a116b51 644", b"--- a/foo.txt", b"+++ b/bar.txt", b"@@ -1,2 +1,2 @@", b"-old", b"+new", b" same" ], f.getvalue().splitlines()) def test_object_diff_add_blob(self): f = BytesIO() store = MemoryObjectStore() b2 = Blob.from_string(b"new\nsame\n") store.add_object(b2) write_object_diff(f, store, (None, None, None), (b"bar.txt", 0o644, b2.id)) self.assertEqual([ b'diff --git /dev/null b/bar.txt', b'new mode 644', b'index 0000000..a116b51 644', b'--- /dev/null', b'+++ b/bar.txt', b'@@ -0,0 +1,2 @@', b'+new', b'+same' ], f.getvalue().splitlines()) def test_object_diff_remove_blob(self): f = BytesIO() b1 = Blob.from_string(b"new\nsame\n") store = MemoryObjectStore() store.add_object(b1) write_object_diff(f, store, (b"bar.txt", 0o644, b1.id), (None, None, None)) self.assertEqual([ b'diff --git a/bar.txt /dev/null', b'deleted mode 644', b'index a116b51..0000000', b'--- a/bar.txt', b'+++ /dev/null', b'@@ -1,2 +0,0 @@', b'-new', b'-same' ], f.getvalue().splitlines()) def test_object_diff_bin_blob_force(self): f = BytesIO() # Prepare two slightly different PNG headers b1 = Blob.from_string( b"\x89\x50\x4e\x47\x0d\x0a\x1a\x0a" b"\x00\x00\x00\x0d\x49\x48\x44\x52" b"\x00\x00\x01\xd5\x00\x00\x00\x9f" b"\x08\x04\x00\x00\x00\x05\x04\x8b") b2 = Blob.from_string( b"\x89\x50\x4e\x47\x0d\x0a\x1a\x0a" b"\x00\x00\x00\x0d\x49\x48\x44\x52" b"\x00\x00\x01\xd5\x00\x00\x00\x9f" b"\x08\x03\x00\x00\x00\x98\xd3\xb3") store = MemoryObjectStore() store.add_objects([(b1, None), (b2, None)]) write_object_diff( f, store, (b'foo.png', 0o644, b1.id), (b'bar.png', 0o644, b2.id), diff_binary=True) self.assertEqual([ b'diff --git a/foo.png b/bar.png', b'index f73e47d..06364b7 644', b'--- a/foo.png', b'+++ b/bar.png', b'@@ -1,4 +1,4 @@', b' \x89PNG', b' \x1a', b' \x00\x00\x00', b'-IHDR\x00\x00\x01\xd5\x00\x00\x00' b'\x9f\x08\x04\x00\x00\x00\x05\x04\x8b', b'\\ No newline at end of file', b'+IHDR\x00\x00\x01\xd5\x00\x00\x00\x9f' b'\x08\x03\x00\x00\x00\x98\xd3\xb3', b'\\ No newline at end of file' ], f.getvalue().splitlines()) def test_object_diff_bin_blob(self): f = BytesIO() # Prepare two slightly different PNG headers b1 = Blob.from_string( b"\x89\x50\x4e\x47\x0d\x0a\x1a\x0a" b"\x00\x00\x00\x0d\x49\x48\x44\x52" b"\x00\x00\x01\xd5\x00\x00\x00\x9f" b"\x08\x04\x00\x00\x00\x05\x04\x8b") b2 = Blob.from_string( b"\x89\x50\x4e\x47\x0d\x0a\x1a\x0a" b"\x00\x00\x00\x0d\x49\x48\x44\x52" b"\x00\x00\x01\xd5\x00\x00\x00\x9f" b"\x08\x03\x00\x00\x00\x98\xd3\xb3") store = MemoryObjectStore() store.add_objects([(b1, None), (b2, None)]) write_object_diff(f, store, (b'foo.png', 0o644, b1.id), (b'bar.png', 0o644, b2.id)) self.assertEqual([ b'diff --git a/foo.png b/bar.png', b'index f73e47d..06364b7 644', b'Binary files a/foo.png and b/bar.png differ' ], f.getvalue().splitlines()) def test_object_diff_add_bin_blob(self): f = BytesIO() b2 = Blob.from_string( b'\x89\x50\x4e\x47\x0d\x0a\x1a\x0a' b'\x00\x00\x00\x0d\x49\x48\x44\x52' b'\x00\x00\x01\xd5\x00\x00\x00\x9f' b'\x08\x03\x00\x00\x00\x98\xd3\xb3') store = MemoryObjectStore() store.add_object(b2) write_object_diff(f, store, (None, None, None), (b'bar.png', 0o644, b2.id)) self.assertEqual([ b'diff --git /dev/null b/bar.png', b'new mode 644', b'index 0000000..06364b7 644', b'Binary files /dev/null and b/bar.png differ' ], f.getvalue().splitlines()) def test_object_diff_remove_bin_blob(self): f = BytesIO() b1 = Blob.from_string( b'\x89\x50\x4e\x47\x0d\x0a\x1a\x0a' b'\x00\x00\x00\x0d\x49\x48\x44\x52' b'\x00\x00\x01\xd5\x00\x00\x00\x9f' b'\x08\x04\x00\x00\x00\x05\x04\x8b') store = MemoryObjectStore() store.add_object(b1) write_object_diff(f, store, (b'foo.png', 0o644, b1.id), (None, None, None)) self.assertEqual([ b'diff --git a/foo.png /dev/null', b'deleted mode 644', b'index f73e47d..0000000', b'Binary files a/foo.png and /dev/null differ' ], f.getvalue().splitlines()) def test_object_diff_kind_change(self): f = BytesIO() b1 = Blob.from_string(b"new\nsame\n") store = MemoryObjectStore() store.add_object(b1) write_object_diff( f, store, (b"bar.txt", 0o644, b1.id), (b"bar.txt", 0o160000, b"06d0bdd9e2e20377b3180e4986b14c8549b393e4")) self.assertEqual([ b'diff --git a/bar.txt b/bar.txt', b'old mode 644', b'new mode 160000', b'index a116b51..06d0bdd 160000', b'--- a/bar.txt', b'+++ b/bar.txt', b'@@ -1,2 +1 @@', b'-new', b'-same', b'+Submodule commit 06d0bdd9e2e20377b3180e4986b14c8549b393e4', ], f.getvalue().splitlines()) diff --git a/dulwich/tests/test_porcelain.py b/dulwich/tests/test_porcelain.py index aa8587f0..0e77c250 100644 --- a/dulwich/tests/test_porcelain.py +++ b/dulwich/tests/test_porcelain.py @@ -1,1170 +1,1275 @@ # 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 Repo +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() - repo_dir = tempfile.mkdtemp() - self.addCleanup(shutil.rmtree, repo_dir) - self.repo = Repo.init(repo_dir) - - def tearDown(self): - super(PorcelainTestCase, self).tearDown() - self.repo.close() + 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.assertEqual(r.path, target_path) target_repo = Repo(target_path) - self.assertEqual(target_repo.head(), c3.id) + 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: - self.assertRaises(KeyError, r.head) + 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() 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') + 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') + 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') + 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'', committer=b'') + 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'', committer=b'') + 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'', committer=b'') + 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') + 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') + 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(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'', committer=b'') + 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_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'', committer=b'') + 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'', committer=b'') + 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'', committer=b'') + 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'', committer=b'', + 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'00919e65bdcf4a22cdd4f3700604a275cd2aaf146b23 HEAD\x00 report-status ' # noqa: E501 + 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'003f9e65bdcf4a22cdd4f3700604a275cd2aaf146b23 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') + 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') + 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) + porcelain.fetch(target_path, self.repo.path, + outstream=outstream, errstream=errstream) # 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) + + # 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) + 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'', committer=b'') + 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'', committer=b'') + 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') 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'', committer=b'') + author=b'author ', + committer=b'committer ') self.assertEqual({ b'refs/heads/master': cid, b'HEAD': cid}, porcelain.ls_remote(self.repo.path)) 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") 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") self.assertEqual( ['foo'], list(porcelain.check_ignore(self.repo, ['foo']))) self.assertEqual([], list(porcelain.check_ignore(self.repo, ['bar']))) def test_check_added(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") self.assertEqual( [], list(porcelain.check_ignore(self.repo, ['foo']))) self.assertEqual( ['foo'], list(porcelain.check_ignore(self.repo, ['foo'], no_index=True))) 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('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')) diff --git a/dulwich/tests/test_refs.py b/dulwich/tests/test_refs.py index 517102be..2ec94444 100644 --- a/dulwich/tests/test_refs.py +++ b/dulwich/tests/test_refs.py @@ -1,554 +1,579 @@ # 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, 'refs', 'some', 'ref'), 'rb') self.assertEqual(b'42d06bd4b77fed026b154d16493e5deab78f02ec', f.read()[:40]) f.close() 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, '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, 'refs', 'heads', '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, 'refs', 'heads', 'master.lock'))) self.assertFalse(os.path.exists( os.path.join(self._refs.path, '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, 'refs', 'heads', '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, '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, 'refs', 'heads', 'master.lock'))) self.assertFalse(os.path.exists( os.path.join(self._refs.path, '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_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_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, 'refs', 'tags', u'schön') 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()) _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 3b361be0..7f04128b 100644 --- a/dulwich/tests/test_repository.py +++ b/dulwich/tests/test_repository.py @@ -1,929 +1,947 @@ # -*- 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_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_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_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_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_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): + 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): + 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/dulwich/web.py b/dulwich/web.py index 8563f038..ef3686bb 100644 --- a/dulwich/web.py +++ b/dulwich/web.py @@ -1,513 +1,510 @@ # web.py -- WSGI smart-http server # Copyright (C) 2010 Google, Inc. # Copyright (C) 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. # """HTTP server for dulwich that implements the git smart HTTP protocol.""" from io import BytesIO import shutil import tempfile import gzip import os import re import sys import time from wsgiref.simple_server import ( WSGIRequestHandler, ServerHandler, WSGIServer, make_server, ) try: from urlparse import parse_qs except ImportError: from urllib.parse import parse_qs from dulwich import log_utils from dulwich.protocol import ( ReceivableProtocol, ) from dulwich.repo import ( Repo, ) from dulwich.server import ( DictBackend, DEFAULT_HANDLERS, generate_info_refs, generate_objects_info_packs, ) logger = log_utils.getLogger(__name__) # HTTP error strings HTTP_OK = '200 OK' HTTP_NOT_FOUND = '404 Not Found' HTTP_FORBIDDEN = '403 Forbidden' HTTP_ERROR = '500 Internal Server Error' def date_time_string(timestamp=None): # From BaseHTTPRequestHandler.date_time_string in BaseHTTPServer.py in the # Python 2.6.5 standard library, following modifications: # - Made a global rather than an instance method. # - weekdayname and monthname are renamed and locals rather than class # variables. # Copyright (c) 2001-2010 Python Software Foundation; All Rights Reserved weekdays = ['Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat', 'Sun'] months = [None, 'Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec'] if timestamp is None: timestamp = time.time() year, month, day, hh, mm, ss, wd, y, z = time.gmtime(timestamp) return '%s, %02d %3s %4d %02d:%02d:%02d GMD' % ( weekdays[wd], day, months[month], year, hh, mm, ss) def url_prefix(mat): """Extract the URL prefix from a regex match. :param mat: A regex match object. :returns: The URL prefix, defined as the text before the match in the original string. Normalized to start with one leading slash and end with zero. """ return '/' + mat.string[:mat.start()].strip('/') def get_repo(backend, mat): """Get a Repo instance for the given backend and URL regex match.""" return backend.open_repository(url_prefix(mat)) def send_file(req, f, content_type): """Send a file-like object to the request output. :param req: The HTTPGitRequest object to send output to. :param f: An open file-like object to send; will be closed. :param content_type: The MIME type for the file. :return: Iterator over the contents of the file, as chunks. """ if f is None: yield req.not_found('File not found') return try: req.respond(HTTP_OK, content_type) while True: data = f.read(10240) if not data: break yield data - f.close() except IOError: - f.close() yield req.error('Error reading file') - except: + finally: f.close() - raise def _url_to_path(url): return url.replace('/', os.path.sep) def get_text_file(req, backend, mat): req.nocache() path = _url_to_path(mat.group()) logger.info('Sending plain text file %s', path) return send_file(req, get_repo(backend, mat).get_named_file(path), 'text/plain') def get_loose_object(req, backend, mat): sha = (mat.group(1) + mat.group(2)).encode('ascii') logger.info('Sending loose object %s', sha) object_store = get_repo(backend, mat).object_store if not object_store.contains_loose(sha): yield req.not_found('Object not found') return try: data = object_store[sha].as_legacy_object() except IOError: yield req.error('Error reading object') return req.cache_forever() req.respond(HTTP_OK, 'application/x-git-loose-object') yield data def get_pack_file(req, backend, mat): req.cache_forever() path = _url_to_path(mat.group()) logger.info('Sending pack file %s', path) return send_file(req, get_repo(backend, mat).get_named_file(path), 'application/x-git-packed-objects') def get_idx_file(req, backend, mat): req.cache_forever() path = _url_to_path(mat.group()) logger.info('Sending pack file %s', path) return send_file(req, get_repo(backend, mat).get_named_file(path), 'application/x-git-packed-objects-toc') def get_info_refs(req, backend, mat): params = parse_qs(req.environ['QUERY_STRING']) service = params.get('service', [None])[0] if service and not req.dumb: handler_cls = req.handlers.get(service.encode('ascii'), None) if handler_cls is None: yield req.forbidden('Unsupported service') return req.nocache() write = req.respond( HTTP_OK, 'application/x-%s-advertisement' % service) proto = ReceivableProtocol(BytesIO().read, write) handler = handler_cls(backend, [url_prefix(mat)], proto, http_req=req, advertise_refs=True) handler.proto.write_pkt_line( b'# service=' + service.encode('ascii') + b'\n') handler.proto.write_pkt_line(None) handler.handle() else: # non-smart fallback # TODO: select_getanyfile() (see http-backend.c) req.nocache() req.respond(HTTP_OK, 'text/plain') logger.info('Emulating dumb info/refs') repo = get_repo(backend, mat) for text in generate_info_refs(repo): yield text def get_info_packs(req, backend, mat): req.nocache() req.respond(HTTP_OK, 'text/plain') logger.info('Emulating dumb info/packs') return generate_objects_info_packs(get_repo(backend, mat)) class _LengthLimitedFile(object): """Wrapper class to limit the length of reads from a file-like object. This is used to ensure EOF is read from the wsgi.input object once Content-Length bytes are read. This behavior is required by the WSGI spec but not implemented in wsgiref as of 2.5. """ def __init__(self, input, max_bytes): self._input = input self._bytes_avail = max_bytes def read(self, size=-1): if self._bytes_avail <= 0: return b'' if size == -1 or size > self._bytes_avail: size = self._bytes_avail self._bytes_avail -= size return self._input.read(size) # TODO: support more methods as necessary def handle_service_request(req, backend, mat): service = mat.group().lstrip('/') logger.info('Handling service request for %s', service) handler_cls = req.handlers.get(service.encode('ascii'), None) if handler_cls is None: yield req.forbidden('Unsupported service') return req.nocache() write = req.respond(HTTP_OK, 'application/x-%s-result' % service) proto = ReceivableProtocol(req.environ['wsgi.input'].read, write) handler = handler_cls(backend, [url_prefix(mat)], proto, http_req=req) handler.handle() class HTTPGitRequest(object): """Class encapsulating the state of a single git HTTP request. :ivar environ: the WSGI environment for the request. """ def __init__(self, environ, start_response, dumb=False, handlers=None): self.environ = environ self.dumb = dumb self.handlers = handlers self._start_response = start_response self._cache_headers = [] self._headers = [] def add_header(self, name, value): """Add a header to the response.""" self._headers.append((name, value)) def respond(self, status=HTTP_OK, content_type=None, headers=None): """Begin a response with the given status and other headers.""" if headers: self._headers.extend(headers) if content_type: self._headers.append(('Content-Type', content_type)) self._headers.extend(self._cache_headers) return self._start_response(status, self._headers) def not_found(self, message): """Begin a HTTP 404 response and return the text of a message.""" self._cache_headers = [] logger.info('Not found: %s', message) self.respond(HTTP_NOT_FOUND, 'text/plain') return message.encode('ascii') def forbidden(self, message): """Begin a HTTP 403 response and return the text of a message.""" self._cache_headers = [] logger.info('Forbidden: %s', message) self.respond(HTTP_FORBIDDEN, 'text/plain') return message.encode('ascii') def error(self, message): """Begin a HTTP 500 response and return the text of a message.""" self._cache_headers = [] logger.error('Error: %s', message) self.respond(HTTP_ERROR, 'text/plain') return message.encode('ascii') def nocache(self): """Set the response to never be cached by the client.""" self._cache_headers = [ ('Expires', 'Fri, 01 Jan 1980 00:00:00 GMT'), ('Pragma', 'no-cache'), ('Cache-Control', 'no-cache, max-age=0, must-revalidate'), ] def cache_forever(self): """Set the response to be cached forever by the client.""" now = time.time() self._cache_headers = [ ('Date', date_time_string(now)), ('Expires', date_time_string(now + 31536000)), ('Cache-Control', 'public, max-age=31536000'), ] class HTTPGitApplication(object): """Class encapsulating the state of a git WSGI application. :ivar backend: the Backend object backing this application """ services = { ('GET', re.compile('/HEAD$')): get_text_file, ('GET', re.compile('/info/refs$')): get_info_refs, ('GET', re.compile('/objects/info/alternates$')): get_text_file, ('GET', re.compile('/objects/info/http-alternates$')): get_text_file, ('GET', re.compile('/objects/info/packs$')): get_info_packs, ('GET', re.compile('/objects/([0-9a-f]{2})/([0-9a-f]{38})$')): get_loose_object, ('GET', re.compile('/objects/pack/pack-([0-9a-f]{40})\\.pack$')): get_pack_file, ('GET', re.compile('/objects/pack/pack-([0-9a-f]{40})\\.idx$')): get_idx_file, ('POST', re.compile('/git-upload-pack$')): handle_service_request, ('POST', re.compile('/git-receive-pack$')): handle_service_request, } def __init__(self, backend, dumb=False, handlers=None, fallback_app=None): self.backend = backend self.dumb = dumb self.handlers = dict(DEFAULT_HANDLERS) self.fallback_app = fallback_app if handlers is not None: self.handlers.update(handlers) def __call__(self, environ, start_response): path = environ['PATH_INFO'] method = environ['REQUEST_METHOD'] req = HTTPGitRequest(environ, start_response, dumb=self.dumb, handlers=self.handlers) # environ['QUERY_STRING'] has qs args handler = None for smethod, spath in self.services.keys(): if smethod != method: continue mat = spath.search(path) if mat: handler = self.services[smethod, spath] break if handler is None: if self.fallback_app is not None: return self.fallback_app(environ, start_response) else: return [req.not_found('Sorry, that method is not supported')] return handler(req, self.backend, mat) class GunzipFilter(object): """WSGI middleware that unzips gzip-encoded requests before passing on to the underlying application. """ def __init__(self, application): self.app = application def __call__(self, environ, start_response): if environ.get('HTTP_CONTENT_ENCODING', '') == 'gzip': try: environ['wsgi.input'].tell() wsgi_input = environ['wsgi.input'] except (AttributeError, IOError, NotImplementedError): # The gzip implementation in the standard library of Python 2.x # requires working '.seek()' and '.tell()' methods on the input # stream. Read the data into a temporary file to work around # this limitation. wsgi_input = tempfile.SpooledTemporaryFile(16 * 1024 * 1024) shutil.copyfileobj(environ['wsgi.input'], wsgi_input) wsgi_input.seek(0) environ['wsgi.input'] = gzip.GzipFile( filename=None, fileobj=wsgi_input, mode='r') del environ['HTTP_CONTENT_ENCODING'] if 'CONTENT_LENGTH' in environ: del environ['CONTENT_LENGTH'] return self.app(environ, start_response) class LimitedInputFilter(object): """WSGI middleware that limits the input length of a request to that specified in Content-Length. """ def __init__(self, application): self.app = application def __call__(self, environ, start_response): # This is not necessary if this app is run from a conforming WSGI # server. Unfortunately, there's no way to tell that at this point. # TODO: git may used HTTP/1.1 chunked encoding instead of specifying # content-length content_length = environ.get('CONTENT_LENGTH', '') if content_length: environ['wsgi.input'] = _LengthLimitedFile( environ['wsgi.input'], int(content_length)) return self.app(environ, start_response) def make_wsgi_chain(*args, **kwargs): """Factory function to create an instance of HTTPGitApplication, correctly wrapped with needed middleware. """ app = HTTPGitApplication(*args, **kwargs) wrapped_app = LimitedInputFilter(GunzipFilter(app)) return wrapped_app class ServerHandlerLogger(ServerHandler): """ServerHandler that uses dulwich's logger for logging exceptions.""" def log_exception(self, exc_info): if sys.version_info < (2, 7): logger.exception('Exception happened during processing of request') else: logger.exception('Exception happened during processing of request', exc_info=exc_info) def log_message(self, format, *args): logger.info(format, *args) def log_error(self, *args): logger.error(*args) class WSGIRequestHandlerLogger(WSGIRequestHandler): """WSGIRequestHandler that uses dulwich's logger for logging exceptions.""" def log_exception(self, exc_info): logger.exception('Exception happened during processing of request', exc_info=exc_info) def log_message(self, format, *args): logger.info(format, *args) def log_error(self, *args): logger.error(*args) def handle(self): """Handle a single HTTP request""" self.raw_requestline = self.rfile.readline() if not self.parse_request(): # An error code has been sent, just exit return handler = ServerHandlerLogger( self.rfile, self.wfile, self.get_stderr(), self.get_environ() ) handler.request_handler = self # backpointer for logging handler.run(self.server.get_app()) class WSGIServerLogger(WSGIServer): def handle_error(self, request, client_address): """Handle an error. """ logger.exception( 'Exception happened during processing of request from %s' % str(client_address)) def main(argv=sys.argv): """Entry point for starting an HTTP 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=8000, help="Port to listen on.") options, args = parser.parse_args(argv) if len(args) > 1: gitdir = args[1] else: gitdir = os.getcwd() log_utils.default_logging_config() backend = DictBackend({'/': Repo(gitdir)}) app = make_wsgi_chain(backend) server = make_server(options.listen_address, options.port, app, handler_class=WSGIRequestHandlerLogger, server_class=WSGIServerLogger) logger.info('Listening for HTTP connections on %s:%d', options.listen_address, options.port) server.serve_forever() if __name__ == '__main__': main() diff --git a/setup.cfg b/setup.cfg index 71afdc0b..a2c4ef84 100644 --- a/setup.cfg +++ b/setup.cfg @@ -1,6 +1 @@ [build_ext] - -[egg_info] -tag_build = -tag_date = 0 - diff --git a/setup.py b/setup.py index c20f9328..5d282059 100755 --- a/setup.py +++ b/setup.py @@ -1,116 +1,128 @@ #!/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 os import sys -dulwich_version_string = '0.18.5' +dulwich_version_string = '0.19.0' 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 l in out.splitlines(): - l = l.decode("utf8") + for line in out.splitlines(): + line = line.decode("utf8") # Also parse only first digit, because 3.2.1 can't be parsed nicely - if l.startswith('Xcode') and int(l.split()[1].split('.')[0]) >= 4: + 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']} + setup_kwargs['install_requires'] = ['urllib3[secure]>=1.21'] + setup_kwargs['include_package_data'] = True + setup_kwargs['test_suite'] = 'dulwich.tests.test_suite' + setup_kwargs['tests_require'] = tests_require + if sys.platform == 'win32': # Win32 setup breaks with non-ascii characters. author = "Jelmer Vernooij" else: author = "Jelmer Vernooij" setup(name='dulwich', description='Python Git Library', keywords='git', version=dulwich_version_string, url='https://www.dulwich.io/', license='Apachev2 or later or GPLv2', author_email='jelmer@jelmer.uk', long_description=""" Python implementation of the Git file formats and protocols, without the need to have git installed. All functionality is available in pure Python. Optional C extensions can be built for improved performance. The project is named after the part of London that Mr. and Mrs. Git live in in the particular Monty Python sketch. """, 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'], 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', ], ext_modules=ext_modules, - test_suite='dulwich.tests.test_suite', - tests_require=tests_require, distclass=DulwichDistribution, - include_package_data=True, + **setup_kwargs )