diff --git a/.gitignore b/.gitignore deleted file mode 100644 index 90a3431c..00000000 --- a/.gitignore +++ /dev/null @@ -1,13 +0,0 @@ -_trial_temp -build -MANIFEST -dist -apidocs -*,cover -.testrepository -*.pyc -*.so -*~ -*.swp -docs/tutorial/index.html -dulwich.egg-info/ diff --git a/.testr.conf b/.testr.conf deleted file mode 100644 index 50438612..00000000 --- a/.testr.conf +++ /dev/null @@ -1,4 +0,0 @@ -[DEFAULT] -test_command=PYTHONPATH=. python -m subunit.run $IDOPTION $LISTOPT dulwich.tests.test_suite -test_id_option=--load-list $IDFILE -test_list_option=--list diff --git a/.travis.yml b/.travis.yml deleted file mode 100644 index 3c7e55fa..00000000 --- a/.travis.yml +++ /dev/null @@ -1,16 +0,0 @@ -language: python -# Workaround to make 2.7 use system site packages, and 2.6 and 3.4 not use system -# site packages. -# https://github.com/travis-ci/travis-ci/issues/2219#issuecomment-41804942 -python: -- "2.6" -- "2.7_with_system_site_packages" -- "3.4" -- "pypy" -script: - - PYTHONHASHSEED=random python setup.py test - - make check-noextensions -install: - - sudo apt-get update - - sudo apt-get install -qq git python-setuptools python-gevent python-fastimport python-mock - - if [[ $TRAVIS_PYTHON_VERSION == 2* ]]; then pip install unittest2; fi diff --git a/AUTHORS b/AUTHORS index 4990cac5..525aacf0 100644 --- a/AUTHORS +++ b/AUTHORS @@ -1,11 +1,11 @@ -Jelmer Vernooij +Jelmer Vernooij James Westby John Carr Dave Borowitz Chris Eberle "milki" Gary van der Merwe Hervé Cauwelier wrote the original tutorial. See the revision history for a full list of contributors. diff --git a/MANIFEST.in b/MANIFEST.in index e997dc07..6aa209b0 100644 --- a/MANIFEST.in +++ b/MANIFEST.in @@ -1,11 +1,15 @@ include NEWS include AUTHORS include README.md include Makefile include COPYING include HACKING +include CONTRIBUTING 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 diff --git a/Makefile b/Makefile index da33c882..a7dc89d7 100644 --- a/Makefile +++ b/Makefile @@ -1,60 +1,64 @@ PYTHON = python PYFLAKES = pyflakes PEP8 = pep8 SETUP = $(PYTHON) setup.py PYDOCTOR ?= pydoctor ifeq ($(shell $(PYTHON) -c "import sys; print(sys.version_info >= (2, 7))"),True) TESTRUNNER ?= unittest else TESTRUNNER ?= unittest2.__main__ endif RUNTEST = PYTHONHASHSEED=random PYTHONPATH=.:$(PYTHONPATH) $(PYTHON) -m $(TESTRUNNER) $(TEST_OPTIONS) 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 before-push: check git diff origin/master | $(PEP8) --diff diff --git a/NEWS b/NEWS index 8c7cec86..f7ba758f 100644 --- a/NEWS +++ b/NEWS @@ -1,1198 +1,1218 @@ -0.10.2 UNRELEASED +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 new file mode 100644 index 00000000..c700355a --- /dev/null +++ b/PKG-INFO @@ -0,0 +1,29 @@ +Metadata-Version: 1.1 +Name: dulwich +Version: 0.11.1 +Summary: Python Git Library +Home-page: https://www.dulwich.io/ +Author: Jelmer Vernooij +Author-email: jelmer@jelmer.uk +License: GPLv2 or later +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 :: GNU General Public License v2 or later (GPLv2+) +Classifier: Programming Language :: Python :: 2.6 +Classifier: Programming Language :: Python :: 2.7 +Classifier: Programming Language :: Python :: 3.4 +Classifier: Programming Language :: Python :: Implementation :: CPython +Classifier: Programming Language :: Python :: Implementation :: PyPy +Classifier: Operating System :: POSIX +Classifier: Topic :: Software Development :: Version Control diff --git a/README.md b/README.md index aa85b48f..5f63dffd 100644 --- a/README.md +++ b/README.md @@ -1,50 +1,50 @@ [![Build Status](https://travis-ci.org/jelmer/dulwich.png?branch=master)](https://travis-ci.org/jelmer/dulwich) 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. -Homepage: https://samba.org/~jelmer/dulwich/ -Author: Jelmer Vernooij +Homepage: https://www.dulwich.io/ +Author: Jelmer Vernooij 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" Further documentation --------------------- The dulwich documentation can be found in doc/ and on the web: -http://www.samba.org/~jelmer/dulwich/docs/ +https://www.dulwich.io/docs/ The API reference can be generated using pydoctor, by running "make pydoctor", or on the web: -http://www.samba.org/~jelmer/dulwich/apidocs +https://www.dulwich.io/apidocs Help ---- There is a #dulwich IRC channel on Freenode, and a dulwich mailing list at https://launchpad.net/~dulwich-users. Supported versions of Python ---------------------------- At the moment, Dulwich supports (and is tested on) CPython 2.6, 2.7, 3.4, 3.5 and Pypy. The ``dulwich.web`` module is currently broken on Python 3 (issue #295). diff --git a/README.swift b/README.swift deleted file mode 100644 index 2595e634..00000000 --- a/README.swift +++ /dev/null @@ -1,133 +0,0 @@ -Openstack Swift as backend for Dulwich -====================================== -Fabien Boucher - -The module dulwich/contrib/swift.py implements dulwich.repo.BaseRepo -in order to being compatible with Openstack Swift. -We can then use Dulwich as server (Git server) and instead of using -a regular POSIX file system to store repository objects we use the -object storage Swift via its own API. - -c Git client <---> Dulwich server <---> Openstack Swift API - -This implementation is still a work in progress and we can say that -is a Beta version so you need to be prepared to find bugs. - -Configuration file ------------------- - -We need to provide some configuration values in order to let Dulwich -talk and authenticate against Swift. The following config file must -be used as template: - - [swift] - # Authentication URL (Keystone or Swift) - auth_url = http://127.0.0.1:5000/v2.0 - # Authentication version to use - auth_ver = 2 - # The tenant and username separated by a semicolon - username = admin;admin - # The user password - password = pass - # The Object storage region to use (auth v2) (Default RegionOne) - region_name = RegionOne - # The Object storage endpoint URL to use (auth v2) (Default internalURL) - endpoint_type = internalURL - # Concurrency to use for parallel tasks (Default 10) - concurrency = 10 - # Size of the HTTP pool (Default 10) - http_pool_length = 10 - # Timeout delay for HTTP connections (Default 20) - http_timeout = 20 - # Chunk size to read from pack (Bytes) (Default 12228) - chunk_length = 12228 - # Cache size (MBytes) (Default 20) - cache_length = 20 - - -Note that for now we use the same tenant to perform the requests -against Swift. Therefor there is only one Swift account used -for storing repositories. Each repository will be contained in -a Swift container. - -How to start unittest ---------------------- - -There is no need to have a Swift cluster running to run the unitests. -Just run the following command in the Dulwich source directory: - - $ PYTHONPATH=. python -m dulwich.contrib.test_swift - -How to start functional tests ------------------------------ - -We provide some basic tests to perform smoke tests against a real Swift -cluster. To run those functional tests you need a properly configured -configuration file. The tests can be run as follow: - - $ DULWICH_SWIFT_CFG=/etc/swift-dul.conf PYTHONPATH=. python -m dulwich.contrib.test_swift_smoke - -How to install --------------- - -Install the Dulwich library via the setup.py. The dependencies will be -automatically retrieved from pypi: - - $ python ./setup.py install - -How to run the server ---------------------- - -Start the server using the following command: - - $ python -m dulwich.contrib.swift daemon -c /etc/swift-dul.conf -l 127.0.0.1 - -Note that a lot of request will be performed against the Swift -cluster so it is better to start the Dulwich server as close -as possible of the Swift proxy. The best solution is to run -the server on the Swift proxy node to reduce the latency. - -How to use ----------- - -Once you have validated that the functional tests is working as expected and -the server is running we can init a bare repository. Run this -command with the name of the repository to create: - - $ python -m dulwich.contrib.swift init -c /etc/swift-dul.conf edeploy - -The repository name will be the container that will contain all the Git -objects for the repository. Then standard c Git client can be used to -perform operations againt this repository. - -As an example we can clone the previously empty bare repository: - - $ git clone git://localhost/edeploy - -Then push an existing project in it: - - $ git clone https://github.com/enovance/edeploy.git edeployclone - $ cd edeployclone - $ git remote add alt git://localhost/edeploy - $ git push alt master - $ git ls-remote alt - 9dc50a9a9bff1e232a74e365707f22a62492183e HEAD - 9dc50a9a9bff1e232a74e365707f22a62492183e refs/heads/master - -The other Git commands can be used the way you do usually against -a regular repository. - -Note the daemon subcommands starts a Git server listening for the -Git protocol. Therefor there is no authentication or encryption -at all between the cGIT client and the GIT server (Dulwich). - -Note on the .info file for pack object --------------------------------------- - -The Swift interface of Dulwich relies only on the pack format -to store Git objects. Instead of using only an index (pack-sha.idx) -along with the pack, we add a second file (pack-sha.info). This file -is automatically created when a client pushes some references on the -repository. The purpose of this file is to speed up pack creation -server side when a client fetches some references. Currently this -.info format is not optimized and may change in future. diff --git a/appveyor.yml b/appveyor.yml index ad3a4d80..7494512e 100644 --- a/appveyor.yml +++ b/appveyor.yml @@ -1,20 +1,29 @@ environment: matrix: - PYTHON: "C:\\Python27" - PYTHON_ARCH: "32" PYWIN32_URL: "https://downloads.sourceforge.net/project/pywin32/pywin32/Build%20219/pywin32-219.win32-py2.7.exe" - PYTHON: "C:\\Python34" - PYTHON_ARCH: "32" PYWIN32_URL: "https://downloads.sourceforge.net/project/pywin32/pywin32/Build%20219/pywin32-219.win32-py3.4.exe" + - PYTHON: "C:\\Python27-x64" + PYWIN32_URL: "https://downloads.sourceforge.net/project/pywin32/pywin32/Build%20219/pywin32-219.win-amd64-py2.7.exe" + + - PYTHON: "C:\\Python34-x64" + PYWIN32_URL: "https://downloads.sourceforge.net/project/pywin32/pywin32/Build%20219/pywin32-219.win-amd64-py3.4.exe" + install: - ps: (new-object net.webclient).DownloadFile($env:PYWIN32_URL, 'c:\\pywin32.exe') - "%PYTHON%/Scripts/easy_install.exe c:\\pywin32.exe" + - "%PYTHON%/Scripts/easy_install.exe wheel" build: off test_script: - "%WITH_COMPILER% %PYTHON%/python setup.py test" +after_test: + - "%WITH_COMPILER% %PYTHON%/python setup.py bdist_wheel" +artifacts: + - path: dist\* diff --git a/bin/dulwich b/bin/dulwich index e1af313f..7b935652 100755 --- a/bin/dulwich +++ b/bin/dulwich @@ -1,381 +1,421 @@ #!/usr/bin/python -u # # dulwich - Simple command-line interface to Dulwich # Copyright (C) 2008-2011 Jelmer Vernooij # vim: expandtab # # This program is free software; you can redistribute it and/or # modify it under the terms of the GNU General Public License # as published by the Free Software Foundation; version 2 # or (at your option) a later version of the License. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program; if not, write to the Free Software # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, # MA 02110-1301, USA. """Simple command-line interface to Dulwich> This is a very simple command-line wrapper for Dulwich. It is by no means intended to be a full-blown Git command-line interface but just a way to test Dulwich. """ import os import sys from getopt import getopt import optparse import signal def signal_int(signal, frame): sys.exit(1) signal.signal(signal.SIGINT, signal_int) from dulwich import porcelain from dulwich.client import get_transport_and_path from dulwich.errors import ApplyDeltaError from dulwich.index import Index from dulwich.pack import Pack, sha_to_hex from dulwich.patch import write_tree_diff from dulwich.repo import Repo def cmd_archive(args): opts, args = getopt(args, "", []) client, path = get_transport_and_path(args.pop(0)) location = args.pop(0) committish = args.pop(0) porcelain.archive(location, committish, outstream=sys.stdout, errstream=sys.stderr) def cmd_add(args): opts, args = getopt(args, "", []) porcelain.add(".", paths=args) def cmd_rm(args): opts, args = getopt(args, "", []) porcelain.rm(".", paths=args) def cmd_fetch_pack(args): opts, args = getopt(args, "", ["all"]) opts = dict(opts) client, path = get_transport_and_path(args.pop(0)) r = Repo(".") if "--all" in opts: determine_wants = r.object_store.determine_wants_all else: determine_wants = lambda x: [y for y in args if not y in r.object_store] client.fetch(path, r, determine_wants) def cmd_fetch(args): opts, args = getopt(args, "", []) opts = dict(opts) client, path = get_transport_and_path(args.pop(0)) r = Repo(".") if "--all" in opts: determine_wants = r.object_store.determine_wants_all refs = client.fetch(path, r, progress=sys.stdout.write) print("Remote refs:") for item in refs.items(): print("%s -> %s" % item) def cmd_log(args): opts, args = getopt(args, "", []) if len(args) > 0: path = args.pop(0) else: path = "." porcelain.log(repo=path, outstream=sys.stdout) def cmd_diff(args): opts, args = getopt(args, "", []) if args == []: print("Usage: dulwich diff COMMITID") sys.exit(1) r = Repo(".") commit_id = args[0] commit = r[commit_id] parent_commit = r[commit.parents[0]] write_tree_diff(sys.stdout, r.object_store, parent_commit.tree, commit.tree) def cmd_dump_pack(args): opts, args = getopt(args, "", []) if args == []: print("Usage: dulwich dump-pack FILENAME") sys.exit(1) basename, _ = os.path.splitext(args[0]) x = Pack(basename) print("Object names checksum: %s" % x.name()) print("Checksum: %s" % sha_to_hex(x.get_stored_checksum())) if not x.check(): print("CHECKSUM DOES NOT MATCH") print("Length: %d" % len(x)) for name in x: try: print("\t%s" % x[name]) except KeyError as k: print("\t%s: Unable to resolve base %s" % (name, k)) except ApplyDeltaError as e: print("\t%s: Unable to apply delta: %r" % (name, e)) def cmd_dump_index(args): opts, args = getopt(args, "", []) if args == []: print("Usage: dulwich dump-index FILENAME") sys.exit(1) filename = args[0] idx = Index(filename) for o in idx: print(o, idx[o]) def cmd_init(args): opts, args = getopt(args, "", ["bare"]) opts = dict(opts) if args == []: path = os.getcwd() else: path = args[0] porcelain.init(path, bare=("--bare" in opts)) def cmd_clone(args): opts, args = getopt(args, "", ["bare"]) opts = dict(opts) if args == []: print("usage: dulwich clone host:path [PATH]") sys.exit(1) source = args.pop(0) if len(args) > 0: target = args.pop(0) else: target = None porcelain.clone(source, target, bare=("--bare" in opts)) def cmd_commit(args): opts, args = getopt(args, "", ["message"]) opts = dict(opts) porcelain.commit(".", message=opts["--message"]) def cmd_commit_tree(args): opts, args = getopt(args, "", ["message"]) if args == []: print("usage: dulwich commit-tree tree") sys.exit(1) opts = dict(opts) porcelain.commit_tree(".", tree=args[0], message=opts["--message"]) def cmd_update_server_info(args): porcelain.update_server_info(".") def cmd_symbolic_ref(args): opts, args = getopt(args, "", ["ref-name", "force"]) if not args: print("Usage: dulwich symbolic-ref REF_NAME [--force]") sys.exit(1) ref_name = args.pop(0) porcelain.symbolic_ref(".", ref_name=ref_name, force='--force' in args) def cmd_show(args): opts, args = getopt(args, "", []) porcelain.show(".", args) def cmd_diff_tree(args): opts, args = getopt(args, "", []) if len(args) < 2: print("Usage: dulwich diff-tree OLD-TREE NEW-TREE") sys.exit(1) porcelain.diff_tree(".", args[0], args[1]) def cmd_rev_list(args): opts, args = getopt(args, "", []) if len(args) < 1: print('Usage: dulwich rev-list COMMITID...') sys.exit(1) porcelain.rev_list('.', args) def cmd_tag(args): opts, args = getopt(args, '', []) if len(args) < 2: print('Usage: dulwich tag NAME') sys.exit(1) porcelain.tag('.', args[0]) +def cmd_repack(args): + opts, args = getopt(args, "", []) + opts = dict(opts) + porcelain.repack('.') + + def cmd_reset(args): opts, args = getopt(args, "", ["hard", "soft", "mixed"]) opts = dict(opts) mode = "" if "--hard" in opts: mode = "hard" elif "--soft" in opts: mode = "soft" elif "--mixed" in opts: mode = "mixed" porcelain.reset('.', mode=mode, *args) def cmd_daemon(args): from dulwich import log_utils from dulwich.protocol import TCP_GIT_PORT parser = optparse.OptionParser() parser.add_option("-l", "--listen_address", dest="listen_address", default="localhost", help="Binding IP address.") parser.add_option("-p", "--port", dest="port", type=int, default=TCP_GIT_PORT, help="Binding TCP port.") options, args = parser.parse_args(args) log_utils.default_logging_config() if len(args) >= 1: gitdir = args[0] else: gitdir = '.' from dulwich import porcelain porcelain.daemon(gitdir, address=options.listen_address, port=options.port) def cmd_web_daemon(args): from dulwich import log_utils parser = optparse.OptionParser() parser.add_option("-l", "--listen_address", dest="listen_address", default="", help="Binding IP address.") parser.add_option("-p", "--port", dest="port", type=int, default=8000, help="Binding TCP port.") options, args = parser.parse_args(args) log_utils.default_logging_config() if len(args) >= 1: gitdir = args[0] else: gitdir = '.' from dulwich import porcelain porcelain.web_daemon(gitdir, address=options.listen_address, port=options.port) def cmd_receive_pack(args): parser = optparse.OptionParser() options, args = parser.parse_args(args) if len(args) >= 1: gitdir = args[0] else: gitdir = '.' porcelain.receive_pack(gitdir) def cmd_upload_pack(args): parser = optparse.OptionParser() options, args = parser.parse_args(args) if len(args) >= 1: gitdir = args[0] else: gitdir = '.' porcelain.upload_pack(gitdir) def cmd_status(args): parser = optparse.OptionParser() options, args = parser.parse_args(args) if len(args) >= 1: gitdir = args[0] else: gitdir = '.' status = porcelain.status(gitdir) if status.staged: sys.stdout.write("Changes to be committed:\n\n") for kind, names in status.staged.items(): for name in names: sys.stdout.write("\t%s: %s\n" % (kind, name)) sys.stdout.write("\n") if status.unstaged: sys.stdout.write("Changes not staged for commit:\n\n") for name in status.unstaged: sys.stdout.write("\t%s\n" % name.decode(sys.getfilesystemencoding())) sys.stdout.write("\n") if status.untracked: sys.stdout.write("Untracked files:\n\n") for name in status.untracked: sys.stdout.write("\t%s\n" % name) sys.stdout.write("\n") +def cmd_ls_remote(args): + opts, args = getopt(args, '', []) + if len(args) < 1: + print('Usage: dulwich ls-remote URL') + sys.exit(1) + refs = porcelain.ls_remote(args[0]) + for ref in sorted(refs): + sys.stdout.write("%s\t%s\n" % (ref, refs[ref])) + + +def cmd_pack_objects(args): + opts, args = getopt(args, '', ['stdout']) + opts = dict(opts) + if len(args) < 1 and not '--stdout' in args: + print('Usage: dulwich pack-objects basename') + sys.exit(1) + object_ids = [l.strip() for l in sys.stdin.readlines()] + basename = args[0] + if '--stdout' in opts: + packf = getattr(sys.stdout, 'buffer', sys.stdout) + idxf = None + close = [] + else: + packf = open(basename + '.pack', 'w') + idxf = open(basename + '.idx', 'w') + close = [packf, idxf] + porcelain.pack_objects('.', object_ids, packf, idxf) + for f in close: + f.close() + + commands = { "add": cmd_add, "archive": cmd_archive, "clone": cmd_clone, "commit": cmd_commit, "commit-tree": cmd_commit_tree, "daemon": cmd_daemon, "diff": cmd_diff, "diff-tree": cmd_diff_tree, "dump-pack": cmd_dump_pack, "dump-index": cmd_dump_index, "fetch-pack": cmd_fetch_pack, "fetch": cmd_fetch, "init": cmd_init, "log": cmd_log, + "ls-remote": cmd_ls_remote, + "pack-objects": cmd_pack_objects, "receive-pack": cmd_receive_pack, + "repack": cmd_repack, "reset": cmd_reset, "rev-list": cmd_rev_list, "rm": cmd_rm, "show": cmd_show, "status": cmd_status, "symbolic-ref": cmd_symbolic_ref, "tag": cmd_tag, "update-server-info": cmd_update_server_info, "upload-pack": cmd_upload_pack, "web-daemon": cmd_web_daemon, } if len(sys.argv) < 2: print("Usage: %s <%s> [OPTIONS...]" % (sys.argv[0], "|".join(commands.keys()))) sys.exit(1) cmd = sys.argv[1] if not cmd in commands: print("No such subcommand: %s" % cmd) sys.exit(1) commands[cmd](sys.argv[2:]) diff --git a/docs/index.txt b/docs/index.txt index 076f9a35..113fba3a 100644 --- a/docs/index.txt +++ b/docs/index.txt @@ -1,36 +1,36 @@ .. _index: ====================================== dulwich - Python implementation of Git ====================================== Overview ======== -.. include:: ../README +.. include:: ../README.md Documentation ============= .. toctree:: :maxdepth: 2 performance protocol tutorial/index Changelog ========= .. include:: ../NEWS Indices and tables ================== * :ref:`genindex` * :ref:`modindex` * :ref:`search` diff --git a/docs/tutorial/.gitignore b/docs/tutorial/.gitignore deleted file mode 100644 index 6b71f091..00000000 --- a/docs/tutorial/.gitignore +++ /dev/null @@ -1,2 +0,0 @@ -*.html -myrepo diff --git a/dulwich.cfg b/dulwich.cfg index 208f0564..de2d0a84 100644 --- a/dulwich.cfg +++ b/dulwich.cfg @@ -1,5 +1,5 @@ packages: dulwich docformat: restructuredtext projectname: Dulwich -projecturl: http://samba.org/~jelmer/dulwich/ +projecturl: https://www.dulwich.io/ htmloutput: apidocs diff --git a/dulwich.egg-info/PKG-INFO b/dulwich.egg-info/PKG-INFO new file mode 100644 index 00000000..c700355a --- /dev/null +++ b/dulwich.egg-info/PKG-INFO @@ -0,0 +1,29 @@ +Metadata-Version: 1.1 +Name: dulwich +Version: 0.11.1 +Summary: Python Git Library +Home-page: https://www.dulwich.io/ +Author: Jelmer Vernooij +Author-email: jelmer@jelmer.uk +License: GPLv2 or later +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 :: GNU General Public License v2 or later (GPLv2+) +Classifier: Programming Language :: Python :: 2.6 +Classifier: Programming Language :: Python :: 2.7 +Classifier: Programming Language :: Python :: 3.4 +Classifier: Programming Language :: Python :: Implementation :: CPython +Classifier: Programming Language :: Python :: Implementation :: PyPy +Classifier: Operating System :: POSIX +Classifier: Topic :: Software Development :: Version Control diff --git a/dulwich.egg-info/SOURCES.txt b/dulwich.egg-info/SOURCES.txt new file mode 100644 index 00000000..7f66e893 --- /dev/null +++ b/dulwich.egg-info/SOURCES.txt @@ -0,0 +1,187 @@ +AUTHORS +CONTRIBUTING +COPYING +MANIFEST.in +Makefile +NEWS +README.md +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/file-format.txt +docs/tutorial/index.txt +docs/tutorial/introduction.txt +docs/tutorial/object-store.txt +docs/tutorial/remote.txt +docs/tutorial/repo.txt +docs/tutorial/tag.txt +dulwich/__init__.py +dulwich/_compat.py +dulwich/_diff_tree.c +dulwich/_objects.c +dulwich/_pack.c +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/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/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/pbr.json +dulwich.egg-info/top_level.txt +dulwich/contrib/__init__.py +dulwich/contrib/swift.py +dulwich/contrib/test_swift.py +dulwich/contrib/test_swift_smoke.py +dulwich/tests/__init__.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_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_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 new file mode 100644 index 00000000..8b137891 --- /dev/null +++ b/dulwich.egg-info/dependency_links.txt @@ -0,0 +1 @@ + diff --git a/dulwich.egg-info/pbr.json b/dulwich.egg-info/pbr.json new file mode 100644 index 00000000..d22ce1fe --- /dev/null +++ b/dulwich.egg-info/pbr.json @@ -0,0 +1 @@ +{"is_release": false, "git_version": "b732930"} \ No newline at end of file diff --git a/dulwich.egg-info/top_level.txt b/dulwich.egg-info/top_level.txt new file mode 100644 index 00000000..e8413a49 --- /dev/null +++ b/dulwich.egg-info/top_level.txt @@ -0,0 +1 @@ +dulwich diff --git a/dulwich/__init__.py b/dulwich/__init__.py index fa6e5b63..5670c3cf 100644 --- a/dulwich/__init__.py +++ b/dulwich/__init__.py @@ -1,24 +1,24 @@ # __init__.py -- The git module of dulwich # Copyright (C) 2007 James Westby # Copyright (C) 2008 Jelmer Vernooij # # This program is free software; you can redistribute it and/or # modify it under the terms of the GNU General Public License # as published by the Free Software Foundation; version 2 # of the License or (at your option) any later version of # the License. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program; if not, write to the Free Software # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, # MA 02110-1301, USA. """Python implementation of the Git file formats and protocols.""" -__version__ = (0, 10, 2) +__version__ = (0, 11, 1) diff --git a/dulwich/_objects.c b/dulwich/_objects.c index 8fa2b644..df25a263 100644 --- a/dulwich/_objects.c +++ b/dulwich/_objects.c @@ -1,305 +1,305 @@ /* * Copyright (C) 2009 Jelmer Vernooij * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License * as published by the Free Software Foundation; version 2 * of the License or (at your option) a later version of the License. * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License * along with this program; if not, write to the Free Software * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, * MA 02110-1301, USA. */ #include #include #include #if (PY_VERSION_HEX < 0x02050000) typedef int Py_ssize_t; #endif #if defined(__MINGW32_VERSION) || defined(__APPLE__) size_t rep_strnlen(char *text, size_t maxlen); size_t rep_strnlen(char *text, size_t maxlen) { const char *last = memchr(text, '\0', maxlen); return last ? (size_t) (last - text) : maxlen; } #define strnlen rep_strnlen #endif #define bytehex(x) (((x)<0xa)?('0'+(x)):('a'-0xa+(x))) static PyObject *tree_entry_cls; static PyObject *object_format_exception_cls; static PyObject *sha_to_pyhex(const unsigned char *sha) { char hexsha[41]; int i; for (i = 0; i < 20; i++) { hexsha[i*2] = bytehex((sha[i] & 0xF0) >> 4); hexsha[i*2+1] = bytehex(sha[i] & 0x0F); } return PyString_FromStringAndSize(hexsha, 40); } static PyObject *py_parse_tree(PyObject *self, PyObject *args, PyObject *kw) { char *text, *start, *end; int len, namelen, strict; PyObject *ret, *item, *name, *sha, *py_strict = NULL; static char *kwlist[] = {"text", "strict", NULL}; if (!PyArg_ParseTupleAndKeywords(args, kw, "s#|O", kwlist, &text, &len, &py_strict)) return NULL; strict = py_strict ? PyObject_IsTrue(py_strict) : 0; /* TODO: currently this returns a list; if memory usage is a concern, * consider rewriting as a custom iterator object */ ret = PyList_New(0); if (ret == NULL) { return NULL; } start = text; end = text + len; while (text < end) { long mode; if (strict && text[0] == '0') { PyErr_SetString(object_format_exception_cls, "Illegal leading zero on mode"); Py_DECREF(ret); return NULL; } mode = strtol(text, &text, 8); if (*text != ' ') { PyErr_SetString(PyExc_ValueError, "Expected space"); Py_DECREF(ret); return NULL; } text++; namelen = strnlen(text, len - (text - start)); name = PyString_FromStringAndSize(text, namelen); if (name == NULL) { Py_DECREF(ret); return NULL; } if (text + namelen + 20 >= end) { PyErr_SetString(PyExc_ValueError, "SHA truncated"); Py_DECREF(ret); Py_DECREF(name); return NULL; } sha = sha_to_pyhex((unsigned char *)text+namelen+1); if (sha == NULL) { Py_DECREF(ret); Py_DECREF(name); return NULL; } item = Py_BuildValue("(NlN)", name, mode, sha); if (item == NULL) { Py_DECREF(ret); Py_DECREF(sha); Py_DECREF(name); return NULL; } if (PyList_Append(ret, item) == -1) { Py_DECREF(ret); Py_DECREF(item); return NULL; } Py_DECREF(item); text += namelen+21; } return ret; } struct tree_item { const char *name; int mode; PyObject *tuple; }; int cmp_tree_item(const void *_a, const void *_b) { const struct tree_item *a = _a, *b = _b; const char *remain_a, *remain_b; int ret, common; if (strlen(a->name) > strlen(b->name)) { common = strlen(b->name); remain_a = a->name + common; remain_b = (S_ISDIR(b->mode)?"/":""); } else if (strlen(b->name) > strlen(a->name)) { common = strlen(a->name); remain_a = (S_ISDIR(a->mode)?"/":""); remain_b = b->name + common; } else { /* strlen(a->name) == strlen(b->name) */ common = 0; remain_a = a->name; remain_b = b->name; } ret = strncmp(a->name, b->name, common); if (ret != 0) return ret; return strcmp(remain_a, remain_b); } int cmp_tree_item_name_order(const void *_a, const void *_b) { const struct tree_item *a = _a, *b = _b; return strcmp(a->name, b->name); } static PyObject *py_sorted_tree_items(PyObject *self, PyObject *args) { struct tree_item *qsort_entries = NULL; int name_order, num_entries, n = 0, i; PyObject *entries, *py_name_order, *ret, *key, *value, *py_mode, *py_sha; Py_ssize_t pos = 0; int (*cmp)(const void *, const void *); if (!PyArg_ParseTuple(args, "OO", &entries, &py_name_order)) goto error; if (!PyDict_Check(entries)) { PyErr_SetString(PyExc_TypeError, "Argument not a dictionary"); goto error; } name_order = PyObject_IsTrue(py_name_order); if (name_order == -1) goto error; cmp = name_order ? cmp_tree_item_name_order : cmp_tree_item; num_entries = PyDict_Size(entries); if (PyErr_Occurred()) goto error; qsort_entries = PyMem_New(struct tree_item, num_entries); if (!qsort_entries) { PyErr_NoMemory(); goto error; } while (PyDict_Next(entries, &pos, &key, &value)) { if (!PyString_Check(key)) { PyErr_SetString(PyExc_TypeError, "Name is not a string"); goto error; } if (PyTuple_Size(value) != 2) { PyErr_SetString(PyExc_ValueError, "Tuple has invalid size"); goto error; } py_mode = PyTuple_GET_ITEM(value, 0); - if (!PyInt_Check(py_mode)) { + if (!PyInt_Check(py_mode) && !PyLong_Check(py_mode)) { PyErr_SetString(PyExc_TypeError, "Mode is not an integral type"); goto error; } py_sha = PyTuple_GET_ITEM(value, 1); if (!PyString_Check(py_sha)) { PyErr_SetString(PyExc_TypeError, "SHA is not a string"); goto error; } qsort_entries[n].name = PyString_AS_STRING(key); - qsort_entries[n].mode = PyInt_AS_LONG(py_mode); + qsort_entries[n].mode = PyInt_AsLong(py_mode); qsort_entries[n].tuple = PyObject_CallFunctionObjArgs( tree_entry_cls, key, py_mode, py_sha, NULL); if (qsort_entries[n].tuple == NULL) goto error; n++; } qsort(qsort_entries, num_entries, sizeof(struct tree_item), cmp); ret = PyList_New(num_entries); if (ret == NULL) { PyErr_NoMemory(); goto error; } for (i = 0; i < num_entries; i++) { PyList_SET_ITEM(ret, i, qsort_entries[i].tuple); } PyMem_Free(qsort_entries); return ret; error: for (i = 0; i < n; i++) { Py_XDECREF(qsort_entries[i].tuple); } PyMem_Free(qsort_entries); return NULL; } static PyMethodDef py_objects_methods[] = { { "parse_tree", (PyCFunction)py_parse_tree, METH_VARARGS | METH_KEYWORDS, NULL }, { "sorted_tree_items", py_sorted_tree_items, METH_VARARGS, NULL }, { NULL, NULL, 0, NULL } }; PyMODINIT_FUNC init_objects(void) { PyObject *m, *objects_mod, *errors_mod; m = Py_InitModule3("_objects", py_objects_methods, NULL); if (m == NULL) { #if PY_MAJOR_VERSION < 3 return; #else return NULL; #endif } errors_mod = PyImport_ImportModule("dulwich.errors"); if (errors_mod == NULL) { #if PY_MAJOR_VERSION < 3 return; #else return NULL; #endif } object_format_exception_cls = PyObject_GetAttrString( errors_mod, "ObjectFormatException"); Py_DECREF(errors_mod); if (object_format_exception_cls == NULL) { #if PY_MAJOR_VERSION < 3 return; #else return NULL; #endif } /* This is a circular import but should be safe since this module is * imported at at the very bottom of objects.py. */ objects_mod = PyImport_ImportModule("dulwich.objects"); if (objects_mod == NULL) { #if PY_MAJOR_VERSION < 3 return; #else return NULL; #endif } tree_entry_cls = PyObject_GetAttrString(objects_mod, "TreeEntry"); Py_DECREF(objects_mod); if (tree_entry_cls == NULL) { #if PY_MAJOR_VERSION < 3 return; #else return NULL; #endif } } diff --git a/dulwich/client.py b/dulwich/client.py index c4c111dc..1017f919 100644 --- a/dulwich/client.py +++ b/dulwich/client.py @@ -1,1199 +1,1252 @@ # client.py -- Implementation of the server side git protocols # Copyright (C) 2008-2013 Jelmer Vernooij # Copyright (C) 2008 John Carr # # This program is free software; you can redistribute it and/or # modify it under the terms of the GNU General Public License # as published by the Free Software Foundation; either version 2 # or (at your option) a later version of the License. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program; if not, write to the Free Software # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, # MA 02110-1301, USA. """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 * report-status * delete-refs Known capabilities that are not supported: * shallow * no-progress * include-tag """ __docformat__ = 'restructuredText' from contextlib import closing from io import BytesIO, BufferedReader import dulwich import select +import shlex import socket import subprocess import sys try: import urllib2 import urlparse except ImportError: import urllib.request as urllib2 import urllib.parse as urlparse from dulwich.errors import ( GitProtocolError, NotGitRepository, SendPackError, UpdateRefsError, ) from dulwich.protocol import ( _RBUFSIZE, CAPABILITY_DELETE_REFS, CAPABILITY_MULTI_ACK, CAPABILITY_MULTI_ACK_DETAILED, CAPABILITY_OFS_DELTA, CAPABILITY_REPORT_STATUS, CAPABILITY_SIDE_BAND_64K, CAPABILITY_THIN_PACK, 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, ) from dulwich.pack import ( write_pack_objects, ) from dulwich.refs import ( read_info_refs, ) def _fileno_can_read(fileno): """Check if a file descriptor is readable.""" return len(select.select([fileno], [], [], 0)[0]) > 0 COMMON_CAPABILITIES = [CAPABILITY_OFS_DELTA, CAPABILITY_SIDE_BAND_64K] FETCH_CAPABILITIES = ([CAPABILITY_THIN_PACK, CAPABILITY_MULTI_ACK, CAPABILITY_MULTI_ACK_DETAILED] + COMMON_CAPABILITIES) SEND_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([ ref.decode('ascii') for ref in ref_status if ref 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 refs, set(server_capabilities) # 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): """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(FETCH_CAPABILITIES) self._send_capabilities = set(SEND_CAPABILITIES) if not thin_packs: self._fetch_capabilities.remove(CAPABILITY_THIN_PACK) def send_pack(self, path, determine_wants, generate_pack_contents, progress=None, write_pack=write_pack_objects): """Upload a pack to a remote repository. - :param path: Repository path + :param path: Repository path (as bytestring) :param generate_pack_contents: Function that can return a sequence of the shas of the objects 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 """ 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 + :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 :param progress: Optional progress function :return: remote refs as dictionary """ if determine_wants is None: determine_wants = target.object_store.determine_wants_all + f, commit, abort = target.object_store.add_pack() try: result = self.fetch_pack( path, determine_wants, target.get_graph_walker(), f.write, progress) except: 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 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) """ 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([ref for ref in ref_status if ref 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: New refs :return: (have, want) tuple """ want = [] have = [x for x in old_refs.values() if not x == ZERO_SHA] sent_capabilities = False all_refs = set(new_refs.keys()).union(set(old_refs.keys())) for refname in all_refs: old_sha1 = old_refs.get(refname, ZERO_SHA) new_sha1 = new_refs.get(refname, ZERO_SHA) 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 _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 b"side-band-64k" in capabilities: if progress is None: progress = lambda x: None 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 _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 progress = lambda x: None 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.""" 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. + :param path: The path we should pass to the service. (as bytestirng) """ raise NotImplementedError() def send_pack(self, path, determine_wants, generate_pack_contents, progress=None, write_pack=write_pack_objects): """Upload a pack to a remote repository. - :param path: Repository path + :param path: Repository path (as bytestring) :param generate_pack_contents: Function that can return a sequence of the shas of the objects 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 """ proto, unused_can_read = self._connect(b'receive-pack', path) with proto: old_refs, server_capabilities = read_pkt_refs(proto) negotiated_capabilities = self._send_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 = determine_wants(dict(old_refs)) except: proto.write_pkt_line(None) raise if not CAPABILITY_DELETE_REFS 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 old_refs == new_refs: return new_refs objects = generate_pack_contents(have, want) dowrite = len(objects) > 0 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) 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 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) """ proto, can_read = self._connect(b'upload-pack', path) with proto: refs, server_capabilities = read_pkt_refs(proto) negotiated_capabilities = ( self._fetch_capabilities & server_capabilities) if refs is None: proto.write_pkt_line(None) return refs try: wants = determine_wants(refs) except: 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 refs 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 refs + 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) + 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, *args, **kwargs): if port is None: port = TCP_GIT_PORT self._host = host self._port = port TraditionalGitClient.__init__(self, *args, **kwargs) def _connect(self, cmd, path): + if type(cmd) is not bytes: + raise TypeError(path) + if type(path) is not bytes: + raise TypeError(path) 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:] - proto.send_cmd(b'git-' + cmd, path, b'host=' + self._host) + # 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 subprocess.mswindows: from msvcrt import get_osfhandle from win32pipe import PeekNamedPipe handle = get_osfhandle(self.proc.stdout.fileno()) data, total_bytes_avail, msg_bytes_left = PeekNamedPipe(handle, 0) return total_bytes_avail != 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, *args, **kwargs): self._connection = None self._stderr = None self._stderr = kwargs.get('stderr') if 'stderr' in kwargs: del kwargs['stderr'] TraditionalGitClient.__init__(self, *args, **kwargs) git_command = None def _connect(self, service, path): + if type(service) is not bytes: + raise TypeError(path) + if type(path) is not bytes: + raise TypeError(path) import subprocess if self.git_command is None: git_command = find_git_command() - argv = git_command + [service, path] - argv = ['git', service.decode('ascii'), path] + 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): """Create a new LocalGitClient instance. - :param path: Path to the local repository :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 send_pack(self, path, determine_wants, generate_pack_contents, progress=None, write_pack=write_pack_objects): """Upload a pack to a remote repository. - :param path: Repository path + :param path: Repository path (as bytestring) :param generate_pack_contents: Function that can return a sequence of the shas of the objects 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 """ from dulwich.repo import Repo with closing(Repo(path)) as target: old_refs = target.get_refs() new_refs = determine_wants(dict(old_refs)) have = [sha1 for sha1 in old_refs.values() if sha1 != ZERO_SHA] want = [] all_refs = set(new_refs.keys()).union(set(old_refs.keys())) for refname in all_refs: old_sha1 = old_refs.get(refname, ZERO_SHA) new_sha1 = new_refs.get(refname, ZERO_SHA) if new_sha1 not in have and new_sha1 != ZERO_SHA: want.append(new_sha1) if not want and old_refs == new_refs: return new_refs target.object_store.add_objects(generate_pack_contents(have, want)) for name, sha in new_refs.items(): target.refs[name] = sha return new_refs def fetch(self, path, target, determine_wants=None, progress=None): """Fetch into a target repository. - :param path: Path to fetch from + :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 :param progress: Optional progress function :return: remote refs as dictionary """ from dulwich.repo import Repo with closing(Repo(path)) as r: return r.fetch(target, determine_wants=determine_wants, progress=progress) 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) """ from dulwich.repo import Repo with closing(Repo(path)) as r: objects_iter = r.fetch_objects(determine_wants, graph_walker, progress) # 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 write_pack_objects(ProtocolFile(None, pack_data), objects_iter) + def get_refs(self, path): + """Retrieve the current refs from a git smart server.""" + from dulwich.repo import Repo + + with closing(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): 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) def run_command(self, host, command, username=None, port=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 + :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 """ raise NotImplementedError(self.run_command) class SubprocessSSHVendor(SSHVendor): """SSH vendor that shells out to the local 'ssh' command.""" def run_command(self, host, command, username=None, port=None): + if (type(command) is not list or + not all([isinstance(b, bytes) for b in command])): + raise TypeError(command) + import subprocess #FIXME: This has no way to deal with passwords.. args = ['ssh', '-x'] if port is not None: args.extend(['-p', str(port)]) if username is not None: host = '%s@%s' % (username, host) args.append(host) proc = subprocess.Popen(args + command, stdin=subprocess.PIPE, stdout=subprocess.PIPE) return SubprocessWrapper(proc) try: import paramiko except ImportError: pass else: 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 = '' # 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): def __init__(self): self.ssh_kwargs = {} def run_command(self, host, command, username=None, port=None, progress_stderr=None): - + if (type(command) is not list or + not all([isinstance(b, bytes) for b in command])): + raise TypeError(command) # Paramiko needs an explicit port. None is not valid if port is None: port = 22 client = paramiko.SSHClient() policy = paramiko.client.MissingHostKeyPolicy() client.set_missing_host_key_policy(policy) client.connect(host, username=username, port=port, **self.ssh_kwargs) # Open SSH session channel = client.get_transport().open_session() # Run commands - channel.exec_command(*command) + channel.exec_command(subprocess.list2cmdline(command)) return ParamikoWrapper( client, channel, progress_stderr=progress_stderr) # Can be overridden by users get_ssh_vendor = SubprocessSSHVendor class SSHGitClient(TraditionalGitClient): def __init__(self, host, port=None, username=None, *args, **kwargs): self.host = host self.port = port self.username = username TraditionalGitClient.__init__(self, *args, **kwargs) self.alternative_paths = {} def _get_cmd_path(self, cmd): - cmd = cmd.decode('ascii') - return self.alternative_paths.get(cmd, 'git-' + cmd) + cmd = self.alternative_paths.get(cmd, b'git-' + cmd) + assert isinstance(cmd, bytes) + if sys.version_info[:2] <= (2, 6): + return shlex.split(cmd) + else: + # TODO(jelmer): Don't decode/encode here + return [x.encode('ascii') for x in shlex.split(cmd.decode('ascii'))] def _connect(self, cmd, path): - if path.startswith("/~"): + if type(cmd) is not bytes: + raise TypeError(path) + if type(path) is not bytes: + raise TypeError(path) + if path.startswith(b"/~"): path = path[1:] + argv = self._get_cmd_path(cmd) + [path] con = get_ssh_vendor().run_command( - self.host, [self._get_cmd_path(cmd), path], - port=self.port, username=self.username) + self.host, argv, port=self.port, username=self.username) return (Protocol(con.read, con.write, con.close, report_activity=self._report_activity), con.can_read) def default_user_agent_string(): return "dulwich/%s" % ".".join([str(x) for x in dulwich.__version__]) def default_urllib2_opener(config): if config is not None: proxy_server = config.get("http", "proxy") 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: user_agent = config.get("http", "useragent") else: user_agent = None if user_agent is None: user_agent = default_user_agent_string() opener.addheaders = [('User-agent', user_agent)] return opener class HttpGitClient(GitClient): def __init__(self, base_url, dumb=None, opener=None, config=None, *args, **kwargs): self.base_url = base_url.rstrip("/") + "/" self.dumb = dumb if opener is None: self.opener = default_urllib2_opener(config) else: self.opener = opener GitClient.__init__(self, *args, **kwargs) def __repr__(self): return "%s(%r, dumb=%r)" % (type(self).__name__, self.base_url, self.dumb) def _get_url(self, path): return urlparse.urljoin(self.base_url, path).rstrip("/") + "/" def _http_request(self, url, headers={}, data=None): 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" % e.code) return resp def _discover_references(self, service, url): assert url[-1] == "/" url = urlparse.urljoin(url, "info/refs") headers = {} if self.dumb is not False: url += "?service=%s" % service headers["Content-Type"] = "application/x-%s-request" % service resp = self._http_request(url, headers) try: self.dumb = (not resp.info().gettype().startswith("application/x-git-")) if not self.dumb: proto = Protocol(resp.read, None) # The first line should mention the service pkts = list(proto.read_pkt_seq()) if pkts != [('# service=%s\n' % service)]: raise GitProtocolError( "unexpected first line %r from smart server" % pkts) return read_pkt_refs(proto) else: return read_info_refs(resp), set() finally: resp.close() def _smart_request(self, service, url, data): assert url[-1] == "/" url = urlparse.urljoin(url, service) headers = {"Content-Type": "application/x-%s-request" % service} resp = self._http_request(url, headers, data) if resp.info().gettype() != ("application/x-%s-result" % service): raise GitProtocolError("Invalid content-type from server: %s" % resp.info().gettype()) return resp def send_pack(self, path, determine_wants, generate_pack_contents, progress=None, write_pack=write_pack_objects): """Upload a pack to a remote repository. - :param path: Repository path + :param path: Repository path (as bytestring) :param generate_pack_contents: Function that can return a sequence of the shas of the objects 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 """ url = self._get_url(path) old_refs, server_capabilities = self._discover_references( b"git-receive-pack", url) negotiated_capabilities = self._send_capabilities & server_capabilities if CAPABILITY_REPORT_STATUS in negotiated_capabilities: self._report_status_parser = ReportStatusParser() new_refs = determine_wants(dict(old_refs)) if new_refs is None: 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 old_refs == new_refs: return new_refs objects = generate_pack_contents(have, want) if len(objects) > 0: write_pack(req_proto.write_file(), objects) resp = self._smart_request(b"git-receive-pack", url, data=req_data.getvalue()) try: resp_proto = Protocol(resp.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: Dictionary with the refs of the remote repository """ url = self._get_url(path) refs, server_capabilities = self._discover_references( b"git-upload-pack", url) negotiated_capabilities = self._fetch_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 refs 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 = self._smart_request( b"git-upload-pack", url, data=req_data.getvalue()) try: resp_proto = Protocol(resp.read, None) self._handle_upload_pack_tail(resp_proto, negotiated_capabilities, graph_walker, pack_data, progress) return refs 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 + :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(parsed.hostname, port=parsed.port, **kwargs), parsed.path) elif parsed.scheme == 'git+ssh': path = parsed.path if path.startswith('/'): path = parsed.path[1:] return SSHGitClient(parsed.hostname, port=parsed.port, username=parsed.username, **kwargs), path elif parsed.scheme in ('http', 'https'): return HttpGitClient(urlparse.urlunparse(parsed), config=config, **kwargs), parsed.path elif parsed.scheme == 'file': return default_local_git_client_cls(**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 + :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(':') return SSHGitClient(hostname, **kwargs), path elif '@' in location and ':' in location: # SSH with user@host:foo. user_host, path = location.split(':') user, host = user_host.rsplit('@') 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 7d337226..d67356f5 100644 --- a/dulwich/config.py +++ b/dulwich/config.py @@ -1,402 +1,418 @@ # config.py - Reading and writing Git config files # Copyright (C) 2011-2013 Jelmer Vernooij # # This program is free software; you can redistribute it and/or # modify it under the terms of the GNU General Public License # as published by the Free Software Foundation; version 2 # of the License or (at your option) a later version. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program; if not, write to the Free Software # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, # MA 02110-1301, USA. """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 try: from collections import ( OrderedDict, MutableMapping, ) except ImportError: from dulwich._compat import ( OrderedDict, MutableMapping ) from dulwich.file import GitFile 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) class ConfigDict(Config, MutableMapping): """Git configuration stored in a dictionary.""" def __init__(self, values=None): """Create a new ConfigDict.""" if values is None: values = OrderedDict() self._values = 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): if not isinstance(section, tuple): section = (section, ) 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, ) self._values.setdefault(section, OrderedDict())[name] = value def iteritems(self, section): return self._values.get(section, OrderedDict()).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 value.endswith(b"\t")): return b'"' + _escape_value(value) + b'"' 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() - block = bytearray() + whitespace = bytearray() in_quotes = False - for c in value: - if c == ord(b"\""): + 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) - ret.extend(_unescape_value(block)) - block = bytearray() - elif c in (ord(b"#"), ord(b";")) and 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: - block.append(c) + if whitespace: + ret.extend(whitespace) + whitespace = bytearray() + ret.append(c) + i += 1 if in_quotes: - raise ValueError("value starts with quote but lacks end quote") - - ret.extend(_unescape_value(block).rstrip()) + raise ValueError("missing end quote") return bytes(ret) def _unescape_value(value): """Unescape a value.""" - if type(value) != bytearray: - raise TypeError("expected: bytearray") - 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"), - } ret = bytearray() i = 0 - while i < len(value): - if value[i] == ord(b"\\"): - i += 1 - ret.append(table[value[i]]) - else: - ret.append(value[i]) - i += 1 + return ret def _escape_value(value): """Escape a value.""" return value.replace(b"\\", b"\\\\").replace(b"\n", b"\\n").replace(b"\t", b"\\t").replace(b"\"", b"\\\"") 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] 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: 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() 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() if not _check_variable_name(setting): raise ValueError("invalid variable name %s" % setting) if value.endswith(b"\\\n"): value = value[:-2] continuation = True else: continuation = False value = _parse_string(value) ret._values[section][setting] = value if not continuation: setting = None else: # continuation line if line.endswith(b"\\\n"): line = line[:-2] continuation = True else: continuation = False value = _parse_string(line) ret._values[section][setting] += value if not continuation: 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 = _escape_value(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_backends(cls): """Retrieve the default configuration. This will look in the users' home directory and the system configuration. """ paths = [] paths.append(os.path.expanduser("~/.gitconfig")) 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): 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) diff --git a/dulwich/file.py b/dulwich/file.py index 230af579..c13ffb3b 100644 --- a/dulwich/file.py +++ b/dulwich/file.py @@ -1,168 +1,170 @@ # file.py -- Safe access to git files # Copyright (C) 2010 Google, Inc. # # This program is free software; you can redistribute it and/or # modify it under the terms of the GNU General Public License # as published by the Free Software Foundation; version 2 # of the License or (at your option) a later version of the License. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program; if not, write to the Free Software # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, # MA 02110-1301, USA. """Safe access to git files.""" import errno +import io import os +import sys import tempfile -import io def ensure_dir_exists(dirname): """Ensure a directory exists, creating if necessary.""" try: os.makedirs(dirname) except OSError as e: if e.errno != errno.EEXIST: raise -def fancy_rename(oldname, newname): +def _fancy_rename(oldname, newname): """Rename file with temporary backup file to rollback if rename fails""" if not os.path.exists(newname): try: os.rename(oldname, newname) except OSError: raise return # destination file exists try: (fd, tmpfile) = tempfile.mkstemp(".tmp", prefix=oldname+".", dir=".") os.close(fd) os.remove(tmpfile) except OSError: # either file could not be created (e.g. permission problem) # or could not be deleted (e.g. rude virus scanner) raise try: os.rename(newname, tmpfile) except OSError: raise # no rename occurred try: os.rename(oldname, newname) except OSError: os.rename(tmpfile, newname) raise os.remove(tmpfile) def GitFile(filename, mode='rb', bufsize=-1): """Create a file object that obeys the git file locking protocol. :return: a builtin file object or a _GitFile object :note: See _GitFile for a description of the file locking protocol. Only read-only and write-only (binary) modes are supported; r+, w+, and a are not. To read and write from the same file, you can take advantage of the fact that opening a file for write does not actually open the file you request. """ if 'a' in mode: raise IOError('append mode not supported for Git files') if '+' in mode: raise IOError('read/write mode not supported for Git files') if 'b' not in mode: raise IOError('text mode not supported for Git files') if 'w' in mode: return _GitFile(filename, mode, bufsize) else: return io.open(filename, mode, bufsize) class _GitFile(object): """File that follows the git locking protocol for writes. All writes to a file foo will be written into foo.lock in the same directory, and the lockfile will be renamed to overwrite the original file on close. :note: You *must* call close() or abort() on a _GitFile for the lock to be released. Typically this will happen in a finally block. """ PROXY_PROPERTIES = set(['closed', 'encoding', 'errors', 'mode', 'name', 'newlines', 'softspace']) PROXY_METHODS = ('__iter__', 'flush', 'fileno', 'isatty', 'read', 'readline', 'readlines', 'seek', 'tell', 'truncate', 'write', 'writelines') def __init__(self, filename, mode, bufsize): self._filename = filename self._lockfilename = '%s.lock' % self._filename fd = os.open(self._lockfilename, os.O_RDWR | os.O_CREAT | os.O_EXCL | getattr(os, "O_BINARY", 0)) self._file = os.fdopen(fd, mode, bufsize) self._closed = False for method in self.PROXY_METHODS: setattr(self, method, getattr(self._file, method)) def abort(self): """Close and discard the lockfile without overwriting the target. If the file is already closed, this is a no-op. """ if self._closed: return self._file.close() try: os.remove(self._lockfilename) self._closed = True except OSError as e: # The file may have been removed already, which is ok. if e.errno != errno.ENOENT: raise self._closed = True def close(self): """Close this file, saving the lockfile over the original. :note: If this method fails, it will attempt to delete the lockfile. However, it is not guaranteed to do so (e.g. if a filesystem becomes suddenly read-only), which will prevent future writes to this file until the lockfile is removed manually. :raises OSError: if the original file could not be overwritten. The lock file is still closed, so further attempts to write to the same file object will raise ValueError. """ if self._closed: return self._file.close() try: try: os.rename(self._lockfilename, self._filename) except OSError as e: - # Windows versions prior to Vista don't support atomic renames - if e.errno != errno.EEXIST: + if sys.platform == 'win32' and e.errno == errno.EEXIST: + # Windows versions prior to Vista don't support atomic renames + _fancy_rename(self._lockfilename, self._filename) + else: raise - fancy_rename(self._lockfilename, self._filename) finally: self.abort() def __enter__(self): return self def __exit__(self, exc_type, exc_val, exc_tb): self.close() def __getattr__(self, name): """Proxy property calls to the underlying file.""" if name in self.PROXY_PROPERTIES: return getattr(self._file, name) raise AttributeError(name) diff --git a/dulwich/objects.py b/dulwich/objects.py index 9e3a0e80..3502965f 100644 --- a/dulwich/objects.py +++ b/dulwich/objects.py @@ -1,1258 +1,1272 @@ # objects.py -- Access to base git objects # Copyright (C) 2007 James Westby # Copyright (C) 2008-2013 Jelmer Vernooij # # This program is free software; you can redistribute it and/or # modify it under the terms of the GNU General Public License # as published by the Free Software Foundation; version 2 # of the License or (at your option) a later version of the License. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program; if not, write to the Free Software # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, # MA 02110-1301, USA. """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, ) 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 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): obj._ensure_parsed() setattr(obj, "_"+name, value) obj._needs_serialization = True def get(obj): obj._ensure_parsed() 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 git_line(*items): """Formats items into a space sepreated 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__ = ('_needs_parsing', '_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_parsing: self._ensure_parsed() elif self._needs_serialization: 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() 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 _ensure_parsed(self): if self._needs_parsing: if not self._chunked_text: raise AssertionError("ShaFile needs chunked text") self._deserialize(self._chunked_text) self._needs_parsing = False 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_parsing = False 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 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_parsing = False 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 _make_sha(self): ret = sha1() ret.update(self._header()) for chunk in self.as_raw_chunks(): ret.update(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) + 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_parsing = False 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): self._ensure_parsed() return self._chunked_text def _set_chunked(self, chunks): self._chunked_text = chunks def _serialize(self): if not self._chunked_text: self._ensure_parsed() 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 _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 = "" for l in f: if l.startswith(b' '): v += l[1:] else: if k is not None: yield (k, v.rstrip(b'\n')) if l == b'\n': # Empty line indicates end of headers break (k, v) = l.split(b' ', 1) 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._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") 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))) 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 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) 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). """ self._ensure_parsed() return (self._object_class, self._object_sha) def _set_object(self, value): self._ensure_parsed() (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: 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] 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): self._ensure_parsed() return name in self._entries def __getitem__(self, name): self._ensure_parsed() 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._ensure_parsed() self._entries[name] = (mode, hexsha) self._needs_serialization = True def __delitem__(self, name): self._ensure_parsed() del self._entries[name] self._needs_serialization = True def __len__(self): self._ensure_parsed() return len(self._entries) def __iter__(self): self._ensure_parsed() 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._ensure_parsed() 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 """ self._ensure_parsed() 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(): if mode & stat.S_IFDIR: kind = "tree" else: kind = "blob" text.append("%04o %s %s\t%s\n" % (mode, kind, hexsha, name)) 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_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)) elif field == _COMMITTER_HEADER: committer, timetext, timezonetext = value.rsplit(b' ', 2) commit_time = int(timetext) commit_info = (committer, commit_time, parse_timezone(timezonetext)) 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', '_parents', '_extra', '_encoding', '_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 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") 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.as_raw_string() 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 chunks[-1] = chunks[-1].rstrip(b' \n') 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.""" self._ensure_parsed() return self._parents def _set_parents(self, value): """Set a list of parents of this commit.""" self._ensure_parsed() 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.""" self._ensure_parsed() return self._extra extra = property(_get_extra, doc="Extra header fields not understood (presumably added in a " "newer version of git). Kept verbatim so the object can " "be correctly reserialized. For private commit metadata, use " "pseudo-headers in Commit.message, rather than this field.") author = serializable_property("author", "The name of the author of the commit") committer = serializable_property("committer", "The name of the committer of the commit") message = serializable_property( "message", "The commit message") commit_time = serializable_property("commit_time", "The timestamp of the commit. As the number of seconds since the epoch.") commit_timezone = serializable_property("commit_timezone", "The zone the commit time is in") author_time = serializable_property("author_time", "The timestamp the commit was written. As the number of " "seconds since the epoch.") author_timezone = serializable_property( "author_timezone", "Returns the zone the author time is in.") encoding = serializable_property( "encoding", "Encoding of the commit message.") mergetag = serializable_property( "mergetag", "Associated signed tag.") gpgsig = serializable_property( "gpgsig", "GPG Signature.") OBJECT_CLASSES = ( Commit, Tree, Blob, Tag, ) _TYPE_MAP = {} for cls in OBJECT_CLASSES: _TYPE_MAP[cls.type_name] = cls _TYPE_MAP[cls.type_num] = cls # Hold on to the pure-python implementations for testing _parse_tree_py = parse_tree _sorted_tree_items_py = sorted_tree_items try: # Try to import C versions from dulwich._objects import parse_tree, sorted_tree_items except ImportError: pass diff --git a/dulwich/objectspec.py b/dulwich/objectspec.py index 5f4bc16d..f1500424 100644 --- a/dulwich/objectspec.py +++ b/dulwich/objectspec.py @@ -1,46 +1,136 @@ # objectspec.py -- Object specification # Copyright (C) 2014 Jelmer Vernooij # # This program is free software; you can redistribute it and/or # modify it under the terms of the GNU General Public License # as published by the Free Software Foundation; version 2 # of the License or (at your option) a later version of the License. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program; if not, write to the Free Software # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, # MA 02110-1301, USA. """Object specification.""" +def to_bytes(text): + if getattr(text, "encode", None) is not None: + text = text.encode('ascii') + return text + + def parse_object(repo, objectish): """Parse a string referring to an object. :param repo: A `Repo` object :param objectish: A string referring to an object :return: A git object :raise KeyError: If the object can not be found """ - if getattr(objectish, "encode", None) is not None: - objectish = objectish.encode('ascii') + objectish = to_bytes(objectish) return repo[objectish] +def parse_ref(container, refspec): + """Parse a string referring to a reference. + + :param container: A RefsContainer object + :param refspec: A string referring to a ref + :return: A ref + :raise KeyError: If the ref can not be found + """ + refspec = to_bytes(refspec) + for ref in [refspec, b"refs/heads/" + refspec]: + if ref in container: + return ref + else: + raise KeyError(refspec) + + +def parse_reftuple(lh_container, rh_container, refspec): + """Parse a reftuple spec. + + :param lh_container: A RefsContainer object + :param hh_container: A RefsContainer object + :param refspec: A string + :return: A tuple with left and right ref + :raise KeyError: If one of the refs can not be found + """ + if refspec.startswith(b"+"): + force = True + refspec = refspec[1:] + else: + force = False + refspec = to_bytes(refspec) + if b":" in refspec: + (lh, rh) = refspec.split(b":") + else: + lh = rh = refspec + if rh == b"": + lh = None + else: + lh = parse_ref(lh_container, lh) + if rh == b"": + rh = None + else: + try: + rh = parse_ref(rh_container, rh) + except KeyError: + # TODO: check force? + if not b"/" in rh: + rh = b"refs/heads/" + rh + return (lh, rh, force) + + +def parse_reftuples(lh_container, rh_container, refspecs): + """Parse a list of reftuple specs to a list of reftuples. + + :param lh_container: A RefsContainer object + :param hh_container: A RefsContainer object + :param refspecs: A list of refspecs or a string + :return: A list of refs + :raise KeyError: If one of the refs can not be found + """ + if not isinstance(refspecs, list): + refspecs = [refspecs] + ret = [] + # TODO: Support * in refspecs + for refspec in refspecs: + ret.append(parse_reftuple(lh_container, rh_container, refspec)) + return ret + + +def parse_refs(container, refspecs): + """Parse a list of refspecs to a list of refs. + + :param container: A RefsContainer object + :param refspecs: A list of refspecs or a string + :return: A list of refs + :raise KeyError: If one of the refs can not be found + """ + # TODO: Support * in refspecs + if not isinstance(refspecs, list): + refspecs = [refspecs] + ret = [] + for refspec in refspecs: + ret.append(parse_ref(container, refspec)) + return ret + + def parse_commit_range(repo, committishs): """Parse a string referring to a range of commits. :param repo: A `Repo` object :param committishs: A string referring to a range of commits. :return: An iterator over `Commit` objects :raise KeyError: When the reference commits can not be found :raise ValueError: If the range can not be parsed """ - if getattr(committishs, "encode", None) is not None: - committishs = committishs.encode('ascii') + committishs = to_bytes(committishs) return iter([repo[committishs]]) diff --git a/dulwich/pack.py b/dulwich/pack.py index 3cba3fed..577ae5ae 100644 --- a/dulwich/pack.py +++ b/dulwich/pack.py @@ -1,1944 +1,1963 @@ # pack.py -- For dealing with packed git objects. # Copyright (C) 2007 James Westby # Copyright (C) 2008-2013 Jelmer Vernooij # # This program is free software; you can redistribute it and/or # modify it under the terms of the GNU General Public License # as published by the Free Software Foundation; version 2 # of the License or (at your option) a later version. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program; if not, write to the Free Software # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, # MA 02110-1301, USA. """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 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 hashlib import sha1 from os import ( SEEK_CUR, SEEK_END, ) from struct import unpack_from import zlib from dulwich.errors import ( ApplyDeltaError, ChecksumMismatch, ) from dulwich.file import GitFile from dulwich.lru_cache import ( LRUSizeCache, ) from dulwich.objects import ( 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_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 = {} for name, idx, crc32 in entries: self._by_sha[name] = idx 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 _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) 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 i-th 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) @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. """ - if type not in DELTA_TYPES: - return type, obj - - if get_ref is None: - get_ref = self.get_ref - if type == OFS_DELTA: - (delta_offset, delta) = obj - # TODO: clean up asserts and replace with nicer error messages - assert isinstance(offset, int) or isinstance(offset, long) - assert isinstance(delta_offset, int) or isinstance(offset, long) - base_offset = offset-delta_offset - type, base_obj = self.get_object_at(base_offset) - assert isinstance(type, int) - elif type == REF_DELTA: - (basename, delta) = obj - assert isinstance(basename, bytes) and len(basename) == 20 - base_offset, type, base_obj = get_ref(basename) - assert isinstance(type, int) - type, base_chunks = self.resolve_object(base_offset, type, base_obj) - chunks = apply_delta(base_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 offset is not None: - self._offset_cache[offset] = type, chunks - return type, chunks + # 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 + assert ( + isinstance(base_offset, int) + or isinstance(base_offset, long)) + assert ( + isinstance(delta_offset, int) + or isinstance(base_offset, long)) + 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) self._file.seek(-len(unused), SEEK_CUR) # Back up over unused data. 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 self._file.seek(-len(unused), SEEK_CUR) # Back up over unused data. 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 = list(self.iterentries(progress=progress)) ret.sort() 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_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. - unpacked = self._resolve_object(offset, obj_type_num, base_chunks) - yield self._result(unpacked) + 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) - pending = chain(self._pending_ofs.pop(unpacked.offset, []), - self._pending_ref.pop(unpacked.sha(), [])) - for new_offset in pending: - for new_result in self._follow_chain( - new_offset, unpacked.obj_type_num, unpacked.obj_chunks): - yield new_result + 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 around a 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 around a 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 = [(k, v[0], v[1]) for (k, v) in entries.items()] entries.sort() 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 """ 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): """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: pack_contents = deltify_pack_objects(objects, delta_window_size) else: pack_contents = ( (o.type_num, o.sha().digest(), None, o.as_raw_string()) for (o, path) in objects) return write_pack_data(f, len(objects), 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(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 except ImportError: pass diff --git a/dulwich/porcelain.py b/dulwich/porcelain.py index bf986428..cc39adce 100644 --- a/dulwich/porcelain.py +++ b/dulwich/porcelain.py @@ -1,764 +1,848 @@ # porcelain.py -- Porcelain-like layer on top of Dulwich # Copyright (C) 2013 Jelmer Vernooij # # This program is free software; you can redistribute it and/or # modify it under the terms of the GNU General Public License # as published by the Free Software Foundation; either version 2 # or (at your option) a later version of the License. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program; if not, write to the Free Software # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, # MA 02110-1301, USA. """Simple wrapper that provides porcelain-like functions on top of Dulwich. Currently implemented: * archive * add * branch{_create,_delete,_list} * clone * commit * commit-tree * daemon * diff-tree * fetch * init + * ls-remote * pull * push * rm * 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. """ __docformat__ = 'restructuredText' from collections import namedtuple from contextlib import ( closing, contextmanager, ) import os import sys import time from dulwich.client import ( get_transport_and_path, SubprocessGitClient, ) from dulwich.errors import ( SendPackError, UpdateRefsError, ) from dulwich.index import get_unstaged_changes from dulwich.objects import ( + Commit, Tag, parse_timezone, ) -from dulwich.objectspec import parse_object +from dulwich.objectspec import ( + parse_object, + parse_reftuples, + ) +from dulwich.pack import ( + write_pack_index, + write_pack_objects, + ) from dulwich.patch import write_tree_diff from dulwich.protocol import Protocol 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') +def encode_path(path): + """Encode a path as bytestring.""" + # TODO(jelmer): Use something other than ascii? + if not isinstance(path, bytes): + path = path.encode('ascii') + return path + + 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 archive(path, committish=None, outstream=sys.stdout, errstream=sys.stderr): """Create an archive. :param path: 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) """ client = SubprocessGitClient() if committish is None: committish = "HEAD" + if not isinstance(path, bytes): + path = path.encode(sys.getfilesystemencoding()) # TODO(jelmer): This invokes C git; this introduces a dependency. # Instead, dulwich should have its own archiver implementation. client.archive(path, committish, outstream.write, errstream.write, errstream.write) 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 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): """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 with open_repo_closing(repo) as r: return r.do_commit(message=message, author=author, committer=committer) 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=sys.stdout, outstream=None): """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 errstream: Optional stream to write progress to :param outstream: Optional stream to write progress to (deprecated) :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") client, host_path = get_transport_and_path(source) 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(host_path, r, determine_wants=r.object_store.determine_wants_all, progress=errstream.write) r[b"HEAD"] = remote_refs[b"HEAD"] if checkout: - errstream.write(b'Checking out HEAD') + errstream.write(b'Checking out HEAD\n') r.reset_index() except: 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. """ # FIXME: Support patterns, directories. with open_repo_closing(repo) as r: if not paths: # If nothing is specified, add all non-ignored files. paths = [] for dirpath, dirnames, filenames in os.walk(r.path): # Skip .git and below. if '.git' in dirnames: dirnames.remove('.git') for filename in filenames: paths.append(os.path.join(dirpath[len(r.path)+1:], filename)) r.stage(paths) def rm(repo=".", paths=None): """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: del index[p.encode(sys.getfilesystemencoding())] index.write() -def commit_decode(commit, contents): +def commit_decode(commit, contents, default_encoding='utf-8'): if commit.encoding is not None: return contents.decode(commit.encoding, "replace") - return contents.decode("utf-8", "replace") + return contents.decode(default_encoding, "replace") -def print_commit(commit, outstream=sys.stdout): +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(b"-" * 50 + b"\n") - outstream.write(b"commit: " + commit.id + b"\n") + outstream.write("-" * 50 + "\n") + outstream.write("commit: " + commit.id.decode('ascii') + "\n") if len(commit.parents) > 1: - outstream.write(b"merge: " + b"...".join(commit.parents[1:]) + b"\n") - outstream.write(b"author: " + commit.author + b"\n") - outstream.write(b"committer: " + commit.committer + b"\n") - outstream.write(b"\n") - outstream.write(commit.message + b"\n") - outstream.write(b"\n") + outstream.write("merge: " + + "...".join([c.decode('ascii') for c in commit.parents[1:]]) + "\n") + outstream.write("author: " + decode(commit.author) + "\n") + outstream.write("committer: " + decode(commit.committer) + "\n") + outstream.write("\n") + outstream.write(decode(commit.message) + "\n") + outstream.write("\n") -def print_tag(tag, outstream=sys.stdout): +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(b"Tagger: " + tag.tagger + b"\n") - outstream.write(b"Date: " + tag.tag_time + b"\n") - outstream.write(b"\n") - outstream.write(tag.message + b"\n") - outstream.write(b"\n") + 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, outstream=sys.stdout): +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(blob.data) + outstream.write(decode(blob.data)) -def show_commit(repo, commit, outstream=sys.stdout): +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, outstream) + print_commit(commit, decode=decode, outstream=outstream) parent_commit = repo[commit.parents[0]] write_tree_diff(outstream, repo.object_store, parent_commit.tree, commit.tree) -def show_tree(repo, tree, outstream=sys.stdout): +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("%s\n" % n) + outstream.write(decode(n) + "\n") -def show_tag(repo, tag, outstream=sys.stdout): +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, outstream) + print_tag(tag, decode, outstream) show_object(repo, repo[tag.object[1]], outstream) -def show_object(repo, obj, 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, outstream) + }[obj.type_name](repo, obj, decode, outstream) def log(repo=".", outstream=sys.stdout, max_entries=None): """Write commit logs. :param repo: Path to repository :param outstream: Stream to write log output to :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) for entry in walker: - print_commit(entry.commit, outstream) + decode = lambda x: commit_decode(entry.commit, x) + print_commit(entry.commit, decode, outstream) -def show(repo=".", objects=None, outstream=sys.stdout): +# TODO(jelmer): better default for encoding? +def show(repo=".", objects=None, outstream=sys.stdout, default_encoding='utf-8'): """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: - show_object(r, parse_object(r, objectish), outstream) + o = parse_object(r, objectish) + if isinstance(o, Commit): + decode = lambda x: commit_decode(o, x, default_encoding) + else: + decode = lambda x: 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) tag_obj.tag_time = tag_time if tag_time is None: tag_time = int(time.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 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 = list(r.refs.as_dict(b"refs/tags")) tags.sort() 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] def reset(repo, mode, committish="HEAD"): """Reset current HEAD to the specified state. :param repo: Path to repository :param mode: Mode ("hard", "soft", "mixed") """ if mode != "hard": raise ValueError("hard is the only mode currently supported") with open_repo_closing(repo) as r: tree = r[committish].tree r.reset_index() -def push(repo, remote_location, refs_path, +def push(repo, remote_location, refspecs=None, outstream=sys.stdout, errstream=sys.stderr): """Remote push with dulwich via dulwich.client :param repo: Path to repository :param remote_location: Location of the remote - :param refs_path: relative path to the refs to push to remote + :param refspecs: relative path to the 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) + selected_refs = [] + def update_refs(refs): - new_refs = r.get_refs() - refs[refs_path] = new_refs[b'HEAD'] - del new_refs[b'HEAD'] + selected_refs.extend(parse_reftuples(r.refs, refs, refspecs)) + # TODO: Handle selected_refs == {None: None} + for (lh, rh, force) in selected_refs: + if lh is None: + del refs[rh] + else: + refs[rh] = r.refs[lh] return refs err_encoding = getattr(errstream, 'encoding', 'utf-8') remote_location_bytes = remote_location.encode(err_encoding) try: client.send_pack(path, update_refs, r.object_store.generate_pack_contents, progress=errstream.write) - errstream.write(b"Push to " + remote_location_bytes + b" successful.\n") + 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") + errstream.write(b"Push to " + remote_location_bytes + + b" failed -> " + e.message.encode(err_encoding) + + b"\n") -def pull(repo, remote_location, refs_path, +def pull(repo, remote_location, refspecs=None, outstream=sys.stdout, errstream=sys.stderr): """Pull from remote via dulwich.client :param repo: Path to repository :param remote_location: Location of the remote - :param refs_path: relative path to the fetched refs + :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: + 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) - remote_refs = client.fetch(path, r, progress=errstream.write) - r[b'HEAD'] = remote_refs[refs_path] + remote_refs = client.fetch(path, r, progress=errstream.write, + determine_wants=determine_wants) + for (lh, rh, force) in selected_refs: + r.refs[rh] = remote_refs[lh] + if selected_refs: + r[b'HEAD'] = remote_refs[selected_refs[0][1]] # Perform 'git checkout .' - syncs staged changes tree = r[b"HEAD"].tree r.reset_index() def status(repo="."): """Returns staged, unstaged, and untracked changes relative to the HEAD. :param repo: Path to repository or repository object :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 unstaged_changes = list(get_unstaged_changes(r.open_index(), r.path)) # TODO - Status of untracked - add untracked changes, need gitignore. untracked_changes = [] return GitStatus(tracked_changes, unstaged_changes, untracked_changes) 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': [], } for change in index.changes_from_tree(r.object_store, r[b'HEAD'].tree): 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) 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) 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 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): names = name else: raise TypeError("Unexpected branch name type %r" % name) for name in names: del r.refs[b"refs/heads/" + 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 isinstance(name, bytes): names = [name] elif isinstance(name, list): names = name else: raise TypeError("Unexpected branch name type %r" % name) 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 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=sys.stderr): """Fetch objects from a remote server. :param repo: Path to the repository :param remote_location: String identifying a 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) remote_refs = client.fetch(path, r, progress=errstream.write) return remote_refs + + +def ls_remote(remote): + client, host_path = get_transport_and_path(remote) + return client.get_refs(encode_path(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 = [(k, v[0], v[1]) for (k, v) in entries.items()] + entries.sort() + write_pack_index(idxf, entries, data_sum) diff --git a/dulwich/refs.py b/dulwich/refs.py index 34a68008..bbbbf4aa 100644 --- a/dulwich/refs.py +++ b/dulwich/refs.py @@ -1,759 +1,760 @@ # refs.py -- For dealing with git refs # Copyright (C) 2008-2013 Jelmer Vernooij # # This program is free software; you can redistribute it and/or # modify it under the terms of the GNU General Public License # as published by the Free Software Foundation; version 2 # of the License or (at your option) any later version of # the License. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program; if not, write to the Free Software # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, # MA 02110-1301, USA. """Ref handling. """ import errno import os +import sys from dulwich.errors import ( PackedRefsException, RefFormatError, ) from dulwich.objects import ( - hex_to_sha, git_line, valid_hexsha, ) from dulwich.file import ( GitFile, ensure_dir_exists, ) SYMREF = b'ref: ' LOCAL_BRANCH_PREFIX = b'refs/heads/' BAD_REF_CHARS = set(b'\177 ~^:?*[') 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): """Make a ref point at another ref. :param name: Name of the ref to set :param other: Name of the ref to point at """ 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): for name, value in other.items(): self[b'/'.join((base, name))] = value 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'' 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 (refname, sha), where refname is the name of the last reference in the symbolic reference chain """ contents = SYMREF + name depth = 0 while contents.startswith(SYMREF): refname = contents[len(SYMREF):] contents = self.read_ref(refname) if not contents: break depth += 1 if depth > 5: raise KeyError(name) return refname, 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): """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. :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.""" 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): """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. :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) 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): 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): self._refs[name] = SYMREF + other def set_if_equals(self, name, old_ref, new_ref): if old_ref is not None and self._refs.get(name, None) != old_ref: return False realname, _ = self._follow(name) self._check_refname(realname) self._refs[realname] = new_ref return True def add_if_new(self, name, ref): if name in self._refs: return False self._refs[name] = ref return True def remove_if_equals(self, name, old_ref): if old_ref is not None and self._refs.get(name, None) != old_ref: return False del self._refs[name] 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(b'^{}'): 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): self.path = 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('ascii')) + .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)).strip("/").encode('ascii') + 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. """ - name = name.decode('ascii') + 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) 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 == errno.ENOENT: 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): """Make a ref point at another ref. :param name: Name of the ref to set :param other: Name of the ref to point at """ 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 finally: f.close() def set_if_equals(self, name, old_ref, new_ref): """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. :return: True if the set was successful, False otherwise. """ self._check_refname(name) try: realname, _ = self._follow(name) except KeyError: 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, None) 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 return True def add_if_new(self, name, ref): """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. :return: True if the add was successful, False otherwise. """ try: realname, contents = self._follow(name) if contents is not None: return False except KeyError: 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 return True def remove_if_equals(self, name, old_ref): """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. :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, None) 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) 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').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'#': continue l = l.rstrip(b'\r\n') if l.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:]) sha, name = _split_ref_line(last) last = None yield (sha, name, l[1:]) else: if last: sha, name = _split_ref_line(last) yield (sha, name, None) last = l 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("\r\n").split("\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 + b'^{}\n' is_local_branch = lambda x: x.startswith(b'refs/heads/') diff --git a/dulwich/repo.py b/dulwich/repo.py index 12faefcc..8851fbdf 100644 --- a/dulwich/repo.py +++ b/dulwich/repo.py @@ -1,989 +1,1009 @@ # repo.py -- For dealing with git repositories. # Copyright (C) 2007 James Westby # Copyright (C) 2008-2013 Jelmer Vernooij # # This program is free software; you can redistribute it and/or # modify it under the terms of the GNU General Public License # as published by the Free Software Foundation; version 2 # of the License or (at your option) any later version of # the License. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program; if not, write to the Free Software # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, # MA 02110-1301, USA. """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 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 ( check_ref_format, RefsContainer, DictRefsContainer, InfoRefsContainer, DiskRefsContainer, read_packed_refs, read_packed_refs_with_peeled, write_packed_refs, SYMREF, ) import warnings OBJECTDIR = 'objects' REFSDIR = 'refs' REFSDIR_TAGS = 'tags' REFSDIR_HEADS = 'heads' INDEX_FILENAME = "index" BASE_DIRECTORIES = [ ["branches"], [REFSDIR], [REFSDIR, REFSDIR_TAGS], [REFSDIR, REFSDIR_HEADS], ["hooks"], ["info"] ] 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 _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(b"core", b"filemode", b"true") cf.set(b"core", b"bare", bare) cf.set(b"core", b"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)) + 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: haves = [] # TODO: filter the haves commits from iter_shas. # the specific commits aren't missing. 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. """ config = self.get_config_stack() return (config.get((b"user", ), b"name") + b" <" + config.get((b"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() 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 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) except KeyError: c.parents = merge_heads self.object_store.add_object(c) ok = self.refs.add_if_new(ref, c.id) 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 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): if os.path.isdir(os.path.join(root, ".git", OBJECTDIR)): self.bare = False self._controldir = os.path.join(root, ".git") 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(os.path.join(root, ".git"))): import re with open(os.path.join(root, ".git"), 'r') as f: _, path = re.match('(gitdir: )(.+$)', f.read()).groups() self.bare = False self._controldir = os.path.join(root, path) else: raise NotGitRepository( "No git repository was found at %(path)s" % dict(path=root) ) self.path = root object_store = DiskObjectStore(os.path.join(self.controldir(), OBJECTDIR)) refs = DiskRefsContainer(self.controldir()) BaseRepo.__init__(self, object_store, refs) self._graftpoints = {} graft_file = self.get_named_file(os.path.join("info", "grafts")) if graft_file: with graft_file: self._graftpoints.update(parse_graftpoints(graft_file)) graft_file = self.get_named_file("shallow") 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()) + @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 _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): """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. """ # TODO(dborowitz): sanitize filenames, since this is used directly by # the dumb web serving code. path = path.lstrip(os.path.sep) try: return open(os.path.join(self.controldir(), 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()) 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: 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) 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) self.fetch(target) target.refs.import_refs( b'refs/remotes/' + origin, self.refs.as_dict(b'refs/heads')) target.refs.import_refs( b'refs/tags', self.refs.as_dict(b'refs/tags')) try: target.refs.add_if_new( b'refs/heads/master', self.refs[b'refs/heads/master']) except KeyError: pass # Update target head head, head_sha = self.refs._follow(b'HEAD') if head is not None and head_sha is not None: target.refs.set_symbolic_ref(b'HEAD', head) 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"): 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', b"refs/heads/master") 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, ".git") os.mkdir(controldir) cls._init_maybe_bare(controldir, False) return cls(path) @classmethod def init_bare(cls, path): """Create a new bare repository. ``path`` should already exist and be an emty directory. :param path: Path to create bare repository in :return: a `Repo` instance """ return cls._init_maybe_bare(path, True) create = init_bare def close(self): """Close any files opened by this repository.""" self.object_store.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._named_files = {} self.bare = True self._config = ConfigFile() 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 def get_description(self): """Retrieve the repository description. This defaults to None, for no description. """ return None @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._init_files(bare=True) return ret diff --git a/dulwich/server.py b/dulwich/server.py index 6fcae3a9..2afb45f9 100644 --- a/dulwich/server.py +++ b/dulwich/server.py @@ -1,1081 +1,1082 @@ # server.py -- Implementation of the server side git protocols # Copyright (C) 2008 John Carr # Coprygith (C) 2011-2012 Jelmer Vernooij # # This program is free software; you can redistribute it and/or # modify it under the terms of the GNU General Public License # as published by the Free Software Foundation; version 2 # or (at your option) any later version of the License. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program; if not, write to the Free Software # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, # MA 02110-1301, USA. """Git smart network protocol server implementation. For more detailed implementation on the network protocol, see the Documentation/technical directory in the cgit distribution, and in particular: * Documentation/technical/protocol-capabilities.txt * Documentation/technical/pack-protocol.txt Currently supported capabilities: * include-tag * thin-pack * multi_ack_detailed * multi_ack * side-band-64k * ofs-delta * no-progress * report-status * delete-refs * shallow """ import collections import os import socket import sys import zlib try: import SocketServer except ImportError: import socketserver as SocketServer from dulwich.errors import ( ApplyDeltaError, ChecksumMismatch, GitProtocolError, NotGitRepository, UnexpectedCommandError, ObjectFormatException, ) from dulwich import log_utils from dulwich.objects import ( Commit, valid_hexsha, ) from dulwich.pack import ( write_pack_objects, ) from dulwich.protocol import ( BufferedPktLineWriter, CAPABILITY_DELETE_REFS, CAPABILITY_INCLUDE_TAG, CAPABILITY_MULTI_ACK_DETAILED, CAPABILITY_MULTI_ACK, CAPABILITY_NO_DONE, CAPABILITY_NO_PROGRESS, CAPABILITY_OFS_DELTA, CAPABILITY_REPORT_STATUS, CAPABILITY_SHALLOW, CAPABILITY_SIDE_BAND_64K, CAPABILITY_THIN_PACK, COMMAND_DEEPEN, COMMAND_DONE, COMMAND_HAVE, COMMAND_SHALLOW, COMMAND_UNSHALLOW, COMMAND_WANT, MULTI_ACK, MULTI_ACK_DETAILED, Protocol, ProtocolFile, ReceivableProtocol, SIDE_BAND_CHANNEL_DATA, SIDE_BAND_CHANNEL_PROGRESS, SIDE_BAND_CHANNEL_FATAL, SINGLE_ACK, TCP_GIT_PORT, ZERO_SHA, ack_type, extract_capabilities, extract_want_line_capabilities, ) from dulwich.refs import ( write_info_refs, ) from dulwich.repo import ( Repo, ) logger = log_utils.getLogger(__name__) class Backend(object): """A backend for the Git smart server implementation.""" def open_repository(self, path): """Open the repository at a path. :param path: Path to the repository :raise NotGitRepository: no git repository was found at path :return: Instance of BackendRepo """ raise NotImplementedError(self.open_repository) class BackendRepo(object): """Repository abstraction used by the Git server. The methods required here are a subset of those provided by dulwich.repo.Repo. """ object_store = None refs = None def get_refs(self): """ Get all the refs in the repository :return: dict of name -> sha """ raise NotImplementedError def get_peeled(self, name): """Return the cached peeled value of a ref, if available. :param name: Name of the ref to peel :return: The peeled value of the ref. If the ref is known not point to a tag, this will be the SHA the ref refers to. If no cached information about a tag is available, this method may return None, but it should attempt to peel the tag if possible. """ return None def fetch_objects(self, determine_wants, graph_walker, progress, get_tagged=None): """ Yield the objects required for a list of commits. :param progress: is a callback to send progress messages to the client :param get_tagged: Function that returns a dict of pointed-to sha -> tag sha for including tags. """ raise NotImplementedError class DictBackend(Backend): """Trivial backend that looks up Git repositories in a dictionary.""" def __init__(self, repos): self.repos = repos def open_repository(self, path): logger.debug('Opening repository at %s', path) try: return self.repos[path] except KeyError: raise NotGitRepository( "No git repository was found at %(path)s" % dict(path=path) ) class FileSystemBackend(Backend): """Simple backend that looks up Git repositories in the local file system.""" def __init__(self, root=os.sep): super(FileSystemBackend, self).__init__() self.root = (os.path.abspath(root) + os.sep).replace(os.sep * 2, os.sep) def open_repository(self, path): logger.debug('opening repository at %s', path) abspath = os.path.abspath(os.path.join(self.root, path)) + os.sep normcase_abspath = os.path.normcase(abspath) normcase_root = os.path.normcase(self.root) if not normcase_abspath.startswith(normcase_root): raise NotGitRepository("Path %r not inside root %r" % (path, self.root)) return Repo(abspath) class Handler(object): """Smart protocol command handler base class.""" def __init__(self, backend, proto, http_req=None): self.backend = backend self.proto = proto self.http_req = http_req self._client_capabilities = None # Flags needed for the no-done capability self._done_received = False @classmethod def capability_line(cls): return b"".join([b" " + c for c in cls.capabilities()]) @classmethod def capabilities(cls): raise NotImplementedError(cls.capabilities) @classmethod def innocuous_capabilities(cls): return (CAPABILITY_INCLUDE_TAG, CAPABILITY_THIN_PACK, CAPABILITY_NO_PROGRESS, CAPABILITY_OFS_DELTA) @classmethod def required_capabilities(cls): """Return a list of capabilities that we require the client to have.""" return [] def set_client_capabilities(self, caps): allowable_caps = set(self.innocuous_capabilities()) allowable_caps.update(self.capabilities()) for cap in caps: if cap not in allowable_caps: raise GitProtocolError('Client asked for capability %s that ' 'was not advertised.' % cap) for cap in self.required_capabilities(): if cap not in caps: raise GitProtocolError('Client does not support required ' 'capability %s.' % cap) self._client_capabilities = set(caps) logger.info('Client capabilities: %s', caps) def has_capability(self, cap): if self._client_capabilities is None: raise GitProtocolError('Server attempted to access capability %s ' 'before asking client' % cap) return cap in self._client_capabilities def notify_done(self): self._done_received = True class UploadPackHandler(Handler): """Protocol handler for uploading a pack to the server.""" def __init__(self, backend, args, proto, http_req=None, advertise_refs=False): Handler.__init__(self, backend, proto, http_req=http_req) self.repo = backend.open_repository(args[0]) self._graph_walker = None self.advertise_refs = advertise_refs # A state variable for denoting that the have list is still # being processed, and the client is not accepting any other # data (such as side-band, see the progress method here). self._processing_have_lines = False @classmethod def capabilities(cls): return (CAPABILITY_MULTI_ACK_DETAILED, CAPABILITY_MULTI_ACK, CAPABILITY_SIDE_BAND_64K, CAPABILITY_THIN_PACK, CAPABILITY_OFS_DELTA, CAPABILITY_NO_PROGRESS, CAPABILITY_INCLUDE_TAG, CAPABILITY_SHALLOW, CAPABILITY_NO_DONE) @classmethod def required_capabilities(cls): return (CAPABILITY_SIDE_BAND_64K, CAPABILITY_THIN_PACK, CAPABILITY_OFS_DELTA) def progress(self, message): if self.has_capability(CAPABILITY_NO_PROGRESS) or self._processing_have_lines: return self.proto.write_sideband(SIDE_BAND_CHANNEL_PROGRESS, message) def get_tagged(self, refs=None, repo=None): """Get a dict of peeled values of tags to their original tag shas. :param refs: dict of refname -> sha of possible tags; defaults to all of the backend's refs. :param repo: optional Repo instance for getting peeled refs; defaults to the backend's repo, if available :return: dict of peeled_sha -> tag_sha, where tag_sha is the sha of a tag whose peeled value is peeled_sha. """ if not self.has_capability(CAPABILITY_INCLUDE_TAG): return {} if refs is None: refs = self.repo.get_refs() if repo is None: repo = getattr(self.repo, "repo", None) if repo is None: # Bail if we don't have a Repo available; this is ok since # clients must be able to handle if the server doesn't include # all relevant tags. # TODO: fix behavior when missing return {} tagged = {} for name, sha in refs.items(): peeled_sha = repo.get_peeled(name) if peeled_sha != sha: tagged[peeled_sha] = sha return tagged def handle(self): write = lambda x: self.proto.write_sideband(SIDE_BAND_CHANNEL_DATA, x) graph_walker = ProtocolGraphWalker(self, self.repo.object_store, self.repo.get_peeled) objects_iter = self.repo.fetch_objects( graph_walker.determine_wants, graph_walker, self.progress, get_tagged=self.get_tagged) # Note the fact that client is only processing responses related # to the have lines it sent, and any other data (including side- # band) will be be considered a fatal error. self._processing_have_lines = True # Did the process short-circuit (e.g. in a stateless RPC call)? Note # that the client still expects a 0-object pack in most cases. # Also, if it also happens that the object_iter is instantiated # with a graph walker with an implementation that talks over the # wire (which is this instance of this class) this will actually # iterate through everything and write things out to the wire. if len(objects_iter) == 0: return # The provided haves are processed, and it is safe to send side- # band data now. self._processing_have_lines = False if not graph_walker.handle_done( not self.has_capability(CAPABILITY_NO_DONE), self._done_received): return self.progress(b"dul-daemon says what\n") self.progress(("counting objects: %d, done.\n" % len(objects_iter)).encode('ascii')) write_pack_objects(ProtocolFile(None, write), objects_iter) self.progress(b"how was that, then?\n") # we are done self.proto.write_pkt_line(None) def _split_proto_line(line, allowed): """Split a line read from the wire. :param line: The line read from the wire. :param allowed: An iterable of command names that should be allowed. Command names not listed below as possible return values will be ignored. If None, any commands from the possible return values are allowed. :return: a tuple having one of the following forms: ('want', obj_id) ('have', obj_id) ('done', None) (None, None) (for a flush-pkt) :raise UnexpectedCommandError: if the line cannot be parsed into one of the allowed return values. """ if not line: fields = [None] else: fields = line.rstrip(b'\n').split(b' ', 1) command = fields[0] if allowed is not None and command not in allowed: raise UnexpectedCommandError(command) if len(fields) == 1 and command in (COMMAND_DONE, None): return (command, None) elif len(fields) == 2: if command in (COMMAND_WANT, COMMAND_HAVE, COMMAND_SHALLOW, COMMAND_UNSHALLOW): if not valid_hexsha(fields[1]): raise GitProtocolError("Invalid sha") return tuple(fields) elif command == COMMAND_DEEPEN: return command, int(fields[1]) raise GitProtocolError('Received invalid line from client: %r' % line) def _find_shallow(store, heads, depth): """Find shallow commits according to a given depth. :param store: An ObjectStore for looking up objects. :param heads: Iterable of head SHAs to start walking from. - :param depth: The depth of ancestors to include. + :param depth: The depth of ancestors to include. A depth of one includes + only the heads themselves. :return: A tuple of (shallow, not_shallow), sets of SHAs that should be considered shallow and unshallow according to the arguments. Note that these sets may overlap if a commit is reachable along multiple paths. """ parents = {} def get_parents(sha): result = parents.get(sha, None) if not result: result = store[sha].parents parents[sha] = result return result todo = [] # stack of (sha, depth) for head_sha in heads: obj = store.peel_sha(head_sha) if isinstance(obj, Commit): - todo.append((obj.id, 0)) + todo.append((obj.id, 1)) not_shallow = set() shallow = set() while todo: sha, cur_depth = todo.pop() if cur_depth < depth: not_shallow.add(sha) new_depth = cur_depth + 1 todo.extend((p, new_depth) for p in get_parents(sha)) else: shallow.add(sha) return shallow, not_shallow def _want_satisfied(store, haves, want, earliest): o = store[want] pending = collections.deque([o]) while pending: commit = pending.popleft() if commit.id in haves: return True if commit.type_name != b"commit": # non-commit wants are assumed to be satisfied continue for parent in commit.parents: parent_obj = store[parent] # TODO: handle parents with later commit times than children if parent_obj.commit_time >= earliest: pending.append(parent_obj) return False def _all_wants_satisfied(store, haves, wants): """Check whether all the current wants are satisfied by a set of haves. :param store: Object store to retrieve objects from :param haves: A set of commits we know the client has. :param wants: A set of commits the client wants :note: Wants are specified with set_wants rather than passed in since in the current interface they are determined outside this class. """ haves = set(haves) if haves: earliest = min([store[h].commit_time for h in haves]) else: earliest = 0 unsatisfied_wants = set() for want in wants: if not _want_satisfied(store, haves, want, earliest): return False return True class ProtocolGraphWalker(object): """A graph walker that knows the git protocol. As a graph walker, this class implements ack(), next(), and reset(). It also contains some base methods for interacting with the wire and walking the commit tree. The work of determining which acks to send is passed on to the implementation instance stored in _impl. The reason for this is that we do not know at object creation time what ack level the protocol requires. A call to set_ack_level() is required to set up the implementation, before any calls to next() or ack() are made. """ def __init__(self, handler, object_store, get_peeled): self.handler = handler self.store = object_store self.get_peeled = get_peeled self.proto = handler.proto self.http_req = handler.http_req self.advertise_refs = handler.advertise_refs self._wants = [] self.shallow = set() self.client_shallow = set() self.unshallow = set() self._cached = False self._cache = [] self._cache_index = 0 self._impl = None def determine_wants(self, heads): """Determine the wants for a set of heads. The given heads are advertised to the client, who then specifies which refs he wants using 'want' lines. This portion of the protocol is the same regardless of ack type, and in fact is used to set the ack type of the ProtocolGraphWalker. If the client has the 'shallow' capability, this method also reads and responds to the 'shallow' and 'deepen' lines from the client. These are not part of the wants per se, but they set up necessary state for walking the graph. Additionally, later code depends on this method consuming everything up to the first 'have' line. :param heads: a dict of refname->SHA1 to advertise :return: a list of SHA1s requested by the client """ values = set(heads.values()) if self.advertise_refs or not self.http_req: for i, (ref, sha) in enumerate(sorted(heads.items())): line = sha + b' ' + ref if not i: line += b'\x00' + self.handler.capability_line() self.proto.write_pkt_line(line + b'\n') peeled_sha = self.get_peeled(ref) if peeled_sha != sha: self.proto.write_pkt_line(peeled_sha + b' ' + ref + b'^{}\n') # i'm done.. self.proto.write_pkt_line(None) if self.advertise_refs: return [] # Now client will sending want want want commands want = self.proto.read_pkt_line() if not want: return [] line, caps = extract_want_line_capabilities(want) self.handler.set_client_capabilities(caps) self.set_ack_type(ack_type(caps)) allowed = (COMMAND_WANT, COMMAND_SHALLOW, COMMAND_DEEPEN, None) command, sha = _split_proto_line(line, allowed) want_revs = [] while command == COMMAND_WANT: if sha not in values: raise GitProtocolError( 'Client wants invalid object %s' % sha) want_revs.append(sha) command, sha = self.read_proto_line(allowed) self.set_wants(want_revs) if command in (COMMAND_SHALLOW, COMMAND_DEEPEN): self.unread_proto_line(command, sha) self._handle_shallow_request(want_revs) if self.http_req and self.proto.eof(): # The client may close the socket at this point, expecting a # flush-pkt from the server. We might be ready to send a packfile at # this point, so we need to explicitly short-circuit in this case. return [] return want_revs def unread_proto_line(self, command, value): if isinstance(value, int): value = str(value).encode('ascii') self.proto.unread_pkt_line(command + b' ' + value) def ack(self, have_ref): if len(have_ref) != 40: raise ValueError("invalid sha %r" % have_ref) return self._impl.ack(have_ref) def reset(self): self._cached = True self._cache_index = 0 def next(self): if not self._cached: if not self._impl and self.http_req: return None return next(self._impl) self._cache_index += 1 if self._cache_index > len(self._cache): return None return self._cache[self._cache_index] __next__ = next def read_proto_line(self, allowed): """Read a line from the wire. :param allowed: An iterable of command names that should be allowed. :return: A tuple of (command, value); see _split_proto_line. :raise UnexpectedCommandError: If an error occurred reading the line. """ return _split_proto_line(self.proto.read_pkt_line(), allowed) def _handle_shallow_request(self, wants): while True: command, val = self.read_proto_line((COMMAND_DEEPEN, COMMAND_SHALLOW)) if command == COMMAND_DEEPEN: depth = val break self.client_shallow.add(val) self.read_proto_line((None,)) # consume client's flush-pkt shallow, not_shallow = _find_shallow(self.store, wants, depth) # Update self.shallow instead of reassigning it since we passed a # reference to it before this method was called. self.shallow.update(shallow - not_shallow) new_shallow = self.shallow - self.client_shallow unshallow = self.unshallow = not_shallow & self.client_shallow for sha in sorted(new_shallow): self.proto.write_pkt_line(COMMAND_SHALLOW + b' ' + sha) for sha in sorted(unshallow): self.proto.write_pkt_line(COMMAND_UNSHALLOW + b' ' + sha) self.proto.write_pkt_line(None) def notify_done(self): # relay the message down to the handler. self.handler.notify_done() def send_ack(self, sha, ack_type=b''): if ack_type: ack_type = b' ' + ack_type self.proto.write_pkt_line(b'ACK ' + sha + ack_type + b'\n') def send_nak(self): self.proto.write_pkt_line(b'NAK\n') def handle_done(self, done_required, done_received): # Delegate this to the implementation. return self._impl.handle_done(done_required, done_received) def set_wants(self, wants): self._wants = wants def all_wants_satisfied(self, haves): """Check whether all the current wants are satisfied by a set of haves. :param haves: A set of commits we know the client has. :note: Wants are specified with set_wants rather than passed in since in the current interface they are determined outside this class. """ return _all_wants_satisfied(self.store, haves, self._wants) def set_ack_type(self, ack_type): impl_classes = { MULTI_ACK: MultiAckGraphWalkerImpl, MULTI_ACK_DETAILED: MultiAckDetailedGraphWalkerImpl, SINGLE_ACK: SingleAckGraphWalkerImpl, } self._impl = impl_classes[ack_type](self) _GRAPH_WALKER_COMMANDS = (COMMAND_HAVE, COMMAND_DONE, None) class SingleAckGraphWalkerImpl(object): """Graph walker implementation that speaks the single-ack protocol.""" def __init__(self, walker): self.walker = walker self._common = [] def ack(self, have_ref): if not self._common: self.walker.send_ack(have_ref) self._common.append(have_ref) def next(self): command, sha = self.walker.read_proto_line(_GRAPH_WALKER_COMMANDS) if command in (None, COMMAND_DONE): # defer the handling of done self.walker.notify_done() return None elif command == COMMAND_HAVE: return sha __next__ = next def handle_done(self, done_required, done_received): if not self._common: self.walker.send_nak() if done_required and not done_received: # we are not done, especially when done is required; skip # the pack for this request and especially do not handle # the done. return False if not done_received and not self._common: # Okay we are not actually done then since the walker picked # up no haves. This is usually triggered when client attempts # to pull from a source that has no common base_commit. # See: test_server.MultiAckDetailedGraphWalkerImplTestCase.\ # test_multi_ack_stateless_nodone return False return True class MultiAckGraphWalkerImpl(object): """Graph walker implementation that speaks the multi-ack protocol.""" def __init__(self, walker): self.walker = walker self._found_base = False self._common = [] def ack(self, have_ref): self._common.append(have_ref) if not self._found_base: self.walker.send_ack(have_ref, b'continue') if self.walker.all_wants_satisfied(self._common): self._found_base = True # else we blind ack within next def next(self): while True: command, sha = self.walker.read_proto_line(_GRAPH_WALKER_COMMANDS) if command is None: self.walker.send_nak() # in multi-ack mode, a flush-pkt indicates the client wants to # flush but more have lines are still coming continue elif command == COMMAND_DONE: self.walker.notify_done() return None elif command == COMMAND_HAVE: if self._found_base: # blind ack self.walker.send_ack(sha, b'continue') return sha __next__ = next def handle_done(self, done_required, done_received): if done_required and not done_received: # we are not done, especially when done is required; skip # the pack for this request and especially do not handle # the done. return False if not done_received and not self._common: # Okay we are not actually done then since the walker picked # up no haves. This is usually triggered when client attempts # to pull from a source that has no common base_commit. # See: test_server.MultiAckDetailedGraphWalkerImplTestCase.\ # test_multi_ack_stateless_nodone return False # don't nak unless no common commits were found, even if not # everything is satisfied if self._common: self.walker.send_ack(self._common[-1]) else: self.walker.send_nak() return True class MultiAckDetailedGraphWalkerImpl(object): """Graph walker implementation speaking the multi-ack-detailed protocol.""" def __init__(self, walker): self.walker = walker self._common = [] def ack(self, have_ref): # Should only be called iff have_ref is common self._common.append(have_ref) self.walker.send_ack(have_ref, b'common') def next(self): while True: command, sha = self.walker.read_proto_line(_GRAPH_WALKER_COMMANDS) if command is None: if self.walker.all_wants_satisfied(self._common): self.walker.send_ack(self._common[-1], b'ready') self.walker.send_nak() if self.walker.http_req: # The HTTP version of this request a flush-pkt always # signifies an end of request, so we also return # nothing here as if we are done (but not really, as # it depends on whether no-done capability was # specified and that's handled in handle_done which # may or may not call post_nodone_check depending on # that). return None elif command == COMMAND_DONE: # Let the walker know that we got a done. self.walker.notify_done() break elif command == COMMAND_HAVE: # return the sha and let the caller ACK it with the # above ack method. return sha # don't nak unless no common commits were found, even if not # everything is satisfied __next__ = next def handle_done(self, done_required, done_received): if done_required and not done_received: # we are not done, especially when done is required; skip # the pack for this request and especially do not handle # the done. return False if not done_received and not self._common: # Okay we are not actually done then since the walker picked # up no haves. This is usually triggered when client attempts # to pull from a source that has no common base_commit. # See: test_server.MultiAckDetailedGraphWalkerImplTestCase.\ # test_multi_ack_stateless_nodone return False # don't nak unless no common commits were found, even if not # everything is satisfied if self._common: self.walker.send_ack(self._common[-1]) else: self.walker.send_nak() return True class ReceivePackHandler(Handler): """Protocol handler for downloading a pack from the client.""" def __init__(self, backend, args, proto, http_req=None, advertise_refs=False): Handler.__init__(self, backend, proto, http_req=http_req) self.repo = backend.open_repository(args[0]) self.advertise_refs = advertise_refs @classmethod def capabilities(cls): return (CAPABILITY_REPORT_STATUS, CAPABILITY_DELETE_REFS, CAPABILITY_OFS_DELTA, CAPABILITY_SIDE_BAND_64K, CAPABILITY_NO_DONE) def _apply_pack(self, refs): all_exceptions = (IOError, OSError, ChecksumMismatch, ApplyDeltaError, AssertionError, socket.error, zlib.error, ObjectFormatException) status = [] will_send_pack = False for command in refs: if command[1] != ZERO_SHA: will_send_pack = True if will_send_pack: # TODO: more informative error messages than just the exception string try: recv = getattr(self.proto, "recv", None) self.repo.object_store.add_thin_pack(self.proto.read, recv) status.append((b'unpack', b'ok')) except all_exceptions as e: status.append((b'unpack', str(e).replace('\n', ''))) # The pack may still have been moved in, but it may contain broken # objects. We trust a later GC to clean it up. else: # The git protocol want to find a status entry related to unpack process # even if no pack data has been sent. status.append((b'unpack', b'ok')) for oldsha, sha, ref in refs: ref_status = b'ok' try: if sha == ZERO_SHA: if not CAPABILITY_DELETE_REFS in self.capabilities(): raise GitProtocolError( 'Attempted to delete refs without delete-refs ' 'capability.') try: del self.repo.refs[ref] except all_exceptions: ref_status = b'failed to delete' else: try: self.repo.refs[ref] = sha except all_exceptions: ref_status = b'failed to write' except KeyError as e: ref_status = b'bad ref' status.append((ref, ref_status)) return status def _report_status(self, status): if self.has_capability(CAPABILITY_SIDE_BAND_64K): writer = BufferedPktLineWriter( lambda d: self.proto.write_sideband(SIDE_BAND_CHANNEL_DATA, d)) write = writer.write def flush(): writer.flush() self.proto.write_pkt_line(None) else: write = self.proto.write_pkt_line flush = lambda: None for name, msg in status: if name == b'unpack': write(b'unpack ' + msg + b'\n') elif msg == b'ok': write(b'ok ' + name + b'\n') else: write(b'ng ' + name + b' ' + msg + b'\n') write(None) flush() def handle(self): if self.advertise_refs or not self.http_req: refs = sorted(self.repo.get_refs().items()) if refs: self.proto.write_pkt_line( refs[0][1] + b' ' + refs[0][0] + b'\0' + self.capability_line() + b'\n') for i in range(1, len(refs)): ref = refs[i] self.proto.write_pkt_line(ref[1] + b' ' + ref[0] + b'\n') else: self.proto.write_pkt_line(ZERO_SHA + b" capabilities^{}\0" + self.capability_line()) self.proto.write_pkt_line(None) if self.advertise_refs: return client_refs = [] ref = self.proto.read_pkt_line() # if ref is none then client doesnt want to send us anything.. if ref is None: return ref, caps = extract_capabilities(ref) self.set_client_capabilities(caps) # client will now send us a list of (oldsha, newsha, ref) while ref: client_refs.append(ref.split()) ref = self.proto.read_pkt_line() # backend can now deal with this refs and read a pack using self.read status = self._apply_pack(client_refs) # when we have read all the pack from the client, send a status report # if the client asked for it if self.has_capability(CAPABILITY_REPORT_STATUS): self._report_status(status) # Default handler classes for git services. DEFAULT_HANDLERS = { b'git-upload-pack': UploadPackHandler, b'git-receive-pack': ReceivePackHandler, } class TCPGitRequestHandler(SocketServer.StreamRequestHandler): def __init__(self, handlers, *args, **kwargs): self.handlers = handlers SocketServer.StreamRequestHandler.__init__(self, *args, **kwargs) def handle(self): proto = ReceivableProtocol(self.connection.recv, self.wfile.write) command, args = proto.read_cmd() logger.info('Handling %s request, args=%s', command, args) cls = self.handlers.get(command, None) if not callable(cls): raise GitProtocolError('Invalid service %s' % command) h = cls(self.server.backend, args, proto) h.handle() class TCPGitServer(SocketServer.TCPServer): allow_reuse_address = True serve = SocketServer.TCPServer.serve_forever def _make_handler(self, *args, **kwargs): return TCPGitRequestHandler(self.handlers, *args, **kwargs) def __init__(self, backend, listen_addr, port=TCP_GIT_PORT, handlers=None): self.handlers = dict(DEFAULT_HANDLERS) if handlers is not None: self.handlers.update(handlers) self.backend = backend logger.info('Listening for TCP connections on %s:%d', listen_addr, port) SocketServer.TCPServer.__init__(self, (listen_addr, port), self._make_handler) def verify_request(self, request, client_address): logger.info('Handling request from %s', client_address) return True def handle_error(self, request, client_address): logger.exception('Exception happened during processing of request ' 'from %s', client_address) def main(argv=sys.argv): """Entry point for starting a TCP git server.""" import optparse parser = optparse.OptionParser() parser.add_option("-l", "--listen_address", dest="listen_address", default="localhost", help="Binding IP address.") parser.add_option("-p", "--port", dest="port", type=int, default=TCP_GIT_PORT, help="Binding TCP port.") options, args = parser.parse_args(argv) log_utils.default_logging_config() if len(args) > 1: gitdir = args[1] else: gitdir = '.' from dulwich import porcelain porcelain.daemon(gitdir, address=options.listen_address, port=options.port) def serve_command(handler_cls, argv=sys.argv, backend=None, inf=sys.stdin, outf=sys.stdout): """Serve a single command. This is mostly useful for the implementation of commands used by e.g. git+ssh. :param handler_cls: `Handler` class to use for the request :param argv: execv-style command-line arguments. Defaults to sys.argv. :param backend: `Backend` to use :param inf: File-like object to read from, defaults to standard input. :param outf: File-like object to write to, defaults to standard output. :return: Exit code for use with sys.exit. 0 on success, 1 on failure. """ if backend is None: backend = FileSystemBackend() def send_fn(data): outf.write(data) outf.flush() proto = Protocol(inf.read, send_fn) handler = handler_cls(backend, argv[1:], proto) # FIXME: Catch exceptions and write a single-line summary to outf. handler.handle() return 0 def generate_info_refs(repo): """Generate an info refs file.""" refs = repo.get_refs() return write_info_refs(refs, repo.object_store) def generate_objects_info_packs(repo): """Generate an index for for packs.""" for pack in repo.object_store.packs: yield b'P ' + pack.data.filename.encode(sys.getfilesystemencoding()) + b'\n' def update_server_info(repo): """Generate server info for dumb file access. This generates info/refs and objects/info/packs, similar to "git update-server-info". """ repo._put_named_file(os.path.join('info', 'refs'), b"".join(generate_info_refs(repo))) repo._put_named_file(os.path.join('objects', 'info', 'packs'), b"".join(generate_objects_info_packs(repo))) if __name__ == '__main__': main() diff --git a/dulwich/tests/compat/server_utils.py b/dulwich/tests/compat/server_utils.py index 164cfeea..67231887 100644 --- a/dulwich/tests/compat/server_utils.py +++ b/dulwich/tests/compat/server_utils.py @@ -1,279 +1,300 @@ # server_utils.py -- Git server compatibility utilities # Copyright (C) 2010 Google, Inc. # # This program is free software; you can redistribute it and/or # modify it under the terms of the GNU General Public License # as published by the Free Software Foundation; version 2 # of the License or (at your option) any later version of # the License. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program; if not, write to the Free Software # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, # MA 02110-1301, USA. """Utilities for testing git server compatibility.""" import errno import os import shutil import socket import tempfile from dulwich.repo import Repo from dulwich.objects import hex_to_sha from dulwich.server import ( ReceivePackHandler, ) from dulwich.tests.utils import ( tear_down_repo, ) from dulwich.tests.compat.utils import ( run_git_or_fail, ) from dulwich.tests.compat.utils import require_git_version class _StubRepo(object): """A stub repo that just contains a path to tear down.""" def __init__(self, name): temp_dir = tempfile.mkdtemp() self.path = os.path.join(temp_dir, name) os.mkdir(self.path) def close(self): pass def _get_shallow(repo): shallow_file = repo.get_named_file('shallow') if not shallow_file: return [] shallows = [] with shallow_file: for line in shallow_file: sha = line.strip() if not sha: continue hex_to_sha(sha) shallows.append(sha) return shallows class ServerTests(object): """Base tests for testing servers. Does not inherit from TestCase so tests are not automatically run. """ min_single_branch_version = (1, 7, 10,) def import_repos(self): self._old_repo = self.import_repo('server_old.export') self._new_repo = self.import_repo('server_new.export') def url(self, port): return '%s://localhost:%s/' % (self.protocol, port) def branch_args(self, branches=None): if branches is None: branches = ['master', 'branch'] return ['%s:%s' % (b, b) for b in branches] def test_push_to_dulwich(self): self.import_repos() self.assertReposNotEqual(self._old_repo, self._new_repo) port = self._start_server(self._old_repo) run_git_or_fail(['push', self.url(port)] + self.branch_args(), cwd=self._new_repo.path) self.assertReposEqual(self._old_repo, self._new_repo) def test_push_to_dulwich_no_op(self): self._old_repo = self.import_repo('server_old.export') self._new_repo = self.import_repo('server_old.export') self.assertReposEqual(self._old_repo, self._new_repo) port = self._start_server(self._old_repo) run_git_or_fail(['push', self.url(port)] + self.branch_args(), cwd=self._new_repo.path) self.assertReposEqual(self._old_repo, self._new_repo) def test_push_to_dulwich_remove_branch(self): self._old_repo = self.import_repo('server_old.export') self._new_repo = self.import_repo('server_old.export') self.assertReposEqual(self._old_repo, self._new_repo) port = self._start_server(self._old_repo) run_git_or_fail(['push', self.url(port), ":master"], cwd=self._new_repo.path) self.assertEqual( list(self._old_repo.get_refs().keys()), [b"refs/heads/branch"]) def test_fetch_from_dulwich(self): self.import_repos() self.assertReposNotEqual(self._old_repo, self._new_repo) port = self._start_server(self._new_repo) run_git_or_fail(['fetch', self.url(port)] + self.branch_args(), cwd=self._old_repo.path) # flush the pack cache so any new packs are picked up self._old_repo.object_store._pack_cache_time = 0 self.assertReposEqual(self._old_repo, self._new_repo) def test_fetch_from_dulwich_no_op(self): self._old_repo = self.import_repo('server_old.export') self._new_repo = self.import_repo('server_old.export') self.assertReposEqual(self._old_repo, self._new_repo) port = self._start_server(self._new_repo) run_git_or_fail(['fetch', self.url(port)] + self.branch_args(), cwd=self._old_repo.path) # flush the pack cache so any new packs are picked up self._old_repo.object_store._pack_cache_time = 0 self.assertReposEqual(self._old_repo, self._new_repo) def test_clone_from_dulwich_empty(self): old_repo_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, old_repo_dir) self._old_repo = Repo.init_bare(old_repo_dir) port = self._start_server(self._old_repo) new_repo_base_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, new_repo_base_dir) new_repo_dir = os.path.join(new_repo_base_dir, 'empty_new') run_git_or_fail(['clone', self.url(port), new_repo_dir], cwd=new_repo_base_dir) new_repo = Repo(new_repo_dir) self.assertReposEqual(self._old_repo, new_repo) def test_lsremote_from_dulwich(self): self._repo = self.import_repo('server_old.export') port = self._start_server(self._repo) o = run_git_or_fail(['ls-remote', self.url(port)]) self.assertEqual(len(o.split(b'\n')), 4) def test_new_shallow_clone_from_dulwich(self): require_git_version(self.min_single_branch_version) self._source_repo = self.import_repo('server_new.export') self._stub_repo = _StubRepo('shallow') self.addCleanup(tear_down_repo, self._stub_repo) port = self._start_server(self._source_repo) # Fetch at depth 1 run_git_or_fail(['clone', '--mirror', '--depth=1', '--no-single-branch', self.url(port), self._stub_repo.path]) clone = self._stub_repo = Repo(self._stub_repo.path) - expected_shallow = [b'94de09a530df27ac3bb613aaecdd539e0a0655e1', - b'da5cd81e1883c62a25bb37c4d1f8ad965b29bf8d'] + expected_shallow = [b'35e0b59e187dd72a0af294aedffc213eaa4d03ff', + b'514dc6d3fbfe77361bcaef320c4d21b72bc10be9'] self.assertEqual(expected_shallow, _get_shallow(clone)) self.assertReposNotEqual(clone, self._source_repo) + def test_shallow_clone_from_git_is_identical(self): + require_git_version(self.min_single_branch_version) + self._source_repo = self.import_repo('server_new.export') + self._stub_repo_git = _StubRepo('shallow-git') + self.addCleanup(tear_down_repo, self._stub_repo_git) + self._stub_repo_dw = _StubRepo('shallow-dw') + self.addCleanup(tear_down_repo, self._stub_repo_dw) + + # shallow clone using stock git, then using dulwich + run_git_or_fail(['clone', '--mirror', '--depth=1', '--no-single-branch', + 'file://' + self._source_repo.path, + self._stub_repo_git.path]) + + port = self._start_server(self._source_repo) + run_git_or_fail(['clone', '--mirror', '--depth=1', '--no-single-branch', + self.url(port), self._stub_repo_dw.path]) + + # compare the two clones; they should be equal + self.assertReposEqual(Repo(self._stub_repo_git.path), + Repo(self._stub_repo_dw.path)) + def test_fetch_same_depth_into_shallow_clone_from_dulwich(self): require_git_version(self.min_single_branch_version) self._source_repo = self.import_repo('server_new.export') self._stub_repo = _StubRepo('shallow') self.addCleanup(tear_down_repo, self._stub_repo) port = self._start_server(self._source_repo) - # Fetch at depth 1 - run_git_or_fail(['clone', '--mirror', '--depth=1', '--no-single-branch', + # Fetch at depth 2 + run_git_or_fail(['clone', '--mirror', '--depth=2', '--no-single-branch', self.url(port), self._stub_repo.path]) clone = self._stub_repo = Repo(self._stub_repo.path) # Fetching at the same depth is a no-op. run_git_or_fail( - ['fetch', '--depth=1', self.url(port)] + self.branch_args(), + ['fetch', '--depth=2', self.url(port)] + self.branch_args(), cwd=self._stub_repo.path) expected_shallow = [b'94de09a530df27ac3bb613aaecdd539e0a0655e1', b'da5cd81e1883c62a25bb37c4d1f8ad965b29bf8d'] self.assertEqual(expected_shallow, _get_shallow(clone)) self.assertReposNotEqual(clone, self._source_repo) def test_fetch_full_depth_into_shallow_clone_from_dulwich(self): require_git_version(self.min_single_branch_version) self._source_repo = self.import_repo('server_new.export') self._stub_repo = _StubRepo('shallow') self.addCleanup(tear_down_repo, self._stub_repo) port = self._start_server(self._source_repo) - # Fetch at depth 1 - run_git_or_fail(['clone', '--mirror', '--depth=1', '--no-single-branch', + # Fetch at depth 2 + run_git_or_fail(['clone', '--mirror', '--depth=2', '--no-single-branch', self.url(port), self._stub_repo.path]) clone = self._stub_repo = Repo(self._stub_repo.path) # Fetching at the same depth is a no-op. run_git_or_fail( - ['fetch', '--depth=1', self.url(port)] + self.branch_args(), + ['fetch', '--depth=2', self.url(port)] + self.branch_args(), cwd=self._stub_repo.path) - # The whole repo only has depth 3, so it should equal server_new. + # The whole repo only has depth 4, so it should equal server_new. run_git_or_fail( - ['fetch', '--depth=3', self.url(port)] + self.branch_args(), + ['fetch', '--depth=4', self.url(port)] + self.branch_args(), cwd=self._stub_repo.path) self.assertEqual([], _get_shallow(clone)) self.assertReposEqual(clone, self._source_repo) def test_fetch_from_dulwich_issue_88_standard(self): # Basically an integration test to see that the ACK/NAK # generation works on repos with common head. self._source_repo = self.import_repo('issue88_expect_ack_nak_server.export') self._client_repo = self.import_repo('issue88_expect_ack_nak_client.export') port = self._start_server(self._source_repo) run_git_or_fail(['fetch', self.url(port), 'master',], cwd=self._client_repo.path) self.assertObjectStoreEqual( self._source_repo.object_store, self._client_repo.object_store) def test_fetch_from_dulwich_issue_88_alternative(self): # likewise, but the case where the two repos have no common parent self._source_repo = self.import_repo('issue88_expect_ack_nak_other.export') self._client_repo = self.import_repo('issue88_expect_ack_nak_client.export') port = self._start_server(self._source_repo) self.assertRaises(KeyError, self._client_repo.get_object, b'02a14da1fc1fc13389bbf32f0af7d8899f2b2323') run_git_or_fail(['fetch', self.url(port), 'master',], cwd=self._client_repo.path) self.assertEqual(b'commit', self._client_repo.get_object( b'02a14da1fc1fc13389bbf32f0af7d8899f2b2323').type_name) def test_push_to_dulwich_issue_88_standard(self): # Same thing, but we reverse the role of the server/client # and do a push instead. self._source_repo = self.import_repo('issue88_expect_ack_nak_client.export') self._client_repo = self.import_repo('issue88_expect_ack_nak_server.export') port = self._start_server(self._source_repo) run_git_or_fail(['push', self.url(port), 'master',], cwd=self._client_repo.path) self.assertReposEqual(self._source_repo, self._client_repo) # TODO(dborowitz): Come up with a better way of testing various permutations of # capabilities. The only reason it is the way it is now is that side-band-64k # was only recently introduced into git-receive-pack. class NoSideBand64kReceivePackHandler(ReceivePackHandler): """ReceivePackHandler that does not support side-band-64k.""" @classmethod def capabilities(cls): return tuple(c for c in ReceivePackHandler.capabilities() if c != b'side-band-64k') def ignore_error(error): """Check whether this error is safe to ignore.""" (e_type, e_value, e_tb) = error return (issubclass(e_type, socket.error) and e_value[0] in (errno.ECONNRESET, errno.EPIPE)) diff --git a/dulwich/tests/compat/test_client.py b/dulwich/tests/compat/test_client.py index e05a192b..8d388046 100644 --- a/dulwich/tests/compat/test_client.py +++ b/dulwich/tests/compat/test_client.py @@ -1,518 +1,533 @@ # test_client.py -- Compatibilty tests for git client. # Copyright (C) 2010 Google, Inc. # # This program is free software; you can redistribute it and/or # modify it under the terms of the GNU General Public License # as published by the Free Software Foundation; version 2 # of the License or (at your option) any later version of # the License. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program; if not, write to the Free Software # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, # MA 02110-1301, USA. """Compatibilty tests between the Dulwich client and the cgit server.""" from contextlib import closing 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 if sys.platform == 'win32': import ctypes from dulwich import ( client, errors, file, index, protocol, objects, repo, ) from dulwich.tests import ( get_safe_env, SkipTest, + expectedFailure, ) from dulwich.tests.utils import ( skipIfPY3, ) from dulwich.tests.compat.utils import ( CompatTestCase, check_for_daemon, import_repo_to_dir, run_git_or_fail, _DEFAULT_GIT, rmtree_ro, ) 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 closing(repo.Repo(repo_dir)) as src: with closing(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 closing(repo.Repo(srcpath)) as src: sendrefs = dict(src.get_refs()) del sendrefs[b'HEAD'] - c.send_pack(self._build_path('/dest'), lambda _: sendrefs, + c.send_pack(self._build_path(b'/dest'), lambda _: sendrefs, src.object_store.generate_pack_contents) 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 closing(repo.Repo(srcpath)) as src: sendrefs = dict(src.get_refs()) del sendrefs[b'HEAD'] - c.send_pack(self._build_path('/dest'), lambda _: sendrefs, + c.send_pack(self._build_path(b'/dest'), lambda _: sendrefs, src.object_store.generate_pack_contents) 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 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 closing(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) + c.send_pack(self._build_path(b'/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 closing(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) + c.send_pack(self._build_path(b'/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) + c.archive(self._build_path(b'/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 closing(repo.Repo(os.path.join(self.gitroot, 'dest'))) as dest: - refs = c.fetch(self._build_path('/server_new.export'), dest) + refs = c.fetch(self._build_path(b'/server_new.export'), dest) for r in 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 closing(repo.Repo(repo_dir)) as dest: - refs = c.fetch(self._build_path('/dest'), dest) + refs = c.fetch(self._build_path(b'/dest'), dest) for r in 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 closing(repo.Repo(os.path.join(self.gitroot, 'dest'))) as dest: - refs = c.fetch(self._build_path('/server_new.export'), dest) + refs = c.fetch(self._build_path(b'/server_new.export'), dest) for r in 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 closing(repo.Repo(os.path.join(self.gitroot, 'dest'))) as dest: - refs = c.fetch(self._build_path('/server_new.export'), dest, + refs = c.fetch(self._build_path(b'/server_new.export'), dest, lambda refs: [protocol.ZERO_SHA]) for r in refs.items(): dest.refs.set_if_equals(r[0], None, r[1]) def test_send_remove_branch(self): with closing(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'] gen_pack = lambda have, want: [] c = self._client() self.assertEqual(dest.refs[b"refs/heads/abranch"], dummy_commit) - c.send_pack(self._build_path('/dest'), lambda _: sendrefs, gen_pack) + c.send_pack(self._build_path(b'/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(b'/server_new.export')) + + repo_dir = os.path.join(self.gitroot, 'server_new.export') + with closing(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) env = get_safe_env() 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, env=env, 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(b'localhost') + return client.TCPGitClient('localhost') def _build_path(self, path): - return path.encode(sys.getfilesystemencoding()) + 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): cmd, path = command - cmd = cmd.split('-', 1) + cmd = cmd.split(b'-', 1) p = subprocess.Popen(cmd + [path], bufsize=0, env=get_safe_env(), 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(b'localhost') + return client.SSHGitClient('localhost') def _build_path(self, path): - return self.gitroot + path + return self.gitroot.encode(sys.getfilesystemencoding()) + 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 + return self.gitroot.encode(sys.getfilesystemencoding()) + 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, 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 if self.headers.typeheader is None: env['CONTENT_TYPE'] = self.headers.type else: env['CONTENT_TYPE'] = self.headers.typeheader 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 = filter(None, self.headers.getheaders('cookie')) if co: env['HTTP_COOKIE'] = ', '.join(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.send_response(200, "Script output follows") 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) @skipIfPY3 class DulwichHttpClientTest(CompatTestCase, DulwichClientTestBase): min_git_version = (1, 7, 0, 2) def setUp(self): CompatTestCase.setUp(self) DulwichClientTestBase.setUp(self) self._httpd = HTTPGitServer(("localhost", 0), self.gitroot) self.addCleanup(self._httpd.shutdown) threading.Thread(target=self._httpd.serve_forever).start() run_git_or_fail(['config', 'http.uploadpack', 'true'], cwd=self.dest) run_git_or_fail(['config', 'http.receivepack', 'true'], cwd=self.dest) def tearDown(self): DulwichClientTestBase.tearDown(self) CompatTestCase.tearDown(self) self._httpd.shutdown() self._httpd.socket.close() def _client(self): return client.HttpGitClient(self._httpd.get_url()) def _build_path(self, path): return path def test_archive(self): raise SkipTest("exporting archives not supported over http") diff --git a/dulwich/tests/compat/test_web.py b/dulwich/tests/compat/test_web.py index 6773af6f..a84d1ea8 100644 --- a/dulwich/tests/compat/test_web.py +++ b/dulwich/tests/compat/test_web.py @@ -1,202 +1,207 @@ # test_web.py -- Compatibility tests for the git web server. # Copyright (C) 2010 Google, Inc. # # This program is free software; you can redistribute it and/or # modify it under the terms of the GNU General Public License # as published by the Free Software Foundation; version 2 # of the License or (at your option) any later version of # the License. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program; if not, write to the Free Software # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, # MA 02110-1301, USA. """Compatibility tests between Dulwich and the cgit HTTP server. warning: these tests should be fairly stable, but when writing/debugging new tests, deadlocks may freeze the test process such that it cannot be Ctrl-C'ed. On POSIX systems, you can kill the tests with Ctrl-Z, "kill %". """ import threading from wsgiref import simple_server import sys from dulwich.server import ( DictBackend, UploadPackHandler, ReceivePackHandler, ) from dulwich.tests import ( SkipTest, skipIf, ) from dulwich.tests.utils import ( skipIfPY3, ) from dulwich.web import ( make_wsgi_chain, HTTPGitApplication, WSGIRequestHandlerLogger, WSGIServerLogger, ) from dulwich.tests.compat.server_utils import ( ServerTests, NoSideBand64kReceivePackHandler, ) from dulwich.tests.compat.utils import ( CompatTestCase, ) @skipIf(sys.platform == 'win32', 'Broken on windows, with very long fail time.') class WebTests(ServerTests): """Base tests for web server tests. Contains utility and setUp/tearDown methods, but does non inherit from TestCase so tests are not automatically run. """ protocol = 'http' def _start_server(self, repo): backend = DictBackend({'/': repo}) app = self._make_app(backend) dul_server = simple_server.make_server( 'localhost', 0, app, server_class=WSGIServerLogger, handler_class=WSGIRequestHandlerLogger) self.addCleanup(dul_server.shutdown) self.addCleanup(dul_server.server_close) threading.Thread(target=dul_server.serve_forever).start() self._server = dul_server _, port = dul_server.socket.getsockname() return port @skipIf(sys.platform == 'win32', 'Broken on windows, with very long fail time.') @skipIfPY3 class SmartWebTestCase(WebTests, CompatTestCase): """Test cases for smart HTTP server. This server test case does not use side-band-64k in git-receive-pack. """ min_git_version = (1, 6, 6) def _handlers(self): return {'git-receive-pack': NoSideBand64kReceivePackHandler} def _check_app(self, app): receive_pack_handler_cls = app.handlers[b'git-receive-pack'] caps = receive_pack_handler_cls.capabilities() self.assertFalse(b'side-band-64k' in caps) def _make_app(self, backend): app = make_wsgi_chain(backend, handlers=self._handlers()) to_check = app # peel back layers until we're at the base application while not issubclass(to_check.__class__, HTTPGitApplication): to_check = to_check.app self._check_app(to_check) return app def patch_capabilities(handler, caps_removed): # Patch a handler's capabilities by specifying a list of them to be # removed, and return the original classmethod for restoration. original_capabilities = handler.capabilities filtered_capabilities = tuple( i for i in original_capabilities() if i not in caps_removed) def capabilities(cls): return filtered_capabilities handler.capabilities = classmethod(capabilities) return original_capabilities @skipIf(sys.platform == 'win32', 'Broken on windows, with very long fail time.') @skipIfPY3 class SmartWebSideBand64kTestCase(SmartWebTestCase): """Test cases for smart HTTP server with side-band-64k support.""" # side-band-64k in git-receive-pack was introduced in git 1.7.0.2 min_git_version = (1, 7, 0, 2) def setUp(self): self.o_uph_cap = patch_capabilities(UploadPackHandler, ("no-done",)) self.o_rph_cap = patch_capabilities(ReceivePackHandler, ("no-done",)) super(SmartWebSideBand64kTestCase, self).setUp() def tearDown(self): super(SmartWebSideBand64kTestCase, self).tearDown() UploadPackHandler.capabilities = self.o_uph_cap ReceivePackHandler.capabilities = self.o_rph_cap def _handlers(self): return None # default handlers include side-band-64k def _check_app(self, app): receive_pack_handler_cls = app.handlers[b'git-receive-pack'] caps = receive_pack_handler_cls.capabilities() self.assertTrue(b'side-band-64k' in caps) self.assertFalse(b'no-done' in caps) class SmartWebSideBand64kNoDoneTestCase(SmartWebTestCase): """Test cases for smart HTTP server with side-band-64k and no-done support. """ # no-done was introduced in git 1.7.4 min_git_version = (1, 7, 4) def _handlers(self): return None # default handlers include side-band-64k def _check_app(self, app): receive_pack_handler_cls = app.handlers[b'git-receive-pack'] caps = receive_pack_handler_cls.capabilities() self.assertTrue(b'side-band-64k' in caps) self.assertTrue(b'no-done' in caps) @skipIf(sys.platform == 'win32', 'Broken on windows, with very long fail time.') @skipIfPY3 class DumbWebTestCase(WebTests, CompatTestCase): """Test cases for dumb HTTP server.""" def _make_app(self, backend): return make_wsgi_chain(backend, dumb=True) def test_push_to_dulwich(self): # Note: remove this if dulwich implements dumb web pushing. raise SkipTest('Dumb web pushing not supported.') def test_push_to_dulwich_remove_branch(self): # Note: remove this if dumb pushing is supported raise SkipTest('Dumb web pushing not supported.') def test_new_shallow_clone_from_dulwich(self): # Note: remove this if C git and dulwich implement dumb web shallow # clones. raise SkipTest('Dumb web shallow cloning not supported.') + def test_shallow_clone_from_git_is_identical(self): + # Note: remove this if C git and dulwich implement dumb web shallow + # clones. + raise SkipTest('Dumb web shallow cloning not supported.') + def test_fetch_same_depth_into_shallow_clone_from_dulwich(self): # Note: remove this if C git and dulwich implement dumb web shallow # clones. raise SkipTest('Dumb web shallow cloning not supported.') def test_fetch_full_depth_into_shallow_clone_from_dulwich(self): # Note: remove this if C git and dulwich implement dumb web shallow # clones. raise SkipTest('Dumb web shallow cloning not supported.') def test_push_to_dulwich_issue_88_standard(self): raise SkipTest('Dumb web pushing not supported.') diff --git a/dulwich/tests/test_blackbox.py b/dulwich/tests/test_blackbox.py index c265f513..abd22563 100644 --- a/dulwich/tests/test_blackbox.py +++ b/dulwich/tests/test_blackbox.py @@ -1,70 +1,73 @@ # test_blackbox.py -- blackbox tests # Copyright (C) 2010 Jelmer Vernooij # # This program is free software; you can redistribute it and/or # modify it under the terms of the GNU General Public License # as published by the Free Software Foundation; version 2 # of the License or (at your option) a later version. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program; if not, write to the Free Software # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, # MA 02110-1301, USA. """Blackbox tests for Dulwich commands.""" import tempfile import shutil from dulwich.repo import ( Repo, ) from dulwich.tests import ( BlackboxTestCase, ) class GitReceivePackTests(BlackboxTestCase): """Blackbox tests for dul-receive-pack.""" def setUp(self): super(GitReceivePackTests, self).setUp() self.path = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, self.path) self.repo = Repo.init(self.path) def test_basic(self): process = self.run_command("dul-receive-pack", [self.path]) (stdout, stderr) = process.communicate(b"0000") - self.assertEqual(b'', stderr, stderr) self.assertEqual(b'0000', stdout[-4:]) self.assertEqual(0, process.returncode) def test_missing_arg(self): process = self.run_command("dul-receive-pack", []) (stdout, stderr) = process.communicate() - self.assertEqual([b'usage: dul-receive-pack '], stderr.splitlines()) + self.assertEqual( + [b'usage: dul-receive-pack '], + stderr.splitlines()[-1:]) self.assertEqual(b'', stdout) self.assertEqual(1, process.returncode) class GitUploadPackTests(BlackboxTestCase): """Blackbox tests for dul-upload-pack.""" def setUp(self): super(GitUploadPackTests, self).setUp() self.path = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, self.path) self.repo = Repo.init(self.path) def test_missing_arg(self): process = self.run_command("dul-upload-pack", []) (stdout, stderr) = process.communicate() - self.assertEqual([b'usage: dul-upload-pack '], stderr.splitlines()) + self.assertEqual( + [b'usage: dul-upload-pack '], + stderr.splitlines()[-1:]) self.assertEqual(b'', stdout) self.assertEqual(1, process.returncode) diff --git a/dulwich/tests/test_client.py b/dulwich/tests/test_client.py index 62b5f6b2..90c86444 100644 --- a/dulwich/tests/test_client.py +++ b/dulwich/tests/test_client.py @@ -1,644 +1,662 @@ # test_client.py -- Tests for the git protocol, client side # Copyright (C) 2009 Jelmer Vernooij # # This program is free software; you can redistribute it and/or # modify it under the terms of the GNU General Public License # as published by the Free Software Foundation; version 2 # or (at your option) any later version of the License. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program; if not, write to the Free Software # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, # MA 02110-1301, USA. from contextlib import closing from io import BytesIO import sys import shutil import tempfile from dulwich import ( client, ) from dulwich.client import ( LocalGitClient, TraditionalGitClient, TCPGitClient, SubprocessGitClient, SSHGitClient, HttpGitClient, ReportStatusParser, SendPackError, UpdateRefsError, get_transport_and_path, get_transport_and_path_from_url, ) from dulwich.tests import ( TestCase, ) from dulwich.protocol import ( TCP_GIT_PORT, Protocol, ) from dulwich.pack import ( 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, ) 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 # 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): self.assertEqual(set([b'multi_ack', b'side-band-64k', b'ofs-delta', b'thin-pack', b'multi_ack_detailed']), set(self.client._fetch_capabilities)) self.assertEqual(set([b'ofs-delta', b'report-status', b'side-band-64k']), 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) self.client.fetch_pack(b'/', lambda heads: [], None, None) def test_fetch_pack_none(self): self.rin.write( b'008855dcc6bf963f922e1ed5c4bbaaefcfacef57b1d7 HEAD.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) self.client.fetch_pack(b'bla', lambda heads: [], None, None, None) 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, ''), ] self.assertRaises(UpdateRefsError, self.client.send_pack, "blah", determine_wants, generate_pack_contents) 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 {} self.client.send_pack(b'/', determine_wants, generate_pack_contents) self.assertEqual(self.rout.getvalue(), b'0000') 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 {} self.client.send_pack(b'/', determine_wants, generate_pack_contents) 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 {} f = BytesIO() write_pack_objects(f, {}) self.client.send_pack('/', determine_wants, generate_pack_contents) 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''), ] f = BytesIO() write_pack_objects(f, generate_pack_contents(None, None)) self.client.send_pack(b'/', determine_wants, generate_pack_contents) 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 {} self.assertRaises(UpdateRefsError, self.client.send_pack, b"/", determine_wants, generate_pack_contents) 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_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_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_ssh_abspath_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_port_abspath_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_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) 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_abspath_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_abspath_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_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 def run_command(self, host, command, username=None, port=None): + if (type(command) is not list or + not all([isinstance(b, bytes) for b in command])): + raise TypeError(command) + self.host = host self.command = command self.username = username self.port = port 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_default_command(self): - self.assertEqual('git-upload-pack', + self.assertEqual([b'git-upload-pack'], self.client._get_cmd_path(b'upload-pack')) def test_alternative_command_path(self): - self.client.alternative_paths['upload-pack'] = ( - '/usr/lib/git/git-upload-pack') - self.assertEqual('/usr/lib/git/git-upload-pack', + 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', b'-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", "/path/to/repo") + 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) + self.assertEqual([b"git-command", b"/path/to/repo"], server.command) - client._connect(b"relative-command", "/~/path/to/repo") - self.assertEqual(["git-relative-command", "~/path/to/repo"], + client._connect(b"relative-command", b"/~/path/to/repo") + self.assertEqual([b"git-relative-command", b"~/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_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)) def test_fetch_empty(self): c = LocalGitClient() s = open_repo('a.git') self.addCleanup(tear_down_repo, s) out = BytesIO() walker = {} c.fetch_pack(s.path, lambda heads: [], graph_walker=walker, pack_data=out.write) 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() c.fetch_pack(s.path, lambda heads: [b"a90fa2d900a17e99b433217e988c4eb4a2e9a097"], graph_walker=walker, pack_data=out.write) # 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 closing(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): 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) self.assertEqual(local.refs[ref_name], new_refs[ref_name]) for name, sha in new_refs.items(): self.assertEqual(new_refs[name], target.refs[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) diff --git a/dulwich/tests/test_config.py b/dulwich/tests/test_config.py index f9440f03..a32d45cb 100644 --- a/dulwich/tests/test_config.py +++ b/dulwich/tests/test_config.py @@ -1,287 +1,294 @@ # test_config.py -- Tests for reading and writing configuration files # Copyright (C) 2011 Jelmer Vernooij # # This program is free software; you can redistribute it and/or # modify it under the terms of the GNU General Public License # as published by the Free Software Foundation; either version 2 # or (at your option) a later version of the License. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program; if not, write to the Free Software # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, # MA 02110-1301, USA. """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, _unescape_value, ) -from dulwich.tests import TestCase +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] repositoryformatversion = 0 filemode = true bare = false logallrefupdates = 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_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): 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): 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")) + #@expectedFailure + def test_quoted(self): + cf = self.from_file(b"""[gui] + fontdiff = -family \\\"Ubuntu Mono\\\" -size 11 -weight normal -slant roman -underline 0 -overstrike 0 +""") + self.assertEqual(ConfigFile({(b'gui', ): { + b'fontdiff': b'-family "Ubuntu Mono" -size 11 -weight normal -slant roman -underline 0 -overstrike 0', + }}), cf) + 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 UnescapeTests(TestCase): - - def test_nothing(self): - self.assertEqual(b"", bytes(_unescape_value(bytearray()))) - - def test_tab(self): - self.assertEqual(b"\tbar\t", bytes(_unescape_value(bytearray(b"\\tbar\\t")))) - - def test_newline(self): - self.assertEqual(b"\nbar\t", bytes(_unescape_value(bytearray(b"\\nbar\\t")))) - - def test_quote(self): - self.assertEqual(b"\"foo\"", bytes(_unescape_value(bytearray(b"\\\"foo\\\"")))) - - 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")) diff --git a/dulwich/tests/test_file.py b/dulwich/tests/test_file.py index 2ea4d3f1..e1bc8122 100644 --- a/dulwich/tests/test_file.py +++ b/dulwich/tests/test_file.py @@ -1,213 +1,213 @@ # test_file.py -- Test for git files # Copyright (C) 2010 Google, Inc. # # This program is free software; you can redistribute it and/or # modify it under the terms of the GNU General Public License # as published by the Free Software Foundation; version 2 # of the License or (at your option) a later version of the License. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program; if not, write to the Free Software # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, # MA 02110-1301, USA. import errno import io import os import shutil import sys import tempfile -from dulwich.file import GitFile, fancy_rename +from dulwich.file import GitFile, _fancy_rename from dulwich.tests import ( SkipTest, TestCase, ) class FancyRenameTests(TestCase): def setUp(self): super(FancyRenameTests, self).setUp() self._tempdir = tempfile.mkdtemp() self.foo = self.path('foo') self.bar = self.path('bar') self.create(self.foo, b'foo contents') def tearDown(self): shutil.rmtree(self._tempdir) super(FancyRenameTests, self).tearDown() def path(self, filename): return os.path.join(self._tempdir, filename) def create(self, path, contents): f = open(path, 'wb') f.write(contents) f.close() def test_no_dest_exists(self): self.assertFalse(os.path.exists(self.bar)) - fancy_rename(self.foo, self.bar) + _fancy_rename(self.foo, self.bar) self.assertFalse(os.path.exists(self.foo)) new_f = open(self.bar, 'rb') self.assertEqual(b'foo contents', new_f.read()) new_f.close() def test_dest_exists(self): self.create(self.bar, b'bar contents') - fancy_rename(self.foo, self.bar) + _fancy_rename(self.foo, self.bar) self.assertFalse(os.path.exists(self.foo)) new_f = open(self.bar, 'rb') self.assertEqual(b'foo contents', new_f.read()) new_f.close() def test_dest_opened(self): if sys.platform != "win32": raise SkipTest("platform allows overwriting open files") self.create(self.bar, b'bar contents') dest_f = open(self.bar, 'rb') - self.assertRaises(OSError, fancy_rename, self.foo, self.bar) + self.assertRaises(OSError, _fancy_rename, self.foo, self.bar) dest_f.close() self.assertTrue(os.path.exists(self.path('foo'))) new_f = open(self.foo, 'rb') self.assertEqual(b'foo contents', new_f.read()) new_f.close() new_f = open(self.bar, 'rb') self.assertEqual(b'bar contents', new_f.read()) new_f.close() class GitFileTests(TestCase): def setUp(self): super(GitFileTests, self).setUp() self._tempdir = tempfile.mkdtemp() f = open(self.path('foo'), 'wb') f.write(b'foo contents') f.close() def tearDown(self): shutil.rmtree(self._tempdir) super(GitFileTests, self).tearDown() def path(self, filename): return os.path.join(self._tempdir, filename) def test_invalid(self): foo = self.path('foo') self.assertRaises(IOError, GitFile, foo, mode='r') self.assertRaises(IOError, GitFile, foo, mode='ab') self.assertRaises(IOError, GitFile, foo, mode='r+b') self.assertRaises(IOError, GitFile, foo, mode='w+b') self.assertRaises(IOError, GitFile, foo, mode='a+bU') def test_readonly(self): f = GitFile(self.path('foo'), 'rb') self.assertTrue(isinstance(f, io.IOBase)) self.assertEqual(b'foo contents', f.read()) self.assertEqual(b'', f.read()) f.seek(4) self.assertEqual(b'contents', f.read()) f.close() def test_default_mode(self): f = GitFile(self.path('foo')) self.assertEqual(b'foo contents', f.read()) f.close() def test_write(self): foo = self.path('foo') foo_lock = '%s.lock' % foo orig_f = open(foo, 'rb') self.assertEqual(orig_f.read(), b'foo contents') orig_f.close() self.assertFalse(os.path.exists(foo_lock)) f = GitFile(foo, 'wb') self.assertFalse(f.closed) self.assertRaises(AttributeError, getattr, f, 'not_a_file_property') self.assertTrue(os.path.exists(foo_lock)) f.write(b'new stuff') f.seek(4) f.write(b'contents') f.close() self.assertFalse(os.path.exists(foo_lock)) new_f = open(foo, 'rb') self.assertEqual(b'new contents', new_f.read()) new_f.close() def test_open_twice(self): foo = self.path('foo') f1 = GitFile(foo, 'wb') f1.write(b'new') try: f2 = GitFile(foo, 'wb') self.fail() except OSError as e: self.assertEqual(errno.EEXIST, e.errno) else: f2.close() f1.write(b' contents') f1.close() # Ensure trying to open twice doesn't affect original. f = open(foo, 'rb') self.assertEqual(b'new contents', f.read()) f.close() def test_abort(self): foo = self.path('foo') foo_lock = '%s.lock' % foo orig_f = open(foo, 'rb') self.assertEqual(orig_f.read(), b'foo contents') orig_f.close() f = GitFile(foo, 'wb') f.write(b'new contents') f.abort() self.assertTrue(f.closed) self.assertFalse(os.path.exists(foo_lock)) new_orig_f = open(foo, 'rb') self.assertEqual(new_orig_f.read(), b'foo contents') new_orig_f.close() def test_abort_close(self): foo = self.path('foo') f = GitFile(foo, 'wb') f.abort() try: f.close() except (IOError, OSError): self.fail() f = GitFile(foo, 'wb') f.close() try: f.abort() except (IOError, OSError): self.fail() def test_abort_close_removed(self): foo = self.path('foo') f = GitFile(foo, 'wb') f._file.close() os.remove(foo+".lock") f.abort() self.assertTrue(f._closed) diff --git a/dulwich/tests/test_object_store.py b/dulwich/tests/test_object_store.py index 2b603f0c..44579031 100644 --- a/dulwich/tests/test_object_store.py +++ b/dulwich/tests/test_object_store.py @@ -1,469 +1,470 @@ # test_object_store.py -- tests for object_store.py # Copyright (C) 2008 Jelmer Vernooij # # This program is free software; you can redistribute it and/or # modify it under the terms of the GNU General Public License # as published by the Free Software Foundation; version 2 # or (at your option) any later version of the License. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program; if not, write to the Free Software # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, # MA 02110-1301, USA. """Tests for the object store interface.""" from contextlib import closing from io import BytesIO import os import shutil import tempfile from dulwich.index import ( commit_tree, ) from dulwich.errors import ( NotTreeError, ) from dulwich.objects import ( sha_to_hex, Blob, Tree, TreeEntry, ) from dulwich.object_store import ( DiskObjectStore, MemoryObjectStore, ObjectStoreGraphWalker, 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_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 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: 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) self.assertEqual([], list(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()) 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_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: 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)) diff --git a/dulwich/tests/test_objectspec.py b/dulwich/tests/test_objectspec.py index 29e39e39..019de54e 100644 --- a/dulwich/tests/test_objectspec.py +++ b/dulwich/tests/test_objectspec.py @@ -1,66 +1,139 @@ # test_objectspec.py -- tests for objectspec.py # Copyright (C) 2014 Jelmer Vernooij # # This program is free software; you can redistribute it and/or # modify it under the terms of the GNU General Public License # as published by the Free Software Foundation; version 2 # of the License or (at your option) any later version of # the License. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program; if not, write to the Free Software # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, # MA 02110-1301, USA. """Tests for revision spec parsing.""" # TODO: Round-trip parse-serialize-parse and serialize-parse-serialize tests. from dulwich.objects import ( Blob, ) from dulwich.objectspec import ( parse_object, parse_commit_range, + parse_ref, + parse_refs, + parse_reftuple, + parse_reftuples, ) from dulwich.repo import MemoryRepo from dulwich.tests import ( TestCase, ) from dulwich.tests.utils import ( build_commit_graph, ) class ParseObjectTests(TestCase): """Test parse_object.""" def test_nonexistent(self): r = MemoryRepo() self.assertRaises(KeyError, parse_object, r, "thisdoesnotexist") def test_blob_by_sha(self): r = MemoryRepo() b = Blob.from_string(b"Blah") r.object_store.add_object(b) self.assertEqual(b, parse_object(r, b.id)) class ParseCommitRangeTests(TestCase): """Test parse_commit_range.""" def test_nonexistent(self): r = MemoryRepo() self.assertRaises(KeyError, parse_commit_range, r, "thisdoesnotexist") def test_commit_by_sha(self): r = MemoryRepo() c1, c2, c3 = build_commit_graph(r.object_store, [[1], [2, 1], [3, 1, 2]]) self.assertEqual([c1], list(parse_commit_range(r, c1.id))) + + +class ParseRefTests(TestCase): + + def test_nonexistent(self): + r = {} + self.assertRaises(KeyError, parse_ref, r, b"thisdoesnotexist") + + def test_head(self): + r = {b"refs/heads/foo": "bla"} + self.assertEqual(b"refs/heads/foo", parse_ref(r, b"foo")) + + def test_full(self): + r = {b"refs/heads/foo": "bla"} + self.assertEqual(b"refs/heads/foo", parse_ref(r, b"refs/heads/foo")) + + +class ParseRefsTests(TestCase): + + def test_nonexistent(self): + r = {} + self.assertRaises(KeyError, parse_refs, r, [b"thisdoesnotexist"]) + + def test_head(self): + r = {b"refs/heads/foo": "bla"} + self.assertEqual([b"refs/heads/foo"], parse_refs(r, [b"foo"])) + + def test_full(self): + r = {b"refs/heads/foo": "bla"} + self.assertEqual([b"refs/heads/foo"], parse_refs(r, b"refs/heads/foo")) + + +class ParseReftupleTests(TestCase): + + def test_nonexistent(self): + r = {} + self.assertRaises(KeyError, parse_reftuple, r, r, b"thisdoesnotexist") + + def test_head(self): + r = {b"refs/heads/foo": "bla"} + self.assertEqual((b"refs/heads/foo", b"refs/heads/foo", False), + parse_reftuple(r, r, b"foo")) + self.assertEqual((b"refs/heads/foo", b"refs/heads/foo", True), + parse_reftuple(r, r, b"+foo")) + self.assertEqual((b"refs/heads/foo", b"refs/heads/foo", True), + parse_reftuple(r, {}, b"+foo")) + + def test_full(self): + r = {b"refs/heads/foo": "bla"} + self.assertEqual((b"refs/heads/foo", b"refs/heads/foo", False), + parse_reftuple(r, r, b"refs/heads/foo")) + + +class ParseReftuplesTests(TestCase): + + def test_nonexistent(self): + r = {} + self.assertRaises(KeyError, parse_reftuples, r, r, + [b"thisdoesnotexist"]) + + def test_head(self): + r = {b"refs/heads/foo": "bla"} + self.assertEqual([(b"refs/heads/foo", b"refs/heads/foo", False)], + parse_reftuples(r, r, [b"foo"])) + + def test_full(self): + r = {b"refs/heads/foo": "bla"} + self.assertEqual([(b"refs/heads/foo", b"refs/heads/foo", False)], + parse_reftuples(r, r, b"refs/heads/foo")) diff --git a/dulwich/tests/test_pack.py b/dulwich/tests/test_pack.py index 3d491dff..35029c0f 100644 --- a/dulwich/tests/test_pack.py +++ b/dulwich/tests/test_pack.py @@ -1,1054 +1,1054 @@ # test_pack.py -- Tests for the handling of git packs. # Copyright (C) 2007 James Westby # Copyright (C) 2008 Jelmer Vernooij # # This program is free software; you can redistribute it and/or # modify it under the terms of the GNU General Public License # as published by the Free Software Foundation; version 2 # of the License, or (at your option) any later version of the license. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program; if not, write to the Free Software # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, # MA 02110-1301, USA. """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_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') 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_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, 1, 3, 4], entries, + 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() entries = 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_porcelain.py b/dulwich/tests/test_porcelain.py index 5f3b127d..8aa0a5e3 100644 --- a/dulwich/tests/test_porcelain.py +++ b/dulwich/tests/test_porcelain.py @@ -1,733 +1,755 @@ # test_porcelain.py -- porcelain tests # Copyright (C) 2013 Jelmer Vernooij # # This program is free software; you can redistribute it and/or # modify it under the terms of the GNU General Public License # as published by the Free Software Foundation; version 2 # of the License or (at your option) a later version. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program; if not, write to the Free Software # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, # MA 02110-1301, USA. """Tests for dulwich.porcelain.""" from contextlib import closing from io import BytesIO +try: + from StringIO import StringIO +except ImportError: + from io import StringIO import os import shutil import tarfile import tempfile from dulwich import porcelain from dulwich.diff_tree import tree_changes from dulwich.objects import ( Blob, Tag, Tree, ) from dulwich.repo import Repo from dulwich.tests import ( TestCase, ) from dulwich.tests.compat.utils import require_git_version from dulwich.tests.utils import ( build_commit_graph, 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() class ArchiveTests(PorcelainTestCase): """Tests for the archive command.""" def test_simple(self): # TODO(jelmer): Remove this once dulwich has its own implementation of archive. require_git_version((1, 5, 0)) 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) 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 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) self.assertEqual(Repo(target_path).head(), c3.id) self.assertTrue(b'f1' not in os.listdir(target_path)) self.assertTrue(b'f2' not in os.listdir(target_path)) 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 closing(porcelain.clone(self.repo.path, target_path, checkout=True, errstream=errstream)) as r: self.assertEqual(r.path, target_path) with closing(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) r = porcelain.clone(self.repo.path, target_path, bare=True, errstream=errstream) self.assertEqual(r.path, target_path) self.assertEqual(Repo(target_path).head(), c3.id) 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 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) 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 with open(os.path.join(self.repo.path, 'blah'), 'w') as f: f.write("\n") porcelain.add(repo=self.repo.path, paths=['blah']) porcelain.commit(repo=self.repo.path, message=b'test', author=b'test', committer=b'test') # Add a second test file and a file in a directory with open(os.path.join(self.repo.path, 'foo'), 'w') as f: f.write("\n") os.mkdir(os.path.join(self.repo.path, 'adir')) with open(os.path.join(self.repo.path, 'adir', 'afile'), 'w') as f: f.write("\n") porcelain.add(self.repo.path) # 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_file(self): with open(os.path.join(self.repo.path, 'foo'), 'w') as f: f.write("BAR") porcelain.add(self.repo.path, paths=["foo"]) class RemoveTests(PorcelainTestCase): def test_remove_file(self): with open(os.path.join(self.repo.path, 'foo'), 'w') as f: f.write("BAR") porcelain.add(self.repo.path, paths=["foo"]) porcelain.rm(self.repo.path, paths=["foo"]) 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 = BytesIO() + outstream = StringIO() porcelain.log(self.repo.path, outstream=outstream) - self.assertEqual(3, outstream.getvalue().count(b"-" * 50)) + 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 = BytesIO() + outstream = StringIO() porcelain.log(self.repo.path, outstream=outstream, max_entries=1) - self.assertEqual(1, outstream.getvalue().count(b"-" * 50)) + 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 = BytesIO() + outstream = StringIO() porcelain.show(self.repo.path, objects=c3.id, outstream=outstream) - self.assertTrue(outstream.getvalue().startswith(b"-" * 50)) + 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 = BytesIO() + outstream = StringIO() porcelain.show(self.repo.path, objects=[c3.id], outstream=outstream) - self.assertTrue(outstream.getvalue().startswith(b"-" * 50)) + 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 = BytesIO() + outstream = StringIO() porcelain.show(self.repo.path, objects=[b.id], outstream=outstream) - self.assertEqual(outstream.getvalue(), b"The Foo\n") + self.assertEqual(outstream.getvalue(), "The Foo\n") 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) 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()]) 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): with open(os.path.join(self.repo.path, 'foo'), 'w') as f: f.write("BAR") porcelain.add(self.repo.path, paths=["foo"]) 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) 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'') # 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 = porcelain.clone(self.repo.path, target=clone_path, + errstream=errstream) 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=[os.path.basename(fullpath)]) porcelain.commit(repo=clone_path, message=b'push', author=b'', committer=b'') # Setup a non-checked out branch in the remote refs_path = b"refs/heads/foo" - self.repo[refs_path] = self.repo[b'HEAD'] + self.repo.refs[refs_path] = self.repo[b'HEAD'].id # Push to the remote - porcelain.push(clone_path, self.repo.path, refs_path, outstream=outstream, - errstream=errstream) + porcelain.push(clone_path, self.repo.path, b"HEAD:" + refs_path, outstream=outstream, + errstream=errstream) # Check that the target and source with closing(Repo(clone_path)) as r_clone: 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')) + self.assertEqual(os.path.basename(fullpath), + change.new.path.decode('ascii')) class PullTests(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) filename = os.path.basename(fullpath) porcelain.add(repo=self.repo.path, paths=filename) 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) target_repo.close() # create a second file to be pushed handle, fullpath = tempfile.mkstemp(dir=self.repo.path) os.close(handle) filename = os.path.basename(fullpath) porcelain.add(repo=self.repo.path, paths=filename) porcelain.commit(repo=self.repo.path, message=b'test2', author=b'test2', committer=b'test2') + self.assertTrue(b'refs/heads/master' in self.repo.refs) + self.assertTrue(b'refs/heads/master' in target_repo.refs) + # Pull changes into the cloned repo porcelain.pull(target_path, self.repo.path, b'refs/heads/master', outstream=outstream, errstream=errstream) # Check the target repo for pushed changes with closing(Repo(target_path)) as r: self.assertEqual(r[b'HEAD'].id, self.repo[b'HEAD'].id) class StatusTests(PorcelainTestCase): 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=['foo']) porcelain.commit(repo=self.repo.path, message=b'test status', author=b'', committer=b'') # 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=filename_add) 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' with open(os.path.join(self.repo.path, filename), 'w') as f: f.write('stuff') porcelain.add(repo=self.repo.path, paths=filename) porcelain.commit(repo=self.repo.path, message=b'test status', author=b'', committer=b'') filename = 'foo' with open(os.path.join(self.repo.path, filename), 'w') as f: f.write('stuff') porcelain.add(repo=self.repo.path, paths=filename) 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=filename) porcelain.commit(repo=self.repo.path, message=b'test status', author=b'', committer=b'') with open(fullpath, 'w') as f: f.write('otherstuff') porcelain.add(repo=self.repo.path, paths=filename) 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' with open(os.path.join(self.repo.path, filename), 'w') as f: f.write('stuff') porcelain.add(repo=self.repo.path, paths=filename) porcelain.commit(repo=self.repo.path, message=b'test status', author=b'', committer=b'') porcelain.rm(repo=self.repo.path, paths=[filename]) 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) # 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' with open(os.path.join(self.repo.path, filename), 'w') as f: f.write('stuff') porcelain.add(repo=self.repo.path, paths=filename) self.repo.do_commit(message=b'test status', author=b'', committer=b'', 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'006d9e65bdcf4a22cdd4f3700604a275cd2aaf146b23 HEAD\x00 report-status ' b'delete-refs ofs-delta side-band-64k no-done', b'003f9e65bdcf4a22cdd4f3700604a275cd2aaf146b23 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)) 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) filename = os.path.basename(fullpath) porcelain.add(repo=self.repo.path, paths=filename) porcelain.commit(repo=self.repo.path, message=b'test', author=b'test', committer=b'test') # Setup target repo target_path = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, target_path) target_repo = porcelain.clone(self.repo.path, target=target_path, errstream=errstream) # create a second file to be pushed handle, fullpath = tempfile.mkstemp(dir=self.repo.path) os.close(handle) filename = os.path.basename(fullpath) porcelain.add(repo=self.repo.path, paths=filename) porcelain.commit(repo=self.repo.path, message=b'test2', author=b'test2', committer=b'test2') self.assertFalse(self.repo[b'HEAD'].id in target_repo) target_repo.close() # Fetch changes into the cloned repo porcelain.fetch(target_path, self.repo.path, outstream=outstream, errstream=errstream) # Check the target repo for pushed changes with closing(Repo(target_path)) as r: self.assertTrue(self.repo[b'HEAD'].id in r) + + +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) + filename = os.path.basename(fullpath) + porcelain.add(repo=self.repo.path, paths=filename) + porcelain.repack(self.repo) diff --git a/dulwich/tests/test_refs.py b/dulwich/tests/test_refs.py index e3b64313..3a645c65 100644 --- a/dulwich/tests/test_refs.py +++ b/dulwich/tests/test_refs.py @@ -1,492 +1,509 @@ # test_refs.py -- tests for refs.py +# encoding: utf-8 # Copyright (C) 2013 Jelmer Vernooij # # This program is free software; you can redistribute it and/or # modify it under the terms of the GNU General Public License # as published by the Free Software Foundation; version 2 # of the License or (at your option) any later version of # the License. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program; if not, write to the Free Software # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, # MA 02110-1301, USA. """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.refs import ( DictRefsContainer, InfoRefsContainer, check_ref_format, _split_ref_line, read_packed_refs_with_peeled, read_packed_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', } class RefsContainerTests(object): def test_keys(self): actual_keys = set(self._refs.keys()) self.assertEqual(set(self._refs.allkeys()), actual_keys) # ignore the symref loop if it exists actual_keys.discard(b'refs/heads/loop') 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 self.assertEqual(_TEST_REFS, self._refs.as_dict()) 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']) 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.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) 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') self.assertEqual(b'ref: refs/heads/master', next(iter(f)).rstrip(b'\n')) f.close() # 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'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 UnicodeDecodeError: + raise SkipTest("filesystem encoding doesn't support special character") + p = os.path.join(self._repo.path, 'refs', 'tags', 'schön') + with open(p, 'w') as f: + f.write('00' * 20) + + expected_refs = dict(_TEST_REFS) + expected_refs[encoded_ref] = b'00' * 20 + + self.assertEqual(expected_refs, self._repo.get_refs()) + _TEST_REFS_SERIALIZED = ( b'42d06bd4b77fed026b154d16493e5deab78f02ec\trefs/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 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) # ignore the symref loop if it exists actual_keys.discard(b'refs/heads/loop') expected_refs = dict(_TEST_REFS) del expected_refs[b'HEAD'] 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'] 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')) diff --git a/dulwich/tests/test_repository.py b/dulwich/tests/test_repository.py index 032fda68..2fee9257 100644 --- a/dulwich/tests/test_repository.py +++ b/dulwich/tests/test_repository.py @@ -1,767 +1,792 @@ # -*- coding: utf-8 -*- # test_repository.py -- tests for repository.py # Copyright (C) 2007 James Westby # # This program is free software; you can redistribute it and/or # modify it under the terms of the GNU General Public License # as published by the Free Software Foundation; version 2 # of the License or (at your option) any later version of # the License. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program; if not, write to the Free Software # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, # MA 02110-1301, USA. """Tests for the repository.""" from contextlib import closing 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 ( Repo, MemoryRepo, ) 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) 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) 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) for k, _ in test_keys: self.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 closing(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']) 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 closing(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()) r = Repo.init(repo_dir) self.addCleanup(shutil.rmtree, repo_dir) 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() r = Repo.init(repo_dir) self.addCleanup(shutil.rmtree, repo_dir) 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() r = Repo.init(repo_dir) self.addCleanup(shutil.rmtree, repo_dir) (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) self.assertEqual(len(warnings_list), 1, warnings_list) self.assertIsInstance(warnings_list[-1], UserWarning) self.assertTrue("post-commit hook failed: " in str(warnings_list[-1])) self.assertEqual([commit_sha], r[commit_sha2].parents) 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): return False r.refs.set_if_equals = set_if_equals def add_if_new(name, new_ref): 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_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_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('/') diff --git a/dulwich/tests/test_server.py b/dulwich/tests/test_server.py index 120e05a9..6f77937d 100644 --- a/dulwich/tests/test_server.py +++ b/dulwich/tests/test_server.py @@ -1,1084 +1,1084 @@ # test_server.py -- Tests for the git server # Copyright (C) 2010 Google, Inc. # # This program is free software; you can redistribute it and/or # modify it under the terms of the GNU General Public License # as published by the Free Software Foundation; version 2 # or (at your option) any later version of the License. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program; if not, write to the Free Software # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, # MA 02110-1301, USA. """Tests for the smart protocol server.""" from io import BytesIO import os import shutil import tempfile from dulwich.errors import ( GitProtocolError, NotGitRepository, UnexpectedCommandError, HangupException, ) from dulwich.object_store import ( MemoryObjectStore, ) from dulwich.repo import ( MemoryRepo, Repo, ) from dulwich.server import ( Backend, DictBackend, FileSystemBackend, Handler, MultiAckGraphWalkerImpl, MultiAckDetailedGraphWalkerImpl, _split_proto_line, serve_command, _find_shallow, ProtocolGraphWalker, ReceivePackHandler, SingleAckGraphWalkerImpl, UploadPackHandler, update_server_info, ) from dulwich.tests import TestCase from dulwich.tests.utils import ( make_commit, make_tag, ) from dulwich.protocol import ( ZERO_SHA, ) ONE = b'1' * 40 TWO = b'2' * 40 THREE = b'3' * 40 FOUR = b'4' * 40 FIVE = b'5' * 40 SIX = b'6' * 40 class TestProto(object): def __init__(self): self._output = [] self._received = {0: [], 1: [], 2: [], 3: []} def set_output(self, output_lines): self._output = output_lines def read_pkt_line(self): if self._output: data = self._output.pop(0) if data is not None: return data.rstrip() + b'\n' else: # flush-pkt ('0000'). return None else: raise HangupException() def write_sideband(self, band, data): self._received[band].append(data) def write_pkt_line(self, data): self._received[0].append(data) def get_received_line(self, band=0): lines = self._received[band] return lines.pop(0) class TestGenericHandler(Handler): def __init__(self): Handler.__init__(self, Backend(), None) @classmethod def capabilities(cls): return (b'cap1', b'cap2', b'cap3') @classmethod def required_capabilities(cls): return (b'cap2',) class HandlerTestCase(TestCase): def setUp(self): super(HandlerTestCase, self).setUp() self._handler = TestGenericHandler() def assertSucceeds(self, func, *args, **kwargs): try: func(*args, **kwargs) except GitProtocolError as e: self.fail(e) def test_capability_line(self): self.assertEqual(b' cap1 cap2 cap3', self._handler.capability_line()) def test_set_client_capabilities(self): set_caps = self._handler.set_client_capabilities self.assertSucceeds(set_caps, [b'cap2']) self.assertSucceeds(set_caps, [b'cap1', b'cap2']) # different order self.assertSucceeds(set_caps, [b'cap3', b'cap1', b'cap2']) # error cases self.assertRaises(GitProtocolError, set_caps, [b'capxxx', b'cap2']) self.assertRaises(GitProtocolError, set_caps, [b'cap1', b'cap3']) # ignore innocuous but unknown capabilities self.assertRaises(GitProtocolError, set_caps, [b'cap2', b'ignoreme']) self.assertFalse(b'ignoreme' in self._handler.capabilities()) self._handler.innocuous_capabilities = lambda: (b'ignoreme',) self.assertSucceeds(set_caps, [b'cap2', b'ignoreme']) def test_has_capability(self): self.assertRaises(GitProtocolError, self._handler.has_capability, b'cap') caps = self._handler.capabilities() self._handler.set_client_capabilities(caps) for cap in caps: self.assertTrue(self._handler.has_capability(cap)) self.assertFalse(self._handler.has_capability(b'capxxx')) class UploadPackHandlerTestCase(TestCase): def setUp(self): super(UploadPackHandlerTestCase, self).setUp() self._repo = MemoryRepo.init_bare([], {}) backend = DictBackend({b'/': self._repo}) self._handler = UploadPackHandler( backend, [b'/', b'host=lolcathost'], TestProto()) def test_progress(self): caps = self._handler.required_capabilities() self._handler.set_client_capabilities(caps) self._handler.progress(b'first message') self._handler.progress(b'second message') self.assertEqual(b'first message', self._handler.proto.get_received_line(2)) self.assertEqual(b'second message', self._handler.proto.get_received_line(2)) self.assertRaises(IndexError, self._handler.proto.get_received_line, 2) def test_no_progress(self): caps = list(self._handler.required_capabilities()) + [b'no-progress'] self._handler.set_client_capabilities(caps) self._handler.progress(b'first message') self._handler.progress(b'second message') self.assertRaises(IndexError, self._handler.proto.get_received_line, 2) def test_get_tagged(self): refs = { b'refs/tags/tag1': ONE, b'refs/tags/tag2': TWO, b'refs/heads/master': FOUR, # not a tag, no peeled value } # repo needs to peel this object self._repo.object_store.add_object(make_commit(id=FOUR)) self._repo.refs._update(refs) peeled = { b'refs/tags/tag1': b'1234' * 10, b'refs/tags/tag2': b'5678' * 10, } self._repo.refs._update_peeled(peeled) caps = list(self._handler.required_capabilities()) + [b'include-tag'] self._handler.set_client_capabilities(caps) self.assertEqual({b'1234' * 10: ONE, b'5678' * 10: TWO}, self._handler.get_tagged(refs, repo=self._repo)) # non-include-tag case caps = self._handler.required_capabilities() self._handler.set_client_capabilities(caps) self.assertEqual({}, self._handler.get_tagged(refs, repo=self._repo)) class FindShallowTests(TestCase): def setUp(self): super(FindShallowTests, self).setUp() self._store = MemoryObjectStore() def make_commit(self, **attrs): commit = make_commit(**attrs) self._store.add_object(commit) return commit def make_linear_commits(self, n, message=b''): commits = [] parents = [] for _ in range(n): commits.append(self.make_commit(parents=parents, message=message)) parents = [commits[-1].id] return commits def assertSameElements(self, expected, actual): self.assertEqual(set(expected), set(actual)) def test_linear(self): c1, c2, c3 = self.make_linear_commits(3) self.assertEqual((set([c3.id]), set([])), - _find_shallow(self._store, [c3.id], 0)) - self.assertEqual((set([c2.id]), set([c3.id])), _find_shallow(self._store, [c3.id], 1)) - self.assertEqual((set([c1.id]), set([c2.id, c3.id])), + self.assertEqual((set([c2.id]), set([c3.id])), _find_shallow(self._store, [c3.id], 2)) - self.assertEqual((set([]), set([c1.id, c2.id, c3.id])), + self.assertEqual((set([c1.id]), set([c2.id, c3.id])), _find_shallow(self._store, [c3.id], 3)) + self.assertEqual((set([]), set([c1.id, c2.id, c3.id])), + _find_shallow(self._store, [c3.id], 4)) def test_multiple_independent(self): a = self.make_linear_commits(2, message=b'a') b = self.make_linear_commits(2, message=b'b') c = self.make_linear_commits(2, message=b'c') heads = [a[1].id, b[1].id, c[1].id] self.assertEqual((set([a[0].id, b[0].id, c[0].id]), set(heads)), - _find_shallow(self._store, heads, 1)) + _find_shallow(self._store, heads, 2)) def test_multiple_overlapping(self): # Create the following commit tree: # 1--2 # \ # 3--4 c1, c2 = self.make_linear_commits(2) c3 = self.make_commit(parents=[c1.id]) c4 = self.make_commit(parents=[c3.id]) # 1 is shallow along the path from 4, but not along the path from 2. self.assertEqual((set([c1.id]), set([c1.id, c2.id, c3.id, c4.id])), - _find_shallow(self._store, [c2.id, c4.id], 2)) + _find_shallow(self._store, [c2.id, c4.id], 3)) def test_merge(self): c1 = self.make_commit() c2 = self.make_commit() c3 = self.make_commit(parents=[c1.id, c2.id]) self.assertEqual((set([c1.id, c2.id]), set([c3.id])), - _find_shallow(self._store, [c3.id], 1)) + _find_shallow(self._store, [c3.id], 2)) def test_tag(self): c1, c2 = self.make_linear_commits(2) tag = make_tag(c2, name=b'tag') self._store.add_object(tag) self.assertEqual((set([c1.id]), set([c2.id])), - _find_shallow(self._store, [tag.id], 1)) + _find_shallow(self._store, [tag.id], 2)) class TestUploadPackHandler(UploadPackHandler): @classmethod def required_capabilities(self): return () class ReceivePackHandlerTestCase(TestCase): def setUp(self): super(ReceivePackHandlerTestCase, self).setUp() self._repo = MemoryRepo.init_bare([], {}) backend = DictBackend({b'/': self._repo}) self._handler = ReceivePackHandler( backend, [b'/', b'host=lolcathost'], TestProto()) def test_apply_pack_del_ref(self): refs = { b'refs/heads/master': TWO, b'refs/heads/fake-branch': ONE} self._repo.refs._update(refs) update_refs = [[ONE, ZERO_SHA, b'refs/heads/fake-branch'], ] status = self._handler._apply_pack(update_refs) self.assertEqual(status[0][0], b'unpack') self.assertEqual(status[0][1], b'ok') self.assertEqual(status[1][0], b'refs/heads/fake-branch') self.assertEqual(status[1][1], b'ok') class ProtocolGraphWalkerEmptyTestCase(TestCase): def setUp(self): super(ProtocolGraphWalkerEmptyTestCase, self).setUp() self._repo = MemoryRepo.init_bare([], {}) backend = DictBackend({b'/': self._repo}) self._walker = ProtocolGraphWalker( TestUploadPackHandler(backend, [b'/', b'host=lolcats'], TestProto()), self._repo.object_store, self._repo.get_peeled) def test_empty_repository(self): # The server should wait for a flush packet. self._walker.proto.set_output([]) self.assertRaises(HangupException, self._walker.determine_wants, {}) self.assertEqual(None, self._walker.proto.get_received_line()) self._walker.proto.set_output([None]) self.assertEqual([], self._walker.determine_wants({})) self.assertEqual(None, self._walker.proto.get_received_line()) class ProtocolGraphWalkerTestCase(TestCase): def setUp(self): super(ProtocolGraphWalkerTestCase, self).setUp() # Create the following commit tree: # 3---5 # / # 1---2---4 commits = [ make_commit(id=ONE, parents=[], commit_time=111), make_commit(id=TWO, parents=[ONE], commit_time=222), make_commit(id=THREE, parents=[ONE], commit_time=333), make_commit(id=FOUR, parents=[TWO], commit_time=444), make_commit(id=FIVE, parents=[THREE], commit_time=555), ] self._repo = MemoryRepo.init_bare(commits, {}) backend = DictBackend({b'/': self._repo}) self._walker = ProtocolGraphWalker( TestUploadPackHandler(backend, [b'/', b'host=lolcats'], TestProto()), self._repo.object_store, self._repo.get_peeled) def test_all_wants_satisfied_no_haves(self): self._walker.set_wants([ONE]) self.assertFalse(self._walker.all_wants_satisfied([])) self._walker.set_wants([TWO]) self.assertFalse(self._walker.all_wants_satisfied([])) self._walker.set_wants([THREE]) self.assertFalse(self._walker.all_wants_satisfied([])) def test_all_wants_satisfied_have_root(self): self._walker.set_wants([ONE]) self.assertTrue(self._walker.all_wants_satisfied([ONE])) self._walker.set_wants([TWO]) self.assertTrue(self._walker.all_wants_satisfied([ONE])) self._walker.set_wants([THREE]) self.assertTrue(self._walker.all_wants_satisfied([ONE])) def test_all_wants_satisfied_have_branch(self): self._walker.set_wants([TWO]) self.assertTrue(self._walker.all_wants_satisfied([TWO])) # wrong branch self._walker.set_wants([THREE]) self.assertFalse(self._walker.all_wants_satisfied([TWO])) def test_all_wants_satisfied(self): self._walker.set_wants([FOUR, FIVE]) # trivial case: wants == haves self.assertTrue(self._walker.all_wants_satisfied([FOUR, FIVE])) # cases that require walking the commit tree self.assertTrue(self._walker.all_wants_satisfied([ONE])) self.assertFalse(self._walker.all_wants_satisfied([TWO])) self.assertFalse(self._walker.all_wants_satisfied([THREE])) self.assertTrue(self._walker.all_wants_satisfied([TWO, THREE])) def test_split_proto_line(self): allowed = (b'want', b'done', None) self.assertEqual((b'want', ONE), _split_proto_line(b'want ' + ONE + b'\n', allowed)) self.assertEqual((b'want', TWO), _split_proto_line(b'want ' + TWO + b'\n', allowed)) self.assertRaises(GitProtocolError, _split_proto_line, b'want xxxx\n', allowed) self.assertRaises(UnexpectedCommandError, _split_proto_line, b'have ' + THREE + b'\n', allowed) self.assertRaises(GitProtocolError, _split_proto_line, b'foo ' + FOUR + b'\n', allowed) self.assertRaises(GitProtocolError, _split_proto_line, b'bar', allowed) self.assertEqual((b'done', None), _split_proto_line(b'done\n', allowed)) self.assertEqual((None, None), _split_proto_line(b'', allowed)) def test_determine_wants(self): self._walker.proto.set_output([None]) self.assertEqual([], self._walker.determine_wants({})) self.assertEqual(None, self._walker.proto.get_received_line()) self._walker.proto.set_output([ b'want ' + ONE + b' multi_ack', b'want ' + TWO, None, ]) heads = { b'refs/heads/ref1': ONE, b'refs/heads/ref2': TWO, b'refs/heads/ref3': THREE, } self._repo.refs._update(heads) self.assertEqual([ONE, TWO], self._walker.determine_wants(heads)) self._walker.advertise_refs = True self.assertEqual([], self._walker.determine_wants(heads)) self._walker.advertise_refs = False self._walker.proto.set_output([b'want ' + FOUR + b' multi_ack', None]) self.assertRaises(GitProtocolError, self._walker.determine_wants, heads) self._walker.proto.set_output([None]) self.assertEqual([], self._walker.determine_wants(heads)) self._walker.proto.set_output([b'want ' + ONE + b' multi_ack', b'foo', None]) self.assertRaises(GitProtocolError, self._walker.determine_wants, heads) self._walker.proto.set_output([b'want ' + FOUR + b' multi_ack', None]) self.assertRaises(GitProtocolError, self._walker.determine_wants, heads) def test_determine_wants_advertisement(self): self._walker.proto.set_output([None]) # advertise branch tips plus tag heads = { b'refs/heads/ref4': FOUR, b'refs/heads/ref5': FIVE, b'refs/heads/tag6': SIX, } self._repo.refs._update(heads) self._repo.refs._update_peeled(heads) self._repo.refs._update_peeled({b'refs/heads/tag6': FIVE}) self._walker.determine_wants(heads) lines = [] while True: line = self._walker.proto.get_received_line() if line is None: break # strip capabilities list if present if b'\x00' in line: line = line[:line.index(b'\x00')] lines.append(line.rstrip()) self.assertEqual([ FOUR + b' refs/heads/ref4', FIVE + b' refs/heads/ref5', FIVE + b' refs/heads/tag6^{}', SIX + b' refs/heads/tag6', ], sorted(lines)) # ensure peeled tag was advertised immediately following tag for i, line in enumerate(lines): if line.endswith(b' refs/heads/tag6'): self.assertEqual(FIVE + b' refs/heads/tag6^{}', lines[i+1]) # TODO: test commit time cutoff def _handle_shallow_request(self, lines, heads): self._walker.proto.set_output(lines + [None]) self._walker._handle_shallow_request(heads) def assertReceived(self, expected): self.assertEqual( expected, list(iter(self._walker.proto.get_received_line, None))) def test_handle_shallow_request_no_client_shallows(self): - self._handle_shallow_request([b'deepen 1\n'], [FOUR, FIVE]) + self._handle_shallow_request([b'deepen 2\n'], [FOUR, FIVE]) self.assertEqual(set([TWO, THREE]), self._walker.shallow) self.assertReceived([ b'shallow ' + TWO, b'shallow ' + THREE, ]) def test_handle_shallow_request_no_new_shallows(self): lines = [ b'shallow ' + TWO + b'\n', b'shallow ' + THREE + b'\n', - b'deepen 1\n', + b'deepen 2\n', ] self._handle_shallow_request(lines, [FOUR, FIVE]) self.assertEqual(set([TWO, THREE]), self._walker.shallow) self.assertReceived([]) def test_handle_shallow_request_unshallows(self): lines = [ b'shallow ' + TWO + b'\n', - b'deepen 2\n', + b'deepen 3\n', ] self._handle_shallow_request(lines, [FOUR, FIVE]) self.assertEqual(set([ONE]), self._walker.shallow) self.assertReceived([ b'shallow ' + ONE, b'unshallow ' + TWO, # THREE is unshallow but was is not shallow in the client ]) class TestProtocolGraphWalker(object): def __init__(self): self.acks = [] self.lines = [] self.wants_satisified = False self.http_req = None self.advertise_refs = False self._impl = None self.done_required = True self.done_received = False self._empty = False self.pack_sent = False def read_proto_line(self, allowed): command, sha = self.lines.pop(0) if allowed is not None: assert command in allowed return command, sha def send_ack(self, sha, ack_type=b''): self.acks.append((sha, ack_type)) def send_nak(self): self.acks.append((None, b'nak')) def all_wants_satisfied(self, haves): if haves: return self.wants_satisified def pop_ack(self): if not self.acks: return None return self.acks.pop(0) def handle_done(self): if not self._impl: return # Whether or not PACK is sent after is determined by this, so # record this value. self.pack_sent = self._impl.handle_done(self.done_required, self.done_received) return self.pack_sent def notify_done(self): self.done_received = True class AckGraphWalkerImplTestCase(TestCase): """Base setup and asserts for AckGraphWalker tests.""" def setUp(self): super(AckGraphWalkerImplTestCase, self).setUp() self._walker = TestProtocolGraphWalker() self._walker.lines = [ (b'have', TWO), (b'have', ONE), (b'have', THREE), (b'done', None), ] self._impl = self.impl_cls(self._walker) self._walker._impl = self._impl def assertNoAck(self): self.assertEqual(None, self._walker.pop_ack()) def assertAcks(self, acks): for sha, ack_type in acks: self.assertEqual((sha, ack_type), self._walker.pop_ack()) self.assertNoAck() def assertAck(self, sha, ack_type=b''): self.assertAcks([(sha, ack_type)]) def assertNak(self): self.assertAck(None, b'nak') def assertNextEquals(self, sha): self.assertEqual(sha, next(self._impl)) def assertNextEmpty(self): # This is necessary because of no-done - the assumption that it # it safe to immediately send out the final ACK is no longer # true but the test is still needed for it. TestProtocolWalker # does implement the handle_done which will determine whether # the final confirmation can be sent. self.assertRaises(IndexError, next, self._impl) self._walker.handle_done() class SingleAckGraphWalkerImplTestCase(AckGraphWalkerImplTestCase): impl_cls = SingleAckGraphWalkerImpl def test_single_ack(self): self.assertNextEquals(TWO) self.assertNoAck() self.assertNextEquals(ONE) self._impl.ack(ONE) self.assertAck(ONE) self.assertNextEquals(THREE) self._impl.ack(THREE) self.assertNoAck() self.assertNextEquals(None) self.assertNoAck() def test_single_ack_flush(self): # same as ack test but ends with a flush-pkt instead of done self._walker.lines[-1] = (None, None) self.assertNextEquals(TWO) self.assertNoAck() self.assertNextEquals(ONE) self._impl.ack(ONE) self.assertAck(ONE) self.assertNextEquals(THREE) self.assertNoAck() self.assertNextEquals(None) self.assertNoAck() def test_single_ack_nak(self): self.assertNextEquals(TWO) self.assertNoAck() self.assertNextEquals(ONE) self.assertNoAck() self.assertNextEquals(THREE) self.assertNoAck() self.assertNextEquals(None) self.assertNextEmpty() self.assertNak() def test_single_ack_nak_flush(self): # same as nak test but ends with a flush-pkt instead of done self._walker.lines[-1] = (None, None) self.assertNextEquals(TWO) self.assertNoAck() self.assertNextEquals(ONE) self.assertNoAck() self.assertNextEquals(THREE) self.assertNoAck() self.assertNextEquals(None) self.assertNextEmpty() self.assertNak() class MultiAckGraphWalkerImplTestCase(AckGraphWalkerImplTestCase): impl_cls = MultiAckGraphWalkerImpl def test_multi_ack(self): self.assertNextEquals(TWO) self.assertNoAck() self.assertNextEquals(ONE) self._impl.ack(ONE) self.assertAck(ONE, b'continue') self.assertNextEquals(THREE) self._impl.ack(THREE) self.assertAck(THREE, b'continue') self.assertNextEquals(None) self.assertNextEmpty() self.assertAck(THREE) def test_multi_ack_partial(self): self.assertNextEquals(TWO) self.assertNoAck() self.assertNextEquals(ONE) self._impl.ack(ONE) self.assertAck(ONE, b'continue') self.assertNextEquals(THREE) self.assertNoAck() self.assertNextEquals(None) self.assertNextEmpty() self.assertAck(ONE) def test_multi_ack_flush(self): self._walker.lines = [ (b'have', TWO), (None, None), (b'have', ONE), (b'have', THREE), (b'done', None), ] self.assertNextEquals(TWO) self.assertNoAck() self.assertNextEquals(ONE) self.assertNak() # nak the flush-pkt self._impl.ack(ONE) self.assertAck(ONE, b'continue') self.assertNextEquals(THREE) self._impl.ack(THREE) self.assertAck(THREE, b'continue') self.assertNextEquals(None) self.assertNextEmpty() self.assertAck(THREE) def test_multi_ack_nak(self): self.assertNextEquals(TWO) self.assertNoAck() self.assertNextEquals(ONE) self.assertNoAck() self.assertNextEquals(THREE) self.assertNoAck() self.assertNextEquals(None) self.assertNextEmpty() self.assertNak() class MultiAckDetailedGraphWalkerImplTestCase(AckGraphWalkerImplTestCase): impl_cls = MultiAckDetailedGraphWalkerImpl def test_multi_ack(self): self.assertNextEquals(TWO) self.assertNoAck() self.assertNextEquals(ONE) self._impl.ack(ONE) self.assertAck(ONE, b'common') self.assertNextEquals(THREE) self._impl.ack(THREE) self.assertAck(THREE, b'common') # done is read. self._walker.wants_satisified = True self.assertNextEquals(None) self._walker.lines.append((None, None)) self.assertNextEmpty() self.assertAcks([(THREE, b'ready'), (None, b'nak'), (THREE, b'')]) # PACK is sent self.assertTrue(self._walker.pack_sent) def test_multi_ack_nodone(self): self._walker.done_required = False self.assertNextEquals(TWO) self.assertNoAck() self.assertNextEquals(ONE) self._impl.ack(ONE) self.assertAck(ONE, b'common') self.assertNextEquals(THREE) self._impl.ack(THREE) self.assertAck(THREE, b'common') # done is read. self._walker.wants_satisified = True self.assertNextEquals(None) self._walker.lines.append((None, None)) self.assertNextEmpty() self.assertAcks([(THREE, b'ready'), (None, b'nak'), (THREE, b'')]) # PACK is sent self.assertTrue(self._walker.pack_sent) def test_multi_ack_flush_end(self): # transmission ends with a flush-pkt without a done but no-done is # assumed. self._walker.lines[-1] = (None, None) self.assertNextEquals(TWO) self.assertNoAck() self.assertNextEquals(ONE) self._impl.ack(ONE) self.assertAck(ONE, b'common') self.assertNextEquals(THREE) self._impl.ack(THREE) self.assertAck(THREE, b'common') # no done is read self._walker.wants_satisified = True self.assertNextEmpty() self.assertAcks([(THREE, b'ready'), (None, b'nak')]) # PACK is NOT sent self.assertFalse(self._walker.pack_sent) def test_multi_ack_flush_end_nodone(self): # transmission ends with a flush-pkt without a done but no-done is # assumed. self._walker.lines[-1] = (None, None) self._walker.done_required = False self.assertNextEquals(TWO) self.assertNoAck() self.assertNextEquals(ONE) self._impl.ack(ONE) self.assertAck(ONE, b'common') self.assertNextEquals(THREE) self._impl.ack(THREE) self.assertAck(THREE, b'common') # no done is read, but pretend it is (last 'ACK 'commit_id' '') self._walker.wants_satisified = True self.assertNextEmpty() self.assertAcks([(THREE, b'ready'), (None, b'nak'), (THREE, b'')]) # PACK is sent self.assertTrue(self._walker.pack_sent) def test_multi_ack_partial(self): self.assertNextEquals(TWO) self.assertNoAck() self.assertNextEquals(ONE) self._impl.ack(ONE) self.assertAck(ONE, b'common') self.assertNextEquals(THREE) self.assertNoAck() self.assertNextEquals(None) self.assertNextEmpty() self.assertAck(ONE) def test_multi_ack_flush(self): # same as ack test but contains a flush-pkt in the middle self._walker.lines = [ (b'have', TWO), (None, None), (b'have', ONE), (b'have', THREE), (b'done', None), (None, None), ] self.assertNextEquals(TWO) self.assertNoAck() self.assertNextEquals(ONE) self.assertNak() # nak the flush-pkt self._impl.ack(ONE) self.assertAck(ONE, b'common') self.assertNextEquals(THREE) self._impl.ack(THREE) self.assertAck(THREE, b'common') self._walker.wants_satisified = True self.assertNextEquals(None) self.assertNextEmpty() self.assertAcks([(THREE, b'ready'), (None, b'nak'), (THREE, b'')]) def test_multi_ack_nak(self): self.assertNextEquals(TWO) self.assertNoAck() self.assertNextEquals(ONE) self.assertNoAck() self.assertNextEquals(THREE) self.assertNoAck() # Done is sent here. self.assertNextEquals(None) self.assertNextEmpty() self.assertNak() self.assertNextEmpty() self.assertTrue(self._walker.pack_sent) def test_multi_ack_nak_nodone(self): self._walker.done_required = False self.assertNextEquals(TWO) self.assertNoAck() self.assertNextEquals(ONE) self.assertNoAck() self.assertNextEquals(THREE) self.assertNoAck() # Done is sent here. self.assertFalse(self._walker.pack_sent) self.assertNextEquals(None) self.assertNextEmpty() self.assertTrue(self._walker.pack_sent) self.assertNak() self.assertNextEmpty() def test_multi_ack_nak_flush(self): # same as nak test but contains a flush-pkt in the middle self._walker.lines = [ (b'have', TWO), (None, None), (b'have', ONE), (b'have', THREE), (b'done', None), ] self.assertNextEquals(TWO) self.assertNoAck() self.assertNextEquals(ONE) self.assertNak() self.assertNextEquals(THREE) self.assertNoAck() self.assertNextEquals(None) self.assertNextEmpty() self.assertNak() def test_multi_ack_stateless(self): # transmission ends with a flush-pkt self._walker.lines[-1] = (None, None) self._walker.http_req = True self.assertNextEquals(TWO) self.assertNoAck() self.assertNextEquals(ONE) self.assertNoAck() self.assertNextEquals(THREE) self.assertNoAck() self.assertFalse(self._walker.pack_sent) self.assertNextEquals(None) self.assertNak() self.assertNextEmpty() self.assertNoAck() self.assertFalse(self._walker.pack_sent) def test_multi_ack_stateless_nodone(self): self._walker.done_required = False # transmission ends with a flush-pkt self._walker.lines[-1] = (None, None) self._walker.http_req = True self.assertNextEquals(TWO) self.assertNoAck() self.assertNextEquals(ONE) self.assertNoAck() self.assertNextEquals(THREE) self.assertNoAck() self.assertFalse(self._walker.pack_sent) self.assertNextEquals(None) self.assertNak() self.assertNextEmpty() self.assertNoAck() # PACK will still not be sent. self.assertFalse(self._walker.pack_sent) class FileSystemBackendTests(TestCase): """Tests for FileSystemBackend.""" def setUp(self): super(FileSystemBackendTests, self).setUp() self.path = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, self.path) self.repo = Repo.init(self.path) self.backend = FileSystemBackend() def test_nonexistant(self): self.assertRaises(NotGitRepository, self.backend.open_repository, "/does/not/exist/unless/foo") def test_absolute(self): repo = self.backend.open_repository(self.path) self.assertEqual( os.path.normcase(os.path.abspath(repo.path)), os.path.normcase(os.path.abspath(self.repo.path))) def test_child(self): self.assertRaises(NotGitRepository, self.backend.open_repository, os.path.join(self.path, "foo")) def test_bad_repo_path(self): backend = FileSystemBackend() self.assertRaises(NotGitRepository, lambda: backend.open_repository('/ups')) class DictBackendTests(TestCase): """Tests for DictBackend.""" def test_nonexistant(self): repo = MemoryRepo.init_bare([], {}) backend = DictBackend({b'/': repo}) self.assertRaises(NotGitRepository, backend.open_repository, "/does/not/exist/unless/foo") def test_bad_repo_path(self): repo = MemoryRepo.init_bare([], {}) backend = DictBackend({b'/': repo}) self.assertRaises(NotGitRepository, lambda: backend.open_repository('/ups')) class ServeCommandTests(TestCase): """Tests for serve_command.""" def setUp(self): super(ServeCommandTests, self).setUp() self.backend = DictBackend({}) def serve_command(self, handler_cls, args, inf, outf): return serve_command(handler_cls, [b"test"] + args, backend=self.backend, inf=inf, outf=outf) def test_receive_pack(self): commit = make_commit(id=ONE, parents=[], commit_time=111) self.backend.repos[b"/"] = MemoryRepo.init_bare( [commit], {b"refs/heads/master": commit.id}) outf = BytesIO() exitcode = self.serve_command(ReceivePackHandler, [b"/"], BytesIO(b"0000"), outf) outlines = outf.getvalue().splitlines() self.assertEqual(2, len(outlines)) self.assertEqual(b"1111111111111111111111111111111111111111 refs/heads/master", outlines[0][4:].split(b"\x00")[0]) self.assertEqual(b"0000", outlines[-1]) self.assertEqual(0, exitcode) class UpdateServerInfoTests(TestCase): """Tests for update_server_info.""" def setUp(self): super(UpdateServerInfoTests, self).setUp() self.path = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, self.path) self.repo = Repo.init(self.path) def test_empty(self): update_server_info(self.repo) with open(os.path.join(self.path, ".git", "info", "refs"), 'rb') as f: self.assertEqual(b'', f.read()) with open(os.path.join(self.path, ".git", "objects", "info", "packs"), 'rb') as f: self.assertEqual(b'', f.read()) def test_simple(self): commit_id = self.repo.do_commit( message=b"foo", committer=b"Joe Example ", ref=b"refs/heads/foo") update_server_info(self.repo) with open(os.path.join(self.path, ".git", "info", "refs"), 'rb') as f: self.assertEqual(f.read(), commit_id + b'\trefs/heads/foo\n') with open(os.path.join(self.path, ".git", "objects", "info", "packs"), 'rb') as f: self.assertEqual(f.read(), b'') diff --git a/examples/clone.py b/examples/clone.py index 03e5dd92..c14fa9f9 100644 --- a/examples/clone.py +++ b/examples/clone.py @@ -1,34 +1,18 @@ #!/usr/bin/python # This trivial script demonstrates how to clone a remote repository. # # Example usage: # python examples/clone.py git://github.com/jelmer/dulwich dulwich-clone import sys from getopt import getopt -from dulwich.repo import Repo -from dulwich.client import get_transport_and_path +from dulwich import porcelain opts, args = getopt(sys.argv, "", []) opts = dict(opts) if len(args) < 2: print("usage: %s host:path path" % (args[0], )) sys.exit(1) -# Connect to the remote repository -client, host_path = get_transport_and_path(args[1]) -path = args[2] - -# Create the local repository -r = Repo.init(path, mkdir=True) - -# Fetch the remote objects -remote_refs = client.fetch(host_path, r, - determine_wants=r.object_store.determine_wants_all, - progress=sys.stdout.write) - -# Update the local head to point at the right object -r["HEAD"] = remote_refs["HEAD"] - -r._build_tree() +porcelain.clone(args[1], args[2]) diff --git a/relicensing-apachev2.txt b/relicensing-apachev2.txt deleted file mode 100644 index 13adac87..00000000 --- a/relicensing-apachev2.txt +++ /dev/null @@ -1,110 +0,0 @@ -At the moment, Dulwich is licensed under the GNU General Public License, -version 2 or later. - -We'd like to relicense Dulwich under the Apache v2 (or later) license, as -the GPL is problematic for many free software Python projects that are under -BSD-style licenses. See also https://github.com/jelmer/dulwich/issues/153 - -For reference, a full copy of the Apachev2 license can be found here: -https://www.apache.org/licenses/LICENSE-2.0 - -New contributions to Dulwich should be dual licensed under the GNU GPLv2 (or -later) and the Apachev2 (or later) licenses. - -Contributions made prior were contributed under the GPLv2 (or later) license -alone. The following contributors have not (yet) relicensed their code under -dual Apachev2/GPLv2: - -Aaron O'Mullan -Abderrahim Kitouni -Adam "Cezar" Jenkins -Alberto Ruiz -Alexander Belchenko -Alex Holmes -Ali Sabil -Andi McClure -André Roth -Andres Lowrie -Artem Tikhomirov -Augie Fackler -Benjamin Pollack -Brendan Cully -Brian Visel -Bruce Duncan -Bruno Renié -Chaiwat Suttipongsakul -Chow Loong Jin -Chris Eberle -Chris Reid -codingtony -dak180 -Damien Tournoud -Dan Callaghan -Daniele Sluijters -David Bennett -David Blewett -David Borowitz -David Carr -David Keijser -David Ostrovsky -David Pursehouse -DeeKey -Dirk -diryboy -D-Key -Dmitrij D. Czarkoff -Dmitriy -Dov Feldstern -Fabien Boucher -Gary van der Merwé -Hal Wine -Hannu Valtonen -Hans Kolek -Hervé Cauwelier -Hwee Miin Koh -Jameson Nash -James Westby -Jason R. Coombs -John Arbash Meinel -John Carr -Jonathan Chu -kwatters -Lukasz Balcerzak -Marc Brinkmann -Marcin Kuźmiński -Martin Packman -Max Bowsher -max -Max Shawabkeh -Michael K -Mike Edgar -Mike Williams -Nick Stenning -Nick Ward -Nix -Pascal Quantin -Paul Chen -Paul Hummer -rfaulk -Ricardo Salveti -Risto Kankkunen -Robert Brown -Rod Cloutier -Roland Mas -Ronald Blaschke -Ross Light -Ryan Faulkner -Ryan McKern -Sam Vilain -Siddharth Agarwal -Stefan Zimmermann -Takeshi Kanemoto -Tay Ray Chuan -Ted Horst -Timo Schmid -Tommy Yu -Travis Cline -Víðir Valberg Guðmundsson -William Grant -Yifan Zhang -Yuval Langer diff --git a/setup.cfg b/setup.cfg index a2c4ef84..f8e48de9 100644 --- a/setup.cfg +++ b/setup.cfg @@ -1 +1,7 @@ [build_ext] + +[egg_info] +tag_build = +tag_date = 0 +tag_svn_revision = 0 + diff --git a/setup.py b/setup.py index 95028ceb..eb6d683d 100755 --- a/setup.py +++ b/setup.py @@ -1,111 +1,112 @@ #!/usr/bin/python # Setup file for dulwich -# Copyright (C) 2008-2011 Jelmer Vernooij +# Copyright (C) 2008-2011 Jelmer Vernooij try: from setuptools import setup, Extension except ImportError: from distutils.core import setup, Extension from distutils.core import Distribution -dulwich_version_string = '0.10.2' +dulwich_version_string = '0.11.1' include_dirs = [] # Windows MSVC support import os import sys if sys.platform == 'win32': 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") # 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: os.environ['ARCHFLAGS'] = '' if sys.version_info[0] == 2: - tests_require = ['fastimport', 'mock'] + tests_require = ['fastimport'] if not '__pypy__' in sys.modules and not sys.platform == 'win32': - tests_require.extend(['gevent', 'geventhttpclient']) + tests_require.extend([ + 'gevent', 'geventhttpclient', 'mock', 'setuptools>=17.1']) + if sys.version_info < (2, 7): + tests_require.append('unittest2') else: # fastimport, gevent, geventhttpclient are not available for PY3 # mock only used for test_swift, which requires gevent/geventhttpclient tests_require = [] -if sys.version_info < (2, 7): - tests_require.append('unittest2') if sys.version_info[0] > 2 and sys.platform == 'win32': # C Modules don't build for python3 windows, and prevent tests from running ext_modules = [] else: 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(name='dulwich', description='Python Git Library', keywords='git', version=dulwich_version_string, - url='https://samba.org/~jelmer/dulwich', + url='https://www.dulwich.io/', license='GPLv2 or later', author='Jelmer Vernooij', - author_email='jelmer@samba.org', + 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 :: GNU General Public License v2 or later (GPLv2+)', 'Programming Language :: Python :: 2.6', 'Programming Language :: Python :: 2.7', 'Programming Language :: Python :: 3.4', 'Programming Language :: Python :: Implementation :: CPython', 'Programming Language :: Python :: Implementation :: PyPy', 'Operating System :: POSIX', '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, ) diff --git a/tox.ini b/tox.ini index 3cef5a26..07e7b733 100644 --- a/tox.ini +++ b/tox.ini @@ -1,26 +1,20 @@ [tox] downloadcache = {toxworkdir}/cache/ -envlist = py27, pypy, py27-noext, pypy-noext +envlist = py26, py27, pypy, py27-noext, pypy-noext, py34, py34-noext [testenv] deps = unittest2 commands = make check recreate = True whitelist_externals = make -[testenv:py24] -setenv = - PIP_INSECURE=1 - - -[testenv:py25] -setenv = - PIP_INSECURE=1 - [testenv:py27-noext] commands = make check-noextensions [testenv:pypy-noext] commands = make check-noextensions + +[testenv:py34-noext] +commands = make check-noextensions