diff --git a/.travis.yml b/.travis.yml index 966730aa..da03b82b 100644 --- a/.travis.yml +++ b/.travis.yml @@ -1,69 +1,67 @@ language: python sudo: false cache: pip python: - - 2.7 - - 3.4 - 3.5 - 3.6 + - 3.7 + - 3.8 - pypy3.5 env: - PYTHONHASHSEED=random TEST_REQUIRE="gevent greenlet geventhttpclient fastimport" PURE=false matrix: include: - python: pypy env: TEST_REQUIRE=fastimport - python: 3.7 env: TEST_REQUIRE=fastimport dist: xenial sudo: true - python: 3.8 env: TEST_REQUIRE=fastimport dist: xenial sudo: true - python: 3.8 env: TEST_REQUIRE=fastimport dist: xenial sudo: true - python: 3.6 env: PURE=true - - python: 2.7 - env: PURE=true install: - travis_retry pip install -U pip coverage codecov flake8 $TEST_REQUIRE script: - if [ $PURE = false ]; then python setup.py build_ext -i; fi - python -m coverage run -p -m unittest dulwich.tests.test_suite # Style - make style - if [ $PURE = true ]; then SETUP_ARGS=--pure; fi - python setup.py $SETUP_ARGS bdist_wheel after_success: - python -m coverage combine - codecov deploy: provider: pypi user: dulwich-bot password: secure: Q8DDDojBugQWzXvmmEQiU90UkVPk+OYoFZwv1H9LYpQ4u5CfwQNWpf8qXYhlGMdr/gzWaSWsqLvgWLpzfkvqS4Vyk2bO9mr+dSskfD8uwc82LiiL9CNd/NY03CjH9RaFgVMD/+exMjY/yCtlyH1jL4kjgOyNnC+x4B37CliZHcE= skip_cleanup: true skip_existing: true file_glob: true file: - dist/dulwich*.whl - dist/dulwich*.tar.gz on: tags: true repo: dulwich/dulwich diff --git a/NEWS b/NEWS index 0621219e..c2279371 100644 --- a/NEWS +++ b/NEWS @@ -1,2023 +1,2027 @@ +0.20.0 UNRELEASED + + * Drop support for Python 2. (Jelmer Vernooij) + 0.19.17 UNRELEASED * Don't break when encountering block devices. (Jelmer Vernooij) * Decode URL paths in HttpGitClient using utf-8 rather than file system encoding. (Manuel Jacob) * Fix pushing from a shallow clone. (Brecht Machiels, #705) 0.19.16 2020-04-17 * Don't send "deepen None" to server if graph walker supports shallow. (Jelmer Vernooij, #747) * Support tweaking the compression level for loose objects through the "core.looseCompression" and "core.compression" settings. (Jelmer Vernooij) * Support tweaking the compression level for pack objects through the "core.packCompression" and "core.compression" settings. (Jelmer Vernooij) * Add a "dulwich.contrib.diffstat" module. (Kevin Hendricks) 0.19.15 2020-01-26 * Properly handle files that are just executable for the current user. (Jelmer Vernooij, #734) * Fix handling of stored encoding in ``dulwich.porcelain.get_object_by_path`` on Python 3. (Jelmer Vernooij) * Support the include_trees and rename_detector arguments at the same time when diffing trees. (Jelmer Vernooij) 0.19.14 2019-11-30 * Strip superfluous <> around email. (monnerat) * Stop checking for ref validity client-side. Users can still call check_wants manually. (Jelmer Vernooij) * Switch over to Google-style docstrings. (Jelmer Vernooij) * Add a ``dulwich.porcelain.active_branch`` function. (Jelmer Vernooij) * Cleanup new directory if clone fails. (Jelmer Vernooij, #733) * Expand "~" in global exclude path. (Jelmer Vernooij) 0.19.13 2019-08-19 BUG FIXES * Avoid ``PermissionError``, since it is Python3-specific. (Jelmer Vernooij) * Fix regression that added a dependency on C git for the test suite. (Jelmer Vernooij, #720) * Fix compatibility with Python 3.8 - mostly deprecation warnings. (Jelmer Vernooij) 0.19.12 2019-08-13 BUG FIXES * Update directory detection for `get_unstaged_changes` for Python 3. (Boris Feld, #684) * Add a basic ``porcelain.clean``. (Lane Barlow, #398) * Fix output format of ``porcelain.diff`` to match that of C Git. (Boris Feld) * Return a 404 not found error when repository is not found. * Mark ``.git`` directories as hidden on Windows. (Martin Packman, #585) * Implement ``RefsContainer.__iter__`` (Jelmer Vernooij, #717) * Don't trust modes if they can't be modified after a file has been created. (Jelmer Vernooij, #719) 0.19.11 2019-02-07 IMPROVEMENTS * Use fullname from gecos field, if available. (Jelmer Vernooij) * Support ``GIT_AUTHOR_NAME`` / ``GIT_AUTHOR_EMAIL``. (Jelmer Vernooij) * Add support for short ids in parse_commit. (Jelmer Vernooij) * Add support for ``prune`` and ``prune_tags`` arguments to ``porcelain.fetch``. (Jelmer Vernooij, #681) BUG FIXES * Fix handling of race conditions when new packs appear. (Jelmer Vernooij) 0.19.10 2018-01-15 IMPROVEMENTS * Add `dulwich.porcelain.write_tree`. (Jelmer Vernooij) * Support reading ``MERGE_HEADS`` in ``Repo.do_commit``. (Jelmer Vernooij) * Import from ``collections.abc`` rather than ``collections`` where applicable. Required for 3.8 compatibility. (Jelmer Vernooij) * Support plain strings as refspec arguments to ``dulwich.porcelain.push``. (Jelmer Vernooij) * Add support for creating signed tags. (Jelmer Vernooij, #542) BUG FIXES * Handle invalid ref that pretends to be a sub-folder under a valid ref. (KS Chan) 0.19.9 2018-11-17 BUG FIXES * Avoid fetching ghosts in ``Repo.fetch``. (Jelmer Vernooij) * Preserve port and username in parsed HTTP URLs. (Jelmer Vernooij) * Add basic server side implementation of ``git-upload-archive``. (Jelmer Vernooij) 0.19.8 2018-11-06 * Fix encoding when reading README file in setup.py. (egor , #668) 0.19.7 2018-11-05 CHANGES * Drop support for Python 3 < 3.4. This is because pkg_resources (which get used by setuptools and mock) no longer supports 3.3 and earlier. (Jelmer Vernooij) IMPROVEMENTS * Support ``depth`` argument to ``GitClient.fetch_pack`` and support fetching and updating shallow metadata. (Jelmer Vernooij, #240) BUG FIXES * Don't write to stdout and stderr when they are not available (such as is the case for pythonw). (Sylvia van Os, #652) * Fix compatibility with newer versions of git, which expect CONTENT_LENGTH to be set to 0 for empty body requests. (Jelmer Vernooij, #657) * Raise an exception client-side when a caller tries to request SHAs that are not directly referenced the servers' refs. (Jelmer Vernooij) * Raise more informative errors when unable to connect to repository over SSH or subprocess. (Jelmer Vernooij) * Handle commit identity fields with multiple ">" characters. (Nicolas Dandrimont) IMPROVEMENTS * ``dulwich.porcelain.get_object_by_path`` method for easily accessing a path in another tree. (Jelmer Vernooij) * Support the ``i18n.commitEncoding`` setting in config. (Jelmer Vernooij) 0.19.6 2018-08-11 BUG FIXES * Fix support for custom transport arguments in ``dulwich.porcelain.clone``. (Semyon Slepov) * Fix compatibility with Python 3.8 (Jelmer Vernooij, Daniel M. Capella) * Fix some corner cases in ``path_to_tree_path``. (Romain Keramitas) * Support paths as bytestrings in various places in ``dulwich.index`` (Jelmer Vernooij) * Avoid setup.cfg for now, since it seems to break pypi metadata. (Jelmer Vernooij, #658) 0.19.5 2018-07-08 IMPROVEMENTS * Add ``porcelain.describe``. (Sylvia van Os) BUG FIXES * Fix regression in ``dulwich.porcelain.clone`` that prevented cloning of remote repositories. (Jelmer Vernooij, #639) * Don't leave around empty parent directories for removed refs. (Damien Tournoud, #640) 0.19.4 2018-06-24 IMPROVEMENTS * Add ``porcelain.ls_files``. (Jelmer Vernooij) * Add ``Index.items``. (Jelmer Vernooij) BUG FIXES * Avoid unicode characters (e.g. the digraph ij in my surname) in setup.cfg, since setuptools doesn't deal well with them. See https://github.com/pypa/setuptools/issues/1062. (Jelmer Vernooij, #637) 0.19.3 2018-06-17 IMPROVEMENTS * Add really basic `dulwich.porcelain.fsck` implementation. (Jelmer Vernooij) * When the `DULWICH_PDB` environment variable is set, make SIGQUIT open pdb in the 'dulwich' command. * Add `checkout` argument to `Repo.clone`. (Jelmer Vernooij, #503) * Add `Repo.get_shallow` method. (Jelmer Vernooij) * Add basic `dulwich.stash` module. (Jelmer Vernooij) * Support a `prefix` argument to `dulwich.archive.tar_stream`. (Jelmer Vernooij) BUG FIXES * Fix handling of encoding for tags. (Jelmer Vernooij, #608) * Fix tutorial tests on Python 3. (Jelmer Vernooij, #573) * Fix remote refs created by `porcelain.fetch`. (Daniel Andersson, #623) * More robust pack creation on Windows. (Daniel Andersson) * Fix recursive option for `porcelain.ls_tree`. (Romain Keramitas) TESTS * Some improvements to paramiko tests. (Filipp Frizzy) 0.19.2 2018-04-07 BUG FIXES * Fix deprecated Index.iterblobs method. (Jelmer Vernooij) 0.19.1 2018-04-05 IMPROVEMENTS * Add 'dulwich.mailmap' file for reading mailmap files. (Jelmer Vernooij) * Dulwich no longer depends on urllib3[secure]. Instead, "dulwich[https]" can be used to pull in the necessary dependencies for HTTPS support. (Jelmer Vernooij, #616) * Support the `http.sslVerify` and `http.sslCAInfo` configuration options. (Jelmer Vernooij) * Factor out `dulwich.client.parse_rsync_url` function. (Jelmer Vernooij) * Fix repeat HTTP requests using the same smart HTTP client. (Jelmer Vernooij) * New 'client.PLinkSSHVendor' for creating connections using PuTTY's plink.exe. (Adam Bradley, Filipp Frizzy) * Only pass in `key_filename` and `password` to SSHVendor implementations if those parameters are set. (This helps with older SSHVendor implementations) (Jelmer Vernooij) API CHANGES * Index.iterblobs has been renamed to Index.iterobjects. (Jelmer Vernooij) 0.19.0 2018-03-10 BUG FIXES * Make `dulwich.archive` set the gzip header file modification time so that archives created from the same Git tree are always identical. (#577, Jonas Haag) * Allow comment characters (#, ;) within configuration file strings (Daniel Andersson, #579) * Raise exception when passing in invalid author/committer values to Repo.do_commit(). (Jelmer Vernooij, #602) IMPROVEMENTS * Add a fastimport ``extra``. (Jelmer Vernooij) * Start writing reflog entries. (Jelmer Vernooij) * Add ability to use password and keyfile ssh options with SSHVendor. (Filipp Kucheryavy) * Add ``change_type_same`` flag to ``tree_changes``. (Jelmer Vernooij) API CHANGES * ``GitClient.send_pack`` now accepts a ``generate_pack_data`` rather than a ``generate_pack_contents`` function for performance reasons. (Jelmer Vernooij) * Dulwich now uses urllib3 internally for HTTP requests. The `opener` argument to `dulwich.client.HttpGitClient` that took a `urllib2` opener instance has been replaced by a `pool_manager` argument that takes a `urllib3` pool manager instance. (Daniel Andersson) 0.18.6 2017-11-11 BUG FIXES * Fix handling of empty repositories in ``porcelain.clone``. (#570, Jelmer Vernooij) * Raise an error when attempting to add paths that are not under the repository. (Jelmer Vernooij) * Fix error message for missing trailing ]. (Daniel Andersson) * Raise EmptyFileException when corruption (in the form of an empty file) is detected. (Antoine R. Dumont, #582) IMPROVEMENTS * Enforce date field parsing consistency. This also add checks on those date fields for potential overflow. (Antoine R. Dumont, #567) 0.18.5 2017-10-29 BUG FIXES * Fix cwd for hooks. (Fabian Grünbichler) * Fix setting of origin in config when non-standard origin is passed into ``Repo.clone``. (Kenneth Lareau, #565) * Prevent setting SSH arguments from SSH URLs when using SSH through a subprocess. Note that Dulwich doesn't support cloning submodules. (CVE-2017-16228) (Jelmer Vernooij) IMPROVEMENTS * Silently ignored directories in ``Repo.stage``. (Jelmer Vernooij, #564) API CHANGES * GitFile now raises ``FileLocked`` when encountering a lock rather than OSError(EEXIST). (Jelmer Vernooij) 0.18.4 2017-10-01 BUG FIXES * Make default User-Agent start with "git/" because GitHub won't response to HTTP smart server requests otherwise (and reply with a 404). (Jelmer vernooij, #562) 0.18.3 2017-09-03 BUG FIXES * Read config during porcelain operations that involve remotes. (Jelmer Vernooij, #545) * Fix headers of empty chunks in unified diffs. (Taras Postument, #543) * Properly follow redirects over HTTP. (Jelmer Vernooij, #117) IMPROVEMENTS * Add ``dulwich.porcelain.update_head``. (Jelmer Vernooij, #439) * ``GitClient.fetch_pack`` now returns symrefs. (Jelmer Vernooij, #485) * The server now supports providing symrefs. (Jelmer Vernooij, #485) * Add ``dulwich.object_store.commit_tree_changes`` to incrementally commit changes to a tree structure. (Jelmer Vernooij) * Add basic ``PackBasedObjectStore.repack`` method. (Jelmer Vernooij, Earl Chew, #296, #549, #552) 0.18.2 2017-08-01 TEST FIXES * Use constant timestamp so tests pass in all timezones, not just BST. (Jelmer Vernooij) 0.18.1 2017-07-31 BUG FIXES * Fix syntax error in dulwich.contrib.test_swift_smoke. (Jelmer Vernooij) 0.18.0 2017-07-31 BUG FIXES * Fix remaining tests on Windows. (Jelmer Vernooij, #493) * Fix build of C extensions with Python 3 on Windows. (Jelmer Vernooij) * Pass 'mkdir' argument onto Repo.init_bare in Repo.clone. (Jelmer Vernooij, #504) * In ``dulwich.porcelain.add``, if no files are specified, add from current working directory rather than repository root. (Jelmer Vernooij, #521) * Properly deal with submodules in 'porcelain.status'. (Jelmer Vernooij, #517) * ``dulwich.porcelain.remove`` now actually removes files from disk, not just from the index. (Jelmer Vernooij, #488) * Fix handling of "reset" command with markers and without "from". (Antoine Pietri) * Fix handling of "merge" command with markers. (Antoine Pietri) * Support treeish argument to porcelain.reset(), rather than requiring a ref/commit id. (Jelmer Vernooij) * Handle race condition when mtime doesn't change between writes/reads. (Jelmer Vernooij, #541) * Fix ``dulwich.porcelain.show`` on commits with Python 3. (Jelmer Vernooij, #532) IMPROVEMENTS * Add basic support for reading ignore files in ``dulwich.ignore``. ``dulwich.porcelain.add`` and ``dulwich.porcelain.status`` now honor ignores. (Jelmer Vernooij, Segev Finer, #524, #526) * New ``dulwich.porcelain.check_ignore`` command. (Jelmer Vernooij) * ``dulwich.porcelain.status`` now supports a ``ignored`` argument. (Jelmer Vernooij) DOCUMENTATION * Clarified docstrings for Client.{send_pack,fetch_pack} implementations. (Jelmer Vernooij, #523) 0.17.3 2017-03-20 PLATFORM SUPPORT * List Python 3.3 as supported. (Jelmer Vernooij, #513) BUG FIXES * Fix compatibility with pypy 3. (Jelmer Vernooij) 0.17.2 2017-03-19 BUG FIXES * Add workaround for https://bitbucket.org/pypy/pypy/issues/2499/cpyext-pystring_asstring-doesnt-work, fixing Dulwich when used with C extensions on pypy < 5.6. (Victor Stinner) * Properly quote config values with a '#' character in them. (Jelmer Vernooij, #511) 0.17.1 2017-03-01 IMPROVEMENTS * Add basic 'dulwich pull' command. (Jelmer Vernooij) BUG FIXES * Cope with existing submodules during pull. (Jelmer Vernooij, #505) 0.17.0 2017-03-01 TEST FIXES * Skip test that requires sync to synchronize filesystems if os.sync is not available. (Koen Martens) IMPROVEMENTS * Implement MemoryRepo.{set_description,get_description}. (Jelmer Vernooij) * Raise exception in Repo.stage() when absolute paths are passed in. Allow passing in relative paths to porcelain.add().(Jelmer Vernooij) BUG FIXES * Handle multi-line quoted values in config files. (Jelmer Vernooij, #495) * Allow porcelain.clone of repository without HEAD. (Jelmer Vernooij, #501) * Support passing tag ids to Walker()'s include argument. (Jelmer Vernooij) * Don't strip trailing newlines from extra headers. (Nicolas Dandrimont) * Set bufsize=0 for subprocess interaction with SSH client. Fixes hangs on Python 3. (René Stern, #434) * Don't drop first slash for SSH paths, except for those starting with "~". (Jelmer Vernooij, René Stern, #463) * Properly log off after retrieving just refs. (Jelmer Vernooij) 0.16.3 2016-01-14 TEST FIXES * Remove racy check that relies on clock time changing between writes. (Jelmer Vernooij) IMPROVEMENTS * Add porcelain.remote_add. (Jelmer Vernooij) 0.16.2 2016-01-14 IMPROVEMENTS * Fixed failing test-cases on windows. (Koen Martens) API CHANGES * Repo is now a context manager, so that it can be easily closed using a ``with`` statement. (Søren Løvborg) TEST FIXES * Only run worktree list compat tests against git 2.7.0, when 'git worktree list' was introduced. (Jelmer Vernooij) BUG FIXES * Ignore filemode when building index when core.filemode is false. (Koen Martens) * Initialize core.filemode configuration setting by probing the filesystem for trustable permissions. (Koen Martens) * Fix ``porcelain.reset`` to respect the comittish argument. (Koen Martens) * Fix dulwich.porcelain.ls_remote() on Python 3. (#471, Jelmer Vernooij) * Allow both unicode and byte strings for host paths in dulwich.client. (#435, Jelmer Vernooij) * Add remote from porcelain.clone. (#466, Jelmer Vernooij) * Fix unquoting of credentials before passing to urllib2. (#475, Volodymyr Holovko) * Cope with submodules in `build_index_from_tree`. (#477, Jelmer Vernooij) * Handle deleted files in `get_unstaged_changes`. (#483, Doug Hellmann) * Don't overwrite files when they haven't changed in `build_file_from_blob`. (#479, Benoît HERVIER) * Check for existence of index file before opening pack. Fixes a race when new packs are being added. (#482, wme) 0.16.1 2016-12-25 BUG FIXES * Fix python3 compatibility for dulwich.contrib.release_robot. (Jelmer Vernooij) 0.16.0 2016-12-24 IMPROVEMENTS * Add support for worktrees. See `git-worktree(1)` and `gitrepository-layout(5)`. (Laurent Rineau) * Add support for `commondir` file in Git control directories. (Laurent Rineau) * Add support for passwords in HTTP URLs. (Jon Bain, Mika Mäenpää) * Add `release_robot` script to contrib, allowing easy finding of current version based on Git tags. (Mark Mikofski) * Add ``Blob.splitlines`` method. (Jelmer Vernooij) BUG FIXES * Fix handling of ``Commit.tree`` being set to an actual tree object rather than a tree id. (Jelmer Vernooij) * Return remote refs from LocalGitClient.fetch_pack(), consistent with the documentation for that method. (#461, Jelmer Vernooij) * Fix handling of unknown URL schemes in get_transport_and_path. (#465, Jelmer Vernooij) 0.15.0 2016-10-09 BUG FIXES * Allow missing trailing LF when reading service name from HTTP servers. (Jelmer Vernooij, Andrew Shadura, #442) * Fix dulwich.porcelain.pull() on Python3. (Jelmer Vernooij, #451) * Properly pull in tags during dulwich.porcelain.clone. (Jelmer Vernooij, #408) CHANGES * Changed license from "GNU General Public License, version 2.0 or later" to "Apache License, version 2.0 or later or GNU General Public License, version 2.0 or later". (#153) IMPROVEMENTS * Add ``dulwich.porcelain.ls_tree`` implementation. (Jelmer Vernooij) 0.14.1 2016-07-05 BUG FIXES * Fix regression removing untouched refs when pushing over SSH. (Jelmer Vernooij #441) * Skip Python3 tests for SWIFT contrib module, as it has not yet been ported. 0.14.0 2016-07-03 BUG FIXES * Fix ShaFile.id after modification of a copied ShaFile. (Félix Mattrat, Jelmer Vernooij) * Support removing refs from porcelain.push. (Jelmer Vernooij, #437) * Stop magic protocol ref `capabilities^{}` from leaking out to clients. (Jelmer Vernooij, #254) IMPROVEMENTS * Add `dulwich.config.parse_submodules` function. * Add `RefsContainer.follow` method. (#438) 0.13.0 2016-04-24 IMPROVEMENTS * Support `ssh://` URLs in get_transport_and_path_from_url(). (Jelmer Vernooij, #402) * Support missing empty line after headers in Git commits and tags. (Nicolas Dandrimont, #413) * Fix `dulwich.porcelain.status` when used in empty trees. (Jelmer Vernooij, #415) * Return copies of objects in MemoryObjectStore rather than references, making the behaviour more consistent with that of DiskObjectStore. (Félix Mattrat, Jelmer Vernooij) * Fix ``dulwich.web`` on Python3. (#295, Jonas Haag) CHANGES * Drop support for Python 2.6. * Fix python3 client web support. (Jelmer Vernooij) BUG FIXES * Fix hang on Gzip decompression. (Jonas Haag) * Don't rely on working tell() and seek() methods on wsgi.input. (Jonas Haag) * Support fastexport/fastimport functionality on python3 with newer versions of fastimport (>= 0.9.5). (Jelmer Vernooij, Félix Mattrat) 0.12.0 2015-12-13 IMPROVEMENTS * Add a `dulwich.archive` module that can create tarballs. Based on code from Jonas Haag in klaus. * Add a `dulwich.reflog` module for reading and writing reflogs. (Jelmer Vernooij) * Fix handling of ambiguous refs in `parse_ref` to make it match the behaviour described in https://git-scm.com/docs/gitrevisions. (Chris Bunney) * Support Python3 in C modules. (Lele Gaifax) BUG FIXES * Simplify handling of SSH command invocation. Fixes quoting of paths. Thanks, Thomas Liebetraut. (#384) * Fix inconsistent handling of trailing slashes for DictRefsContainer. (#383) * Add hack to support thin packs duing fetch(), albeit while requiring the entire pack file to be loaded into memory. (jsbain) CHANGES * This will be the last release to support Python 2.6. 0.11.2 2015-09-18 IMPROVEMENTS * Add support for agent= capability. (Jelmer Vernooij, #298) * Add support for quiet capability. (Jelmer Vernooij) CHANGES * The ParamikoSSHVendor class has been moved to * dulwich.contrib.paramiko_vendor, as it's currently untested. (Jelmer Vernooij, #364) 0.11.1 2015-09-13 Fix-up release to exclude broken blame.py file. 0.11.0 2015-09-13 IMPROVEMENTS * Extended Python3 support to most of the codebase. (Gary van der Merwe, Jelmer Vernooij) * The `Repo` object has a new `close` method that can be called to close any open resources. (Gary van der Merwe) * Support 'git.bat' in SubprocessGitClient on Windows. (Stefan Zimmermann) * Advertise 'ofs-delta' capability in receive-pack server side capabilities. (Jelmer Vernooij) * Switched `default_local_git_client_cls` to `LocalGitClient`. (Gary van der Merwe) * Add `porcelain.ls_remote` and `GitClient.get_refs`. (Michael Edgar) * Add `Repo.discover` method. (B. M. Corser) * Add `dulwich.objectspec.parse_refspec`. (Jelmer Vernooij) * Add `porcelain.pack_objects` and `porcelain.repack`. (Jelmer Vernooij) BUG FIXES * Fix handling of 'done' in graph walker and implement the 'no-done' capability. (Tommy Yu, #88) * Avoid recursion limit issues resolving deltas. (William Grant, #81) * Allow arguments in local client binary path overrides. (Jelmer Vernooij) * Fix handling of commands with arguments in paramiko SSH client. (Andreas Klöckner, Jelmer Vernooij, #363) * Fix parsing of quoted strings in configs. (Jelmer Vernooij, #305) 0.10.1 2015-03-25 BUG FIXES * Return `ApplyDeltaError` when encountering delta errors in both C extensions and native delta application code. (Jelmer Vernooij, #259) 0.10.0 2015-03-22 BUG FIXES * In dulwich.index.build_index_from_tree, by default refuse to create entries that start with .git/. * Fix running of testsuite when installed. (Jelmer Vernooij, #223) * Use a block cache in _find_content_rename_candidates(), improving performance. (Mike Williams) * Add support for ``core.protectNTFS`` setting. (Jelmer Vernooij) * Fix TypeError when fetching empty updates. (Hwee Miin Koh) * Resolve delta refs when pulling into a MemoryRepo. (Max Shawabkeh, #256) * Fix handling of tags of non-commits in missing object finder. (Augie Fackler, #211) * Explicitly disable mmap on plan9 where it doesn't work. (Jeff Sickel) IMPROVEMENTS * New public method `Repo.reset_index`. (Jelmer Vernooij) * Prevent duplicate parsing of loose files in objects directory when reading. Thanks to David Keijser for the report. (Jelmer Vernooij, #231) 0.9.9 2015-03-20 SECURITY BUG FIXES * Fix buffer overflow in C implementation of pack apply_delta(). (CVE-2015-0838) Thanks to Ivan Fratric of the Google Security Team for reporting this issue. (Jelmer Vernooij) 0.9.8 2014-11-30 BUG FIXES * Various fixes to improve test suite running on Windows. (Gary van der Merwe) * Limit delta copy length to 64K in v2 pack files. (Robert Brown) * Strip newline from final ACKed SHA while fetching packs. (Michael Edgar) * Remove assignment to PyList_SIZE() that was causing segfaults on pypy. (Jelmer Vernooij, #196) IMPROVEMENTS * Add porcelain 'receive-pack' and 'upload-pack'. (Jelmer Vernooij) * Handle SIGINT signals in bin/dulwich. (Jelmer Vernooij) * Add 'status' support to bin/dulwich. (Jelmer Vernooij) * Add 'branch_create', 'branch_list', 'branch_delete' porcelain. (Jelmer Vernooij) * Add 'fetch' porcelain. (Jelmer Vernooij) * Add 'tag_delete' porcelain. (Jelmer Vernooij) * Add support for serializing/deserializing 'gpgsig' attributes in Commit. (Jelmer Vernooij) CHANGES * dul-web is now available as 'dulwich web-daemon'. (Jelmer Vernooij) * dulwich.porcelain.tag has been renamed to tag_create. dulwich.porcelain.list_tags has been renamed to tag_list. (Jelmer Vernooij) API CHANGES * Restore support for Python 2.6. (Jelmer Vernooij, Gary van der Merwe) 0.9.7 2014-06-08 BUG FIXES * Fix tests dependent on hash ordering. (Michael Edgar) * Support staging symbolic links in Repo.stage. (Robert Brown) * Ensure that all files object are closed when running the test suite. (Gary van der Merwe) * When writing OFS_DELTA pack entries, write correct offset. (Augie Fackler) * Fix handler of larger copy operations in packs. (Augie Fackler) * Various fixes to improve test suite running on Windows. (Gary van der Merwe) * Fix logic for extra adds of identical files in rename detector. (Robert Brown) IMPROVEMENTS * Add porcelain 'status'. (Ryan Faulkner) * Add porcelain 'daemon'. (Jelmer Vernooij) * Add `dulwich.greenthreads` module which provides support for concurrency of some object store operations. (Fabien Boucher) * Various changes to improve compatibility with Python 3. (Gary van der Merwe, Hannu Valtonen, michael-k) * Add OpenStack Swift backed repository implementation in dulwich.contrib. See README.swift for details. (Fabien Boucher) API CHANGES * An optional close function can be passed to the Protocol class. This will be called by its close method. (Gary van der Merwe) * All classes with close methods are now context managers, so that they can be easily closed using a `with` statement. (Gary van der Merwe) * Remove deprecated `num_objects` argument to `write_pack` methods. (Jelmer Vernooij) OTHER CHANGES * The 'dul-daemon' script has been removed. The same functionality is now available as 'dulwich daemon'. (Jelmer Vernooij) 0.9.6 2014-04-23 IMPROVEMENTS * Add support for recursive add in 'git add'. (Ryan Faulkner, Jelmer Vernooij) * Add porcelain 'list_tags'. (Ryan Faulkner) * Add porcelain 'push'. (Ryan Faulkner) * Add porcelain 'pull'. (Ryan Faulkner) * Support 'http.proxy' in HttpGitClient. (Jelmer Vernooij, #1096030) * Support 'http.useragent' in HttpGitClient. (Jelmer Vernooij) * In server, wait for clients to send empty list of wants when talking to empty repository. (Damien Tournoud) * Various changes to improve compatibility with Python 3. (Gary van der Merwe) BUG FIXES * Support unseekable 'wsgi.input' streams. (Jonas Haag) * Raise TypeError when passing unicode() object to Repo.__getitem__. (Jonas Haag) * Fix handling of `reset` command in dulwich.fastexport. (Jelmer Vernooij, #1249029) * In client, don't wait for server to close connection first. Fixes hang when used against GitHub server implementation. (Siddharth Agarwal) * DeltaChainIterator: fix a corner case where an object is inflated as an object already in the repository. (Damien Tournoud, #135) * Stop leaking file handles during pack reload. (Damien Tournoud) * Avoid reopening packs during pack cache reload. (Jelmer Vernooij) API CHANGES * Drop support for Python 2.6. (Jelmer Vernooij) 0.9.5 2014-02-23 IMPROVEMENTS * Add porcelain 'tag'. (Ryan Faulkner) * New module `dulwich.objectspec` for parsing strings referencing objects and commit ranges. (Jelmer Vernooij) * Add shallow branch support. (milki) * Allow passing urllib2 `opener` into HttpGitClient. (Dov Feldstern, #909037) CHANGES * Drop support for Python 2.4 and 2.5. (Jelmer Vernooij) API CHANGES * Remove long deprecated ``Repo.commit``, ``Repo.get_blob``, ``Repo.tree`` and ``Repo.tag``. (Jelmer Vernooij) * Remove long deprecated ``Repo.revision_history`` and ``Repo.ref``. (Jelmer Vernooij) * Remove long deprecated ``Tree.entries``. (Jelmer Vernooij) BUG FIXES * Raise KeyError rather than TypeError when passing in unicode object of length 20 or 40 to Repo.__getitem__. (Jelmer Vernooij) * Use 'rm' rather than 'unlink' in tests, since the latter does not exist on OpenBSD and other platforms. (Dmitrij D. Czarkoff) 0.9.4 2013-11-30 IMPROVEMENTS * Add ssh_kwargs attribute to ParamikoSSHVendor. (milki) * Add Repo.set_description(). (Víðir Valberg Guðmundsson) * Add a basic `dulwich.porcelain` module. (Jelmer Vernooij, Marcin Kuzminski) * Various performance improvements for object access. (Jelmer Vernooij) * New function `get_transport_and_path_from_url`, similar to `get_transport_and_path` but only supports URLs. (Jelmer Vernooij) * Add support for file:// URLs in `get_transport_and_path_from_url`. (Jelmer Vernooij) * Add LocalGitClient implementation. (Jelmer Vernooij) BUG FIXES * Support filesystems with 64bit inode and device numbers. (André Roth) CHANGES * Ref handling has been moved to dulwich.refs. (Jelmer Vernooij) API CHANGES * Remove long deprecated RefsContainer.set_ref(). (Jelmer Vernooij) * Repo.ref() is now deprecated in favour of Repo.refs[]. (Jelmer Vernooij) FEATURES * Add support for graftpoints. (milki) 0.9.3 2013-09-27 BUG FIXES * Fix path for stdint.h in MANIFEST.in. (Jelmer Vernooij) 0.9.2 2013-09-26 BUG FIXES * Include stdint.h in MANIFEST.in (Mark Mikofski) 0.9.1 2013-09-22 BUG FIXES * Support lookups of 40-character refs in BaseRepo.__getitem__. (Chow Loong Jin, Jelmer Vernooij) * Fix fetching packs with side-band-64k capability disabled. (David Keijser, Jelmer Vernooij) * Several fixes in send-pack protocol behaviour - handling of empty pack files and deletes. (milki, #1063087) * Fix capability negotiation when fetching packs over HTTP. (#1072461, William Grant) * Enforce determine_wants returning an empty list rather than None. (Fabien Boucher, Jelmer Vernooij) * In the server, support pushes just removing refs. (Fabien Boucher, Jelmer Vernooij) IMPROVEMENTS * Support passing a single revision to BaseRepo.get_walker() rather than a list of revisions. (Alberto Ruiz) * Add `Repo.get_description` method. (Jelmer Vernooij) * Support thin packs in Pack.iterobjects() and Pack.get_raw(). (William Grant) * Add `MemoryObjectStore.add_pack` and `MemoryObjectStore.add_thin_pack` methods. (David Bennett) * Add paramiko-based SSH vendor. (Aaron O'Mullan) * Support running 'dulwich.server' and 'dulwich.web' using 'python -m'. (Jelmer Vernooij) * Add ObjectStore.close(). (Jelmer Vernooij) * Raise appropriate NotImplementedError when encountering dumb HTTP servers. (Jelmer Vernooij) API CHANGES * SSHVendor.connect_ssh has been renamed to SSHVendor.run_command. (Jelmer Vernooij) * ObjectStore.add_pack() now returns a 3-tuple. The last element will be an abort() method that can be used to cancel the pack operation. (Jelmer Vernooij) 0.9.0 2013-05-31 BUG FIXES * Push efficiency - report missing objects only. (#562676, Artem Tikhomirov) * Use indentation consistent with C Git in config files. (#1031356, Curt Moore, Jelmer Vernooij) * Recognize and skip binary files in diff function. (Takeshi Kanemoto) * Fix handling of relative paths in dulwich.client.get_transport_and_path. (Brian Visel, #1169368) * Preserve ordering of entries in configuration. (Benjamin Pollack) * Support ~ expansion in SSH client paths. (milki, #1083439) * Support relative paths in alternate paths. (milki, Michel Lespinasse, #1175007) * Log all error messages from wsgiref server to the logging module. This makes the test suit quiet again. (Gary van der Merwe) * Support passing None for empty tree in changes_from_tree. (Kevin Watters) * Support fetching empty repository in client. (milki, #1060462) IMPROVEMENTS: * Add optional honor_filemode flag to build_index_from_tree. (Mark Mikofski) * Support core/filemode setting when building trees. (Jelmer Vernooij) * Add chapter on tags in tutorial. (Ryan Faulkner) FEATURES * Add support for mergetags. (milki, #963525) * Add support for posix shell hooks. (milki) 0.8.7 2012-11-27 BUG FIXES * Fix use of alternates in ``DiskObjectStore``.{__contains__,__iter__}. (Dmitriy) * Fix compatibility with Python 2.4. (David Carr) 0.8.6 2012-11-09 API CHANGES * dulwich.__init__ no longer imports client, protocol, repo and server modules. (Jelmer Vernooij) FEATURES * ConfigDict now behaves more like a dictionary. (Adam 'Cezar' Jenkins, issue #58) * HTTPGitApplication now takes an optional `fallback_app` argument. (Jonas Haag, issue #67) * Support for large pack index files. (Jameson Nash) TESTING * Make index entry tests a little bit less strict, to cope with slightly different behaviour on various platforms. (Jelmer Vernooij) * ``setup.py test`` (available when setuptools is installed) now runs all tests, not just the basic unit tests. (Jelmer Vernooij) BUG FIXES * Commit._deserialize now actually deserializes the current state rather than the previous one. (Yifan Zhang, issue #59) * Handle None elements in lists of TreeChange objects. (Alex Holmes) * Support cloning repositories without HEAD set. (D-Key, Jelmer Vernooij, issue #69) * Support ``MemoryRepo.get_config``. (Jelmer Vernooij) * In ``get_transport_and_path``, pass extra keyword arguments on to HttpGitClient. (Jelmer Vernooij) 0.8.5 2012-03-29 BUG FIXES * Avoid use of 'with' in dulwich.index. (Jelmer Vernooij) * Be a little bit strict about OS behaviour in index tests. Should fix the tests on Debian GNU/kFreeBSD. (Jelmer Vernooij) 0.8.4 2012-03-28 BUG FIXES * Options on the same line as sections in config files are now supported. (Jelmer Vernooij, #920553) * Only negotiate capabilities that are also supported by the server. (Rod Cloutier, Risto Kankkunen) * Fix parsing of invalid timezone offsets with two minus signs. (Jason R. Coombs, #697828) * Reset environment variables during tests, to avoid test isolation leaks reading ~/.gitconfig. (Risto Kankkunen) TESTS * $HOME is now explicitly specified for tests that use it to read ``~/.gitconfig``, to prevent test isolation issues. (Jelmer Vernooij, #920330) FEATURES * Additional arguments to get_transport_and_path are now passed on to the constructor of the transport. (Sam Vilain) * The WSGI server now transparently handles when a git client submits data using Content-Encoding: gzip. (David Blewett, Jelmer Vernooij) * Add dulwich.index.build_index_from_tree(). (milki) 0.8.3 2012-01-21 FEATURES * The config parser now supports the git-config file format as described in git-config(1) and can write git config files. (Jelmer Vernooij, #531092, #768687) * ``Repo.do_commit`` will now use the user identity from .git/config or ~/.gitconfig if none was explicitly specified. (Jelmer Vernooij) BUG FIXES * Allow ``determine_wants`` methods to include the zero sha in their return value. (Jelmer Vernooij) 0.8.2 2011-12-18 BUG FIXES * Cope with different zlib buffer sizes in sha1 file parser. (Jelmer Vernooij) * Fix get_transport_and_path for HTTP/HTTPS URLs. (Bruno Renié) * Avoid calling free_objects() on NULL in error cases. (Chris Eberle) * Fix use --bare argument to 'dulwich init'. (Chris Eberle) * Properly abort connections when the determine_wants function raises an exception. (Jelmer Vernooij, #856769) * Tweak xcodebuild hack to deal with more error output. (Jelmer Vernooij, #903840) FEATURES * Add support for retrieving tarballs from remote servers. (Jelmer Vernooij, #379087) * New method ``update_server_info`` which generates data for dumb server access. (Jelmer Vernooij, #731235) 0.8.1 2011-10-31 FEATURES * Repo.do_commit has a new argument 'ref'. * Repo.do_commit has a new argument 'merge_heads'. (Jelmer Vernooij) * New ``Repo.get_walker`` method. (Jelmer Vernooij) * New ``Repo.clone`` method. (Jelmer Vernooij, #725369) * ``GitClient.send_pack`` now supports the 'side-band-64k' capability. (Jelmer Vernooij) * ``HttpGitClient`` which supports the smart server protocol over HTTP. "dumb" access is not yet supported. (Jelmer Vernooij, #373688) * Add basic support for alternates. (Jelmer Vernooij, #810429) CHANGES * unittest2 or python >= 2.7 is now required for the testsuite. testtools is no longer supported. (Jelmer Vernooij, #830713) BUG FIXES * Fix compilation with older versions of MSVC. (Martin gz) * Special case 'refs/stash' as a valid ref. (Jelmer Vernooij, #695577) * Smart protocol clients can now change refs even if they are not uploading new data. (Jelmer Vernooij, #855993) * Don't compile C extensions when running in pypy. (Ronny Pfannschmidt, #881546) * Use different name for strnlen replacement function to avoid clashing with system strnlen. (Jelmer Vernooij, #880362) API CHANGES * ``Repo.revision_history`` is now deprecated in favor of ``Repo.get_walker``. (Jelmer Vernooij) 0.8.0 2011-08-07 FEATURES * New DeltaChainIterator abstract class for quickly iterating all objects in a pack, with implementations for pack indexing and inflation. (Dave Borowitz) * New walk module with a Walker class for customizable commit walking. (Dave Borowitz) * New tree_changes_for_merge function in diff_tree. (Dave Borowitz) * Easy rename detection in RenameDetector even without find_copies_harder. (Dave Borowitz) BUG FIXES * Avoid storing all objects in memory when writing pack. (Jelmer Vernooij, #813268) * Support IPv6 for git:// connections. (Jelmer Vernooij, #801543) * Improve performance of Repo.revision_history(). (Timo Schmid, #535118) * Fix use of SubprocessWrapper on Windows. (Paulo Madeira, #670035) * Fix compilation on newer versions of Mac OS X (Lion and up). (Ryan McKern, #794543) * Prevent raising ValueError for correct refs in RefContainer.__delitem__. * Correctly return a tuple from MemoryObjectStore.get_raw. (Dave Borowitz) * Fix a bug in reading the pack checksum when there are fewer than 20 bytes left in the buffer. (Dave Borowitz) * Support ~ in git:// URL paths. (Jelmer Vernooij, #813555) * Make ShaFile.__eq__ work when other is not a ShaFile. (Dave Borowitz) * ObjectStore.get_graph_walker() now no longer yields the same revision more than once. This has a significant improvement for performance when wide revision graphs are involved. (Jelmer Vernooij, #818168) * Teach ReceivePackHandler how to read empty packs. (Dave Borowitz) * Don't send a pack with duplicates of the same object. (Dave Borowitz) * Teach the server how to serve a clone of an empty repo. (Dave Borowitz) * Correctly advertise capabilities during receive-pack. (Dave Borowitz) * Fix add/add and add/rename conflicts in tree_changes_for_merge. (Dave Borowitz) * Use correct MIME types in web server. (Dave Borowitz) API CHANGES * write_pack no longer takes the num_objects argument and requires an object to be passed in that is iterable (rather than an iterator) and that provides __len__. (Jelmer Vernooij) * write_pack_data has been renamed to write_pack_objects and no longer takes a num_objects argument. (Jelmer Vernooij) * take_msb_bytes, read_zlib_chunks, unpack_objects, and PackStreamReader.read_objects now take an additional argument indicating a crc32 to compute. (Dave Borowitz) * PackObjectIterator was removed; its functionality is still exposed by PackData.iterobjects. (Dave Borowitz) * Add a sha arg to write_pack_object to incrementally compute a SHA. (Dave Borowitz) * Include offset in PackStreamReader results. (Dave Borowitz) * Move PackStreamReader from server to pack. (Dave Borowitz) * Extract a check_length_and_checksum, compute_file_sha, and pack_object_header pack helper functions. (Dave Borowitz) * Extract a compute_file_sha function. (Dave Borowitz) * Remove move_in_thin_pack as a separate method; add_thin_pack now completes the thin pack and moves it in in one step. Remove ThinPackData as well. (Dave Borowitz) * Custom buffer size in read_zlib_chunks. (Dave Borowitz) * New UnpackedObject data class that replaces ad-hoc tuples in the return value of unpack_object and various DeltaChainIterator methods. (Dave Borowitz) * Add a lookup_path convenience method to Tree. (Dave Borowitz) * Optionally create RenameDetectors without passing in tree SHAs. (Dave Borowitz) * Optionally include unchanged entries in RenameDetectors. (Dave Borowitz) * Optionally pass a RenameDetector to tree_changes. (Dave Borowitz) * Optionally pass a request object through to server handlers. (Dave Borowitz) TEST CHANGES * If setuptools is installed, "python setup.py test" will now run the testsuite. (Jelmer Vernooij) * Add a new build_pack test utility for building packs from a simple spec. (Dave Borowitz) * Add a new build_commit_graph test utility for building commits from a simple spec. (Dave Borowitz) 0.7.1 2011-04-12 BUG FIXES * Fix double decref in _diff_tree.c. (Ted Horst, #715528) * Fix the build on Windows. (Pascal Quantin) * Fix get_transport_and_path compatibility with pre-2.6.5 versions of Python. (Max Bowsher, #707438) * BaseObjectStore.determine_wants_all no longer breaks on zero SHAs. (Jelmer Vernooij) * write_tree_diff() now supports submodules. (Jelmer Vernooij) * Fix compilation for XCode 4 and older versions of distutils.sysconfig. (Daniele Sluijters) IMPROVEMENTS * Sphinxified documentation. (Lukasz Balcerzak) * Add Pack.keep.(Marc Brinkmann) API CHANGES * The order of the parameters to Tree.add(name, mode, sha) has changed, and is now consistent with the rest of Dulwich. Existing code will still work but print a DeprecationWarning. (Jelmer Vernooij, #663550) * Tree.entries() is now deprecated in favour of Tree.items() and Tree.iteritems(). (Jelmer Vernooij) 0.7.0 2011-01-21 FEATURES * New `dulwich.diff_tree` module for simple content-based rename detection. (Dave Borowitz) * Add Tree.items(). (Jelmer Vernooij) * Add eof() and unread_pkt_line() methods to Protocol. (Dave Borowitz) * Add write_tree_diff(). (Jelmer Vernooij) * Add `serve_command` function for git server commands as executables. (Jelmer Vernooij) * dulwich.client.get_transport_and_path now supports rsync-style repository URLs. (Dave Borowitz, #568493) BUG FIXES * Correct short-circuiting operation for no-op fetches in the server. (Dave Borowitz) * Support parsing git mbox patches without a version tail, as generated by Mercurial. (Jelmer Vernooij) * Fix dul-receive-pack and dul-upload-pack. (Jelmer Vernooij) * Zero-padded file modes in Tree objects no longer trigger an exception but the check code warns about them. (Augie Fackler, #581064) * Repo.init() now honors the mkdir flag. (#671159) * The ref format is now checked when setting a ref rather than when reading it back. (Dave Borowitz, #653527) * Make sure pack files are closed correctly. (Tay Ray Chuan) DOCUMENTATION * Run the tutorial inside the test suite. (Jelmer Vernooij) * Reorganized and updated the tutorial. (Jelmer Vernooij, Dave Borowitz, #610550, #610540) 0.6.2 2010-10-16 BUG FIXES * HTTP server correctly handles empty CONTENT_LENGTH. (Dave Borowitz) * Don't error when creating GitFiles with the default mode. (Dave Borowitz) * ThinPackData.from_file now works with resolve_ext_ref callback. (Dave Borowitz) * Provide strnlen() on mingw32 which doesn't have it. (Hans Kolek) * Set bare=true in the configuratin for bare repositories. (Dirk Neumann) FEATURES * Use slots for core objects to save up on memory. (Jelmer Vernooij) * Web server supports streaming progress/pack output. (Dave Borowitz) * New public function dulwich.pack.write_pack_header. (Dave Borowitz) * Distinguish between missing files and read errors in HTTP server. (Dave Borowitz) * Initial work on support for fastimport using python-fastimport. (Jelmer Vernooij) * New dulwich.pack.MemoryPackIndex class. (Jelmer Vernooij) * Delegate SHA peeling to the object store. (Dave Borowitz) TESTS * Use GitFile when modifying packed-refs in tests. (Dave Borowitz) * New tests in test_web with better coverage and fewer ad-hoc mocks. (Dave Borowitz) * Standardize quote delimiters in test_protocol. (Dave Borowitz) * Fix use when testtools is installed. (Jelmer Vernooij) * Add trivial test for write_pack_header. (Jelmer Vernooij) * Refactor some of dulwich.tests.compat.server_utils. (Dave Borowitz) * Allow overwriting id property of objects in test utils. (Dave Borowitz) * Use real in-memory objects rather than stubs for server tests. (Dave Borowitz) * Clean up MissingObjectFinder. (Dave Borowitz) API CHANGES * ObjectStore.iter_tree_contents now walks contents in depth-first, sorted order. (Dave Borowitz) * ObjectStore.iter_tree_contents can optionally yield tree objects as well. (Dave Borowitz). * Add side-band-64k support to ReceivePackHandler. (Dave Borowitz) * Change server capabilities methods to classmethods. (Dave Borowitz) * Tweak server handler injection. (Dave Borowitz) * PackIndex1 and PackIndex2 now subclass FilePackIndex, which is itself a subclass of PackIndex. (Jelmer Vernooij) DOCUMENTATION * Add docstrings for various functions in dulwich.objects. (Jelmer Vernooij) * Clean up docstrings in dulwich.protocol. (Dave Borowitz) * Explicitly specify allowed protocol commands to ProtocolGraphWalker.read_proto_line. (Dave Borowitz) * Add utility functions to DictRefsContainer. (Dave Borowitz) 0.6.1 2010-07-22 BUG FIXES * Fix memory leak in C implementation of sorted_tree_items. (Dave Borowitz) * Use correct path separators for named repo files. (Dave Borowitz) * python > 2.7 and testtools-based test runners will now also pick up skipped tests correctly. (Jelmer Vernooij) FEATURES * Move named file initilization to BaseRepo. (Dave Borowitz) * Add logging utilities and git/HTTP server logging. (Dave Borowitz) * The GitClient interface has been cleaned up and instances are now reusable. (Augie Fackler) * Allow overriding paths to executables in GitSSHClient. (Ross Light, Jelmer Vernooij, #585204) * Add PackBasedObjectStore.pack_loose_objects(). (Jelmer Vernooij) TESTS * Add tests for sorted_tree_items and C implementation. (Dave Borowitz) * Add a MemoryRepo that stores everything in memory. (Dave Borowitz) * Quiet logging output from web tests. (Dave Borowitz) * More flexible version checking for compat tests. (Dave Borowitz) * Compat tests for servers with and without side-band-64k. (Dave Borowitz) CLEANUP * Clean up file headers. (Dave Borowitz) TESTS * Use GitFile when modifying packed-refs in tests. (Dave Borowitz) API CHANGES * dulwich.pack.write_pack_index_v{1,2} now take a file-like object rather than a filename. (Jelmer Vernooij) * Make dul-daemon/dul-web trivial wrappers around server functionality. (Dave Borowitz) * Move reference WSGI handler to web.py. (Dave Borowitz) * Factor out _report_status in ReceivePackHandler. (Dave Borowitz) * Factor out a function to convert a line to a pkt-line. (Dave Borowitz) 0.6.0 2010-05-22 note: This list is most likely incomplete for 0.6.0. BUG FIXES * Fix ReceivePackHandler to disallow removing refs without delete-refs. (Dave Borowitz) * Deal with capabilities required by the client, even if they can not be disabled in the server. (Dave Borowitz) * Fix trailing newlines in generated patch files. (Jelmer Vernooij) * Implement RefsContainer.__contains__. (Jelmer Vernooij) * Cope with \r in ref files on Windows. ( http://github.com/jelmer/dulwich/issues/#issue/13, Jelmer Vernooij) * Fix GitFile breakage on Windows. (Anatoly Techtonik, #557585) * Support packed ref deletion with no peeled refs. (Augie Fackler) * Fix send pack when there is nothing to fetch. (Augie Fackler) * Fix fetch if no progress function is specified. (Augie Fackler) * Allow double-staging of files that are deleted in the index. (Dave Borowitz) * Fix RefsContainer.add_if_new to support dangling symrefs. (Dave Borowitz) * Non-existant index files in non-bare repositories are now treated as empty. (Dave Borowitz) * Always update ShaFile.id when the contents of the object get changed. (Jelmer Vernooij) * Various Python2.4-compatibility fixes. (Dave Borowitz) * Fix thin pack handling. (Dave Borowitz) FEATURES * Add include-tag capability to server. (Dave Borowitz) * New dulwich.fastexport module that can generate fastexport streams. (Jelmer Vernooij) * Implemented BaseRepo.__contains__. (Jelmer Vernooij) * Add __setitem__ to DictRefsContainer. (Dave Borowitz) * Overall improvements checking Git objects. (Dave Borowitz) * Packs are now verified while they are received. (Dave Borowitz) TESTS * Add framework for testing compatibility with C Git. (Dave Borowitz) * Add various tests for the use of non-bare repositories. (Dave Borowitz) * Cope with diffstat not being available on all platforms. (Tay Ray Chuan, Jelmer Vernooij) * Add make_object and make_commit convenience functions to test utils. (Dave Borowitz) API BREAKAGES * The 'committer' and 'message' arguments to Repo.do_commit() have been swapped. 'committer' is now optional. (Jelmer Vernooij) * Repo.get_blob, Repo.commit, Repo.tag and Repo.tree are now deprecated. (Jelmer Vernooij) * RefsContainer.set_ref() was renamed to RefsContainer.set_symbolic_ref(), for clarity. (Jelmer Vernooij) API CHANGES * The primary serialization APIs in dulwich.objects now work with chunks of strings rather than with full-text strings. (Jelmer Vernooij) 0.5.02010-03-03 BUG FIXES * Support custom fields in commits (readonly). (Jelmer Vernooij) * Improved ref handling. (Dave Borowitz) * Rework server protocol to be smarter and interoperate with cgit client. (Dave Borowitz) * Add a GitFile class that uses the same locking protocol for writes as cgit. (Dave Borowitz) * Cope with forward slashes correctly in the index on Windows. (Jelmer Vernooij, #526793) FEATURES * --pure option to setup.py to allow building/installing without the C extensions. (Hal Wine, Anatoly Techtonik, Jelmer Vernooij, #434326) * Implement Repo.get_config(). (Jelmer Vernooij, Augie Fackler) * HTTP dumb and smart server. (Dave Borowitz) * Add abstract baseclass for Repo that does not require file system operations. (Dave Borowitz) 0.4.1 2010-01-03 FEATURES * Add ObjectStore.iter_tree_contents(). (Jelmer Vernooij) * Add Index.changes_from_tree(). (Jelmer Vernooij) * Add ObjectStore.tree_changes(). (Jelmer Vernooij) * Add functionality for writing patches in dulwich.patch. (Jelmer Vernooij) 0.4.0 2009-10-07 DOCUMENTATION * Added tutorial. API CHANGES * dulwich.object_store.tree_lookup_path will now return the mode and sha of the object found rather than the object itself. BUG FIXES * Use binascii.hexlify / binascii.unhexlify for better performance. * Cope with extra unknown data in index files by ignoring it (for now). * Add proper error message when server unexpectedly hangs up. (#415843) * Correctly write opcode for equal in create_delta. 0.3.3 2009-07-23 FEATURES * Implement ShaFile.__hash__(). * Implement Tree.__len__() BUG FIXES * Check for 'objects' and 'refs' directories when looking for a Git repository. (#380818) 0.3.2 2009-05-20 BUG FIXES * Support the encoding field in Commits. * Some Windows compatibility fixes. * Fixed several issues in commit support. FEATURES * Basic support for handling submodules. 0.3.1 2009-05-13 FEATURES * Implemented Repo.__getitem__, Repo.__setitem__ and Repo.__delitem__ to access content. API CHANGES * Removed Repo.set_ref, Repo.remove_ref, Repo.tags, Repo.get_refs and Repo.heads in favor of Repo.refs, a dictionary-like object for accessing refs. BUG FIXES * Removed import of 'sha' module in objects.py, which was causing deprecation warnings on Python 2.6. 0.3.0 2009-05-10 FEATURES * A new function 'commit_tree' has been added that can commit a tree based on an index. BUG FIXES * The memory usage when generating indexes has been significantly reduced. * A memory leak in the C implementation of parse_tree has been fixed. * The send-pack smart server command now works. (Thanks Scott Chacon) * The handling of short timestamps (less than 10 digits) has been fixed. * The handling of timezones has been fixed. 0.2.1 2009-04-30 BUG FIXES * Fix compatibility with Python2.4. 0.2.0 2009-04-30 FEATURES * Support for activity reporting in smart protocol client. * Optional C extensions for better performance in a couple of places that are performance-critical. 0.1.1 2009-03-13 BUG FIXES * Fixed regression in Repo.find_missing_objects() * Don't fetch ^{} objects from remote hosts, as requesting them causes a hangup. * Always write pack to disk completely before calculating checksum. FEATURES * Allow disabling thin packs when talking to remote hosts. 0.1.0 2009-01-24 * Initial release. diff --git a/README.rst b/README.rst index fb64ed58..46172632 100644 --- a/README.rst +++ b/README.rst @@ -1,97 +1,97 @@ .. image:: https://travis-ci.org/dulwich/dulwich.png?branch=master :alt: Build Status :target: https://travis-ci.org/dulwich/dulwich .. image:: https://ci.appveyor.com/api/projects/status/mob7g4vnrfvvoweb?svg=true :alt: Windows Build Status :target: https://ci.appveyor.com/project/jelmer/dulwich/branch/master This is the Dulwich project. It aims to provide an interface to git repos (both local and remote) that doesn't call out to git directly but instead uses pure Python. **Main website**: **License**: Apache License, version 2 or GNU General Public License, version 2 or later. The project is named after the part of London that Mr. and Mrs. Git live in in the particular Monty Python sketch. Installation ------------ By default, Dulwich' setup.py will attempt to build and install the optional C extensions. The reason for this is that they significantly improve the performance since some low-level operations that are executed often are much slower in CPython. If you don't want to install the C bindings, specify the --pure argument to setup.py:: $ python setup.py --pure install or if you are installing from pip:: $ pip install dulwich --global-option="--pure" Note that you can also specify --global-option in a `requirements.txt `_ file, e.g. like this:: dulwich --global-option=--pure Getting started --------------- Dulwich comes with both a lower-level API and higher-level plumbing ("porcelain"). For example, to use the lower level API to access the commit message of the last commit:: >>> from dulwich.repo import Repo >>> r = Repo('.') >>> r.head() '57fbe010446356833a6ad1600059d80b1e731e15' >>> c = r[r.head()] >>> c >>> c.message 'Add note about encoding.\n' And to print it using porcelain:: >>> from dulwich import porcelain >>> porcelain.log('.', max_entries=1) -------------------------------------------------- commit: 57fbe010446356833a6ad1600059d80b1e731e15 Author: Jelmer Vernooij Date: Sat Apr 29 2017 23:57:34 +0000 Add note about encoding. Further documentation --------------------- The dulwich documentation can be found in docs/ and built by running ``make doc``. It can also be found `on the web `_. Help ---- There is a *#dulwich* IRC channel on the `Freenode `_, and `dulwich-announce `_ and `dulwich-discuss `_ mailing lists. Contributing ------------ For a full list of contributors, see the git logs or `AUTHORS `_. If you'd like to contribute to Dulwich, see the `CONTRIBUTING `_ file and `list of open issues `_. Supported versions of Python ---------------------------- -At the moment, Dulwich supports (and is tested on) CPython 2.7, 3.4, 3.5, 3.6, -3.7 and PyPy. +At the moment, Dulwich supports (and is tested on) CPython 3.5, 3.6, +3.7, 3.8 and Pypy. diff --git a/dulwich/__init__.py b/dulwich/__init__.py index 36caf9b4..8558ea92 100644 --- a/dulwich/__init__.py +++ b/dulwich/__init__.py @@ -1,25 +1,25 @@ # __init__.py -- The git module of dulwich # Copyright (C) 2007 James Westby # Copyright (C) 2008 Jelmer Vernooij # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """Python implementation of the Git file formats and protocols.""" -__version__ = (0, 19, 17) +__version__ = (0, 20, 0) diff --git a/dulwich/client.py b/dulwich/client.py index e4be8b08..0a0a9811 100644 --- a/dulwich/client.py +++ b/dulwich/client.py @@ -1,1901 +1,1898 @@ # client.py -- Implementation of the client side git protocols # Copyright (C) 2008-2013 Jelmer Vernooij # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """Client side support for the Git protocol. The Dulwich client supports the following capabilities: * thin-pack * multi_ack_detailed * multi_ack * side-band-64k * ofs-delta * quiet * report-status * delete-refs * shallow Known capabilities that are not supported: * no-progress * include-tag """ from contextlib import closing from io import BytesIO, BufferedReader import errno import os import select import socket import subprocess import sys try: from urllib import quote as urlquote from urllib import unquote as urlunquote except ImportError: from urllib.parse import quote as urlquote from urllib.parse import unquote as urlunquote try: import urlparse except ImportError: import urllib.parse as urlparse import dulwich from dulwich.config import get_xdg_config_home_path from dulwich.errors import ( GitProtocolError, NotGitRepository, SendPackError, UpdateRefsError, ) from dulwich.protocol import ( HangupException, _RBUFSIZE, agent_string, capability_agent, extract_capability_names, CAPABILITY_AGENT, CAPABILITY_DELETE_REFS, CAPABILITY_INCLUDE_TAG, CAPABILITY_MULTI_ACK, CAPABILITY_MULTI_ACK_DETAILED, CAPABILITY_OFS_DELTA, CAPABILITY_QUIET, CAPABILITY_REPORT_STATUS, CAPABILITY_SHALLOW, CAPABILITY_SYMREF, CAPABILITY_SIDE_BAND_64K, CAPABILITY_THIN_PACK, CAPABILITIES_REF, KNOWN_RECEIVE_CAPABILITIES, KNOWN_UPLOAD_CAPABILITIES, COMMAND_DEEPEN, COMMAND_SHALLOW, COMMAND_UNSHALLOW, COMMAND_DONE, COMMAND_HAVE, COMMAND_WANT, SIDE_BAND_CHANNEL_DATA, SIDE_BAND_CHANNEL_PROGRESS, SIDE_BAND_CHANNEL_FATAL, PktLineParser, Protocol, ProtocolFile, TCP_GIT_PORT, ZERO_SHA, extract_capabilities, parse_capability, ) from dulwich.pack import ( write_pack_data, write_pack_objects, ) from dulwich.refs import ( read_info_refs, ANNOTATED_TAG_SUFFIX, ) class InvalidWants(Exception): """Invalid wants.""" def __init__(self, wants): Exception.__init__( self, "requested wants not in server provided refs: %r" % wants) def _fileno_can_read(fileno): """Check if a file descriptor is readable. """ return len(select.select([fileno], [], [], 0)[0]) > 0 def _win32_peek_avail(handle): """Wrapper around PeekNamedPipe to check how many bytes are available. """ from ctypes import byref, wintypes, windll c_avail = wintypes.DWORD() c_message = wintypes.DWORD() success = windll.kernel32.PeekNamedPipe( handle, None, 0, None, byref(c_avail), byref(c_message)) if not success: raise OSError(wintypes.GetLastError()) return c_avail.value COMMON_CAPABILITIES = [CAPABILITY_OFS_DELTA, CAPABILITY_SIDE_BAND_64K] UPLOAD_CAPABILITIES = ([CAPABILITY_THIN_PACK, CAPABILITY_MULTI_ACK, CAPABILITY_MULTI_ACK_DETAILED, CAPABILITY_SHALLOW] + COMMON_CAPABILITIES) RECEIVE_CAPABILITIES = ( [CAPABILITY_REPORT_STATUS, CAPABILITY_DELETE_REFS] + 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. Raises: SendPackError: Raised when the server could not unpack UpdateRefsError: Raised when refs could not be updated """ if self._pack_status not in (b'unpack ok', None): raise SendPackError(self._pack_status) if not self._ref_status_ok: ref_status = {} ok = set() for status in self._ref_statuses: if b' ' not in status: # malformed response, move on to the next one continue status, ref = status.split(b' ', 1) if status == b'ng': if b' ' in ref: ref, status = ref.split(b' ', 1) else: ok.add(ref) ref_status[ref] = status # TODO(jelmer): don't assume encoding of refs is ascii. raise UpdateRefsError(', '.join([ refname.decode('ascii') for refname in ref_status if refname not in ok]) + ' failed to update', ref_status=ref_status) def handle_packet(self, pkt): """Handle a packet. Raises: 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.decode('utf-8', 'replace')) if server_capabilities is None: (ref, server_capabilities) = extract_capabilities(ref) refs[ref] = sha if len(refs) == 0: return {}, set([]) if refs == {CAPABILITIES_REF: ZERO_SHA}: refs = {} return refs, set(server_capabilities) class FetchPackResult(object): """Result of a fetch-pack operation. Attributes: refs: Dictionary with all remote refs symrefs: Dictionary with remote symrefs agent: User agent string """ _FORWARDED_ATTRS = [ 'clear', 'copy', 'fromkeys', 'get', 'has_key', 'items', 'iteritems', 'iterkeys', 'itervalues', 'keys', 'pop', 'popitem', 'setdefault', 'update', 'values', 'viewitems', 'viewkeys', 'viewvalues'] def __init__(self, refs, symrefs, agent, new_shallow=None, new_unshallow=None): self.refs = refs self.symrefs = symrefs self.agent = agent self.new_shallow = new_shallow self.new_unshallow = new_unshallow def _warn_deprecated(self): import warnings warnings.warn( "Use FetchPackResult.refs instead.", DeprecationWarning, stacklevel=3) def __eq__(self, other): if isinstance(other, dict): self._warn_deprecated() return (self.refs == other) return (self.refs == other.refs and self.symrefs == other.symrefs and self.agent == other.agent) def __contains__(self, name): self._warn_deprecated() return name in self.refs def __getitem__(self, name): self._warn_deprecated() return self.refs[name] def __len__(self): self._warn_deprecated() return len(self.refs) def __iter__(self): self._warn_deprecated() return iter(self.refs) def __getattribute__(self, name): if name in type(self)._FORWARDED_ATTRS: self._warn_deprecated() return getattr(self.refs, name) return super(FetchPackResult, self).__getattribute__(name) def __repr__(self): return "%s(%r, %r, %r)" % ( self.__class__.__name__, self.refs, self.symrefs, self.agent) def _read_shallow_updates(proto): new_shallow = set() new_unshallow = set() for pkt in proto.read_pkt_seq(): cmd, sha = pkt.split(b' ', 1) if cmd == COMMAND_SHALLOW: new_shallow.add(sha.strip()) elif cmd == COMMAND_UNSHALLOW: new_unshallow.add(sha.strip()) else: raise GitProtocolError('unknown command %s' % pkt) return (new_shallow, new_unshallow) # TODO(durin42): this doesn't correctly degrade if the server doesn't # support some capabilities. This should work properly with servers # that don't support multi_ack. class GitClient(object): """Git smart server client.""" def __init__(self, thin_packs=True, report_activity=None, quiet=False, include_tags=False): """Create a new GitClient instance. Args: thin_packs: Whether or not thin packs should be retrieved report_activity: Optional callback for reporting transport activity. include_tags: send annotated tags when sending the objects they point to """ self._report_activity = report_activity self._report_status_parser = None self._fetch_capabilities = set(UPLOAD_CAPABILITIES) self._fetch_capabilities.add(capability_agent()) self._send_capabilities = set(RECEIVE_CAPABILITIES) self._send_capabilities.add(capability_agent()) if quiet: self._send_capabilities.add(CAPABILITY_QUIET) if not thin_packs: self._fetch_capabilities.remove(CAPABILITY_THIN_PACK) if include_tags: self._fetch_capabilities.add(CAPABILITY_INCLUDE_TAG) def get_url(self, path): """Retrieves full url to given path. Args: path: Repository path (as string) Returns: Url to path (as string) """ raise NotImplementedError(self.get_url) @classmethod def from_parsedurl(cls, parsedurl, **kwargs): """Create an instance of this client from a urlparse.parsed object. Args: parsedurl: Result of urlparse.urlparse() Returns: A `GitClient` object """ raise NotImplementedError(cls.from_parsedurl) def send_pack(self, path, update_refs, generate_pack_data, progress=None): """Upload a pack to a remote repository. Args: path: Repository path (as bytestring) update_refs: Function to determine changes to remote refs. Receive dict with existing remote refs, returns dict with changed refs (name -> sha, where sha=ZERO_SHA for deletions) generate_pack_data: Function that can return a tuple with number of objects and list of pack data to include progress: Optional progress function Returns: new_refs dictionary containing the changes that were made {refname: new_ref}, including deleted refs. Raises: SendPackError: if server rejects the pack data 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, depth=None): """Fetch into a target repository. Args: path: Path to fetch from (as bytestring) target: Target repository to fetch into determine_wants: Optional function to determine what refs to fetch. Receives dictionary of name->sha, should return list of shas to fetch. Defaults to all shas. progress: Optional progress function depth: Depth to fetch at Returns: Dictionary with all remote refs (not just those fetched) """ if determine_wants is None: determine_wants = target.object_store.determine_wants_all if CAPABILITY_THIN_PACK in self._fetch_capabilities: # TODO(jelmer): Avoid reading entire file into memory and # only processing it after the whole file has been fetched. f = BytesIO() def commit(): if f.tell(): f.seek(0) target.object_store.add_thin_pack(f.read, None) def abort(): pass else: f, commit, abort = target.object_store.add_pack() try: result = self.fetch_pack( path, determine_wants, target.get_graph_walker(), f.write, progress=progress, depth=depth) except BaseException: abort() raise else: commit() target.update_shallow(result.new_shallow, result.new_unshallow) return result def fetch_pack(self, path, determine_wants, graph_walker, pack_data, progress=None, depth=None): """Retrieve a pack from a git smart server. Args: path: Remote path to fetch from determine_wants: Function determine what refs to fetch. Receives dictionary of name->sha, should return list of shas to fetch. graph_walker: Object with next() and ack(). pack_data: Callback called for each bit of data in the pack progress: Callback for progress reports (strings) depth: Shallow fetch depth Returns: FetchPackResult object """ raise NotImplementedError(self.fetch_pack) def get_refs(self, path): """Retrieve the current refs from a git smart server. Args: path: Path to the repo to fetch from. (as bytestring) Returns: """ raise NotImplementedError(self.get_refs) def _parse_status_report(self, proto): unpack = proto.read_pkt_line().strip() if unpack != b'unpack ok': st = True # flush remaining error data while st is not None: st = proto.read_pkt_line() raise SendPackError(unpack) statuses = [] errs = False ref_status = proto.read_pkt_line() while ref_status: ref_status = ref_status.strip() statuses.append(ref_status) if not ref_status.startswith(b'ok '): errs = True ref_status = proto.read_pkt_line() if errs: ref_status = {} ok = set() for status in statuses: if b' ' not in status: # malformed response, move on to the next one continue status, ref = status.split(b' ', 1) if status == b'ng': if b' ' in ref: ref, status = ref.split(b' ', 1) else: ok.add(ref) ref_status[ref] = status raise UpdateRefsError(', '.join([ refname for refname in ref_status if refname not in ok]) + b' failed to update', ref_status=ref_status) def _read_side_band64k_data(self, proto, channel_callbacks): """Read per-channel data. This requires the side-band-64k capability. Args: proto: Protocol object to read from 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. Args: proto: Protocol object to read from capabilities: List of negotiated capabilities old_refs: Old refs, as received from the server new_refs: Refs to change Returns: have, want) tuple """ want = [] have = [x for x in old_refs.values() if not x == ZERO_SHA] sent_capabilities = False for refname in new_refs: if not isinstance(refname, bytes): raise TypeError('refname is not a bytestring: %r' % refname) old_sha1 = old_refs.get(refname, ZERO_SHA) if not isinstance(old_sha1, bytes): raise TypeError('old sha1 for %s is not a bytestring: %r' % (refname, old_sha1)) new_sha1 = new_refs.get(refname, ZERO_SHA) if not isinstance(new_sha1, bytes): raise TypeError('old sha1 for %s is not a bytestring %r' % (refname, new_sha1)) if old_sha1 != new_sha1: if sent_capabilities: proto.write_pkt_line(old_sha1 + b' ' + new_sha1 + b' ' + refname) else: proto.write_pkt_line( old_sha1 + b' ' + new_sha1 + b' ' + refname + b'\0' + b' '.join(sorted(capabilities))) sent_capabilities = True if new_sha1 not in have and new_sha1 != ZERO_SHA: want.append(new_sha1) proto.write_pkt_line(None) return (have, want) def _negotiate_receive_pack_capabilities(self, server_capabilities): negotiated_capabilities = ( self._send_capabilities & server_capabilities) unknown_capabilities = ( # noqa: F841 extract_capability_names(server_capabilities) - KNOWN_RECEIVE_CAPABILITIES) # TODO(jelmer): warn about unknown capabilities return negotiated_capabilities def _handle_receive_pack_tail(self, proto, capabilities, progress=None): """Handle the tail of a 'git-receive-pack' request. Args: proto: Protocol object to read from capabilities: List of negotiated capabilities progress: Optional progress reporting function Returns: """ if CAPABILITY_SIDE_BAND_64K in capabilities: if progress is None: def progress(x): pass channel_callbacks = {2: progress} if CAPABILITY_REPORT_STATUS in capabilities: channel_callbacks[1] = PktLineParser( self._report_status_parser.handle_packet).parse self._read_side_band64k_data(proto, channel_callbacks) else: if CAPABILITY_REPORT_STATUS in capabilities: for pkt in proto.read_pkt_seq(): self._report_status_parser.handle_packet(pkt) if self._report_status_parser is not None: self._report_status_parser.check() def _negotiate_upload_pack_capabilities(self, server_capabilities): unknown_capabilities = ( # noqa: F841 extract_capability_names(server_capabilities) - KNOWN_UPLOAD_CAPABILITIES) # TODO(jelmer): warn about unknown capabilities symrefs = {} agent = None for capability in server_capabilities: k, v = parse_capability(capability) if k == CAPABILITY_SYMREF: (src, dst) = v.split(b':', 1) symrefs[src] = dst if k == CAPABILITY_AGENT: agent = v negotiated_capabilities = ( self._fetch_capabilities & server_capabilities) return (negotiated_capabilities, symrefs, agent) def _handle_upload_pack_head(self, proto, capabilities, graph_walker, wants, can_read, depth): """Handle the head of a 'git-upload-pack' request. Args: proto: Protocol object to read from capabilities: List of negotiated capabilities graph_walker: GraphWalker instance to call .ack() on wants: List of commits to fetch can_read: function that returns a boolean that indicates whether there is extra graph data to read on proto depth: Depth for request Returns: """ assert isinstance(wants, list) and isinstance(wants[0], bytes) proto.write_pkt_line(COMMAND_WANT + b' ' + wants[0] + b' ' + b' '.join(sorted(capabilities)) + b'\n') for want in wants[1:]: proto.write_pkt_line(COMMAND_WANT + b' ' + want + b'\n') if depth not in (0, None) or getattr(graph_walker, 'shallow', None): if CAPABILITY_SHALLOW not in capabilities: raise GitProtocolError( "server does not support shallow capability required for " "depth") for sha in graph_walker.shallow: proto.write_pkt_line(COMMAND_SHALLOW + b' ' + sha + b'\n') if depth is not None: proto.write_pkt_line(COMMAND_DEEPEN + b' ' + str(depth).encode('ascii') + b'\n') proto.write_pkt_line(None) if can_read is not None: (new_shallow, new_unshallow) = _read_shallow_updates(proto) else: new_shallow = new_unshallow = None else: new_shallow = new_unshallow = set() proto.write_pkt_line(None) have = next(graph_walker) while have: proto.write_pkt_line(COMMAND_HAVE + b' ' + have + b'\n') if can_read is not None and can_read(): pkt = proto.read_pkt_line() parts = pkt.rstrip(b'\n').split(b' ') if parts[0] == b'ACK': graph_walker.ack(parts[1]) if parts[2] in (b'continue', b'common'): pass elif parts[2] == b'ready': break else: raise AssertionError( "%s not in ('continue', 'ready', 'common)" % parts[2]) have = next(graph_walker) proto.write_pkt_line(COMMAND_DONE + b'\n') return (new_shallow, new_unshallow) def _handle_upload_pack_tail(self, proto, capabilities, graph_walker, pack_data, progress=None, rbufsize=_RBUFSIZE): """Handle the tail of a 'git-upload-pack' request. Args: proto: Protocol object to read from capabilities: List of negotiated capabilities graph_walker: GraphWalker instance to call .ack() on pack_data: Function to call with pack data progress: Optional progress reporting function rbufsize: Read buffer size Returns: """ pkt = proto.read_pkt_line() while pkt: parts = pkt.rstrip(b'\n').split(b' ') if parts[0] == b'ACK': graph_walker.ack(parts[1]) if len(parts) < 3 or parts[2] not in ( b'ready', b'continue', b'common'): break pkt = proto.read_pkt_line() if CAPABILITY_SIDE_BAND_64K in capabilities: if progress is None: # Just ignore progress data def progress(x): pass self._read_side_band64k_data(proto, { SIDE_BAND_CHANNEL_DATA: pack_data, SIDE_BAND_CHANNEL_PROGRESS: progress} ) else: while True: data = proto.read(rbufsize) if data == b"": break pack_data(data) def check_wants(wants, refs): """Check that a set of wants is valid. Args: wants: Set of object SHAs to fetch refs: Refs dictionary to check against Returns: """ missing = set(wants) - { v for (k, v) in refs.items() if not k.endswith(ANNOTATED_TAG_SUFFIX)} if missing: raise InvalidWants(missing) def remote_error_from_stderr(stderr): if stderr is None: return HangupException() for l in stderr.readlines(): if l.startswith(b'ERROR: '): return GitProtocolError( l[len(b'ERROR: '):].decode('utf-8', 'replace')) return GitProtocolError(l.decode('utf-8', 'replace')) return HangupException() class TraditionalGitClient(GitClient): """Traditional Git client.""" DEFAULT_ENCODING = 'utf-8' def __init__(self, path_encoding=DEFAULT_ENCODING, **kwargs): self._remote_path_encoding = path_encoding super(TraditionalGitClient, self).__init__(**kwargs) def _connect(self, cmd, path): """Create a connection to the server. This method is abstract - concrete implementations should implement their own variant which connects to the server and returns an initialized Protocol object with the service ready for use and a can_read function which may be used to see if reads would block. Args: cmd: The git service name to which we should connect. path: The path we should pass to the service. (as bytestirng) """ raise NotImplementedError() def send_pack(self, path, update_refs, generate_pack_data, progress=None): """Upload a pack to a remote repository. Args: path: Repository path (as bytestring) update_refs: Function to determine changes to remote refs. Receive dict with existing remote refs, returns dict with changed refs (name -> sha, where sha=ZERO_SHA for deletions) generate_pack_data: Function that can return a tuple with number of objects and pack data to upload. progress: Optional callback called with progress updates Returns: new_refs dictionary containing the changes that were made {refname: new_ref}, including deleted refs. Raises: SendPackError: if server rejects the pack data UpdateRefsError: if the server supports report-status and rejects ref updates """ proto, unused_can_read, stderr = self._connect(b'receive-pack', path) with proto: try: old_refs, server_capabilities = read_pkt_refs(proto) except HangupException: raise remote_error_from_stderr(stderr) negotiated_capabilities = \ self._negotiate_receive_pack_capabilities(server_capabilities) if CAPABILITY_REPORT_STATUS in negotiated_capabilities: self._report_status_parser = ReportStatusParser() report_status_parser = self._report_status_parser try: new_refs = orig_new_refs = update_refs(dict(old_refs)) except BaseException: proto.write_pkt_line(None) raise if CAPABILITY_DELETE_REFS not in server_capabilities: # Server does not support deletions. Fail later. new_refs = dict(orig_new_refs) for ref, sha in orig_new_refs.items(): if sha == ZERO_SHA: if CAPABILITY_REPORT_STATUS in negotiated_capabilities: report_status_parser._ref_statuses.append( b'ng ' + sha + b' remote does not support deleting refs') report_status_parser._ref_status_ok = False del new_refs[ref] if new_refs is None: proto.write_pkt_line(None) return old_refs if len(new_refs) == 0 and len(orig_new_refs): # NOOP - Original new refs filtered out by policy proto.write_pkt_line(None) if report_status_parser is not None: report_status_parser.check() return old_refs (have, want) = self._handle_receive_pack_head( proto, negotiated_capabilities, old_refs, new_refs) if (not want and set(new_refs.items()).issubset(set(old_refs.items()))): return new_refs pack_data_count, pack_data = generate_pack_data( have, want, ofs_delta=(CAPABILITY_OFS_DELTA in negotiated_capabilities)) dowrite = bool(pack_data_count) dowrite = dowrite or any(old_refs.get(ref) != sha for (ref, sha) in new_refs.items() if sha != ZERO_SHA) if dowrite: write_pack_data(proto.write_file(), pack_data_count, pack_data) self._handle_receive_pack_tail( proto, negotiated_capabilities, progress) return new_refs def fetch_pack(self, path, determine_wants, graph_walker, pack_data, progress=None, depth=None): """Retrieve a pack from a git smart server. Args: path: Remote path to fetch from determine_wants: Function determine what refs to fetch. Receives dictionary of name->sha, should return list of shas to fetch. graph_walker: Object with next() and ack(). pack_data: Callback called for each bit of data in the pack progress: Callback for progress reports (strings) depth: Shallow fetch depth Returns: FetchPackResult object """ proto, can_read, stderr = self._connect(b'upload-pack', path) with proto: try: refs, server_capabilities = read_pkt_refs(proto) except HangupException: raise remote_error_from_stderr(stderr) negotiated_capabilities, symrefs, agent = ( self._negotiate_upload_pack_capabilities( server_capabilities)) if refs is None: proto.write_pkt_line(None) return FetchPackResult(refs, symrefs, agent) try: wants = determine_wants(refs) except BaseException: proto.write_pkt_line(None) raise if wants is not None: wants = [cid for cid in wants if cid != ZERO_SHA] if not wants: proto.write_pkt_line(None) return FetchPackResult(refs, symrefs, agent) (new_shallow, new_unshallow) = self._handle_upload_pack_head( proto, negotiated_capabilities, graph_walker, wants, can_read, depth=depth) self._handle_upload_pack_tail( proto, negotiated_capabilities, graph_walker, pack_data, progress) return FetchPackResult( refs, symrefs, agent, new_shallow, new_unshallow) def get_refs(self, path): """Retrieve the current refs from a git smart server. """ # stock `git ls-remote` uses upload-pack proto, _, stderr = self._connect(b'upload-pack', path) with proto: try: refs, _ = read_pkt_refs(proto) except HangupException: raise remote_error_from_stderr(stderr) proto.write_pkt_line(None) return refs def archive(self, path, committish, write_data, progress=None, write_error=None, format=None, subdirs=None, prefix=None): proto, can_read, stderr = self._connect(b'upload-archive', path) with proto: if format is not None: proto.write_pkt_line(b"argument --format=" + format) proto.write_pkt_line(b"argument " + committish) if subdirs is not None: for subdir in subdirs: proto.write_pkt_line(b"argument " + subdir) if prefix is not None: proto.write_pkt_line(b"argument --prefix=" + prefix) proto.write_pkt_line(None) try: pkt = proto.read_pkt_line() except HangupException: raise remote_error_from_stderr(stderr) if pkt == b"NACK\n": return elif pkt == b"ACK\n": pass elif pkt.startswith(b"ERR "): raise GitProtocolError( pkt[4:].rstrip(b"\n").decode('utf-8', 'replace')) else: raise AssertionError("invalid response %r" % pkt) ret = proto.read_pkt_line() if ret is not None: raise AssertionError("expected pkt tail") self._read_side_band64k_data(proto, { SIDE_BAND_CHANNEL_DATA: write_data, SIDE_BAND_CHANNEL_PROGRESS: progress, SIDE_BAND_CHANNEL_FATAL: write_error}) class TCPGitClient(TraditionalGitClient): """A Git Client that works over TCP directly (i.e. git://).""" def __init__(self, host, port=None, **kwargs): if port is None: port = TCP_GIT_PORT self._host = host self._port = port super(TCPGitClient, self).__init__(**kwargs) @classmethod def from_parsedurl(cls, parsedurl, **kwargs): return cls(parsedurl.hostname, port=parsedurl.port, **kwargs) def get_url(self, path): netloc = self._host if self._port is not None and self._port != TCP_GIT_PORT: netloc += ":%d" % self._port return urlparse.urlunsplit(("git", netloc, path, '', '')) def _connect(self, cmd, path): if not isinstance(cmd, bytes): raise TypeError(cmd) if not isinstance(path, bytes): path = path.encode(self._remote_path_encoding) sockaddrs = socket.getaddrinfo( self._host, self._port, socket.AF_UNSPEC, socket.SOCK_STREAM) s = None err = socket.error("no address found for %s" % self._host) for (family, socktype, proto, canonname, sockaddr) in sockaddrs: s = socket.socket(family, socktype, proto) s.setsockopt(socket.IPPROTO_TCP, socket.TCP_NODELAY, 1) try: s.connect(sockaddr) break except socket.error as e: err = e if s is not None: s.close() s = None if s is None: raise err # -1 means system default buffering rfile = s.makefile('rb', -1) # 0 means unbuffered wfile = s.makefile('wb', 0) def close(): rfile.close() wfile.close() s.close() proto = Protocol(rfile.read, wfile.write, close, report_activity=self._report_activity) if path.startswith(b"/~"): path = path[1:] # TODO(jelmer): Alternative to ascii? proto.send_cmd( b'git-' + cmd, path, b'host=' + self._host.encode('ascii')) return proto, lambda: _fileno_can_read(s), None class SubprocessWrapper(object): """A socket-like object that talks to a subprocess via pipes.""" def __init__(self, proc): self.proc = proc - if sys.version_info[0] == 2: - self.read = proc.stdout.read - else: - self.read = BufferedReader(proc.stdout).read + self.read = BufferedReader(proc.stdout).read self.write = proc.stdin.write @property def stderr(self): return self.proc.stderr def can_read(self): if sys.platform == 'win32': from msvcrt import get_osfhandle handle = get_osfhandle(self.proc.stdout.fileno()) return _win32_peek_avail(handle) != 0 else: return _fileno_can_read(self.proc.stdout.fileno()) def close(self): self.proc.stdin.close() self.proc.stdout.close() if self.proc.stderr: self.proc.stderr.close() self.proc.wait() def find_git_command(): """Find command to run for system Git (usually C Git).""" if sys.platform == 'win32': # support .exe, .bat and .cmd try: # to avoid overhead import win32api except ImportError: # run through cmd.exe with some overhead return ['cmd', '/c', 'git'] else: status, git = win32api.FindExecutable('git') return [git] else: return ['git'] class SubprocessGitClient(TraditionalGitClient): """Git client that talks to a server using a subprocess.""" @classmethod def from_parsedurl(cls, parsedurl, **kwargs): return cls(**kwargs) git_command = None def _connect(self, service, path): if not isinstance(service, bytes): raise TypeError(service) if isinstance(path, bytes): path = path.decode(self._remote_path_encoding) if self.git_command is None: git_command = find_git_command() argv = git_command + [service.decode('ascii'), path] p = subprocess.Popen(argv, bufsize=0, stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE) pw = SubprocessWrapper(p) return (Protocol(pw.read, pw.write, pw.close, report_activity=self._report_activity), pw.can_read, p.stderr) class LocalGitClient(GitClient): """Git Client that just uses a local Repo.""" def __init__(self, thin_packs=True, report_activity=None, config=None): """Create a new LocalGitClient instance. Args: thin_packs: Whether or not thin packs should be retrieved report_activity: Optional callback for reporting transport activity. """ self._report_activity = report_activity # Ignore the thin_packs argument def get_url(self, path): return urlparse.urlunsplit(('file', '', path, '', '')) @classmethod def from_parsedurl(cls, parsedurl, **kwargs): return cls(**kwargs) @classmethod def _open_repo(cls, path): from dulwich.repo import Repo if not isinstance(path, str): path = path.decode(sys.getfilesystemencoding()) return closing(Repo(path)) def send_pack(self, path, update_refs, generate_pack_data, progress=None): """Upload a pack to a remote repository. Args: path: Repository path (as bytestring) update_refs: Function to determine changes to remote refs. Receive dict with existing remote refs, returns dict with changed refs (name -> sha, where sha=ZERO_SHA for deletions) with number of items and pack data to upload. progress: Optional progress function Returns: new_refs dictionary containing the changes that were made {refname: new_ref}, including deleted refs. Raises: SendPackError: if server rejects the pack data UpdateRefsError: if the server supports report-status and rejects ref updates """ if not progress: def progress(x): pass with self._open_repo(path) as target: old_refs = target.get_refs() new_refs = update_refs(dict(old_refs)) have = [sha1 for sha1 in old_refs.values() if sha1 != ZERO_SHA] want = [] for refname, new_sha1 in new_refs.items(): if (new_sha1 not in have and new_sha1 not in want and new_sha1 != ZERO_SHA): want.append(new_sha1) if (not want and set(new_refs.items()).issubset(set(old_refs.items()))): return new_refs target.object_store.add_pack_data( *generate_pack_data(have, want, ofs_delta=True)) for refname, new_sha1 in new_refs.items(): old_sha1 = old_refs.get(refname, ZERO_SHA) if new_sha1 != ZERO_SHA: if not target.refs.set_if_equals( refname, old_sha1, new_sha1): progress('unable to set %s to %s' % (refname, new_sha1)) else: if not target.refs.remove_if_equals(refname, old_sha1): progress('unable to remove %s' % refname) return new_refs def fetch(self, path, target, determine_wants=None, progress=None, depth=None): """Fetch into a target repository. Args: path: Path to fetch from (as bytestring) target: Target repository to fetch into determine_wants: Optional function determine what refs to fetch. Receives dictionary of name->sha, should return list of shas to fetch. Defaults to all shas. progress: Optional progress function depth: Shallow fetch depth Returns: FetchPackResult object """ with self._open_repo(path) as r: refs = r.fetch(target, determine_wants=determine_wants, progress=progress, depth=depth) return FetchPackResult(refs, r.refs.get_symrefs(), agent_string()) def fetch_pack(self, path, determine_wants, graph_walker, pack_data, progress=None, depth=None): """Retrieve a pack from a git smart server. Args: path: Remote path to fetch from determine_wants: Function determine what refs to fetch. Receives dictionary of name->sha, should return list of shas to fetch. graph_walker: Object with next() and ack(). pack_data: Callback called for each bit of data in the pack progress: Callback for progress reports (strings) depth: Shallow fetch depth Returns: FetchPackResult object """ with self._open_repo(path) as r: objects_iter = r.fetch_objects( determine_wants, graph_walker, progress=progress, depth=depth) symrefs = r.refs.get_symrefs() agent = agent_string() # Did the process short-circuit (e.g. in a stateless RPC call)? # Note that the client still expects a 0-object pack in most cases. if objects_iter is None: return FetchPackResult(None, symrefs, agent) protocol = ProtocolFile(None, pack_data) write_pack_objects(protocol, objects_iter) return FetchPackResult(r.get_refs(), symrefs, agent) def get_refs(self, path): """Retrieve the current refs from a git smart server. """ with self._open_repo(path) as target: return target.get_refs() # What Git client to use for local access default_local_git_client_cls = LocalGitClient class SSHVendor(object): """A client side SSH implementation.""" def connect_ssh(self, host, command, username=None, port=None, password=None, key_filename=None): # This function was deprecated in 0.9.1 import warnings warnings.warn( "SSHVendor.connect_ssh has been renamed to SSHVendor.run_command", DeprecationWarning) return self.run_command(host, command, username=username, port=port, password=password, key_filename=key_filename) def run_command(self, host, command, username=None, port=None, password=None, key_filename=None): """Connect to an SSH server. Run a command remotely and return a file-like object for interaction with the remote command. Args: host: Host name command: Command to run (as argv array) username: Optional ame of user to log in as port: Optional SSH port to use password: Optional ssh password for login or private key key_filename: Optional path to private keyfile Returns: """ raise NotImplementedError(self.run_command) class StrangeHostname(Exception): """Refusing to connect to strange SSH hostname.""" def __init__(self, hostname): super(StrangeHostname, self).__init__(hostname) class SubprocessSSHVendor(SSHVendor): """SSH vendor that shells out to the local 'ssh' command.""" def run_command(self, host, command, username=None, port=None, password=None, key_filename=None): if password is not None: raise NotImplementedError( "Setting password not supported by SubprocessSSHVendor.") args = ['ssh', '-x'] if port: args.extend(['-p', str(port)]) if key_filename: args.extend(['-i', str(key_filename)]) if username: host = '%s@%s' % (username, host) if host.startswith('-'): raise StrangeHostname(hostname=host) args.append(host) proc = subprocess.Popen(args + [command], bufsize=0, stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE) return SubprocessWrapper(proc) class PLinkSSHVendor(SSHVendor): """SSH vendor that shells out to the local 'plink' command.""" def run_command(self, host, command, username=None, port=None, password=None, key_filename=None): if sys.platform == 'win32': args = ['plink.exe', '-ssh'] else: args = ['plink', '-ssh'] if password is not None: import warnings warnings.warn( "Invoking PLink with a password exposes the password in the " "process list.") args.extend(['-pw', str(password)]) if port: args.extend(['-P', str(port)]) if key_filename: args.extend(['-i', str(key_filename)]) if username: host = '%s@%s' % (username, host) if host.startswith('-'): raise StrangeHostname(hostname=host) args.append(host) proc = subprocess.Popen(args + [command], bufsize=0, stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE) return SubprocessWrapper(proc) def ParamikoSSHVendor(**kwargs): import warnings warnings.warn( "ParamikoSSHVendor has been moved to dulwich.contrib.paramiko_vendor.", DeprecationWarning) from dulwich.contrib.paramiko_vendor import ParamikoSSHVendor return ParamikoSSHVendor(**kwargs) # Can be overridden by users get_ssh_vendor = SubprocessSSHVendor class SSHGitClient(TraditionalGitClient): def __init__(self, host, port=None, username=None, vendor=None, config=None, password=None, key_filename=None, **kwargs): self.host = host self.port = port self.username = username self.password = password self.key_filename = key_filename super(SSHGitClient, self).__init__(**kwargs) self.alternative_paths = {} if vendor is not None: self.ssh_vendor = vendor else: self.ssh_vendor = get_ssh_vendor() def get_url(self, path): netloc = self.host if self.port is not None: netloc += ":%d" % self.port if self.username is not None: netloc = urlquote(self.username, '@/:') + "@" + netloc return urlparse.urlunsplit(('ssh', netloc, path, '', '')) @classmethod def from_parsedurl(cls, parsedurl, **kwargs): return cls(host=parsedurl.hostname, port=parsedurl.port, username=parsedurl.username, **kwargs) def _get_cmd_path(self, cmd): cmd = self.alternative_paths.get(cmd, b'git-' + cmd) assert isinstance(cmd, bytes) return cmd def _connect(self, cmd, path): if not isinstance(cmd, bytes): raise TypeError(cmd) if isinstance(path, bytes): path = path.decode(self._remote_path_encoding) if path.startswith("/~"): path = path[1:] argv = (self._get_cmd_path(cmd).decode(self._remote_path_encoding) + " '" + path + "'") kwargs = {} if self.password is not None: kwargs['password'] = self.password if self.key_filename is not None: kwargs['key_filename'] = self.key_filename con = self.ssh_vendor.run_command( self.host, argv, port=self.port, username=self.username, **kwargs) return (Protocol(con.read, con.write, con.close, report_activity=self._report_activity), con.can_read, getattr(con, 'stderr', None)) def default_user_agent_string(): # Start user agent with "git/", because GitHub requires this. :-( See # https://github.com/jelmer/dulwich/issues/562 for details. return "git/dulwich/%s" % ".".join([str(x) for x in dulwich.__version__]) def default_urllib3_manager(config, pool_manager_cls=None, proxy_manager_cls=None, **override_kwargs): """Return `urllib3` connection pool manager. Honour detected proxy configurations. Args: config: dulwich.config.ConfigDict` instance with Git configuration. kwargs: Additional arguments for urllib3.ProxyManager Returns: `pool_manager_cls` (defaults to `urllib3.ProxyManager`) instance for proxy configurations, `proxy_manager_cls` (defaults to `urllib3.PoolManager`) instance otherwise. """ proxy_server = user_agent = None ca_certs = ssl_verify = None if config is not None: try: proxy_server = config.get(b"http", b"proxy") except KeyError: pass try: user_agent = config.get(b"http", b"useragent") except KeyError: pass # TODO(jelmer): Support per-host settings try: ssl_verify = config.get_boolean(b"http", b"sslVerify") except KeyError: ssl_verify = True try: ca_certs = config.get(b"http", b"sslCAInfo") except KeyError: ca_certs = None if user_agent is None: user_agent = default_user_agent_string() headers = {"User-agent": user_agent} kwargs = {} if ssl_verify is True: kwargs['cert_reqs'] = "CERT_REQUIRED" elif ssl_verify is False: kwargs['cert_reqs'] = 'CERT_NONE' else: # Default to SSL verification kwargs['cert_reqs'] = "CERT_REQUIRED" if ca_certs is not None: kwargs['ca_certs'] = ca_certs kwargs.update(override_kwargs) # Try really hard to find a SSL certificate path if 'ca_certs' not in kwargs and kwargs.get('cert_reqs') != 'CERT_NONE': try: import certifi except ImportError: pass else: kwargs['ca_certs'] = certifi.where() import urllib3 if proxy_server is not None: if proxy_manager_cls is None: proxy_manager_cls = urllib3.ProxyManager # `urllib3` requires a `str` object in both Python 2 and 3, while # `ConfigDict` coerces entries to `bytes` on Python 3. Compensate. if not isinstance(proxy_server, str): proxy_server = proxy_server.decode() manager = proxy_manager_cls(proxy_server, headers=headers, **kwargs) else: if pool_manager_cls is None: pool_manager_cls = urllib3.PoolManager manager = pool_manager_cls(headers=headers, **kwargs) return manager class HttpGitClient(GitClient): def __init__(self, base_url, dumb=None, pool_manager=None, config=None, username=None, password=None, **kwargs): self._base_url = base_url.rstrip("/") + "/" self._username = username self._password = password self.dumb = dumb if pool_manager is None: self.pool_manager = default_urllib3_manager(config) else: self.pool_manager = pool_manager if username is not None: # No escaping needed: ":" is not allowed in username: # https://tools.ietf.org/html/rfc2617#section-2 credentials = "%s:%s" % (username, password) import urllib3.util basic_auth = urllib3.util.make_headers(basic_auth=credentials) self.pool_manager.headers.update(basic_auth) GitClient.__init__(self, **kwargs) def get_url(self, path): return self._get_url(path).rstrip("/") @classmethod def from_parsedurl(cls, parsedurl, **kwargs): password = parsedurl.password if password is not None: kwargs['password'] = urlunquote(password) username = parsedurl.username if username is not None: kwargs['username'] = urlunquote(username) netloc = parsedurl.hostname if parsedurl.port: netloc = "%s:%s" % (netloc, parsedurl.port) if parsedurl.username: netloc = "%s@%s" % (parsedurl.username, netloc) parsedurl = parsedurl._replace(netloc=netloc) return cls(urlparse.urlunparse(parsedurl), **kwargs) def __repr__(self): return "%s(%r, dumb=%r)" % ( type(self).__name__, self._base_url, self.dumb) def _get_url(self, path): if not isinstance(path, str): # urllib3.util.url._encode_invalid_chars() converts the path back # to bytes using the utf-8 codec. path = path.decode('utf-8') return urlparse.urljoin(self._base_url, path).rstrip("/") + "/" def _http_request(self, url, headers=None, data=None, allow_compression=False): """Perform HTTP request. Args: url: Request URL. headers: Optional custom headers to override defaults. data: Request data. allow_compression: Allow GZipped communication. Returns: Tuple (`response`, `read`), where response is an `urllib3` response object with additional `content_type` and `redirect_location` properties, and `read` is a consumable read method for the response data. """ req_headers = self.pool_manager.headers.copy() if headers is not None: req_headers.update(headers) req_headers["Pragma"] = "no-cache" if allow_compression: req_headers["Accept-Encoding"] = "gzip" else: req_headers["Accept-Encoding"] = "identity" if data is None: resp = self.pool_manager.request("GET", url, headers=req_headers) else: resp = self.pool_manager.request("POST", url, headers=req_headers, body=data) if resp.status == 404: raise NotGitRepository() elif resp.status != 200: raise GitProtocolError("unexpected http resp %d for %s" % (resp.status, url)) # TODO: Optimization available by adding `preload_content=False` to the # request and just passing the `read` method on instead of going via # `BytesIO`, if we can guarantee that the entire response is consumed # before issuing the next to still allow for connection reuse from the # pool. read = BytesIO(resp.data).read resp.content_type = resp.getheader("Content-Type") # Check if geturl() is available (urllib3 version >= 1.23) try: resp_url = resp.geturl() except AttributeError: # get_redirect_location() is available for urllib3 >= 1.1 resp.redirect_location = resp.get_redirect_location() else: resp.redirect_location = resp_url if resp_url != url else '' return resp, read def _discover_references(self, service, base_url): assert base_url[-1] == "/" tail = "info/refs" headers = {"Accept": "*/*"} if self.dumb is not True: tail += "?service=%s" % service.decode('ascii') url = urlparse.urljoin(base_url, tail) resp, read = self._http_request(url, headers, allow_compression=True) if resp.redirect_location: # Something changed (redirect!), so let's update the base URL if not resp.redirect_location.endswith(tail): raise GitProtocolError( "Redirected from URL %s to URL %s without %s" % ( url, resp.redirect_location, tail)) base_url = resp.redirect_location[:-len(tail)] try: self.dumb = not resp.content_type.startswith("application/x-git-") if not self.dumb: proto = Protocol(read, None) # The first line should mention the service try: [pkt] = list(proto.read_pkt_seq()) except ValueError: raise GitProtocolError( "unexpected number of packets received") if pkt.rstrip(b'\n') != (b'# service=' + service): raise GitProtocolError( "unexpected first line %r from smart server" % pkt) return read_pkt_refs(proto) + (base_url, ) else: return read_info_refs(resp), set(), base_url finally: resp.close() def _smart_request(self, service, url, data): assert url[-1] == "/" url = urlparse.urljoin(url, service) result_content_type = "application/x-%s-result" % service headers = { "Content-Type": "application/x-%s-request" % service, "Accept": result_content_type, "Content-Length": str(len(data)), } resp, read = self._http_request(url, headers, data) if resp.content_type != result_content_type: raise GitProtocolError("Invalid content-type from server: %s" % resp.content_type) return resp, read def send_pack(self, path, update_refs, generate_pack_data, progress=None): """Upload a pack to a remote repository. Args: path: Repository path (as bytestring) update_refs: Function to determine changes to remote refs. Receives dict with existing remote refs, returns dict with changed refs (name -> sha, where sha=ZERO_SHA for deletions) generate_pack_data: Function that can return a tuple with number of elements and pack data to upload. progress: Optional progress function Returns: new_refs dictionary containing the changes that were made {refname: new_ref}, including deleted refs. Raises: SendPackError: if server rejects the pack data UpdateRefsError: if the server supports report-status and rejects ref updates """ url = self._get_url(path) old_refs, server_capabilities, url = self._discover_references( b"git-receive-pack", url) negotiated_capabilities = self._negotiate_receive_pack_capabilities( server_capabilities) negotiated_capabilities.add(capability_agent()) if CAPABILITY_REPORT_STATUS in negotiated_capabilities: self._report_status_parser = ReportStatusParser() new_refs = update_refs(dict(old_refs)) if new_refs is None: # Determine wants function is aborting the push. return old_refs if self.dumb: raise NotImplementedError(self.fetch_pack) req_data = BytesIO() req_proto = Protocol(None, req_data.write) (have, want) = self._handle_receive_pack_head( req_proto, negotiated_capabilities, old_refs, new_refs) if not want and set(new_refs.items()).issubset(set(old_refs.items())): return new_refs pack_data_count, pack_data = generate_pack_data( have, want, ofs_delta=(CAPABILITY_OFS_DELTA in negotiated_capabilities)) if pack_data_count: write_pack_data(req_proto.write_file(), pack_data_count, pack_data) resp, read = self._smart_request("git-receive-pack", url, data=req_data.getvalue()) try: resp_proto = Protocol(read, None) self._handle_receive_pack_tail( resp_proto, negotiated_capabilities, progress) return new_refs finally: resp.close() def fetch_pack(self, path, determine_wants, graph_walker, pack_data, progress=None, depth=None): """Retrieve a pack from a git smart server. Args: path: Path to fetch from determine_wants: Callback that returns list of commits to fetch graph_walker: Object with next() and ack(). pack_data: Callback called for each bit of data in the pack progress: Callback for progress reports (strings) depth: Depth for request Returns: FetchPackResult object """ url = self._get_url(path) refs, server_capabilities, url = self._discover_references( b"git-upload-pack", url) negotiated_capabilities, symrefs, agent = ( self._negotiate_upload_pack_capabilities( server_capabilities)) wants = determine_wants(refs) if wants is not None: wants = [cid for cid in wants if cid != ZERO_SHA] if not wants: return FetchPackResult(refs, symrefs, agent) if self.dumb: raise NotImplementedError(self.send_pack) req_data = BytesIO() req_proto = Protocol(None, req_data.write) (new_shallow, new_unshallow) = self._handle_upload_pack_head( req_proto, negotiated_capabilities, graph_walker, wants, can_read=None, depth=depth) resp, read = self._smart_request( "git-upload-pack", url, data=req_data.getvalue()) try: resp_proto = Protocol(read, None) if new_shallow is None and new_unshallow is None: (new_shallow, new_unshallow) = _read_shallow_updates( resp_proto) self._handle_upload_pack_tail( resp_proto, negotiated_capabilities, graph_walker, pack_data, progress) return FetchPackResult( refs, symrefs, agent, new_shallow, new_unshallow) finally: resp.close() def get_refs(self, path): """Retrieve the current refs from a git smart server. """ url = self._get_url(path) refs, _, _ = self._discover_references( b"git-upload-pack", url) return refs def get_transport_and_path_from_url(url, config=None, **kwargs): """Obtain a git client from a URL. Args: url: URL to open (a unicode string) config: Optional config object thin_packs: Whether or not thin packs should be retrieved report_activity: Optional callback for reporting transport activity. Returns: Tuple with client instance and relative path. """ parsed = urlparse.urlparse(url) if parsed.scheme == 'git': return (TCPGitClient.from_parsedurl(parsed, **kwargs), parsed.path) elif parsed.scheme in ('git+ssh', 'ssh'): return SSHGitClient.from_parsedurl(parsed, **kwargs), parsed.path elif parsed.scheme in ('http', 'https'): return HttpGitClient.from_parsedurl( parsed, config=config, **kwargs), parsed.path elif parsed.scheme == 'file': return default_local_git_client_cls.from_parsedurl( parsed, **kwargs), parsed.path raise ValueError("unknown scheme '%s'" % parsed.scheme) def parse_rsync_url(location): """Parse a rsync-style URL. """ if ':' in location and '@' not in location: # SSH with no user@, zero or one leading slash. (host, path) = location.split(':', 1) user = None elif ':' in location: # SSH with user@host:foo. user_host, path = location.split(':', 1) if '@' in user_host: user, host = user_host.rsplit('@', 1) else: user = None host = user_host else: raise ValueError('not a valid rsync-style URL') return (user, host, path) def get_transport_and_path(location, **kwargs): """Obtain a git client from a URL. Args: location: URL or path (a string) config: Optional config object thin_packs: Whether or not thin packs should be retrieved report_activity: Optional callback for reporting transport activity. Returns: Tuple with client instance and relative path. """ # First, try to parse it as a URL try: return get_transport_and_path_from_url(location, **kwargs) except ValueError: pass if (sys.platform == 'win32' and location[0].isalpha() and location[1:3] == ':\\'): # Windows local path return default_local_git_client_cls(**kwargs), location try: (username, hostname, path) = parse_rsync_url(location) except ValueError: # Otherwise, assume it's a local path. return default_local_git_client_cls(**kwargs), location else: return SSHGitClient(hostname, username=username, **kwargs), path DEFAULT_GIT_CREDENTIALS_PATHS = [ os.path.expanduser('~/.git-credentials'), get_xdg_config_home_path('git', 'credentials')] def get_credentials_from_store(scheme, hostname, username=None, fnames=DEFAULT_GIT_CREDENTIALS_PATHS): for fname in fnames: try: with open(fname, 'rb') as f: for line in f: parsed_line = urlparse.urlparse(line) if (parsed_line.scheme == scheme and parsed_line.hostname == hostname and (username is None or parsed_line.username == username)): return parsed_line.username, parsed_line.password except OSError as e: if e.errno != errno.ENOENT: raise # If the file doesn't exist, try the next one. continue diff --git a/dulwich/contrib/test_swift.py b/dulwich/contrib/test_swift.py index 090d5343..d4b56392 100644 --- a/dulwich/contrib/test_swift.py +++ b/dulwich/contrib/test_swift.py @@ -1,656 +1,484 @@ # test_swift.py -- Unittests for the Swift backend. # Copyright (C) 2013 eNovance SAS # # Author: Fabien Boucher # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """Tests for dulwich.contrib.swift.""" import posixpath from time import time from io import BytesIO try: from StringIO import StringIO except ImportError: from io import StringIO import sys from unittest import skipIf from dulwich.tests import ( TestCase, ) from dulwich.tests.test_object_store import ( ObjectStoreTests, ) from dulwich.tests.utils import ( build_pack, ) from dulwich.objects import ( Blob, Commit, Tree, Tag, parse_timezone, ) from dulwich.pack import ( REF_DELTA, - write_pack_index_v2, - PackData, - load_pack_index_file, ) try: from simplejson import dumps as json_dumps except ImportError: from json import dumps as json_dumps missing_libs = [] try: import gevent # noqa:F401 except ImportError: missing_libs.append("gevent") try: import geventhttpclient # noqa:F401 except ImportError: missing_libs.append("geventhttpclient") try: from mock import patch except ImportError: missing_libs.append("mock") skipmsg = "Required libraries are not installed (%r)" % missing_libs -skipIfPY3 = skipIf(sys.version_info[0] == 3, - "SWIFT module not yet ported to python3.") if not missing_libs: from dulwich.contrib import swift config_file = """[swift] auth_url = http://127.0.0.1:8080/auth/%(version_str)s auth_ver = %(version_int)s username = test;tester password = testing region_name = %(region_name)s endpoint_type = %(endpoint_type)s concurrency = %(concurrency)s chunk_length = %(chunk_length)s cache_length = %(cache_length)s http_pool_length = %(http_pool_length)s http_timeout = %(http_timeout)s """ def_config_file = {'version_str': 'v1.0', 'version_int': 1, 'concurrency': 1, 'chunk_length': 12228, 'cache_length': 1, 'region_name': 'test', 'endpoint_type': 'internalURL', 'http_pool_length': 1, 'http_timeout': 1} def create_swift_connector(store={}): return lambda root, conf: FakeSwiftConnector(root, conf=conf, store=store) class Response(object): def __init__(self, headers={}, status=200, content=None): self.headers = headers self.status_code = status self.content = content def __getitem__(self, key): return self.headers[key] def items(self): return self.headers.items() def read(self): return self.content def fake_auth_request_v1(*args, **kwargs): ret = Response({'X-Storage-Url': 'http://127.0.0.1:8080/v1.0/AUTH_fakeuser', 'X-Auth-Token': '12' * 10}, 200) return ret def fake_auth_request_v1_error(*args, **kwargs): ret = Response({}, 401) return ret def fake_auth_request_v2(*args, **kwargs): s_url = 'http://127.0.0.1:8080/v1.0/AUTH_fakeuser' resp = {'access': {'token': {'id': '12' * 10}, 'serviceCatalog': [ {'type': 'object-store', 'endpoints': [{'region': 'test', 'internalURL': s_url, }, ] }, ] } } ret = Response(status=200, content=json_dumps(resp)) return ret def create_commit(data, marker=b'Default', blob=None): if not blob: blob = Blob.from_string(b'The blob content ' + marker) tree = Tree() tree.add(b"thefile_" + marker, 0o100644, blob.id) cmt = Commit() if data: assert isinstance(data[-1], Commit) cmt.parents = [data[-1].id] cmt.tree = tree.id author = b"John Doe " + marker + b" " cmt.author = cmt.committer = author tz = parse_timezone(b'-0200')[0] cmt.commit_time = cmt.author_time = int(time()) cmt.commit_timezone = cmt.author_timezone = tz cmt.encoding = b"UTF-8" cmt.message = b"The commit message " + marker tag = Tag() tag.tagger = b"john@doe.net" tag.message = b"Annotated tag" tag.tag_timezone = parse_timezone(b'-0200')[0] tag.tag_time = cmt.author_time tag.object = (Commit, cmt.id) tag.name = b"v_" + marker + b"_0.1" return blob, tree, tag, cmt def create_commits(length=1, marker=b'Default'): data = [] for i in range(0, length): _marker = ("%s_%s" % (marker, i)).encode() blob, tree, tag, cmt = create_commit(data, _marker) data.extend([blob, tree, tag, cmt]) return data @skipIf(missing_libs, skipmsg) class FakeSwiftConnector(object): def __init__(self, root, conf, store=None): if store: self.store = store else: self.store = {} self.conf = conf self.root = root self.concurrency = 1 self.chunk_length = 12228 self.cache_length = 1 def put_object(self, name, content): name = posixpath.join(self.root, name) if hasattr(content, 'seek'): content.seek(0) content = content.read() self.store[name] = content def get_object(self, name, range=None): name = posixpath.join(self.root, name) if not range: try: return BytesIO(self.store[name]) except KeyError: return None else: l, r = range.split('-') try: if not l: r = -int(r) return self.store[name][r:] else: return self.store[name][int(l):int(r)] except KeyError: return None def get_container_objects(self): return [{'name': k.replace(self.root + '/', '')} for k in self.store] def create_root(self): if self.root in self.store.keys(): pass else: self.store[self.root] = '' def get_object_stat(self, name): name = posixpath.join(self.root, name) if name not in self.store: return None return {'content-length': len(self.store[name])} -@skipIf(missing_libs, skipmsg) -@skipIfPY3 -class TestSwiftObjectStore(TestCase): - - def setUp(self): - super(TestSwiftObjectStore, self).setUp() - self.conf = swift.load_conf(file=StringIO(config_file % - def_config_file)) - self.fsc = FakeSwiftConnector('fakerepo', conf=self.conf) - - def _put_pack(self, sos, commit_amount=1, marker='Default'): - odata = create_commits(length=commit_amount, marker=marker) - data = [(d.type_num, d.as_raw_string()) for d in odata] - f = BytesIO() - build_pack(f, data, store=sos) - sos.add_thin_pack(f.read, None) - return odata - - def test_load_packs(self): - store = {'fakerepo/objects/pack/pack-'+'1'*40+'.idx': '', - 'fakerepo/objects/pack/pack-'+'1'*40+'.pack': '', - 'fakerepo/objects/pack/pack-'+'1'*40+'.info': '', - 'fakerepo/objects/pack/pack-'+'2'*40+'.idx': '', - 'fakerepo/objects/pack/pack-'+'2'*40+'.pack': '', - 'fakerepo/objects/pack/pack-'+'2'*40+'.info': ''} - fsc = FakeSwiftConnector('fakerepo', conf=self.conf, store=store) - sos = swift.SwiftObjectStore(fsc) - packs = sos.packs - self.assertEqual(len(packs), 2) - for pack in packs: - self.assertTrue(isinstance(pack, swift.SwiftPack)) - - def test_add_thin_pack(self): - sos = swift.SwiftObjectStore(self.fsc) - self._put_pack(sos, 1, 'Default') - self.assertEqual(len(self.fsc.store), 3) - - def test_find_missing_objects(self): - commit_amount = 3 - sos = swift.SwiftObjectStore(self.fsc) - odata = self._put_pack(sos, commit_amount, 'Default') - head = odata[-1].id - i = sos.iter_shas(sos.find_missing_objects([], - [head, ], - progress=None, - get_tagged=None)) - self.assertEqual(len(i), commit_amount * 3) - shas = [d.id for d in odata] - for sha, path in i: - self.assertIn(sha.id, shas) - - def test_find_missing_objects_with_tag(self): - commit_amount = 3 - sos = swift.SwiftObjectStore(self.fsc) - odata = self._put_pack(sos, commit_amount, 'Default') - head = odata[-1].id - peeled_sha = dict([(sha.object[1], sha.id) - for sha in odata if isinstance(sha, Tag)]) - - def get_tagged(): - return peeled_sha - i = sos.iter_shas(sos.find_missing_objects([], - [head, ], - progress=None, - get_tagged=get_tagged)) - self.assertEqual(len(i), commit_amount * 4) - shas = [d.id for d in odata] - for sha, path in i: - self.assertIn(sha.id, shas) - - def test_find_missing_objects_with_common(self): - commit_amount = 3 - sos = swift.SwiftObjectStore(self.fsc) - odata = self._put_pack(sos, commit_amount, 'Default') - head = odata[-1].id - have = odata[7].id - i = sos.iter_shas(sos.find_missing_objects([have, ], - [head, ], - progress=None, - get_tagged=None)) - self.assertEqual(len(i), 3) - - def test_find_missing_objects_multiple_packs(self): - sos = swift.SwiftObjectStore(self.fsc) - commit_amount_a = 3 - odataa = self._put_pack(sos, commit_amount_a, 'Default1') - heada = odataa[-1].id - commit_amount_b = 2 - odatab = self._put_pack(sos, commit_amount_b, 'Default2') - headb = odatab[-1].id - i = sos.iter_shas(sos.find_missing_objects([], - [heada, headb], - progress=None, - get_tagged=None)) - self.assertEqual(len(self.fsc.store), 6) - self.assertEqual(len(i), - commit_amount_a * 3 + - commit_amount_b * 3) - shas = [d.id for d in odataa] - shas.extend([d.id for d in odatab]) - for sha, path in i: - self.assertIn(sha.id, shas) - - def test_add_thin_pack_ext_ref(self): - sos = swift.SwiftObjectStore(self.fsc) - odata = self._put_pack(sos, 1, 'Default1') - ref_blob_content = odata[0].as_raw_string() - ref_blob_id = odata[0].id - new_blob = Blob.from_string(ref_blob_content.replace('blob', - 'yummy blob')) - blob, tree, tag, cmt = \ - create_commit([], marker='Default2', blob=new_blob) - data = [(REF_DELTA, (ref_blob_id, blob.as_raw_string())), - (tree.type_num, tree.as_raw_string()), - (cmt.type_num, cmt.as_raw_string()), - (tag.type_num, tag.as_raw_string())] - f = BytesIO() - build_pack(f, data, store=sos) - sos.add_thin_pack(f.read, None) - self.assertEqual(len(self.fsc.store), 6) - - @skipIf(missing_libs, skipmsg) class TestSwiftRepo(TestCase): def setUp(self): super(TestSwiftRepo, self).setUp() self.conf = swift.load_conf(file=StringIO(config_file % def_config_file)) def test_init(self): store = {'fakerepo/objects/pack': ''} with patch('dulwich.contrib.swift.SwiftConnector', new_callable=create_swift_connector, store=store): swift.SwiftRepo('fakerepo', conf=self.conf) def test_init_no_data(self): with patch('dulwich.contrib.swift.SwiftConnector', new_callable=create_swift_connector): self.assertRaises(Exception, swift.SwiftRepo, 'fakerepo', self.conf) def test_init_bad_data(self): store = {'fakerepo/.git/objects/pack': ''} with patch('dulwich.contrib.swift.SwiftConnector', new_callable=create_swift_connector, store=store): self.assertRaises(Exception, swift.SwiftRepo, 'fakerepo', self.conf) def test_put_named_file(self): store = {'fakerepo/objects/pack': ''} with patch('dulwich.contrib.swift.SwiftConnector', new_callable=create_swift_connector, store=store): repo = swift.SwiftRepo('fakerepo', conf=self.conf) desc = b'Fake repo' repo._put_named_file('description', desc) self.assertEqual(repo.scon.store['fakerepo/description'], desc) def test_init_bare(self): fsc = FakeSwiftConnector('fakeroot', conf=self.conf) with patch('dulwich.contrib.swift.SwiftConnector', new_callable=create_swift_connector, store=fsc.store): swift.SwiftRepo.init_bare(fsc, conf=self.conf) self.assertIn('fakeroot/objects/pack', fsc.store) self.assertIn('fakeroot/info/refs', fsc.store) self.assertIn('fakeroot/description', fsc.store) -@skipIf(missing_libs, skipmsg) -@skipIfPY3 -class TestPackInfoLoadDump(TestCase): - - def setUp(self): - super(TestPackInfoLoadDump, self).setUp() - conf = swift.load_conf(file=StringIO(config_file % - def_config_file)) - sos = swift.SwiftObjectStore( - FakeSwiftConnector('fakerepo', conf=conf)) - commit_amount = 10 - self.commits = create_commits(length=commit_amount, marker="m") - data = [(d.type_num, d.as_raw_string()) for d in self.commits] - f = BytesIO() - fi = BytesIO() - expected = build_pack(f, data, store=sos) - entries = [(sha, ofs, checksum) for - ofs, _, _, sha, checksum in expected] - self.pack_data = PackData.from_file(file=f, size=None) - write_pack_index_v2( - fi, entries, self.pack_data.calculate_checksum()) - fi.seek(0) - self.pack_index = load_pack_index_file('', fi) - -# def test_pack_info_perf(self): -# dump_time = [] -# load_time = [] -# for i in range(0, 100): -# start = time() -# dumps = swift.pack_info_create(self.pack_data, self.pack_index) -# dump_time.append(time() - start) -# for i in range(0, 100): -# start = time() -# pack_infos = swift.load_pack_info('', file=BytesIO(dumps)) -# load_time.append(time() - start) -# print sum(dump_time) / float(len(dump_time)) -# print sum(load_time) / float(len(load_time)) - - def test_pack_info(self): - dumps = swift.pack_info_create(self.pack_data, self.pack_index) - pack_infos = swift.load_pack_info('', file=BytesIO(dumps)) - for obj in self.commits: - self.assertIn(obj.id, pack_infos) - - @skipIf(missing_libs, skipmsg) class TestSwiftInfoRefsContainer(TestCase): def setUp(self): super(TestSwiftInfoRefsContainer, self).setUp() content = ( b"22effb216e3a82f97da599b8885a6cadb488b4c5\trefs/heads/master\n" b"cca703b0e1399008b53a1a236d6b4584737649e4\trefs/heads/dev") self.store = {'fakerepo/info/refs': content} self.conf = swift.load_conf(file=StringIO(config_file % def_config_file)) self.fsc = FakeSwiftConnector('fakerepo', conf=self.conf) self.object_store = {} def test_init(self): """info/refs does not exists""" irc = swift.SwiftInfoRefsContainer(self.fsc, self.object_store) self.assertEqual(len(irc._refs), 0) self.fsc.store = self.store irc = swift.SwiftInfoRefsContainer(self.fsc, self.object_store) self.assertIn(b'refs/heads/dev', irc.allkeys()) self.assertIn(b'refs/heads/master', irc.allkeys()) def test_set_if_equals(self): self.fsc.store = self.store irc = swift.SwiftInfoRefsContainer(self.fsc, self.object_store) irc.set_if_equals(b'refs/heads/dev', b"cca703b0e1399008b53a1a236d6b4584737649e4", b'1'*40) self.assertEqual(irc[b'refs/heads/dev'], b'1'*40) def test_remove_if_equals(self): self.fsc.store = self.store irc = swift.SwiftInfoRefsContainer(self.fsc, self.object_store) irc.remove_if_equals(b'refs/heads/dev', b"cca703b0e1399008b53a1a236d6b4584737649e4") self.assertNotIn(b'refs/heads/dev', irc.allkeys()) @skipIf(missing_libs, skipmsg) class TestSwiftConnector(TestCase): def setUp(self): super(TestSwiftConnector, self).setUp() self.conf = swift.load_conf(file=StringIO(config_file % def_config_file)) with patch('geventhttpclient.HTTPClient.request', fake_auth_request_v1): self.conn = swift.SwiftConnector('fakerepo', conf=self.conf) def test_init_connector(self): self.assertEqual(self.conn.auth_ver, '1') self.assertEqual(self.conn.auth_url, 'http://127.0.0.1:8080/auth/v1.0') self.assertEqual(self.conn.user, 'test:tester') self.assertEqual(self.conn.password, 'testing') self.assertEqual(self.conn.root, 'fakerepo') self.assertEqual(self.conn.storage_url, 'http://127.0.0.1:8080/v1.0/AUTH_fakeuser') self.assertEqual(self.conn.token, '12' * 10) self.assertEqual(self.conn.http_timeout, 1) self.assertEqual(self.conn.http_pool_length, 1) self.assertEqual(self.conn.concurrency, 1) self.conf.set('swift', 'auth_ver', '2') self.conf.set('swift', 'auth_url', 'http://127.0.0.1:8080/auth/v2.0') with patch('geventhttpclient.HTTPClient.request', fake_auth_request_v2): conn = swift.SwiftConnector('fakerepo', conf=self.conf) self.assertEqual(conn.user, 'tester') self.assertEqual(conn.tenant, 'test') self.conf.set('swift', 'auth_ver', '1') self.conf.set('swift', 'auth_url', 'http://127.0.0.1:8080/auth/v1.0') with patch('geventhttpclient.HTTPClient.request', fake_auth_request_v1_error): self.assertRaises(swift.SwiftException, lambda: swift.SwiftConnector('fakerepo', conf=self.conf)) def test_root_exists(self): with patch('geventhttpclient.HTTPClient.request', lambda *args: Response()): self.assertEqual(self.conn.test_root_exists(), True) def test_root_not_exists(self): with patch('geventhttpclient.HTTPClient.request', lambda *args: Response(status=404)): self.assertEqual(self.conn.test_root_exists(), None) def test_create_root(self): with patch('dulwich.contrib.swift.SwiftConnector.test_root_exists', lambda *args: None): with patch('geventhttpclient.HTTPClient.request', lambda *args: Response()): self.assertEqual(self.conn.create_root(), None) def test_create_root_fails(self): with patch('dulwich.contrib.swift.SwiftConnector.test_root_exists', lambda *args: None): with patch('geventhttpclient.HTTPClient.request', lambda *args: Response(status=404)): self.assertRaises(swift.SwiftException, lambda: self.conn.create_root()) def test_get_container_objects(self): with patch('geventhttpclient.HTTPClient.request', lambda *args: Response(content=json_dumps( (({'name': 'a'}, {'name': 'b'}))))): self.assertEqual(len(self.conn.get_container_objects()), 2) def test_get_container_objects_fails(self): with patch('geventhttpclient.HTTPClient.request', lambda *args: Response(status=404)): self.assertEqual(self.conn.get_container_objects(), None) def test_get_object_stat(self): with patch('geventhttpclient.HTTPClient.request', lambda *args: Response(headers={'content-length': '10'})): self.assertEqual(self.conn.get_object_stat('a')['content-length'], '10') def test_get_object_stat_fails(self): with patch('geventhttpclient.HTTPClient.request', lambda *args: Response(status=404)): self.assertEqual(self.conn.get_object_stat('a'), None) def test_put_object(self): with patch('geventhttpclient.HTTPClient.request', lambda *args, **kwargs: Response()): self.assertEqual(self.conn.put_object('a', BytesIO(b'content')), None) def test_put_object_fails(self): with patch('geventhttpclient.HTTPClient.request', lambda *args, **kwargs: Response(status=400)): self.assertRaises(swift.SwiftException, lambda: self.conn.put_object( 'a', BytesIO(b'content'))) def test_get_object(self): with patch('geventhttpclient.HTTPClient.request', lambda *args, **kwargs: Response(content=b'content')): self.assertEqual(self.conn.get_object('a').read(), b'content') with patch('geventhttpclient.HTTPClient.request', lambda *args, **kwargs: Response(content=b'content')): self.assertEqual( self.conn.get_object('a', range='0-6'), b'content') def test_get_object_fails(self): with patch('geventhttpclient.HTTPClient.request', lambda *args, **kwargs: Response(status=404)): self.assertEqual(self.conn.get_object('a'), None) def test_del_object(self): with patch('geventhttpclient.HTTPClient.request', lambda *args: Response()): self.assertEqual(self.conn.del_object('a'), None) def test_del_root(self): with patch('dulwich.contrib.swift.SwiftConnector.del_object', lambda *args: None): with patch('dulwich.contrib.swift.SwiftConnector.' 'get_container_objects', lambda *args: ({'name': 'a'}, {'name': 'b'})): with patch('geventhttpclient.HTTPClient.request', lambda *args: Response()): self.assertEqual(self.conn.del_root(), None) @skipIf(missing_libs, skipmsg) class SwiftObjectStoreTests(ObjectStoreTests, TestCase): def setUp(self): TestCase.setUp(self) conf = swift.load_conf(file=StringIO(config_file % def_config_file)) fsc = FakeSwiftConnector('fakerepo', conf=conf) self.store = swift.SwiftObjectStore(fsc) diff --git a/dulwich/diff_tree.py b/dulwich/diff_tree.py index a1e8d63c..4e759f4d 100644 --- a/dulwich/diff_tree.py +++ b/dulwich/diff_tree.py @@ -1,624 +1,623 @@ # diff_tree.py -- Utilities for diffing files and trees. # Copyright (C) 2010 Google, Inc. # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """Utilities for diffing files and trees.""" import sys from collections import ( defaultdict, namedtuple, ) from io import BytesIO from itertools import chain import stat from dulwich.objects import ( S_ISGITLINK, TreeEntry, ) # TreeChange type constants. CHANGE_ADD = 'add' CHANGE_MODIFY = 'modify' CHANGE_DELETE = 'delete' CHANGE_RENAME = 'rename' CHANGE_COPY = 'copy' CHANGE_UNCHANGED = 'unchanged' RENAME_CHANGE_TYPES = (CHANGE_RENAME, CHANGE_COPY) _NULL_ENTRY = TreeEntry(None, None, None) _MAX_SCORE = 100 RENAME_THRESHOLD = 60 MAX_FILES = 200 REWRITE_THRESHOLD = None class TreeChange(namedtuple('TreeChange', ['type', 'old', 'new'])): """Named tuple a single change between two trees.""" @classmethod def add(cls, new): return cls(CHANGE_ADD, _NULL_ENTRY, new) @classmethod def delete(cls, old): return cls(CHANGE_DELETE, old, _NULL_ENTRY) def _tree_entries(path, tree): result = [] if not tree: return result for entry in tree.iteritems(name_order=True): result.append(entry.in_path(path)) return result def _merge_entries(path, tree1, tree2): """Merge the entries of two trees. Args: path: A path to prepend to all tree entry names. tree1: The first Tree object to iterate, or None. tree2: The second Tree object to iterate, or None. Returns: A list of pairs of TreeEntry objects for each pair of entries in the trees. If an entry exists in one tree but not the other, the other entry will have all attributes set to None. If neither entry's path is None, they are guaranteed to match. """ entries1 = _tree_entries(path, tree1) entries2 = _tree_entries(path, tree2) i1 = i2 = 0 len1 = len(entries1) len2 = len(entries2) result = [] while i1 < len1 and i2 < len2: entry1 = entries1[i1] entry2 = entries2[i2] if entry1.path < entry2.path: result.append((entry1, _NULL_ENTRY)) i1 += 1 elif entry1.path > entry2.path: result.append((_NULL_ENTRY, entry2)) i2 += 1 else: result.append((entry1, entry2)) i1 += 1 i2 += 1 for i in range(i1, len1): result.append((entries1[i], _NULL_ENTRY)) for i in range(i2, len2): result.append((_NULL_ENTRY, entries2[i])) return result def _is_tree(entry): mode = entry.mode if mode is None: return False return stat.S_ISDIR(mode) def walk_trees(store, tree1_id, tree2_id, prune_identical=False): """Recursively walk all the entries of two trees. Iteration is depth-first pre-order, as in e.g. os.walk. Args: store: An ObjectStore for looking up objects. tree1_id: The SHA of the first Tree object to iterate, or None. tree2_id: The SHA of the second Tree object to iterate, or None. param prune_identical: If True, identical subtrees will not be walked. Returns: Iterator over Pairs of TreeEntry objects for each pair of entries in the trees and their subtrees recursively. If an entry exists in one tree but not the other, the other entry will have all attributes set to None. If neither entry's path is None, they are guaranteed to match. """ # This could be fairly easily generalized to >2 trees if we find a use # case. mode1 = tree1_id and stat.S_IFDIR or None mode2 = tree2_id and stat.S_IFDIR or None todo = [(TreeEntry(b'', mode1, tree1_id), TreeEntry(b'', mode2, tree2_id))] while todo: entry1, entry2 = todo.pop() is_tree1 = _is_tree(entry1) is_tree2 = _is_tree(entry2) if prune_identical and is_tree1 and is_tree2 and entry1 == entry2: continue tree1 = is_tree1 and store[entry1.sha] or None tree2 = is_tree2 and store[entry2.sha] or None path = entry1.path or entry2.path todo.extend(reversed(_merge_entries(path, tree1, tree2))) yield entry1, entry2 def _skip_tree(entry, include_trees): if entry.mode is None or (not include_trees and stat.S_ISDIR(entry.mode)): return _NULL_ENTRY return entry def tree_changes(store, tree1_id, tree2_id, want_unchanged=False, rename_detector=None, include_trees=False, change_type_same=False): """Find the differences between the contents of two trees. Args: store: An ObjectStore for looking up objects. tree1_id: The SHA of the source tree. tree2_id: The SHA of the target tree. want_unchanged: If True, include TreeChanges for unmodified entries as well. include_trees: Whether to include trees rename_detector: RenameDetector object for detecting renames. change_type_same: Whether to report change types in the same entry or as delete+add. Returns: Iterator over TreeChange instances for each change between the source and target tree. """ if (rename_detector is not None and tree1_id is not None and tree2_id is not None): for change in rename_detector.changes_with_renames( tree1_id, tree2_id, want_unchanged=want_unchanged, include_trees=include_trees): yield change return entries = walk_trees(store, tree1_id, tree2_id, prune_identical=(not want_unchanged)) for entry1, entry2 in entries: if entry1 == entry2 and not want_unchanged: continue # Treat entries for trees as missing. entry1 = _skip_tree(entry1, include_trees) entry2 = _skip_tree(entry2, include_trees) if entry1 != _NULL_ENTRY and entry2 != _NULL_ENTRY: if (stat.S_IFMT(entry1.mode) != stat.S_IFMT(entry2.mode) and not change_type_same): # File type changed: report as delete/add. yield TreeChange.delete(entry1) entry1 = _NULL_ENTRY change_type = CHANGE_ADD elif entry1 == entry2: change_type = CHANGE_UNCHANGED else: change_type = CHANGE_MODIFY elif entry1 != _NULL_ENTRY: change_type = CHANGE_DELETE elif entry2 != _NULL_ENTRY: change_type = CHANGE_ADD else: # Both were None because at least one was a tree. continue yield TreeChange(change_type, entry1, entry2) def _all_eq(seq, key, value): for e in seq: if key(e) != value: return False return True def _all_same(seq, key): return _all_eq(seq[1:], key, key(seq[0])) def tree_changes_for_merge(store, parent_tree_ids, tree_id, rename_detector=None): """Get the tree changes for a merge tree relative to all its parents. Args: store: An ObjectStore for looking up objects. parent_tree_ids: An iterable of the SHAs of the parent trees. tree_id: The SHA of the merge tree. rename_detector: RenameDetector object for detecting renames. Returns: Iterator over lists of TreeChange objects, one per conflicted path in the merge. Each list contains one element per parent, with the TreeChange for that path relative to that parent. An element may be None if it never existed in one parent and was deleted in two others. A path is only included in the output if it is a conflict, i.e. its SHA in the merge tree is not found in any of the parents, or in the case of deletes, if not all of the old SHAs match. """ all_parent_changes = [tree_changes(store, t, tree_id, rename_detector=rename_detector) for t in parent_tree_ids] num_parents = len(parent_tree_ids) changes_by_path = defaultdict(lambda: [None] * num_parents) # Organize by path. for i, parent_changes in enumerate(all_parent_changes): for change in parent_changes: if change.type == CHANGE_DELETE: path = change.old.path else: path = change.new.path changes_by_path[path][i] = change def old_sha(c): return c.old.sha def change_type(c): return c.type # Yield only conflicting changes. for _, changes in sorted(changes_by_path.items()): assert len(changes) == num_parents have = [c for c in changes if c is not None] if _all_eq(have, change_type, CHANGE_DELETE): if not _all_same(have, old_sha): yield changes elif not _all_same(have, change_type): yield changes elif None not in changes: # If no change was found relative to one parent, that means the SHA # must have matched the SHA in that parent, so it is not a # conflict. yield changes _BLOCK_SIZE = 64 def _count_blocks(obj): """Count the blocks in an object. Splits the data into blocks either on lines or <=64-byte chunks of lines. Args: obj: The object to count blocks for. Returns: A dict of block hashcode -> total bytes occurring. """ block_counts = defaultdict(int) block = BytesIO() n = 0 # Cache attrs as locals to avoid expensive lookups in the inner loop. block_write = block.write block_seek = block.seek block_truncate = block.truncate block_getvalue = block.getvalue for c in chain(*obj.as_raw_chunks()): - if sys.version_info[0] == 3: - c = c.to_bytes(1, 'big') + c = c.to_bytes(1, 'big') block_write(c) n += 1 if c == b'\n' or n == _BLOCK_SIZE: value = block_getvalue() block_counts[hash(value)] += len(value) block_seek(0) block_truncate() n = 0 if n > 0: last_block = block_getvalue() block_counts[hash(last_block)] += len(last_block) return block_counts def _common_bytes(blocks1, blocks2): """Count the number of common bytes in two block count dicts. Args: block1: The first dict of block hashcode -> total bytes. block2: The second dict of block hashcode -> total bytes. Returns: The number of bytes in common between blocks1 and blocks2. This is only approximate due to possible hash collisions. """ # Iterate over the smaller of the two dicts, since this is symmetrical. if len(blocks1) > len(blocks2): blocks1, blocks2 = blocks2, blocks1 score = 0 for block, count1 in blocks1.items(): count2 = blocks2.get(block) if count2: score += min(count1, count2) return score def _similarity_score(obj1, obj2, block_cache=None): """Compute a similarity score for two objects. Args: obj1: The first object to score. obj2: The second object to score. block_cache: An optional dict of SHA to block counts to cache results between calls. Returns: The similarity score between the two objects, defined as the number of bytes in common between the two objects divided by the maximum size, scaled to the range 0-100. """ if block_cache is None: block_cache = {} if obj1.id not in block_cache: block_cache[obj1.id] = _count_blocks(obj1) if obj2.id not in block_cache: block_cache[obj2.id] = _count_blocks(obj2) common_bytes = _common_bytes(block_cache[obj1.id], block_cache[obj2.id]) max_size = max(obj1.raw_length(), obj2.raw_length()) if not max_size: return _MAX_SCORE return int(float(common_bytes) * _MAX_SCORE / max_size) def _tree_change_key(entry): # Sort by old path then new path. If only one exists, use it for both keys. path1 = entry.old.path path2 = entry.new.path if path1 is None: path1 = path2 if path2 is None: path2 = path1 return (path1, path2) class RenameDetector(object): """Object for handling rename detection between two trees.""" def __init__(self, store, rename_threshold=RENAME_THRESHOLD, max_files=MAX_FILES, rewrite_threshold=REWRITE_THRESHOLD, find_copies_harder=False): """Initialize the rename detector. Args: store: An ObjectStore for looking up objects. rename_threshold: The threshold similarity score for considering an add/delete pair to be a rename/copy; see _similarity_score. max_files: The maximum number of adds and deletes to consider, or None for no limit. The detector is guaranteed to compare no more than max_files ** 2 add/delete pairs. This limit is provided because rename detection can be quadratic in the project size. If the limit is exceeded, no content rename detection is attempted. rewrite_threshold: The threshold similarity score below which a modify should be considered a delete/add, or None to not break modifies; see _similarity_score. find_copies_harder: If True, consider unmodified files when detecting copies. """ self._store = store self._rename_threshold = rename_threshold self._rewrite_threshold = rewrite_threshold self._max_files = max_files self._find_copies_harder = find_copies_harder self._want_unchanged = False def _reset(self): self._adds = [] self._deletes = [] self._changes = [] def _should_split(self, change): if (self._rewrite_threshold is None or change.type != CHANGE_MODIFY or change.old.sha == change.new.sha): return False old_obj = self._store[change.old.sha] new_obj = self._store[change.new.sha] return _similarity_score(old_obj, new_obj) < self._rewrite_threshold def _add_change(self, change): if change.type == CHANGE_ADD: self._adds.append(change) elif change.type == CHANGE_DELETE: self._deletes.append(change) elif self._should_split(change): self._deletes.append(TreeChange.delete(change.old)) self._adds.append(TreeChange.add(change.new)) elif ((self._find_copies_harder and change.type == CHANGE_UNCHANGED) or change.type == CHANGE_MODIFY): # Treat all modifies as potential deletes for rename detection, # but don't split them (to avoid spurious renames). Setting # find_copies_harder means we treat unchanged the same as # modified. self._deletes.append(change) else: self._changes.append(change) def _collect_changes(self, tree1_id, tree2_id): want_unchanged = self._find_copies_harder or self._want_unchanged for change in tree_changes(self._store, tree1_id, tree2_id, want_unchanged=want_unchanged, include_trees=self._include_trees): self._add_change(change) def _prune(self, add_paths, delete_paths): self._adds = [a for a in self._adds if a.new.path not in add_paths] self._deletes = [d for d in self._deletes if d.old.path not in delete_paths] def _find_exact_renames(self): add_map = defaultdict(list) for add in self._adds: add_map[add.new.sha].append(add.new) delete_map = defaultdict(list) for delete in self._deletes: # Keep track of whether the delete was actually marked as a delete. # If not, it needs to be marked as a copy. is_delete = delete.type == CHANGE_DELETE delete_map[delete.old.sha].append((delete.old, is_delete)) add_paths = set() delete_paths = set() for sha, sha_deletes in delete_map.items(): sha_adds = add_map[sha] for (old, is_delete), new in zip(sha_deletes, sha_adds): if stat.S_IFMT(old.mode) != stat.S_IFMT(new.mode): continue if is_delete: delete_paths.add(old.path) add_paths.add(new.path) new_type = is_delete and CHANGE_RENAME or CHANGE_COPY self._changes.append(TreeChange(new_type, old, new)) num_extra_adds = len(sha_adds) - len(sha_deletes) # TODO(dborowitz): Less arbitrary way of dealing with extra copies. old = sha_deletes[0][0] if num_extra_adds > 0: for new in sha_adds[-num_extra_adds:]: add_paths.add(new.path) self._changes.append(TreeChange(CHANGE_COPY, old, new)) self._prune(add_paths, delete_paths) def _should_find_content_renames(self): return len(self._adds) * len(self._deletes) <= self._max_files ** 2 def _rename_type(self, check_paths, delete, add): if check_paths and delete.old.path == add.new.path: # If the paths match, this must be a split modify, so make sure it # comes out as a modify. return CHANGE_MODIFY elif delete.type != CHANGE_DELETE: # If it's in deletes but not marked as a delete, it must have been # added due to find_copies_harder, and needs to be marked as a # copy. return CHANGE_COPY return CHANGE_RENAME def _find_content_rename_candidates(self): candidates = self._candidates = [] # TODO: Optimizations: # - Compare object sizes before counting blocks. # - Skip if delete's S_IFMT differs from all adds. # - Skip if adds or deletes is empty. # Match C git's behavior of not attempting to find content renames if # the matrix size exceeds the threshold. if not self._should_find_content_renames(): return block_cache = {} check_paths = self._rename_threshold is not None for delete in self._deletes: if S_ISGITLINK(delete.old.mode): continue # Git links don't exist in this repo. old_sha = delete.old.sha old_obj = self._store[old_sha] block_cache[old_sha] = _count_blocks(old_obj) for add in self._adds: if stat.S_IFMT(delete.old.mode) != stat.S_IFMT(add.new.mode): continue new_obj = self._store[add.new.sha] score = _similarity_score(old_obj, new_obj, block_cache=block_cache) if score > self._rename_threshold: new_type = self._rename_type(check_paths, delete, add) rename = TreeChange(new_type, delete.old, add.new) candidates.append((-score, rename)) def _choose_content_renames(self): # Sort scores from highest to lowest, but keep names in ascending # order. self._candidates.sort() delete_paths = set() add_paths = set() for _, change in self._candidates: new_path = change.new.path if new_path in add_paths: continue old_path = change.old.path orig_type = change.type if old_path in delete_paths: change = TreeChange(CHANGE_COPY, change.old, change.new) # If the candidate was originally a copy, that means it came from a # modified or unchanged path, so we don't want to prune it. if orig_type != CHANGE_COPY: delete_paths.add(old_path) add_paths.add(new_path) self._changes.append(change) self._prune(add_paths, delete_paths) def _join_modifies(self): if self._rewrite_threshold is None: return modifies = {} delete_map = dict((d.old.path, d) for d in self._deletes) for add in self._adds: path = add.new.path delete = delete_map.get(path) if (delete is not None and stat.S_IFMT(delete.old.mode) == stat.S_IFMT(add.new.mode)): modifies[path] = TreeChange(CHANGE_MODIFY, delete.old, add.new) self._adds = [a for a in self._adds if a.new.path not in modifies] self._deletes = [a for a in self._deletes if a.new.path not in modifies] self._changes += modifies.values() def _sorted_changes(self): result = [] result.extend(self._adds) result.extend(self._deletes) result.extend(self._changes) result.sort(key=_tree_change_key) return result def _prune_unchanged(self): if self._want_unchanged: return self._deletes = [ d for d in self._deletes if d.type != CHANGE_UNCHANGED] def changes_with_renames(self, tree1_id, tree2_id, want_unchanged=False, include_trees=False): """Iterate TreeChanges between two tree SHAs, with rename detection.""" self._reset() self._want_unchanged = want_unchanged self._include_trees = include_trees self._collect_changes(tree1_id, tree2_id) self._find_exact_renames() self._find_content_rename_candidates() self._choose_content_renames() self._join_modifies() self._prune_unchanged() return self._sorted_changes() # Hold on to the pure-python implementations for testing. _is_tree_py = _is_tree _merge_entries_py = _merge_entries _count_blocks_py = _count_blocks try: # Try to import C versions from dulwich._diff_tree import _is_tree, _merge_entries, _count_blocks except ImportError: pass diff --git a/dulwich/fastexport.py b/dulwich/fastexport.py index 89454164..89ae5932 100644 --- a/dulwich/fastexport.py +++ b/dulwich/fastexport.py @@ -1,249 +1,245 @@ # __init__.py -- Fast export/import functionality # Copyright (C) 2010-2013 Jelmer Vernooij # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """Fast export/import functionality.""" import sys from dulwich.index import ( commit_tree, ) from dulwich.objects import ( Blob, Commit, Tag, ZERO_SHA, ) -from fastimport import __version__ as fastimport_version -if (fastimport_version <= (0, 9, 5) and - sys.version_info[0] == 3 and sys.version_info[1] < 5): - raise ImportError("Older versions of fastimport don't support python3<3.5") from fastimport import ( # noqa: E402 commands, errors as fastimport_errors, parser, processor, ) import stat # noqa: E402 def split_email(text): (name, email) = text.rsplit(b" <", 1) return (name, email.rstrip(b">")) class GitFastExporter(object): """Generate a fast-export output stream for Git objects.""" def __init__(self, outf, store): self.outf = outf self.store = store self.markers = {} self._marker_idx = 0 def print_cmd(self, cmd): self.outf.write(getattr(cmd, "__bytes__", cmd.__repr__)() + b"\n") def _allocate_marker(self): self._marker_idx += 1 return ("%d" % (self._marker_idx,)).encode('ascii') def _export_blob(self, blob): marker = self._allocate_marker() self.markers[marker] = blob.id return (commands.BlobCommand(marker, blob.data), marker) def emit_blob(self, blob): (cmd, marker) = self._export_blob(blob) self.print_cmd(cmd) return marker def _iter_files(self, base_tree, new_tree): for ((old_path, new_path), (old_mode, new_mode), (old_hexsha, new_hexsha)) in \ self.store.tree_changes(base_tree, new_tree): if new_path is None: yield commands.FileDeleteCommand(old_path) continue if not stat.S_ISDIR(new_mode): blob = self.store[new_hexsha] marker = self.emit_blob(blob) if old_path != new_path and old_path is not None: yield commands.FileRenameCommand(old_path, new_path) if old_mode != new_mode or old_hexsha != new_hexsha: prefixed_marker = b':' + marker yield commands.FileModifyCommand( new_path, new_mode, prefixed_marker, None ) def _export_commit(self, commit, ref, base_tree=None): file_cmds = list(self._iter_files(base_tree, commit.tree)) marker = self._allocate_marker() if commit.parents: from_ = commit.parents[0] merges = commit.parents[1:] else: from_ = None merges = [] author, author_email = split_email(commit.author) committer, committer_email = split_email(commit.committer) cmd = commands.CommitCommand( ref, marker, (author, author_email, commit.author_time, commit.author_timezone), (committer, committer_email, commit.commit_time, commit.commit_timezone), commit.message, from_, merges, file_cmds) return (cmd, marker) def emit_commit(self, commit, ref, base_tree=None): cmd, marker = self._export_commit(commit, ref, base_tree) self.print_cmd(cmd) return marker class GitImportProcessor(processor.ImportProcessor): """An import processor that imports into a Git repository using Dulwich. """ # FIXME: Batch creation of objects? def __init__(self, repo, params=None, verbose=False, outf=None): processor.ImportProcessor.__init__(self, params, verbose) self.repo = repo self.last_commit = ZERO_SHA self.markers = {} self._contents = {} def lookup_object(self, objectish): if objectish.startswith(b":"): return self.markers[objectish[1:]] return objectish def import_stream(self, stream): p = parser.ImportParser(stream) self.process(p.iter_commands) return self.markers def blob_handler(self, cmd): """Process a BlobCommand.""" blob = Blob.from_string(cmd.data) self.repo.object_store.add_object(blob) if cmd.mark: self.markers[cmd.mark] = blob.id def checkpoint_handler(self, cmd): """Process a CheckpointCommand.""" pass def commit_handler(self, cmd): """Process a CommitCommand.""" commit = Commit() if cmd.author is not None: author = cmd.author else: author = cmd.committer (author_name, author_email, author_timestamp, author_timezone) = author (committer_name, committer_email, commit_timestamp, commit_timezone) = cmd.committer commit.author = author_name + b" <" + author_email + b">" commit.author_timezone = author_timezone commit.author_time = int(author_timestamp) commit.committer = committer_name + b" <" + committer_email + b">" commit.commit_timezone = commit_timezone commit.commit_time = int(commit_timestamp) commit.message = cmd.message commit.parents = [] if cmd.from_: cmd.from_ = self.lookup_object(cmd.from_) self._reset_base(cmd.from_) for filecmd in cmd.iter_files(): if filecmd.name == b"filemodify": if filecmd.data is not None: blob = Blob.from_string(filecmd.data) self.repo.object_store.add(blob) blob_id = blob.id else: blob_id = self.lookup_object(filecmd.dataref) self._contents[filecmd.path] = (filecmd.mode, blob_id) elif filecmd.name == b"filedelete": del self._contents[filecmd.path] elif filecmd.name == b"filecopy": self._contents[filecmd.dest_path] = self._contents[ filecmd.src_path] elif filecmd.name == b"filerename": self._contents[filecmd.new_path] = self._contents[ filecmd.old_path] del self._contents[filecmd.old_path] elif filecmd.name == b"filedeleteall": self._contents = {} else: raise Exception("Command %s not supported" % filecmd.name) commit.tree = commit_tree( self.repo.object_store, ((path, hexsha, mode) for (path, (mode, hexsha)) in self._contents.items())) if self.last_commit != ZERO_SHA: commit.parents.append(self.last_commit) for merge in cmd.merges: commit.parents.append(self.lookup_object(merge)) self.repo.object_store.add_object(commit) self.repo[cmd.ref] = commit.id self.last_commit = commit.id if cmd.mark: self.markers[cmd.mark] = commit.id def progress_handler(self, cmd): """Process a ProgressCommand.""" pass def _reset_base(self, commit_id): if self.last_commit == commit_id: return self._contents = {} self.last_commit = commit_id if commit_id != ZERO_SHA: tree_id = self.repo[commit_id].tree for (path, mode, hexsha) in ( self.repo.object_store.iter_tree_contents(tree_id)): self._contents[path] = (mode, hexsha) def reset_handler(self, cmd): """Process a ResetCommand.""" if cmd.from_ is None: from_ = ZERO_SHA else: from_ = self.lookup_object(cmd.from_) self._reset_base(from_) self.repo.refs[cmd.ref] = from_ def tag_handler(self, cmd): """Process a TagCommand.""" tag = Tag() tag.tagger = cmd.tagger tag.message = cmd.message tag.name = cmd.tag self.repo.add_object(tag) self.repo.refs["refs/tags/" + tag.name] = tag.id def feature_handler(self, cmd): """Process a FeatureCommand.""" raise fastimport_errors.UnknownFeature(cmd.feature_name) diff --git a/dulwich/hooks.py b/dulwich/hooks.py index 32f98844..4c586844 100644 --- a/dulwich/hooks.py +++ b/dulwich/hooks.py @@ -1,202 +1,197 @@ # hooks.py -- for dealing with git hooks # Copyright (C) 2012-2013 Jelmer Vernooij and others. # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """Access to hooks.""" import os import subprocess import sys import tempfile from dulwich.errors import ( HookError, ) class Hook(object): """Generic hook object.""" def execute(self, *args): """Execute the hook with the given args Args: args: argument list to hook Raises: HookError: hook execution failure Returns: a hook may return a useful value """ raise NotImplementedError(self.execute) class ShellHook(Hook): """Hook by executable file Implements standard githooks(5) [0]: [0] http://www.kernel.org/pub/software/scm/git/docs/githooks.html """ def __init__(self, name, path, numparam, pre_exec_callback=None, post_exec_callback=None, cwd=None): """Setup shell hook definition Args: name: name of hook for error messages path: absolute path to executable file numparam: number of requirements parameters pre_exec_callback: closure for setup before execution Defaults to None. Takes in the variable argument list from the execute functions and returns a modified argument list for the shell hook. post_exec_callback: closure for cleanup after execution Defaults to None. Takes in a boolean for hook success and the modified argument list and returns the final hook return value if applicable cwd: working directory to switch to when executing the hook """ self.name = name self.filepath = path self.numparam = numparam self.pre_exec_callback = pre_exec_callback self.post_exec_callback = post_exec_callback self.cwd = cwd - if sys.version_info[0] == 2 and sys.platform == 'win32': - # Python 2 on windows does not support unicode file paths - # http://bugs.python.org/issue1759845 - self.filepath = self.filepath.encode(sys.getfilesystemencoding()) - def execute(self, *args): """Execute the hook with given args""" if len(args) != self.numparam: raise HookError("Hook %s executed with wrong number of args. \ Expected %d. Saw %d. args: %s" % (self.name, self.numparam, len(args), args)) if (self.pre_exec_callback is not None): args = self.pre_exec_callback(*args) try: ret = subprocess.call([self.filepath] + list(args), cwd=self.cwd) if ret != 0: if (self.post_exec_callback is not None): self.post_exec_callback(0, *args) raise HookError("Hook %s exited with non-zero status" % (self.name)) if (self.post_exec_callback is not None): return self.post_exec_callback(1, *args) except OSError: # no file. silent failure. if (self.post_exec_callback is not None): self.post_exec_callback(0, *args) class PreCommitShellHook(ShellHook): """pre-commit shell hook""" def __init__(self, controldir): filepath = os.path.join(controldir, 'hooks', 'pre-commit') ShellHook.__init__(self, 'pre-commit', filepath, 0, cwd=controldir) class PostCommitShellHook(ShellHook): """post-commit shell hook""" def __init__(self, controldir): filepath = os.path.join(controldir, 'hooks', 'post-commit') ShellHook.__init__(self, 'post-commit', filepath, 0, cwd=controldir) class CommitMsgShellHook(ShellHook): """commit-msg shell hook Args: args[0]: commit message Returns: new commit message or None """ def __init__(self, controldir): filepath = os.path.join(controldir, 'hooks', 'commit-msg') def prepare_msg(*args): (fd, path) = tempfile.mkstemp() with os.fdopen(fd, 'wb') as f: f.write(args[0]) return (path,) def clean_msg(success, *args): if success: with open(args[0], 'rb') as f: new_msg = f.read() os.unlink(args[0]) return new_msg os.unlink(args[0]) ShellHook.__init__(self, 'commit-msg', filepath, 1, prepare_msg, clean_msg, controldir) class PostReceiveShellHook(ShellHook): """post-receive shell hook""" def __init__(self, controldir): self.controldir = controldir filepath = os.path.join(controldir, 'hooks', 'post-receive') ShellHook.__init__(self, 'post-receive', filepath, 0) def execute(self, client_refs): # do nothing if the script doesn't exist if not os.path.exists(self.filepath): return None try: env = os.environ.copy() env['GIT_DIR'] = self.controldir p = subprocess.Popen( self.filepath, stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE, env=env ) # client_refs is a list of (oldsha, newsha, ref) in_data = '\n'.join([' '.join(ref) for ref in client_refs]) out_data, err_data = p.communicate(in_data) if (p.returncode != 0) or err_data: err_fmt = "post-receive exit code: %d\n" \ + "stdout:\n%s\nstderr:\n%s" err_msg = err_fmt % (p.returncode, out_data, err_data) raise HookError(err_msg) return out_data except OSError as err: raise HookError(repr(err)) diff --git a/dulwich/index.py b/dulwich/index.py index f99e016b..f8df3509 100644 --- a/dulwich/index.py +++ b/dulwich/index.py @@ -1,848 +1,848 @@ # index.py -- File parser/writer for the git index file # Copyright (C) 2008-2013 Jelmer Vernooij # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """Parser for the git index file format.""" import collections import errno import os import stat import struct import sys from dulwich.file import GitFile from dulwich.objects import ( Blob, S_IFGITLINK, S_ISGITLINK, Tree, hex_to_sha, sha_to_hex, ) from dulwich.pack import ( SHA1Reader, SHA1Writer, ) IndexEntry = collections.namedtuple( 'IndexEntry', [ 'ctime', 'mtime', 'dev', 'ino', 'mode', 'uid', 'gid', 'size', 'sha', 'flags']) FLAG_STAGEMASK = 0x3000 FLAG_VALID = 0x8000 FLAG_EXTENDED = 0x4000 def pathsplit(path): """Split a /-delimited path into a directory part and a basename. Args: path: The path to split. Returns: Tuple with directory name and basename """ try: (dirname, basename) = path.rsplit(b"/", 1) except ValueError: return (b"", path) else: return (dirname, basename) def pathjoin(*args): """Join a /-delimited path. """ return b"/".join([p for p in args if p]) def read_cache_time(f): """Read a cache time. Args: f: File-like object to read from Returns: Tuple with seconds and nanoseconds """ return struct.unpack(">LL", f.read(8)) def write_cache_time(f, t): """Write a cache time. Args: f: File-like object to write to t: Time to write (as int, float or tuple with secs and nsecs) """ if isinstance(t, int): t = (t, 0) elif isinstance(t, float): (secs, nsecs) = divmod(t, 1.0) t = (int(secs), int(nsecs * 1000000000)) elif not isinstance(t, tuple): raise TypeError(t) f.write(struct.pack(">LL", *t)) def read_cache_entry(f): """Read an entry from a cache file. Args: f: File-like object to read from Returns: tuple with: device, inode, mode, uid, gid, size, sha, flags """ beginoffset = f.tell() ctime = read_cache_time(f) mtime = read_cache_time(f) (dev, ino, mode, uid, gid, size, sha, flags, ) = \ struct.unpack(">LLLLLL20sH", f.read(20 + 4 * 6 + 2)) name = f.read((flags & 0x0fff)) # Padding: real_size = ((f.tell() - beginoffset + 8) & ~7) f.read((beginoffset + real_size) - f.tell()) return (name, ctime, mtime, dev, ino, mode, uid, gid, size, sha_to_hex(sha), flags & ~0x0fff) def write_cache_entry(f, entry): """Write an index entry to a file. Args: f: File object entry: Entry to write, tuple with: (name, ctime, mtime, dev, ino, mode, uid, gid, size, sha, flags) """ beginoffset = f.tell() (name, ctime, mtime, dev, ino, mode, uid, gid, size, sha, flags) = entry write_cache_time(f, ctime) write_cache_time(f, mtime) flags = len(name) | (flags & ~0x0fff) f.write(struct.pack( b'>LLLLLL20sH', dev & 0xFFFFFFFF, ino & 0xFFFFFFFF, mode, uid, gid, size, hex_to_sha(sha), flags)) f.write(name) real_size = ((f.tell() - beginoffset + 8) & ~7) f.write(b'\0' * ((beginoffset + real_size) - f.tell())) def read_index(f): """Read an index file, yielding the individual entries.""" header = f.read(4) if header != b'DIRC': raise AssertionError("Invalid index file header: %r" % header) (version, num_entries) = struct.unpack(b'>LL', f.read(4 * 2)) assert version in (1, 2) for i in range(num_entries): yield read_cache_entry(f) def read_index_dict(f): """Read an index file and return it as a dictionary. Args: f: File object to read from """ ret = {} for x in read_index(f): ret[x[0]] = IndexEntry(*x[1:]) return ret def write_index(f, entries): """Write an index file. Args: f: File-like object to write to entries: Iterable over the entries to write """ f.write(b'DIRC') f.write(struct.pack(b'>LL', 2, len(entries))) for x in entries: write_cache_entry(f, x) def write_index_dict(f, entries): """Write an index file based on the contents of a dictionary. """ entries_list = [] for name in sorted(entries): entries_list.append((name,) + tuple(entries[name])) write_index(f, entries_list) def cleanup_mode(mode): """Cleanup a mode value. This will return a mode that can be stored in a tree object. Args: mode: Mode to clean up. """ if stat.S_ISLNK(mode): return stat.S_IFLNK elif stat.S_ISDIR(mode): return stat.S_IFDIR elif S_ISGITLINK(mode): return S_IFGITLINK ret = stat.S_IFREG | 0o644 if mode & 0o100: ret |= 0o111 return ret class Index(object): """A Git Index file.""" def __init__(self, filename): """Open an index file. Args: filename: Path to the index file """ self._filename = filename self.clear() self.read() @property def path(self): return self._filename def __repr__(self): return "%s(%r)" % (self.__class__.__name__, self._filename) def write(self): """Write current contents of index to disk.""" f = GitFile(self._filename, 'wb') try: f = SHA1Writer(f) write_index_dict(f, self._byname) finally: f.close() def read(self): """Read current contents of index from disk.""" if not os.path.exists(self._filename): return f = GitFile(self._filename, 'rb') try: f = SHA1Reader(f) for x in read_index(f): self[x[0]] = IndexEntry(*x[1:]) # FIXME: Additional data? f.read(os.path.getsize(self._filename)-f.tell()-20) f.check_sha() finally: f.close() def __len__(self): """Number of entries in this index file.""" return len(self._byname) def __getitem__(self, name): """Retrieve entry by relative path. Returns: tuple with (ctime, mtime, dev, ino, mode, uid, gid, size, sha, flags) """ return self._byname[name] def __iter__(self): """Iterate over the paths in this index.""" return iter(self._byname) def get_sha1(self, path): """Return the (git object) SHA1 for the object at a path.""" return self[path].sha def get_mode(self, path): """Return the POSIX file mode for the object at a path.""" return self[path].mode def iterobjects(self): """Iterate over path, sha, mode tuples for use with commit_tree.""" for path in self: entry = self[path] yield path, entry.sha, cleanup_mode(entry.mode) def iterblobs(self): import warnings warnings.warn('Use iterobjects() instead.', PendingDeprecationWarning) return self.iterobjects() def clear(self): """Remove all contents from this index.""" self._byname = {} def __setitem__(self, name, x): assert isinstance(name, bytes) assert len(x) == 10 # Remove the old entry if any self._byname[name] = IndexEntry(*x) def __delitem__(self, name): assert isinstance(name, bytes) del self._byname[name] def iteritems(self): return self._byname.items() def items(self): return self._byname.items() def update(self, entries): for name, value in entries.items(): self[name] = value def changes_from_tree(self, object_store, tree, want_unchanged=False): """Find the differences between the contents of this index and a tree. Args: object_store: Object store to use for retrieving tree contents tree: SHA1 of the root tree want_unchanged: Whether unchanged files should be reported Returns: Iterator over tuples with (oldpath, newpath), (oldmode, newmode), (oldsha, newsha) """ def lookup_entry(path): entry = self[path] return entry.sha, cleanup_mode(entry.mode) for (name, mode, sha) in changes_from_tree( self._byname.keys(), lookup_entry, object_store, tree, want_unchanged=want_unchanged): yield (name, mode, sha) def commit(self, object_store): """Create a new tree from an index. Args: object_store: Object store to save the tree in Returns: Root tree SHA """ return commit_tree(object_store, self.iterobjects()) def commit_tree(object_store, blobs): """Commit a new tree. Args: object_store: Object store to add trees to blobs: Iterable over blob path, sha, mode entries Returns: SHA1 of the created tree. """ trees = {b'': {}} def add_tree(path): if path in trees: return trees[path] dirname, basename = pathsplit(path) t = add_tree(dirname) assert isinstance(basename, bytes) newtree = {} t[basename] = newtree trees[path] = newtree return newtree for path, sha, mode in blobs: tree_path, basename = pathsplit(path) tree = add_tree(tree_path) tree[basename] = (mode, sha) def build_tree(path): tree = Tree() for basename, entry in trees[path].items(): if isinstance(entry, dict): mode = stat.S_IFDIR sha = build_tree(pathjoin(path, basename)) else: (mode, sha) = entry tree.add(basename, mode, sha) object_store.add_object(tree) return tree.id return build_tree(b'') def commit_index(object_store, index): """Create a new tree from an index. Args: object_store: Object store to save the tree in index: Index file Note: This function is deprecated, use index.commit() instead. Returns: Root tree sha. """ return commit_tree(object_store, index.iterobjects()) def changes_from_tree(names, lookup_entry, object_store, tree, want_unchanged=False): """Find the differences between the contents of a tree and a working copy. Args: names: Iterable of names in the working copy lookup_entry: Function to lookup an entry in the working copy object_store: Object store to use for retrieving tree contents tree: SHA1 of the root tree, or None for an empty tree want_unchanged: Whether unchanged files should be reported Returns: Iterator over tuples with (oldpath, newpath), (oldmode, newmode), (oldsha, newsha) """ # TODO(jelmer): Support a include_trees option other_names = set(names) if tree is not None: for (name, mode, sha) in object_store.iter_tree_contents(tree): try: (other_sha, other_mode) = lookup_entry(name) except KeyError: # Was removed yield ((name, None), (mode, None), (sha, None)) else: other_names.remove(name) if (want_unchanged or other_sha != sha or other_mode != mode): yield ((name, name), (mode, other_mode), (sha, other_sha)) # Mention added files for name in other_names: try: (other_sha, other_mode) = lookup_entry(name) except KeyError: pass else: yield ((None, name), (None, other_mode), (None, other_sha)) def index_entry_from_stat(stat_val, hex_sha, flags, mode=None): """Create a new index entry from a stat value. Args: stat_val: POSIX stat_result instance hex_sha: Hex sha of the object flags: Index flags """ if mode is None: mode = cleanup_mode(stat_val.st_mode) return IndexEntry( stat_val.st_ctime, stat_val.st_mtime, stat_val.st_dev, stat_val.st_ino, mode, stat_val.st_uid, stat_val.st_gid, stat_val.st_size, hex_sha, flags) def build_file_from_blob(blob, mode, target_path, honor_filemode=True): """Build a file or symlink on disk based on a Git object. Args: obj: The git object mode: File mode target_path: Path to write to honor_filemode: An optional flag to honor core.filemode setting in config file, default is core.filemode=True, change executable bit Returns: stat object for the file """ try: oldstat = os.lstat(target_path) except OSError as e: if e.errno == errno.ENOENT: oldstat = None else: raise contents = blob.as_raw_string() if stat.S_ISLNK(mode): # FIXME: This will fail on Windows. What should we do instead? if oldstat: os.unlink(target_path) - if sys.platform == 'win32' and sys.version_info[0] == 3: + if sys.platform == 'win32': # os.readlink on Python3 on Windows requires a unicode string. # TODO(jelmer): Don't assume tree_encoding == fs_encoding tree_encoding = sys.getfilesystemencoding() contents = contents.decode(tree_encoding) target_path = target_path.decode(tree_encoding) os.symlink(contents, target_path) else: if oldstat is not None and oldstat.st_size == len(contents): with open(target_path, 'rb') as f: if f.read() == contents: return oldstat with open(target_path, 'wb') as f: # Write out file f.write(contents) if honor_filemode: os.chmod(target_path, mode) return os.lstat(target_path) INVALID_DOTNAMES = (b".git", b".", b"..", b"") def validate_path_element_default(element): return element.lower() not in INVALID_DOTNAMES def validate_path_element_ntfs(element): stripped = element.rstrip(b". ").lower() if stripped in INVALID_DOTNAMES: return False if stripped == b"git~1": return False return True def validate_path(path, element_validator=validate_path_element_default): """Default path validator that just checks for .git/.""" parts = path.split(b"/") for p in parts: if not element_validator(p): return False else: return True def build_index_from_tree(root_path, index_path, object_store, tree_id, honor_filemode=True, validate_path_element=validate_path_element_default): """Generate and materialize index from a tree Args: tree_id: Tree to materialize root_path: Target dir for materialized index files index_path: Target path for generated index object_store: Non-empty object store holding tree contents honor_filemode: An optional flag to honor core.filemode setting in config file, default is core.filemode=True, change executable bit validate_path_element: Function to validate path elements to check out; default just refuses .git and .. directories. Note: existing index is wiped and contents are not merged in a working dir. Suitable only for fresh clones. """ index = Index(index_path) if not isinstance(root_path, bytes): root_path = root_path.encode(sys.getfilesystemencoding()) for entry in object_store.iter_tree_contents(tree_id): if not validate_path(entry.path, validate_path_element): continue full_path = _tree_to_fs_path(root_path, entry.path) if not os.path.exists(os.path.dirname(full_path)): os.makedirs(os.path.dirname(full_path)) # TODO(jelmer): Merge new index into working tree if S_ISGITLINK(entry.mode): if not os.path.isdir(full_path): os.mkdir(full_path) st = os.lstat(full_path) # TODO(jelmer): record and return submodule paths else: obj = object_store[entry.sha] st = build_file_from_blob( obj, entry.mode, full_path, honor_filemode=honor_filemode) # Add file to index if not honor_filemode or S_ISGITLINK(entry.mode): # we can not use tuple slicing to build a new tuple, # because on windows that will convert the times to # longs, which causes errors further along st_tuple = (entry.mode, st.st_ino, st.st_dev, st.st_nlink, st.st_uid, st.st_gid, st.st_size, st.st_atime, st.st_mtime, st.st_ctime) st = st.__class__(st_tuple) index[entry.path] = index_entry_from_stat(st, entry.sha, 0) index.write() def blob_from_path_and_stat(fs_path, st): """Create a blob from a path and a stat object. Args: fs_path: Full file system path to file st: A stat object Returns: A `Blob` object """ assert isinstance(fs_path, bytes) blob = Blob() if stat.S_ISLNK(st.st_mode): if sys.platform == 'win32': # os.readlink on Python3 on Windows requires a unicode string. # TODO(jelmer): Don't assume tree_encoding == fs_encoding tree_encoding = sys.getfilesystemencoding() fs_path = fs_path.decode(tree_encoding) blob.data = os.readlink(fs_path).encode(tree_encoding) else: blob.data = os.readlink(fs_path) else: with open(fs_path, 'rb') as f: blob.data = f.read() return blob def read_submodule_head(path): """Read the head commit of a submodule. Args: path: path to the submodule Returns: HEAD sha, None if not a valid head/repository """ from dulwich.errors import NotGitRepository from dulwich.repo import Repo # Repo currently expects a "str", so decode if necessary. # TODO(jelmer): Perhaps move this into Repo() ? if not isinstance(path, str): path = path.decode(sys.getfilesystemencoding()) try: repo = Repo(path) except NotGitRepository: return None try: return repo.head() except KeyError: return None def _has_directory_changed(tree_path, entry): """Check if a directory has changed after getting an error. When handling an error trying to create a blob from a path, call this function. It will check if the path is a directory. If it's a directory and a submodule, check the submodule head to see if it's has changed. If not, consider the file as changed as Git tracked a file and not a directory. Return true if the given path should be considered as changed and False otherwise or if the path is not a directory. """ # This is actually a directory if os.path.exists(os.path.join(tree_path, b'.git')): # Submodule head = read_submodule_head(tree_path) if entry.sha != head: return True else: # The file was changed to a directory, so consider it removed. return True return False def get_unstaged_changes(index, root_path, filter_blob_callback=None): """Walk through an index and check for differences against working tree. Args: index: index to check root_path: path in which to find files Returns: iterator over paths with unstaged changes """ # For each entry in the index check the sha1 & ensure not staged if not isinstance(root_path, bytes): root_path = root_path.encode(sys.getfilesystemencoding()) for tree_path, entry in index.iteritems(): full_path = _tree_to_fs_path(root_path, tree_path) try: st = os.lstat(full_path) if stat.S_ISDIR(st.st_mode): if _has_directory_changed(tree_path, entry): yield tree_path continue if not stat.S_ISREG(st.st_mode) and not stat.S_ISLNK(st.st_mode): continue blob = blob_from_path_and_stat(full_path, st) if filter_blob_callback is not None: blob = filter_blob_callback(blob, tree_path) except EnvironmentError as e: if e.errno == errno.ENOENT: # The file was removed, so we assume that counts as # different from whatever file used to exist. yield tree_path else: raise else: if blob.id != entry.sha: yield tree_path os_sep_bytes = os.sep.encode('ascii') def _tree_to_fs_path(root_path, tree_path): """Convert a git tree path to a file system path. Args: root_path: Root filesystem path tree_path: Git tree path as bytes Returns: File system path. """ assert isinstance(tree_path, bytes) if os_sep_bytes != b'/': sep_corrected_path = tree_path.replace(b'/', os_sep_bytes) else: sep_corrected_path = tree_path return os.path.join(root_path, sep_corrected_path) def _fs_to_tree_path(fs_path, fs_encoding=None): """Convert a file system path to a git tree path. Args: fs_path: File system path. fs_encoding: File system encoding Returns: Git tree path as bytes """ if fs_encoding is None: fs_encoding = sys.getfilesystemencoding() if not isinstance(fs_path, bytes): fs_path_bytes = fs_path.encode(fs_encoding) else: fs_path_bytes = fs_path if os_sep_bytes != b'/': tree_path = fs_path_bytes.replace(os_sep_bytes, b'/') else: tree_path = fs_path_bytes return tree_path def index_entry_from_path(path, object_store=None): """Create an index from a filesystem path. This returns an index value for files, symlinks and tree references. for directories and non-existant files it returns None Args: path: Path to create an index entry for object_store: Optional object store to save new blobs in Returns: An index entry; None for directories """ assert isinstance(path, bytes) st = os.lstat(path) if stat.S_ISDIR(st.st_mode): if os.path.exists(os.path.join(path, b'.git')): head = read_submodule_head(path) if head is None: return None return index_entry_from_stat( st, head, 0, mode=S_IFGITLINK) return None if stat.S_ISREG(st.st_mode) or stat.S_ISLNK(st.st_mode): blob = blob_from_path_and_stat(path, st) if object_store is not None: object_store.add_object(blob) return index_entry_from_stat(st, blob.id, 0) return None def iter_fresh_entries(paths, root_path, object_store=None): """Iterate over current versions of index entries on disk. Args: paths: Paths to iterate over root_path: Root path to access from store: Optional store to save new blobs in Returns: Iterator over path, index_entry """ for path in paths: p = _tree_to_fs_path(root_path, path) try: entry = index_entry_from_path(p, object_store=object_store) except EnvironmentError as e: if e.errno in (errno.ENOENT, errno.EISDIR): entry = None else: raise yield path, entry def iter_fresh_blobs(index, root_path): """Iterate over versions of blobs on disk referenced by index. Don't use this function; it removes missing entries from index. Args: index: Index file root_path: Root path to access from include_deleted: Include deleted entries with sha and mode set to None Returns: Iterator over path, sha, mode """ import warnings warnings.warn(PendingDeprecationWarning, "Use iter_fresh_objects instead.") for entry in iter_fresh_objects( index, root_path, include_deleted=True): if entry[1] is None: del index[entry[0]] else: yield entry def iter_fresh_objects(paths, root_path, include_deleted=False, object_store=None): """Iterate over versions of objecs on disk referenced by index. Args: index: Index file root_path: Root path to access from include_deleted: Include deleted entries with sha and mode set to None object_store: Optional object store to report new items to Returns: Iterator over path, sha, mode """ for path, entry in iter_fresh_entries(paths, root_path, object_store=object_store): if entry is None: if include_deleted: yield path, None, None else: entry = IndexEntry(*entry) yield path, entry.sha, cleanup_mode(entry.mode) def refresh_index(index, root_path): """Refresh the contents of an index. This is the equivalent to running 'git commit -a'. Args: index: Index to update root_path: Root filesystem path """ for path, entry in iter_fresh_entries(index, root_path): index[path] = path diff --git a/dulwich/objects.py b/dulwich/objects.py index a9914a52..eeb330f7 100644 --- a/dulwich/objects.py +++ b/dulwich/objects.py @@ -1,1440 +1,1435 @@ # objects.py -- Access to base git objects # Copyright (C) 2007 James Westby # Copyright (C) 2008-2013 Jelmer Vernooij # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """Access to base git objects.""" import binascii from io import BytesIO from collections import namedtuple import os import posixpath import stat import sys import warnings import zlib from hashlib import sha1 from dulwich.errors import ( ChecksumMismatch, NotBlobError, NotCommitError, NotTagError, NotTreeError, ObjectFormatException, FileFormatException, ) from dulwich.file import GitFile ZERO_SHA = b'0' * 40 # Header fields for commits _TREE_HEADER = b'tree' _PARENT_HEADER = b'parent' _AUTHOR_HEADER = b'author' _COMMITTER_HEADER = b'committer' _ENCODING_HEADER = b'encoding' _MERGETAG_HEADER = b'mergetag' _GPGSIG_HEADER = b'gpgsig' # Header fields for objects _OBJECT_HEADER = b'object' _TYPE_HEADER = b'type' _TAG_HEADER = b'tag' _TAGGER_HEADER = b'tagger' S_IFGITLINK = 0o160000 MAX_TIME = 9223372036854775807 # (2**63) - 1 - signed long int max BEGIN_PGP_SIGNATURE = b"-----BEGIN PGP SIGNATURE-----" class EmptyFileException(FileFormatException): """An unexpectedly empty file was encountered.""" def S_ISGITLINK(m): """Check if a mode indicates a submodule. Args: m: Mode to check Returns: a ``boolean`` """ return (stat.S_IFMT(m) == S_IFGITLINK) def _decompress(string): dcomp = zlib.decompressobj() dcomped = dcomp.decompress(string) dcomped += dcomp.flush() return dcomped def sha_to_hex(sha): """Takes a string and returns the hex of the sha within""" hexsha = binascii.hexlify(sha) assert len(hexsha) == 40, "Incorrect length of sha1 string: %d" % hexsha return hexsha def hex_to_sha(hex): """Takes a hex sha and returns a binary sha""" assert len(hex) == 40, "Incorrect length of hexsha: %s" % hex try: return binascii.unhexlify(hex) except TypeError as exc: if not isinstance(hex, bytes): raise raise ValueError(exc.args[0]) def valid_hexsha(hex): if len(hex) != 40: return False try: binascii.unhexlify(hex) except (TypeError, binascii.Error): return False else: return True def hex_to_filename(path, hex): """Takes a hex sha and returns its filename relative to the given path.""" # os.path.join accepts bytes or unicode, but all args must be of the same # type. Make sure that hex which is expected to be bytes, is the same type # as path. if getattr(path, 'encode', None) is not None: hex = hex.decode('ascii') dir = hex[:2] file = hex[2:] # Check from object dir return os.path.join(path, dir, file) def filename_to_hex(filename): """Takes an object filename and returns its corresponding hex sha.""" # grab the last (up to) two path components names = filename.rsplit(os.path.sep, 2)[-2:] errmsg = "Invalid object filename: %s" % filename assert len(names) == 2, errmsg base, rest = names assert len(base) == 2 and len(rest) == 38, errmsg hex = (base + rest).encode('ascii') hex_to_sha(hex) return hex def object_header(num_type, length): """Return an object header for the given numeric type and text length.""" return (object_class(num_type).type_name + b' ' + str(length).encode('ascii') + b'\0') def serializable_property(name, docstring=None): """A property that helps tracking whether serialization is necessary. """ def set(obj, value): setattr(obj, "_"+name, value) obj._needs_serialization = True def get(obj): return getattr(obj, "_"+name) return property(get, set, doc=docstring) def object_class(type): """Get the object class corresponding to the given type. Args: type: Either a type name string or a numeric type. Returns: 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. Args: hex: Hex string to check error_msg: Error message to use in exception Raises: 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. Args: identity: Identity string error_msg: Error message to use in exception """ email_start = identity.find(b'<') email_end = identity.find(b'>') if (email_start < 0 or email_end < 0 or email_end <= email_start or identity.find(b'<', email_start + 1) >= 0 or identity.find(b'>', email_end + 1) >= 0 or not identity.endswith(b'>')): raise ObjectFormatException(error_msg) def check_time(time_seconds): """Check if the specified time is not prone to overflow error. This will raise an exception if the time is not valid. Args: time_info: author/committer/tagger info """ # Prevent overflow error if time_seconds > MAX_TIME: raise ObjectFormatException( 'Date field should not exceed %s' % MAX_TIME) def git_line(*items): """Formats items into a space separated line.""" return b' '.join(items) + b'\n' class FixedSha(object): """SHA object that behaves like hashlib's but is given a fixed value.""" __slots__ = ('_hexsha', '_sha') def __init__(self, hexsha): if getattr(hexsha, 'encode', None) is not None: hexsha = hexsha.encode('ascii') if not isinstance(hexsha, bytes): raise TypeError('Expected bytes for hexsha, got %r' % hexsha) self._hexsha = hexsha self._sha = hex_to_sha(hexsha) def digest(self): """Return the raw SHA digest.""" return self._sha def hexdigest(self): """Return the hex SHA digest.""" return self._hexsha.decode('ascii') class ShaFile(object): """A git SHA file.""" __slots__ = ('_chunked_text', '_sha', '_needs_serialization') @staticmethod def _parse_legacy_object_header(magic, f): """Parse a legacy object, creating it but not reading the file.""" bufsize = 1024 decomp = zlib.decompressobj() header = decomp.decompress(magic) start = 0 end = -1 while end < 0: extra = f.read(bufsize) header += decomp.decompress(extra) magic += extra end = header.find(b'\0', start) start = len(header) header = header[:end] type_name, size = header.split(b' ', 1) try: int(size) # sanity check except ValueError as e: raise ObjectFormatException("Object size not an integer: %s" % e) 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, compression_level=-1): """Return chunks representing the object in the experimental format. Returns: List of strings """ compobj = zlib.compressobj(compression_level) yield compobj.compress(self._header()) for chunk in self.as_raw_chunks(): yield compobj.compress(chunk) yield compobj.flush() def as_legacy_object(self, compression_level=-1): """Return string representing the object in the experimental format. """ return b''.join(self.as_legacy_object_chunks( compression_level=compression_level)) def as_raw_chunks(self): """Return chunks with serialization of the object. Returns: List of strings, not necessarily one per line """ if self._needs_serialization: self._sha = None self._chunked_text = self._serialize() self._needs_serialization = False return self._chunked_text def as_raw_string(self): """Return raw string with serialization of the object. Returns: String object """ return b''.join(self.as_raw_chunks()) - if sys.version_info[0] >= 3: - def __bytes__(self): - """Return raw string serialization of this object.""" - return self.as_raw_string() - else: - def __str__(self): - """Return raw string serialization of this object.""" - return self.as_raw_string() + def __bytes__(self): + """Return raw string serialization of this object.""" + return self.as_raw_string() def __hash__(self): """Return unique hash for this object.""" return hash(self.id) def as_pretty_string(self): """Return a string representing this object, fit for display.""" return self.as_raw_string() def set_raw_string(self, text, sha=None): """Set the contents of this object from a serialized string.""" if not isinstance(text, bytes): raise TypeError('Expected bytes for text, got %r' % text) self.set_raw_chunks([text], sha) def set_raw_chunks(self, chunks, sha=None): """Set the contents of this object from a list of chunks.""" self._chunked_text = chunks self._deserialize(chunks) if sha is None: self._sha = None else: self._sha = FixedSha(sha) self._needs_serialization = False @staticmethod def _parse_object_header(magic, f): """Parse a new style object, creating it but not reading the file.""" num_type = (ord(magic[0:1]) >> 4) & 7 obj_class = object_class(num_type) if not obj_class: raise ObjectFormatException("Not a known type %d" % num_type) return obj_class() def _parse_object(self, map): """Parse a new style object, setting self._text.""" # skip type and size; type must have already been determined, and # we trust zlib to fail if it's otherwise corrupted byte = ord(map[0:1]) used = 1 while (byte & 0x80) != 0: byte = ord(map[used:used+1]) used += 1 raw = map[used:] self.set_raw_string(_decompress(raw)) @classmethod def _is_legacy_object(cls, magic): b0 = ord(magic[0:1]) b1 = ord(magic[1:2]) word = (b0 << 8) + b1 return (b0 & 0x8F) == 0x08 and (word % 31) == 0 @classmethod def _parse_file(cls, f): map = f.read() if not map: raise EmptyFileException('Corrupted empty file detected') if cls._is_legacy_object(map): obj = cls._parse_legacy_object_header(map, f) obj._parse_legacy_object(map) else: obj = cls._parse_object_header(map, f) obj._parse_object(map) return obj def __init__(self): """Don't call this directly""" self._sha = None self._chunked_text = [] self._needs_serialization = True def _deserialize(self, chunks): raise NotImplementedError(self._deserialize) def _serialize(self): raise NotImplementedError(self._serialize) @classmethod def from_path(cls, path): """Open a SHA file from disk.""" with GitFile(path, 'rb') as f: return cls.from_file(f) @classmethod def from_file(cls, f): """Get the contents of a SHA file on disk.""" try: obj = cls._parse_file(f) obj._sha = None return obj except (IndexError, ValueError): raise ObjectFormatException("invalid object header") @staticmethod def from_raw_string(type_num, string, sha=None): """Creates an object of the indicated type from the raw string given. Args: type_num: The numeric type of the object. string: The raw uncompressed contents. 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. Args: type_num: The numeric type of the object. chunks: An iterable of the raw uncompressed contents. 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. Args: member: the member variable to check for error_msg: the message for an error if the member is missing Raises: 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. Raises: ObjectFormatException: if the object is malformed in some way ChecksumMismatch: if the object was created with a SHA that does not match its contents """ # TODO: if we find that error-checking during object parsing is a # performance bottleneck, those checks should be moved to the class's # check() method during optimization so we can still check the object # when necessary. old_sha = self.id try: self._deserialize(self.as_raw_chunks()) self._sha = None new_sha = self.id except Exception as e: raise ObjectFormatException(e) if old_sha != new_sha: raise ChecksumMismatch(new_sha, old_sha) def _header(self): return object_header(self.type, self.raw_length()) def raw_length(self): """Returns the length of the raw string of this object.""" ret = 0 for chunk in self.as_raw_chunks(): ret += len(chunk) return ret def sha(self): """The SHA1 object that is the name of this object.""" if self._sha is None or self._needs_serialization: # this is a local because as_raw_chunks() overwrites self._sha new_sha = sha1() new_sha.update(self._header()) for chunk in self.as_raw_chunks(): new_sha.update(chunk) self._sha = new_sha return self._sha def copy(self): """Create a new copy of this SHA1 object from its raw string""" obj_class = object_class(self.get_type()) return obj_class.from_raw_string( self.get_type(), self.as_raw_string(), self.id) @property def id(self): """The hex SHA of this object.""" return self.sha().hexdigest().encode('ascii') def get_type(self): """Return the type number for this object class.""" return self.type_num def set_type(self, type): """Set the type number for this object class.""" self.type_num = type # DEPRECATED: use type_num or type_name as needed. type = property(get_type, set_type) def __repr__(self): return "<%s %s>" % (self.__class__.__name__, self.id) def __ne__(self, other): """Check whether this object does not match the other.""" return not isinstance(other, ShaFile) or self.id != other.id def __eq__(self, other): """Return True if the SHAs of the two objects match. """ return isinstance(other, ShaFile) and self.id == other.id def __lt__(self, other): """Return whether SHA of this object is less than the other. """ if not isinstance(other, ShaFile): raise TypeError return self.id < other.id def __le__(self, other): """Check whether SHA of this object is less than or equal to the other. """ if not isinstance(other, ShaFile): raise TypeError return self.id <= other.id def __cmp__(self, other): """Compare the SHA of this object with that of the other object. """ if not isinstance(other, ShaFile): raise TypeError return cmp(self.id, other.id) # noqa: F821 class Blob(ShaFile): """A Git Blob object.""" __slots__ = () type_name = b'blob' type_num = 3 def __init__(self): super(Blob, self).__init__() self._chunked_text = [] self._needs_serialization = False def _get_data(self): return self.as_raw_string() def _set_data(self, data): self.set_raw_string(data) data = property(_get_data, _set_data, "The text contained within the blob object.") def _get_chunked(self): return self._chunked_text def _set_chunked(self, chunks): self._chunked_text = chunks def _serialize(self): return self._chunked_text def _deserialize(self, chunks): self._chunked_text = chunks chunked = property( _get_chunked, _set_chunked, "The text within the blob object, as chunks (not necessarily lines).") @classmethod def from_path(cls, path): blob = ShaFile.from_path(path) if not isinstance(blob, cls): raise NotBlobError(path) return blob def check(self): """Check this object for internal consistency. Raises: ObjectFormatException: if the object is malformed in some way """ super(Blob, self).check() def splitlines(self): """Return list of lines in this blob. This preserves the original line endings. """ chunks = self.chunked if not chunks: return [] if len(chunks) == 1: return chunks[0].splitlines(True) remaining = None ret = [] for chunk in chunks: lines = chunk.splitlines(True) if len(lines) > 1: ret.append((remaining or b"") + lines[0]) ret.extend(lines[1:-1]) remaining = lines[-1] elif len(lines) == 1: if remaining is None: remaining = lines.pop() else: remaining += lines.pop() if remaining is not None: ret.append(remaining) return ret def _parse_message(chunks): """Parse a message with a list of fields and a body. Args: chunks: the raw chunks of the tag or commit object. Returns: iterator of tuples of (field, value), one per header line, in the order read from the text, possibly including duplicates. Includes a field named None for the freeform tag/commit text. """ f = BytesIO(b''.join(chunks)) k = None v = "" eof = False def _strip_last_newline(value): """Strip the last newline from value""" if value and value.endswith(b'\n'): return value[:-1] return value # Parse the headers # # Headers can contain newlines. The next line is indented with a space. # We store the latest key as 'k', and the accumulated value as 'v'. for line in f: if line.startswith(b' '): # Indented continuation of the previous line v += line[1:] else: if k is not None: # We parsed a new header, return its value yield (k, _strip_last_newline(v)) if line == b'\n': # Empty line indicates end of headers break (k, v) = line.split(b' ', 1) else: # We reached end of file before the headers ended. We still need to # return the previous header, then we need to return a None field for # the text. eof = True if k is not None: yield (k, _strip_last_newline(v)) yield (None, None) if not eof: # We didn't reach the end of file while parsing headers. We can return # the rest of the file as a message. yield (None, f.read()) f.close() class Tag(ShaFile): """A Git Tag object.""" type_name = b'tag' type_num = 4 __slots__ = ('_tag_timezone_neg_utc', '_name', '_object_sha', '_object_class', '_tag_time', '_tag_timezone', '_tagger', '_message', '_signature') def __init__(self): super(Tag, self).__init__() self._tagger = None self._tag_time = None self._tag_timezone = None self._tag_timezone_neg_utc = False self._signature = None @classmethod def from_path(cls, filename): tag = ShaFile.from_path(filename) if not isinstance(tag, cls): raise NotTagError(filename) return tag def check(self): """Check this object for internal consistency. Raises: ObjectFormatException: if the object is malformed in some way """ super(Tag, self).check() self._check_has_member("_object_sha", "missing object sha") self._check_has_member("_object_class", "missing object type") self._check_has_member("_name", "missing tag name") if not self._name: raise ObjectFormatException("empty tag name") check_hexsha(self._object_sha, "invalid object sha") if getattr(self, "_tagger", None): check_identity(self._tagger, "invalid tagger") self._check_has_member("_tag_time", "missing tag time") check_time(self._tag_time) last = None for field, _ in _parse_message(self._chunked_text): if field == _OBJECT_HEADER and last is not None: raise ObjectFormatException("unexpected object") elif field == _TYPE_HEADER and last != _OBJECT_HEADER: raise ObjectFormatException("unexpected type") elif field == _TAG_HEADER and last != _TYPE_HEADER: raise ObjectFormatException("unexpected tag name") elif field == _TAGGER_HEADER and last != _TAG_HEADER: raise ObjectFormatException("unexpected tagger") last = field def _serialize(self): chunks = [] chunks.append(git_line(_OBJECT_HEADER, self._object_sha)) chunks.append(git_line(_TYPE_HEADER, self._object_class.type_name)) chunks.append(git_line(_TAG_HEADER, self._name)) if self._tagger: if self._tag_time is None: chunks.append(git_line(_TAGGER_HEADER, self._tagger)) else: chunks.append(git_line( _TAGGER_HEADER, self._tagger, str(self._tag_time).encode('ascii'), format_timezone( self._tag_timezone, self._tag_timezone_neg_utc))) if self._message is not None: chunks.append(b'\n') # To close headers chunks.append(self._message) if self._signature is not None: chunks.append(self._signature) return chunks def _deserialize(self, chunks): """Grab the metadata attached to the tag""" self._tagger = None self._tag_time = None self._tag_timezone = None self._tag_timezone_neg_utc = False for field, value in _parse_message(chunks): if field == _OBJECT_HEADER: self._object_sha = value elif field == _TYPE_HEADER: obj_class = object_class(value) if not obj_class: raise ObjectFormatException("Not a known type: %s" % value) self._object_class = obj_class elif field == _TAG_HEADER: self._name = value elif field == _TAGGER_HEADER: (self._tagger, self._tag_time, (self._tag_timezone, self._tag_timezone_neg_utc)) = parse_time_entry(value) elif field is None: if value is None: self._message = None self._signature = None else: try: sig_idx = value.index(BEGIN_PGP_SIGNATURE) except ValueError: self._message = value self._signature = None else: self._message = value[:sig_idx] self._signature = value[sig_idx:] else: raise ObjectFormatException("Unknown field %s" % field) def _get_object(self): """Get the object pointed to by this tag. Returns: tuple of (object class, sha). """ return (self._object_class, self._object_sha) def _set_object(self, value): (self._object_class, self._object_sha) = value self._needs_serialization = True object = property(_get_object, _set_object) name = serializable_property("name", "The name of this tag") tagger = serializable_property( "tagger", "Returns the name of the person who created this tag") tag_time = serializable_property( "tag_time", "The creation timestamp of the tag. As the number of seconds " "since the epoch") tag_timezone = serializable_property( "tag_timezone", "The timezone that tag_time is in.") message = serializable_property( "message", "the message attached to this tag") signature = serializable_property( "signature", "Optional detached GPG signature") class TreeEntry(namedtuple('TreeEntry', ['path', 'mode', 'sha'])): """Named tuple encapsulating a single tree entry.""" def in_path(self, path): """Return a copy of this entry with the given path prepended.""" if not isinstance(self.path, bytes): raise TypeError('Expected bytes for path, got %r' % path) return TreeEntry(posixpath.join(path, self.path), self.mode, self.sha) def parse_tree(text, strict=False): """Parse a tree text. Args: text: Serialized text to parse Returns: iterator of tuples of (name, mode, sha) Raises: ObjectFormatException: if the object was malformed in some way """ count = 0 length = len(text) while count < length: mode_end = text.index(b' ', count) mode_text = text[count:mode_end] if strict and mode_text.startswith(b'0'): raise ObjectFormatException("Invalid mode '%s'" % mode_text) try: mode = int(mode_text, 8) except ValueError: raise ObjectFormatException("Invalid mode '%s'" % mode_text) name_end = text.index(b'\0', mode_end) name = text[mode_end+1:name_end] count = name_end+21 sha = text[name_end+1:count] if len(sha) != 20: raise ObjectFormatException("Sha has invalid length") hexsha = sha_to_hex(sha) yield (name, mode, hexsha) def serialize_tree(items): """Serialize the items in a tree to a text. Args: items: Sorted iterable over (name, mode, sha) tuples Returns: 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. Args: 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. entries: Dictionary mapping names to (mode, sha) tuples Returns: 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. Args: entry: (name, value) tuplee """ (name, value) = entry if stat.S_ISDIR(value[0]): name += b'/' return name def key_entry_name_order(entry): """Sort key for tree entry in name order.""" return entry[0] def pretty_format_tree_entry(name, mode, hexsha, encoding="utf-8"): """Pretty format tree entry. Args: name: Name of the directory entry mode: Mode of entry hexsha: Hexsha of the referenced object Returns: string describing the tree entry """ if mode & stat.S_IFDIR: kind = "tree" else: kind = "blob" return "%04o %s %s\t%s\n" % ( mode, kind, hexsha.decode('ascii'), name.decode(encoding, 'replace')) class Tree(ShaFile): """A Git tree object""" type_name = b'tree' type_num = 2 __slots__ = ('_entries') def __init__(self): super(Tree, self).__init__() self._entries = {} @classmethod def from_path(cls, filename): tree = ShaFile.from_path(filename) if not isinstance(tree, cls): raise NotTreeError(filename) return tree def __contains__(self, name): return name in self._entries def __getitem__(self, name): return self._entries[name] def __setitem__(self, name, value): """Set a tree entry by name. Args: name: The name of the entry, as a string. value: A tuple of (mode, hexsha), where mode is the mode of the entry as an integral type and hexsha is the hex SHA of the entry as a string. """ mode, hexsha = value self._entries[name] = (mode, hexsha) self._needs_serialization = True def __delitem__(self, name): del self._entries[name] self._needs_serialization = True def __len__(self): return len(self._entries) def __iter__(self): return iter(self._entries) def add(self, name, mode, hexsha): """Add an entry to the tree. Args: mode: The mode of the entry as an integral type. Not all possible modes are supported by git; see check() for details. name: The name of the entry, as a string. hexsha: The hex SHA of the entry as a string. """ if isinstance(name, int) and isinstance(mode, bytes): (name, mode) = (mode, name) warnings.warn( "Please use Tree.add(name, mode, hexsha)", category=DeprecationWarning, stacklevel=2) self._entries[name] = mode, hexsha self._needs_serialization = True def iteritems(self, name_order=False): """Iterate over entries. Args: name_order: If True, iterate in name order instead of tree order. Returns: Iterator over (name, mode, sha) tuples """ return sorted_tree_items(self._entries, name_order) def items(self): """Return the sorted entries in this tree. Returns: 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. Raises: ObjectFormatException: if the object is malformed in some way """ super(Tree, self).check() last = None allowed_modes = (stat.S_IFREG | 0o755, stat.S_IFREG | 0o644, stat.S_IFLNK, stat.S_IFDIR, S_IFGITLINK, # TODO: optionally exclude as in git fsck --strict stat.S_IFREG | 0o664) for name, mode, sha in parse_tree(b''.join(self._chunked_text), True): check_hexsha(sha, 'invalid sha %s' % sha) if b'/' in name or name in (b'', b'.', b'..', b'.git'): raise ObjectFormatException( 'invalid name %s' % name.decode('utf-8', 'replace')) if mode not in allowed_modes: raise ObjectFormatException('invalid mode %06o' % mode) entry = (name, (mode, sha)) if last: if key_entry(last) > key_entry(entry): raise ObjectFormatException('entries not sorted') if name == last[0]: raise ObjectFormatException('duplicate entry %s' % name) last = entry def _serialize(self): return list(serialize_tree(self.iteritems())) def as_pretty_string(self): text = [] for name, mode, hexsha in self.iteritems(): text.append(pretty_format_tree_entry(name, mode, hexsha)) return "".join(text) def lookup_path(self, lookup_obj, path): """Look up an object in a Git tree. Args: lookup_obj: Callback for retrieving object by SHA1 path: Path to lookup Returns: 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'). Args: text: Text to parse. Returns: 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. Args: offset: Timezone offset as seconds difference to UTC unnecessary_negative_timezone: Whether to use a minus sign for UTC or positive timezones (-0000 and --700 rather than +0000 / +0700). """ if offset % 60 != 0: raise ValueError("Unable to handle non-minute offset.") if offset < 0 or unnecessary_negative_timezone: sign = '-' offset = -offset else: sign = '+' return ('%c%02d%02d' % (sign, offset / 3600, (offset / 60) % 60)).encode('ascii') def parse_time_entry(value): """Parse time entry behavior Args: value: Bytes representing a git commit/tag line Raises: ObjectFormatException in case of parsing error (malformed field date) Returns: Tuple of (author, time, (timezone, timezone_neg_utc)) """ try: sep = value.rindex(b'> ') except ValueError: return (value, None, (None, False)) try: person = value[0:sep+1] rest = value[sep+2:] timetext, timezonetext = rest.rsplit(b' ', 1) time = int(timetext) timezone, timezone_neg_utc = parse_timezone(timezonetext) except ValueError as e: raise ObjectFormatException(e) return person, time, (timezone, timezone_neg_utc) def parse_commit(chunks): """Parse a commit object from chunks. Args: chunks: Chunks to parse Returns: Tuple of (tree, parents, author_info, commit_info, encoding, mergetag, gpgsig, message, extra) """ parents = [] extra = [] tree = None author_info = (None, None, (None, None)) commit_info = (None, None, (None, None)) encoding = None mergetag = [] message = None gpgsig = None for field, value in _parse_message(chunks): # TODO(jelmer): Enforce ordering if field == _TREE_HEADER: tree = value elif field == _PARENT_HEADER: parents.append(value) elif field == _AUTHOR_HEADER: author_info = parse_time_entry(value) elif field == _COMMITTER_HEADER: commit_info = parse_time_entry(value) elif field == _ENCODING_HEADER: encoding = value elif field == _MERGETAG_HEADER: mergetag.append(Tag.from_string(value + b'\n')) elif field == _GPGSIG_HEADER: gpgsig = value elif field is None: message = value else: extra.append((field, value)) return (tree, parents, author_info, commit_info, encoding, mergetag, gpgsig, message, extra) class Commit(ShaFile): """A git commit object""" type_name = b'commit' type_num = 1 __slots__ = ('_parents', '_encoding', '_extra', '_author_timezone_neg_utc', '_commit_timezone_neg_utc', '_commit_time', '_author_time', '_author_timezone', '_commit_timezone', '_author', '_committer', '_tree', '_message', '_mergetag', '_gpgsig') def __init__(self): super(Commit, self).__init__() self._parents = [] self._encoding = None self._mergetag = [] self._gpgsig = None self._extra = [] self._author_timezone_neg_utc = False self._commit_timezone_neg_utc = False @classmethod def from_path(cls, path): commit = ShaFile.from_path(path) if not isinstance(commit, cls): raise NotCommitError(path) return commit def _deserialize(self, chunks): (self._tree, self._parents, author_info, commit_info, self._encoding, self._mergetag, self._gpgsig, self._message, self._extra) = ( parse_commit(chunks)) (self._author, self._author_time, (self._author_timezone, self._author_timezone_neg_utc)) = author_info (self._committer, self._commit_time, (self._commit_timezone, self._commit_timezone_neg_utc)) = commit_info def check(self): """Check this object for internal consistency. Raises: ObjectFormatException: if the object is malformed in some way """ super(Commit, self).check() self._check_has_member("_tree", "missing tree") self._check_has_member("_author", "missing author") self._check_has_member("_committer", "missing committer") self._check_has_member("_author_time", "missing author time") self._check_has_member("_commit_time", "missing commit time") for parent in self._parents: check_hexsha(parent, "invalid parent sha") check_hexsha(self._tree, "invalid tree sha") check_identity(self._author, "invalid author") check_identity(self._committer, "invalid committer") check_time(self._author_time) check_time(self._commit_time) last = None for field, _ in _parse_message(self._chunked_text): if field == _TREE_HEADER and last is not None: raise ObjectFormatException("unexpected tree") elif field == _PARENT_HEADER and last not in (_PARENT_HEADER, _TREE_HEADER): raise ObjectFormatException("unexpected parent") elif field == _AUTHOR_HEADER and last not in (_TREE_HEADER, _PARENT_HEADER): raise ObjectFormatException("unexpected author") elif field == _COMMITTER_HEADER and last != _AUTHOR_HEADER: raise ObjectFormatException("unexpected committer") elif field == _ENCODING_HEADER and last != _COMMITTER_HEADER: raise ObjectFormatException("unexpected encoding") last = field # TODO: optionally check for duplicate parents def _serialize(self): chunks = [] tree_bytes = ( self._tree.id if isinstance(self._tree, Tree) else self._tree) chunks.append(git_line(_TREE_HEADER, tree_bytes)) for p in self._parents: chunks.append(git_line(_PARENT_HEADER, p)) chunks.append(git_line( _AUTHOR_HEADER, self._author, str(self._author_time).encode('ascii'), format_timezone( self._author_timezone, self._author_timezone_neg_utc))) chunks.append(git_line( _COMMITTER_HEADER, self._committer, str(self._commit_time).encode('ascii'), format_timezone(self._commit_timezone, self._commit_timezone_neg_utc))) if self.encoding: chunks.append(git_line(_ENCODING_HEADER, self.encoding)) for mergetag in self.mergetag: mergetag_chunks = mergetag.as_raw_string().split(b'\n') chunks.append(git_line(_MERGETAG_HEADER, mergetag_chunks[0])) # Embedded extra header needs leading space for chunk in mergetag_chunks[1:]: chunks.append(b' ' + chunk + b'\n') # No trailing empty line if chunks[-1].endswith(b' \n'): chunks[-1] = chunks[-1][:-2] for k, v in self.extra: if b'\n' in k or b'\n' in v: raise AssertionError( "newline in extra data: %r -> %r" % (k, v)) chunks.append(git_line(k, v)) if self.gpgsig: sig_chunks = self.gpgsig.split(b'\n') chunks.append(git_line(_GPGSIG_HEADER, sig_chunks[0])) for chunk in sig_chunks[1:]: chunks.append(git_line(b'', chunk)) chunks.append(b'\n') # There must be a new line after the headers chunks.append(self._message) return chunks tree = serializable_property( "tree", "Tree that is the state of this commit") def _get_parents(self): """Return a list of parents of this commit.""" return self._parents def _set_parents(self, value): """Set a list of parents of this commit.""" self._needs_serialization = True self._parents = value parents = property(_get_parents, _set_parents, doc="Parents of this commit, by their SHA1.") def _get_extra(self): """Return extra settings of this commit.""" return self._extra extra = property( _get_extra, doc="Extra header fields not understood (presumably added in a " "newer version of git). Kept verbatim so the object can " "be correctly reserialized. For private commit metadata, use " "pseudo-headers in Commit.message, rather than this field.") author = serializable_property( "author", "The name of the author of the commit") committer = serializable_property( "committer", "The name of the committer of the commit") message = serializable_property( "message", "The commit message") commit_time = serializable_property( "commit_time", "The timestamp of the commit. As the number of seconds since the " "epoch.") commit_timezone = serializable_property( "commit_timezone", "The zone the commit time is in") author_time = serializable_property( "author_time", "The timestamp the commit was written. As the number of " "seconds since the epoch.") author_timezone = serializable_property( "author_timezone", "Returns the zone the author time is in.") encoding = serializable_property( "encoding", "Encoding of the commit message.") mergetag = serializable_property( "mergetag", "Associated signed tag.") gpgsig = serializable_property( "gpgsig", "GPG Signature.") OBJECT_CLASSES = ( Commit, Tree, Blob, Tag, ) _TYPE_MAP = {} for cls in OBJECT_CLASSES: _TYPE_MAP[cls.type_name] = cls _TYPE_MAP[cls.type_num] = cls # Hold on to the pure-python implementations for testing _parse_tree_py = parse_tree _sorted_tree_items_py = sorted_tree_items try: # Try to import C versions from dulwich._objects import parse_tree, sorted_tree_items except ImportError: pass diff --git a/dulwich/porcelain.py b/dulwich/porcelain.py index b4a5d8c3..7e88e61e 100644 --- a/dulwich/porcelain.py +++ b/dulwich/porcelain.py @@ -1,1619 +1,1615 @@ # porcelain.py -- Porcelain-like layer on top of Dulwich # Copyright (C) 2013 Jelmer Vernooij # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """Simple wrapper that provides porcelain-like functions on top of Dulwich. Currently implemented: * archive * add * branch{_create,_delete,_list} * check-ignore * checkout * clone * commit * commit-tree * daemon * describe * diff-tree * fetch * init * ls-files * ls-remote * ls-tree * pull * push * rm * remote{_add} * receive-pack * reset * rev-list * tag{_create,_delete,_list} * upload-pack * update-server-info * status * symbolic-ref These functions are meant to behave similarly to the git subcommands. Differences in behaviour are considered bugs. Functions should generally accept both unicode strings and bytestrings """ from collections import namedtuple from contextlib import ( closing, contextmanager, ) from io import BytesIO, RawIOBase import datetime import os import posixpath import shutil import stat import sys import time from dulwich.archive import ( tar_stream, ) from dulwich.client import ( get_transport_and_path, ) from dulwich.config import ( StackedConfig, ) from dulwich.diff_tree import ( CHANGE_ADD, CHANGE_DELETE, CHANGE_MODIFY, CHANGE_RENAME, CHANGE_COPY, RENAME_CHANGE_TYPES, ) from dulwich.errors import ( SendPackError, UpdateRefsError, ) from dulwich.ignore import IgnoreFilterManager from dulwich.index import ( blob_from_path_and_stat, get_unstaged_changes, ) from dulwich.object_store import ( tree_lookup_path, ) from dulwich.objects import ( Commit, Tag, format_timezone, parse_timezone, pretty_format_tree_entry, ) from dulwich.objectspec import ( parse_commit, parse_object, parse_ref, parse_reftuples, parse_tree, ) from dulwich.pack import ( write_pack_index, write_pack_objects, ) from dulwich.patch import write_tree_diff from dulwich.protocol import ( Protocol, ZERO_SHA, ) from dulwich.refs import ( ANNOTATED_TAG_SUFFIX, LOCAL_BRANCH_PREFIX, strip_peeled_refs, ) from dulwich.repo import (BaseRepo, Repo) from dulwich.server import ( FileSystemBackend, TCPGitServer, ReceivePackHandler, UploadPackHandler, update_server_info as server_update_server_info, ) # Module level tuple definition for status output GitStatus = namedtuple('GitStatus', 'staged unstaged untracked') class NoneStream(RawIOBase): """Fallback if stdout or stderr are unavailable, does nothing.""" def read(self, size=-1): return None def readall(self): return None def readinto(self, b): return None def write(self, b): return None -if sys.version_info[0] == 2: - default_bytes_out_stream = sys.stdout or NoneStream() - default_bytes_err_stream = sys.stderr or NoneStream() -else: - default_bytes_out_stream = ( - getattr(sys.stdout, 'buffer', None) or NoneStream()) - default_bytes_err_stream = ( - getattr(sys.stderr, 'buffer', None) or NoneStream()) +default_bytes_out_stream = ( + getattr(sys.stdout, 'buffer', None) or NoneStream()) +default_bytes_err_stream = ( + getattr(sys.stderr, 'buffer', None) or NoneStream()) DEFAULT_ENCODING = 'utf-8' class RemoteExists(Exception): """Raised when the remote already exists.""" def open_repo(path_or_repo): """Open an argument that can be a repository or a path for a repository.""" if isinstance(path_or_repo, BaseRepo): return path_or_repo return Repo(path_or_repo) @contextmanager def _noop_context_manager(obj): """Context manager that has the same api as closing but does nothing.""" yield obj def open_repo_closing(path_or_repo): """Open an argument that can be a repository or a path for a repository. returns a context manager that will close the repo on exit if the argument is a path, else does nothing if the argument is a repo. """ if isinstance(path_or_repo, BaseRepo): return _noop_context_manager(path_or_repo) return closing(Repo(path_or_repo)) def path_to_tree_path(repopath, path): """Convert a path to a path usable in an index, e.g. bytes and relative to the repository root. Args: repopath: Repository path, absolute or relative to the cwd path: A path, absolute or relative to the cwd Returns: A path formatted for use in e.g. an index """ if not isinstance(path, bytes): path = path.encode(sys.getfilesystemencoding()) if not isinstance(repopath, bytes): repopath = repopath.encode(sys.getfilesystemencoding()) treepath = os.path.relpath(path, repopath) if treepath.startswith(b'..'): raise ValueError('Path not in repo') if os.path.sep != '/': treepath = treepath.replace(os.path.sep.encode('ascii'), b'/') return treepath def archive(repo, committish=None, outstream=default_bytes_out_stream, errstream=default_bytes_err_stream): """Create an archive. Args: repo: Path of repository for which to generate an archive. committish: Commit SHA1 or ref to use outstream: Output stream (defaults to stdout) errstream: Error stream (defaults to stderr) """ if committish is None: committish = "HEAD" with open_repo_closing(repo) as repo_obj: c = parse_commit(repo_obj, committish) for chunk in tar_stream( repo_obj.object_store, repo_obj.object_store[c.tree], c.commit_time): outstream.write(chunk) def update_server_info(repo="."): """Update server info files for a repository. Args: 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. Args: repo: path to the repository ref_name: short name of the new ref force: force settings without checking if it exists in refs/heads """ with open_repo_closing(repo) as repo_obj: ref_path = _make_branch_ref(ref_name) if not force and ref_path not in repo_obj.refs.keys(): raise ValueError('fatal: ref `%s` is not a ref' % ref_name) repo_obj.refs.set_symbolic_ref(b'HEAD', ref_path) def commit(repo=".", message=None, author=None, committer=None, encoding=None): """Create a new commit. Args: repo: Path to repository message: Optional commit message author: Optional author name and email committer: Optional committer name and email Returns: SHA1 of the new commit """ # FIXME: Support --all argument # FIXME: Support --signoff argument if getattr(message, 'encode', None): message = message.encode(encoding or DEFAULT_ENCODING) if getattr(author, 'encode', None): author = author.encode(encoding or DEFAULT_ENCODING) if getattr(committer, 'encode', None): committer = committer.encode(encoding or DEFAULT_ENCODING) with open_repo_closing(repo) as r: return r.do_commit( message=message, author=author, committer=committer, encoding=encoding) def commit_tree(repo, tree, message=None, author=None, committer=None): """Create a new commit object. Args: repo: Path to repository tree: An existing tree object author: Optional author name and email 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. Args: path: Path to repository. bare: Whether to create a bare repository. Returns: A Repo instance """ if not os.path.exists(path): os.mkdir(path) if bare: return Repo.init_bare(path) else: return Repo.init(path) def clone(source, target=None, bare=False, checkout=None, errstream=default_bytes_err_stream, outstream=None, origin=b"origin", depth=None, **kwargs): """Clone a local or remote git repository. Args: source: Path or URL for source repository target: Path to target repository (optional) bare: Whether or not to create a bare repository checkout: Whether or not to check-out HEAD after cloning errstream: Optional stream to write progress to outstream: Optional stream to write progress to (deprecated) origin: Name of remote from the repository used to clone depth: Depth to fetch at Returns: The new repository """ # TODO(jelmer): This code overlaps quite a bit with Repo.clone if outstream is not None: import warnings warnings.warn( "outstream= has been deprecated in favour of errstream=.", DeprecationWarning, stacklevel=3) errstream = outstream if checkout is None: checkout = (not bare) if checkout and bare: raise ValueError("checkout and bare are incompatible") if target is None: target = source.split("/")[-1] if not os.path.exists(target): os.mkdir(target) if bare: r = Repo.init_bare(target) else: r = Repo.init(target) reflog_message = b'clone: from ' + source.encode('utf-8') try: fetch_result = fetch( r, source, origin, errstream=errstream, message=reflog_message, depth=depth, **kwargs) target_config = r.get_config() if not isinstance(source, bytes): source = source.encode(DEFAULT_ENCODING) target_config.set((b'remote', origin), b'url', source) target_config.set( (b'remote', origin), b'fetch', b'+refs/heads/*:refs/remotes/' + origin + b'/*') target_config.write_to_path() # TODO(jelmer): Support symref capability, # https://github.com/jelmer/dulwich/issues/485 try: head = r[fetch_result[b'HEAD']] except KeyError: head = None else: r[b'HEAD'] = head.id if checkout and not bare and head is not None: errstream.write(b'Checking out ' + head.id + b'\n') r.reset_index(head.tree) except BaseException: shutil.rmtree(target) r.close() raise return r def add(repo=".", paths=None): """Add files to the staging area. Args: repo: Repository for the files paths: Paths to add. No value passed stages all modified files. Returns: Tuple with set of added files and ignored files """ ignored = set() with open_repo_closing(repo) as r: ignore_manager = IgnoreFilterManager.from_repo(r) if not paths: paths = list( get_untracked_paths(os.getcwd(), r.path, r.open_index())) relpaths = [] if not isinstance(paths, list): paths = [paths] for p in paths: relpath = os.path.relpath(p, r.path) if relpath.startswith('..' + os.path.sep): raise ValueError('path %r is not in repo' % relpath) # FIXME: Support patterns, directories. if ignore_manager.is_ignored(relpath): ignored.add(relpath) continue relpaths.append(relpath) r.stage(relpaths) return (relpaths, ignored) def _is_subdir(subdir, parentdir): """Check whether subdir is parentdir or a subdir of parentdir If parentdir or subdir is a relative path, it will be disamgibuated relative to the pwd. """ parentdir_abs = os.path.realpath(parentdir) + os.path.sep subdir_abs = os.path.realpath(subdir) + os.path.sep return subdir_abs.startswith(parentdir_abs) # TODO: option to remove ignored files also, in line with `git clean -fdx` def clean(repo=".", target_dir=None): """Remove any untracked files from the target directory recursively Equivalent to running `git clean -fd` in target_dir. Args: repo: Repository where the files may be tracked target_dir: Directory to clean - current directory if None """ if target_dir is None: target_dir = os.getcwd() with open_repo_closing(repo) as r: if not _is_subdir(target_dir, r.path): raise ValueError("target_dir must be in the repo's working dir") index = r.open_index() ignore_manager = IgnoreFilterManager.from_repo(r) paths_in_wd = _walk_working_dir_paths(target_dir, r.path) # Reverse file visit order, so that files and subdirectories are # removed before containing directory for ap, is_dir in reversed(list(paths_in_wd)): if is_dir: # All subdirectories and files have been removed if untracked, # so dir contains no tracked files iff it is empty. is_empty = len(os.listdir(ap)) == 0 if is_empty: os.rmdir(ap) else: ip = path_to_tree_path(r.path, ap) is_tracked = ip in index rp = os.path.relpath(ap, r.path) is_ignored = ignore_manager.is_ignored(rp) if not is_tracked and not is_ignored: os.remove(ap) def remove(repo=".", paths=None, cached=False): """Remove files from the staging area. Args: repo: Repository for the files paths: Paths to remove """ with open_repo_closing(repo) as r: index = r.open_index() for p in paths: full_path = os.path.abspath(p).encode(sys.getfilesystemencoding()) tree_path = path_to_tree_path(r.path, p) try: index_sha = index[tree_path].sha except KeyError: raise Exception('%s did not match any files' % p) if not cached: try: st = os.lstat(full_path) except OSError: pass else: try: blob = blob_from_path_and_stat(full_path, st) except IOError: pass else: try: committed_sha = tree_lookup_path( r.__getitem__, r[r.head()].tree, tree_path)[1] except KeyError: committed_sha = None if blob.id != index_sha and index_sha != committed_sha: raise Exception( 'file has staged content differing ' 'from both the file and head: %s' % p) if index_sha != committed_sha: raise Exception( 'file has staged changes: %s' % p) os.remove(full_path) del index[tree_path] index.write() rm = remove def commit_decode(commit, contents, default_encoding=DEFAULT_ENCODING): if commit.encoding: encoding = commit.encoding.decode('ascii') else: encoding = default_encoding return contents.decode(encoding, "replace") def commit_encode(commit, contents, default_encoding=DEFAULT_ENCODING): if commit.encoding: encoding = commit.encoding.decode('ascii') else: encoding = default_encoding return contents.encode(encoding) def print_commit(commit, decode, outstream=sys.stdout): """Write a human-readable commit log entry. Args: commit: A `Commit` object outstream: A stream file to write to """ outstream.write("-" * 50 + "\n") outstream.write("commit: " + commit.id.decode('ascii') + "\n") if len(commit.parents) > 1: outstream.write( "merge: " + "...".join([c.decode('ascii') for c in commit.parents[1:]]) + "\n") outstream.write("Author: " + decode(commit.author) + "\n") if commit.author != commit.committer: outstream.write("Committer: " + decode(commit.committer) + "\n") time_tuple = time.gmtime(commit.author_time + commit.author_timezone) time_str = time.strftime("%a %b %d %Y %H:%M:%S", time_tuple) timezone_str = format_timezone(commit.author_timezone).decode('ascii') outstream.write("Date: " + time_str + " " + timezone_str + "\n") outstream.write("\n") outstream.write(decode(commit.message) + "\n") outstream.write("\n") def print_tag(tag, decode, outstream=sys.stdout): """Write a human-readable tag. Args: tag: A `Tag` object decode: Function for decoding bytes to unicode string outstream: A stream to write to """ outstream.write("Tagger: " + decode(tag.tagger) + "\n") time_tuple = time.gmtime(tag.tag_time + tag.tag_timezone) time_str = time.strftime("%a %b %d %Y %H:%M:%S", time_tuple) timezone_str = format_timezone(tag.tag_timezone).decode('ascii') outstream.write("Date: " + time_str + " " + timezone_str + "\n") outstream.write("\n") outstream.write(decode(tag.message) + "\n") outstream.write("\n") def show_blob(repo, blob, decode, outstream=sys.stdout): """Write a blob to a stream. Args: repo: A `Repo` object blob: A `Blob` object decode: Function for decoding bytes to unicode string outstream: A stream file to write to """ outstream.write(decode(blob.data)) def show_commit(repo, commit, decode, outstream=sys.stdout): """Show a commit to a stream. Args: repo: A `Repo` object commit: A `Commit` object decode: Function for decoding bytes to unicode string outstream: Stream to write to """ print_commit(commit, decode=decode, outstream=outstream) if commit.parents: parent_commit = repo[commit.parents[0]] base_tree = parent_commit.tree else: base_tree = None diffstream = BytesIO() write_tree_diff( diffstream, repo.object_store, base_tree, commit.tree) diffstream.seek(0) outstream.write(commit_decode(commit, diffstream.getvalue())) def show_tree(repo, tree, decode, outstream=sys.stdout): """Print a tree to a stream. Args: repo: A `Repo` object tree: A `Tree` object decode: Function for decoding bytes to unicode string outstream: Stream to write to """ for n in tree: outstream.write(decode(n) + "\n") def show_tag(repo, tag, decode, outstream=sys.stdout): """Print a tag to a stream. Args: repo: A `Repo` object tag: A `Tag` object decode: Function for decoding bytes to unicode string outstream: Stream to write to """ print_tag(tag, decode, outstream) show_object(repo, repo[tag.object[1]], decode, outstream) def show_object(repo, obj, decode, outstream): return { b"tree": show_tree, b"blob": show_blob, b"commit": show_commit, b"tag": show_tag, }[obj.type_name](repo, obj, decode, outstream) def print_name_status(changes): """Print a simple status summary, listing changed files. """ for change in changes: if not change: continue if isinstance(change, list): change = change[0] if change.type == CHANGE_ADD: path1 = change.new.path path2 = '' kind = 'A' elif change.type == CHANGE_DELETE: path1 = change.old.path path2 = '' kind = 'D' elif change.type == CHANGE_MODIFY: path1 = change.new.path path2 = '' kind = 'M' elif change.type in RENAME_CHANGE_TYPES: path1 = change.old.path path2 = change.new.path if change.type == CHANGE_RENAME: kind = 'R' elif change.type == CHANGE_COPY: kind = 'C' yield '%-8s%-20s%-20s' % (kind, path1, path2) def log(repo=".", paths=None, outstream=sys.stdout, max_entries=None, reverse=False, name_status=False): """Write commit logs. Args: repo: Path to repository paths: Optional set of specific paths to print entries for outstream: Stream to write log output to reverse: Reverse order in which entries are printed name_status: Print name status max_entries: Optional maximum number of entries to display """ with open_repo_closing(repo) as r: walker = r.get_walker( max_entries=max_entries, paths=paths, reverse=reverse) for entry in walker: def decode(x): return commit_decode(entry.commit, x) print_commit(entry.commit, decode, outstream) if name_status: outstream.writelines( [l+'\n' for l in print_name_status(entry.changes())]) # TODO(jelmer): better default for encoding? def show(repo=".", objects=None, outstream=sys.stdout, default_encoding=DEFAULT_ENCODING): """Print the changes in a commit. Args: repo: Path to repository objects: Objects to show (defaults to [HEAD]) outstream: Stream to write to default_encoding: Default encoding to use if none is set in the commit """ if objects is None: objects = ["HEAD"] if not isinstance(objects, list): objects = [objects] with open_repo_closing(repo) as r: for objectish in objects: o = parse_object(r, objectish) if isinstance(o, Commit): def decode(x): return commit_decode(o, x, default_encoding) else: def decode(x): return x.decode(default_encoding) show_object(r, o, decode, outstream) def diff_tree(repo, old_tree, new_tree, outstream=sys.stdout): """Compares the content and mode of blobs found via two tree objects. Args: repo: Path to repository old_tree: Id of old tree new_tree: Id of new tree 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. Args: repo: Path to repository commits: Commits over which to iterate 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, sign=False): """Creates a tag in git via dulwich calls: Args: repo: Path to repository tag: tag string author: tag author (optional, if annotated is set) message: tag message (optional) annotated: whether to create an annotated tag objectish: object the tag should point at, defaults to HEAD tag_time: Optional time for annotated tag tag_timezone: Optional timezone for annotated tag sign: GPG Sign the tag """ with open_repo_closing(repo) as r: object = parse_object(r, objectish) if annotated: # Create the tag object tag_obj = Tag() if author is None: # TODO(jelmer): Don't use repo private method. author = r._get_user_identity(r.get_config_stack()) tag_obj.tagger = author tag_obj.message = message tag_obj.name = tag tag_obj.object = (type(object), object.id) if tag_time is None: tag_time = int(time.time()) tag_obj.tag_time = tag_time if tag_timezone is None: # TODO(jelmer) Use current user timezone rather than UTC tag_timezone = 0 elif isinstance(tag_timezone, str): tag_timezone = parse_timezone(tag_timezone) tag_obj.tag_timezone = tag_timezone if sign: import gpg with gpg.Context(armor=True) as c: tag_obj.signature, unused_result = c.sign( tag_obj.as_raw_string()) r.object_store.add_object(tag_obj) tag_id = tag_obj.id else: tag_id = object.id r.refs[_make_tag_ref(tag)] = tag_id def list_tags(*args, **kwargs): import warnings warnings.warn("list_tags has been deprecated in favour of tag_list.", DeprecationWarning) return tag_list(*args, **kwargs) def tag_list(repo, outstream=sys.stdout): """List all tags. Args: repo: Path to repository outstream: Stream to write tags to """ with open_repo_closing(repo) as r: tags = sorted(r.refs.as_dict(b"refs/tags")) return tags def tag_delete(repo, name): """Remove a tag. Args: repo: Path to repository name: Name of tag to remove """ with open_repo_closing(repo) as r: if isinstance(name, bytes): names = [name] elif isinstance(name, list): names = name else: raise TypeError("Unexpected tag name type %r" % name) for name in names: del r.refs[_make_tag_ref(name)] def reset(repo, mode, treeish="HEAD"): """Reset current HEAD to the specified state. Args: repo: Path to repository mode: Mode ("hard", "soft", "mixed") treeish: Treeish to reset to """ if mode != "hard": raise ValueError("hard is the only mode currently supported") with open_repo_closing(repo) as r: tree = parse_tree(r, treeish) r.reset_index(tree.id) def push(repo, remote_location, refspecs, outstream=default_bytes_out_stream, errstream=default_bytes_err_stream, **kwargs): """Remote push with dulwich via dulwich.client Args: repo: Path to repository remote_location: Location of the remote refspecs: Refs to push to remote outstream: A stream file to write output errstream: A stream file to write errors """ # Open the repo with open_repo_closing(repo) as r: # Get the client and path client, path = get_transport_and_path( remote_location, config=r.get_config_stack(), **kwargs) selected_refs = [] def update_refs(refs): selected_refs.extend(parse_reftuples(r.refs, refs, refspecs)) new_refs = {} # TODO: Handle selected_refs == {None: None} for (lh, rh, force) in selected_refs: if lh is None: new_refs[rh] = ZERO_SHA else: new_refs[rh] = r.refs[lh] return new_refs err_encoding = getattr(errstream, 'encoding', None) or DEFAULT_ENCODING remote_location_bytes = client.get_url(path).encode(err_encoding) try: client.send_pack( path, update_refs, generate_pack_data=r.generate_pack_data, progress=errstream.write) errstream.write( b"Push to " + remote_location_bytes + b" successful.\n") except UpdateRefsError as e: errstream.write(b"Push to " + remote_location_bytes + b" failed -> " + e.message.encode(err_encoding) + b"\n") except SendPackError as e: errstream.write(b"Push to " + remote_location_bytes + b" failed -> " + e.args[0] + b"\n") def pull(repo, remote_location=None, refspecs=None, outstream=default_bytes_out_stream, errstream=default_bytes_err_stream, **kwargs): """Pull from remote via dulwich.client Args: repo: Path to repository remote_location: Location of the remote refspec: refspecs to fetch outstream: A stream file to write to output errstream: A stream file to write to errors """ # Open the repo with open_repo_closing(repo) as r: if remote_location is None: config = r.get_config() remote_name = get_branch_remote(r.path) section = (b'remote', remote_name) if config.has_section(section): url = config.get(section, 'url') remote_location = url.decode() if refspecs is None: refspecs = [b"HEAD"] selected_refs = [] def determine_wants(remote_refs): selected_refs.extend( parse_reftuples(remote_refs, r.refs, refspecs)) return [remote_refs[lh] for (lh, rh, force) in selected_refs] client, path = get_transport_and_path( remote_location, config=r.get_config_stack(), **kwargs) fetch_result = client.fetch( path, r, progress=errstream.write, determine_wants=determine_wants) for (lh, rh, force) in selected_refs: r.refs[rh] = fetch_result.refs[lh] if selected_refs: r[b'HEAD'] = fetch_result.refs[selected_refs[0][1]] # Perform 'git checkout .' - syncs staged changes tree = r[b"HEAD"].tree r.reset_index(tree=tree) def status(repo=".", ignored=False): """Returns staged, unstaged, and untracked changes relative to the HEAD. Args: repo: Path to repository or repository object ignored: Whether to include ignored files in `untracked` Returns: GitStatus tuple, staged - dict with lists of staged paths (diff index/HEAD) unstaged - list of unstaged paths (diff index/working-tree) untracked - list of untracked, un-ignored & non-.git paths """ with open_repo_closing(repo) as r: # 1. Get status of staged tracked_changes = get_tree_changes(r) # 2. Get status of unstaged index = r.open_index() normalizer = r.get_blob_normalizer() filter_callback = normalizer.checkin_normalize unstaged_changes = list( get_unstaged_changes(index, r.path, filter_callback) ) ignore_manager = IgnoreFilterManager.from_repo(r) untracked_paths = get_untracked_paths(r.path, r.path, index) if ignored: untracked_changes = list(untracked_paths) else: untracked_changes = [ p for p in untracked_paths if not ignore_manager.is_ignored(p)] return GitStatus(tracked_changes, unstaged_changes, untracked_changes) def _walk_working_dir_paths(frompath, basepath): """Get path, is_dir for files in working dir from frompath Args: frompath: Path to begin walk basepath: Path to compare to """ for dirpath, dirnames, filenames in os.walk(frompath): # Skip .git and below. if '.git' in dirnames: dirnames.remove('.git') if dirpath != basepath: continue if '.git' in filenames: filenames.remove('.git') if dirpath != basepath: continue if dirpath != frompath: yield dirpath, True for filename in filenames: filepath = os.path.join(dirpath, filename) yield filepath, False def get_untracked_paths(frompath, basepath, index): """Get untracked paths. Args: ;param frompath: Path to walk basepath: Path to compare to index: Index to check against """ for ap, is_dir in _walk_working_dir_paths(frompath, basepath): if not is_dir: ip = path_to_tree_path(basepath, ap) if ip not in index: yield os.path.relpath(ap, frompath) def get_tree_changes(repo): """Return add/delete/modify changes to tree by comparing index to HEAD. Args: repo: repo path or object Returns: dict with lists for each type of change """ with open_repo_closing(repo) as r: index = r.open_index() # Compares the Index to the HEAD & determines changes # Iterate through the changes and report add/delete/modify # TODO: call out to dulwich.diff_tree somehow. tracked_changes = { 'add': [], 'delete': [], 'modify': [], } try: tree_id = r[b'HEAD'].tree except KeyError: tree_id = None for change in index.changes_from_tree(r.object_store, tree_id): if not change[0][0]: tracked_changes['add'].append(change[0][1]) elif not change[0][1]: tracked_changes['delete'].append(change[0][0]) elif change[0][0] == change[0][1]: tracked_changes['modify'].append(change[0][0]) else: raise AssertionError('git mv ops not yet supported') return tracked_changes def daemon(path=".", address=None, port=None): """Run a daemon serving Git requests over TCP/IP. Args: path: Path to the directory to serve. address: Optional address to listen on (defaults to ::) 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. Args: path: Path to the directory to serve address: Optional address to listen on (defaults to ::) 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. Args: path: Path to the repository inf: Input stream to communicate with client outf: Output stream to communicate with client """ if outf is None: outf = getattr(sys.stdout, 'buffer', sys.stdout) if inf is None: inf = getattr(sys.stdin, 'buffer', sys.stdin) path = os.path.expanduser(path) backend = FileSystemBackend(path) def send_fn(data): outf.write(data) outf.flush() proto = Protocol(inf.read, send_fn) handler = UploadPackHandler(backend, [path], proto) # FIXME: Catch exceptions and write a single-line summary to outf. handler.handle() return 0 def receive_pack(path=".", inf=None, outf=None): """Receive a pack file after negotiating its contents using smart protocol. Args: path: Path to the repository inf: Input stream to communicate with client outf: Output stream to communicate with client """ if outf is None: outf = getattr(sys.stdout, 'buffer', sys.stdout) if inf is None: inf = getattr(sys.stdin, 'buffer', sys.stdin) path = os.path.expanduser(path) backend = FileSystemBackend(path) def send_fn(data): outf.write(data) outf.flush() proto = Protocol(inf.read, send_fn) handler = ReceivePackHandler(backend, [path], proto) # FIXME: Catch exceptions and write a single-line summary to outf. handler.handle() return 0 def _make_branch_ref(name): if getattr(name, 'encode', None): name = name.encode(DEFAULT_ENCODING) return LOCAL_BRANCH_PREFIX + name def _make_tag_ref(name): if getattr(name, 'encode', None): name = name.encode(DEFAULT_ENCODING) return b"refs/tags/" + name def branch_delete(repo, name): """Delete a branch. Args: repo: Path to the repository name: Name of the branch """ with open_repo_closing(repo) as r: if isinstance(name, list): names = name else: names = [name] for name in names: del r.refs[_make_branch_ref(name)] def branch_create(repo, name, objectish=None, force=False): """Create a branch. Args: repo: Path to the repository name: Name of the new branch objectish: Target object to point new branch at (defaults to HEAD) force: Force creation of branch, even if it already exists """ with open_repo_closing(repo) as r: if objectish is None: objectish = "HEAD" object = parse_object(r, objectish) refname = _make_branch_ref(name) ref_message = b"branch: Created from " + objectish.encode('utf-8') if force: r.refs.set_if_equals(refname, None, object.id, message=ref_message) else: if not r.refs.add_if_new(refname, object.id, message=ref_message): raise KeyError("Branch with name %s already exists." % name) def branch_list(repo): """List all branches. Args: repo: Path to the repository """ with open_repo_closing(repo) as r: return r.refs.keys(base=LOCAL_BRANCH_PREFIX) def active_branch(repo): """Return the active branch in the repository, if any. Args: repo: Repository to open Returns: branch name Raises: KeyError: if the repository does not have a working tree IndexError: if HEAD is floating """ with open_repo_closing(repo) as r: active_ref = r.refs.follow(b'HEAD')[0][1] if not active_ref.startswith(LOCAL_BRANCH_PREFIX): raise ValueError(active_ref) return active_ref[len(LOCAL_BRANCH_PREFIX):] def get_branch_remote(repo): """Return the active branch's remote name, if any. Args: repo: Repository to open Returns: remote name Raises: KeyError: if the repository does not have a working tree """ with open_repo_closing(repo) as r: branch_name = active_branch(r.path) config = r.get_config() try: remote_name = config.get((b'branch', branch_name), 'remote') except KeyError: remote_name = b'origin' return remote_name def fetch(repo, remote_location, remote_name=b'origin', outstream=sys.stdout, errstream=default_bytes_err_stream, message=None, depth=None, prune=False, prune_tags=False, **kwargs): """Fetch objects from a remote server. Args: repo: Path to the repository remote_location: String identifying a remote server remote_name: Name for remote server outstream: Output stream (defaults to stdout) errstream: Error stream (defaults to stderr) message: Reflog message (defaults to b"fetch: from ") depth: Depth to fetch at prune: Prune remote removed refs prune_tags: Prune reomte removed tags Returns: Dictionary with refs on the remote """ if message is None: message = b'fetch: from ' + remote_location.encode("utf-8") with open_repo_closing(repo) as r: client, path = get_transport_and_path( remote_location, config=r.get_config_stack(), **kwargs) fetch_result = client.fetch(path, r, progress=errstream.write, depth=depth) stripped_refs = strip_peeled_refs(fetch_result.refs) branches = { n[len(LOCAL_BRANCH_PREFIX):]: v for (n, v) in stripped_refs.items() if n.startswith(LOCAL_BRANCH_PREFIX)} r.refs.import_refs( b'refs/remotes/' + remote_name, branches, message=message, prune=prune) tags = { n[len(b'refs/tags/'):]: v for (n, v) in stripped_refs.items() if n.startswith(b'refs/tags/') and not n.endswith(ANNOTATED_TAG_SUFFIX)} r.refs.import_refs( b'refs/tags', tags, message=message, prune=prune_tags) return fetch_result.refs def ls_remote(remote, config=None, **kwargs): """List the refs in a remote. Args: remote: Remote repository location config: Configuration to use Returns: Dictionary with remote refs """ if config is None: config = StackedConfig.default() client, host_path = get_transport_and_path(remote, config=config, **kwargs) return client.get_refs(host_path) def repack(repo): """Repack loose files in a repository. Currently this only packs loose objects. Args: 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. Args: repo: Path to the repository object_ids: List of object ids to write packf: File-like object to write to idxf: File-like object to write to (can be None) """ with open_repo_closing(repo) as r: entries, data_sum = write_pack_objects( packf, r.object_store.iter_shas((oid, None) for oid in object_ids), delta_window_size=delta_window_size) if idxf is not None: entries = sorted([(k, v[0], v[1]) for (k, v) in entries.items()]) write_pack_index(idxf, entries, data_sum) def ls_tree(repo, treeish=b"HEAD", outstream=sys.stdout, recursive=False, name_only=False): """List contents of a tree. Args: repo: Path to the repository tree_ish: Tree id to list outstream: Output stream (defaults to stdout) recursive: Whether to recursively list files name_only: Only print item name """ def list_tree(store, treeid, base): for (name, mode, sha) in store[treeid].iteritems(): if base: name = posixpath.join(base, name) if name_only: outstream.write(name + b"\n") else: outstream.write(pretty_format_tree_entry(name, mode, sha)) if stat.S_ISDIR(mode) and recursive: list_tree(store, sha, name) with open_repo_closing(repo) as r: tree = parse_tree(r, treeish) list_tree(r.object_store, tree.id, "") def remote_add(repo, name, url): """Add a remote. Args: repo: Path to the repository name: Remote name url: Remote URL """ if not isinstance(name, bytes): name = name.encode(DEFAULT_ENCODING) if not isinstance(url, bytes): url = url.encode(DEFAULT_ENCODING) with open_repo_closing(repo) as r: c = r.get_config() section = (b'remote', name) if c.has_section(section): raise RemoteExists(section) c.set(section, b"url", url) c.write_to_path() def check_ignore(repo, paths, no_index=False): """Debug gitignore files. Args: repo: Path to the repository paths: List of paths to check for no_index: Don't check index Returns: List of ignored files """ with open_repo_closing(repo) as r: index = r.open_index() ignore_manager = IgnoreFilterManager.from_repo(r) for path in paths: if not no_index and path_to_tree_path(r.path, path) in index: continue if os.path.isabs(path): path = os.path.relpath(path, r.path) if ignore_manager.is_ignored(path): yield path def update_head(repo, target, detached=False, new_branch=None): """Update HEAD to point at a new branch/commit. Note that this does not actually update the working tree. Args: repo: Path to the repository detach: Create a detached head target: Branch or committish to switch to new_branch: New branch to create """ with open_repo_closing(repo) as r: if new_branch is not None: to_set = _make_branch_ref(new_branch) else: to_set = b"HEAD" if detached: # TODO(jelmer): Provide some way so that the actual ref gets # updated rather than what it points to, so the delete isn't # necessary. del r.refs[to_set] r.refs[to_set] = parse_commit(r, target).id else: r.refs.set_symbolic_ref(to_set, parse_ref(r, target)) if new_branch is not None: r.refs.set_symbolic_ref(b"HEAD", to_set) def check_mailmap(repo, contact): """Check canonical name and email of contact. Args: repo: Path to the repository contact: Contact name and/or email Returns: Canonical contact data """ with open_repo_closing(repo) as r: from dulwich.mailmap import Mailmap import errno try: mailmap = Mailmap.from_path(os.path.join(r.path, '.mailmap')) except IOError as e: if e.errno != errno.ENOENT: raise mailmap = Mailmap() return mailmap.lookup(contact) def fsck(repo): """Check a repository. Args: repo: A path to the repository Returns: Iterator over errors/warnings """ with open_repo_closing(repo) as r: # TODO(jelmer): check pack files # TODO(jelmer): check graph # TODO(jelmer): check refs for sha in r.object_store: o = r.object_store[sha] try: o.check() except Exception as e: yield (sha, e) def stash_list(repo): """List all stashes in a repository.""" with open_repo_closing(repo) as r: from dulwich.stash import Stash stash = Stash.from_repo(r) return enumerate(list(stash.stashes())) def stash_push(repo): """Push a new stash onto the stack.""" with open_repo_closing(repo) as r: from dulwich.stash import Stash stash = Stash.from_repo(r) stash.push() def stash_pop(repo): """Pop a new stash from the stack.""" with open_repo_closing(repo) as r: from dulwich.stash import Stash stash = Stash.from_repo(r) stash.pop() def ls_files(repo): """List all files in an index.""" with open_repo_closing(repo) as r: return sorted(r.open_index()) def describe(repo): """Describe the repository version. Args: projdir: git repository root Returns: a string description of the current git revision Examples: "gabcdefh", "v0.1" or "v0.1-5-gabcdefh". """ # Get the repository with open_repo_closing(repo) as r: # Get a list of all tags refs = r.get_refs() tags = {} for key, value in refs.items(): key = key.decode() obj = r.get_object(value) if u'tags' not in key: continue _, tag = key.rsplit(u'/', 1) try: commit = obj.object except AttributeError: continue else: commit = r.get_object(commit[1]) tags[tag] = [ datetime.datetime(*time.gmtime(commit.commit_time)[:6]), commit.id.decode('ascii'), ] sorted_tags = sorted(tags.items(), key=lambda tag: tag[1][0], reverse=True) # If there are no tags, return the current commit if len(sorted_tags) == 0: return 'g{}'.format(r[r.head()].id.decode('ascii')[:7]) # We're now 0 commits from the top commit_count = 0 # Get the latest commit latest_commit = r[r.head()] # Walk through all commits walker = r.get_walker() for entry in walker: # Check if tag commit_id = entry.commit.id.decode('ascii') for tag in sorted_tags: tag_name = tag[0] tag_commit = tag[1][1] if commit_id == tag_commit: if commit_count == 0: return tag_name else: return '{}-{}-g{}'.format( tag_name, commit_count, latest_commit.id.decode('ascii')[:7]) commit_count += 1 # Return plain commit if no parent tag can be found return 'g{}'.format(latest_commit.id.decode('ascii')[:7]) def get_object_by_path(repo, path, committish=None): """Get an object by path. Args: repo: A path to the repository path: Path to look up committish: Commit to look up path in Returns: A `ShaFile` object """ if committish is None: committish = "HEAD" # Get the repository with open_repo_closing(repo) as r: commit = parse_commit(r, committish) base_tree = commit.tree if not isinstance(path, bytes): path = commit_encode(commit, path) (mode, sha) = tree_lookup_path( r.object_store.__getitem__, base_tree, path) return r[sha] def write_tree(repo): """Write a tree object from the index. Args: repo: Repository for which to write tree Returns: tree id for the tree that was written """ with open_repo_closing(repo) as r: return r.open_index().commit(r.object_store) diff --git a/dulwich/tests/test_repository.py b/dulwich/tests/test_repository.py index ef543c0a..37158420 100644 --- a/dulwich/tests/test_repository.py +++ b/dulwich/tests/test_repository.py @@ -1,1149 +1,1149 @@ # -*- coding: utf-8 -*- # test_repository.py -- tests for repository.py # Copyright (C) 2007 James Westby # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """Tests for the repository.""" import locale import os import stat import shutil import sys import tempfile import warnings from dulwich import errors from dulwich.object_store import ( tree_lookup_path, ) from dulwich import objects from dulwich.config import Config from dulwich.errors import NotGitRepository from dulwich.repo import ( InvalidUserIdentity, Repo, MemoryRepo, check_user_identity, ) from dulwich.tests import ( TestCase, skipIf, ) from dulwich.tests.utils import ( open_repo, tear_down_repo, setup_warning_catcher, ) missing_sha = b'b91fa4d900e17e99b433218e988c4eb4a3e9a097' class CreateRepositoryTests(TestCase): def assertFileContentsEqual(self, expected, repo, path): f = repo.get_named_file(path) if not f: self.assertEqual(expected, None) else: with f: self.assertEqual(expected, f.read()) def _check_repo_contents(self, repo, expect_bare): self.assertEqual(expect_bare, repo.bare) self.assertFileContentsEqual( b'Unnamed repository', repo, 'description') self.assertFileContentsEqual( b'', repo, os.path.join('info', 'exclude')) self.assertFileContentsEqual(None, repo, 'nonexistent file') barestr = b'bare = ' + str(expect_bare).lower().encode('ascii') with repo.get_named_file('config') as f: config_text = f.read() self.assertTrue(barestr in config_text, "%r" % config_text) expect_filemode = sys.platform != 'win32' barestr = b'filemode = ' + str(expect_filemode).lower().encode('ascii') with repo.get_named_file('config') as f: config_text = f.read() self.assertTrue(barestr in config_text, "%r" % config_text) def test_create_memory(self): repo = MemoryRepo.init_bare([], {}) self._check_repo_contents(repo, True) def test_create_disk_bare(self): tmp_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, tmp_dir) repo = Repo.init_bare(tmp_dir) self.assertEqual(tmp_dir, repo._controldir) self._check_repo_contents(repo, True) def test_create_disk_non_bare(self): tmp_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, tmp_dir) repo = Repo.init(tmp_dir) self.assertEqual(os.path.join(tmp_dir, '.git'), repo._controldir) self._check_repo_contents(repo, False) def test_create_disk_non_bare_mkdir(self): tmp_dir = tempfile.mkdtemp() target_dir = os.path.join(tmp_dir, "target") self.addCleanup(shutil.rmtree, tmp_dir) repo = Repo.init(target_dir, mkdir=True) self.assertEqual(os.path.join(target_dir, '.git'), repo._controldir) self._check_repo_contents(repo, False) def test_create_disk_bare_mkdir(self): tmp_dir = tempfile.mkdtemp() target_dir = os.path.join(tmp_dir, "target") self.addCleanup(shutil.rmtree, tmp_dir) repo = Repo.init_bare(target_dir, mkdir=True) self.assertEqual(target_dir, repo._controldir) self._check_repo_contents(repo, True) class MemoryRepoTests(TestCase): def test_set_description(self): r = MemoryRepo.init_bare([], {}) description = b"Some description" r.set_description(description) self.assertEqual(description, r.get_description()) class RepositoryRootTests(TestCase): def mkdtemp(self): return tempfile.mkdtemp() def open_repo(self, name): temp_dir = self.mkdtemp() repo = open_repo(name, temp_dir) self.addCleanup(tear_down_repo, repo) return repo def test_simple_props(self): r = self.open_repo('a.git') self.assertEqual(r.controldir(), r.path) def test_setitem(self): r = self.open_repo('a.git') r[b"refs/tags/foo"] = b'a90fa2d900a17e99b433217e988c4eb4a2e9a097' self.assertEqual(b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', r[b"refs/tags/foo"].id) def test_getitem_unicode(self): r = self.open_repo('a.git') test_keys = [ (b'refs/heads/master', True), (b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', True), (b'11' * 19 + b'--', False), ] for k, contained in test_keys: self.assertEqual(k in r, contained) # Avoid deprecation warning under Py3.2+ if getattr(self, 'assertRaisesRegex', None): assertRaisesRegexp = self.assertRaisesRegex else: assertRaisesRegexp = self.assertRaisesRegexp for k, _ in test_keys: assertRaisesRegexp( TypeError, "'name' must be bytestring, not int", r.__getitem__, 12 ) def test_delitem(self): r = self.open_repo('a.git') del r[b'refs/heads/master'] self.assertRaises(KeyError, lambda: r[b'refs/heads/master']) del r[b'HEAD'] self.assertRaises(KeyError, lambda: r[b'HEAD']) self.assertRaises(ValueError, r.__delitem__, b'notrefs/foo') def test_get_refs(self): r = self.open_repo('a.git') self.assertEqual({ b'HEAD': b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', b'refs/heads/master': b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', b'refs/tags/mytag': b'28237f4dc30d0d462658d6b937b08a0f0b6ef55a', b'refs/tags/mytag-packed': b'b0931cadc54336e78a1d980420e3268903b57a50', }, r.get_refs()) def test_head(self): r = self.open_repo('a.git') self.assertEqual(r.head(), b'a90fa2d900a17e99b433217e988c4eb4a2e9a097') def test_get_object(self): r = self.open_repo('a.git') obj = r.get_object(r.head()) self.assertEqual(obj.type_name, b'commit') def test_get_object_non_existant(self): r = self.open_repo('a.git') self.assertRaises(KeyError, r.get_object, missing_sha) def test_contains_object(self): r = self.open_repo('a.git') self.assertTrue(r.head() in r) def test_contains_ref(self): r = self.open_repo('a.git') self.assertTrue(b"HEAD" in r) def test_get_no_description(self): r = self.open_repo('a.git') self.assertIs(None, r.get_description()) def test_get_description(self): r = self.open_repo('a.git') with open(os.path.join(r.path, 'description'), 'wb') as f: f.write(b"Some description") self.assertEqual(b"Some description", r.get_description()) def test_set_description(self): r = self.open_repo('a.git') description = b"Some description" r.set_description(description) self.assertEqual(description, r.get_description()) def test_contains_missing(self): r = self.open_repo('a.git') self.assertFalse(b"bar" in r) def test_get_peeled(self): # unpacked ref r = self.open_repo('a.git') tag_sha = b'28237f4dc30d0d462658d6b937b08a0f0b6ef55a' self.assertNotEqual(r[tag_sha].sha().hexdigest(), r.head()) self.assertEqual(r.get_peeled(b'refs/tags/mytag'), r.head()) # packed ref with cached peeled value packed_tag_sha = b'b0931cadc54336e78a1d980420e3268903b57a50' parent_sha = r[r.head()].parents[0] self.assertNotEqual(r[packed_tag_sha].sha().hexdigest(), parent_sha) self.assertEqual(r.get_peeled(b'refs/tags/mytag-packed'), parent_sha) # TODO: add more corner cases to test repo def test_get_peeled_not_tag(self): r = self.open_repo('a.git') self.assertEqual(r.get_peeled(b'HEAD'), r.head()) def test_get_walker(self): r = self.open_repo('a.git') # include defaults to [r.head()] self.assertEqual( [e.commit.id for e in r.get_walker()], [r.head(), b'2a72d929692c41d8554c07f6301757ba18a65d91']) self.assertEqual( [e.commit.id for e in r.get_walker([b'2a72d929692c41d8554c07f6301757ba18a65d91'])], [b'2a72d929692c41d8554c07f6301757ba18a65d91']) self.assertEqual( [e.commit.id for e in r.get_walker(b'2a72d929692c41d8554c07f6301757ba18a65d91')], [b'2a72d929692c41d8554c07f6301757ba18a65d91']) def assertFilesystemHidden(self, path): if sys.platform != 'win32': return import ctypes from ctypes.wintypes import DWORD, LPCWSTR GetFileAttributesW = ctypes.WINFUNCTYPE(DWORD, LPCWSTR)( ('GetFileAttributesW', ctypes.windll.kernel32)) self.assertTrue(2 & GetFileAttributesW(path)) def test_init_existing(self): tmp_dir = self.mkdtemp() self.addCleanup(shutil.rmtree, tmp_dir) t = Repo.init(tmp_dir) self.addCleanup(t.close) self.assertEqual(os.listdir(tmp_dir), ['.git']) self.assertFilesystemHidden(os.path.join(tmp_dir, '.git')) def test_init_mkdir(self): tmp_dir = self.mkdtemp() self.addCleanup(shutil.rmtree, tmp_dir) repo_dir = os.path.join(tmp_dir, 'a-repo') t = Repo.init(repo_dir, mkdir=True) self.addCleanup(t.close) self.assertEqual(os.listdir(repo_dir), ['.git']) self.assertFilesystemHidden(os.path.join(repo_dir, '.git')) def test_init_mkdir_unicode(self): repo_name = u'\xa7' try: repo_name.encode(sys.getfilesystemencoding()) except UnicodeEncodeError: self.skipTest('filesystem lacks unicode support') tmp_dir = self.mkdtemp() self.addCleanup(shutil.rmtree, tmp_dir) repo_dir = os.path.join(tmp_dir, repo_name) t = Repo.init(repo_dir, mkdir=True) self.addCleanup(t.close) self.assertEqual(os.listdir(repo_dir), ['.git']) self.assertFilesystemHidden(os.path.join(repo_dir, '.git')) @skipIf(sys.platform == 'win32', 'fails on Windows') def test_fetch(self): r = self.open_repo('a.git') tmp_dir = self.mkdtemp() self.addCleanup(shutil.rmtree, tmp_dir) t = Repo.init(tmp_dir) self.addCleanup(t.close) r.fetch(t) self.assertIn(b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', t) self.assertIn(b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', t) self.assertIn(b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', t) self.assertIn(b'28237f4dc30d0d462658d6b937b08a0f0b6ef55a', t) self.assertIn(b'b0931cadc54336e78a1d980420e3268903b57a50', t) @skipIf(sys.platform == 'win32', 'fails on Windows') def test_fetch_ignores_missing_refs(self): r = self.open_repo('a.git') missing = b'1234566789123456789123567891234657373833' r.refs[b'refs/heads/blah'] = missing tmp_dir = self.mkdtemp() self.addCleanup(shutil.rmtree, tmp_dir) t = Repo.init(tmp_dir) self.addCleanup(t.close) r.fetch(t) self.assertIn(b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', t) self.assertIn(b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', t) self.assertIn(b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', t) self.assertIn(b'28237f4dc30d0d462658d6b937b08a0f0b6ef55a', t) self.assertIn(b'b0931cadc54336e78a1d980420e3268903b57a50', t) self.assertNotIn(missing, t) def test_clone(self): r = self.open_repo('a.git') tmp_dir = self.mkdtemp() self.addCleanup(shutil.rmtree, tmp_dir) with r.clone(tmp_dir, mkdir=False) as t: self.assertEqual({ b'HEAD': b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', b'refs/remotes/origin/master': b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', b'refs/heads/master': b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', b'refs/tags/mytag': b'28237f4dc30d0d462658d6b937b08a0f0b6ef55a', b'refs/tags/mytag-packed': b'b0931cadc54336e78a1d980420e3268903b57a50', }, t.refs.as_dict()) shas = [e.commit.id for e in r.get_walker()] self.assertEqual(shas, [t.head(), b'2a72d929692c41d8554c07f6301757ba18a65d91']) c = t.get_config() encoded_path = r.path if not isinstance(encoded_path, bytes): encoded_path = encoded_path.encode(sys.getfilesystemencoding()) self.assertEqual(encoded_path, c.get((b'remote', b'origin'), b'url')) self.assertEqual( b'+refs/heads/*:refs/remotes/origin/*', c.get((b'remote', b'origin'), b'fetch')) def test_clone_no_head(self): temp_dir = self.mkdtemp() self.addCleanup(shutil.rmtree, temp_dir) repo_dir = os.path.join(os.path.dirname(__file__), 'data', 'repos') dest_dir = os.path.join(temp_dir, 'a.git') shutil.copytree(os.path.join(repo_dir, 'a.git'), dest_dir, symlinks=True) r = Repo(dest_dir) del r.refs[b"refs/heads/master"] del r.refs[b"HEAD"] t = r.clone(os.path.join(temp_dir, 'b.git'), mkdir=True) self.assertEqual({ b'refs/tags/mytag': b'28237f4dc30d0d462658d6b937b08a0f0b6ef55a', b'refs/tags/mytag-packed': b'b0931cadc54336e78a1d980420e3268903b57a50', }, t.refs.as_dict()) def test_clone_empty(self): """Test clone() doesn't crash if HEAD points to a non-existing ref. This simulates cloning server-side bare repository either when it is still empty or if user renames master branch and pushes private repo to the server. Non-bare repo HEAD always points to an existing ref. """ r = self.open_repo('empty.git') tmp_dir = self.mkdtemp() self.addCleanup(shutil.rmtree, tmp_dir) r.clone(tmp_dir, mkdir=False, bare=True) def test_clone_bare(self): r = self.open_repo('a.git') tmp_dir = self.mkdtemp() self.addCleanup(shutil.rmtree, tmp_dir) t = r.clone(tmp_dir, mkdir=False) t.close() def test_clone_checkout_and_bare(self): r = self.open_repo('a.git') tmp_dir = self.mkdtemp() self.addCleanup(shutil.rmtree, tmp_dir) self.assertRaises(ValueError, r.clone, tmp_dir, mkdir=False, checkout=True, bare=True) def test_merge_history(self): r = self.open_repo('simple_merge.git') shas = [e.commit.id for e in r.get_walker()] self.assertEqual(shas, [b'5dac377bdded4c9aeb8dff595f0faeebcc8498cc', b'ab64bbdcc51b170d21588e5c5d391ee5c0c96dfd', b'4cffe90e0a41ad3f5190079d7c8f036bde29cbe6', b'60dacdc733de308bb77bb76ce0fb0f9b44c9769e', b'0d89f20333fbb1d2f3a94da77f4981373d8f4310']) def test_out_of_order_merge(self): """Test that revision history is ordered by date, not parent order.""" r = self.open_repo('ooo_merge.git') shas = [e.commit.id for e in r.get_walker()] self.assertEqual(shas, [b'7601d7f6231db6a57f7bbb79ee52e4d462fd44d1', b'f507291b64138b875c28e03469025b1ea20bc614', b'fb5b0425c7ce46959bec94d54b9a157645e114f5', b'f9e39b120c68182a4ba35349f832d0e4e61f485c']) def test_get_tags_empty(self): r = self.open_repo('ooo_merge.git') self.assertEqual({}, r.refs.as_dict(b'refs/tags')) def test_get_config(self): r = self.open_repo('ooo_merge.git') self.assertIsInstance(r.get_config(), Config) def test_get_config_stack(self): r = self.open_repo('ooo_merge.git') self.assertIsInstance(r.get_config_stack(), Config) @skipIf(not getattr(os, 'symlink', None), 'Requires symlink support') def test_submodule(self): temp_dir = self.mkdtemp() self.addCleanup(shutil.rmtree, temp_dir) repo_dir = os.path.join(os.path.dirname(__file__), 'data', 'repos') shutil.copytree(os.path.join(repo_dir, 'a.git'), os.path.join(temp_dir, 'a.git'), symlinks=True) rel = os.path.relpath(os.path.join(repo_dir, 'submodule'), temp_dir) os.symlink(os.path.join(rel, 'dotgit'), os.path.join(temp_dir, '.git')) with Repo(temp_dir) as r: self.assertEqual(r.head(), b'a90fa2d900a17e99b433217e988c4eb4a2e9a097') def test_common_revisions(self): """ This test demonstrates that ``find_common_revisions()`` actually returns common heads, not revisions; dulwich already uses ``find_common_revisions()`` in such a manner (see ``Repo.fetch_objects()``). """ expected_shas = set([b'60dacdc733de308bb77bb76ce0fb0f9b44c9769e']) # Source for objects. r_base = self.open_repo('simple_merge.git') # Re-create each-side of the merge in simple_merge.git. # # Since the trees and blobs are missing, the repository created is # corrupted, but we're only checking for commits for the purpose of # this test, so it's immaterial. r1_dir = self.mkdtemp() self.addCleanup(shutil.rmtree, r1_dir) r1_commits = [b'ab64bbdcc51b170d21588e5c5d391ee5c0c96dfd', # HEAD b'60dacdc733de308bb77bb76ce0fb0f9b44c9769e', b'0d89f20333fbb1d2f3a94da77f4981373d8f4310'] r2_dir = self.mkdtemp() self.addCleanup(shutil.rmtree, r2_dir) r2_commits = [b'4cffe90e0a41ad3f5190079d7c8f036bde29cbe6', # HEAD b'60dacdc733de308bb77bb76ce0fb0f9b44c9769e', b'0d89f20333fbb1d2f3a94da77f4981373d8f4310'] r1 = Repo.init_bare(r1_dir) for c in r1_commits: r1.object_store.add_object(r_base.get_object(c)) r1.refs[b'HEAD'] = r1_commits[0] r2 = Repo.init_bare(r2_dir) for c in r2_commits: r2.object_store.add_object(r_base.get_object(c)) r2.refs[b'HEAD'] = r2_commits[0] # Finally, the 'real' testing! shas = r2.object_store.find_common_revisions(r1.get_graph_walker()) self.assertEqual(set(shas), expected_shas) shas = r1.object_store.find_common_revisions(r2.get_graph_walker()) self.assertEqual(set(shas), expected_shas) def test_shell_hook_pre_commit(self): if os.name != 'posix': self.skipTest('shell hook tests requires POSIX shell') pre_commit_fail = """#!/bin/sh exit 1 """ pre_commit_success = """#!/bin/sh exit 0 """ repo_dir = os.path.join(self.mkdtemp()) self.addCleanup(shutil.rmtree, repo_dir) r = Repo.init(repo_dir) self.addCleanup(r.close) pre_commit = os.path.join(r.controldir(), 'hooks', 'pre-commit') with open(pre_commit, 'w') as f: f.write(pre_commit_fail) os.chmod(pre_commit, stat.S_IREAD | stat.S_IWRITE | stat.S_IEXEC) self.assertRaises(errors.CommitError, r.do_commit, 'failed commit', committer='Test Committer ', author='Test Author ', commit_timestamp=12345, commit_timezone=0, author_timestamp=12345, author_timezone=0) with open(pre_commit, 'w') as f: f.write(pre_commit_success) os.chmod(pre_commit, stat.S_IREAD | stat.S_IWRITE | stat.S_IEXEC) commit_sha = r.do_commit( b'empty commit', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12395, commit_timezone=0, author_timestamp=12395, author_timezone=0) self.assertEqual([], r[commit_sha].parents) def test_shell_hook_commit_msg(self): if os.name != 'posix': self.skipTest('shell hook tests requires POSIX shell') commit_msg_fail = """#!/bin/sh exit 1 """ commit_msg_success = """#!/bin/sh exit 0 """ repo_dir = self.mkdtemp() self.addCleanup(shutil.rmtree, repo_dir) r = Repo.init(repo_dir) self.addCleanup(r.close) commit_msg = os.path.join(r.controldir(), 'hooks', 'commit-msg') with open(commit_msg, 'w') as f: f.write(commit_msg_fail) os.chmod(commit_msg, stat.S_IREAD | stat.S_IWRITE | stat.S_IEXEC) self.assertRaises(errors.CommitError, r.do_commit, b'failed commit', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12345, commit_timezone=0, author_timestamp=12345, author_timezone=0) with open(commit_msg, 'w') as f: f.write(commit_msg_success) os.chmod(commit_msg, stat.S_IREAD | stat.S_IWRITE | stat.S_IEXEC) commit_sha = r.do_commit( b'empty commit', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12395, commit_timezone=0, author_timestamp=12395, author_timezone=0) self.assertEqual([], r[commit_sha].parents) def test_shell_hook_post_commit(self): if os.name != 'posix': self.skipTest('shell hook tests requires POSIX shell') repo_dir = self.mkdtemp() self.addCleanup(shutil.rmtree, repo_dir) r = Repo.init(repo_dir) self.addCleanup(r.close) (fd, path) = tempfile.mkstemp(dir=repo_dir) os.close(fd) post_commit_msg = """#!/bin/sh rm """ + path + """ """ root_sha = r.do_commit( b'empty commit', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12345, commit_timezone=0, author_timestamp=12345, author_timezone=0) self.assertEqual([], r[root_sha].parents) post_commit = os.path.join(r.controldir(), 'hooks', 'post-commit') with open(post_commit, 'wb') as f: f.write(post_commit_msg.encode(locale.getpreferredencoding())) os.chmod(post_commit, stat.S_IREAD | stat.S_IWRITE | stat.S_IEXEC) commit_sha = r.do_commit( b'empty commit', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12345, commit_timezone=0, author_timestamp=12345, author_timezone=0) self.assertEqual([root_sha], r[commit_sha].parents) self.assertFalse(os.path.exists(path)) post_commit_msg_fail = """#!/bin/sh exit 1 """ with open(post_commit, 'w') as f: f.write(post_commit_msg_fail) os.chmod(post_commit, stat.S_IREAD | stat.S_IWRITE | stat.S_IEXEC) warnings.simplefilter("always", UserWarning) self.addCleanup(warnings.resetwarnings) warnings_list, restore_warnings = setup_warning_catcher() self.addCleanup(restore_warnings) commit_sha2 = r.do_commit( b'empty commit', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12345, commit_timezone=0, author_timestamp=12345, author_timezone=0) expected_warning = UserWarning( 'post-commit hook failed: Hook post-commit exited with ' 'non-zero status',) for w in warnings_list: if (type(w) == type(expected_warning) and w.args == expected_warning.args): break else: raise AssertionError( 'Expected warning %r not in %r' % (expected_warning, warnings_list)) self.assertEqual([commit_sha], r[commit_sha2].parents) def test_as_dict(self): def check(repo): self.assertEqual( repo.refs.subkeys(b'refs/tags'), repo.refs.subkeys(b'refs/tags/')) self.assertEqual( repo.refs.as_dict(b'refs/tags'), repo.refs.as_dict(b'refs/tags/')) self.assertEqual( repo.refs.as_dict(b'refs/heads'), repo.refs.as_dict(b'refs/heads/')) bare = self.open_repo('a.git') tmp_dir = self.mkdtemp() self.addCleanup(shutil.rmtree, tmp_dir) with bare.clone(tmp_dir, mkdir=False) as nonbare: check(nonbare) check(bare) def test_working_tree(self): temp_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, temp_dir) worktree_temp_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, worktree_temp_dir) r = Repo.init(temp_dir) self.addCleanup(r.close) root_sha = r.do_commit( b'empty commit', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12345, commit_timezone=0, author_timestamp=12345, author_timezone=0) r.refs[b'refs/heads/master'] = root_sha w = Repo._init_new_working_directory(worktree_temp_dir, r) self.addCleanup(w.close) new_sha = w.do_commit( b'new commit', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12345, commit_timezone=0, author_timestamp=12345, author_timezone=0) w.refs[b'HEAD'] = new_sha self.assertEqual(os.path.abspath(r.controldir()), os.path.abspath(w.commondir())) self.assertEqual(r.refs.keys(), w.refs.keys()) self.assertNotEqual(r.head(), w.head()) class BuildRepoRootTests(TestCase): """Tests that build on-disk repos from scratch. Repos live in a temp dir and are torn down after each test. They start with a single commit in master having single file named 'a'. """ def get_repo_dir(self): return os.path.join(tempfile.mkdtemp(), 'test') def setUp(self): super(BuildRepoRootTests, self).setUp() self._repo_dir = self.get_repo_dir() os.makedirs(self._repo_dir) r = self._repo = Repo.init(self._repo_dir) self.addCleanup(tear_down_repo, r) self.assertFalse(r.bare) self.assertEqual(b'ref: refs/heads/master', r.refs.read_ref(b'HEAD')) self.assertRaises(KeyError, lambda: r.refs[b'refs/heads/master']) with open(os.path.join(r.path, 'a'), 'wb') as f: f.write(b'file contents') r.stage(['a']) commit_sha = r.do_commit( b'msg', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12345, commit_timezone=0, author_timestamp=12345, author_timezone=0) self.assertEqual([], r[commit_sha].parents) self._root_commit = commit_sha def test_get_shallow(self): self.assertEqual(set(), self._repo.get_shallow()) with open(os.path.join(self._repo.path, '.git', 'shallow'), 'wb') as f: f.write(b'a90fa2d900a17e99b433217e988c4eb4a2e9a097\n') self.assertEqual({b'a90fa2d900a17e99b433217e988c4eb4a2e9a097'}, self._repo.get_shallow()) def test_update_shallow(self): self._repo.update_shallow(None, None) # no op self.assertEqual(set(), self._repo.get_shallow()) self._repo.update_shallow( [b'a90fa2d900a17e99b433217e988c4eb4a2e9a097'], None) self.assertEqual( {b'a90fa2d900a17e99b433217e988c4eb4a2e9a097'}, self._repo.get_shallow()) self._repo.update_shallow( [b'a90fa2d900a17e99b433217e988c4eb4a2e9a097'], [b'f9e39b120c68182a4ba35349f832d0e4e61f485c']) self.assertEqual({b'a90fa2d900a17e99b433217e988c4eb4a2e9a097'}, self._repo.get_shallow()) def test_build_repo(self): r = self._repo self.assertEqual(b'ref: refs/heads/master', r.refs.read_ref(b'HEAD')) self.assertEqual(self._root_commit, r.refs[b'refs/heads/master']) expected_blob = objects.Blob.from_string(b'file contents') self.assertEqual(expected_blob.data, r[expected_blob.id].data) actual_commit = r[self._root_commit] self.assertEqual(b'msg', actual_commit.message) def test_commit_modified(self): r = self._repo with open(os.path.join(r.path, 'a'), 'wb') as f: f.write(b'new contents') r.stage(['a']) commit_sha = r.do_commit( b'modified a', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12395, commit_timezone=0, author_timestamp=12395, author_timezone=0) self.assertEqual([self._root_commit], r[commit_sha].parents) a_mode, a_id = tree_lookup_path(r.get_object, r[commit_sha].tree, b'a') self.assertEqual(stat.S_IFREG | 0o644, a_mode) self.assertEqual(b'new contents', r[a_id].data) @skipIf(not getattr(os, 'symlink', None), 'Requires symlink support') def test_commit_symlink(self): r = self._repo os.symlink('a', os.path.join(r.path, 'b')) r.stage(['a', 'b']) commit_sha = r.do_commit( b'Symlink b', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12395, commit_timezone=0, author_timestamp=12395, author_timezone=0) self.assertEqual([self._root_commit], r[commit_sha].parents) b_mode, b_id = tree_lookup_path(r.get_object, r[commit_sha].tree, b'b') self.assertTrue(stat.S_ISLNK(b_mode)) self.assertEqual(b'a', r[b_id].data) def test_commit_merge_heads_file(self): tmp_dir = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, tmp_dir) r = Repo.init(tmp_dir) with open(os.path.join(r.path, 'a'), 'w') as f: f.write('initial text') c1 = r.do_commit( b'initial commit', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12395, commit_timezone=0, author_timestamp=12395, author_timezone=0) with open(os.path.join(r.path, 'a'), 'w') as f: f.write('merged text') with open(os.path.join(r.path, '.git', 'MERGE_HEADS'), 'w') as f: f.write('c27a2d21dd136312d7fa9e8baabb82561a1727d0\n') r.stage(['a']) commit_sha = r.do_commit( b'deleted a', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12395, commit_timezone=0, author_timestamp=12395, author_timezone=0) self.assertEqual([ c1, b'c27a2d21dd136312d7fa9e8baabb82561a1727d0'], r[commit_sha].parents) def test_commit_deleted(self): r = self._repo os.remove(os.path.join(r.path, 'a')) r.stage(['a']) commit_sha = r.do_commit( b'deleted a', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12395, commit_timezone=0, author_timestamp=12395, author_timezone=0) self.assertEqual([self._root_commit], r[commit_sha].parents) self.assertEqual([], list(r.open_index())) tree = r[r[commit_sha].tree] self.assertEqual([], list(tree.iteritems())) def test_commit_follows(self): r = self._repo r.refs.set_symbolic_ref(b'HEAD', b'refs/heads/bla') commit_sha = r.do_commit( b'commit with strange character', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12395, commit_timezone=0, author_timestamp=12395, author_timezone=0, ref=b'HEAD') self.assertEqual(commit_sha, r[b'refs/heads/bla'].id) def test_commit_encoding(self): r = self._repo commit_sha = r.do_commit( b'commit with strange character \xee', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12395, commit_timezone=0, author_timestamp=12395, author_timezone=0, encoding=b"iso8859-1") self.assertEqual(b"iso8859-1", r[commit_sha].encoding) def test_compression_level(self): r = self._repo c = r.get_config() c.set(('core',), 'compression', '3') c.set(('core',), 'looseCompression', '4') c.write_to_path() r = Repo(self._repo_dir) self.assertEqual(r.object_store.loose_compression_level, 4) def test_commit_encoding_from_config(self): r = self._repo c = r.get_config() c.set(('i18n',), 'commitEncoding', 'iso8859-1') c.write_to_path() commit_sha = r.do_commit( b'commit with strange character \xee', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12395, commit_timezone=0, author_timestamp=12395, author_timezone=0) self.assertEqual(b"iso8859-1", r[commit_sha].encoding) def test_commit_config_identity(self): # commit falls back to the users' identity if it wasn't specified r = self._repo c = r.get_config() c.set((b"user", ), b"name", b"Jelmer") c.set((b"user", ), b"email", b"jelmer@apache.org") c.write_to_path() commit_sha = r.do_commit(b'message') self.assertEqual( b"Jelmer ", r[commit_sha].author) self.assertEqual( b"Jelmer ", r[commit_sha].committer) def test_commit_config_identity_strips_than(self): # commit falls back to the users' identity if it wasn't specified, # and strips superfluous <> r = self._repo c = r.get_config() c.set((b"user", ), b"name", b"Jelmer") c.set((b"user", ), b"email", b"") 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 overrideEnv(self, name, value): def restore(): if oldval is not None: os.environ[name] = oldval else: del os.environ[name] oldval = os.environ.get(name) os.environ[name] = value self.addCleanup(restore) def test_commit_config_identity_from_env(self): # commit falls back to the users' identity if it wasn't specified self.overrideEnv('GIT_COMMITTER_NAME', 'joe') self.overrideEnv('GIT_COMMITTER_EMAIL', 'joe@example.com') 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"joe ", r[commit_sha].committer) def test_commit_fail_ref(self): r = self._repo def set_if_equals(name, old_ref, new_ref, **kwargs): return False r.refs.set_if_equals = set_if_equals def add_if_new(name, new_ref, **kwargs): self.fail('Unexpected call to add_if_new') r.refs.add_if_new = add_if_new old_shas = set(r.object_store) self.assertRaises(errors.CommitError, r.do_commit, b'failed commit', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12345, commit_timezone=0, author_timestamp=12345, author_timezone=0) new_shas = set(r.object_store) - old_shas self.assertEqual(1, len(new_shas)) # Check that the new commit (now garbage) was added. new_commit = r[new_shas.pop()] self.assertEqual(r[self._root_commit].tree, new_commit.tree) self.assertEqual(b'failed commit', new_commit.message) def test_commit_branch(self): r = self._repo commit_sha = r.do_commit( b'commit to branch', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12395, commit_timezone=0, author_timestamp=12395, author_timezone=0, ref=b"refs/heads/new_branch") self.assertEqual(self._root_commit, r[b"HEAD"].id) self.assertEqual(commit_sha, r[b"refs/heads/new_branch"].id) self.assertEqual([], r[commit_sha].parents) self.assertTrue(b"refs/heads/new_branch" in r) new_branch_head = commit_sha commit_sha = r.do_commit( b'commit to branch 2', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12395, commit_timezone=0, author_timestamp=12395, author_timezone=0, ref=b"refs/heads/new_branch") self.assertEqual(self._root_commit, r[b"HEAD"].id) self.assertEqual(commit_sha, r[b"refs/heads/new_branch"].id) self.assertEqual([new_branch_head], r[commit_sha].parents) def test_commit_merge_heads(self): r = self._repo merge_1 = r.do_commit( b'commit to branch 2', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12395, commit_timezone=0, author_timestamp=12395, author_timezone=0, ref=b"refs/heads/new_branch") commit_sha = r.do_commit( b'commit with merge', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12395, commit_timezone=0, author_timestamp=12395, author_timezone=0, merge_heads=[merge_1]) self.assertEqual( [self._root_commit, merge_1], r[commit_sha].parents) def test_commit_dangling_commit(self): r = self._repo old_shas = set(r.object_store) old_refs = r.get_refs() commit_sha = r.do_commit( b'commit with no ref', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12395, commit_timezone=0, author_timestamp=12395, author_timezone=0, ref=None) new_shas = set(r.object_store) - old_shas # New sha is added, but no new refs self.assertEqual(1, len(new_shas)) new_commit = r[new_shas.pop()] self.assertEqual(r[self._root_commit].tree, new_commit.tree) self.assertEqual([], r[commit_sha].parents) self.assertEqual(old_refs, r.get_refs()) def test_commit_dangling_commit_with_parents(self): r = self._repo old_shas = set(r.object_store) old_refs = r.get_refs() commit_sha = r.do_commit( b'commit with no ref', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12395, commit_timezone=0, author_timestamp=12395, author_timezone=0, ref=None, merge_heads=[self._root_commit]) new_shas = set(r.object_store) - old_shas # New sha is added, but no new refs self.assertEqual(1, len(new_shas)) new_commit = r[new_shas.pop()] self.assertEqual(r[self._root_commit].tree, new_commit.tree) self.assertEqual([self._root_commit], r[commit_sha].parents) self.assertEqual(old_refs, r.get_refs()) def test_stage_absolute(self): r = self._repo os.remove(os.path.join(r.path, 'a')) self.assertRaises(ValueError, r.stage, [os.path.join(r.path, 'a')]) def test_stage_deleted(self): r = self._repo os.remove(os.path.join(r.path, 'a')) r.stage(['a']) r.stage(['a']) # double-stage a deleted path def test_stage_directory(self): r = self._repo os.mkdir(os.path.join(r.path, 'c')) r.stage(['c']) self.assertEqual([b'a'], list(r.open_index())) - @skipIf(sys.platform == 'win32' and sys.version_info[:2] >= (3, 6), + @skipIf(sys.platform == 'win32', 'tries to implicitly decode as utf8') def test_commit_no_encode_decode(self): r = self._repo repo_path_bytes = r.path.encode(sys.getfilesystemencoding()) encodings = ('utf8', 'latin1') names = [u'À'.encode(encoding) for encoding in encodings] for name, encoding in zip(names, encodings): full_path = os.path.join(repo_path_bytes, name) with open(full_path, 'wb') as f: f.write(encoding.encode('ascii')) # These files are break tear_down_repo, so cleanup these files # ourselves. self.addCleanup(os.remove, full_path) r.stage(names) commit_sha = r.do_commit( b'Files with different encodings', committer=b'Test Committer ', author=b'Test Author ', commit_timestamp=12395, commit_timezone=0, author_timestamp=12395, author_timezone=0, ref=None, merge_heads=[self._root_commit]) for name, encoding in zip(names, encodings): mode, id = tree_lookup_path(r.get_object, r[commit_sha].tree, name) self.assertEqual(stat.S_IFREG | 0o644, mode) self.assertEqual(encoding.encode('ascii'), r[id].data) def test_discover_intended(self): path = os.path.join(self._repo_dir, 'b/c') r = Repo.discover(path) self.assertEqual(r.head(), self._repo.head()) def test_discover_isrepo(self): r = Repo.discover(self._repo_dir) self.assertEqual(r.head(), self._repo.head()) def test_discover_notrepo(self): with self.assertRaises(NotGitRepository): Repo.discover('/') class CheckUserIdentityTests(TestCase): def test_valid(self): check_user_identity(b'Me ') def test_invalid(self): self.assertRaises(InvalidUserIdentity, check_user_identity, b'No Email') self.assertRaises(InvalidUserIdentity, check_user_identity, b'Fullname ') self.assertRaises(InvalidUserIdentity, check_user_identity, b'Fullname >order<>') diff --git a/dulwich/web.py b/dulwich/web.py index 3e4469e6..eb66304b 100644 --- a/dulwich/web.py +++ b/dulwich/web.py @@ -1,524 +1,521 @@ # web.py -- WSGI smart-http server # Copyright (C) 2010 Google, Inc. # Copyright (C) 2012 Jelmer Vernooij # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """HTTP server for dulwich that implements the git smart HTTP protocol.""" from io import BytesIO import shutil import tempfile import gzip import os import re import sys import time from wsgiref.simple_server import ( WSGIRequestHandler, ServerHandler, WSGIServer, make_server, ) try: from urlparse import parse_qs except ImportError: from urllib.parse import parse_qs from dulwich import log_utils from dulwich.protocol import ( ReceivableProtocol, ) from dulwich.repo import ( NotGitRepository, Repo, ) from dulwich.server import ( DictBackend, DEFAULT_HANDLERS, generate_info_refs, generate_objects_info_packs, ) logger = log_utils.getLogger(__name__) # HTTP error strings HTTP_OK = '200 OK' HTTP_NOT_FOUND = '404 Not Found' HTTP_FORBIDDEN = '403 Forbidden' HTTP_ERROR = '500 Internal Server Error' def date_time_string(timestamp=None): # From BaseHTTPRequestHandler.date_time_string in BaseHTTPServer.py in the # Python 2.6.5 standard library, following modifications: # - Made a global rather than an instance method. # - weekdayname and monthname are renamed and locals rather than class # variables. # Copyright (c) 2001-2010 Python Software Foundation; All Rights Reserved weekdays = ['Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat', 'Sun'] months = [None, 'Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec'] if timestamp is None: timestamp = time.time() year, month, day, hh, mm, ss, wd, y, z = time.gmtime(timestamp) return '%s, %02d %3s %4d %02d:%02d:%02d GMD' % ( weekdays[wd], day, months[month], year, hh, mm, ss) def url_prefix(mat): """Extract the URL prefix from a regex match. Args: mat: A regex match object. Returns: The URL prefix, defined as the text before the match in the original string. Normalized to start with one leading slash and end with zero. """ return '/' + mat.string[:mat.start()].strip('/') def get_repo(backend, mat): """Get a Repo instance for the given backend and URL regex match.""" return backend.open_repository(url_prefix(mat)) def send_file(req, f, content_type): """Send a file-like object to the request output. Args: req: The HTTPGitRequest object to send output to. f: An open file-like object to send; will be closed. content_type: The MIME type for the file. Returns: Iterator over the contents of the file, as chunks. """ if f is None: yield req.not_found('File not found') return try: req.respond(HTTP_OK, content_type) while True: data = f.read(10240) if not data: break yield data except IOError: yield req.error('Error reading file') finally: f.close() def _url_to_path(url): return url.replace('/', os.path.sep) def get_text_file(req, backend, mat): req.nocache() path = _url_to_path(mat.group()) logger.info('Sending plain text file %s', path) return send_file(req, get_repo(backend, mat).get_named_file(path), 'text/plain') def get_loose_object(req, backend, mat): sha = (mat.group(1) + mat.group(2)).encode('ascii') logger.info('Sending loose object %s', sha) object_store = get_repo(backend, mat).object_store if not object_store.contains_loose(sha): yield req.not_found('Object not found') return try: data = object_store[sha].as_legacy_object() except IOError: yield req.error('Error reading object') return req.cache_forever() req.respond(HTTP_OK, 'application/x-git-loose-object') yield data def get_pack_file(req, backend, mat): req.cache_forever() path = _url_to_path(mat.group()) logger.info('Sending pack file %s', path) return send_file(req, get_repo(backend, mat).get_named_file(path), 'application/x-git-packed-objects') def get_idx_file(req, backend, mat): req.cache_forever() path = _url_to_path(mat.group()) logger.info('Sending pack file %s', path) return send_file(req, get_repo(backend, mat).get_named_file(path), 'application/x-git-packed-objects-toc') def get_info_refs(req, backend, mat): params = parse_qs(req.environ['QUERY_STRING']) service = params.get('service', [None])[0] try: repo = get_repo(backend, mat) except NotGitRepository as e: yield req.not_found(str(e)) return if service and not req.dumb: handler_cls = req.handlers.get(service.encode('ascii'), None) if handler_cls is None: yield req.forbidden('Unsupported service') return req.nocache() write = req.respond( HTTP_OK, 'application/x-%s-advertisement' % service) proto = ReceivableProtocol(BytesIO().read, write) handler = handler_cls(backend, [url_prefix(mat)], proto, http_req=req, advertise_refs=True) handler.proto.write_pkt_line( b'# service=' + service.encode('ascii') + b'\n') handler.proto.write_pkt_line(None) handler.handle() else: # non-smart fallback # TODO: select_getanyfile() (see http-backend.c) req.nocache() req.respond(HTTP_OK, 'text/plain') logger.info('Emulating dumb info/refs') for text in generate_info_refs(repo): yield text def get_info_packs(req, backend, mat): req.nocache() req.respond(HTTP_OK, 'text/plain') logger.info('Emulating dumb info/packs') return generate_objects_info_packs(get_repo(backend, mat)) class _LengthLimitedFile(object): """Wrapper class to limit the length of reads from a file-like object. This is used to ensure EOF is read from the wsgi.input object once Content-Length bytes are read. This behavior is required by the WSGI spec but not implemented in wsgiref as of 2.5. """ def __init__(self, input, max_bytes): self._input = input self._bytes_avail = max_bytes def read(self, size=-1): if self._bytes_avail <= 0: return b'' if size == -1 or size > self._bytes_avail: size = self._bytes_avail self._bytes_avail -= size return self._input.read(size) # TODO: support more methods as necessary def handle_service_request(req, backend, mat): service = mat.group().lstrip('/') logger.info('Handling service request for %s', service) handler_cls = req.handlers.get(service.encode('ascii'), None) if handler_cls is None: yield req.forbidden('Unsupported service') return try: get_repo(backend, mat) except NotGitRepository as e: yield req.not_found(str(e)) return req.nocache() write = req.respond(HTTP_OK, 'application/x-%s-result' % service) proto = ReceivableProtocol(req.environ['wsgi.input'].read, write) # TODO(jelmer): Find a way to pass in repo, rather than having handler_cls # reopen. handler = handler_cls(backend, [url_prefix(mat)], proto, http_req=req) handler.handle() class HTTPGitRequest(object): """Class encapsulating the state of a single git HTTP request. :ivar environ: the WSGI environment for the request. """ def __init__(self, environ, start_response, dumb=False, handlers=None): self.environ = environ self.dumb = dumb self.handlers = handlers self._start_response = start_response self._cache_headers = [] self._headers = [] def add_header(self, name, value): """Add a header to the response.""" self._headers.append((name, value)) def respond(self, status=HTTP_OK, content_type=None, headers=None): """Begin a response with the given status and other headers.""" if headers: self._headers.extend(headers) if content_type: self._headers.append(('Content-Type', content_type)) self._headers.extend(self._cache_headers) return self._start_response(status, self._headers) def not_found(self, message): """Begin a HTTP 404 response and return the text of a message.""" self._cache_headers = [] logger.info('Not found: %s', message) self.respond(HTTP_NOT_FOUND, 'text/plain') return message.encode('ascii') def forbidden(self, message): """Begin a HTTP 403 response and return the text of a message.""" self._cache_headers = [] logger.info('Forbidden: %s', message) self.respond(HTTP_FORBIDDEN, 'text/plain') return message.encode('ascii') def error(self, message): """Begin a HTTP 500 response and return the text of a message.""" self._cache_headers = [] logger.error('Error: %s', message) self.respond(HTTP_ERROR, 'text/plain') return message.encode('ascii') def nocache(self): """Set the response to never be cached by the client.""" self._cache_headers = [ ('Expires', 'Fri, 01 Jan 1980 00:00:00 GMT'), ('Pragma', 'no-cache'), ('Cache-Control', 'no-cache, max-age=0, must-revalidate'), ] def cache_forever(self): """Set the response to be cached forever by the client.""" now = time.time() self._cache_headers = [ ('Date', date_time_string(now)), ('Expires', date_time_string(now + 31536000)), ('Cache-Control', 'public, max-age=31536000'), ] class HTTPGitApplication(object): """Class encapsulating the state of a git WSGI application. :ivar backend: the Backend object backing this application """ services = { ('GET', re.compile('/HEAD$')): get_text_file, ('GET', re.compile('/info/refs$')): get_info_refs, ('GET', re.compile('/objects/info/alternates$')): get_text_file, ('GET', re.compile('/objects/info/http-alternates$')): get_text_file, ('GET', re.compile('/objects/info/packs$')): get_info_packs, ('GET', re.compile('/objects/([0-9a-f]{2})/([0-9a-f]{38})$')): get_loose_object, ('GET', re.compile('/objects/pack/pack-([0-9a-f]{40})\\.pack$')): get_pack_file, ('GET', re.compile('/objects/pack/pack-([0-9a-f]{40})\\.idx$')): get_idx_file, ('POST', re.compile('/git-upload-pack$')): handle_service_request, ('POST', re.compile('/git-receive-pack$')): handle_service_request, } def __init__(self, backend, dumb=False, handlers=None, fallback_app=None): self.backend = backend self.dumb = dumb self.handlers = dict(DEFAULT_HANDLERS) self.fallback_app = fallback_app if handlers is not None: self.handlers.update(handlers) def __call__(self, environ, start_response): path = environ['PATH_INFO'] method = environ['REQUEST_METHOD'] req = HTTPGitRequest(environ, start_response, dumb=self.dumb, handlers=self.handlers) # environ['QUERY_STRING'] has qs args handler = None for smethod, spath in self.services.keys(): if smethod != method: continue mat = spath.search(path) if mat: handler = self.services[smethod, spath] break if handler is None: if self.fallback_app is not None: return self.fallback_app(environ, start_response) else: return [req.not_found('Sorry, that method is not supported')] return handler(req, self.backend, mat) class GunzipFilter(object): """WSGI middleware that unzips gzip-encoded requests before passing on to the underlying application. """ def __init__(self, application): self.app = application def __call__(self, environ, start_response): if environ.get('HTTP_CONTENT_ENCODING', '') == 'gzip': try: environ['wsgi.input'].tell() wsgi_input = environ['wsgi.input'] except (AttributeError, IOError, NotImplementedError): # The gzip implementation in the standard library of Python 2.x # requires working '.seek()' and '.tell()' methods on the input # stream. Read the data into a temporary file to work around # this limitation. wsgi_input = tempfile.SpooledTemporaryFile(16 * 1024 * 1024) shutil.copyfileobj(environ['wsgi.input'], wsgi_input) wsgi_input.seek(0) environ['wsgi.input'] = gzip.GzipFile( filename=None, fileobj=wsgi_input, mode='r') del environ['HTTP_CONTENT_ENCODING'] if 'CONTENT_LENGTH' in environ: del environ['CONTENT_LENGTH'] return self.app(environ, start_response) class LimitedInputFilter(object): """WSGI middleware that limits the input length of a request to that specified in Content-Length. """ def __init__(self, application): self.app = application def __call__(self, environ, start_response): # This is not necessary if this app is run from a conforming WSGI # server. Unfortunately, there's no way to tell that at this point. # TODO: git may used HTTP/1.1 chunked encoding instead of specifying # content-length content_length = environ.get('CONTENT_LENGTH', '') if content_length: environ['wsgi.input'] = _LengthLimitedFile( environ['wsgi.input'], int(content_length)) return self.app(environ, start_response) def make_wsgi_chain(*args, **kwargs): """Factory function to create an instance of HTTPGitApplication, correctly wrapped with needed middleware. """ app = HTTPGitApplication(*args, **kwargs) wrapped_app = LimitedInputFilter(GunzipFilter(app)) return wrapped_app class ServerHandlerLogger(ServerHandler): """ServerHandler that uses dulwich's logger for logging exceptions.""" def log_exception(self, exc_info): - if sys.version_info < (2, 7): - logger.exception('Exception happened during processing of request') - else: - logger.exception('Exception happened during processing of request', - exc_info=exc_info) + logger.exception('Exception happened during processing of request', + exc_info=exc_info) def log_message(self, format, *args): logger.info(format, *args) def log_error(self, *args): logger.error(*args) class WSGIRequestHandlerLogger(WSGIRequestHandler): """WSGIRequestHandler that uses dulwich's logger for logging exceptions.""" def log_exception(self, exc_info): logger.exception('Exception happened during processing of request', exc_info=exc_info) def log_message(self, format, *args): logger.info(format, *args) def log_error(self, *args): logger.error(*args) def handle(self): """Handle a single HTTP request""" self.raw_requestline = self.rfile.readline() if not self.parse_request(): # An error code has been sent, just exit return handler = ServerHandlerLogger( self.rfile, self.wfile, self.get_stderr(), self.get_environ() ) handler.request_handler = self # backpointer for logging handler.run(self.server.get_app()) class WSGIServerLogger(WSGIServer): def handle_error(self, request, client_address): """Handle an error. """ logger.exception( 'Exception happened during processing of request from %s' % str(client_address)) def main(argv=sys.argv): """Entry point for starting an HTTP git server.""" import optparse parser = optparse.OptionParser() parser.add_option("-l", "--listen_address", dest="listen_address", default="localhost", help="Binding IP address.") parser.add_option("-p", "--port", dest="port", type=int, default=8000, help="Port to listen on.") options, args = parser.parse_args(argv) if len(args) > 1: gitdir = args[1] else: gitdir = os.getcwd() log_utils.default_logging_config() backend = DictBackend({'/': Repo(gitdir)}) app = make_wsgi_chain(backend) server = make_server(options.listen_address, options.port, app, handler_class=WSGIRequestHandlerLogger, server_class=WSGIServerLogger) logger.info('Listening for HTTP connections on %s:%d', options.listen_address, options.port) server.serve_forever() if __name__ == '__main__': main() diff --git a/setup.py b/setup.py index 1a906403..f9cade2a 100755 --- a/setup.py +++ b/setup.py @@ -1,126 +1,116 @@ #!/usr/bin/python # encoding: utf-8 # Setup file for dulwich # Copyright (C) 2008-2016 Jelmer Vernooij try: from setuptools import setup, Extension except ImportError: from distutils.core import setup, Extension has_setuptools = False else: has_setuptools = True from distutils.core import Distribution import io import os import sys -dulwich_version_string = '0.19.17' - -include_dirs = [] -# Windows MSVC support -if sys.platform == 'win32' and sys.version_info[:2] < (3, 6): - # Include dulwich/ for fallback stdint.h - include_dirs.append('dulwich') +dulwich_version_string = '0.20.0' class DulwichDistribution(Distribution): def is_pure(self): if self.pure: return True def has_ext_modules(self): return not self.pure global_options = Distribution.global_options + [ ('pure', None, "use pure Python code instead of C " "extensions (slower on CPython)")] pure = False if sys.platform == 'darwin' and os.path.exists('/usr/bin/xcodebuild'): # XCode 4.0 dropped support for ppc architecture, which is hardcoded in # distutils.sysconfig import subprocess p = subprocess.Popen( ['/usr/bin/xcodebuild', '-version'], stdout=subprocess.PIPE, stderr=subprocess.PIPE, env={}) out, err = p.communicate() for line in out.splitlines(): line = line.decode("utf8") # Also parse only first digit, because 3.2.1 can't be parsed nicely if (line.startswith('Xcode') and int(line.split()[1].split('.')[0]) >= 4): os.environ['ARCHFLAGS'] = '' tests_require = ['fastimport'] if '__pypy__' not in sys.modules and not sys.platform == 'win32': tests_require.extend([ 'gevent', 'geventhttpclient', 'mock', 'setuptools>=17.1']) ext_modules = [ - Extension('dulwich._objects', ['dulwich/_objects.c'], - include_dirs=include_dirs), - Extension('dulwich._pack', ['dulwich/_pack.c'], - include_dirs=include_dirs), - Extension('dulwich._diff_tree', ['dulwich/_diff_tree.c'], - include_dirs=include_dirs), + Extension('dulwich._objects', ['dulwich/_objects.c']), + Extension('dulwich._pack', ['dulwich/_pack.c']), + Extension('dulwich._diff_tree', ['dulwich/_diff_tree.c']), ] setup_kwargs = {} if has_setuptools: setup_kwargs['extras_require'] = { 'fastimport': ['fastimport'], 'https': ['urllib3[secure]>=1.24.1'], 'pgp': ['gpg'], } setup_kwargs['install_requires'] = ['urllib3>=1.24.1', 'certifi'] setup_kwargs['include_package_data'] = True setup_kwargs['test_suite'] = 'dulwich.tests.test_suite' setup_kwargs['tests_require'] = tests_require with io.open(os.path.join(os.path.dirname(__file__), "README.rst"), encoding="utf-8") as f: description = f.read() setup(name='dulwich', author="Jelmer Vernooij", author_email="jelmer@jelmer.uk", url="https://www.dulwich.io/", long_description=description, description="Python Git Library", version=dulwich_version_string, license='Apachev2 or later or GPLv2', project_urls={ "Bug Tracker": "https://github.com/dulwich/dulwich/issues", "Repository": "https://www.dulwich.io/code/", "GitHub": "https://github.com/dulwich/dulwich", }, keywords="git vcs", packages=['dulwich', 'dulwich.tests', 'dulwich.tests.compat', 'dulwich.contrib'], package_data={'': ['../docs/tutorial/*.txt']}, scripts=['bin/dulwich', 'bin/dul-receive-pack', 'bin/dul-upload-pack'], ext_modules=ext_modules, distclass=DulwichDistribution, classifiers=[ 'Development Status :: 4 - Beta', 'License :: OSI Approved :: Apache Software License', - 'Programming Language :: Python :: 2.7', 'Programming Language :: Python :: 3.4', 'Programming Language :: Python :: 3.5', 'Programming Language :: Python :: 3.6', 'Programming Language :: Python :: Implementation :: CPython', 'Programming Language :: Python :: Implementation :: PyPy', 'Operating System :: POSIX', 'Operating System :: Microsoft :: Windows', 'Topic :: Software Development :: Version Control', ], **setup_kwargs ) diff --git a/tox.ini b/tox.ini index b75a4b70..6419afc7 100644 --- a/tox.ini +++ b/tox.ini @@ -1,24 +1,24 @@ [tox] downloadcache = {toxworkdir}/cache/ -envlist = py27, pypy, py27-noext, pypy-noext, py33, py33-noext, py34, py34-noext, py35, py35-noext, py36, py36-noext +envlist = pypy, pypy-noext, py35, py35-noext, py36, py36-noext, py37, py37-noext, py38, py38-noext [testenv] commands = make check recreate = True whitelist_externals = make -[testenv:py27-noext] +[testenv:pypy-noext] commands = make check-noextensions -[testenv:pypy-noext] +[testenv:py35-noext] commands = make check-noextensions -[testenv:py34-noext] +[testenv:py36-noext] commands = make check-noextensions -[testenv:py35-noext] +[testenv:py37-noext] commands = make check-noextensions -[testenv:py36-noext] +[testenv:py38-noext] commands = make check-noextensions