diff --git a/.github/workflows/pythonpackage.yml b/.github/workflows/pythonpackage.yml index 14e72afa..bb19e378 100644 --- a/.github/workflows/pythonpackage.yml +++ b/.github/workflows/pythonpackage.yml @@ -1,57 +1,57 @@ name: Python package on: [push, pull_request] jobs: build: runs-on: ${{ matrix.os }} strategy: matrix: os: [ubuntu-latest, macos-latest, windows-latest] - python-version: [3.5, 3.6, 3.7, 3.8, pypy3] + python-version: [3.5, 3.6, 3.7, 3.8, 3.9, pypy3] exclude: # sqlite3 exit handling seems to get in the way - os: macos-latest python-version: pypy3 # doesn't support passing in bytestrings to os.scandir - os: windows-latest python-version: pypy3 # path encoding - os: windows-latest python-version: 3.5 # path encoding - os: macos-latest python-version: 3.5 fail-fast: false steps: - uses: actions/checkout@v2 - name: Set up Python ${{ matrix.python-version }} uses: actions/setup-python@v2 with: python-version: ${{ matrix.python-version }} - name: Install dependencies run: | python -m pip install --upgrade pip pip install -U pip coverage codecov flake8 fastimport - name: Install mypy run: | pip install -U mypy if: "matrix.python-version != 'pypy3'" - name: Style checks run: | python -m flake8 - name: Typing checks run: | python -m mypy dulwich if: "matrix.python-version != 'pypy3'" - name: Build run: | python setup.py build_ext -i - name: Coverage test suite run run: | python -m coverage run -p -m unittest dulwich.tests.test_suite - name: Upload coverage details run: | codecov diff --git a/.github/workflows/pythonpublish.yml b/.github/workflows/pythonpublish.yml index ea1198cd..49e5d72a 100644 --- a/.github/workflows/pythonpublish.yml +++ b/.github/workflows/pythonpublish.yml @@ -1,60 +1,60 @@ name: Upload Python Package on: push: tags: - dulwich-* jobs: deploy: runs-on: ${{ matrix.os }} strategy: matrix: os: [macos-latest, windows-latest] - python-version: ['3.5', '3.6', '3.7', '3.8'] + python-version: ['3.5', '3.6', '3.7', '3.8', '3.9'] include: - os: ubuntu-latest python-version: '3.x' # path encoding exclude: - os: windows-latest python-version: 3.5 fail-fast: false steps: - uses: actions/checkout@v2 - name: Set up Python ${{ matrix.python-version }} uses: actions/setup-python@v2 with: python-version: ${{ matrix.python-version }} - name: Install dependencies run: | python -m pip install --upgrade pip pip install setuptools wheel twine fastimport - name: Run test suite run: | python -m unittest dulwich.tests.test_suite - name: Build run: | python setup.py sdist bdist_wheel mkdir wheelhouse mv dist/*.whl wheelhouse if: "matrix.os != 'ubuntu-latest'" - name: Build and publish (Linux) uses: RalfG/python-wheels-manylinux-build@v0.2.2 if: "matrix.os == 'ubuntu-latest'" - name: Publish (Linux) env: TWINE_USERNAME: ${{ secrets.PYPI_USERNAME }} TWINE_PASSWORD: ${{ secrets.PYPI_PASSWORD }} run: | twine upload wheelhouse/*manylinux* if: "matrix.os == 'ubuntu-latest'" - name: Publish env: TWINE_USERNAME: ${{ secrets.PYPI_USERNAME }} TWINE_PASSWORD: ${{ secrets.PYPI_PASSWORD }} run: | twine upload wheelhouse/* if: "matrix.os != 'ubuntu-latest'" diff --git a/NEWS b/NEWS index f7bf079f..5821dad9 100644 --- a/NEWS +++ b/NEWS @@ -1,2114 +1,2129 @@ +0.20.8 2020-10-29 + + * Build wheels on Mac OS X / Windows for Python 3.9. + (Jelmer Vernooij) + +0.20.7 2020-10-29 + + * Check core.repositoryformatversion. (Jelmer Vernooij, #803) + + * Fix ACK/NACK handling in archive command handling in dulwich.client. + (DzmitrySudnik, #805) + 0.20.6 2020-08-29 * Add a ``RefsContainer.watch`` interface. (Jelmer Vernooij, #751) * Fix pushing of new branches from porcelain.push. (Jelmer Vernooij, #788) * Honor shallows when pushing from a shallow clone. (Jelmer Vernooij, #794) * Fix porcelain.path_to_tree_path for Python 3.5. (Boris Feld, #777) + * Add support for honor proxy environment variables for HTTP. + (Aurélien Campéas, #797) + 0.20.5 2020-06-22 * Print a clearer exception when setup.py is executed on Python < 3.5. (Jelmer Vernooij, #783) * Send an empty pack to clients if they requested objects, even if they already have those objects. Thanks to Martijn Pieters for the detailed bug report. (Jelmer Vernooij, #781) * porcelain.pull: Don't ask for objects that we already have. (Jelmer Vernooij, #782) * Add LCA implementation. (Kevin Hendricks) * Add functionality for finding the merge base. (Kevin Hendricks) * Check for diverged branches during push. (Jelmer Vernooij, #494) * Check for fast-forward during pull. (Jelmer Vernooij, #666) * Return a SendPackResult object from GitClient.send_pack(). (Jelmer Vernooij) * ``GitClient.send_pack`` now sets the ``ref_status`` attribute on its return value to a dictionary mapping ref names to error messages. Previously, it raised UpdateRefsError if any of the refs failed to update. (Jelmer Vernooij, #780) * Add a ``porcelain.Error`` object that most errors in porcelain derive from. (Jelmer Vernooij) * Fix argument parsing in dulwich command-line app. (Jelmer Vernooij, #784) 0.20.3 2020-06-14 * Add support for remembering remote refs after push/pull. (Jelmer Vernooij, #752) * Support passing tree and output encoding to dulwich.patch.unified_diff. (Jelmer Vernooij, #763) * Fix pushing of new refs over HTTP(S) when there are no new objects to be sent. (Jelmer Vernooij, #739) * Raise new error HTTPUnauthorized when the server sends back a 401. The client can then retry with credentials. (Jelmer Vernooij, #691) * Move the guts of bin/dulwich to dulwich.cli, so it is easier to test or import. (Jelmer Vernooij) * Install dulwich script from entry_points when setuptools is available, making it slightly easier to use on Windows. (Jelmer Vernooij, #540) * Set python_requires>=3.5 in setup.py. (Manuel Jacob) 0.20.2 2020-06-01 * Brown bag release to fix uploads of Windows wheels. 0.20.1 2020-06-01 * Publish binary wheels for: Windows, Linux, Mac OS X. (Jelmer Vernooij, #711, #710, #629) 0.20.0 2020-06-01 * Drop support for Python 2. (Jelmer Vernooij) * Only return files from the loose store that look like git objects. (Nicolas Dandrimont) * Ignore agent= capability if sent by client. (Jelmer Vernooij) * 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/PKG-INFO b/PKG-INFO index 29a221f8..826843a2 100644 --- a/PKG-INFO +++ b/PKG-INFO @@ -1,122 +1,123 @@ Metadata-Version: 2.1 Name: dulwich -Version: 0.20.6 +Version: 0.20.8 Summary: Python Git Library Home-page: https://www.dulwich.io/ Author: Jelmer Vernooij Author-email: jelmer@jelmer.uk License: Apachev2 or later or GPLv2 Project-URL: Bug Tracker, https://github.com/dulwich/dulwich/issues Project-URL: Repository, https://www.dulwich.io/code/ Project-URL: GitHub, https://github.com/dulwich/dulwich Description: 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 3.5, 3.6, - 3.7, 3.8 and Pypy. + At the moment, Dulwich supports (and is tested on) CPython 3.5 and later and + Pypy. The latest release series to support Python 2.x was the 0.19 series. See the 0.19 branch in the Dulwich git repository. Keywords: git vcs Platform: UNKNOWN Classifier: Development Status :: 4 - Beta Classifier: License :: OSI Approved :: Apache Software License Classifier: Programming Language :: Python :: 3.5 Classifier: Programming Language :: Python :: 3.6 Classifier: Programming Language :: Python :: 3.7 Classifier: Programming Language :: Python :: 3.8 +Classifier: Programming Language :: Python :: 3.9 Classifier: Programming Language :: Python :: Implementation :: CPython Classifier: Programming Language :: Python :: Implementation :: PyPy Classifier: Operating System :: POSIX Classifier: Operating System :: Microsoft :: Windows Classifier: Topic :: Software Development :: Version Control Requires-Python: >=3.5 Provides-Extra: fastimport Provides-Extra: https Provides-Extra: pgp Provides-Extra: watch diff --git a/README.rst b/README.rst index 9903c191..0c3e1fa6 100644 --- a/README.rst +++ b/README.rst @@ -1,92 +1,92 @@ 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 3.5, 3.6, -3.7, 3.8 and Pypy. +At the moment, Dulwich supports (and is tested on) CPython 3.5 and later and +Pypy. The latest release series to support Python 2.x was the 0.19 series. See the 0.19 branch in the Dulwich git repository. diff --git a/SECURITY.md b/SECURITY.md new file mode 100644 index 00000000..f1f27068 --- /dev/null +++ b/SECURITY.md @@ -0,0 +1,12 @@ +# Security Policy + +## Supported Versions + +| Version | Supported | +| -------- | ------------------ | +| 0.20.x | :white_check_mark: | +| < 0.20.x | :x: | + +## Reporting a Vulnerability + +Please report security issues by e-mail to jelmer@jelmer.uk, ideally PGP encrypted to the key at https://jelmer.uk/D729A457.asc diff --git a/dulwich.egg-info/PKG-INFO b/dulwich.egg-info/PKG-INFO index 29a221f8..826843a2 100644 --- a/dulwich.egg-info/PKG-INFO +++ b/dulwich.egg-info/PKG-INFO @@ -1,122 +1,123 @@ Metadata-Version: 2.1 Name: dulwich -Version: 0.20.6 +Version: 0.20.8 Summary: Python Git Library Home-page: https://www.dulwich.io/ Author: Jelmer Vernooij Author-email: jelmer@jelmer.uk License: Apachev2 or later or GPLv2 Project-URL: Bug Tracker, https://github.com/dulwich/dulwich/issues Project-URL: Repository, https://www.dulwich.io/code/ Project-URL: GitHub, https://github.com/dulwich/dulwich Description: 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 3.5, 3.6, - 3.7, 3.8 and Pypy. + At the moment, Dulwich supports (and is tested on) CPython 3.5 and later and + Pypy. The latest release series to support Python 2.x was the 0.19 series. See the 0.19 branch in the Dulwich git repository. Keywords: git vcs Platform: UNKNOWN Classifier: Development Status :: 4 - Beta Classifier: License :: OSI Approved :: Apache Software License Classifier: Programming Language :: Python :: 3.5 Classifier: Programming Language :: Python :: 3.6 Classifier: Programming Language :: Python :: 3.7 Classifier: Programming Language :: Python :: 3.8 +Classifier: Programming Language :: Python :: 3.9 Classifier: Programming Language :: Python :: Implementation :: CPython Classifier: Programming Language :: Python :: Implementation :: PyPy Classifier: Operating System :: POSIX Classifier: Operating System :: Microsoft :: Windows Classifier: Topic :: Software Development :: Version Control Requires-Python: >=3.5 Provides-Extra: fastimport Provides-Extra: https Provides-Extra: pgp Provides-Extra: watch diff --git a/dulwich.egg-info/SOURCES.txt b/dulwich.egg-info/SOURCES.txt index a6351981..0fc3a71c 100644 --- a/dulwich.egg-info/SOURCES.txt +++ b/dulwich.egg-info/SOURCES.txt @@ -1,229 +1,230 @@ .coveragerc .gitignore .mailmap .testr.conf AUTHORS CODE_OF_CONDUCT.md CONTRIBUTING.rst COPYING MANIFEST.in Makefile NEWS README.rst README.swift.rst +SECURITY.md TODO build.cmd dulwich.cfg requirements.txt setup.cfg setup.py status.yaml tox.ini .github/workflows/pythonpackage.yml .github/workflows/pythonpublish.yml bin/dul-receive-pack bin/dul-upload-pack bin/dulwich devscripts/PREAMBLE.c devscripts/PREAMBLE.py devscripts/replace-preamble.sh docs/Makefile docs/conf.py docs/index.txt docs/make.bat docs/performance.txt docs/protocol.txt docs/api/index.txt docs/tutorial/.gitignore docs/tutorial/Makefile docs/tutorial/conclusion.txt docs/tutorial/encoding.txt docs/tutorial/file-format.txt docs/tutorial/index.txt docs/tutorial/introduction.txt docs/tutorial/object-store.txt docs/tutorial/porcelain.txt docs/tutorial/remote.txt docs/tutorial/repo.txt docs/tutorial/tag.txt dulwich/__init__.py dulwich/_diff_tree.c dulwich/_objects.c dulwich/_pack.c dulwich/archive.py dulwich/cli.py dulwich/client.py dulwich/config.py dulwich/diff_tree.py dulwich/errors.py dulwich/fastexport.py dulwich/file.py dulwich/graph.py dulwich/greenthreads.py dulwich/hooks.py dulwich/ignore.py dulwich/index.py dulwich/lfs.py dulwich/line_ending.py dulwich/log_utils.py dulwich/lru_cache.py dulwich/mailmap.py dulwich/object_store.py dulwich/objects.py dulwich/objectspec.py dulwich/pack.py dulwich/patch.py dulwich/porcelain.py dulwich/protocol.py dulwich/reflog.py dulwich/refs.py dulwich/repo.py dulwich/server.py dulwich/stash.py dulwich/stdint.h dulwich/walk.py dulwich/web.py dulwich.egg-info/PKG-INFO dulwich.egg-info/SOURCES.txt dulwich.egg-info/dependency_links.txt dulwich.egg-info/entry_points.txt dulwich.egg-info/requires.txt dulwich.egg-info/top_level.txt dulwich/contrib/README.md dulwich/contrib/__init__.py dulwich/contrib/diffstat.py dulwich/contrib/paramiko_vendor.py dulwich/contrib/release_robot.py dulwich/contrib/swift.py dulwich/contrib/test_release_robot.py dulwich/contrib/test_swift.py dulwich/contrib/test_swift_smoke.py dulwich/tests/__init__.py dulwich/tests/test_archive.py dulwich/tests/test_blackbox.py dulwich/tests/test_client.py dulwich/tests/test_config.py dulwich/tests/test_diff_tree.py dulwich/tests/test_fastexport.py dulwich/tests/test_file.py dulwich/tests/test_grafts.py dulwich/tests/test_graph.py dulwich/tests/test_greenthreads.py dulwich/tests/test_hooks.py dulwich/tests/test_ignore.py dulwich/tests/test_index.py dulwich/tests/test_lfs.py dulwich/tests/test_line_ending.py dulwich/tests/test_lru_cache.py dulwich/tests/test_mailmap.py dulwich/tests/test_missing_obj_finder.py dulwich/tests/test_object_store.py dulwich/tests/test_objects.py dulwich/tests/test_objectspec.py dulwich/tests/test_pack.py dulwich/tests/test_patch.py dulwich/tests/test_porcelain.py dulwich/tests/test_protocol.py dulwich/tests/test_reflog.py dulwich/tests/test_refs.py dulwich/tests/test_repository.py dulwich/tests/test_server.py dulwich/tests/test_stash.py dulwich/tests/test_utils.py dulwich/tests/test_walk.py dulwich/tests/test_web.py dulwich/tests/utils.py dulwich/tests/compat/__init__.py dulwich/tests/compat/server_utils.py dulwich/tests/compat/test_client.py dulwich/tests/compat/test_pack.py dulwich/tests/compat/test_patch.py dulwich/tests/compat/test_repository.py dulwich/tests/compat/test_server.py dulwich/tests/compat/test_utils.py dulwich/tests/compat/test_web.py dulwich/tests/compat/utils.py dulwich/tests/data/blobs/11/11111111111111111111111111111111111111 dulwich/tests/data/blobs/6f/670c0fb53f9463760b7295fbb814e965fb20c8 dulwich/tests/data/blobs/95/4a536f7819d40e6f637f849ee187dd10066349 dulwich/tests/data/blobs/e6/9de29bb2d1d6434b8b29ae775ad8c2e48c5391 dulwich/tests/data/commits/0d/89f20333fbb1d2f3a94da77f4981373d8f4310 dulwich/tests/data/commits/5d/ac377bdded4c9aeb8dff595f0faeebcc8498cc dulwich/tests/data/commits/60/dacdc733de308bb77bb76ce0fb0f9b44c9769e dulwich/tests/data/indexes/index dulwich/tests/data/packs/pack-bc63ddad95e7321ee734ea11a7a62d314e0d7481.idx dulwich/tests/data/packs/pack-bc63ddad95e7321ee734ea11a7a62d314e0d7481.pack dulwich/tests/data/repos/.gitattributes dulwich/tests/data/repos/issue88_expect_ack_nak_client.export dulwich/tests/data/repos/issue88_expect_ack_nak_other.export dulwich/tests/data/repos/issue88_expect_ack_nak_server.export dulwich/tests/data/repos/server_new.export dulwich/tests/data/repos/server_old.export dulwich/tests/data/repos/a.git/HEAD dulwich/tests/data/repos/a.git/packed-refs dulwich/tests/data/repos/a.git/objects/28/237f4dc30d0d462658d6b937b08a0f0b6ef55a dulwich/tests/data/repos/a.git/objects/2a/72d929692c41d8554c07f6301757ba18a65d91 dulwich/tests/data/repos/a.git/objects/4e/f30bbfe26431a69c3820d3a683df54d688f2ec dulwich/tests/data/repos/a.git/objects/4f/2e6529203aa6d44b5af6e3292c837ceda003f9 dulwich/tests/data/repos/a.git/objects/7d/9a07d797595ef11344549b8d08198e48c15364 dulwich/tests/data/repos/a.git/objects/a2/96d0bb611188cabb256919f36bc30117cca005 dulwich/tests/data/repos/a.git/objects/a9/0fa2d900a17e99b433217e988c4eb4a2e9a097 dulwich/tests/data/repos/a.git/objects/b0/931cadc54336e78a1d980420e3268903b57a50 dulwich/tests/data/repos/a.git/objects/ff/d47d45845a8f6576491e1edb97e3fe6a850e7f dulwich/tests/data/repos/a.git/refs/heads/master dulwich/tests/data/repos/a.git/refs/tags/mytag dulwich/tests/data/repos/empty.git/HEAD dulwich/tests/data/repos/empty.git/config dulwich/tests/data/repos/empty.git/objects/info/.gitignore dulwich/tests/data/repos/empty.git/objects/pack/.gitignore dulwich/tests/data/repos/empty.git/refs/heads/.gitignore dulwich/tests/data/repos/empty.git/refs/tags/.gitignore dulwich/tests/data/repos/ooo_merge.git/HEAD dulwich/tests/data/repos/ooo_merge.git/objects/29/69be3e8ee1c0222396a5611407e4769f14e54b dulwich/tests/data/repos/ooo_merge.git/objects/38/74e9c60a6d149c44c928140f250d81e6381520 dulwich/tests/data/repos/ooo_merge.git/objects/6f/670c0fb53f9463760b7295fbb814e965fb20c8 dulwich/tests/data/repos/ooo_merge.git/objects/70/c190eb48fa8bbb50ddc692a17b44cb781af7f6 dulwich/tests/data/repos/ooo_merge.git/objects/76/01d7f6231db6a57f7bbb79ee52e4d462fd44d1 dulwich/tests/data/repos/ooo_merge.git/objects/90/182552c4a85a45ec2a835cadc3451bebdfe870 dulwich/tests/data/repos/ooo_merge.git/objects/95/4a536f7819d40e6f637f849ee187dd10066349 dulwich/tests/data/repos/ooo_merge.git/objects/b2/a2766a2879c209ab1176e7e778b81ae422eeaa dulwich/tests/data/repos/ooo_merge.git/objects/f5/07291b64138b875c28e03469025b1ea20bc614 dulwich/tests/data/repos/ooo_merge.git/objects/f9/e39b120c68182a4ba35349f832d0e4e61f485c dulwich/tests/data/repos/ooo_merge.git/objects/fb/5b0425c7ce46959bec94d54b9a157645e114f5 dulwich/tests/data/repos/ooo_merge.git/refs/heads/master dulwich/tests/data/repos/refs.git/HEAD dulwich/tests/data/repos/refs.git/packed-refs dulwich/tests/data/repos/refs.git/objects/3b/9e5457140e738c2dcd39bf6d7acf88379b90d1 dulwich/tests/data/repos/refs.git/objects/3e/c9c43c84ff242e3ef4a9fc5bc111fd780a76a8 dulwich/tests/data/repos/refs.git/objects/42/d06bd4b77fed026b154d16493e5deab78f02ec dulwich/tests/data/repos/refs.git/objects/a1/8114c31713746a33a2e70d9914d1ef3e781425 dulwich/tests/data/repos/refs.git/objects/cd/a609072918d7b70057b6bef9f4c2537843fcfe dulwich/tests/data/repos/refs.git/objects/df/6800012397fb85c56e7418dd4eb9405dee075c dulwich/tests/data/repos/refs.git/refs/heads/40-char-ref-aaaaaaaaaaaaaaaaaa dulwich/tests/data/repos/refs.git/refs/heads/loop dulwich/tests/data/repos/refs.git/refs/heads/master dulwich/tests/data/repos/refs.git/refs/tags/refs-0.2 dulwich/tests/data/repos/simple_merge.git/HEAD dulwich/tests/data/repos/simple_merge.git/objects/0d/89f20333fbb1d2f3a94da77f4981373d8f4310 dulwich/tests/data/repos/simple_merge.git/objects/1b/6318f651a534b38f9c7aedeebbd56c1e896853 dulwich/tests/data/repos/simple_merge.git/objects/29/69be3e8ee1c0222396a5611407e4769f14e54b dulwich/tests/data/repos/simple_merge.git/objects/4c/ffe90e0a41ad3f5190079d7c8f036bde29cbe6 dulwich/tests/data/repos/simple_merge.git/objects/5d/ac377bdded4c9aeb8dff595f0faeebcc8498cc dulwich/tests/data/repos/simple_merge.git/objects/60/dacdc733de308bb77bb76ce0fb0f9b44c9769e dulwich/tests/data/repos/simple_merge.git/objects/6f/670c0fb53f9463760b7295fbb814e965fb20c8 dulwich/tests/data/repos/simple_merge.git/objects/70/c190eb48fa8bbb50ddc692a17b44cb781af7f6 dulwich/tests/data/repos/simple_merge.git/objects/90/182552c4a85a45ec2a835cadc3451bebdfe870 dulwich/tests/data/repos/simple_merge.git/objects/95/4a536f7819d40e6f637f849ee187dd10066349 dulwich/tests/data/repos/simple_merge.git/objects/ab/64bbdcc51b170d21588e5c5d391ee5c0c96dfd dulwich/tests/data/repos/simple_merge.git/objects/d4/bdad6549dfedf25d3b89d21f506aff575b28a7 dulwich/tests/data/repos/simple_merge.git/objects/d8/0c186a03f423a81b39df39dc87fd269736ca86 dulwich/tests/data/repos/simple_merge.git/objects/e6/9de29bb2d1d6434b8b29ae775ad8c2e48c5391 dulwich/tests/data/repos/simple_merge.git/refs/heads/master dulwich/tests/data/repos/submodule/dotgit dulwich/tests/data/tags/71/033db03a03c6a36721efcf1968dd8f8e0cf023 dulwich/tests/data/trees/70/c190eb48fa8bbb50ddc692a17b44cb781af7f6 examples/clone.py examples/config.py examples/diff.py examples/latest_change.py examples/memoryrepo.py \ No newline at end of file diff --git a/dulwich/__init__.py b/dulwich/__init__.py index b6767615..f78ca4e0 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, 20, 6) +__version__ = (0, 20, 8) diff --git a/dulwich/client.py b/dulwich/client.py index 9453b13a..b7aefd6f 100644 --- a/dulwich/client.py +++ b/dulwich/client.py @@ -1,1927 +1,1934 @@ # 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 os import select import socket import subprocess import sys from typing import Optional, Dict, Callable, Set from urllib.parse import ( quote as urlquote, unquote as urlunquote, urlparse, urljoin, urlunsplit, urlunparse, ) import dulwich from dulwich.config import get_xdg_config_home_path from dulwich.errors import ( GitProtocolError, NotGitRepository, SendPackError, ) 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) class HTTPUnauthorized(Exception): """Raised when authentication fails.""" def __init__(self, www_authenticate): Exception.__init__(self, "No valid credentials provided") self.www_authenticate = www_authenticate 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_statuses = [] def check(self): """Check if there were any errors and, if so, raise exceptions. Raises: SendPackError: Raised when the server could not unpack Returns: iterator over refs """ if self._pack_status not in (b'unpack ok', None): raise SendPackError(self._pack_status) for status in self._ref_statuses: try: status, rest = status.split(b' ', 1) except ValueError: # malformed response, move on to the next one continue if status == b'ng': ref, error = rest.split(b' ', 1) yield ref, error.decode('utf-8') elif status == b'ok': yield rest, None else: raise GitProtocolError('invalid ref status %r' % 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) 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', 'items', '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) class SendPackResult(object): """Result of a upload-pack operation. Attributes: refs: Dictionary with all remote refs agent: User agent string ref_status: Optional dictionary mapping ref name to error message (if it failed to update), or None if it was updated successfully """ _FORWARDED_ATTRS = [ 'clear', 'copy', 'fromkeys', 'get', 'items', 'keys', 'pop', 'popitem', 'setdefault', 'update', 'values', 'viewitems', 'viewkeys', 'viewvalues'] def __init__(self, refs, agent=None, ref_status=None): self.refs = refs self.agent = agent self.ref_status = ref_status def _warn_deprecated(self): import warnings warnings.warn( "Use SendPackResult.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.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(SendPackResult, self).__getattribute__(name) def __repr__(self): return "%s(%r, %r)" % ( self.__class__.__name__, self.refs, 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() 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: SendPackResult object Raises: SendPackError: if server rejects the pack data """ 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 _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) @staticmethod def _should_send_pack(new_refs): # The packfile MUST NOT be sent if the only command used is delete. return any(sha != ZERO_SHA for sha in new_refs.values()) 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) agent = None for capability in server_capabilities: k, v = parse_capability(capability) if k == CAPABILITY_AGENT: agent = v unknown_capabilities = ( # noqa: F841 extract_capability_names(server_capabilities) - KNOWN_RECEIVE_CAPABILITIES) # TODO(jelmer): warn about unknown capabilities return negotiated_capabilities, agent def _handle_receive_pack_tail( self, proto: Protocol, capabilities: Set[bytes], progress: Callable[[bytes], None] = None ) -> Optional[Dict[bytes, Optional[str]]]: """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: dict mapping ref name to: error message if the ref failed to update None if it was updated successfully """ 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: return dict(self._report_status_parser.check()) return None 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() lines = [line.rstrip(b'\n') for line in stderr.readlines()] for line in lines: if line.startswith(b'ERROR: '): return GitProtocolError( line[len(b'ERROR: '):].decode('utf-8', 'replace')) return HangupException(lines) 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: SendPackResult Raises: SendPackError: if server rejects the pack data """ 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, agent = \ 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 set(new_refs.items()).issubset(set(old_refs.items())): proto.write_pkt_line(None) return SendPackResult(new_refs, agent=agent, ref_status={}) 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 ' + ref + 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 SendPackResult(old_refs, agent=agent, ref_status={}) 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: ref_status = dict(report_status_parser.check()) else: ref_status = None return SendPackResult( old_refs, agent=agent, ref_status=ref_status) (have, want) = self._handle_receive_pack_head( proto, negotiated_capabilities, old_refs, new_refs) pack_data_count, pack_data = generate_pack_data( have, want, ofs_delta=(CAPABILITY_OFS_DELTA in negotiated_capabilities)) if self._should_send_pack(new_refs): write_pack_data(proto.write_file(), pack_data_count, pack_data) ref_status = self._handle_receive_pack_tail( proto, negotiated_capabilities, progress) return SendPackResult(new_refs, agent=agent, ref_status=ref_status) 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": + if pkt == b"NACK\n" or pkt == b"NACK": return - elif pkt == b"ACK\n": + elif pkt == b"ACK\n" or pkt == b"ACK": 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 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 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 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 = os.fsdecode(path) 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: SendPackResult Raises: SendPackError: if server rejects the pack data """ 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 SendPackResult(new_refs, ref_status={}) target.object_store.add_pack_data( *generate_pack_data(have, want, ofs_delta=True)) ref_status = {} 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): msg = 'unable to set %s to %s' % (refname, new_sha1) progress(msg) ref_status[refname] = msg else: if not target.refs.remove_if_equals(refname, old_sha1): progress('unable to remove %s' % refname) ref_status[refname] = 'unable to remove' return SendPackResult(new_refs, ref_status=ref_status) 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 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 proxy_server is None: + for proxyname in ('https_proxy', 'http_proxy', 'all_proxy'): + proxy_server = os.environ.get(proxyname) + if proxy_server is not None: + break + if config is not None: - try: - proxy_server = config.get(b"http", b"proxy") - except KeyError: - pass + if proxy_server is 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(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 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 == 401: raise HTTPUnauthorized(resp.getheader('WWW-Authenticate')) 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 = 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 = 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: SendPackResult Raises: SendPackError: if server rejects the pack data """ url = self._get_url(path) old_refs, server_capabilities, url = self._discover_references( b"git-receive-pack", url) negotiated_capabilities, agent = ( 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 SendPackResult(old_refs, agent=agent, ref_status={}) if set(new_refs.items()).issubset(set(old_refs.items())): return SendPackResult(new_refs, agent=agent, ref_status={}) 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) pack_data_count, pack_data = generate_pack_data( have, want, ofs_delta=(CAPABILITY_OFS_DELTA in negotiated_capabilities)) if self._should_send_pack(new_refs): 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) ref_status = self._handle_receive_pack_tail( resp_proto, negotiated_capabilities, progress) return SendPackResult( new_refs, agent=agent, ref_status=ref_status) 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.fetch_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(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(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 FileNotFoundError: # If the file doesn't exist, try the next one. continue diff --git a/dulwich/protocol.py b/dulwich/protocol.py index 48ba16f0..343a06df 100644 --- a/dulwich/protocol.py +++ b/dulwich/protocol.py @@ -1,568 +1,576 @@ # protocol.py -- Shared parts of the git protocols # Copyright (C) 2008 John Carr # Copyright (C) 2008-2012 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. # """Generic functions for talking the git smart server protocol.""" from io import BytesIO from os import ( SEEK_END, ) import socket import dulwich from dulwich.errors import ( HangupException, GitProtocolError, ) TCP_GIT_PORT = 9418 ZERO_SHA = b"0" * 40 SINGLE_ACK = 0 MULTI_ACK = 1 MULTI_ACK_DETAILED = 2 # pack data SIDE_BAND_CHANNEL_DATA = 1 # progress messages SIDE_BAND_CHANNEL_PROGRESS = 2 # fatal error message just before stream aborts SIDE_BAND_CHANNEL_FATAL = 3 CAPABILITY_ATOMIC = b'atomic' CAPABILITY_DEEPEN_SINCE = b'deepen-since' CAPABILITY_DEEPEN_NOT = b'deepen-not' CAPABILITY_DEEPEN_RELATIVE = b'deepen-relative' CAPABILITY_DELETE_REFS = b'delete-refs' CAPABILITY_INCLUDE_TAG = b'include-tag' CAPABILITY_MULTI_ACK = b'multi_ack' CAPABILITY_MULTI_ACK_DETAILED = b'multi_ack_detailed' CAPABILITY_NO_DONE = b'no-done' CAPABILITY_NO_PROGRESS = b'no-progress' CAPABILITY_OFS_DELTA = b'ofs-delta' CAPABILITY_QUIET = b'quiet' CAPABILITY_REPORT_STATUS = b'report-status' CAPABILITY_SHALLOW = b'shallow' CAPABILITY_SIDE_BAND = b'side-band' CAPABILITY_SIDE_BAND_64K = b'side-band-64k' CAPABILITY_THIN_PACK = b'thin-pack' CAPABILITY_AGENT = b'agent' CAPABILITY_SYMREF = b'symref' CAPABILITY_ALLOW_TIP_SHA1_IN_WANT = b'allow-tip-sha1-in-want' CAPABILITY_ALLOW_REACHABLE_SHA1_IN_WANT = b'allow-reachable-sha1-in-want' # Magic ref that is used to attach capabilities to when # there are no refs. Should always be ste to ZERO_SHA. CAPABILITIES_REF = b'capabilities^{}' COMMON_CAPABILITIES = [ CAPABILITY_OFS_DELTA, CAPABILITY_SIDE_BAND, CAPABILITY_SIDE_BAND_64K, CAPABILITY_AGENT, CAPABILITY_NO_PROGRESS] KNOWN_UPLOAD_CAPABILITIES = set(COMMON_CAPABILITIES + [ CAPABILITY_THIN_PACK, CAPABILITY_MULTI_ACK, CAPABILITY_MULTI_ACK_DETAILED, CAPABILITY_INCLUDE_TAG, CAPABILITY_DEEPEN_SINCE, CAPABILITY_SYMREF, CAPABILITY_SHALLOW, CAPABILITY_DEEPEN_NOT, CAPABILITY_DEEPEN_RELATIVE, CAPABILITY_ALLOW_TIP_SHA1_IN_WANT, CAPABILITY_ALLOW_REACHABLE_SHA1_IN_WANT, ]) KNOWN_RECEIVE_CAPABILITIES = set(COMMON_CAPABILITIES + [ CAPABILITY_REPORT_STATUS, CAPABILITY_DELETE_REFS, CAPABILITY_QUIET, CAPABILITY_ATOMIC, ]) def agent_string(): return ('dulwich/%d.%d.%d' % dulwich.__version__).encode('ascii') def capability_agent(): return CAPABILITY_AGENT + b'=' + agent_string() def capability_symref(from_ref, to_ref): return CAPABILITY_SYMREF + b'=' + from_ref + b':' + to_ref def extract_capability_names(capabilities): return set(parse_capability(c)[0] for c in capabilities) def parse_capability(capability): parts = capability.split(b'=', 1) if len(parts) == 1: return (parts[0], None) return tuple(parts) def symref_capabilities(symrefs): return [capability_symref(*k) for k in symrefs] COMMAND_DEEPEN = b'deepen' COMMAND_SHALLOW = b'shallow' COMMAND_UNSHALLOW = b'unshallow' COMMAND_DONE = b'done' COMMAND_WANT = b'want' COMMAND_HAVE = b'have' class ProtocolFile(object): """A dummy file for network ops that expect file-like objects.""" def __init__(self, read, write): self.read = read self.write = write def tell(self): pass def close(self): pass +def format_cmd_pkt(cmd, *args): + return cmd + b" " + b"".join([(a + b"\0") for a in args]) + + +def parse_cmd_pkt(line): + splice_at = line.find(b" ") + cmd, args = line[:splice_at], line[splice_at+1:] + assert args[-1:] == b"\x00" + return cmd, args[:-1].split(b"\0") + + def pkt_line(data): """Wrap data in a pkt-line. Args: data: The data to wrap, as a str or None. Returns: The data prefixed with its length in pkt-line format; if data was None, returns the flush-pkt ('0000'). """ if data is None: return b'0000' return ('%04x' % (len(data) + 4)).encode('ascii') + data class Protocol(object): """Class for interacting with a remote git process over the wire. Parts of the git wire protocol use 'pkt-lines' to communicate. A pkt-line consists of the length of the line as a 4-byte hex string, followed by the payload data. The length includes the 4-byte header. The special line '0000' indicates the end of a section of input and is called a 'flush-pkt'. For details on the pkt-line format, see the cgit distribution: Documentation/technical/protocol-common.txt """ def __init__(self, read, write, close=None, report_activity=None): self.read = read self.write = write self._close = close self.report_activity = report_activity self._readahead = None def close(self): if self._close: self._close() def __enter__(self): return self def __exit__(self, exc_type, exc_val, exc_tb): self.close() def read_pkt_line(self): """Reads a pkt-line from the remote git process. This method may read from the readahead buffer; see unread_pkt_line. Returns: The next string from the stream, without the length prefix, or None for a flush-pkt ('0000'). """ if self._readahead is None: read = self.read else: read = self._readahead.read self._readahead = None try: sizestr = read(4) if not sizestr: raise HangupException() size = int(sizestr, 16) if size == 0: if self.report_activity: self.report_activity(4, 'read') return None if self.report_activity: self.report_activity(size, 'read') pkt_contents = read(size-4) except socket.error as e: raise GitProtocolError(e) else: if len(pkt_contents) + 4 != size: raise GitProtocolError( 'Length of pkt read %04x does not match length prefix %04x' % (len(pkt_contents) + 4, size)) return pkt_contents def eof(self): """Test whether the protocol stream has reached EOF. Note that this refers to the actual stream EOF and not just a flush-pkt. Returns: True if the stream is at EOF, False otherwise. """ try: next_line = self.read_pkt_line() except HangupException: return True self.unread_pkt_line(next_line) return False def unread_pkt_line(self, data): """Unread a single line of data into the readahead buffer. This method can be used to unread a single pkt-line into a fixed readahead buffer. Args: data: The data to unread, without the length prefix. Raises: ValueError: If more than one pkt-line is unread. """ if self._readahead is not None: raise ValueError('Attempted to unread multiple pkt-lines.') self._readahead = BytesIO(pkt_line(data)) def read_pkt_seq(self): """Read a sequence of pkt-lines from the remote git process. Returns: Yields each line of data up to but not including the next flush-pkt. """ pkt = self.read_pkt_line() while pkt: yield pkt pkt = self.read_pkt_line() def write_pkt_line(self, line): """Sends a pkt-line to the remote git process. Args: line: A string containing the data to send, without the length prefix. """ try: line = pkt_line(line) self.write(line) if self.report_activity: self.report_activity(len(line), 'write') except socket.error as e: raise GitProtocolError(e) def write_file(self): """Return a writable file-like object for this protocol.""" class ProtocolFile(object): def __init__(self, proto): self._proto = proto self._offset = 0 def write(self, data): self._proto.write(data) self._offset += len(data) def tell(self): return self._offset def close(self): pass return ProtocolFile(self) def write_sideband(self, channel, blob): """Write multiplexed data to the sideband. Args: channel: An int specifying the channel to write to. blob: A blob of data (as a string) to send on this channel. """ # a pktline can be a max of 65520. a sideband line can therefore be # 65520-5 = 65515 # WTF: Why have the len in ASCII, but the channel in binary. while blob: self.write_pkt_line(bytes(bytearray([channel])) + blob[:65515]) blob = blob[65515:] def send_cmd(self, cmd, *args): """Send a command and some arguments to a git server. Only used for the TCP git protocol (git://). Args: cmd: The remote service to access. args: List of arguments to send to remove service. """ - self.write_pkt_line(cmd + b" " + b"".join([(a + b"\0") for a in args])) + self.write_pkt_line(format_cmd_pkt(cmd, *args)) def read_cmd(self): """Read a command and some arguments from the git client Only used for the TCP git protocol (git://). Returns: A tuple of (command, [list of arguments]). """ line = self.read_pkt_line() - splice_at = line.find(b" ") - cmd, args = line[:splice_at], line[splice_at+1:] - assert args[-1:] == b"\x00" - return cmd, args[:-1].split(b"\0") + return parse_cmd_pkt(line) _RBUFSIZE = 8192 # Default read buffer size. class ReceivableProtocol(Protocol): """Variant of Protocol that allows reading up to a size without blocking. This class has a recv() method that behaves like socket.recv() in addition to a read() method. If you want to read n bytes from the wire and block until exactly n bytes (or EOF) are read, use read(n). If you want to read at most n bytes from the wire but don't care if you get less, use recv(n). Note that recv(n) will still block until at least one byte is read. """ def __init__(self, recv, write, close=None, report_activity=None, rbufsize=_RBUFSIZE): super(ReceivableProtocol, self).__init__( self.read, write, close=close, report_activity=report_activity) self._recv = recv self._rbuf = BytesIO() self._rbufsize = rbufsize def read(self, size): # From _fileobj.read in socket.py in the Python 2.6.5 standard library, # with the following modifications: # - omit the size <= 0 branch # - seek back to start rather than 0 in case some buffer has been # consumed. # - use SEEK_END instead of the magic number. # Copyright (c) 2001-2010 Python Software Foundation; All Rights # Reserved # Licensed under the Python Software Foundation License. # TODO: see if buffer is more efficient than cBytesIO. assert size > 0 # Our use of BytesIO rather than lists of string objects returned by # recv() minimizes memory usage and fragmentation that occurs when # rbufsize is large compared to the typical return value of recv(). buf = self._rbuf start = buf.tell() buf.seek(0, SEEK_END) # buffer may have been partially consumed by recv() buf_len = buf.tell() - start if buf_len >= size: # Already have size bytes in our buffer? Extract and return. buf.seek(start) rv = buf.read(size) self._rbuf = BytesIO() self._rbuf.write(buf.read()) self._rbuf.seek(0) return rv self._rbuf = BytesIO() # reset _rbuf. we consume it via buf. while True: left = size - buf_len # recv() will malloc the amount of memory given as its # parameter even though it often returns much less data # than that. The returned data string is short lived # as we copy it into a BytesIO and free it. This avoids # fragmentation issues on many platforms. data = self._recv(left) if not data: break n = len(data) if n == size and not buf_len: # Shortcut. Avoid buffer data copies when: # - We have no data in our buffer. # AND # - Our call to recv returned exactly the # number of bytes we were asked to read. return data if n == left: buf.write(data) del data # explicit free break assert n <= left, "_recv(%d) returned %d bytes" % (left, n) buf.write(data) buf_len += n del data # explicit free # assert buf_len == buf.tell() buf.seek(start) return buf.read() def recv(self, size): assert size > 0 buf = self._rbuf start = buf.tell() buf.seek(0, SEEK_END) buf_len = buf.tell() buf.seek(start) left = buf_len - start if not left: # only read from the wire if our read buffer is exhausted data = self._recv(self._rbufsize) if len(data) == size: # shortcut: skip the buffer if we read exactly size bytes return data buf = BytesIO() buf.write(data) buf.seek(0) del data # explicit free self._rbuf = buf return buf.read(size) def extract_capabilities(text): """Extract a capabilities list from a string, if present. Args: text: String to extract from Returns: Tuple with text with capabilities removed and list of capabilities """ if b"\0" not in text: return text, [] text, capabilities = text.rstrip().split(b"\0") return (text, capabilities.strip().split(b" ")) def extract_want_line_capabilities(text): """Extract a capabilities list from a want line, if present. Note that want lines have capabilities separated from the rest of the line by a space instead of a null byte. Thus want lines have the form: want obj-id cap1 cap2 ... Args: text: Want line to extract from Returns: Tuple with text with capabilities removed and list of capabilities """ split_text = text.rstrip().split(b" ") if len(split_text) < 3: return text, [] return (b" ".join(split_text[:2]), split_text[2:]) def ack_type(capabilities): """Extract the ack type from a capabilities list.""" if b'multi_ack_detailed' in capabilities: return MULTI_ACK_DETAILED elif b'multi_ack' in capabilities: return MULTI_ACK return SINGLE_ACK class BufferedPktLineWriter(object): """Writer that wraps its data in pkt-lines and has an independent buffer. Consecutive calls to write() wrap the data in a pkt-line and then buffers it until enough lines have been written such that their total length (including length prefix) reach the buffer size. """ def __init__(self, write, bufsize=65515): """Initialize the BufferedPktLineWriter. Args: write: A write callback for the underlying writer. bufsize: The internal buffer size, including length prefixes. """ self._write = write self._bufsize = bufsize self._wbuf = BytesIO() self._buflen = 0 def write(self, data): """Write data, wrapping it in a pkt-line.""" line = pkt_line(data) line_len = len(line) over = self._buflen + line_len - self._bufsize if over >= 0: start = line_len - over self._wbuf.write(line[:start]) self.flush() else: start = 0 saved = line[start:] self._wbuf.write(saved) self._buflen += len(saved) def flush(self): """Flush all data from the buffer.""" data = self._wbuf.getvalue() if data: self._write(data) self._len = 0 self._wbuf = BytesIO() class PktLineParser(object): """Packet line parser that hands completed packets off to a callback. """ def __init__(self, handle_pkt): self.handle_pkt = handle_pkt self._readahead = BytesIO() def parse(self, data): """Parse a fragment of data and call back for any completed packets. """ self._readahead.write(data) buf = self._readahead.getvalue() if len(buf) < 4: return while len(buf) >= 4: size = int(buf[:4], 16) if size == 0: self.handle_pkt(None) buf = buf[4:] elif size <= len(buf): self.handle_pkt(buf[4:size]) buf = buf[size:] else: break self._readahead = BytesIO() self._readahead.write(buf) def get_tail(self): """Read back any unused data.""" return self._readahead.getvalue() diff --git a/dulwich/repo.py b/dulwich/repo.py index f27efc9e..a63608ef 100644 --- a/dulwich/repo.py +++ b/dulwich/repo.py @@ -1,1533 +1,1546 @@ # repo.py -- For dealing with git repositories. # Copyright (C) 2007 James Westby # Copyright (C) 2008-2013 Jelmer Vernooij # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """Repository access. This module contains the base class for git repositories (BaseRepo) and an implementation which uses a repository on local disk (Repo). """ from io import BytesIO import os import sys import stat import time from typing import Optional, Tuple, TYPE_CHECKING, List, Dict, Union, Iterable if TYPE_CHECKING: # There are no circular imports here, but we try to defer imports as long # as possible to reduce start-up time for anything that doesn't need # these imports. from dulwich.config import StackedConfig, ConfigFile from dulwich.index import Index from dulwich.errors import ( NoIndexPresent, NotBlobError, NotCommitError, NotGitRepository, NotTreeError, NotTagError, CommitError, RefFormatError, HookError, ) from dulwich.file import ( GitFile, ) from dulwich.object_store import ( DiskObjectStore, MemoryObjectStore, BaseObjectStore, ObjectStoreGraphWalker, ) from dulwich.objects import ( check_hexsha, valid_hexsha, Blob, Commit, ShaFile, Tag, Tree, ) from dulwich.pack import ( pack_objects_to_data, ) from dulwich.hooks import ( Hook, PreCommitShellHook, PostCommitShellHook, CommitMsgShellHook, PostReceiveShellHook, ) from dulwich.line_ending import BlobNormalizer from dulwich.refs import ( # noqa: F401 ANNOTATED_TAG_SUFFIX, check_ref_format, RefsContainer, DictRefsContainer, InfoRefsContainer, DiskRefsContainer, read_packed_refs, read_packed_refs_with_peeled, write_packed_refs, SYMREF, ) import warnings CONTROLDIR = '.git' OBJECTDIR = 'objects' REFSDIR = 'refs' REFSDIR_TAGS = 'tags' REFSDIR_HEADS = 'heads' INDEX_FILENAME = "index" COMMONDIR = 'commondir' GITDIR = 'gitdir' WORKTREES = 'worktrees' BASE_DIRECTORIES = [ ["branches"], [REFSDIR], [REFSDIR, REFSDIR_TAGS], [REFSDIR, REFSDIR_HEADS], ["hooks"], ["info"] ] DEFAULT_REF = b'refs/heads/master' class InvalidUserIdentity(Exception): """User identity is not of the format 'user '""" def __init__(self, identity): self.identity = identity def _get_default_identity() -> Tuple[str, str]: import getpass import socket username = getpass.getuser() try: import pwd except ImportError: fullname = None else: try: gecos = pwd.getpwnam(username).pw_gecos except KeyError: fullname = None else: fullname = gecos.split(',')[0] if not fullname: fullname = username email = os.environ.get('EMAIL') if email is None: email = "{}@{}".format(username, socket.gethostname()) return (fullname, email) def get_user_identity( config: 'StackedConfig', kind: Optional[str] = None) -> bytes: """Determine the identity to use for new commits. If kind is set, this first checks GIT_${KIND}_NAME and GIT_${KIND}_EMAIL. If those variables are not set, then it will fall back to reading the user.name and user.email settings from the specified configuration. If that also fails, then it will fall back to using the current users' identity as obtained from the host system (e.g. the gecos field, $EMAIL, $USER@$(hostname -f). Args: kind: Optional kind to return identity for, usually either "AUTHOR" or "COMMITTER". Returns: A user identity """ user = None # type: Optional[bytes] email = None # type: Optional[bytes] if kind: user_uc = os.environ.get("GIT_" + kind + "_NAME") if user_uc is not None: user = user_uc.encode('utf-8') email_uc = os.environ.get("GIT_" + kind + "_EMAIL") if email_uc is not None: email = email_uc.encode('utf-8') if user is None: try: user = config.get(("user", ), "name") except KeyError: user = None if email is None: try: email = config.get(("user", ), "email") except KeyError: email = None default_user, default_email = _get_default_identity() if user is None: user = default_user.encode('utf-8') if email is None: email = default_email.encode('utf-8') if email.startswith(b'<') and email.endswith(b'>'): email = email[1:-1] return user + b" <" + email + b">" def check_user_identity(identity): """Verify that a user identity is formatted correctly. Args: identity: User identity bytestring Raises: InvalidUserIdentity: Raised when identity is invalid """ try: fst, snd = identity.split(b' <', 1) except ValueError: raise InvalidUserIdentity(identity) if b'>' not in snd: raise InvalidUserIdentity(identity) def parse_graftpoints( graftpoints: Iterable[bytes]) -> Dict[bytes, List[bytes]]: """Convert a list of graftpoints into a dict Args: graftpoints: Iterator of graftpoint lines Each line is formatted as: []* Resulting dictionary is: : [*] https://git.wiki.kernel.org/index.php/GraftPoint """ grafts = {} for line in graftpoints: raw_graft = line.split(None, 1) commit = raw_graft[0] if len(raw_graft) == 2: parents = raw_graft[1].split() else: parents = [] for sha in [commit] + parents: check_hexsha(sha, 'Invalid graftpoint') grafts[commit] = parents return grafts def serialize_graftpoints(graftpoints: Dict[bytes, List[bytes]]) -> bytes: """Convert a dictionary of grafts into string The graft dictionary is: : [*] Each line is formatted as: []* https://git.wiki.kernel.org/index.php/GraftPoint """ graft_lines = [] for commit, parents in graftpoints.items(): if parents: graft_lines.append(commit + b' ' + b' '.join(parents)) else: graft_lines.append(commit) return b'\n'.join(graft_lines) def _set_filesystem_hidden(path): """Mark path as to be hidden if supported by platform and filesystem. On win32 uses SetFileAttributesW api: """ if sys.platform == 'win32': import ctypes from ctypes.wintypes import BOOL, DWORD, LPCWSTR FILE_ATTRIBUTE_HIDDEN = 2 SetFileAttributesW = ctypes.WINFUNCTYPE(BOOL, LPCWSTR, DWORD)( ("SetFileAttributesW", ctypes.windll.kernel32)) if isinstance(path, bytes): path = os.fsdecode(path) if not SetFileAttributesW(path, FILE_ATTRIBUTE_HIDDEN): pass # Could raise or log `ctypes.WinError()` here # Could implement other platform specific filesytem hiding here class ParentsProvider(object): def __init__(self, store, grafts={}, shallows=[]): self.store = store self.grafts = grafts self.shallows = set(shallows) def get_parents(self, commit_id, commit=None): try: return self.grafts[commit_id] except KeyError: pass if commit_id in self.shallows: return [] if commit is None: commit = self.store[commit_id] return commit.parents class BaseRepo(object): """Base class for a git repository. :ivar object_store: Dictionary-like object for accessing the objects :ivar refs: Dictionary-like object with the refs in this repository """ def __init__(self, object_store: BaseObjectStore, refs: RefsContainer): """Open a repository. This shouldn't be called directly, but rather through one of the base classes, such as MemoryRepo or Repo. Args: object_store: Object store to use refs: Refs container to use """ self.object_store = object_store self.refs = refs self._graftpoints = {} # type: Dict[bytes, List[bytes]] self.hooks = {} # type: Dict[str, Hook] def _determine_file_mode(self) -> bool: """Probe the file-system to determine whether permissions can be trusted. Returns: True if permissions can be trusted, False otherwise. """ raise NotImplementedError(self._determine_file_mode) def _init_files(self, bare: bool) -> None: """Initialize a default set of named files.""" from dulwich.config import ConfigFile self._put_named_file('description', b"Unnamed repository") f = BytesIO() cf = ConfigFile() cf.set("core", "repositoryformatversion", "0") if self._determine_file_mode(): cf.set("core", "filemode", True) else: cf.set("core", "filemode", False) cf.set("core", "bare", bare) cf.set("core", "logallrefupdates", True) cf.write_to_file(f) self._put_named_file('config', f.getvalue()) self._put_named_file(os.path.join('info', 'exclude'), b'') def get_named_file(self, path): """Get a file from the control dir with a specific name. Although the filename should be interpreted as a filename relative to the control dir in a disk-based Repo, the object returned need not be pointing to a file in that location. Args: path: The path to the file, relative to the control dir. Returns: An open file object, or None if the file does not exist. """ raise NotImplementedError(self.get_named_file) def _put_named_file(self, path, contents): """Write a file to the control dir with the given name and contents. Args: path: The path to the file, relative to the control dir. contents: A string to write to the file. """ raise NotImplementedError(self._put_named_file) def _del_named_file(self, path): """Delete a file in the contrl directory with the given name.""" raise NotImplementedError(self._del_named_file) def open_index(self): """Open the index for this repository. Raises: NoIndexPresent: If no index is present Returns: The matching `Index` """ raise NotImplementedError(self.open_index) def fetch(self, target, determine_wants=None, progress=None, depth=None): """Fetch objects into another repository. Args: target: The target repository determine_wants: Optional function to determine what refs to fetch. progress: Optional progress function depth: Optional shallow fetch depth Returns: The local refs """ if determine_wants is None: determine_wants = target.object_store.determine_wants_all count, pack_data = self.fetch_pack_data( determine_wants, target.get_graph_walker(), progress=progress, depth=depth) target.object_store.add_pack_data(count, pack_data, progress) return self.get_refs() def fetch_pack_data(self, determine_wants, graph_walker, progress, get_tagged=None, depth=None): """Fetch the pack data required for a set of revisions. Args: determine_wants: Function that takes a dictionary with heads and returns the list of heads to fetch. graph_walker: Object that can iterate over the list of revisions to fetch and has an "ack" method that will be called to acknowledge that a revision is present. progress: Simple progress function that will be called with updated progress strings. get_tagged: Function that returns a dict of pointed-to sha -> tag sha for including tags. depth: Shallow fetch depth Returns: count and iterator over pack data """ # TODO(jelmer): Fetch pack data directly, don't create objects first. objects = self.fetch_objects(determine_wants, graph_walker, progress, get_tagged, depth=depth) return pack_objects_to_data(objects) def fetch_objects(self, determine_wants, graph_walker, progress, get_tagged=None, depth=None): """Fetch the missing objects required for a set of revisions. Args: determine_wants: Function that takes a dictionary with heads and returns the list of heads to fetch. graph_walker: Object that can iterate over the list of revisions to fetch and has an "ack" method that will be called to acknowledge that a revision is present. progress: Simple progress function that will be called with updated progress strings. get_tagged: Function that returns a dict of pointed-to sha -> tag sha for including tags. depth: Shallow fetch depth Returns: iterator over objects, with __len__ implemented """ if depth not in (None, 0): raise NotImplementedError("depth not supported yet") refs = {} for ref, sha in self.get_refs().items(): try: obj = self.object_store[sha] except KeyError: warnings.warn( 'ref %s points at non-present sha %s' % ( ref.decode('utf-8', 'replace'), sha.decode('ascii')), UserWarning) continue else: if isinstance(obj, Tag): refs[ref + ANNOTATED_TAG_SUFFIX] = obj.object[1] refs[ref] = sha wants = determine_wants(refs) if not isinstance(wants, list): raise TypeError("determine_wants() did not return a list") shallows = getattr(graph_walker, 'shallow', frozenset()) unshallows = getattr(graph_walker, 'unshallow', frozenset()) if wants == []: # TODO(dborowitz): find a way to short-circuit that doesn't change # this interface. if shallows or unshallows: # Do not send a pack in shallow short-circuit path return None return [] # If the graph walker is set up with an implementation that can # ACK/NAK to the wire, it will write data to the client through # this call as a side-effect. haves = self.object_store.find_common_revisions(graph_walker) # Deal with shallow requests separately because the haves do # not reflect what objects are missing if shallows or unshallows: # TODO: filter the haves commits from iter_shas. the specific # commits aren't missing. haves = [] parents_provider = ParentsProvider( self.object_store, shallows=shallows) def get_parents(commit): return parents_provider.get_parents(commit.id, commit) return self.object_store.iter_shas( self.object_store.find_missing_objects( haves, wants, self.get_shallow(), progress, get_tagged, get_parents=get_parents)) def generate_pack_data(self, have, want, progress=None, ofs_delta=None): """Generate pack data objects for a set of wants/haves. Args: have: List of SHA1s of objects that should not be sent want: List of SHA1s of objects that should be sent ofs_delta: Whether OFS deltas can be included progress: Optional progress reporting method """ return self.object_store.generate_pack_data( have, want, shallow=self.get_shallow(), progress=progress, ofs_delta=ofs_delta) def get_graph_walker(self, heads=None): """Retrieve a graph walker. A graph walker is used by a remote repository (or proxy) to find out which objects are present in this repository. Args: heads: Repository heads to use (optional) Returns: A graph walker object """ if heads is None: heads = [ sha for sha in self.refs.as_dict(b'refs/heads').values() if sha in self.object_store] parents_provider = ParentsProvider(self.object_store) return ObjectStoreGraphWalker( heads, parents_provider.get_parents, shallow=self.get_shallow()) def get_refs(self) -> Dict[bytes, bytes]: """Get dictionary with all refs. Returns: A ``dict`` mapping ref names to SHA1s """ return self.refs.as_dict() def head(self) -> bytes: """Return the SHA1 pointed at by HEAD.""" return self.refs[b'HEAD'] def _get_object(self, sha, cls): assert len(sha) in (20, 40) ret = self.get_object(sha) if not isinstance(ret, cls): if cls is Commit: raise NotCommitError(ret) elif cls is Blob: raise NotBlobError(ret) elif cls is Tree: raise NotTreeError(ret) elif cls is Tag: raise NotTagError(ret) else: raise Exception("Type invalid: %r != %r" % ( ret.type_name, cls.type_name)) return ret def get_object(self, sha: bytes) -> ShaFile: """Retrieve the object with the specified SHA. Args: sha: SHA to retrieve Returns: A ShaFile object Raises: KeyError: when the object can not be found """ return self.object_store[sha] def parents_provider(self): return ParentsProvider( self.object_store, grafts=self._graftpoints, shallows=self.get_shallow()) def get_parents(self, sha: bytes, commit: Commit = None) -> List[bytes]: """Retrieve the parents of a specific commit. If the specific commit is a graftpoint, the graft parents will be returned instead. Args: sha: SHA of the commit for which to retrieve the parents commit: Optional commit matching the sha Returns: List of parents """ return self.parents_provider().get_parents(sha, commit) def get_config(self): """Retrieve the config object. Returns: `ConfigFile` object for the ``.git/config`` file. """ raise NotImplementedError(self.get_config) def get_description(self): """Retrieve the description for this repository. Returns: String with the description of the repository as set by the user. """ raise NotImplementedError(self.get_description) def set_description(self, description): """Set the description for this repository. Args: description: Text to set as description for this repository. """ raise NotImplementedError(self.set_description) def get_config_stack(self) -> 'StackedConfig': """Return a config stack for this repository. This stack accesses the configuration for both this repository itself (.git/config) and the global configuration, which usually lives in ~/.gitconfig. Returns: `Config` instance for this repository """ from dulwich.config import StackedConfig backends = [self.get_config()] + StackedConfig.default_backends() return StackedConfig(backends, writable=backends[0]) def get_shallow(self): """Get the set of shallow commits. Returns: Set of shallow commits. """ f = self.get_named_file('shallow') if f is None: return set() with f: return set(line.strip() for line in f) def update_shallow(self, new_shallow, new_unshallow): """Update the list of shallow objects. Args: new_shallow: Newly shallow objects new_unshallow: Newly no longer shallow objects """ shallow = self.get_shallow() if new_shallow: shallow.update(new_shallow) if new_unshallow: shallow.difference_update(new_unshallow) self._put_named_file( 'shallow', b''.join([sha + b'\n' for sha in shallow])) def get_peeled(self, ref): """Get the peeled value of a ref. Args: ref: The refname to peel. Returns: The fully-peeled SHA1 of a tag object, after peeling all intermediate tags; if the original ref does not point to a tag, this will equal the original SHA1. """ cached = self.refs.get_peeled(ref) if cached is not None: return cached return self.object_store.peel_sha(self.refs[ref]).id def get_walker(self, include=None, *args, **kwargs): """Obtain a walker for this repository. Args: include: Iterable of SHAs of commits to include along with their ancestors. Defaults to [HEAD] exclude: Iterable of SHAs of commits to exclude along with their ancestors, overriding includes. order: ORDER_* constant specifying the order of results. Anything other than ORDER_DATE may result in O(n) memory usage. reverse: If True, reverse the order of output, requiring O(n) memory. max_entries: The maximum number of entries to yield, or None for no limit. paths: Iterable of file or subtree paths to show entries for. rename_detector: diff.RenameDetector object for detecting renames. follow: If True, follow path across renames/copies. Forces a default rename_detector. since: Timestamp to list commits after. until: Timestamp to list commits before. queue_cls: A class to use for a queue of commits, supporting the iterator protocol. The constructor takes a single argument, the Walker. Returns: A `Walker` object """ from dulwich.walk import Walker if include is None: include = [self.head()] if isinstance(include, str): include = [include] kwargs['get_parents'] = lambda commit: self.get_parents( commit.id, commit) return Walker(self.object_store, include, *args, **kwargs) def __getitem__(self, name): """Retrieve a Git object by SHA1 or ref. Args: name: A Git object SHA1 or a ref name Returns: A `ShaFile` object, such as a Commit or Blob Raises: KeyError: when the specified ref or object does not exist """ if not isinstance(name, bytes): raise TypeError("'name' must be bytestring, not %.80s" % type(name).__name__) if len(name) in (20, 40): try: return self.object_store[name] except (KeyError, ValueError): pass try: return self.object_store[self.refs[name]] except RefFormatError: raise KeyError(name) def __contains__(self, name: bytes) -> bool: """Check if a specific Git object or ref is present. Args: name: Git object SHA1 or ref name """ if len(name) == 20 or (len(name) == 40 and valid_hexsha(name)): return name in self.object_store or name in self.refs else: return name in self.refs def __setitem__(self, name: bytes, value: Union[ShaFile, bytes]): """Set a ref. Args: name: ref name value: Ref value - either a ShaFile object, or a hex sha """ if name.startswith(b"refs/") or name == b'HEAD': if isinstance(value, ShaFile): self.refs[name] = value.id elif isinstance(value, bytes): self.refs[name] = value else: raise TypeError(value) else: raise ValueError(name) def __delitem__(self, name: bytes): """Remove a ref. Args: name: Name of the ref to remove """ if name.startswith(b"refs/") or name == b"HEAD": del self.refs[name] else: raise ValueError(name) def _get_user_identity( self, config: 'StackedConfig', kind: str = None) -> bytes: """Determine the identity to use for new commits. """ # TODO(jelmer): Deprecate this function in favor of get_user_identity return get_user_identity(config) def _add_graftpoints(self, updated_graftpoints: Dict[bytes, List[bytes]]): """Add or modify graftpoints Args: updated_graftpoints: Dict of commit shas to list of parent shas """ # Simple validation for commit, parents in updated_graftpoints.items(): for sha in [commit] + parents: check_hexsha(sha, 'Invalid graftpoint') self._graftpoints.update(updated_graftpoints) def _remove_graftpoints(self, to_remove: List[bytes] = []) -> None: """Remove graftpoints Args: to_remove: List of commit shas """ for sha in to_remove: del self._graftpoints[sha] def _read_heads(self, name): f = self.get_named_file(name) if f is None: return [] with f: return [line.strip() for line in f.readlines() if line.strip()] def do_commit(self, message=None, committer=None, author=None, commit_timestamp=None, commit_timezone=None, author_timestamp=None, author_timezone=None, tree=None, encoding=None, ref=b'HEAD', merge_heads=None): """Create a new commit. If not specified, `committer` and `author` default to get_user_identity(..., 'COMMITTER') and get_user_identity(..., 'AUTHOR') respectively. Args: message: Commit message committer: Committer fullname author: Author fullname commit_timestamp: Commit timestamp (defaults to now) commit_timezone: Commit timestamp timezone (defaults to GMT) author_timestamp: Author timestamp (defaults to commit timestamp) author_timezone: Author timestamp timezone (defaults to commit timestamp timezone) tree: SHA1 of the tree root to use (if not specified the current index will be committed). encoding: Encoding ref: Optional ref to commit to (defaults to current branch) merge_heads: Merge heads (defaults to .git/MERGE_HEADS) Returns: New commit SHA1 """ import time c = Commit() if tree is None: index = self.open_index() c.tree = index.commit(self.object_store) else: if len(tree) != 40: raise ValueError("tree must be a 40-byte hex sha string") c.tree = tree try: self.hooks['pre-commit'].execute() except HookError as e: raise CommitError(e) except KeyError: # no hook defined, silent fallthrough pass config = self.get_config_stack() if merge_heads is None: merge_heads = self._read_heads('MERGE_HEADS') if committer is None: committer = get_user_identity(config, kind='COMMITTER') check_user_identity(committer) c.committer = committer if commit_timestamp is None: # FIXME: Support GIT_COMMITTER_DATE environment variable commit_timestamp = time.time() c.commit_time = int(commit_timestamp) if commit_timezone is None: # FIXME: Use current user timezone rather than UTC commit_timezone = 0 c.commit_timezone = commit_timezone if author is None: author = get_user_identity(config, kind='AUTHOR') c.author = author check_user_identity(author) if author_timestamp is None: # FIXME: Support GIT_AUTHOR_DATE environment variable author_timestamp = commit_timestamp c.author_time = int(author_timestamp) if author_timezone is None: author_timezone = commit_timezone c.author_timezone = author_timezone if encoding is None: try: encoding = config.get(('i18n', ), 'commitEncoding') except KeyError: pass # No dice if encoding is not None: c.encoding = encoding if message is None: # FIXME: Try to read commit message from .git/MERGE_MSG raise ValueError("No commit message specified") try: c.message = self.hooks['commit-msg'].execute(message) if c.message is None: c.message = message except HookError as e: raise CommitError(e) except KeyError: # no hook defined, message not modified c.message = message if ref is None: # Create a dangling commit c.parents = merge_heads self.object_store.add_object(c) else: try: old_head = self.refs[ref] c.parents = [old_head] + merge_heads self.object_store.add_object(c) ok = self.refs.set_if_equals( ref, old_head, c.id, message=b"commit: " + message, committer=committer, timestamp=commit_timestamp, timezone=commit_timezone) except KeyError: c.parents = merge_heads self.object_store.add_object(c) ok = self.refs.add_if_new( ref, c.id, message=b"commit: " + message, committer=committer, timestamp=commit_timestamp, timezone=commit_timezone) if not ok: # Fail if the atomic compare-and-swap failed, leaving the # commit and all its objects as garbage. raise CommitError("%s changed during commit" % (ref,)) self._del_named_file('MERGE_HEADS') try: self.hooks['post-commit'].execute() except HookError as e: # silent failure warnings.warn("post-commit hook failed: %s" % e, UserWarning) except KeyError: # no hook defined, silent fallthrough pass return c.id def read_gitfile(f): """Read a ``.git`` file. The first line of the file should start with "gitdir: " Args: f: File-like object to read from Returns: A path """ cs = f.read() if not cs.startswith("gitdir: "): raise ValueError("Expected file to start with 'gitdir: '") return cs[len("gitdir: "):].rstrip("\n") +class UnsupportedVersion(Exception): + """Unsupported repository version.""" + + def __init__(self, version): + self.version = version + + class Repo(BaseRepo): """A git repository backed by local disk. To open an existing repository, call the contructor with the path of the repository. To create a new repository, use the Repo.init class method. """ def __init__(self, root): hidden_path = os.path.join(root, CONTROLDIR) if os.path.isdir(os.path.join(hidden_path, OBJECTDIR)): self.bare = False self._controldir = hidden_path elif (os.path.isdir(os.path.join(root, OBJECTDIR)) and os.path.isdir(os.path.join(root, REFSDIR))): self.bare = True self._controldir = root elif os.path.isfile(hidden_path): self.bare = False with open(hidden_path, 'r') as f: path = read_gitfile(f) self.bare = False self._controldir = os.path.join(root, path) else: raise NotGitRepository( "No git repository was found at %(path)s" % dict(path=root) ) commondir = self.get_named_file(COMMONDIR) if commondir is not None: with commondir: self._commondir = os.path.join( self.controldir(), os.fsdecode(commondir.read().rstrip(b"\r\n"))) else: self._commondir = self._controldir self.path = root config = self.get_config() + try: + format_version = int(config.get("core", "repositoryformatversion")) + except KeyError: + format_version = 0 + if format_version != 0: + raise UnsupportedVersion(format_version) object_store = DiskObjectStore.from_config( os.path.join(self.commondir(), OBJECTDIR), config) refs = DiskRefsContainer(self.commondir(), self._controldir, logger=self._write_reflog) BaseRepo.__init__(self, object_store, refs) self._graftpoints = {} graft_file = self.get_named_file(os.path.join("info", "grafts"), basedir=self.commondir()) if graft_file: with graft_file: self._graftpoints.update(parse_graftpoints(graft_file)) graft_file = self.get_named_file("shallow", basedir=self.commondir()) if graft_file: with graft_file: self._graftpoints.update(parse_graftpoints(graft_file)) self.hooks['pre-commit'] = PreCommitShellHook(self.controldir()) self.hooks['commit-msg'] = CommitMsgShellHook(self.controldir()) self.hooks['post-commit'] = PostCommitShellHook(self.controldir()) self.hooks['post-receive'] = PostReceiveShellHook(self.controldir()) def _write_reflog(self, ref, old_sha, new_sha, committer, timestamp, timezone, message): from .reflog import format_reflog_line path = os.path.join(self.controldir(), 'logs', os.fsdecode(ref)) try: os.makedirs(os.path.dirname(path)) except FileExistsError: pass if committer is None: config = self.get_config_stack() committer = self._get_user_identity(config) check_user_identity(committer) if timestamp is None: timestamp = int(time.time()) if timezone is None: timezone = 0 # FIXME with open(path, 'ab') as f: f.write(format_reflog_line(old_sha, new_sha, committer, timestamp, timezone, message) + b'\n') @classmethod def discover(cls, start='.'): """Iterate parent directories to discover a repository Return a Repo object for the first parent directory that looks like a Git repository. Args: start: The directory to start discovery from (defaults to '.') """ remaining = True path = os.path.abspath(start) while remaining: try: return cls(path) except NotGitRepository: path, remaining = os.path.split(path) raise NotGitRepository( "No git repository was found at %(path)s" % dict(path=start) ) def controldir(self): """Return the path of the control directory.""" return self._controldir def commondir(self): """Return the path of the common directory. For a main working tree, it is identical to controldir(). For a linked working tree, it is the control directory of the main working tree.""" return self._commondir def _determine_file_mode(self): """Probe the file-system to determine whether permissions can be trusted. Returns: True if permissions can be trusted, False otherwise. """ fname = os.path.join(self.path, '.probe-permissions') with open(fname, 'w') as f: f.write('') st1 = os.lstat(fname) try: os.chmod(fname, st1.st_mode ^ stat.S_IXUSR) except PermissionError: return False st2 = os.lstat(fname) os.unlink(fname) mode_differs = st1.st_mode != st2.st_mode st2_has_exec = (st2.st_mode & stat.S_IXUSR) != 0 return mode_differs and st2_has_exec def _put_named_file(self, path, contents): """Write a file to the control dir with the given name and contents. Args: path: The path to the file, relative to the control dir. contents: A string to write to the file. """ path = path.lstrip(os.path.sep) with GitFile(os.path.join(self.controldir(), path), 'wb') as f: f.write(contents) def _del_named_file(self, path): try: os.unlink(os.path.join(self.controldir(), path)) except FileNotFoundError: return def get_named_file(self, path, basedir=None): """Get a file from the control dir with a specific name. Although the filename should be interpreted as a filename relative to the control dir in a disk-based Repo, the object returned need not be pointing to a file in that location. Args: path: The path to the file, relative to the control dir. basedir: Optional argument that specifies an alternative to the control dir. Returns: An open file object, or None if the file does not exist. """ # TODO(dborowitz): sanitize filenames, since this is used directly by # the dumb web serving code. if basedir is None: basedir = self.controldir() path = path.lstrip(os.path.sep) try: return open(os.path.join(basedir, path), 'rb') except FileNotFoundError: return None def index_path(self): """Return path to the index file.""" return os.path.join(self.controldir(), INDEX_FILENAME) def open_index(self) -> 'Index': """Open the index for this repository. Raises: NoIndexPresent: If no index is present Returns: The matching `Index` """ from dulwich.index import Index if not self.has_index(): raise NoIndexPresent() return Index(self.index_path()) def has_index(self): """Check if an index is present.""" # Bare repos must never have index files; non-bare repos may have a # missing index file, which is treated as empty. return not self.bare def stage(self, fs_paths): """Stage a set of paths. Args: fs_paths: List of paths, relative to the repository path """ root_path_bytes = os.fsencode(self.path) if not isinstance(fs_paths, list): fs_paths = [fs_paths] from dulwich.index import ( blob_from_path_and_stat, index_entry_from_stat, _fs_to_tree_path, ) index = self.open_index() blob_normalizer = self.get_blob_normalizer() for fs_path in fs_paths: if not isinstance(fs_path, bytes): fs_path = os.fsencode(fs_path) if os.path.isabs(fs_path): raise ValueError( "path %r should be relative to " "repository root, not absolute" % fs_path) tree_path = _fs_to_tree_path(fs_path) full_path = os.path.join(root_path_bytes, fs_path) try: st = os.lstat(full_path) except OSError: # File no longer exists try: del index[tree_path] except KeyError: pass # already removed else: if (not stat.S_ISREG(st.st_mode) and not stat.S_ISLNK(st.st_mode)): try: del index[tree_path] except KeyError: pass else: blob = blob_from_path_and_stat(full_path, st) blob = blob_normalizer.checkin_normalize(blob, fs_path) self.object_store.add_object(blob) index[tree_path] = index_entry_from_stat(st, blob.id, 0) index.write() def clone(self, target_path, mkdir=True, bare=False, origin=b"origin", checkout=None): """Clone this repository. Args: target_path: Target path mkdir: Create the target directory bare: Whether to create a bare repository origin: Base name for refs in target repository cloned from this repository Returns: Created repository as `Repo` """ if not bare: target = self.init(target_path, mkdir=mkdir) else: if checkout: raise ValueError("checkout and bare are incompatible") target = self.init_bare(target_path, mkdir=mkdir) self.fetch(target) encoded_path = self.path if not isinstance(encoded_path, bytes): encoded_path = os.fsencode(encoded_path) ref_message = b"clone: from " + encoded_path target.refs.import_refs( b'refs/remotes/' + origin, self.refs.as_dict(b'refs/heads'), message=ref_message) target.refs.import_refs( b'refs/tags', self.refs.as_dict(b'refs/tags'), message=ref_message) try: target.refs.add_if_new( DEFAULT_REF, self.refs[DEFAULT_REF], message=ref_message) except KeyError: pass target_config = target.get_config() target_config.set(('remote', 'origin'), 'url', encoded_path) target_config.set(('remote', 'origin'), 'fetch', '+refs/heads/*:refs/remotes/origin/*') target_config.write_to_path() # Update target head head_chain, head_sha = self.refs.follow(b'HEAD') if head_chain and head_sha is not None: target.refs.set_symbolic_ref(b'HEAD', head_chain[-1], message=ref_message) target[b'HEAD'] = head_sha if checkout is None: checkout = (not bare) if checkout: # Checkout HEAD to target dir target.reset_index() return target def reset_index(self, tree=None): """Reset the index back to a specific tree. Args: tree: Tree SHA to reset to, None for current HEAD tree. """ from dulwich.index import ( build_index_from_tree, validate_path_element_default, validate_path_element_ntfs, ) if tree is None: tree = self[b'HEAD'].tree config = self.get_config() honor_filemode = config.get_boolean( b'core', b'filemode', os.name != "nt") if config.get_boolean(b'core', b'core.protectNTFS', os.name == "nt"): validate_path_element = validate_path_element_ntfs else: validate_path_element = validate_path_element_default return build_index_from_tree( self.path, self.index_path(), self.object_store, tree, honor_filemode=honor_filemode, validate_path_element=validate_path_element) def get_config(self) -> 'ConfigFile': """Retrieve the config object. Returns: `ConfigFile` object for the ``.git/config`` file. """ from dulwich.config import ConfigFile path = os.path.join(self._controldir, 'config') try: return ConfigFile.from_path(path) except FileNotFoundError: ret = ConfigFile() ret.path = path return ret def get_description(self): """Retrieve the description of this repository. Returns: A string describing the repository or None. """ path = os.path.join(self._controldir, 'description') try: with GitFile(path, 'rb') as f: return f.read() except FileNotFoundError: return None def __repr__(self): return "" % self.path def set_description(self, description): """Set the description for this repository. Args: description: Text to set as description for this repository. """ self._put_named_file('description', description) @classmethod def _init_maybe_bare(cls, path, bare): for d in BASE_DIRECTORIES: os.mkdir(os.path.join(path, *d)) DiskObjectStore.init(os.path.join(path, OBJECTDIR)) ret = cls(path) ret.refs.set_symbolic_ref(b'HEAD', DEFAULT_REF) ret._init_files(bare) return ret @classmethod def init(cls, path, mkdir=False): """Create a new repository. Args: path: Path in which to create the repository mkdir: Whether to create the directory Returns: `Repo` instance """ if mkdir: os.mkdir(path) controldir = os.path.join(path, CONTROLDIR) os.mkdir(controldir) _set_filesystem_hidden(controldir) cls._init_maybe_bare(controldir, False) return cls(path) @classmethod def _init_new_working_directory(cls, path, main_repo, identifier=None, mkdir=False): """Create a new working directory linked to a repository. Args: path: Path in which to create the working tree. main_repo: Main repository to reference identifier: Worktree identifier mkdir: Whether to create the directory Returns: `Repo` instance """ if mkdir: os.mkdir(path) if identifier is None: identifier = os.path.basename(path) main_worktreesdir = os.path.join(main_repo.controldir(), WORKTREES) worktree_controldir = os.path.join(main_worktreesdir, identifier) gitdirfile = os.path.join(path, CONTROLDIR) with open(gitdirfile, 'wb') as f: f.write(b'gitdir: ' + os.fsencode(worktree_controldir) + b'\n') try: os.mkdir(main_worktreesdir) except FileExistsError: pass try: os.mkdir(worktree_controldir) except FileExistsError: pass with open(os.path.join(worktree_controldir, GITDIR), 'wb') as f: f.write(os.fsencode(gitdirfile) + b'\n') with open(os.path.join(worktree_controldir, COMMONDIR), 'wb') as f: f.write(b'../..\n') with open(os.path.join(worktree_controldir, 'HEAD'), 'wb') as f: f.write(main_repo.head() + b'\n') r = cls(path) r.reset_index() return r @classmethod def init_bare(cls, path, mkdir=False): """Create a new bare repository. ``path`` should already exist and be an empty directory. Args: path: Path to create bare repository in Returns: a `Repo` instance """ if mkdir: os.mkdir(path) return cls._init_maybe_bare(path, True) create = init_bare def close(self): """Close any files opened by this repository.""" self.object_store.close() def __enter__(self): return self def __exit__(self, exc_type, exc_val, exc_tb): self.close() def get_blob_normalizer(self): """ Return a BlobNormalizer object """ # TODO Parse the git attributes files git_attributes = {} return BlobNormalizer( self.get_config_stack(), git_attributes ) class MemoryRepo(BaseRepo): """Repo that stores refs, objects, and named files in memory. MemoryRepos are always bare: they have no working tree and no index, since those have a stronger dependency on the filesystem. """ def __init__(self): from dulwich.config import ConfigFile self._reflog = [] refs_container = DictRefsContainer({}, logger=self._append_reflog) BaseRepo.__init__(self, MemoryObjectStore(), refs_container) self._named_files = {} self.bare = True self._config = ConfigFile() self._description = None def _append_reflog(self, *args): self._reflog.append(args) def set_description(self, description): self._description = description def get_description(self): return self._description def _determine_file_mode(self): """Probe the file-system to determine whether permissions can be trusted. Returns: True if permissions can be trusted, False otherwise. """ return sys.platform != 'win32' def _put_named_file(self, path, contents): """Write a file to the control dir with the given name and contents. Args: path: The path to the file, relative to the control dir. contents: A string to write to the file. """ self._named_files[path] = contents def _del_named_file(self, path): try: del self._named_files[path] except KeyError: pass def get_named_file(self, path, basedir=None): """Get a file from the control dir with a specific name. Although the filename should be interpreted as a filename relative to the control dir in a disk-baked Repo, the object returned need not be pointing to a file in that location. Args: path: The path to the file, relative to the control dir. Returns: An open file object, or None if the file does not exist. """ contents = self._named_files.get(path, None) if contents is None: return None return BytesIO(contents) def open_index(self): """Fail to open index for this repo, since it is bare. Raises: NoIndexPresent: Raised when no index is present """ raise NoIndexPresent() def get_config(self): """Retrieve the config object. Returns: `ConfigFile` object. """ return self._config @classmethod def init_bare(cls, objects, refs): """Create a new bare repository in memory. Args: objects: Objects for the new repository, as iterable refs: Refs as dictionary, mapping names to object SHA1s """ ret = cls() for obj in objects: ret.object_store.add_object(obj) for refname, sha in refs.items(): ret.refs.add_if_new(refname, sha) ret._init_files(bare=True) return ret diff --git a/dulwich/server.py b/dulwich/server.py index 10e2bf36..02714d56 100644 --- a/dulwich/server.py +++ b/dulwich/server.py @@ -1,1226 +1,1226 @@ # server.py -- Implementation of the server side git protocols # Copyright (C) 2008 John Carr # Coprygith (C) 2011-2012 Jelmer Vernooij # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # """Git smart network protocol server implementation. For more detailed implementation on the network protocol, see the Documentation/technical directory in the cgit distribution, and in particular: * Documentation/technical/protocol-capabilities.txt * Documentation/technical/pack-protocol.txt Currently supported capabilities: * include-tag * thin-pack * multi_ack_detailed * multi_ack * side-band-64k * ofs-delta * no-progress * report-status * delete-refs * shallow * symref """ import collections import os import socket import sys import time from typing import List, Tuple, Dict, Optional, Iterable import zlib import socketserver from dulwich.archive import tar_stream from dulwich.errors import ( ApplyDeltaError, ChecksumMismatch, GitProtocolError, HookError, NotGitRepository, UnexpectedCommandError, ObjectFormatException, ) from dulwich import log_utils from dulwich.objects import ( Commit, valid_hexsha, ) from dulwich.pack import ( write_pack_objects, ) from dulwich.protocol import ( # noqa: F401 BufferedPktLineWriter, capability_agent, CAPABILITIES_REF, CAPABILITY_AGENT, CAPABILITY_DELETE_REFS, CAPABILITY_INCLUDE_TAG, CAPABILITY_MULTI_ACK_DETAILED, CAPABILITY_MULTI_ACK, CAPABILITY_NO_DONE, CAPABILITY_NO_PROGRESS, CAPABILITY_OFS_DELTA, CAPABILITY_QUIET, CAPABILITY_REPORT_STATUS, CAPABILITY_SHALLOW, CAPABILITY_SIDE_BAND_64K, CAPABILITY_THIN_PACK, COMMAND_DEEPEN, COMMAND_DONE, COMMAND_HAVE, COMMAND_SHALLOW, COMMAND_UNSHALLOW, COMMAND_WANT, MULTI_ACK, MULTI_ACK_DETAILED, Protocol, ProtocolFile, ReceivableProtocol, SIDE_BAND_CHANNEL_DATA, SIDE_BAND_CHANNEL_PROGRESS, SIDE_BAND_CHANNEL_FATAL, SINGLE_ACK, TCP_GIT_PORT, ZERO_SHA, ack_type, extract_capabilities, extract_want_line_capabilities, symref_capabilities, ) from dulwich.refs import ( ANNOTATED_TAG_SUFFIX, write_info_refs, ) from dulwich.repo import ( BaseRepo, Repo, ) logger = log_utils.getLogger(__name__) class Backend(object): """A backend for the Git smart server implementation.""" def open_repository(self, path): """Open the repository at a path. Args: path: Path to the repository Raises: NotGitRepository: no git repository was found at path Returns: Instance of BackendRepo """ raise NotImplementedError(self.open_repository) class BackendRepo(object): """Repository abstraction used by the Git server. The methods required here are a subset of those provided by dulwich.repo.Repo. """ object_store = None refs = None def get_refs(self) -> Dict[bytes, bytes]: """ Get all the refs in the repository Returns: dict of name -> sha """ raise NotImplementedError def get_peeled(self, name: bytes) -> Optional[bytes]: """Return the cached peeled value of a ref, if available. Args: name: Name of the ref to peel Returns: The peeled value of the ref. If the ref is known not point to a tag, this will be the SHA the ref refers to. If no cached information about a tag is available, this method may return None, but it should attempt to peel the tag if possible. """ return None def fetch_objects(self, determine_wants, graph_walker, progress, get_tagged=None): """ Yield the objects required for a list of commits. Args: progress: is a callback to send progress messages to the client get_tagged: Function that returns a dict of pointed-to sha -> tag sha for including tags. """ raise NotImplementedError class DictBackend(Backend): """Trivial backend that looks up Git repositories in a dictionary.""" def __init__(self, repos): self.repos = repos def open_repository(self, path: str) -> BaseRepo: logger.debug('Opening repository at %s', path) try: return self.repos[path] except KeyError: raise NotGitRepository( "No git repository was found at %(path)s" % dict(path=path) ) class FileSystemBackend(Backend): """Simple backend looking up Git repositories in the local file system.""" def __init__(self, root=os.sep): super(FileSystemBackend, self).__init__() self.root = (os.path.abspath(root) + os.sep).replace( os.sep * 2, os.sep) def open_repository(self, path): logger.debug('opening repository at %s', path) abspath = os.path.abspath(os.path.join(self.root, path)) + os.sep normcase_abspath = os.path.normcase(abspath) normcase_root = os.path.normcase(self.root) if not normcase_abspath.startswith(normcase_root): raise NotGitRepository( "Path %r not inside root %r" % (path, self.root)) return Repo(abspath) class Handler(object): """Smart protocol command handler base class.""" def __init__(self, backend, proto, stateless_rpc=None): self.backend = backend self.proto = proto self.stateless_rpc = stateless_rpc def handle(self): raise NotImplementedError(self.handle) class PackHandler(Handler): """Protocol handler for packs.""" def __init__(self, backend, proto, stateless_rpc=None): super(PackHandler, self).__init__(backend, proto, stateless_rpc) self._client_capabilities = None # Flags needed for the no-done capability self._done_received = False @classmethod def capability_line(cls, capabilities): logger.info('Sending capabilities: %s', capabilities) return b"".join([b" " + c for c in capabilities]) @classmethod def capabilities(cls) -> Iterable[bytes]: raise NotImplementedError(cls.capabilities) @classmethod def innocuous_capabilities(cls) -> Iterable[bytes]: return [CAPABILITY_INCLUDE_TAG, CAPABILITY_THIN_PACK, CAPABILITY_NO_PROGRESS, CAPABILITY_OFS_DELTA, capability_agent()] @classmethod def required_capabilities(cls) -> Iterable[bytes]: """Return a list of capabilities that we require the client to have.""" return [] def set_client_capabilities(self, caps: Iterable[bytes]) -> None: allowable_caps = set(self.innocuous_capabilities()) allowable_caps.update(self.capabilities()) for cap in caps: if cap.startswith(CAPABILITY_AGENT + b'='): continue if cap not in allowable_caps: raise GitProtocolError('Client asked for capability %r that ' 'was not advertised.' % cap) for cap in self.required_capabilities(): if cap not in caps: raise GitProtocolError('Client does not support required ' 'capability %r.' % cap) self._client_capabilities = set(caps) logger.info('Client capabilities: %s', caps) def has_capability(self, cap: bytes) -> bool: if self._client_capabilities is None: raise GitProtocolError('Server attempted to access capability %r ' 'before asking client' % cap) return cap in self._client_capabilities def notify_done(self) -> None: self._done_received = True class UploadPackHandler(PackHandler): """Protocol handler for uploading a pack to the client.""" def __init__(self, backend, args, proto, stateless_rpc=None, advertise_refs=False): super(UploadPackHandler, self).__init__( backend, proto, stateless_rpc=stateless_rpc) self.repo = backend.open_repository(args[0]) self._graph_walker = None self.advertise_refs = advertise_refs # A state variable for denoting that the have list is still # being processed, and the client is not accepting any other # data (such as side-band, see the progress method here). self._processing_have_lines = False @classmethod def capabilities(cls): return [CAPABILITY_MULTI_ACK_DETAILED, CAPABILITY_MULTI_ACK, CAPABILITY_SIDE_BAND_64K, CAPABILITY_THIN_PACK, CAPABILITY_OFS_DELTA, CAPABILITY_NO_PROGRESS, CAPABILITY_INCLUDE_TAG, CAPABILITY_SHALLOW, CAPABILITY_NO_DONE] @classmethod def required_capabilities(cls): return (CAPABILITY_SIDE_BAND_64K, CAPABILITY_THIN_PACK, CAPABILITY_OFS_DELTA) def progress(self, message): if (self.has_capability(CAPABILITY_NO_PROGRESS) or self._processing_have_lines): return self.proto.write_sideband(SIDE_BAND_CHANNEL_PROGRESS, message) def get_tagged(self, refs=None, repo=None): """Get a dict of peeled values of tags to their original tag shas. Args: refs: dict of refname -> sha of possible tags; defaults to all of the backend's refs. repo: optional Repo instance for getting peeled refs; defaults to the backend's repo, if available Returns: dict of peeled_sha -> tag_sha, where tag_sha is the sha of a tag whose peeled value is peeled_sha. """ if not self.has_capability(CAPABILITY_INCLUDE_TAG): return {} if refs is None: refs = self.repo.get_refs() if repo is None: repo = getattr(self.repo, "repo", None) if repo is None: # Bail if we don't have a Repo available; this is ok since # clients must be able to handle if the server doesn't include # all relevant tags. # TODO: fix behavior when missing return {} # TODO(jelmer): Integrate this with the refs logic in # Repo.fetch_objects tagged = {} for name, sha in refs.items(): peeled_sha = repo.get_peeled(name) if peeled_sha != sha: tagged[peeled_sha] = sha return tagged def handle(self): def write(x): return self.proto.write_sideband(SIDE_BAND_CHANNEL_DATA, x) graph_walker = _ProtocolGraphWalker( self, self.repo.object_store, self.repo.get_peeled, self.repo.refs.get_symrefs) wants = [] def wants_wrapper(refs): wants.extend(graph_walker.determine_wants(refs)) return wants objects_iter = self.repo.fetch_objects( wants_wrapper, graph_walker, self.progress, get_tagged=self.get_tagged) # Note the fact that client is only processing responses related # to the have lines it sent, and any other data (including side- # band) will be be considered a fatal error. self._processing_have_lines = True # Did the process short-circuit (e.g. in a stateless RPC call)? Note # that the client still expects a 0-object pack in most cases. # Also, if it also happens that the object_iter is instantiated # with a graph walker with an implementation that talks over the # wire (which is this instance of this class) this will actually # iterate through everything and write things out to the wire. if len(wants) == 0: return # The provided haves are processed, and it is safe to send side- # band data now. self._processing_have_lines = False if not graph_walker.handle_done( not self.has_capability(CAPABILITY_NO_DONE), self._done_received): return self.progress( ("counting objects: %d, done.\n" % len(objects_iter)).encode( 'ascii')) write_pack_objects(ProtocolFile(None, write), objects_iter) # we are done self.proto.write_pkt_line(None) def _split_proto_line(line, allowed): """Split a line read from the wire. Args: line: The line read from the wire. allowed: An iterable of command names that should be allowed. Command names not listed below as possible return values will be ignored. If None, any commands from the possible return values are allowed. Returns: a tuple having one of the following forms: ('want', obj_id) ('have', obj_id) ('done', None) (None, None) (for a flush-pkt) Raises: UnexpectedCommandError: if the line cannot be parsed into one of the allowed return values. """ if not line: fields = [None] else: fields = line.rstrip(b'\n').split(b' ', 1) command = fields[0] if allowed is not None and command not in allowed: raise UnexpectedCommandError(command) if len(fields) == 1 and command in (COMMAND_DONE, None): return (command, None) elif len(fields) == 2: if command in (COMMAND_WANT, COMMAND_HAVE, COMMAND_SHALLOW, COMMAND_UNSHALLOW): if not valid_hexsha(fields[1]): raise GitProtocolError("Invalid sha") return tuple(fields) elif command == COMMAND_DEEPEN: return command, int(fields[1]) raise GitProtocolError('Received invalid line from client: %r' % line) def _find_shallow(store, heads, depth): """Find shallow commits according to a given depth. Args: store: An ObjectStore for looking up objects. heads: Iterable of head SHAs to start walking from. depth: The depth of ancestors to include. A depth of one includes only the heads themselves. Returns: A tuple of (shallow, not_shallow), sets of SHAs that should be considered shallow and unshallow according to the arguments. Note that these sets may overlap if a commit is reachable along multiple paths. """ parents = {} def get_parents(sha): result = parents.get(sha, None) if not result: result = store[sha].parents parents[sha] = result return result todo = [] # stack of (sha, depth) for head_sha in heads: obj = store.peel_sha(head_sha) if isinstance(obj, Commit): todo.append((obj.id, 1)) not_shallow = set() shallow = set() while todo: sha, cur_depth = todo.pop() if cur_depth < depth: not_shallow.add(sha) new_depth = cur_depth + 1 todo.extend((p, new_depth) for p in get_parents(sha)) else: shallow.add(sha) return shallow, not_shallow def _want_satisfied(store, haves, want, earliest): o = store[want] pending = collections.deque([o]) known = set([want]) while pending: commit = pending.popleft() if commit.id in haves: return True if commit.type_name != b"commit": # non-commit wants are assumed to be satisfied continue for parent in commit.parents: if parent in known: continue known.add(parent) parent_obj = store[parent] # TODO: handle parents with later commit times than children if parent_obj.commit_time >= earliest: pending.append(parent_obj) return False def _all_wants_satisfied(store, haves, wants): """Check whether all the current wants are satisfied by a set of haves. Args: store: Object store to retrieve objects from haves: A set of commits we know the client has. wants: A set of commits the client wants Note: Wants are specified with set_wants rather than passed in since in the current interface they are determined outside this class. """ haves = set(haves) if haves: earliest = min([store[h].commit_time for h in haves]) else: earliest = 0 for want in wants: if not _want_satisfied(store, haves, want, earliest): return False return True class _ProtocolGraphWalker(object): """A graph walker that knows the git protocol. As a graph walker, this class implements ack(), next(), and reset(). It also contains some base methods for interacting with the wire and walking the commit tree. The work of determining which acks to send is passed on to the implementation instance stored in _impl. The reason for this is that we do not know at object creation time what ack level the protocol requires. A call to set_ack_type() is required to set up the implementation, before any calls to next() or ack() are made. """ def __init__(self, handler, object_store, get_peeled, get_symrefs): self.handler = handler self.store = object_store self.get_peeled = get_peeled self.get_symrefs = get_symrefs self.proto = handler.proto self.stateless_rpc = handler.stateless_rpc self.advertise_refs = handler.advertise_refs self._wants = [] self.shallow = set() self.client_shallow = set() self.unshallow = set() self._cached = False self._cache = [] self._cache_index = 0 self._impl = None def determine_wants(self, heads): """Determine the wants for a set of heads. The given heads are advertised to the client, who then specifies which refs they want using 'want' lines. This portion of the protocol is the same regardless of ack type, and in fact is used to set the ack type of the ProtocolGraphWalker. If the client has the 'shallow' capability, this method also reads and responds to the 'shallow' and 'deepen' lines from the client. These are not part of the wants per se, but they set up necessary state for walking the graph. Additionally, later code depends on this method consuming everything up to the first 'have' line. Args: heads: a dict of refname->SHA1 to advertise Returns: a list of SHA1s requested by the client """ symrefs = self.get_symrefs() values = set(heads.values()) if self.advertise_refs or not self.stateless_rpc: for i, (ref, sha) in enumerate(sorted(heads.items())): try: peeled_sha = self.get_peeled(ref) except KeyError: # Skip refs that are inaccessible # TODO(jelmer): Integrate with Repo.fetch_objects refs # logic. continue line = sha + b' ' + ref if not i: line += (b'\x00' + self.handler.capability_line( self.handler.capabilities() + symref_capabilities(symrefs.items()))) self.proto.write_pkt_line(line + b'\n') if peeled_sha != sha: self.proto.write_pkt_line( peeled_sha + b' ' + ref + ANNOTATED_TAG_SUFFIX + b'\n') # i'm done.. self.proto.write_pkt_line(None) if self.advertise_refs: return [] # Now client will sending want want want commands want = self.proto.read_pkt_line() if not want: return [] line, caps = extract_want_line_capabilities(want) self.handler.set_client_capabilities(caps) self.set_ack_type(ack_type(caps)) allowed = (COMMAND_WANT, COMMAND_SHALLOW, COMMAND_DEEPEN, None) command, sha = _split_proto_line(line, allowed) want_revs = [] while command == COMMAND_WANT: if sha not in values: raise GitProtocolError( 'Client wants invalid object %s' % sha) want_revs.append(sha) command, sha = self.read_proto_line(allowed) self.set_wants(want_revs) if command in (COMMAND_SHALLOW, COMMAND_DEEPEN): self.unread_proto_line(command, sha) self._handle_shallow_request(want_revs) if self.stateless_rpc and self.proto.eof(): # The client may close the socket at this point, expecting a # flush-pkt from the server. We might be ready to send a packfile # at this point, so we need to explicitly short-circuit in this # case. return [] return want_revs def unread_proto_line(self, command, value): if isinstance(value, int): value = str(value).encode('ascii') self.proto.unread_pkt_line(command + b' ' + value) def ack(self, have_ref): if len(have_ref) != 40: raise ValueError("invalid sha %r" % have_ref) return self._impl.ack(have_ref) def reset(self): self._cached = True self._cache_index = 0 def next(self): if not self._cached: if not self._impl and self.stateless_rpc: return None return next(self._impl) self._cache_index += 1 if self._cache_index > len(self._cache): return None return self._cache[self._cache_index] __next__ = next def read_proto_line(self, allowed): """Read a line from the wire. Args: allowed: An iterable of command names that should be allowed. Returns: A tuple of (command, value); see _split_proto_line. Raises: UnexpectedCommandError: If an error occurred reading the line. """ return _split_proto_line(self.proto.read_pkt_line(), allowed) def _handle_shallow_request(self, wants): while True: command, val = self.read_proto_line( (COMMAND_DEEPEN, COMMAND_SHALLOW)) if command == COMMAND_DEEPEN: depth = val break self.client_shallow.add(val) self.read_proto_line((None,)) # consume client's flush-pkt shallow, not_shallow = _find_shallow(self.store, wants, depth) # Update self.shallow instead of reassigning it since we passed a # reference to it before this method was called. self.shallow.update(shallow - not_shallow) new_shallow = self.shallow - self.client_shallow unshallow = self.unshallow = not_shallow & self.client_shallow for sha in sorted(new_shallow): self.proto.write_pkt_line(COMMAND_SHALLOW + b' ' + sha) for sha in sorted(unshallow): self.proto.write_pkt_line(COMMAND_UNSHALLOW + b' ' + sha) self.proto.write_pkt_line(None) def notify_done(self): # relay the message down to the handler. self.handler.notify_done() def send_ack(self, sha, ack_type=b''): if ack_type: ack_type = b' ' + ack_type self.proto.write_pkt_line(b'ACK ' + sha + ack_type + b'\n') def send_nak(self): self.proto.write_pkt_line(b'NAK\n') def handle_done(self, done_required, done_received): # Delegate this to the implementation. return self._impl.handle_done(done_required, done_received) def set_wants(self, wants): self._wants = wants def all_wants_satisfied(self, haves): """Check whether all the current wants are satisfied by a set of haves. Args: haves: A set of commits we know the client has. Note: Wants are specified with set_wants rather than passed in since in the current interface they are determined outside this class. """ return _all_wants_satisfied(self.store, haves, self._wants) def set_ack_type(self, ack_type): impl_classes = { MULTI_ACK: MultiAckGraphWalkerImpl, MULTI_ACK_DETAILED: MultiAckDetailedGraphWalkerImpl, SINGLE_ACK: SingleAckGraphWalkerImpl, } self._impl = impl_classes[ack_type](self) _GRAPH_WALKER_COMMANDS = (COMMAND_HAVE, COMMAND_DONE, None) class SingleAckGraphWalkerImpl(object): """Graph walker implementation that speaks the single-ack protocol.""" def __init__(self, walker): self.walker = walker self._common = [] def ack(self, have_ref): if not self._common: self.walker.send_ack(have_ref) self._common.append(have_ref) def next(self): command, sha = self.walker.read_proto_line(_GRAPH_WALKER_COMMANDS) if command in (None, COMMAND_DONE): # defer the handling of done self.walker.notify_done() return None elif command == COMMAND_HAVE: return sha __next__ = next def handle_done(self, done_required, done_received): if not self._common: self.walker.send_nak() if done_required and not done_received: # we are not done, especially when done is required; skip # the pack for this request and especially do not handle # the done. return False if not done_received and not self._common: # Okay we are not actually done then since the walker picked # up no haves. This is usually triggered when client attempts # to pull from a source that has no common base_commit. # See: test_server.MultiAckDetailedGraphWalkerImplTestCase.\ # test_multi_ack_stateless_nodone return False return True class MultiAckGraphWalkerImpl(object): """Graph walker implementation that speaks the multi-ack protocol.""" def __init__(self, walker): self.walker = walker self._found_base = False self._common = [] def ack(self, have_ref): self._common.append(have_ref) if not self._found_base: self.walker.send_ack(have_ref, b'continue') if self.walker.all_wants_satisfied(self._common): self._found_base = True # else we blind ack within next def next(self): while True: command, sha = self.walker.read_proto_line(_GRAPH_WALKER_COMMANDS) if command is None: self.walker.send_nak() # in multi-ack mode, a flush-pkt indicates the client wants to # flush but more have lines are still coming continue elif command == COMMAND_DONE: self.walker.notify_done() return None elif command == COMMAND_HAVE: if self._found_base: # blind ack self.walker.send_ack(sha, b'continue') return sha __next__ = next def handle_done(self, done_required, done_received): if done_required and not done_received: # we are not done, especially when done is required; skip # the pack for this request and especially do not handle # the done. return False if not done_received and not self._common: # Okay we are not actually done then since the walker picked # up no haves. This is usually triggered when client attempts # to pull from a source that has no common base_commit. # See: test_server.MultiAckDetailedGraphWalkerImplTestCase.\ # test_multi_ack_stateless_nodone return False # don't nak unless no common commits were found, even if not # everything is satisfied if self._common: self.walker.send_ack(self._common[-1]) else: self.walker.send_nak() return True class MultiAckDetailedGraphWalkerImpl(object): """Graph walker implementation speaking the multi-ack-detailed protocol.""" def __init__(self, walker): self.walker = walker self._common = [] def ack(self, have_ref): # Should only be called iff have_ref is common self._common.append(have_ref) self.walker.send_ack(have_ref, b'common') def next(self): while True: command, sha = self.walker.read_proto_line(_GRAPH_WALKER_COMMANDS) if command is None: if self.walker.all_wants_satisfied(self._common): self.walker.send_ack(self._common[-1], b'ready') self.walker.send_nak() if self.walker.stateless_rpc: # The HTTP version of this request a flush-pkt always # signifies an end of request, so we also return # nothing here as if we are done (but not really, as # it depends on whether no-done capability was # specified and that's handled in handle_done which # may or may not call post_nodone_check depending on # that). return None elif command == COMMAND_DONE: # Let the walker know that we got a done. self.walker.notify_done() break elif command == COMMAND_HAVE: # return the sha and let the caller ACK it with the # above ack method. return sha # don't nak unless no common commits were found, even if not # everything is satisfied __next__ = next def handle_done(self, done_required, done_received): if done_required and not done_received: # we are not done, especially when done is required; skip # the pack for this request and especially do not handle # the done. return False if not done_received and not self._common: # Okay we are not actually done then since the walker picked # up no haves. This is usually triggered when client attempts # to pull from a source that has no common base_commit. # See: test_server.MultiAckDetailedGraphWalkerImplTestCase.\ # test_multi_ack_stateless_nodone return False # don't nak unless no common commits were found, even if not # everything is satisfied if self._common: self.walker.send_ack(self._common[-1]) else: self.walker.send_nak() return True class ReceivePackHandler(PackHandler): """Protocol handler for downloading a pack from the client.""" def __init__(self, backend, args, proto, stateless_rpc=None, advertise_refs=False): super(ReceivePackHandler, self).__init__( backend, proto, stateless_rpc=stateless_rpc) self.repo = backend.open_repository(args[0]) self.advertise_refs = advertise_refs @classmethod def capabilities(cls) -> Iterable[bytes]: return [CAPABILITY_REPORT_STATUS, CAPABILITY_DELETE_REFS, CAPABILITY_QUIET, CAPABILITY_OFS_DELTA, CAPABILITY_SIDE_BAND_64K, CAPABILITY_NO_DONE] def _apply_pack( self, refs: List[Tuple[bytes, bytes, bytes]] ) -> List[Tuple[bytes, bytes]]: all_exceptions = (IOError, OSError, ChecksumMismatch, ApplyDeltaError, AssertionError, socket.error, zlib.error, ObjectFormatException) status = [] will_send_pack = False for command in refs: if command[1] != ZERO_SHA: will_send_pack = True if will_send_pack: # TODO: more informative error messages than just the exception # string try: recv = getattr(self.proto, "recv", None) self.repo.object_store.add_thin_pack(self.proto.read, recv) status.append((b'unpack', b'ok')) except all_exceptions as e: status.append( (b'unpack', str(e).replace('\n', '').encode('utf-8'))) # The pack may still have been moved in, but it may contain # broken objects. We trust a later GC to clean it up. else: # The git protocol want to find a status entry related to unpack # process even if no pack data has been sent. status.append((b'unpack', b'ok')) for oldsha, sha, ref in refs: ref_status = b'ok' try: if sha == ZERO_SHA: if CAPABILITY_DELETE_REFS not in self.capabilities(): raise GitProtocolError( 'Attempted to delete refs without delete-refs ' 'capability.') try: self.repo.refs.remove_if_equals(ref, oldsha) except all_exceptions: ref_status = b'failed to delete' else: try: self.repo.refs.set_if_equals(ref, oldsha, sha) except all_exceptions: ref_status = b'failed to write' except KeyError: ref_status = b'bad ref' status.append((ref, ref_status)) return status def _report_status(self, status: List[Tuple[bytes, bytes]]) -> None: if self.has_capability(CAPABILITY_SIDE_BAND_64K): writer = BufferedPktLineWriter( lambda d: self.proto.write_sideband(SIDE_BAND_CHANNEL_DATA, d)) write = writer.write def flush(): writer.flush() self.proto.write_pkt_line(None) else: write = self.proto.write_pkt_line def flush(): pass for name, msg in status: if name == b'unpack': write(b'unpack ' + msg + b'\n') elif msg == b'ok': write(b'ok ' + name + b'\n') else: write(b'ng ' + name + b' ' + msg + b'\n') write(None) flush() def _on_post_receive(self, client_refs): hook = self.repo.hooks.get('post-receive', None) if not hook: return try: output = hook.execute(client_refs) if output: self.proto.write_sideband(SIDE_BAND_CHANNEL_PROGRESS, output) except HookError as err: self.proto.write_sideband(SIDE_BAND_CHANNEL_FATAL, repr(err)) def handle(self) -> None: if self.advertise_refs or not self.stateless_rpc: refs = sorted(self.repo.get_refs().items()) symrefs = sorted(self.repo.refs.get_symrefs().items()) if not refs: refs = [(CAPABILITIES_REF, ZERO_SHA)] self.proto.write_pkt_line( refs[0][1] + b' ' + refs[0][0] + b'\0' + self.capability_line( self.capabilities() + symref_capabilities(symrefs)) + b'\n') for i in range(1, len(refs)): ref = refs[i] self.proto.write_pkt_line(ref[1] + b' ' + ref[0] + b'\n') self.proto.write_pkt_line(None) if self.advertise_refs: return client_refs = [] ref = self.proto.read_pkt_line() # if ref is none then client doesnt want to send us anything.. if ref is None: return ref, caps = extract_capabilities(ref) self.set_client_capabilities(caps) # client will now send us a list of (oldsha, newsha, ref) while ref: client_refs.append(ref.split()) ref = self.proto.read_pkt_line() # backend can now deal with this refs and read a pack using self.read status = self._apply_pack(client_refs) self._on_post_receive(client_refs) # when we have read all the pack from the client, send a status report # if the client asked for it if self.has_capability(CAPABILITY_REPORT_STATUS): self._report_status(status) class UploadArchiveHandler(Handler): def __init__(self, backend, args, proto, stateless_rpc=None): super(UploadArchiveHandler, self).__init__( backend, proto, stateless_rpc) self.repo = backend.open_repository(args[0]) def handle(self): def write(x): return self.proto.write_sideband(SIDE_BAND_CHANNEL_DATA, x) arguments = [] for pkt in self.proto.read_pkt_seq(): (key, value) = pkt.split(b' ', 1) if key != b'argument': raise GitProtocolError('unknown command %s' % key) arguments.append(value.rstrip(b'\n')) prefix = b'' format = 'tar' i = 0 store = self.repo.object_store while i < len(arguments): argument = arguments[i] if argument == b'--prefix': i += 1 prefix = arguments[i] elif argument == b'--format': i += 1 format = arguments[i].decode('ascii') else: commit_sha = self.repo.refs[argument] tree = store[store[commit_sha].tree] i += 1 - self.proto.write_pkt_line(b'ACK\n') + self.proto.write_pkt_line(b'ACK') self.proto.write_pkt_line(None) for chunk in tar_stream( store, tree, mtime=time.time(), prefix=prefix, format=format): write(chunk) self.proto.write_pkt_line(None) # Default handler classes for git services. DEFAULT_HANDLERS = { b'git-upload-pack': UploadPackHandler, b'git-receive-pack': ReceivePackHandler, b'git-upload-archive': UploadArchiveHandler, } class TCPGitRequestHandler(socketserver.StreamRequestHandler): def __init__(self, handlers, *args, **kwargs): self.handlers = handlers socketserver.StreamRequestHandler.__init__(self, *args, **kwargs) def handle(self): proto = ReceivableProtocol(self.connection.recv, self.wfile.write) command, args = proto.read_cmd() logger.info('Handling %s request, args=%s', command, args) cls = self.handlers.get(command, None) if not callable(cls): raise GitProtocolError('Invalid service %s' % command) h = cls(self.server.backend, args, proto) h.handle() class TCPGitServer(socketserver.TCPServer): allow_reuse_address = True serve = socketserver.TCPServer.serve_forever def _make_handler(self, *args, **kwargs): return TCPGitRequestHandler(self.handlers, *args, **kwargs) def __init__(self, backend, listen_addr, port=TCP_GIT_PORT, handlers=None): self.handlers = dict(DEFAULT_HANDLERS) if handlers is not None: self.handlers.update(handlers) self.backend = backend logger.info('Listening for TCP connections on %s:%d', listen_addr, port) socketserver.TCPServer.__init__(self, (listen_addr, port), self._make_handler) def verify_request(self, request, client_address): logger.info('Handling request from %s', client_address) return True def handle_error(self, request, client_address): logger.exception('Exception happened during processing of request ' 'from %s', client_address) def main(argv=sys.argv): """Entry point for starting a TCP git server.""" import optparse parser = optparse.OptionParser() parser.add_option("-l", "--listen_address", dest="listen_address", default="localhost", help="Binding IP address.") parser.add_option("-p", "--port", dest="port", type=int, default=TCP_GIT_PORT, help="Binding TCP port.") options, args = parser.parse_args(argv) log_utils.default_logging_config() if len(args) > 1: gitdir = args[1] else: gitdir = '.' # TODO(jelmer): Support git-daemon-export-ok and --export-all. backend = FileSystemBackend(gitdir) server = TCPGitServer(backend, options.listen_address, options.port) server.serve_forever() def serve_command(handler_cls, argv=sys.argv, backend=None, inf=sys.stdin, outf=sys.stdout): """Serve a single command. This is mostly useful for the implementation of commands used by e.g. git+ssh. Args: handler_cls: `Handler` class to use for the request argv: execv-style command-line arguments. Defaults to sys.argv. backend: `Backend` to use inf: File-like object to read from, defaults to standard input. outf: File-like object to write to, defaults to standard output. Returns: Exit code for use with sys.exit. 0 on success, 1 on failure. """ if backend is None: backend = FileSystemBackend() def send_fn(data): outf.write(data) outf.flush() proto = Protocol(inf.read, send_fn) handler = handler_cls(backend, argv[1:], proto) # FIXME: Catch exceptions and write a single-line summary to outf. handler.handle() return 0 def generate_info_refs(repo): """Generate an info refs file.""" refs = repo.get_refs() return write_info_refs(refs, repo.object_store) def generate_objects_info_packs(repo): """Generate an index for for packs.""" for pack in repo.object_store.packs: yield ( b'P ' + os.fsencode(pack.data.filename) + b'\n') def update_server_info(repo): """Generate server info for dumb file access. This generates info/refs and objects/info/packs, similar to "git update-server-info". """ repo._put_named_file( os.path.join('info', 'refs'), b"".join(generate_info_refs(repo))) repo._put_named_file( os.path.join('objects', 'info', 'packs'), b"".join(generate_objects_info_packs(repo))) if __name__ == '__main__': main() diff --git a/dulwich/tests/test_client.py b/dulwich/tests/test_client.py index 9816d2b3..b5135857 100644 --- a/dulwich/tests/test_client.py +++ b/dulwich/tests/test_client.py @@ -1,1390 +1,1402 @@ # test_client.py -- Tests for the git protocol, client side # Copyright (C) 2009 Jelmer Vernooij # # Dulwich is dual-licensed under the Apache License, Version 2.0 and the GNU # General Public License as public by the Free Software Foundation; version 2.0 # or (at your option) any later version. You can redistribute it and/or # modify it under the terms of either of these two licenses. # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. # # You should have received a copy of the licenses; if not, see # for a copy of the GNU General Public License # and for a copy of the Apache # License, Version 2.0. # from io import BytesIO import base64 import os import sys import shutil import tempfile import warnings from urllib.parse import ( quote as urlquote, urlparse, ) import dulwich from dulwich import ( client, ) from dulwich.client import ( InvalidWants, LocalGitClient, TraditionalGitClient, TCPGitClient, SSHGitClient, HttpGitClient, FetchPackResult, ReportStatusParser, SendPackError, StrangeHostname, SubprocessSSHVendor, PLinkSSHVendor, HangupException, GitProtocolError, check_wants, default_urllib3_manager, get_credentials_from_store, get_transport_and_path, get_transport_and_path_from_url, parse_rsync_url, _remote_error_from_stderr, ) from dulwich.config import ( ConfigDict, ) from dulwich.tests import ( TestCase, ) from dulwich.protocol import ( TCP_GIT_PORT, Protocol, ) from dulwich.pack import ( pack_objects_to_data, write_pack_data, write_pack_objects, ) from dulwich.objects import ( Commit, Tree ) from dulwich.repo import ( MemoryRepo, Repo, ) from dulwich.tests import skipIf from dulwich.tests.utils import ( open_repo, tear_down_repo, setup_warning_catcher, ) class DummyClient(TraditionalGitClient): def __init__(self, can_read, read, write): self.can_read = can_read self.read = read self.write = write TraditionalGitClient.__init__(self) def _connect(self, service, path): return Protocol(self.read, self.write), self.can_read, None class DummyPopen(): def __init__(self, *args, **kwards): self.stdin = BytesIO(b"stdin") self.stdout = BytesIO(b"stdout") self.stderr = BytesIO(b"stderr") self.returncode = 0 self.args = args self.kwargs = kwards def communicate(self, *args, **kwards): return ('Running', '') def wait(self, *args, **kwards): return False # TODO(durin42): add unit-level tests of GitClient class GitClientTests(TestCase): def setUp(self): super(GitClientTests, self).setUp() self.rout = BytesIO() self.rin = BytesIO() self.client = DummyClient(lambda x: True, self.rin.read, self.rout.write) def test_caps(self): agent_cap = ( 'agent=dulwich/%d.%d.%d' % dulwich.__version__).encode('ascii') self.assertEqual(set([b'multi_ack', b'side-band-64k', b'ofs-delta', b'thin-pack', b'multi_ack_detailed', b'shallow', agent_cap]), set(self.client._fetch_capabilities)) self.assertEqual( set([b'delete-refs', b'ofs-delta', b'report-status', b'side-band-64k', agent_cap]), set(self.client._send_capabilities)) def test_archive_ack(self): self.rin.write( b'0009NACK\n' b'0000') self.rin.seek(0) self.client.archive(b'bla', b'HEAD', None, None) self.assertEqual(self.rout.getvalue(), b'0011argument HEAD0000') def test_fetch_empty(self): self.rin.write(b'0000') self.rin.seek(0) def check_heads(heads): self.assertEqual(heads, {}) return [] ret = self.client.fetch_pack(b'/', check_heads, None, None) self.assertEqual({}, ret.refs) self.assertEqual({}, ret.symrefs) def test_fetch_pack_ignores_magic_ref(self): self.rin.write( b'00000000000000000000000000000000000000000000 capabilities^{}' b'\x00 multi_ack ' b'thin-pack side-band side-band-64k ofs-delta shallow no-progress ' b'include-tag\n' b'0000') self.rin.seek(0) def check_heads(heads): self.assertEqual({}, heads) return [] ret = self.client.fetch_pack(b'bla', check_heads, None, None, None) self.assertEqual({}, ret.refs) self.assertEqual({}, ret.symrefs) self.assertEqual(self.rout.getvalue(), b'0000') def test_fetch_pack_none(self): self.rin.write( b'008855dcc6bf963f922e1ed5c4bbaaefcfacef57b1d7 HEAD\x00multi_ack ' b'thin-pack side-band side-band-64k ofs-delta shallow no-progress ' b'include-tag\n' b'0000') self.rin.seek(0) ret = self.client.fetch_pack( b'bla', lambda heads: [], None, None, None) self.assertEqual( {b'HEAD': b'55dcc6bf963f922e1ed5c4bbaaefcfacef57b1d7'}, ret.refs) self.assertEqual({}, ret.symrefs) self.assertEqual(self.rout.getvalue(), b'0000') def test_send_pack_no_sideband64k_with_update_ref_error(self): # No side-bank-64k reported by server shouldn't try to parse # side band data pkts = [b'55dcc6bf963f922e1ed5c4bbaaefcfacef57b1d7 capabilities^{}' b'\x00 report-status delete-refs ofs-delta\n', b'', b"unpack ok", b"ng refs/foo/bar pre-receive hook declined", b''] for pkt in pkts: if pkt == b'': self.rin.write(b"0000") else: self.rin.write(("%04x" % (len(pkt)+4)).encode('ascii') + pkt) self.rin.seek(0) tree = Tree() commit = Commit() commit.tree = tree commit.parents = [] commit.author = commit.committer = b'test user' commit.commit_time = commit.author_time = 1174773719 commit.commit_timezone = commit.author_timezone = 0 commit.encoding = b'UTF-8' commit.message = b'test message' def update_refs(refs): return {b'refs/foo/bar': commit.id, } def generate_pack_data(have, want, ofs_delta=False): return pack_objects_to_data([(commit, None), (tree, ''), ]) result = self.client.send_pack("blah", update_refs, generate_pack_data) self.assertEqual( {b'refs/foo/bar': 'pre-receive hook declined'}, result.ref_status) self.assertEqual({b'refs/foo/bar': commit.id}, result.refs) def test_send_pack_none(self): # Set ref to current value self.rin.write( b'0078310ca9477129b8586fa2afc779c1f57cf64bba6c ' b'refs/heads/master\x00 report-status delete-refs ' b'side-band-64k quiet ofs-delta\n' b'0000') self.rin.seek(0) def update_refs(refs): return { b'refs/heads/master': b'310ca9477129b8586fa2afc779c1f57cf64bba6c' } def generate_pack_data(have, want, ofs_delta=False): return 0, [] self.client.send_pack(b'/', update_refs, generate_pack_data) self.assertEqual(self.rout.getvalue(), b'0000') def test_send_pack_keep_and_delete(self): self.rin.write( b'0063310ca9477129b8586fa2afc779c1f57cf64bba6c ' b'refs/heads/master\x00report-status delete-refs ofs-delta\n' b'003f310ca9477129b8586fa2afc779c1f57cf64bba6c refs/heads/keepme\n' b'0000000eunpack ok\n' b'0019ok refs/heads/master\n' b'0000') self.rin.seek(0) def update_refs(refs): return {b'refs/heads/master': b'0' * 40} def generate_pack_data(have, want, ofs_delta=False): return 0, [] self.client.send_pack(b'/', update_refs, generate_pack_data) self.assertEqual( self.rout.getvalue(), b'008b310ca9477129b8586fa2afc779c1f57cf64bba6c ' b'0000000000000000000000000000000000000000 ' b'refs/heads/master\x00delete-refs ofs-delta report-status0000') def test_send_pack_delete_only(self): self.rin.write( b'0063310ca9477129b8586fa2afc779c1f57cf64bba6c ' b'refs/heads/master\x00report-status delete-refs ofs-delta\n' b'0000000eunpack ok\n' b'0019ok refs/heads/master\n' b'0000') self.rin.seek(0) def update_refs(refs): return {b'refs/heads/master': b'0' * 40} def generate_pack_data(have, want, ofs_delta=False): return 0, [] self.client.send_pack(b'/', update_refs, generate_pack_data) self.assertEqual( self.rout.getvalue(), b'008b310ca9477129b8586fa2afc779c1f57cf64bba6c ' b'0000000000000000000000000000000000000000 ' b'refs/heads/master\x00delete-refs ofs-delta report-status0000') def test_send_pack_new_ref_only(self): self.rin.write( b'0063310ca9477129b8586fa2afc779c1f57cf64bba6c ' b'refs/heads/master\x00report-status delete-refs ofs-delta\n' b'0000000eunpack ok\n' b'0019ok refs/heads/blah12\n' b'0000') self.rin.seek(0) def update_refs(refs): return { b'refs/heads/blah12': b'310ca9477129b8586fa2afc779c1f57cf64bba6c', b'refs/heads/master': b'310ca9477129b8586fa2afc779c1f57cf64bba6c' } def generate_pack_data(have, want, ofs_delta=False): return 0, [] f = BytesIO() write_pack_objects(f, {}) self.client.send_pack('/', update_refs, generate_pack_data) self.assertEqual( self.rout.getvalue(), b'008b0000000000000000000000000000000000000000 ' b'310ca9477129b8586fa2afc779c1f57cf64bba6c ' b'refs/heads/blah12\x00delete-refs ofs-delta report-status0000' + f.getvalue()) def test_send_pack_new_ref(self): self.rin.write( b'0064310ca9477129b8586fa2afc779c1f57cf64bba6c ' b'refs/heads/master\x00 report-status delete-refs ofs-delta\n' b'0000000eunpack ok\n' b'0019ok refs/heads/blah12\n' b'0000') self.rin.seek(0) tree = Tree() commit = Commit() commit.tree = tree commit.parents = [] commit.author = commit.committer = b'test user' commit.commit_time = commit.author_time = 1174773719 commit.commit_timezone = commit.author_timezone = 0 commit.encoding = b'UTF-8' commit.message = b'test message' def update_refs(refs): return { b'refs/heads/blah12': commit.id, b'refs/heads/master': b'310ca9477129b8586fa2afc779c1f57cf64bba6c' } def generate_pack_data(have, want, ofs_delta=False): return pack_objects_to_data([(commit, None), (tree, b''), ]) f = BytesIO() write_pack_data(f, *generate_pack_data(None, None)) self.client.send_pack(b'/', update_refs, generate_pack_data) self.assertEqual( self.rout.getvalue(), b'008b0000000000000000000000000000000000000000 ' + commit.id + b' refs/heads/blah12\x00delete-refs ofs-delta report-status0000' + f.getvalue()) def test_send_pack_no_deleteref_delete_only(self): pkts = [b'310ca9477129b8586fa2afc779c1f57cf64bba6c refs/heads/master' b'\x00 report-status ofs-delta\n', b'', b''] for pkt in pkts: if pkt == b'': self.rin.write(b"0000") else: self.rin.write(("%04x" % (len(pkt)+4)).encode('ascii') + pkt) self.rin.seek(0) def update_refs(refs): return {b'refs/heads/master': b'0' * 40} def generate_pack_data(have, want, ofs_delta=False): return 0, [] result = self.client.send_pack(b"/", update_refs, generate_pack_data) self.assertEqual( result.ref_status, {b'refs/heads/master': 'remote does not support deleting refs'}) self.assertEqual( result.refs, {b'refs/heads/master': b'310ca9477129b8586fa2afc779c1f57cf64bba6c'}) self.assertEqual(self.rout.getvalue(), b'0000') class TestGetTransportAndPath(TestCase): def test_tcp(self): c, path = get_transport_and_path('git://foo.com/bar/baz') self.assertTrue(isinstance(c, TCPGitClient)) self.assertEqual('foo.com', c._host) self.assertEqual(TCP_GIT_PORT, c._port) self.assertEqual('/bar/baz', path) def test_tcp_port(self): c, path = get_transport_and_path('git://foo.com:1234/bar/baz') self.assertTrue(isinstance(c, TCPGitClient)) self.assertEqual('foo.com', c._host) self.assertEqual(1234, c._port) self.assertEqual('/bar/baz', path) def test_git_ssh_explicit(self): c, path = get_transport_and_path('git+ssh://foo.com/bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo.com', c.host) self.assertEqual(None, c.port) self.assertEqual(None, c.username) self.assertEqual('/bar/baz', path) def test_ssh_explicit(self): c, path = get_transport_and_path('ssh://foo.com/bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo.com', c.host) self.assertEqual(None, c.port) self.assertEqual(None, c.username) self.assertEqual('/bar/baz', path) def test_ssh_port_explicit(self): c, path = get_transport_and_path( 'git+ssh://foo.com:1234/bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo.com', c.host) self.assertEqual(1234, c.port) self.assertEqual('/bar/baz', path) def test_username_and_port_explicit_unknown_scheme(self): c, path = get_transport_and_path( 'unknown://git@server:7999/dply/stuff.git') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('unknown', c.host) self.assertEqual('//git@server:7999/dply/stuff.git', path) def test_username_and_port_explicit(self): c, path = get_transport_and_path( 'ssh://git@server:7999/dply/stuff.git') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('git', c.username) self.assertEqual('server', c.host) self.assertEqual(7999, c.port) self.assertEqual('/dply/stuff.git', path) def test_ssh_abspath_doubleslash(self): c, path = get_transport_and_path('git+ssh://foo.com//bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo.com', c.host) self.assertEqual(None, c.port) self.assertEqual(None, c.username) self.assertEqual('//bar/baz', path) def test_ssh_port(self): c, path = get_transport_and_path( 'git+ssh://foo.com:1234/bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo.com', c.host) self.assertEqual(1234, c.port) self.assertEqual('/bar/baz', path) def test_ssh_implicit(self): c, path = get_transport_and_path('foo:/bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo', c.host) self.assertEqual(None, c.port) self.assertEqual(None, c.username) self.assertEqual('/bar/baz', path) def test_ssh_host(self): c, path = get_transport_and_path('foo.com:/bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo.com', c.host) self.assertEqual(None, c.port) self.assertEqual(None, c.username) self.assertEqual('/bar/baz', path) def test_ssh_user_host(self): c, path = get_transport_and_path('user@foo.com:/bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo.com', c.host) self.assertEqual(None, c.port) self.assertEqual('user', c.username) self.assertEqual('/bar/baz', path) def test_ssh_relpath(self): c, path = get_transport_and_path('foo:bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo', c.host) self.assertEqual(None, c.port) self.assertEqual(None, c.username) self.assertEqual('bar/baz', path) def test_ssh_host_relpath(self): c, path = get_transport_and_path('foo.com:bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo.com', c.host) self.assertEqual(None, c.port) self.assertEqual(None, c.username) self.assertEqual('bar/baz', path) def test_ssh_user_host_relpath(self): c, path = get_transport_and_path('user@foo.com:bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo.com', c.host) self.assertEqual(None, c.port) self.assertEqual('user', c.username) self.assertEqual('bar/baz', path) def test_local(self): c, path = get_transport_and_path('foo.bar/baz') self.assertTrue(isinstance(c, LocalGitClient)) self.assertEqual('foo.bar/baz', path) @skipIf(sys.platform != 'win32', 'Behaviour only happens on windows.') def test_local_abs_windows_path(self): c, path = get_transport_and_path('C:\\foo.bar\\baz') self.assertTrue(isinstance(c, LocalGitClient)) self.assertEqual('C:\\foo.bar\\baz', path) def test_error(self): # Need to use a known urlparse.uses_netloc URL scheme to get the # expected parsing of the URL on Python versions less than 2.6.5 c, path = get_transport_and_path('prospero://bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) def test_http(self): url = 'https://github.com/jelmer/dulwich' c, path = get_transport_and_path(url) self.assertTrue(isinstance(c, HttpGitClient)) self.assertEqual('/jelmer/dulwich', path) def test_http_auth(self): url = 'https://user:passwd@github.com/jelmer/dulwich' c, path = get_transport_and_path(url) self.assertTrue(isinstance(c, HttpGitClient)) self.assertEqual('/jelmer/dulwich', path) self.assertEqual('user', c._username) self.assertEqual('passwd', c._password) def test_http_auth_with_username(self): url = 'https://github.com/jelmer/dulwich' c, path = get_transport_and_path( url, username='user2', password='blah') self.assertTrue(isinstance(c, HttpGitClient)) self.assertEqual('/jelmer/dulwich', path) self.assertEqual('user2', c._username) self.assertEqual('blah', c._password) def test_http_auth_with_username_and_in_url(self): url = 'https://user:passwd@github.com/jelmer/dulwich' c, path = get_transport_and_path( url, username='user2', password='blah') self.assertTrue(isinstance(c, HttpGitClient)) self.assertEqual('/jelmer/dulwich', path) self.assertEqual('user', c._username) self.assertEqual('passwd', c._password) def test_http_no_auth(self): url = 'https://github.com/jelmer/dulwich' c, path = get_transport_and_path(url) self.assertTrue(isinstance(c, HttpGitClient)) self.assertEqual('/jelmer/dulwich', path) self.assertIs(None, c._username) self.assertIs(None, c._password) class TestGetTransportAndPathFromUrl(TestCase): def test_tcp(self): c, path = get_transport_and_path_from_url('git://foo.com/bar/baz') self.assertTrue(isinstance(c, TCPGitClient)) self.assertEqual('foo.com', c._host) self.assertEqual(TCP_GIT_PORT, c._port) self.assertEqual('/bar/baz', path) def test_tcp_port(self): c, path = get_transport_and_path_from_url('git://foo.com:1234/bar/baz') self.assertTrue(isinstance(c, TCPGitClient)) self.assertEqual('foo.com', c._host) self.assertEqual(1234, c._port) self.assertEqual('/bar/baz', path) def test_ssh_explicit(self): c, path = get_transport_and_path_from_url('git+ssh://foo.com/bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo.com', c.host) self.assertEqual(None, c.port) self.assertEqual(None, c.username) self.assertEqual('/bar/baz', path) def test_ssh_port_explicit(self): c, path = get_transport_and_path_from_url( 'git+ssh://foo.com:1234/bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo.com', c.host) self.assertEqual(1234, c.port) self.assertEqual('/bar/baz', path) def test_ssh_homepath(self): c, path = get_transport_and_path_from_url( 'git+ssh://foo.com/~/bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo.com', c.host) self.assertEqual(None, c.port) self.assertEqual(None, c.username) self.assertEqual('/~/bar/baz', path) def test_ssh_port_homepath(self): c, path = get_transport_and_path_from_url( 'git+ssh://foo.com:1234/~/bar/baz') self.assertTrue(isinstance(c, SSHGitClient)) self.assertEqual('foo.com', c.host) self.assertEqual(1234, c.port) self.assertEqual('/~/bar/baz', path) def test_ssh_host_relpath(self): self.assertRaises( ValueError, get_transport_and_path_from_url, 'foo.com:bar/baz') def test_ssh_user_host_relpath(self): self.assertRaises( ValueError, get_transport_and_path_from_url, 'user@foo.com:bar/baz') def test_local_path(self): self.assertRaises( ValueError, get_transport_and_path_from_url, 'foo.bar/baz') def test_error(self): # Need to use a known urlparse.uses_netloc URL scheme to get the # expected parsing of the URL on Python versions less than 2.6.5 self.assertRaises( ValueError, get_transport_and_path_from_url, 'prospero://bar/baz') def test_http(self): url = 'https://github.com/jelmer/dulwich' c, path = get_transport_and_path_from_url(url) self.assertTrue(isinstance(c, HttpGitClient)) self.assertEqual('https://github.com', c.get_url(b'/')) self.assertEqual('/jelmer/dulwich', path) def test_http_port(self): url = 'https://github.com:9090/jelmer/dulwich' c, path = get_transport_and_path_from_url(url) self.assertEqual('https://github.com:9090', c.get_url(b'/')) self.assertTrue(isinstance(c, HttpGitClient)) self.assertEqual('/jelmer/dulwich', path) def test_file(self): c, path = get_transport_and_path_from_url('file:///home/jelmer/foo') self.assertTrue(isinstance(c, LocalGitClient)) self.assertEqual('/home/jelmer/foo', path) class TestSSHVendor(object): def __init__(self): self.host = None self.command = "" self.username = None self.port = None self.password = None self.key_filename = None def run_command(self, host, command, username=None, port=None, password=None, key_filename=None): self.host = host self.command = command self.username = username self.port = port self.password = password self.key_filename = key_filename class Subprocess: pass setattr(Subprocess, 'read', lambda: None) setattr(Subprocess, 'write', lambda: None) setattr(Subprocess, 'close', lambda: None) setattr(Subprocess, 'can_read', lambda: None) return Subprocess() class SSHGitClientTests(TestCase): def setUp(self): super(SSHGitClientTests, self).setUp() self.server = TestSSHVendor() self.real_vendor = client.get_ssh_vendor client.get_ssh_vendor = lambda: self.server self.client = SSHGitClient('git.samba.org') def tearDown(self): super(SSHGitClientTests, self).tearDown() client.get_ssh_vendor = self.real_vendor def test_get_url(self): path = '/tmp/repo.git' c = SSHGitClient('git.samba.org') url = c.get_url(path) self.assertEqual('ssh://git.samba.org/tmp/repo.git', url) def test_get_url_with_username_and_port(self): path = '/tmp/repo.git' c = SSHGitClient('git.samba.org', port=2222, username='user') url = c.get_url(path) self.assertEqual('ssh://user@git.samba.org:2222/tmp/repo.git', url) def test_default_command(self): self.assertEqual( b'git-upload-pack', self.client._get_cmd_path(b'upload-pack')) def test_alternative_command_path(self): self.client.alternative_paths[b'upload-pack'] = ( b'/usr/lib/git/git-upload-pack') self.assertEqual( b'/usr/lib/git/git-upload-pack', self.client._get_cmd_path(b'upload-pack')) def test_alternative_command_path_spaces(self): self.client.alternative_paths[b'upload-pack'] = ( b'/usr/lib/git/git-upload-pack -ibla') self.assertEqual(b"/usr/lib/git/git-upload-pack -ibla", self.client._get_cmd_path(b'upload-pack')) def test_connect(self): server = self.server client = self.client client.username = b"username" client.port = 1337 client._connect(b"command", b"/path/to/repo") self.assertEqual(b"username", server.username) self.assertEqual(1337, server.port) self.assertEqual("git-command '/path/to/repo'", server.command) client._connect(b"relative-command", b"/~/path/to/repo") self.assertEqual("git-relative-command '~/path/to/repo'", server.command) class ReportStatusParserTests(TestCase): def test_invalid_pack(self): parser = ReportStatusParser() parser.handle_packet(b"unpack error - foo bar") parser.handle_packet(b"ok refs/foo/bar") parser.handle_packet(None) self.assertRaises(SendPackError, list, parser.check()) def test_update_refs_error(self): parser = ReportStatusParser() parser.handle_packet(b"unpack ok") parser.handle_packet(b"ng refs/foo/bar need to pull") parser.handle_packet(None) self.assertEqual( [(b'refs/foo/bar', 'need to pull')], list(parser.check())) def test_ok(self): parser = ReportStatusParser() parser.handle_packet(b"unpack ok") parser.handle_packet(b"ok refs/foo/bar") parser.handle_packet(None) self.assertEqual([(b'refs/foo/bar', None)], list(parser.check())) class LocalGitClientTests(TestCase): def test_get_url(self): path = "/tmp/repo.git" c = LocalGitClient() url = c.get_url(path) self.assertEqual('file:///tmp/repo.git', url) def test_fetch_into_empty(self): c = LocalGitClient() t = MemoryRepo() s = open_repo('a.git') self.addCleanup(tear_down_repo, s) self.assertEqual(s.get_refs(), c.fetch(s.path, t).refs) def test_fetch_empty(self): c = LocalGitClient() s = open_repo('a.git') self.addCleanup(tear_down_repo, s) out = BytesIO() walker = {} ret = c.fetch_pack( s.path, lambda heads: [], graph_walker=walker, pack_data=out.write) self.assertEqual({ b'HEAD': b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', b'refs/heads/master': b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', b'refs/tags/mytag': b'28237f4dc30d0d462658d6b937b08a0f0b6ef55a', b'refs/tags/mytag-packed': b'b0931cadc54336e78a1d980420e3268903b57a50' }, ret.refs) self.assertEqual( {b'HEAD': b'refs/heads/master'}, ret.symrefs) self.assertEqual( b"PACK\x00\x00\x00\x02\x00\x00\x00\x00\x02\x9d\x08" b"\x82;\xd8\xa8\xea\xb5\x10\xadj\xc7\\\x82<\xfd>\xd3\x1e", out.getvalue()) def test_fetch_pack_none(self): c = LocalGitClient() s = open_repo('a.git') self.addCleanup(tear_down_repo, s) out = BytesIO() walker = MemoryRepo().get_graph_walker() ret = c.fetch_pack( s.path, lambda heads: [b"a90fa2d900a17e99b433217e988c4eb4a2e9a097"], graph_walker=walker, pack_data=out.write) self.assertEqual({b'HEAD': b'refs/heads/master'}, ret.symrefs) self.assertEqual({ b'HEAD': b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', b'refs/heads/master': b'a90fa2d900a17e99b433217e988c4eb4a2e9a097', b'refs/tags/mytag': b'28237f4dc30d0d462658d6b937b08a0f0b6ef55a', b'refs/tags/mytag-packed': b'b0931cadc54336e78a1d980420e3268903b57a50' }, ret.refs) # Hardcoding is not ideal, but we'll fix that some other day.. self.assertTrue(out.getvalue().startswith( b'PACK\x00\x00\x00\x02\x00\x00\x00\x07')) def test_send_pack_without_changes(self): local = open_repo('a.git') self.addCleanup(tear_down_repo, local) target = open_repo('a.git') self.addCleanup(tear_down_repo, target) self.send_and_verify(b"master", local, target) def test_send_pack_with_changes(self): local = open_repo('a.git') self.addCleanup(tear_down_repo, local) target_path = tempfile.mkdtemp() self.addCleanup(shutil.rmtree, target_path) with Repo.init_bare(target_path) as target: self.send_and_verify(b"master", local, target) def test_get_refs(self): local = open_repo('refs.git') self.addCleanup(tear_down_repo, local) client = LocalGitClient() refs = client.get_refs(local.path) self.assertDictEqual(local.refs.as_dict(), refs) def send_and_verify(self, branch, local, target): """Send branch from local to remote repository and verify it worked.""" client = LocalGitClient() ref_name = b"refs/heads/" + branch result = client.send_pack(target.path, lambda _: {ref_name: local.refs[ref_name]}, local.generate_pack_data) self.assertEqual(local.refs[ref_name], result.refs[ref_name]) self.assertIs(None, result.agent) self.assertEqual({}, result.ref_status) obj_local = local.get_object(result.refs[ref_name]) obj_target = target.get_object(result.refs[ref_name]) self.assertEqual(obj_local, obj_target) class HttpGitClientTests(TestCase): def test_get_url(self): base_url = 'https://github.com/jelmer/dulwich' path = '/jelmer/dulwich' c = HttpGitClient(base_url) url = c.get_url(path) self.assertEqual('https://github.com/jelmer/dulwich', url) def test_get_url_bytes_path(self): base_url = 'https://github.com/jelmer/dulwich' path_bytes = b'/jelmer/dulwich' c = HttpGitClient(base_url) url = c.get_url(path_bytes) self.assertEqual('https://github.com/jelmer/dulwich', url) def test_get_url_with_username_and_passwd(self): base_url = 'https://github.com/jelmer/dulwich' path = '/jelmer/dulwich' c = HttpGitClient(base_url, username='USERNAME', password='PASSWD') url = c.get_url(path) self.assertEqual('https://github.com/jelmer/dulwich', url) def test_init_username_passwd_set(self): url = 'https://github.com/jelmer/dulwich' c = HttpGitClient(url, config=None, username='user', password='passwd') self.assertEqual('user', c._username) self.assertEqual('passwd', c._password) basic_auth = c.pool_manager.headers['authorization'] auth_string = '%s:%s' % ('user', 'passwd') b64_credentials = base64.b64encode(auth_string.encode('latin1')) expected_basic_auth = 'Basic %s' % b64_credentials.decode('latin1') self.assertEqual(basic_auth, expected_basic_auth) def test_init_no_username_passwd(self): url = 'https://github.com/jelmer/dulwich' c = HttpGitClient(url, config=None) self.assertIs(None, c._username) self.assertIs(None, c._password) self.assertNotIn('authorization', c.pool_manager.headers) def test_from_parsedurl_on_url_with_quoted_credentials(self): original_username = 'john|the|first' quoted_username = urlquote(original_username) original_password = 'Ya#1$2%3' quoted_password = urlquote(original_password) url = 'https://{username}:{password}@github.com/jelmer/dulwich'.format( username=quoted_username, password=quoted_password ) c = HttpGitClient.from_parsedurl(urlparse(url)) self.assertEqual(original_username, c._username) self.assertEqual(original_password, c._password) basic_auth = c.pool_manager.headers['authorization'] auth_string = '%s:%s' % (original_username, original_password) b64_credentials = base64.b64encode(auth_string.encode('latin1')) expected_basic_auth = 'Basic %s' % b64_credentials.decode('latin1') self.assertEqual(basic_auth, expected_basic_auth) def test_url_redirect_location(self): from urllib3.response import HTTPResponse test_data = { 'https://gitlab.com/inkscape/inkscape/': { 'redirect_url': 'https://gitlab.com/inkscape/inkscape.git/', 'refs_data': (b'001e# service=git-upload-pack\n00000032' b'fb2bebf4919a011f0fd7cec085443d0031228e76 ' b'HEAD\n0000') }, 'https://github.com/jelmer/dulwich/': { 'redirect_url': 'https://github.com/jelmer/dulwich/', 'refs_data': (b'001e# service=git-upload-pack\n00000032' b'3ff25e09724aa4d86ea5bca7d5dd0399a3c8bfcf ' b'HEAD\n0000') } } tail = 'info/refs?service=git-upload-pack' # we need to mock urllib3.PoolManager as this test will fail # otherwise without an active internet connection class PoolManagerMock(): def __init__(self): self.headers = {} def request(self, method, url, fields=None, headers=None, redirect=True): base_url = url[:-len(tail)] redirect_base_url = test_data[base_url]['redirect_url'] redirect_url = redirect_base_url + tail headers = { 'Content-Type': 'application/x-git-upload-pack-advertisement' } body = test_data[base_url]['refs_data'] # urllib3 handles automatic redirection by default status = 200 request_url = redirect_url # simulate urllib3 behavior when redirect parameter is False if redirect is False: request_url = url if redirect_base_url != base_url: body = '' headers['location'] = redirect_url status = 301 return HTTPResponse(body=body, headers=headers, request_method=method, request_url=request_url, status=status) pool_manager = PoolManagerMock() for base_url in test_data.keys(): # instantiate HttpGitClient with mocked pool manager c = HttpGitClient(base_url, pool_manager=pool_manager, config=None) # call method that detects url redirection _, _, processed_url = c._discover_references(b'git-upload-pack', base_url) # send the same request as the method above without redirection resp = c.pool_manager.request('GET', base_url + tail, redirect=False) # check expected behavior of urllib3 redirect_location = resp.get_redirect_location() if resp.status == 200: self.assertFalse(redirect_location) if redirect_location: # check that url redirection has been correctly detected self.assertEqual(processed_url, redirect_location[:-len(tail)]) else: # check also the no redirection case self.assertEqual(processed_url, base_url) class TCPGitClientTests(TestCase): def test_get_url(self): host = 'github.com' path = '/jelmer/dulwich' c = TCPGitClient(host) url = c.get_url(path) self.assertEqual('git://github.com/jelmer/dulwich', url) def test_get_url_with_port(self): host = 'github.com' path = '/jelmer/dulwich' port = 9090 c = TCPGitClient(host, port=port) url = c.get_url(path) self.assertEqual('git://github.com:9090/jelmer/dulwich', url) class DefaultUrllib3ManagerTest(TestCase): def test_no_config(self): manager = default_urllib3_manager(config=None) self.assertEqual(manager.connection_pool_kw['cert_reqs'], 'CERT_REQUIRED') def test_config_no_proxy(self): import urllib3 manager = default_urllib3_manager(config=ConfigDict()) self.assertNotIsInstance(manager, urllib3.ProxyManager) self.assertIsInstance(manager, urllib3.PoolManager) def test_config_no_proxy_custom_cls(self): import urllib3 class CustomPoolManager(urllib3.PoolManager): pass manager = default_urllib3_manager(config=ConfigDict(), pool_manager_cls=CustomPoolManager) self.assertIsInstance(manager, CustomPoolManager) def test_config_ssl(self): config = ConfigDict() config.set(b'http', b'sslVerify', b'true') manager = default_urllib3_manager(config=config) self.assertEqual(manager.connection_pool_kw['cert_reqs'], 'CERT_REQUIRED') def test_config_no_ssl(self): config = ConfigDict() config.set(b'http', b'sslVerify', b'false') manager = default_urllib3_manager(config=config) self.assertEqual(manager.connection_pool_kw['cert_reqs'], 'CERT_NONE') def test_config_proxy(self): import urllib3 config = ConfigDict() config.set(b'http', b'proxy', b'http://localhost:3128/') manager = default_urllib3_manager(config=config) self.assertIsInstance(manager, urllib3.ProxyManager) self.assertTrue(hasattr(manager, 'proxy')) self.assertEqual(manager.proxy.scheme, 'http') self.assertEqual(manager.proxy.host, 'localhost') self.assertEqual(manager.proxy.port, 3128) + def test_environment_proxy(self): + import urllib3 + config = ConfigDict() + os.environ['http_proxy'] = 'http://myproxy:8080' + manager = default_urllib3_manager(config=config) + self.assertIsInstance(manager, urllib3.ProxyManager) + self.assertTrue(hasattr(manager, 'proxy')) + self.assertEqual(manager.proxy.scheme, 'http') + self.assertEqual(manager.proxy.host, 'myproxy') + self.assertEqual(manager.proxy.port, 8080) + del os.environ['http_proxy'] + def test_config_proxy_custom_cls(self): import urllib3 class CustomProxyManager(urllib3.ProxyManager): pass config = ConfigDict() config.set(b'http', b'proxy', b'http://localhost:3128/') manager = default_urllib3_manager(config=config, proxy_manager_cls=CustomProxyManager) self.assertIsInstance(manager, CustomProxyManager) def test_config_no_verify_ssl(self): manager = default_urllib3_manager(config=None, cert_reqs="CERT_NONE") self.assertEqual(manager.connection_pool_kw['cert_reqs'], 'CERT_NONE') class SubprocessSSHVendorTests(TestCase): def setUp(self): # Monkey Patch client subprocess popen self._orig_popen = dulwich.client.subprocess.Popen dulwich.client.subprocess.Popen = DummyPopen def tearDown(self): dulwich.client.subprocess.Popen = self._orig_popen def test_run_command_dashes(self): vendor = SubprocessSSHVendor() self.assertRaises(StrangeHostname, vendor.run_command, '--weird-host', 'git-clone-url') def test_run_command_password(self): vendor = SubprocessSSHVendor() self.assertRaises(NotImplementedError, vendor.run_command, 'host', 'git-clone-url', password='12345') def test_run_command_password_and_privkey(self): vendor = SubprocessSSHVendor() self.assertRaises(NotImplementedError, vendor.run_command, 'host', 'git-clone-url', password='12345', key_filename='/tmp/id_rsa') def test_run_command_with_port_username_and_privkey(self): expected = ['ssh', '-x', '-p', '2200', '-i', '/tmp/id_rsa', 'user@host', 'git-clone-url'] vendor = SubprocessSSHVendor() command = vendor.run_command( 'host', 'git-clone-url', username='user', port='2200', key_filename='/tmp/id_rsa') args = command.proc.args self.assertListEqual(expected, args[0]) class PLinkSSHVendorTests(TestCase): def setUp(self): # Monkey Patch client subprocess popen self._orig_popen = dulwich.client.subprocess.Popen dulwich.client.subprocess.Popen = DummyPopen def tearDown(self): dulwich.client.subprocess.Popen = self._orig_popen def test_run_command_dashes(self): vendor = PLinkSSHVendor() self.assertRaises(StrangeHostname, vendor.run_command, '--weird-host', 'git-clone-url') def test_run_command_password_and_privkey(self): vendor = PLinkSSHVendor() warnings.simplefilter("always", UserWarning) self.addCleanup(warnings.resetwarnings) warnings_list, restore_warnings = setup_warning_catcher() self.addCleanup(restore_warnings) command = vendor.run_command( 'host', 'git-clone-url', password='12345', key_filename='/tmp/id_rsa') expected_warning = UserWarning( 'Invoking PLink with a password exposes the password in the ' 'process list.') for w in warnings_list: if (type(w) == type(expected_warning) and w.args == expected_warning.args): break else: raise AssertionError( 'Expected warning %r not in %r' % (expected_warning, warnings_list)) args = command.proc.args if sys.platform == 'win32': binary = ['plink.exe', '-ssh'] else: binary = ['plink', '-ssh'] expected = binary + [ '-pw', '12345', '-i', '/tmp/id_rsa', 'host', 'git-clone-url'] self.assertListEqual(expected, args[0]) def test_run_command_password(self): if sys.platform == 'win32': binary = ['plink.exe', '-ssh'] else: binary = ['plink', '-ssh'] expected = binary + ['-pw', '12345', 'host', 'git-clone-url'] vendor = PLinkSSHVendor() warnings.simplefilter("always", UserWarning) self.addCleanup(warnings.resetwarnings) warnings_list, restore_warnings = setup_warning_catcher() self.addCleanup(restore_warnings) command = vendor.run_command('host', 'git-clone-url', password='12345') expected_warning = UserWarning( 'Invoking PLink with a password exposes the password in the ' 'process list.') for w in warnings_list: if (type(w) == type(expected_warning) and w.args == expected_warning.args): break else: raise AssertionError( 'Expected warning %r not in %r' % (expected_warning, warnings_list)) args = command.proc.args self.assertListEqual(expected, args[0]) def test_run_command_with_port_username_and_privkey(self): if sys.platform == 'win32': binary = ['plink.exe', '-ssh'] else: binary = ['plink', '-ssh'] expected = binary + [ '-P', '2200', '-i', '/tmp/id_rsa', 'user@host', 'git-clone-url'] vendor = PLinkSSHVendor() command = vendor.run_command( 'host', 'git-clone-url', username='user', port='2200', key_filename='/tmp/id_rsa') args = command.proc.args self.assertListEqual(expected, args[0]) class RsyncUrlTests(TestCase): def test_simple(self): self.assertEqual( parse_rsync_url('foo:bar/path'), (None, 'foo', 'bar/path')) self.assertEqual( parse_rsync_url('user@foo:bar/path'), ('user', 'foo', 'bar/path')) def test_path(self): self.assertRaises(ValueError, parse_rsync_url, '/path') class CheckWantsTests(TestCase): def test_fine(self): check_wants( [b'2f3dc7a53fb752a6961d3a56683df46d4d3bf262'], {b'refs/heads/blah': b'2f3dc7a53fb752a6961d3a56683df46d4d3bf262'}) def test_missing(self): self.assertRaises( InvalidWants, check_wants, [b'2f3dc7a53fb752a6961d3a56683df46d4d3bf262'], {b'refs/heads/blah': b'3f3dc7a53fb752a6961d3a56683df46d4d3bf262'}) def test_annotated(self): self.assertRaises( InvalidWants, check_wants, [b'2f3dc7a53fb752a6961d3a56683df46d4d3bf262'], {b'refs/heads/blah': b'3f3dc7a53fb752a6961d3a56683df46d4d3bf262', b'refs/heads/blah^{}': b'2f3dc7a53fb752a6961d3a56683df46d4d3bf262'}) class FetchPackResultTests(TestCase): def test_eq(self): self.assertEqual( FetchPackResult( {b'refs/heads/master': b'2f3dc7a53fb752a6961d3a56683df46d4d3bf262'}, {}, b'user/agent'), FetchPackResult( {b'refs/heads/master': b'2f3dc7a53fb752a6961d3a56683df46d4d3bf262'}, {}, b'user/agent')) class GitCredentialStoreTests(TestCase): @classmethod def setUpClass(cls): with tempfile.NamedTemporaryFile(delete=False) as f: f.write(b'https://user:pass@example.org') cls.fname = f.name @classmethod def tearDownClass(cls): os.unlink(cls.fname) def test_nonmatching_scheme(self): self.assertEqual( get_credentials_from_store( b'http', b'example.org', fnames=[self.fname]), None) def test_nonmatching_hostname(self): self.assertEqual( get_credentials_from_store( b'https', b'noentry.org', fnames=[self.fname]), None) def test_match_without_username(self): self.assertEqual( get_credentials_from_store( b'https', b'example.org', fnames=[self.fname]), (b'user', b'pass')) def test_match_with_matching_username(self): self.assertEqual( get_credentials_from_store( b'https', b'example.org', b'user', fnames=[self.fname]), (b'user', b'pass')) def test_no_match_with_nonmatching_username(self): self.assertEqual( get_credentials_from_store( b'https', b'example.org', b'otheruser', fnames=[self.fname]), None) class RemoteErrorFromStderrTests(TestCase): def test_nothing(self): self.assertEqual( _remote_error_from_stderr(None), HangupException()) def test_error_line(self): b = BytesIO(b"""\ This is some random output. ERROR: This is the actual error with a tail """) self.assertEqual( _remote_error_from_stderr(b), GitProtocolError("This is the actual error")) def test_no_error_line(self): b = BytesIO(b"""\ This is output without an error line. And this line is just random noise, too. """) self.assertEqual( _remote_error_from_stderr(b), HangupException([ b"This is output without an error line.", b"And this line is just random noise, too."])) diff --git a/dulwich/tests/test_repository.py b/dulwich/tests/test_repository.py index 5502cc6d..73d37bdc 100644 --- a/dulwich/tests/test_repository.py +++ b/dulwich/tests/test_repository.py @@ -1,1148 +1,1156 @@ # -*- 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, + UnsupportedVersion, ) 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) self.assertFalse(b"z" * 40 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_parents(self): r = self.open_repo('a.git') self.assertEqual( [b'2a72d929692c41d8554c07f6301757ba18a65d91'], r.get_parents(b'a90fa2d900a17e99b433217e988c4eb4a2e9a097')) r.update_shallow( [b'a90fa2d900a17e99b433217e988c4eb4a2e9a097'], None) self.assertEqual( [], r.get_parents(b'a90fa2d900a17e99b433217e988c4eb4a2e9a097')) 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: os.fsencode(repo_name) 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 = os.fsencode(encoded_path) 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) 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 1',) 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_repositoryformatversion(self): + r = self._repo + c = r.get_config() + c.set(('core',), 'repositoryformatversion', '2') + c.write_to_path() + self.assertRaises(UnsupportedVersion, Repo, self._repo_dir) + 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 in ('win32', 'darwin'), 'tries to implicitly decode as utf8') def test_commit_no_encode_decode(self): r = self._repo repo_path_bytes = os.fsencode(r.path) 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/setup.py b/setup.py index 7426379c..124ff9fb 100755 --- a/setup.py +++ b/setup.py @@ -1,134 +1,135 @@ #!/usr/bin/python3 # 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 from typing import Dict, Any if sys.version_info < (3, 5): raise Exception( 'Dulwich only supports Python 3.5 and later. ' 'For 2.7 support, please install a version prior to 0.20') -dulwich_version_string = '0.20.6' +dulwich_version_string = '0.20.8' 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']), Extension('dulwich._pack', ['dulwich/_pack.c']), Extension('dulwich._diff_tree', ['dulwich/_diff_tree.c']), ] setup_kwargs = {} # type: Dict[str, Any] scripts = ['bin/dul-receive-pack', 'bin/dul-upload-pack'] if has_setuptools: setup_kwargs['extras_require'] = { 'fastimport': ['fastimport'], 'https': ['urllib3[secure]>=1.24.1'], 'pgp': ['gpg'], 'watch': ['pyinotify'], } 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 setup_kwargs['entry_points'] = { "console_scripts": [ "dulwich=dulwich.cli:main", ]} setup_kwargs['python_requires'] = '>=3.5' else: scripts.append('bin/dulwich') 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=scripts, ext_modules=ext_modules, distclass=DulwichDistribution, classifiers=[ 'Development Status :: 4 - Beta', 'License :: OSI Approved :: Apache Software License', 'Programming Language :: Python :: 3.5', 'Programming Language :: Python :: 3.6', 'Programming Language :: Python :: 3.7', 'Programming Language :: Python :: 3.8', + 'Programming Language :: Python :: 3.9', 'Programming Language :: Python :: Implementation :: CPython', 'Programming Language :: Python :: Implementation :: PyPy', 'Operating System :: POSIX', 'Operating System :: Microsoft :: Windows', 'Topic :: Software Development :: Version Control', ], **setup_kwargs )