diff --git a/CONTRIBUTORS b/CONTRIBUTORS new file mode 100644 index 0000000..fafdafb --- /dev/null +++ b/CONTRIBUTORS @@ -0,0 +1 @@ +Aastha Asthana diff --git a/PKG-INFO b/PKG-INFO index b02cdab..07ba24e 100644 --- a/PKG-INFO +++ b/PKG-INFO @@ -1,102 +1,102 @@ Metadata-Version: 2.1 Name: swh.loader.git -Version: 0.9.0 +Version: 0.9.1 Summary: Software Heritage git loader Home-page: https://forge.softwareheritage.org/diffusion/DLDG/ Author: Software Heritage developers Author-email: swh-devel@inria.fr License: UNKNOWN Project-URL: Bug Reports, https://forge.softwareheritage.org/maniphest Project-URL: Funding, https://www.softwareheritage.org/donate Project-URL: Source, https://forge.softwareheritage.org/source/swh-loader-git Project-URL: Documentation, https://docs.softwareheritage.org/devel/swh-loader-git/ Description: swh-loader-git ============== The Software Heritage Git Loader is a tool and a library to walk a local Git repository and inject into the SWH dataset all contained files that weren't known before. The main entry points are - :class:`swh.loader.git.loader.GitLoader` for the main loader which ingests a remote git repository's contents. - :class:`swh.loader.git.from_disk.GitLoaderFromDisk` which ingests a local git clone repository. - :class:`swh.loader.git.loader.GitLoaderFromArchive` which ingests a git repository wrapped in an archive. License ------- This program is free software: you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version. This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. See top-level LICENSE file for the full text of the GNU General Public License along with this program. Dependencies ------------ ### Runtime - python3 - python3-dulwich - python3-retrying - python3-swh.core - python3-swh.model - python3-swh.storage - python3-swh.scheduler ### Test - python3-nose Requirements ------------ - implementation language, Python3 - coding guidelines: conform to PEP8 - Git access: via dulwich CLI Run ---------- You can run the loader from a remote origin (*loader*) or from an origin on disk (*from_disk*) directly by calling: ``` swh loader -C run git ``` or "git_disk". ## Configuration sample /tmp/git.yml: ``` storage: cls: remote args: url: http://localhost:5002/ ``` Platform: UNKNOWN Classifier: Programming Language :: Python :: 3 Classifier: Intended Audience :: Developers Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3) Classifier: Operating System :: OS Independent Classifier: Development Status :: 5 - Production/Stable Requires-Python: >=3.7 Description-Content-Type: text/markdown Provides-Extra: testing diff --git a/swh.loader.git.egg-info/PKG-INFO b/swh.loader.git.egg-info/PKG-INFO index b02cdab..07ba24e 100644 --- a/swh.loader.git.egg-info/PKG-INFO +++ b/swh.loader.git.egg-info/PKG-INFO @@ -1,102 +1,102 @@ Metadata-Version: 2.1 Name: swh.loader.git -Version: 0.9.0 +Version: 0.9.1 Summary: Software Heritage git loader Home-page: https://forge.softwareheritage.org/diffusion/DLDG/ Author: Software Heritage developers Author-email: swh-devel@inria.fr License: UNKNOWN Project-URL: Bug Reports, https://forge.softwareheritage.org/maniphest Project-URL: Funding, https://www.softwareheritage.org/donate Project-URL: Source, https://forge.softwareheritage.org/source/swh-loader-git Project-URL: Documentation, https://docs.softwareheritage.org/devel/swh-loader-git/ Description: swh-loader-git ============== The Software Heritage Git Loader is a tool and a library to walk a local Git repository and inject into the SWH dataset all contained files that weren't known before. The main entry points are - :class:`swh.loader.git.loader.GitLoader` for the main loader which ingests a remote git repository's contents. - :class:`swh.loader.git.from_disk.GitLoaderFromDisk` which ingests a local git clone repository. - :class:`swh.loader.git.loader.GitLoaderFromArchive` which ingests a git repository wrapped in an archive. License ------- This program is free software: you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version. This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. See top-level LICENSE file for the full text of the GNU General Public License along with this program. Dependencies ------------ ### Runtime - python3 - python3-dulwich - python3-retrying - python3-swh.core - python3-swh.model - python3-swh.storage - python3-swh.scheduler ### Test - python3-nose Requirements ------------ - implementation language, Python3 - coding guidelines: conform to PEP8 - Git access: via dulwich CLI Run ---------- You can run the loader from a remote origin (*loader*) or from an origin on disk (*from_disk*) directly by calling: ``` swh loader -C run git ``` or "git_disk". ## Configuration sample /tmp/git.yml: ``` storage: cls: remote args: url: http://localhost:5002/ ``` Platform: UNKNOWN Classifier: Programming Language :: Python :: 3 Classifier: Intended Audience :: Developers Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3) Classifier: Operating System :: OS Independent Classifier: Development Status :: 5 - Production/Stable Requires-Python: >=3.7 Description-Content-Type: text/markdown Provides-Extra: testing diff --git a/swh.loader.git.egg-info/SOURCES.txt b/swh.loader.git.egg-info/SOURCES.txt index 6df8683..2c3e5eb 100644 --- a/swh.loader.git.egg-info/SOURCES.txt +++ b/swh.loader.git.egg-info/SOURCES.txt @@ -1,56 +1,57 @@ .gitignore .pre-commit-config.yaml AUTHORS CODE_OF_CONDUCT.md +CONTRIBUTORS LICENSE MANIFEST.in Makefile README.md conftest.py mypy.ini pyproject.toml pytest.ini requirements-swh.txt requirements-test.txt requirements.txt setup.cfg setup.py tox.ini bin/dir-git-repo-meta.sh docs/.gitignore docs/Makefile docs/conf.py docs/index.rst docs/_static/.placeholder docs/_templates/.placeholder docs/attic/api-backend-protocol.txt docs/attic/git-loading-design.txt resources/local-loader-git.ini resources/remote-loader-git.ini resources/updater.ini resources/test/back.ini resources/test/db-manager.ini swh/__init__.py swh.loader.git.egg-info/PKG-INFO swh.loader.git.egg-info/SOURCES.txt swh.loader.git.egg-info/dependency_links.txt swh.loader.git.egg-info/entry_points.txt swh.loader.git.egg-info/requires.txt swh.loader.git.egg-info/top_level.txt swh/loader/__init__.py swh/loader/git/__init__.py swh/loader/git/converters.py swh/loader/git/from_disk.py swh/loader/git/loader.py swh/loader/git/py.typed swh/loader/git/tasks.py swh/loader/git/utils.py swh/loader/git/tests/__init__.py swh/loader/git/tests/conftest.py swh/loader/git/tests/test_converters.py swh/loader/git/tests/test_from_disk.py swh/loader/git/tests/test_loader.py swh/loader/git/tests/test_tasks.py swh/loader/git/tests/test_utils.py swh/loader/git/tests/data/testrepo.tgz swh/loader/git/tests/data/git-repos/example-submodule.bundle \ No newline at end of file diff --git a/swh/loader/git/converters.py b/swh/loader/git/converters.py index 46dd66c..0afa681 100644 --- a/swh/loader/git/converters.py +++ b/swh/loader/git/converters.py @@ -1,182 +1,182 @@ # Copyright (C) 2015-2020 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information """Convert dulwich objects to dictionaries suitable for swh.storage""" from typing import Any, Dict, Optional from swh.model.hashutil import DEFAULT_ALGORITHMS, MultiHash, hash_to_bytes from swh.model.model import ( BaseContent, Content, Directory, DirectoryEntry, ObjectType, Person, Release, Revision, RevisionType, SkippedContent, TargetType, Timestamp, TimestampWithTimezone, ) HASH_ALGORITHMS = DEFAULT_ALGORITHMS - {"sha1_git"} def dulwich_blob_to_content_id(blob) -> Dict[str, Any]: """Convert a dulwich blob to a Software Heritage content id""" if blob.type_name != b"blob": raise ValueError("Argument is not a blob.") size = blob.raw_length() data = blob.as_raw_string() hashes = MultiHash.from_data(data, HASH_ALGORITHMS).digest() hashes["sha1_git"] = blob.sha().digest() hashes["length"] = size return hashes def dulwich_blob_to_content(blob, max_content_size=None) -> BaseContent: """Convert a dulwich blob to a Software Heritage content """ if blob.type_name != b"blob": raise ValueError("Argument is not a blob.") hashes = dulwich_blob_to_content_id(blob) if max_content_size is not None and hashes["length"] >= max_content_size: return SkippedContent(status="absent", reason="Content too large", **hashes,) else: return Content(data=blob.as_raw_string(), status="visible", **hashes,) def dulwich_tree_to_directory(tree, log=None) -> Directory: """Format a tree as a directory""" if tree.type_name != b"tree": raise ValueError("Argument is not a tree.") entries = [] entry_mode_map = { 0o040000: "dir", 0o160000: "rev", 0o100644: "file", 0o100755: "file", 0o120000: "file", } for entry in tree.iteritems(): entries.append( DirectoryEntry( type=entry_mode_map.get(entry.mode, "file"), perms=entry.mode, name=entry.path, target=hash_to_bytes(entry.sha.decode("ascii")), ) ) return Directory(id=tree.sha().digest(), entries=tuple(entries),) def parse_author(name_email: bytes) -> Person: """Parse an author line""" return Person.from_fullname(name_email) def dulwich_tsinfo_to_timestamp( timestamp, timezone, timezone_neg_utc ) -> TimestampWithTimezone: """Convert the dulwich timestamp information to a structure compatible with Software Heritage""" return TimestampWithTimezone( timestamp=Timestamp(seconds=int(timestamp), microseconds=0,), offset=timezone // 60, negative_utc=timezone_neg_utc if timezone == 0 else False, ) def dulwich_commit_to_revision(commit, log=None) -> Revision: if commit.type_name != b"commit": raise ValueError("Argument is not a commit.") - git_metadata = [] + extra_headers = [] if commit.encoding is not None: - git_metadata.append((b"encoding", commit.encoding)) + extra_headers.append((b"encoding", commit.encoding)) if commit.mergetag: for mergetag in commit.mergetag: raw_string = mergetag.as_raw_string() assert raw_string.endswith(b"\n") - git_metadata.append((b"mergetag", raw_string[:-1])) + extra_headers.append((b"mergetag", raw_string[:-1])) if commit.extra: - git_metadata.extend((k, v) for k, v in commit.extra) + extra_headers.extend((k, v) for k, v in commit.extra) if commit.gpgsig: - git_metadata.append((b"gpgsig", commit.gpgsig)) + extra_headers.append((b"gpgsig", commit.gpgsig)) return Revision( id=commit.sha().digest(), author=parse_author(commit.author), date=dulwich_tsinfo_to_timestamp( commit.author_time, commit.author_timezone, commit._author_timezone_neg_utc, ), committer=parse_author(commit.committer), committer_date=dulwich_tsinfo_to_timestamp( commit.commit_time, commit.commit_timezone, commit._commit_timezone_neg_utc, ), type=RevisionType.GIT, directory=bytes.fromhex(commit.tree.decode()), message=commit.message, metadata=None, - extra_headers=tuple(git_metadata), + extra_headers=tuple(extra_headers), synthetic=False, parents=tuple(bytes.fromhex(p.decode()) for p in commit.parents), ) DULWICH_TARGET_TYPES = { b"blob": TargetType.CONTENT, b"tree": TargetType.DIRECTORY, b"commit": TargetType.REVISION, b"tag": TargetType.RELEASE, } DULWICH_OBJECT_TYPES = { b"blob": ObjectType.CONTENT, b"tree": ObjectType.DIRECTORY, b"commit": ObjectType.REVISION, b"tag": ObjectType.RELEASE, } def dulwich_tag_to_release(tag, log=None) -> Release: if tag.type_name != b"tag": raise ValueError("Argument is not a tag.") target_type, target = tag.object if tag.tagger: author: Optional[Person] = parse_author(tag.tagger) if not tag.tag_time: date = None else: date = dulwich_tsinfo_to_timestamp( tag.tag_time, tag.tag_timezone, tag._tag_timezone_neg_utc, ) else: author = date = None return Release( id=tag.sha().digest(), author=author, date=date, name=tag.name, target=bytes.fromhex(target.decode()), target_type=DULWICH_OBJECT_TYPES[target_type.type_name], message=tag._message, metadata=None, synthetic=False, ) diff --git a/swh/loader/git/loader.py b/swh/loader/git/loader.py index 8a8049c..cac59a8 100644 --- a/swh/loader/git/loader.py +++ b/swh/loader/git/loader.py @@ -1,476 +1,476 @@ # Copyright (C) 2016-2021 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information from dataclasses import dataclass import datetime from io import BytesIO import logging import os import pickle import sys from typing import Any, Callable, Dict, Iterable, Iterator, List, Optional, Set, Type import dulwich.client from dulwich.errors import GitProtocolError, NotGitRepository from dulwich.object_store import ObjectStoreGraphWalker from dulwich.objects import ShaFile from dulwich.pack import PackData, PackInflater from swh.loader.core.loader import DVCSLoader from swh.loader.exception import NotFound from swh.model import hashutil from swh.model.model import ( BaseContent, Directory, Origin, Release, Revision, Snapshot, SnapshotBranch, TargetType, ) from swh.storage.algos.snapshot import snapshot_get_latest from swh.storage.interface import StorageInterface from . import converters, utils logger = logging.getLogger(__name__) class RepoRepresentation: """Repository representation for a Software Heritage origin.""" def __init__( self, storage, base_snapshot: Optional[Snapshot] = None, ignore_history=False ): self.storage = storage self.ignore_history = ignore_history if base_snapshot and not ignore_history: self.base_snapshot: Snapshot = base_snapshot else: self.base_snapshot = Snapshot(branches={}) self.heads: Set[bytes] = set() def get_parents(self, commit: bytes) -> List[bytes]: """This method should return the list of known parents""" return [] def graph_walker(self) -> ObjectStoreGraphWalker: return ObjectStoreGraphWalker(self.heads, self.get_parents) def determine_wants(self, refs: Dict[bytes, bytes]) -> List[bytes]: """Get the list of bytehex sha1s that the git loader should fetch. This compares the remote refs sent by the server with the base snapshot provided by the loader. """ if not refs: return [] # Cache existing heads local_heads: Set[bytes] = set() for branch_name, branch in self.base_snapshot.branches.items(): if not branch or branch.target_type == TargetType.ALIAS: continue local_heads.add(hashutil.hash_to_hex(branch.target).encode()) self.heads = local_heads # Get the remote heads that we want to fetch remote_heads: Set[bytes] = set() for ref_name, ref_target in refs.items(): if utils.ignore_branch_name(ref_name): continue remote_heads.add(ref_target) return list(remote_heads - local_heads) @dataclass class FetchPackReturn: remote_refs: Dict[bytes, bytes] symbolic_refs: Dict[bytes, bytes] pack_buffer: BytesIO pack_size: int class GitLoader(DVCSLoader): """A bulk loader for a git repository""" visit_type = "git" def __init__( self, storage: StorageInterface, url: str, base_url: Optional[str] = None, ignore_history: bool = False, repo_representation: Type[RepoRepresentation] = RepoRepresentation, pack_size_bytes: int = 4 * 1024 * 1024 * 1024, save_data_path: Optional[str] = None, max_content_size: Optional[int] = None, ): """Initialize the bulk updater. Args: repo_representation: swh's repository representation which is in charge of filtering between known and remote data. """ super().__init__( storage=storage, save_data_path=save_data_path, max_content_size=max_content_size, ) self.origin_url = url self.base_url = base_url self.ignore_history = ignore_history self.repo_representation = repo_representation self.pack_size_bytes = pack_size_bytes # state initialized in fetch_data self.remote_refs: Dict[bytes, bytes] = {} self.symbolic_refs: Dict[bytes, bytes] = {} self.ref_object_types: Dict[bytes, Optional[TargetType]] = {} def fetch_pack_from_origin( self, origin_url: str, base_snapshot: Optional[Snapshot], do_activity: Callable[[bytes], None], ) -> FetchPackReturn: """Fetch a pack from the origin""" pack_buffer = BytesIO() base_repo = self.repo_representation( storage=self.storage, base_snapshot=base_snapshot, ignore_history=self.ignore_history, ) # Hardcode the use of the tcp transport (for GitHub origins) # Even if the Dulwich API lets us process the packfile in chunks as it's # received, the HTTP transport implementation needs to entirely allocate # the packfile in memory *twice*, once in the HTTP library, and once in # a BytesIO managed by Dulwich, before passing chunks to the `do_pack` # method Overall this triples the memory usage before we can even try to # interrupt the loader before it overruns its memory limit. # In contrast, the Dulwich TCP transport just gives us the read handle # on the underlying socket, doing no processing or copying of the bytes. # We can interrupt it as soon as we've received too many bytes. transport_url = origin_url if transport_url.startswith("https://github.com/"): transport_url = "git" + transport_url[5:] client, path = dulwich.client.get_transport_and_path( transport_url, thin_packs=False ) size_limit = self.pack_size_bytes def do_pack(data: bytes) -> None: cur_size = pack_buffer.tell() would_write = len(data) if cur_size + would_write > size_limit: raise IOError( f"Pack file too big for repository {origin_url}, " - "limit is {size_limit} bytes, current size is {cur_size}, " - "would write {would_write}" + f"limit is {size_limit} bytes, current size is {cur_size}, " + f"would write {would_write}" ) pack_buffer.write(data) pack_result = client.fetch_pack( path, base_repo.determine_wants, base_repo.graph_walker(), do_pack, progress=do_activity, ) remote_refs = pack_result.refs or {} symbolic_refs = pack_result.symrefs or {} pack_buffer.flush() pack_size = pack_buffer.tell() pack_buffer.seek(0) logger.debug("Fetched pack size: %s", pack_size) return FetchPackReturn( remote_refs=utils.filter_refs(remote_refs), symbolic_refs=utils.filter_refs(symbolic_refs), pack_buffer=pack_buffer, pack_size=pack_size, ) def prepare_origin_visit(self) -> None: self.visit_date = datetime.datetime.now(tz=datetime.timezone.utc) self.origin = Origin(url=self.origin_url) def get_full_snapshot(self, origin_url) -> Optional[Snapshot]: return snapshot_get_latest(self.storage, origin_url) def prepare(self) -> None: assert self.origin is not None prev_snapshot: Optional[Snapshot] = None if not self.ignore_history: prev_snapshot = self.get_full_snapshot(self.origin.url) if self.base_url and prev_snapshot is None: base_origin = list(self.storage.origin_get([self.base_url]))[0] if base_origin: prev_snapshot = self.get_full_snapshot(base_origin.url) if prev_snapshot is not None: self.base_snapshot = prev_snapshot else: self.base_snapshot = Snapshot(branches={}) def fetch_data(self) -> bool: assert self.origin is not None def do_progress(msg: bytes) -> None: sys.stderr.buffer.write(msg) sys.stderr.flush() try: fetch_info = self.fetch_pack_from_origin( self.origin.url, self.base_snapshot, do_progress ) except NotGitRepository as e: raise NotFound(e) except GitProtocolError as e: # unfortunately, that kind of error is not specific to a not found # scenario... It depends on the value of message within the exception. for msg in [ "Repository unavailable", # e.g DMCA takedown "Repository not found", "unexpected http resp 401", ]: if msg in e.args[0]: raise NotFound(e) # otherwise transmit the error raise self.pack_buffer = fetch_info.pack_buffer self.pack_size = fetch_info.pack_size self.remote_refs = fetch_info.remote_refs self.ref_object_types = {sha1: None for sha1 in self.remote_refs.values()} self.symbolic_refs = fetch_info.symbolic_refs self.log.info( "Listed %d refs for repo %s" % (len(self.remote_refs), self.origin.url), extra={ "swh_type": "git_repo_list_refs", "swh_repo": self.origin.url, "swh_num_refs": len(self.remote_refs), }, ) # No more data to fetch return False def save_data(self) -> None: """Store a pack for archival""" assert isinstance(self.visit_date, datetime.datetime) write_size = 8192 pack_dir = self.get_save_data_path() pack_name = "%s.pack" % self.visit_date.isoformat() refs_name = "%s.refs" % self.visit_date.isoformat() with open(os.path.join(pack_dir, pack_name), "xb") as f: self.pack_buffer.seek(0) while True: r = self.pack_buffer.read(write_size) if not r: break f.write(r) self.pack_buffer.seek(0) with open(os.path.join(pack_dir, refs_name), "xb") as f: pickle.dump(self.remote_refs, f) def iter_objects(self, object_type: bytes) -> Iterator[ShaFile]: """Read all the objects of type `object_type` from the packfile""" self.pack_buffer.seek(0) for obj in PackInflater.for_pack_data( PackData.from_file(self.pack_buffer, self.pack_size) ): if obj.type_name != object_type: continue yield obj def get_contents(self) -> Iterable[BaseContent]: """Format the blobs from the git repository as swh contents""" for raw_obj in self.iter_objects(b"blob"): if raw_obj.id in self.ref_object_types: self.ref_object_types[raw_obj.id] = TargetType.CONTENT yield converters.dulwich_blob_to_content( raw_obj, max_content_size=self.max_content_size ) def get_directories(self) -> Iterable[Directory]: """Format the trees as swh directories""" for raw_obj in self.iter_objects(b"tree"): if raw_obj.id in self.ref_object_types: self.ref_object_types[raw_obj.id] = TargetType.DIRECTORY yield converters.dulwich_tree_to_directory(raw_obj, log=self.log) def get_revisions(self) -> Iterable[Revision]: """Format commits as swh revisions""" for raw_obj in self.iter_objects(b"commit"): if raw_obj.id in self.ref_object_types: self.ref_object_types[raw_obj.id] = TargetType.REVISION yield converters.dulwich_commit_to_revision(raw_obj, log=self.log) def get_releases(self) -> Iterable[Release]: """Retrieve all the release objects from the git repository""" for raw_obj in self.iter_objects(b"tag"): if raw_obj.id in self.ref_object_types: self.ref_object_types[raw_obj.id] = TargetType.RELEASE yield converters.dulwich_tag_to_release(raw_obj, log=self.log) def get_snapshot(self) -> Snapshot: """Get the snapshot for the current visit. The main complexity of this function is mapping target objects to their types, as the `refs` dictionaries returned by the git server only give us the identifiers for the target objects, and not their types. The loader itself only knows the types of the objects that it has fetched from the server (as it has parsed them while loading them to the archive). As we only fetched an increment between the previous snapshot and the current state of the server, we are missing the type information for the objects that would already have been referenced by the previous snapshot, and that the git server didn't send us. We infer the type of these objects from the previous snapshot. """ branches: Dict[bytes, Optional[SnapshotBranch]] = {} unfetched_refs: Dict[bytes, bytes] = {} # Retrieve types from the objects loaded by the current loader for ref_name, ref_object in self.remote_refs.items(): if ref_name in self.symbolic_refs: continue target = hashutil.hash_to_bytes(ref_object.decode()) target_type = self.ref_object_types.get(ref_object) if target_type: branches[ref_name] = SnapshotBranch( target=target, target_type=target_type ) else: # The object pointed at by this ref was not fetched, supposedly # because it existed in the base snapshot. We record it here, # and we can get it from the base snapshot later. unfetched_refs[ref_name] = target dangling_branches = {} # Handle symbolic references as alias branches for ref_name, target in self.symbolic_refs.items(): branches[ref_name] = SnapshotBranch( target_type=TargetType.ALIAS, target=target, ) if target not in branches and target not in unfetched_refs: # This handles the case where the pointer is "dangling". # There's a chance that a further symbolic reference # override this default value, which is totally fine. dangling_branches[target] = ref_name branches[target] = None if unfetched_refs: # Handle inference of object types from the contents of the # previous snapshot unknown_objects = {} base_snapshot_reverse_branches = { branch.target: branch for branch in self.base_snapshot.branches.values() if branch and branch.target_type != TargetType.ALIAS } for ref_name, target in unfetched_refs.items(): branch = base_snapshot_reverse_branches.get(target) branches[ref_name] = branch if not branch: unknown_objects[ref_name] = target if unknown_objects: # This object was referenced by the server; We did not fetch # it, and we do not know it from the previous snapshot. This is # likely a bug in the loader. raise RuntimeError( "Unknown objects referenced by remote refs: %s" % ( ", ".join( f"{name.decode()}: {hashutil.hash_to_hex(obj)}" for name, obj in unknown_objects.items() ) ) ) utils.warn_dangling_branches( branches, dangling_branches, self.log, self.origin_url ) self.snapshot = Snapshot(branches=branches) return self.snapshot def load_status(self) -> Dict[str, Any]: """The load was eventful if the current snapshot is different to the one we retrieved at the beginning of the run""" eventful = False if self.base_snapshot and self.snapshot: eventful = self.snapshot.id != self.base_snapshot.id elif self.snapshot: eventful = bool(self.snapshot.branches) return {"status": ("eventful" if eventful else "uneventful")} if __name__ == "__main__": import click logging.basicConfig( level=logging.DEBUG, format="%(asctime)s %(process)d %(message)s" ) @click.command() @click.option("--origin-url", help="Origin url", required=True) @click.option("--base-url", default=None, help="Optional Base url") @click.option( "--ignore-history/--no-ignore-history", help="Ignore the repository history", default=False, ) def main(origin_url: str, base_url: str, ignore_history: bool) -> Dict[str, Any]: from swh.storage import get_storage storage = get_storage(cls="memory") loader = GitLoader( storage, origin_url, base_url=base_url, ignore_history=ignore_history, ) return loader.load() main()