diff --git a/swh/loader/package/loader.py b/swh/loader/package/loader.py index 6b70468..4d0b6d9 100644 --- a/swh/loader/package/loader.py +++ b/swh/loader/package/loader.py @@ -1,1063 +1,1080 @@ # Copyright (C) 2019-2021 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 import datetime import hashlib from itertools import islice import json import logging import os import string import sys import tempfile from typing import ( Any, Dict, Generic, Iterable, Iterator, List, Mapping, Optional, Sequence, Set, Tuple, TypeVar, ) import attr from requests.exceptions import ContentDecodingError import sentry_sdk from swh.core.tarball import uncompress from swh.loader.core.loader import BaseLoader from swh.loader.exception import NotFound from swh.loader.package.utils import download from swh.model import from_disk from swh.model.hashutil import hash_to_hex from swh.model.model import ( ExtID, MetadataAuthority, MetadataAuthorityType, MetadataFetcher, ) from swh.model.model import ( Origin, OriginVisit, OriginVisitStatus, RawExtrinsicMetadata, Release, Revision, Sha1Git, Snapshot, ) from swh.model.model import ObjectType as ModelObjectType from swh.model.swhids import CoreSWHID, ExtendedObjectType, ExtendedSWHID, ObjectType from swh.storage.algos.snapshot import snapshot_get_latest from swh.storage.interface import StorageInterface from swh.storage.utils import now logger = logging.getLogger(__name__) SWH_METADATA_AUTHORITY = MetadataAuthority( type=MetadataAuthorityType.REGISTRY, url="https://softwareheritage.org/", metadata={}, ) """Metadata authority for extrinsic metadata generated by Software Heritage. Used for metadata on "original artifacts", ie. length, filename, and checksums of downloaded archive files.""" PartialExtID = Tuple[str, int, bytes] """The ``extid_type`` and ``extid`` fields of an :class:`ExtID` object.""" @attr.s class RawExtrinsicMetadataCore: """Contains the core of the metadata extracted by a loader, that will be used to build a full RawExtrinsicMetadata object by adding object identifier, context, and provenance information.""" format = attr.ib(type=str) metadata = attr.ib(type=bytes) discovery_date = attr.ib(type=Optional[datetime.datetime], default=None) """Defaults to the visit date.""" @attr.s class BasePackageInfo: """Compute the primary key for a dict using the id_keys as primary key composite. Args: d: A dict entry to compute the primary key on id_keys: Sequence of keys to use as primary key Returns: The identity for that dict entry """ url = attr.ib(type=str) filename = attr.ib(type=Optional[str]) version = attr.ib(type=str) """Version name/number.""" MANIFEST_FORMAT: Optional[string.Template] = None """If not None, used by the default extid() implementation to format a manifest, before hashing it to produce an ExtID.""" EXTID_TYPE: str = "package-manifest-sha256" EXTID_VERSION: int = 0 # The following attribute has kw_only=True in order to allow subclasses # to add attributes. Without kw_only, attributes without default values cannot # go after attributes with default values. # See directory_extrinsic_metadata = attr.ib( type=List[RawExtrinsicMetadataCore], default=[], kw_only=True, ) """:term:`extrinsic metadata` collected by the loader, that will be attached to the loaded directory and added to the Metadata storage.""" # TODO: add support for metadata for releases and contents def extid(self) -> Optional[PartialExtID]: """Returns a unique intrinsic identifier of this package info, or None if this package info is not 'deduplicatable' (meaning that we will always load it, instead of checking the ExtID storage to see if we already did)""" if self.MANIFEST_FORMAT is None: return None else: manifest = self.MANIFEST_FORMAT.substitute( {k: str(v) for (k, v) in attr.asdict(self).items()} ) return ( self.EXTID_TYPE, self.EXTID_VERSION, hashlib.sha256(manifest.encode()).digest(), ) TPackageInfo = TypeVar("TPackageInfo", bound=BasePackageInfo) class PackageLoader(BaseLoader, Generic[TPackageInfo]): # Origin visit type (str) set by the loader visit_type = "" visit_date: datetime.datetime def __init__( self, storage: StorageInterface, url: str, max_content_size: Optional[int] = None, ): """Loader's constructor. This raises exception if the minimal required configuration is missing (cf. fn:`check` method). Args: storage: Storage instance url: Origin url to load data from """ super().__init__(storage=storage, max_content_size=max_content_size) self.url = url self.visit_date = datetime.datetime.now(tz=datetime.timezone.utc) def get_versions(self) -> Sequence[str]: """Return the list of all published package versions. Raises: class:`swh.loader.exception.NotFound` error when failing to read the published package versions. Returns: Sequence of published versions """ return [] def get_package_info(self, version: str) -> Iterator[Tuple[str, TPackageInfo]]: """Given a release version of a package, retrieve the associated package information for such version. Args: version: Package version Returns: (branch name, package metadata) """ yield from {} def build_release( self, p_info: TPackageInfo, uncompressed_path: str, directory: Sha1Git ) -> Optional[Release]: """Build the release from the archive metadata (extrinsic artifact metadata) and the intrinsic metadata. Args: p_info: Package information uncompressed_path: Artifact uncompressed path on disk """ raise NotImplementedError("build_release") def get_default_version(self) -> str: """Retrieve the latest release version if any. Returns: Latest version """ return "" def last_snapshot(self) -> Optional[Snapshot]: """Retrieve the last snapshot out of the last visit. """ return snapshot_get_latest(self.storage, self.url) def new_packageinfo_to_extid(self, p_info: TPackageInfo) -> Optional[PartialExtID]: return p_info.extid() def _get_known_extids( self, packages_info: List[TPackageInfo] ) -> Dict[PartialExtID, List[CoreSWHID]]: """Compute the ExtIDs from new PackageInfo objects, searches which are already loaded in the archive, and returns them if any.""" # Compute the ExtIDs of all the new packages, grouped by extid type new_extids: Dict[Tuple[str, int], List[bytes]] = {} for p_info in packages_info: res = p_info.extid() if res is not None: (extid_type, extid_version, extid_extid) = res new_extids.setdefault((extid_type, extid_version), []).append( extid_extid ) # For each extid type, call extid_get_from_extid() with all the extids of # that type, and store them in the '(type, extid) -> target' map. known_extids: Dict[PartialExtID, List[CoreSWHID]] = {} for ((extid_type, extid_version), extids) in new_extids.items(): for extid in self.storage.extid_get_from_extid( extid_type, extids, version=extid_version ): if extid is not None: key = (extid.extid_type, extid_version, extid.extid) known_extids.setdefault(key, []).append(extid.target) return known_extids def resolve_object_from_extids( self, known_extids: Dict[PartialExtID, List[CoreSWHID]], p_info: TPackageInfo, whitelist: Set[Sha1Git], ) -> Optional[CoreSWHID]: """Resolve the revision/release from known ExtIDs and a package info object. If the artifact has already been downloaded, this will return the existing release (or revision) targeting that uncompressed artifact directory. Otherwise, this returns None. Args: known_extids: Dict built from a list of ExtID, with the target as value p_info: Package information whitelist: Any ExtID with target not in this set is filtered out Returns: None or release/revision SWHID """ new_extid = p_info.extid() if new_extid is None: return None extid_targets = set() for extid_target in known_extids.get(new_extid, []): if extid_target.object_id not in whitelist: # There is a known ExtID for this package, but its target is not # in the snapshot. # This can happen for three reasons: # # 1. a loader crashed after writing the ExtID, but before writing # the snapshot # 2. some other loader loaded the same artifact, but produced # a different revision, causing an additional ExtID object # to be written. We will probably find this loader's ExtID # in a future iteration of this loop. # Note that for now, this is impossible, as each loader has a # completely different extid_type, but this is an implementation # detail of each loader. # 3. we took a snapshot, then the package disappeared, # then we took another snapshot, and the package reappeared # # In case of 1, we must actually load the package now, # so let's do it. # TODO: detect when we are in case 3 using release_missing # or revision_missing instead of the snapshot. continue elif extid_target.object_type in (ObjectType.RELEASE, ObjectType.REVISION): extid_targets.add(extid_target) else: # Note that this case should never be reached unless there is a # collision between a revision hash and some non-revision object's # hash, but better safe than sorry. logger.warning( "%s is in the whitelist, but is not a revision/release.", hash_to_hex(extid_target.object_type), ) if extid_targets: # This is a known package version, as we have an extid to reference it. # Let's return one of them. # If there is a release extid, return it. release_extid_targets = { extid_target for extid_target in extid_targets if extid_target.object_type == ObjectType.RELEASE } - if release_extid_targets: - assert len(release_extid_targets) == 1, release_extid_targets - return list(release_extid_targets)[0] + extid_target2 = self.select_extid_target(p_info, release_extid_targets) + if extid_target2: + return extid_target2 # If there is no release extid (ie. if the package was only loaded with # older versions of this loader, which produced revision objects instead # of releases), return a revision extid. assert len(extid_targets) == 1, extid_targets extid_target = list(extid_targets)[0] assert extid_target.object_type == ObjectType.REVISION, extid_targets return extid_target else: # No target found (this is probably a new package version) return None + def select_extid_target( + self, p_info: TPackageInfo, extid_targets: Set[CoreSWHID] + ) -> Optional[CoreSWHID]: + """Given a list of release extid targets, choses one appropriate for the + given package info. + + Package loaders shyould implement this if their ExtIDs may map to multiple + releases, so they can fetch releases from the storage and inspect their fields + to select the right one for this ``p_info``. + """ + if extid_targets: + # The base package loader does not have the domain-specific knowledge + # to select the right release -> crash if there is more than one. + assert len(extid_targets) == 1, extid_targets + return list(extid_targets)[0] + return None + def download_package( self, p_info: TPackageInfo, tmpdir: str ) -> List[Tuple[str, Mapping]]: """Download artifacts for a specific package. All downloads happen in in the tmpdir folder. Default implementation expects the artifacts package info to be about one artifact per package. Note that most implementation have 1 artifact per package. But some implementation have multiple artifacts per package (debian), some have none, the package is the artifact (gnu). Args: artifacts_package_info: Information on the package artifacts to download (url, filename, etc...) tmpdir: Location to retrieve such artifacts Returns: List of (path, computed hashes) """ try: return [download(p_info.url, dest=tmpdir, filename=p_info.filename)] except ContentDecodingError: # package might be erroneously marked as gzip compressed while is is not, # try to download its raw bytes again without attempting to uncompress # the input stream return [ download( p_info.url, dest=tmpdir, filename=p_info.filename, extra_request_headers={"Accept-Encoding": "identity"}, ) ] def uncompress( self, dl_artifacts: List[Tuple[str, Mapping[str, Any]]], dest: str ) -> str: """Uncompress the artifact(s) in the destination folder dest. Optionally, this could need to use the p_info dict for some more information (debian). """ uncompressed_path = os.path.join(dest, "src") for a_path, _ in dl_artifacts: uncompress(a_path, dest=uncompressed_path) return uncompressed_path def extra_branches(self) -> Dict[bytes, Mapping[str, Any]]: """Return an extra dict of branches that are used to update the set of branches. """ return {} def finalize_visit( self, *, snapshot: Optional[Snapshot], visit: OriginVisit, status_visit: str, status_load: str, failed_branches: List[str], errors: Optional[List[str]] = None, ) -> Dict[str, Any]: """Finalize the visit: - flush eventual unflushed data to storage - update origin visit's status - return the task's status """ self.storage.flush() snapshot_id: Optional[bytes] = None if snapshot and snapshot.id: # to prevent the snapshot.id to b"" snapshot_id = snapshot.id assert visit.visit visit_status = OriginVisitStatus( origin=self.url, visit=visit.visit, type=self.visit_type, date=now(), status=status_visit, snapshot=snapshot_id, ) self.storage.origin_visit_status_add([visit_status]) result: Dict[str, Any] = { "status": status_load, } if snapshot_id: result["snapshot_id"] = hash_to_hex(snapshot_id) if failed_branches: logger.warning("%d failed branches", len(failed_branches)) for i, urls in enumerate(islice(failed_branches, 50)): prefix_url = "Failed branches: " if i == 0 else "" logger.warning("%s%s", prefix_url, urls) return result def load(self) -> Dict: """Load for a specific origin the associated contents. 1. Get the list of versions in an origin. 2. Get the snapshot from the previous run of the loader, and filter out versions that were already loaded, if their :term:`extids ` match Then, for each remaining version in the origin 3. Fetch the files for one package version By default, this can be implemented as a simple HTTP request. Loaders with more specific requirements can override this, e.g.: the PyPI loader checks the integrity of the downloaded files; the Debian loader has to download and check several files for one package version. 4. Extract the downloaded files. By default, this would be a universal archive/tarball extraction. Loaders for specific formats can override this method (for instance, the Debian loader uses dpkg-source -x). 5. Convert the extracted directory to a set of Software Heritage objects Using swh.model.from_disk. 6. Extract the metadata from the unpacked directories This would only be applicable for "smart" loaders like npm (parsing the package.json), PyPI (parsing the PKG-INFO file) or Debian (parsing debian/changelog and debian/control). On "minimal-metadata" sources such as the GNU archive, the lister should provide the minimal set of metadata needed to populate the revision/release objects (authors, dates) as an argument to the task. 7. Generate the revision/release objects for the given version. From the data generated at steps 3 and 4. end for each 8. Generate and load the snapshot for the visit Using the revisions/releases collected at step 7., and the branch information from step 2., generate a snapshot and load it into the Software Heritage archive """ status_load = "uneventful" # either: eventful, uneventful, failed status_visit = "full" # see swh.model.model.OriginVisitStatus snapshot = None failed_branches: List[str] = [] # Prepare origin and origin_visit origin = Origin(url=self.url) try: self.storage.origin_add([origin]) visit = list( self.storage.origin_visit_add( [ OriginVisit( origin=self.url, date=self.visit_date, type=self.visit_type, ) ] ) )[0] except Exception as e: logger.exception("Failed to initialize origin_visit for %s", self.url) sentry_sdk.capture_exception(e) return {"status": "failed"} # Get the previous snapshot for this origin. It is then used to see which # of the package's versions are already loaded in the archive. try: last_snapshot = self.last_snapshot() logger.debug("last snapshot: %s", last_snapshot) except Exception as e: logger.exception("Failed to get previous state for %s", self.url) sentry_sdk.capture_exception(e) return self.finalize_visit( snapshot=snapshot, visit=visit, failed_branches=failed_branches, status_visit="failed", status_load="failed", errors=[str(e)], ) load_exceptions: List[Exception] = [] # Get the list of all version names try: versions = self.get_versions() except NotFound as e: return self.finalize_visit( snapshot=snapshot, visit=visit, failed_branches=failed_branches, status_visit="not_found", status_load="failed", errors=[str(e)], ) except Exception as e: return self.finalize_visit( snapshot=snapshot, visit=visit, failed_branches=failed_branches, status_visit="failed", status_load="failed", errors=[str(e)], ) # Get the metadata of each version's package packages_info: List[Tuple[str, TPackageInfo]] = [ (branch_name, p_info) for version in versions for (branch_name, p_info) in self.get_package_info(version) ] # Compute the ExtID of each of these packages known_extids = self._get_known_extids([p_info for (_, p_info) in packages_info]) if last_snapshot is None: last_snapshot_targets: Set[Sha1Git] = set() else: last_snapshot_targets = { branch.target for branch in last_snapshot.branches.values() } new_extids: Set[ExtID] = set() tmp_releases: Dict[str, List[Tuple[str, Sha1Git]]] = { version: [] for version in versions } errors = [] for (branch_name, p_info) in packages_info: logger.debug("package_info: %s", p_info) # Check if the package was already loaded, using its ExtID swhid = self.resolve_object_from_extids( known_extids, p_info, last_snapshot_targets ) if swhid is not None and swhid.object_type == ObjectType.REVISION: # This package was already loaded, but by an older version # of this loader, which produced revisions instead of releases. # Let's fetch the revision's data, and "upgrade" it into a release. (rev,) = self.storage.revision_get([swhid.object_id]) if not rev: logger.error( "Failed to upgrade branch %s from revision to " "release, %s is missing from the storage. " "Falling back to re-loading from the origin.", branch_name, swhid, ) else: rev = None if swhid is None or (swhid.object_type == ObjectType.REVISION and not rev): # No matching revision or release found in the last snapshot, load it. release_id = None try: res = self._load_release(p_info, origin) if res: (release_id, directory_id) = res assert release_id assert directory_id self._load_extrinsic_directory_metadata( p_info, release_id, directory_id ) self.storage.flush() status_load = "eventful" except Exception as e: self.storage.clear_buffers() load_exceptions.append(e) sentry_sdk.capture_exception(e) error = f"Failed to load branch {branch_name} for {self.url}" logger.exception(error) failed_branches.append(branch_name) errors.append(f"{error}: {e}") continue if release_id is None: continue add_extid = True elif swhid.object_type == ObjectType.REVISION: # If 'rev' was None, the previous block would have run. assert rev is not None rel = rev2rel(rev, p_info.version) self.storage.release_add([rel]) logger.debug("Upgraded %s to %s", swhid, rel.swhid()) release_id = rel.id # Create a new extid for this package, so the next run of this loader # will be able to find the new release, and use it (instead of the # old revision) add_extid = True elif swhid.object_type == ObjectType.RELEASE: # This package was already loaded, nothing to do. release_id = swhid.object_id add_extid = False else: assert False, f"Unexpected object type: {swhid}" assert release_id is not None if add_extid: partial_extid = p_info.extid() if partial_extid is not None: (extid_type, extid_version, extid) = partial_extid release_swhid = CoreSWHID( object_type=ObjectType.RELEASE, object_id=release_id ) new_extids.add( ExtID( extid_type=extid_type, extid_version=extid_version, extid=extid, target=release_swhid, ) ) tmp_releases[p_info.version].append((branch_name, release_id)) if load_exceptions: status_visit = "partial" if not tmp_releases: # We could not load any releases; fail completely return self.finalize_visit( snapshot=snapshot, visit=visit, failed_branches=failed_branches, status_visit="failed", status_load="failed", errors=errors, ) try: # Retrieve the default release version (the "latest" one) default_version = self.get_default_version() logger.debug("default version: %s", default_version) # Retrieve extra branches extra_branches = self.extra_branches() logger.debug("extra branches: %s", extra_branches) snapshot = self._load_snapshot( default_version, tmp_releases, extra_branches ) self.storage.flush() except Exception as e: error = f"Failed to build snapshot for origin {self.url}" logger.exception(error) errors.append(f"{error}: {e}") sentry_sdk.capture_exception(e) status_visit = "failed" status_load = "failed" if snapshot: try: metadata_objects = self.build_extrinsic_snapshot_metadata(snapshot.id) self._load_metadata_objects(metadata_objects) except Exception as e: error = f"Failed to load extrinsic snapshot metadata for {self.url}" logger.exception(error) errors.append(f"{error}: {e}") sentry_sdk.capture_exception(e) status_visit = "partial" status_load = "failed" try: metadata_objects = self.build_extrinsic_origin_metadata() self._load_metadata_objects(metadata_objects) except Exception as e: error = f"Failed to load extrinsic origin metadata for {self.url}" logger.exception(error) errors.append(f"{error}: {e}") sentry_sdk.capture_exception(e) status_visit = "partial" status_load = "failed" self._load_extids(new_extids) return self.finalize_visit( snapshot=snapshot, visit=visit, failed_branches=failed_branches, status_visit=status_visit, status_load=status_load, errors=errors, ) def _load_directory( self, dl_artifacts: List[Tuple[str, Mapping[str, Any]]], tmpdir: str ) -> Tuple[str, from_disk.Directory]: uncompressed_path = self.uncompress(dl_artifacts, dest=tmpdir) logger.debug("uncompressed_path: %s", uncompressed_path) directory = from_disk.Directory.from_disk( path=uncompressed_path.encode("utf-8"), max_content_length=self.max_content_size, ) contents, skipped_contents, directories = from_disk.iter_directory(directory) logger.debug("Number of skipped contents: %s", len(skipped_contents)) self.storage.skipped_content_add(skipped_contents) logger.debug("Number of contents: %s", len(contents)) self.storage.content_add(contents) logger.debug("Number of directories: %s", len(directories)) self.storage.directory_add(directories) return (uncompressed_path, directory) def _load_release( self, p_info: TPackageInfo, origin ) -> Optional[Tuple[Sha1Git, Sha1Git]]: """Does all the loading of a release itself: * downloads a package and uncompresses it * loads it from disk * adds contents, directories, and release to self.storage * returns (release_id, directory_id) Raises exception when unable to download or uncompress artifacts """ with tempfile.TemporaryDirectory() as tmpdir: dl_artifacts = self.download_package(p_info, tmpdir) (uncompressed_path, directory) = self._load_directory(dl_artifacts, tmpdir) # FIXME: This should be release. cf. D409 release = self.build_release( p_info, uncompressed_path, directory=directory.hash ) if not release: # Some artifacts are missing intrinsic metadata # skipping those return None metadata = [metadata for (filepath, metadata) in dl_artifacts] assert release.target is not None, release assert release.target_type == ModelObjectType.DIRECTORY, release metadata_target = ExtendedSWHID( object_type=ExtendedObjectType.DIRECTORY, object_id=release.target ) original_artifact_metadata = RawExtrinsicMetadata( target=metadata_target, discovery_date=self.visit_date, authority=SWH_METADATA_AUTHORITY, fetcher=self.get_metadata_fetcher(), format="original-artifacts-json", metadata=json.dumps(metadata).encode(), origin=self.url, release=release.swhid(), ) self._load_metadata_objects([original_artifact_metadata]) logger.debug("Release: %s", release) self.storage.release_add([release]) assert directory.hash return (release.id, directory.hash) def _load_snapshot( self, default_version: str, releases: Dict[str, List[Tuple[str, bytes]]], extra_branches: Dict[bytes, Mapping[str, Any]], ) -> Optional[Snapshot]: """Build snapshot out of the current releases stored and extra branches. Then load it in the storage. """ logger.debug("releases: %s", releases) # Build and load the snapshot branches = {} # type: Dict[bytes, Mapping[str, Any]] for version, branch_name_releases in releases.items(): if version == default_version and len(branch_name_releases) == 1: # only 1 branch (no ambiguity), we can create an alias # branch 'HEAD' branch_name, _ = branch_name_releases[0] # except for some corner case (deposit) if branch_name != "HEAD": branches[b"HEAD"] = { "target_type": "alias", "target": branch_name.encode("utf-8"), } for branch_name, target in branch_name_releases: branches[branch_name.encode("utf-8")] = { "target_type": "release", "target": target, } # Deal with extra-branches for name, branch_target in extra_branches.items(): if name in branches: logger.error("Extra branch '%s' has been ignored", name) else: branches[name] = branch_target snapshot_data = {"branches": branches} logger.debug("snapshot: %s", snapshot_data) snapshot = Snapshot.from_dict(snapshot_data) logger.debug("snapshot: %s", snapshot) self.storage.snapshot_add([snapshot]) return snapshot def get_loader_name(self) -> str: """Returns a fully qualified name of this loader.""" return f"{self.__class__.__module__}.{self.__class__.__name__}" def get_loader_version(self) -> str: """Returns the version of the current loader.""" module_name = self.__class__.__module__ or "" module_name_parts = module_name.split(".") # Iterate rootward through the package hierarchy until we find a parent of this # loader's module with a __version__ attribute. for prefix_size in range(len(module_name_parts), 0, -1): package_name = ".".join(module_name_parts[0:prefix_size]) module = sys.modules[package_name] if hasattr(module, "__version__"): return module.__version__ # type: ignore # If this loader's class has no parent package with a __version__, # it should implement it itself. raise NotImplementedError( f"Could not dynamically find the version of {self.get_loader_name()}." ) def get_metadata_fetcher(self) -> MetadataFetcher: """Returns a MetadataFetcher instance representing this package loader; which is used to for adding provenance information to extracted extrinsic metadata, if any.""" return MetadataFetcher( name=self.get_loader_name(), version=self.get_loader_version(), metadata={}, ) def get_metadata_authority(self) -> MetadataAuthority: """For package loaders that get extrinsic metadata, returns the authority the metadata are coming from. """ raise NotImplementedError("get_metadata_authority") def get_extrinsic_origin_metadata(self) -> List[RawExtrinsicMetadataCore]: """Returns metadata items, used by build_extrinsic_origin_metadata.""" return [] def build_extrinsic_origin_metadata(self) -> List[RawExtrinsicMetadata]: """Builds a list of full RawExtrinsicMetadata objects, using metadata returned by get_extrinsic_origin_metadata.""" metadata_items = self.get_extrinsic_origin_metadata() if not metadata_items: # If this package loader doesn't write metadata, no need to require # an implementation for get_metadata_authority. return [] authority = self.get_metadata_authority() fetcher = self.get_metadata_fetcher() metadata_objects = [] for item in metadata_items: metadata_objects.append( RawExtrinsicMetadata( target=Origin(self.url).swhid(), discovery_date=item.discovery_date or self.visit_date, authority=authority, fetcher=fetcher, format=item.format, metadata=item.metadata, ) ) return metadata_objects def get_extrinsic_snapshot_metadata(self) -> List[RawExtrinsicMetadataCore]: """Returns metadata items, used by build_extrinsic_snapshot_metadata.""" return [] def build_extrinsic_snapshot_metadata( self, snapshot_id: Sha1Git ) -> List[RawExtrinsicMetadata]: """Builds a list of full RawExtrinsicMetadata objects, using metadata returned by get_extrinsic_snapshot_metadata.""" metadata_items = self.get_extrinsic_snapshot_metadata() if not metadata_items: # If this package loader doesn't write metadata, no need to require # an implementation for get_metadata_authority. return [] authority = self.get_metadata_authority() fetcher = self.get_metadata_fetcher() metadata_objects = [] for item in metadata_items: metadata_objects.append( RawExtrinsicMetadata( target=ExtendedSWHID( object_type=ExtendedObjectType.SNAPSHOT, object_id=snapshot_id ), discovery_date=item.discovery_date or self.visit_date, authority=authority, fetcher=fetcher, format=item.format, metadata=item.metadata, origin=self.url, ) ) return metadata_objects def build_extrinsic_directory_metadata( self, p_info: TPackageInfo, release_id: Sha1Git, directory_id: Sha1Git, ) -> List[RawExtrinsicMetadata]: if not p_info.directory_extrinsic_metadata: # If this package loader doesn't write metadata, no need to require # an implementation for get_metadata_authority. return [] authority = self.get_metadata_authority() fetcher = self.get_metadata_fetcher() metadata_objects = [] for item in p_info.directory_extrinsic_metadata: metadata_objects.append( RawExtrinsicMetadata( target=ExtendedSWHID( object_type=ExtendedObjectType.DIRECTORY, object_id=directory_id ), discovery_date=item.discovery_date or self.visit_date, authority=authority, fetcher=fetcher, format=item.format, metadata=item.metadata, origin=self.url, release=CoreSWHID( object_type=ObjectType.RELEASE, object_id=release_id ), ) ) return metadata_objects def _load_extrinsic_directory_metadata( self, p_info: TPackageInfo, release_id: Sha1Git, directory_id: Sha1Git, ) -> None: metadata_objects = self.build_extrinsic_directory_metadata( p_info, release_id, directory_id ) self._load_metadata_objects(metadata_objects) def _load_metadata_objects( self, metadata_objects: List[RawExtrinsicMetadata] ) -> None: if not metadata_objects: # If this package loader doesn't write metadata, no need to require # an implementation for get_metadata_authority. return self._create_authorities(mo.authority for mo in metadata_objects) self._create_fetchers(mo.fetcher for mo in metadata_objects) self.storage.raw_extrinsic_metadata_add(metadata_objects) def _create_authorities(self, authorities: Iterable[MetadataAuthority]) -> None: deduplicated_authorities = { (authority.type, authority.url): authority for authority in authorities } if authorities: self.storage.metadata_authority_add(list(deduplicated_authorities.values())) def _create_fetchers(self, fetchers: Iterable[MetadataFetcher]) -> None: deduplicated_fetchers = { (fetcher.name, fetcher.version): fetcher for fetcher in fetchers } if fetchers: self.storage.metadata_fetcher_add(list(deduplicated_fetchers.values())) def _load_extids(self, extids: Set[ExtID]) -> None: if not extids: return try: self.storage.extid_add(list(extids)) except Exception as e: logger.exception("Failed to load new ExtIDs for %s", self.url) sentry_sdk.capture_exception(e) # No big deal, it just means the next visit will load the same versions # again. def rev2rel(rev: Revision, version: str) -> Release: """Converts a revision to a release.""" message = rev.message if message and not message.endswith(b"\n"): message += b"\n" return Release( name=version.encode(), message=message, target=rev.directory, target_type=ModelObjectType.DIRECTORY, synthetic=rev.synthetic, author=rev.author, date=rev.date, ) diff --git a/swh/loader/package/nixguix/loader.py b/swh/loader/package/nixguix/loader.py index 004e4eb..2497010 100644 --- a/swh/loader/package/nixguix/loader.py +++ b/swh/loader/package/nixguix/loader.py @@ -1,284 +1,303 @@ # Copyright (C) 2020-2021 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 import copy import json import logging import re -from typing import Any, Dict, Iterator, List, Mapping, Optional, Tuple +from typing import Any, Dict, Iterator, List, Mapping, Optional, Set, Tuple import attr from swh.loader.package.loader import ( BasePackageInfo, PackageLoader, PartialExtID, RawExtrinsicMetadataCore, ) from swh.loader.package.utils import EMPTY_AUTHOR, api_info, cached_method from swh.model import hashutil from swh.model.model import ( MetadataAuthority, MetadataAuthorityType, ObjectType, Release, Sha1Git, ) +from swh.model.swhids import CoreSWHID from swh.storage.interface import StorageInterface logger = logging.getLogger(__name__) EXTID_TYPE = "subresource-integrity" """The ExtID is an ASCII string, as defined by https://w3c.github.io/webappsec-subresource-integrity/""" EXTID_VERSION = 0 @attr.s class NixGuixPackageInfo(BasePackageInfo): raw_info = attr.ib(type=Dict[str, Any]) integrity = attr.ib(type=str) """Hash of the archive, formatted as in the Subresource Integrity specification.""" @classmethod def from_metadata( cls, metadata: Dict[str, Any], version: str ) -> "NixGuixPackageInfo": return cls( url=metadata["url"], filename=None, version=version, integrity=metadata["integrity"], raw_info=metadata, ) def extid(self) -> PartialExtID: return (EXTID_TYPE, EXTID_VERSION, self.integrity.encode("ascii")) class NixGuixLoader(PackageLoader[NixGuixPackageInfo]): """Load sources from a sources.json file. This loader is used to load sources used by functional package manager (eg. Nix and Guix). """ visit_type = "nixguix" def __init__( self, storage: StorageInterface, url: str, unsupported_file_extensions: List[str] = [], max_content_size: Optional[int] = None, ): super().__init__(storage=storage, url=url, max_content_size=max_content_size) self.provider_url = url self.unsupported_file_extensions = unsupported_file_extensions # Note: this could be renamed get_artifacts in the PackageLoader # base class. @cached_method def raw_sources(self): return retrieve_sources(self.url) @cached_method def supported_sources(self): raw_sources = self.raw_sources() return clean_sources( parse_sources(raw_sources), self.unsupported_file_extensions ) @cached_method def integrity_by_url(self) -> Dict[str, str]: sources = self.supported_sources() return {s["urls"][0]: s["integrity"] for s in sources["sources"]} def get_versions(self) -> List[str]: """The first mirror of the mirror list is used as branch name in the snapshot. """ return list(self.integrity_by_url().keys()) def get_metadata_authority(self): return MetadataAuthority( type=MetadataAuthorityType.FORGE, url=self.url, metadata={}, ) def get_extrinsic_snapshot_metadata(self): return [ RawExtrinsicMetadataCore( format="nixguix-sources-json", metadata=self.raw_sources(), ), ] # Note: this could be renamed get_artifact_info in the PackageLoader # base class. def get_package_info(self, url) -> Iterator[Tuple[str, NixGuixPackageInfo]]: # TODO: try all mirrors and not only the first one. A source # can be fetched from several urls, called mirrors. We # currently only use the first one, but if the first one # fails, we should try the second one and so on. integrity = self.integrity_by_url()[url] p_info = NixGuixPackageInfo.from_metadata( {"url": url, "integrity": integrity}, version=url ) yield url, p_info + def select_extid_target( + self, p_info: NixGuixPackageInfo, extid_targets: Set[CoreSWHID] + ) -> Optional[CoreSWHID]: + if extid_targets: + # The archive URL is part of the release name. As that URL is not + # intrinsic metadata, it means different releases may be created for + # the same SRI so they have the same extid. + # Therefore, we need to pick the one with the right URL. + releases = self.storage.release_get( + [target.object_id for target in extid_targets] + ) + extid_targets = { + release.swhid() + for release in releases + if release is not None and release.name == p_info.version.encode() + } + return super().select_extid_target(p_info, extid_targets) + def extra_branches(self) -> Dict[bytes, Mapping[str, Any]]: """We add a branch to the snapshot called 'evaluation' pointing to the revision used to generate the sources.json file. This revision is specified in the sources.json file itself. For the nixpkgs origin, this revision is coming from the github.com/nixos/nixpkgs repository. Note this repository is not loaded explicitly. So, this pointer can target a nonexistent revision for a time. However, the github and gnu loaders are supposed to load this revision and should create the revision pointed by this branch. This branch can be used to identify the snapshot associated to a Nix/Guix evaluation. """ # The revision used to create the sources.json file. For Nix, # this revision belongs to the github.com/nixos/nixpkgs # repository revision = self.supported_sources()["revision"] return { b"evaluation": { "target_type": "revision", "target": hashutil.hash_to_bytes(revision), } } def build_release( self, p_info: NixGuixPackageInfo, uncompressed_path: str, directory: Sha1Git ) -> Optional[Release]: return Release( name=p_info.version.encode(), message=None, author=EMPTY_AUTHOR, date=None, target=directory, target_type=ObjectType.DIRECTORY, synthetic=True, ) def retrieve_sources(url: str) -> bytes: """Retrieve sources. Potentially raise NotFound error.""" return api_info(url, allow_redirects=True) def parse_sources(raw_sources: bytes) -> Dict[str, Any]: return json.loads(raw_sources.decode("utf-8")) def make_pattern_unsupported_file_extension(unsupported_file_extensions: List[str],): """Make a regexp pattern for unsupported file extension out of a list of unsupported archive extension list. """ return re.compile( rf".*\.({'|'.join(map(re.escape, unsupported_file_extensions))})$", re.DOTALL ) def clean_sources( sources: Dict[str, Any], unsupported_file_extensions=[] ) -> Dict[str, Any]: """Validate and clean the sources structure. First, ensure all top level keys are present. Then, walk the sources list and remove sources that do not contain required keys. Filter out source entries whose: - required keys are missing - source type is not supported - urls attribute type is not a list - extension is known not to be supported by the loader Raises: ValueError if: - a required top level key is missing - top-level version is not 1 Returns: source Dict cleaned up """ pattern_unsupported_file = make_pattern_unsupported_file_extension( unsupported_file_extensions ) # Required top level keys required_keys = ["version", "revision", "sources"] missing_keys = [] for required_key in required_keys: if required_key not in sources: missing_keys.append(required_key) if missing_keys != []: raise ValueError( f"sources structure invalid, missing: {','.join(missing_keys)}" ) # Only the version 1 is currently supported version = int(sources["version"]) if version != 1: raise ValueError( f"The sources structure version '{sources['version']}' is not supported" ) # If a source doesn't contain required attributes, this source is # skipped but others could still be archived. verified_sources = [] for source in sources["sources"]: valid = True required_keys = ["urls", "integrity", "type"] for required_key in required_keys: if required_key not in source: logger.info( f"Skip source '{source}' because key '{required_key}' is missing", ) valid = False if valid and source["type"] != "url": logger.info( f"Skip source '{source}' because the type {source['type']} " "is not supported", ) valid = False if valid and not isinstance(source["urls"], list): logger.info( f"Skip source {source} because the urls attribute is not a list" ) valid = False if valid and len(source["urls"]) > 0: # Filter out unsupported archives supported_sources: List[str] = [] for source_url in source["urls"]: if pattern_unsupported_file.match(source_url): logger.info(f"Skip unsupported artifact url {source_url}") continue supported_sources.append(source_url) if len(supported_sources) == 0: logger.info( f"Skip source {source} because urls only reference " "unsupported artifacts. Unsupported " f"artifacts so far: {pattern_unsupported_file}" ) continue new_source = copy.deepcopy(source) new_source["urls"] = supported_sources verified_sources.append(new_source) sources["sources"] = verified_sources return sources diff --git a/swh/loader/package/nixguix/tests/data/https_github.com/owner-3_repository-1_revision-1.tgz b/swh/loader/package/nixguix/tests/data/https_github.com/owner-3_repository-1_revision-1.tgz new file mode 120000 index 0000000..ae1450f --- /dev/null +++ b/swh/loader/package/nixguix/tests/data/https_github.com/owner-3_repository-1_revision-1.tgz @@ -0,0 +1 @@ +owner-1_repository-1_revision-1.tgz \ No newline at end of file diff --git a/swh/loader/package/nixguix/tests/data/https_nix-community.github.io/nixpkgs-swh_sources.json b/swh/loader/package/nixguix/tests/data/https_nix-community.github.io/nixpkgs-swh_sources.json index bba29f0..401c0ed 100644 --- a/swh/loader/package/nixguix/tests/data/https_nix-community.github.io/nixpkgs-swh_sources.json +++ b/swh/loader/package/nixguix/tests/data/https_nix-community.github.io/nixpkgs-swh_sources.json @@ -1,16 +1,21 @@ { "sources": [ { "type": "url", "urls": [ "https://github.com/owner-1/repository-1/revision-1.tgz" ], "integrity": "sha256-3vm2Nt+O4zHf3Ovd/qsv1gKTEUwodX9FLxlrQdry0zs=" }, + { + "type": "url", + "urls": [ "https://github.com/owner-3/repository-1/revision-1.tgz" ], + "integrity": "sha256-3vm2Nt+O4zHf3Ovd/qsv1gKTEUwodX9FLxlrQdry0zs=" + }, { "type": "url", "urls": [ "https://example.com/file.txt" ], "integrity": "sha256-Q0copBCnj1b8G1iZw1k0NuYasMcx6QctleltspAgXlM=" } ], "version": "1", "revision": "cc4e04c26672dd74e5fd0fecb78b435fb55368f7" } diff --git a/swh/loader/package/nixguix/tests/test_nixguix.py b/swh/loader/package/nixguix/tests/test_nixguix.py index cea7b76..f9904f6 100644 --- a/swh/loader/package/nixguix/tests/test_nixguix.py +++ b/swh/loader/package/nixguix/tests/test_nixguix.py @@ -1,645 +1,649 @@ # Copyright (C) 2020-2021 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 import json import logging import os from typing import Dict, Optional, Tuple import pytest from swh.loader.package import __version__ from swh.loader.package.archive.loader import ArchiveLoader from swh.loader.package.nixguix.loader import ( NixGuixLoader, clean_sources, make_pattern_unsupported_file_extension, parse_sources, retrieve_sources, ) from swh.loader.package.utils import download from swh.loader.tests import assert_last_visit_matches from swh.loader.tests import check_snapshot as check_snapshot_full from swh.loader.tests import get_stats from swh.model.hashutil import hash_to_bytes from swh.model.model import ( MetadataAuthority, MetadataAuthorityType, MetadataFetcher, ObjectType, Person, RawExtrinsicMetadata, Release, Snapshot, SnapshotBranch, TargetType, ) from swh.model.swhids import ExtendedObjectType, ExtendedSWHID from swh.storage.algos.origin import origin_get_latest_visit_status from swh.storage.algos.snapshot import snapshot_get_all_branches from swh.storage.exc import HashCollision from swh.storage.interface import PagedResult, StorageInterface sources_url = "https://nix-community.github.io/nixpkgs-swh/sources.json" @pytest.fixture def raw_sources(datadir) -> bytes: with open( os.path.join( datadir, "https_nix-community.github.io", "nixpkgs-swh_sources.json" ), "rb", ) as f: return f.read() SNAPSHOT1 = Snapshot( - id=hash_to_bytes("efe5145f85af3fc87f34102d8b8481cd5198f4f8"), + id=hash_to_bytes("fafcfe32016d018bd892114fce211f37a36a092a"), branches={ b"evaluation": SnapshotBranch( target=hash_to_bytes("cc4e04c26672dd74e5fd0fecb78b435fb55368f7"), target_type=TargetType.REVISION, ), b"https://github.com/owner-1/repository-1/revision-1.tgz": SnapshotBranch( target=hash_to_bytes("df7811b9644ed8ef088e2e7add62ed32b0bab15f"), target_type=TargetType.RELEASE, ), + b"https://github.com/owner-3/repository-1/revision-1.tgz": SnapshotBranch( + target=hash_to_bytes("dc7dc10a664396d5c88adc56352904db231bde14"), + target_type=TargetType.RELEASE, + ), }, ) def check_snapshot(snapshot: Snapshot, storage: StorageInterface): # The `evaluation` branch is allowed to be unresolvable. It's possible at current # nixguix visit time, it is not yet visited (the git loader is in charge of its # visit for now). For more details, check the # swh.loader.package.nixguix.NixGuixLoader.extra_branches docstring. check_snapshot_full( snapshot, storage, allowed_empty=[(TargetType.REVISION, b"evaluation")] ) assert isinstance(snapshot, Snapshot) # then ensure the snapshot revisions are structurally as expected revision_ids = [] for name, branch in snapshot.branches.items(): if name == b"evaluation": continue # skipping that particular branch (cf. previous comment) if branch.target_type == TargetType.REVISION: revision_ids.append(branch.target) revisions = storage.revision_get(revision_ids) for rev in revisions: assert rev is not None metadata = rev.metadata assert not metadata def test_retrieve_sources(swh_storage, requests_mock_datadir): j = parse_sources(retrieve_sources(sources_url)) assert "sources" in j.keys() - assert len(j["sources"]) == 2 + assert len(j["sources"]) == 3 def test_nixguix_url_not_found(swh_storage, requests_mock_datadir): """When failing to read from the url, the visit is marked as not_found. Here the sources url does not exist, so requests_mock_datadir returns a 404. Resulting in a NotFound raised within the package loader's main loop. This results in the task with status failed and a visit_status with status "not_found". """ unknown_url = "https://non-existing-url/" loader = NixGuixLoader(swh_storage, unknown_url) # during the retrieval step load_status = loader.load() assert load_status == {"status": "failed"} assert_last_visit_matches( swh_storage, unknown_url, status="not_found", type="nixguix", snapshot=None ) assert len(requests_mock_datadir.request_history) == 1 assert requests_mock_datadir.request_history[0].url == unknown_url def test_nixguix_url_with_decoding_error(swh_storage, requests_mock_datadir): """Other errors during communication with the url, the visit is marked as failed requests_mock_datadir will intercept the requests to sources_url. Since the file exists, returns a 200 with the requested content of the query. As file.txt is no json, fails do decode and raises a JSONDecodeError. In effect failing the visit. """ sources_url = "https://example.com/file.txt" loader = NixGuixLoader(swh_storage, sources_url) load_status = loader.load() assert load_status == {"status": "failed"} assert_last_visit_matches( swh_storage, sources_url, status="failed", type="nixguix", snapshot=None ) assert len(requests_mock_datadir.request_history) == 1 assert requests_mock_datadir.request_history[0].url == sources_url def test_clean_sources_invalid_schema(swh_storage, requests_mock_datadir): sources = {} with pytest.raises(ValueError, match="sources structure invalid, missing: .*"): clean_sources(sources) def test_clean_sources_invalid_version(swh_storage, requests_mock_datadir): for version_ok in [1, "1"]: # Check those versions are fine clean_sources({"version": version_ok, "sources": [], "revision": "my-revision"}) for version_ko in [0, "0", 2, "2"]: # Check version != 1 raise an error with pytest.raises( ValueError, match="sources structure version .* is not supported" ): clean_sources( {"version": version_ko, "sources": [], "revision": "my-revision"} ) def test_clean_sources_invalid_sources(swh_storage, requests_mock_datadir): valid_sources = [ # 1 valid source {"type": "url", "urls": ["my-url.tar.gz"], "integrity": "my-integrity"}, ] sources = { "version": 1, "sources": valid_sources + [ # integrity is missing {"type": "url", "urls": ["my-url.tgz"],}, # urls is not a list {"type": "url", "urls": "my-url.zip", "integrity": "my-integrity"}, # type is not url {"type": "git", "urls": ["my-url.zip"], "integrity": "my-integrity"}, # missing fields which got double-checked nonetheless... {"integrity": "my-integrity"}, ], "revision": "my-revision", } clean = clean_sources(sources) assert len(clean["sources"]) == len(valid_sources) def test_make_pattern_unsupported_file_extension(): unsupported_extensions = ["el", "c", "txt"] supported_extensions = ["Z", "7z"] # for test actual_unsupported_pattern = make_pattern_unsupported_file_extension( unsupported_extensions ) for supported_ext in supported_extensions: assert supported_ext not in unsupported_extensions supported_filepath = f"anything.{supported_ext}" actual_match = actual_unsupported_pattern.match(supported_filepath) assert not actual_match for unsupported_ext in unsupported_extensions: unsupported_filepath = f"something.{unsupported_ext}" actual_match = actual_unsupported_pattern.match(unsupported_filepath) assert actual_match def test_clean_sources_unsupported_artifacts(swh_storage, requests_mock_datadir): unsupported_file_extensions = [ "iso", "whl", "gem", "pom", "msi", "pod", "png", "rock", "ttf", "jar", "c", "el", "rpm", "diff", "patch", ] supported_sources = [ { "type": "url", "urls": [f"https://server.org/my-url.{ext}"], "integrity": "my-integrity", } for ext in [ "known-unknown-but-ok", # this is fine as well with the current approach "zip", "tar.gz", "tgz", "tar.bz2", "tbz", "tbz2", "tar.xz", "tar", "zip", "7z", "Z", ] ] unsupported_sources = [ { "type": "url", "urls": [f"https://server.org/my-url.{ext}"], "integrity": "my-integrity", } for ext in unsupported_file_extensions ] sources = { "version": 1, "sources": supported_sources + unsupported_sources, "revision": "my-revision", } clean = clean_sources(sources, unsupported_file_extensions) assert len(clean["sources"]) == len(supported_sources) def test_loader_one_visit(swh_storage, requests_mock_datadir, raw_sources): loader = NixGuixLoader(swh_storage, sources_url) load_status = loader.load() expected_snapshot_id = SNAPSHOT1.id expected_snapshot_id_hex = expected_snapshot_id.hex() assert load_status == { "status": "eventful", "snapshot_id": expected_snapshot_id_hex, } release_id = SNAPSHOT1.branches[ b"https://github.com/owner-1/repository-1/revision-1.tgz" ].target check_snapshot(SNAPSHOT1, storage=swh_storage) assert swh_storage.release_get([release_id])[0] == Release( id=release_id, name=b"https://github.com/owner-1/repository-1/revision-1.tgz", message=None, target=hash_to_bytes("4de2e07d3742718d928e974b8a4c721b9f7b33bf"), target_type=ObjectType.DIRECTORY, synthetic=True, author=Person.from_fullname(b""), date=None, ) stats = get_stats(swh_storage) assert { "content": 1, "directory": 3, "origin": 1, "origin_visit": 1, - "release": 1, + "release": 2, "revision": 0, "skipped_content": 0, "snapshot": 1, } == stats # The visit is partial because urls pointing to non tarball file # are not handled yet assert_last_visit_matches( swh_storage, sources_url, status="partial", type="nixguix" ) visit_status = origin_get_latest_visit_status(swh_storage, sources_url) snapshot_swhid = ExtendedSWHID( object_type=ExtendedObjectType.SNAPSHOT, object_id=visit_status.snapshot ) metadata_authority = MetadataAuthority( type=MetadataAuthorityType.FORGE, url=sources_url, ) expected_metadata = [ RawExtrinsicMetadata( target=snapshot_swhid, authority=metadata_authority, fetcher=MetadataFetcher( name="swh.loader.package.nixguix.loader.NixGuixLoader", version=__version__, ), discovery_date=loader.visit_date, format="nixguix-sources-json", metadata=raw_sources, origin=sources_url, ) ] assert swh_storage.raw_extrinsic_metadata_get( snapshot_swhid, metadata_authority, ) == PagedResult(next_page_token=None, results=expected_metadata,) def test_uncompress_failure(swh_storage, requests_mock_datadir): """Non tarball files are currently not supported and the uncompress function fails on such kind of files. However, even in this case of failure (because of the url https://example.com/file.txt), a snapshot and a visit has to be created (with a status partial since all files are not archived). """ loader = NixGuixLoader(swh_storage, sources_url) loader_status = loader.load() sources = loader.supported_sources()["sources"] urls = [s["urls"][0] for s in sources] assert "https://example.com/file.txt" in urls assert loader_status["status"] == "eventful" # The visit is partial because urls pointing to non tarball files # are not handled yet assert_last_visit_matches( swh_storage, sources_url, status="partial", type="nixguix" ) def test_loader_incremental(swh_storage, requests_mock_datadir): """Ensure a second visit do not download artifact already downloaded by the previous visit. """ loader = NixGuixLoader(swh_storage, sources_url) load_status = loader.load() loader.load() assert load_status == {"status": "eventful", "snapshot_id": SNAPSHOT1.id.hex()} assert_last_visit_matches( swh_storage, sources_url, status="partial", type="nixguix", snapshot=SNAPSHOT1.id, ) check_snapshot(SNAPSHOT1, storage=swh_storage) urls = [ m.url for m in requests_mock_datadir.request_history if m.url == ("https://github.com/owner-1/repository-1/revision-1.tgz") ] # The artifact # 'https://github.com/owner-1/repository-1/revision-1.tgz' is only # visited one time assert len(urls) == 1 def test_loader_two_visits(swh_storage, requests_mock_datadir_visits): """To ensure there is only one origin, but two visits, two revisions and two snapshots are created. The first visit creates a snapshot containing one tarball. The second visit creates a snapshot containing the same tarball and another tarball. """ loader = NixGuixLoader(swh_storage, sources_url) load_status = loader.load() assert load_status == {"status": "eventful", "snapshot_id": SNAPSHOT1.id.hex()} assert_last_visit_matches( swh_storage, sources_url, status="partial", type="nixguix", snapshot=SNAPSHOT1.id, ) check_snapshot(SNAPSHOT1, storage=swh_storage) stats = get_stats(swh_storage) assert { "content": 1, "directory": 3, "origin": 1, "origin_visit": 1, - "release": 1, + "release": 2, "revision": 0, "skipped_content": 0, "snapshot": 1, } == stats loader = NixGuixLoader(swh_storage, sources_url) load_status = loader.load() expected_snapshot_id_hex = "c1983a0a3f647548e1fb92f30339da6848fe9f7a" expected_snapshot_id = hash_to_bytes(expected_snapshot_id_hex) assert load_status == { "status": "eventful", "snapshot_id": expected_snapshot_id_hex, } assert_last_visit_matches( swh_storage, sources_url, status="partial", type="nixguix", snapshot=expected_snapshot_id, ) # This ensures visits are incremental. Indeed, if we request a # second time an url, because of the requests_mock_datadir_visits # fixture, the file has to end with `_visit1`. expected_snapshot = Snapshot( id=expected_snapshot_id, branches={ b"evaluation": SnapshotBranch( target=hash_to_bytes("602140776b2ce6c9159bcf52ada73a297c063d5e"), target_type=TargetType.REVISION, ), b"https://github.com/owner-1/repository-1/revision-1.tgz": SnapshotBranch( target=hash_to_bytes("df7811b9644ed8ef088e2e7add62ed32b0bab15f"), target_type=TargetType.RELEASE, ), b"https://github.com/owner-2/repository-1/revision-1.tgz": SnapshotBranch( target=hash_to_bytes("5cc0115cd643902b837cb6cfbc9f5865bc5a7cb2"), target_type=TargetType.RELEASE, ), }, ) check_snapshot(expected_snapshot, storage=swh_storage) stats = get_stats(swh_storage) assert { "content": 2, "directory": 5, "origin": 1, "origin_visit": 2, - "release": 2, + "release": 3, "revision": 0, "skipped_content": 0, "snapshot": 2, } == stats def test_evaluation_branch(swh_storage, requests_mock_datadir): loader = NixGuixLoader(swh_storage, sources_url) res = loader.load() assert res["status"] == "eventful" assert_last_visit_matches( swh_storage, sources_url, status="partial", type="nixguix", snapshot=SNAPSHOT1.id, ) check_snapshot(SNAPSHOT1, storage=swh_storage) def test_eoferror(swh_storage, requests_mock_datadir): """Load a truncated archive which is invalid to make the uncompress function raising the exception EOFError. We then check if a snapshot is created, meaning this error is well managed. """ sources = ( "https://nix-community.github.io/nixpkgs-swh/sources-EOFError.json" # noqa ) loader = NixGuixLoader(swh_storage, sources) loader.load() expected_snapshot = Snapshot( id=hash_to_bytes("4257fa2350168c6bfec726a06452ea27a2c0cb33"), branches={ b"evaluation": SnapshotBranch( target=hash_to_bytes("cc4e04c26672dd74e5fd0fecb78b435fb55368f7"), target_type=TargetType.REVISION, ), }, ) check_snapshot(expected_snapshot, storage=swh_storage) def fake_download( url: str, dest: str, hashes: Dict = {}, filename: Optional[str] = None, auth: Optional[Tuple[str, str]] = None, ) -> Tuple[str, Dict]: """Fake download which raises HashCollision (for the sake of test simpliciy, let's accept that makes sense) For tests purpose only. """ if url == "https://example.com/file.txt": # instead of failing because it's a file not dealt with by the nix guix # loader, make it raise a hash collision raise HashCollision("sha1", "f92d74e3874587aaf443d1db961d4e26dde13e9c", []) return download(url, dest, hashes, filename, auth) def test_raise_exception(swh_storage, requests_mock_datadir, mocker): mock_download = mocker.patch("swh.loader.package.loader.download") mock_download.side_effect = fake_download loader = NixGuixLoader(swh_storage, sources_url) res = loader.load() assert res == { "status": "eventful", "snapshot_id": SNAPSHOT1.id.hex(), } # The visit is partial because some artifact downloads failed assert_last_visit_matches( swh_storage, sources_url, status="partial", type="nixguix", snapshot=SNAPSHOT1.id, ) check_snapshot(SNAPSHOT1, storage=swh_storage) - assert len(mock_download.mock_calls) == 2 + assert len(mock_download.mock_calls) == 3 def test_load_nixguix_one_common_artifact_from_other_loader( swh_storage, datadir, requests_mock_datadir_visits, caplog ): """Misformatted revision should be caught and logged, then loading continues """ caplog.set_level(logging.ERROR, "swh.loader.package.nixguix.loader") # 1. first ingest with for example the archive loader gnu_url = "https://ftp.gnu.org/gnu/8sync/" release = "0.1.0" artifact_url = f"https://ftp.gnu.org/gnu/8sync/8sync-{release}.tar.gz" gnu_artifacts = [ { "time": 944729610, "url": artifact_url, "length": 221837, "filename": f"8sync-{release}.tar.gz", "version": release, } ] archive_loader = ArchiveLoader(swh_storage, url=gnu_url, artifacts=gnu_artifacts) actual_load_status = archive_loader.load() expected_snapshot_id = "9efecc835e8f99254934f256b5301b94f348fd17" assert actual_load_status["status"] == "eventful" assert actual_load_status["snapshot_id"] == expected_snapshot_id # noqa assert_last_visit_matches( archive_loader.storage, gnu_url, status="full", type="tar", snapshot=hash_to_bytes(expected_snapshot_id), ) # 2. Then ingest with the nixguix loader which lists the same artifact within its # sources.json # ensure test setup is ok data_sources = os.path.join( datadir, "https_nix-community.github.io", "nixpkgs-swh_sources_special.json" ) all_sources = json.loads(open(data_sources).read()) found = False for source in all_sources["sources"]: if source["urls"][0] == artifact_url: found = True assert ( found is True ), f"test setup error: {artifact_url} must be in {data_sources}" # first visit with a snapshot, ok sources_url = "https://nix-community.github.io/nixpkgs-swh/sources_special.json" loader = NixGuixLoader(swh_storage, sources_url) actual_load_status2 = loader.load() assert actual_load_status2["status"] == "eventful" snapshot_id = actual_load_status2["snapshot_id"] assert_last_visit_matches( swh_storage, sources_url, status="full", type="nixguix", snapshot=hash_to_bytes(snapshot_id), ) snapshot = snapshot_get_all_branches(swh_storage, hash_to_bytes(snapshot_id)) assert snapshot