diff --git a/swh/loader/core/loader.py b/swh/loader/core/loader.py index 5c540e4..46787c6 100644 --- a/swh/loader/core/loader.py +++ b/swh/loader/core/loader.py @@ -1,433 +1,519 @@ # Copyright (C) 2015-2022 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 import logging import os -from typing import Any, Dict, Iterable, Optional +from typing import Any, Dict, Iterable, List, Optional + +import sentry_sdk from swh.core.config import load_from_envvar +from swh.loader.core.metadata_fetchers import CredentialsType, get_fetchers_for_lister from swh.loader.exception import NotFound from swh.model.model import ( BaseContent, Content, Directory, Origin, OriginVisit, OriginVisitStatus, + RawExtrinsicMetadata, Release, Revision, Sha1Git, SkippedContent, Snapshot, ) from swh.storage import get_storage from swh.storage.interface import StorageInterface from swh.storage.utils import now DEFAULT_CONFIG: Dict[str, Any] = { "max_content_size": 100 * 1024 * 1024, } class BaseLoader: """Base class for (D)VCS loaders (e.g Svn, Git, Mercurial, ...) or PackageLoader (e.g PyPI, Npm, CRAN, ...) A loader retrieves origin information (git/mercurial/svn repositories, pypi/npm/... package artifacts), ingests the contents/directories/revisions/releases/snapshot read from those artifacts and send them to the archive through the storage backend. The main entry point for the loader is the :func:`load` function. 2 static methods (:func:`from_config`, :func:`from_configfile`) centralizes and eases the loader instantiation from either configuration dict or configuration file. Some class examples: - :class:`SvnLoader` - :class:`GitLoader` - :class:`PyPILoader` - :class:`NpmLoader` + Args: + lister_name: Name of the lister which triggered this load. + If provided, the loader will try to use the forge's API to retrieve extrinsic + metadata + lister_instance_name: Name of the lister instance which triggered this load. + Must be None iff lister_name is, but it may be the empty string for listers + with a single instance. """ visit_type: str origin: Origin loaded_snapshot_id: Optional[Sha1Git] def __init__( self, storage: StorageInterface, origin_url: str, logging_class: Optional[str] = None, save_data_path: Optional[str] = None, max_content_size: Optional[int] = None, + lister_name: Optional[str] = None, + lister_instance_name: Optional[str] = None, + metadata_fetcher_credentials: CredentialsType = None, ): - super().__init__() + if lister_name == "": + raise ValueError("lister_name must not be the empty string") + if lister_name is None and lister_instance_name is not None: + raise ValueError( + f"lister_name is None but lister_instance_name is {lister_instance_name!r}" + ) + if lister_name is not None and lister_instance_name is None: + raise ValueError( + f"lister_instance_name is None but lister_name is {lister_name!r}" + ) + self.storage = storage self.origin = Origin(url=origin_url) self.max_content_size = int(max_content_size) if max_content_size else None + self.lister_name = lister_name + self.lister_instance_name = lister_instance_name + self.metadata_fetcher_credentials = metadata_fetcher_credentials or {} if logging_class is None: logging_class = "%s.%s" % ( self.__class__.__module__, self.__class__.__name__, ) self.log = logging.getLogger(logging_class) _log = logging.getLogger("requests.packages.urllib3.connectionpool") _log.setLevel(logging.WARN) # possibly overridden in self.prepare method self.visit_date = datetime.datetime.now(tz=datetime.timezone.utc) self.loaded_snapshot_id = None if save_data_path: path = save_data_path os.stat(path) if not os.access(path, os.R_OK | os.W_OK): raise PermissionError("Permission denied: %r" % path) self.save_data_path = save_data_path @classmethod def from_config(cls, storage: Dict[str, Any], **config: Any): """Instantiate a loader from a configuration dict. This is basically a backwards-compatibility shim for the CLI. Args: storage: instantiation config for the storage config: the configuration dict for the loader, with the following keys: - credentials (optional): credentials list for the scheduler - any other kwargs passed to the loader. Returns: the instantiated loader """ # Drop the legacy config keys which aren't used for this generation of loader. for legacy_key in ("storage", "celery"): config.pop(legacy_key, None) # Instantiate the storage storage_instance = get_storage(**storage) return cls(storage=storage_instance, **config) @classmethod def from_configfile(cls, **kwargs: Any): """Instantiate a loader from the configuration loaded from the SWH_CONFIG_FILENAME envvar, with potential extra keyword arguments if their value is not None. Args: kwargs: kwargs passed to the loader instantiation """ config = dict(load_from_envvar(DEFAULT_CONFIG)) config.update({k: v for k, v in kwargs.items() if v is not None}) return cls.from_config(**config) def save_data(self) -> None: """Save the data associated to the current load""" raise NotImplementedError def get_save_data_path(self) -> str: """The path to which we archive the loader's raw data""" if not hasattr(self, "__save_data_path"): year = str(self.visit_date.year) assert self.origin url = self.origin.url.encode("utf-8") origin_url_hash = hashlib.sha1(url).hexdigest() path = "%s/sha1:%s/%s/%s" % ( self.save_data_path, origin_url_hash[0:2], origin_url_hash, year, ) os.makedirs(path, exist_ok=True) self.__save_data_path = path return self.__save_data_path def flush(self) -> None: """Flush any potential buffered data not sent to swh-storage.""" self.storage.flush() def cleanup(self) -> None: """Last step executed by the loader.""" raise NotImplementedError def _store_origin_visit(self) -> None: """Store origin and visit references. Sets the self.visit references.""" assert self.origin self.storage.origin_add([self.origin]) assert isinstance(self.visit_type, str) self.visit = list( self.storage.origin_visit_add( [ OriginVisit( origin=self.origin.url, date=self.visit_date, type=self.visit_type, ) ] ) )[0] def prepare(self) -> None: """Second step executed by the loader to prepare some state needed by the loader. Raises NotFound exception if the origin to ingest is not found. """ raise NotImplementedError def get_origin(self) -> Origin: """Get the origin that is currently being loaded. self.origin should be set in :func:`prepare_origin` Returns: dict: an origin ready to be sent to storage by :func:`origin_add`. """ assert self.origin return self.origin def fetch_data(self) -> bool: """Fetch the data from the source the loader is currently loading (ex: git/hg/svn/... repository). Returns: a value that is interpreted as a boolean. If True, fetch_data needs to be called again to complete loading. """ raise NotImplementedError def store_data(self): """Store fetched data in the database. Should call the :func:`maybe_load_xyz` methods, which handle the bundles sent to storage, rather than send directly. """ raise NotImplementedError def load_status(self) -> Dict[str, str]: """Detailed loading status. Defaults to logging an eventful load. Returns: a dictionary that is eventually passed back as the task's result to the scheduler, allowing tuning of the task recurrence mechanism. """ return { "status": "eventful", } def post_load(self, success: bool = True) -> None: """Permit the loader to do some additional actions according to status after the loading is done. The flag success indicates the loading's status. Defaults to doing nothing. This is up to the implementer of this method to make sure this does not break. Args: success (bool): the success status of the loading """ pass def visit_status(self) -> str: """Detailed visit status. Defaults to logging a full visit. """ return "full" def pre_cleanup(self) -> None: """As a first step, will try and check for dangling data to cleanup. This should do its best to avoid raising issues. """ pass def load(self) -> Dict[str, str]: r"""Loading logic for the loader to follow: - Store the actual ``origin_visit`` to storage - Call :meth:`prepare` to prepare any eventual state - Call :meth:`get_origin` to get the origin we work with and store - while True: - Call :meth:`fetch_data` to fetch the data to store - Call :meth:`store_data` to store the data - Call :meth:`cleanup` to clean up any eventual state put in place in :meth:`prepare` method. """ try: self.pre_cleanup() except Exception: msg = "Cleaning up dangling data failed! Continue loading." self.log.warning(msg) self._store_origin_visit() assert ( self.visit.visit ), "The method `_store_origin_visit` should set the visit (OriginVisit)" self.log.info( "Load origin '%s' with type '%s'", self.origin.url, self.visit.type ) + try: + metadata = self.build_extrinsic_origin_metadata() + self.load_metadata_objects(metadata) + except Exception as e: + sentry_sdk.capture_exception(e) + # Do not fail the whole task if this is the only failure + self.log.exception( + "Failure while loading extrinsic origin metadata.", + extra={ + "swh_task_args": [], + "swh_task_kwargs": { + "origin": self.origin.url, + "lister_name": self.lister_name, + "lister_instance_name": self.lister_instance_name, + }, + }, + ) + try: self.prepare() while True: more_data_to_fetch = self.fetch_data() self.store_data() if not more_data_to_fetch: break visit_status = OriginVisitStatus( origin=self.origin.url, visit=self.visit.visit, type=self.visit_type, date=now(), status=self.visit_status(), snapshot=self.loaded_snapshot_id, ) self.storage.origin_visit_status_add([visit_status]) self.post_load() except Exception as e: if isinstance(e, NotFound): status = "not_found" task_status = "uneventful" else: status = "partial" if self.loaded_snapshot_id else "failed" task_status = "failed" self.log.exception( "Loading failure, updating to `%s` status", status, extra={ "swh_task_args": [], - "swh_task_kwargs": {"origin": self.origin.url}, + "swh_task_kwargs": { + "origin": self.origin.url, + "lister_name": self.lister_name, + "lister_instance_name": self.lister_instance_name, + }, }, ) visit_status = OriginVisitStatus( origin=self.origin.url, visit=self.visit.visit, type=self.visit_type, date=now(), status=status, snapshot=self.loaded_snapshot_id, ) self.storage.origin_visit_status_add([visit_status]) self.post_load(success=False) return {"status": task_status} finally: self.flush() self.cleanup() return self.load_status() + def load_metadata_objects( + self, metadata_objects: List[RawExtrinsicMetadata] + ) -> None: + if not metadata_objects: + return + + authorities = {mo.authority for mo in metadata_objects} + self.storage.metadata_authority_add(list(authorities)) + + fetchers = {mo.fetcher for mo in metadata_objects} + self.storage.metadata_fetcher_add(list(fetchers)) + + self.storage.raw_extrinsic_metadata_add(metadata_objects) + + def build_extrinsic_origin_metadata(self) -> List[RawExtrinsicMetadata]: + """Builds a list of full RawExtrinsicMetadata objects, using + a metadata fetcher returned by :func:`get_fetcher_classes`.""" + if self.lister_name is None: + self.log.debug("lister_not provided, skipping extrinsic origin metadata") + return [] + + assert ( + self.lister_instance_name is not None + ), "lister_instance_name is None, but lister_name is not" + + metadata = [] + for cls in get_fetchers_for_lister(self.lister_name): + metadata_fetcher = cls( + origin=self.origin, + lister_name=self.lister_name, + lister_instance_name=self.lister_instance_name, + credentials=self.metadata_fetcher_credentials, + ) + metadata.extend(metadata_fetcher.get_origin_metadata()) + + return metadata + class DVCSLoader(BaseLoader): """This base class is a pattern for dvcs loaders (e.g. git, mercurial). Those loaders are able to load all the data in one go. For example, the loader defined in swh-loader-git :class:`BulkUpdater`. For other loaders (stateful one, (e.g :class:`SWHSvnLoader`), inherit directly from :class:`BaseLoader`. """ def cleanup(self) -> None: """Clean up an eventual state installed for computations.""" pass def has_contents(self) -> bool: """Checks whether we need to load contents""" return True def get_contents(self) -> Iterable[BaseContent]: """Get the contents that need to be loaded""" raise NotImplementedError def has_directories(self) -> bool: """Checks whether we need to load directories""" return True def get_directories(self) -> Iterable[Directory]: """Get the directories that need to be loaded""" raise NotImplementedError def has_revisions(self) -> bool: """Checks whether we need to load revisions""" return True def get_revisions(self) -> Iterable[Revision]: """Get the revisions that need to be loaded""" raise NotImplementedError def has_releases(self) -> bool: """Checks whether we need to load releases""" return True def get_releases(self) -> Iterable[Release]: """Get the releases that need to be loaded""" raise NotImplementedError def get_snapshot(self) -> Snapshot: """Get the snapshot that needs to be loaded""" raise NotImplementedError def eventful(self) -> bool: """Whether the load was eventful""" raise NotImplementedError def store_data(self) -> None: assert self.origin if self.save_data_path: self.save_data() if self.has_contents(): for obj in self.get_contents(): if isinstance(obj, Content): self.storage.content_add([obj]) elif isinstance(obj, SkippedContent): self.storage.skipped_content_add([obj]) else: raise TypeError(f"Unexpected content type: {obj}") if self.has_directories(): for directory in self.get_directories(): self.storage.directory_add([directory]) if self.has_revisions(): for revision in self.get_revisions(): self.storage.revision_add([revision]) if self.has_releases(): for release in self.get_releases(): self.storage.release_add([release]) snapshot = self.get_snapshot() self.storage.snapshot_add([snapshot]) self.flush() self.loaded_snapshot_id = snapshot.id diff --git a/swh/loader/core/metadata_fetchers.py b/swh/loader/core/metadata_fetchers.py new file mode 100644 index 0000000..88a625c --- /dev/null +++ b/swh/loader/core/metadata_fetchers.py @@ -0,0 +1,47 @@ +# Copyright (C) 2022 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 functools +from typing import Dict, List, Optional, Set, Type + +import pkg_resources +from typing_extensions import Protocol, runtime_checkable + +from swh.model.model import Origin, RawExtrinsicMetadata + +CredentialsType = Optional[Dict[str, Dict[str, List[Dict[str, str]]]]] + + +@runtime_checkable +class MetadataFetcherProtocol(Protocol): + """Interface provided by :class:`swh.loader.metadata.base.BaseMetadataFetcher` + to loaders, via setuptools entrypoints.""" + + SUPPORTED_LISTERS: Set[str] + + def __init__( + self, + origin: Origin, + credentials: CredentialsType, + lister_name: str, + lister_instance_name: str, + ): + ... + + def get_origin_metadata(self) -> List[RawExtrinsicMetadata]: + ... + + +@functools.lru_cache() +def _fetchers() -> List[Type[MetadataFetcherProtocol]]: + classes = [] + for entry_point in pkg_resources.iter_entry_points("swh.loader.metadata"): + classes.append(entry_point.load()) + + return classes + + +def get_fetchers_for_lister(lister_name: str) -> List[Type[MetadataFetcherProtocol]]: + return [cls for cls in _fetchers() if lister_name in cls.SUPPORTED_LISTERS] diff --git a/swh/loader/core/tests/test_loader.py b/swh/loader/core/tests/test_loader.py index 0cc9454..fa845ec 100644 --- a/swh/loader/core/tests/test_loader.py +++ b/swh/loader/core/tests/test_loader.py @@ -1,250 +1,307 @@ # Copyright (C) 2018-2021 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 import logging +from unittest.mock import MagicMock + +import pytest from swh.loader.core.loader import BaseLoader, DVCSLoader from swh.loader.exception import NotFound from swh.loader.tests import assert_last_visit_matches from swh.model.hashutil import hash_to_bytes from swh.model.model import ( MetadataAuthority, MetadataAuthorityType, MetadataFetcher, Origin, RawExtrinsicMetadata, Snapshot, ) +import swh.storage.exc ORIGIN = Origin(url="some-url") METADATA_AUTHORITY = MetadataAuthority( type=MetadataAuthorityType.FORGE, url="http://example.org/" ) REMD = RawExtrinsicMetadata( target=ORIGIN.swhid(), discovery_date=datetime.datetime.now(tz=datetime.timezone.utc), authority=METADATA_AUTHORITY, fetcher=MetadataFetcher( name="test fetcher", version="0.0.1", ), format="test-format", metadata=b'{"foo": "bar"}', ) class DummyLoader: """Base Loader to overload and simplify the base class (technical: to avoid repetition in other *Loader classes)""" visit_type = "git" def __init__(self, storage, *args, **kwargs): super().__init__(storage, ORIGIN.url, *args, **kwargs) def cleanup(self): pass def prepare(self, *args, **kwargs): pass def fetch_data(self): pass def get_snapshot_id(self): return None class DummyDVCSLoader(DummyLoader, DVCSLoader): """DVCS Loader that does nothing in regards to DAG objects.""" def get_contents(self): return [] def get_directories(self): return [] def get_revisions(self): return [] def get_releases(self): return [] def get_snapshot(self): return Snapshot(branches={}) def eventful(self): return False class DummyBaseLoader(DummyLoader, BaseLoader): """Buffered loader will send new data when threshold is reached""" def store_data(self): pass +class DummyMetadataFetcher: + SUPPORTED_LISTERS = {"fake-lister"} + + def __init__(self, origin, credentials, lister_name, lister_instance_name): + pass + + def get_origin_metadata(self): + return [REMD] + + def test_base_loader(swh_storage): loader = DummyBaseLoader(swh_storage) result = loader.load() assert result == {"status": "eventful"} def test_base_loader_with_config(swh_storage): loader = DummyBaseLoader(swh_storage, "logger-name") result = loader.load() assert result == {"status": "eventful"} +def test_base_loader_with_known_lister_name(swh_storage, mocker): + fetcher_cls = MagicMock(wraps=DummyMetadataFetcher) + fetcher_cls.SUPPORTED_LISTERS = DummyMetadataFetcher.SUPPORTED_LISTERS + mocker.patch( + "swh.loader.core.metadata_fetchers._fetchers", return_value=[fetcher_cls] + ) + + loader = DummyBaseLoader( + swh_storage, lister_name="fake-lister", lister_instance_name="" + ) + result = loader.load() + assert result == {"status": "eventful"} + + fetcher_cls.assert_called_once() + fetcher_cls.assert_called_once_with( + origin=ORIGIN, + credentials={}, + lister_name="fake-lister", + lister_instance_name="", + ) + assert swh_storage.raw_extrinsic_metadata_get( + ORIGIN.swhid(), METADATA_AUTHORITY + ).results == [REMD] + + +def test_base_loader_with_unknown_lister_name(swh_storage, mocker): + fetcher_cls = MagicMock(wraps=DummyMetadataFetcher) + fetcher_cls.SUPPORTED_LISTERS = DummyMetadataFetcher.SUPPORTED_LISTERS + mocker.patch( + "swh.loader.core.metadata_fetchers._fetchers", return_value=[fetcher_cls] + ) + + loader = DummyBaseLoader( + swh_storage, lister_name="other-lister", lister_instance_name="" + ) + result = loader.load() + assert result == {"status": "eventful"} + + fetcher_cls.assert_not_called() + with pytest.raises(swh.storage.exc.StorageArgumentException): + swh_storage.raw_extrinsic_metadata_get(ORIGIN.swhid(), METADATA_AUTHORITY) + + def test_dvcs_loader(swh_storage): loader = DummyDVCSLoader(swh_storage) result = loader.load() assert result == {"status": "eventful"} def test_dvcs_loader_with_config(swh_storage): loader = DummyDVCSLoader(swh_storage, "another-logger") result = loader.load() assert result == {"status": "eventful"} def test_loader_logger_default_name(swh_storage): loader = DummyBaseLoader(swh_storage) assert isinstance(loader.log, logging.Logger) assert loader.log.name == "swh.loader.core.tests.test_loader.DummyBaseLoader" loader = DummyDVCSLoader(swh_storage) assert isinstance(loader.log, logging.Logger) assert loader.log.name == "swh.loader.core.tests.test_loader.DummyDVCSLoader" def test_loader_logger_with_name(swh_storage): loader = DummyBaseLoader(swh_storage, "some.logger.name") assert isinstance(loader.log, logging.Logger) assert loader.log.name == "some.logger.name" def test_loader_save_data_path(swh_storage, tmp_path): loader = DummyBaseLoader(swh_storage, "some.logger.name.1", save_data_path=tmp_path) url = "http://bitbucket.org/something" loader.origin = Origin(url=url) loader.visit_date = datetime.datetime(year=2019, month=10, day=1) hash_url = hashlib.sha1(url.encode("utf-8")).hexdigest() expected_save_path = "%s/sha1:%s/%s/2019" % (str(tmp_path), hash_url[0:2], hash_url) save_path = loader.get_save_data_path() assert save_path == expected_save_path def _check_load_failure(caplog, loader, exc_class, exc_text, status="partial"): """Check whether a failed load properly logged its exception, and that the snapshot didn't get referenced in storage""" assert isinstance(loader, DVCSLoader) # was implicit so far for record in caplog.records: if record.levelname != "ERROR": continue assert "Loading failure" in record.message assert record.exc_info exc = record.exc_info[1] assert isinstance(exc, exc_class) assert exc_text in exc.args[0] # Check that the get_snapshot operation would have succeeded assert loader.get_snapshot() is not None # And confirm that the visit doesn't reference a snapshot visit = assert_last_visit_matches(loader.storage, ORIGIN.url, status) if status != "partial": assert visit.snapshot is None # But that the snapshot didn't get loaded assert loader.loaded_snapshot_id is None class DummyDVCSLoaderExc(DummyDVCSLoader): """A loader which raises an exception when loading some contents""" def get_contents(self): raise RuntimeError("Failed to get contents!") def test_dvcs_loader_exc_partial_visit(swh_storage, caplog): logger_name = "dvcsloaderexc" caplog.set_level(logging.ERROR, logger=logger_name) loader = DummyDVCSLoaderExc(swh_storage, logging_class=logger_name) # fake the loading ending up in a snapshot loader.loaded_snapshot_id = hash_to_bytes( "9e4dd2b40d1b46b70917c0949aa2195c823a648e" ) result = loader.load() # loading failed assert result == {"status": "failed"} # still resulted in a partial visit with a snapshot (somehow) _check_load_failure( caplog, loader, RuntimeError, "Failed to get contents!", ) class BrokenStorageProxy: def __init__(self, storage): self.storage = storage def __getattr__(self, attr): return getattr(self.storage, attr) def snapshot_add(self, snapshots): raise RuntimeError("Failed to add snapshot!") class DummyDVCSLoaderStorageExc(DummyDVCSLoader): """A loader which raises an exception when loading some contents""" def __init__(self, *args, **kwargs): super().__init__(*args, **kwargs) self.storage = BrokenStorageProxy(self.storage) def test_dvcs_loader_storage_exc_failed_visit(swh_storage, caplog): logger_name = "dvcsloaderexc" caplog.set_level(logging.ERROR, logger=logger_name) loader = DummyDVCSLoaderStorageExc(swh_storage, logging_class=logger_name) result = loader.load() assert result == {"status": "failed"} _check_load_failure( caplog, loader, RuntimeError, "Failed to add snapshot!", status="failed" ) class DummyDVCSLoaderNotFound(DummyDVCSLoader, BaseLoader): """A loader which raises a not_found exception during the prepare method call""" def prepare(*args, **kwargs): raise NotFound("Unknown origin!") def load_status(self): return { "status": "uneventful", } def test_loader_not_found(swh_storage, caplog): loader = DummyDVCSLoaderNotFound(swh_storage) result = loader.load() assert result == {"status": "uneventful"} _check_load_failure(caplog, loader, NotFound, "Unknown origin!", status="not_found") diff --git a/swh/loader/package/loader.py b/swh/loader/package/loader.py index e63329e..158686d 100644 --- a/swh/loader/package/loader.py +++ b/swh/loader/package/loader.py @@ -1,1103 +1,1075 @@ # 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]): def __init__(self, storage: StorageInterface, url: str, **kwargs: Any): """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, origin_url=url, **kwargs) 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.origin.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 } # Exclude missing targets missing_releases = { CoreSWHID(object_type=ObjectType.RELEASE, object_id=id_) for id_ in self.storage.release_missing( [swhid.object_id for swhid in release_extid_targets] ) } if missing_releases: logger.error( "Found ExtIDs pointing to missing releases: %s", missing_releases ) release_extid_targets -= missing_releases 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 when possible. revision_extid_targets = { extid_target for extid_target in extid_targets if extid_target.object_type == ObjectType.REVISION } if revision_extid_targets: assert len(extid_targets) == 1, extid_targets extid_target = list(extid_targets)[0] return extid_target # 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.origin.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.origin.url) try: self.storage.origin_add([origin]) visit = list( self.storage.origin_visit_add( [ OriginVisit( origin=self.origin.url, date=self.visit_date, type=self.visit_type, ) ] ) )[0] except Exception as e: logger.exception( "Failed to initialize origin_visit for %s", self.origin.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.origin.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.origin.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.origin.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) + self.load_metadata_objects(metadata_objects) except Exception as e: error = ( f"Failed to load extrinsic snapshot metadata for {self.origin.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) + self.load_metadata_objects(metadata_objects) except Exception as e: error = f"Failed to load extrinsic origin metadata for {self.origin.url}" logger.exception(error) errors.append(f"{error}: {e}") sentry_sdk.capture_exception(e) status_visit = "partial" status_load = "failed" if 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.origin.url, release=release.swhid(), ) - self._load_metadata_objects([original_artifact_metadata]) + 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=self.origin.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.origin.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.origin.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())) + self.load_metadata_objects(metadata_objects) 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.origin.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, )