diff --git a/swh/loader/package/deposit/loader.py b/swh/loader/package/deposit/loader.py index 9901d48..78bdc97 100644 --- a/swh/loader/package/deposit/loader.py +++ b/swh/loader/package/deposit/loader.py @@ -1,351 +1,351 @@ # Copyright (C) 2019-2020 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import datetime from datetime import timezone import json import logging from typing import Any, Dict, Iterator, List, Mapping, Optional, Sequence, Tuple, Union import attr import requests from swh.loader.package.loader import ( BasePackageInfo, PackageLoader, RawExtrinsicMetadataCore, ) from swh.loader.package.utils import cached_method, download from swh.model.hashutil import hash_to_bytes, hash_to_hex from swh.model.model import ( MetadataAuthority, MetadataAuthorityType, MetadataFetcher, Person, Revision, RevisionType, Sha1Git, TimestampWithTimezone, ) from swh.storage.algos.snapshot import snapshot_get_all_branches logger = logging.getLogger(__name__) def now() -> datetime.datetime: return datetime.datetime.now(tz=timezone.utc) @attr.s class DepositPackageInfo(BasePackageInfo): filename = attr.ib(type=str) # instead of Optional[str] raw_info = attr.ib(type=Dict[str, Any]) author_date = attr.ib(type=datetime.datetime) """codemeta:dateCreated if any, deposit completed_date otherwise""" commit_date = attr.ib(type=datetime.datetime) """codemeta:datePublished if any, deposit completed_date otherwise""" client = attr.ib(type=str) id = attr.ib(type=int) """Internal ID of the deposit in the deposit DB""" collection = attr.ib(type=str) """The collection in the deposit; see SWORD specification.""" author = attr.ib(type=Person) committer = attr.ib(type=Person) revision_parents = attr.ib(type=Tuple[Sha1Git, ...]) """Revisions created from previous deposits, that will be used as parents of the revision created for this deposit.""" @classmethod def from_metadata( cls, metadata: Dict[str, Any], url: str, filename: str ) -> "DepositPackageInfo": # Note: # `date` and `committer_date` are always transmitted by the deposit read api # which computes itself the values. The loader needs to use those to create the # revision. all_metadata_raw: List[str] = metadata["metadata_raw"] raw_info = { "origin": metadata["origin"], "origin_metadata": { "metadata": metadata["metadata_dict"], "provider": metadata["provider"], "tool": metadata["tool"], }, } depo = metadata["deposit"] return cls( url=url, filename=filename, author_date=depo["author_date"], commit_date=depo["committer_date"], client=depo["client"], id=depo["id"], collection=depo["collection"], author=parse_author(depo["author"]), committer=parse_author(depo["committer"]), revision_parents=tuple(hash_to_bytes(p) for p in depo["revision_parents"]), raw_info=raw_info, - revision_extrinsic_metadata=[ + directory_extrinsic_metadata=[ RawExtrinsicMetadataCore( discovery_date=now(), metadata=raw_metadata.encode(), format="sword-v2-atom-codemeta-v2", ) for raw_metadata in all_metadata_raw ], ) class DepositLoader(PackageLoader[DepositPackageInfo]): """Load pypi origin's artifact releases into swh archive. """ visit_type = "deposit" def __init__(self, url: str, deposit_id: str): """Constructor Args: url: Origin url to associate the artifacts/metadata to deposit_id: Deposit identity """ super().__init__(url=url) config_deposit = self.config["deposit"] self.deposit_id = deposit_id self.client = ApiClient(url=config_deposit["url"], auth=config_deposit["auth"]) def get_versions(self) -> Sequence[str]: # only 1 branch 'HEAD' with no alias since we only have 1 snapshot # branch return ["HEAD"] def get_metadata_authority(self) -> MetadataAuthority: provider = self.metadata()["provider"] assert provider["provider_type"] == MetadataAuthorityType.DEPOSIT_CLIENT.value return MetadataAuthority( type=MetadataAuthorityType.DEPOSIT_CLIENT, url=provider["provider_url"], metadata={ "name": provider["provider_name"], **(provider["metadata"] or {}), }, ) def get_metadata_fetcher(self) -> MetadataFetcher: tool = self.metadata()["tool"] return MetadataFetcher( name=tool["name"], version=tool["version"], metadata=tool["configuration"], ) def get_package_info( self, version: str ) -> Iterator[Tuple[str, DepositPackageInfo]]: p_info = DepositPackageInfo.from_metadata( self.metadata(), url=self.url, filename="archive.zip", ) yield "HEAD", p_info def download_package( self, p_info: DepositPackageInfo, tmpdir: str ) -> List[Tuple[str, Mapping]]: """Override to allow use of the dedicated deposit client """ return [self.client.archive_get(self.deposit_id, tmpdir, p_info.filename)] def build_revision( self, p_info: DepositPackageInfo, uncompressed_path: str, directory: Sha1Git ) -> Optional[Revision]: message = ( f"{p_info.client}: Deposit {p_info.id} in collection {p_info.collection}" ).encode("utf-8") return Revision( type=RevisionType.TAR, message=message, author=p_info.author, date=TimestampWithTimezone.from_dict(p_info.author_date), committer=p_info.committer, committer_date=TimestampWithTimezone.from_dict(p_info.commit_date), parents=p_info.revision_parents, directory=directory, synthetic=True, metadata={ "extrinsic": { "provider": self.client.metadata_url(self.deposit_id), "when": self.visit_date.isoformat(), "raw": p_info.raw_info, }, }, ) def get_extrinsic_origin_metadata(self) -> List[RawExtrinsicMetadataCore]: metadata = self.metadata() all_metadata_raw: List[str] = metadata["metadata_raw"] origin_metadata = json.dumps( { "metadata": all_metadata_raw, "provider": metadata["provider"], "tool": metadata["tool"], } ).encode() return [ RawExtrinsicMetadataCore( discovery_date=now(), metadata=raw_meta.encode(), format="sword-v2-atom-codemeta-v2", ) for raw_meta in all_metadata_raw ] + [ RawExtrinsicMetadataCore( discovery_date=now(), metadata=origin_metadata, format="original-artifacts-json", ) ] @cached_method def metadata(self): """Returns metadata from the deposit server""" return self.client.metadata_get(self.deposit_id) def load(self) -> Dict: # First making sure the deposit is known prior to trigger a loading try: self.metadata() except ValueError: logger.error(f"Unknown deposit {self.deposit_id}, ignoring") return {"status": "failed"} # Then usual loading r = super().load() success = r["status"] != "failed" # Update deposit status try: if not success: self.client.status_update(self.deposit_id, status="failed") return r snapshot_id = hash_to_bytes(r["snapshot_id"]) snapshot = snapshot_get_all_branches(self.storage, snapshot_id) if not snapshot: return r branches = snapshot.branches logger.debug("branches: %s", branches) if not branches: return r rev_id = branches[b"HEAD"].target revision = self.storage.revision_get([rev_id])[0] if not revision: return r # update the deposit's status to success with its # revision-id and directory-id self.client.status_update( self.deposit_id, status="done", revision_id=hash_to_hex(rev_id), directory_id=hash_to_hex(revision.directory), snapshot_id=r["snapshot_id"], origin_url=self.url, ) except Exception: logger.exception("Problem when trying to update the deposit's status") return {"status": "failed"} return r def parse_author(author) -> Person: """See prior fixme """ return Person( fullname=author["fullname"].encode("utf-8"), name=author["name"].encode("utf-8"), email=author["email"].encode("utf-8"), ) class ApiClient: """Private Deposit Api client """ def __init__(self, url, auth: Optional[Mapping[str, str]]): self.base_url = url.rstrip("/") self.auth = None if not auth else (auth["username"], auth["password"]) def do(self, method: str, url: str, *args, **kwargs): """Internal method to deal with requests, possibly with basic http authentication. Args: method (str): supported http methods as in get/post/put Returns: The request's execution output """ method_fn = getattr(requests, method) if self.auth: kwargs["auth"] = self.auth return method_fn(url, *args, **kwargs) def archive_get( self, deposit_id: Union[int, str], tmpdir: str, filename: str ) -> Tuple[str, Dict]: """Retrieve deposit's archive artifact locally """ url = f"{self.base_url}/{deposit_id}/raw/" return download(url, dest=tmpdir, filename=filename, auth=self.auth) def metadata_url(self, deposit_id: Union[int, str]) -> str: return f"{self.base_url}/{deposit_id}/meta/" def metadata_get(self, deposit_id: Union[int, str]) -> Dict[str, Any]: """Retrieve deposit's metadata artifact as json """ url = self.metadata_url(deposit_id) r = self.do("get", url) if r.ok: return r.json() msg = f"Problem when retrieving deposit metadata at {url}" logger.error(msg) raise ValueError(msg) def status_update( self, deposit_id: Union[int, str], status: str, revision_id: Optional[str] = None, directory_id: Optional[str] = None, snapshot_id: Optional[str] = None, origin_url: Optional[str] = None, ): """Update deposit's information including status, and persistent identifiers result of the loading. """ url = f"{self.base_url}/{deposit_id}/update/" payload = {"status": status} if revision_id: payload["revision_id"] = revision_id if directory_id: payload["directory_id"] = directory_id if snapshot_id: payload["snapshot_id"] = snapshot_id if origin_url: payload["origin_url"] = origin_url self.do("put", url, json=payload) diff --git a/swh/loader/package/deposit/tests/test_deposit.py b/swh/loader/package/deposit/tests/test_deposit.py index fe6d07a..41fd6b2 100644 --- a/swh/loader/package/deposit/tests/test_deposit.py +++ b/swh/loader/package/deposit/tests/test_deposit.py @@ -1,429 +1,433 @@ # Copyright (C) 2019-2020 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import json import re from typing import List import attr import pytest from swh.core.pytest_plugin import requests_mock_datadir_factory from swh.loader.package.deposit.loader import DepositLoader from swh.loader.package.loader import now from swh.loader.package.tests.common import check_metadata_paths from swh.loader.tests import assert_last_visit_matches, check_snapshot, get_stats from swh.model.hashutil import hash_to_bytes, hash_to_hex from swh.model.identifiers import SWHID from swh.model.model import ( MetadataAuthority, MetadataAuthorityType, MetadataFetcher, MetadataTargetType, RawExtrinsicMetadata, Snapshot, SnapshotBranch, TargetType, ) DEPOSIT_URL = "https://deposit.softwareheritage.org/1/private" @pytest.fixture def requests_mock_datadir(requests_mock_datadir): """Enhance default mock data to mock put requests as the loader does some internal update queries there. """ requests_mock_datadir.put(re.compile("https")) return requests_mock_datadir def test_deposit_init_ok(swh_config, swh_loader_config): url = "some-url" deposit_id = 999 loader = DepositLoader(url, deposit_id) # Something that does not exist assert loader.url == url assert loader.client is not None assert loader.client.base_url == swh_loader_config["deposit"]["url"] def test_deposit_loading_unknown_deposit(swh_config, requests_mock_datadir): """Loading an unknown deposit should fail no origin, no visit, no snapshot """ # private api url form: 'https://deposit.s.o/1/private/hal/666/raw/' url = "some-url" unknown_deposit_id = 667 loader = DepositLoader(url, unknown_deposit_id) # does not exist actual_load_status = loader.load() assert actual_load_status == {"status": "failed"} stats = get_stats(loader.storage) assert { "content": 0, "directory": 0, "origin": 0, "origin_visit": 0, "release": 0, "revision": 0, "skipped_content": 0, "snapshot": 0, } == stats requests_mock_datadir_missing_one = requests_mock_datadir_factory( ignore_urls=[f"{DEPOSIT_URL}/666/raw/",] ) def test_deposit_loading_failure_to_retrieve_1_artifact( swh_config, requests_mock_datadir_missing_one ): """Deposit with missing artifact ends up with an uneventful/partial visit """ # private api url form: 'https://deposit.s.o/1/private/hal/666/raw/' url = "some-url-2" deposit_id = 666 loader = DepositLoader(url, deposit_id) actual_load_status = loader.load() assert actual_load_status["status"] == "uneventful" assert actual_load_status["snapshot_id"] is not None assert_last_visit_matches(loader.storage, url, status="partial", type="deposit") stats = get_stats(loader.storage) assert { "content": 0, "directory": 0, "origin": 1, "origin_visit": 1, "release": 0, "revision": 0, "skipped_content": 0, "snapshot": 1, } == stats def test_revision_metadata_structure(swh_config, requests_mock_datadir): url = "https://hal-test.archives-ouvertes.fr/some-external-id" deposit_id = 666 loader = DepositLoader(url, deposit_id) actual_load_status = loader.load() assert actual_load_status["status"] == "eventful" assert actual_load_status["snapshot_id"] is not None expected_revision_id = hash_to_bytes("637318680351f5d78856d13264faebbd91efe9bb") revision = loader.storage.revision_get([expected_revision_id])[0] assert revision is not None check_metadata_paths( revision.metadata, paths=[ ("extrinsic.provider", str), ("extrinsic.when", str), ("extrinsic.raw", dict), ("original_artifact", list), ], ) # Only 2 top-level keys now assert set(revision.metadata.keys()) == {"extrinsic", "original_artifact"} for original_artifact in revision.metadata["original_artifact"]: check_metadata_paths( original_artifact, paths=[("filename", str), ("length", int), ("checksums", dict),], ) def test_deposit_loading_ok(swh_config, requests_mock_datadir): url = "https://hal-test.archives-ouvertes.fr/some-external-id" deposit_id = 666 loader = DepositLoader(url, deposit_id) actual_load_status = loader.load() expected_snapshot_id = "b2b327b33dc85818bd23c3ccda8b7e675a66ecbd" assert actual_load_status == { "status": "eventful", "snapshot_id": expected_snapshot_id, } assert_last_visit_matches(loader.storage, url, status="full", type="deposit") stats = get_stats(loader.storage) assert { "content": 303, "directory": 12, "origin": 1, "origin_visit": 1, "release": 0, "revision": 1, "skipped_content": 0, "snapshot": 1, } == stats revision_id_hex = "637318680351f5d78856d13264faebbd91efe9bb" revision_id = hash_to_bytes(revision_id_hex) expected_snapshot = Snapshot( id=hash_to_bytes(expected_snapshot_id), branches={ b"HEAD": SnapshotBranch( target=revision_id, target_type=TargetType.REVISION, ), }, ) check_snapshot(expected_snapshot, storage=loader.storage) revision = loader.storage.revision_get([revision_id])[0] assert revision is not None # check metadata fetcher = MetadataFetcher(name="swh-deposit", version="0.0.1",) authority = MetadataAuthority( type=MetadataAuthorityType.DEPOSIT_CLIENT, url="https://hal-test.archives-ouvertes.fr/", ) # Check origin metadata orig_meta = loader.storage.raw_extrinsic_metadata_get( MetadataTargetType.ORIGIN, url, authority ) assert orig_meta.next_page_token is None raw_meta = loader.client.metadata_get(deposit_id) all_metadata_raw: List[str] = raw_meta["metadata_raw"] # 2 raw metadata xml + 1 json dict assert len(orig_meta.results) == len(all_metadata_raw) + 1 orig_meta0 = orig_meta.results[0] assert orig_meta0.authority == authority assert orig_meta0.fetcher == fetcher - # Check revision metadata - revision_swhid = SWHID(object_type="revision", object_id=revision_id) - actual_rev_meta = loader.storage.raw_extrinsic_metadata_get( - MetadataTargetType.REVISION, revision_swhid, authority + # Check directory metadata + directory_id = hash_to_hex(revision.directory) + directory_swhid = SWHID(object_type="directory", object_id=directory_id) + actual_dir_meta = loader.storage.raw_extrinsic_metadata_get( + MetadataTargetType.DIRECTORY, directory_swhid, authority ) - assert actual_rev_meta.next_page_token is None - assert len(actual_rev_meta.results) == len(all_metadata_raw) - for rev_meta in actual_rev_meta.results: - assert rev_meta.authority == authority - assert rev_meta.fetcher == fetcher - assert rev_meta.metadata.decode() in all_metadata_raw + assert actual_dir_meta.next_page_token is None + assert len(actual_dir_meta.results) == len(all_metadata_raw) + for dir_meta in actual_dir_meta.results: + assert dir_meta.authority == authority + assert dir_meta.fetcher == fetcher + assert dir_meta.metadata.decode() in all_metadata_raw # Retrieve the information for deposit status update query to the deposit urls = [ m for m in requests_mock_datadir.request_history if m.url == f"{DEPOSIT_URL}/{deposit_id}/update/" ] assert len(urls) == 1 update_query = urls[0] body = update_query.json() expected_body = { "status": "done", "revision_id": revision_id_hex, "directory_id": hash_to_hex(revision.directory), "snapshot_id": expected_snapshot_id, "origin_url": url, } assert body == expected_body def test_deposit_loading_ok_2(swh_config, requests_mock_datadir): """Field dates should be se appropriately """ external_id = "some-external-id" url = f"https://hal-test.archives-ouvertes.fr/{external_id}" deposit_id = 777 loader = DepositLoader(url, deposit_id) actual_load_status = loader.load() expected_snapshot_id = "3e68440fdd7c81d283f8f3aebb6f0c8657864192" assert actual_load_status == { "status": "eventful", "snapshot_id": expected_snapshot_id, } assert_last_visit_matches(loader.storage, url, status="full", type="deposit") revision_id = "564d18943d71be80d0d73b43a77cfb205bcde96c" expected_snapshot = Snapshot( id=hash_to_bytes(expected_snapshot_id), branches={ b"HEAD": SnapshotBranch( target=hash_to_bytes(revision_id), target_type=TargetType.REVISION ) }, ) check_snapshot(expected_snapshot, storage=loader.storage) raw_meta = loader.client.metadata_get(deposit_id) # Ensure the date fields are set appropriately in the revision # Retrieve the revision revision = loader.storage.revision_get([hash_to_bytes(revision_id)])[0] assert revision assert revision.date.to_dict() == raw_meta["deposit"]["author_date"] assert revision.committer_date.to_dict() == raw_meta["deposit"]["committer_date"] read_api = f"{DEPOSIT_URL}/{deposit_id}/meta/" provider = { "provider_name": "hal", "provider_type": "deposit_client", "provider_url": "https://hal-test.archives-ouvertes.fr/", "metadata": None, } tool = { "name": "swh-deposit", "version": "0.0.1", "configuration": {"sword_version": "2"}, } assert revision.metadata == { "extrinsic": { "provider": read_api, "raw": { "origin": {"type": "deposit", "url": url,}, "origin_metadata": { "metadata": raw_meta["metadata_dict"], "provider": provider, "tool": tool, }, }, "when": revision.metadata["extrinsic"]["when"], # dynamic }, "original_artifact": [ { "checksums": { "sha1": "f8c63d7c890a7453498e6cf9fef215d85ec6801d", "sha256": "474bf646aeeff6d945eb752b1a9f8a40f3d81a88909ee7bd2d08cc822aa361e6", # noqa }, "filename": "archive.zip", "length": 956830, "url": "https://deposit.softwareheritage.org/1/private/777/raw/", } ], } fetcher = MetadataFetcher(name="swh-deposit", version="0.0.1",) authority = MetadataAuthority( type=MetadataAuthorityType.DEPOSIT_CLIENT, url="https://hal-test.archives-ouvertes.fr/", ) # Check the origin metadata swh side origin_extrinsic_metadata = loader.storage.raw_extrinsic_metadata_get( MetadataTargetType.ORIGIN, url, authority ) assert origin_extrinsic_metadata.next_page_token is None all_metadata_raw: List[str] = raw_meta["metadata_raw"] # 1 raw metadata xml + 1 json dict assert len(origin_extrinsic_metadata.results) == len(all_metadata_raw) + 1 expected_metadata = [] for idx, raw_meta in enumerate(all_metadata_raw): origin_meta = origin_extrinsic_metadata.results[idx] expected_metadata.append( RawExtrinsicMetadata( type=MetadataTargetType.ORIGIN, id=url, discovery_date=origin_meta.discovery_date, metadata=raw_meta.encode(), format="sword-v2-atom-codemeta-v2", authority=authority, fetcher=fetcher, ) ) origin_metadata = { "metadata": all_metadata_raw, "provider": provider, "tool": tool, } expected_metadata.append( RawExtrinsicMetadata( type=MetadataTargetType.ORIGIN, id=url, discovery_date=origin_extrinsic_metadata.results[-1].discovery_date, metadata=json.dumps(origin_metadata).encode(), format="original-artifacts-json", authority=authority, fetcher=fetcher, ) ) assert len(origin_extrinsic_metadata.results) == len(expected_metadata) for orig_meta in origin_extrinsic_metadata.results: assert orig_meta in expected_metadata # Check the revision metadata swh side - revision_swhid = SWHID(object_type="revision", object_id=revision_id) - actual_revision_metadata = loader.storage.raw_extrinsic_metadata_get( - MetadataTargetType.REVISION, revision_swhid, authority + directory_id = hash_to_hex(revision.directory) + directory_swhid = SWHID(object_type="directory", object_id=directory_id) + actual_directory_metadata = loader.storage.raw_extrinsic_metadata_get( + MetadataTargetType.DIRECTORY, directory_swhid, authority ) - assert actual_revision_metadata.next_page_token is None - assert len(actual_revision_metadata.results) == len(all_metadata_raw) + assert actual_directory_metadata.next_page_token is None + assert len(actual_directory_metadata.results) == len(all_metadata_raw) - rev_metadata_template = RawExtrinsicMetadata( - type=MetadataTargetType.REVISION, - id=revision_swhid, + revision_swhid = SWHID(object_type="revision", object_id=revision_id) + dir_metadata_template = RawExtrinsicMetadata( + type=MetadataTargetType.DIRECTORY, + id=directory_swhid, format="sword-v2-atom-codemeta-v2", authority=authority, fetcher=fetcher, origin=url, + revision=revision_swhid, # to satisfy the constructor discovery_date=now(), metadata=b"", ) - expected_revision_metadata = [] + expected_directory_metadata = [] for idx, raw_meta in enumerate(all_metadata_raw): - rev_metadata = actual_revision_metadata.results[idx] - expected_revision_metadata.append( + dir_metadata = actual_directory_metadata.results[idx] + expected_directory_metadata.append( attr.evolve( - rev_metadata_template, - discovery_date=rev_metadata.discovery_date, + dir_metadata_template, + discovery_date=dir_metadata.discovery_date, metadata=raw_meta.encode(), ) ) - assert actual_revision_metadata.results == expected_revision_metadata + assert actual_directory_metadata.results == expected_directory_metadata # Retrieve the information for deposit status update query to the deposit urls = [ m for m in requests_mock_datadir.request_history if m.url == f"{DEPOSIT_URL}/{deposit_id}/update/" ] assert len(urls) == 1 update_query = urls[0] body = update_query.json() expected_body = { "status": "done", "revision_id": revision_id, "directory_id": hash_to_hex(revision.directory), "snapshot_id": expected_snapshot_id, "origin_url": url, } assert body == expected_body diff --git a/swh/loader/package/loader.py b/swh/loader/package/loader.py index 2472b23..cfff3f1 100644 --- a/swh/loader/package/loader.py +++ b/swh/loader/package/loader.py @@ -1,788 +1,801 @@ # Copyright (C) 2019-2020 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import datetime from itertools import islice import json import logging import os import sys import tempfile from typing import ( Any, Dict, Generic, Iterable, Iterator, List, Mapping, Optional, Sequence, Tuple, TypeVar, ) import attr import sentry_sdk from swh.core.config import load_from_envvar from swh.core.tarball import uncompress from swh.loader.package.utils import download from swh.model import from_disk from swh.model.collections import ImmutableDict from swh.model.hashutil import hash_to_hex from swh.model.identifiers import SWHID from swh.model.model import ( MetadataAuthority, MetadataAuthorityType, MetadataFetcher, MetadataTargetType, Origin, OriginVisit, OriginVisitStatus, RawExtrinsicMetadata, Revision, Sha1Git, Snapshot, TargetType, ) from swh.storage import get_storage 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.""" @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]) # 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 - revision_extrinsic_metadata = attr.ib( + directory_extrinsic_metadata = attr.ib( type=List[RawExtrinsicMetadataCore], default=[], kw_only=True, ) # TODO: add support for metadata for directories and contents @property def ID_KEYS(self): raise NotImplementedError(f"{self.__class__.__name__} is missing ID_KEYS") def artifact_identity(self): return [getattr(self, k) for k in self.ID_KEYS] TPackageInfo = TypeVar("TPackageInfo", bound=BasePackageInfo) DEFAULT_CONFIG = { "max_content_size": 100 * 1024 * 1024, "create_authorities": True, "create_fetchers": True, } class PackageLoader(Generic[TPackageInfo]): # Origin visit type (str) set by the loader visit_type = "" def __init__(self, url): """Loader's constructor. This raises exception if the minimal required configuration is missing (cf. fn:`check` method). Args: url (str): Origin url to load data from """ # This expects to use the environment variable SWH_CONFIG_FILENAME self.config = load_from_envvar(DEFAULT_CONFIG) self._check_configuration() self.storage: StorageInterface = get_storage(**self.config["storage"]) self.url = url self.visit_date = datetime.datetime.now(tz=datetime.timezone.utc) self.max_content_size = self.config["max_content_size"] def _check_configuration(self): """Checks the minimal configuration required is set for the loader. If some required configuration is missing, exception detailing the issue is raised. """ if "storage" not in self.config: raise ValueError("Misconfiguration, at least the storage key should be set") def get_versions(self) -> Sequence[str]: """Return the list of all 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_revision( self, p_info: TPackageInfo, uncompressed_path: str, directory: Sha1Git ) -> Optional[Revision]: """Build the revision from the archive metadata (extrinsic artifact metadata) and the intrinsic metadata. Args: p_info: Package information uncompressed_path: Artifact uncompressed path on disk Returns: Revision object """ raise NotImplementedError("build_revision") 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 known_artifacts( self, snapshot: Optional[Snapshot] ) -> Dict[Sha1Git, Optional[ImmutableDict[str, object]]]: """Retrieve the known releases/artifact for the origin. Args snapshot: snapshot for the visit Returns: Dict of keys revision id (bytes), values a metadata Dict. """ if not snapshot: return {} # retrieve only revisions (e.g the alias we do not want here) revs = [ rev.target for rev in snapshot.branches.values() if rev and rev.target_type == TargetType.REVISION ] known_revisions = self.storage.revision_get(revs) return { revision.id: revision.metadata for revision in known_revisions if revision } def resolve_revision_from( self, known_artifacts: Dict, p_info: TPackageInfo, ) -> Optional[bytes]: """Resolve the revision from a snapshot and an artifact metadata dict. If the artifact has already been downloaded, this will return the existing revision targeting that uncompressed artifact directory. Otherwise, this returns None. Args: snapshot: Snapshot p_info: Package information Returns: None or revision identifier """ 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) """ return [download(p_info.url, dest=tmpdir, filename=p_info.filename)] 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 load(self) -> Dict: """Load for a specific origin the associated contents. for each package version of the origin 1. 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. 2. 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). 3. Convert the extracted directory to a set of Software Heritage objects Using swh.model.from_disk. 4. 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. 5. Generate the revision/release objects for the given version. From the data generated at steps 3 and 4. end for each 6. Generate and load the snapshot for the visit Using the revisions/releases collected at step 5., and the branch information from step 0., generate a snapshot and load it into the Software Heritage archive """ status_load = "uneventful" # either: eventful, uneventful, failed status_visit = "full" # either: partial, full tmp_revisions = {} # type: Dict[str, List] snapshot = None failed_branches: List[str] = [] def finalize_visit() -> 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, 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 # 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"} try: last_snapshot = self.last_snapshot() logger.debug("last snapshot: %s", last_snapshot) known_artifacts = self.known_artifacts(last_snapshot) logger.debug("known artifacts: %s", known_artifacts) except Exception as e: logger.exception("Failed to get previous state for %s", self.url) sentry_sdk.capture_exception(e) status_visit = "partial" status_load = "failed" return finalize_visit() load_exceptions: List[Exception] = [] for version in self.get_versions(): # for each logger.debug("version: %s", version) tmp_revisions[version] = [] # `p_` stands for `package_` for branch_name, p_info in self.get_package_info(version): logger.debug("package_info: %s", p_info) revision_id = self.resolve_revision_from(known_artifacts, p_info) if revision_id is None: try: - revision_id = self._load_revision(p_info, origin) - if revision_id: - self._load_extrinsic_revision_metadata(p_info, revision_id) + res = self._load_revision(p_info, origin) + if res: + (revision_id, directory_id) = res + assert revision_id + assert directory_id + self._load_extrinsic_directory_metadata( + p_info, revision_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) logger.exception( "Failed loading branch %s for %s", branch_name, self.url ) failed_branches.append(branch_name) continue if revision_id is None: continue tmp_revisions[version].append((branch_name, revision_id)) if load_exceptions: status_visit = "partial" if not tmp_revisions: # We could not load any revisions; fail completely status_visit = "partial" status_load = "failed" return finalize_visit() 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_revisions, extra_branches ) self.storage.flush() except Exception as e: logger.exception("Failed to build snapshot for origin %s", self.url) sentry_sdk.capture_exception(e) status_visit = "partial" 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: logger.exception( "Failed to load extrinsic snapshot metadata for %s", self.url ) 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: logger.exception( "Failed to load extrinsic origin metadata for %s", self.url ) sentry_sdk.capture_exception(e) status_visit = "partial" status_load = "failed" return finalize_visit() 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_revision(self, p_info: TPackageInfo, origin) -> Optional[Sha1Git]: + def _load_revision( + self, p_info: TPackageInfo, origin + ) -> Optional[Tuple[Sha1Git, Sha1Git]]: """Does all the loading of a revision itself: * downloads a package and uncompresses it * loads it from disk * adds contents, directories, and revision to self.storage - * returns (revision_id, loaded) + * returns (revision_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 revision = self.build_revision( p_info, uncompressed_path, directory=directory.hash ) if not revision: # Some artifacts are missing intrinsic metadata # skipping those return None metadata = [metadata for (filepath, metadata) in dl_artifacts] extra_metadata: Tuple[str, Any] = ( "original_artifact", metadata, ) if revision.metadata is not None: full_metadata = list(revision.metadata.items()) + [extra_metadata] else: full_metadata = [extra_metadata] # TODO: don't add these extrinsic metadata to the revision. revision = attr.evolve(revision, metadata=ImmutableDict(full_metadata)) original_artifact_metadata = RawExtrinsicMetadata( type=MetadataTargetType.REVISION, id=SWHID(object_type="revision", object_id=revision.id), 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, ) self._load_metadata_objects([original_artifact_metadata]) logger.debug("Revision: %s", revision) self.storage.revision_add([revision]) - return revision.id + assert directory.hash + return (revision.id, directory.hash) def _load_snapshot( self, default_version: str, revisions: Dict[str, List[Tuple[str, bytes]]], extra_branches: Dict[bytes, Mapping[str, Any]], ) -> Optional[Snapshot]: """Build snapshot out of the current revisions stored and extra branches. Then load it in the storage. """ logger.debug("revisions: %s", revisions) # Build and load the snapshot branches = {} # type: Dict[bytes, Mapping[str, Any]] for version, branch_name_revisions in revisions.items(): if version == default_version and len(branch_name_revisions) == 1: # only 1 branch (no ambiguity), we can create an alias # branch 'HEAD' branch_name, _ = branch_name_revisions[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_revisions: branches[branch_name.encode("utf-8")] = { "target_type": "revision", "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( type=MetadataTargetType.ORIGIN, id=self.url, 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( type=MetadataTargetType.SNAPSHOT, id=SWHID(object_type="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_revision_metadata( - self, p_info: TPackageInfo, revision_id: Sha1Git + def build_extrinsic_directory_metadata( + self, p_info: TPackageInfo, revision_id: Sha1Git, directory_id: Sha1Git, ) -> List[RawExtrinsicMetadata]: - if not p_info.revision_extrinsic_metadata: + 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.revision_extrinsic_metadata: + for item in p_info.directory_extrinsic_metadata: metadata_objects.append( RawExtrinsicMetadata( - type=MetadataTargetType.REVISION, - id=SWHID(object_type="revision", object_id=revision_id), + type=MetadataTargetType.DIRECTORY, + id=SWHID(object_type="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, + revision=SWHID( + object_type="revision", object_id=hash_to_hex(revision_id) + ), ) ) return metadata_objects - def _load_extrinsic_revision_metadata( - self, p_info: TPackageInfo, revision_id: Sha1Git + def _load_extrinsic_directory_metadata( + self, p_info: TPackageInfo, revision_id: Sha1Git, directory_id: Sha1Git, ) -> None: - metadata_objects = self.build_extrinsic_revision_metadata(p_info, revision_id) + metadata_objects = self.build_extrinsic_directory_metadata( + p_info, revision_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())) diff --git a/swh/loader/package/npm/loader.py b/swh/loader/package/npm/loader.py index 9b92929..348b036 100644 --- a/swh/loader/package/npm/loader.py +++ b/swh/loader/package/npm/loader.py @@ -1,339 +1,339 @@ # Copyright (C) 2019-2020 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information from codecs import BOM_UTF8 import json import logging import os from typing import Any, Dict, Iterator, List, Optional, Sequence, Tuple, Union from urllib.parse import quote import attr import chardet from swh.loader.package.loader import ( BasePackageInfo, PackageLoader, RawExtrinsicMetadataCore, ) from swh.loader.package.utils import api_info, cached_method, release_name from swh.model.model import ( MetadataAuthority, MetadataAuthorityType, Person, Revision, RevisionType, Sha1Git, TimestampWithTimezone, ) logger = logging.getLogger(__name__) EMPTY_PERSON = Person(fullname=b"", name=None, email=None) @attr.s class NpmPackageInfo(BasePackageInfo): raw_info = attr.ib(type=Dict[str, Any]) date = attr.ib(type=Optional[str]) shasum = attr.ib(type=str) """sha1 checksum""" version = attr.ib(type=str) @classmethod def from_metadata( cls, project_metadata: Dict[str, Any], version: str ) -> "NpmPackageInfo": package_metadata = project_metadata["versions"][version] url = package_metadata["dist"]["tarball"] # No date available in intrinsic metadata: retrieve it from the API # metadata, using the version number that the API claims this package # has. extrinsic_version = package_metadata["version"] if "time" in project_metadata: date = project_metadata["time"][extrinsic_version] elif "mtime" in package_metadata: date = package_metadata["mtime"] else: date = None return cls( url=url, filename=os.path.basename(url), date=date, shasum=package_metadata["dist"]["shasum"], version=extrinsic_version, raw_info=package_metadata, - revision_extrinsic_metadata=[ + directory_extrinsic_metadata=[ RawExtrinsicMetadataCore( format="replicate-npm-package-json", metadata=json.dumps(package_metadata).encode(), ) ], ) class NpmLoader(PackageLoader[NpmPackageInfo]): """Load npm origin's artifact releases into swh archive. """ visit_type = "npm" def __init__(self, url: str): """Constructor Args str: origin url (e.g. https://www.npmjs.com/package/) """ super().__init__(url=url) package_name = url.split("https://www.npmjs.com/package/")[1] safe_name = quote(package_name, safe="") self.provider_url = f"https://replicate.npmjs.com/{safe_name}/" self._info: Dict[str, Any] = {} self._versions = None @cached_method def _raw_info(self) -> bytes: return api_info(self.provider_url) @cached_method def info(self) -> Dict: """Return the project metadata information (fetched from npm registry) """ return json.loads(self._raw_info()) def get_versions(self) -> Sequence[str]: return sorted(list(self.info()["versions"].keys())) def get_default_version(self) -> str: return self.info()["dist-tags"].get("latest", "") def get_metadata_authority(self): return MetadataAuthority( type=MetadataAuthorityType.FORGE, url="https://npmjs.com/", metadata={}, ) def get_package_info(self, version: str) -> Iterator[Tuple[str, NpmPackageInfo]]: p_info = NpmPackageInfo.from_metadata( project_metadata=self.info(), version=version ) yield release_name(version), p_info def resolve_revision_from( self, known_artifacts: Dict, p_info: NpmPackageInfo ) -> Optional[bytes]: return artifact_to_revision_id(known_artifacts, p_info) def build_revision( self, p_info: NpmPackageInfo, uncompressed_path: str, directory: Sha1Git ) -> Optional[Revision]: i_metadata = extract_intrinsic_metadata(uncompressed_path) if not i_metadata: return None author = extract_npm_package_author(i_metadata) message = i_metadata["version"].encode("ascii") if p_info.date is None: url = p_info.url artifact_name = os.path.basename(url) raise ValueError( "Origin %s: Cannot determine upload time for artifact %s." % (p_info.url, artifact_name) ) date = TimestampWithTimezone.from_iso8601(p_info.date) # FIXME: this is to remain bug-compatible with earlier versions: date = attr.evolve(date, timestamp=attr.evolve(date.timestamp, microseconds=0)) r = Revision( type=RevisionType.TAR, message=message, author=author, date=date, committer=author, committer_date=date, parents=(), directory=directory, synthetic=True, metadata={ "intrinsic": {"tool": "package.json", "raw": i_metadata,}, "extrinsic": { "provider": self.provider_url, "when": self.visit_date.isoformat(), "raw": p_info.raw_info, }, }, ) return r def artifact_to_revision_id( known_artifacts: Dict, p_info: NpmPackageInfo ) -> Optional[bytes]: """Given metadata artifact, solves the associated revision id. The following code allows to deal with 2 metadata formats: - old format sample:: { 'package_source': { 'sha1': '05181c12cd8c22035dd31155656826b85745da37', } } - new format sample:: { 'original_artifact': [{ 'checksums': { 'sha256': '6975816f2c5ad4046acc676ba112f2fff945b01522d63948531f11f11e0892ec', # noqa ... }, }], ... } """ shasum = p_info.shasum for rev_id, known_artifact in known_artifacts.items(): known_original_artifact = known_artifact.get("original_artifact") if not known_original_artifact: # previous loader-npm version kept original artifact elsewhere known_original_artifact = known_artifact.get("package_source") if not known_original_artifact: continue original_hash = known_original_artifact["sha1"] else: assert isinstance(known_original_artifact, list) original_hash = known_original_artifact[0]["checksums"]["sha1"] if shasum == original_hash: return rev_id return None def _author_str(author_data: Union[Dict, List, str]) -> str: """Parse author from package.json author fields """ if isinstance(author_data, dict): author_str = "" name = author_data.get("name") if name is not None: if isinstance(name, str): author_str += name elif isinstance(name, list): author_str += _author_str(name[0]) if len(name) > 0 else "" email = author_data.get("email") if email is not None: author_str += f" <{email}>" result = author_str elif isinstance(author_data, list): result = _author_str(author_data[0]) if len(author_data) > 0 else "" else: result = author_data return result def extract_npm_package_author(package_json: Dict[str, Any]) -> Person: """ Extract package author from a ``package.json`` file content and return it in swh format. Args: package_json: Dict holding the content of parsed ``package.json`` file Returns: Person """ for author_key in ("author", "authors"): if author_key in package_json: author_data = package_json[author_key] if author_data is None: return EMPTY_PERSON author_str = _author_str(author_data) return Person.from_fullname(author_str.encode()) return EMPTY_PERSON def _lstrip_bom(s, bom=BOM_UTF8): if s.startswith(bom): return s[len(bom) :] else: return s def load_json(json_bytes): """ Try to load JSON from bytes and return a dictionary. First try to decode from utf-8. If the decoding failed, try to detect the encoding and decode again with replace error handling. If JSON is malformed, an empty dictionary will be returned. Args: json_bytes (bytes): binary content of a JSON file Returns: dict: JSON data loaded in a dictionary """ json_data = {} try: json_str = _lstrip_bom(json_bytes).decode("utf-8") except UnicodeDecodeError: encoding = chardet.detect(json_bytes)["encoding"] if encoding: json_str = json_bytes.decode(encoding, "replace") try: json_data = json.loads(json_str) except json.decoder.JSONDecodeError: pass return json_data def extract_intrinsic_metadata(dir_path: str) -> Dict: """Given an uncompressed path holding the pkginfo file, returns a pkginfo parsed structure as a dict. The release artifact contains at their root one folder. For example: $ tar tvf zprint-0.0.6.tar.gz drwxr-xr-x root/root 0 2018-08-22 11:01 zprint-0.0.6/ ... Args: dir_path (str): Path to the uncompressed directory representing a release artifact from npm. Returns: the pkginfo parsed structure as a dict if any or None if none was present. """ # Retrieve the root folder of the archive if not os.path.exists(dir_path): return {} lst = os.listdir(dir_path) if len(lst) == 0: return {} project_dirname = lst[0] package_json_path = os.path.join(dir_path, project_dirname, "package.json") if not os.path.exists(package_json_path): return {} with open(package_json_path, "rb") as package_json_file: package_json_bytes = package_json_file.read() return load_json(package_json_bytes) diff --git a/swh/loader/package/npm/tests/test_npm.py b/swh/loader/package/npm/tests/test_npm.py index 23865c5..dc7c8d0 100644 --- a/swh/loader/package/npm/tests/test_npm.py +++ b/swh/loader/package/npm/tests/test_npm.py @@ -1,701 +1,705 @@ # Copyright (C) 2019-2020 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import json import os import pytest from swh.loader.package import __version__ from swh.loader.package.npm.loader import ( NpmLoader, _author_str, artifact_to_revision_id, extract_npm_package_author, ) from swh.loader.package.tests.common import check_metadata_paths from swh.loader.tests import assert_last_visit_matches, check_snapshot, get_stats from swh.model.hashutil import hash_to_bytes from swh.model.identifiers import SWHID from swh.model.model import ( MetadataAuthority, MetadataAuthorityType, MetadataFetcher, MetadataTargetType, Person, RawExtrinsicMetadata, Snapshot, SnapshotBranch, TargetType, ) from swh.storage.interface import PagedResult @pytest.fixture def org_api_info(datadir) -> bytes: with open(os.path.join(datadir, "https_replicate.npmjs.com", "org"), "rb",) as f: return f.read() def test_npm_author_str(): for author, expected_author in [ ("author", "author"), ( ["Al from quantum leap", "hal from 2001 space odyssey"], "Al from quantum leap", ), ([], ""), ({"name": "groot", "email": "groot@galaxy.org",}, "groot "), ({"name": "somebody",}, "somebody"), ({"email": "no@one.org"}, " "), # note first elt is an extra blank ({"name": "no one", "email": None,}, "no one"), ({"email": None,}, ""), ({"name": None}, ""), ({"name": None, "email": None,}, ""), ({}, ""), (None, None), ({"name": []}, "",), ( {"name": ["Susan McSween", "William H. Bonney", "Doc Scurlock",]}, "Susan McSween", ), (None, None), ]: assert _author_str(author) == expected_author def test_extract_npm_package_author(datadir): package_metadata_filepath = os.path.join( datadir, "https_replicate.npmjs.com", "org_visit1" ) with open(package_metadata_filepath) as json_file: package_metadata = json.load(json_file) extract_npm_package_author(package_metadata["versions"]["0.0.2"]) == Person( fullname=b"mooz ", name=b"mooz", email=b"stillpedant@gmail.com", ) assert extract_npm_package_author(package_metadata["versions"]["0.0.3"]) == Person( fullname=b"Masafumi Oyamada ", name=b"Masafumi Oyamada", email=b"stillpedant@gmail.com", ) package_json = json.loads( """ { "name": "highlightjs-line-numbers.js", "version": "2.7.0", "description": "Highlight.js line numbers plugin.", "main": "src/highlightjs-line-numbers.js", "dependencies": {}, "devDependencies": { "gulp": "^4.0.0", "gulp-rename": "^1.4.0", "gulp-replace": "^0.6.1", "gulp-uglify": "^1.2.0" }, "repository": { "type": "git", "url": "https://github.com/wcoder/highlightjs-line-numbers.js.git" }, "author": "Yauheni Pakala ", "license": "MIT", "bugs": { "url": "https://github.com/wcoder/highlightjs-line-numbers.js/issues" }, "homepage": "http://wcoder.github.io/highlightjs-line-numbers.js/" }""" ) assert extract_npm_package_author(package_json) == Person( fullname=b"Yauheni Pakala ", name=b"Yauheni Pakala", email=b"evgeniy.pakalo@gmail.com", ) package_json = json.loads( """ { "name": "3-way-diff", "version": "0.0.1", "description": "3-way diffing of JavaScript objects", "main": "index.js", "authors": [ { "name": "Shawn Walsh", "url": "https://github.com/shawnpwalsh" }, { "name": "Markham F Rollins IV", "url": "https://github.com/mrollinsiv" } ], "keywords": [ "3-way diff", "3 way diff", "three-way diff", "three way diff" ], "devDependencies": { "babel-core": "^6.20.0", "babel-preset-es2015": "^6.18.0", "mocha": "^3.0.2" }, "dependencies": { "lodash": "^4.15.0" } }""" ) assert extract_npm_package_author(package_json) == Person( fullname=b"Shawn Walsh", name=b"Shawn Walsh", email=None ) package_json = json.loads( """ { "name": "yfe-ynpm", "version": "1.0.0", "homepage": "http://gitlab.ywwl.com/yfe/yfe-ynpm", "repository": { "type": "git", "url": "git@gitlab.ywwl.com:yfe/yfe-ynpm.git" }, "author": [ "fengmk2 (https://fengmk2.com)", "xufuzi (https://7993.org)" ], "license": "MIT" }""" ) assert extract_npm_package_author(package_json) == Person( fullname=b"fengmk2 (https://fengmk2.com)", name=b"fengmk2", email=b"fengmk2@gmail.com", ) package_json = json.loads( """ { "name": "umi-plugin-whale", "version": "0.0.8", "description": "Internal contract component", "authors": { "name": "xiaohuoni", "email": "448627663@qq.com" }, "repository": "alitajs/whale", "devDependencies": { "np": "^3.0.4", "umi-tools": "*" }, "license": "MIT" }""" ) assert extract_npm_package_author(package_json) == Person( fullname=b"xiaohuoni <448627663@qq.com>", name=b"xiaohuoni", email=b"448627663@qq.com", ) package_json_no_authors = json.loads( """{ "authors": null, "license": "MIT" }""" ) assert extract_npm_package_author(package_json_no_authors) == Person( fullname=b"", name=None, email=None ) def normalize_hashes(hashes): if isinstance(hashes, str): return hash_to_bytes(hashes) if isinstance(hashes, list): return [hash_to_bytes(x) for x in hashes] return {hash_to_bytes(k): hash_to_bytes(v) for k, v in hashes.items()} _expected_new_contents_first_visit = normalize_hashes( [ "4ce3058e16ab3d7e077f65aabf855c34895bf17c", "858c3ceee84c8311adc808f8cdb30d233ddc9d18", "0fa33b4f5a4e0496da6843a38ff1af8b61541996", "85a410f8ef8eb8920f2c384a9555566ad4a2e21b", "9163ac8025923d5a45aaac482262893955c9b37b", "692cf623b8dd2c5df2c2998fd95ae4ec99882fb4", "18c03aac6d3e910efb20039c15d70ab5e0297101", "41265c42446aac17ca769e67d1704f99e5a1394d", "783ff33f5882813dca9239452c4a7cadd4dba778", "b029cfb85107aee4590c2434a3329bfcf36f8fa1", "112d1900b4c2e3e9351050d1b542c9744f9793f3", "5439bbc4bd9a996f1a38244e6892b71850bc98fd", "d83097a2f994b503185adf4e719d154123150159", "d0939b4898e83090ee55fd9d8a60e312cfadfbaf", "b3523a26f7147e4af40d9d462adaae6d49eda13e", "cd065fb435d6fb204a8871bcd623d0d0e673088c", "2854a40855ad839a54f4b08f5cff0cf52fca4399", "b8a53bbaac34ebb8c6169d11a4b9f13b05c583fe", "0f73d56e1cf480bded8a1ecf20ec6fc53c574713", "0d9882b2dfafdce31f4e77fe307d41a44a74cefe", "585fc5caab9ead178a327d3660d35851db713df1", "e8cd41a48d79101977e3036a87aeb1aac730686f", "5414efaef33cceb9f3c9eb5c4cc1682cd62d14f7", "9c3cc2763bf9e9e37067d3607302c4776502df98", "3649a68410e354c83cd4a38b66bd314de4c8f5c9", "e96ed0c091de1ebdf587104eaf63400d1974a1fe", "078ca03d2f99e4e6eab16f7b75fbb7afb699c86c", "38de737da99514de6559ff163c988198bc91367a", ] ) _expected_new_directories_first_visit = normalize_hashes( [ "3370d20d6f96dc1c9e50f083e2134881db110f4f", "42753c0c2ab00c4501b552ac4671c68f3cf5aece", "d7895533ef5edbcffdea3f057d9fef3a1ef845ce", "80579be563e2ef3e385226fe7a3f079b377f142c", "3b0ddc6a9e58b4b53c222da4e27b280b6cda591c", "bcad03ce58ac136f26f000990fc9064e559fe1c0", "5fc7e82a1bc72e074665c6078c6d3fad2f13d7ca", "e3cd26beba9b1e02f6762ef54bd9ac80cc5f25fd", "584b5b4b6cf7f038095e820b99386a9c232de931", "184c8d6d0d242f2b1792ef9d3bf396a5434b7f7a", "bb5f4ee143c970367eb409f2e4c1104898048b9d", "1b95491047add1103db0dfdfa84a9735dcb11e88", "a00c6de13471a2d66e64aca140ddb21ef5521e62", "5ce6c1cd5cda2d546db513aaad8c72a44c7771e2", "c337091e349b6ac10d38a49cdf8c2401ef9bb0f2", "202fafcd7c0f8230e89d5496ad7f44ab12b807bf", "775cc516543be86c15c1dc172f49c0d4e6e78235", "ff3d1ead85a14f891e8b3fa3a89de39db1b8de2e", ] ) _expected_new_revisions_first_visit = normalize_hashes( { "d8a1c7474d2956ac598a19f0f27d52f7015f117e": ( "42753c0c2ab00c4501b552ac4671c68f3cf5aece" ), "5f9eb78af37ffd12949f235e86fac04898f9f72a": ( "3370d20d6f96dc1c9e50f083e2134881db110f4f" ), "ba019b192bdb94bd0b5bd68b3a5f92b5acc2239a": ( "d7895533ef5edbcffdea3f057d9fef3a1ef845ce" ), } ) def package_url(package): return "https://www.npmjs.com/package/%s" % package def package_metadata_url(package): return "https://replicate.npmjs.com/%s/" % package def test_revision_metadata_structure(swh_config, requests_mock_datadir): package = "org" loader = NpmLoader(package_url(package)) actual_load_status = loader.load() assert actual_load_status["status"] == "eventful" assert actual_load_status["snapshot_id"] is not None expected_revision_id = hash_to_bytes("d8a1c7474d2956ac598a19f0f27d52f7015f117e") revision = loader.storage.revision_get([expected_revision_id])[0] assert revision is not None check_metadata_paths( revision.metadata, paths=[ ("intrinsic.tool", str), ("intrinsic.raw", dict), ("extrinsic.provider", str), ("extrinsic.when", str), ("extrinsic.raw", dict), ("original_artifact", list), ], ) for original_artifact in revision.metadata["original_artifact"]: check_metadata_paths( original_artifact, paths=[("filename", str), ("length", int), ("checksums", dict),], ) def test_npm_loader_first_visit(swh_config, requests_mock_datadir, org_api_info): package = "org" url = package_url(package) loader = NpmLoader(url) actual_load_status = loader.load() expected_snapshot_id = hash_to_bytes("d0587e1195aed5a8800411a008f2f2d627f18e2d") assert actual_load_status == { "status": "eventful", "snapshot_id": expected_snapshot_id.hex(), } assert_last_visit_matches( loader.storage, url, status="full", type="npm", snapshot=expected_snapshot_id ) stats = get_stats(loader.storage) assert { "content": len(_expected_new_contents_first_visit), "directory": len(_expected_new_directories_first_visit), "origin": 1, "origin_visit": 1, "release": 0, "revision": len(_expected_new_revisions_first_visit), "skipped_content": 0, "snapshot": 1, } == stats contents = loader.storage.content_get(_expected_new_contents_first_visit) count = sum(0 if content is None else 1 for content in contents) assert count == len(_expected_new_contents_first_visit) assert ( list(loader.storage.directory_missing(_expected_new_directories_first_visit)) == [] ) assert ( list(loader.storage.revision_missing(_expected_new_revisions_first_visit)) == [] ) versions = [ ("0.0.2", "d8a1c7474d2956ac598a19f0f27d52f7015f117e"), ("0.0.3", "5f9eb78af37ffd12949f235e86fac04898f9f72a"), ("0.0.4", "ba019b192bdb94bd0b5bd68b3a5f92b5acc2239a"), ] expected_snapshot = Snapshot( id=expected_snapshot_id, branches={ b"HEAD": SnapshotBranch( target=b"releases/0.0.4", target_type=TargetType.ALIAS ), **{ b"releases/" + version_name.encode(): SnapshotBranch( target=hash_to_bytes(version_id), target_type=TargetType.REVISION, ) for (version_name, version_id) in versions }, }, ) check_snapshot(expected_snapshot, loader.storage) metadata_authority = MetadataAuthority( type=MetadataAuthorityType.FORGE, url="https://npmjs.com/", ) - for (version_name, version_id) in versions: - revision_swhid = SWHID(object_type="revision", object_id=version_id,) + for (version_name, revision_id) in versions: + revision = loader.storage.revision_get([hash_to_bytes(revision_id)])[0] + directory_id = revision.directory + directory_swhid = SWHID(object_type="directory", object_id=directory_id,) + revision_swhid = SWHID(object_type="revision", object_id=revision_id,) expected_metadata = [ RawExtrinsicMetadata( - type=MetadataTargetType.REVISION, - id=revision_swhid, + type=MetadataTargetType.DIRECTORY, + id=directory_swhid, authority=metadata_authority, fetcher=MetadataFetcher( name="swh.loader.package.npm.loader.NpmLoader", version=__version__, ), discovery_date=loader.visit_date, format="replicate-npm-package-json", metadata=json.dumps( json.loads(org_api_info)["versions"][version_name] ).encode(), origin="https://www.npmjs.com/package/org", + revision=revision_swhid, ) ] assert loader.storage.raw_extrinsic_metadata_get( - type=MetadataTargetType.REVISION, - id=revision_swhid, + type=MetadataTargetType.DIRECTORY, + id=directory_swhid, authority=metadata_authority, ) == PagedResult(next_page_token=None, results=expected_metadata,) def test_npm_loader_incremental_visit(swh_config, requests_mock_datadir_visits): package = "org" url = package_url(package) loader = NpmLoader(url) expected_snapshot_id = hash_to_bytes("d0587e1195aed5a8800411a008f2f2d627f18e2d") actual_load_status = loader.load() assert actual_load_status == { "status": "eventful", "snapshot_id": expected_snapshot_id.hex(), } assert_last_visit_matches( loader.storage, url, status="full", type="npm", snapshot=expected_snapshot_id ) stats = get_stats(loader.storage) assert { "content": len(_expected_new_contents_first_visit), "directory": len(_expected_new_directories_first_visit), "origin": 1, "origin_visit": 1, "release": 0, "revision": len(_expected_new_revisions_first_visit), "skipped_content": 0, "snapshot": 1, } == stats # reset loader internal state del loader._cached_info del loader._cached__raw_info actual_load_status2 = loader.load() assert actual_load_status2["status"] == "eventful" snap_id2 = actual_load_status2["snapshot_id"] assert snap_id2 is not None assert snap_id2 != actual_load_status["snapshot_id"] assert_last_visit_matches(loader.storage, url, status="full", type="npm") stats = get_stats(loader.storage) assert { # 3 new releases artifacts "content": len(_expected_new_contents_first_visit) + 14, "directory": len(_expected_new_directories_first_visit) + 15, "origin": 1, "origin_visit": 2, "release": 0, "revision": len(_expected_new_revisions_first_visit) + 3, "skipped_content": 0, "snapshot": 2, } == stats urls = [ m.url for m in requests_mock_datadir_visits.request_history if m.url.startswith("https://registry.npmjs.org") ] assert len(urls) == len(set(urls)) # we visited each artifact once across @pytest.mark.usefixtures("requests_mock_datadir") def test_npm_loader_version_divergence(swh_config): package = "@aller_shared" url = package_url(package) loader = NpmLoader(url) actual_load_status = loader.load() expected_snapshot_id = hash_to_bytes("b11ebac8c9d0c9e5063a2df693a18e3aba4b2f92") assert actual_load_status == { "status": "eventful", "snapshot_id": expected_snapshot_id.hex(), } assert_last_visit_matches( loader.storage, url, status="full", type="npm", snapshot=expected_snapshot_id ) stats = get_stats(loader.storage) assert { # 1 new releases artifacts "content": 534, "directory": 153, "origin": 1, "origin_visit": 1, "release": 0, "revision": 2, "skipped_content": 0, "snapshot": 1, } == stats expected_snapshot = Snapshot( id=expected_snapshot_id, branches={ b"HEAD": SnapshotBranch( target_type=TargetType.ALIAS, target=b"releases/0.1.0" ), b"releases/0.1.0": SnapshotBranch( target_type=TargetType.REVISION, target=hash_to_bytes("845673bfe8cbd31b1eaf757745a964137e6f9116"), ), b"releases/0.1.1-alpha.14": SnapshotBranch( target_type=TargetType.REVISION, target=hash_to_bytes("05181c12cd8c22035dd31155656826b85745da37"), ), }, ) check_snapshot(expected_snapshot, loader.storage) def test_npm_artifact_to_revision_id_none(): """Current loader version should stop soon if nothing can be found """ class artifact_metadata: shasum = "05181c12cd8c22035dd31155656826b85745da37" known_artifacts = { "b11ebac8c9d0c9e5063a2df693a18e3aba4b2f92": {}, } assert artifact_to_revision_id(known_artifacts, artifact_metadata) is None def test_npm_artifact_to_revision_id_old_loader_version(): """Current loader version should solve old metadata scheme """ class artifact_metadata: shasum = "05181c12cd8c22035dd31155656826b85745da37" known_artifacts = { hash_to_bytes("b11ebac8c9d0c9e5063a2df693a18e3aba4b2f92"): { "package_source": {"sha1": "something-wrong"} }, hash_to_bytes("845673bfe8cbd31b1eaf757745a964137e6f9116"): { "package_source": {"sha1": "05181c12cd8c22035dd31155656826b85745da37",} }, } assert artifact_to_revision_id(known_artifacts, artifact_metadata) == hash_to_bytes( "845673bfe8cbd31b1eaf757745a964137e6f9116" ) def test_npm_artifact_to_revision_id_current_loader_version(): """Current loader version should be able to solve current metadata scheme """ class artifact_metadata: shasum = "05181c12cd8c22035dd31155656826b85745da37" known_artifacts = { hash_to_bytes("b11ebac8c9d0c9e5063a2df693a18e3aba4b2f92"): { "original_artifact": [ {"checksums": {"sha1": "05181c12cd8c22035dd31155656826b85745da37"},} ], }, hash_to_bytes("845673bfe8cbd31b1eaf757745a964137e6f9116"): { "original_artifact": [{"checksums": {"sha1": "something-wrong"},}], }, } assert artifact_to_revision_id(known_artifacts, artifact_metadata) == hash_to_bytes( "b11ebac8c9d0c9e5063a2df693a18e3aba4b2f92" ) def test_npm_artifact_with_no_intrinsic_metadata(swh_config, requests_mock_datadir): """Skip artifact with no intrinsic metadata during ingestion """ package = "nativescript-telerik-analytics" url = package_url(package) loader = NpmLoader(url) actual_load_status = loader.load() # no branch as one artifact without any intrinsic metadata expected_snapshot = Snapshot( id=hash_to_bytes("1a8893e6a86f444e8be8e7bda6cb34fb1735a00e"), branches={}, ) assert actual_load_status == { "status": "eventful", "snapshot_id": expected_snapshot.id.hex(), } check_snapshot(expected_snapshot, loader.storage) assert_last_visit_matches( loader.storage, url, status="full", type="npm", snapshot=expected_snapshot.id ) def test_npm_artifact_with_no_upload_time(swh_config, requests_mock_datadir): """With no time upload, artifact is skipped """ package = "jammit-no-time" url = package_url(package) loader = NpmLoader(url) actual_load_status = loader.load() # no branch as one artifact without any intrinsic metadata expected_snapshot = Snapshot( id=hash_to_bytes("1a8893e6a86f444e8be8e7bda6cb34fb1735a00e"), branches={}, ) assert actual_load_status == { "status": "uneventful", "snapshot_id": expected_snapshot.id.hex(), } check_snapshot(expected_snapshot, loader.storage) assert_last_visit_matches( loader.storage, url, status="partial", type="npm", snapshot=expected_snapshot.id ) def test_npm_artifact_use_mtime_if_no_time(swh_config, requests_mock_datadir): """With no time upload, artifact is skipped """ package = "jammit-express" url = package_url(package) loader = NpmLoader(url) actual_load_status = loader.load() expected_snapshot_id = hash_to_bytes("d6e08e19159f77983242877c373c75222d5ae9dd") assert actual_load_status == { "status": "eventful", "snapshot_id": expected_snapshot_id.hex(), } # artifact is used expected_snapshot = Snapshot( id=expected_snapshot_id, branches={ b"HEAD": SnapshotBranch( target_type=TargetType.ALIAS, target=b"releases/0.0.1" ), b"releases/0.0.1": SnapshotBranch( target_type=TargetType.REVISION, target=hash_to_bytes("9e4dd2b40d1b46b70917c0949aa2195c823a648e"), ), }, ) check_snapshot(expected_snapshot, loader.storage) assert_last_visit_matches( loader.storage, url, status="full", type="npm", snapshot=expected_snapshot.id ) def test_npm_no_artifact(swh_config, requests_mock_datadir): """If no artifacts at all is found for origin, the visit fails completely """ package = "catify" url = package_url(package) loader = NpmLoader(url) actual_load_status = loader.load() assert actual_load_status == { "status": "failed", } assert_last_visit_matches(loader.storage, url, status="partial", type="npm") diff --git a/swh/loader/package/pypi/loader.py b/swh/loader/package/pypi/loader.py index 619e31e..fa88084 100644 --- a/swh/loader/package/pypi/loader.py +++ b/swh/loader/package/pypi/loader.py @@ -1,284 +1,284 @@ # Copyright (C) 2019-2020 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import json import logging import os from typing import Any, Dict, Iterator, Optional, Sequence, Tuple from urllib.parse import urlparse import attr from pkginfo import UnpackedSDist from swh.loader.package.loader import ( BasePackageInfo, PackageLoader, RawExtrinsicMetadataCore, ) from swh.loader.package.utils import EMPTY_AUTHOR, api_info, cached_method, release_name from swh.model.model import ( MetadataAuthority, MetadataAuthorityType, Person, Revision, RevisionType, Sha1Git, TimestampWithTimezone, ) logger = logging.getLogger(__name__) @attr.s class PyPIPackageInfo(BasePackageInfo): raw_info = attr.ib(type=Dict[str, Any]) comment_text = attr.ib(type=Optional[str]) sha256 = attr.ib(type=str) upload_time = attr.ib(type=str) @classmethod def from_metadata(cls, metadata: Dict[str, Any]) -> "PyPIPackageInfo": return cls( url=metadata["url"], filename=metadata["filename"], raw_info=metadata, comment_text=metadata.get("comment_text"), sha256=metadata["digests"]["sha256"], upload_time=metadata["upload_time"], - revision_extrinsic_metadata=[ + directory_extrinsic_metadata=[ RawExtrinsicMetadataCore( format="pypi-project-json", metadata=json.dumps(metadata).encode(), ) ], ) class PyPILoader(PackageLoader[PyPIPackageInfo]): """Load pypi origin's artifact releases into swh archive. """ visit_type = "pypi" def __init__(self, url): super().__init__(url=url) self.provider_url = pypi_api_url(self.url) @cached_method def _raw_info(self) -> bytes: return api_info(self.provider_url) @cached_method def info(self) -> Dict: """Return the project metadata information (fetched from pypi registry) """ return json.loads(self._raw_info()) def get_versions(self) -> Sequence[str]: return self.info()["releases"].keys() def get_default_version(self) -> str: return self.info()["info"]["version"] def get_metadata_authority(self): p_url = urlparse(self.url) return MetadataAuthority( type=MetadataAuthorityType.FORGE, url=f"{p_url.scheme}://{p_url.netloc}/", metadata={}, ) def get_package_info(self, version: str) -> Iterator[Tuple[str, PyPIPackageInfo]]: res = [] for meta in self.info()["releases"][version]: if meta["packagetype"] != "sdist": continue p_info = PyPIPackageInfo.from_metadata(meta) res.append((version, p_info)) if len(res) == 1: version, p_info = res[0] yield release_name(version), p_info else: for version, p_info in res: yield release_name(version, p_info.filename), p_info def resolve_revision_from( self, known_artifacts: Dict, p_info: PyPIPackageInfo ) -> Optional[bytes]: return artifact_to_revision_id(known_artifacts, p_info) def build_revision( self, p_info: PyPIPackageInfo, uncompressed_path: str, directory: Sha1Git ) -> Optional[Revision]: i_metadata = extract_intrinsic_metadata(uncompressed_path) if not i_metadata: return None # from intrinsic metadata name = i_metadata["version"] _author = author(i_metadata) # from extrinsic metadata message = p_info.comment_text or "" message = "%s: %s" % (name, message) if message else name date = TimestampWithTimezone.from_iso8601(p_info.upload_time) return Revision( type=RevisionType.TAR, message=message.encode("utf-8"), author=_author, date=date, committer=_author, committer_date=date, parents=(), directory=directory, synthetic=True, metadata={ "intrinsic": {"tool": "PKG-INFO", "raw": i_metadata,}, "extrinsic": { "provider": self.provider_url, "when": self.visit_date.isoformat(), "raw": p_info.raw_info, }, }, ) def artifact_to_revision_id( known_artifacts: Dict, p_info: PyPIPackageInfo ) -> Optional[bytes]: """Given metadata artifact, solves the associated revision id. The following code allows to deal with 2 metadata formats (column metadata in 'revision') - old format sample:: { 'original_artifact': { 'sha256': '6975816f2c5ad4046acc676ba112f2fff945b01522d63948531f11f11e0892ec', # noqa ... }, ... } - new format sample:: { 'original_artifact': [{ 'checksums': { 'sha256': '6975816f2c5ad4046acc676ba112f2fff945b01522d63948531f11f11e0892ec', # noqa ... }, }], ... } """ sha256 = p_info.sha256 for rev_id, known_artifact in known_artifacts.items(): original_artifact = known_artifact["original_artifact"] if isinstance(original_artifact, dict): # previous loader-pypi version stored metadata as dict original_sha256 = original_artifact["sha256"] if sha256 == original_sha256: return rev_id continue # new pypi loader actually store metadata dict differently... assert isinstance(original_artifact, list) # current loader-pypi stores metadata as list of dict for original_artifact in known_artifact["original_artifact"]: if sha256 == original_artifact["checksums"]["sha256"]: return rev_id return None def pypi_api_url(url: str) -> str: """Compute api url from a project url Args: url (str): PyPI instance's url (e.g: https://pypi.org/project/requests) This deals with correctly transforming the project's api url (e.g https://pypi.org/pypi/requests/json) Returns: api url """ p_url = urlparse(url) project_name = p_url.path.rstrip("/").split("/")[-1] url = "%s://%s/pypi/%s/json" % (p_url.scheme, p_url.netloc, project_name) return url def extract_intrinsic_metadata(dir_path: str) -> Dict: """Given an uncompressed path holding the pkginfo file, returns a pkginfo parsed structure as a dict. The release artifact contains at their root one folder. For example: $ tar tvf zprint-0.0.6.tar.gz drwxr-xr-x root/root 0 2018-08-22 11:01 zprint-0.0.6/ ... Args: dir_path (str): Path to the uncompressed directory representing a release artifact from pypi. Returns: the pkginfo parsed structure as a dict if any or None if none was present. """ # Retrieve the root folder of the archive if not os.path.exists(dir_path): return {} lst = os.listdir(dir_path) if len(lst) != 1: return {} project_dirname = lst[0] pkginfo_path = os.path.join(dir_path, project_dirname, "PKG-INFO") if not os.path.exists(pkginfo_path): return {} pkginfo = UnpackedSDist(pkginfo_path) raw = pkginfo.__dict__ raw.pop("filename") # this gets added with the ondisk location return raw def author(data: Dict) -> Person: """Given a dict of project/release artifact information (coming from PyPI), returns an author subset. Args: data (dict): Representing either artifact information or release information. Returns: swh-model dict representing a person. """ name = data.get("author") email = data.get("author_email") fullname = None # type: Optional[str] if email: fullname = "%s <%s>" % (name, email) else: fullname = name if not fullname: return EMPTY_AUTHOR if name is not None: name = name.encode("utf-8") if email is not None: email = email.encode("utf-8") return Person(fullname=fullname.encode("utf-8"), name=name, email=email) diff --git a/swh/loader/package/pypi/tests/test_pypi.py b/swh/loader/package/pypi/tests/test_pypi.py index 2f91bcb..cc6db8a 100644 --- a/swh/loader/package/pypi/tests/test_pypi.py +++ b/swh/loader/package/pypi/tests/test_pypi.py @@ -1,874 +1,878 @@ # Copyright (C) 2019-2020 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import copy import json import os from os import path from unittest.mock import patch import pytest import yaml from swh.core.pytest_plugin import requests_mock_datadir_factory from swh.core.tarball import uncompress from swh.loader.package import __version__ from swh.loader.package.pypi.loader import ( PyPILoader, artifact_to_revision_id, author, extract_intrinsic_metadata, pypi_api_url, ) from swh.loader.package.tests.common import check_metadata_paths from swh.loader.tests import assert_last_visit_matches, check_snapshot, get_stats from swh.model.hashutil import hash_to_bytes, hash_to_hex from swh.model.identifiers import SWHID from swh.model.model import ( MetadataAuthority, MetadataAuthorityType, MetadataFetcher, MetadataTargetType, Person, RawExtrinsicMetadata, Snapshot, SnapshotBranch, TargetType, ) from swh.storage.interface import PagedResult @pytest.fixture def _0805nexter_api_info(datadir) -> bytes: with open( os.path.join(datadir, "https_pypi.org", "pypi_0805nexter_json"), "rb", ) as f: return f.read() def test_author_basic(): data = { "author": "i-am-groot", "author_email": "iam@groot.org", } actual_author = author(data) expected_author = Person( fullname=b"i-am-groot ", name=b"i-am-groot", email=b"iam@groot.org", ) assert actual_author == expected_author def test_author_empty_email(): data = { "author": "i-am-groot", "author_email": "", } actual_author = author(data) expected_author = Person(fullname=b"i-am-groot", name=b"i-am-groot", email=b"",) assert actual_author == expected_author def test_author_empty_name(): data = { "author": "", "author_email": "iam@groot.org", } actual_author = author(data) expected_author = Person( fullname=b" ", name=b"", email=b"iam@groot.org", ) assert actual_author == expected_author def test_author_malformed(): data = { "author": "['pierre', 'paul', 'jacques']", "author_email": None, } actual_author = author(data) expected_author = Person( fullname=b"['pierre', 'paul', 'jacques']", name=b"['pierre', 'paul', 'jacques']", email=None, ) assert actual_author == expected_author def test_author_malformed_2(): data = { "author": "[marie, jeanne]", "author_email": "[marie@some, jeanne@thing]", } actual_author = author(data) expected_author = Person( fullname=b"[marie, jeanne] <[marie@some, jeanne@thing]>", name=b"[marie, jeanne]", email=b"[marie@some, jeanne@thing]", ) assert actual_author == expected_author def test_author_malformed_3(): data = { "author": "[marie, jeanne, pierre]", "author_email": "[marie@somewhere.org, jeanne@somewhere.org]", } actual_author = author(data) expected_author = Person( fullname=( b"[marie, jeanne, pierre] " b"<[marie@somewhere.org, jeanne@somewhere.org]>" ), name=b"[marie, jeanne, pierre]", email=b"[marie@somewhere.org, jeanne@somewhere.org]", ) actual_author == expected_author # configuration error # def test_badly_configured_loader_raise(tmp_path, swh_loader_config, monkeypatch): """Badly configured loader should raise""" wrong_config = copy.deepcopy(swh_loader_config) wrong_config.pop("storage") conf_path = os.path.join(str(tmp_path), "loader.yml") with open(conf_path, "w") as f: f.write(yaml.dump(wrong_config)) monkeypatch.setenv("SWH_CONFIG_FILENAME", conf_path) with pytest.raises(ValueError, match="Misconfiguration"): PyPILoader(url="some-url") def test_pypi_api_url(): """Compute pypi api url from the pypi project url should be ok""" url = pypi_api_url("https://pypi.org/project/requests") assert url == "https://pypi.org/pypi/requests/json" def test_pypi_api_url_with_slash(): """Compute pypi api url from the pypi project url should be ok""" url = pypi_api_url("https://pypi.org/project/requests/") assert url == "https://pypi.org/pypi/requests/json" @pytest.mark.fs def test_extract_intrinsic_metadata(tmp_path, datadir): """Parsing existing archive's PKG-INFO should yield results""" uncompressed_archive_path = str(tmp_path) archive_path = path.join( datadir, "https_files.pythonhosted.org", "0805nexter-1.1.0.zip" ) uncompress(archive_path, dest=uncompressed_archive_path) actual_metadata = extract_intrinsic_metadata(uncompressed_archive_path) expected_metadata = { "metadata_version": "1.0", "name": "0805nexter", "version": "1.1.0", "summary": "a simple printer of nested lest", "home_page": "http://www.hp.com", "author": "hgtkpython", "author_email": "2868989685@qq.com", "platforms": ["UNKNOWN"], } assert actual_metadata == expected_metadata @pytest.mark.fs def test_extract_intrinsic_metadata_failures(tmp_path): """Parsing inexistent path/archive/PKG-INFO yield None""" tmp_path = str(tmp_path) # py3.5 work around (PosixPath issue) # inexistent first level path assert extract_intrinsic_metadata("/something-inexistent") == {} # inexistent second level path (as expected by pypi archives) assert extract_intrinsic_metadata(tmp_path) == {} # inexistent PKG-INFO within second level path existing_path_no_pkginfo = path.join(tmp_path, "something") os.mkdir(existing_path_no_pkginfo) assert extract_intrinsic_metadata(tmp_path) == {} # LOADER SCENARIO # # "edge" cases (for the same origin) # # no release artifact: # {visit full, status: uneventful, no contents, etc...} requests_mock_datadir_missing_all = requests_mock_datadir_factory( ignore_urls=[ "https://files.pythonhosted.org/packages/ec/65/c0116953c9a3f47de89e71964d6c7b0c783b01f29fa3390584dbf3046b4d/0805nexter-1.1.0.zip", # noqa "https://files.pythonhosted.org/packages/c4/a0/4562cda161dc4ecbbe9e2a11eb365400c0461845c5be70d73869786809c4/0805nexter-1.2.0.zip", # noqa ] ) def test_no_release_artifact(swh_config, requests_mock_datadir_missing_all): """Load a pypi project with all artifacts missing ends up with no snapshot """ url = "https://pypi.org/project/0805nexter" loader = PyPILoader(url) actual_load_status = loader.load() assert actual_load_status["status"] == "uneventful" assert actual_load_status["snapshot_id"] is not None stats = get_stats(loader.storage) assert { "content": 0, "directory": 0, "origin": 1, "origin_visit": 1, "release": 0, "revision": 0, "skipped_content": 0, "snapshot": 1, } == stats assert_last_visit_matches(loader.storage, url, status="partial", type="pypi") # problem during loading: # {visit: partial, status: uneventful, no snapshot} def test_release_with_traceback(swh_config, requests_mock_datadir): url = "https://pypi.org/project/0805nexter" with patch( "swh.loader.package.pypi.loader.PyPILoader.last_snapshot", side_effect=ValueError("Fake problem to fail the visit"), ): loader = PyPILoader(url) actual_load_status = loader.load() assert actual_load_status == {"status": "failed"} stats = get_stats(loader.storage) assert { "content": 0, "directory": 0, "origin": 1, "origin_visit": 1, "release": 0, "revision": 0, "skipped_content": 0, "snapshot": 0, } == stats assert_last_visit_matches(loader.storage, url, status="partial", type="pypi") # problem during loading: failure early enough in between swh contents... # some contents (contents, directories, etc...) have been written in storage # {visit: partial, status: eventful, no snapshot} # problem during loading: failure late enough we can have snapshots (some # revisions are written in storage already) # {visit: partial, status: eventful, snapshot} # "normal" cases (for the same origin) # requests_mock_datadir_missing_one = requests_mock_datadir_factory( ignore_urls=[ "https://files.pythonhosted.org/packages/ec/65/c0116953c9a3f47de89e71964d6c7b0c783b01f29fa3390584dbf3046b4d/0805nexter-1.1.0.zip", # noqa ] ) # some missing release artifacts: # {visit partial, status: eventful, 1 snapshot} def test_revision_metadata_structure( swh_config, requests_mock_datadir, _0805nexter_api_info ): url = "https://pypi.org/project/0805nexter" loader = PyPILoader(url) actual_load_status = loader.load() assert actual_load_status["status"] == "eventful" assert actual_load_status["snapshot_id"] is not None expected_revision_id = hash_to_bytes("e445da4da22b31bfebb6ffc4383dbf839a074d21") revision = loader.storage.revision_get([expected_revision_id])[0] assert revision is not None check_metadata_paths( revision.metadata, paths=[ ("intrinsic.tool", str), ("intrinsic.raw", dict), ("extrinsic.provider", str), ("extrinsic.when", str), ("extrinsic.raw", dict), ("original_artifact", list), ], ) for original_artifact in revision.metadata["original_artifact"]: check_metadata_paths( original_artifact, paths=[("filename", str), ("length", int), ("checksums", dict),], ) revision_swhid = SWHID( object_type="revision", object_id=hash_to_hex(expected_revision_id) ) + directory_swhid = SWHID( + object_type="directory", object_id=hash_to_hex(revision.directory) + ) metadata_authority = MetadataAuthority( type=MetadataAuthorityType.FORGE, url="https://pypi.org/", ) expected_metadata = [ RawExtrinsicMetadata( - type=MetadataTargetType.REVISION, - id=revision_swhid, + type=MetadataTargetType.DIRECTORY, + id=directory_swhid, authority=metadata_authority, fetcher=MetadataFetcher( name="swh.loader.package.pypi.loader.PyPILoader", version=__version__, ), discovery_date=loader.visit_date, format="pypi-project-json", metadata=json.dumps( json.loads(_0805nexter_api_info)["releases"]["1.2.0"][0] ).encode(), origin=url, + revision=revision_swhid, ) ] assert loader.storage.raw_extrinsic_metadata_get( - type=MetadataTargetType.REVISION, - id=revision_swhid, + type=MetadataTargetType.DIRECTORY, + id=directory_swhid, authority=metadata_authority, ) == PagedResult(next_page_token=None, results=expected_metadata,) def test_visit_with_missing_artifact(swh_config, requests_mock_datadir_missing_one): """Load a pypi project with some missing artifacts ends up with 1 snapshot """ url = "https://pypi.org/project/0805nexter" loader = PyPILoader(url) actual_load_status = loader.load() expected_snapshot_id = hash_to_bytes("dd0e4201a232b1c104433741dbf45895b8ac9355") assert actual_load_status == { "status": "eventful", "snapshot_id": expected_snapshot_id.hex(), } stats = get_stats(loader.storage) assert { "content": 3, "directory": 2, "origin": 1, "origin_visit": 1, "release": 0, "revision": 1, "skipped_content": 0, "snapshot": 1, } == stats expected_contents = map( hash_to_bytes, [ "405859113963cb7a797642b45f171d6360425d16", "e5686aa568fdb1d19d7f1329267082fe40482d31", "83ecf6ec1114fd260ca7a833a2d165e71258c338", ], ) assert list(loader.storage.content_missing_per_sha1(expected_contents)) == [] expected_dirs = map( hash_to_bytes, [ "b178b66bd22383d5f16f4f5c923d39ca798861b4", "c3a58f8b57433a4b56caaa5033ae2e0931405338", ], ) assert list(loader.storage.directory_missing(expected_dirs)) == [] # {revision hash: directory hash} expected_revs = { hash_to_bytes("e445da4da22b31bfebb6ffc4383dbf839a074d21"): hash_to_bytes( "b178b66bd22383d5f16f4f5c923d39ca798861b4" ), # noqa } assert list(loader.storage.revision_missing(expected_revs)) == [] expected_snapshot = Snapshot( id=hash_to_bytes(expected_snapshot_id), branches={ b"releases/1.2.0": SnapshotBranch( target=hash_to_bytes("e445da4da22b31bfebb6ffc4383dbf839a074d21"), target_type=TargetType.REVISION, ), b"HEAD": SnapshotBranch( target=b"releases/1.2.0", target_type=TargetType.ALIAS, ), }, ) check_snapshot(expected_snapshot, storage=loader.storage) assert_last_visit_matches( loader.storage, url, status="partial", type="pypi", snapshot=expected_snapshot_id, ) def test_visit_with_1_release_artifact(swh_config, requests_mock_datadir): """With no prior visit, load a pypi project ends up with 1 snapshot """ url = "https://pypi.org/project/0805nexter" loader = PyPILoader(url) actual_load_status = loader.load() expected_snapshot_id = hash_to_bytes("ba6e158ada75d0b3cfb209ffdf6daa4ed34a227a") assert actual_load_status == { "status": "eventful", "snapshot_id": expected_snapshot_id.hex(), } stats = get_stats(loader.storage) assert { "content": 6, "directory": 4, "origin": 1, "origin_visit": 1, "release": 0, "revision": 2, "skipped_content": 0, "snapshot": 1, } == stats expected_contents = map( hash_to_bytes, [ "a61e24cdfdab3bb7817f6be85d37a3e666b34566", "938c33483285fd8ad57f15497f538320df82aeb8", "a27576d60e08c94a05006d2e6d540c0fdb5f38c8", "405859113963cb7a797642b45f171d6360425d16", "e5686aa568fdb1d19d7f1329267082fe40482d31", "83ecf6ec1114fd260ca7a833a2d165e71258c338", ], ) assert list(loader.storage.content_missing_per_sha1(expected_contents)) == [] expected_dirs = map( hash_to_bytes, [ "05219ba38bc542d4345d5638af1ed56c7d43ca7d", "cf019eb456cf6f78d8c4674596f1c9a97ece8f44", "b178b66bd22383d5f16f4f5c923d39ca798861b4", "c3a58f8b57433a4b56caaa5033ae2e0931405338", ], ) assert list(loader.storage.directory_missing(expected_dirs)) == [] # {revision hash: directory hash} expected_revs = { hash_to_bytes("4c99891f93b81450385777235a37b5e966dd1571"): hash_to_bytes( "05219ba38bc542d4345d5638af1ed56c7d43ca7d" ), # noqa hash_to_bytes("e445da4da22b31bfebb6ffc4383dbf839a074d21"): hash_to_bytes( "b178b66bd22383d5f16f4f5c923d39ca798861b4" ), # noqa } assert list(loader.storage.revision_missing(expected_revs)) == [] expected_snapshot = Snapshot( id=expected_snapshot_id, branches={ b"releases/1.1.0": SnapshotBranch( target=hash_to_bytes("4c99891f93b81450385777235a37b5e966dd1571"), target_type=TargetType.REVISION, ), b"releases/1.2.0": SnapshotBranch( target=hash_to_bytes("e445da4da22b31bfebb6ffc4383dbf839a074d21"), target_type=TargetType.REVISION, ), b"HEAD": SnapshotBranch( target=b"releases/1.2.0", target_type=TargetType.ALIAS, ), }, ) check_snapshot(expected_snapshot, loader.storage) assert_last_visit_matches( loader.storage, url, status="full", type="pypi", snapshot=expected_snapshot_id ) def test_multiple_visits_with_no_change(swh_config, requests_mock_datadir): """Multiple visits with no changes results in 1 same snapshot """ url = "https://pypi.org/project/0805nexter" loader = PyPILoader(url) actual_load_status = loader.load() snapshot_id = hash_to_bytes("ba6e158ada75d0b3cfb209ffdf6daa4ed34a227a") assert actual_load_status == { "status": "eventful", "snapshot_id": snapshot_id.hex(), } assert_last_visit_matches( loader.storage, url, status="full", type="pypi", snapshot=snapshot_id ) stats = get_stats(loader.storage) assert { "content": 6, "directory": 4, "origin": 1, "origin_visit": 1, "release": 0, "revision": 2, "skipped_content": 0, "snapshot": 1, } == stats expected_snapshot = Snapshot( id=snapshot_id, branches={ b"releases/1.1.0": SnapshotBranch( target=hash_to_bytes("4c99891f93b81450385777235a37b5e966dd1571"), target_type=TargetType.REVISION, ), b"releases/1.2.0": SnapshotBranch( target=hash_to_bytes("e445da4da22b31bfebb6ffc4383dbf839a074d21"), target_type=TargetType.REVISION, ), b"HEAD": SnapshotBranch( target=b"releases/1.2.0", target_type=TargetType.ALIAS, ), }, ) check_snapshot(expected_snapshot, loader.storage) actual_load_status2 = loader.load() assert actual_load_status2 == { "status": "uneventful", "snapshot_id": actual_load_status2["snapshot_id"], } visit_status2 = assert_last_visit_matches( loader.storage, url, status="full", type="pypi" ) stats2 = get_stats(loader.storage) expected_stats2 = stats.copy() expected_stats2["origin_visit"] = 1 + 1 assert expected_stats2 == stats2 # same snapshot assert visit_status2.snapshot == snapshot_id def test_incremental_visit(swh_config, requests_mock_datadir_visits): """With prior visit, 2nd load will result with a different snapshot """ url = "https://pypi.org/project/0805nexter" loader = PyPILoader(url) visit1_actual_load_status = loader.load() visit1_stats = get_stats(loader.storage) expected_snapshot_id = hash_to_bytes("ba6e158ada75d0b3cfb209ffdf6daa4ed34a227a") assert visit1_actual_load_status == { "status": "eventful", "snapshot_id": expected_snapshot_id.hex(), } assert_last_visit_matches( loader.storage, url, status="full", type="pypi", snapshot=expected_snapshot_id ) assert { "content": 6, "directory": 4, "origin": 1, "origin_visit": 1, "release": 0, "revision": 2, "skipped_content": 0, "snapshot": 1, } == visit1_stats # Reset internal state del loader._cached__raw_info del loader._cached_info visit2_actual_load_status = loader.load() visit2_stats = get_stats(loader.storage) assert visit2_actual_load_status["status"] == "eventful", visit2_actual_load_status expected_snapshot_id2 = hash_to_bytes("2e5149a7b0725d18231a37b342e9b7c4e121f283") assert visit2_actual_load_status == { "status": "eventful", "snapshot_id": expected_snapshot_id2.hex(), } assert_last_visit_matches( loader.storage, url, status="full", type="pypi", snapshot=expected_snapshot_id2 ) assert { "content": 6 + 1, # 1 more content "directory": 4 + 2, # 2 more directories "origin": 1, "origin_visit": 1 + 1, "release": 0, "revision": 2 + 1, # 1 more revision "skipped_content": 0, "snapshot": 1 + 1, # 1 more snapshot } == visit2_stats expected_contents = map( hash_to_bytes, [ "a61e24cdfdab3bb7817f6be85d37a3e666b34566", "938c33483285fd8ad57f15497f538320df82aeb8", "a27576d60e08c94a05006d2e6d540c0fdb5f38c8", "405859113963cb7a797642b45f171d6360425d16", "e5686aa568fdb1d19d7f1329267082fe40482d31", "83ecf6ec1114fd260ca7a833a2d165e71258c338", "92689fa2b7fb4d4fc6fb195bf73a50c87c030639", ], ) assert list(loader.storage.content_missing_per_sha1(expected_contents)) == [] expected_dirs = map( hash_to_bytes, [ "05219ba38bc542d4345d5638af1ed56c7d43ca7d", "cf019eb456cf6f78d8c4674596f1c9a97ece8f44", "b178b66bd22383d5f16f4f5c923d39ca798861b4", "c3a58f8b57433a4b56caaa5033ae2e0931405338", "e226e7e4ad03b4fc1403d69a18ebdd6f2edd2b3a", "52604d46843b898f5a43208045d09fcf8731631b", ], ) assert list(loader.storage.directory_missing(expected_dirs)) == [] # {revision hash: directory hash} expected_revs = { hash_to_bytes("4c99891f93b81450385777235a37b5e966dd1571"): hash_to_bytes( "05219ba38bc542d4345d5638af1ed56c7d43ca7d" ), # noqa hash_to_bytes("e445da4da22b31bfebb6ffc4383dbf839a074d21"): hash_to_bytes( "b178b66bd22383d5f16f4f5c923d39ca798861b4" ), # noqa hash_to_bytes("51247143b01445c9348afa9edfae31bf7c5d86b1"): hash_to_bytes( "e226e7e4ad03b4fc1403d69a18ebdd6f2edd2b3a" ), # noqa } assert list(loader.storage.revision_missing(expected_revs)) == [] expected_snapshot = Snapshot( id=expected_snapshot_id2, branches={ b"releases/1.1.0": SnapshotBranch( target=hash_to_bytes("4c99891f93b81450385777235a37b5e966dd1571"), target_type=TargetType.REVISION, ), b"releases/1.2.0": SnapshotBranch( target=hash_to_bytes("e445da4da22b31bfebb6ffc4383dbf839a074d21"), target_type=TargetType.REVISION, ), b"releases/1.3.0": SnapshotBranch( target=hash_to_bytes("51247143b01445c9348afa9edfae31bf7c5d86b1"), target_type=TargetType.REVISION, ), b"HEAD": SnapshotBranch( target=b"releases/1.3.0", target_type=TargetType.ALIAS, ), }, ) check_snapshot(expected_snapshot, loader.storage) assert_last_visit_matches( loader.storage, url, status="full", type="pypi", snapshot=expected_snapshot.id ) urls = [ m.url for m in requests_mock_datadir_visits.request_history if m.url.startswith("https://files.pythonhosted.org") ] # visited each artifact once across 2 visits assert len(urls) == len(set(urls)) # release artifact, no new artifact # {visit full, status uneventful, same snapshot as before} # release artifact, old artifact with different checksums # {visit full, status full, new snapshot with shared history and some new # different history} # release with multiple sdist artifacts per pypi "version" # snapshot branch output is different def test_visit_1_release_with_2_artifacts(swh_config, requests_mock_datadir): """With no prior visit, load a pypi project ends up with 1 snapshot """ url = "https://pypi.org/project/nexter" loader = PyPILoader(url) actual_load_status = loader.load() expected_snapshot_id = hash_to_bytes("a27e638a4dad6fbfa273c6ebec1c4bf320fb84c6") assert actual_load_status == { "status": "eventful", "snapshot_id": expected_snapshot_id.hex(), } expected_snapshot = Snapshot( id=expected_snapshot_id, branches={ b"releases/1.1.0/nexter-1.1.0.zip": SnapshotBranch( target=hash_to_bytes("4c99891f93b81450385777235a37b5e966dd1571"), target_type=TargetType.REVISION, ), b"releases/1.1.0/nexter-1.1.0.tar.gz": SnapshotBranch( target=hash_to_bytes("0bf88f5760cca7665d0af4d6575d9301134fe11a"), target_type=TargetType.REVISION, ), }, ) check_snapshot(expected_snapshot, loader.storage) assert_last_visit_matches( loader.storage, url, status="full", type="pypi", snapshot=expected_snapshot.id ) def test_pypi_artifact_to_revision_id_none(): """Current loader version should stop soon if nothing can be found """ class artifact_metadata: sha256 = "6975816f2c5ad4046acc676ba112f2fff945b01522d63948531f11f11e0892ec" assert artifact_to_revision_id({}, artifact_metadata) is None known_artifacts = { "b11ebac8c9d0c9e5063a2df693a18e3aba4b2f92": { "original_artifact": {"sha256": "something-irrelevant",}, }, } assert artifact_to_revision_id(known_artifacts, artifact_metadata) is None def test_pypi_artifact_to_revision_id_old_loader_version(): """Current loader version should solve old metadata scheme """ class artifact_metadata: sha256 = "6975816f2c5ad4046acc676ba112f2fff945b01522d63948531f11f11e0892ec" known_artifacts = { hash_to_bytes("b11ebac8c9d0c9e5063a2df693a18e3aba4b2f92"): { "original_artifact": {"sha256": "something-wrong",}, }, hash_to_bytes("845673bfe8cbd31b1eaf757745a964137e6f9116"): { "original_artifact": { "sha256": "6975816f2c5ad4046acc676ba112f2fff945b01522d63948531f11f11e0892ec", # noqa }, }, } assert artifact_to_revision_id(known_artifacts, artifact_metadata) == hash_to_bytes( "845673bfe8cbd31b1eaf757745a964137e6f9116" ) def test_pypi_artifact_to_revision_id_current_loader_version(): """Current loader version should be able to solve current metadata scheme """ class artifact_metadata: sha256 = "6975816f2c5ad4046acc676ba112f2fff945b01522d63948531f11f11e0892ec" known_artifacts = { hash_to_bytes("b11ebac8c9d0c9e5063a2df693a18e3aba4b2f92"): { "original_artifact": [ { "checksums": { "sha256": "6975816f2c5ad4046acc676ba112f2fff945b01522d63948531f11f11e0892ec", # noqa }, } ], }, hash_to_bytes("845673bfe8cbd31b1eaf757745a964137e6f9116"): { "original_artifact": [{"checksums": {"sha256": "something-wrong"},}], }, } assert artifact_to_revision_id(known_artifacts, artifact_metadata) == hash_to_bytes( "b11ebac8c9d0c9e5063a2df693a18e3aba4b2f92" ) def test_pypi_artifact_with_no_intrinsic_metadata(swh_config, requests_mock_datadir): """Skip artifact with no intrinsic metadata during ingestion """ url = "https://pypi.org/project/upymenu" loader = PyPILoader(url) actual_load_status = loader.load() expected_snapshot_id = hash_to_bytes("1a8893e6a86f444e8be8e7bda6cb34fb1735a00e") assert actual_load_status == { "status": "eventful", "snapshot_id": expected_snapshot_id.hex(), } # no branch as one artifact without any intrinsic metadata expected_snapshot = Snapshot(id=expected_snapshot_id, branches={}) check_snapshot(expected_snapshot, loader.storage) assert_last_visit_matches( loader.storage, url, status="full", type="pypi", snapshot=expected_snapshot.id ) diff --git a/swh/loader/package/tests/test_loader_metadata.py b/swh/loader/package/tests/test_loader_metadata.py index b409d77..8fe22e2 100644 --- a/swh/loader/package/tests/test_loader_metadata.py +++ b/swh/loader/package/tests/test_loader_metadata.py @@ -1,242 +1,246 @@ # Copyright (C) 2019-2020 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import datetime from typing import Iterator, List, Sequence, Tuple import attr from swh.loader.package import __version__ from swh.loader.package.loader import ( BasePackageInfo, PackageLoader, RawExtrinsicMetadataCore, ) from swh.model.hashutil import hash_to_bytes from swh.model.identifiers import SWHID from swh.model.model import ( MetadataAuthority, MetadataAuthorityType, MetadataFetcher, MetadataTargetType, Person, RawExtrinsicMetadata, Revision, RevisionType, Sha1Git, ) from swh.storage import get_storage EMPTY_SNAPSHOT_ID = "1a8893e6a86f444e8be8e7bda6cb34fb1735a00e" FULL_SNAPSHOT_ID = "4a9b608c9f01860a627237dd2409d1d50ec4b054" AUTHORITY = MetadataAuthority( type=MetadataAuthorityType.FORGE, url="http://example.org/", ) ORIGIN_URL = "http://example.org/archive.tgz" REVISION_ID = hash_to_bytes("8ff44f081d43176474b267de5451f2c2e88089d0") REVISION_SWHID = SWHID(object_type="revision", object_id=REVISION_ID) +DIRECTORY_ID = hash_to_bytes("aa" * 20) +DIRECTORY_SWHID = SWHID(object_type="directory", object_id=DIRECTORY_ID) FETCHER = MetadataFetcher( name="swh.loader.package.tests.test_loader_metadata.MetadataTestLoader", version=__version__, ) DISCOVERY_DATE = datetime.datetime.now(tz=datetime.timezone.utc) -REVISION_METADATA = [ +DIRECTORY_METADATA = [ RawExtrinsicMetadata( - type=MetadataTargetType.REVISION, - id=REVISION_SWHID, + type=MetadataTargetType.DIRECTORY, + id=DIRECTORY_SWHID, discovery_date=DISCOVERY_DATE, authority=AUTHORITY, fetcher=FETCHER, format="test-format1", metadata=b"foo bar", origin=ORIGIN_URL, + revision=REVISION_SWHID, ), RawExtrinsicMetadata( - type=MetadataTargetType.REVISION, - id=REVISION_SWHID, + type=MetadataTargetType.DIRECTORY, + id=DIRECTORY_SWHID, discovery_date=DISCOVERY_DATE + datetime.timedelta(seconds=1), authority=AUTHORITY, fetcher=FETCHER, format="test-format2", metadata=b"bar baz", origin=ORIGIN_URL, + revision=REVISION_SWHID, ), ] ORIGIN_METADATA = [ RawExtrinsicMetadata( type=MetadataTargetType.ORIGIN, id=ORIGIN_URL, discovery_date=datetime.datetime.now(tz=datetime.timezone.utc), authority=AUTHORITY, fetcher=FETCHER, format="test-format3", metadata=b"baz qux", ), ] class MetadataTestLoader(PackageLoader[BasePackageInfo]): def get_versions(self) -> Sequence[str]: return ["v1.0.0"] def _load_directory(self, dl_artifacts, tmpdir): class directory: - hash = None + hash = DIRECTORY_ID return (None, directory) # just enough for _load_revision to work def download_package(self, p_info: BasePackageInfo, tmpdir: str): return [("path", {"artifact_key": "value", "length": 0})] def build_revision( self, p_info: BasePackageInfo, uncompressed_path: str, directory: Sha1Git ): return Revision( id=REVISION_ID, message=b"", author=Person.from_fullname(b""), committer=Person.from_fullname(b""), date=None, committer_date=None, type=RevisionType.TAR, directory=b"foo", synthetic=False, ) def get_metadata_authority(self): return attr.evolve(AUTHORITY, metadata={}) def get_package_info(self, version: str) -> Iterator[Tuple[str, BasePackageInfo]]: - m0 = REVISION_METADATA[0] - m1 = REVISION_METADATA[1] + m0 = DIRECTORY_METADATA[0] + m1 = DIRECTORY_METADATA[1] p_info = BasePackageInfo( url=ORIGIN_URL, filename="archive.tgz", - revision_extrinsic_metadata=[ + directory_extrinsic_metadata=[ RawExtrinsicMetadataCore(m0.format, m0.metadata, m0.discovery_date), RawExtrinsicMetadataCore(m1.format, m1.metadata, m1.discovery_date), ], ) yield (version, p_info) def get_extrinsic_origin_metadata(self) -> List[RawExtrinsicMetadataCore]: m = ORIGIN_METADATA[0] return [RawExtrinsicMetadataCore(m.format, m.metadata, m.discovery_date)] def test_load_artifact_metadata(swh_config, caplog): storage = get_storage("memory") loader = MetadataTestLoader(ORIGIN_URL) loader.storage = storage load_status = loader.load() assert load_status == { "status": "eventful", "snapshot_id": FULL_SNAPSHOT_ID, } authority = MetadataAuthority( type=MetadataAuthorityType.REGISTRY, url="https://softwareheritage.org/", ) result = storage.raw_extrinsic_metadata_get( MetadataTargetType.REVISION, REVISION_SWHID, authority, ) assert result.next_page_token is None assert len(result.results) == 1 assert result.results[0] == RawExtrinsicMetadata( type=MetadataTargetType.REVISION, id=REVISION_SWHID, discovery_date=result.results[0].discovery_date, authority=authority, fetcher=FETCHER, format="original-artifacts-json", metadata=b'[{"artifact_key": "value", "length": 0}]', origin=ORIGIN_URL, ) def test_load_metadata(swh_config, caplog): storage = get_storage("memory") loader = MetadataTestLoader(ORIGIN_URL) loader.storage = storage load_status = loader.load() assert load_status == { "status": "eventful", "snapshot_id": FULL_SNAPSHOT_ID, } result = storage.raw_extrinsic_metadata_get( - MetadataTargetType.REVISION, REVISION_SWHID, AUTHORITY, + MetadataTargetType.DIRECTORY, DIRECTORY_SWHID, AUTHORITY, ) assert result.next_page_token is None - assert result.results == REVISION_METADATA + assert result.results == DIRECTORY_METADATA result = storage.raw_extrinsic_metadata_get( MetadataTargetType.ORIGIN, ORIGIN_URL, AUTHORITY, ) assert result.next_page_token is None assert result.results == ORIGIN_METADATA assert caplog.text == "" def test_existing_authority(swh_config, caplog): storage = get_storage("memory") loader = MetadataTestLoader(ORIGIN_URL) loader.storage = storage loader.config["create_authorities"] = False storage.metadata_authority_add([attr.evolve(AUTHORITY, metadata={})]) load_status = loader.load() assert load_status == { "status": "eventful", "snapshot_id": FULL_SNAPSHOT_ID, } result = storage.raw_extrinsic_metadata_get( - MetadataTargetType.REVISION, REVISION_SWHID, AUTHORITY, + MetadataTargetType.DIRECTORY, DIRECTORY_SWHID, AUTHORITY, ) assert result.next_page_token is None - assert result.results == REVISION_METADATA + assert result.results == DIRECTORY_METADATA assert caplog.text == "" def test_existing_fetcher(swh_config, caplog): storage = get_storage("memory") loader = MetadataTestLoader(ORIGIN_URL) loader.storage = storage loader.config["create_fetchers"] = False storage.metadata_fetcher_add([attr.evolve(FETCHER, metadata={})]) load_status = loader.load() assert load_status == { "status": "eventful", "snapshot_id": FULL_SNAPSHOT_ID, } result = storage.raw_extrinsic_metadata_get( - MetadataTargetType.REVISION, REVISION_SWHID, AUTHORITY, + MetadataTargetType.DIRECTORY, DIRECTORY_SWHID, AUTHORITY, ) assert result.next_page_token is None - assert result.results == REVISION_METADATA + assert result.results == DIRECTORY_METADATA assert caplog.text == ""