diff --git a/PKG-INFO b/PKG-INFO index df3645f..8f0707c 100644 --- a/PKG-INFO +++ b/PKG-INFO @@ -1,29 +1,29 @@ Metadata-Version: 2.1 Name: swh.loader.core -Version: 0.0.49 +Version: 0.0.50 Summary: Software Heritage Base Loader Home-page: https://forge.softwareheritage.org/diffusion/DLDBASE Author: Software Heritage developers Author-email: swh-devel@inria.fr License: UNKNOWN Project-URL: Bug Reports, https://forge.softwareheritage.org/maniphest Project-URL: Funding, https://www.softwareheritage.org/donate Project-URL: Source, https://forge.softwareheritage.org/source/swh-loader-core Description: SWH-loader-core =============== The Software Heritage Core Loader is a low-level loading utilities and helpers used by other loaders. The main entry points are classes: - :class:`swh.loader.core.loader.SWHLoader` for stateful loaders - :class:`swh.loader.core.loader.SWHStatelessLoader` for stateless loaders Platform: UNKNOWN Classifier: Programming Language :: Python :: 3 Classifier: Intended Audience :: Developers Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3) Classifier: Operating System :: OS Independent Classifier: Development Status :: 5 - Production/Stable Description-Content-Type: text/markdown Provides-Extra: testing diff --git a/swh.loader.core.egg-info/PKG-INFO b/swh.loader.core.egg-info/PKG-INFO index df3645f..8f0707c 100644 --- a/swh.loader.core.egg-info/PKG-INFO +++ b/swh.loader.core.egg-info/PKG-INFO @@ -1,29 +1,29 @@ Metadata-Version: 2.1 Name: swh.loader.core -Version: 0.0.49 +Version: 0.0.50 Summary: Software Heritage Base Loader Home-page: https://forge.softwareheritage.org/diffusion/DLDBASE Author: Software Heritage developers Author-email: swh-devel@inria.fr License: UNKNOWN Project-URL: Bug Reports, https://forge.softwareheritage.org/maniphest Project-URL: Funding, https://www.softwareheritage.org/donate Project-URL: Source, https://forge.softwareheritage.org/source/swh-loader-core Description: SWH-loader-core =============== The Software Heritage Core Loader is a low-level loading utilities and helpers used by other loaders. The main entry points are classes: - :class:`swh.loader.core.loader.SWHLoader` for stateful loaders - :class:`swh.loader.core.loader.SWHStatelessLoader` for stateless loaders Platform: UNKNOWN Classifier: Programming Language :: Python :: 3 Classifier: Intended Audience :: Developers Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3) Classifier: Operating System :: OS Independent Classifier: Development Status :: 5 - Production/Stable Description-Content-Type: text/markdown Provides-Extra: testing diff --git a/swh/loader/package/debian.py b/swh/loader/package/debian.py index cb76800..d89cc05 100644 --- a/swh/loader/package/debian.py +++ b/swh/loader/package/debian.py @@ -1,394 +1,394 @@ # Copyright (C) 2017-2019 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 email.utils import iso8601 import logging import re import subprocess from dateutil.parser import parse as parse_date from debian.changelog import Changelog from debian.deb822 import Dsc from os import path from typing import ( Any, Dict, Generator, List, Mapping, Optional, Sequence, Tuple ) from swh.loader.package.loader import PackageLoader from swh.loader.package.utils import download, release_name logger = logging.getLogger(__name__) UPLOADERS_SPLIT = re.compile(r'(?<=\>)\s*,\s*') class DebianLoader(PackageLoader): """Load debian origins into swh archive. """ - visit_type = 'debian' + visit_type = 'deb' def __init__(self, url: str, date: str, packages: Mapping[str, Any]): """Debian Loader implementation. Args: url: Origin url (e.g. deb://Debian/packages/cicero) date: Ignored packages: versioned packages and associated artifacts, example:: { 'stretch/contrib/0.7.2-3': { 'name': 'cicero', 'version': '0.7.2-3' 'files': { 'cicero_0.7.2-3.diff.gz': { 'md5sum': 'a93661b6a48db48d59ba7d26796fc9ce', 'name': 'cicero_0.7.2-3.diff.gz', 'sha256': 'f039c9642fe15c75bed5254315e2a29f...', 'size': 3964, 'uri': 'http://d.d.o/cicero_0.7.2-3.diff.gz', }, 'cicero_0.7.2-3.dsc': { 'md5sum': 'd5dac83eb9cfc9bb52a15eb618b4670a', 'name': 'cicero_0.7.2-3.dsc', 'sha256': '35b7f1048010c67adfd8d70e4961aefb...', 'size': 1864, 'uri': 'http://d.d.o/cicero_0.7.2-3.dsc', }, 'cicero_0.7.2.orig.tar.gz': { 'md5sum': '4353dede07c5728319ba7f5595a7230a', 'name': 'cicero_0.7.2.orig.tar.gz', 'sha256': '63f40f2436ea9f67b44e2d4bd669dbab...', 'size': 96527, 'uri': 'http://d.d.o/cicero_0.7.2.orig.tar.gz', } }, }, # ... } """ super().__init__(url=url) self.packages = packages def get_versions(self) -> Sequence[str]: """Returns the keys of the packages input (e.g. stretch/contrib/0.7.2-3, etc...) """ return list(self.packages.keys()) def get_package_info(self, version: str) -> Generator[ Tuple[str, Mapping[str, Any]], None, None]: meta = self.packages[version] p_info = meta.copy() p_info['raw'] = meta yield release_name(version), p_info def resolve_revision_from( self, known_package_artifacts: Dict, artifact_metadata: Dict) \ -> Optional[bytes]: artifacts_to_fetch = artifact_metadata['files'] logger.debug('k_p_artifacts: %s', known_package_artifacts) logger.debug('artifacts_to_fetch: %s', artifacts_to_fetch) for rev_id, known_artifacts in known_package_artifacts.items(): logger.debug('Revision: %s', rev_id) logger.debug('Associated known_artifacts: %s', known_artifacts) known_artifacts = known_artifacts['extrinsic']['raw']['files'] rev_found = True for a_name, k_artifact in known_artifacts.items(): artifact_to_fetch = artifacts_to_fetch.get(a_name) logger.debug('artifact_to_fetch: %s', artifact_to_fetch) if artifact_to_fetch is None: # as soon as we do not see an artifact, we consider we need # to check the other revision rev_found = False if k_artifact['sha256'] != artifact_to_fetch['sha256']: # Hash is different, we consider we need to check the other # revisions rev_found = False if rev_found: logger.debug('Existing revision %s found for new artifacts.', rev_id) return rev_id logger.debug('No existing revision found for the new artifacts.') return None def download_package(self, p_info: Mapping[str, Any], tmpdir: str) -> List[Tuple[str, Mapping]]: """Contrary to other package loaders (1 package, 1 artifact), `a_metadata` represents the package's datafiles set to fetch: - .orig.tar.gz - .dsc - .diff.gz This is delegated to the `download_package` function. """ all_hashes = download_package(p_info, tmpdir) logger.debug('all_hashes: %s', all_hashes) res = [] for hashes in all_hashes.values(): res.append((tmpdir, hashes)) logger.debug('res: %s', res) return res def uncompress(self, dl_artifacts: List[Tuple[str, Mapping[str, Any]]], dest: str) -> str: logger.debug('dl_artifacts: %s', dl_artifacts) return extract_package(dl_artifacts, dest=dest) def build_revision(self, a_metadata: Mapping[str, Any], uncompressed_path: str) -> Dict: dsc_url, dsc_name = dsc_information(a_metadata) if not dsc_name: raise ValueError( 'dsc name for url %s should not be None' % dsc_url) dsc_path = path.join(path.dirname(uncompressed_path), dsc_name) i_metadata = get_package_metadata( a_metadata, dsc_path, uncompressed_path) logger.debug('i_metadata: %s', i_metadata) logger.debug('a_metadata: %s', a_metadata) msg = 'Synthetic revision for Debian source package %s version %s' % ( a_metadata['name'], a_metadata['version']) date = iso8601.parse_date(i_metadata['changelog']['date']) author = prepare_person(i_metadata['changelog']['person']) # inspired from swh.loader.debian.converters.package_metadata_to_revision # noqa return { 'type': 'dsc', 'message': msg.encode('utf-8'), 'author': author, 'date': date, 'committer': author, 'committer_date': date, 'parents': [], 'metadata': { 'intrinsic': { 'tool': 'dsc', 'raw': i_metadata, }, 'extrinsic': { 'provider': dsc_url, 'when': self.visit_date.isoformat(), 'raw': a_metadata, }, } } def uid_to_person(uid: str) -> Mapping[str, str]: """Convert an uid to a person suitable for insertion. Args: uid: an uid of the form "Name " Returns: a dictionary with the following keys: - name: the name associated to the uid - email: the mail associated to the uid - fullname: the actual uid input """ logger.debug('uid: %s', uid) ret = { 'name': '', 'email': '', 'fullname': uid, } name, mail = email.utils.parseaddr(uid) if name and email: ret['name'] = name ret['email'] = mail else: ret['name'] = uid return ret def prepare_person(person: Mapping[str, str]) -> Mapping[str, bytes]: """Prepare person for swh serialization... Args: A person dict Returns: A person dict ready for storage """ ret = {} for key, value in person.items(): ret[key] = value.encode('utf-8') return ret def download_package( package: Mapping[str, Any], tmpdir: Any) -> Mapping[str, Any]: """Fetch a source package in a temporary directory and check the checksums for all files. Args: package: Dict defining the set of files representing a debian package tmpdir: Where to download and extract the files to ingest Returns: Dict of swh hashes per filename key """ all_hashes = {} for filename, fileinfo in package['files'].items(): uri = fileinfo['uri'] logger.debug('fileinfo: %s', fileinfo) extrinsic_hashes = {'sha256': fileinfo['sha256']} logger.debug('extrinsic_hashes(%s): %s', filename, extrinsic_hashes) filepath, hashes = download(uri, dest=tmpdir, filename=filename, hashes=extrinsic_hashes) all_hashes[filename] = hashes logger.debug('all_hashes: %s', all_hashes) return all_hashes def dsc_information(package: Mapping[str, Any]) -> Tuple[ Optional[str], Optional[str]]: """Retrieve dsc information from a package. Args: package: Package metadata information Returns: Tuple of dsc file's uri, dsc's full disk path """ dsc_name = None dsc_url = None for filename, fileinfo in package['files'].items(): if filename.endswith('.dsc'): if dsc_name: raise ValueError( 'Package %s_%s references several dsc files' % (package['name'], package['version']) ) dsc_url = fileinfo['uri'] dsc_name = filename return dsc_url, dsc_name def extract_package(dl_artifacts: List[Tuple[str, Mapping]], dest: str) -> str: """Extract a Debian source package to a given directory. Note that after extraction the target directory will be the root of the extracted package, rather than containing it. Args: package: package information dictionary dest: directory where the package files are stored Returns: Package extraction directory """ a_path = dl_artifacts[0][0] logger.debug('dl_artifacts: %s', dl_artifacts) for _, hashes in dl_artifacts: logger.debug('hashes: %s', hashes) filename = hashes['filename'] if filename.endswith('.dsc'): dsc_name = filename break dsc_path = path.join(a_path, dsc_name) destdir = path.join(dest, 'extracted') logfile = path.join(dest, 'extract.log') logger.debug('extract Debian source package %s in %s' % (dsc_path, destdir), extra={ 'swh_type': 'deb_extract', 'swh_dsc': dsc_path, 'swh_destdir': destdir, }) cmd = ['dpkg-source', '--no-copy', '--no-check', '--ignore-bad-version', '-x', dsc_path, destdir] try: with open(logfile, 'w') as stdout: subprocess.check_call(cmd, stdout=stdout, stderr=subprocess.STDOUT) except subprocess.CalledProcessError as e: logdata = open(logfile, 'r').read() raise ValueError('dpkg-source exited with code %s: %s' % (e.returncode, logdata)) from None return destdir def get_package_metadata(package: Mapping[str, Any], dsc_path: str, extracted_path: str) -> Mapping[str, Any]: """Get the package metadata from the source package at dsc_path, extracted in extracted_path. Args: package: the package dict (with a dsc_path key) dsc_path: path to the package's dsc file extracted_path: the path where the package got extracted Returns: dict: a dictionary with the following keys: - history: list of (package_name, package_version) tuples parsed from the package changelog """ with open(dsc_path, 'rb') as dsc: parsed_dsc = Dsc(dsc) # Parse the changelog to retrieve the rest of the package information changelog_path = path.join(extracted_path, 'debian/changelog') with open(changelog_path, 'rb') as changelog: try: parsed_changelog = Changelog(changelog) except UnicodeDecodeError: logger.warning('Unknown encoding for changelog %s,' ' falling back to iso' % changelog_path, extra={ 'swh_type': 'deb_changelog_encoding', 'swh_name': package['name'], 'swh_version': str(package['version']), 'swh_changelog': changelog_path, }) # need to reset as Changelog scrolls to the end of the file changelog.seek(0) parsed_changelog = Changelog(changelog, encoding='iso-8859-15') package_info = { 'name': package['name'], 'version': str(package['version']), 'changelog': { 'person': uid_to_person(parsed_changelog.author), 'date': parse_date(parsed_changelog.date).isoformat(), 'history': [(block.package, str(block.version)) for block in parsed_changelog][1:], } } maintainers = [ uid_to_person(parsed_dsc['Maintainer']), ] maintainers.extend( uid_to_person(person) for person in UPLOADERS_SPLIT.split(parsed_dsc.get('Uploaders', '')) ) package_info['maintainers'] = maintainers return package_info diff --git a/swh/loader/package/deposit.py b/swh/loader/package/deposit.py index 3177ad4..1fe1752 100644 --- a/swh/loader/package/deposit.py +++ b/swh/loader/package/deposit.py @@ -1,154 +1,154 @@ # Copyright (C) 2019 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 logging from typing import Any, Dict, Generator, Mapping, Sequence, Tuple -from swh.model.hashutil import hash_to_hex +from swh.model.hashutil import hash_to_hex, hash_to_bytes from swh.loader.package.loader import PackageLoader from swh.deposit.client import PrivateApiDepositClient as ApiClient logger = logging.getLogger(__name__) class DepositLoader(PackageLoader): """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) # For now build back existing api urls # archive_url: Private api url to retrieve archive artifact self.archive_url = '/%s/raw/' % deposit_id # metadata_url: Private api url to retrieve the deposit metadata self.metadata_url = '/%s/meta/' % deposit_id # deposit_update_url: Private api to push pids and status update on the # deposit id self.deposit_update_url = '/%s/update/' % deposit_id self.client = ApiClient() self._metadata = None @property def metadata(self): if self._metadata is None: self._metadata = self.client.metadata_get(self.metadata_url) return self._metadata def get_versions(self) -> Sequence[str]: # only 1 branch 'HEAD' with no alias since we only have 1 snapshot # branch return ['HEAD'] def get_package_info(self, version: str) -> Generator[ Tuple[str, Mapping[str, Any]], None, None]: p_info = { 'url': self.client.base_url + self.archive_url, 'filename': 'archive.zip', 'raw': self.metadata, } yield 'HEAD', p_info def build_revision( self, a_metadata: Dict, uncompressed_path: str) -> Dict: revision = a_metadata.pop('revision') metadata = { 'extrinsic': { 'provider': '%s/%s' % ( self.client.base_url, self.metadata_url), 'when': self.visit_date.isoformat(), 'raw': a_metadata, }, } # FIXME: the deposit no longer needs to build the revision revision['metadata'].update(metadata) revision['author'] = parse_author(revision['author']) revision['committer'] = parse_author(revision['committer']) revision['message'] = revision['message'].encode('utf-8') revision['type'] = 'tar' return revision def load(self) -> Dict: # Usual loading r = super().load() success = r['status'] != 'failed' if success: # Update archive with metadata information origin_metadata = self.metadata['origin_metadata'] logger.debug('origin_metadata: %s', origin_metadata) tools = self.storage.tool_add([origin_metadata['tool']]) logger.debug('tools: %s', tools) tool_id = tools[0]['id'] provider = origin_metadata['provider'] # FIXME: Shall we delete this info? provider_id = self.storage.metadata_provider_add( provider['provider_name'], provider['provider_type'], provider['provider_url'], metadata=None) metadata = origin_metadata['metadata'] self.storage.origin_metadata_add( self.url, self.visit_date, provider_id, tool_id, metadata) # Update deposit status try: if not success: self.client.status_update( self.deposit_update_url, status='failed') return r - snapshot_id = r['snapshot_id'] + snapshot_id = hash_to_bytes(r['snapshot_id']) branches = self.storage.snapshot_get(snapshot_id)['branches'] logger.debug('branches: %s', branches) if not branches: return r rev_id = branches[b'HEAD']['target'] revision = next(self.storage.revision_get([rev_id])) # Retrieve the revision identifier dir_id = revision['directory'] # update the deposit's status to success with its # revision-id and directory-id self.client.status_update( self.deposit_update_url, status='done', revision_id=hash_to_hex(rev_id), directory_id=hash_to_hex(dir_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): """See prior fixme """ return { 'fullname': author['fullname'].encode('utf-8'), 'name': author['name'].encode('utf-8'), 'email': author['email'].encode('utf-8'), } diff --git a/swh/loader/package/loader.py b/swh/loader/package/loader.py index 4c7d462..f53db3a 100644 --- a/swh/loader/package/loader.py +++ b/swh/loader/package/loader.py @@ -1,394 +1,395 @@ # Copyright (C) 2019 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import datetime import logging import tempfile import os from typing import ( Any, Dict, Generator, List, Mapping, Optional, Sequence, Tuple ) from swh.core.tarball import uncompress from swh.core.config import SWHConfig from swh.model.from_disk import Directory +from swh.model.hashutil import hash_to_hex from swh.model.identifiers import ( revision_identifier, snapshot_identifier, identifier_to_bytes ) from swh.storage import get_storage from swh.storage.algos.snapshot import snapshot_get_all_branches from swh.loader.core.converters import content_for_storage from swh.loader.package.utils import download logger = logging.getLogger(__name__) # Not implemented yet: # - clean up disk routines from previous killed workers (when OOMkilled) # -> separation of concern would like this to be abstracted from the code # -> experience tells us it's complicated to do as such (T903, T964, T982, # etc...) # # - model: swh.model.merkle.from_disk should output swh.model.model.* objects # to avoid this layer's conversion routine call # -> Take this up within swh.model's current implementation class PackageLoader: # 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 = SWHConfig.parse_config_file() self._check_configuration() self.storage = get_storage(**self.config['storage']) self.url = url self.visit_date = datetime.datetime.now(tz=datetime.timezone.utc) 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) -> Generator[ Tuple[str, Mapping[str, Any]], None, None]: """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, a_metadata: Dict, uncompressed_path: str) -> Dict: """Build the revision dict from the archive metadata (extrinsic artifact metadata) and the intrinsic metadata. Args: a_metadata: Artifact metadata uncompressed_path: Artifact uncompressed path on disk Returns: SWH data dict """ return {} def get_default_version(self) -> str: """Retrieve the latest release version if any. Returns: Latest version """ return '' def last_snapshot(self) -> Optional[Dict]: """Retrieve the last snapshot """ snapshot = None visit = self.storage.origin_visit_get_latest( self.url, require_snapshot=True) if visit: snapshot = snapshot_get_all_branches( self.storage, visit['snapshot']) return snapshot def known_artifacts(self, snapshot: Optional[Dict]) -> Dict: """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 or 'branches' not in 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'] == 'revision'] known_revisions = self.storage.revision_get(revs) ret = {} for revision in known_revisions: if not revision: # revision_get can return None continue ret[revision['id']] = revision['metadata'] return ret def resolve_revision_from( self, known_artifacts: Dict, artifact_metadata: Dict) \ -> 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 artifact_metadata: Information dict Returns: None or revision identifier """ return None def download_package(self, p_info: Mapping[str, Any], 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) """ a_uri = p_info['url'] filename = p_info.get('filename') return [download(a_uri, dest=tmpdir, filename=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 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 try: # Prepare origin and origin_visit origin = {'url': self.url} self.storage.origin_add_one(origin) visit_id = self.storage.origin_visit_add( origin=self.url, date=self.visit_date, type=self.visit_type)['visit'] 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) # Retrieve the default release version (the "latest" one) default_version = self.get_default_version() logger.debug('default version: %s', default_version) 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['raw']) if revision_id is None: with tempfile.TemporaryDirectory() as tmpdir: try: dl_artifacts = self.download_package( p_info, tmpdir) except Exception: logger.exception('Unable to retrieve %s', p_info) status_visit = 'partial' continue uncompressed_path = self.uncompress( dl_artifacts, dest=tmpdir) logger.debug('uncompressed_path: %s', uncompressed_path) directory = Directory.from_disk( path=uncompressed_path.encode('utf-8'), data=True) # noqa # FIXME: Try not to load the full raw content in # memory objects = directory.collect() contents = objects['content'].values() logger.debug('Number of contents: %s', len(contents)) self.storage.content_add( [content_for_storage(x) for x in contents]) status_load = 'eventful' directories = list(objects['directory'].values()) logger.debug('Number of directories: %s', len(directories)) self.storage.directory_add(directories) # FIXME: This should be release. cf. D409 revision = self.build_revision( p_info['raw'], uncompressed_path) revision.update({ 'synthetic': True, 'directory': directory.hash, }) revision['metadata'].update({ 'original_artifact': [ hashes for _, hashes in dl_artifacts ], }) revision['id'] = revision_id = identifier_to_bytes( revision_identifier(revision)) logger.debug('Revision: %s', revision) self.storage.revision_add([revision]) tmp_revisions[version].append((branch_name, revision_id)) logger.debug('tmp_revisions: %s', tmp_revisions) # Build and load the snapshot branches = {} # type: Dict[bytes, Mapping[str, Any]] for version, branch_name_revisions in tmp_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, } snapshot = { 'branches': branches } logger.debug('snapshot: %s', snapshot) snapshot['id'] = identifier_to_bytes( snapshot_identifier(snapshot)) logger.debug('snapshot: %s', snapshot) self.storage.snapshot_add([snapshot]) if hasattr(self.storage, 'flush'): self.storage.flush() except Exception: logger.exception('Fail to load %s' % self.url) status_visit = 'partial' status_load = 'failed' finally: self.storage.origin_visit_update( origin=self.url, visit_id=visit_id, status=status_visit, snapshot=snapshot and snapshot['id']) result = { 'status': status_load, } # type: Dict[str, Any] if snapshot: - result['snapshot_id'] = snapshot['id'] + result['snapshot_id'] = hash_to_hex(snapshot['id']) return result diff --git a/swh/loader/package/tests/test_archive.py b/swh/loader/package/tests/test_archive.py index d128a44..c67e249 100644 --- a/swh/loader/package/tests/test_archive.py +++ b/swh/loader/package/tests/test_archive.py @@ -1,344 +1,366 @@ # Copyright (C) 2019 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 swh.model.hashutil import hash_to_bytes from swh.loader.package.archive import ArchiveLoader, artifact_identity from swh.loader.package.tests.common import ( check_snapshot, check_metadata_paths, get_stats ) URL = 'https://ftp.gnu.org/gnu/8sync/' GNU_ARTIFACTS = [ { 'time': 944729610, 'url': 'https://ftp.gnu.org/gnu/8sync/8sync-0.1.0.tar.gz', 'length': 221837, 'filename': '8sync-0.1.0.tar.gz', 'version': '0.1.0', } ] _expected_new_contents_first_visit = [ 'e9258d81faf5881a2f96a77ba609396f82cb97ad', '1170cf105b04b7e2822a0e09d2acf71da7b9a130', 'fbd27c3f41f2668624ffc80b7ba5db9b92ff27ac', '0057bec9b5422aff9256af240b177ac0e3ac2608', '2b8d0d0b43a1078fc708930c8ddc2956a86c566e', '27de3b3bc6545d2a797aeeb4657c0e215a0c2e55', '2e6db43f5cd764e677f416ff0d0c78c7a82ef19b', 'ae9be03bd2a06ed8f4f118d3fe76330bb1d77f62', 'edeb33282b2bffa0e608e9d2fd960fd08093c0ea', 'd64e64d4c73679323f8d4cde2643331ba6c20af9', '7a756602914be889c0a2d3952c710144b3e64cb0', '84fb589b554fcb7f32b806951dcf19518d67b08f', '8624bcdae55baeef00cd11d5dfcfa60f68710a02', 'e08441aeab02704cfbd435d6445f7c072f8f524e', 'f67935bc3a83a67259cda4b2d43373bd56703844', '809788434b433eb2e3cfabd5d591c9a659d5e3d8', '7d7c6c8c5ebaeff879f61f37083a3854184f6c41', 'b99fec102eb24bffd53ab61fc30d59e810f116a2', '7d149b28eaa228b3871c91f0d5a95a2fa7cb0c68', 'f0c97052e567948adf03e641301e9983c478ccff', '7fb724242e2b62b85ca64190c31dcae5303e19b3', '4f9709e64a9134fe8aefb36fd827b84d8b617ab5', '7350628ccf194c2c3afba4ac588c33e3f3ac778d', '0bb892d9391aa706dc2c3b1906567df43cbe06a2', '49d4c0ce1a16601f1e265d446b6c5ea6b512f27c', '6b5cc594ac466351450f7f64a0b79fdaf4435ad3', '3046e5d1f70297e2a507b98224b6222c9688d610', '1572607d456d7f633bc6065a2b3048496d679a31', ] _expected_new_directories_first_visit = [ 'daabc65ec75d487b1335ffc101c0ac11c803f8fc', '263be23b4a8101d3ad0d9831319a3e0f2b065f36', '7f6e63ba6eb3e2236f65892cd822041f1a01dd5c', '4db0a3ecbc976083e2dac01a62f93729698429a3', 'dfef1c80e1098dd5deda664bb44a9ab1f738af13', 'eca971d346ea54d95a6e19d5051f900237fafdaa', '3aebc29ed1fccc4a6f2f2010fb8e57882406b528', ] _expected_new_revisions_first_visit = { '44183488c0774ce3c957fa19ba695cf18a4a42b3': '3aebc29ed1fccc4a6f2f2010fb8e57882406b528' } _expected_branches_first_visit = { 'HEAD': { 'target_type': 'alias', 'target': 'releases/0.1.0', }, 'releases/0.1.0': { 'target_type': 'revision', 'target': '44183488c0774ce3c957fa19ba695cf18a4a42b3', }, } # hash is different then before as we changed the snapshot # gnu used to use `release/` (singular) instead of plural _expected_new_snapshot_first_visit_id = 'c419397fd912039825ebdbea378bc6283f006bf5' # noqa def visit_with_no_artifact_found(swh_config, requests_mock_datadir): url = URL unknown_artifact_url = 'https://ftp.g.o/unknown/8sync-0.1.0.tar.gz' loader = ArchiveLoader(url, artifacts=[ { 'time': 944729610, 'url': unknown_artifact_url, # unknown artifact 'length': 221837, 'filename': '8sync-0.1.0.tar.gz', 'version': '0.1.0', } ]) 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, 'person': 0, 'release': 0, 'revision': 0, 'skipped_content': 0, 'snapshot': 1, } == stats origin_visit = next(loader.storage.origin_visit_get(url)) assert origin_visit['status'] == 'partial' + assert origin_visit['type'] == 'tar' def test_check_revision_metadata_structure(swh_config, requests_mock_datadir): loader = ArchiveLoader(url=URL, artifacts=GNU_ARTIFACTS) 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( '44183488c0774ce3c957fa19ba695cf18a4a42b3') revision = list(loader.storage.revision_get([expected_revision_id]))[0] assert revision is not None check_metadata_paths(revision['metadata'], paths=[ ('intrinsic', 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_visit_with_release_artifact_no_prior_visit( swh_config, requests_mock_datadir): """With no prior visit, load a gnu project ends up with 1 snapshot """ loader = ArchiveLoader(url=URL, artifacts=GNU_ARTIFACTS) actual_load_status = loader.load() assert actual_load_status['status'] == 'eventful' + assert actual_load_status['snapshot_id'] == _expected_new_snapshot_first_visit_id # noqa 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, 'person': 1, 'release': 0, 'revision': len(_expected_new_revisions_first_visit), 'skipped_content': 0, 'snapshot': 1 } == stats expected_contents = map(hash_to_bytes, _expected_new_contents_first_visit) assert list(loader.storage.content_missing_per_sha1(expected_contents)) \ == [] expected_dirs = map(hash_to_bytes, _expected_new_directories_first_visit) assert list(loader.storage.directory_missing(expected_dirs)) == [] expected_revs = map(hash_to_bytes, _expected_new_revisions_first_visit) assert list(loader.storage.revision_missing(expected_revs)) == [] expected_snapshot = { 'id': _expected_new_snapshot_first_visit_id, 'branches': _expected_branches_first_visit, } check_snapshot(expected_snapshot, loader.storage) def test_2_visits_without_change(swh_config, requests_mock_datadir): """With no prior visit, load a gnu project ends up with 1 snapshot """ url = URL loader = ArchiveLoader(url, artifacts=GNU_ARTIFACTS) actual_load_status = loader.load() assert actual_load_status['status'] == 'eventful' + assert actual_load_status['snapshot_id'] is not None origin_visit = list(loader.storage.origin_visit_get(url))[-1] assert origin_visit['status'] == 'full' + assert origin_visit['type'] == 'tar' actual_load_status2 = loader.load() assert actual_load_status2['status'] == 'uneventful' + assert actual_load_status2['snapshot_id'] is not None + + assert actual_load_status['snapshot_id'] == actual_load_status2[ + 'snapshot_id'] + origin_visit2 = list(loader.storage.origin_visit_get(url))[-1] assert origin_visit2['status'] == 'full' + assert origin_visit2['type'] == 'tar' urls = [ m.url for m in requests_mock_datadir.request_history if m.url.startswith('https://ftp.gnu.org') ] assert len(urls) == 1 def test_2_visits_with_new_artifact(swh_config, requests_mock_datadir): """With no prior visit, load a gnu project ends up with 1 snapshot """ url = URL artifact1 = GNU_ARTIFACTS[0] loader = ArchiveLoader(url, [artifact1]) actual_load_status = loader.load() assert actual_load_status['status'] == 'eventful' + assert actual_load_status['snapshot_id'] is not None + origin_visit = list(loader.storage.origin_visit_get(url))[-1] assert origin_visit['status'] == 'full' + assert origin_visit['type'] == 'tar' 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, 'person': 1, 'release': 0, 'revision': len(_expected_new_revisions_first_visit), 'skipped_content': 0, 'snapshot': 1 } == stats urls = [ m.url for m in requests_mock_datadir.request_history if m.url.startswith('https://ftp.gnu.org') ] assert len(urls) == 1 artifact2 = { 'time': 1480991830, 'url': 'https://ftp.gnu.org/gnu/8sync/8sync-0.2.0.tar.gz', 'length': 238466, 'filename': '8sync-0.2.0.tar.gz', 'version': '0.2.0', } loader2 = ArchiveLoader(url, [artifact1, artifact2]) # implementation detail: share the storage in between visits loader2.storage = loader.storage stats2 = get_stats(loader2.storage) assert stats == stats2 # ensure we share the storage actual_load_status2 = loader2.load() assert actual_load_status2['status'] == 'eventful' + assert actual_load_status2['snapshot_id'] is not None stats2 = get_stats(loader.storage) assert { 'content': len(_expected_new_contents_first_visit) + 14, 'directory': len(_expected_new_directories_first_visit) + 8, 'origin': 1, 'origin_visit': 1 + 1, 'person': 1, 'release': 0, 'revision': len(_expected_new_revisions_first_visit) + 1, 'skipped_content': 0, 'snapshot': 1 + 1, } == stats2 origin_visit2 = list(loader.storage.origin_visit_get(url))[-1] assert origin_visit2['status'] == 'full' + assert origin_visit2['type'] == 'tar' urls = [ m.url for m in requests_mock_datadir.request_history if m.url.startswith('https://ftp.gnu.org') ] # 1 artifact (2nd time no modification) + 1 new artifact assert len(urls) == 2 def test_artifact_identity(): """Compute primary key should return the right identity """ data = { 'a': 1, 'b': 2, 'length': 221837, 'filename': '8sync-0.1.0.tar.gz', 'version': '0.1.0', } for id_keys, expected_id in [ (['a', 'b'], [1, 2]), ([], []), (['a', 'key-that-does-not-exist'], [1, None]) ]: actual_id = artifact_identity(data, id_keys=id_keys) assert actual_id == expected_id def test_2_visits_without_change_not_gnu(swh_config, requests_mock_datadir): """Load a project archive (not gnu) ends up with 1 snapshot """ url = 'https://something.else.org/8sync/' artifacts = [ # this is not a gnu artifact { 'time': '1999-12-09T09:53:30+00:00', # it's also not a timestamp 'sha256': 'd5d1051e59b2be6f065a9fc6aedd3a391e44d0274b78b9bb4e2b57a09134dbe4', # noqa # keep a gnu artifact reference to avoid adding other test files 'url': 'https://ftp.gnu.org/gnu/8sync/8sync-0.2.0.tar.gz', 'length': 238466, 'filename': '8sync-0.2.0.tar.gz', 'version': '0.2.0', } ] # Here the loader defines the id_keys to use for existence in the snapshot # It's not the default archive loader which loader = ArchiveLoader( url, artifacts=artifacts, identity_artifact_keys=[ 'sha256', 'length', 'url']) actual_load_status = loader.load() assert actual_load_status['status'] == 'eventful' + assert actual_load_status['snapshot_id'] is not None origin_visit = list(loader.storage.origin_visit_get(url))[-1] assert origin_visit['status'] == 'full' + assert origin_visit['type'] == 'tar' actual_load_status2 = loader.load() assert actual_load_status2['status'] == 'uneventful' + assert actual_load_status2['snapshot_id'] == actual_load_status[ + 'snapshot_id'] origin_visit2 = list(loader.storage.origin_visit_get(url))[-1] assert origin_visit2['status'] == 'full' + assert origin_visit2['type'] == 'tar' urls = [ m.url for m in requests_mock_datadir.request_history if m.url.startswith('https://ftp.gnu.org') ] assert len(urls) == 1 diff --git a/swh/loader/package/tests/test_debian.py b/swh/loader/package/tests/test_debian.py index 2b632be..0c6d39d 100644 --- a/swh/loader/package/tests/test_debian.py +++ b/swh/loader/package/tests/test_debian.py @@ -1,371 +1,388 @@ # Copyright (C) 2019 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 logging import pytest from os import path from swh.loader.package.debian import ( DebianLoader, download_package, dsc_information, uid_to_person, prepare_person, get_package_metadata, extract_package ) from swh.loader.package.tests.common import check_snapshot, get_stats logger = logging.getLogger(__name__) PACKAGE_FILES = { 'name': 'cicero', 'version': '0.7.2-3', 'files': { 'cicero_0.7.2-3.diff.gz': { 'md5sum': 'a93661b6a48db48d59ba7d26796fc9ce', 'name': 'cicero_0.7.2-3.diff.gz', 'sha256': 'f039c9642fe15c75bed5254315e2a29f9f2700da0e29d9b0729b3ffc46c8971c', # noqa 'size': 3964, 'uri': 'http://deb.debian.org/debian/pool/contrib/c/cicero/cicero_0.7.2-3.diff.gz' # noqa }, 'cicero_0.7.2-3.dsc': { 'md5sum': 'd5dac83eb9cfc9bb52a15eb618b4670a', 'name': 'cicero_0.7.2-3.dsc', 'sha256': '35b7f1048010c67adfd8d70e4961aefd8800eb9a83a4d1cc68088da0009d9a03', # noqa 'size': 1864, 'uri': 'http://deb.debian.org/debian/pool/contrib/c/cicero/cicero_0.7.2-3.dsc'}, # noqa 'cicero_0.7.2.orig.tar.gz': { 'md5sum': '4353dede07c5728319ba7f5595a7230a', 'name': 'cicero_0.7.2.orig.tar.gz', 'sha256': '63f40f2436ea9f67b44e2d4bd669dbabe90e2635a204526c20e0b3c8ee957786', # noqa 'size': 96527, 'uri': 'http://deb.debian.org/debian/pool/contrib/c/cicero/cicero_0.7.2.orig.tar.gz' # noqa } }, } PACKAGE_FILES2 = { 'name': 'cicero', 'version': '0.7.2-4', 'files': { 'cicero_0.7.2-4.diff.gz': { 'md5sum': '1e7e6fc4a59d57c98082a3af78145734', 'name': 'cicero_0.7.2-4.diff.gz', 'sha256': '2e6fa296ee7005473ff58d0971f4fd325617b445671480e9f2cfb738d5dbcd01', # noqa 'size': 4038, 'uri': 'http://deb.debian.org/debian/pool/contrib/c/cicero/cicero_0.7.2-4.diff.gz' # noqa }, 'cicero_0.7.2-4.dsc': { 'md5sum': '1a6c8855a73b4282bb31d15518f18cde', 'name': 'cicero_0.7.2-4.dsc', 'sha256': '913ee52f7093913420de5cbe95d63cfa817f1a1daf997961149501894e754f8b', # noqa 'size': 1881, 'uri': 'http://deb.debian.org/debian/pool/contrib/c/cicero/cicero_0.7.2-4.dsc'}, # noqa 'cicero_0.7.2.orig.tar.gz': { 'md5sum': '4353dede07c5728319ba7f5595a7230a', 'name': 'cicero_0.7.2.orig.tar.gz', 'sha256': '63f40f2436ea9f67b44e2d4bd669dbabe90e2635a204526c20e0b3c8ee957786', # noqa 'size': 96527, 'uri': 'http://deb.debian.org/debian/pool/contrib/c/cicero/cicero_0.7.2.orig.tar.gz' # noqa } } } PACKAGE_PER_VERSION = { 'stretch/contrib/0.7.2-3': PACKAGE_FILES, } PACKAGES_PER_VERSION = { 'stretch/contrib/0.7.2-3': PACKAGE_FILES, 'buster/contrib/0.7.2-4': PACKAGE_FILES2, } def test_debian_first_visit( swh_config, requests_mock_datadir): """With no prior visit, load a gnu project ends up with 1 snapshot """ loader = DebianLoader( url='deb://Debian/packages/cicero', date='2019-10-12T05:58:09.165557+00:00', packages=PACKAGE_PER_VERSION) actual_load_status = loader.load() - assert actual_load_status['status'] == 'eventful' + expected_snapshot_id = '3b6b66e6ee4e7d903a379a882684a2a50480c0b4' + assert actual_load_status == { + 'status': 'eventful', + 'snapshot_id': expected_snapshot_id + } stats = get_stats(loader.storage) assert { 'content': 42, 'directory': 2, 'origin': 1, 'origin_visit': 1, 'person': 1, 'release': 0, 'revision': 1, # all artifacts under 1 revision 'skipped_content': 0, 'snapshot': 1 } == stats expected_snapshot = { - 'id': '3b6b66e6ee4e7d903a379a882684a2a50480c0b4', + 'id': expected_snapshot_id, 'branches': { 'releases/stretch/contrib/0.7.2-3': { 'target_type': 'revision', 'target': '2807f5b3f84368b4889a9ae827fe85854ffecf07', } }, } # different than the previous loader as no release is done check_snapshot(expected_snapshot, loader.storage) def test_debian_first_visit_then_another_visit( swh_config, requests_mock_datadir): - """With no prior visit, load a gnu project ends up with 1 snapshot + """With no prior visit, load a debian project ends up with 1 snapshot """ url = 'deb://Debian/packages/cicero' loader = DebianLoader( url=url, date='2019-10-12T05:58:09.165557+00:00', packages=PACKAGE_PER_VERSION) actual_load_status = loader.load() - assert actual_load_status['status'] == 'eventful' + + expected_snapshot_id = '3b6b66e6ee4e7d903a379a882684a2a50480c0b4' + assert actual_load_status == { + 'status': 'eventful', + 'snapshot_id': expected_snapshot_id + } + origin_visit = next(loader.storage.origin_visit_get(url)) assert origin_visit['status'] == 'full' + assert origin_visit['type'] == 'deb' stats = get_stats(loader.storage) assert { 'content': 42, 'directory': 2, 'origin': 1, 'origin_visit': 1, 'person': 1, 'release': 0, 'revision': 1, # all artifacts under 1 revision 'skipped_content': 0, 'snapshot': 1 } == stats expected_snapshot = { - 'id': '3b6b66e6ee4e7d903a379a882684a2a50480c0b4', + 'id': expected_snapshot_id, 'branches': { 'releases/stretch/contrib/0.7.2-3': { 'target_type': 'revision', 'target': '2807f5b3f84368b4889a9ae827fe85854ffecf07', } }, } # different than the previous loader as no release is done check_snapshot(expected_snapshot, loader.storage) # No change in between load actual_load_status2 = loader.load() assert actual_load_status2['status'] == 'uneventful' origin_visit2 = list(loader.storage.origin_visit_get(url)) assert origin_visit2[-1]['status'] == 'full' + assert origin_visit2[-1]['type'] == 'deb' stats2 = get_stats(loader.storage) assert { 'content': 42 + 0, 'directory': 2 + 0, 'origin': 1, 'origin_visit': 1 + 1, # a new visit occurred 'person': 1, 'release': 0, 'revision': 1, 'skipped_content': 0, 'snapshot': 1, # same snapshot across 2 visits } == stats2 urls = [ m.url for m in requests_mock_datadir.request_history if m.url.startswith('http://deb.debian.org') ] # visited each package artifact twice across 2 visits assert len(urls) == len(set(urls)) def test_uid_to_person(): uid = 'Someone Name ' actual_person = uid_to_person(uid) assert actual_person == { 'name': 'Someone Name', 'email': 'someone@orga.org', 'fullname': uid, } def test_prepare_person(): actual_author = prepare_person({ 'name': 'Someone Name', 'email': 'someone@orga.org', 'fullname': 'Someone Name ', }) assert actual_author == { 'name': b'Someone Name', 'email': b'someone@orga.org', 'fullname': b'Someone Name ', } def test_download_package(datadir, tmpdir, requests_mock_datadir): tmpdir = str(tmpdir) # py3.5 work around (LocalPath issue) all_hashes = download_package(PACKAGE_FILES, tmpdir) assert all_hashes == { 'cicero_0.7.2-3.diff.gz': { 'checksums': { 'blake2s256': '08b1c438e70d2474bab843d826515147fa4a817f8c4baaf3ddfbeb5132183f21', # noqa 'sha1': '0815282053f21601b0ec4adf7a8fe47eace3c0bc', 'sha1_git': '834ac91da3a9da8f23f47004bb456dd5bd16fe49', 'sha256': 'f039c9642fe15c75bed5254315e2a29f9f2700da0e29d9b0729b3ffc46c8971c' # noqa }, 'filename': 'cicero_0.7.2-3.diff.gz', 'length': 3964}, 'cicero_0.7.2-3.dsc': { 'checksums': { 'blake2s256': '8c002bead3e35818eaa9d00826f3d141345707c58fb073beaa8abecf4bde45d2', # noqa 'sha1': 'abbec4e8efbbc80278236e1dd136831eac08accd', 'sha1_git': '1f94b2086fa1142c2df6b94092f5c5fa11093a8e', 'sha256': '35b7f1048010c67adfd8d70e4961aefd8800eb9a83a4d1cc68088da0009d9a03' # noqa }, 'filename': 'cicero_0.7.2-3.dsc', 'length': 1864}, 'cicero_0.7.2.orig.tar.gz': { 'checksums': { 'blake2s256': '9809aa8d2e2dad7f34cef72883db42b0456ab7c8f1418a636eebd30ab71a15a6', # noqa 'sha1': 'a286efd63fe2c9c9f7bb30255c3d6fcdcf390b43', 'sha1_git': 'aa0a38978dce86d531b5b0299b4a616b95c64c74', 'sha256': '63f40f2436ea9f67b44e2d4bd669dbabe90e2635a204526c20e0b3c8ee957786' # noqa }, 'filename': 'cicero_0.7.2.orig.tar.gz', 'length': 96527 } } def test_dsc_information_ok(): fname = 'cicero_0.7.2-3.dsc' dsc_url, dsc_name = dsc_information(PACKAGE_FILES) assert dsc_url == PACKAGE_FILES['files'][fname]['uri'] assert dsc_name == PACKAGE_FILES['files'][fname]['name'] def test_dsc_information_not_found(): fname = 'cicero_0.7.2-3.dsc' package_files = copy.deepcopy(PACKAGE_FILES) package_files['files'].pop(fname) dsc_url, dsc_name = dsc_information(package_files) assert dsc_url is None assert dsc_name is None def test_dsc_information_too_many_dsc_entries(): # craft an extra dsc file fname = 'cicero_0.7.2-3.dsc' package_files = copy.deepcopy(PACKAGE_FILES) data = package_files['files'][fname] fname2 = fname.replace('cicero', 'ciceroo') package_files['files'][fname2] = data with pytest.raises( ValueError, match='Package %s_%s references several dsc' % ( package_files['name'], package_files['version'])): dsc_information(package_files) def test_get_package_metadata(requests_mock_datadir, datadir, tmp_path): tmp_path = str(tmp_path) # py3.5 compat. package = PACKAGE_FILES logger.debug('package: %s', package) # download the packages all_hashes = download_package(package, tmp_path) # Retrieve information from package _, dsc_name = dsc_information(package) dl_artifacts = [(tmp_path, hashes) for hashes in all_hashes.values()] # Extract information from package extracted_path = extract_package(dl_artifacts, tmp_path) # Retrieve information on package dsc_path = path.join(path.dirname(extracted_path), dsc_name) actual_package_info = get_package_metadata( package, dsc_path, extracted_path) logger.debug('actual_package_info: %s', actual_package_info) assert actual_package_info == { 'changelog': { 'date': '2014-10-19T16:52:35+02:00', 'history': [ ('cicero', '0.7.2-2'), ('cicero', '0.7.2-1'), ('cicero', '0.7-1') ], 'person': { 'email': 'sthibault@debian.org', 'fullname': 'Samuel Thibault ', 'name': 'Samuel Thibault' } }, 'maintainers': [ { 'email': 'debian-accessibility@lists.debian.org', 'fullname': 'Debian Accessibility Team ' '', 'name': 'Debian Accessibility Team' }, { 'email': 'sthibault@debian.org', 'fullname': 'Samuel Thibault ', 'name': 'Samuel Thibault' } ], 'name': 'cicero', 'version': '0.7.2-3' } def test_debian_multiple_packages(swh_config, requests_mock_datadir): url = 'deb://Debian/packages/cicero' loader = DebianLoader( url=url, date='2019-10-12T05:58:09.165557+00:00', packages=PACKAGES_PER_VERSION) actual_load_status = loader.load() - assert actual_load_status['status'] == 'eventful' + expected_snapshot_id = 'defc19021187f3727293121fcf6c5c82cb923604' + assert actual_load_status == { + 'status': 'eventful', + 'snapshot_id': expected_snapshot_id + } origin_visit = next(loader.storage.origin_visit_get(url)) assert origin_visit['status'] == 'full' + assert origin_visit['type'] == 'deb' expected_snapshot = { - 'id': 'defc19021187f3727293121fcf6c5c82cb923604', + 'id': expected_snapshot_id, 'branches': { 'releases/stretch/contrib/0.7.2-3': { 'target_type': 'revision', 'target': '2807f5b3f84368b4889a9ae827fe85854ffecf07', }, 'releases/buster/contrib/0.7.2-4': { 'target_type': 'revision', 'target': '8224139c274c984147ef4b09aa0e462c55a10bd3', } }, } check_snapshot(expected_snapshot, loader.storage) diff --git a/swh/loader/package/tests/test_deposit.py b/swh/loader/package/tests/test_deposit.py index 8e580e9..9b157cd 100644 --- a/swh/loader/package/tests/test_deposit.py +++ b/swh/loader/package/tests/test_deposit.py @@ -1,204 +1,213 @@ # Copyright (C) 2019 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 re from swh.model.hashutil import hash_to_bytes from swh.loader.package.deposit import DepositLoader from swh.loader.package.tests.common import ( check_snapshot, check_metadata_paths, get_stats ) from swh.core.pytest_plugin import requests_mock_datadir_factory def test_deposit_init_ok(swh_config): url = 'some-url' deposit_id = 999 loader = DepositLoader(url, deposit_id) # Something that does not exist assert loader.url == url assert loader.archive_url == '/%s/raw/' % deposit_id assert loader.metadata_url == '/%s/meta/' % deposit_id assert loader.deposit_update_url == '/%s/update/' % deposit_id assert loader.client is not None def test_deposit_loading_failure_to_fetch_metadata(swh_config): """Error during fetching artifact ends us with failed/partial visit """ # private api url form: 'https://deposit.s.o/1/private/hal/666/raw/' url = 'some-url' unknown_deposit_id = 666 loader = DepositLoader(url, unknown_deposit_id) # does not exist actual_load_status = loader.load() - assert actual_load_status['status'] == 'failed' + assert actual_load_status == {'status': 'failed'} stats = get_stats(loader.storage) assert { 'content': 0, 'directory': 0, 'origin': 1, 'origin_visit': 1, 'person': 0, 'release': 0, 'revision': 0, 'skipped_content': 0, 'snapshot': 0, } == stats origin_visit = next(loader.storage.origin_visit_get(url)) assert origin_visit['status'] == 'partial' + assert origin_visit['type'] == 'deposit' requests_mock_datadir_missing_one = requests_mock_datadir_factory(ignore_urls=[ 'https://deposit.softwareheritage.org/1/private/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) assert loader.archive_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, 'person': 0, 'release': 0, 'revision': 0, 'skipped_content': 0, 'snapshot': 1, } == stats origin_visit = next(loader.storage.origin_visit_get(url)) assert origin_visit['status'] == 'partial' + assert origin_visit['type'] == 'deposit' def test_revision_metadata_structure(swh_config, requests_mock_datadir): # do not care for deposit update query requests_mock_datadir.put(re.compile('https')) url = 'https://hal-test.archives-ouvertes.fr/some-external-id' deposit_id = 666 loader = DepositLoader(url, deposit_id) assert loader.archive_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( '9471c606239bccb1f269564c9ea114e1eeab9eb4') revision = list(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), ]) 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): requests_mock_datadir.put(re.compile('https')) # do not care for put url = 'https://hal-test.archives-ouvertes.fr/some-external-id' deposit_id = 666 loader = DepositLoader(url, deposit_id) assert loader.archive_url actual_load_status = loader.load() - assert actual_load_status['status'] == 'eventful' + expected_snapshot_id = '453f455d0efb69586143cd6b6e5897f9906b53a7' + assert actual_load_status == { + 'status': 'eventful', + 'snapshot_id': expected_snapshot_id, + } stats = get_stats(loader.storage) assert { 'content': 303, 'directory': 12, 'origin': 1, 'origin_visit': 1, 'person': 1, 'release': 0, 'revision': 1, 'skipped_content': 0, 'snapshot': 1, } == stats origin_visit = next(loader.storage.origin_visit_get(url)) assert origin_visit['status'] == 'full' + assert origin_visit['type'] == 'deposit' expected_branches = { 'HEAD': { 'target': '9471c606239bccb1f269564c9ea114e1eeab9eb4', 'target_type': 'revision', }, } expected_snapshot = { - 'id': '453f455d0efb69586143cd6b6e5897f9906b53a7', + 'id': expected_snapshot_id, 'branches': expected_branches, } check_snapshot(expected_snapshot, storage=loader.storage) # check metadata tool = { "name": "swh-deposit", "version": "0.0.1", "configuration": { "sword_version": "2", } } tool = loader.storage.tool_get(tool) assert tool is not None assert tool['id'] is not None provider = { "provider_name": "hal", "provider_type": "deposit_client", "provider_url": "https://hal-test.archives-ouvertes.fr/", "metadata": None, } provider = loader.storage.metadata_provider_get_by(provider) assert provider is not None assert provider['id'] is not None metadata = list(loader.storage.origin_metadata_get_by( url, provider_type='deposit_client')) assert metadata is not None assert isinstance(metadata, list) assert len(metadata) == 1 metadata0 = metadata[0] assert metadata0['provider_id'] == provider['id'] assert metadata0['provider_type'] == 'deposit_client' assert metadata0['tool_id'] == tool['id'] diff --git a/swh/loader/package/tests/test_npm.py b/swh/loader/package/tests/test_npm.py index 2ca63d0..2175d87 100644 --- a/swh/loader/package/tests/test_npm.py +++ b/swh/loader/package/tests/test_npm.py @@ -1,526 +1,536 @@ # Copyright (C) 2019 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 from swh.model.hashutil import hash_to_bytes from swh.loader.package.npm import ( parse_npm_package_author, extract_npm_package_author ) from swh.loader.package.tests.common import ( check_snapshot, check_metadata_paths, get_stats ) from swh.loader.package.npm import NpmLoader def _parse_author_string_test(author_str, expected_result): assert parse_npm_package_author(author_str) == expected_result assert parse_npm_package_author(' %s' % author_str) == expected_result assert parse_npm_package_author('%s ' % author_str) == expected_result def test_parse_npm_package_author(): _parse_author_string_test( 'John Doe', { 'name': 'John Doe' } ) _parse_author_string_test( '', { 'email': 'john.doe@foo.bar' } ) _parse_author_string_test( '(https://john.doe)', { 'url': 'https://john.doe' } ) _parse_author_string_test( 'John Doe ', { 'name': 'John Doe', 'email': 'john.doe@foo.bar' } ) _parse_author_string_test( 'John Doe', { 'name': 'John Doe', 'email': 'john.doe@foo.bar' } ) _parse_author_string_test( 'John Doe (https://john.doe)', { 'name': 'John Doe', 'url': 'https://john.doe' } ) _parse_author_string_test( 'John Doe(https://john.doe)', { 'name': 'John Doe', 'url': 'https://john.doe' } ) _parse_author_string_test( ' (https://john.doe)', { 'email': 'john.doe@foo.bar', 'url': 'https://john.doe' } ) _parse_author_string_test( '(https://john.doe) ', { 'email': 'john.doe@foo.bar', 'url': 'https://john.doe' } ) _parse_author_string_test( 'John Doe (https://john.doe)', { 'name': 'John Doe', 'email': 'john.doe@foo.bar', 'url': 'https://john.doe' } ) _parse_author_string_test( 'John Doe (https://john.doe) ', { 'name': 'John Doe', 'email': 'john.doe@foo.bar', 'url': 'https://john.doe' } ) _parse_author_string_test( 'John Doe (https://john.doe)', { 'name': 'John Doe', 'email': 'john.doe@foo.bar', 'url': 'https://john.doe' } ) _parse_author_string_test( 'John Doe(https://john.doe)', { 'name': 'John Doe', 'email': 'john.doe@foo.bar', 'url': 'https://john.doe' } ) _parse_author_string_test('', {}) _parse_author_string_test('<>', {}) _parse_author_string_test(' <>', {}) _parse_author_string_test('<>()', {}) _parse_author_string_test('<> ()', {}) _parse_author_string_test('()', {}) _parse_author_string_test(' ()', {}) _parse_author_string_test( 'John Doe <> ()', { 'name': 'John Doe' } ) _parse_author_string_test( 'John Doe <>', { 'name': 'John Doe' } ) _parse_author_string_test( 'John Doe ()', { 'name': 'John Doe' } ) 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']) == \ { 'fullname': b'mooz ', 'name': b'mooz', 'email': b'stillpedant@gmail.com' } assert ( extract_npm_package_author(package_metadata['versions']['0.0.3']) == { '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/" }''') # noqa assert extract_npm_package_author(package_json) == \ { '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) == \ { '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) == \ { 'fullname': b'fengmk2 ', '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) == \ { 'fullname': b'xiaohuoni <448627663@qq.com>', 'name': b'xiaohuoni', 'email': b'448627663@qq.com' } 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, package_url(package), package_metadata_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 = list(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): package = 'org' loader = NpmLoader(package, package_url(package), package_metadata_url(package)) actual_load_status = loader.load() - assert actual_load_status['status'] == 'eventful' + expected_snapshot_id = 'd0587e1195aed5a8800411a008f2f2d627f18e2d' + assert actual_load_status == { + 'status': 'eventful', + 'snapshot_id': 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, 'person': 2, 'release': 0, 'revision': len(_expected_new_revisions_first_visit), 'skipped_content': 0, 'snapshot': 1, } == stats assert len(list(loader.storage.content_get( _expected_new_contents_first_visit))) == 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)) == [] expected_snapshot = { - 'id': 'd0587e1195aed5a8800411a008f2f2d627f18e2d', + 'id': expected_snapshot_id, 'branches': { 'HEAD': { 'target': 'releases/0.0.4', 'target_type': 'alias' }, 'releases/0.0.2': { 'target': 'd8a1c7474d2956ac598a19f0f27d52f7015f117e', 'target_type': 'revision' }, 'releases/0.0.3': { 'target': '5f9eb78af37ffd12949f235e86fac04898f9f72a', 'target_type': 'revision' }, 'releases/0.0.4': { 'target': 'ba019b192bdb94bd0b5bd68b3a5f92b5acc2239a', 'target_type': 'revision' } } } check_snapshot(expected_snapshot, loader.storage) def test_npm_loader_incremental_visit( swh_config, requests_mock_datadir_visits): package = 'org' url = package_url(package) metadata_url = package_metadata_url(package) loader = NpmLoader(package, url, metadata_url) actual_load_status = loader.load() - assert actual_load_status['status'] == 'eventful' + assert actual_load_status['status'] is not None origin_visit = list(loader.storage.origin_visit_get(url))[-1] assert origin_visit['status'] == 'full' + assert origin_visit['type'] == 'npm' 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, 'person': 2, 'release': 0, 'revision': len(_expected_new_revisions_first_visit), 'skipped_content': 0, 'snapshot': 1, } == stats loader._info = None # reset loader internal state 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'] + origin_visit2 = list(loader.storage.origin_visit_get(url))[-1] assert origin_visit2['status'] == 'full' + assert origin_visit2['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, 'person': 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 diff --git a/swh/loader/package/tests/test_pypi.py b/swh/loader/package/tests/test_pypi.py index 5a05a97..0358af5 100644 --- a/swh/loader/package/tests/test_pypi.py +++ b/swh/loader/package/tests/test_pypi.py @@ -1,661 +1,701 @@ # Copyright (C) 2019 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 os from os import path import pytest from unittest.mock import patch from swh.core.tarball import uncompress from swh.core.pytest_plugin import requests_mock_datadir_factory from swh.model.hashutil import hash_to_bytes from swh.loader.package.pypi import ( PyPILoader, pypi_api_url, author, extract_intrinsic_metadata ) from swh.loader.package.tests.common import ( check_snapshot, check_metadata_paths, get_stats ) def test_author_basic(): data = { 'author': "i-am-groot", 'author_email': 'iam@groot.org', } actual_author = author(data) expected_author = { '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 = { '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 = { '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 = { '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 = { '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 = { 'fullname': b'[marie, jeanne, pierre] <[marie@somewhere.org, jeanne@somewhere.org]>', # noqa '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(monkeypatch): """Badly configured loader should raise""" monkeypatch.delenv('SWH_CONFIG_FILENAME', raising=False) with pytest.raises(ValueError) as e: PyPILoader(url='some-url') assert 'Misconfiguration' in e.value.args[0] 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' @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 inexistant path/archive/PKG-INFO yield None""" tmp_path = str(tmp_path) # py3.5 work around (PosixPath issue) # inexistant first level path assert extract_intrinsic_metadata('/something-inexistant') == {} # inexistant second level path (as expected by pypi archives) assert extract_intrinsic_metadata(tmp_path) == {} # inexistant 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, 'person': 0, 'release': 0, 'revision': 0, 'skipped_content': 0, 'snapshot': 1, } == stats origin_visit = next(loader.storage.origin_visit_get(url)) assert origin_visit['status'] == 'partial' + assert origin_visit['type'] == 'pypi' # problem during loading: # {visit: partial, status: uneventful, no snapshot} def test_release_with_traceback(swh_config): url = 'https://pypi.org/project/0805nexter' with patch('swh.loader.package.pypi.PyPILoader.get_default_version', side_effect=ValueError('Problem')): loader = PyPILoader(url) actual_load_status = loader.load() - assert actual_load_status['status'] == 'failed' + assert actual_load_status == {'status': 'failed'} stats = get_stats(loader.storage) assert { 'content': 0, 'directory': 0, 'origin': 1, 'origin_visit': 1, 'person': 0, 'release': 0, 'revision': 0, 'skipped_content': 0, 'snapshot': 0, } == stats origin_visit = next(loader.storage.origin_visit_get(url)) assert origin_visit['status'] == 'partial' + assert origin_visit['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): 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 = list(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_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() - assert actual_load_status['status'] == 'eventful' + expected_snapshot_id = 'dd0e4201a232b1c104433741dbf45895b8ac9355' + assert actual_load_status == { + 'status': 'eventful', + 'snapshot_id': expected_snapshot_id + } stats = get_stats(loader.storage) assert { 'content': 3, 'directory': 2, 'origin': 1, 'origin_visit': 1, 'person': 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_branches = { 'releases/1.2.0': { 'target': 'e445da4da22b31bfebb6ffc4383dbf839a074d21', 'target_type': 'revision', }, 'HEAD': { 'target': 'releases/1.2.0', 'target_type': 'alias', }, } expected_snapshot = { - 'id': 'dd0e4201a232b1c104433741dbf45895b8ac9355', + 'id': expected_snapshot_id, 'branches': expected_branches, } check_snapshot(expected_snapshot, storage=loader.storage) origin_visit = next(loader.storage.origin_visit_get(url)) assert origin_visit['status'] == 'partial' + assert origin_visit['type'] == 'pypi' 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() - assert actual_load_status['status'] == 'eventful' + expected_snapshot_id = 'ba6e158ada75d0b3cfb209ffdf6daa4ed34a227a' + assert actual_load_status == { + 'status': 'eventful', + 'snapshot_id': expected_snapshot_id + } stats = get_stats(loader.storage) assert { 'content': 6, 'directory': 4, 'origin': 1, 'origin_visit': 1, 'person': 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_branches = { 'releases/1.1.0': { 'target': '4c99891f93b81450385777235a37b5e966dd1571', 'target_type': 'revision', }, 'releases/1.2.0': { 'target': 'e445da4da22b31bfebb6ffc4383dbf839a074d21', 'target_type': 'revision', }, 'HEAD': { 'target': 'releases/1.2.0', 'target_type': 'alias', }, } expected_snapshot = { - 'id': 'ba6e158ada75d0b3cfb209ffdf6daa4ed34a227a', + 'id': expected_snapshot_id, 'branches': expected_branches, } check_snapshot(expected_snapshot, loader.storage) origin_visit = next(loader.storage.origin_visit_get(url)) assert origin_visit['status'] == 'full' + assert origin_visit['type'] == 'pypi' 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() - assert actual_load_status['status'] == 'eventful' + snapshot_id = 'ba6e158ada75d0b3cfb209ffdf6daa4ed34a227a' + assert actual_load_status == { + 'status': 'eventful', + 'snapshot_id': snapshot_id, + } stats = get_stats(loader.storage) assert { 'content': 6, 'directory': 4, 'origin': 1, 'origin_visit': 1, 'person': 1, 'release': 0, 'revision': 2, 'skipped_content': 0, 'snapshot': 1 } == stats expected_branches = { 'releases/1.1.0': { 'target': '4c99891f93b81450385777235a37b5e966dd1571', 'target_type': 'revision', }, 'releases/1.2.0': { 'target': 'e445da4da22b31bfebb6ffc4383dbf839a074d21', 'target_type': 'revision', }, 'HEAD': { 'target': 'releases/1.2.0', 'target_type': 'alias', }, } - snapshot_id = 'ba6e158ada75d0b3cfb209ffdf6daa4ed34a227a' expected_snapshot = { 'id': snapshot_id, 'branches': expected_branches, } check_snapshot(expected_snapshot, loader.storage) origin_visit = next(loader.storage.origin_visit_get(url)) assert origin_visit['status'] == 'full' + assert origin_visit['type'] == 'pypi' actual_load_status2 = loader.load() - assert actual_load_status2['status'] == 'uneventful' + assert actual_load_status2 == { + 'status': 'uneventful', + 'snapshot_id': actual_load_status2['snapshot_id'] + } stats2 = get_stats(loader.storage) expected_stats2 = stats.copy() expected_stats2['origin_visit'] = 1 + 1 assert expected_stats2 == stats2 # same snapshot actual_snapshot_id = origin_visit['snapshot'] assert actual_snapshot_id == hash_to_bytes(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) - assert visit1_actual_load_status['status'] == 'eventful' + expected_snapshot_id = 'ba6e158ada75d0b3cfb209ffdf6daa4ed34a227a' + assert visit1_actual_load_status == { + 'status': 'eventful', + 'snapshot_id': expected_snapshot_id + } + origin_visit1 = next(loader.storage.origin_visit_get(url)) assert origin_visit1['status'] == 'full' + assert origin_visit1['type'] == 'pypi' assert { 'content': 6, 'directory': 4, 'origin': 1, 'origin_visit': 1, 'person': 1, 'release': 0, 'revision': 2, 'skipped_content': 0, 'snapshot': 1 } == visit1_stats # Reset internal state loader._info = None visit2_actual_load_status = loader.load() visit2_stats = get_stats(loader.storage) assert visit2_actual_load_status['status'] == 'eventful' + expected_snapshot_id2 = '2e5149a7b0725d18231a37b342e9b7c4e121f283' + assert visit2_actual_load_status == { + 'status': 'eventful', + 'snapshot_id': expected_snapshot_id2 + } + visits = list(loader.storage.origin_visit_get(url)) assert len(visits) == 2 assert visits[1]['status'] == 'full' + assert visits[1]['type'] == 'pypi' assert { 'content': 6 + 1, # 1 more content 'directory': 4 + 2, # 2 more directories 'origin': 1, 'origin_visit': 1 + 1, 'person': 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_branches = { 'releases/1.1.0': { 'target': '4c99891f93b81450385777235a37b5e966dd1571', 'target_type': 'revision', }, 'releases/1.2.0': { 'target': 'e445da4da22b31bfebb6ffc4383dbf839a074d21', 'target_type': 'revision', }, 'releases/1.3.0': { 'target': '51247143b01445c9348afa9edfae31bf7c5d86b1', 'target_type': 'revision', }, 'HEAD': { 'target': 'releases/1.3.0', 'target_type': 'alias', }, } expected_snapshot = { - 'id': '2e5149a7b0725d18231a37b342e9b7c4e121f283', + 'id': expected_snapshot_id2, 'branches': expected_branches, } check_snapshot(expected_snapshot, loader.storage) origin_visit = list(loader.storage.origin_visit_get(url))[-1] assert origin_visit['status'] == 'full' + assert origin_visit['type'] == 'pypi' 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() - assert actual_load_status['status'] == 'eventful' + expected_snapshot_id = 'a27e638a4dad6fbfa273c6ebec1c4bf320fb84c6' + assert actual_load_status == { + 'status': 'eventful', + 'snapshot_id': expected_snapshot_id, + } expected_branches = { 'releases/1.1.0/nexter-1.1.0.zip': { 'target': '4c99891f93b81450385777235a37b5e966dd1571', 'target_type': 'revision', }, 'releases/1.1.0/nexter-1.1.0.tar.gz': { 'target': '0bf88f5760cca7665d0af4d6575d9301134fe11a', 'target_type': 'revision', }, } expected_snapshot = { - 'id': 'a27e638a4dad6fbfa273c6ebec1c4bf320fb84c6', + 'id': expected_snapshot_id, 'branches': expected_branches, } check_snapshot(expected_snapshot, loader.storage) origin_visit = next(loader.storage.origin_visit_get(url)) assert origin_visit['status'] == 'full' + assert origin_visit['type'] == 'pypi' diff --git a/version.txt b/version.txt index 03326f7..954c12e 100644 --- a/version.txt +++ b/version.txt @@ -1 +1 @@ -v0.0.49-0-g772821a \ No newline at end of file +v0.0.50-0-g7204d4f \ No newline at end of file