diff --git a/swh/loader/package/loader.py b/swh/loader/package/loader.py index 2c5a083..76e115d 100644 --- a/swh/loader/package/loader.py +++ b/swh/loader/package/loader.py @@ -1,384 +1,385 @@ # 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.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, i_metadata: Dict) -> Dict: """Build the revision dict from the archive metadata (extrinsic artifact metadata) and the intrinsic metadata. Returns: SWH data dict """ return {} def get_default_release(self) -> str: """Retrieve the latest release version Returns: Latest version """ return '' def last_snapshot(self) -> Optional[Dict]: """Retrieve the last snapshot """ visit = self.storage.origin_visit_get_latest( self.url, require_snapshot=True) if visit: return snapshot_get_all_branches( self.storage, visit['snapshot']['id']) def known_artifacts(self, snapshot: 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) -> [Tuple[str, Dict]]: """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([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 (the "latest" one) default_release = self.get_default_release() logger.debug('default release: %s', default_release) 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( map(content_for_storage, contents)) status_load = 'eventful' directories = 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 = {} for version, branch_name_revisions in tmp_revisions.items(): if len(branch_name_revisions) == 1: branch_name, target = branch_name_revisions[0] if branch_name != 'HEAD': branches[b'HEAD'] = { 'target_type': 'alias', 'target': branch_name.encode('utf-8'), } for branch_name, target in branch_name_revisions: branch_name = branch_name.encode('utf-8') branches[branch_name] = { '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) result = { 'status': status_load, } if snapshot: result['snapshot_id'] = snapshot['id'] return result diff --git a/swh/loader/package/npm.py b/swh/loader/package/npm.py index 09cdfdd..980a300 100644 --- a/swh/loader/package/npm.py +++ b/swh/loader/package/npm.py @@ -1,295 +1,295 @@ # 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 logging import os import re from codecs import BOM_UTF8 from typing import Any, Dict, Generator, Mapping, Sequence, Tuple, Optional import chardet import iso8601 from swh.model.identifiers import normalize_timestamp from swh.loader.package.loader import PackageLoader from swh.loader.package.utils import api_info logger = logging.getLogger(__name__) _EMPTY_AUTHOR = {'fullname': b'', 'name': None, 'email': None} # https://github.com/jonschlinkert/author-regex _author_regexp = r'([^<(]+?)?[ \t]*(?:<([^>(]+?)>)?[ \t]*(?:\(([^)]+?)\)|$)' def parse_npm_package_author(author_str): """ Parse npm package author string. It works with a flexible range of formats, as detailed below:: name name (url) name (url) name (url) name(url) name (url) name (url) name(url) name(url) name (url) name(url) name name (url) (url) (url) (url) (url) Args: author_str (str): input author string Returns: dict: A dict that may contain the following keys: * name * email * url """ author = {} matches = re.findall(_author_regexp, author_str.replace('<>', '').replace('()', ''), re.M) for match in matches: if match[0].strip(): author['name'] = match[0].strip() if match[1].strip(): author['email'] = match[1].strip() if match[2].strip(): author['url'] = match[2].strip() return author def extract_npm_package_author(package_json): """ Extract package author from a ``package.json`` file content and return it in swh format. Args: package_json (dict): Dict holding the content of parsed ``package.json`` file Returns: dict: A dict with the following keys: * fullname * name * email """ def _author_str(author_data): if type(author_data) is dict: author_str = '' if 'name' in author_data: author_str += author_data['name'] if 'email' in author_data: author_str += ' <%s>' % author_data['email'] return author_str elif type(author_data) is list: return _author_str(author_data[0]) if len(author_data) > 0 else '' else: return author_data author_data = {} for author_key in ('author', 'authors'): if author_key in package_json: author_str = _author_str(package_json[author_key]) author_data = parse_npm_package_author(author_str) name = author_data.get('name') email = author_data.get('email') fullname = None if name and email: fullname = '%s <%s>' % (name, email) elif name: fullname = name if not fullname: return _EMPTY_AUTHOR if fullname: fullname = fullname.encode('utf-8') if name: name = name.encode('utf-8') if email: email = email.encode('utf-8') return {'fullname': fullname, 'name': name, 'email': email} 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) class NpmLoader(PackageLoader): visit_type = 'npm' def __init__(self, package_name, package_url, package_metadata_url): super().__init__(url=package_url) self.provider_url = package_metadata_url self._info = None self._versions = None # if package_url is None: # package_url = 'https://www.npmjs.com/package/%s' % package_name # if package_metadata_url is None: # package_metadata_url = 'https://replicate.npmjs.com/%s/' %\ # quote(package_name, safe='') @property def info(self) -> Dict: """Return the project metadata information (fetched from npm registry) """ if not self._info: self._info = api_info(self.provider_url) return self._info def get_versions(self) -> Sequence[str]: - return sorted(self.info['versions'].keys()) + return sorted(list(self.info['versions'].keys())) def get_default_release(self) -> str: return self.info['dist-tags'].get('latest', '') def get_package_info(self, version: str) -> Generator[ Tuple[str, Mapping[str, Any]], None, None]: meta = self.info['versions'][version] url = meta['dist']['tarball'] p_info = { 'url': url, 'filename': os.path.basename(url), 'raw': meta, } yield 'releases/%s' % version, p_info def resolve_revision_from( self, known_artifacts: Dict, artifact_metadata: Dict) \ -> Optional[bytes]: shasum = artifact_metadata['dist']['shasum'] for rev_id, known_artifact in known_artifacts.items(): original_artifact = known_artifact['original_artifact'][0] if shasum == original_artifact['checksums']['sha1']: return rev_id def build_revision( self, a_metadata: Dict, uncompressed_path: str) -> Dict: i_metadata = extract_intrinsic_metadata(uncompressed_path) # from intrinsic metadata author = extract_npm_package_author(i_metadata) # extrinsic metadata version = i_metadata['version'] date = self.info['time'][version] date = iso8601.parse_date(date) date = normalize_timestamp(int(date.timestamp())) message = version.encode('ascii') return { 'type': 'tar', 'message': message, 'author': author, 'date': date, 'committer': author, 'committer_date': date, 'parents': [], 'metadata': { 'intrinsic': { 'tool': 'package.json', 'raw': i_metadata, }, 'extrinsic': { 'provider': self.provider_url, 'when': self.visit_date.isoformat(), 'raw': a_metadata, }, }, } diff --git a/swh/loader/package/tests/common.py b/swh/loader/package/tests/common.py index a46cd58..1c2a9c1 100644 --- a/swh/loader/package/tests/common.py +++ b/swh/loader/package/tests/common.py @@ -1,101 +1,106 @@ # 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 os import path import logging from typing import Dict, List, Tuple from swh.model.hashutil import hash_to_bytes, hash_to_hex logger = logging.getLogger(__file__) DATADIR = path.join(path.abspath(path.dirname(__file__)), 'resources') def decode_target(target): """Test helper to ease readability in test """ if not target: return target target_type = target['target_type'] if target_type == 'alias': decoded_target = target['target'].decode('utf-8') else: decoded_target = hash_to_hex(target['target']) return { 'target': decoded_target, 'target_type': target_type } def check_snapshot(expected_snapshot, storage): """Check for snapshot match. Provide the hashes as hexadecimal, the conversion is done within the method. Args: expected_snapshot (dict): full snapshot with hex ids storage (Storage): expected storage """ expected_snapshot_id = expected_snapshot['id'] expected_branches = expected_snapshot['branches'] snap = storage.snapshot_get(hash_to_bytes(expected_snapshot_id)) - assert snap is not None + if snap is None: + # display known snapshots instead + from pprint import pprint + for snap_id, (_snap, branches) in storage._snapshots.items(): + pprint(_snap.to_dict()) + raise AssertionError('Snapshot is not found') branches = { branch.decode('utf-8'): decode_target(target) for branch, target in snap['branches'].items() } assert expected_branches == branches def check_metadata(metadata: Dict, key_path: str, raw_type: str): """Given a metadata dict, ensure the associated key_path value is of type raw_type. Args: metadata: Dict to check key_path: Path to check raw_type: Type to check the path with Raises: Assertion error in case of mismatch """ data = metadata keys = key_path.split('.') for k in keys: try: data = data[k] except (TypeError, KeyError) as e: # KeyError: because path too long # TypeError: data is not a dict raise AssertionError(e) assert isinstance(data, raw_type) def check_metadata_paths(metadata: Dict, paths: List[Tuple[str, str]]): """Given a metadata dict, ensure the keys are of expected types Args: metadata: Dict to check key_path: Path to check raw_type: Type to check the path with Raises: Assertion error in case of mismatch """ for key_path, raw_type in paths: check_metadata(metadata, key_path, raw_type) diff --git a/swh/loader/package/tests/test_npm.py b/swh/loader/package/tests/test_npm.py index 654c472..3bb776f 100644 --- a/swh/loader/package/tests/test_npm.py +++ b/swh/loader/package/tests/test_npm.py @@ -1,531 +1,526 @@ # 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 ) 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'} ) -_expected_new_snapshot_first_visit_id = normalize_hashes( - 'd0587e1195aed5a8800411a008f2f2d627f18e2d') - -_expected_branches_first_visit = { - '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' - } -} - 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' 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' stats = loader.storage.stat_counters() 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': _expected_new_snapshot_first_visit_id, - 'branches': _expected_branches_first_visit, + 'id': 'd0587e1195aed5a8800411a008f2f2d627f18e2d', + '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' origin_visit = list(loader.storage.origin_visit_get(url))[-1] assert origin_visit['status'] == 'full' stats = loader.storage.stat_counters() 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' origin_visit2 = list(loader.storage.origin_visit_get(url))[-1] assert origin_visit2['status'] == 'full' stats = loader.storage.stat_counters() 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