diff --git a/swh/indexer/metadata.py b/swh/indexer/metadata.py index 0a5f0c7..1ee09bb 100644 --- a/swh/indexer/metadata.py +++ b/swh/indexer/metadata.py @@ -1,340 +1,340 @@ # Copyright (C) 2017 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 click import logging from swh.indexer.indexer import ContentIndexer, RevisionIndexer, OriginIndexer from swh.indexer.metadata_dictionary import MAPPINGS from swh.indexer.metadata_detector import detect_metadata from swh.indexer.metadata_detector import extract_minimal_metadata_dict from swh.indexer.storage import INDEXER_CFG_KEY from swh.model import hashutil class ContentMetadataIndexer(ContentIndexer): """Content-level indexer This indexer is in charge of: - filtering out content already indexed in content_metadata - reading content from objstorage with the content's id sha1 - computing translated_metadata by given context - using the metadata_dictionary as the 'swh-metadata-translator' tool - store result in content_metadata table """ CONFIG_BASE_FILENAME = 'indexer/content_metadata' def __init__(self, tool, config): # twisted way to use the exact same config of RevisionMetadataIndexer # object that uses internally ContentMetadataIndexer self.config = config self.config['tools'] = tool super().__init__() def filter(self, ids): """Filter out known sha1s and return only missing ones. """ yield from self.idx_storage.content_metadata_missing(( { 'id': sha1, 'indexer_configuration_id': self.tool['id'], } for sha1 in ids )) def index(self, id, data): """Index sha1s' content and store result. Args: id (bytes): content's identifier data (bytes): raw content in bytes Returns: dict: dictionary representing a content_metadata. If the translation wasn't successful the translated_metadata keys will be returned as None """ result = { 'id': id, 'indexer_configuration_id': self.tool['id'], 'translated_metadata': None } try: mapping_name = self.tool['tool_configuration']['context'] result['translated_metadata'] = MAPPINGS[mapping_name] \ .translate(data) # a twisted way to keep result with indexer object for get_results self.results.append(result) except Exception: self.log.exception( "Problem during tool retrieval of metadata translation") return result def persist_index_computations(self, results, policy_update): """Persist the results in storage. Args: results ([dict]): list of content_metadata, dict with the following keys: - id (bytes): content's identifier (sha1) - translated_metadata (jsonb): detected metadata policy_update ([str]): either 'update-dups' or 'ignore-dups' to respectively update duplicates or ignore them """ self.idx_storage.content_metadata_add( results, conflict_update=(policy_update == 'update-dups')) def get_results(self): """can be called only if run method was called before Returns: list: list of content_metadata entries calculated by current indexer """ return self.results class RevisionMetadataIndexer(RevisionIndexer): """Revision-level indexer This indexer is in charge of: - filtering revisions already indexed in revision_metadata table with defined computation tool - retrieve all entry_files in root directory - use metadata_detector for file_names containing metadata - compute metadata translation if necessary and possible (depends on tool) - send sha1s to content indexing if possible - store the results for revision """ CONFIG_BASE_FILENAME = 'indexer/revision_metadata' ADDITIONAL_CONFIG = { 'tools': ('dict', { 'name': 'swh-metadata-detector', 'version': '0.0.2', 'configuration': { 'type': 'local', 'context': ['NpmMapping', 'CodemetaMapping'] }, }), } ContentMetadataIndexer = ContentMetadataIndexer def prepare(self): super().prepare() self.tool = self.tools[0] def filter(self, sha1_gits): """Filter out known sha1s and return only missing ones. """ yield from self.idx_storage.revision_metadata_missing(( { 'id': sha1_git, 'indexer_configuration_id': self.tool['id'], } for sha1_git in sha1_gits )) def index(self, rev): """Index rev by processing it and organizing result. use metadata_detector to iterate on filenames - if one filename detected -> sends file to content indexer - if multiple file detected -> translation needed at revision level Args: rev (bytes): revision artifact from storage Returns: dict: dictionary representing a revision_metadata, with keys: - id (str): rev's identifier (sha1_git) - indexer_configuration_id (bytes): tool used - translated_metadata: dict of retrieved metadata """ result = { - 'id': rev['id'].decode(), + 'id': rev['id'], 'indexer_configuration_id': self.tool['id'], 'translated_metadata': None } try: root_dir = rev['directory'] dir_ls = self.storage.directory_ls(root_dir, recursive=False) files = [entry for entry in dir_ls if entry['type'] == 'file'] detected_files = detect_metadata(files) result['translated_metadata'] = self.translate_revision_metadata( detected_files) except Exception as e: self.log.exception( 'Problem when indexing rev: %r', e) return result def persist_index_computations(self, results, policy_update): """Persist the results in storage. Args: results ([dict]): list of content_mimetype, dict with the following keys: - id (bytes): content's identifier (sha1) - mimetype (bytes): mimetype in bytes - encoding (bytes): encoding in bytes policy_update ([str]): either 'update-dups' or 'ignore-dups' to respectively update duplicates or ignore them """ # TODO: add functions in storage to keep data in revision_metadata self.idx_storage.revision_metadata_add( results, conflict_update=(policy_update == 'update-dups')) def translate_revision_metadata(self, detected_files): """ Determine plan of action to translate metadata when containing one or multiple detected files: Args: detected_files (dict): dictionary mapping context names (e.g., "npm", "authors") to list of sha1 Returns: dict: dict with translated metadata according to the CodeMeta vocabulary """ translated_metadata = [] tool = { 'name': 'swh-metadata-translator', 'version': '0.0.2', 'configuration': { 'type': 'local', 'context': None }, } # TODO: iterate on each context, on each file # -> get raw_contents # -> translate each content config = { INDEXER_CFG_KEY: self.idx_storage, 'objstorage': self.objstorage } for context in detected_files.keys(): tool['configuration']['context'] = context c_metadata_indexer = self.ContentMetadataIndexer(tool, config) # sha1s that are in content_metadata table sha1s_in_storage = [] metadata_generator = self.idx_storage.content_metadata_get( detected_files[context]) for c in metadata_generator: # extracting translated_metadata sha1 = c['id'] sha1s_in_storage.append(sha1) local_metadata = c['translated_metadata'] # local metadata is aggregated if local_metadata: translated_metadata.append(local_metadata) sha1s_filtered = [item for item in detected_files[context] if item not in sha1s_in_storage] if sha1s_filtered: # schedule indexation of content try: c_metadata_indexer.run(sha1s_filtered, policy_update='ignore-dups') # on the fly possibility: results = c_metadata_indexer.get_results() for result in results: local_metadata = result['translated_metadata'] translated_metadata.append(local_metadata) except Exception as e: self.log.warning("""Exception while indexing content""", e) # transform translated_metadata into min set with swh-metadata-detector min_metadata = extract_minimal_metadata_dict(translated_metadata) return min_metadata class OriginMetadataIndexer(OriginIndexer): CONFIG_BASE_FILENAME = 'indexer/origin_intrinsic_metadata' ADDITIONAL_CONFIG = { 'tools': ('list', []) } def check(self, **kwargs): kwargs['check_tools'] = False super().check(**kwargs) def filter(self, ids): return ids def run(self, origin_head, policy_update): """Expected to be called with the result of RevisionMetadataIndexer as first argument; ie. not a list of ids as other indexers would. Args: - * `origin_head` (dict): {str(origin_id): rev_id.encode()} + * `origin_head` (dict): {str(origin_id): rev_id} keys `origin_id` and `revision_id`, which is the result of OriginHeadIndexer. * `policy_update`: `'ignore-dups'` or `'update-dups'` """ - origin_head_map = {int(origin_id): rev_id + origin_head_map = {int(origin_id): hashutil.hash_to_bytes(rev_id) for (origin_id, rev_id) in origin_head.items()} # Fix up the argument order. revisions_metadata has to be the # first argument because of celery.chain; the next line calls # run() with the usual order, ie. origin ids first. return super().run(ids=list(origin_head_map), policy_update=policy_update, parse_ids=False, origin_head_map=origin_head_map) def index(self, origin, *, origin_head_map): # Get the last revision of the origin. revision_id = origin_head_map[origin['id']] revision_metadata = self.idx_storage \ .revision_metadata_get([revision_id]) for item in revision_metadata: assert item['id'] == revision_id # Get the metadata of that revision, and return it return { 'origin_id': origin['id'], 'metadata': item['translated_metadata'], 'from_revision': revision_id, 'indexer_configuration_id': item['indexer_configuration_id'], } def persist_index_computations(self, results, policy_update): self.idx_storage.origin_intrinsic_metadata_add( results, conflict_update=(policy_update == 'update-dups')) @click.command() @click.option('--revs', '-i', help='Default sha1_git to lookup', multiple=True) def main(revs): _git_sha1s = list(map(hashutil.hash_to_bytes, revs)) rev_metadata_indexer = RevisionMetadataIndexer() rev_metadata_indexer.run(_git_sha1s, 'update-dups') if __name__ == '__main__': logging.basicConfig(level=logging.INFO) main() diff --git a/swh/indexer/origin_head.py b/swh/indexer/origin_head.py index 424fb57..35ea767 100644 --- a/swh/indexer/origin_head.py +++ b/swh/indexer/origin_head.py @@ -1,219 +1,221 @@ # Copyright (C) 2018 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 import click import logging from swh.scheduler import get_scheduler from swh.scheduler.utils import create_task_dict from swh.indexer.indexer import OriginIndexer +from swh.model.hashutil import hash_to_hex + class OriginHeadIndexer(OriginIndexer): """Origin-level indexer. This indexer is in charge of looking up the revision that acts as the "head" of an origin. In git, this is usually the commit pointed to by the 'master' branch.""" ADDITIONAL_CONFIG = { 'tools': ('dict', { 'name': 'origin-metadata', 'version': '0.0.1', 'configuration': {}, }), 'tasks': ('dict', { 'revision_metadata': 'revision_metadata', 'origin_intrinsic_metadata': 'origin_metadata', }) } CONFIG_BASE_FILENAME = 'indexer/origin_head' def filter(self, ids): yield from ids def persist_index_computations(self, results, policy_update): """Do nothing. The indexer's results are not persistent, they should only be piped to another indexer.""" pass def next_step(self, results, task): """Once the head is found, call the RevisionMetadataIndexer on these revisions, then call the OriginMetadataIndexer with both the origin_id and the revision metadata, so it can copy the revision metadata to the origin's metadata. Args: results (Iterable[dict]): Iterable of return values from `index`. """ super().next_step(results, task) revision_metadata_task = self.config['tasks']['revision_metadata'] origin_intrinsic_metadata_task = self.config['tasks'][ 'origin_intrinsic_metadata'] if revision_metadata_task is None and \ origin_intrinsic_metadata_task is None: return assert revision_metadata_task is not None assert origin_intrinsic_metadata_task is not None # Second task to run after this one: copy the revision's metadata # to the origin sub_task = create_task_dict( origin_intrinsic_metadata_task, 'oneshot', origin_head={ str(result['origin_id']): - result['revision_id'].decode() + hash_to_hex(result['revision_id']) for result in results}, policy_update='update-dups', ) del sub_task['next_run'] # Not json-serializable # First task to run after this one: index the metadata of the # revision task = create_task_dict( revision_metadata_task, 'oneshot', - ids=[res['revision_id'].decode() for res in results], + ids=[hash_to_hex(res['revision_id']) for res in results], policy_update='update-dups', next_step=sub_task, ) if getattr(self, 'scheduler', None): scheduler = self.scheduler else: scheduler = get_scheduler(**self.config['scheduler']) scheduler.create_tasks([task]) # Dispatch def index(self, origin): origin_id = origin['id'] latest_snapshot = self.storage.snapshot_get_latest(origin_id) method = getattr(self, '_try_get_%s_head' % origin['type'], None) if method is None: method = self._try_get_head_generic rev_id = method(latest_snapshot) if rev_id is None: return None result = { 'origin_id': origin_id, 'revision_id': rev_id, } return result # VCSs def _try_get_vcs_head(self, snapshot): try: if isinstance(snapshot, dict): branches = snapshot['branches'] if branches[b'HEAD']['target_type'] == 'revision': return branches[b'HEAD']['target'] except KeyError: return None _try_get_hg_head = _try_get_git_head = _try_get_vcs_head # Tarballs _archive_filename_re = re.compile( rb'^' rb'(?P.*)[-_]' rb'(?P[0-9]+(\.[0-9])*)' rb'(?P[-+][a-zA-Z0-9.~]+?)?' rb'(?P(\.[a-zA-Z0-9]+)+)' rb'$') @classmethod def _parse_version(cls, filename): """Extracts the release version from an archive filename, to get an ordering whose maximum is likely to be the last version of the software >>> OriginHeadIndexer._parse_version(b'foo') (-inf,) >>> OriginHeadIndexer._parse_version(b'foo.tar.gz') (-inf,) >>> OriginHeadIndexer._parse_version(b'gnu-hello-0.0.1.tar.gz') (0, 0, 1, 0) >>> OriginHeadIndexer._parse_version(b'gnu-hello-0.0.1-beta2.tar.gz') (0, 0, 1, -1, 'beta2') >>> OriginHeadIndexer._parse_version(b'gnu-hello-0.0.1+foobar.tar.gz') (0, 0, 1, 1, 'foobar') """ res = cls._archive_filename_re.match(filename) if res is None: return (float('-infinity'),) version = [int(n) for n in res.group('version').decode().split('.')] if res.group('preversion') is None: version.append(0) else: preversion = res.group('preversion').decode() if preversion.startswith('-'): version.append(-1) version.append(preversion[1:]) elif preversion.startswith('+'): version.append(1) version.append(preversion[1:]) else: assert False, res.group('preversion') return tuple(version) def _try_get_ftp_head(self, snapshot): archive_names = list(snapshot['branches']) max_archive_name = max(archive_names, key=self._parse_version) r = self._try_resolve_target(snapshot['branches'], max_archive_name) return r # Generic def _try_get_head_generic(self, snapshot): # Works on 'deposit', 'svn', and 'pypi'. try: if isinstance(snapshot, dict): branches = snapshot['branches'] except KeyError: return None else: return ( self._try_resolve_target(branches, b'HEAD') or self._try_resolve_target(branches, b'master') ) def _try_resolve_target(self, branches, target_name): try: target = branches[target_name] while target['target_type'] == 'alias': target = branches[target['target']] if target['target_type'] == 'revision': return target['target'] elif target['target_type'] == 'content': return None # TODO elif target['target_type'] == 'directory': return None # TODO elif target['target_type'] == 'release': return None # TODO else: assert False except KeyError: return None @click.command() @click.option('--origins', '-i', help='Origins to lookup, in the "type+url" format', multiple=True) def main(origins): rev_metadata_indexer = OriginHeadIndexer() rev_metadata_indexer.run(origins) if __name__ == '__main__': logging.basicConfig(level=logging.INFO) main() diff --git a/swh/indexer/storage/db.py b/swh/indexer/storage/db.py index c60692c..0fea30c 100644 --- a/swh/indexer/storage/db.py +++ b/swh/indexer/storage/db.py @@ -1,396 +1,396 @@ # Copyright (C) 2015-2018 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 import hashutil from swh.storage.db import BaseDb, stored_procedure, cursor_to_bytes from swh.storage.db import line_to_bytes, execute_values_to_bytes class Db(BaseDb): """Proxy to the SWH Indexer DB, with wrappers around stored procedures """ content_mimetype_hash_keys = ['id', 'indexer_configuration_id'] def _missing_from_list(self, table, data, hash_keys, cur=None): """Read from table the data with hash_keys that are missing. Args: table (str): Table name (e.g content_mimetype, content_language, etc...) data (dict): Dict of data to read from hash_keys ([str]): List of keys to read in the data dict. Yields: The data which is missing from the db. """ cur = self._cursor(cur) keys = ', '.join(hash_keys) equality = ' AND '.join( ('t.%s = c.%s' % (key, key)) for key in hash_keys ) yield from execute_values_to_bytes( cur, """ select %s from (values %%s) as t(%s) where not exists ( select 1 from %s c where %s ) """ % (keys, keys, table, equality), (tuple(m[k] for k in hash_keys) for m in data) ) def content_mimetype_missing_from_list(self, mimetypes, cur=None): """List missing mimetypes. """ yield from self._missing_from_list( 'content_mimetype', mimetypes, self.content_mimetype_hash_keys, cur=cur) content_mimetype_cols = [ 'id', 'mimetype', 'encoding', 'tool_id', 'tool_name', 'tool_version', 'tool_configuration'] @stored_procedure('swh_mktemp_content_mimetype') def mktemp_content_mimetype(self, cur=None): pass def content_mimetype_add_from_temp(self, conflict_update, cur=None): self._cursor(cur).execute("SELECT swh_content_mimetype_add(%s)", (conflict_update, )) def _convert_key(self, key, main_table='c'): """Convert keys according to specific use in the module. Args: key (str): Key expression to change according to the alias used in the query main_table (str): Alias to use for the main table. Default to c for content_{something}. Expected: Tables content_{something} being aliased as 'c' (something in {language, mimetype, ...}), table indexer_configuration being aliased as 'i'. """ if key == 'id': return '%s.id' % main_table elif key == 'tool_id': return 'i.id as tool_id' elif key == 'licenses': return ''' array(select name from fossology_license where id = ANY( array_agg(%s.license_id))) as licenses''' % main_table return key def _get_from_list(self, table, ids, cols, cur=None, id_col='id'): """Fetches entries from the `table` such that their `id` field (or whatever is given to `id_col`) is in `ids`. Returns the columns `cols`. The `cur`sor is used to connect to the database. """ cur = self._cursor(cur) keys = map(self._convert_key, cols) query = """ select {keys} from (values %s) as t(id) inner join {table} c on c.{id_col}=t.id inner join indexer_configuration i on c.indexer_configuration_id=i.id; """.format( keys=', '.join(keys), id_col=id_col, table=table) yield from execute_values_to_bytes( cur, query, ((_id,) for _id in ids) ) content_indexer_names = { 'mimetype': 'content_mimetype', 'fossology_license': 'content_fossology_license', } def content_get_range(self, content_type, start, end, indexer_configuration_id, limit=1000, with_textual_data=False, cur=None): """Retrieve contents with content_type, within range [start, end] bound by limit and associated to the given indexer configuration id. When asking to work on textual content, that filters on the mimetype table with any mimetype that is not binary. """ cur = self._cursor(cur) table = self.content_indexer_names[content_type] if with_textual_data: extra = """inner join content_mimetype cm on (t.id=cm.id and cm.mimetype like 'text/%%')""" else: extra = "" query = """select t.id from %s t inner join indexer_configuration ic on t.indexer_configuration_id=ic.id %s where ic.id=%%s and %%s <= t.id and t.id <= %%s order by t.indexer_configuration_id, t.id limit %%s""" % (table, extra) cur.execute(query, (indexer_configuration_id, start, end, limit)) yield from cursor_to_bytes(cur) def content_mimetype_get_from_list(self, ids, cur=None): yield from self._get_from_list( 'content_mimetype', ids, self.content_mimetype_cols, cur=cur) content_language_hash_keys = ['id', 'indexer_configuration_id'] def content_language_missing_from_list(self, languages, cur=None): """List missing languages. """ yield from self._missing_from_list( 'content_language', languages, self.content_language_hash_keys, cur=cur) content_language_cols = [ 'id', 'lang', 'tool_id', 'tool_name', 'tool_version', 'tool_configuration'] @stored_procedure('swh_mktemp_content_language') def mktemp_content_language(self, cur=None): pass def content_language_add_from_temp(self, conflict_update, cur=None): self._cursor(cur).execute("SELECT swh_content_language_add(%s)", (conflict_update, )) def content_language_get_from_list(self, ids, cur=None): yield from self._get_from_list( 'content_language', ids, self.content_language_cols, cur=cur) content_ctags_hash_keys = ['id', 'indexer_configuration_id'] def content_ctags_missing_from_list(self, ctags, cur=None): """List missing ctags. """ yield from self._missing_from_list( 'content_ctags', ctags, self.content_ctags_hash_keys, cur=cur) content_ctags_cols = [ 'id', 'name', 'kind', 'line', 'lang', 'tool_id', 'tool_name', 'tool_version', 'tool_configuration'] @stored_procedure('swh_mktemp_content_ctags') def mktemp_content_ctags(self, cur=None): pass def content_ctags_add_from_temp(self, conflict_update, cur=None): self._cursor(cur).execute("SELECT swh_content_ctags_add(%s)", (conflict_update, )) def content_ctags_get_from_list(self, ids, cur=None): cur = self._cursor(cur) keys = map(self._convert_key, self.content_ctags_cols) yield from execute_values_to_bytes( cur, """ select %s from (values %%s) as t(id) inner join content_ctags c on c.id=t.id inner join indexer_configuration i on c.indexer_configuration_id=i.id order by line """ % ', '.join(keys), ((_id,) for _id in ids) ) def content_ctags_search(self, expression, last_sha1, limit, cur=None): cur = self._cursor(cur) if not last_sha1: query = """SELECT %s FROM swh_content_ctags_search(%%s, %%s)""" % ( ','.join(self.content_ctags_cols)) cur.execute(query, (expression, limit)) else: if last_sha1 and isinstance(last_sha1, bytes): last_sha1 = '\\x%s' % hashutil.hash_to_hex(last_sha1) elif last_sha1: last_sha1 = '\\x%s' % last_sha1 query = """SELECT %s FROM swh_content_ctags_search(%%s, %%s, %%s)""" % ( ','.join(self.content_ctags_cols)) cur.execute(query, (expression, limit, last_sha1)) yield from cursor_to_bytes(cur) content_fossology_license_cols = [ 'id', 'tool_id', 'tool_name', 'tool_version', 'tool_configuration', 'licenses'] @stored_procedure('swh_mktemp_content_fossology_license') def mktemp_content_fossology_license(self, cur=None): pass def content_fossology_license_add_from_temp(self, conflict_update, cur=None): """Add new licenses per content. """ self._cursor(cur).execute( "SELECT swh_content_fossology_license_add(%s)", (conflict_update, )) def content_fossology_license_get_from_list(self, ids, cur=None): """Retrieve licenses per id. """ cur = self._cursor(cur) keys = map(self._convert_key, self.content_fossology_license_cols) yield from execute_values_to_bytes( cur, """ select %s from (values %%s) as t(id) inner join content_fossology_license c on t.id=c.id inner join indexer_configuration i on i.id=c.indexer_configuration_id group by c.id, i.id, i.tool_name, i.tool_version, i.tool_configuration; """ % ', '.join(keys), ((_id,) for _id in ids) ) content_metadata_hash_keys = ['id', 'indexer_configuration_id'] def content_metadata_missing_from_list(self, metadata, cur=None): """List missing metadata. """ yield from self._missing_from_list( 'content_metadata', metadata, self.content_metadata_hash_keys, cur=cur) content_metadata_cols = [ 'id', 'translated_metadata', 'tool_id', 'tool_name', 'tool_version', 'tool_configuration'] @stored_procedure('swh_mktemp_content_metadata') def mktemp_content_metadata(self, cur=None): pass def content_metadata_add_from_temp(self, conflict_update, cur=None): self._cursor(cur).execute("SELECT swh_content_metadata_add(%s)", (conflict_update, )) def content_metadata_get_from_list(self, ids, cur=None): yield from self._get_from_list( 'content_metadata', ids, self.content_metadata_cols, cur=cur) revision_metadata_hash_keys = ['id', 'indexer_configuration_id'] def revision_metadata_missing_from_list(self, metadata, cur=None): """List missing metadata. """ yield from self._missing_from_list( 'revision_metadata', metadata, self.revision_metadata_hash_keys, cur=cur) revision_metadata_cols = [ 'id', 'translated_metadata', 'tool_id', 'tool_name', 'tool_version', 'tool_configuration'] @stored_procedure('swh_mktemp_revision_metadata') def mktemp_revision_metadata(self, cur=None): pass def revision_metadata_add_from_temp(self, conflict_update, cur=None): self._cursor(cur).execute("SELECT swh_revision_metadata_add(%s)", (conflict_update, )) def revision_metadata_get_from_list(self, ids, cur=None): yield from self._get_from_list( 'revision_metadata', ids, self.revision_metadata_cols, cur=cur) origin_intrinsic_metadata_cols = [ 'origin_id', 'metadata', 'from_revision', 'tool_id', 'tool_name', 'tool_version', 'tool_configuration'] origin_intrinsic_metadata_regconfig = 'pg_catalog.simple' """The dictionary used to normalize 'metadata' and queries. 'pg_catalog.simple' provides no stopword, so it should be suitable for proper names and non-English content. When updating this value, make sure to add a new index on origin_intrinsic_metadata.metadata.""" @stored_procedure('swh_mktemp_origin_intrinsic_metadata') def mktemp_origin_intrinsic_metadata(self, cur=None): pass def origin_intrinsic_metadata_add_from_temp( self, conflict_update, cur=None): cur = self._cursor(cur) cur.execute( "SELECT swh_origin_intrinsic_metadata_add(%s)", (conflict_update, )) def origin_intrinsic_metadata_get_from_list(self, orig_ids, cur=None): yield from self._get_from_list( 'origin_intrinsic_metadata', orig_ids, self.origin_intrinsic_metadata_cols, cur=cur, id_col='origin_id') def origin_intrinsic_metadata_search_fulltext(self, terms, *, limit, cur=None): regconfig = self.origin_intrinsic_metadata_regconfig tsquery_template = ' && '.join("plainto_tsquery('%s', %%s)" % regconfig for _ in terms) tsquery_args = [(term,) for term in terms] keys = map(self._convert_key, self.origin_intrinsic_metadata_cols) query = ("SELECT {keys} FROM origin_intrinsic_metadata AS oim " "INNER JOIN indexer_configuration AS i " "ON oim.indexer_configuration_id=i.id " "JOIN LATERAL (SELECT {tsquery_template}) AS s(tsq) ON true " "WHERE to_tsvector('{regconfig}', metadata) @@ tsq " "ORDER BY ts_rank(oim.metadata_tsvector, tsq, 1) DESC " "LIMIT %s;" ).format(keys=', '.join(keys), regconfig=regconfig, tsquery_template=tsquery_template) cur.execute(query, tsquery_args + [limit]) - yield from cur + yield from cursor_to_bytes(cur) indexer_configuration_cols = ['id', 'tool_name', 'tool_version', 'tool_configuration'] @stored_procedure('swh_mktemp_indexer_configuration') def mktemp_indexer_configuration(self, cur=None): pass def indexer_configuration_add_from_temp(self, cur=None): cur = self._cursor(cur) cur.execute("SELECT %s from swh_indexer_configuration_add()" % ( ','.join(self.indexer_configuration_cols), )) yield from cursor_to_bytes(cur) def indexer_configuration_get(self, tool_name, tool_version, tool_configuration, cur=None): cur = self._cursor(cur) cur.execute('''select %s from indexer_configuration where tool_name=%%s and tool_version=%%s and tool_configuration=%%s''' % ( ','.join(self.indexer_configuration_cols)), (tool_name, tool_version, tool_configuration)) data = cur.fetchone() if not data: return None return line_to_bytes(data) diff --git a/swh/indexer/tests/test_metadata.py b/swh/indexer/tests/test_metadata.py index f36cd1d..174c73c 100644 --- a/swh/indexer/tests/test_metadata.py +++ b/swh/indexer/tests/test_metadata.py @@ -1,478 +1,480 @@ # Copyright (C) 2017-2018 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 unittest import logging from swh.indexer.metadata_dictionary import CROSSWALK_TABLE, MAPPINGS from swh.indexer.metadata_detector import detect_metadata from swh.indexer.metadata_detector import extract_minimal_metadata_dict from swh.indexer.metadata import ContentMetadataIndexer from swh.indexer.metadata import RevisionMetadataIndexer from swh.indexer.tests.test_utils import MockObjStorage, MockStorage from swh.indexer.tests.test_utils import MockIndexerStorage +from swh.model.hashutil import hash_to_bytes + class ContentMetadataTestIndexer(ContentMetadataIndexer): """Specific Metadata whose configuration is enough to satisfy the indexing tests. """ def prepare(self): self.idx_storage = MockIndexerStorage() self.log = logging.getLogger('swh.indexer') self.objstorage = MockObjStorage() self.tools = self.register_tools(self.config['tools']) self.tool = self.tools[0] self.results = [] class RevisionMetadataTestIndexer(RevisionMetadataIndexer): """Specific indexer whose configuration is enough to satisfy the indexing tests. """ ContentMetadataIndexer = ContentMetadataTestIndexer def prepare(self): self.config = { 'storage': { 'cls': 'remote', 'args': { 'url': 'http://localhost:9999', } }, 'tools': { 'name': 'swh-metadata-detector', 'version': '0.0.2', 'configuration': { 'type': 'local', 'context': 'NpmMapping' } } } self.storage = MockStorage() self.idx_storage = MockIndexerStorage() self.log = logging.getLogger('swh.indexer') self.objstorage = MockObjStorage() self.tools = self.register_tools(self.config['tools']) self.tool = self.tools[0] self.results = [] class Metadata(unittest.TestCase): """ Tests metadata_mock_tool tool for Metadata detection """ def setUp(self): """ shows the entire diff in the results """ self.maxDiff = None self.content_tool = { 'name': 'swh-metadata-translator', 'version': '0.0.2', 'configuration': { 'type': 'local', 'context': 'NpmMapping' } } MockIndexerStorage.added_data = [] def test_crosstable(self): self.assertEqual(CROSSWALK_TABLE['NodeJS'], { 'repository': 'http://schema.org/codeRepository', 'os': 'http://schema.org/operatingSystem', 'cpu': 'http://schema.org/processorRequirements', 'engines': 'http://schema.org/processorRequirements', 'author': 'http://schema.org/author', 'author.email': 'http://schema.org/email', 'author.name': 'http://schema.org/name', 'contributor': 'http://schema.org/contributor', 'keywords': 'http://schema.org/keywords', 'license': 'http://schema.org/license', 'version': 'http://schema.org/version', 'description': 'http://schema.org/description', 'name': 'http://schema.org/name', 'bugs': 'https://codemeta.github.io/terms/issueTracker', 'homepage': 'http://schema.org/url' }) def test_compute_metadata_none(self): """ testing content empty content is empty should return None """ # given content = b"" # None if no metadata was found or an error occurred declared_metadata = None # when result = MAPPINGS["NpmMapping"].translate(content) # then self.assertEqual(declared_metadata, result) def test_compute_metadata_npm(self): """ testing only computation of metadata with hard_mapping_npm """ # given content = b""" { "name": "test_metadata", "version": "0.0.2", "description": "Simple package.json test for indexer", "repository": { "type": "git", "url": "https://github.com/moranegg/metadata_test" }, "author": { "email": "moranegg@example.com", "name": "Morane G" } } """ declared_metadata = { '@context': 'https://doi.org/10.5063/schema/codemeta-2.0', 'type': 'SoftwareSourceCode', 'name': 'test_metadata', 'version': '0.0.2', 'description': 'Simple package.json test for indexer', 'schema:codeRepository': 'git+https://github.com/moranegg/metadata_test', 'schema:author': { 'type': 'Person', 'name': 'Morane G', 'email': 'moranegg@example.com', }, } # when result = MAPPINGS["NpmMapping"].translate(content) # then self.assertEqual(declared_metadata, result) def test_extract_minimal_metadata_dict(self): """ Test the creation of a coherent minimal metadata set """ # given metadata_list = [{ '@context': 'https://doi.org/10.5063/schema/codemeta-2.0', 'name': 'test_1', 'version': '0.0.2', 'description': 'Simple package.json test for indexer', 'schema:codeRepository': 'git+https://github.com/moranegg/metadata_test', }, { '@context': 'https://doi.org/10.5063/schema/codemeta-2.0', 'name': 'test_0_1', 'version': '0.0.2', 'description': 'Simple package.json test for indexer', 'schema:codeRepository': 'git+https://github.com/moranegg/metadata_test' }, { '@context': 'https://doi.org/10.5063/schema/codemeta-2.0', 'name': 'test_metadata', 'version': '0.0.2', 'schema:author': 'moranegg', }] # when results = extract_minimal_metadata_dict(metadata_list) # then expected_results = { '@context': 'https://doi.org/10.5063/schema/codemeta-2.0', "version": '0.0.2', "description": 'Simple package.json test for indexer', "name": ['test_1', 'test_0_1', 'test_metadata'], "schema:author": 'moranegg', "schema:codeRepository": 'git+https://github.com/moranegg/metadata_test', } self.assertEqual(expected_results, results) def test_index_content_metadata_npm(self): """ testing NPM with package.json - one sha1 uses a file that can't be translated to metadata and should return None in the translated metadata """ # given sha1s = ['26a9f72a7c87cc9205725cfd879f514ff4f3d8d5', 'd4c647f0fc257591cc9ba1722484229780d1c607', '02fb2c89e14f7fab46701478c83779c7beb7b069'] # this metadata indexer computes only metadata for package.json # in npm context with a hard mapping metadata_indexer = ContentMetadataTestIndexer( tool=self.content_tool, config={}) # when metadata_indexer.run(sha1s, policy_update='ignore-dups') results = metadata_indexer.idx_storage.added_data expected_results = [('content_metadata', False, [{ 'indexer_configuration_id': 30, 'translated_metadata': { '@context': 'https://doi.org/10.5063/schema/codemeta-2.0', 'type': 'SoftwareSourceCode', 'schema:codeRepository': 'git+https://github.com/moranegg/metadata_test', 'description': 'Simple package.json test for indexer', 'name': 'test_metadata', 'version': '0.0.1' }, 'id': '26a9f72a7c87cc9205725cfd879f514ff4f3d8d5' }, { 'indexer_configuration_id': 30, 'translated_metadata': { '@context': 'https://doi.org/10.5063/schema/codemeta-2.0', 'type': 'SoftwareSourceCode', 'codemeta:issueTracker': 'https://github.com/npm/npm/issues', 'schema:author': { 'type': 'Person', 'name': 'Isaac Z. Schlueter', 'email': 'i@izs.me', 'schema:url': 'http://blog.izs.me', }, 'schema:codeRepository': 'git+https://github.com/npm/npm', 'description': 'a package manager for JavaScript', 'schema:license': 'Artistic-2.0', 'version': '5.0.3', 'name': 'npm', 'keywords': [ 'install', 'modules', 'package manager', 'package.json' ], 'schema:url': 'https://docs.npmjs.com/' }, 'id': 'd4c647f0fc257591cc9ba1722484229780d1c607' }, { 'indexer_configuration_id': 30, 'translated_metadata': None, 'id': '02fb2c89e14f7fab46701478c83779c7beb7b069' }])] # The assertion below returns False sometimes because of nested lists self.assertEqual(expected_results, results) def test_detect_metadata_package_json(self): # given df = [{ 'sha1_git': b'abc', 'name': b'index.js', 'target': b'abc', 'length': 897, 'status': 'visible', 'type': 'file', 'perms': 33188, 'dir_id': b'dir_a', 'sha1': b'bcd' }, { 'sha1_git': b'aab', 'name': b'package.json', 'target': b'aab', 'length': 712, 'status': 'visible', 'type': 'file', 'perms': 33188, 'dir_id': b'dir_a', 'sha1': b'cde' }] # when results = detect_metadata(df) expected_results = { 'NpmMapping': [ b'cde' ] } # then self.assertEqual(expected_results, results) def test_compute_metadata_valid_codemeta(self): raw_content = ( b"""{ "@context": "https://doi.org/10.5063/schema/codemeta-2.0", "@type": "SoftwareSourceCode", "identifier": "CodeMeta", "description": "CodeMeta is a concept vocabulary that can be used to standardize the exchange of software metadata across repositories and organizations.", "name": "CodeMeta: Minimal metadata schemas for science software and code, in JSON-LD", "codeRepository": "https://github.com/codemeta/codemeta", "issueTracker": "https://github.com/codemeta/codemeta/issues", "license": "https://spdx.org/licenses/Apache-2.0", "version": "2.0", "author": [ { "@type": "Person", "givenName": "Carl", "familyName": "Boettiger", "email": "cboettig@gmail.com", "@id": "http://orcid.org/0000-0002-1642-628X" }, { "@type": "Person", "givenName": "Matthew B.", "familyName": "Jones", "email": "jones@nceas.ucsb.edu", "@id": "http://orcid.org/0000-0003-0077-4738" } ], "maintainer": { "@type": "Person", "givenName": "Carl", "familyName": "Boettiger", "email": "cboettig@gmail.com", "@id": "http://orcid.org/0000-0002-1642-628X" }, "contIntegration": "https://travis-ci.org/codemeta/codemeta", "developmentStatus": "active", "downloadUrl": "https://github.com/codemeta/codemeta/archive/2.0.zip", "funder": { "@id": "https://doi.org/10.13039/100000001", "@type": "Organization", "name": "National Science Foundation" }, "funding":"1549758; Codemeta: A Rosetta Stone for Metadata in Scientific Software", "keywords": [ "metadata", "software" ], "version":"2.0", "dateCreated":"2017-06-05", "datePublished":"2017-06-05", "programmingLanguage": "JSON-LD" }""") # noqa expected_result = { "@context": "https://doi.org/10.5063/schema/codemeta-2.0", "type": "SoftwareSourceCode", "identifier": "CodeMeta", "description": "CodeMeta is a concept vocabulary that can " "be used to standardize the exchange of software metadata " "across repositories and organizations.", "name": "CodeMeta: Minimal metadata schemas for science " "software and code, in JSON-LD", "codeRepository": "https://github.com/codemeta/codemeta", "issueTracker": "https://github.com/codemeta/codemeta/issues", "license": "https://spdx.org/licenses/Apache-2.0", "version": "2.0", "author": [ { "type": "Person", "givenName": "Carl", "familyName": "Boettiger", "email": "cboettig@gmail.com", "id": "http://orcid.org/0000-0002-1642-628X" }, { "type": "Person", "givenName": "Matthew B.", "familyName": "Jones", "email": "jones@nceas.ucsb.edu", "id": "http://orcid.org/0000-0003-0077-4738" } ], "maintainer": { "type": "Person", "givenName": "Carl", "familyName": "Boettiger", "email": "cboettig@gmail.com", "id": "http://orcid.org/0000-0002-1642-628X" }, "contIntegration": "https://travis-ci.org/codemeta/codemeta", "developmentStatus": "active", "downloadUrl": "https://github.com/codemeta/codemeta/archive/2.0.zip", "funder": { "id": "https://doi.org/10.13039/100000001", "type": "Organization", "name": "National Science Foundation" }, "funding": "1549758; Codemeta: A Rosetta Stone for Metadata " "in Scientific Software", "keywords": [ "metadata", "software" ], "version": "2.0", "dateCreated": "2017-06-05", "datePublished": "2017-06-05", "programmingLanguage": "JSON-LD" } result = MAPPINGS["CodemetaMapping"].translate(raw_content) self.assertEqual(result, expected_result) def test_compute_metadata_maven(self): raw_content = b""" Maven Default Project 4.0.0 com.mycompany.app my-app 1.2.3 central Maven Repository Switchboard default http://repo1.maven.org/maven2 false """ result = MAPPINGS["MavenMapping"].translate(raw_content) self.assertEqual(result, { '@context': 'https://doi.org/10.5063/schema/codemeta-2.0', 'type': 'SoftwareSourceCode', 'name': 'Maven Default Project', 'schema:identifier': 'com.mycompany.app', 'version': '1.2.3', 'schema:codeRepository': 'http://repo1.maven.org/maven2/com/mycompany/app/my-app', }) def test_revision_metadata_indexer(self): metadata_indexer = RevisionMetadataTestIndexer() sha1_gits = [ - b'8dbb6aeb036e7fd80664eb8bfd1507881af1ba9f', + hash_to_bytes('8dbb6aeb036e7fd80664eb8bfd1507881af1ba9f'), ] metadata_indexer.run(sha1_gits, 'update-dups') results = metadata_indexer.idx_storage.added_data expected_results = [('revision_metadata', True, [{ - 'id': '8dbb6aeb036e7fd80664eb8bfd1507881af1ba9f', + 'id': hash_to_bytes('8dbb6aeb036e7fd80664eb8bfd1507881af1ba9f'), 'translated_metadata': { '@context': 'https://doi.org/10.5063/schema/codemeta-2.0', 'url': 'https://github.com/librariesio/yarn-parser#readme', 'schema:codeRepository': 'git+https://github.com/librariesio/yarn-parser.git', 'schema:author': 'Andrew Nesbitt', 'license': 'AGPL-3.0', 'version': '1.0.0', 'description': 'Tiny web service for parsing yarn.lock files', 'codemeta:issueTracker': 'https://github.com/librariesio/yarn-parser/issues', 'name': 'yarn-parser', 'keywords': ['yarn', 'parse', 'lock', 'dependencies'], }, 'indexer_configuration_id': 7 }])] # then self.assertEqual(expected_results, results) diff --git a/swh/indexer/tests/test_origin_metadata.py b/swh/indexer/tests/test_origin_metadata.py index 510ae1a..2b651cc 100644 --- a/swh/indexer/tests/test_origin_metadata.py +++ b/swh/indexer/tests/test_origin_metadata.py @@ -1,122 +1,125 @@ # Copyright (C) 2018 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 time import logging import unittest from celery import task from swh.indexer.metadata import OriginMetadataIndexer from swh.indexer.tests.test_utils import MockObjStorage, MockStorage from swh.indexer.tests.test_utils import MockIndexerStorage from swh.indexer.tests.test_origin_head import OriginHeadTestIndexer from swh.indexer.tests.test_metadata import RevisionMetadataTestIndexer from swh.scheduler.tests.scheduler_testing import SchedulerTestFixture +from swh.model.hashutil import hash_to_bytes + class OriginMetadataTestIndexer(OriginMetadataIndexer): def prepare(self): self.config = { 'storage': { 'cls': 'remote', 'args': { 'url': 'http://localhost:9999', } }, 'tools': [], } self.storage = MockStorage() self.idx_storage = MockIndexerStorage() self.log = logging.getLogger('swh.indexer') self.objstorage = MockObjStorage() self.tools = self.register_tools(self.config['tools']) self.results = [] @task def revision_metadata_test_task(*args, **kwargs): indexer = RevisionMetadataTestIndexer() indexer.run(*args, **kwargs) return indexer.results @task def origin_intrinsic_metadata_test_task(*args, **kwargs): indexer = OriginMetadataTestIndexer() indexer.run(*args, **kwargs) return indexer.results class OriginHeadTestIndexer(OriginHeadTestIndexer): def prepare(self): super().prepare() self.config['tasks'] = { 'revision_metadata': 'revision_metadata_test_task', 'origin_intrinsic_metadata': 'origin_intrinsic_metadata_test_task', } class TestOriginMetadata(SchedulerTestFixture, unittest.TestCase): def setUp(self): super().setUp() self.maxDiff = None MockIndexerStorage.added_data = [] self.add_scheduler_task_type( 'revision_metadata_test_task', 'swh.indexer.tests.test_origin_metadata.' 'revision_metadata_test_task') self.add_scheduler_task_type( 'origin_intrinsic_metadata_test_task', 'swh.indexer.tests.test_origin_metadata.' 'origin_intrinsic_metadata_test_task') RevisionMetadataTestIndexer.scheduler = self.scheduler def tearDown(self): del RevisionMetadataTestIndexer.scheduler super().tearDown() def test_pipeline(self): indexer = OriginHeadTestIndexer() indexer.scheduler = self.scheduler indexer.run(["git+https://github.com/librariesio/yarn-parser"]) self.run_ready_tasks() # Run the first task time.sleep(0.1) # Give it time to complete and schedule the 2nd one self.run_ready_tasks() # Run the second task metadata = { '@context': 'https://doi.org/10.5063/schema/codemeta-2.0', 'url': 'https://github.com/librariesio/yarn-parser#readme', 'schema:codeRepository': 'git+https://github.com/librariesio/yarn-parser.git', 'schema:author': 'Andrew Nesbitt', 'license': 'AGPL-3.0', 'version': '1.0.0', 'description': 'Tiny web service for parsing yarn.lock files', 'codemeta:issueTracker': 'https://github.com/librariesio/yarn-parser/issues', 'name': 'yarn-parser', 'keywords': ['yarn', 'parse', 'lock', 'dependencies'], } rev_metadata = { - 'id': '8dbb6aeb036e7fd80664eb8bfd1507881af1ba9f', + 'id': hash_to_bytes('8dbb6aeb036e7fd80664eb8bfd1507881af1ba9f'), 'translated_metadata': metadata, 'indexer_configuration_id': 7, } origin_metadata = { 'origin_id': 54974445, - 'from_revision': '8dbb6aeb036e7fd80664eb8bfd1507881af1ba9f', + 'from_revision': hash_to_bytes( + '8dbb6aeb036e7fd80664eb8bfd1507881af1ba9f'), 'metadata': metadata, 'indexer_configuration_id': 7, } expected_results = [ ('origin_intrinsic_metadata', True, [origin_metadata]), ('revision_metadata', True, [rev_metadata])] results = list(indexer.idx_storage.added_data) self.assertCountEqual(expected_results, results) diff --git a/swh/indexer/tests/test_utils.py b/swh/indexer/tests/test_utils.py index da1f11d..9ccefc6 100644 --- a/swh/indexer/tests/test_utils.py +++ b/swh/indexer/tests/test_utils.py @@ -1,728 +1,732 @@ # Copyright (C) 2017-2018 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.objstorage.exc import ObjNotFoundError from swh.model import hashutil +from swh.model.hashutil import hash_to_bytes ORIGINS = [ { 'id': 52189575, 'lister': None, 'project': None, 'type': 'git', 'url': 'https://github.com/SoftwareHeritage/swh-storage'}, { 'id': 4423668, 'lister': None, 'project': None, 'type': 'ftp', 'url': 'rsync://ftp.gnu.org/gnu/3dldf'}, { 'id': 77775770, 'lister': None, 'project': None, 'type': 'deposit', 'url': 'https://forge.softwareheritage.org/source/jesuisgpl/'}, { 'id': 85072327, 'lister': None, 'project': None, 'type': 'pypi', 'url': 'https://pypi.org/project/limnoria/'}, { 'id': 49908349, 'lister': None, 'project': None, 'type': 'svn', 'url': 'http://0-512-md.googlecode.com/svn/'}, { 'id': 54974445, 'lister': None, 'project': None, 'type': 'git', 'url': 'https://github.com/librariesio/yarn-parser'}, ] SNAPSHOTS = { 52189575: { 'branches': { b'refs/heads/add-revision-origin-cache': { 'target': b'L[\xce\x1c\x88\x8eF\t\xf1"\x19\x1e\xfb\xc0' b's\xe7/\xe9l\x1e', 'target_type': 'revision'}, b'HEAD': { 'target': b'8K\x12\x00d\x03\xcc\xe4]bS\xe3\x8f{\xd7}' b'\xac\xefrm', 'target_type': 'revision'}, b'refs/tags/v0.0.103': { 'target': b'\xb6"Im{\xfdLb\xb0\x94N\xea\x96m\x13x\x88+' b'\x0f\xdd', 'target_type': 'release'}, }}, 4423668: { 'branches': { b'3DLDF-1.1.4.tar.gz': { 'target': b'dJ\xfb\x1c\x91\xf4\x82B%]6\xa2\x90|\xd3\xfc' b'"G\x99\x11', 'target_type': 'revision'}, b'3DLDF-2.0.2.tar.gz': { 'target': b'\xb6\x0e\xe7\x9e9\xac\xaa\x19\x9e=' b'\xd1\xc5\x00\\\xc6\xfc\xe0\xa6\xb4V', 'target_type': 'revision'}, b'3DLDF-2.0.3-examples.tar.gz': { 'target': b'!H\x19\xc0\xee\x82-\x12F1\xbd\x97' b'\xfe\xadZ\x80\x80\xc1\x83\xff', 'target_type': 'revision'}, b'3DLDF-2.0.3.tar.gz': { 'target': b'\x8e\xa9\x8e/\xea}\x9feF\xf4\x9f\xfd\xee' b'\xcc\x1a\xb4`\x8c\x8by', 'target_type': 'revision'}, b'3DLDF-2.0.tar.gz': { 'target': b'F6*\xff(?\x19a\xef\xb6\xc2\x1fv$S\xe3G' b'\xd3\xd1m', b'target_type': 'revision'} }}, 77775770: { 'branches': { b'master': { 'target': b'\xe7n\xa4\x9c\x9f\xfb\xb7\xf76\x11\x08{' b'\xa6\xe9\x99\xb1\x9e]q\xeb', 'target_type': 'revision'} }, 'id': b"h\xc0\xd2a\x04\xd4~'\x8d\xd6\xbe\x07\xeda\xfa\xfbV" b"\x1d\r "}, 85072327: { 'branches': { b'HEAD': { 'target': b'releases/2018.09.09', 'target_type': 'alias'}, b'releases/2018.09.01': { 'target': b'<\xee1(\xe8\x8d_\xc1\xc9\xa6rT\xf1\x1d' b'\xbb\xdfF\xfdw\xcf', 'target_type': 'revision'}, b'releases/2018.09.09': { 'target': b'\x83\xb9\xb6\xc7\x05\xb1%\xd0\xfem\xd8k' b'A\x10\x9d\xc5\xfa2\xf8t', 'target_type': 'revision'}}, 'id': b'{\xda\x8e\x84\x7fX\xff\x92\x80^\x93V\x18\xa3\xfay' b'\x12\x9e\xd6\xb3'}, 49908349: { 'branches': { b'master': { 'target': b'\xe4?r\xe1,\x88\xab\xec\xe7\x9a\x87\xb8' b'\xc9\xad#.\x1bw=\x18', 'target_type': 'revision'}}, 'id': b'\xa1\xa2\x8c\n\xb3\x87\xa8\xf9\xe0a\x8c\xb7' b'\x05\xea\xb8\x1f\xc4H\xf4s'}, 54974445: { 'branches': { b'HEAD': { - 'target': b'8dbb6aeb036e7fd80664eb8bfd1507881af1ba9f', + 'target': hash_to_bytes( + '8dbb6aeb036e7fd80664eb8bfd1507881af1ba9f'), 'target_type': 'revision'}}} } SHA1_TO_LICENSES = { '01c9379dfc33803963d07c1ccc748d3fe4c96bb5': ['GPL'], '02fb2c89e14f7fab46701478c83779c7beb7b069': ['Apache2.0'], '103bc087db1d26afc3a0283f38663d081e9b01e6': ['MIT'], '688a5ef812c53907562fe379d4b3851e69c7cb15': ['AGPL'], 'da39a3ee5e6b4b0d3255bfef95601890afd80709': [], } SHA1_TO_CTAGS = { '01c9379dfc33803963d07c1ccc748d3fe4c96bb5': [{ 'name': 'foo', 'kind': 'str', 'line': 10, 'lang': 'bar', }], 'd4c647f0fc257591cc9ba1722484229780d1c607': [{ 'name': 'let', 'kind': 'int', 'line': 100, 'lang': 'haskell', }], '688a5ef812c53907562fe379d4b3851e69c7cb15': [{ 'name': 'symbol', 'kind': 'float', 'line': 99, 'lang': 'python', }], } class MockObjStorage: """Mock an swh-objstorage objstorage with predefined contents. """ data = {} def __init__(self): self.data = { '01c9379dfc33803963d07c1ccc748d3fe4c96bb5': b'this is some text', '688a5ef812c53907562fe379d4b3851e69c7cb15': b'another text', '8986af901dd2043044ce8f0d8fc039153641cf17': b'yet another text', '02fb2c89e14f7fab46701478c83779c7beb7b069': b""" import unittest import logging from swh.indexer.mimetype import ContentMimetypeIndexer from swh.indexer.tests.test_utils import MockObjStorage class MockStorage(): def content_mimetype_add(self, mimetypes): self.state = mimetypes self.conflict_update = conflict_update def indexer_configuration_add(self, tools): return [{ 'id': 10, }] """, '103bc087db1d26afc3a0283f38663d081e9b01e6': b""" #ifndef __AVL__ #define __AVL__ typedef struct _avl_tree avl_tree; typedef struct _data_t { int content; } data_t; """, '93666f74f1cf635c8c8ac118879da6ec5623c410': b""" (should 'pygments (recognize 'lisp 'easily)) """, '26a9f72a7c87cc9205725cfd879f514ff4f3d8d5': b""" { "name": "test_metadata", "version": "0.0.1", "description": "Simple package.json test for indexer", "repository": { "type": "git", "url": "https://github.com/moranegg/metadata_test" } } """, 'd4c647f0fc257591cc9ba1722484229780d1c607': b""" { "version": "5.0.3", "name": "npm", "description": "a package manager for JavaScript", "keywords": [ "install", "modules", "package manager", "package.json" ], "preferGlobal": true, "config": { "publishtest": false }, "homepage": "https://docs.npmjs.com/", "author": "Isaac Z. Schlueter (http://blog.izs.me)", "repository": { "type": "git", "url": "https://github.com/npm/npm" }, "bugs": { "url": "https://github.com/npm/npm/issues" }, "dependencies": { "JSONStream": "~1.3.1", "abbrev": "~1.1.0", "ansi-regex": "~2.1.1", "ansicolors": "~0.3.2", "ansistyles": "~0.1.3" }, "devDependencies": { "tacks": "~1.2.6", "tap": "~10.3.2" }, "license": "Artistic-2.0" } """, 'a7ab314d8a11d2c93e3dcf528ca294e7b431c449': b""" """, 'da39a3ee5e6b4b0d3255bfef95601890afd80709': b'', } def __iter__(self): yield from self.data.keys() def __contains__(self, sha1): return self.data.get(sha1) is not None def get(self, sha1): raw_content = self.data.get(sha1) if raw_content is None: raise ObjNotFoundError(sha1) return raw_content class MockIndexerStorage(): """Mock an swh-indexer storage. """ added_data = [] revision_metadata = {} def indexer_configuration_add(self, tools): results = [] for tool in tools: results.append(self._indexer_configuration_add_one(tool)) return results def _indexer_configuration_add_one(self, tool): if tool['tool_name'] == 'swh-metadata-translator': return { 'id': 30, 'tool_name': 'swh-metadata-translator', 'tool_version': '0.0.1', 'tool_configuration': { 'type': 'local', 'context': 'NpmMapping' }, } elif tool['tool_name'] == 'swh-metadata-detector': return { 'id': 7, 'tool_name': 'swh-metadata-detector', 'tool_version': '0.0.1', 'tool_configuration': { 'type': 'local', 'context': 'NpmMapping' }, } elif tool['tool_name'] == 'origin-metadata': return { 'id': 8, 'tool_name': 'origin-metadata', 'tool_version': '0.0.1', 'tool_configuration': {}, } else: assert False, 'Unknown tool {tool_name}'.format(**tool) def content_metadata_missing(self, sha1s): yield from [] def content_metadata_add(self, metadata, conflict_update=None): self.added_data.append( ('content_metadata', conflict_update, metadata)) def revision_metadata_add(self, metadata, conflict_update=None): assert conflict_update self.added_data.append( ('revision_metadata', conflict_update, metadata)) for item in metadata: + assert isinstance(item['id'], bytes) self.revision_metadata.setdefault(item['id'], []).append(item) def revision_metadata_get(self, ids): for id_ in ids: + assert isinstance(id_, bytes) yield from self.revision_metadata.get(id_) def origin_intrinsic_metadata_add(self, metadata, conflict_update=None): self.added_data.append( ('origin_intrinsic_metadata', conflict_update, metadata)) def content_metadata_get(self, sha1s): return [{ 'tool': { 'configuration': { 'type': 'local', 'context': 'NpmMapping' }, 'version': '0.0.1', 'id': 6, 'name': 'swh-metadata-translator' }, 'id': b'cde', 'translated_metadata': { '@context': 'https://doi.org/10.5063/schema/codemeta-2.0', 'type': 'SoftwareSourceCode', 'codemeta:issueTracker': 'https://github.com/librariesio/yarn-parser/issues', 'version': '1.0.0', 'name': 'yarn-parser', 'schema:author': 'Andrew Nesbitt', 'url': 'https://github.com/librariesio/yarn-parser#readme', 'processorRequirements': {'node': '7.5'}, 'license': 'AGPL-3.0', 'keywords': ['yarn', 'parse', 'lock', 'dependencies'], 'schema:codeRepository': 'git+https://github.com/librariesio/yarn-parser.git', 'description': 'Tiny web service for parsing yarn.lock files', } }] class MockStorage(): """Mock a real swh-storage storage to simplify reading indexers' outputs. """ def origin_get(self, id_): for origin in ORIGINS: for (k, v) in id_.items(): if origin[k] != v: break else: # This block is run iff we didn't break, ie. if all supplied # parts of the id are set to the expected value. return origin assert False, id_ def snapshot_get_latest(self, origin_id): if origin_id in SNAPSHOTS: return SNAPSHOTS[origin_id] else: assert False, origin_id def revision_get(self, revisions): return [{ - 'id': b'8dbb6aeb036e7fd80664eb8bfd1507881af1ba9f', + 'id': hash_to_bytes('8dbb6aeb036e7fd80664eb8bfd1507881af1ba9f'), 'committer': { 'id': 26, 'name': b'Andrew Nesbitt', 'fullname': b'Andrew Nesbitt ', 'email': b'andrewnez@gmail.com' }, 'synthetic': False, 'date': { 'negative_utc': False, 'timestamp': { 'seconds': 1487596456, 'microseconds': 0 }, 'offset': 0 }, 'directory': b'10' }] def directory_ls(self, directory, recursive=False, cur=None): # with directory: b'\x9d', return [{ 'sha1_git': b'abc', 'name': b'index.js', 'target': b'abc', 'length': 897, 'status': 'visible', 'type': 'file', 'perms': 33188, 'dir_id': b'10', 'sha1': b'bcd' }, { 'sha1_git': b'aab', 'name': b'package.json', 'target': b'aab', 'length': 712, 'status': 'visible', 'type': 'file', 'perms': 33188, 'dir_id': b'10', 'sha1': b'cde' }, { 'dir_id': b'10', 'target': b'11', 'type': 'dir', 'length': None, 'name': b'.github', 'sha1': None, 'perms': 16384, 'sha1_git': None, 'status': None, 'sha256': None }] class BasicMockStorage(): """In memory implementation to fake the content_get_range api. FIXME: To remove when the actual in-memory lands. """ contents = [] def __init__(self, contents): self.contents = contents def content_get_range(self, start, end, limit=1000): # to make input test data consilient with actual runtime the # other way of doing properly things would be to rewrite all # tests (that's another task entirely so not right now) if isinstance(start, bytes): start = hashutil.hash_to_hex(start) if isinstance(end, bytes): end = hashutil.hash_to_hex(end) results = [] _next_id = None counter = 0 for c in self.contents: _id = c['sha1'] if start <= _id and _id <= end: results.append(c) if counter >= limit: break counter += 1 return { 'contents': results, 'next': _next_id } class BasicMockIndexerStorage(): """Mock Indexer storage to simplify reading indexers' outputs. """ state = [] def _internal_add(self, data, conflict_update=None): """All content indexer have the same structure. So reuse `data` as the same data. It's either mimetype, language, fossology_license, etc... """ self.state = data self.conflict_update = conflict_update def content_mimetype_add(self, data, conflict_update=None): self._internal_add(data, conflict_update=conflict_update) def content_fossology_license_add(self, data, conflict_update=None): self._internal_add(data, conflict_update=conflict_update) def content_language_add(self, data, conflict_update=None): self._internal_add(data, conflict_update=conflict_update) def content_ctags_add(self, data, conflict_update=None): self._internal_add(data, conflict_update=conflict_update) def _internal_get_range(self, start, end, indexer_configuration_id, limit=1000): """Same logic as _internal_add, we retrieve indexed data given an identifier. So the code here does not change even though the underlying data does. """ # to make input test data consilient with actual runtime the # other way of doing properly things would be to rewrite all # tests (that's another task entirely so not right now) if isinstance(start, bytes): start = hashutil.hash_to_hex(start) if isinstance(end, bytes): end = hashutil.hash_to_hex(end) results = [] _next = None counter = 0 for m in self.state: _id = m['id'] _tool_id = m['indexer_configuration_id'] if (start <= _id and _id <= end and _tool_id == indexer_configuration_id): results.append(_id) if counter >= limit: break counter += 1 return { 'ids': results, 'next': _next } def content_mimetype_get_range( self, start, end, indexer_configuration_id, limit=1000): return self._internal_get_range( start, end, indexer_configuration_id, limit=limit) def content_fossology_license_get_range( self, start, end, indexer_configuration_id, limit=1000): return self._internal_get_range( start, end, indexer_configuration_id, limit=limit) def indexer_configuration_add(self, tools): return [{ 'id': 10, }] class CommonIndexerNoTool: """Mixin to wronly initialize content indexer""" def prepare(self): super().prepare() self.tools = None class CommonIndexerWithErrorsTest: """Test indexer configuration checks. """ Indexer = None RangeIndexer = None def test_wrong_unknown_configuration_tool(self): """Indexer with unknown configuration tool fails check""" with self.assertRaisesRegex(ValueError, 'Tools None is unknown'): print('indexer: %s' % self.Indexer) self.Indexer() def test_wrong_unknown_configuration_tool_range(self): """Range Indexer with unknown configuration tool fails check""" if self.RangeIndexer is not None: with self.assertRaisesRegex(ValueError, 'Tools None is unknown'): self.RangeIndexer() class CommonContentIndexerTest: def assert_results_ok(self, actual_results, expected_results=None): if expected_results is None: expected_results = self.expected_results for indexed_data in actual_results: _id = indexed_data['id'] self.assertEqual(indexed_data, expected_results[_id]) _tool_id = indexed_data['indexer_configuration_id'] self.assertEqual(_tool_id, self.indexer.tool['id']) def test_index(self): """Known sha1 have their data indexed """ sha1s = [self.id0, self.id1, self.id2] # when self.indexer.run(sha1s, policy_update='update-dups') actual_results = self.indexer.idx_storage.state self.assertTrue(self.indexer.idx_storage.conflict_update) self.assert_results_ok(actual_results) # 2nd pass self.indexer.run(sha1s, policy_update='ignore-dups') self.assertFalse(self.indexer.idx_storage.conflict_update) self.assert_results_ok(actual_results) def test_index_one_unknown_sha1(self): """Unknown sha1 are not indexed""" sha1s = [self.id1, '799a5ef812c53907562fe379d4b3851e69c7cb15', # unknown '800a5ef812c53907562fe379d4b3851e69c7cb15'] # unknown # when self.indexer.run(sha1s, policy_update='update-dups') actual_results = self.indexer.idx_storage.state # then expected_results = { k: v for k, v in self.expected_results.items() if k in sha1s } self.assert_results_ok(actual_results, expected_results) class CommonContentIndexerRangeTest: """Allows to factorize tests on range indexer. """ def assert_results_ok(self, start, end, actual_results, expected_results=None): if expected_results is None: expected_results = self.expected_results for indexed_data in actual_results: _id = indexed_data['id'] self.assertEqual(indexed_data, expected_results[_id]) self.assertTrue(start <= _id and _id <= end) _tool_id = indexed_data['indexer_configuration_id'] self.assertEqual(_tool_id, self.indexer.tool['id']) def test__index_contents(self): """Indexing contents without existing data results in indexed data """ start, end = [self.contents[0], self.contents[2]] # output hex ids # given actual_results = list(self.indexer._index_contents( start, end, indexed={})) self.assert_results_ok(start, end, actual_results) def test__index_contents_with_indexed_data(self): """Indexing contents with existing data results in less indexed data """ start, end = [self.contents[0], self.contents[2]] # output hex ids data_indexed = [self.id0, self.id2] # given actual_results = self.indexer._index_contents( start, end, indexed=set(data_indexed)) # craft the expected results expected_results = self.expected_results.copy() for already_indexed_key in data_indexed: expected_results.pop(already_indexed_key) self.assert_results_ok( start, end, actual_results, expected_results) def test_generate_content_get(self): """Optimal indexing should result in indexed data """ start, end = [self.contents[0], self.contents[2]] # output hex ids # given actual_results = self.indexer.run(start, end) # then self.assertTrue(actual_results) def test_generate_content_get_input_as_bytes(self): """Optimal indexing should result in indexed data Input are in bytes here. """ _start, _end = [self.contents[0], self.contents[2]] # output hex ids start, end = map(hashutil.hash_to_bytes, (_start, _end)) # given actual_results = self.indexer.run( # checks the bytes input this time start, end, skip_existing=False) # no data so same result # then self.assertTrue(actual_results) def test_generate_content_get_no_result(self): """No result indexed returns False""" start, end = ['0000000000000000000000000000000000000000', '0000000000000000000000000000000000000001'] # given actual_results = self.indexer.run( start, end, incremental=False) # then self.assertFalse(actual_results) class NoDiskIndexer: """Mixin to override the DiskIndexer behavior avoiding side-effects in tests. """ def write_to_temp(self, filename, data): # noop return filename def cleanup(self, content_path): # noop return None