diff --git a/swh/indexer/storage/__init__.py b/swh/indexer/storage/__init__.py index 5707012..d7592bb 100644 --- a/swh/indexer/storage/__init__.py +++ b/swh/indexer/storage/__init__.py @@ -1,756 +1,803 @@ # 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 import json import psycopg2 from collections import defaultdict from swh.core.api import remote_api_endpoint from swh.storage.common import db_transaction_generator, db_transaction from swh.storage.exc import StorageDBError from .db import Db +from ..metadata_dictionary import MAPPINGS from . import converters INDEXER_CFG_KEY = 'indexer_storage' def get_indexer_storage(cls, args): """Get an indexer storage object of class `storage_class` with arguments `storage_args`. Args: cls (str): storage's class, either 'local' or 'remote' args (dict): dictionary of arguments passed to the storage class constructor Returns: an instance of swh.indexer's storage (either local or remote) Raises: ValueError if passed an unknown storage class. """ if cls == 'remote': from .api.client import RemoteStorage as IndexerStorage elif cls == 'local': from . import IndexerStorage elif cls == 'memory': from .in_memory import IndexerStorage else: raise ValueError('Unknown indexer storage class `%s`' % cls) return IndexerStorage(**args) class IndexerStorage: """SWH Indexer Storage """ def __init__(self, db, min_pool_conns=1, max_pool_conns=10): """ Args: db_conn: either a libpq connection string, or a psycopg2 connection """ try: if isinstance(db, psycopg2.extensions.connection): self._pool = None self._db = Db(db) else: self._pool = psycopg2.pool.ThreadedConnectionPool( min_pool_conns, max_pool_conns, db ) self._db = None except psycopg2.OperationalError as e: raise StorageDBError(e) def get_db(self): if self._db: return self._db return Db.from_pool(self._pool) @remote_api_endpoint('check_config') def check_config(self, *, check_write): """Check that the storage is configured and ready to go.""" # Check permissions on one of the tables with self.get_db().transaction() as cur: if check_write: check = 'INSERT' else: check = 'SELECT' cur.execute( "select has_table_privilege(current_user, 'content_mimetype', %s)", # noqa (check,) ) return cur.fetchone()[0] return True @remote_api_endpoint('content_mimetype/missing') @db_transaction_generator() def content_mimetype_missing(self, mimetypes, db=None, cur=None): """Generate mimetypes missing from storage. Args: mimetypes (iterable): iterable of dict with keys: - **id** (bytes): sha1 identifier - **indexer_configuration_id** (int): tool used to compute the results Yields: tuple (id, indexer_configuration_id): missing id """ for obj in db.content_mimetype_missing_from_list(mimetypes, cur): yield obj[0] def _content_get_range(self, content_type, start, end, indexer_configuration_id, limit=1000, with_textual_data=False, db=None, cur=None): """Retrieve ids of type content_type within range [start, end] bound by limit. Args: **content_type** (str): content's type (mimetype, language, etc...) **start** (bytes): Starting identifier range (expected smaller than end) **end** (bytes): Ending identifier range (expected larger than start) **indexer_configuration_id** (int): The tool used to index data **limit** (int): Limit result (default to 1000) **with_textual_data** (bool): Deal with only textual content (True) or all content (all contents by defaults, False) Raises: ValueError for; - limit to None - wrong content_type provided Returns: a dict with keys: - **ids** [bytes]: iterable of content ids within the range. - **next** (Optional[bytes]): The next range of sha1 starts at this sha1 if any """ if limit is None: raise ValueError('Development error: limit should not be None') if content_type not in db.content_indexer_names: err = 'Development error: Wrong type. Should be one of [%s]' % ( ','.join(db.content_indexer_names)) raise ValueError(err) ids = [] next_id = None for counter, obj in enumerate(db.content_get_range( content_type, start, end, indexer_configuration_id, limit=limit+1, with_textual_data=with_textual_data, cur=cur)): _id = obj[0] if counter >= limit: next_id = _id break ids.append(_id) return { 'ids': ids, 'next': next_id } @remote_api_endpoint('content_mimetype/range') @db_transaction() def content_mimetype_get_range(self, start, end, indexer_configuration_id, limit=1000, db=None, cur=None): """Retrieve mimetypes within range [start, end] bound by limit. Args: **start** (bytes): Starting identifier range (expected smaller than end) **end** (bytes): Ending identifier range (expected larger than start) **indexer_configuration_id** (int): The tool used to index data **limit** (int): Limit result (default to 1000) Raises: ValueError for limit to None Returns: a dict with keys: - **ids** [bytes]: iterable of content ids within the range. - **next** (Optional[bytes]): The next range of sha1 starts at this sha1 if any """ return self._content_get_range('mimetype', start, end, indexer_configuration_id, limit=limit, db=db, cur=cur) @remote_api_endpoint('content_mimetype/add') @db_transaction() def content_mimetype_add(self, mimetypes, conflict_update=False, db=None, cur=None): """Add mimetypes not present in storage. Args: mimetypes (iterable): dictionaries with keys: - **id** (bytes): sha1 identifier - **mimetype** (bytes): raw content's mimetype - **encoding** (bytes): raw content's encoding - **indexer_configuration_id** (int): tool's id used to compute the results - **conflict_update** (bool): Flag to determine if we want to overwrite (``True``) or skip duplicates (``False``, the default) """ db.mktemp_content_mimetype(cur) db.copy_to(mimetypes, 'tmp_content_mimetype', ['id', 'mimetype', 'encoding', 'indexer_configuration_id'], cur) db.content_mimetype_add_from_temp(conflict_update, cur) @remote_api_endpoint('content_mimetype') @db_transaction_generator() def content_mimetype_get(self, ids, db=None, cur=None): """Retrieve full content mimetype per ids. Args: ids (iterable): sha1 identifier Yields: mimetypes (iterable): dictionaries with keys: - **id** (bytes): sha1 identifier - **mimetype** (bytes): raw content's mimetype - **encoding** (bytes): raw content's encoding - **tool** (dict): Tool used to compute the language """ for c in db.content_mimetype_get_from_list(ids, cur): yield converters.db_to_mimetype( dict(zip(db.content_mimetype_cols, c))) @remote_api_endpoint('content_language/missing') @db_transaction_generator() def content_language_missing(self, languages, db=None, cur=None): """List languages missing from storage. Args: languages (iterable): dictionaries with keys: - **id** (bytes): sha1 identifier - **indexer_configuration_id** (int): tool used to compute the results Yields: an iterable of missing id for the tuple (id, indexer_configuration_id) """ for obj in db.content_language_missing_from_list(languages, cur): yield obj[0] @remote_api_endpoint('content_language') @db_transaction_generator() def content_language_get(self, ids, db=None, cur=None): """Retrieve full content language per ids. Args: ids (iterable): sha1 identifier Yields: languages (iterable): dictionaries with keys: - **id** (bytes): sha1 identifier - **lang** (bytes): raw content's language - **tool** (dict): Tool used to compute the language """ for c in db.content_language_get_from_list(ids, cur): yield converters.db_to_language( dict(zip(db.content_language_cols, c))) @remote_api_endpoint('content_language/add') @db_transaction() def content_language_add(self, languages, conflict_update=False, db=None, cur=None): """Add languages not present in storage. Args: languages (iterable): dictionaries with keys: - **id** (bytes): sha1 - **lang** (bytes): language detected conflict_update (bool): Flag to determine if we want to overwrite (true) or skip duplicates (false, the default) """ db.mktemp_content_language(cur) # empty language is mapped to 'unknown' db.copy_to( ({ 'id': l['id'], 'lang': 'unknown' if not l['lang'] else l['lang'], 'indexer_configuration_id': l['indexer_configuration_id'], } for l in languages), 'tmp_content_language', ['id', 'lang', 'indexer_configuration_id'], cur) db.content_language_add_from_temp(conflict_update, cur) @remote_api_endpoint('content/ctags/missing') @db_transaction_generator() def content_ctags_missing(self, ctags, db=None, cur=None): """List ctags missing from storage. Args: ctags (iterable): dicts with keys: - **id** (bytes): sha1 identifier - **indexer_configuration_id** (int): tool used to compute the results Yields: an iterable of missing id for the tuple (id, indexer_configuration_id) """ for obj in db.content_ctags_missing_from_list(ctags, cur): yield obj[0] @remote_api_endpoint('content/ctags') @db_transaction_generator() def content_ctags_get(self, ids, db=None, cur=None): """Retrieve ctags per id. Args: ids (iterable): sha1 checksums Yields: Dictionaries with keys: - **id** (bytes): content's identifier - **name** (str): symbol's name - **kind** (str): symbol's kind - **lang** (str): language for that content - **tool** (dict): tool used to compute the ctags' info """ for c in db.content_ctags_get_from_list(ids, cur): yield converters.db_to_ctags(dict(zip(db.content_ctags_cols, c))) @remote_api_endpoint('content/ctags/add') @db_transaction() def content_ctags_add(self, ctags, conflict_update=False, db=None, cur=None): """Add ctags not present in storage Args: ctags (iterable): dictionaries with keys: - **id** (bytes): sha1 - **ctags** ([list): List of dictionary with keys: name, kind, line, lang """ def _convert_ctags(__ctags): """Convert ctags dict to list of ctags. """ for ctags in __ctags: yield from converters.ctags_to_db(ctags) db.mktemp_content_ctags(cur) db.copy_to(list(_convert_ctags(ctags)), tblname='tmp_content_ctags', columns=['id', 'name', 'kind', 'line', 'lang', 'indexer_configuration_id'], cur=cur) db.content_ctags_add_from_temp(conflict_update, cur) @remote_api_endpoint('content/ctags/search') @db_transaction_generator() def content_ctags_search(self, expression, limit=10, last_sha1=None, db=None, cur=None): """Search through content's raw ctags symbols. Args: expression (str): Expression to search for limit (int): Number of rows to return (default to 10). last_sha1 (str): Offset from which retrieving data (default to ''). Yields: rows of ctags including id, name, lang, kind, line, etc... """ for obj in db.content_ctags_search(expression, last_sha1, limit, cur=cur): yield converters.db_to_ctags(dict(zip(db.content_ctags_cols, obj))) @remote_api_endpoint('content/fossology_license') @db_transaction_generator() def content_fossology_license_get(self, ids, db=None, cur=None): """Retrieve licenses per id. Args: ids (iterable): sha1 checksums Yields: `{id: facts}` where `facts` is a dict with the following keys: - **licenses** ([str]): associated licenses for that content - **tool** (dict): Tool used to compute the license """ d = defaultdict(list) for c in db.content_fossology_license_get_from_list(ids, cur): license = dict(zip(db.content_fossology_license_cols, c)) id_ = license['id'] d[id_].append(converters.db_to_fossology_license(license)) for id_, facts in d.items(): yield {id_: facts} @remote_api_endpoint('content/fossology_license/add') @db_transaction() def content_fossology_license_add(self, licenses, conflict_update=False, db=None, cur=None): """Add licenses not present in storage. Args: licenses (iterable): dictionaries with keys: - **id**: sha1 - **licenses** ([bytes]): List of licenses associated to sha1 - **tool** (str): nomossa conflict_update: Flag to determine if we want to overwrite (true) or skip duplicates (false, the default) Returns: list: content_license entries which failed due to unknown licenses """ # Then, we add the correct ones db.mktemp_content_fossology_license(cur) db.copy_to( ({ 'id': sha1['id'], 'indexer_configuration_id': sha1['indexer_configuration_id'], 'license': license, } for sha1 in licenses for license in sha1['licenses']), tblname='tmp_content_fossology_license', columns=['id', 'license', 'indexer_configuration_id'], cur=cur) db.content_fossology_license_add_from_temp(conflict_update, cur) @remote_api_endpoint('content/fossology_license/range') @db_transaction() def content_fossology_license_get_range( self, start, end, indexer_configuration_id, limit=1000, db=None, cur=None): """Retrieve licenses within range [start, end] bound by limit. Args: **start** (bytes): Starting identifier range (expected smaller than end) **end** (bytes): Ending identifier range (expected larger than start) **indexer_configuration_id** (int): The tool used to index data **limit** (int): Limit result (default to 1000) Raises: ValueError for limit to None Returns: a dict with keys: - **ids** [bytes]: iterable of content ids within the range. - **next** (Optional[bytes]): The next range of sha1 starts at this sha1 if any """ return self._content_get_range('fossology_license', start, end, indexer_configuration_id, limit=limit, with_textual_data=True, db=db, cur=cur) @remote_api_endpoint('content_metadata/missing') @db_transaction_generator() def content_metadata_missing(self, metadata, db=None, cur=None): """List metadata missing from storage. Args: metadata (iterable): dictionaries with keys: - **id** (bytes): sha1 identifier - **indexer_configuration_id** (int): tool used to compute the results Yields: missing sha1s """ for obj in db.content_metadata_missing_from_list(metadata, cur): yield obj[0] @remote_api_endpoint('content_metadata') @db_transaction_generator() def content_metadata_get(self, ids, db=None, cur=None): """Retrieve metadata per id. Args: ids (iterable): sha1 checksums Yields: dictionaries with the following keys: id (bytes) translated_metadata (str): associated metadata tool (dict): tool used to compute metadata """ for c in db.content_metadata_get_from_list(ids, cur): yield converters.db_to_metadata( dict(zip(db.content_metadata_cols, c))) @remote_api_endpoint('content_metadata/add') @db_transaction() def content_metadata_add(self, metadata, conflict_update=False, db=None, cur=None): """Add metadata not present in storage. Args: metadata (iterable): dictionaries with keys: - **id**: sha1 - **translated_metadata**: arbitrary dict conflict_update: Flag to determine if we want to overwrite (true) or skip duplicates (false, the default) """ db.mktemp_content_metadata(cur) db.copy_to(metadata, 'tmp_content_metadata', ['id', 'translated_metadata', 'indexer_configuration_id'], cur) db.content_metadata_add_from_temp(conflict_update, cur) @remote_api_endpoint('revision_metadata/missing') @db_transaction_generator() def revision_metadata_missing(self, metadata, db=None, cur=None): """List metadata missing from storage. Args: metadata (iterable): dictionaries with keys: - **id** (bytes): sha1_git revision identifier - **indexer_configuration_id** (int): tool used to compute the results Yields: missing ids """ for obj in db.revision_metadata_missing_from_list(metadata, cur): yield obj[0] @remote_api_endpoint('revision_metadata') @db_transaction_generator() def revision_metadata_get(self, ids, db=None, cur=None): """Retrieve revision metadata per id. Args: ids (iterable): sha1 checksums Yields: dictionaries with the following keys: - **id** (bytes) - **translated_metadata** (str): associated metadata - **tool** (dict): tool used to compute metadata - **mappings** (List[str]): list of mappings used to translate these metadata """ for c in db.revision_metadata_get_from_list(ids, cur): yield converters.db_to_metadata( dict(zip(db.revision_metadata_cols, c))) @remote_api_endpoint('revision_metadata/add') @db_transaction() def revision_metadata_add(self, metadata, conflict_update=False, db=None, cur=None): """Add metadata not present in storage. Args: metadata (iterable): dictionaries with keys: - **id**: sha1_git of revision - **translated_metadata**: arbitrary dict - **indexer_configuration_id**: tool used to compute metadata - **mappings** (List[str]): list of mappings used to translate these metadata conflict_update: Flag to determine if we want to overwrite (true) or skip duplicates (false, the default) """ db.mktemp_revision_metadata(cur) db.copy_to(metadata, 'tmp_revision_metadata', ['id', 'translated_metadata', 'mappings', 'indexer_configuration_id'], cur) db.revision_metadata_add_from_temp(conflict_update, cur) @remote_api_endpoint('origin_intrinsic_metadata') @db_transaction_generator() def origin_intrinsic_metadata_get(self, ids, db=None, cur=None): """Retrieve origin metadata per id. Args: ids (iterable): origin identifiers Yields: list: dictionaries with the following keys: - **origin_id** (int) - **metadata** (str): associated metadata - **tool** (dict): tool used to compute metadata - **mappings** (List[str]): list of mappings used to translate these metadata """ for c in db.origin_intrinsic_metadata_get_from_list(ids, cur): yield converters.db_to_metadata( dict(zip(db.origin_intrinsic_metadata_cols, c))) @remote_api_endpoint('origin_intrinsic_metadata/add') @db_transaction() def origin_intrinsic_metadata_add(self, metadata, conflict_update=False, db=None, cur=None): """Add origin metadata not present in storage. Args: metadata (iterable): dictionaries with keys: - **origin_id**: origin identifier - **from_revision**: sha1 id of the revision used to generate these metadata. - **metadata**: arbitrary dict - **indexer_configuration_id**: tool used to compute metadata - **mappings** (List[str]): list of mappings used to translate these metadata conflict_update: Flag to determine if we want to overwrite (true) or skip duplicates (false, the default) """ db.mktemp_origin_intrinsic_metadata(cur) db.copy_to(metadata, 'tmp_origin_intrinsic_metadata', ['origin_id', 'metadata', 'indexer_configuration_id', 'from_revision', 'mappings'], cur) db.origin_intrinsic_metadata_add_from_temp(conflict_update, cur) @remote_api_endpoint('origin_intrinsic_metadata/search/fulltext') @db_transaction_generator() def origin_intrinsic_metadata_search_fulltext( self, conjunction, limit=100, db=None, cur=None): """Returns the list of origins whose metadata contain all the terms. Args: conjunction (List[str]): List of terms to be searched for. limit (int): The maximum number of results to return Yields: list: dictionaries with the following keys: - **id** (int) - **metadata** (str): associated metadata - **tool** (dict): tool used to compute metadata - **mappings** (List[str]): list of mappings used to translate these metadata """ for c in db.origin_intrinsic_metadata_search_fulltext( conjunction, limit=limit, cur=cur): yield converters.db_to_metadata( dict(zip(db.origin_intrinsic_metadata_cols, c))) + @remote_api_endpoint('origin_intrinsic_metadata/stats') + @db_transaction() + def origin_intrinsic_metadata_stats( + self, db=None, cur=None): + """Returns counts of indexed metadata per origins, broken down + into metadata types. + + Returns: + dict: dictionary with keys: + + - total (int): total number of origins that were indexed + (possibly yielding an empty metadata dictionary) + - non_empty (int): total number of origins that we extracted + a non-empty metadata dictionary from + - per_mapping (dict): a dictionary with mapping names as + keys and number of origins whose indexing used this + mapping. Note that indexing a given origin may use + 0, 1, or many mappings. + """ + mapping_names = [m.name for m in MAPPINGS.values()] + select_parts = [] + + # Count rows for each mapping + for mapping_name in mapping_names: + select_parts.append(( + "sum(case when (mappings @> ARRAY['%s']) " + " then 1 else 0 end)" + ) % mapping_name) + + # Total + select_parts.append("sum(1)") + + # Rows whose metadata has at least one key that is not '@context' + select_parts.append( + "sum(case when ('{}'::jsonb @> (metadata - '@context')) " + " then 0 else 1 end)") + cur.execute('select ' + ', '.join(select_parts) + + ' from origin_intrinsic_metadata') + results = dict(zip(mapping_names + ['total', 'non_empty'], + cur.fetchone())) + return { + 'total': results.pop('total'), + 'non_empty': results.pop('non_empty'), + 'per_mapping': results, + } + @remote_api_endpoint('indexer_configuration/add') @db_transaction_generator() def indexer_configuration_add(self, tools, db=None, cur=None): """Add new tools to the storage. Args: tools ([dict]): List of dictionary representing tool to insert in the db. Dictionary with the following keys: - **tool_name** (str): tool's name - **tool_version** (str): tool's version - **tool_configuration** (dict): tool's configuration (free form dict) Returns: List of dict inserted in the db (holding the id key as well). The order of the list is not guaranteed to match the order of the initial list. """ db.mktemp_indexer_configuration(cur) db.copy_to(tools, 'tmp_indexer_configuration', ['tool_name', 'tool_version', 'tool_configuration'], cur) tools = db.indexer_configuration_add_from_temp(cur) for line in tools: yield dict(zip(db.indexer_configuration_cols, line)) @remote_api_endpoint('indexer_configuration/data') @db_transaction() def indexer_configuration_get(self, tool, db=None, cur=None): """Retrieve tool information. Args: tool (dict): Dictionary representing a tool with the following keys: - **tool_name** (str): tool's name - **tool_version** (str): tool's version - **tool_configuration** (dict): tool's configuration (free form dict) Returns: The same dictionary with an `id` key, None otherwise. """ tool_conf = tool['tool_configuration'] if isinstance(tool_conf, dict): tool_conf = json.dumps(tool_conf) idx = db.indexer_configuration_get(tool['tool_name'], tool['tool_version'], tool_conf) if not idx: return None return dict(zip(db.indexer_configuration_cols, idx)) diff --git a/swh/indexer/storage/in_memory.py b/swh/indexer/storage/in_memory.py index 6e146ce..bbe0880 100644 --- a/swh/indexer/storage/in_memory.py +++ b/swh/indexer/storage/in_memory.py @@ -1,712 +1,743 @@ # 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 bisect from collections import defaultdict, Counter import itertools import json import operator import math import re +from ..metadata_dictionary import MAPPINGS + SHA1_DIGEST_SIZE = 160 def _transform_tool(tool): return { 'id': tool['id'], 'name': tool['tool_name'], 'version': tool['tool_version'], 'configuration': tool['tool_configuration'], } class SubStorage: """Implements common missing/get/add logic for each indexer type.""" def __init__(self, tools): self._tools = tools self._sorted_ids = [] self._data = {} # map (id_, tool_id) -> metadata_dict self._tools_per_id = defaultdict(set) # map id_ -> Set[tool_id] def missing(self, ids): """List data missing from storage. Args: data (iterable): dictionaries with keys: - **id** (bytes): sha1 identifier - **indexer_configuration_id** (int): tool used to compute the results Yields: missing sha1s """ for id_ in ids: tool_id = id_['indexer_configuration_id'] id_ = id_['id'] if tool_id not in self._tools_per_id.get(id_, set()): yield id_ def get(self, ids): """Retrieve data per id. Args: ids (iterable): sha1 checksums Yields: dict: dictionaries with the following keys: - **id** (bytes) - **tool** (dict): tool used to compute metadata - arbitrary data (as provided to `add`) """ for id_ in ids: for tool_id in self._tools_per_id.get(id_, set()): key = (id_, tool_id) yield { 'id': id_, 'tool': _transform_tool(self._tools[tool_id]), **self._data[key], } def get_all(self): yield from self.get(list(self._tools_per_id)) def get_range(self, start, end, indexer_configuration_id, limit): """Retrieve data within range [start, end] bound by limit. Args: **start** (bytes): Starting identifier range (expected smaller than end) **end** (bytes): Ending identifier range (expected larger than start) **indexer_configuration_id** (int): The tool used to index data **limit** (int): Limit result Raises: ValueError for limit to None Returns: a dict with keys: - **ids** [bytes]: iterable of content ids within the range. - **next** (Optional[bytes]): The next range of sha1 starts at this sha1 if any """ if limit is None: raise ValueError('Development error: limit should not be None') from_index = bisect.bisect_left(self._sorted_ids, start) to_index = bisect.bisect_right(self._sorted_ids, end, lo=from_index) if to_index - from_index >= limit: return { 'ids': self._sorted_ids[from_index:from_index+limit], 'next': self._sorted_ids[from_index+limit], } else: return { 'ids': self._sorted_ids[from_index:to_index], 'next': None, } def add(self, data, conflict_update): """Add data not present in storage. Args: data (iterable): dictionaries with keys: - **id**: sha1 - **indexer_configuration_id**: tool used to compute the results - arbitrary data conflict_update (bool): Flag to determine if we want to overwrite (true) or skip duplicates (false) """ for item in data: item = item.copy() tool_id = item.pop('indexer_configuration_id') id_ = item.pop('id') data = item if not conflict_update and \ tool_id in self._tools_per_id.get(id_, set()): # Duplicate, should not be updated continue key = (id_, tool_id) self._data[key] = data self._tools_per_id[id_].add(tool_id) if id_ not in self._sorted_ids: bisect.insort(self._sorted_ids, id_) def add_merge(self, new_data, conflict_update, merged_key): for new_item in new_data: id_ = new_item['id'] tool_id = new_item['indexer_configuration_id'] if conflict_update: all_subitems = [] else: existing = list(self.get([id_])) all_subitems = [ old_subitem for existing_item in existing if existing_item['tool']['id'] == tool_id for old_subitem in existing_item[merged_key] ] for new_subitem in new_item[merged_key]: if new_subitem not in all_subitems: all_subitems.append(new_subitem) self.add([ { 'id': id_, 'indexer_configuration_id': tool_id, merged_key: all_subitems, } ], conflict_update=True) if id_ not in self._sorted_ids: bisect.insort(self._sorted_ids, id_) class IndexerStorage: """In-memory SWH indexer storage.""" def __init__(self): self._tools = {} self._mimetypes = SubStorage(self._tools) self._languages = SubStorage(self._tools) self._content_ctags = SubStorage(self._tools) self._licenses = SubStorage(self._tools) self._content_metadata = SubStorage(self._tools) self._revision_metadata = SubStorage(self._tools) self._origin_intrinsic_metadata = SubStorage(self._tools) def content_mimetype_missing(self, mimetypes): """Generate mimetypes missing from storage. Args: mimetypes (iterable): iterable of dict with keys: - **id** (bytes): sha1 identifier - **indexer_configuration_id** (int): tool used to compute the results Yields: tuple (id, indexer_configuration_id): missing id """ yield from self._mimetypes.missing(mimetypes) def content_mimetype_get_range( self, start, end, indexer_configuration_id, limit=1000): """Retrieve mimetypes within range [start, end] bound by limit. Args: **start** (bytes): Starting identifier range (expected smaller than end) **end** (bytes): Ending identifier range (expected larger than start) **indexer_configuration_id** (int): The tool used to index data **limit** (int): Limit result (default to 1000) Raises: ValueError for limit to None Returns: a dict with keys: - **ids** [bytes]: iterable of content ids within the range. - **next** (Optional[bytes]): The next range of sha1 starts at this sha1 if any """ return self._mimetypes.get_range( start, end, indexer_configuration_id, limit) def content_mimetype_add(self, mimetypes, conflict_update=False): """Add mimetypes not present in storage. Args: mimetypes (iterable): dictionaries with keys: - **id** (bytes): sha1 identifier - **mimetype** (bytes): raw content's mimetype - **encoding** (bytes): raw content's encoding - **indexer_configuration_id** (int): tool's id used to compute the results - **conflict_update** (bool): Flag to determine if we want to overwrite (``True``) or skip duplicates (``False``, the default) """ if not all(isinstance(x['id'], bytes) for x in mimetypes): raise TypeError('identifiers must be bytes.') self._mimetypes.add(mimetypes, conflict_update) def content_mimetype_get(self, ids, db=None, cur=None): """Retrieve full content mimetype per ids. Args: ids (iterable): sha1 identifier Yields: mimetypes (iterable): dictionaries with keys: - **id** (bytes): sha1 identifier - **mimetype** (bytes): raw content's mimetype - **encoding** (bytes): raw content's encoding - **tool** (dict): Tool used to compute the language """ yield from self._mimetypes.get(ids) def content_language_missing(self, languages): """List languages missing from storage. Args: languages (iterable): dictionaries with keys: - **id** (bytes): sha1 identifier - **indexer_configuration_id** (int): tool used to compute the results Yields: an iterable of missing id for the tuple (id, indexer_configuration_id) """ yield from self._languages.missing(languages) def content_language_get(self, ids): """Retrieve full content language per ids. Args: ids (iterable): sha1 identifier Yields: languages (iterable): dictionaries with keys: - **id** (bytes): sha1 identifier - **lang** (bytes): raw content's language - **tool** (dict): Tool used to compute the language """ yield from self._languages.get(ids) def content_language_add(self, languages, conflict_update=False): """Add languages not present in storage. Args: languages (iterable): dictionaries with keys: - **id** (bytes): sha1 - **lang** (bytes): language detected conflict_update (bool): Flag to determine if we want to overwrite (true) or skip duplicates (false, the default) """ if not all(isinstance(x['id'], bytes) for x in languages): raise TypeError('identifiers must be bytes.') self._languages.add(languages, conflict_update) def content_ctags_missing(self, ctags): """List ctags missing from storage. Args: ctags (iterable): dicts with keys: - **id** (bytes): sha1 identifier - **indexer_configuration_id** (int): tool used to compute the results Yields: an iterable of missing id for the tuple (id, indexer_configuration_id) """ yield from self._content_ctags.missing(ctags) def content_ctags_get(self, ids): """Retrieve ctags per id. Args: ids (iterable): sha1 checksums Yields: Dictionaries with keys: - **id** (bytes): content's identifier - **name** (str): symbol's name - **kind** (str): symbol's kind - **lang** (str): language for that content - **tool** (dict): tool used to compute the ctags' info """ for item in self._content_ctags.get(ids): for item_ctags_item in item['ctags']: yield { 'id': item['id'], 'tool': item['tool'], **item_ctags_item } def content_ctags_add(self, ctags, conflict_update=False): """Add ctags not present in storage Args: ctags (iterable): dictionaries with keys: - **id** (bytes): sha1 - **ctags** ([list): List of dictionary with keys: name, kind, line, lang - **indexer_configuration_id**: tool used to compute the results """ if not all(isinstance(x['id'], bytes) for x in ctags): raise TypeError('identifiers must be bytes.') self._content_ctags.add_merge(ctags, conflict_update, 'ctags') def content_ctags_search(self, expression, limit=10, last_sha1=None, db=None, cur=None): """Search through content's raw ctags symbols. Args: expression (str): Expression to search for limit (int): Number of rows to return (default to 10). last_sha1 (str): Offset from which retrieving data (default to ''). Yields: rows of ctags including id, name, lang, kind, line, etc... """ nb_matches = 0 for ((id_, tool_id), item) in \ sorted(self._content_ctags._data.items()): if id_ <= (last_sha1 or bytes(0 for _ in range(SHA1_DIGEST_SIZE))): continue for ctags_item in item['ctags']: if ctags_item['name'] != expression: continue nb_matches += 1 yield { 'id': id_, 'tool': _transform_tool(self._tools[tool_id]), **ctags_item } if nb_matches >= limit: return def content_fossology_license_get(self, ids): """Retrieve licenses per id. Args: ids (iterable): sha1 checksums Yields: `{id: facts}` where `facts` is a dict with the following keys: - **licenses** ([str]): associated licenses for that content - **tool** (dict): Tool used to compute the license """ # Rewrites the output of SubStorage.get from the old format to # the new one. SubStorage.get should be updated once all other # *_get methods use the new format. # See: https://forge.softwareheritage.org/T1433 res = {} for d in self._licenses.get(ids): res.setdefault(d.pop('id'), []).append(d) for (id_, facts) in res.items(): yield {id_: facts} def content_fossology_license_add(self, licenses, conflict_update=False): """Add licenses not present in storage. Args: licenses (iterable): dictionaries with keys: - **id**: sha1 - **licenses** ([bytes]): List of licenses associated to sha1 - **tool** (str): nomossa conflict_update: Flag to determine if we want to overwrite (true) or skip duplicates (false, the default) Returns: list: content_license entries which failed due to unknown licenses """ if not all(isinstance(x['id'], bytes) for x in licenses): raise TypeError('identifiers must be bytes.') self._licenses.add_merge(licenses, conflict_update, 'licenses') def content_fossology_license_get_range( self, start, end, indexer_configuration_id, limit=1000): """Retrieve licenses within range [start, end] bound by limit. Args: **start** (bytes): Starting identifier range (expected smaller than end) **end** (bytes): Ending identifier range (expected larger than start) **indexer_configuration_id** (int): The tool used to index data **limit** (int): Limit result (default to 1000) Raises: ValueError for limit to None Returns: a dict with keys: - **ids** [bytes]: iterable of content ids within the range. - **next** (Optional[bytes]): The next range of sha1 starts at this sha1 if any """ return self._licenses.get_range( start, end, indexer_configuration_id, limit) def content_metadata_missing(self, metadata): """List metadata missing from storage. Args: metadata (iterable): dictionaries with keys: - **id** (bytes): sha1 identifier - **indexer_configuration_id** (int): tool used to compute the results Yields: missing sha1s """ yield from self._content_metadata.missing(metadata) def content_metadata_get(self, ids): """Retrieve metadata per id. Args: ids (iterable): sha1 checksums Yields: dictionaries with the following keys: - **id** (bytes) - **translated_metadata** (str): associated metadata - **tool** (dict): tool used to compute metadata """ yield from self._content_metadata.get(ids) def content_metadata_add(self, metadata, conflict_update=False): """Add metadata not present in storage. Args: metadata (iterable): dictionaries with keys: - **id**: sha1 - **translated_metadata**: arbitrary dict - **indexer_configuration_id**: tool used to compute the results conflict_update: Flag to determine if we want to overwrite (true) or skip duplicates (false, the default) """ if not all(isinstance(x['id'], bytes) for x in metadata): raise TypeError('identifiers must be bytes.') self._content_metadata.add(metadata, conflict_update) def revision_metadata_missing(self, metadata): """List metadata missing from storage. Args: metadata (iterable): dictionaries with keys: - **id** (bytes): sha1_git revision identifier - **indexer_configuration_id** (int): tool used to compute the results Yields: missing ids """ yield from self._revision_metadata.missing(metadata) def revision_metadata_get(self, ids): """Retrieve revision metadata per id. Args: ids (iterable): sha1 checksums Yields: dictionaries with the following keys: - **id** (bytes) - **translated_metadata** (str): associated metadata - **tool** (dict): tool used to compute metadata """ yield from self._revision_metadata.get(ids) def revision_metadata_add(self, metadata, conflict_update=False): """Add metadata not present in storage. Args: metadata (iterable): dictionaries with keys: - **id**: sha1_git of revision - **translated_metadata**: arbitrary dict - **indexer_configuration_id**: tool used to compute metadata conflict_update: Flag to determine if we want to overwrite (true) or skip duplicates (false, the default) """ if not all(isinstance(x['id'], bytes) for x in metadata): raise TypeError('identifiers must be bytes.') self._revision_metadata.add(metadata, conflict_update) def origin_intrinsic_metadata_get(self, ids): """Retrieve origin metadata per id. Args: ids (iterable): origin identifiers Yields: list: dictionaries with the following keys: - **origin_id** (int) - **translated_metadata** (str): associated metadata - **tool** (dict): tool used to compute metadata """ for item in self._origin_intrinsic_metadata.get(ids): item['origin_id'] = item.pop('id') yield item def origin_intrinsic_metadata_add(self, metadata, conflict_update=False): """Add origin metadata not present in storage. Args: metadata (iterable): dictionaries with keys: - **origin_id**: origin identifier - **from_revision**: sha1 id of the revision used to generate these metadata. - **metadata**: arbitrary dict - **indexer_configuration_id**: tool used to compute metadata conflict_update: Flag to determine if we want to overwrite (true) or skip duplicates (false, the default) """ for item in metadata: item = item.copy() item['id'] = item.pop('origin_id') self._origin_intrinsic_metadata.add([item], conflict_update) def origin_intrinsic_metadata_search_fulltext( self, conjunction, limit=100): """Returns the list of origins whose metadata contain all the terms. Args: conjunction (List[str]): List of terms to be searched for. limit (int): The maximum number of results to return Yields: list: dictionaries with the following keys: - **id** (int) - **metadata** (str): associated metadata - **tool** (dict): tool used to compute metadata """ # A very crude fulltext search implementation, but that's enough # to work on English metadata tokens_re = re.compile('[a-zA-Z0-9]+') search_tokens = list(itertools.chain( *map(tokens_re.findall, conjunction))) def rank(data): # Tokenize the metadata text = json.dumps(data['metadata']) text_tokens = tokens_re.findall(text) text_token_occurences = Counter(text_tokens) # Count the number of occurrences of search tokens in the text score = 0 for search_token in search_tokens: if text_token_occurences[search_token] == 0: # Search token is not in the text. return 0 score += text_token_occurences[search_token] # Normalize according to the text's length return score / math.log(len(text_tokens)) results = [(rank(data), data) for data in self._origin_intrinsic_metadata.get_all()] results = [(rank_, data) for (rank_, data) in results if rank_ > 0] results.sort(key=operator.itemgetter(0), # Don't try to order 'data' reverse=True) for (rank_, result) in results[:limit]: result = result.copy() result['origin_id'] = result.pop('id') yield result + def origin_intrinsic_metadata_stats(self): + """Returns statistics on stored intrinsic metadata. + + Returns: + dict: dictionary with keys: + + - total (int): total number of origins that were indexed + (possibly yielding an empty metadata dictionary) + - non_empty (int): total number of origins that we extracted + a non-empty metadata dictionary from + - per_mapping (dict): a dictionary with mapping names as + keys and number of origins whose indexing used this + mapping. Note that indexing a given origin may use + 0, 1, or many mappings. + """ + mapping_count = {m.name: 0 for m in MAPPINGS.values()} + total = non_empty = 0 + for data in self._origin_intrinsic_metadata.get_all(): + total += 1 + if set(data['metadata']) - {'@context'}: + non_empty += 1 + for mapping in data['mappings']: + mapping_count[mapping] += 1 + return { + 'per_mapping': mapping_count, + 'total': total, + 'non_empty': non_empty + } + def indexer_configuration_add(self, tools): """Add new tools to the storage. Args: tools ([dict]): List of dictionary representing tool to insert in the db. Dictionary with the following keys: - **tool_name** (str): tool's name - **tool_version** (str): tool's version - **tool_configuration** (dict): tool's configuration (free form dict) Returns: list: List of dict inserted in the db (holding the id key as well). The order of the list is not guaranteed to match the order of the initial list. """ inserted = [] for tool in tools: tool = tool.copy() id_ = self._tool_key(tool) tool['id'] = id_ self._tools[id_] = tool inserted.append(tool) return inserted def indexer_configuration_get(self, tool): """Retrieve tool information. Args: tool (dict): Dictionary representing a tool with the following keys: - **tool_name** (str): tool's name - **tool_version** (str): tool's version - **tool_configuration** (dict): tool's configuration (free form dict) Returns: The same dictionary with an `id` key, None otherwise. """ return self._tools.get(self._tool_key(tool)) def _tool_key(self, tool): return (tool['tool_name'], tool['tool_version'], json.dumps(tool['tool_configuration'], sort_keys=True)) diff --git a/swh/indexer/tests/storage/test_storage.py b/swh/indexer/tests/storage/test_storage.py index f72f8ca..b3449cc 100644 --- a/swh/indexer/tests/storage/test_storage.py +++ b/swh/indexer/tests/storage/test_storage.py @@ -1,2078 +1,2158 @@ # 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 import os import pytest import unittest from hypothesis import given from swh.model.hashutil import hash_to_bytes from swh.indexer.storage import get_indexer_storage from swh.core.tests.db_testing import SingleDbTestFixture from swh.indexer.tests.storage.generate_data_test import ( gen_content_mimetypes, gen_content_fossology_licenses ) from swh.indexer.tests.storage import SQL_DIR TOOLS = [ { 'tool_name': 'universal-ctags', 'tool_version': '~git7859817b', 'tool_configuration': { "command_line": "ctags --fields=+lnz --sort=no --links=no " "--output-format=json "} }, { 'tool_name': 'swh-metadata-translator', 'tool_version': '0.0.1', 'tool_configuration': {"type": "local", "context": "NpmMapping"}, }, { 'tool_name': 'swh-metadata-detector', 'tool_version': '0.0.1', 'tool_configuration': { "type": "local", "context": ["NpmMapping", "CodemetaMapping"]}, }, { 'tool_name': 'file', 'tool_version': '5.22', 'tool_configuration': {"command_line": "file --mime "}, }, { 'tool_name': 'pygments', 'tool_version': '2.0.1+dfsg-1.1+deb8u1', 'tool_configuration': { "type": "library", "debian-package": "python3-pygments"}, }, { 'tool_name': 'pygments', 'tool_version': '2.0.1+dfsg-1.1+deb8u1', 'tool_configuration': { "type": "library", "debian-package": "python3-pygments", "max_content_size": 10240 }, }, { 'tool_name': 'nomos', 'tool_version': '3.1.0rc2-31-ga2cbb8c', 'tool_configuration': {"command_line": "nomossa "}, } ] @pytest.mark.db class BasePgTestStorage(SingleDbTestFixture): """Base test class for most indexer tests. It adds support for Storage testing to the SingleDbTestFixture class. It will also build the database from the swh-indexed/sql/*.sql files. """ TEST_DB_NAME = 'softwareheritage-test-indexer' TEST_DB_DUMP = os.path.join(SQL_DIR, '*.sql') def setUp(self): super().setUp() self.storage_config = { 'cls': 'local', 'args': { 'db': 'dbname=%s' % self.TEST_DB_NAME, }, } def tearDown(self): self.reset_storage_tables() self.storage = None super().tearDown() def reset_storage_tables(self): excluded = {'indexer_configuration'} self.reset_db_tables(self.TEST_DB_NAME, excluded=excluded) db = self.test_db[self.TEST_DB_NAME] db.conn.commit() class CommonTestStorage: """Base class for Indexer Storage testing. """ def setUp(self): super().setUp() self.storage = get_indexer_storage(**self.storage_config) tools = self.storage.indexer_configuration_add(TOOLS) self.tools = {} for tool in tools: tool_name = tool['tool_name'] while tool_name in self.tools: tool_name += '_' self.tools[tool_name] = { 'id': tool['id'], 'name': tool['tool_name'], 'version': tool['tool_version'], 'configuration': tool['tool_configuration'], } self.sha1_1 = hash_to_bytes('34973274ccef6ab4dfaaf86599792fa9c3fe4689') self.sha1_2 = hash_to_bytes('61c2b3a30496d329e21af70dd2d7e097046d07b7') self.revision_id_1 = hash_to_bytes( '7026b7c1a2af56521e951c01ed20f255fa054238') self.revision_id_2 = hash_to_bytes( '7026b7c1a2af56521e9587659012345678904321') + self.revision_id_3 = hash_to_bytes( + '7026b7c1a2af56521e9587659012345678904320') self.origin_id_1 = 54974445 self.origin_id_2 = 44434342 + self.origin_id_3 = 44434341 def test_check_config(self): self.assertTrue(self.storage.check_config(check_write=True)) self.assertTrue(self.storage.check_config(check_write=False)) def test_content_mimetype_missing(self): # given tool_id = self.tools['file']['id'] mimetypes = [ { 'id': self.sha1_1, 'indexer_configuration_id': tool_id, }, { 'id': self.sha1_2, 'indexer_configuration_id': tool_id, }] # when actual_missing = self.storage.content_mimetype_missing(mimetypes) # then self.assertEqual(list(actual_missing), [ self.sha1_1, self.sha1_2, ]) # given self.storage.content_mimetype_add([{ 'id': self.sha1_2, 'mimetype': 'text/plain', 'encoding': 'utf-8', 'indexer_configuration_id': tool_id, }]) # when actual_missing = self.storage.content_mimetype_missing(mimetypes) # then self.assertEqual(list(actual_missing), [self.sha1_1]) def test_content_mimetype_add__drop_duplicate(self): # given tool_id = self.tools['file']['id'] mimetype_v1 = { 'id': self.sha1_2, 'mimetype': 'text/plain', 'encoding': 'utf-8', 'indexer_configuration_id': tool_id, } # given self.storage.content_mimetype_add([mimetype_v1]) # when actual_mimetypes = list(self.storage.content_mimetype_get( [self.sha1_2])) # then expected_mimetypes_v1 = [{ 'id': self.sha1_2, 'mimetype': 'text/plain', 'encoding': 'utf-8', 'tool': self.tools['file'], }] self.assertEqual(actual_mimetypes, expected_mimetypes_v1) # given mimetype_v2 = mimetype_v1.copy() mimetype_v2.update({ 'mimetype': 'text/html', 'encoding': 'us-ascii', }) self.storage.content_mimetype_add([mimetype_v2]) actual_mimetypes = list(self.storage.content_mimetype_get( [self.sha1_2])) # mimetype did not change as the v2 was dropped. self.assertEqual(actual_mimetypes, expected_mimetypes_v1) def test_content_mimetype_add__update_in_place_duplicate(self): # given tool_id = self.tools['file']['id'] mimetype_v1 = { 'id': self.sha1_2, 'mimetype': 'text/plain', 'encoding': 'utf-8', 'indexer_configuration_id': tool_id, } # given self.storage.content_mimetype_add([mimetype_v1]) # when actual_mimetypes = list(self.storage.content_mimetype_get( [self.sha1_2])) expected_mimetypes_v1 = [{ 'id': self.sha1_2, 'mimetype': 'text/plain', 'encoding': 'utf-8', 'tool': self.tools['file'], }] # then self.assertEqual(actual_mimetypes, expected_mimetypes_v1) # given mimetype_v2 = mimetype_v1.copy() mimetype_v2.update({ 'mimetype': 'text/html', 'encoding': 'us-ascii', }) self.storage.content_mimetype_add([mimetype_v2], conflict_update=True) actual_mimetypes = list(self.storage.content_mimetype_get( [self.sha1_2])) expected_mimetypes_v2 = [{ 'id': self.sha1_2, 'mimetype': 'text/html', 'encoding': 'us-ascii', 'tool': { 'id': self.tools['file']['id'], 'name': 'file', 'version': '5.22', 'configuration': {'command_line': 'file --mime '} } }] # mimetype did change as the v2 was used to overwrite v1 self.assertEqual(actual_mimetypes, expected_mimetypes_v2) def test_content_mimetype_get(self): # given tool_id = self.tools['file']['id'] mimetypes = [self.sha1_2, self.sha1_1] mimetype1 = { 'id': self.sha1_2, 'mimetype': 'text/plain', 'encoding': 'utf-8', 'indexer_configuration_id': tool_id, } # when self.storage.content_mimetype_add([mimetype1]) # then actual_mimetypes = list(self.storage.content_mimetype_get(mimetypes)) # then expected_mimetypes = [{ 'id': self.sha1_2, 'mimetype': 'text/plain', 'encoding': 'utf-8', 'tool': self.tools['file'] }] self.assertEqual(actual_mimetypes, expected_mimetypes) def test_content_language_missing(self): # given tool_id = self.tools['pygments']['id'] languages = [ { 'id': self.sha1_2, 'indexer_configuration_id': tool_id, }, { 'id': self.sha1_1, 'indexer_configuration_id': tool_id, } ] # when actual_missing = list(self.storage.content_language_missing(languages)) # then self.assertEqual(list(actual_missing), [ self.sha1_2, self.sha1_1, ]) # given self.storage.content_language_add([{ 'id': self.sha1_2, 'lang': 'haskell', 'indexer_configuration_id': tool_id, }]) # when actual_missing = list(self.storage.content_language_missing(languages)) # then self.assertEqual(actual_missing, [self.sha1_1]) def test_content_language_get(self): # given tool_id = self.tools['pygments']['id'] language1 = { 'id': self.sha1_2, 'lang': 'common-lisp', 'indexer_configuration_id': tool_id, } # when self.storage.content_language_add([language1]) # then actual_languages = list(self.storage.content_language_get( [self.sha1_2, self.sha1_1])) # then expected_languages = [{ 'id': self.sha1_2, 'lang': 'common-lisp', 'tool': self.tools['pygments'] }] self.assertEqual(actual_languages, expected_languages) def test_content_language_add__drop_duplicate(self): # given tool_id = self.tools['pygments']['id'] language_v1 = { 'id': self.sha1_2, 'lang': 'emacslisp', 'indexer_configuration_id': tool_id, } # given self.storage.content_language_add([language_v1]) # when actual_languages = list(self.storage.content_language_get( [self.sha1_2])) # then expected_languages_v1 = [{ 'id': self.sha1_2, 'lang': 'emacslisp', 'tool': self.tools['pygments'] }] self.assertEqual(actual_languages, expected_languages_v1) # given language_v2 = language_v1.copy() language_v2.update({ 'lang': 'common-lisp', }) self.storage.content_language_add([language_v2]) actual_languages = list(self.storage.content_language_get( [self.sha1_2])) # language did not change as the v2 was dropped. self.assertEqual(actual_languages, expected_languages_v1) def test_content_language_add__update_in_place_duplicate(self): # given tool_id = self.tools['pygments']['id'] language_v1 = { 'id': self.sha1_2, 'lang': 'common-lisp', 'indexer_configuration_id': tool_id, } # given self.storage.content_language_add([language_v1]) # when actual_languages = list(self.storage.content_language_get( [self.sha1_2])) # then expected_languages_v1 = [{ 'id': self.sha1_2, 'lang': 'common-lisp', 'tool': self.tools['pygments'] }] self.assertEqual(actual_languages, expected_languages_v1) # given language_v2 = language_v1.copy() language_v2.update({ 'lang': 'emacslisp', }) self.storage.content_language_add([language_v2], conflict_update=True) actual_languages = list(self.storage.content_language_get( [self.sha1_2])) # language did not change as the v2 was dropped. expected_languages_v2 = [{ 'id': self.sha1_2, 'lang': 'emacslisp', 'tool': self.tools['pygments'] }] # language did change as the v2 was used to overwrite v1 self.assertEqual(actual_languages, expected_languages_v2) def test_content_ctags_missing(self): # given tool_id = self.tools['universal-ctags']['id'] ctags = [ { 'id': self.sha1_2, 'indexer_configuration_id': tool_id, }, { 'id': self.sha1_1, 'indexer_configuration_id': tool_id, } ] # when actual_missing = self.storage.content_ctags_missing(ctags) # then self.assertEqual(list(actual_missing), [ self.sha1_2, self.sha1_1 ]) # given self.storage.content_ctags_add([ { 'id': self.sha1_2, 'indexer_configuration_id': tool_id, 'ctags': [{ 'name': 'done', 'kind': 'variable', 'line': 119, 'lang': 'OCaml', }] }, ]) # when actual_missing = self.storage.content_ctags_missing(ctags) # then self.assertEqual(list(actual_missing), [self.sha1_1]) def test_content_ctags_get(self): # given tool_id = self.tools['universal-ctags']['id'] ctags = [self.sha1_2, self.sha1_1] ctag1 = { 'id': self.sha1_2, 'indexer_configuration_id': tool_id, 'ctags': [ { 'name': 'done', 'kind': 'variable', 'line': 100, 'lang': 'Python', }, { 'name': 'main', 'kind': 'function', 'line': 119, 'lang': 'Python', }] } # when self.storage.content_ctags_add([ctag1]) # then actual_ctags = list(self.storage.content_ctags_get(ctags)) # then expected_ctags = [ { 'id': self.sha1_2, 'tool': self.tools['universal-ctags'], 'name': 'done', 'kind': 'variable', 'line': 100, 'lang': 'Python', }, { 'id': self.sha1_2, 'tool': self.tools['universal-ctags'], 'name': 'main', 'kind': 'function', 'line': 119, 'lang': 'Python', } ] self.assertEqual(actual_ctags, expected_ctags) def test_content_ctags_search(self): # 1. given tool = self.tools['universal-ctags'] tool_id = tool['id'] ctag1 = { 'id': self.sha1_1, 'indexer_configuration_id': tool_id, 'ctags': [ { 'name': 'hello', 'kind': 'function', 'line': 133, 'lang': 'Python', }, { 'name': 'counter', 'kind': 'variable', 'line': 119, 'lang': 'Python', }, { 'name': 'hello', 'kind': 'variable', 'line': 210, 'lang': 'Python', }, ] } ctag2 = { 'id': self.sha1_2, 'indexer_configuration_id': tool_id, 'ctags': [ { 'name': 'hello', 'kind': 'variable', 'line': 100, 'lang': 'C', }, { 'name': 'result', 'kind': 'variable', 'line': 120, 'lang': 'C', }, ] } self.storage.content_ctags_add([ctag1, ctag2]) # 1. when actual_ctags = list(self.storage.content_ctags_search('hello', limit=1)) # 1. then self.assertEqual(actual_ctags, [ { 'id': ctag1['id'], 'tool': tool, 'name': 'hello', 'kind': 'function', 'line': 133, 'lang': 'Python', } ]) # 2. when actual_ctags = list(self.storage.content_ctags_search( 'hello', limit=1, last_sha1=ctag1['id'])) # 2. then self.assertEqual(actual_ctags, [ { 'id': ctag2['id'], 'tool': tool, 'name': 'hello', 'kind': 'variable', 'line': 100, 'lang': 'C', } ]) # 3. when actual_ctags = list(self.storage.content_ctags_search('hello')) # 3. then self.assertEqual(actual_ctags, [ { 'id': ctag1['id'], 'tool': tool, 'name': 'hello', 'kind': 'function', 'line': 133, 'lang': 'Python', }, { 'id': ctag1['id'], 'tool': tool, 'name': 'hello', 'kind': 'variable', 'line': 210, 'lang': 'Python', }, { 'id': ctag2['id'], 'tool': tool, 'name': 'hello', 'kind': 'variable', 'line': 100, 'lang': 'C', }, ]) # 4. when actual_ctags = list(self.storage.content_ctags_search('counter')) # then self.assertEqual(actual_ctags, [{ 'id': ctag1['id'], 'tool': tool, 'name': 'counter', 'kind': 'variable', 'line': 119, 'lang': 'Python', }]) # 5. when actual_ctags = list(self.storage.content_ctags_search('result', limit=1)) # then self.assertEqual(actual_ctags, [{ 'id': ctag2['id'], 'tool': tool, 'name': 'result', 'kind': 'variable', 'line': 120, 'lang': 'C', }]) def test_content_ctags_search_no_result(self): actual_ctags = list(self.storage.content_ctags_search('counter')) self.assertEqual(actual_ctags, []) def test_content_ctags_add__add_new_ctags_added(self): # given tool = self.tools['universal-ctags'] tool_id = tool['id'] ctag_v1 = { 'id': self.sha1_2, 'indexer_configuration_id': tool_id, 'ctags': [{ 'name': 'done', 'kind': 'variable', 'line': 100, 'lang': 'Scheme', }] } # given self.storage.content_ctags_add([ctag_v1]) self.storage.content_ctags_add([ctag_v1]) # conflict does nothing # when actual_ctags = list(self.storage.content_ctags_get( [self.sha1_2])) # then expected_ctags = [{ 'id': self.sha1_2, 'name': 'done', 'kind': 'variable', 'line': 100, 'lang': 'Scheme', 'tool': tool, }] self.assertEqual(actual_ctags, expected_ctags) # given ctag_v2 = ctag_v1.copy() ctag_v2.update({ 'ctags': [ { 'name': 'defn', 'kind': 'function', 'line': 120, 'lang': 'Scheme', } ] }) self.storage.content_ctags_add([ctag_v2]) expected_ctags = [ { 'id': self.sha1_2, 'name': 'done', 'kind': 'variable', 'line': 100, 'lang': 'Scheme', 'tool': tool, }, { 'id': self.sha1_2, 'name': 'defn', 'kind': 'function', 'line': 120, 'lang': 'Scheme', 'tool': tool, } ] actual_ctags = list(self.storage.content_ctags_get( [self.sha1_2])) self.assertEqual(actual_ctags, expected_ctags) def test_content_ctags_add__update_in_place(self): # given tool = self.tools['universal-ctags'] tool_id = tool['id'] ctag_v1 = { 'id': self.sha1_2, 'indexer_configuration_id': tool_id, 'ctags': [{ 'name': 'done', 'kind': 'variable', 'line': 100, 'lang': 'Scheme', }] } # given self.storage.content_ctags_add([ctag_v1]) # when actual_ctags = list(self.storage.content_ctags_get( [self.sha1_2])) # then expected_ctags = [ { 'id': self.sha1_2, 'name': 'done', 'kind': 'variable', 'line': 100, 'lang': 'Scheme', 'tool': tool } ] self.assertEqual(actual_ctags, expected_ctags) # given ctag_v2 = ctag_v1.copy() ctag_v2.update({ 'ctags': [ { 'name': 'done', 'kind': 'variable', 'line': 100, 'lang': 'Scheme', }, { 'name': 'defn', 'kind': 'function', 'line': 120, 'lang': 'Scheme', } ] }) self.storage.content_ctags_add([ctag_v2], conflict_update=True) actual_ctags = list(self.storage.content_ctags_get( [self.sha1_2])) # ctag did change as the v2 was used to overwrite v1 expected_ctags = [ { 'id': self.sha1_2, 'name': 'done', 'kind': 'variable', 'line': 100, 'lang': 'Scheme', 'tool': tool, }, { 'id': self.sha1_2, 'name': 'defn', 'kind': 'function', 'line': 120, 'lang': 'Scheme', 'tool': tool, } ] self.assertEqual(actual_ctags, expected_ctags) def test_content_fossology_license_get(self): # given tool = self.tools['nomos'] tool_id = tool['id'] license1 = { 'id': self.sha1_1, 'licenses': ['GPL-2.0+'], 'indexer_configuration_id': tool_id, } # when self.storage.content_fossology_license_add([license1]) # then actual_licenses = list(self.storage.content_fossology_license_get( [self.sha1_2, self.sha1_1])) expected_license = { self.sha1_1: [{ 'licenses': ['GPL-2.0+'], 'tool': tool, }] } # then self.assertEqual(actual_licenses, [expected_license]) def test_content_fossology_license_add__new_license_added(self): # given tool = self.tools['nomos'] tool_id = tool['id'] license_v1 = { 'id': self.sha1_1, 'licenses': ['Apache-2.0'], 'indexer_configuration_id': tool_id, } # given self.storage.content_fossology_license_add([license_v1]) # conflict does nothing self.storage.content_fossology_license_add([license_v1]) # when actual_licenses = list(self.storage.content_fossology_license_get( [self.sha1_1])) # then expected_license = { self.sha1_1: [{ 'licenses': ['Apache-2.0'], 'tool': tool, }] } self.assertEqual(actual_licenses, [expected_license]) # given license_v2 = license_v1.copy() license_v2.update({ 'licenses': ['BSD-2-Clause'], }) self.storage.content_fossology_license_add([license_v2]) actual_licenses = list(self.storage.content_fossology_license_get( [self.sha1_1])) expected_license = { self.sha1_1: [{ 'licenses': ['Apache-2.0', 'BSD-2-Clause'], 'tool': tool }] } # license did not change as the v2 was dropped. self.assertEqual(actual_licenses, [expected_license]) def test_content_fossology_license_add__update_in_place_duplicate(self): # given tool = self.tools['nomos'] tool_id = tool['id'] license_v1 = { 'id': self.sha1_1, 'licenses': ['CECILL'], 'indexer_configuration_id': tool_id, } # given self.storage.content_fossology_license_add([license_v1]) # conflict does nothing self.storage.content_fossology_license_add([license_v1]) # when actual_licenses = list(self.storage.content_fossology_license_get( [self.sha1_1])) # then expected_license = { self.sha1_1: [{ 'licenses': ['CECILL'], 'tool': tool, }] } self.assertEqual(actual_licenses, [expected_license]) # given license_v2 = license_v1.copy() license_v2.update({ 'licenses': ['CECILL-2.0'] }) self.storage.content_fossology_license_add([license_v2], conflict_update=True) actual_licenses = list(self.storage.content_fossology_license_get( [self.sha1_1])) # license did change as the v2 was used to overwrite v1 expected_license = { self.sha1_1: [{ 'licenses': ['CECILL-2.0'], 'tool': tool, }] } self.assertEqual(actual_licenses, [expected_license]) def test_content_metadata_missing(self): # given tool_id = self.tools['swh-metadata-translator']['id'] metadata = [ { 'id': self.sha1_2, 'indexer_configuration_id': tool_id, }, { 'id': self.sha1_1, 'indexer_configuration_id': tool_id, } ] # when actual_missing = list(self.storage.content_metadata_missing(metadata)) # then self.assertEqual(list(actual_missing), [ self.sha1_2, self.sha1_1, ]) # given self.storage.content_metadata_add([{ 'id': self.sha1_2, 'translated_metadata': { 'other': {}, 'codeRepository': { 'type': 'git', 'url': 'https://github.com/moranegg/metadata_test' }, 'description': 'Simple package.json test for indexer', 'name': 'test_metadata', 'version': '0.0.1' }, 'indexer_configuration_id': tool_id }]) # when actual_missing = list(self.storage.content_metadata_missing(metadata)) # then self.assertEqual(actual_missing, [self.sha1_1]) def test_content_metadata_get(self): # given tool_id = self.tools['swh-metadata-translator']['id'] metadata1 = { 'id': self.sha1_2, 'translated_metadata': { 'other': {}, 'codeRepository': { 'type': 'git', 'url': 'https://github.com/moranegg/metadata_test' }, 'description': 'Simple package.json test for indexer', 'name': 'test_metadata', 'version': '0.0.1' }, 'indexer_configuration_id': tool_id, } # when self.storage.content_metadata_add([metadata1]) # then actual_metadata = list(self.storage.content_metadata_get( [self.sha1_2, self.sha1_1])) expected_metadata = [{ 'id': self.sha1_2, 'translated_metadata': { 'other': {}, 'codeRepository': { 'type': 'git', 'url': 'https://github.com/moranegg/metadata_test' }, 'description': 'Simple package.json test for indexer', 'name': 'test_metadata', 'version': '0.0.1' }, 'tool': self.tools['swh-metadata-translator'] }] self.assertEqual(actual_metadata, expected_metadata) def test_content_metadata_add_drop_duplicate(self): # given tool_id = self.tools['swh-metadata-translator']['id'] metadata_v1 = { 'id': self.sha1_2, 'translated_metadata': { 'other': {}, 'name': 'test_metadata', 'version': '0.0.1' }, 'indexer_configuration_id': tool_id, } # given self.storage.content_metadata_add([metadata_v1]) # when actual_metadata = list(self.storage.content_metadata_get( [self.sha1_2])) expected_metadata_v1 = [{ 'id': self.sha1_2, 'translated_metadata': { 'other': {}, 'name': 'test_metadata', 'version': '0.0.1' }, 'tool': self.tools['swh-metadata-translator'] }] self.assertEqual(actual_metadata, expected_metadata_v1) # given metadata_v2 = metadata_v1.copy() metadata_v2.update({ 'translated_metadata': { 'other': {}, 'name': 'test_drop_duplicated_metadata', 'version': '0.0.1' }, }) self.storage.content_metadata_add([metadata_v2]) # then actual_metadata = list(self.storage.content_metadata_get( [self.sha1_2])) # metadata did not change as the v2 was dropped. self.assertEqual(actual_metadata, expected_metadata_v1) def test_content_metadata_add_update_in_place_duplicate(self): # given tool_id = self.tools['swh-metadata-translator']['id'] metadata_v1 = { 'id': self.sha1_2, 'translated_metadata': { 'other': {}, 'name': 'test_metadata', 'version': '0.0.1' }, 'indexer_configuration_id': tool_id, } # given self.storage.content_metadata_add([metadata_v1]) # when actual_metadata = list(self.storage.content_metadata_get( [self.sha1_2])) # then expected_metadata_v1 = [{ 'id': self.sha1_2, 'translated_metadata': { 'other': {}, 'name': 'test_metadata', 'version': '0.0.1' }, 'tool': self.tools['swh-metadata-translator'] }] self.assertEqual(actual_metadata, expected_metadata_v1) # given metadata_v2 = metadata_v1.copy() metadata_v2.update({ 'translated_metadata': { 'other': {}, 'name': 'test_update_duplicated_metadata', 'version': '0.0.1' }, }) self.storage.content_metadata_add([metadata_v2], conflict_update=True) actual_metadata = list(self.storage.content_metadata_get( [self.sha1_2])) # language did not change as the v2 was dropped. expected_metadata_v2 = [{ 'id': self.sha1_2, 'translated_metadata': { 'other': {}, 'name': 'test_update_duplicated_metadata', 'version': '0.0.1' }, 'tool': self.tools['swh-metadata-translator'] }] # metadata did change as the v2 was used to overwrite v1 self.assertEqual(actual_metadata, expected_metadata_v2) def test_revision_metadata_missing(self): # given tool_id = self.tools['swh-metadata-detector']['id'] metadata = [ { 'id': self.revision_id_1, 'indexer_configuration_id': tool_id, }, { 'id': self.revision_id_2, 'indexer_configuration_id': tool_id, } ] # when actual_missing = list(self.storage.revision_metadata_missing( metadata)) # then self.assertEqual(list(actual_missing), [ self.revision_id_1, self.revision_id_2, ]) # given self.storage.revision_metadata_add([{ 'id': self.revision_id_1, 'translated_metadata': { 'developmentStatus': None, 'version': None, 'operatingSystem': None, 'description': None, 'keywords': None, 'issueTracker': None, 'name': None, 'author': None, 'relatedLink': None, 'url': None, 'license': None, 'maintainer': None, 'email': None, 'softwareRequirements': None, 'identifier': None }, 'mappings': [], 'indexer_configuration_id': tool_id }]) # when actual_missing = list(self.storage.revision_metadata_missing( metadata)) # then self.assertEqual(actual_missing, [self.revision_id_2]) def test_revision_metadata_get(self): # given tool_id = self.tools['swh-metadata-detector']['id'] metadata_rev = { 'id': self.revision_id_2, 'translated_metadata': { 'developmentStatus': None, 'version': None, 'operatingSystem': None, 'description': None, 'keywords': None, 'issueTracker': None, 'name': None, 'author': None, 'relatedLink': None, 'url': None, 'license': None, 'maintainer': None, 'email': None, 'softwareRequirements': None, 'identifier': None }, 'mappings': ['mapping1', 'mapping2'], 'indexer_configuration_id': tool_id } # when self.storage.revision_metadata_add([metadata_rev]) # then actual_metadata = list(self.storage.revision_metadata_get( [self.revision_id_2, self.revision_id_1])) expected_metadata = [{ 'id': self.revision_id_2, 'translated_metadata': metadata_rev['translated_metadata'], 'mappings': ['mapping1', 'mapping2'], 'tool': self.tools['swh-metadata-detector'] }] self.maxDiff = None self.assertEqual(actual_metadata, expected_metadata) def test_revision_metadata_add_drop_duplicate(self): # given tool_id = self.tools['swh-metadata-detector']['id'] metadata_v1 = { 'id': self.revision_id_1, 'translated_metadata': { 'developmentStatus': None, 'version': None, 'operatingSystem': None, 'description': None, 'keywords': None, 'issueTracker': None, 'name': None, 'author': None, 'relatedLink': None, 'url': None, 'license': None, 'maintainer': None, 'email': None, 'softwareRequirements': None, 'identifier': None }, 'mappings': ['mapping1'], 'indexer_configuration_id': tool_id, } # given self.storage.revision_metadata_add([metadata_v1]) # when actual_metadata = list(self.storage.revision_metadata_get( [self.revision_id_1])) expected_metadata_v1 = [{ 'id': self.revision_id_1, 'translated_metadata': metadata_v1['translated_metadata'], 'mappings': ['mapping1'], 'tool': self.tools['swh-metadata-detector'] }] self.assertEqual(actual_metadata, expected_metadata_v1) # given metadata_v2 = metadata_v1.copy() metadata_v2.update({ 'translated_metadata': { 'name': 'test_metadata', 'author': 'MG', }, 'mappings': ['mapping2'], }) self.storage.revision_metadata_add([metadata_v2]) # then actual_metadata = list(self.storage.revision_metadata_get( [self.revision_id_1])) # metadata did not change as the v2 was dropped. self.assertEqual(actual_metadata, expected_metadata_v1) def test_revision_metadata_add_update_in_place_duplicate(self): # given tool_id = self.tools['swh-metadata-detector']['id'] metadata_v1 = { 'id': self.revision_id_2, 'translated_metadata': { 'developmentStatus': None, 'version': None, 'operatingSystem': None, 'description': None, 'keywords': None, 'issueTracker': None, 'name': None, 'author': None, 'relatedLink': None, 'url': None, 'license': None, 'maintainer': None, 'email': None, 'softwareRequirements': None, 'identifier': None }, 'mappings': ['mapping1'], 'indexer_configuration_id': tool_id, } # given self.storage.revision_metadata_add([metadata_v1]) # when actual_metadata = list(self.storage.revision_metadata_get( [self.revision_id_2])) # then expected_metadata_v1 = [{ 'id': self.revision_id_2, 'translated_metadata': metadata_v1['translated_metadata'], 'mappings': ['mapping1'], 'tool': self.tools['swh-metadata-detector'] }] self.assertEqual(actual_metadata, expected_metadata_v1) # given metadata_v2 = metadata_v1.copy() metadata_v2.update({ 'translated_metadata': { 'name': 'test_update_duplicated_metadata', 'author': 'MG' }, 'mappings': ['mapping2'], }) self.storage.revision_metadata_add([metadata_v2], conflict_update=True) actual_metadata = list(self.storage.revision_metadata_get( [self.revision_id_2])) expected_metadata_v2 = [{ 'id': self.revision_id_2, 'translated_metadata': metadata_v2['translated_metadata'], 'mappings': ['mapping2'], 'tool': self.tools['swh-metadata-detector'] }] # metadata did change as the v2 was used to overwrite v1 self.assertEqual(actual_metadata, expected_metadata_v2) def test_origin_intrinsic_metadata_get(self): # given tool_id = self.tools['swh-metadata-detector']['id'] metadata = { 'developmentStatus': None, 'version': None, 'operatingSystem': None, 'description': None, 'keywords': None, 'issueTracker': None, 'name': None, 'author': None, 'relatedLink': None, 'url': None, 'license': None, 'maintainer': None, 'email': None, 'softwareRequirements': None, 'identifier': None, } metadata_rev = { 'id': self.revision_id_2, 'translated_metadata': metadata, 'mappings': ['mapping1'], 'indexer_configuration_id': tool_id, } metadata_origin = { 'origin_id': self.origin_id_1, 'metadata': metadata, 'indexer_configuration_id': tool_id, 'mappings': ['mapping1'], 'from_revision': self.revision_id_2, } # when self.storage.revision_metadata_add([metadata_rev]) self.storage.origin_intrinsic_metadata_add([metadata_origin]) # then actual_metadata = list(self.storage.origin_intrinsic_metadata_get( [self.origin_id_1, 42])) expected_metadata = [{ 'origin_id': self.origin_id_1, 'metadata': metadata, 'tool': self.tools['swh-metadata-detector'], 'from_revision': self.revision_id_2, 'mappings': ['mapping1'], }] self.assertEqual(actual_metadata, expected_metadata) def test_origin_intrinsic_metadata_add_drop_duplicate(self): # given tool_id = self.tools['swh-metadata-detector']['id'] metadata_v1 = { 'developmentStatus': None, 'version': None, 'operatingSystem': None, 'description': None, 'keywords': None, 'issueTracker': None, 'name': None, 'author': None, 'relatedLink': None, 'url': None, 'license': None, 'maintainer': None, 'email': None, 'softwareRequirements': None, 'identifier': None } metadata_rev_v1 = { 'id': self.revision_id_1, 'translated_metadata': metadata_v1.copy(), 'mappings': [], 'indexer_configuration_id': tool_id, } metadata_origin_v1 = { 'origin_id': self.origin_id_1, 'metadata': metadata_v1.copy(), 'indexer_configuration_id': tool_id, 'mappings': [], 'from_revision': self.revision_id_1, } # given self.storage.revision_metadata_add([metadata_rev_v1]) self.storage.origin_intrinsic_metadata_add([metadata_origin_v1]) # when actual_metadata = list(self.storage.origin_intrinsic_metadata_get( [self.origin_id_1, 42])) expected_metadata_v1 = [{ 'origin_id': self.origin_id_1, 'metadata': metadata_v1, 'tool': self.tools['swh-metadata-detector'], 'from_revision': self.revision_id_1, 'mappings': [], }] self.assertEqual(actual_metadata, expected_metadata_v1) # given metadata_v2 = metadata_v1.copy() metadata_v2.update({ 'name': 'test_metadata', 'author': 'MG', }) metadata_rev_v2 = metadata_rev_v1.copy() metadata_origin_v2 = metadata_origin_v1.copy() metadata_rev_v2['translated_metadata'] = metadata_v2 metadata_origin_v2['translated_metadata'] = metadata_v2 self.storage.revision_metadata_add([metadata_rev_v2]) self.storage.origin_intrinsic_metadata_add([metadata_origin_v2]) # then actual_metadata = list(self.storage.origin_intrinsic_metadata_get( [self.origin_id_1])) # metadata did not change as the v2 was dropped. self.assertEqual(actual_metadata, expected_metadata_v1) def test_origin_intrinsic_metadata_add_update_in_place_duplicate(self): # given tool_id = self.tools['swh-metadata-detector']['id'] metadata_v1 = { 'developmentStatus': None, 'version': None, 'operatingSystem': None, 'description': None, 'keywords': None, 'issueTracker': None, 'name': None, 'author': None, 'relatedLink': None, 'url': None, 'license': None, 'maintainer': None, 'email': None, 'softwareRequirements': None, 'identifier': None } metadata_rev_v1 = { 'id': self.revision_id_2, 'translated_metadata': metadata_v1, 'mappings': [], 'indexer_configuration_id': tool_id, } metadata_origin_v1 = { 'origin_id': self.origin_id_1, 'metadata': metadata_v1.copy(), 'indexer_configuration_id': tool_id, 'mappings': [], 'from_revision': self.revision_id_2, } # given self.storage.revision_metadata_add([metadata_rev_v1]) self.storage.origin_intrinsic_metadata_add([metadata_origin_v1]) # when actual_metadata = list(self.storage.origin_intrinsic_metadata_get( [self.origin_id_1])) # then expected_metadata_v1 = [{ 'origin_id': self.origin_id_1, 'metadata': metadata_v1, 'tool': self.tools['swh-metadata-detector'], 'from_revision': self.revision_id_2, 'mappings': [], }] self.assertEqual(actual_metadata, expected_metadata_v1) # given metadata_v2 = metadata_v1.copy() metadata_v2.update({ 'name': 'test_update_duplicated_metadata', 'author': 'MG', }) metadata_rev_v2 = metadata_rev_v1.copy() metadata_origin_v2 = metadata_origin_v1.copy() metadata_rev_v2['translated_metadata'] = metadata_v2 metadata_origin_v2['metadata'] = metadata_v2 self.storage.revision_metadata_add([metadata_rev_v2], conflict_update=True) self.storage.origin_intrinsic_metadata_add([metadata_origin_v2], conflict_update=True) actual_metadata = list(self.storage.origin_intrinsic_metadata_get( [self.origin_id_1])) expected_metadata_v2 = [{ 'origin_id': self.origin_id_1, 'metadata': metadata_v2, 'tool': self.tools['swh-metadata-detector'], 'from_revision': self.revision_id_2, 'mappings': [], }] # metadata did change as the v2 was used to overwrite v1 self.assertEqual(actual_metadata, expected_metadata_v2) def test_origin_intrinsic_metadata_search_fulltext(self): # given tool_id = self.tools['swh-metadata-detector']['id'] metadata1 = { 'author': 'John Doe', } metadata1_rev = { 'id': self.revision_id_1, 'translated_metadata': metadata1, 'mappings': [], 'indexer_configuration_id': tool_id, } metadata1_origin = { 'origin_id': self.origin_id_1, 'metadata': metadata1, 'mappings': [], 'indexer_configuration_id': tool_id, 'from_revision': self.revision_id_1, } metadata2 = { 'author': 'Jane Doe', } metadata2_rev = { 'id': self.revision_id_2, 'translated_metadata': metadata2, 'mappings': [], 'indexer_configuration_id': tool_id, } metadata2_origin = { 'origin_id': self.origin_id_2, 'metadata': metadata2, 'mappings': [], 'indexer_configuration_id': tool_id, 'from_revision': self.revision_id_2, } # when self.storage.revision_metadata_add([metadata1_rev]) self.storage.origin_intrinsic_metadata_add([metadata1_origin]) self.storage.revision_metadata_add([metadata2_rev]) self.storage.origin_intrinsic_metadata_add([metadata2_origin]) # then search = self.storage.origin_intrinsic_metadata_search_fulltext self.assertCountEqual( [res['origin_id'] for res in search(['Doe'])], [self.origin_id_1, self.origin_id_2]) self.assertEqual( [res['origin_id'] for res in search(['John', 'Doe'])], [self.origin_id_1]) self.assertEqual( [res['origin_id'] for res in search(['John'])], [self.origin_id_1]) self.assertEqual( [res['origin_id'] for res in search(['John', 'Jane'])], []) def test_origin_intrinsic_metadata_search_fulltext_rank(self): # given tool_id = self.tools['swh-metadata-detector']['id'] # The following authors have "Random Person" to add some more content # to the JSON data, to work around normalization quirks when there # are few words (rank/(1+ln(nb_words)) is very sensitive to nb_words # for small values of nb_words). metadata1 = { 'author': [ 'Random Person', 'John Doe', 'Jane Doe', ] } metadata1_rev = { 'id': self.revision_id_1, 'translated_metadata': metadata1, 'mappings': [], 'indexer_configuration_id': tool_id, } metadata1_origin = { 'origin_id': self.origin_id_1, 'metadata': metadata1, 'mappings': [], 'indexer_configuration_id': tool_id, 'from_revision': self.revision_id_1, } metadata2 = { 'author': [ 'Random Person', 'Jane Doe', ] } metadata2_rev = { 'id': self.revision_id_2, 'translated_metadata': metadata2, 'mappings': [], 'indexer_configuration_id': tool_id, } metadata2_origin = { 'origin_id': self.origin_id_2, 'metadata': metadata2, 'mappings': [], 'indexer_configuration_id': tool_id, 'from_revision': self.revision_id_2, } # when self.storage.revision_metadata_add([metadata1_rev]) self.storage.origin_intrinsic_metadata_add([metadata1_origin]) self.storage.revision_metadata_add([metadata2_rev]) self.storage.origin_intrinsic_metadata_add([metadata2_origin]) # then search = self.storage.origin_intrinsic_metadata_search_fulltext self.assertEqual( [res['origin_id'] for res in search(['Doe'])], [self.origin_id_1, self.origin_id_2]) self.assertEqual( [res['origin_id'] for res in search(['Doe'], limit=1)], [self.origin_id_1]) self.assertEqual( [res['origin_id'] for res in search(['John'])], [self.origin_id_1]) self.assertEqual( [res['origin_id'] for res in search(['Jane'])], [self.origin_id_2, self.origin_id_1]) self.assertEqual( [res['origin_id'] for res in search(['John', 'Jane'])], [self.origin_id_1]) + def test_origin_intrinsic_metadata_stats(self): + # given + tool_id = self.tools['swh-metadata-detector']['id'] + + metadata1 = { + '@context': 'foo', + 'author': 'John Doe', + } + metadata1_rev = { + 'id': self.revision_id_1, + 'translated_metadata': metadata1, + 'mappings': ['npm'], + 'indexer_configuration_id': tool_id, + } + metadata1_origin = { + 'origin_id': self.origin_id_1, + 'metadata': metadata1, + 'mappings': ['npm'], + 'indexer_configuration_id': tool_id, + 'from_revision': self.revision_id_1, + } + metadata2 = { + '@context': 'foo', + 'author': 'Jane Doe', + } + metadata2_rev = { + 'id': self.revision_id_2, + 'translated_metadata': metadata2, + 'mappings': ['npm', 'gemspec'], + 'indexer_configuration_id': tool_id, + } + metadata2_origin = { + 'origin_id': self.origin_id_2, + 'metadata': metadata2, + 'mappings': ['npm', 'gemspec'], + 'indexer_configuration_id': tool_id, + 'from_revision': self.revision_id_2, + } + metadata3 = { + '@context': 'foo', + } + metadata3_rev = { + 'id': self.revision_id_3, + 'translated_metadata': metadata3, + 'mappings': ['npm', 'gemspec'], + 'indexer_configuration_id': tool_id, + } + metadata3_origin = { + 'origin_id': self.origin_id_3, + 'metadata': metadata3, + 'mappings': ['pkg-info'], + 'indexer_configuration_id': tool_id, + 'from_revision': self.revision_id_3, + } + + # when + self.storage.revision_metadata_add([metadata1_rev]) + self.storage.origin_intrinsic_metadata_add([metadata1_origin]) + self.storage.revision_metadata_add([metadata2_rev]) + self.storage.origin_intrinsic_metadata_add([metadata2_origin]) + self.storage.revision_metadata_add([metadata3_rev]) + self.storage.origin_intrinsic_metadata_add([metadata3_origin]) + + # then + result = self.storage.origin_intrinsic_metadata_stats() + self.assertEqual(result, { + 'per_mapping': { + 'gemspec': 1, + 'npm': 2, + 'pkg-info': 1, + 'codemeta': 0, + 'maven': 0, + }, + 'total': 3, + 'non_empty': 2, + }) + def test_indexer_configuration_add(self): tool = { 'tool_name': 'some-unknown-tool', 'tool_version': 'some-version', 'tool_configuration': {"debian-package": "some-package"}, } actual_tool = self.storage.indexer_configuration_get(tool) self.assertIsNone(actual_tool) # does not exist # add it actual_tools = list(self.storage.indexer_configuration_add([tool])) self.assertEqual(len(actual_tools), 1) actual_tool = actual_tools[0] self.assertIsNotNone(actual_tool) # now it exists new_id = actual_tool.pop('id') self.assertEqual(actual_tool, tool) actual_tools2 = list(self.storage.indexer_configuration_add([tool])) actual_tool2 = actual_tools2[0] self.assertIsNotNone(actual_tool2) # now it exists new_id2 = actual_tool2.pop('id') self.assertEqual(new_id, new_id2) self.assertEqual(actual_tool, actual_tool2) def test_indexer_configuration_add_multiple(self): tool = { 'tool_name': 'some-unknown-tool', 'tool_version': 'some-version', 'tool_configuration': {"debian-package": "some-package"}, } actual_tools = list(self.storage.indexer_configuration_add([tool])) self.assertEqual(len(actual_tools), 1) new_tools = [tool, { 'tool_name': 'yet-another-tool', 'tool_version': 'version', 'tool_configuration': {}, }] actual_tools = list(self.storage.indexer_configuration_add(new_tools)) self.assertEqual(len(actual_tools), 2) # order not guaranteed, so we iterate over results to check for tool in actual_tools: _id = tool.pop('id') self.assertIsNotNone(_id) self.assertIn(tool, new_tools) def test_indexer_configuration_get_missing(self): tool = { 'tool_name': 'unknown-tool', 'tool_version': '3.1.0rc2-31-ga2cbb8c', 'tool_configuration': {"command_line": "nomossa "}, } actual_tool = self.storage.indexer_configuration_get(tool) self.assertIsNone(actual_tool) def test_indexer_configuration_get(self): tool = { 'tool_name': 'nomos', 'tool_version': '3.1.0rc2-31-ga2cbb8c', 'tool_configuration': {"command_line": "nomossa "}, } self.storage.indexer_configuration_add([tool]) actual_tool = self.storage.indexer_configuration_get(tool) expected_tool = tool.copy() del actual_tool['id'] self.assertEqual(expected_tool, actual_tool) def test_indexer_configuration_metadata_get_missing_context(self): tool = { 'tool_name': 'swh-metadata-translator', 'tool_version': '0.0.1', 'tool_configuration': {"context": "unknown-context"}, } actual_tool = self.storage.indexer_configuration_get(tool) self.assertIsNone(actual_tool) def test_indexer_configuration_metadata_get(self): tool = { 'tool_name': 'swh-metadata-translator', 'tool_version': '0.0.1', 'tool_configuration': {"type": "local", "context": "NpmMapping"}, } self.storage.indexer_configuration_add([tool]) actual_tool = self.storage.indexer_configuration_get(tool) expected_tool = tool.copy() expected_tool['id'] = actual_tool['id'] self.assertEqual(expected_tool, actual_tool) @pytest.mark.property_based def test_generate_content_mimetype_get_range_limit_none(self): """mimetype_get_range call with wrong limit input should fail""" with self.assertRaises(ValueError) as e: self.storage.content_mimetype_get_range( start=None, end=None, indexer_configuration_id=None, limit=None) self.assertEqual(e.exception.args, ( 'Development error: limit should not be None',)) @pytest.mark.property_based @given(gen_content_mimetypes(min_size=1, max_size=4)) def test_generate_content_mimetype_get_range_no_limit(self, mimetypes): """mimetype_get_range returns mimetypes within range provided""" self.reset_storage_tables() # add mimetypes to storage self.storage.content_mimetype_add(mimetypes) # All ids from the db content_ids = sorted([c['id'] for c in mimetypes]) start = content_ids[0] end = content_ids[-1] # retrieve mimetypes tool_id = mimetypes[0]['indexer_configuration_id'] actual_result = self.storage.content_mimetype_get_range( start, end, indexer_configuration_id=tool_id) actual_ids = actual_result['ids'] actual_next = actual_result['next'] self.assertEqual(len(mimetypes), len(actual_ids)) self.assertIsNone(actual_next) self.assertEqual(content_ids, actual_ids) @pytest.mark.property_based @given(gen_content_mimetypes(min_size=4, max_size=4)) def test_generate_content_mimetype_get_range_limit(self, mimetypes): """mimetype_get_range paginates results if limit exceeded""" self.reset_storage_tables() # add mimetypes to storage self.storage.content_mimetype_add(mimetypes) # input the list of sha1s we want from storage content_ids = sorted([c['id'] for c in mimetypes]) start = content_ids[0] end = content_ids[-1] # retrieve mimetypes limited to 3 results limited_results = len(mimetypes) - 1 tool_id = mimetypes[0]['indexer_configuration_id'] actual_result = self.storage.content_mimetype_get_range( start, end, indexer_configuration_id=tool_id, limit=limited_results) actual_ids = actual_result['ids'] actual_next = actual_result['next'] self.assertEqual(limited_results, len(actual_ids)) self.assertIsNotNone(actual_next) self.assertEqual(actual_next, content_ids[-1]) expected_mimetypes = content_ids[:-1] self.assertEqual(expected_mimetypes, actual_ids) # retrieve next part actual_results2 = self.storage.content_mimetype_get_range( start=end, end=end, indexer_configuration_id=tool_id) actual_ids2 = actual_results2['ids'] actual_next2 = actual_results2['next'] self.assertIsNone(actual_next2) expected_mimetypes2 = [content_ids[-1]] self.assertEqual(expected_mimetypes2, actual_ids2) @pytest.mark.property_based def test_generate_content_fossology_license_get_range_limit_none(self): """license_get_range call with wrong limit input should fail""" with self.assertRaises(ValueError) as e: self.storage.content_fossology_license_get_range( start=None, end=None, indexer_configuration_id=None, limit=None) self.assertEqual(e.exception.args, ( 'Development error: limit should not be None',)) @pytest.mark.property_based def prepare_mimetypes_from(self, fossology_licenses): """Fossology license needs some consistent data in db to run. """ mimetypes = [] for c in fossology_licenses: mimetypes.append({ 'id': c['id'], 'mimetype': 'text/plain', 'encoding': 'utf-8', 'indexer_configuration_id': c['indexer_configuration_id'], }) return mimetypes @pytest.mark.property_based @given(gen_content_fossology_licenses(min_size=1, max_size=4)) def test_generate_content_fossology_license_get_range_no_limit( self, fossology_licenses): """license_get_range returns licenses within range provided""" self.reset_storage_tables() # craft some consistent mimetypes mimetypes = self.prepare_mimetypes_from(fossology_licenses) self.storage.content_mimetype_add(mimetypes) # add fossology_licenses to storage self.storage.content_fossology_license_add(fossology_licenses) # All ids from the db content_ids = sorted([c['id'] for c in fossology_licenses]) start = content_ids[0] end = content_ids[-1] # retrieve fossology_licenses tool_id = fossology_licenses[0]['indexer_configuration_id'] actual_result = self.storage.content_fossology_license_get_range( start, end, indexer_configuration_id=tool_id) actual_ids = actual_result['ids'] actual_next = actual_result['next'] self.assertEqual(len(fossology_licenses), len(actual_ids)) self.assertIsNone(actual_next) self.assertEqual(content_ids, actual_ids) @pytest.mark.property_based @given(gen_content_fossology_licenses(min_size=1, max_size=4), gen_content_mimetypes(min_size=1, max_size=1)) def test_generate_content_fossology_license_get_range_no_limit_with_filter( self, fossology_licenses, mimetypes): """This filters non textual, then returns results within range""" self.reset_storage_tables() # craft some consistent mimetypes _mimetypes = self.prepare_mimetypes_from(fossology_licenses) # add binary mimetypes which will get filtered out in results for m in mimetypes: _mimetypes.append({ 'mimetype': 'binary', **m, }) self.storage.content_mimetype_add(_mimetypes) # add fossology_licenses to storage self.storage.content_fossology_license_add(fossology_licenses) # All ids from the db content_ids = sorted([c['id'] for c in fossology_licenses]) start = content_ids[0] end = content_ids[-1] # retrieve fossology_licenses tool_id = fossology_licenses[0]['indexer_configuration_id'] actual_result = self.storage.content_fossology_license_get_range( start, end, indexer_configuration_id=tool_id) actual_ids = actual_result['ids'] actual_next = actual_result['next'] self.assertEqual(len(fossology_licenses), len(actual_ids)) self.assertIsNone(actual_next) self.assertEqual(content_ids, actual_ids) @pytest.mark.property_based @given(gen_content_fossology_licenses(min_size=4, max_size=4)) def test_generate_fossology_license_get_range_limit( self, fossology_licenses): """fossology_license_get_range paginates results if limit exceeded""" self.reset_storage_tables() # craft some consistent mimetypes mimetypes = self.prepare_mimetypes_from(fossology_licenses) # add fossology_licenses to storage self.storage.content_mimetype_add(mimetypes) self.storage.content_fossology_license_add(fossology_licenses) # input the list of sha1s we want from storage content_ids = sorted([c['id'] for c in fossology_licenses]) start = content_ids[0] end = content_ids[-1] # retrieve fossology_licenses limited to 3 results limited_results = len(fossology_licenses) - 1 tool_id = fossology_licenses[0]['indexer_configuration_id'] actual_result = self.storage.content_fossology_license_get_range( start, end, indexer_configuration_id=tool_id, limit=limited_results) actual_ids = actual_result['ids'] actual_next = actual_result['next'] self.assertEqual(limited_results, len(actual_ids)) self.assertIsNotNone(actual_next) self.assertEqual(actual_next, content_ids[-1]) expected_fossology_licenses = content_ids[:-1] self.assertEqual(expected_fossology_licenses, actual_ids) # retrieve next part actual_results2 = self.storage.content_fossology_license_get_range( start=end, end=end, indexer_configuration_id=tool_id) actual_ids2 = actual_results2['ids'] actual_next2 = actual_results2['next'] self.assertIsNone(actual_next2) expected_fossology_licenses2 = [content_ids[-1]] self.assertEqual(expected_fossology_licenses2, actual_ids2) @pytest.mark.db class IndexerTestStorage(CommonTestStorage, BasePgTestStorage, unittest.TestCase): """Running the tests locally. For the client api tests (remote storage), see `class`:swh.indexer.storage.test_api_client:TestRemoteStorage class. """ pass