diff --git a/PKG-INFO b/PKG-INFO index 2421a83..7a828ec 100644 --- a/PKG-INFO +++ b/PKG-INFO @@ -1,69 +1,69 @@ Metadata-Version: 2.1 Name: swh.indexer -Version: 0.0.61 +Version: 0.0.62 Summary: Software Heritage Content Indexer Home-page: https://forge.softwareheritage.org/diffusion/78/ Author: Software Heritage developers Author-email: swh-devel@inria.fr License: UNKNOWN Project-URL: Bug Reports, https://forge.softwareheritage.org/maniphest Project-URL: Funding, https://www.softwareheritage.org/donate Project-URL: Source, https://forge.softwareheritage.org/source/swh-indexer Description: swh-indexer ============ Tools to compute multiple indexes on SWH's raw contents: - content: - mimetype - ctags - language - fossology-license - metadata - revision: - metadata An indexer is in charge of: - looking up objects - extracting information from those objects - store those information in the swh-indexer db There are multiple indexers working on different object types: - content indexer: works with content sha1 hashes - revision indexer: works with revision sha1 hashes - origin indexer: works with origin identifiers Indexation procedure: - receive batch of ids - retrieve the associated data depending on object type - compute for that object some index - store the result to swh's storage Current content indexers: - mimetype (queue swh_indexer_content_mimetype): detect the encoding and mimetype - language (queue swh_indexer_content_language): detect the programming language - ctags (queue swh_indexer_content_ctags): compute tags information - fossology-license (queue swh_indexer_fossology_license): compute the license - metadata: translate file into translated_metadata dict Current revision indexers: - metadata: detects files containing metadata and retrieves translated_metadata in content_metadata table in storage or run content indexer to translate files. Platform: UNKNOWN Classifier: Programming Language :: Python :: 3 Classifier: Intended Audience :: Developers Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3) Classifier: Operating System :: OS Independent Classifier: Development Status :: 5 - Production/Stable Description-Content-Type: text/markdown Provides-Extra: testing diff --git a/sql/upgrades/117.sql b/sql/upgrades/117.sql new file mode 100644 index 0000000..2ca6c6f --- /dev/null +++ b/sql/upgrades/117.sql @@ -0,0 +1,8 @@ +-- SWH Indexer DB schema upgrade +-- from_version: 116 +-- to_version: 117 +-- description: Add fulltext search index for origin intrinsic metadata + +alter table origin_intrinsic_metadata add column metadata_tsvector tsvector; +update origin_intrinsic_metadata set metadata_tsvector = to_tsvector('pg_catalog.simple', metadata); +create index origin_intrinsic_metadata_fulltext_idx on origin_intrinsic_metadata using gin (metadata_tsvector); diff --git a/swh.indexer.egg-info/PKG-INFO b/swh.indexer.egg-info/PKG-INFO index 2421a83..7a828ec 100644 --- a/swh.indexer.egg-info/PKG-INFO +++ b/swh.indexer.egg-info/PKG-INFO @@ -1,69 +1,69 @@ Metadata-Version: 2.1 Name: swh.indexer -Version: 0.0.61 +Version: 0.0.62 Summary: Software Heritage Content Indexer Home-page: https://forge.softwareheritage.org/diffusion/78/ Author: Software Heritage developers Author-email: swh-devel@inria.fr License: UNKNOWN Project-URL: Bug Reports, https://forge.softwareheritage.org/maniphest Project-URL: Funding, https://www.softwareheritage.org/donate Project-URL: Source, https://forge.softwareheritage.org/source/swh-indexer Description: swh-indexer ============ Tools to compute multiple indexes on SWH's raw contents: - content: - mimetype - ctags - language - fossology-license - metadata - revision: - metadata An indexer is in charge of: - looking up objects - extracting information from those objects - store those information in the swh-indexer db There are multiple indexers working on different object types: - content indexer: works with content sha1 hashes - revision indexer: works with revision sha1 hashes - origin indexer: works with origin identifiers Indexation procedure: - receive batch of ids - retrieve the associated data depending on object type - compute for that object some index - store the result to swh's storage Current content indexers: - mimetype (queue swh_indexer_content_mimetype): detect the encoding and mimetype - language (queue swh_indexer_content_language): detect the programming language - ctags (queue swh_indexer_content_ctags): compute tags information - fossology-license (queue swh_indexer_fossology_license): compute the license - metadata: translate file into translated_metadata dict Current revision indexers: - metadata: detects files containing metadata and retrieves translated_metadata in content_metadata table in storage or run content indexer to translate files. Platform: UNKNOWN Classifier: Programming Language :: Python :: 3 Classifier: Intended Audience :: Developers Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3) Classifier: Operating System :: OS Independent Classifier: Development Status :: 5 - Production/Stable Description-Content-Type: text/markdown Provides-Extra: testing diff --git a/swh.indexer.egg-info/SOURCES.txt b/swh.indexer.egg-info/SOURCES.txt index 09416d3..a45db37 100644 --- a/swh.indexer.egg-info/SOURCES.txt +++ b/swh.indexer.egg-info/SOURCES.txt @@ -1,95 +1,96 @@ .gitignore AUTHORS CONTRIBUTORS LICENSE MANIFEST.in Makefile Makefile.local README.md codemeta.json conftest.py pytest.ini requirements-swh.txt requirements-test.txt requirements.txt setup.py tox.ini version.txt debian/changelog debian/compat debian/control debian/copyright debian/rules debian/source/format docs/.gitignore docs/Makefile docs/README.md docs/conf.py docs/dev-info.rst docs/index.rst docs/_static/.placeholder docs/_templates/.placeholder sql/createdb-stamp sql/filldb-stamp sql/bin/db-upgrade sql/bin/dot_add_content sql/doc/json sql/doc/json/.gitignore sql/doc/json/Makefile sql/doc/json/indexer_configuration.tool_configuration.schema.json sql/doc/json/revision_metadata.translated_metadata.json sql/json/.gitignore sql/json/Makefile sql/json/indexer_configuration.tool_configuration.schema.json sql/json/revision_metadata.translated_metadata.json sql/upgrades/115.sql sql/upgrades/116.sql +sql/upgrades/117.sql swh/__init__.py swh.indexer.egg-info/PKG-INFO swh.indexer.egg-info/SOURCES.txt swh.indexer.egg-info/dependency_links.txt swh.indexer.egg-info/requires.txt swh.indexer.egg-info/top_level.txt swh/indexer/__init__.py swh/indexer/codemeta.py swh/indexer/ctags.py swh/indexer/fossology_license.py swh/indexer/indexer.py swh/indexer/language.py swh/indexer/metadata.py swh/indexer/metadata_detector.py swh/indexer/metadata_dictionary.py swh/indexer/mimetype.py swh/indexer/origin_head.py swh/indexer/rehash.py swh/indexer/tasks.py swh/indexer/data/codemeta/CITATION swh/indexer/data/codemeta/LICENSE swh/indexer/data/codemeta/codemeta.jsonld swh/indexer/data/codemeta/crosswalk.csv swh/indexer/sql/10-swh-init.sql swh/indexer/sql/20-swh-enums.sql swh/indexer/sql/30-swh-schema.sql swh/indexer/sql/40-swh-func.sql swh/indexer/sql/50-swh-data.sql swh/indexer/sql/60-swh-indexes.sql swh/indexer/storage/__init__.py swh/indexer/storage/converters.py swh/indexer/storage/db.py swh/indexer/storage/api/__init__.py swh/indexer/storage/api/client.py swh/indexer/storage/api/server.py swh/indexer/tests/__init__.py swh/indexer/tests/test_ctags.py swh/indexer/tests/test_fossology_license.py swh/indexer/tests/test_language.py swh/indexer/tests/test_metadata.py swh/indexer/tests/test_mimetype.py swh/indexer/tests/test_origin_head.py swh/indexer/tests/test_origin_metadata.py swh/indexer/tests/test_utils.py swh/indexer/tests/storage/__init__.py swh/indexer/tests/storage/generate_data_test.py swh/indexer/tests/storage/test_api_client.py swh/indexer/tests/storage/test_converters.py swh/indexer/tests/storage/test_storage.py \ No newline at end of file diff --git a/swh/indexer/indexer.py b/swh/indexer/indexer.py index e8fa96d..72d8b78 100644 --- a/swh/indexer/indexer.py +++ b/swh/indexer/indexer.py @@ -1,584 +1,585 @@ # Copyright (C) 2016-2018 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 abc import os import logging import shutil import tempfile import datetime from copy import deepcopy from swh.scheduler import get_scheduler from swh.storage import get_storage from swh.core.config import SWHConfig from swh.objstorage import get_objstorage from swh.objstorage.exc import ObjNotFoundError from swh.indexer.storage import get_indexer_storage, INDEXER_CFG_KEY from swh.model import hashutil from swh.core import utils class DiskIndexer: """Mixin intended to be used with other SomethingIndexer classes. Indexers inheriting from this class are a category of indexers which needs the disk for their computations. Note: This expects `self.working_directory` variable defined at runtime. """ def write_to_temp(self, filename, data): """Write the sha1's content in a temporary file. Args: filename (str): one of sha1's many filenames data (bytes): the sha1's content to write in temporary file Returns: The path to the temporary file created. That file is filled in with the raw content's data. """ os.makedirs(self.working_directory, exist_ok=True) temp_dir = tempfile.mkdtemp(dir=self.working_directory) content_path = os.path.join(temp_dir, filename) with open(content_path, 'wb') as f: f.write(data) return content_path def cleanup(self, content_path): """Remove content_path from working directory. Args: content_path (str): the file to remove """ temp_dir = os.path.dirname(content_path) shutil.rmtree(temp_dir) class BaseIndexer(SWHConfig, metaclass=abc.ABCMeta): """Base class for indexers to inherit from. The main entry point is the :func:`run` function which is in charge of triggering the computations on the batch dict/ids received. Indexers can: - filter out ids whose data has already been indexed. - retrieve ids data from storage or objstorage - index this data depending on the object and store the result in storage. To implement a new object type indexer, inherit from the BaseIndexer and implement indexing: :func:`run`: object_ids are different depending on object. For example: sha1 for content, sha1_git for revision, directory, release, and id for origin To implement a new concrete indexer, inherit from the object level classes: :class:`ContentIndexer`, :class:`RevisionIndexer`, :class:`OriginIndexer`. Then you need to implement the following functions: :func:`filter`: filter out data already indexed (in storage). :func:`index_object`: compute index on id with data (retrieved from the storage or the objstorage by the id key) and return the resulting index computation. :func:`persist_index_computations`: persist the results of multiple index computations in the storage. The new indexer implementation can also override the following functions: :func:`prepare`: Configuration preparation for the indexer. When overriding, this must call the `super().prepare()` instruction. :func:`check`: Configuration check for the indexer. When overriding, this must call the `super().check()` instruction. :func:`register_tools`: This should return a dict of the tool(s) to use when indexing or filtering. """ CONFIG = 'indexer/base' DEFAULT_CONFIG = { INDEXER_CFG_KEY: ('dict', { 'cls': 'remote', 'args': { 'url': 'http://localhost:5007/' } }), 'storage': ('dict', { 'cls': 'remote', 'args': { 'url': 'http://localhost:5002/', } }), 'objstorage': ('dict', { 'cls': 'remote', 'args': { 'url': 'http://localhost:5003/', } }) } ADDITIONAL_CONFIG = {} def __init__(self): """Prepare and check that the indexer is ready to run. """ super().__init__() self.prepare() self.check() def prepare(self): """Prepare the indexer's needed runtime configuration. Without this step, the indexer cannot possibly run. """ self.config = self.parse_config_file( additional_configs=[self.ADDITIONAL_CONFIG]) if self.config['storage']: self.storage = get_storage(**self.config['storage']) objstorage = self.config['objstorage'] self.objstorage = get_objstorage(objstorage['cls'], objstorage['args']) idx_storage = self.config[INDEXER_CFG_KEY] self.idx_storage = get_indexer_storage(**idx_storage) _log = logging.getLogger('requests.packages.urllib3.connectionpool') _log.setLevel(logging.WARN) self.log = logging.getLogger('swh.indexer') self.tools = list(self.register_tools(self.config['tools'])) - def check(self): + def check(self, *, check_tools=True): """Check the indexer's configuration is ok before proceeding. If ok, does nothing. If not raise error. """ - if not self.tools: + if check_tools and not self.tools: raise ValueError('Tools %s is unknown, cannot continue' % self.tools) def _prepare_tool(self, tool): """Prepare the tool dict to be compliant with the storage api. """ return {'tool_%s' % key: value for key, value in tool.items()} def register_tools(self, tools): """Permit to register tools to the storage. Add a sensible default which can be overridden if not sufficient. (For now, all indexers use only one tool) Expects the self.config['tools'] property to be set with one or more tools. Args: tools (dict/[dict]): Either a dict or a list of dict. Returns: List of dict with additional id key. Raises: ValueError if not a list nor a dict. """ tools = self.config['tools'] if isinstance(tools, list): tools = map(self._prepare_tool, tools) elif isinstance(tools, dict): tools = [self._prepare_tool(tools)] else: raise ValueError('Configuration tool(s) must be a dict or list!') - return self.idx_storage.indexer_configuration_add(tools) + if tools: + return self.idx_storage.indexer_configuration_add(tools) @abc.abstractmethod def index(self, id, data): """Index computation for the id and associated raw data. Args: id (bytes): identifier data (bytes): id's data from storage or objstorage depending on object type Returns: a dict that makes sense for the persist_index_computations function. """ pass @abc.abstractmethod def persist_index_computations(self, results, policy_update): """Persist the computation resulting from the index. Args: results ([result]): List of results. One result is the result of the index function. policy_update ([str]): either 'update-dups' or 'ignore-dups' to respectively update duplicates or ignore them Returns: None """ pass def next_step(self, results, task): """Do something else with computations results (e.g. send to another queue, ...). (This is not an abstractmethod since it is optional). Args: results ([result]): List of results (dict) as returned by index function. task (dict): a dict in the form expected by `scheduler.backend.SchedulerBackend.create_tasks` without `next_run`, plus a `result_name` key. Returns: None """ if task: if getattr(self, 'scheduler', None): scheduler = self.scheduler else: scheduler = get_scheduler(**self.config['scheduler']) task = deepcopy(task) result_name = task.pop('result_name') task['next_run'] = datetime.datetime.now() task['arguments']['kwargs'][result_name] = self.results scheduler.create_tasks([task]) @abc.abstractmethod def run(self, ids, policy_update, next_step=None, **kwargs): """Given a list of ids: - retrieves the data from the storage - executes the indexing computations - stores the results (according to policy_update) Args: ids ([bytes]): id's identifier list policy_update (str): either 'update-dups' or 'ignore-dups' to respectively update duplicates or ignore them next_step (dict): a dict in the form expected by `scheduler.backend.SchedulerBackend.create_tasks` without `next_run`, plus a `result_name` key. **kwargs: passed to the `index` method """ pass class ContentIndexer(BaseIndexer): """A content indexer working on a list of ids directly. To work on indexer range, use the :class:`ContentRangeIndexer` instead. Note: :class:`ContentIndexer` is not an instantiable object. To use it, one should inherit from this class and override the methods mentioned in the :class:`BaseIndexer` class. """ @abc.abstractmethod def filter(self, ids): """Filter missing ids for that particular indexer. Args: ids ([bytes]): list of ids Yields: iterator of missing ids """ pass def run(self, ids, policy_update, next_step=None, **kwargs): """Given a list of ids: - retrieve the content from the storage - execute the indexing computations - store the results (according to policy_update) Args: ids ([bytes]): sha1's identifier list policy_update (str): either 'update-dups' or 'ignore-dups' to respectively update duplicates or ignore them next_step (dict): a dict in the form expected by `scheduler.backend.SchedulerBackend.create_tasks` without `next_run`, plus a `result_name` key. **kwargs: passed to the `index` method """ results = [] try: for sha1 in ids: try: raw_content = self.objstorage.get(sha1) except ObjNotFoundError: self.log.warning('Content %s not found in objstorage' % hashutil.hash_to_hex(sha1)) continue res = self.index(sha1, raw_content, **kwargs) if res: # If no results, skip it results.append(res) self.persist_index_computations(results, policy_update) self.results = results return self.next_step(results, task=next_step) except Exception: self.log.exception( 'Problem when reading contents metadata.') class ContentRangeIndexer(BaseIndexer): """A content range indexer. This expects as input a range of ids to index. To work on a list of ids, use the :class:`ContentIndexer` instead. Note: :class:`ContentRangeIndexer` is not an instantiable object. To use it, one should inherit from this class and override the methods mentioned in the :class:`BaseIndexer` class. """ @abc.abstractmethod def indexed_contents_in_range(self, start, end): """Retrieve indexed contents within range [start, end]. Args **start** (bytes): Starting bound from range identifier **end** (bytes): End range identifier Yields: Content identifier (bytes) present in the range [start, end] """ pass def _list_contents_to_index(self, start, end, indexed): """Compute from storage the new contents to index in the range [start, end]. The already indexed contents are skipped. Args: **start** (bytes): Starting bound from range identifier **end** (bytes): End range identifier **indexed** (Set[bytes]): Set of content already indexed. Yields: Identifier (bytes) of contents to index. """ while start: result = self.storage.content_get_range(start, end) contents = result['contents'] for c in contents: _id = c['sha1'] if _id in indexed: continue yield _id start = result['next'] def _index_contents(self, start, end, indexed, **kwargs): """Index the contents from within range [start, end] Args: **start** (bytes): Starting bound from range identifier **end** (bytes): End range identifier **indexed** (Set[bytes]): Set of content already indexed. Yields: Data indexed (dict) to persist using the indexer storage """ for sha1 in self._list_contents_to_index(start, end, indexed): try: raw_content = self.objstorage.get(sha1) except ObjNotFoundError: self.log.warning('Content %s not found in objstorage' % hashutil.hash_to_hex(sha1)) continue res = self.index(sha1, raw_content, **kwargs) if res: yield res def run(self, start, end, skip_existing=True, **kwargs): """Given a range of content ids, compute the indexing computations on the contents within. Either the indexer is incremental (filter out existing computed data) or not (compute everything from scratch). Args: **start** (Union[bytes, str]): Starting range identifier **end** (Union[bytes, str]): Ending range identifier **skip_existing** (bool): Skip existing indexed data (default) or not **kwargs: passed to the `index` method Returns: a boolean. True if data was indexed, False otherwise. """ with_indexed_data = False try: if isinstance(start, str): start = hashutil.hash_to_bytes(start) if isinstance(end, str): end = hashutil.hash_to_bytes(end) if skip_existing: indexed = set(self.indexed_contents_in_range(start, end)) else: indexed = set() index_computations = self._index_contents(start, end, indexed) for results in utils.grouper(index_computations, n=self.config['write_batch_size']): self.persist_index_computations( results, policy_update='update-dups') with_indexed_data = True return with_indexed_data except Exception: self.log.exception( 'Problem when computing metadata.') class OriginIndexer(BaseIndexer): """An object type indexer, inherits from the :class:`BaseIndexer` and implements Origin indexing using the run method Note: the :class:`OriginIndexer` is not an instantiable object. To use it in another context one should inherit from this class and override the methods mentioned in the :class:`BaseIndexer` class. """ def run(self, ids, policy_update='update-dups', parse_ids=True, next_step=None, **kwargs): """Given a list of origin ids: - retrieve origins from storage - execute the indexing computations - store the results (according to policy_update) Args: ids ([Union[int, Tuple[str, bytes]]]): list of origin ids or (type, url) tuples. policy_update (str): either 'update-dups' or 'ignore-dups' to respectively update duplicates (default) or ignore them next_step (dict): a dict in the form expected by `scheduler.backend.SchedulerBackend.create_tasks` without `next_run`, plus a `result_name` key. parse_ids (bool): Do we need to parse id or not (default) **kwargs: passed to the `index` method """ if parse_ids: ids = [o.split('+', 1) if ':' in o else int(o) # type+url or id for o in ids] results = [] for id_ in ids: if isinstance(id_, (tuple, list)): if len(id_) != 2: raise TypeError('Expected a (type, url) tuple.') (type_, url) = id_ params = {'type': type_, 'url': url} elif isinstance(id_, int): params = {'id': id_} else: raise TypeError('Invalid value in "ids": %r' % id_) origin = self.storage.origin_get(params) if not origin: self.log.warning('Origins %s not found in storage' % list(ids)) continue try: res = self.index(origin, **kwargs) if origin: # If no results, skip it results.append(res) except Exception: self.log.exception( 'Problem when processing origin %s' % id_) self.persist_index_computations(results, policy_update) self.results = results return self.next_step(results, task=next_step) class RevisionIndexer(BaseIndexer): """An object type indexer, inherits from the :class:`BaseIndexer` and implements Revision indexing using the run method Note: the :class:`RevisionIndexer` is not an instantiable object. To use it in another context one should inherit from this class and override the methods mentioned in the :class:`BaseIndexer` class. """ def run(self, ids, policy_update, next_step=None): """Given a list of sha1_gits: - retrieve revisions from storage - execute the indexing computations - store the results (according to policy_update) Args: ids ([bytes or str]): sha1_git's identifier list policy_update (str): either 'update-dups' or 'ignore-dups' to respectively update duplicates or ignore them """ results = [] ids = [id_.encode() if isinstance(id_, str) else id_ for id_ in ids] revs = self.storage.revision_get(ids) for rev in revs: if not rev: self.log.warning('Revisions %s not found in storage' % list(map(hashutil.hash_to_hex, ids))) continue try: res = self.index(rev) if res: # If no results, skip it results.append(res) except Exception: self.log.exception( 'Problem when processing revision') self.persist_index_computations(results, policy_update) self.results = results return self.next_step(results, task=next_step) diff --git a/swh/indexer/metadata.py b/swh/indexer/metadata.py index 799849e..4406c11 100644 --- a/swh/indexer/metadata.py +++ b/swh/indexer/metadata.py @@ -1,335 +1,343 @@ # 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 """ - try: - result = { - 'id': rev['id'].decode(), - 'indexer_configuration_id': self.tool['id'], - 'translated_metadata': None - } + result = { + 'id': rev['id'].decode(), + '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): + ADDITIONAL_CONFIG = { + 'tools': ('list', []) + } + + def check(self, **kwargs): + kwargs['check_tools'] = False + super().check(**kwargs) + def filter(self, ids): return ids def run(self, revisions_metadata, policy_update, *, origin_head): """Expected to be called with the result of RevisionMetadataIndexer as first argument; ie. not a list of ids as other indexers would. Args: * `revisions_metadata` (List[dict]): contains metadata from revisions, along with the respective revision ids. It is passed by RevisionMetadataIndexer via a Celery chain triggered by OriginIndexer.next_step. * `policy_update`: `'ignore-dups'` or `'update-dups'` * `origin_head` (dict): {str(origin_id): rev_id.encode()} keys `origin_id` and `revision_id`, which is the result of OriginHeadIndexer. """ origin_head_map = {int(origin_id): 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, revisions_metadata=revisions_metadata, origin_head_map=origin_head_map) def index(self, origin, *, revisions_metadata, origin_head_map): # Get the last revision of the origin. revision_id = origin_head_map[origin['id']] # Get the metadata of that revision, and return it for revision_metadata in revisions_metadata: if revision_metadata['id'] == revision_id: return { 'origin_id': origin['id'], 'metadata': revision_metadata['translated_metadata'], 'from_revision': revision_id, 'indexer_configuration_id': revision_metadata['indexer_configuration_id'], } raise KeyError('%r not in %r' % (revision_id, [r['id'] for r in revisions_metadata])) 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/sql/30-swh-schema.sql b/swh/indexer/sql/30-swh-schema.sql index 6f45f14..0e4a0d7 100644 --- a/swh/indexer/sql/30-swh-schema.sql +++ b/swh/indexer/sql/30-swh-schema.sql @@ -1,140 +1,141 @@ --- --- Software Heritage Indexers Data Model --- -- drop schema if exists swh cascade; -- create schema swh; -- set search_path to swh; create table dbversion ( version int primary key, release timestamptz, description text ); insert into dbversion(version, release, description) values(116, now(), 'Work In Progress'); -- Computing metadata on sha1's contents -- a SHA1 checksum (not necessarily originating from Git) create domain sha1 as bytea check (length(value) = 20); -- a Git object ID, i.e., a SHA1 checksum create domain sha1_git as bytea check (length(value) = 20); create table indexer_configuration ( id serial not null, tool_name text not null, tool_version text not null, tool_configuration jsonb ); comment on table indexer_configuration is 'Indexer''s configuration version'; comment on column indexer_configuration.id is 'Tool identifier'; comment on column indexer_configuration.tool_version is 'Tool name'; comment on column indexer_configuration.tool_version is 'Tool version'; comment on column indexer_configuration.tool_configuration is 'Tool configuration: command line, flags, etc...'; -- Properties (mimetype, encoding, etc...) create table content_mimetype ( id sha1 not null, mimetype bytea not null, encoding bytea not null, indexer_configuration_id bigint not null ); comment on table content_mimetype is 'Metadata associated to a raw content'; comment on column content_mimetype.mimetype is 'Raw content Mimetype'; comment on column content_mimetype.encoding is 'Raw content encoding'; comment on column content_mimetype.indexer_configuration_id is 'Tool used to compute the information'; -- Language metadata create table content_language ( id sha1 not null, lang languages not null, indexer_configuration_id bigint not null ); comment on table content_language is 'Language information on a raw content'; comment on column content_language.lang is 'Language information'; comment on column content_language.indexer_configuration_id is 'Tool used to compute the information'; -- ctags information per content create table content_ctags ( id sha1 not null, name text not null, kind text not null, line bigint not null, lang ctags_languages not null, indexer_configuration_id bigint not null ); comment on table content_ctags is 'Ctags information on a raw content'; comment on column content_ctags.id is 'Content identifier'; comment on column content_ctags.name is 'Symbol name'; comment on column content_ctags.kind is 'Symbol kind (function, class, variable, const...)'; comment on column content_ctags.line is 'Symbol line'; comment on column content_ctags.lang is 'Language information for that content'; comment on column content_ctags.indexer_configuration_id is 'Tool used to compute the information'; create table fossology_license( id smallserial, name text not null ); comment on table fossology_license is 'Possible license recognized by license indexer'; comment on column fossology_license.id is 'License identifier'; comment on column fossology_license.name is 'License name'; create table content_fossology_license ( id sha1 not null, license_id smallserial not null, indexer_configuration_id bigint not null ); comment on table content_fossology_license is 'license associated to a raw content'; comment on column content_fossology_license.id is 'Raw content identifier'; comment on column content_fossology_license.license_id is 'One of the content''s license identifier'; comment on column content_fossology_license.indexer_configuration_id is 'Tool used to compute the information'; -- The table content_metadata provides a translation to files -- identified as potentially containning metadata with a translation tool (indexer_configuration_id) create table content_metadata( id sha1 not null, translated_metadata jsonb not null, indexer_configuration_id bigint not null ); comment on table content_metadata is 'metadata semantically translated from a content file'; comment on column content_metadata.id is 'sha1 of content file'; comment on column content_metadata.translated_metadata is 'result of translation with defined format'; comment on column content_metadata.indexer_configuration_id is 'tool used for translation'; -- The table revision_metadata provides a minimal set of intrinsic metadata -- detected with the detection tool (indexer_configuration_id) and aggregated -- from the content_metadata translation. create table revision_metadata( id sha1_git not null, translated_metadata jsonb not null, indexer_configuration_id bigint not null ); comment on table revision_metadata is 'metadata semantically detected and translated in a revision'; comment on column revision_metadata.id is 'sha1_git of revision'; comment on column revision_metadata.translated_metadata is 'result of detection and translation with defined format'; comment on column revision_metadata.indexer_configuration_id is 'tool used for detection'; create table origin_intrinsic_metadata( origin_id bigserial not null, metadata jsonb, indexer_configuration_id bigint not null, - from_revision sha1_git not null + from_revision sha1_git not null, + metadata_tsvector tsvector ); comment on table origin_intrinsic_metadata is 'keeps intrinsic metadata for an origin'; comment on column origin_intrinsic_metadata.origin_id is 'the entry id in origin'; comment on column origin_intrinsic_metadata.metadata is 'metadata extracted from a revision'; comment on column origin_intrinsic_metadata.indexer_configuration_id is 'tool used to generate this metadata'; comment on column origin_intrinsic_metadata.from_revision is 'sha1 of the revision this metadata was copied from.'; diff --git a/swh/indexer/sql/40-swh-func.sql b/swh/indexer/sql/40-swh-func.sql index 5e87671..af035f3 100644 --- a/swh/indexer/sql/40-swh-func.sql +++ b/swh/indexer/sql/40-swh-func.sql @@ -1,429 +1,447 @@ -- Postgresql index helper function create or replace function hash_sha1(text) returns text language sql strict immutable as $$ select encode(public.digest($1, 'sha1'), 'hex') $$; comment on function hash_sha1(text) is 'Compute sha1 hash as text'; -- create a temporary table called tmp_TBLNAME, mimicking existing table -- TBLNAME -- -- Args: -- tblname: name of the table to mimick create or replace function swh_mktemp(tblname regclass) returns void language plpgsql as $$ begin execute format(' create temporary table tmp_%1$I (like %1$I including defaults) on commit drop; alter table tmp_%1$I drop column if exists object_id; ', tblname); return; end $$; -- create a temporary table for content_mimetype tmp_content_mimetype, create or replace function swh_mktemp_content_mimetype() returns void language sql as $$ create temporary table tmp_content_mimetype ( like content_mimetype including defaults ) on commit drop; $$; comment on function swh_mktemp_content_mimetype() IS 'Helper table to add mimetype information'; -- add tmp_content_mimetype entries to content_mimetype, overwriting -- duplicates if conflict_update is true, skipping duplicates otherwise. -- -- If filtering duplicates is in order, the call to -- swh_content_mimetype_missing must take place before calling this -- function. -- -- -- operates in bulk: 0. swh_mktemp(content_mimetype), 1. COPY to tmp_content_mimetype, -- 2. call this function create or replace function swh_content_mimetype_add(conflict_update boolean) returns void language plpgsql as $$ begin if conflict_update then insert into content_mimetype (id, mimetype, encoding, indexer_configuration_id) select id, mimetype, encoding, indexer_configuration_id from tmp_content_mimetype tcm on conflict(id, indexer_configuration_id) do update set mimetype = excluded.mimetype, encoding = excluded.encoding; else insert into content_mimetype (id, mimetype, encoding, indexer_configuration_id) select id, mimetype, encoding, indexer_configuration_id from tmp_content_mimetype tcm on conflict(id, indexer_configuration_id) do nothing; end if; return; end $$; comment on function swh_content_mimetype_add(boolean) IS 'Add new content mimetypes'; -- add tmp_content_language entries to content_language, overwriting -- duplicates if conflict_update is true, skipping duplicates otherwise. -- -- If filtering duplicates is in order, the call to -- swh_content_language_missing must take place before calling this -- function. -- -- operates in bulk: 0. swh_mktemp(content_language), 1. COPY to -- tmp_content_language, 2. call this function create or replace function swh_content_language_add(conflict_update boolean) returns void language plpgsql as $$ begin if conflict_update then insert into content_language (id, lang, indexer_configuration_id) select id, lang, indexer_configuration_id from tmp_content_language tcl on conflict(id, indexer_configuration_id) do update set lang = excluded.lang; else insert into content_language (id, lang, indexer_configuration_id) select id, lang, indexer_configuration_id from tmp_content_language tcl on conflict(id, indexer_configuration_id) do nothing; end if; return; end $$; comment on function swh_content_language_add(boolean) IS 'Add new content languages'; -- create a temporary table for retrieving content_language create or replace function swh_mktemp_content_language() returns void language sql as $$ create temporary table tmp_content_language ( like content_language including defaults ) on commit drop; $$; comment on function swh_mktemp_content_language() is 'Helper table to add content language'; -- create a temporary table for content_ctags tmp_content_ctags, create or replace function swh_mktemp_content_ctags() returns void language sql as $$ create temporary table tmp_content_ctags ( like content_ctags including defaults ) on commit drop; $$; comment on function swh_mktemp_content_ctags() is 'Helper table to add content ctags'; -- add tmp_content_ctags entries to content_ctags, overwriting -- duplicates if conflict_update is true, skipping duplicates otherwise. -- -- operates in bulk: 0. swh_mktemp(content_ctags), 1. COPY to tmp_content_ctags, -- 2. call this function create or replace function swh_content_ctags_add(conflict_update boolean) returns void language plpgsql as $$ begin if conflict_update then delete from content_ctags where id in (select tmp.id from tmp_content_ctags tmp inner join indexer_configuration i on i.id=tmp.indexer_configuration_id); end if; insert into content_ctags (id, name, kind, line, lang, indexer_configuration_id) select id, name, kind, line, lang, indexer_configuration_id from tmp_content_ctags tct on conflict(id, hash_sha1(name), kind, line, lang, indexer_configuration_id) do nothing; return; end $$; comment on function swh_content_ctags_add(boolean) IS 'Add new ctags symbols per content'; create type content_ctags_signature as ( id sha1, name text, kind text, line bigint, lang ctags_languages, tool_id integer, tool_name text, tool_version text, tool_configuration jsonb ); -- Search within ctags content. -- create or replace function swh_content_ctags_search( expression text, l integer default 10, last_sha1 sha1 default '\x0000000000000000000000000000000000000000') returns setof content_ctags_signature language sql as $$ select c.id, name, kind, line, lang, i.id as tool_id, tool_name, tool_version, tool_configuration from content_ctags c inner join indexer_configuration i on i.id = c.indexer_configuration_id where hash_sha1(name) = hash_sha1(expression) and c.id > last_sha1 order by id limit l; $$; comment on function swh_content_ctags_search(text, integer, sha1) IS 'Equality search through ctags'' symbols'; -- create a temporary table for content_fossology_license tmp_content_fossology_license, create or replace function swh_mktemp_content_fossology_license() returns void language sql as $$ create temporary table tmp_content_fossology_license ( id sha1, license text, indexer_configuration_id integer ) on commit drop; $$; comment on function swh_mktemp_content_fossology_license() is 'Helper table to add content license'; -- add tmp_content_fossology_license entries to content_fossology_license, overwriting -- duplicates if conflict_update is true, skipping duplicates otherwise. -- -- operates in bulk: 0. swh_mktemp(content_fossology_license), 1. COPY to -- tmp_content_fossology_license, 2. call this function create or replace function swh_content_fossology_license_add(conflict_update boolean) returns void language plpgsql as $$ begin -- insert unknown licenses first insert into fossology_license (name) select distinct license from tmp_content_fossology_license tmp where not exists (select 1 from fossology_license where name=tmp.license) on conflict(name) do nothing; if conflict_update then -- delete from content_fossology_license c -- using tmp_content_fossology_license tmp, indexer_configuration i -- where c.id = tmp.id and i.id=tmp.indexer_configuration_id delete from content_fossology_license where id in (select tmp.id from tmp_content_fossology_license tmp inner join indexer_configuration i on i.id=tmp.indexer_configuration_id); end if; insert into content_fossology_license (id, license_id, indexer_configuration_id) select tcl.id, (select id from fossology_license where name = tcl.license) as license, indexer_configuration_id from tmp_content_fossology_license tcl on conflict(id, license_id, indexer_configuration_id) do nothing; return; end $$; comment on function swh_content_fossology_license_add(boolean) IS 'Add new content licenses'; -- content_metadata functions -- add tmp_content_metadata entries to content_metadata, overwriting -- duplicates if conflict_update is true, skipping duplicates otherwise. -- -- If filtering duplicates is in order, the call to -- swh_content_metadata_missing must take place before calling this -- function. -- -- operates in bulk: 0. swh_mktemp(content_language), 1. COPY to -- tmp_content_metadata, 2. call this function create or replace function swh_content_metadata_add(conflict_update boolean) returns void language plpgsql as $$ begin if conflict_update then insert into content_metadata (id, translated_metadata, indexer_configuration_id) select id, translated_metadata, indexer_configuration_id from tmp_content_metadata tcm on conflict(id, indexer_configuration_id) do update set translated_metadata = excluded.translated_metadata; else insert into content_metadata (id, translated_metadata, indexer_configuration_id) select id, translated_metadata, indexer_configuration_id from tmp_content_metadata tcm on conflict(id, indexer_configuration_id) do nothing; end if; return; end $$; comment on function swh_content_metadata_add(boolean) IS 'Add new content metadata'; -- create a temporary table for retrieving content_metadata create or replace function swh_mktemp_content_metadata() returns void language sql as $$ create temporary table tmp_content_metadata ( like content_metadata including defaults ) on commit drop; $$; comment on function swh_mktemp_content_metadata() is 'Helper table to add content metadata'; -- end content_metadata functions -- add tmp_revision_metadata entries to revision_metadata, overwriting -- duplicates if conflict_update is true, skipping duplicates otherwise. -- -- If filtering duplicates is in order, the call to -- swh_revision_metadata_missing must take place before calling this -- function. -- -- operates in bulk: 0. swh_mktemp(content_language), 1. COPY to -- tmp_revision_metadata, 2. call this function create or replace function swh_revision_metadata_add(conflict_update boolean) returns void language plpgsql as $$ begin if conflict_update then insert into revision_metadata (id, translated_metadata, indexer_configuration_id) select id, translated_metadata, indexer_configuration_id from tmp_revision_metadata tcm on conflict(id, indexer_configuration_id) do update set translated_metadata = excluded.translated_metadata; else insert into revision_metadata (id, translated_metadata, indexer_configuration_id) select id, translated_metadata, indexer_configuration_id from tmp_revision_metadata tcm on conflict(id, indexer_configuration_id) do nothing; end if; return; end $$; comment on function swh_revision_metadata_add(boolean) IS 'Add new revision metadata'; -- create a temporary table for retrieving revision_metadata create or replace function swh_mktemp_revision_metadata() returns void language sql as $$ create temporary table tmp_revision_metadata ( like revision_metadata including defaults ) on commit drop; $$; comment on function swh_mktemp_revision_metadata() is 'Helper table to add revision metadata'; -- create a temporary table for retrieving origin_intrinsic_metadata create or replace function swh_mktemp_origin_intrinsic_metadata() returns void language sql as $$ create temporary table tmp_origin_intrinsic_metadata ( like origin_intrinsic_metadata including defaults ) on commit drop; $$; comment on function swh_mktemp_origin_intrinsic_metadata() is 'Helper table to add origin intrinsic metadata'; create or replace function swh_mktemp_indexer_configuration() returns void language sql as $$ create temporary table tmp_indexer_configuration ( like indexer_configuration including defaults ) on commit drop; alter table tmp_indexer_configuration drop column id; $$; -- add tmp_indexer_configuration entries to indexer_configuration, -- skipping duplicates if any. -- -- operates in bulk: 0. create temporary tmp_indexer_configuration, 1. COPY to -- it, 2. call this function to insert and filtering out duplicates create or replace function swh_indexer_configuration_add() returns setof indexer_configuration language plpgsql as $$ begin insert into indexer_configuration(tool_name, tool_version, tool_configuration) select tool_name, tool_version, tool_configuration from tmp_indexer_configuration tmp on conflict(tool_name, tool_version, tool_configuration) do nothing; return query select id, tool_name, tool_version, tool_configuration from tmp_indexer_configuration join indexer_configuration using(tool_name, tool_version, tool_configuration); return; end $$; -- add tmp_origin_intrinsic_metadata entries to origin_intrinsic_metadata, -- overwriting duplicates if conflict_update is true, skipping duplicates -- otherwise. -- -- If filtering duplicates is in order, the call to -- swh_origin_intrinsic_metadata_missing must take place before calling this -- function. -- -- operates in bulk: 0. swh_mktemp(content_language), 1. COPY to -- tmp_origin_intrinsic_metadata, 2. call this function create or replace function swh_origin_intrinsic_metadata_add( conflict_update boolean) returns void language plpgsql as $$ begin + perform swh_origin_intrinsic_metadata_compute_tsvector(); if conflict_update then - insert into origin_intrinsic_metadata (origin_id, metadata, indexer_configuration_id, from_revision) - select origin_id, metadata, indexer_configuration_id, from_revision + insert into origin_intrinsic_metadata (origin_id, metadata, indexer_configuration_id, from_revision, metadata_tsvector) + select origin_id, metadata, indexer_configuration_id, from_revision, + metadata_tsvector from tmp_origin_intrinsic_metadata on conflict(origin_id, indexer_configuration_id) do update set metadata = excluded.metadata; else - insert into origin_intrinsic_metadata (origin_id, metadata, indexer_configuration_id, from_revision) - select origin_id, metadata, indexer_configuration_id, from_revision + insert into origin_intrinsic_metadata (origin_id, metadata, indexer_configuration_id, from_revision, metadata_tsvector) + select origin_id, metadata, indexer_configuration_id, from_revision, + metadata_tsvector from tmp_origin_intrinsic_metadata on conflict(origin_id, indexer_configuration_id) do nothing; end if; return; end $$; + +-- Compute the metadata_tsvector column in tmp_origin_intrinsic_metadata. +-- +-- It uses the "pg_catalog.simple" dictionary, as it has no stopword, +-- so it should be suitable for proper names and non-English text. +create or replace function swh_origin_intrinsic_metadata_compute_tsvector() + returns void + language plpgsql +as $$ +begin + update tmp_origin_intrinsic_metadata + set metadata_tsvector = to_tsvector('pg_catalog.simple', metadata); +end +$$; + comment on function swh_origin_intrinsic_metadata_add(boolean) IS 'Add new origin intrinsic metadata'; diff --git a/swh/indexer/sql/60-swh-indexes.sql b/swh/indexer/sql/60-swh-indexes.sql index 130f3bc..587d811 100644 --- a/swh/indexer/sql/60-swh-indexes.sql +++ b/swh/indexer/sql/60-swh-indexes.sql @@ -1,66 +1,68 @@ -- fossology_license create unique index fossology_license_pkey on fossology_license(id); alter table fossology_license add primary key using index fossology_license_pkey; create unique index on fossology_license(name); -- indexer_configuration create unique index concurrently indexer_configuration_pkey on indexer_configuration(id); alter table indexer_configuration add primary key using index indexer_configuration_pkey; create unique index on indexer_configuration(tool_name, tool_version, tool_configuration); -- content_ctags create index on content_ctags(id); create index on content_ctags(hash_sha1(name)); create unique index on content_ctags(id, hash_sha1(name), kind, line, lang, indexer_configuration_id); alter table content_ctags add constraint content_ctags_indexer_configuration_id_fkey foreign key (indexer_configuration_id) references indexer_configuration(id) not valid; alter table content_ctags validate constraint content_ctags_indexer_configuration_id_fkey; -- content_metadata create unique index content_metadata_pkey on content_metadata(id, indexer_configuration_id); alter table content_metadata add primary key using index content_metadata_pkey; alter table content_metadata add constraint content_metadata_indexer_configuration_id_fkey foreign key (indexer_configuration_id) references indexer_configuration(id) not valid; alter table content_metadata validate constraint content_metadata_indexer_configuration_id_fkey; -- revision_metadata create unique index revision_metadata_pkey on revision_metadata(id, indexer_configuration_id); alter table revision_metadata add primary key using index revision_metadata_pkey; alter table revision_metadata add constraint revision_metadata_indexer_configuration_id_fkey foreign key (indexer_configuration_id) references indexer_configuration(id) not valid; alter table revision_metadata validate constraint revision_metadata_indexer_configuration_id_fkey; -- content_mimetype create unique index content_mimetype_pkey on content_mimetype(id, indexer_configuration_id); alter table content_mimetype add primary key using index content_mimetype_pkey; alter table content_mimetype add constraint content_mimetype_indexer_configuration_id_fkey foreign key (indexer_configuration_id) references indexer_configuration(id) not valid; alter table content_mimetype validate constraint content_mimetype_indexer_configuration_id_fkey; -- content_language create unique index content_language_pkey on content_language(id, indexer_configuration_id); alter table content_language add primary key using index content_language_pkey; alter table content_language add constraint content_language_indexer_configuration_id_fkey foreign key (indexer_configuration_id) references indexer_configuration(id) not valid; alter table content_language validate constraint content_language_indexer_configuration_id_fkey; -- content_fossology_license create unique index content_fossology_license_pkey on content_fossology_license(id, license_id, indexer_configuration_id); alter table content_fossology_license add primary key using index content_fossology_license_pkey; alter table content_fossology_license add constraint content_fossology_license_license_id_fkey foreign key (license_id) references fossology_license(id) not valid; alter table content_fossology_license validate constraint content_fossology_license_license_id_fkey; alter table content_fossology_license add constraint content_fossology_license_indexer_configuration_id_fkey foreign key (indexer_configuration_id) references indexer_configuration(id) not valid; alter table content_fossology_license validate constraint content_fossology_license_indexer_configuration_id_fkey; -- origin_intrinsic_metadata create unique index origin_intrinsic_metadata_pkey on origin_intrinsic_metadata(origin_id, indexer_configuration_id); alter table origin_intrinsic_metadata add primary key using index origin_intrinsic_metadata_pkey; alter table origin_intrinsic_metadata add constraint origin_intrinsic_metadata_indexer_configuration_id_fkey foreign key (indexer_configuration_id) references indexer_configuration(id) not valid; alter table origin_intrinsic_metadata validate constraint origin_intrinsic_metadata_indexer_configuration_id_fkey; alter table origin_intrinsic_metadata add constraint origin_intrinsic_metadata_revision_metadata_fkey foreign key (from_revision, indexer_configuration_id) references revision_metadata(id, indexer_configuration_id) not valid; alter table origin_intrinsic_metadata validate constraint origin_intrinsic_metadata_revision_metadata_fkey; + +create index origin_intrinsic_metadata_fulltext_idx on origin_intrinsic_metadata using gin (metadata_tsvector); diff --git a/swh/indexer/storage/__init__.py b/swh/indexer/storage/__init__.py index 0bdd82b..e6393a6 100644 --- a/swh/indexer/storage/__init__.py +++ b/swh/indexer/storage/__init__.py @@ -1,720 +1,745 @@ # 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 . 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 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 - **language** (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, language """ 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: list: dictionaries with the following keys: - **id** (bytes) - **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 - **license** ([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: an iterable of missing id for the tuple (id, indexer_configuration_id) """ 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: list: 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 Returns: iterable: 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: list: dictionaries with the following keys: - **id** (bytes) - **translated_metadata** (str): associated metadata - **tool** (dict): tool used to compute 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 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', '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: - **id** (int) - **translated_metadata** (str): associated metadata - **tool** (dict): tool used to compute 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 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'], 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 + + """ + 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('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 identifier of the tool if it exists, 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/db.py b/swh/indexer/storage/db.py index 61d89c6..c60692c 100644 --- a/swh/indexer/storage/db.py +++ b/swh/indexer/storage/db.py @@ -1,369 +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 + 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/storage/test_storage.py b/swh/indexer/tests/storage/test_storage.py index 1d39ab4..00af0e6 100644 --- a/swh/indexer/tests/storage/test_storage.py +++ b/swh/indexer/tests/storage/test_storage.py @@ -1,1845 +1,1968 @@ # 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 @pytest.mark.db class BaseTestStorage(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, }, } self.storage = get_indexer_storage(**self.storage_config) 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.origin_id_1 = 54974445 + self.origin_id_2 = 44434342 cur = self.test_db[self.TEST_DB_NAME].cursor tools = {} cur.execute(''' select tool_name, id, tool_version, tool_configuration from indexer_configuration order by id''') for row in cur.fetchall(): key = row[0] while key in tools: key = '_' + key tools[key] = { 'id': row[1], 'name': row[0], 'version': row[2], 'configuration': row[3] } self.tools = tools 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() @pytest.mark.db class CommonTestStorage(BaseTestStorage): """Base class for Indexer Storage testing. """ 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': b'text/plain', 'encoding': b'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': b'text/plain', 'encoding': b'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': b'text/plain', 'encoding': b'utf-8', 'tool': self.tools['file'], }] self.assertEqual(actual_mimetypes, expected_mimetypes_v1) # given mimetype_v2 = mimetype_v1.copy() mimetype_v2.update({ 'mimetype': b'text/html', 'encoding': b'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': b'text/plain', 'encoding': b'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': b'text/plain', 'encoding': b'utf-8', 'tool': self.tools['file'], }] # then self.assertEqual(actual_mimetypes, expected_mimetypes_v1) # given mimetype_v2 = mimetype_v1.copy() mimetype_v2.update({ 'mimetype': b'text/html', 'encoding': b'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': b'text/html', 'encoding': b'us-ascii', 'tool': { 'id': 2, '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': b'text/plain', 'encoding': b'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': b'text/plain', 'encoding': b'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', }, ] } ctag2 = { 'id': self.sha1_2, 'indexer_configuration_id': tool_id, 'ctags': [ { 'name': 'hello', 'kind': 'variable', 'line': 100, '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': 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', }]) 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 }, '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 }, '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'], 'tool': self.tools['swh-metadata-detector'] }] 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 }, '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'], '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', }, }) 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 }, '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'], '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' }, }) 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'], '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, 'indexer_configuration_id': tool_id, } metadata_origin = { 'origin_id': self.origin_id_1, 'metadata': metadata, 'indexer_configuration_id': tool_id, '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, }] 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(), 'indexer_configuration_id': tool_id, } metadata_origin_v1 = { 'origin_id': self.origin_id_1, 'metadata': metadata_v1.copy(), 'indexer_configuration_id': tool_id, '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, }] 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, 'indexer_configuration_id': tool_id, } metadata_origin_v1 = { 'origin_id': self.origin_id_1, 'metadata': metadata_v1.copy(), 'indexer_configuration_id': tool_id, '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, }] 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, }] # 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, + 'indexer_configuration_id': tool_id, + } + metadata1_origin = { + 'origin_id': self.origin_id_1, + 'metadata': metadata1, + '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, + 'indexer_configuration_id': tool_id, + } + metadata2_origin = { + 'origin_id': self.origin_id_2, + 'metadata': metadata2, + '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, + 'indexer_configuration_id': tool_id, + } + metadata1_origin = { + 'origin_id': self.origin_id_1, + 'metadata': metadata1, + '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, + 'indexer_configuration_id': tool_id, + } + metadata2_origin = { + 'origin_id': self.origin_id_2, + 'metadata': metadata2, + '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_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 "}, } actual_tool = self.storage.indexer_configuration_get(tool) expected_tool = tool.copy() expected_tool['id'] = 1 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"}, } 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 class PropBasedTestStorage(BaseTestStorage, unittest.TestCase): """Properties-based tests """ 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',)) @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) @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) 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',)) 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 @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) @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) @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) class IndexerTestStorage(CommonTestStorage, unittest.TestCase): """Running the tests locally. For the client api tests (remote storage), see `class`:swh.indexer.storage.test_api_client:TestRemoteStorage class. """ pass diff --git a/swh/indexer/tests/test_origin_metadata.py b/swh/indexer/tests/test_origin_metadata.py index 08a2346..510ae1a 100644 --- a/swh/indexer/tests/test_origin_metadata.py +++ b/swh/indexer/tests/test_origin_metadata.py @@ -1,127 +1,122 @@ # 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 class OriginMetadataTestIndexer(OriginMetadataIndexer): def prepare(self): self.config = { 'storage': { 'cls': 'remote', 'args': { 'url': 'http://localhost:9999', } }, - 'tools': { - 'name': 'origin-metadata', - 'version': '0.0.1', - 'configuration': {} - } + '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.tool = self.tools[0] 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', 'translated_metadata': metadata, 'indexer_configuration_id': 7, } origin_metadata = { 'origin_id': 54974445, 'from_revision': '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 858ce23..102c28d 100644 --- a/swh/indexer/tests/test_utils.py +++ b/swh/indexer/tests/test_utils.py @@ -1,715 +1,720 @@ # 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 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_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 = [] def indexer_configuration_add(self, tools): - tool = tools[0] + 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 [{ + 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 [{ + 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 [{ + 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): self.added_data.append( ('revision_metadata', conflict_update, metadata)) 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', '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 diff --git a/version.txt b/version.txt index 42e5166..39a457b 100644 --- a/version.txt +++ b/version.txt @@ -1 +1 @@ -v0.0.61-0-g6e7416d \ No newline at end of file +v0.0.62-0-g519286b \ No newline at end of file