diff --git a/MANIFEST.in b/MANIFEST.in index 304d9f7..cfe6e5b 100644 --- a/MANIFEST.in +++ b/MANIFEST.in @@ -1,8 +1,9 @@ include README.md include Makefile include requirements.txt include requirements-swh.txt include version.txt recursive-include sql * recursive-include swh/indexer/sql *.sql recursive-include swh/indexer/data * +recursive-include swh py.typed diff --git a/PKG-INFO b/PKG-INFO index e228fed..2f25003 100644 --- a/PKG-INFO +++ b/PKG-INFO @@ -1,69 +1,69 @@ Metadata-Version: 2.1 Name: swh.indexer -Version: 0.0.155 +Version: 0.0.156 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: Source, https://forge.softwareheritage.org/source/swh-indexer Project-URL: Bug Reports, https://forge.softwareheritage.org/maniphest +Project-URL: Source, https://forge.softwareheritage.org/source/swh-indexer Project-URL: Funding, https://www.softwareheritage.org/donate 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/requirements-swh.txt b/requirements-swh.txt index 4a8746e..330716a 100644 --- a/requirements-swh.txt +++ b/requirements-swh.txt @@ -1,6 +1,6 @@ swh.core[db,http] >= 0.0.65 swh.model >= 0.0.15 swh.objstorage >= 0.0.28 swh.scheduler >= 0.0.47 -swh.storage >= 0.0.143 +swh.storage >= 0.0.156 swh.journal >= 0.0.17 diff --git a/sql/upgrades/127.sql b/sql/upgrades/127.sql new file mode 100644 index 0000000..4f65ac5 --- /dev/null +++ b/sql/upgrades/127.sql @@ -0,0 +1,63 @@ +-- SWH Indexer DB schema upgrade +-- from_version: 126 +-- to_version: 127 +-- description: Remove swh_origin_intrinsic_metadata_add origin_url field and +-- replace id by the former content of origin_url + +insert into dbversion(version, release, description) +values(127, now(), 'Work In Progress'); + +-- replace id column by origin_url +alter table origin_intrinsic_metadata + drop constraint origin_intrinsic_metadata_indexer_configuration_id_fkey; +alter table origin_intrinsic_metadata + drop constraint origin_intrinsic_metadata_pkey; +alter table origin_intrinsic_metadata + drop column id; +alter table origin_intrinsic_metadata + rename column origin_url id; +comment on column origin_intrinsic_metadata.id is 'url of the origin'; + +-- replace functions that operate on this table +create or replace function swh_origin_intrinsic_metadata_add( + conflict_update boolean) + returns void + language plpgsql +as $$ +begin + perform swh_origin_intrinsic_metadata_compute_tsvector(); + if conflict_update then + insert into origin_intrinsic_metadata (id, metadata, indexer_configuration_id, from_revision, metadata_tsvector, mappings) + select id, metadata, indexer_configuration_id, from_revision, + metadata_tsvector, mappings + from tmp_origin_intrinsic_metadata + on conflict(id, indexer_configuration_id) + do update set + metadata = excluded.metadata, + metadata_tsvector = excluded.metadata_tsvector, + mappings = excluded.mappings, + from_revision = excluded.from_revision; + + else + insert into origin_intrinsic_metadata (id, metadata, indexer_configuration_id, from_revision, metadata_tsvector, mappings) + select id, metadata, indexer_configuration_id, from_revision, + metadata_tsvector, mappings + from tmp_origin_intrinsic_metadata + on conflict(id, indexer_configuration_id) + do nothing; + end if; + return; +end +$$; +comment on function swh_origin_intrinsic_metadata_add(boolean) IS 'Add new origin intrinsic metadata'; + +-- recreate indexes/constraints on this table +create unique index origin_intrinsic_metadata_pkey + on origin_intrinsic_metadata(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; diff --git a/swh.indexer.egg-info/PKG-INFO b/swh.indexer.egg-info/PKG-INFO index e228fed..2f25003 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: 0.0.155 +Version: 0.0.156 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: Source, https://forge.softwareheritage.org/source/swh-indexer Project-URL: Bug Reports, https://forge.softwareheritage.org/maniphest +Project-URL: Source, https://forge.softwareheritage.org/source/swh-indexer Project-URL: Funding, https://www.softwareheritage.org/donate 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 5457431..d47b813 100644 --- a/swh.indexer.egg-info/SOURCES.txt +++ b/swh.indexer.egg-info/SOURCES.txt @@ -1,92 +1,94 @@ MANIFEST.in Makefile README.md requirements-swh.txt requirements.txt setup.py version.txt sql/bin/db-upgrade sql/bin/dot_add_content 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 sql/upgrades/118.sql sql/upgrades/119.sql sql/upgrades/120.sql sql/upgrades/121.sql sql/upgrades/122.sql sql/upgrades/123.sql sql/upgrades/124.sql sql/upgrades/125.sql sql/upgrades/126.sql +sql/upgrades/127.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/entry_points.txt swh.indexer.egg-info/requires.txt swh.indexer.egg-info/top_level.txt swh/indexer/__init__.py swh/indexer/cli.py swh/indexer/codemeta.py swh/indexer/ctags.py swh/indexer/fossology_license.py swh/indexer/indexer.py swh/indexer/journal_client.py swh/indexer/metadata.py swh/indexer/metadata_detector.py swh/indexer/mimetype.py swh/indexer/origin_head.py +swh/indexer/py.typed 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/metadata_dictionary/__init__.py swh/indexer/metadata_dictionary/base.py swh/indexer/metadata_dictionary/codemeta.py swh/indexer/metadata_dictionary/maven.py swh/indexer/metadata_dictionary/npm.py swh/indexer/metadata_dictionary/python.py swh/indexer/metadata_dictionary/ruby.py 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/in_memory.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/conftest.py swh/indexer/tests/tasks.py swh/indexer/tests/test_cli.py swh/indexer/tests/test_ctags.py swh/indexer/tests/test_fossology_license.py swh/indexer/tests/test_journal_client.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/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_in_memory.py swh/indexer/tests/storage/test_server.py swh/indexer/tests/storage/test_storage.py \ No newline at end of file diff --git a/swh.indexer.egg-info/requires.txt b/swh.indexer.egg-info/requires.txt index 688cbee..ebdf5b3 100644 --- a/swh.indexer.egg-info/requires.txt +++ b/swh.indexer.egg-info/requires.txt @@ -1,16 +1,16 @@ vcversioner click python-magic>=0.4.13 pyld xmltodict swh.core[db,http]>=0.0.65 swh.model>=0.0.15 swh.objstorage>=0.0.28 swh.scheduler>=0.0.47 -swh.storage>=0.0.143 +swh.storage>=0.0.156 swh.journal>=0.0.17 [testing] pytest<4 pytest-postgresql hypothesis>=3.11.0 diff --git a/swh/__init__.py b/swh/__init__.py index 69e3be5..f14e196 100644 --- a/swh/__init__.py +++ b/swh/__init__.py @@ -1 +1,4 @@ -__path__ = __import__('pkgutil').extend_path(__path__, __name__) +from pkgutil import extend_path +from typing import Iterable + +__path__ = extend_path(__path__, __name__) # type: Iterable[str] diff --git a/swh/indexer/cli.py b/swh/indexer/cli.py index ad94ba4..d14aff5 100644 --- a/swh/indexer/cli.py +++ b/swh/indexer/cli.py @@ -1,259 +1,261 @@ # Copyright (C) 2019 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import functools import json import time import click from swh.core import config from swh.core.cli import CONTEXT_SETTINGS, AliasedGroup from swh.journal.cli import get_journal_client from swh.scheduler import get_scheduler from swh.scheduler.cli_utils import schedule_origin_batches from swh.storage import get_storage from swh.indexer import metadata_dictionary from swh.indexer.journal_client import process_journal_objects from swh.indexer.storage import get_indexer_storage from swh.indexer.storage.api.server import load_and_check_config, app @click.group(name='indexer', context_settings=CONTEXT_SETTINGS, cls=AliasedGroup) @click.option('--config-file', '-C', default=None, type=click.Path(exists=True, dir_okay=False,), help="Configuration file.") @click.pass_context def cli(ctx, config_file): """Software Heritage Indexer tools. The Indexer is used to mine the content of the archive and extract derived information from archive source code artifacts. """ ctx.ensure_object(dict) conf = config.read(config_file) ctx.obj['config'] = conf def _get_api(getter, config, config_key, url): if url: config[config_key] = { 'cls': 'remote', 'args': {'url': url} } elif config_key not in config: raise click.ClickException( 'Missing configuration for {}'.format(config_key)) return getter(**config[config_key]) @cli.group('mapping') def mapping(): '''Manage Software Heritage Indexer mappings.''' pass @mapping.command('list') def mapping_list(): """Prints the list of known mappings.""" mapping_names = [mapping.name for mapping in metadata_dictionary.MAPPINGS.values()] mapping_names.sort() for mapping_name in mapping_names: click.echo(mapping_name) @mapping.command('list-terms') @click.option('--exclude-mapping', multiple=True, help='Exclude the given mapping from the output') @click.option('--concise', is_flag=True, default=False, help='Don\'t print the list of mappings supporting each term.') def mapping_list_terms(concise, exclude_mapping): """Prints the list of known CodeMeta terms, and which mappings support them.""" properties = metadata_dictionary.list_terms() for (property_name, supported_mappings) in sorted(properties.items()): supported_mappings = {m.name for m in supported_mappings} supported_mappings -= set(exclude_mapping) if supported_mappings: if concise: click.echo(property_name) else: click.echo('{}:'.format(property_name)) click.echo('\t' + ', '.join(sorted(supported_mappings))) @mapping.command('translate') @click.argument('mapping-name') @click.argument('file', type=click.File('rb')) def mapping_translate(mapping_name, file): """Prints the list of known mappings.""" mapping_cls = [cls for cls in metadata_dictionary.MAPPINGS.values() if cls.name == mapping_name] if not mapping_cls: raise click.ClickException('Unknown mapping {}'.format(mapping_name)) assert len(mapping_cls) == 1 mapping_cls = mapping_cls[0] mapping = mapping_cls() codemeta_doc = mapping.translate(file.read()) click.echo(json.dumps(codemeta_doc, indent=4)) @cli.group('schedule') @click.option('--scheduler-url', '-s', default=None, help="URL of the scheduler API") @click.option('--indexer-storage-url', '-i', default=None, help="URL of the indexer storage API") @click.option('--storage-url', '-g', default=None, help="URL of the (graph) storage API") @click.option('--dry-run/--no-dry-run', is_flag=True, default=False, help='List only what would be scheduled.') @click.pass_context def schedule(ctx, scheduler_url, storage_url, indexer_storage_url, dry_run): """Manipulate Software Heritage Indexer tasks. Via SWH Scheduler's API.""" ctx.obj['indexer_storage'] = _get_api( get_indexer_storage, ctx.obj['config'], 'indexer_storage', indexer_storage_url ) ctx.obj['storage'] = _get_api( get_storage, ctx.obj['config'], 'storage', storage_url ) ctx.obj['scheduler'] = _get_api( get_scheduler, ctx.obj['config'], 'scheduler', scheduler_url ) if dry_run: ctx.obj['scheduler'] = None def list_origins_by_producer(idx_storage, mappings, tool_ids): - start = 0 + start = '' limit = 10000 while True: origins = list( idx_storage.origin_intrinsic_metadata_search_by_producer( start=start, limit=limit, ids_only=True, mappings=mappings or None, tool_ids=tool_ids or None)) if not origins: break - start = origins[-1]+1 + start = origins[-1] + '\x00' # first possible string after this yield from origins @schedule.command('reindex_origin_metadata') @click.option('--batch-size', '-b', 'origin_batch_size', default=10, show_default=True, type=int, help="Number of origins per task") @click.option('--tool-id', '-t', 'tool_ids', type=int, multiple=True, help="Restrict search of old metadata to this/these tool ids.") @click.option('--mapping', '-m', 'mappings', multiple=True, help="Mapping(s) that should be re-scheduled (eg. 'npm', " "'gemspec', 'maven')") @click.option('--task-type', default='index-origin-metadata', show_default=True, help="Name of the task type to schedule.") @click.pass_context def schedule_origin_metadata_reindex( ctx, origin_batch_size, tool_ids, mappings, task_type): """Schedules indexing tasks for origins that were already indexed.""" idx_storage = ctx.obj['indexer_storage'] scheduler = ctx.obj['scheduler'] origins = list_origins_by_producer(idx_storage, mappings, tool_ids) kwargs = {"policy_update": "update-dups"} schedule_origin_batches( scheduler, task_type, origins, origin_batch_size, kwargs) @cli.command('journal-client') @click.option('--scheduler-url', '-s', default=None, help="URL of the scheduler API") @click.option('--origin-metadata-task-type', default='index-origin-metadata', help='Name of the task running the origin metadata indexer.') @click.option('--broker', 'brokers', type=str, multiple=True, help='Kafka broker to connect to.') @click.option('--prefix', type=str, default=None, help='Prefix of Kafka topic names to read from.') @click.option('--group-id', type=str, help='Consumer/group id for reading from Kafka.') @click.option('--max-messages', '-m', default=None, type=int, help='Maximum number of objects to replay. Default is to ' 'run forever.') @click.pass_context def journal_client(ctx, scheduler_url, origin_metadata_task_type, brokers, prefix, group_id, max_messages): """Listens for new objects from the SWH Journal, and schedules tasks to run relevant indexers (currently, only origin-intrinsic-metadata) on these new objects.""" scheduler = _get_api( get_scheduler, ctx.obj['config'], 'scheduler', scheduler_url ) client = get_journal_client( ctx, brokers=brokers, prefix=prefix, group_id=group_id, - object_types=['origin_visit']) + object_types=['origin_visit'], + max_messages=max_messages, + ) worker_fn = functools.partial( process_journal_objects, scheduler=scheduler, task_names={ 'origin_metadata': origin_metadata_task_type, } ) nb_messages = 0 last_log_time = 0 try: while not max_messages or nb_messages < max_messages: nb_messages += client.process(worker_fn) if time.monotonic() - last_log_time >= 60: print('Processed %d messages.' % nb_messages) last_log_time = time.monotonic() except KeyboardInterrupt: ctx.exit(0) else: print('Done.') @cli.command('rpc-serve') -@click.argument('config-path', required=1) +@click.argument('config-path', required=True) @click.option('--host', default='0.0.0.0', help="Host to run the server") @click.option('--port', default=5007, type=click.INT, help="Binding port of the server") @click.option('--debug/--nodebug', default=True, help="Indicates if the server should run in debug mode") def rpc_server(config_path, host, port, debug): """Starts a Software Heritage Indexer RPC HTTP server.""" api_cfg = load_and_check_config(config_path, type='any') app.config.update(api_cfg) app.run(host, port=int(port), debug=bool(debug)) def main(): return cli(auto_envvar_prefix='SWH_INDEXER') if __name__ == '__main__': main() diff --git a/swh/indexer/fossology_license.py b/swh/indexer/fossology_license.py index 017d918..ed9a431 100644 --- a/swh/indexer/fossology_license.py +++ b/swh/indexer/fossology_license.py @@ -1,172 +1,173 @@ # 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 subprocess -from swh.model import hashutil +from typing import Optional +from swh.model import hashutil from .indexer import ContentIndexer, ContentRangeIndexer, write_to_temp def compute_license(path, log=None): """Determine license from file at path. Args: path: filepath to determine the license Returns: dict: A dict with the following keys: - licenses ([str]): associated detected licenses to path - path (bytes): content filepath """ try: properties = subprocess.check_output(['nomossa', path], universal_newlines=True) if properties: res = properties.rstrip().split(' contains license(s) ') licenses = res[1].split(',') else: licenses = [] return { 'licenses': licenses, 'path': path, } except subprocess.CalledProcessError: if log: from os import path as __path log.exception('Problem during license detection for sha1 %s' % __path.basename(path)) return { 'licenses': [], 'path': path, } class MixinFossologyLicenseIndexer: """Mixin fossology license indexer. See :class:`FossologyLicenseIndexer` and :class:`FossologyLicenseRangeIndexer` """ ADDITIONAL_CONFIG = { 'workdir': ('str', '/tmp/swh/indexer.fossology.license'), 'tools': ('dict', { 'name': 'nomos', 'version': '3.1.0rc2-31-ga2cbb8c', 'configuration': { 'command_line': 'nomossa ', }, }), 'write_batch_size': ('int', 1000), } - CONFIG_BASE_FILENAME = 'indexer/fossology_license' + CONFIG_BASE_FILENAME = 'indexer/fossology_license' # type: Optional[str] def prepare(self): super().prepare() self.working_directory = self.config['workdir'] def index(self, id, data): """Index sha1s' content and store result. Args: id (bytes): content's identifier raw_content (bytes): associated raw content to content id Returns: dict: A dict, representing a content_license, with keys: - id (bytes): content's identifier (sha1) - license (bytes): license in bytes - path (bytes): path - indexer_configuration_id (int): tool used to compute the output """ assert isinstance(id, bytes) with write_to_temp( filename=hashutil.hash_to_hex(id), # use the id as pathname data=data, working_directory=self.working_directory) as content_path: properties = compute_license(path=content_path, log=self.log) properties.update({ 'id': id, 'indexer_configuration_id': self.tool['id'], }) return properties def persist_index_computations(self, results, policy_update): """Persist the results in storage. Args: results ([dict]): list of content_license, dict with the following keys: - id (bytes): content's identifier (sha1) - license (bytes): license in bytes - path (bytes): path policy_update ([str]): either 'update-dups' or 'ignore-dups' to respectively update duplicates or ignore them """ self.idx_storage.content_fossology_license_add( results, conflict_update=(policy_update == 'update-dups')) class FossologyLicenseIndexer( MixinFossologyLicenseIndexer, ContentIndexer): """Indexer in charge of: - filtering out content already indexed - reading content from objstorage per the content's id (sha1) - computing {license, encoding} from that content - store result in storage """ def filter(self, ids): """Filter out known sha1s and return only missing ones. """ yield from self.idx_storage.content_fossology_license_missing(( { 'id': sha1, 'indexer_configuration_id': self.tool['id'], } for sha1 in ids )) class FossologyLicenseRangeIndexer( MixinFossologyLicenseIndexer, ContentRangeIndexer): """FossologyLicense Range Indexer working on range of content identifiers. - filters out the non textual content - (optionally) filters out content already indexed (cf :meth:`.indexed_contents_in_range`) - reads content from objstorage per the content's id (sha1) - computes {mimetype, encoding} from that content - stores result in storage """ def indexed_contents_in_range(self, start, end): """Retrieve indexed content id within range [start, end]. Args: start (bytes): Starting bound from range identifier end (bytes): End range identifier Returns: dict: 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.idx_storage.content_fossology_license_get_range( start, end, self.tool['id']) diff --git a/swh/indexer/indexer.py b/swh/indexer/indexer.py index 867e9ed..1bc69fc 100644 --- a/swh/indexer/indexer.py +++ b/swh/indexer/indexer.py @@ -1,620 +1,621 @@ # 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 contextlib import contextmanager +from typing import Any, Dict, Tuple from swh.scheduler import get_scheduler from swh.scheduler import CONFIG as SWH_CONFIG 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 @contextmanager def write_to_temp(filename, data, working_directory): """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(working_directory, exist_ok=True) temp_dir = tempfile.mkdtemp(dir=working_directory) content_path = os.path.join(temp_dir, filename) with open(content_path, 'wb') as f: f.write(data) yield 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: :meth:`~BaseIndexer.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: :meth:`~BaseIndexer.filter`: filter out data already indexed (in storage). :meth:`~BaseIndexer.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. :meth:`~BaseIndexer.persist_index_computations`: persist the results of multiple index computations in the storage. The new indexer implementation can also override the following functions: :meth:`~BaseIndexer.prepare`: Configuration preparation for the indexer. When overriding, this must call the `super().prepare()` instruction. :meth:`~BaseIndexer.check`: Configuration check for the indexer. When overriding, this must call the `super().check()` instruction. :meth:`~BaseIndexer.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 = {} + ADDITIONAL_CONFIG = {} # type: Dict[str, Tuple[str, Any]] USE_TOOLS = True catch_exceptions = True """Prevents exceptions in `index()` from raising too high. Set to False in tests to properly catch all exceptions.""" def __init__(self, config=None, **kw): """Prepare and check that the indexer is ready to run. """ super().__init__() if config is not None: self.config = config elif SWH_CONFIG: self.config = SWH_CONFIG.copy() else: config_keys = ('base_filename', 'config_filename', 'additional_configs', 'global_config') config_args = {k: v for k, v in kw.items() if k in config_keys} if self.ADDITIONAL_CONFIG: config_args.setdefault('additional_configs', []).append( self.ADDITIONAL_CONFIG) self.config = self.parse_config_file(**config_args) self.prepare() self.check() self.log.debug('%s: config=%s', self, self.config) def prepare(self): """Prepare the indexer's needed runtime configuration. Without this step, the indexer cannot possibly run. """ config_storage = self.config.get('storage') if config_storage: self.storage = get_storage(**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') if self.USE_TOOLS: self.tools = list(self.register_tools( self.config.get('tools', []))) self.results = [] @property def tool(self): return self.tools[0] def check(self): """Check the indexer's configuration is ok before proceeding. If ok, does nothing. If not raise error. """ if self.USE_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: List of dicts with additional id key. Raises: ValueError: if not a list nor a dict. """ if isinstance(tools, list): tools = list(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!') if tools: return self.idx_storage.indexer_configuration_add(tools) else: return [] 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: dict: a dict that makes sense for the :meth:`.persist_index_computations` method. """ raise NotImplementedError() def filter(self, ids): """Filter missing ids for that particular indexer. Args: ids ([bytes]): list of ids Yields: iterator of missing ids """ yield from ids @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 an optional `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', None) task['next_run'] = datetime.datetime.now() if result_name: 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. """ 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 (Iterable[Union[bytes, str]]): 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 an optional `result_name` key. **kwargs: passed to the `index` method """ ids = [hashutil.hash_to_bytes(id_) if isinstance(id_, str) else id_ for id_ in ids] 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: if not self.catch_exceptions: raise 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: bytes: Content identifier 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: bytes: Identifier of contents to index. """ if not isinstance(start, bytes) or not isinstance(end, bytes): raise TypeError('identifiers must be bytes, not %r and %r.' % (start, end)) while start: result = self.storage.content_get_range(start, end) contents = result['contents'] for c in contents: _id = hashutil.hash_to_bytes(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: dict: Data indexed 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: if not isinstance(res['id'], bytes): raise TypeError( '%r.index should return ids as bytes, not %r' % (self.__class__.__name__, res['id'])) yield res def _index_with_skipping_already_done(self, start, end): """Index not already indexed contents in range [start, end]. Args: start** (Union[bytes, str]): Starting range identifier end (Union[bytes, str]): Ending range identifier Yields: bytes: Content identifier present in the range ``[start, end]`` which are not already indexed. """ while start: indexed_page = self.indexed_contents_in_range(start, end) contents = indexed_page['ids'] _end = contents[-1] if contents else end yield from self._index_contents( start, _end, contents) start = indexed_page['next'] 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: bool: 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: gen = self._index_with_skipping_already_done(start, end) else: gen = self._index_contents(start, end, indexed=[]) for results in utils.grouper(gen, n=self.config['write_batch_size']): self.persist_index_computations( results, policy_update='update-dups') with_indexed_data = True except Exception: if not self.catch_exceptions: raise self.log.exception( 'Problem when computing metadata.') finally: return with_indexed_data 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, origin_urls, policy_update='update-dups', next_step=None, **kwargs): - """Given a list of origin ids: + """Given a list of origin urls: - 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. + origin_urls ([str]): list of origin urls. 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 an optional `result_name` key. parse_ids (bool): Do we need to parse id or not (default) **kwargs: passed to the `index` method """ results = self.index_list(origin_urls, **kwargs) self.persist_index_computations(results, policy_update) self.results = results return self.next_step(results, task=next_step) def index_list(self, origins, **kwargs): results = [] for origin in origins: try: res = self.index(origin, **kwargs) if res: # If no results, skip it results.append(res) except Exception: if not self.catch_exceptions: raise self.log.exception( 'Problem when processing origin %s', origin['id']) return results 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 = [hashutil.hash_to_bytes(id_) 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: if not self.catch_exceptions: raise 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 ecb097a..2900221 100644 --- a/swh/indexer/metadata.py +++ b/swh/indexer/metadata.py @@ -1,356 +1,354 @@ # 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 copy import deepcopy from swh.core.utils import grouper from swh.indexer.codemeta import merge_documents from swh.indexer.indexer import ContentIndexer, RevisionIndexer, OriginIndexer from swh.indexer.origin_head import OriginHeadIndexer from swh.indexer.metadata_dictionary import MAPPINGS from swh.indexer.metadata_detector import detect_metadata from swh.indexer.storage import INDEXER_CFG_KEY from swh.model import hashutil REVISION_GET_BATCH_SIZE = 10 ORIGIN_GET_BATCH_SIZE = 10 def call_with_batches(f, args, batch_size): """Calls a function with batches of args, and concatenates the results. """ groups = grouper(args, batch_size) for group in groups: yield from f(list(group)) 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 metadata by given context - using the metadata_dictionary as the 'swh-metadata-translator' tool - store result in content_metadata table """ 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, log_suffix='unknown revision'): """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 metadata keys will be returned as None """ result = { 'id': id, 'indexer_configuration_id': self.tool['id'], 'metadata': None } try: mapping_name = self.tool['tool_configuration']['context'] log_suffix += ', content_id=%s' % hashutil.hash_to_hex(id) result['metadata'] = \ MAPPINGS[mapping_name](log_suffix).translate(data) except Exception: self.log.exception( "Problem during metadata translation " "for content %s" % hashutil.hash_to_hex(id)) if result['metadata'] is None: return None 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) - 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')) class RevisionMetadataIndexer(RevisionIndexer): """Revision-level indexer This indexer is in charge of: - filtering revisions already indexed in revision_intrinsic_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 """ ADDITIONAL_CONFIG = { 'tools': ('dict', { 'name': 'swh-metadata-detector', 'version': '0.0.2', 'configuration': { }, }), } def filter(self, sha1_gits): """Filter out known sha1s and return only missing ones. """ yield from self.idx_storage.revision_intrinsic_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 (dict): revision artifact from storage Returns: dict: dictionary representing a revision_intrinsic_metadata, with keys: - id (str): rev's identifier (sha1_git) - indexer_configuration_id (bytes): tool used - metadata: dict of retrieved metadata """ result = { 'id': rev['id'], 'indexer_configuration_id': self.tool['id'], 'mappings': None, 'metadata': None } try: root_dir = rev['directory'] dir_ls = list(self.storage.directory_ls(root_dir, recursive=False)) if [entry['type'] for entry in dir_ls] == ['dir']: # If the root is just a single directory, recurse into it # eg. PyPI packages, GNU tarballs subdir = dir_ls[0]['target'] dir_ls = self.storage.directory_ls(subdir, recursive=False) files = [entry for entry in dir_ls if entry['type'] == 'file'] detected_files = detect_metadata(files) (mappings, metadata) = self.translate_revision_intrinsic_metadata( detected_files, log_suffix='revision=%s' % hashutil.hash_to_hex(rev['id'])) result['mappings'] = mappings result['metadata'] = metadata 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_intrinsic_metadata self.idx_storage.revision_intrinsic_metadata_add( results, conflict_update=(policy_update == 'update-dups')) def translate_revision_intrinsic_metadata( self, detected_files, log_suffix): """ 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: (List[str], dict): list of mappings used and dict with translated metadata according to the CodeMeta vocabulary """ used_mappings = [MAPPINGS[context].name for context in detected_files] metadata = [] tool = { 'name': 'swh-metadata-translator', 'version': '0.0.2', 'configuration': { }, } # TODO: iterate on each context, on each file # -> get raw_contents # -> translate each content config = { k: self.config[k] for k in [INDEXER_CFG_KEY, 'objstorage', 'storage'] } config['tools'] = [tool] for context in detected_files.keys(): cfg = deepcopy(config) cfg['tools'][0]['configuration']['context'] = context c_metadata_indexer = ContentMetadataIndexer(config=cfg) # 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 metadata sha1 = c['id'] sha1s_in_storage.append(sha1) local_metadata = c['metadata'] # local metadata is aggregated if local_metadata: metadata.append(local_metadata) sha1s_filtered = [item for item in detected_files[context] if item not in sha1s_in_storage] if sha1s_filtered: # content indexing try: c_metadata_indexer.run(sha1s_filtered, policy_update='ignore-dups', log_suffix=log_suffix) # on the fly possibility: for result in c_metadata_indexer.results: local_metadata = result['metadata'] metadata.append(local_metadata) except Exception: self.log.exception( "Exception while indexing metadata on contents") metadata = merge_documents(metadata) return (used_mappings, metadata) class OriginMetadataIndexer(OriginIndexer): ADDITIONAL_CONFIG = RevisionMetadataIndexer.ADDITIONAL_CONFIG USE_TOOLS = False def __init__(self, config=None, **kwargs): super().__init__(config=config, **kwargs) self.origin_head_indexer = OriginHeadIndexer(config=config) self.revision_metadata_indexer = RevisionMetadataIndexer(config=config) def index_list(self, origin_urls): head_rev_ids = [] origins_with_head = [] origins = list(call_with_batches( self.storage.origin_get, [{'url': url} for url in origin_urls], ORIGIN_GET_BATCH_SIZE)) for origin in origins: head_result = self.origin_head_indexer.index(origin['url']) if head_result: - head_result['origin_id'] = origin['id'] origins_with_head.append(origin) head_rev_ids.append(head_result['revision_id']) head_revs = list(call_with_batches( self.storage.revision_get, head_rev_ids, REVISION_GET_BATCH_SIZE)) assert len(head_revs) == len(head_rev_ids) results = [] for (origin, rev) in zip(origins_with_head, head_revs): if not rev: self.log.warning('Missing head revision of origin %r', origin['url']) continue rev_metadata = self.revision_metadata_indexer.index(rev) orig_metadata = { 'from_revision': rev_metadata['id'], - 'id': origin['id'], - 'origin_url': origin['url'], + 'id': origin['url'], 'metadata': rev_metadata['metadata'], 'mappings': rev_metadata['mappings'], 'indexer_configuration_id': rev_metadata['indexer_configuration_id'], } results.append((orig_metadata, rev_metadata)) return results def persist_index_computations(self, results, policy_update): conflict_update = (policy_update == 'update-dups') # Deduplicate revisions rev_metadata = [] orig_metadata = [] revs_to_delete = [] origs_to_delete = [] for (orig_item, rev_item) in results: assert rev_item['metadata'] == orig_item['metadata'] if not rev_item['metadata'] or \ rev_item['metadata'].keys() <= {'@context'}: # If we didn't find any metadata, don't store a DB record # (and delete existing ones, if any) if rev_item not in revs_to_delete: revs_to_delete.append(rev_item) if orig_item not in origs_to_delete: origs_to_delete.append(orig_item) else: if rev_item not in rev_metadata: rev_metadata.append(rev_item) if orig_item not in orig_metadata: orig_metadata.append(orig_item) if rev_metadata: self.idx_storage.revision_intrinsic_metadata_add( rev_metadata, conflict_update=conflict_update) if orig_metadata: self.idx_storage.origin_intrinsic_metadata_add( orig_metadata, conflict_update=conflict_update) # revs_to_delete should always be empty unless we changed a mapping # to detect less files or less content. # However, origs_to_delete may be empty whenever an upstream deletes # a metadata file. if origs_to_delete: self.idx_storage.origin_intrinsic_metadata_delete(origs_to_delete) if revs_to_delete: self.idx_storage.revision_intrinsic_metadata_delete(revs_to_delete) diff --git a/swh/indexer/metadata_dictionary/base.py b/swh/indexer/metadata_dictionary/base.py index 9bc0ef5..4276dd2 100644 --- a/swh/indexer/metadata_dictionary/base.py +++ b/swh/indexer/metadata_dictionary/base.py @@ -1,211 +1,213 @@ # Copyright (C) 2017-2019 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import abc import json import logging +from typing import List + from swh.indexer.codemeta import SCHEMA_URI from swh.indexer.codemeta import compact def merge_values(v1, v2): """If v1 and v2 are of the form `{"@list": l1}` and `{"@list": l2}`, returns `{"@list": l1 + l2}`. Otherwise, make them lists (if they are not already) and concatenate them. >>> merge_values('a', 'b') ['a', 'b'] >>> merge_values(['a', 'b'], 'c') ['a', 'b', 'c'] >>> merge_values({'@list': ['a', 'b']}, {'@list': ['c']}) {'@list': ['a', 'b', 'c']} """ if v1 is None: return v2 elif v2 is None: return v1 elif isinstance(v1, dict) and set(v1) == {'@list'}: assert isinstance(v1['@list'], list) if isinstance(v2, dict) and set(v2) == {'@list'}: assert isinstance(v2['@list'], list) return {'@list': v1['@list'] + v2['@list']} else: raise ValueError('Cannot merge %r and %r' % (v1, v2)) else: if isinstance(v2, dict) and '@list' in v2: raise ValueError('Cannot merge %r and %r' % (v1, v2)) if not isinstance(v1, list): v1 = [v1] if not isinstance(v2, list): v2 = [v2] return v1 + v2 class BaseMapping(metaclass=abc.ABCMeta): """Base class for mappings to inherit from To implement a new mapping: - inherit this class - override translate function """ def __init__(self, log_suffix=''): self.log_suffix = log_suffix self.log = logging.getLogger('%s.%s' % ( self.__class__.__module__, self.__class__.__name__)) @property @abc.abstractmethod def name(self): """A name of this mapping, used as an identifier in the indexer storage.""" pass @classmethod @abc.abstractmethod def detect_metadata_files(cls, files): """ Detects files potentially containing metadata Args: file_entries (list): list of files Returns: list: list of sha1 (possibly empty) """ pass @abc.abstractmethod def translate(self, file_content): pass def normalize_translation(self, metadata): return compact(metadata) class SingleFileMapping(BaseMapping): """Base class for all mappings that use a single file as input.""" @property @abc.abstractmethod def filename(self): """The .json file to extract metadata from.""" pass @classmethod def detect_metadata_files(cls, file_entries): for entry in file_entries: if entry['name'] == cls.filename: return [entry['sha1']] return [] class DictMapping(BaseMapping): """Base class for mappings that take as input a file that is mostly a key-value store (eg. a shallow JSON dict).""" - string_fields = [] + string_fields = [] # type: List[str] '''List of fields that are simple strings, and don't need any normalization.''' @property @abc.abstractmethod def mapping(self): """A translation dict to map dict keys into a canonical name.""" pass @staticmethod def _normalize_method_name(name): return name.replace('-', '_') @classmethod def supported_terms(cls): return { term for (key, term) in cls.mapping.items() if key in cls.string_fields or hasattr(cls, 'translate_' + cls._normalize_method_name(key)) or hasattr(cls, 'normalize_' + cls._normalize_method_name(key))} def _translate_dict(self, content_dict, *, normalize=True): """ Translates content by parsing content from a dict object and translating with the appropriate mapping Args: content_dict (dict): content dict to translate Returns: dict: translated metadata in json-friendly form needed for the indexer """ translated_metadata = {'@type': SCHEMA_URI + 'SoftwareSourceCode'} for k, v in content_dict.items(): # First, check if there is a specific translation # method for this key translation_method = getattr( self, 'translate_' + self._normalize_method_name(k), None) if translation_method: translation_method(translated_metadata, v) elif k in self.mapping: # if there is no method, but the key is known from the # crosswalk table codemeta_key = self.mapping[k] # if there is a normalization method, use it on the value normalization_method = getattr( self, 'normalize_' + self._normalize_method_name(k), None) if normalization_method: v = normalization_method(v) elif k in self.string_fields and isinstance(v, str): pass elif k in self.string_fields and isinstance(v, list): v = [x for x in v if isinstance(x, str)] else: continue # set the translation metadata with the normalized value if codemeta_key in translated_metadata: translated_metadata[codemeta_key] = merge_values( translated_metadata[codemeta_key], v) else: translated_metadata[codemeta_key] = v if normalize: return self.normalize_translation(translated_metadata) else: return translated_metadata class JsonMapping(DictMapping, SingleFileMapping): """Base class for all mappings that use a JSON file as input.""" def translate(self, raw_content): """ Translates content by parsing content from a bytestring containing json data and translating with the appropriate mapping Args: raw_content (bytes): raw content to translate Returns: dict: translated metadata in json-friendly form needed for the indexer """ try: raw_content = raw_content.decode() except UnicodeDecodeError: self.log.warning('Error unidecoding from %s', self.log_suffix) return try: content_dict = json.loads(raw_content) except json.JSONDecodeError: self.log.warning('Error unjsoning from %s', self.log_suffix) return if isinstance(content_dict, dict): return self._translate_dict(content_dict) diff --git a/swh/indexer/mimetype.py b/swh/indexer/mimetype.py index afe700e..d8dda33 100644 --- a/swh/indexer/mimetype.py +++ b/swh/indexer/mimetype.py @@ -1,145 +1,147 @@ # 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 magic +from typing import Optional + from .indexer import ContentIndexer, ContentRangeIndexer if not hasattr(magic.Magic, 'from_buffer'): raise ImportError( 'Expected "import magic" to import python-magic, but file_magic ' 'was imported instead.') def compute_mimetype_encoding(raw_content): """Determine mimetype and encoding from the raw content. Args: raw_content (bytes): content's raw data Returns: dict: mimetype and encoding key and corresponding values (as bytes). """ m = magic.Magic(mime=True, mime_encoding=True) res = m.from_buffer(raw_content) (mimetype, encoding) = res.split('; charset=') return { 'mimetype': mimetype, 'encoding': encoding, } class MixinMimetypeIndexer: """Mixin mimetype indexer. See :class:`MimetypeIndexer` and :class:`MimetypeRangeIndexer` """ ADDITIONAL_CONFIG = { 'tools': ('dict', { 'name': 'file', 'version': '1:5.30-1+deb9u1', 'configuration': { "type": "library", "debian-package": "python3-magic" }, }), 'write_batch_size': ('int', 1000), } - CONFIG_BASE_FILENAME = 'indexer/mimetype' + CONFIG_BASE_FILENAME = 'indexer/mimetype' # type: Optional[str] 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: content's mimetype; dict keys being - **id** (bytes): content's identifier (sha1) - **mimetype** (bytes): mimetype in bytes - **encoding** (bytes): encoding in bytes """ properties = compute_mimetype_encoding(data) properties.update({ 'id': id, 'indexer_configuration_id': self.tool['id'], }) return properties def persist_index_computations(self, results, policy_update): """Persist the results in storage. Args: results ([dict]): list of content's mimetype dicts (see :meth:`.index`) policy_update ([str]): either 'update-dups' or 'ignore-dups' to respectively update duplicates or ignore them """ self.idx_storage.content_mimetype_add( results, conflict_update=(policy_update == 'update-dups')) class MimetypeIndexer(MixinMimetypeIndexer, ContentIndexer): """Mimetype Indexer working on list of content identifiers. It: - (optionally) filters out content already indexed (cf. :meth:`.filter`) - reads content from objstorage per the content's id (sha1) - computes {mimetype, encoding} from that content - stores result in storage """ def filter(self, ids): """Filter out known sha1s and return only missing ones. """ yield from self.idx_storage.content_mimetype_missing(( { 'id': sha1, 'indexer_configuration_id': self.tool['id'], } for sha1 in ids )) class MimetypeRangeIndexer(MixinMimetypeIndexer, ContentRangeIndexer): """Mimetype Range Indexer working on range of content identifiers. It: - (optionally) filters out content already indexed (cf :meth:`.indexed_contents_in_range`) - reads content from objstorage per the content's id (sha1) - computes {mimetype, encoding} from that content - stores result in storage """ def indexed_contents_in_range(self, start, end): """Retrieve indexed content id within range [start, end]. Args: start (bytes): Starting bound from range identifier end (bytes): End range identifier Returns: dict: 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.idx_storage.content_mimetype_get_range( start, end, self.tool['id']) diff --git a/swh/indexer/py.typed b/swh/indexer/py.typed new file mode 100644 index 0000000..1242d43 --- /dev/null +++ b/swh/indexer/py.typed @@ -0,0 +1 @@ +# Marker file for PEP 561. diff --git a/swh/indexer/sql/30-swh-schema.sql b/swh/indexer/sql/30-swh-schema.sql index af05499..ee66dbe 100644 --- a/swh/indexer/sql/30-swh-schema.sql +++ b/swh/indexer/sql/30-swh-schema.sql @@ -1,146 +1,145 @@ --- --- 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(126, now(), 'Work In Progress'); + values(127, 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 text not null, encoding text 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, 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.metadata is 'result of translation with defined format'; comment on column content_metadata.indexer_configuration_id is 'tool used for translation'; -- The table revision_intrinsic_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_intrinsic_metadata( id sha1_git not null, metadata jsonb not null, indexer_configuration_id bigint not null, mappings text array not null ); comment on table revision_intrinsic_metadata is 'metadata semantically detected and translated in a revision'; comment on column revision_intrinsic_metadata.id is 'sha1_git of revision'; comment on column revision_intrinsic_metadata.metadata is 'result of detection and translation with defined format'; comment on column revision_intrinsic_metadata.indexer_configuration_id is 'tool used for detection'; comment on column revision_intrinsic_metadata.mappings is 'type of metadata files used to obtain this metadata (eg. pkg-info, npm)'; create table origin_intrinsic_metadata( - id bigserial not null, - origin_url text, + id text not null, -- origin url metadata jsonb, indexer_configuration_id bigint not null, from_revision sha1_git not null, metadata_tsvector tsvector, mappings text array not null ); comment on table origin_intrinsic_metadata is 'keeps intrinsic metadata for an origin'; -comment on column origin_intrinsic_metadata.id is 'the entry id in origin'; +comment on column origin_intrinsic_metadata.id is 'url of the 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.'; comment on column origin_intrinsic_metadata.mappings is 'type of metadata files used to obtain this metadata (eg. pkg-info, npm)'; diff --git a/swh/indexer/sql/40-swh-func.sql b/swh/indexer/sql/40-swh-func.sql index 69d0c05..31ab57c 100644 --- a/swh/indexer/sql/40-swh-func.sql +++ b/swh/indexer/sql/40-swh-func.sql @@ -1,456 +1,454 @@ -- 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 $$ begin if conflict_update then insert into content_metadata (id, metadata, indexer_configuration_id) select id, metadata, indexer_configuration_id from tmp_content_metadata tcm on conflict(id, indexer_configuration_id) do update set metadata = excluded.metadata; else insert into content_metadata (id, metadata, indexer_configuration_id) select id, metadata, indexer_configuration_id from tmp_content_metadata tcm on conflict(id, indexer_configuration_id) do nothing; end if; return; end $$; 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_intrinsic_metadata entries to revision_intrinsic_metadata, -- overwriting duplicates if conflict_update is true, skipping duplicates -- otherwise. -- -- If filtering duplicates is in order, the call to -- swh_revision_intrinsic_metadata_missing must take place before calling this -- function. -- -- operates in bulk: 0. swh_mktemp(content_language), 1. COPY to -- tmp_revision_intrinsic_metadata, 2. call this function create or replace function swh_revision_intrinsic_metadata_add(conflict_update boolean) returns void language plpgsql as $$ begin if conflict_update then insert into revision_intrinsic_metadata (id, metadata, mappings, indexer_configuration_id) select id, metadata, mappings, indexer_configuration_id from tmp_revision_intrinsic_metadata tcm on conflict(id, indexer_configuration_id) do update set metadata = excluded.metadata, mappings = excluded.mappings; else insert into revision_intrinsic_metadata (id, metadata, mappings, indexer_configuration_id) select id, metadata, mappings, indexer_configuration_id from tmp_revision_intrinsic_metadata tcm on conflict(id, indexer_configuration_id) do nothing; end if; return; end $$; comment on function swh_revision_intrinsic_metadata_add(boolean) IS 'Add new revision intrinsic metadata'; -- create a temporary table for retrieving revision_intrinsic_metadata create or replace function swh_mktemp_revision_intrinsic_metadata() returns void language sql as $$ create temporary table tmp_revision_intrinsic_metadata ( like revision_intrinsic_metadata including defaults ) on commit drop; $$; comment on function swh_mktemp_revision_intrinsic_metadata() is 'Helper table to add revision intrinsic 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 $$ begin perform swh_origin_intrinsic_metadata_compute_tsvector(); if conflict_update then - insert into origin_intrinsic_metadata (id, origin_url, metadata, indexer_configuration_id, from_revision, metadata_tsvector, mappings) - select id, origin_url, metadata, indexer_configuration_id, from_revision, + insert into origin_intrinsic_metadata (id, metadata, indexer_configuration_id, from_revision, metadata_tsvector, mappings) + select id, metadata, indexer_configuration_id, from_revision, metadata_tsvector, mappings from tmp_origin_intrinsic_metadata on conflict(id, indexer_configuration_id) do update set metadata = excluded.metadata, metadata_tsvector = excluded.metadata_tsvector, mappings = excluded.mappings, - origin_url = excluded.origin_url, from_revision = excluded.from_revision; else - insert into origin_intrinsic_metadata (id, origin_url, metadata, indexer_configuration_id, from_revision, metadata_tsvector, mappings) - select id, origin_url, metadata, indexer_configuration_id, from_revision, + insert into origin_intrinsic_metadata (id, metadata, indexer_configuration_id, from_revision, metadata_tsvector, mappings) + select id, metadata, indexer_configuration_id, from_revision, metadata_tsvector, mappings from tmp_origin_intrinsic_metadata on conflict(id, indexer_configuration_id) do nothing; end if; return; end $$; comment on function swh_origin_intrinsic_metadata_add(boolean) IS 'Add new origin intrinsic metadata'; -- 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 $$ begin update tmp_origin_intrinsic_metadata set metadata_tsvector = to_tsvector('pg_catalog.simple', metadata); end $$; - diff --git a/swh/indexer/storage/__init__.py b/swh/indexer/storage/__init__.py index 7f00ea2..d90350d 100644 --- a/swh/indexer/storage/__init__.py +++ b/swh/indexer/storage/__init__.py @@ -1,928 +1,924 @@ # 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' MAPPING_NAMES = ['codemeta', 'gemspec', 'maven', 'npm', 'pkg-info'] def get_indexer_storage(cls, args): """Get an indexer storage object of class `storage_class` with arguments `storage_args`. Args: cls (str): storage's class, either 'local' or 'remote' args (dict): dictionary of arguments passed to the storage class constructor Returns: an instance of swh.indexer's storage (either local or remote) Raises: ValueError if passed an unknown storage class. """ if cls == 'remote': from .api.client import RemoteStorage as IndexerStorage elif cls == 'local': from . import IndexerStorage elif cls == 'memory': from .in_memory import IndexerStorage else: raise ValueError('Unknown indexer storage class `%s`' % cls) return IndexerStorage(**args) def _check_id_duplicates(data): """ If any two dictionaries in `data` have the same id, raises a `ValueError`. Values associated to the key must be hashable. Args: data (List[dict]): List of dictionaries to be inserted >>> _check_id_duplicates([ ... {'id': 'foo', 'data': 'spam'}, ... {'id': 'bar', 'data': 'egg'}, ... ]) >>> _check_id_duplicates([ ... {'id': 'foo', 'data': 'spam'}, ... {'id': 'foo', 'data': 'egg'}, ... ]) Traceback (most recent call last): ... ValueError: The same id is present more than once. """ if len({item['id'] for item in data}) < len(data): raise ValueError('The same id is present more than once.') 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) def put_db(self, db): if db is not self._db: db.put_conn() @remote_api_endpoint('check_config') @db_transaction() def check_config(self, *, check_write, db=None, cur=None): """Check that the storage is configured and ready to go.""" # Check permissions on one of the tables 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] @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) """ _check_id_duplicates(mimetypes) mimetypes.sort(key=lambda m: m['id']) 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) """ _check_id_duplicates(languages) languages.sort(key=lambda m: m['id']) db.mktemp_content_language(cur) # empty language is mapped to 'unknown' db.copy_to( ({ 'id': l['id'], 'lang': 'unknown' if not l['lang'] else l['lang'], 'indexer_configuration_id': l['indexer_configuration_id'], } for l in languages), 'tmp_content_language', ['id', 'lang', 'indexer_configuration_id'], cur) db.content_language_add_from_temp(conflict_update, cur) @remote_api_endpoint('content/ctags/missing') @db_transaction_generator() def content_ctags_missing(self, ctags, db=None, cur=None): """List ctags missing from storage. Args: ctags (iterable): dicts with keys: - **id** (bytes): sha1 identifier - **indexer_configuration_id** (int): tool used to compute the results Yields: an iterable of missing id for the tuple (id, indexer_configuration_id) """ for obj in db.content_ctags_missing_from_list(ctags, cur): yield obj[0] @remote_api_endpoint('content/ctags') @db_transaction_generator() def content_ctags_get(self, ids, db=None, cur=None): """Retrieve ctags per id. Args: ids (iterable): sha1 checksums Yields: Dictionaries with keys: - **id** (bytes): content's identifier - **name** (str): symbol's name - **kind** (str): symbol's kind - **lang** (str): language for that content - **tool** (dict): tool used to compute the ctags' info """ for c in db.content_ctags_get_from_list(ids, cur): yield converters.db_to_ctags(dict(zip(db.content_ctags_cols, c))) @remote_api_endpoint('content/ctags/add') @db_transaction() def content_ctags_add(self, ctags, conflict_update=False, db=None, cur=None): """Add ctags not present in storage Args: ctags (iterable): dictionaries with keys: - **id** (bytes): sha1 - **ctags** ([list): List of dictionary with keys: name, kind, line, lang """ _check_id_duplicates(ctags) ctags.sort(key=lambda m: m['id']) 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: dict: ``{id: facts}`` where ``facts`` is a dict with the following keys: - **licenses** ([str]): associated licenses for that content - **tool** (dict): Tool used to compute the license """ d = defaultdict(list) for c in db.content_fossology_license_get_from_list(ids, cur): license = dict(zip(db.content_fossology_license_cols, c)) id_ = license['id'] d[id_].append(converters.db_to_fossology_license(license)) for id_, facts in d.items(): yield {id_: facts} @remote_api_endpoint('content/fossology_license/add') @db_transaction() def content_fossology_license_add(self, licenses, conflict_update=False, db=None, cur=None): """Add licenses not present in storage. Args: licenses (iterable): dictionaries with keys: - **id**: sha1 - **licenses** ([bytes]): List of licenses associated to sha1 - **tool** (str): nomossa conflict_update: Flag to determine if we want to overwrite (true) or skip duplicates (false, the default) Returns: list: content_license entries which failed due to unknown licenses """ _check_id_duplicates(licenses) licenses.sort(key=lambda m: m['id']) db.mktemp_content_fossology_license(cur) db.copy_to( ({ 'id': sha1['id'], 'indexer_configuration_id': sha1['indexer_configuration_id'], 'license': license, } for sha1 in licenses for license in sha1['licenses']), tblname='tmp_content_fossology_license', columns=['id', 'license', 'indexer_configuration_id'], cur=cur) db.content_fossology_license_add_from_temp(conflict_update, cur) @remote_api_endpoint('content/fossology_license/range') @db_transaction() def content_fossology_license_get_range( self, start, end, indexer_configuration_id, limit=1000, db=None, cur=None): """Retrieve licenses within range [start, end] bound by limit. Args: **start** (bytes): Starting identifier range (expected smaller than end) **end** (bytes): Ending identifier range (expected larger than start) **indexer_configuration_id** (int): The tool used to index data **limit** (int): Limit result (default to 1000) Raises: ValueError for limit to None Returns: a dict with keys: - **ids** [bytes]: iterable of content ids within the range. - **next** (Optional[bytes]): The next range of sha1 starts at this sha1 if any """ return self._content_get_range('fossology_license', start, end, indexer_configuration_id, limit=limit, with_textual_data=True, db=db, cur=cur) @remote_api_endpoint('content_metadata/missing') @db_transaction_generator() def content_metadata_missing(self, metadata, db=None, cur=None): """List metadata missing from storage. Args: metadata (iterable): dictionaries with keys: - **id** (bytes): sha1 identifier - **indexer_configuration_id** (int): tool used to compute the results Yields: missing sha1s """ for obj in db.content_metadata_missing_from_list(metadata, cur): yield obj[0] @remote_api_endpoint('content_metadata') @db_transaction_generator() def content_metadata_get(self, ids, db=None, cur=None): """Retrieve metadata per id. Args: ids (iterable): sha1 checksums Yields: dictionaries with the following keys: id (bytes) 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 - **metadata**: arbitrary dict conflict_update: Flag to determine if we want to overwrite (true) or skip duplicates (false, the default) """ _check_id_duplicates(metadata) metadata.sort(key=lambda m: m['id']) db.mktemp_content_metadata(cur) db.copy_to(metadata, 'tmp_content_metadata', ['id', 'metadata', 'indexer_configuration_id'], cur) db.content_metadata_add_from_temp(conflict_update, cur) @remote_api_endpoint('revision_intrinsic_metadata/missing') @db_transaction_generator() def revision_intrinsic_metadata_missing(self, metadata, db=None, cur=None): """List metadata missing from storage. Args: metadata (iterable): dictionaries with keys: - **id** (bytes): sha1_git revision identifier - **indexer_configuration_id** (int): tool used to compute the results Yields: missing ids """ for obj in db.revision_intrinsic_metadata_missing_from_list( metadata, cur): yield obj[0] @remote_api_endpoint('revision_intrinsic_metadata') @db_transaction_generator() def revision_intrinsic_metadata_get(self, ids, db=None, cur=None): """Retrieve revision metadata per id. Args: ids (iterable): sha1 checksums Yields: dictionaries with the following keys: - **id** (bytes) - **metadata** (str): associated metadata - **tool** (dict): tool used to compute metadata - **mappings** (List[str]): list of mappings used to translate these metadata """ for c in db.revision_intrinsic_metadata_get_from_list(ids, cur): yield converters.db_to_metadata( dict(zip(db.revision_intrinsic_metadata_cols, c))) @remote_api_endpoint('revision_intrinsic_metadata/add') @db_transaction() def revision_intrinsic_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 - **metadata**: arbitrary dict - **indexer_configuration_id**: tool used to compute metadata - **mappings** (List[str]): list of mappings used to translate these metadata conflict_update: Flag to determine if we want to overwrite (true) or skip duplicates (false, the default) """ _check_id_duplicates(metadata) metadata.sort(key=lambda m: m['id']) db.mktemp_revision_intrinsic_metadata(cur) db.copy_to(metadata, 'tmp_revision_intrinsic_metadata', ['id', 'metadata', 'mappings', 'indexer_configuration_id'], cur) db.revision_intrinsic_metadata_add_from_temp(conflict_update, cur) @remote_api_endpoint('revision_intrinsic_metadata/delete') @db_transaction() def revision_intrinsic_metadata_delete(self, entries, db=None, cur=None): """Remove revision metadata from the storage. Args: entries (dict): dictionaries with the following keys: - **id** (bytes): revision identifier - **indexer_configuration_id** (int): tool used to compute metadata """ db.revision_intrinsic_metadata_delete(entries, 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): (legacy) origin identifier - - **origin_url** (str) + - **id** (str): origin url - **from_revision** (bytes): which revision this metadata was extracted from - **metadata** (str): associated metadata - **tool** (dict): tool used to compute metadata - **mappings** (List[str]): list of mappings used to translate these metadata """ for c in db.origin_intrinsic_metadata_get_from_list(ids, cur): yield converters.db_to_metadata( dict(zip(db.origin_intrinsic_metadata_cols, c))) @remote_api_endpoint('origin_intrinsic_metadata/add') @db_transaction() def origin_intrinsic_metadata_add(self, metadata, conflict_update=False, db=None, cur=None): """Add origin metadata not present in storage. Args: metadata (iterable): dictionaries with keys: - - **id**: legacy origin identifier - - **origin_url** + - **id**: origin urls - **from_revision**: sha1 id of the revision used to generate these metadata. - **metadata**: arbitrary dict - **indexer_configuration_id**: tool used to compute metadata - **mappings** (List[str]): list of mappings used to translate these metadata conflict_update: Flag to determine if we want to overwrite (true) or skip duplicates (false, the default) """ _check_id_duplicates(metadata) metadata.sort(key=lambda m: m['id']) db.mktemp_origin_intrinsic_metadata(cur) db.copy_to(metadata, 'tmp_origin_intrinsic_metadata', - ['id', 'origin_url', 'metadata', + ['id', 'metadata', 'indexer_configuration_id', 'from_revision', 'mappings'], cur) db.origin_intrinsic_metadata_add_from_temp(conflict_update, cur) @remote_api_endpoint('origin_intrinsic_metadata/delete') @db_transaction() def origin_intrinsic_metadata_delete( self, entries, db=None, cur=None): """Remove origin metadata from the storage. Args: entries (dict): dictionaries with the following keys: - - **id** (int): origin identifier + - **id** (str): origin urls - **indexer_configuration_id** (int): tool used to compute metadata """ db.origin_intrinsic_metadata_delete(entries, 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): legacy origin identifier - - **origin_url** (str) + - **id** (str): origin urls - **from_revision**: sha1 id of the revision used to generate these metadata. - **metadata** (str): associated metadata - **tool** (dict): tool used to compute metadata - **mappings** (List[str]): list of mappings used to translate these metadata """ for c in db.origin_intrinsic_metadata_search_fulltext( conjunction, limit=limit, cur=cur): yield converters.db_to_metadata( dict(zip(db.origin_intrinsic_metadata_cols, c))) @remote_api_endpoint('origin_intrinsic_metadata/search/by_producer') @db_transaction_generator() def origin_intrinsic_metadata_search_by_producer( - self, start=0, end=None, limit=100, ids_only=False, + self, start='', end=None, limit=100, ids_only=False, mappings=None, tool_ids=None, db=None, cur=None): """Returns the list of origins whose metadata contain all the terms. Args: - start (int): The minimum origin id to return - end (int): The maximum origin id to return + start (str): The minimum origin url to return + end (str): The maximum origin url to return limit (int): The maximum number of results to return - ids_only (bool): Determines whether only origin ids are returned - or the content as well + ids_only (bool): Determines whether only origin urls are + returned or the content as well mappings (List[str]): Returns origins whose intrinsic metadata were generated using at least one of these mappings. Yields: list: list of origin ids (int) if `ids_only=True`, else dictionaries with the following keys: - - **id** (int): legacy origin identifier - - **origin_url** (str) + - **id** (str): origin urls - **from_revision**: sha1 id of the revision used to generate these metadata. - **metadata** (str): associated metadata - **tool** (dict): tool used to compute metadata - **mappings** (List[str]): list of mappings used to translate these metadata """ res = db.origin_intrinsic_metadata_search_by_producer( start, end, limit, ids_only, mappings, tool_ids, cur) if ids_only: - for (origin_id,) in res: - yield origin_id + for (origin,) in res: + yield origin else: for c in res: yield converters.db_to_metadata( dict(zip(db.origin_intrinsic_metadata_cols, c))) @remote_api_endpoint('origin_intrinsic_metadata/stats') @db_transaction() def origin_intrinsic_metadata_stats( self, db=None, cur=None): """Returns counts of indexed metadata per origins, broken down into metadata types. Returns: dict: dictionary with keys: - total (int): total number of origins that were indexed (possibly yielding an empty metadata dictionary) - non_empty (int): total number of origins that we extracted a non-empty metadata dictionary from - per_mapping (dict): a dictionary with mapping names as keys and number of origins whose indexing used this mapping. Note that indexing a given origin may use 0, 1, or many mappings. """ mapping_names = [m for m in MAPPING_NAMES] select_parts = [] # Count rows for each mapping for mapping_name in mapping_names: select_parts.append(( "sum(case when (mappings @> ARRAY['%s']) " " then 1 else 0 end)" ) % mapping_name) # Total select_parts.append("sum(1)") # Rows whose metadata has at least one key that is not '@context' select_parts.append( "sum(case when ('{}'::jsonb @> (metadata - '@context')) " " then 0 else 1 end)") cur.execute('select ' + ', '.join(select_parts) + ' from origin_intrinsic_metadata') results = dict(zip(mapping_names + ['total', 'non_empty'], cur.fetchone())) return { 'total': results.pop('total'), 'non_empty': results.pop('non_empty'), 'per_mapping': results, } @remote_api_endpoint('indexer_configuration/add') @db_transaction_generator() def indexer_configuration_add(self, tools, db=None, cur=None): """Add new tools to the storage. Args: tools ([dict]): List of dictionary representing tool to insert in the db. Dictionary with the following keys: - **tool_name** (str): tool's name - **tool_version** (str): tool's version - **tool_configuration** (dict): tool's configuration (free form dict) Returns: List of dict inserted in the db (holding the id key as well). The order of the list is not guaranteed to match the order of the initial list. """ db.mktemp_indexer_configuration(cur) db.copy_to(tools, 'tmp_indexer_configuration', ['tool_name', 'tool_version', 'tool_configuration'], cur) tools = db.indexer_configuration_add_from_temp(cur) for line in tools: yield dict(zip(db.indexer_configuration_cols, line)) @remote_api_endpoint('indexer_configuration/data') @db_transaction() def indexer_configuration_get(self, tool, db=None, cur=None): """Retrieve tool information. Args: tool (dict): Dictionary representing a tool with the following keys: - **tool_name** (str): tool's name - **tool_version** (str): tool's version - **tool_configuration** (dict): tool's configuration (free form dict) Returns: The same dictionary with an `id` key, None otherwise. """ tool_conf = tool['tool_configuration'] if isinstance(tool_conf, dict): tool_conf = json.dumps(tool_conf) idx = db.indexer_configuration_get(tool['tool_name'], tool['tool_version'], tool_conf) if not idx: return None return dict(zip(db.indexer_configuration_cols, idx)) diff --git a/swh/indexer/storage/db.py b/swh/indexer/storage/db.py index 1b5f859..3c02cf1 100644 --- a/swh/indexer/storage/db.py +++ b/swh/indexer/storage/db.py @@ -1,459 +1,458 @@ # 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.core.db import BaseDb from swh.core.db.db_utils import execute_values_generator, stored_procedure 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_generator( 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_generator( 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 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_generator( 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 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_generator( 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', '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_intrinsic_metadata_hash_keys = [ 'id', 'indexer_configuration_id'] def revision_intrinsic_metadata_missing_from_list( self, metadata, cur=None): """List missing metadata. """ yield from self._missing_from_list( 'revision_intrinsic_metadata', metadata, self.revision_intrinsic_metadata_hash_keys, cur=cur) revision_intrinsic_metadata_cols = [ 'id', 'metadata', 'mappings', 'tool_id', 'tool_name', 'tool_version', 'tool_configuration'] @stored_procedure('swh_mktemp_revision_intrinsic_metadata') def mktemp_revision_intrinsic_metadata(self, cur=None): pass def revision_intrinsic_metadata_add_from_temp( self, conflict_update, cur=None): self._cursor(cur).execute( "SELECT swh_revision_intrinsic_metadata_add(%s)", (conflict_update, )) def revision_intrinsic_metadata_delete( self, entries, cur=None): cur = self._cursor(cur) cur.execute( "DELETE from revision_intrinsic_metadata " "WHERE (id, indexer_configuration_id) IN " " (VALUES %s)" % (', '.join('%s' for _ in entries)), tuple((e['id'], e['indexer_configuration_id']) for e in entries),) def revision_intrinsic_metadata_get_from_list(self, ids, cur=None): yield from self._get_from_list( 'revision_intrinsic_metadata', ids, self.revision_intrinsic_metadata_cols, cur=cur) origin_intrinsic_metadata_cols = [ - 'id', 'origin_url', 'metadata', 'from_revision', 'mappings', + 'id', 'metadata', 'from_revision', 'mappings', '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_delete( self, entries, cur=None): cur = self._cursor(cur) cur.execute( "DELETE from origin_intrinsic_metadata " "WHERE (id, indexer_configuration_id) IN" " (VALUES %s)" % (', '.join('%s' for _ in entries)), tuple((e['id'], e['indexer_configuration_id']) for e in entries),) - def origin_intrinsic_metadata_get_from_list(self, orig_ids, cur=None): + def origin_intrinsic_metadata_get_from_list(self, ids, cur=None): yield from self._get_from_list( - 'origin_intrinsic_metadata', orig_ids, + 'origin_intrinsic_metadata', ids, self.origin_intrinsic_metadata_cols, cur=cur, id_col='id') def origin_intrinsic_metadata_search_fulltext(self, terms, *, limit, cur): 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 = (self._convert_key(col, 'oim') for col in 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 oim.metadata_tsvector @@ 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 def origin_intrinsic_metadata_search_by_producer( self, start, end, limit, ids_only, mappings, tool_ids, cur): if ids_only: keys = 'oim.id' else: keys = ', '.join((self._convert_key(col, 'oim') for col in self.origin_intrinsic_metadata_cols)) query_parts = [ "SELECT %s" % keys, "FROM origin_intrinsic_metadata AS oim", "INNER JOIN indexer_configuration AS i", "ON oim.indexer_configuration_id=i.id", ] args = [] where = [] if start: where.append('oim.id >= %s') args.append(start) if end: where.append('oim.id <= %s') args.append(end) if mappings is not None: where.append('oim.mappings && %s') args.append(mappings) if tool_ids is not None: where.append('oim.indexer_configuration_id = ANY(%s)') args.append(tool_ids) if where: query_parts.append('WHERE') query_parts.append(' AND '.join(where)) if limit: query_parts.append('LIMIT %s') args.append(limit) cur.execute(' '.join(query_parts), args) 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 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)) return cur.fetchone() diff --git a/swh/indexer/storage/in_memory.py b/swh/indexer/storage/in_memory.py index 338aaa8..a7e395b 100644 --- a/swh/indexer/storage/in_memory.py +++ b/swh/indexer/storage/in_memory.py @@ -1,836 +1,832 @@ # Copyright (C) 2018 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import bisect from collections import defaultdict, Counter import itertools import json import operator import math import re from . import MAPPING_NAMES SHA1_DIGEST_SIZE = 160 def _transform_tool(tool): return { 'id': tool['id'], 'name': tool['tool_name'], 'version': tool['tool_version'], 'configuration': tool['tool_configuration'], } class SubStorage: """Implements common missing/get/add logic for each indexer type.""" def __init__(self, tools): self._tools = tools self._sorted_ids = [] self._data = {} # map (id_, tool_id) -> metadata_dict self._tools_per_id = defaultdict(set) # map id_ -> Set[tool_id] def missing(self, ids): """List data missing from storage. Args: data (iterable): dictionaries with keys: - **id** (bytes): sha1 identifier - **indexer_configuration_id** (int): tool used to compute the results Yields: missing sha1s """ for id_ in ids: tool_id = id_['indexer_configuration_id'] id_ = id_['id'] if tool_id not in self._tools_per_id.get(id_, set()): yield id_ def get(self, ids): """Retrieve data per id. Args: ids (iterable): sha1 checksums Yields: dict: dictionaries with the following keys: - **id** (bytes) - **tool** (dict): tool used to compute metadata - arbitrary data (as provided to `add`) """ for id_ in ids: for tool_id in self._tools_per_id.get(id_, set()): key = (id_, tool_id) yield { 'id': id_, 'tool': _transform_tool(self._tools[tool_id]), **self._data[key], } def get_all(self): - yield from self.get(list(self._tools_per_id)) + yield from self.get(self._sorted_ids) def get_range(self, start, end, indexer_configuration_id, limit): """Retrieve data within range [start, end] bound by limit. Args: **start** (bytes): Starting identifier range (expected smaller than end) **end** (bytes): Ending identifier range (expected larger than start) **indexer_configuration_id** (int): The tool used to index data **limit** (int): Limit result Raises: ValueError for limit to None Returns: a dict with keys: - **ids** [bytes]: iterable of content ids within the range. - **next** (Optional[bytes]): The next range of sha1 starts at this sha1 if any """ if limit is None: raise ValueError('Development error: limit should not be None') from_index = bisect.bisect_left(self._sorted_ids, start) to_index = bisect.bisect_right(self._sorted_ids, end, lo=from_index) if to_index - from_index >= limit: return { 'ids': self._sorted_ids[from_index:from_index+limit], 'next': self._sorted_ids[from_index+limit], } else: return { 'ids': self._sorted_ids[from_index:to_index], 'next': None, } def add(self, data, conflict_update): """Add data not present in storage. Args: data (iterable): dictionaries with keys: - **id**: sha1 - **indexer_configuration_id**: tool used to compute the results - arbitrary data conflict_update (bool): Flag to determine if we want to overwrite (true) or skip duplicates (false) """ data = list(data) if len({x['id'] for x in data}) < len(data): # For "exception-compatibility" with the pgsql backend raise ValueError('The same id is present more than once.') for item in data: item = item.copy() tool_id = item.pop('indexer_configuration_id') id_ = item.pop('id') data = item if not conflict_update and \ tool_id in self._tools_per_id.get(id_, set()): # Duplicate, should not be updated continue key = (id_, tool_id) self._data[key] = data self._tools_per_id[id_].add(tool_id) if id_ not in self._sorted_ids: bisect.insort(self._sorted_ids, id_) def add_merge(self, new_data, conflict_update, merged_key): for new_item in new_data: id_ = new_item['id'] tool_id = new_item['indexer_configuration_id'] if conflict_update: all_subitems = [] else: existing = list(self.get([id_])) all_subitems = [ old_subitem for existing_item in existing if existing_item['tool']['id'] == tool_id for old_subitem in existing_item[merged_key] ] for new_subitem in new_item[merged_key]: if new_subitem not in all_subitems: all_subitems.append(new_subitem) self.add([ { 'id': id_, 'indexer_configuration_id': tool_id, merged_key: all_subitems, } ], conflict_update=True) if id_ not in self._sorted_ids: bisect.insort(self._sorted_ids, id_) def delete(self, entries): for entry in entries: (id_, tool_id) = (entry['id'], entry['indexer_configuration_id']) key = (id_, tool_id) if tool_id in self._tools_per_id[id_]: self._tools_per_id[id_].remove(tool_id) if key in self._data: del self._data[key] class IndexerStorage: """In-memory SWH indexer storage.""" def __init__(self): self._tools = {} self._mimetypes = SubStorage(self._tools) self._languages = SubStorage(self._tools) self._content_ctags = SubStorage(self._tools) self._licenses = SubStorage(self._tools) self._content_metadata = SubStorage(self._tools) self._revision_intrinsic_metadata = SubStorage(self._tools) self._origin_intrinsic_metadata = SubStorage(self._tools) def content_mimetype_missing(self, mimetypes): """Generate mimetypes missing from storage. Args: mimetypes (iterable): iterable of dict with keys: - **id** (bytes): sha1 identifier - **indexer_configuration_id** (int): tool used to compute the results Yields: tuple (id, indexer_configuration_id): missing id """ yield from self._mimetypes.missing(mimetypes) def content_mimetype_get_range( self, start, end, indexer_configuration_id, limit=1000): """Retrieve mimetypes within range [start, end] bound by limit. Args: **start** (bytes): Starting identifier range (expected smaller than end) **end** (bytes): Ending identifier range (expected larger than start) **indexer_configuration_id** (int): The tool used to index data **limit** (int): Limit result (default to 1000) Raises: ValueError for limit to None Returns: a dict with keys: - **ids** [bytes]: iterable of content ids within the range. - **next** (Optional[bytes]): The next range of sha1 starts at this sha1 if any """ return self._mimetypes.get_range( start, end, indexer_configuration_id, limit) def content_mimetype_add(self, mimetypes, conflict_update=False): """Add mimetypes not present in storage. Args: mimetypes (iterable): dictionaries with keys: - **id** (bytes): sha1 identifier - **mimetype** (bytes): raw content's mimetype - **encoding** (bytes): raw content's encoding - **indexer_configuration_id** (int): tool's id used to compute the results - **conflict_update** (bool): Flag to determine if we want to overwrite (``True``) or skip duplicates (``False``, the default) """ if not all(isinstance(x['id'], bytes) for x in mimetypes): raise TypeError('identifiers must be bytes.') self._mimetypes.add(mimetypes, conflict_update) def content_mimetype_get(self, ids, db=None, cur=None): """Retrieve full content mimetype per ids. Args: ids (iterable): sha1 identifier Yields: mimetypes (iterable): dictionaries with keys: - **id** (bytes): sha1 identifier - **mimetype** (bytes): raw content's mimetype - **encoding** (bytes): raw content's encoding - **tool** (dict): Tool used to compute the language """ yield from self._mimetypes.get(ids) def content_language_missing(self, languages): """List languages missing from storage. Args: languages (iterable): dictionaries with keys: - **id** (bytes): sha1 identifier - **indexer_configuration_id** (int): tool used to compute the results Yields: an iterable of missing id for the tuple (id, indexer_configuration_id) """ yield from self._languages.missing(languages) def content_language_get(self, ids): """Retrieve full content language per ids. Args: ids (iterable): sha1 identifier Yields: languages (iterable): dictionaries with keys: - **id** (bytes): sha1 identifier - **lang** (bytes): raw content's language - **tool** (dict): Tool used to compute the language """ yield from self._languages.get(ids) def content_language_add(self, languages, conflict_update=False): """Add languages not present in storage. Args: languages (iterable): dictionaries with keys: - **id** (bytes): sha1 - **lang** (bytes): language detected conflict_update (bool): Flag to determine if we want to overwrite (true) or skip duplicates (false, the default) """ if not all(isinstance(x['id'], bytes) for x in languages): raise TypeError('identifiers must be bytes.') self._languages.add(languages, conflict_update) def content_ctags_missing(self, ctags): """List ctags missing from storage. Args: ctags (iterable): dicts with keys: - **id** (bytes): sha1 identifier - **indexer_configuration_id** (int): tool used to compute the results Yields: an iterable of missing id for the tuple (id, indexer_configuration_id) """ yield from self._content_ctags.missing(ctags) def content_ctags_get(self, ids): """Retrieve ctags per id. Args: ids (iterable): sha1 checksums Yields: Dictionaries with keys: - **id** (bytes): content's identifier - **name** (str): symbol's name - **kind** (str): symbol's kind - **lang** (str): language for that content - **tool** (dict): tool used to compute the ctags' info """ for item in self._content_ctags.get(ids): for item_ctags_item in item['ctags']: yield { 'id': item['id'], 'tool': item['tool'], **item_ctags_item } def content_ctags_add(self, ctags, conflict_update=False): """Add ctags not present in storage Args: ctags (iterable): dictionaries with keys: - **id** (bytes): sha1 - **ctags** ([list): List of dictionary with keys: name, kind, line, lang - **indexer_configuration_id**: tool used to compute the results """ if not all(isinstance(x['id'], bytes) for x in ctags): raise TypeError('identifiers must be bytes.') self._content_ctags.add_merge(ctags, conflict_update, 'ctags') def content_ctags_search(self, expression, limit=10, last_sha1=None, db=None, cur=None): """Search through content's raw ctags symbols. Args: expression (str): Expression to search for limit (int): Number of rows to return (default to 10). last_sha1 (str): Offset from which retrieving data (default to ''). Yields: rows of ctags including id, name, lang, kind, line, etc... """ nb_matches = 0 for ((id_, tool_id), item) in \ sorted(self._content_ctags._data.items()): if id_ <= (last_sha1 or bytes(0 for _ in range(SHA1_DIGEST_SIZE))): continue for ctags_item in item['ctags']: if ctags_item['name'] != expression: continue nb_matches += 1 yield { 'id': id_, 'tool': _transform_tool(self._tools[tool_id]), **ctags_item } if nb_matches >= limit: return def content_fossology_license_get(self, ids): """Retrieve licenses per id. Args: ids (iterable): sha1 checksums Yields: dict: ``{id: facts}`` where ``facts`` is a dict with the following keys: - **licenses** ([str]): associated licenses for that content - **tool** (dict): Tool used to compute the license """ # Rewrites the output of SubStorage.get from the old format to # the new one. SubStorage.get should be updated once all other # *_get methods use the new format. # See: https://forge.softwareheritage.org/T1433 res = {} for d in self._licenses.get(ids): res.setdefault(d.pop('id'), []).append(d) for (id_, facts) in res.items(): yield {id_: facts} def content_fossology_license_add(self, licenses, conflict_update=False): """Add licenses not present in storage. Args: licenses (iterable): dictionaries with keys: - **id**: sha1 - **licenses** ([bytes]): List of licenses associated to sha1 - **tool** (str): nomossa conflict_update: Flag to determine if we want to overwrite (true) or skip duplicates (false, the default) Returns: list: content_license entries which failed due to unknown licenses """ if not all(isinstance(x['id'], bytes) for x in licenses): raise TypeError('identifiers must be bytes.') self._licenses.add_merge(licenses, conflict_update, 'licenses') def content_fossology_license_get_range( self, start, end, indexer_configuration_id, limit=1000): """Retrieve licenses within range [start, end] bound by limit. Args: **start** (bytes): Starting identifier range (expected smaller than end) **end** (bytes): Ending identifier range (expected larger than start) **indexer_configuration_id** (int): The tool used to index data **limit** (int): Limit result (default to 1000) Raises: ValueError for limit to None Returns: a dict with keys: - **ids** [bytes]: iterable of content ids within the range. - **next** (Optional[bytes]): The next range of sha1 starts at this sha1 if any """ return self._licenses.get_range( start, end, indexer_configuration_id, limit) def content_metadata_missing(self, metadata): """List metadata missing from storage. Args: metadata (iterable): dictionaries with keys: - **id** (bytes): sha1 identifier - **indexer_configuration_id** (int): tool used to compute the results Yields: missing sha1s """ yield from self._content_metadata.missing(metadata) def content_metadata_get(self, ids): """Retrieve metadata per id. Args: ids (iterable): sha1 checksums Yields: dictionaries with the following keys: - **id** (bytes) - **metadata** (str): associated metadata - **tool** (dict): tool used to compute metadata """ yield from self._content_metadata.get(ids) def content_metadata_add(self, metadata, conflict_update=False): """Add metadata not present in storage. Args: metadata (iterable): dictionaries with keys: - **id**: sha1 - **metadata**: arbitrary dict - **indexer_configuration_id**: tool used to compute the results conflict_update: Flag to determine if we want to overwrite (true) or skip duplicates (false, the default) """ if not all(isinstance(x['id'], bytes) for x in metadata): raise TypeError('identifiers must be bytes.') self._content_metadata.add(metadata, conflict_update) def revision_intrinsic_metadata_missing(self, metadata): """List metadata missing from storage. Args: metadata (iterable): dictionaries with keys: - **id** (bytes): sha1_git revision identifier - **indexer_configuration_id** (int): tool used to compute the results Yields: missing ids """ yield from self._revision_intrinsic_metadata.missing(metadata) def revision_intrinsic_metadata_get(self, ids): """Retrieve revision metadata per id. Args: ids (iterable): sha1 checksums Yields: dictionaries with the following keys: - **id** (bytes) - **metadata** (str): associated metadata - **tool** (dict): tool used to compute metadata - **mappings** (List[str]): list of mappings used to translate these metadata """ yield from self._revision_intrinsic_metadata.get(ids) def revision_intrinsic_metadata_add(self, metadata, conflict_update=False): """Add metadata not present in storage. Args: metadata (iterable): dictionaries with keys: - **id**: sha1_git of revision - **metadata**: arbitrary dict - **indexer_configuration_id**: tool used to compute metadata - **mappings** (List[str]): list of mappings used to translate these metadata conflict_update: Flag to determine if we want to overwrite (true) or skip duplicates (false, the default) """ if not all(isinstance(x['id'], bytes) for x in metadata): raise TypeError('identifiers must be bytes.') self._revision_intrinsic_metadata.add(metadata, conflict_update) def revision_intrinsic_metadata_delete(self, entries): """Remove revision metadata from the storage. Args: entries (dict): dictionaries with the following keys: - **revision** (int): origin identifier - **id** (int): tool used to compute metadata """ self._revision_intrinsic_metadata.delete(entries) def origin_intrinsic_metadata_get(self, ids): """Retrieve origin metadata per id. Args: ids (iterable): origin identifiers Yields: list: dictionaries with the following keys: - - **id** (int) - - **origin_url** (str) + - **id** (str): origin url - **from_revision** (bytes): which revision this metadata was extracted from - **metadata** (str): associated metadata - **tool** (dict): tool used to compute metadata - **mappings** (List[str]): list of mappings used to translate these metadata """ yield from self._origin_intrinsic_metadata.get(ids) def origin_intrinsic_metadata_add(self, metadata, conflict_update=False): """Add origin metadata not present in storage. Args: metadata (iterable): dictionaries with keys: - - **id**: origin identifier - - **origin_url** + - **id**: origin url - **from_revision**: sha1 id of the revision used to generate these metadata. - **metadata**: arbitrary dict - **indexer_configuration_id**: tool used to compute metadata - **mappings** (List[str]): list of mappings used to translate these metadata conflict_update: Flag to determine if we want to overwrite (true) or skip duplicates (false, the default) """ self._origin_intrinsic_metadata.add(metadata, conflict_update) def origin_intrinsic_metadata_delete(self, entries): """Remove origin metadata from the storage. Args: entries (dict): dictionaries with the following keys: - - **id** (int): origin identifier + - **id** (str): origin url - **indexer_configuration_id** (int): tool used to compute metadata """ self._origin_intrinsic_metadata.delete(entries) def origin_intrinsic_metadata_search_fulltext( self, conjunction, limit=100): """Returns the list of origins whose metadata contain all the terms. Args: conjunction (List[str]): List of terms to be searched for. limit (int): The maximum number of results to return Yields: list: dictionaries with the following keys: - - **id** (int) - - **origin_url** (str) + - **id** (str): origin url - **from_revision** (bytes): which revision this metadata was extracted from - **metadata** (str): associated metadata - **tool** (dict): tool used to compute metadata - **mappings** (List[str]): list of mappings used to translate these metadata """ # A very crude fulltext search implementation, but that's enough # to work on English metadata tokens_re = re.compile('[a-zA-Z0-9]+') search_tokens = list(itertools.chain( *map(tokens_re.findall, conjunction))) def rank(data): # Tokenize the metadata text = json.dumps(data['metadata']) text_tokens = tokens_re.findall(text) text_token_occurences = Counter(text_tokens) # Count the number of occurrences of search tokens in the text score = 0 for search_token in search_tokens: if text_token_occurences[search_token] == 0: # Search token is not in the text. return 0 score += text_token_occurences[search_token] # Normalize according to the text's length return score / math.log(len(text_tokens)) results = [(rank(data), data) for data in self._origin_intrinsic_metadata.get_all()] results = [(rank_, data) for (rank_, data) in results if rank_ > 0] results.sort(key=operator.itemgetter(0), # Don't try to order 'data' reverse=True) for (rank_, result) in results[:limit]: yield result def origin_intrinsic_metadata_search_by_producer( - self, start=0, end=None, limit=100, ids_only=False, + self, start='', end=None, limit=100, ids_only=False, mappings=None, tool_ids=None, db=None, cur=None): """Returns the list of origins whose metadata contain all the terms. Args: - start (int): The minimum origin id to return - end (int): The maximum origin id to return + start (str): The minimum origin url to return + end (str): The maximum origin url to return limit (int): The maximum number of results to return ids_only (bool): Determines whether only origin ids are returned or the content as well mappings (List[str]): Returns origins whose intrinsic metadata were generated using at least one of these mappings. Yields: list: list of origin ids (int) if `ids_only=True`, else dictionaries with the following keys: - - **id** (int) - - **origin_url** (str) + - **id** (str): origin url - **from_revision**: sha1 id of the revision used to generate these metadata. - **metadata** (str): associated metadata - **tool** (dict): tool used to compute metadata - **mappings** (List[str]): list of mappings used to translate these metadata """ nb_results = 0 if mappings is not None: mappings = frozenset(mappings) if tool_ids is not None: tool_ids = frozenset(tool_ids) for entry in self._origin_intrinsic_metadata.get_all(): if entry['id'] < start or (end and entry['id'] > end): continue if nb_results >= limit: return if mappings is not None and mappings.isdisjoint(entry['mappings']): continue if tool_ids is not None and entry['tool']['id'] not in tool_ids: continue if ids_only: yield entry['id'] else: yield entry nb_results += 1 def origin_intrinsic_metadata_stats(self): """Returns statistics on stored intrinsic metadata. Returns: dict: dictionary with keys: - total (int): total number of origins that were indexed (possibly yielding an empty metadata dictionary) - non_empty (int): total number of origins that we extracted a non-empty metadata dictionary from - per_mapping (dict): a dictionary with mapping names as keys and number of origins whose indexing used this mapping. Note that indexing a given origin may use 0, 1, or many mappings. """ mapping_count = {m: 0 for m in MAPPING_NAMES} total = non_empty = 0 for data in self._origin_intrinsic_metadata.get_all(): total += 1 if set(data['metadata']) - {'@context'}: non_empty += 1 for mapping in data['mappings']: mapping_count[mapping] += 1 return { 'per_mapping': mapping_count, 'total': total, 'non_empty': non_empty } def indexer_configuration_add(self, tools): """Add new tools to the storage. Args: tools ([dict]): List of dictionary representing tool to insert in the db. Dictionary with the following keys: - **tool_name** (str): tool's name - **tool_version** (str): tool's version - **tool_configuration** (dict): tool's configuration (free form dict) Returns: list: List of dict inserted in the db (holding the id key as well). The order of the list is not guaranteed to match the order of the initial list. """ inserted = [] for tool in tools: tool = tool.copy() id_ = self._tool_key(tool) tool['id'] = id_ self._tools[id_] = tool inserted.append(tool) return inserted def indexer_configuration_get(self, tool): """Retrieve tool information. Args: tool (dict): Dictionary representing a tool with the following keys: - **tool_name** (str): tool's name - **tool_version** (str): tool's version - **tool_configuration** (dict): tool's configuration (free form dict) Returns: The same dictionary with an `id` key, None otherwise. """ return self._tools.get(self._tool_key(tool)) def _tool_key(self, tool): return hash((tool['tool_name'], tool['tool_version'], json.dumps(tool['tool_configuration'], sort_keys=True))) diff --git a/swh/indexer/tests/conftest.py b/swh/indexer/tests/conftest.py index 5f651bf..78f1975 100644 --- a/swh/indexer/tests/conftest.py +++ b/swh/indexer/tests/conftest.py @@ -1,71 +1,71 @@ from datetime import timedelta from unittest.mock import patch import pytest from swh.objstorage import get_objstorage from swh.scheduler.tests.conftest import * # noqa from swh.storage.in_memory import Storage from swh.indexer.storage.in_memory import IndexerStorage from .utils import fill_storage, fill_obj_storage TASK_NAMES = ['revision_intrinsic_metadata', 'origin_intrinsic_metadata'] @pytest.fixture def indexer_scheduler(swh_scheduler): for taskname in TASK_NAMES: swh_scheduler.create_task_type({ 'type': taskname, 'description': 'The {} indexer testing task'.format(taskname), 'backend_name': 'swh.indexer.tests.tasks.{}'.format(taskname), 'default_interval': timedelta(days=1), 'min_interval': timedelta(hours=6), 'max_interval': timedelta(days=12), 'num_retries': 3, }) return swh_scheduler @pytest.fixture def idx_storage(): """An instance of swh.indexer.storage.in_memory.IndexerStorage that gets injected into all indexers classes.""" idx_storage = IndexerStorage() with patch('swh.indexer.storage.in_memory.IndexerStorage') \ as idx_storage_mock: idx_storage_mock.return_value = idx_storage yield idx_storage @pytest.fixture def storage(): """An instance of swh.storage.in_memory.Storage that gets injected into all indexers classes.""" storage = Storage() fill_storage(storage) with patch('swh.storage.in_memory.Storage') as storage_mock: storage_mock.return_value = storage yield storage @pytest.fixture def obj_storage(): """An instance of swh.objstorage.objstorage_in_memory.InMemoryObjStorage that gets injected into all indexers classes.""" objstorage = get_objstorage('memory', {}) fill_obj_storage(objstorage) with patch.dict('swh.objstorage._STORAGE_CLASSES', {'memory': lambda: objstorage}): yield objstorage -@pytest.fixture(scope='session') +@pytest.fixture(scope='session') # type: ignore # expected redefinition def celery_includes(): return [ 'swh.indexer.tests.tasks', 'swh.indexer.tasks', ] diff --git a/swh/indexer/tests/storage/test_storage.py b/swh/indexer/tests/storage/test_storage.py index b11806a..5167058 100644 --- a/swh/indexer/tests/storage/test_storage.py +++ b/swh/indexer/tests/storage/test_storage.py @@ -1,1994 +1,1972 @@ # 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 threading import unittest import pytest from hypothesis import given from swh.model.hashutil import hash_to_bytes from swh.indexer.storage import get_indexer_storage, MAPPING_NAMES from swh.core.db.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 from swh.indexer.metadata_dictionary import MAPPINGS TOOLS = [ { 'tool_name': 'universal-ctags', 'tool_version': '~git7859817b', 'tool_configuration': { "command_line": "ctags --fields=+lnz --sort=no --links=no " "--output-format=json "} }, { 'tool_name': 'swh-metadata-translator', 'tool_version': '0.0.1', 'tool_configuration': {"type": "local", "context": "NpmMapping"}, }, { 'tool_name': 'swh-metadata-detector', 'tool_version': '0.0.1', 'tool_configuration': { "type": "local", "context": ["NpmMapping", "CodemetaMapping"]}, }, { 'tool_name': 'swh-metadata-detector2', 'tool_version': '0.0.1', 'tool_configuration': { "type": "local", "context": ["NpmMapping", "CodemetaMapping"]}, }, { 'tool_name': 'file', 'tool_version': '5.22', 'tool_configuration': {"command_line": "file --mime "}, }, { 'tool_name': 'pygments', 'tool_version': '2.0.1+dfsg-1.1+deb8u1', 'tool_configuration': { "type": "library", "debian-package": "python3-pygments"}, }, { 'tool_name': 'pygments', 'tool_version': '2.0.1+dfsg-1.1+deb8u1', 'tool_configuration': { "type": "library", "debian-package": "python3-pygments", "max_content_size": 10240 }, }, { 'tool_name': 'nomos', 'tool_version': '3.1.0rc2-31-ga2cbb8c', 'tool_configuration': {"command_line": "nomossa "}, } ] @pytest.mark.db class BasePgTestStorage(SingleDbTestFixture): """Base test class for most indexer tests. It adds support for Storage testing to the SingleDbTestFixture class. It will also build the database from the swh-indexed/sql/*.sql files. """ TEST_DB_NAME = 'softwareheritage-test-indexer' TEST_DB_DUMP = os.path.join(SQL_DIR, '*.sql') def setUp(self): super().setUp() self.storage_config = { 'cls': 'local', 'args': { 'db': 'dbname=%s' % self.TEST_DB_NAME, }, } def tearDown(self): self.reset_storage_tables() self.storage = None super().tearDown() def reset_storage_tables(self): excluded = {'indexer_configuration'} self.reset_db_tables(self.TEST_DB_NAME, excluded=excluded) db = self.test_db[self.TEST_DB_NAME] db.conn.commit() def gen_generic_endpoint_tests(endpoint_type, tool_name, example_data1, example_data2): def rename(f): f.__name__ = 'test_' + endpoint_type + f.__name__ return f def endpoint(self, endpoint_name): return getattr(self.storage, endpoint_type + '_' + endpoint_name) @rename def missing(self): # given tool_id = self.tools[tool_name]['id'] query = [ { 'id': self.sha1_1, 'indexer_configuration_id': tool_id, }, { 'id': self.sha1_2, 'indexer_configuration_id': tool_id, }] # when actual_missing = endpoint(self, 'missing')(query) # then self.assertEqual(list(actual_missing), [ self.sha1_1, self.sha1_2, ]) # given endpoint(self, 'add')([{ 'id': self.sha1_2, **example_data1, 'indexer_configuration_id': tool_id, }]) # when actual_missing = endpoint(self, 'missing')(query) # then self.assertEqual(list(actual_missing), [self.sha1_1]) @rename def add__drop_duplicate(self): # given tool_id = self.tools[tool_name]['id'] data_v1 = { 'id': self.sha1_2, **example_data1, 'indexer_configuration_id': tool_id, } # given endpoint(self, 'add')([data_v1]) # when actual_data = list(endpoint(self, 'get')([self.sha1_2])) # then expected_data_v1 = [{ 'id': self.sha1_2, **example_data1, 'tool': self.tools[tool_name], }] self.assertEqual(actual_data, expected_data_v1) # given data_v2 = data_v1.copy() data_v2.update(example_data2) endpoint(self, 'add')([data_v2]) actual_data = list(endpoint(self, 'get')([self.sha1_2])) # data did not change as the v2 was dropped. self.assertEqual(actual_data, expected_data_v1) @rename def add__update_in_place_duplicate(self): # given tool_id = self.tools[tool_name]['id'] data_v1 = { 'id': self.sha1_2, **example_data1, 'indexer_configuration_id': tool_id, } # given endpoint(self, 'add')([data_v1]) # when actual_data = list(endpoint(self, 'get')([self.sha1_2])) expected_data_v1 = [{ 'id': self.sha1_2, **example_data1, 'tool': self.tools[tool_name], }] # then self.assertEqual(actual_data, expected_data_v1) # given data_v2 = data_v1.copy() data_v2.update(example_data2) endpoint(self, 'add')([data_v2], conflict_update=True) actual_data = list(endpoint(self, 'get')([self.sha1_2])) expected_data_v2 = [{ 'id': self.sha1_2, **example_data2, 'tool': self.tools[tool_name], }] # data did change as the v2 was used to overwrite v1 self.assertEqual(actual_data, expected_data_v2) @rename def add__update_in_place_deadlock(self): # given tool_id = self.tools[tool_name]['id'] hashes = [ hash_to_bytes( '34973274ccef6ab4dfaaf86599792fa9c3fe4{:03d}'.format(i)) for i in range(1000)] data_v1 = [ { 'id': hash_, **example_data1, 'indexer_configuration_id': tool_id, } for hash_ in hashes ] data_v2 = [ { 'id': hash_, **example_data2, 'indexer_configuration_id': tool_id, } for hash_ in hashes ] # Remove one item from each, so that both queries have to succeed for # all items to be in the DB. data_v2a = data_v2[1:] data_v2b = list(reversed(data_v2[0:-1])) # given endpoint(self, 'add')(data_v1) # when actual_data = list(endpoint(self, 'get')(hashes)) expected_data_v1 = [ { 'id': hash_, **example_data1, 'tool': self.tools[tool_name], } for hash_ in hashes ] # then self.assertEqual(actual_data, expected_data_v1) # given def f1(): endpoint(self, 'add')(data_v2a, conflict_update=True) def f2(): endpoint(self, 'add')(data_v2b, conflict_update=True) t1 = threading.Thread(target=f1) t2 = threading.Thread(target=f2) t2.start() t1.start() t1.join() t2.join() actual_data = list(endpoint(self, 'get')(hashes)) expected_data_v2 = [ { 'id': hash_, **example_data2, 'tool': self.tools[tool_name], } for hash_ in hashes ] self.assertCountEqual(actual_data, expected_data_v2) def add__duplicate_twice(self): # given tool_id = self.tools[tool_name]['id'] data_rev1 = { 'id': self.revision_id_2, **example_data1, 'indexer_configuration_id': tool_id } data_rev2 = { 'id': self.revision_id_2, **example_data2, 'indexer_configuration_id': tool_id } # when endpoint(self, 'add')([data_rev1]) with self.assertRaises(ValueError): endpoint(self, 'add')( [data_rev2, data_rev2], conflict_update=True) # then actual_data = list(endpoint(self, 'get')( [self.revision_id_2, self.revision_id_1])) expected_data = [{ 'id': self.revision_id_2, **example_data1, 'tool': self.tools[tool_name] }] self.assertEqual(actual_data, expected_data) @rename def get(self): # given tool_id = self.tools[tool_name]['id'] query = [self.sha1_2, self.sha1_1] data1 = { 'id': self.sha1_2, **example_data1, 'indexer_configuration_id': tool_id, } # when endpoint(self, 'add')([data1]) # then actual_data = list(endpoint(self, 'get')(query)) # then expected_data = [{ 'id': self.sha1_2, **example_data1, 'tool': self.tools[tool_name] }] self.assertEqual(actual_data, expected_data) @rename def delete(self): # given tool_id = self.tools[tool_name]['id'] query = [self.sha1_2, self.sha1_1] data1 = { 'id': self.sha1_2, **example_data1, 'indexer_configuration_id': tool_id, } # when endpoint(self, 'add')([data1]) endpoint(self, 'delete')([ { 'id': self.sha1_2, 'indexer_configuration_id': tool_id, } ]) # then actual_data = list(endpoint(self, 'get')(query)) # then self.assertEqual(actual_data, []) @rename def delete_nonexisting(self): tool_id = self.tools[tool_name]['id'] endpoint(self, 'delete')([ { 'id': self.sha1_2, 'indexer_configuration_id': tool_id, } ]) return ( missing, add__drop_duplicate, add__update_in_place_duplicate, add__update_in_place_deadlock, add__duplicate_twice, get, delete, delete_nonexisting, ) class CommonTestStorage: """Base class for Indexer Storage testing. """ - def setUp(self): + def setUp(self, *args, **kwargs): super().setUp() self.storage = get_indexer_storage(**self.storage_config) tools = self.storage.indexer_configuration_add(TOOLS) self.tools = {} for tool in tools: tool_name = tool['tool_name'] while tool_name in self.tools: tool_name += '_' self.tools[tool_name] = { 'id': tool['id'], 'name': tool['tool_name'], 'version': tool['tool_version'], 'configuration': tool['tool_configuration'], } self.sha1_1 = hash_to_bytes('34973274ccef6ab4dfaaf86599792fa9c3fe4689') self.sha1_2 = hash_to_bytes('61c2b3a30496d329e21af70dd2d7e097046d07b7') self.revision_id_1 = hash_to_bytes( '7026b7c1a2af56521e951c01ed20f255fa054238') self.revision_id_2 = hash_to_bytes( '7026b7c1a2af56521e9587659012345678904321') self.revision_id_3 = hash_to_bytes( '7026b7c1a2af56521e9587659012345678904320') - self.origin_id_1 = 44434341 - self.origin_id_2 = 44434342 - self.origin_id_3 = 54974445 + self.origin_url_1 = 'file:///dev/0/zero' # 44434341 + self.origin_url_2 = 'file:///dev/1/one' # 44434342 + self.origin_url_3 = 'file:///dev/2/two' # 54974445 def test_check_config(self): self.assertTrue(self.storage.check_config(check_write=True)) self.assertTrue(self.storage.check_config(check_write=False)) # generate content_mimetype tests ( test_content_mimetype_missing, test_content_mimetype_add__drop_duplicate, test_content_mimetype_add__update_in_place_duplicate, test_content_mimetype_add__update_in_place_deadlock, test_content_mimetype_add__duplicate_twice, test_content_mimetype_get, _, # content_mimetype_detete, _, # content_mimetype_detete_nonexisting, ) = gen_generic_endpoint_tests( endpoint_type='content_mimetype', tool_name='file', example_data1={ 'mimetype': 'text/plain', 'encoding': 'utf-8', }, example_data2={ 'mimetype': 'text/html', 'encoding': 'us-ascii', }, ) # content_language tests ( test_content_language_missing, test_content_language_add__drop_duplicate, test_content_language_add__update_in_place_duplicate, test_content_language_add__update_in_place_deadlock, test_content_language_add__duplicate_twice, test_content_language_get, _, # test_content_language_delete, _, # test_content_language_delete_nonexisting, ) = gen_generic_endpoint_tests( endpoint_type='content_language', tool_name='pygments', example_data1={ 'lang': 'haskell', }, example_data2={ 'lang': 'common-lisp', }, ) # content_ctags tests ( test_content_ctags_missing, # the following tests are disabled because CTAGS behave differently _, # test_content_ctags_add__drop_duplicate, _, # test_content_ctags_add__update_in_place_duplicate, _, # test_content_ctags_add__update_in_place_deadlock, _, # test_content_ctags_add__duplicate_twice, _, # test_content_ctags_get, _, # test_content_ctags_delete, _, # test_content_ctags_delete_nonexisting, ) = gen_generic_endpoint_tests( endpoint_type='content_ctags', tool_name='universal-ctags', example_data1={ 'ctags': [{ 'name': 'done', 'kind': 'variable', 'line': 119, 'lang': 'OCaml', }] }, example_data2={ 'ctags': [ { 'name': 'done', 'kind': 'variable', 'line': 100, 'lang': 'Python', }, { 'name': 'main', 'kind': 'function', 'line': 119, 'lang': 'Python', }] }, ) def test_content_ctags_search(self): # 1. given tool = self.tools['universal-ctags'] tool_id = tool['id'] ctag1 = { 'id': self.sha1_1, 'indexer_configuration_id': tool_id, 'ctags': [ { 'name': 'hello', 'kind': 'function', 'line': 133, 'lang': 'Python', }, { 'name': 'counter', 'kind': 'variable', 'line': 119, 'lang': 'Python', }, { 'name': 'hello', 'kind': 'variable', 'line': 210, 'lang': 'Python', }, ] } ctag2 = { 'id': self.sha1_2, 'indexer_configuration_id': tool_id, 'ctags': [ { 'name': 'hello', 'kind': 'variable', 'line': 100, 'lang': 'C', }, { 'name': 'result', 'kind': 'variable', 'line': 120, 'lang': 'C', }, ] } self.storage.content_ctags_add([ctag1, ctag2]) # 1. when actual_ctags = list(self.storage.content_ctags_search('hello', limit=1)) # 1. then self.assertEqual(actual_ctags, [ { 'id': ctag1['id'], 'tool': tool, 'name': 'hello', 'kind': 'function', 'line': 133, 'lang': 'Python', } ]) # 2. when actual_ctags = list(self.storage.content_ctags_search( 'hello', limit=1, last_sha1=ctag1['id'])) # 2. then self.assertEqual(actual_ctags, [ { 'id': ctag2['id'], 'tool': tool, 'name': 'hello', 'kind': 'variable', 'line': 100, 'lang': 'C', } ]) # 3. when actual_ctags = list(self.storage.content_ctags_search('hello')) # 3. then self.assertEqual(actual_ctags, [ { 'id': ctag1['id'], 'tool': tool, 'name': 'hello', 'kind': 'function', 'line': 133, 'lang': 'Python', }, { 'id': ctag1['id'], 'tool': tool, 'name': 'hello', 'kind': 'variable', 'line': 210, 'lang': 'Python', }, { 'id': ctag2['id'], 'tool': tool, 'name': 'hello', 'kind': 'variable', 'line': 100, 'lang': 'C', }, ]) # 4. when actual_ctags = list(self.storage.content_ctags_search('counter')) # then self.assertEqual(actual_ctags, [{ 'id': ctag1['id'], 'tool': tool, 'name': 'counter', 'kind': 'variable', 'line': 119, 'lang': 'Python', }]) # 5. when actual_ctags = list(self.storage.content_ctags_search('result', limit=1)) # then self.assertEqual(actual_ctags, [{ 'id': ctag2['id'], 'tool': tool, 'name': 'result', 'kind': 'variable', 'line': 120, 'lang': 'C', }]) def test_content_ctags_search_no_result(self): actual_ctags = list(self.storage.content_ctags_search('counter')) self.assertEqual(actual_ctags, []) def test_content_ctags_add__add_new_ctags_added(self): # given tool = self.tools['universal-ctags'] tool_id = tool['id'] ctag_v1 = { 'id': self.sha1_2, 'indexer_configuration_id': tool_id, 'ctags': [{ 'name': 'done', 'kind': 'variable', 'line': 100, 'lang': 'Scheme', }] } # given self.storage.content_ctags_add([ctag_v1]) self.storage.content_ctags_add([ctag_v1]) # conflict does nothing # when actual_ctags = list(self.storage.content_ctags_get( [self.sha1_2])) # then expected_ctags = [{ 'id': self.sha1_2, 'name': 'done', 'kind': 'variable', 'line': 100, 'lang': 'Scheme', 'tool': tool, }] self.assertEqual(actual_ctags, expected_ctags) # given ctag_v2 = ctag_v1.copy() ctag_v2.update({ 'ctags': [ { 'name': 'defn', 'kind': 'function', 'line': 120, 'lang': 'Scheme', } ] }) self.storage.content_ctags_add([ctag_v2]) expected_ctags = [ { 'id': self.sha1_2, 'name': 'done', 'kind': 'variable', 'line': 100, 'lang': 'Scheme', 'tool': tool, }, { 'id': self.sha1_2, 'name': 'defn', 'kind': 'function', 'line': 120, 'lang': 'Scheme', 'tool': tool, } ] actual_ctags = list(self.storage.content_ctags_get( [self.sha1_2])) self.assertEqual(actual_ctags, expected_ctags) def test_content_ctags_add__update_in_place(self): # given tool = self.tools['universal-ctags'] tool_id = tool['id'] ctag_v1 = { 'id': self.sha1_2, 'indexer_configuration_id': tool_id, 'ctags': [{ 'name': 'done', 'kind': 'variable', 'line': 100, 'lang': 'Scheme', }] } # given self.storage.content_ctags_add([ctag_v1]) # when actual_ctags = list(self.storage.content_ctags_get( [self.sha1_2])) # then expected_ctags = [ { 'id': self.sha1_2, 'name': 'done', 'kind': 'variable', 'line': 100, 'lang': 'Scheme', 'tool': tool } ] self.assertEqual(actual_ctags, expected_ctags) # given ctag_v2 = ctag_v1.copy() ctag_v2.update({ 'ctags': [ { 'name': 'done', 'kind': 'variable', 'line': 100, 'lang': 'Scheme', }, { 'name': 'defn', 'kind': 'function', 'line': 120, 'lang': 'Scheme', } ] }) self.storage.content_ctags_add([ctag_v2], conflict_update=True) actual_ctags = list(self.storage.content_ctags_get( [self.sha1_2])) # ctag did change as the v2 was used to overwrite v1 expected_ctags = [ { 'id': self.sha1_2, 'name': 'done', 'kind': 'variable', 'line': 100, 'lang': 'Scheme', 'tool': tool, }, { 'id': self.sha1_2, 'name': 'defn', 'kind': 'function', 'line': 120, 'lang': 'Scheme', 'tool': tool, } ] self.assertEqual(actual_ctags, expected_ctags) # content_fossology_license tests ( _, # The endpoint content_fossology_license_missing does not exist # the following tests are disabled because fossology_license tests # behave differently _, # test_content_fossology_license_add__drop_duplicate, _, # test_content_fossology_license_add__update_in_place_duplicate, _, # test_content_fossology_license_add__update_in_place_deadlock, _, # test_content_metadata_add__duplicate_twice, _, # test_content_fossology_license_get, _, # test_content_fossology_license_delete, _, # test_content_fossology_license_delete_nonexisting, ) = gen_generic_endpoint_tests( endpoint_type='content_fossology_license', tool_name='nomos', example_data1={ 'licenses': ['Apache-2.0'], }, example_data2={ 'licenses': ['BSD-2-Clause'], }, ) 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]) # content_metadata tests ( test_content_metadata_missing, test_content_metadata_add__drop_duplicate, test_content_metadata_add__update_in_place_duplicate, test_content_metadata_add__update_in_place_deadlock, test_content_metadata_add__duplicate_twice, test_content_metadata_get, _, # test_content_metadata_delete, _, # test_content_metadata_delete_nonexisting, ) = gen_generic_endpoint_tests( endpoint_type='content_metadata', tool_name='swh-metadata-detector', example_data1={ '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' }, }, example_data2={ 'metadata': { 'other': {}, 'name': 'test_metadata', 'version': '0.0.1' }, }, ) # revision_intrinsic_metadata tests ( test_revision_intrinsic_metadata_missing, test_revision_intrinsic_metadata_add__drop_duplicate, test_revision_intrinsic_metadata_add__update_in_place_duplicate, test_revision_intrinsic_metadata_add__update_in_place_deadlock, test_revision_intrinsic_metadata_add__duplicate_twice, test_revision_intrinsic_metadata_get, test_revision_intrinsic_metadata_delete, test_revision_intrinsic_metadata_delete_nonexisting, ) = gen_generic_endpoint_tests( endpoint_type='revision_intrinsic_metadata', tool_name='swh-metadata-detector', example_data1={ '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' }, 'mappings': ['mapping1'], }, example_data2={ 'metadata': { 'other': {}, 'name': 'test_metadata', 'version': '0.0.1' }, 'mappings': ['mapping2'], }, ) def test_origin_intrinsic_metadata_get(self): # given tool_id = self.tools['swh-metadata-detector']['id'] metadata = { 'version': None, 'name': None, } metadata_rev = { 'id': self.revision_id_2, 'metadata': metadata, 'mappings': ['mapping1'], 'indexer_configuration_id': tool_id, } metadata_origin = { - 'id': self.origin_id_1, - 'origin_url': 'file:///dev/zero', + 'id': self.origin_url_1, 'metadata': metadata, 'indexer_configuration_id': tool_id, 'mappings': ['mapping1'], 'from_revision': self.revision_id_2, } # when self.storage.revision_intrinsic_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])) + [self.origin_url_1, 'no://where'])) expected_metadata = [{ - 'id': self.origin_id_1, - 'origin_url': 'file:///dev/zero', + 'id': self.origin_url_1, 'metadata': metadata, 'tool': self.tools['swh-metadata-detector'], 'from_revision': self.revision_id_2, 'mappings': ['mapping1'], }] self.assertEqual(actual_metadata, expected_metadata) def test_origin_intrinsic_metadata_delete(self): # given tool_id = self.tools['swh-metadata-detector']['id'] metadata = { 'version': None, 'name': None, } metadata_rev = { 'id': self.revision_id_2, 'metadata': metadata, 'mappings': ['mapping1'], 'indexer_configuration_id': tool_id, } metadata_origin = { - 'id': self.origin_id_1, - 'origin_url': 'file:///dev/zero', + 'id': self.origin_url_1, 'metadata': metadata, 'indexer_configuration_id': tool_id, 'mappings': ['mapping1'], 'from_revision': self.revision_id_2, } metadata_origin2 = metadata_origin.copy() - metadata_origin2['id'] = self.origin_id_2 + metadata_origin2['id'] = self.origin_url_2 # when self.storage.revision_intrinsic_metadata_add([metadata_rev]) self.storage.origin_intrinsic_metadata_add([ metadata_origin, metadata_origin2]) self.storage.origin_intrinsic_metadata_delete([ { - 'id': self.origin_id_1, + 'id': self.origin_url_1, 'indexer_configuration_id': tool_id } ]) # then actual_metadata = list(self.storage.origin_intrinsic_metadata_get( - [self.origin_id_1, self.origin_id_2, 42])) + [self.origin_url_1, self.origin_url_2, 'no://where'])) for item in actual_metadata: item['indexer_configuration_id'] = item.pop('tool')['id'] self.assertEqual(actual_metadata, [metadata_origin2]) def test_origin_intrinsic_metadata_delete_nonexisting(self): tool_id = self.tools['swh-metadata-detector']['id'] self.storage.origin_intrinsic_metadata_delete([ { - 'id': self.origin_id_1, + 'id': self.origin_url_1, 'indexer_configuration_id': tool_id } ]) def test_origin_intrinsic_metadata_add_drop_duplicate(self): # given tool_id = self.tools['swh-metadata-detector']['id'] metadata_v1 = { 'version': None, 'name': None, } metadata_rev_v1 = { 'id': self.revision_id_1, - 'origin_url': 'file:///dev/zero', 'metadata': metadata_v1.copy(), 'mappings': [], 'indexer_configuration_id': tool_id, } metadata_origin_v1 = { - 'id': self.origin_id_1, - 'origin_url': 'file:///dev/zero', + 'id': self.origin_url_1, 'metadata': metadata_v1.copy(), 'indexer_configuration_id': tool_id, 'mappings': [], 'from_revision': self.revision_id_1, } # given self.storage.revision_intrinsic_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])) + [self.origin_url_1, 'no://where'])) expected_metadata_v1 = [{ - 'id': self.origin_id_1, - 'origin_url': 'file:///dev/zero', + 'id': self.origin_url_1, 'metadata': metadata_v1, 'tool': self.tools['swh-metadata-detector'], 'from_revision': self.revision_id_1, 'mappings': [], }] self.assertEqual(actual_metadata, expected_metadata_v1) # given metadata_v2 = metadata_v1.copy() metadata_v2.update({ 'name': 'test_metadata', 'author': 'MG', }) metadata_rev_v2 = metadata_rev_v1.copy() metadata_origin_v2 = metadata_origin_v1.copy() metadata_rev_v2['metadata'] = metadata_v2 metadata_origin_v2['metadata'] = metadata_v2 self.storage.revision_intrinsic_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])) + [self.origin_url_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 = { 'version': None, 'name': None, } metadata_rev_v1 = { 'id': self.revision_id_2, 'metadata': metadata_v1, 'mappings': [], 'indexer_configuration_id': tool_id, } metadata_origin_v1 = { - 'id': self.origin_id_1, - 'origin_url': 'file:///dev/zero', + 'id': self.origin_url_1, 'metadata': metadata_v1.copy(), 'indexer_configuration_id': tool_id, 'mappings': [], 'from_revision': self.revision_id_2, } # given self.storage.revision_intrinsic_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])) + [self.origin_url_1])) # then expected_metadata_v1 = [{ - 'id': self.origin_id_1, - 'origin_url': 'file:///dev/zero', + 'id': self.origin_url_1, 'metadata': metadata_v1, 'tool': self.tools['swh-metadata-detector'], 'from_revision': self.revision_id_2, 'mappings': [], }] self.assertEqual(actual_metadata, expected_metadata_v1) # given metadata_v2 = metadata_v1.copy() metadata_v2.update({ 'name': 'test_update_duplicated_metadata', 'author': 'MG', }) metadata_rev_v2 = metadata_rev_v1.copy() metadata_origin_v2 = metadata_origin_v1.copy() metadata_rev_v2['metadata'] = metadata_v2 metadata_origin_v2 = { - 'id': self.origin_id_1, - 'origin_url': 'file:///dev/null', + 'id': self.origin_url_1, 'metadata': metadata_v2.copy(), 'indexer_configuration_id': tool_id, 'mappings': ['npm'], 'from_revision': self.revision_id_1, } self.storage.revision_intrinsic_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])) + [self.origin_url_1])) expected_metadata_v2 = [{ - 'id': self.origin_id_1, - 'origin_url': 'file:///dev/null', + 'id': self.origin_url_1, 'metadata': metadata_v2, 'tool': self.tools['swh-metadata-detector'], 'from_revision': self.revision_id_1, 'mappings': ['npm'], }] # metadata did change as the v2 was used to overwrite v1 self.assertEqual(actual_metadata, expected_metadata_v2) def test_origin_intrinsic_metadata_add__update_in_place_deadlock(self): # given tool_id = self.tools['swh-metadata-detector']['id'] ids = list(range(10)) example_data1 = { 'metadata': { 'version': None, 'name': None, }, 'mappings': [], } example_data2 = { 'metadata': { 'version': 'v1.1.1', 'name': 'foo', }, 'mappings': [], } metadata_rev_v1 = { 'id': self.revision_id_2, 'metadata': { 'version': None, 'name': None, }, 'mappings': [], 'indexer_configuration_id': tool_id, } data_v1 = [ { - 'id': id_, - 'origin_url': 'file:///tmp/origin%d' % id_, + 'id': 'file:///tmp/origin%d' % id_, 'from_revision': self.revision_id_2, **example_data1, 'indexer_configuration_id': tool_id, } for id_ in ids ] data_v2 = [ { - 'id': id_, - 'origin_url': 'file:///tmp/origin%d' % id_, + 'id': 'file:///tmp/origin%d' % id_, 'from_revision': self.revision_id_2, **example_data2, 'indexer_configuration_id': tool_id, } for id_ in ids ] # Remove one item from each, so that both queries have to succeed for # all items to be in the DB. data_v2a = data_v2[1:] data_v2b = list(reversed(data_v2[0:-1])) # given self.storage.revision_intrinsic_metadata_add([metadata_rev_v1]) self.storage.origin_intrinsic_metadata_add(data_v1) # when - actual_data = list(self.storage.origin_intrinsic_metadata_get(ids)) + origins = ['file:///tmp/origin%d' % i for i in ids] + actual_data = list(self.storage.origin_intrinsic_metadata_get(origins)) expected_data_v1 = [ { - 'id': id_, - 'origin_url': 'file:///tmp/origin%d' % id_, + 'id': 'file:///tmp/origin%d' % id_, 'from_revision': self.revision_id_2, **example_data1, 'tool': self.tools['swh-metadata-detector'], } for id_ in ids ] # then self.assertEqual(actual_data, expected_data_v1) # given def f1(): self.storage.origin_intrinsic_metadata_add( data_v2a, conflict_update=True) def f2(): self.storage.origin_intrinsic_metadata_add( data_v2b, conflict_update=True) t1 = threading.Thread(target=f1) t2 = threading.Thread(target=f2) t2.start() t1.start() t1.join() t2.join() - actual_data = list(self.storage.origin_intrinsic_metadata_get(ids)) + actual_data = list(self.storage.origin_intrinsic_metadata_get(origins)) expected_data_v2 = [ { - 'id': id_, - 'origin_url': 'file:///tmp/origin%d' % id_, + 'id': 'file:///tmp/origin%d' % id_, 'from_revision': self.revision_id_2, **example_data2, 'tool': self.tools['swh-metadata-detector'], } for id_ in ids ] self.maxDiff = None self.assertCountEqual(actual_data, expected_data_v2) def test_origin_intrinsic_metadata_add__duplicate_twice(self): # given tool_id = self.tools['swh-metadata-detector']['id'] metadata = { 'developmentStatus': None, 'name': None, } metadata_rev = { 'id': self.revision_id_2, 'metadata': metadata, 'mappings': ['mapping1'], 'indexer_configuration_id': tool_id, } metadata_origin = { - 'id': self.origin_id_1, - 'origin_url': 'file:///dev/zero', + 'id': self.origin_url_1, 'metadata': metadata, 'indexer_configuration_id': tool_id, 'mappings': ['mapping1'], 'from_revision': self.revision_id_2, } # when self.storage.revision_intrinsic_metadata_add([metadata_rev]) with self.assertRaises(ValueError): self.storage.origin_intrinsic_metadata_add([ metadata_origin, metadata_origin]) 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, 'metadata': metadata1, 'mappings': [], 'indexer_configuration_id': tool_id, } metadata1_origin = { - 'id': self.origin_id_1, - 'origin_url': 'file:///dev/zero', + 'id': self.origin_url_1, 'metadata': metadata1, 'mappings': [], 'indexer_configuration_id': tool_id, 'from_revision': self.revision_id_1, } metadata2 = { 'author': 'Jane Doe', } metadata2_rev = { 'id': self.revision_id_2, - 'origin_url': 'file:///dev/zero', + 'origin': self.origin_url_1, 'metadata': metadata2, 'mappings': [], 'indexer_configuration_id': tool_id, } metadata2_origin = { - 'id': self.origin_id_2, - 'origin_url': 'file:///dev/zero', + 'id': self.origin_url_2, 'metadata': metadata2, 'mappings': [], 'indexer_configuration_id': tool_id, 'from_revision': self.revision_id_2, } # when self.storage.revision_intrinsic_metadata_add([metadata1_rev]) self.storage.origin_intrinsic_metadata_add([metadata1_origin]) self.storage.revision_intrinsic_metadata_add([metadata2_rev]) self.storage.origin_intrinsic_metadata_add([metadata2_origin]) # then search = self.storage.origin_intrinsic_metadata_search_fulltext self.assertCountEqual( [res['id'] for res in search(['Doe'])], - [self.origin_id_1, self.origin_id_2]) + [self.origin_url_1, self.origin_url_2]) self.assertEqual( [res['id'] for res in search(['John', 'Doe'])], - [self.origin_id_1]) + [self.origin_url_1]) self.assertEqual( [res['id'] for res in search(['John'])], - [self.origin_id_1]) + [self.origin_url_1]) self.assertEqual( [res['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, 'metadata': metadata1, 'mappings': [], 'indexer_configuration_id': tool_id, } metadata1_origin = { - 'id': self.origin_id_1, - 'origin_url': 'file:///dev/zero', + 'id': self.origin_url_1, 'metadata': metadata1, 'mappings': [], 'indexer_configuration_id': tool_id, 'from_revision': self.revision_id_1, } metadata2 = { 'author': [ 'Random Person', 'Jane Doe', ] } metadata2_rev = { 'id': self.revision_id_2, 'metadata': metadata2, 'mappings': [], 'indexer_configuration_id': tool_id, } metadata2_origin = { - 'id': self.origin_id_2, - 'origin_url': 'file:///dev/zero', + 'id': self.origin_url_2, 'metadata': metadata2, 'mappings': [], 'indexer_configuration_id': tool_id, 'from_revision': self.revision_id_2, } # when self.storage.revision_intrinsic_metadata_add([metadata1_rev]) self.storage.origin_intrinsic_metadata_add([metadata1_origin]) self.storage.revision_intrinsic_metadata_add([metadata2_rev]) self.storage.origin_intrinsic_metadata_add([metadata2_origin]) # then search = self.storage.origin_intrinsic_metadata_search_fulltext self.assertEqual( [res['id'] for res in search(['Doe'])], - [self.origin_id_1, self.origin_id_2]) + [self.origin_url_1, self.origin_url_2]) self.assertEqual( [res['id'] for res in search(['Doe'], limit=1)], - [self.origin_id_1]) + [self.origin_url_1]) self.assertEqual( [res['id'] for res in search(['John'])], - [self.origin_id_1]) + [self.origin_url_1]) self.assertEqual( [res['id'] for res in search(['Jane'])], - [self.origin_id_2, self.origin_id_1]) + [self.origin_url_2, self.origin_url_1]) self.assertEqual( [res['id'] for res in search(['John', 'Jane'])], - [self.origin_id_1]) + [self.origin_url_1]) def _fill_origin_intrinsic_metadata(self): tool1_id = self.tools['swh-metadata-detector']['id'] tool2_id = self.tools['swh-metadata-detector2']['id'] metadata1 = { '@context': 'foo', 'author': 'John Doe', } metadata1_rev = { 'id': self.revision_id_1, 'metadata': metadata1, 'mappings': ['npm'], 'indexer_configuration_id': tool1_id, } metadata1_origin = { - 'id': self.origin_id_1, - 'origin_url': 'file:///dev/zero', + 'id': self.origin_url_1, 'metadata': metadata1, 'mappings': ['npm'], 'indexer_configuration_id': tool1_id, 'from_revision': self.revision_id_1, } metadata2 = { '@context': 'foo', 'author': 'Jane Doe', } metadata2_rev = { 'id': self.revision_id_2, 'metadata': metadata2, 'mappings': ['npm', 'gemspec'], 'indexer_configuration_id': tool2_id, } metadata2_origin = { - 'id': self.origin_id_2, - 'origin_url': 'file:///dev/zero', + 'id': self.origin_url_2, 'metadata': metadata2, 'mappings': ['npm', 'gemspec'], 'indexer_configuration_id': tool2_id, 'from_revision': self.revision_id_2, } metadata3 = { '@context': 'foo', } metadata3_rev = { 'id': self.revision_id_3, 'metadata': metadata3, 'mappings': ['npm', 'gemspec'], 'indexer_configuration_id': tool2_id, } metadata3_origin = { - 'id': self.origin_id_3, - 'origin_url': 'file:///dev/zero', + 'id': self.origin_url_3, 'metadata': metadata3, 'mappings': ['pkg-info'], 'indexer_configuration_id': tool2_id, 'from_revision': self.revision_id_3, } self.storage.revision_intrinsic_metadata_add([metadata1_rev]) self.storage.origin_intrinsic_metadata_add([metadata1_origin]) self.storage.revision_intrinsic_metadata_add([metadata2_rev]) self.storage.origin_intrinsic_metadata_add([metadata2_origin]) self.storage.revision_intrinsic_metadata_add([metadata3_rev]) self.storage.origin_intrinsic_metadata_add([metadata3_origin]) def test_origin_intrinsic_metadata_search_by_producer(self): self._fill_origin_intrinsic_metadata() tool1 = self.tools['swh-metadata-detector'] tool2 = self.tools['swh-metadata-detector2'] endpoint = self.storage.origin_intrinsic_metadata_search_by_producer # test pagination self.assertCountEqual( endpoint(ids_only=True), - [self.origin_id_1, self.origin_id_2, self.origin_id_3]) + [self.origin_url_1, self.origin_url_2, self.origin_url_3]) self.assertCountEqual( - endpoint(start=0, ids_only=True), - [self.origin_id_1, self.origin_id_2, self.origin_id_3]) + endpoint(start=self.origin_url_1, ids_only=True), + [self.origin_url_1, self.origin_url_2, self.origin_url_3]) self.assertCountEqual( - endpoint(start=0, limit=2, ids_only=True), - [self.origin_id_1, self.origin_id_2]) + endpoint(start=self.origin_url_1, limit=2, ids_only=True), + [self.origin_url_1, self.origin_url_2]) self.assertCountEqual( - endpoint(start=self.origin_id_1+1, ids_only=True), - [self.origin_id_2, self.origin_id_3]) + endpoint(start=self.origin_url_1+'2', ids_only=True), + [self.origin_url_2, self.origin_url_3]) self.assertCountEqual( - endpoint(start=self.origin_id_1+1, end=self.origin_id_3-1, + endpoint(start=self.origin_url_1+'2', end=self.origin_url_3[:-1], ids_only=True), - [self.origin_id_2]) + [self.origin_url_2]) # test mappings filtering self.assertCountEqual( endpoint(mappings=['npm'], ids_only=True), - [self.origin_id_1, self.origin_id_2]) + [self.origin_url_1, self.origin_url_2]) self.assertCountEqual( endpoint(mappings=['npm', 'gemspec'], ids_only=True), - [self.origin_id_1, self.origin_id_2]) + [self.origin_url_1, self.origin_url_2]) self.assertCountEqual( endpoint(mappings=['gemspec'], ids_only=True), - [self.origin_id_2]) + [self.origin_url_2]) self.assertCountEqual( endpoint(mappings=['pkg-info'], ids_only=True), - [self.origin_id_3]) + [self.origin_url_3]) self.assertCountEqual( endpoint(mappings=['foobar'], ids_only=True), []) # test pagination + mappings self.assertCountEqual( endpoint(mappings=['npm'], limit=1, ids_only=True), - [self.origin_id_1]) + [self.origin_url_1]) # test tool filtering self.assertCountEqual( endpoint(tool_ids=[tool1['id']], ids_only=True), - [self.origin_id_1]) + [self.origin_url_1]) self.assertCountEqual( endpoint(tool_ids=[tool2['id']], ids_only=True), - [self.origin_id_2, self.origin_id_3]) + [self.origin_url_2, self.origin_url_3]) self.assertCountEqual( endpoint(tool_ids=[tool1['id'], tool2['id']], ids_only=True), - [self.origin_id_1, self.origin_id_2, self.origin_id_3]) + [self.origin_url_1, self.origin_url_2, self.origin_url_3]) # test ids_only=False self.assertEqual(list(endpoint(mappings=['gemspec'])), [{ - 'id': self.origin_id_2, - 'origin_url': 'file:///dev/zero', + 'id': self.origin_url_2, 'metadata': { '@context': 'foo', 'author': 'Jane Doe', }, 'mappings': ['npm', 'gemspec'], 'tool': tool2, 'from_revision': self.revision_id_2, }]) def test_origin_intrinsic_metadata_stats(self): self._fill_origin_intrinsic_metadata() result = self.storage.origin_intrinsic_metadata_stats() self.assertEqual(result, { 'per_mapping': { 'gemspec': 1, 'npm': 2, 'pkg-info': 1, 'codemeta': 0, 'maven': 0, }, 'total': 3, 'non_empty': 2, }) def test_indexer_configuration_add(self): tool = { 'tool_name': 'some-unknown-tool', 'tool_version': 'some-version', 'tool_configuration': {"debian-package": "some-package"}, } actual_tool = self.storage.indexer_configuration_get(tool) self.assertIsNone(actual_tool) # does not exist # add it actual_tools = list(self.storage.indexer_configuration_add([tool])) self.assertEqual(len(actual_tools), 1) actual_tool = actual_tools[0] self.assertIsNotNone(actual_tool) # now it exists new_id = actual_tool.pop('id') self.assertEqual(actual_tool, tool) actual_tools2 = list(self.storage.indexer_configuration_add([tool])) actual_tool2 = actual_tools2[0] self.assertIsNotNone(actual_tool2) # now it exists new_id2 = actual_tool2.pop('id') self.assertEqual(new_id, new_id2) self.assertEqual(actual_tool, actual_tool2) def test_indexer_configuration_add_multiple(self): tool = { 'tool_name': 'some-unknown-tool', 'tool_version': 'some-version', 'tool_configuration': {"debian-package": "some-package"}, } actual_tools = list(self.storage.indexer_configuration_add([tool])) self.assertEqual(len(actual_tools), 1) new_tools = [tool, { 'tool_name': 'yet-another-tool', 'tool_version': 'version', 'tool_configuration': {}, }] actual_tools = list(self.storage.indexer_configuration_add(new_tools)) self.assertEqual(len(actual_tools), 2) # order not guaranteed, so we iterate over results to check for tool in actual_tools: _id = tool.pop('id') self.assertIsNotNone(_id) self.assertIn(tool, new_tools) def test_indexer_configuration_get_missing(self): tool = { 'tool_name': 'unknown-tool', 'tool_version': '3.1.0rc2-31-ga2cbb8c', 'tool_configuration': {"command_line": "nomossa "}, } actual_tool = self.storage.indexer_configuration_get(tool) self.assertIsNone(actual_tool) def test_indexer_configuration_get(self): tool = { 'tool_name': 'nomos', 'tool_version': '3.1.0rc2-31-ga2cbb8c', 'tool_configuration': {"command_line": "nomossa "}, } self.storage.indexer_configuration_add([tool]) actual_tool = self.storage.indexer_configuration_get(tool) expected_tool = tool.copy() del actual_tool['id'] self.assertEqual(expected_tool, actual_tool) def test_indexer_configuration_metadata_get_missing_context(self): tool = { 'tool_name': 'swh-metadata-translator', 'tool_version': '0.0.1', 'tool_configuration': {"context": "unknown-context"}, } actual_tool = self.storage.indexer_configuration_get(tool) self.assertIsNone(actual_tool) def test_indexer_configuration_metadata_get(self): tool = { 'tool_name': 'swh-metadata-translator', 'tool_version': '0.0.1', 'tool_configuration': {"type": "local", "context": "NpmMapping"}, } self.storage.indexer_configuration_add([tool]) actual_tool = self.storage.indexer_configuration_get(tool) expected_tool = tool.copy() expected_tool['id'] = actual_tool['id'] self.assertEqual(expected_tool, actual_tool) @pytest.mark.property_based def test_generate_content_mimetype_get_range_limit_none(self): """mimetype_get_range call with wrong limit input should fail""" with self.assertRaises(ValueError) as e: self.storage.content_mimetype_get_range( start=None, end=None, indexer_configuration_id=None, limit=None) self.assertEqual(e.exception.args, ( 'Development error: limit should not be None',)) @pytest.mark.property_based @given(gen_content_mimetypes(min_size=1, max_size=4)) def test_generate_content_mimetype_get_range_no_limit(self, mimetypes): """mimetype_get_range returns mimetypes within range provided""" self.reset_storage_tables() # add mimetypes to storage self.storage.content_mimetype_add(mimetypes) # All ids from the db content_ids = sorted([c['id'] for c in mimetypes]) start = content_ids[0] end = content_ids[-1] # retrieve mimetypes tool_id = mimetypes[0]['indexer_configuration_id'] actual_result = self.storage.content_mimetype_get_range( start, end, indexer_configuration_id=tool_id) actual_ids = actual_result['ids'] actual_next = actual_result['next'] self.assertEqual(len(mimetypes), len(actual_ids)) self.assertIsNone(actual_next) self.assertEqual(content_ids, actual_ids) @pytest.mark.property_based @given(gen_content_mimetypes(min_size=4, max_size=4)) def test_generate_content_mimetype_get_range_limit(self, mimetypes): """mimetype_get_range paginates results if limit exceeded""" self.reset_storage_tables() # add mimetypes to storage self.storage.content_mimetype_add(mimetypes) # input the list of sha1s we want from storage content_ids = sorted([c['id'] for c in mimetypes]) start = content_ids[0] end = content_ids[-1] # retrieve mimetypes limited to 3 results limited_results = len(mimetypes) - 1 tool_id = mimetypes[0]['indexer_configuration_id'] actual_result = self.storage.content_mimetype_get_range( start, end, indexer_configuration_id=tool_id, limit=limited_results) actual_ids = actual_result['ids'] actual_next = actual_result['next'] self.assertEqual(limited_results, len(actual_ids)) self.assertIsNotNone(actual_next) self.assertEqual(actual_next, content_ids[-1]) expected_mimetypes = content_ids[:-1] self.assertEqual(expected_mimetypes, actual_ids) # retrieve next part actual_results2 = self.storage.content_mimetype_get_range( start=end, end=end, indexer_configuration_id=tool_id) actual_ids2 = actual_results2['ids'] actual_next2 = actual_results2['next'] self.assertIsNone(actual_next2) expected_mimetypes2 = [content_ids[-1]] self.assertEqual(expected_mimetypes2, actual_ids2) @pytest.mark.property_based def test_generate_content_fossology_license_get_range_limit_none(self): """license_get_range call with wrong limit input should fail""" with self.assertRaises(ValueError) as e: self.storage.content_fossology_license_get_range( start=None, end=None, indexer_configuration_id=None, limit=None) self.assertEqual(e.exception.args, ( 'Development error: limit should not be None',)) @pytest.mark.property_based def prepare_mimetypes_from(self, fossology_licenses): """Fossology license needs some consistent data in db to run. """ mimetypes = [] for c in fossology_licenses: mimetypes.append({ 'id': c['id'], 'mimetype': 'text/plain', 'encoding': 'utf-8', 'indexer_configuration_id': c['indexer_configuration_id'], }) return mimetypes @pytest.mark.property_based @given(gen_content_fossology_licenses(min_size=1, max_size=4)) def test_generate_content_fossology_license_get_range_no_limit( self, fossology_licenses): """license_get_range returns licenses within range provided""" self.reset_storage_tables() # craft some consistent mimetypes mimetypes = self.prepare_mimetypes_from(fossology_licenses) self.storage.content_mimetype_add(mimetypes) # add fossology_licenses to storage self.storage.content_fossology_license_add(fossology_licenses) # All ids from the db content_ids = sorted([c['id'] for c in fossology_licenses]) start = content_ids[0] end = content_ids[-1] # retrieve fossology_licenses tool_id = fossology_licenses[0]['indexer_configuration_id'] actual_result = self.storage.content_fossology_license_get_range( start, end, indexer_configuration_id=tool_id) actual_ids = actual_result['ids'] actual_next = actual_result['next'] self.assertEqual(len(fossology_licenses), len(actual_ids)) self.assertIsNone(actual_next) self.assertEqual(content_ids, actual_ids) @pytest.mark.property_based @given(gen_content_fossology_licenses(min_size=1, max_size=4), gen_content_mimetypes(min_size=1, max_size=1)) def test_generate_content_fossology_license_get_range_no_limit_with_filter( self, fossology_licenses, mimetypes): """This filters non textual, then returns results within range""" self.reset_storage_tables() # craft some consistent mimetypes _mimetypes = self.prepare_mimetypes_from(fossology_licenses) # add binary mimetypes which will get filtered out in results for m in mimetypes: _mimetypes.append({ 'mimetype': 'binary', **m, }) self.storage.content_mimetype_add(_mimetypes) # add fossology_licenses to storage self.storage.content_fossology_license_add(fossology_licenses) # All ids from the db content_ids = sorted([c['id'] for c in fossology_licenses]) start = content_ids[0] end = content_ids[-1] # retrieve fossology_licenses tool_id = fossology_licenses[0]['indexer_configuration_id'] actual_result = self.storage.content_fossology_license_get_range( start, end, indexer_configuration_id=tool_id) actual_ids = actual_result['ids'] actual_next = actual_result['next'] self.assertEqual(len(fossology_licenses), len(actual_ids)) self.assertIsNone(actual_next) self.assertEqual(content_ids, actual_ids) @pytest.mark.property_based @given(gen_content_fossology_licenses(min_size=4, max_size=4)) def test_generate_fossology_license_get_range_limit( self, fossology_licenses): """fossology_license_get_range paginates results if limit exceeded""" self.reset_storage_tables() # craft some consistent mimetypes mimetypes = self.prepare_mimetypes_from(fossology_licenses) # add fossology_licenses to storage self.storage.content_mimetype_add(mimetypes) self.storage.content_fossology_license_add(fossology_licenses) # input the list of sha1s we want from storage content_ids = sorted([c['id'] for c in fossology_licenses]) start = content_ids[0] end = content_ids[-1] # retrieve fossology_licenses limited to 3 results limited_results = len(fossology_licenses) - 1 tool_id = fossology_licenses[0]['indexer_configuration_id'] actual_result = self.storage.content_fossology_license_get_range( start, end, indexer_configuration_id=tool_id, limit=limited_results) actual_ids = actual_result['ids'] actual_next = actual_result['next'] self.assertEqual(limited_results, len(actual_ids)) self.assertIsNotNone(actual_next) self.assertEqual(actual_next, content_ids[-1]) expected_fossology_licenses = content_ids[:-1] self.assertEqual(expected_fossology_licenses, actual_ids) # retrieve next part actual_results2 = self.storage.content_fossology_license_get_range( start=end, end=end, indexer_configuration_id=tool_id) actual_ids2 = actual_results2['ids'] actual_next2 = actual_results2['next'] self.assertIsNone(actual_next2) expected_fossology_licenses2 = [content_ids[-1]] self.assertEqual(expected_fossology_licenses2, actual_ids2) @pytest.mark.db class IndexerTestStorage(CommonTestStorage, BasePgTestStorage, unittest.TestCase): """Running the tests locally. For the client api tests (remote storage), see `class`:swh.indexer.storage.test_api_client:TestRemoteStorage class. """ pass def test_mapping_names(): assert set(MAPPING_NAMES) == {m.name for m in MAPPINGS.values()} diff --git a/swh/indexer/tests/test_cli.py b/swh/indexer/tests/test_cli.py index 70bd442..8dad2c7 100644 --- a/swh/indexer/tests/test_cli.py +++ b/swh/indexer/tests/test_cli.py @@ -1,362 +1,361 @@ # Copyright (C) 2019 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information from functools import reduce import re import tempfile from unittest.mock import patch from click.testing import CliRunner from swh.journal.tests.utils import FakeKafkaMessage, MockedKafkaConsumer from swh.model.hashutil import hash_to_bytes from swh.indexer.cli import cli CLI_CONFIG = ''' scheduler: cls: foo args: {} storage: cls: memory args: {} indexer_storage: cls: memory args: {} ''' def fill_idx_storage(idx_storage, nb_rows): tools = [ { 'tool_name': 'tool %d' % i, 'tool_version': '0.0.1', 'tool_configuration': {}, } for i in range(2) ] tools = idx_storage.indexer_configuration_add(tools) origin_metadata = [ { - 'id': origin_id, - 'origin_url': 'file:///dev/zero', + 'id': 'file://dev/%04d' % origin_id, 'from_revision': hash_to_bytes('abcd{:0>4}'.format(origin_id)), 'indexer_configuration_id': tools[origin_id % 2]['id'], 'metadata': {'name': 'origin %d' % origin_id}, 'mappings': ['mapping%d' % (origin_id % 10)] } for origin_id in range(nb_rows) ] revision_metadata = [ { 'id': hash_to_bytes('abcd{:0>4}'.format(origin_id)), 'indexer_configuration_id': tools[origin_id % 2]['id'], 'metadata': {'name': 'origin %d' % origin_id}, 'mappings': ['mapping%d' % (origin_id % 10)] } for origin_id in range(nb_rows) ] idx_storage.revision_intrinsic_metadata_add(revision_metadata) idx_storage.origin_intrinsic_metadata_add(origin_metadata) return [tool['id'] for tool in tools] def _origins_in_task_args(tasks): """Returns the set of origins contained in the arguments of the provided tasks (assumed to be of type index-origin-metadata).""" return reduce( set.union, (set(task['arguments']['args'][0]) for task in tasks), set() ) def _assert_tasks_for_origins(tasks, origins): expected_kwargs = {"policy_update": "update-dups"} assert {task['type'] for task in tasks} == {'index-origin-metadata'} assert all(len(task['arguments']['args']) == 1 for task in tasks) for task in tasks: assert task['arguments']['kwargs'] == expected_kwargs, task - assert _origins_in_task_args(tasks) == set(origins) + assert _origins_in_task_args(tasks) == set([ + 'file://dev/%04d' % i for i in origins]) def invoke(scheduler, catch_exceptions, args): runner = CliRunner() with patch('swh.indexer.cli.get_scheduler') as get_scheduler_mock, \ tempfile.NamedTemporaryFile('a', suffix='.yml') as config_fd: config_fd.write(CLI_CONFIG) config_fd.seek(0) get_scheduler_mock.return_value = scheduler result = runner.invoke(cli, ['-C' + config_fd.name] + args) if not catch_exceptions and result.exception: print(result.output) raise result.exception return result def test_mapping_list(indexer_scheduler): result = invoke(indexer_scheduler, False, [ 'mapping', 'list', ]) expected_output = '\n'.join([ 'codemeta', 'gemspec', 'maven', 'npm', 'pkg-info', '', ]) assert result.exit_code == 0, result.output assert result.output == expected_output def test_mapping_list_terms(indexer_scheduler): result = invoke(indexer_scheduler, False, [ 'mapping', 'list-terms', ]) assert result.exit_code == 0, result.output assert re.search(r'http://schema.org/url:\n.*npm', result.output) assert re.search(r'http://schema.org/url:\n.*codemeta', result.output) assert re.search( r'https://codemeta.github.io/terms/developmentStatus:\n\tcodemeta', result.output) def test_mapping_list_terms_exclude(indexer_scheduler): result = invoke(indexer_scheduler, False, [ 'mapping', 'list-terms', '--exclude-mapping', 'codemeta' ]) assert result.exit_code == 0, result.output assert re.search(r'http://schema.org/url:\n.*npm', result.output) assert not re.search(r'http://schema.org/url:\n.*codemeta', result.output) assert not re.search( r'https://codemeta.github.io/terms/developmentStatus:\n\tcodemeta', result.output) @patch('swh.scheduler.cli.utils.TASK_BATCH_SIZE', 3) @patch('swh.scheduler.cli_utils.TASK_BATCH_SIZE', 3) def test_origin_metadata_reindex_empty_db( indexer_scheduler, idx_storage, storage): result = invoke(indexer_scheduler, False, [ 'schedule', 'reindex_origin_metadata', ]) expected_output = ( 'Nothing to do (no origin metadata matched the criteria).\n' ) assert result.exit_code == 0, result.output assert result.output == expected_output tasks = indexer_scheduler.search_tasks() assert len(tasks) == 0 @patch('swh.scheduler.cli.utils.TASK_BATCH_SIZE', 3) @patch('swh.scheduler.cli_utils.TASK_BATCH_SIZE', 3) def test_origin_metadata_reindex_divisor( indexer_scheduler, idx_storage, storage): """Tests the re-indexing when origin_batch_size*task_batch_size is a divisor of nb_origins.""" fill_idx_storage(idx_storage, 90) result = invoke(indexer_scheduler, False, [ 'schedule', 'reindex_origin_metadata', ]) # Check the output expected_output = ( 'Scheduled 3 tasks (30 origins).\n' 'Scheduled 6 tasks (60 origins).\n' 'Scheduled 9 tasks (90 origins).\n' 'Done.\n' ) assert result.exit_code == 0, result.output assert result.output == expected_output # Check scheduled tasks tasks = indexer_scheduler.search_tasks() assert len(tasks) == 9 _assert_tasks_for_origins(tasks, range(90)) @patch('swh.scheduler.cli.utils.TASK_BATCH_SIZE', 3) @patch('swh.scheduler.cli_utils.TASK_BATCH_SIZE', 3) def test_origin_metadata_reindex_dry_run( indexer_scheduler, idx_storage, storage): """Tests the re-indexing when origin_batch_size*task_batch_size is a divisor of nb_origins.""" fill_idx_storage(idx_storage, 90) result = invoke(indexer_scheduler, False, [ 'schedule', '--dry-run', 'reindex_origin_metadata', ]) # Check the output expected_output = ( 'Scheduled 3 tasks (30 origins).\n' 'Scheduled 6 tasks (60 origins).\n' 'Scheduled 9 tasks (90 origins).\n' 'Done.\n' ) assert result.exit_code == 0, result.output assert result.output == expected_output # Check scheduled tasks tasks = indexer_scheduler.search_tasks() assert len(tasks) == 0 @patch('swh.scheduler.cli.utils.TASK_BATCH_SIZE', 3) @patch('swh.scheduler.cli_utils.TASK_BATCH_SIZE', 3) def test_origin_metadata_reindex_nondivisor( indexer_scheduler, idx_storage, storage): """Tests the re-indexing when neither origin_batch_size or task_batch_size is a divisor of nb_origins.""" fill_idx_storage(idx_storage, 70) result = invoke(indexer_scheduler, False, [ 'schedule', 'reindex_origin_metadata', '--batch-size', '20', ]) # Check the output expected_output = ( 'Scheduled 3 tasks (60 origins).\n' 'Scheduled 4 tasks (70 origins).\n' 'Done.\n' ) assert result.exit_code == 0, result.output assert result.output == expected_output # Check scheduled tasks tasks = indexer_scheduler.search_tasks() assert len(tasks) == 4 _assert_tasks_for_origins(tasks, range(70)) @patch('swh.scheduler.cli.utils.TASK_BATCH_SIZE', 3) @patch('swh.scheduler.cli_utils.TASK_BATCH_SIZE', 3) def test_origin_metadata_reindex_filter_one_mapping( indexer_scheduler, idx_storage, storage): """Tests the re-indexing when origin_batch_size*task_batch_size is a divisor of nb_origins.""" fill_idx_storage(idx_storage, 110) result = invoke(indexer_scheduler, False, [ 'schedule', 'reindex_origin_metadata', '--mapping', 'mapping1', ]) # Check the output expected_output = ( 'Scheduled 2 tasks (11 origins).\n' 'Done.\n' ) assert result.exit_code == 0, result.output assert result.output == expected_output # Check scheduled tasks tasks = indexer_scheduler.search_tasks() assert len(tasks) == 2 _assert_tasks_for_origins( tasks, [1, 11, 21, 31, 41, 51, 61, 71, 81, 91, 101]) @patch('swh.scheduler.cli.utils.TASK_BATCH_SIZE', 3) @patch('swh.scheduler.cli_utils.TASK_BATCH_SIZE', 3) def test_origin_metadata_reindex_filter_two_mappings( indexer_scheduler, idx_storage, storage): """Tests the re-indexing when origin_batch_size*task_batch_size is a divisor of nb_origins.""" fill_idx_storage(idx_storage, 110) result = invoke(indexer_scheduler, False, [ 'schedule', 'reindex_origin_metadata', '--mapping', 'mapping1', '--mapping', 'mapping2', ]) # Check the output expected_output = ( 'Scheduled 3 tasks (22 origins).\n' 'Done.\n' ) assert result.exit_code == 0, result.output assert result.output == expected_output # Check scheduled tasks tasks = indexer_scheduler.search_tasks() assert len(tasks) == 3 _assert_tasks_for_origins( tasks, [1, 11, 21, 31, 41, 51, 61, 71, 81, 91, 101, 2, 12, 22, 32, 42, 52, 62, 72, 82, 92, 102]) @patch('swh.scheduler.cli.utils.TASK_BATCH_SIZE', 3) @patch('swh.scheduler.cli_utils.TASK_BATCH_SIZE', 3) def test_origin_metadata_reindex_filter_one_tool( indexer_scheduler, idx_storage, storage): """Tests the re-indexing when origin_batch_size*task_batch_size is a divisor of nb_origins.""" tool_ids = fill_idx_storage(idx_storage, 110) result = invoke(indexer_scheduler, False, [ 'schedule', 'reindex_origin_metadata', '--tool-id', str(tool_ids[0]), ]) # Check the output expected_output = ( 'Scheduled 3 tasks (30 origins).\n' 'Scheduled 6 tasks (55 origins).\n' 'Done.\n' ) assert result.exit_code == 0, result.output assert result.output == expected_output # Check scheduled tasks tasks = indexer_scheduler.search_tasks() assert len(tasks) == 6 _assert_tasks_for_origins( tasks, [x*2 for x in range(55)]) def test_journal_client(storage, indexer_scheduler): - """Tests the re-indexing when origin_batch_size*task_batch_size is a - divisor of nb_origins.""" + """Test the 'swh indexer journal-client' cli tool.""" message = FakeKafkaMessage('swh.journal.objects.origin_visit', 'bogus', { 'status': 'full', 'origin': { - 'url': 'file:///dev/zero', + 'url': 'file://dev/0000', } }) consumer = MockedKafkaConsumer([message]) with patch('swh.journal.client.Consumer', return_value=consumer): result = invoke(indexer_scheduler, False, [ 'journal-client', '--max-messages', '1', '--broker', '192.0.2.1', '--prefix', 'swh.journal.objects', '--group-id', 'test-consumer', ]) # Check the output expected_output = ( 'Processed 1 messages.\n' 'Done.\n' ) assert result.exit_code == 0, result.output assert result.output == expected_output # Check scheduled tasks tasks = indexer_scheduler.search_tasks() assert len(tasks) == 1 _assert_tasks_for_origins( tasks, - ['file:///dev/zero']) + [0]) diff --git a/swh/indexer/tests/test_fossology_license.py b/swh/indexer/tests/test_fossology_license.py index 75803ed..cd6030b 100644 --- a/swh/indexer/tests/test_fossology_license.py +++ b/swh/indexer/tests/test_fossology_license.py @@ -1,180 +1,181 @@ # Copyright (C) 2017-2018 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import unittest -from unittest.mock import patch - import pytest +from unittest.mock import patch +from typing import Any, Dict + from swh.indexer import fossology_license from swh.indexer.fossology_license import ( FossologyLicenseIndexer, FossologyLicenseRangeIndexer, compute_license ) from swh.indexer.tests.utils import ( SHA1_TO_LICENSES, CommonContentIndexerTest, CommonContentIndexerRangeTest, BASE_TEST_CONFIG, fill_storage, fill_obj_storage, filter_dict, ) class BasicTest(unittest.TestCase): @patch('swh.indexer.fossology_license.subprocess') def test_compute_license(self, mock_subprocess): """Computing licenses from a raw content should return results """ for path, intermediary_result, output in [ (b'some/path', None, []), (b'some/path/2', [], []), (b'other/path', ' contains license(s) GPL,AGPL', ['GPL', 'AGPL'])]: mock_subprocess.check_output.return_value = intermediary_result actual_result = compute_license(path, log=None) self.assertEqual(actual_result, { 'licenses': output, 'path': path, }) def mock_compute_license(path, log=None): """path is the content identifier """ if isinstance(id, bytes): path = path.decode('utf-8') # path is something like /tmp/tmpXXX/ so we keep only the sha1 part path = path.split('/')[-1] return { 'licenses': SHA1_TO_LICENSES.get(path) } CONFIG = { **BASE_TEST_CONFIG, 'workdir': '/tmp', 'tools': { 'name': 'nomos', 'version': '3.1.0rc2-31-ga2cbb8c', 'configuration': { 'command_line': 'nomossa ', }, }, -} +} # type: Dict[str, Any] RANGE_CONFIG = dict(list(CONFIG.items()) + [('write_batch_size', 100)]) class TestFossologyLicenseIndexer(CommonContentIndexerTest, unittest.TestCase): """Language indexer test scenarios: - Known sha1s in the input list have their data indexed - Unknown sha1 in the input list are not indexed """ def get_indexer_results(self, ids): yield from self.idx_storage.content_fossology_license_get(ids) def setUp(self): super().setUp() # replace actual license computation with a mock self.orig_compute_license = fossology_license.compute_license fossology_license.compute_license = mock_compute_license self.indexer = FossologyLicenseIndexer(CONFIG) self.indexer.catch_exceptions = False self.idx_storage = self.indexer.idx_storage fill_storage(self.indexer.storage) fill_obj_storage(self.indexer.objstorage) self.id0 = '01c9379dfc33803963d07c1ccc748d3fe4c96bb5' self.id1 = '688a5ef812c53907562fe379d4b3851e69c7cb15' self.id2 = 'da39a3ee5e6b4b0d3255bfef95601890afd80709' # empty content tool = {k.replace('tool_', ''): v for (k, v) in self.indexer.tool.items()} # then self.expected_results = { self.id0: { 'tool': tool, 'licenses': SHA1_TO_LICENSES[self.id0], }, self.id1: { 'tool': tool, 'licenses': SHA1_TO_LICENSES[self.id1], }, self.id2: { 'tool': tool, 'licenses': SHA1_TO_LICENSES[self.id2], } } def tearDown(self): super().tearDown() fossology_license.compute_license = self.orig_compute_license class TestFossologyLicenseRangeIndexer( CommonContentIndexerRangeTest, unittest.TestCase): """Range Fossology License Indexer tests. - new data within range are indexed - no data outside a range are indexed - with filtering existing indexed data prior to compute new index - without filtering existing indexed data prior to compute new index """ def setUp(self): super().setUp() # replace actual license computation with a mock self.orig_compute_license = fossology_license.compute_license fossology_license.compute_license = mock_compute_license self.indexer = FossologyLicenseRangeIndexer(config=RANGE_CONFIG) self.indexer.catch_exceptions = False fill_storage(self.indexer.storage) fill_obj_storage(self.indexer.objstorage) self.id0 = '01c9379dfc33803963d07c1ccc748d3fe4c96bb5' self.id1 = '02fb2c89e14f7fab46701478c83779c7beb7b069' self.id2 = '103bc087db1d26afc3a0283f38663d081e9b01e6' tool_id = self.indexer.tool['id'] self.expected_results = { self.id0: { 'id': self.id0, 'indexer_configuration_id': tool_id, 'licenses': SHA1_TO_LICENSES[self.id0] }, self.id1: { 'id': self.id1, 'indexer_configuration_id': tool_id, 'licenses': SHA1_TO_LICENSES[self.id1] }, self.id2: { 'id': self.id2, 'indexer_configuration_id': tool_id, 'licenses': SHA1_TO_LICENSES[self.id2] } } def tearDown(self): super().tearDown() fossology_license.compute_license = self.orig_compute_license def test_fossology_w_no_tool(): with pytest.raises(ValueError): FossologyLicenseIndexer(config=filter_dict(CONFIG, 'tools')) def test_fossology_range_w_no_tool(): with pytest.raises(ValueError): FossologyLicenseRangeIndexer(config=filter_dict(RANGE_CONFIG, 'tools')) diff --git a/swh/indexer/tests/test_metadata.py b/swh/indexer/tests/test_metadata.py index 045f4de..ccdd7e7 100644 --- a/swh/indexer/tests/test_metadata.py +++ b/swh/indexer/tests/test_metadata.py @@ -1,1207 +1,1211 @@ # Copyright (C) 2017-2018 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import json import unittest +import attr + from hypothesis import given, strategies, settings, HealthCheck from swh.model.hashutil import hash_to_bytes from swh.indexer.codemeta import CODEMETA_TERMS, CROSSWALK_TABLE from swh.indexer.codemeta import merge_documents from swh.indexer.metadata_dictionary import MAPPINGS from swh.indexer.metadata_dictionary.base import merge_values +from swh.indexer.metadata_dictionary.maven import MavenMapping +from swh.indexer.metadata_dictionary.npm import NpmMapping +from swh.indexer.metadata_dictionary.ruby import GemspecMapping from swh.indexer.metadata_detector import ( detect_metadata ) from swh.indexer.metadata import ( ContentMetadataIndexer, RevisionMetadataIndexer ) from .utils import ( BASE_TEST_CONFIG, fill_obj_storage, fill_storage, YARN_PARSER_METADATA, json_document_strategy, xml_document_strategy, ) TRANSLATOR_TOOL = { 'name': 'swh-metadata-translator', 'version': '0.0.2', 'configuration': { 'type': 'local', 'context': 'NpmMapping' } } class ContentMetadataTestIndexer(ContentMetadataIndexer): """Specific Metadata whose configuration is enough to satisfy the indexing tests. """ def parse_config_file(self, *args, **kwargs): assert False, 'should not be called; the rev indexer configures it.' REVISION_METADATA_CONFIG = { **BASE_TEST_CONFIG, 'tools': TRANSLATOR_TOOL, } class Metadata(unittest.TestCase): """ Tests metadata_mock_tool tool for Metadata detection """ def setUp(self): """ shows the entire diff in the results """ self.maxDiff = None self.npm_mapping = MAPPINGS['NpmMapping']() self.codemeta_mapping = MAPPINGS['CodemetaMapping']() self.maven_mapping = MAPPINGS['MavenMapping']() self.pkginfo_mapping = MAPPINGS['PythonPkginfoMapping']() self.gemspec_mapping = MAPPINGS['GemspecMapping']() def test_crosstable(self): self.assertEqual(CROSSWALK_TABLE['NodeJS'], { 'repository': 'http://schema.org/codeRepository', 'os': 'http://schema.org/operatingSystem', 'cpu': 'http://schema.org/processorRequirements', 'engines': 'http://schema.org/processorRequirements', 'author': 'http://schema.org/author', 'author.email': 'http://schema.org/email', 'author.name': 'http://schema.org/name', 'contributor': 'http://schema.org/contributor', 'keywords': 'http://schema.org/keywords', 'license': 'http://schema.org/license', 'version': 'http://schema.org/version', 'description': 'http://schema.org/description', 'name': 'http://schema.org/name', 'bugs': 'https://codemeta.github.io/terms/issueTracker', 'homepage': 'http://schema.org/url' }) def test_merge_values(self): self.assertEqual( merge_values('a', 'b'), ['a', 'b']) self.assertEqual( merge_values(['a', 'b'], 'c'), ['a', 'b', 'c']) self.assertEqual( merge_values('a', ['b', 'c']), ['a', 'b', 'c']) self.assertEqual( merge_values({'@list': ['a']}, {'@list': ['b']}), {'@list': ['a', 'b']}) self.assertEqual( merge_values({'@list': ['a', 'b']}, {'@list': ['c']}), {'@list': ['a', 'b', 'c']}) with self.assertRaises(ValueError): merge_values({'@list': ['a']}, 'b') with self.assertRaises(ValueError): merge_values('a', {'@list': ['b']}) with self.assertRaises(ValueError): merge_values({'@list': ['a']}, ['b']) with self.assertRaises(ValueError): merge_values(['a'], {'@list': ['b']}) self.assertEqual( merge_values('a', None), 'a') self.assertEqual( merge_values(['a', 'b'], None), ['a', 'b']) self.assertEqual( merge_values(None, ['b', 'c']), ['b', 'c']) self.assertEqual( merge_values({'@list': ['a']}, None), {'@list': ['a']}) self.assertEqual( merge_values(None, {'@list': ['a']}), {'@list': ['a']}) def test_compute_metadata_none(self): """ testing content empty content is empty should return None """ # given content = b"" # None if no metadata was found or an error occurred declared_metadata = None # when result = self.npm_mapping.translate(content) # then self.assertEqual(declared_metadata, result) def test_compute_metadata_npm(self): """ testing only computation of metadata with hard_mapping_npm """ # given content = b""" { "name": "test_metadata", "version": "0.0.2", "description": "Simple package.json test for indexer", "repository": { "type": "git", "url": "https://github.com/moranegg/metadata_test" }, "author": { "email": "moranegg@example.com", "name": "Morane G" } } """ declared_metadata = { '@context': 'https://doi.org/10.5063/schema/codemeta-2.0', 'type': 'SoftwareSourceCode', 'name': 'test_metadata', 'version': '0.0.2', 'description': 'Simple package.json test for indexer', 'codeRepository': 'git+https://github.com/moranegg/metadata_test', 'author': [{ 'type': 'Person', 'name': 'Morane G', 'email': 'moranegg@example.com', }], } # when result = self.npm_mapping.translate(content) # then self.assertEqual(declared_metadata, result) def test_merge_documents(self): """ Test the creation of a coherent minimal metadata set """ # given metadata_list = [{ '@context': 'https://doi.org/10.5063/schema/codemeta-2.0', 'name': 'test_1', 'version': '0.0.2', 'description': 'Simple package.json test for indexer', 'codeRepository': 'git+https://github.com/moranegg/metadata_test', }, { '@context': 'https://doi.org/10.5063/schema/codemeta-2.0', 'name': 'test_0_1', 'version': '0.0.2', 'description': 'Simple package.json test for indexer', 'codeRepository': 'git+https://github.com/moranegg/metadata_test' }, { '@context': 'https://doi.org/10.5063/schema/codemeta-2.0', 'name': 'test_metadata', 'version': '0.0.2', 'author': 'moranegg', }] # when results = merge_documents(metadata_list) # then expected_results = { '@context': 'https://doi.org/10.5063/schema/codemeta-2.0', "version": '0.0.2', "description": 'Simple package.json test for indexer', "name": ['test_1', 'test_0_1', 'test_metadata'], "author": ['moranegg'], "codeRepository": 'git+https://github.com/moranegg/metadata_test', } self.assertEqual(expected_results, results) def test_index_content_metadata_npm(self): """ testing NPM with package.json - one sha1 uses a file that can't be translated to metadata and should return None in the translated metadata """ # given sha1s = [ hash_to_bytes('26a9f72a7c87cc9205725cfd879f514ff4f3d8d5'), hash_to_bytes('d4c647f0fc257591cc9ba1722484229780d1c607'), hash_to_bytes('02fb2c89e14f7fab46701478c83779c7beb7b069'), ] # this metadata indexer computes only metadata for package.json # in npm context with a hard mapping config = BASE_TEST_CONFIG.copy() config['tools'] = [TRANSLATOR_TOOL] metadata_indexer = ContentMetadataTestIndexer(config=config) fill_obj_storage(metadata_indexer.objstorage) fill_storage(metadata_indexer.storage) # when metadata_indexer.run(sha1s, policy_update='ignore-dups') results = list(metadata_indexer.idx_storage.content_metadata_get( sha1s)) expected_results = [{ 'metadata': { '@context': 'https://doi.org/10.5063/schema/codemeta-2.0', 'type': 'SoftwareSourceCode', 'codeRepository': 'git+https://github.com/moranegg/metadata_test', 'description': 'Simple package.json test for indexer', 'name': 'test_metadata', 'version': '0.0.1' }, 'id': hash_to_bytes('26a9f72a7c87cc9205725cfd879f514ff4f3d8d5'), }, { 'metadata': { '@context': 'https://doi.org/10.5063/schema/codemeta-2.0', 'type': 'SoftwareSourceCode', 'issueTracker': 'https://github.com/npm/npm/issues', 'author': [{ 'type': 'Person', 'name': 'Isaac Z. Schlueter', 'email': 'i@izs.me', 'url': 'http://blog.izs.me', }], 'codeRepository': 'git+https://github.com/npm/npm', 'description': 'a package manager for JavaScript', 'license': 'https://spdx.org/licenses/Artistic-2.0', 'version': '5.0.3', 'name': 'npm', 'keywords': [ 'install', 'modules', 'package manager', 'package.json' ], 'url': 'https://docs.npmjs.com/' }, 'id': hash_to_bytes('d4c647f0fc257591cc9ba1722484229780d1c607') }] for result in results: del result['tool'] # The assertion below returns False sometimes because of nested lists self.assertEqual(expected_results, results) def test_npm_bugs_normalization(self): # valid dictionary package_json = b"""{ "name": "foo", "bugs": { "url": "https://github.com/owner/project/issues", "email": "foo@example.com" } }""" result = self.npm_mapping.translate(package_json) self.assertEqual(result, { '@context': 'https://doi.org/10.5063/schema/codemeta-2.0', 'name': 'foo', 'issueTracker': 'https://github.com/owner/project/issues', 'type': 'SoftwareSourceCode', }) # "invalid" dictionary package_json = b"""{ "name": "foo", "bugs": { "email": "foo@example.com" } }""" result = self.npm_mapping.translate(package_json) self.assertEqual(result, { '@context': 'https://doi.org/10.5063/schema/codemeta-2.0', 'name': 'foo', 'type': 'SoftwareSourceCode', }) # string package_json = b"""{ "name": "foo", "bugs": "https://github.com/owner/project/issues" }""" result = self.npm_mapping.translate(package_json) self.assertEqual(result, { '@context': 'https://doi.org/10.5063/schema/codemeta-2.0', 'name': 'foo', 'issueTracker': 'https://github.com/owner/project/issues', 'type': 'SoftwareSourceCode', }) def test_npm_repository_normalization(self): # normal package_json = b"""{ "name": "foo", "repository": { "type" : "git", "url" : "https://github.com/npm/cli.git" } }""" result = self.npm_mapping.translate(package_json) self.assertEqual(result, { '@context': 'https://doi.org/10.5063/schema/codemeta-2.0', 'name': 'foo', 'codeRepository': 'git+https://github.com/npm/cli.git', 'type': 'SoftwareSourceCode', }) # missing url package_json = b"""{ "name": "foo", "repository": { "type" : "git" } }""" result = self.npm_mapping.translate(package_json) self.assertEqual(result, { '@context': 'https://doi.org/10.5063/schema/codemeta-2.0', 'name': 'foo', 'type': 'SoftwareSourceCode', }) # github shortcut package_json = b"""{ "name": "foo", "repository": "github:npm/cli" }""" result = self.npm_mapping.translate(package_json) expected_result = { '@context': 'https://doi.org/10.5063/schema/codemeta-2.0', 'name': 'foo', 'codeRepository': 'git+https://github.com/npm/cli.git', 'type': 'SoftwareSourceCode', } self.assertEqual(result, expected_result) # github shortshortcut package_json = b"""{ "name": "foo", "repository": "npm/cli" }""" result = self.npm_mapping.translate(package_json) self.assertEqual(result, expected_result) # gitlab shortcut package_json = b"""{ "name": "foo", "repository": "gitlab:user/repo" }""" result = self.npm_mapping.translate(package_json) self.assertEqual(result, { '@context': 'https://doi.org/10.5063/schema/codemeta-2.0', 'name': 'foo', 'codeRepository': 'git+https://gitlab.com/user/repo.git', 'type': 'SoftwareSourceCode', }) def test_detect_metadata_package_json(self): # given df = [{ 'sha1_git': b'abc', 'name': b'index.js', 'target': b'abc', 'length': 897, 'status': 'visible', 'type': 'file', 'perms': 33188, 'dir_id': b'dir_a', 'sha1': b'bcd' }, { 'sha1_git': b'aab', 'name': b'package.json', 'target': b'aab', 'length': 712, 'status': 'visible', 'type': 'file', 'perms': 33188, 'dir_id': b'dir_a', 'sha1': b'cde' }] # when results = detect_metadata(df) expected_results = { 'NpmMapping': [ b'cde' ] } # then self.assertEqual(expected_results, results) def test_compute_metadata_valid_codemeta(self): raw_content = ( b"""{ "@context": "https://doi.org/10.5063/schema/codemeta-2.0", "@type": "SoftwareSourceCode", "identifier": "CodeMeta", "description": "CodeMeta is a concept vocabulary that can be used to standardize the exchange of software metadata across repositories and organizations.", "name": "CodeMeta: Minimal metadata schemas for science software and code, in JSON-LD", "codeRepository": "https://github.com/codemeta/codemeta", "issueTracker": "https://github.com/codemeta/codemeta/issues", "license": "https://spdx.org/licenses/Apache-2.0", "version": "2.0", "author": [ { "@type": "Person", "givenName": "Carl", "familyName": "Boettiger", "email": "cboettig@gmail.com", "@id": "http://orcid.org/0000-0002-1642-628X" }, { "@type": "Person", "givenName": "Matthew B.", "familyName": "Jones", "email": "jones@nceas.ucsb.edu", "@id": "http://orcid.org/0000-0003-0077-4738" } ], "maintainer": { "@type": "Person", "givenName": "Carl", "familyName": "Boettiger", "email": "cboettig@gmail.com", "@id": "http://orcid.org/0000-0002-1642-628X" }, "contIntegration": "https://travis-ci.org/codemeta/codemeta", "developmentStatus": "active", "downloadUrl": "https://github.com/codemeta/codemeta/archive/2.0.zip", "funder": { "@id": "https://doi.org/10.13039/100000001", "@type": "Organization", "name": "National Science Foundation" }, "funding":"1549758; Codemeta: A Rosetta Stone for Metadata in Scientific Software", "keywords": [ "metadata", "software" ], "version":"2.0", "dateCreated":"2017-06-05", "datePublished":"2017-06-05", "programmingLanguage": "JSON-LD" }""") # noqa expected_result = { "@context": "https://doi.org/10.5063/schema/codemeta-2.0", "type": "SoftwareSourceCode", "identifier": "CodeMeta", "description": "CodeMeta is a concept vocabulary that can " "be used to standardize the exchange of software metadata " "across repositories and organizations.", "name": "CodeMeta: Minimal metadata schemas for science " "software and code, in JSON-LD", "codeRepository": "https://github.com/codemeta/codemeta", "issueTracker": "https://github.com/codemeta/codemeta/issues", "license": "https://spdx.org/licenses/Apache-2.0", "version": "2.0", "author": [ { "type": "Person", "givenName": "Carl", "familyName": "Boettiger", "email": "cboettig@gmail.com", "id": "http://orcid.org/0000-0002-1642-628X" }, { "type": "Person", "givenName": "Matthew B.", "familyName": "Jones", "email": "jones@nceas.ucsb.edu", "id": "http://orcid.org/0000-0003-0077-4738" } ], "maintainer": { "type": "Person", "givenName": "Carl", "familyName": "Boettiger", "email": "cboettig@gmail.com", "id": "http://orcid.org/0000-0002-1642-628X" }, "contIntegration": "https://travis-ci.org/codemeta/codemeta", "developmentStatus": "active", "downloadUrl": "https://github.com/codemeta/codemeta/archive/2.0.zip", "funder": { "id": "https://doi.org/10.13039/100000001", "type": "Organization", "name": "National Science Foundation" }, "funding": "1549758; Codemeta: A Rosetta Stone for Metadata " "in Scientific Software", "keywords": [ "metadata", "software" ], "version": "2.0", "dateCreated": "2017-06-05", "datePublished": "2017-06-05", "programmingLanguage": "JSON-LD" } result = self.codemeta_mapping.translate(raw_content) self.assertEqual(result, expected_result) def test_compute_metadata_codemeta_alternate_context(self): raw_content = ( b"""{ "@context": "https://raw.githubusercontent.com/codemeta/codemeta/master/codemeta.jsonld", "@type": "SoftwareSourceCode", "identifier": "CodeMeta" }""") # noqa expected_result = { "@context": "https://doi.org/10.5063/schema/codemeta-2.0", "type": "SoftwareSourceCode", "identifier": "CodeMeta", } result = self.codemeta_mapping.translate(raw_content) self.assertEqual(result, expected_result) def test_compute_metadata_maven(self): raw_content = b""" Maven Default Project 4.0.0 com.mycompany.app my-app 1.2.3 central Maven Repository Switchboard default http://repo1.maven.org/maven2 false Apache License, Version 2.0 https://www.apache.org/licenses/LICENSE-2.0.txt repo A business-friendly OSS license """ result = self.maven_mapping.translate(raw_content) self.assertEqual(result, { '@context': 'https://doi.org/10.5063/schema/codemeta-2.0', 'type': 'SoftwareSourceCode', 'name': 'Maven Default Project', 'identifier': 'com.mycompany.app', 'version': '1.2.3', 'license': 'https://www.apache.org/licenses/LICENSE-2.0.txt', 'codeRepository': 'http://repo1.maven.org/maven2/com/mycompany/app/my-app', }) def test_compute_metadata_maven_empty(self): raw_content = b""" """ result = self.maven_mapping.translate(raw_content) self.assertEqual(result, { '@context': 'https://doi.org/10.5063/schema/codemeta-2.0', 'type': 'SoftwareSourceCode', }) def test_compute_metadata_maven_almost_empty(self): raw_content = b""" """ result = self.maven_mapping.translate(raw_content) self.assertEqual(result, { '@context': 'https://doi.org/10.5063/schema/codemeta-2.0', 'type': 'SoftwareSourceCode', }) def test_compute_metadata_maven_invalid_xml(self): expected_warning = ( 'WARNING:swh.indexer.metadata_dictionary.maven.MavenMapping:' 'Error parsing XML from foo') raw_content = b""" """ with self.assertLogs('swh.indexer.metadata_dictionary', level='WARNING') as cm: result = MAPPINGS["MavenMapping"]('foo').translate(raw_content) self.assertEqual(cm.output, [expected_warning]) self.assertEqual(result, None) raw_content = b""" """ with self.assertLogs('swh.indexer.metadata_dictionary', level='WARNING') as cm: result = MAPPINGS["MavenMapping"]('foo').translate(raw_content) self.assertEqual(cm.output, [expected_warning]) self.assertEqual(result, None) def test_compute_metadata_maven_unknown_encoding(self): expected_warning = ( 'WARNING:swh.indexer.metadata_dictionary.maven.MavenMapping:' 'Error detecting XML encoding from foo') raw_content = b""" """ with self.assertLogs('swh.indexer.metadata_dictionary', level='WARNING') as cm: result = MAPPINGS["MavenMapping"]('foo').translate(raw_content) self.assertEqual(cm.output, [expected_warning]) self.assertEqual(result, None) raw_content = b""" """ with self.assertLogs('swh.indexer.metadata_dictionary', level='WARNING') as cm: result = MAPPINGS["MavenMapping"]('foo').translate(raw_content) self.assertEqual(cm.output, [expected_warning]) self.assertEqual(result, None) def test_compute_metadata_maven_invalid_encoding(self): expected_warning = ( 'WARNING:swh.indexer.metadata_dictionary.maven.MavenMapping:' 'Error unidecoding XML from foo') raw_content = b""" """ with self.assertLogs('swh.indexer.metadata_dictionary', level='WARNING') as cm: result = MAPPINGS["MavenMapping"]('foo').translate(raw_content) self.assertEqual(cm.output, [expected_warning]) self.assertEqual(result, None) def test_compute_metadata_maven_minimal(self): raw_content = b""" Maven Default Project 4.0.0 com.mycompany.app my-app 1.2.3 """ result = self.maven_mapping.translate(raw_content) self.assertEqual(result, { '@context': 'https://doi.org/10.5063/schema/codemeta-2.0', 'type': 'SoftwareSourceCode', 'name': 'Maven Default Project', 'identifier': 'com.mycompany.app', 'version': '1.2.3', 'codeRepository': 'https://repo.maven.apache.org/maven2/com/mycompany/app/my-app', }) def test_compute_metadata_maven_empty_nodes(self): raw_content = b""" Maven Default Project 4.0.0 com.mycompany.app my-app 1.2.3 """ result = self.maven_mapping.translate(raw_content) self.assertEqual(result, { '@context': 'https://doi.org/10.5063/schema/codemeta-2.0', 'type': 'SoftwareSourceCode', 'name': 'Maven Default Project', 'identifier': 'com.mycompany.app', 'version': '1.2.3', 'codeRepository': 'https://repo.maven.apache.org/maven2/com/mycompany/app/my-app', }) raw_content = b""" Maven Default Project 4.0.0 com.mycompany.app my-app """ result = self.maven_mapping.translate(raw_content) self.assertEqual(result, { '@context': 'https://doi.org/10.5063/schema/codemeta-2.0', 'type': 'SoftwareSourceCode', 'name': 'Maven Default Project', 'identifier': 'com.mycompany.app', 'codeRepository': 'https://repo.maven.apache.org/maven2/com/mycompany/app/my-app', }) raw_content = b""" 4.0.0 com.mycompany.app my-app 1.2.3 """ result = self.maven_mapping.translate(raw_content) self.assertEqual(result, { '@context': 'https://doi.org/10.5063/schema/codemeta-2.0', 'type': 'SoftwareSourceCode', 'identifier': 'com.mycompany.app', 'version': '1.2.3', 'codeRepository': 'https://repo.maven.apache.org/maven2/com/mycompany/app/my-app', }) raw_content = b""" Maven Default Project 4.0.0 com.mycompany.app my-app 1.2.3 """ result = self.maven_mapping.translate(raw_content) self.assertEqual(result, { '@context': 'https://doi.org/10.5063/schema/codemeta-2.0', 'type': 'SoftwareSourceCode', 'name': 'Maven Default Project', 'identifier': 'com.mycompany.app', 'version': '1.2.3', 'codeRepository': 'https://repo.maven.apache.org/maven2/com/mycompany/app/my-app', }) raw_content = b""" 1.2.3 """ result = self.maven_mapping.translate(raw_content) self.assertEqual(result, { '@context': 'https://doi.org/10.5063/schema/codemeta-2.0', 'type': 'SoftwareSourceCode', 'version': '1.2.3', }) def test_compute_metadata_maven_invalid_licenses(self): raw_content = b""" Maven Default Project 4.0.0 com.mycompany.app my-app 1.2.3 foo """ result = self.maven_mapping.translate(raw_content) self.assertEqual(result, { '@context': 'https://doi.org/10.5063/schema/codemeta-2.0', 'type': 'SoftwareSourceCode', 'name': 'Maven Default Project', 'identifier': 'com.mycompany.app', 'version': '1.2.3', 'codeRepository': 'https://repo.maven.apache.org/maven2/com/mycompany/app/my-app', }) def test_compute_metadata_maven_multiple(self): '''Tests when there are multiple code repos and licenses.''' raw_content = b""" Maven Default Project 4.0.0 com.mycompany.app my-app 1.2.3 central Maven Repository Switchboard default http://repo1.maven.org/maven2 false example Example Maven Repo default http://example.org/maven2 Apache License, Version 2.0 https://www.apache.org/licenses/LICENSE-2.0.txt repo A business-friendly OSS license MIT license https://opensource.org/licenses/MIT """ result = self.maven_mapping.translate(raw_content) self.assertEqual(result, { '@context': 'https://doi.org/10.5063/schema/codemeta-2.0', 'type': 'SoftwareSourceCode', 'name': 'Maven Default Project', 'identifier': 'com.mycompany.app', 'version': '1.2.3', 'license': [ 'https://www.apache.org/licenses/LICENSE-2.0.txt', 'https://opensource.org/licenses/MIT', ], 'codeRepository': [ 'http://repo1.maven.org/maven2/com/mycompany/app/my-app', 'http://example.org/maven2/com/mycompany/app/my-app', ] }) def test_compute_metadata_pkginfo(self): raw_content = (b"""\ Metadata-Version: 2.1 Name: swh.core Version: 0.0.49 Summary: Software Heritage core utilities Home-page: https://forge.softwareheritage.org/diffusion/DCORE/ 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-core Description: swh-core ======== \x20 core library for swh's modules: - config parser - hash computations - serialization - logging mechanism \x20 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 """) # noqa result = self.pkginfo_mapping.translate(raw_content) self.assertCountEqual(result['description'], [ 'Software Heritage core utilities', # note the comma here 'swh-core\n' '========\n' '\n' "core library for swh's modules:\n" '- config parser\n' '- hash computations\n' '- serialization\n' '- logging mechanism\n' ''], result) del result['description'] self.assertEqual(result, { '@context': 'https://doi.org/10.5063/schema/codemeta-2.0', 'type': 'SoftwareSourceCode', 'url': 'https://forge.softwareheritage.org/diffusion/DCORE/', 'name': 'swh.core', 'author': [{ 'type': 'Person', 'name': 'Software Heritage developers', 'email': 'swh-devel@inria.fr', }], 'version': '0.0.49', }) def test_compute_metadata_pkginfo_utf8(self): raw_content = (b'''\ Metadata-Version: 1.1 Name: snowpyt Description-Content-Type: UNKNOWN Description: foo Hydrology N\xc2\xb083 ''') # noqa result = self.pkginfo_mapping.translate(raw_content) self.assertEqual(result, { '@context': 'https://doi.org/10.5063/schema/codemeta-2.0', 'type': 'SoftwareSourceCode', 'name': 'snowpyt', 'description': 'foo\nHydrology N°83', }) def test_compute_metadata_pkginfo_keywords(self): raw_content = (b"""\ Metadata-Version: 2.1 Name: foo Keywords: foo bar baz """) # noqa result = self.pkginfo_mapping.translate(raw_content) self.assertEqual(result, { '@context': 'https://doi.org/10.5063/schema/codemeta-2.0', 'type': 'SoftwareSourceCode', 'name': 'foo', 'keywords': ['foo', 'bar', 'baz'], }) def test_compute_metadata_pkginfo_license(self): raw_content = (b"""\ Metadata-Version: 2.1 Name: foo License: MIT """) # noqa result = self.pkginfo_mapping.translate(raw_content) self.assertEqual(result, { '@context': 'https://doi.org/10.5063/schema/codemeta-2.0', 'type': 'SoftwareSourceCode', 'name': 'foo', 'license': 'MIT', }) def test_gemspec_base(self): raw_content = b""" Gem::Specification.new do |s| s.name = 'example' s.version = '0.1.0' s.licenses = ['MIT'] s.summary = "This is an example!" s.description = "Much longer explanation of the example!" s.authors = ["Ruby Coder"] s.email = 'rubycoder@example.com' s.files = ["lib/example.rb"] s.homepage = 'https://rubygems.org/gems/example' s.metadata = { "source_code_uri" => "https://github.com/example/example" } end""" result = self.gemspec_mapping.translate(raw_content) self.assertCountEqual(result.pop('description'), [ "This is an example!", "Much longer explanation of the example!" ]) self.assertEqual(result, { '@context': 'https://doi.org/10.5063/schema/codemeta-2.0', 'type': 'SoftwareSourceCode', 'author': ['Ruby Coder'], 'name': 'example', 'license': 'https://spdx.org/licenses/MIT', 'codeRepository': 'https://rubygems.org/gems/example', 'email': 'rubycoder@example.com', 'version': '0.1.0', }) def test_gemspec_two_author_fields(self): raw_content = b""" Gem::Specification.new do |s| s.authors = ["Ruby Coder1"] s.author = "Ruby Coder2" end""" result = self.gemspec_mapping.translate(raw_content) self.assertCountEqual(result.pop('author'), [ 'Ruby Coder1', 'Ruby Coder2']) self.assertEqual(result, { '@context': 'https://doi.org/10.5063/schema/codemeta-2.0', 'type': 'SoftwareSourceCode', }) def test_gemspec_invalid_author(self): raw_content = b""" Gem::Specification.new do |s| s.author = ["Ruby Coder"] end""" result = self.gemspec_mapping.translate(raw_content) self.assertEqual(result, { '@context': 'https://doi.org/10.5063/schema/codemeta-2.0', 'type': 'SoftwareSourceCode', }) raw_content = b""" Gem::Specification.new do |s| s.author = "Ruby Coder1", end""" result = self.gemspec_mapping.translate(raw_content) self.assertEqual(result, { '@context': 'https://doi.org/10.5063/schema/codemeta-2.0', 'type': 'SoftwareSourceCode', }) raw_content = b""" Gem::Specification.new do |s| s.authors = ["Ruby Coder1", ["Ruby Coder2"]] end""" result = self.gemspec_mapping.translate(raw_content) self.assertEqual(result, { '@context': 'https://doi.org/10.5063/schema/codemeta-2.0', 'type': 'SoftwareSourceCode', 'author': ['Ruby Coder1'], }) def test_gemspec_alternative_header(self): raw_content = b""" require './lib/version' Gem::Specification.new { |s| s.name = 'rb-system-with-aliases' s.summary = 'execute system commands with aliases' } """ result = self.gemspec_mapping.translate(raw_content) self.assertEqual(result, { '@context': 'https://doi.org/10.5063/schema/codemeta-2.0', 'type': 'SoftwareSourceCode', 'name': 'rb-system-with-aliases', 'description': 'execute system commands with aliases', }) @settings(suppress_health_check=[HealthCheck.too_slow]) - @given(json_document_strategy( - keys=list(MAPPINGS['NpmMapping'].mapping))) + @given(json_document_strategy(keys=list(NpmMapping.mapping))) def test_npm_adversarial(self, doc): raw = json.dumps(doc).encode() self.npm_mapping.translate(raw) @settings(suppress_health_check=[HealthCheck.too_slow]) @given(json_document_strategy(keys=CODEMETA_TERMS)) def test_codemeta_adversarial(self, doc): raw = json.dumps(doc).encode() self.codemeta_mapping.translate(raw) @settings(suppress_health_check=[HealthCheck.too_slow]) @given(xml_document_strategy( - keys=list(MAPPINGS['MavenMapping'].mapping), + keys=list(MavenMapping.mapping), root='project', xmlns='http://maven.apache.org/POM/4.0.0')) def test_maven_adversarial(self, doc): self.maven_mapping.translate(doc) @settings(suppress_health_check=[HealthCheck.too_slow]) @given(strategies.dictionaries( # keys strategies.one_of( strategies.text(), - *map(strategies.just, MAPPINGS['GemspecMapping'].mapping) + *map(strategies.just, GemspecMapping.mapping) ), # values strategies.recursive( strategies.characters(), lambda children: strategies.lists(children, 1) ) )) def test_gemspec_adversarial(self, doc): parts = [b'Gem::Specification.new do |s|\n'] for (k, v) in doc.items(): parts.append(' s.{} = {}\n'.format(k, repr(v)).encode()) parts.append(b'end\n') self.gemspec_mapping.translate(b''.join(parts)) def test_revision_metadata_indexer(self): metadata_indexer = RevisionMetadataIndexer( config=REVISION_METADATA_CONFIG) fill_obj_storage(metadata_indexer.objstorage) fill_storage(metadata_indexer.storage) tool = metadata_indexer.idx_storage.indexer_configuration_get( {'tool_'+k: v for (k, v) in TRANSLATOR_TOOL.items()}) assert tool is not None metadata_indexer.idx_storage.content_metadata_add([{ 'indexer_configuration_id': tool['id'], 'id': b'cde', 'metadata': YARN_PARSER_METADATA, }]) sha1_gits = [ hash_to_bytes('8dbb6aeb036e7fd80664eb8bfd1507881af1ba9f'), ] metadata_indexer.run(sha1_gits, 'update-dups') results = list( metadata_indexer.idx_storage. revision_intrinsic_metadata_get(sha1_gits)) expected_results = [{ 'id': hash_to_bytes('8dbb6aeb036e7fd80664eb8bfd1507881af1ba9f'), 'tool': TRANSLATOR_TOOL, 'metadata': YARN_PARSER_METADATA, 'mappings': ['npm'], }] for result in results: del result['tool']['id'] # then self.assertEqual(expected_results, results) def test_revision_metadata_indexer_single_root_dir(self): metadata_indexer = RevisionMetadataIndexer( config=REVISION_METADATA_CONFIG) fill_obj_storage(metadata_indexer.objstorage) fill_storage(metadata_indexer.storage) # Add a parent directory, that is the only directory at the root # of the revision rev_id = hash_to_bytes('8dbb6aeb036e7fd80664eb8bfd1507881af1ba9f') rev = metadata_indexer.storage._revisions[rev_id] subdir_id = rev.directory - rev.directory = b'123456' + rev = attr.evolve(rev, directory=b'123456') metadata_indexer.storage.directory_add([{ 'id': b'123456', 'entries': [{ 'name': b'foobar-1.0.0', 'type': 'dir', 'target': subdir_id, 'perms': 16384, }], }]) tool = metadata_indexer.idx_storage.indexer_configuration_get( {'tool_'+k: v for (k, v) in TRANSLATOR_TOOL.items()}) assert tool is not None metadata_indexer.idx_storage.content_metadata_add([{ 'indexer_configuration_id': tool['id'], 'id': b'cde', 'metadata': YARN_PARSER_METADATA, }]) sha1_gits = [ hash_to_bytes('8dbb6aeb036e7fd80664eb8bfd1507881af1ba9f'), ] metadata_indexer.run(sha1_gits, 'update-dups') results = list( metadata_indexer.idx_storage. revision_intrinsic_metadata_get(sha1_gits)) expected_results = [{ 'id': hash_to_bytes('8dbb6aeb036e7fd80664eb8bfd1507881af1ba9f'), 'tool': TRANSLATOR_TOOL, 'metadata': YARN_PARSER_METADATA, 'mappings': ['npm'], }] for result in results: del result['tool']['id'] # then self.assertEqual(expected_results, results) diff --git a/swh/indexer/tests/test_mimetype.py b/swh/indexer/tests/test_mimetype.py index 72a0503..cf39bc3 100644 --- a/swh/indexer/tests/test_mimetype.py +++ b/swh/indexer/tests/test_mimetype.py @@ -1,145 +1,147 @@ # Copyright (C) 2017-2018 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import pytest import unittest +from typing import Any, Dict + from swh.indexer.mimetype import ( MimetypeIndexer, MimetypeRangeIndexer, compute_mimetype_encoding ) from swh.indexer.tests.utils import ( CommonContentIndexerTest, CommonContentIndexerRangeTest, BASE_TEST_CONFIG, fill_storage, fill_obj_storage, filter_dict, ) class BasicTest(unittest.TestCase): def test_compute_mimetype_encoding(self): """Compute mimetype encoding should return results""" for _input, _mimetype, _encoding in [ ('du français'.encode(), 'text/plain', 'utf-8'), (b'def __init__(self):', 'text/x-python', 'us-ascii')]: actual_result = compute_mimetype_encoding(_input) self.assertEqual(actual_result, { 'mimetype': _mimetype, 'encoding': _encoding }) CONFIG = { **BASE_TEST_CONFIG, 'tools': { 'name': 'file', 'version': '1:5.30-1+deb9u1', 'configuration': { "type": "library", "debian-package": "python3-magic" }, }, -} +} # type: Dict[str, Any] class TestMimetypeIndexer(CommonContentIndexerTest, unittest.TestCase): """Mimetype indexer test scenarios: - Known sha1s in the input list have their data indexed - Unknown sha1 in the input list are not indexed """ legacy_get_format = True def get_indexer_results(self, ids): yield from self.idx_storage.content_mimetype_get(ids) def setUp(self): self.indexer = MimetypeIndexer(config=CONFIG) self.indexer.catch_exceptions = False self.idx_storage = self.indexer.idx_storage fill_storage(self.indexer.storage) fill_obj_storage(self.indexer.objstorage) self.id0 = '01c9379dfc33803963d07c1ccc748d3fe4c96bb5' self.id1 = '688a5ef812c53907562fe379d4b3851e69c7cb15' self.id2 = 'da39a3ee5e6b4b0d3255bfef95601890afd80709' tool = {k.replace('tool_', ''): v for (k, v) in self.indexer.tool.items()} self.expected_results = { self.id0: { 'id': self.id0, 'tool': tool, 'mimetype': 'text/plain', 'encoding': 'us-ascii', }, self.id1: { 'id': self.id1, 'tool': tool, 'mimetype': 'text/plain', 'encoding': 'us-ascii', }, self.id2: { 'id': self.id2, 'tool': tool, 'mimetype': 'application/x-empty', 'encoding': 'binary', } } RANGE_CONFIG = dict(list(CONFIG.items()) + [('write_batch_size', 100)]) class TestMimetypeRangeIndexer( CommonContentIndexerRangeTest, unittest.TestCase): """Range Mimetype Indexer tests. - new data within range are indexed - no data outside a range are indexed - with filtering existing indexed data prior to compute new index - without filtering existing indexed data prior to compute new index """ def setUp(self): super().setUp() self.indexer = MimetypeRangeIndexer(config=RANGE_CONFIG) self.indexer.catch_exceptions = False fill_storage(self.indexer.storage) fill_obj_storage(self.indexer.objstorage) self.id0 = '01c9379dfc33803963d07c1ccc748d3fe4c96bb5' self.id1 = '02fb2c89e14f7fab46701478c83779c7beb7b069' self.id2 = '103bc087db1d26afc3a0283f38663d081e9b01e6' tool_id = self.indexer.tool['id'] self.expected_results = { self.id0: { 'encoding': 'us-ascii', 'id': self.id0, 'indexer_configuration_id': tool_id, 'mimetype': 'text/plain'}, self.id1: { 'encoding': 'us-ascii', 'id': self.id1, 'indexer_configuration_id': tool_id, 'mimetype': 'text/x-python'}, self.id2: { 'encoding': 'us-ascii', 'id': self.id2, 'indexer_configuration_id': tool_id, 'mimetype': 'text/plain'} } def test_mimetype_w_no_tool(): with pytest.raises(ValueError): MimetypeIndexer(config=filter_dict(CONFIG, 'tools')) def test_mimetype_range_w_no_tool(): with pytest.raises(ValueError): MimetypeRangeIndexer(config=filter_dict(CONFIG, 'tools')) diff --git a/swh/indexer/tests/test_origin_head.py b/swh/indexer/tests/test_origin_head.py index 5842363..a023174 100644 --- a/swh/indexer/tests/test_origin_head.py +++ b/swh/indexer/tests/test_origin_head.py @@ -1,158 +1,157 @@ # Copyright (C) 2017-2018 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import unittest from swh.indexer.origin_head import OriginHeadIndexer from swh.indexer.tests.utils import ( BASE_TEST_CONFIG, fill_storage ) ORIGIN_HEAD_CONFIG = { **BASE_TEST_CONFIG, 'tools': { 'name': 'origin-metadata', 'version': '0.0.1', 'configuration': {}, }, 'tasks': { 'revision_intrinsic_metadata': None, 'origin_intrinsic_metadata': None, } } class OriginHeadTestIndexer(OriginHeadIndexer): """Specific indexer whose configuration is enough to satisfy the indexing tests. """ def parse_config_file(self, *args, **kwargs): return ORIGIN_HEAD_CONFIG def persist_index_computations(self, results, policy_update): self.results = results class OriginHead(unittest.TestCase): def setUp(self): self.indexer = OriginHeadTestIndexer() self.indexer.catch_exceptions = False fill_storage(self.indexer.storage) def test_git(self): self.indexer.run( ['https://github.com/SoftwareHeritage/swh-storage']) self.assertEqual(self.indexer.results, [{ 'revision_id': b'8K\x12\x00d\x03\xcc\xe4]bS\xe3\x8f{' b'\xd7}\xac\xefrm', 'origin_url': 'https://github.com/SoftwareHeritage/swh-storage'}]) def test_git_partial_snapshot(self): """Checks partial snapshots are ignored.""" origin_url = 'https://github.com/SoftwareHeritage/swh-core' self.indexer.storage.origin_add_one({ - 'type': 'git', 'url': origin_url, }) visit = self.indexer.storage.origin_visit_add( - origin_url, '2019-02-27') + origin_url, '2019-02-27', type='git', + ) self.indexer.storage.snapshot_add([{ 'id': b'foo', 'branches': { b'foo': None, b'HEAD': { 'target_type': 'alias', 'target': b'foo', } } }]) self.indexer.storage.origin_visit_update( origin_url, visit['visit'], status='partial', snapshot=b'foo') self.indexer.run([origin_url]) self.assertEqual(self.indexer.results, []) def test_vcs_missing_snapshot(self): self.indexer.storage.origin_add([{ 'type': 'git', 'url': 'https://github.com/SoftwareHeritage/swh-indexer', }]) self.indexer.run( ['https://github.com/SoftwareHeritage/swh-indexer']) self.assertEqual(self.indexer.results, []) def test_pypi_missing_branch(self): origin_url = 'https://pypi.org/project/abcdef/' self.indexer.storage.origin_add_one({ - 'type': 'pypi', 'url': origin_url, }) visit = self.indexer.storage.origin_visit_add( - origin_url, '2019-02-27') + origin_url, '2019-02-27', type='pypi') self.indexer.storage.snapshot_add([{ 'id': b'foo', 'branches': { b'foo': None, b'HEAD': { 'target_type': 'alias', 'target': b'foo', } } }]) self.indexer.storage.origin_visit_update( origin_url, visit['visit'], status='full', snapshot=b'foo') self.indexer.run(['https://pypi.org/project/abcdef/']) self.assertEqual(self.indexer.results, []) def test_ftp(self): self.indexer.run( ['rsync://ftp.gnu.org/gnu/3dldf']) self.assertEqual(self.indexer.results, [{ 'revision_id': b'\x8e\xa9\x8e/\xea}\x9feF\xf4\x9f\xfd\xee' b'\xcc\x1a\xb4`\x8c\x8by', 'origin_url': 'rsync://ftp.gnu.org/gnu/3dldf'}]) def test_ftp_missing_snapshot(self): self.indexer.storage.origin_add([{ 'type': 'ftp', 'url': 'rsync://ftp.gnu.org/gnu/foobar', }]) self.indexer.run( ['rsync://ftp.gnu.org/gnu/foobar']) self.assertEqual(self.indexer.results, []) def test_deposit(self): self.indexer.run( ['https://forge.softwareheritage.org/source/' 'jesuisgpl/']) self.assertEqual(self.indexer.results, [{ 'revision_id': b'\xe7n\xa4\x9c\x9f\xfb\xb7\xf76\x11\x08{' b'\xa6\xe9\x99\xb1\x9e]q\xeb', 'origin_url': 'https://forge.softwareheritage.org/source/' 'jesuisgpl/'}]) def test_deposit_missing_snapshot(self): self.indexer.storage.origin_add([{ 'type': 'deposit', 'url': 'https://forge.softwareheritage.org/source/foobar', }]) self.indexer.run( ['https://forge.softwareheritage.org/source/foobar']) self.assertEqual(self.indexer.results, []) def test_pypi(self): self.indexer.run( ['https://pypi.org/project/limnoria/']) self.assertEqual(self.indexer.results, [{ 'revision_id': b'\x83\xb9\xb6\xc7\x05\xb1%\xd0\xfem\xd8k' b'A\x10\x9d\xc5\xfa2\xf8t', 'origin_url': 'https://pypi.org/project/limnoria/'}]) def test_svn(self): self.indexer.run( ['http://0-512-md.googlecode.com/svn/']) self.assertEqual(self.indexer.results, [{ 'revision_id': b'\xe4?r\xe1,\x88\xab\xec\xe7\x9a\x87\xb8' b'\xc9\xad#.\x1bw=\x18', 'origin_url': 'http://0-512-md.googlecode.com/svn/'}]) diff --git a/swh/indexer/tests/test_origin_metadata.py b/swh/indexer/tests/test_origin_metadata.py index 8c0dbea..3fc4791 100644 --- a/swh/indexer/tests/test_origin_metadata.py +++ b/swh/indexer/tests/test_origin_metadata.py @@ -1,254 +1,239 @@ # Copyright (C) 2018-2019 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information from unittest.mock import patch from swh.model.hashutil import hash_to_bytes from swh.indexer.metadata import OriginMetadataIndexer from .utils import YARN_PARSER_METADATA from .test_metadata import REVISION_METADATA_CONFIG -def test_origin_metadata_indexer( - idx_storage, storage, obj_storage): +def test_origin_metadata_indexer(idx_storage, storage, obj_storage): indexer = OriginMetadataIndexer(config=REVISION_METADATA_CONFIG) indexer.run(["https://github.com/librariesio/yarn-parser"]) - origin = storage.origin_get({ - 'url': 'https://github.com/librariesio/yarn-parser'}) + origin = 'https://github.com/librariesio/yarn-parser' rev_id = hash_to_bytes('8dbb6aeb036e7fd80664eb8bfd1507881af1ba9f') rev_metadata = { 'id': rev_id, 'metadata': YARN_PARSER_METADATA, 'mappings': ['npm'], } origin_metadata = { - 'id': origin['id'], - 'origin_url': origin['url'], + 'id': origin, 'from_revision': rev_id, 'metadata': YARN_PARSER_METADATA, 'mappings': ['npm'], } results = list( indexer.idx_storage.revision_intrinsic_metadata_get([rev_id])) for result in results: del result['tool'] assert results == [rev_metadata] results = list(indexer.idx_storage.origin_intrinsic_metadata_get([ - origin['id']])) + origin])) for result in results: del result['tool'] assert results == [origin_metadata] def test_origin_metadata_indexer_duplicate_origin( idx_storage, storage, obj_storage): indexer = OriginMetadataIndexer(config=REVISION_METADATA_CONFIG) indexer.storage = storage indexer.idx_storage = idx_storage indexer.run(["https://github.com/librariesio/yarn-parser"]) indexer.run(["https://github.com/librariesio/yarn-parser"]*2) - origin = storage.origin_get({ - 'url': 'https://github.com/librariesio/yarn-parser'}) + origin = 'https://github.com/librariesio/yarn-parser' rev_id = hash_to_bytes('8dbb6aeb036e7fd80664eb8bfd1507881af1ba9f') results = list( indexer.idx_storage.revision_intrinsic_metadata_get([rev_id])) assert len(results) == 1 results = list(indexer.idx_storage.origin_intrinsic_metadata_get([ - origin['id']])) + origin])) assert len(results) == 1 def test_origin_metadata_indexer_missing_head( idx_storage, storage, obj_storage): storage.origin_add([{ 'type': 'git', 'url': 'https://example.com' }]) indexer = OriginMetadataIndexer(config=REVISION_METADATA_CONFIG) indexer.run(["https://example.com"]) - origin = storage.origin_get({ - 'url': 'https://example.com'}) + origin = 'https://example.com' results = list(indexer.idx_storage.origin_intrinsic_metadata_get([ - origin['id']])) + origin])) assert results == [] def test_origin_metadata_indexer_partial_missing_head( idx_storage, storage, obj_storage): storage.origin_add([{ 'type': 'git', 'url': 'https://example.com' }]) indexer = OriginMetadataIndexer(config=REVISION_METADATA_CONFIG) indexer.run(["https://example.com", "https://github.com/librariesio/yarn-parser"]) - origin1 = storage.origin_get({ - 'url': 'https://example.com'}) - origin2 = storage.origin_get({ - 'url': 'https://github.com/librariesio/yarn-parser'}) + origin1 = 'https://example.com' + origin2 = 'https://github.com/librariesio/yarn-parser' rev_id = hash_to_bytes('8dbb6aeb036e7fd80664eb8bfd1507881af1ba9f') rev_metadata = { 'id': rev_id, 'metadata': YARN_PARSER_METADATA, 'mappings': ['npm'], } origin_metadata = { - 'id': origin2['id'], - 'origin_url': origin2['url'], + 'id': origin2, 'from_revision': rev_id, 'metadata': YARN_PARSER_METADATA, 'mappings': ['npm'], } results = list( indexer.idx_storage.revision_intrinsic_metadata_get([rev_id])) for result in results: del result['tool'] assert results == [rev_metadata] results = list(indexer.idx_storage.origin_intrinsic_metadata_get([ - origin1['id'], origin2['id']])) + origin1, origin2])) for result in results: del result['tool'] assert results == [origin_metadata] def test_origin_metadata_indexer_duplicate_revision( idx_storage, storage, obj_storage): indexer = OriginMetadataIndexer(config=REVISION_METADATA_CONFIG) indexer.storage = storage indexer.idx_storage = idx_storage indexer.run(["https://github.com/librariesio/yarn-parser", "https://github.com/librariesio/yarn-parser.git"]) - origin1 = storage.origin_get({ - 'url': 'https://github.com/librariesio/yarn-parser'}) - origin2 = storage.origin_get({ - 'url': 'https://github.com/librariesio/yarn-parser.git'}) - assert origin1['id'] != origin2['id'] + origin1 = 'https://github.com/librariesio/yarn-parser' + origin2 = 'https://github.com/librariesio/yarn-parser.git' rev_id = hash_to_bytes('8dbb6aeb036e7fd80664eb8bfd1507881af1ba9f') results = list( indexer.idx_storage.revision_intrinsic_metadata_get([rev_id])) assert len(results) == 1 - results = list(indexer.idx_storage.origin_intrinsic_metadata_get([ - origin1['id'], origin2['id']])) + results = list(indexer.idx_storage.origin_intrinsic_metadata_get( + [origin1, origin2])) assert len(results) == 2 def test_origin_metadata_indexer_no_metadata_file( idx_storage, storage, obj_storage): indexer = OriginMetadataIndexer(config=REVISION_METADATA_CONFIG) with patch('swh.indexer.metadata_dictionary.npm.NpmMapping.filename', b'foo.json'): indexer.run(["https://github.com/librariesio/yarn-parser"]) - origin = storage.origin_get({ - 'url': 'https://github.com/librariesio/yarn-parser'}) + origin = 'https://github.com/librariesio/yarn-parser' rev_id = hash_to_bytes('8dbb6aeb036e7fd80664eb8bfd1507881af1ba9f') results = list( indexer.idx_storage.revision_intrinsic_metadata_get([rev_id])) assert results == [] results = list(indexer.idx_storage.origin_intrinsic_metadata_get([ - origin['id']])) + origin])) assert results == [] def test_origin_metadata_indexer_no_metadata( idx_storage, storage, obj_storage): indexer = OriginMetadataIndexer(config=REVISION_METADATA_CONFIG) with patch('swh.indexer.metadata.RevisionMetadataIndexer' '.translate_revision_intrinsic_metadata', return_value=(['npm'], {'@context': 'foo'})): indexer.run(["https://github.com/librariesio/yarn-parser"]) - origin = storage.origin_get({ - 'url': 'https://github.com/librariesio/yarn-parser'}) + origin = 'https://github.com/librariesio/yarn-parser' rev_id = hash_to_bytes('8dbb6aeb036e7fd80664eb8bfd1507881af1ba9f') results = list( indexer.idx_storage.revision_intrinsic_metadata_get([rev_id])) assert results == [] results = list(indexer.idx_storage.origin_intrinsic_metadata_get([ - origin['id']])) + origin])) assert results == [] def test_origin_metadata_indexer_error( idx_storage, storage, obj_storage): indexer = OriginMetadataIndexer(config=REVISION_METADATA_CONFIG) with patch('swh.indexer.metadata.RevisionMetadataIndexer' '.translate_revision_intrinsic_metadata', return_value=None): indexer.run(["https://github.com/librariesio/yarn-parser"]) - origin = storage.origin_get({ - 'url': 'https://github.com/librariesio/yarn-parser'}) + origin = 'https://github.com/librariesio/yarn-parser' rev_id = hash_to_bytes('8dbb6aeb036e7fd80664eb8bfd1507881af1ba9f') results = list( indexer.idx_storage.revision_intrinsic_metadata_get([rev_id])) assert results == [] results = list(indexer.idx_storage.origin_intrinsic_metadata_get([ - origin['id']])) + origin])) assert results == [] def test_origin_metadata_indexer_delete_metadata( idx_storage, storage, obj_storage): indexer = OriginMetadataIndexer(config=REVISION_METADATA_CONFIG) indexer.run(["https://github.com/librariesio/yarn-parser"]) - origin = storage.origin_get({ - 'url': 'https://github.com/librariesio/yarn-parser'}) + origin = 'https://github.com/librariesio/yarn-parser' rev_id = hash_to_bytes('8dbb6aeb036e7fd80664eb8bfd1507881af1ba9f') results = list( indexer.idx_storage.revision_intrinsic_metadata_get([rev_id])) assert results != [] results = list(indexer.idx_storage.origin_intrinsic_metadata_get([ - origin['id']])) + origin])) assert results != [] with patch('swh.indexer.metadata_dictionary.npm.NpmMapping.filename', b'foo.json'): indexer.run(["https://github.com/librariesio/yarn-parser"]) results = list( indexer.idx_storage.revision_intrinsic_metadata_get([rev_id])) assert results == [] results = list(indexer.idx_storage.origin_intrinsic_metadata_get([ - origin['id']])) + origin])) assert results == [] diff --git a/swh/indexer/tests/utils.py b/swh/indexer/tests/utils.py index f09927e..7d8d0c6 100644 --- a/swh/indexer/tests/utils.py +++ b/swh/indexer/tests/utils.py @@ -1,749 +1,760 @@ # Copyright (C) 2017-2019 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import abc import datetime import functools import random import unittest from hypothesis import strategies from swh.model import hashutil from swh.model.hashutil import hash_to_bytes, hash_to_hex from swh.indexer.storage import INDEXER_CFG_KEY BASE_TEST_CONFIG = { 'storage': { 'cls': 'memory', 'args': { }, }, 'objstorage': { 'cls': 'memory', 'args': { }, }, INDEXER_CFG_KEY: { 'cls': 'memory', 'args': { }, }, } -ORIGINS = [ +ORIGIN_VISITS = [ { 'type': 'git', 'url': 'https://github.com/SoftwareHeritage/swh-storage'}, { 'type': 'ftp', 'url': 'rsync://ftp.gnu.org/gnu/3dldf'}, { 'type': 'deposit', 'url': 'https://forge.softwareheritage.org/source/jesuisgpl/'}, { 'type': 'pypi', 'url': 'https://pypi.org/project/limnoria/'}, { 'type': 'svn', 'url': 'http://0-512-md.googlecode.com/svn/'}, { 'type': 'git', 'url': 'https://github.com/librariesio/yarn-parser'}, { 'type': 'git', 'url': 'https://github.com/librariesio/yarn-parser.git'}, ] SNAPSHOTS = [ { 'origin': 'https://github.com/SoftwareHeritage/swh-storage', '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'}, }}, { 'origin': 'rsync://ftp.gnu.org/gnu/3dldf', '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', 'target_type': 'revision'} }}, { 'origin': 'https://forge.softwareheritage.org/source/jesuisgpl/', '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 "}, { 'origin': 'https://pypi.org/project/limnoria/', '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'}, { 'origin': 'http://0-512-md.googlecode.com/svn/', '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'}, { 'origin': 'https://github.com/librariesio/yarn-parser', 'branches': { b'HEAD': { 'target': hash_to_bytes( '8dbb6aeb036e7fd80664eb8bfd1507881af1ba9f'), 'target_type': 'revision'}}}, { 'origin': 'https://github.com/librariesio/yarn-parser.git', 'branches': { b'HEAD': { 'target': hash_to_bytes( '8dbb6aeb036e7fd80664eb8bfd1507881af1ba9f'), 'target_type': 'revision'}}}, ] REVISIONS = [{ 'id': hash_to_bytes('8dbb6aeb036e7fd80664eb8bfd1507881af1ba9f'), 'message': 'Improve search functionality', 'author': { 'name': b'Andrew Nesbitt', 'fullname': b'Andrew Nesbitt ', 'email': b'andrewnez@gmail.com' }, 'committer': { 'name': b'Andrew Nesbitt', 'fullname': b'Andrew Nesbitt ', 'email': b'andrewnez@gmail.com' }, 'committer_date': { 'negative_utc': None, 'offset': 120, 'timestamp': { 'microseconds': 0, 'seconds': 1380883849 } }, 'type': 'git', 'synthetic': False, 'date': { 'negative_utc': False, 'timestamp': { 'seconds': 1487596456, 'microseconds': 0 }, 'offset': 0 }, 'directory': b'10' }] DIRECTORY_ID = b'10' DIRECTORY_ENTRIES = [{ 'name': b'index.js', 'type': 'file', 'target': b'abc', 'perms': 33188, }, { 'name': b'package.json', 'type': 'file', 'target': b'cde', 'perms': 33188, }, { 'name': b'.github', 'type': 'dir', 'target': b'11', 'perms': 16384, } ] 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', }], } OBJ_STORAGE_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 MimetypeIndexer 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'', # 626364 hash_to_hex(b'bcd'): b'unimportant content for bcd', # 636465 hash_to_hex(b'cde'): b""" { "name": "yarn-parser", "version": "1.0.0", "description": "Tiny web service for parsing yarn.lock files", "main": "index.js", "scripts": { "start": "node index.js", "test": "mocha" }, "engines": { "node": "9.8.0" }, "repository": { "type": "git", "url": "git+https://github.com/librariesio/yarn-parser.git" }, "keywords": [ "yarn", "parse", "lock", "dependencies" ], "author": "Andrew Nesbitt", "license": "AGPL-3.0", "bugs": { "url": "https://github.com/librariesio/yarn-parser/issues" }, "homepage": "https://github.com/librariesio/yarn-parser#readme", "dependencies": { "@yarnpkg/lockfile": "^1.0.0", "body-parser": "^1.15.2", "express": "^4.14.0" }, "devDependencies": { "chai": "^4.1.2", "mocha": "^5.2.0", "request": "^2.87.0", "test": "^0.6.0" } } """ } YARN_PARSER_METADATA = { '@context': 'https://doi.org/10.5063/schema/codemeta-2.0', 'url': 'https://github.com/librariesio/yarn-parser#readme', 'codeRepository': 'git+git+https://github.com/librariesio/yarn-parser.git', 'author': [{ 'type': 'Person', 'name': 'Andrew Nesbitt' }], 'license': 'https://spdx.org/licenses/AGPL-3.0', 'version': '1.0.0', 'description': 'Tiny web service for parsing yarn.lock files', 'issueTracker': 'https://github.com/librariesio/yarn-parser/issues', 'name': 'yarn-parser', 'keywords': ['yarn', 'parse', 'lock', 'dependencies'], 'type': 'SoftwareSourceCode', } json_dict_keys = strategies.one_of( strategies.characters(), - *map(strategies.just, ['type', 'url', 'name', 'email', '@id', - '@context', 'repository', 'license', - 'repositories', 'licenses' - ]), + strategies.just('type'), + strategies.just('url'), + strategies.just('name'), + strategies.just('email'), + strategies.just('@id'), + strategies.just('@context'), + strategies.just('repository'), + strategies.just('license'), + strategies.just('repositories'), + strategies.just('licenses'), ) """Hypothesis strategy that generates strings, with an emphasis on those that are often used as dictionary keys in metadata files.""" generic_json_document = strategies.recursive( strategies.none() | strategies.booleans() | strategies.floats() | strategies.characters(), lambda children: ( strategies.lists(children, 1) | strategies.dictionaries(json_dict_keys, children, min_size=1) ) ) """Hypothesis strategy that generates possible values for values of JSON metadata files.""" def json_document_strategy(keys=None): """Generates an hypothesis strategy that generates metadata files for a JSON-based format that uses the given keys.""" if keys is None: keys = strategies.characters() else: keys = strategies.one_of(map(strategies.just, keys)) return strategies.dictionaries(keys, generic_json_document, min_size=1) def _tree_to_xml(root, xmlns, data): def encode(s): "Skips unpaired surrogates generated by json_document_strategy" return s.encode('utf8', 'replace') def to_xml(data, indent=b' '): if data is None: return b'' elif isinstance(data, (bool, str, int, float)): return indent + encode(str(data)) elif isinstance(data, list): return b'\n'.join(to_xml(v, indent=indent) for v in data) elif isinstance(data, dict): lines = [] for (key, value) in data.items(): lines.append(indent + encode('<{}>'.format(key))) lines.append(to_xml(value, indent=indent+b' ')) lines.append(indent + encode(''.format(key))) return b'\n'.join(lines) else: raise TypeError(data) return b'\n'.join([ '<{} xmlns="{}">'.format(root, xmlns).encode(), to_xml(data), ''.format(root).encode(), ]) class TreeToXmlTest(unittest.TestCase): def test_leaves(self): self.assertEqual( _tree_to_xml('root', 'http://example.com', None), b'\n\n' ) self.assertEqual( _tree_to_xml('root', 'http://example.com', True), b'\n True\n' ) self.assertEqual( _tree_to_xml('root', 'http://example.com', 'abc'), b'\n abc\n' ) self.assertEqual( _tree_to_xml('root', 'http://example.com', 42), b'\n 42\n' ) self.assertEqual( _tree_to_xml('root', 'http://example.com', 3.14), b'\n 3.14\n' ) def test_dict(self): self.assertIn( _tree_to_xml('root', 'http://example.com', { 'foo': 'bar', 'baz': 'qux' }), [ b'\n' b' \n bar\n \n' b' \n qux\n \n' b'', b'\n' b' \n qux\n \n' b' \n bar\n \n' b'' ] ) def test_list(self): self.assertEqual( _tree_to_xml('root', 'http://example.com', [ {'foo': 'bar'}, {'foo': 'baz'}, ]), b'\n' b' \n bar\n \n' b' \n baz\n \n' b'' ) def xml_document_strategy(keys, root, xmlns): """Generates an hypothesis strategy that generates metadata files for an XML format that uses the given keys.""" return strategies.builds( functools.partial(_tree_to_xml, root, xmlns), json_document_strategy(keys)) def filter_dict(d, keys): 'return a copy of the dict with keys deleted' if not isinstance(keys, (list, tuple)): keys = (keys, ) return dict((k, v) for (k, v) in d.items() if k not in keys) def fill_obj_storage(obj_storage): """Add some content in an object storage.""" for (obj_id, content) in OBJ_STORAGE_DATA.items(): obj_storage.add(content, obj_id=hash_to_bytes(obj_id)) def fill_storage(storage): - for origin in ORIGINS: - storage.origin_add_one(origin) + visit_types = {} + for visit in ORIGIN_VISITS: + storage.origin_add_one({'url': visit['url']}) + visit_types[visit['url']] = visit['type'] for snap in SNAPSHOTS: origin_url = snap['origin'] - visit = storage.origin_visit_add(origin_url, datetime.datetime.now()) + visit = storage.origin_visit_add( + origin=origin_url, + date=datetime.datetime.now(), + type=visit_types[origin_url]) snap_id = snap.get('id') or \ bytes([random.randint(0, 255) for _ in range(32)]) storage.snapshot_add([{ 'id': snap_id, 'branches': snap['branches'] }]) storage.origin_visit_update( origin_url, visit['visit'], status='full', snapshot=snap_id) storage.revision_add(REVISIONS) contents = [] for (obj_id, content) in OBJ_STORAGE_DATA.items(): content_hashes = hashutil.MultiHash.from_data(content).digest() contents.append({ 'data': content, 'length': len(content), 'status': 'visible', 'sha1': hash_to_bytes(obj_id), 'sha1_git': hash_to_bytes(obj_id), 'sha256': content_hashes['sha256'], 'blake2s256': content_hashes['blake2s256'] }) storage.content_add(contents) storage.directory_add([{ 'id': DIRECTORY_ID, 'entries': DIRECTORY_ENTRIES, }]) class CommonContentIndexerTest(metaclass=abc.ABCMeta): legacy_get_format = False """True if and only if the tested indexer uses the legacy format. see: https://forge.softwareheritage.org/T1433 """ def get_indexer_results(self, ids): """Override this for indexers that don't have a mock storage.""" return self.indexer.idx_storage.state def assert_legacy_results_ok(self, sha1s, expected_results=None): # XXX old format, remove this when all endpoints are # updated to the new one # see: https://forge.softwareheritage.org/T1433 sha1s = [sha1 if isinstance(sha1, bytes) else hash_to_bytes(sha1) for sha1 in sha1s] actual_results = list(self.get_indexer_results(sha1s)) if expected_results is None: expected_results = self.expected_results self.assertEqual(len(expected_results), len(actual_results), (expected_results, actual_results)) for indexed_data in actual_results: _id = indexed_data['id'] expected_data = expected_results[hashutil.hash_to_hex(_id)].copy() expected_data['id'] = _id self.assertEqual(indexed_data, expected_data) def assert_results_ok(self, sha1s, expected_results=None): if self.legacy_get_format: self.assert_legacy_results_ok(sha1s, expected_results) return sha1s = [sha1 if isinstance(sha1, bytes) else hash_to_bytes(sha1) for sha1 in sha1s] actual_results = list(self.get_indexer_results(sha1s)) if expected_results is None: expected_results = self.expected_results self.assertEqual(len(expected_results), len(actual_results), (expected_results, actual_results)) for indexed_data in actual_results: (_id, indexed_data) = list(indexed_data.items())[0] expected_data = expected_results[hashutil.hash_to_hex(_id)].copy() expected_data = [expected_data] self.assertEqual(indexed_data, expected_data) 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') self.assert_results_ok(sha1s) # 2nd pass self.indexer.run(sha1s, policy_update='ignore-dups') self.assert_results_ok(sha1s) 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') # then expected_results = { k: v for k, v in self.expected_results.items() if k in sha1s } self.assert_results_ok(sha1s, expected_results) class CommonContentIndexerRangeTest: """Allows to factorize tests on range indexer. """ def setUp(self): self.contents = sorted(OBJ_STORAGE_DATA) def assert_results_ok(self, start, end, actual_results, expected_results=None): if expected_results is None: expected_results = self.expected_results actual_results = list(actual_results) for indexed_data in actual_results: _id = indexed_data['id'] assert isinstance(_id, bytes) indexed_data = indexed_data.copy() indexed_data['id'] = hash_to_hex(indexed_data['id']) self.assertEqual(indexed_data, expected_results[hash_to_hex(_id)]) self.assertTrue(start <= _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 start, end = map(hashutil.hash_to_bytes, (_start, _end)) # 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 start, end = map(hashutil.hash_to_bytes, (_start, _end)) data_indexed = [self.id0, self.id2] # given actual_results = self.indexer._index_contents( start, end, indexed=set(map(hash_to_bytes, 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 start, end = map(hashutil.hash_to_bytes, (_start, _end)) # 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 already indexed data so same result as prior test # then self.assertTrue(actual_results) def test_generate_content_get_no_result(self): """No result indexed returns False""" _start, _end = ['0000000000000000000000000000000000000000', '0000000000000000000000000000000000000001'] start, end = map(hashutil.hash_to_bytes, (_start, _end)) # given actual_results = self.indexer.run( start, end, incremental=False) # then self.assertFalse(actual_results) diff --git a/version.txt b/version.txt index 34fee3b..88600e0 100644 --- a/version.txt +++ b/version.txt @@ -1 +1 @@ -v0.0.155-0-g1d625af \ No newline at end of file +v0.0.156-0-gd27cd13 \ No newline at end of file