diff --git a/PKG-INFO b/PKG-INFO index 5e76949..2d6dd0b 100644 --- a/PKG-INFO +++ b/PKG-INFO @@ -1,71 +1,71 @@ Metadata-Version: 2.1 Name: swh.indexer -Version: 0.4.2 +Version: 0.5.0 Summary: Software Heritage Content Indexer Home-page: https://forge.softwareheritage.org/diffusion/78/ Author: Software Heritage developers Author-email: swh-devel@inria.fr License: UNKNOWN Project-URL: Bug Reports, https://forge.softwareheritage.org/maniphest Project-URL: Funding, https://www.softwareheritage.org/donate Project-URL: Source, https://forge.softwareheritage.org/source/swh-indexer Project-URL: Documentation, https://docs.softwareheritage.org/devel/swh-indexer/ Description: swh-indexer ============ Tools to compute multiple indexes on SWH's raw contents: - content: - mimetype - ctags - language - fossology-license - metadata - revision: - metadata An indexer is in charge of: - looking up objects - extracting information from those objects - store those information in the swh-indexer db There are multiple indexers working on different object types: - content indexer: works with content sha1 hashes - revision indexer: works with revision sha1 hashes - origin indexer: works with origin identifiers Indexation procedure: - receive batch of ids - retrieve the associated data depending on object type - compute for that object some index - store the result to swh's storage Current content indexers: - mimetype (queue swh_indexer_content_mimetype): detect the encoding and mimetype - language (queue swh_indexer_content_language): detect the programming language - ctags (queue swh_indexer_content_ctags): compute tags information - fossology-license (queue swh_indexer_fossology_license): compute the license - metadata: translate file into translated_metadata dict Current revision indexers: - metadata: detects files containing metadata and retrieves translated_metadata in content_metadata table in storage or run content indexer to translate files. Platform: UNKNOWN Classifier: Programming Language :: Python :: 3 Classifier: Intended Audience :: Developers Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3) Classifier: Operating System :: OS Independent Classifier: Development Status :: 5 - Production/Stable Requires-Python: >=3.7 Description-Content-Type: text/markdown Provides-Extra: testing diff --git a/sql/upgrades/133.sql b/sql/upgrades/133.sql new file mode 100644 index 0000000..701ad94 --- /dev/null +++ b/sql/upgrades/133.sql @@ -0,0 +1,184 @@ +-- SWH Indexer DB schema upgrade +-- from_version: 132 +-- to_version: 133 +-- description: remove 'conflict_update' argument + +insert into dbversion(version, release, description) + values(133, now(), 'Work In Progress'); + +drop function swh_content_mimetype_add(conflict_update boolean); +create or replace function swh_content_mimetype_add() + returns bigint + language plpgsql +as $$ +declare + res bigint; +begin + insert into content_mimetype (id, mimetype, encoding, indexer_configuration_id) + select id, mimetype, encoding, indexer_configuration_id + from tmp_content_mimetype tcm + on conflict(id, indexer_configuration_id) + do update set mimetype = excluded.mimetype, + encoding = excluded.encoding; + + get diagnostics res = ROW_COUNT; + return res; +end +$$; + +comment on function swh_content_mimetype_add() IS 'Add new content mimetypes'; + + + +drop function swh_content_language_add(conflict_update boolean); +create or replace function swh_content_language_add() + returns bigint + language plpgsql +as $$ +declare + res bigint; +begin + insert into content_language (id, lang, indexer_configuration_id) + select id, lang, indexer_configuration_id + from tmp_content_language tcl + on conflict(id, indexer_configuration_id) + do update set lang = excluded.lang; + + get diagnostics res = ROW_COUNT; + return res; +end +$$; + +comment on function swh_content_language_add() IS 'Add new content languages'; + + + +drop function swh_content_ctags_add(conflict_update boolean); +create or replace function swh_content_ctags_add() + returns bigint + language plpgsql +as $$ +declare + res bigint; +begin + insert into content_ctags (id, name, kind, line, lang, indexer_configuration_id) + select id, name, kind, line, lang, indexer_configuration_id + from tmp_content_ctags tct + on conflict(id, hash_sha1(name), kind, line, lang, indexer_configuration_id) + do nothing; + + get diagnostics res = ROW_COUNT; + return res; +end +$$; + +comment on function swh_content_ctags_add() IS 'Add new ctags symbols per content'; + + + +drop function swh_content_fossology_license_add(conflict_update boolean); +create or replace function swh_content_fossology_license_add() + returns bigint + language plpgsql +as $$ +declare + res bigint; +begin + -- insert unknown licenses first + insert into fossology_license (name) + select distinct license from tmp_content_fossology_license tmp + where not exists (select 1 from fossology_license where name=tmp.license) + on conflict(name) do nothing; + + insert into content_fossology_license (id, license_id, indexer_configuration_id) + select tcl.id, + (select id from fossology_license where name = tcl.license) as license, + indexer_configuration_id + from tmp_content_fossology_license tcl + on conflict(id, license_id, indexer_configuration_id) + do update set license_id = excluded.license_id; + + get diagnostics res = ROW_COUNT; + return res; +end +$$; + +comment on function swh_content_fossology_license_add() IS 'Add new content licenses'; + + + +drop function swh_content_metadata_add(conflict_update boolean); +create or replace function swh_content_metadata_add() + returns bigint + language plpgsql +as $$ +declare + res bigint; +begin + insert into content_metadata (id, metadata, indexer_configuration_id) + select id, metadata, indexer_configuration_id + from tmp_content_metadata tcm + on conflict(id, indexer_configuration_id) + do update set metadata = excluded.metadata; + + get diagnostics res = ROW_COUNT; + return res; +end +$$; + +comment on function swh_content_metadata_add() IS 'Add new content metadata'; + + + +drop function swh_revision_intrinsic_metadata_add(conflict_update boolean); +create or replace function swh_revision_intrinsic_metadata_add() + returns bigint + language plpgsql +as $$ +declare + res bigint; +begin + insert into revision_intrinsic_metadata (id, metadata, mappings, indexer_configuration_id) + select id, metadata, mappings, indexer_configuration_id + from tmp_revision_intrinsic_metadata tcm + on conflict(id, indexer_configuration_id) + do update set + metadata = excluded.metadata, + mappings = excluded.mappings; + + get diagnostics res = ROW_COUNT; + return res; +end +$$; + +comment on function swh_revision_intrinsic_metadata_add() IS 'Add new revision intrinsic metadata'; + + + +drop function swh_origin_intrinsic_metadata_add(conflict_update boolean); +create or replace function swh_origin_intrinsic_metadata_add() + returns bigint + language plpgsql +as $$ +declare + res bigint; +begin + perform swh_origin_intrinsic_metadata_compute_tsvector(); + + insert into origin_intrinsic_metadata (id, metadata, indexer_configuration_id, from_revision, metadata_tsvector, mappings) + select id, metadata, indexer_configuration_id, from_revision, + metadata_tsvector, mappings + from tmp_origin_intrinsic_metadata + on conflict(id, indexer_configuration_id) + do update set + metadata = excluded.metadata, + metadata_tsvector = excluded.metadata_tsvector, + mappings = excluded.mappings, + from_revision = excluded.from_revision; + + get diagnostics res = ROW_COUNT; + return res; +end +$$; + +comment on function swh_origin_intrinsic_metadata_add() IS 'Add new origin intrinsic metadata'; diff --git a/swh.indexer.egg-info/PKG-INFO b/swh.indexer.egg-info/PKG-INFO index 5e76949..2d6dd0b 100644 --- a/swh.indexer.egg-info/PKG-INFO +++ b/swh.indexer.egg-info/PKG-INFO @@ -1,71 +1,71 @@ Metadata-Version: 2.1 Name: swh.indexer -Version: 0.4.2 +Version: 0.5.0 Summary: Software Heritage Content Indexer Home-page: https://forge.softwareheritage.org/diffusion/78/ Author: Software Heritage developers Author-email: swh-devel@inria.fr License: UNKNOWN Project-URL: Bug Reports, https://forge.softwareheritage.org/maniphest Project-URL: Funding, https://www.softwareheritage.org/donate Project-URL: Source, https://forge.softwareheritage.org/source/swh-indexer Project-URL: Documentation, https://docs.softwareheritage.org/devel/swh-indexer/ Description: swh-indexer ============ Tools to compute multiple indexes on SWH's raw contents: - content: - mimetype - ctags - language - fossology-license - metadata - revision: - metadata An indexer is in charge of: - looking up objects - extracting information from those objects - store those information in the swh-indexer db There are multiple indexers working on different object types: - content indexer: works with content sha1 hashes - revision indexer: works with revision sha1 hashes - origin indexer: works with origin identifiers Indexation procedure: - receive batch of ids - retrieve the associated data depending on object type - compute for that object some index - store the result to swh's storage Current content indexers: - mimetype (queue swh_indexer_content_mimetype): detect the encoding and mimetype - language (queue swh_indexer_content_language): detect the programming language - ctags (queue swh_indexer_content_ctags): compute tags information - fossology-license (queue swh_indexer_fossology_license): compute the license - metadata: translate file into translated_metadata dict Current revision indexers: - metadata: detects files containing metadata and retrieves translated_metadata in content_metadata table in storage or run content indexer to translate files. Platform: UNKNOWN Classifier: Programming Language :: Python :: 3 Classifier: Intended Audience :: Developers Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3) Classifier: Operating System :: OS Independent Classifier: Development Status :: 5 - Production/Stable Requires-Python: >=3.7 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 6f7120d..83d5e9f 100644 --- a/swh.indexer.egg-info/SOURCES.txt +++ b/swh.indexer.egg-info/SOURCES.txt @@ -1,138 +1,139 @@ .gitignore .pre-commit-config.yaml AUTHORS CODE_OF_CONDUCT.md CONTRIBUTORS LICENSE MANIFEST.in Makefile Makefile.local README.md codemeta.json conftest.py mypy.ini pyproject.toml pytest.ini requirements-swh.txt requirements-test.txt requirements.txt setup.cfg setup.py tox.ini docs/.gitignore docs/Makefile docs/Makefile.local docs/README.md docs/conf.py docs/dev-info.rst docs/index.rst docs/metadata-workflow.rst docs/_static/.placeholder docs/_templates/.placeholder docs/images/.gitignore docs/images/Makefile docs/images/tasks-metadata-indexers.uml sql/bin/db-upgrade sql/bin/dot_add_content sql/doc/json sql/doc/json/.gitignore sql/doc/json/Makefile sql/doc/json/indexer_configuration.tool_configuration.schema.json sql/doc/json/revision_metadata.translated_metadata.json sql/json/.gitignore sql/json/Makefile sql/json/indexer_configuration.tool_configuration.schema.json sql/json/revision_metadata.translated_metadata.json sql/upgrades/115.sql sql/upgrades/116.sql sql/upgrades/117.sql 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 sql/upgrades/128.sql sql/upgrades/129.sql sql/upgrades/130.sql sql/upgrades/131.sql sql/upgrades/132.sql +sql/upgrades/133.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-superuser-init.sql swh/indexer/sql/20-enums.sql swh/indexer/sql/30-schema.sql swh/indexer/sql/50-data.sql swh/indexer/sql/50-func.sql swh/indexer/sql/60-indexes.sql swh/indexer/storage/__init__.py swh/indexer/storage/converters.py swh/indexer/storage/db.py swh/indexer/storage/exc.py swh/indexer/storage/in_memory.py swh/indexer/storage/interface.py swh/indexer/storage/metrics.py swh/indexer/storage/model.py swh/indexer/storage/api/__init__.py swh/indexer/storage/api/client.py swh/indexer/storage/api/serializers.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_codemeta.py swh/indexer/tests/test_ctags.py swh/indexer/tests/test_fossology_license.py swh/indexer/tests/test_indexer.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/test_tasks.py swh/indexer/tests/utils.py swh/indexer/tests/storage/__init__.py swh/indexer/tests/storage/conftest.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_init.py swh/indexer/tests/storage/test_metrics.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/cli.py b/swh/indexer/cli.py index 1b2b9d3..0463ef4 100644 --- a/swh/indexer/cli.py +++ b/swh/indexer/cli.py @@ -1,301 +1,301 @@ # Copyright (C) 2019-2020 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 typing import Iterator # WARNING: do not import unnecessary things here to keep cli startup time under # control import click from swh.core.cli import CONTEXT_SETTINGS, AliasedGroup from swh.core.cli import swh as swh_cli_group @swh_cli_group.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 indexer_cli_group(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. """ from swh.core import config 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]) @indexer_cli_group.group("mapping") def mapping(): """Manage Software Heritage Indexer mappings.""" pass @mapping.command("list") def mapping_list(): """Prints the list of known mappings.""" from swh.indexer import metadata_dictionary 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.""" from swh.indexer import metadata_dictionary 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.""" import json from swh.indexer import metadata_dictionary 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)) @indexer_cli_group.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.""" from swh.indexer.storage import get_indexer_storage from swh.scheduler import get_scheduler from swh.storage import get_storage 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) -> Iterator[str]: next_page_token = "" limit = 10000 while next_page_token is not None: result = idx_storage.origin_intrinsic_metadata_search_by_producer( page_token=next_page_token, limit=limit, ids_only=True, mappings=mappings or None, tool_ids=tool_ids or None, ) next_page_token = result.next_page_token yield from result.results @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.""" from swh.scheduler.cli_utils import schedule_origin_batches 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", "retries_left": 1} + kwargs = {"retries_left": 1} schedule_origin_batches(scheduler, task_type, origins, origin_batch_size, kwargs) @indexer_cli_group.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( "--stop-after-objects", "-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, stop_after_objects, ): """Listens for new objects from the SWH Journal, and schedules tasks to run relevant indexers (currently, only origin-intrinsic-metadata) on these new objects.""" import functools from swh.indexer.journal_client import process_journal_objects from swh.journal.client import get_journal_client from swh.scheduler import get_scheduler scheduler = _get_api(get_scheduler, ctx.obj["config"], "scheduler", scheduler_url) client = get_journal_client( cls="kafka", brokers=brokers, prefix=prefix, group_id=group_id, object_types=["origin_visit"], stop_after_objects=stop_after_objects, ) worker_fn = functools.partial( process_journal_objects, scheduler=scheduler, task_names={"origin_metadata": origin_metadata_task_type,}, ) try: client.process(worker_fn) except KeyboardInterrupt: ctx.exit(0) else: print("Done.") finally: client.close() @indexer_cli_group.command("rpc-serve") @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.""" from swh.indexer.storage.api.server import app, load_and_check_config 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 indexer_cli_group(auto_envvar_prefix="SWH_INDEXER") if __name__ == "__main__": main() diff --git a/swh/indexer/ctags.py b/swh/indexer/ctags.py index 4c1e9d7..e024477 100644 --- a/swh/indexer/ctags.py +++ b/swh/indexer/ctags.py @@ -1,151 +1,147 @@ # Copyright (C) 2015-2020 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 subprocess from typing import Any, Dict, Iterator, List, Optional from swh.core.config import merge_configs from swh.indexer.storage import Sha1 from swh.indexer.storage.model import ContentCtagsRow from swh.model import hashutil from .indexer import ContentIndexer, write_to_temp # Options used to compute tags __FLAGS = [ "--fields=+lnz", # +l: language # +n: line number of tag definition # +z: include the symbol's kind (function, variable, ...) "--sort=no", # sort output on tag name "--links=no", # do not follow symlinks "--output-format=json", # outputs in json ] def compute_language(content, log=None): raise NotImplementedError( "Language detection was unreliable, so it is currently disabled. " "See https://forge.softwareheritage.org/D1455" ) def run_ctags(path, lang=None, ctags_command="ctags") -> Iterator[Dict[str, Any]]: """Run ctags on file path with optional language. Args: path: path to the file lang: language for that path (optional) Yields: dict: ctags' output """ optional = [] if lang: optional = ["--language-force=%s" % lang] cmd = [ctags_command] + __FLAGS + optional + [path] output = subprocess.check_output(cmd, universal_newlines=True) for symbol in output.split("\n"): if not symbol: continue js_symbol = json.loads(symbol) yield { "name": js_symbol["name"], "kind": js_symbol["kind"], "line": js_symbol["line"], "lang": js_symbol["language"], } DEFAULT_CONFIG: Dict[str, Any] = { "workdir": "/tmp/swh/indexer.ctags", "tools": { "name": "universal-ctags", "version": "~git7859817b", "configuration": { "command_line": """ctags --fields=+lnz --sort=no --links=no """ """--output-format=json """ }, }, "languages": {}, } class CtagsIndexer(ContentIndexer[ContentCtagsRow]): def __init__(self, *args, **kwargs): super().__init__(*args, **kwargs) self.config = merge_configs(DEFAULT_CONFIG, self.config) self.working_directory = self.config["workdir"] self.language_map = self.config["languages"] def filter(self, ids): """Filter out known sha1s and return only missing ones. """ yield from self.idx_storage.content_ctags_missing( ({"id": sha1, "indexer_configuration_id": self.tool["id"],} for sha1 in ids) ) def index( self, id: Sha1, data: Optional[bytes] = None, **kwargs ) -> List[ContentCtagsRow]: """Index sha1s' content and store result. Args: id (bytes): content's identifier data (bytes): raw content in bytes Returns: dict: a dict representing a content_mimetype with keys: - **id** (bytes): content's identifier (sha1) - **ctags** ([dict]): ctags list of symbols """ assert isinstance(id, bytes) assert data is not None lang = compute_language(data, log=self.log)["lang"] if not lang: return [] ctags_lang = self.language_map.get(lang) if not ctags_lang: return [] ctags = [] filename = hashutil.hash_to_hex(id) with write_to_temp( filename=filename, data=data, working_directory=self.working_directory ) as content_path: for ctag_kwargs in run_ctags(content_path, lang=ctags_lang): ctags.append( ContentCtagsRow( id=id, indexer_configuration_id=self.tool["id"], **ctag_kwargs, ) ) return ctags def persist_index_computations( - self, results: List[ContentCtagsRow], policy_update: str + self, results: List[ContentCtagsRow] ) -> Dict[str, int]: """Persist the results in storage. Args: results: list of ctags returned by index() - policy_update: either 'update-dups' or 'ignore-dups' to - respectively update duplicates or ignore them """ - return self.idx_storage.content_ctags_add( - results, conflict_update=(policy_update == "update-dups") - ) + return self.idx_storage.content_ctags_add(results) diff --git a/swh/indexer/fossology_license.py b/swh/indexer/fossology_license.py index a7a1cc8..e423ccf 100644 --- a/swh/indexer/fossology_license.py +++ b/swh/indexer/fossology_license.py @@ -1,190 +1,185 @@ # Copyright (C) 2016-2020 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 logging import subprocess from typing import Any, Dict, List, Optional from swh.core.config import merge_configs from swh.indexer.storage.interface import IndexerStorageInterface, PagedResult, Sha1 from swh.indexer.storage.model import ContentLicenseRow from swh.model import hashutil from .indexer import ContentIndexer, ContentPartitionIndexer, write_to_temp logger = logging.getLogger(__name__) def compute_license(path) -> Dict: """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: from os import path as __path logger.exception( "Problem during license detection for sha1 %s" % __path.basename(path) ) return { "licenses": [], "path": path, } DEFAULT_CONFIG: Dict[str, Any] = { "workdir": "/tmp/swh/indexer.fossology.license", "tools": { "name": "nomos", "version": "3.1.0rc2-31-ga2cbb8c", "configuration": {"command_line": "nomossa ",}, }, "write_batch_size": 1000, } class MixinFossologyLicenseIndexer: """Mixin fossology license indexer. See :class:`FossologyLicenseIndexer` and :class:`FossologyLicensePartitionIndexer` """ tool: Any idx_storage: IndexerStorageInterface def __init__(self, *args, **kwargs): super().__init__(*args, **kwargs) self.config = merge_configs(DEFAULT_CONFIG, self.config) self.working_directory = self.config["workdir"] def index( self, id: Sha1, data: Optional[bytes] = None, **kwargs ) -> List[ContentLicenseRow]: """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 data is not None 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) return [ ContentLicenseRow( id=id, indexer_configuration_id=self.tool["id"], license=license, ) for license in properties["licenses"] ] def persist_index_computations( - self, results: List[ContentLicenseRow], policy_update: str + self, results: List[ContentLicenseRow] ) -> Dict[str, int]: """Persist the results in storage. Args: results: 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: either 'update-dups' or 'ignore-dups' to - respectively update duplicates or ignore them - """ - return self.idx_storage.content_fossology_license_add( - results, conflict_update=(policy_update == "update-dups") - ) + return self.idx_storage.content_fossology_license_add(results) class FossologyLicenseIndexer( MixinFossologyLicenseIndexer, ContentIndexer[ContentLicenseRow] ): """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 FossologyLicensePartitionIndexer( MixinFossologyLicenseIndexer, ContentPartitionIndexer[ContentLicenseRow] ): """FossologyLicense Range Indexer working on range/partition of content identifiers. - filters out the non textual content - (optionally) filters out content already indexed (cf :meth:`.indexed_contents_in_partition`) - reads content from objstorage per the content's id (sha1) - computes {mimetype, encoding} from that content - stores result in storage """ def indexed_contents_in_partition( self, partition_id: int, nb_partitions: int, page_token: Optional[str] = None ) -> PagedResult[Sha1]: """Retrieve indexed content id within the partition id Args: partition_id: Index of the partition to fetch nb_partitions: Total number of partitions to split into page_token: opaque token used for pagination Returns: PagedResult of Sha1. If next_page_token is None, there is no more data to fetch """ return self.idx_storage.content_fossology_license_get_partition( self.tool["id"], partition_id, nb_partitions, page_token=page_token ) diff --git a/swh/indexer/indexer.py b/swh/indexer/indexer.py index e32e069..3c76c41 100644 --- a/swh/indexer/indexer.py +++ b/swh/indexer/indexer.py @@ -1,609 +1,614 @@ # Copyright (C) 2016-2020 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 from contextlib import contextmanager import logging import os import shutil import tempfile from typing import Any, Dict, Generic, Iterator, List, Optional, Set, TypeVar, Union +import warnings from swh.core import utils from swh.core.config import load_from_envvar, merge_configs from swh.indexer.storage import INDEXER_CFG_KEY, PagedResult, Sha1, get_indexer_storage from swh.indexer.storage.interface import IndexerStorageInterface from swh.model import hashutil from swh.model.model import Revision, Sha1Git from swh.objstorage.exc import ObjNotFoundError from swh.objstorage.factory import get_objstorage from swh.scheduler import CONFIG as SWH_CONFIG from swh.storage import get_storage from swh.storage.interface import StorageInterface @contextmanager def write_to_temp(filename: str, data: bytes, working_directory: str) -> Iterator[str]: """Write the sha1's content in a temporary file. Args: filename: one of sha1's many filenames data: the sha1's content to write in temporary file working_directory: the directory into which the file is written 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) DEFAULT_CONFIG = { INDEXER_CFG_KEY: {"cls": "memory"}, "storage": {"cls": "memory"}, "objstorage": {"cls": "memory"}, } TId = TypeVar("TId") """type of the ids of index()ed objects.""" TData = TypeVar("TData") """type of the objects passed to index().""" TResult = TypeVar("TResult") """return type of index()""" class BaseIndexer(Generic[TId, TData, TResult], 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. """ results: List[TResult] USE_TOOLS = True catch_exceptions = True """Prevents exceptions in `index()` from raising too high. Set to False in tests to properly catch all exceptions.""" scheduler: Any storage: StorageInterface objstorage: Any idx_storage: IndexerStorageInterface def __init__(self, config=None, **kw) -> None: """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: self.config = load_from_envvar() self.config = merge_configs(DEFAULT_CONFIG, self.config) self.prepare() self.check() self.log.debug("%s: config=%s", self, self.config) def prepare(self) -> None: """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) -> Dict: return self.tools[0] def check(self) -> None: """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: Dict[str, Any]) -> Dict[str, Any]: """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: Union[Dict[str, Any], List[Dict[str, Any]]] ) -> List[Dict[str, Any]]: """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: 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: TId, data: Optional[TData], **kwargs) -> List[TResult]: """Index computation for the id and associated raw data. Args: id: identifier or Dict object data: 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: List[TId]) -> Iterator[TId]: """Filter missing ids for that particular indexer. Args: ids: list of ids Yields: iterator of missing ids """ yield from ids @abc.abstractmethod - def persist_index_computations( - self, results: List[TResult], policy_update: str - ) -> Dict[str, int]: + def persist_index_computations(self, results: List[TResult]) -> Dict[str, int]: """Persist the computation resulting from the index. Args: results: List of results. One result is the result of the index function. - policy_update: either 'update-dups' or 'ignore-dups' to - respectively update duplicates or ignore them Returns: a summary dict of what has been inserted in the storage """ return {} class ContentIndexer(BaseIndexer[Sha1, bytes, TResult], Generic[TResult]): """A content indexer working on a list of ids directly. To work on indexer partition, use the :class:`ContentPartitionIndexer` 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: List[Sha1], policy_update: str, **kwargs) -> Dict: + def run(self, ids: List[Sha1], **kwargs) -> Dict: """Given a list of ids: - retrieve the content from the storage - execute the indexing computations - - store the results (according to policy_update) + - store the results 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 **kwargs: passed to the `index` method Returns: A summary Dict of the task's status """ + if "policy_update" in kwargs: + warnings.warn( + "'policy_update' argument is deprecated and ignored.", + DeprecationWarning, + ) + del kwargs["policy_update"] + sha1s = [ hashutil.hash_to_bytes(id_) if isinstance(id_, str) else id_ for id_ in ids ] results = [] summary: Dict = {"status": "uneventful"} try: for sha1 in sha1s: 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.extend(res) summary["status"] = "eventful" - summary = self.persist_index_computations(results, policy_update) + summary = self.persist_index_computations(results) self.results = results except Exception: if not self.catch_exceptions: raise self.log.exception("Problem when reading contents metadata.") summary["status"] = "failed" return summary class ContentPartitionIndexer(BaseIndexer[Sha1, bytes, TResult], Generic[TResult]): """A content partition indexer. This expects as input a partition_id and a nb_partitions. This will then index the contents within that partition. To work on a list of ids, use the :class:`ContentIndexer` instead. Note: :class:`ContentPartitionIndexer` 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_partition( self, partition_id: int, nb_partitions: int, page_token: Optional[str] = None ) -> PagedResult[Sha1]: """Retrieve indexed contents within range [start, end]. Args: partition_id: Index of the partition to fetch nb_partitions: Total number of partitions to split into page_token: opaque token used for pagination Returns: PagedResult of Sha1. If next_page_token is None, there is no more data to fetch """ pass def _list_contents_to_index( self, partition_id: int, nb_partitions: int, indexed: Set[Sha1] ) -> Iterator[Sha1]: """Compute from storage the new contents to index in the partition_id . The already indexed contents are skipped. Args: partition_id: Index of the partition to fetch data from nb_partitions: Total number of partition indexed: Set of content already indexed. Yields: Sha1 id (bytes) of contents to index """ if not isinstance(partition_id, int) or not isinstance(nb_partitions, int): raise TypeError( f"identifiers must be int, not {partition_id!r} and {nb_partitions!r}." ) next_page_token = None while True: result = self.storage.content_get_partition( partition_id, nb_partitions, page_token=next_page_token ) contents = result.results for c in contents: _id = hashutil.hash_to_bytes(c.sha1) if _id in indexed: continue yield _id next_page_token = result.next_page_token if next_page_token is None: break def _index_contents( self, partition_id: int, nb_partitions: int, indexed: Set[Sha1], **kwargs: Any ) -> Iterator[TResult]: """Index the contents within the partition_id. Args: start: Starting bound from range identifier end: End range identifier indexed: Set of content already indexed. Yields: indexing result as dict to persist in the indexer backend """ for sha1 in self._list_contents_to_index(partition_id, nb_partitions, indexed): try: raw_content = self.objstorage.get(sha1) except ObjNotFoundError: self.log.warning(f"Content {sha1.hex()} not found in objstorage") continue yield from self.index(sha1, raw_content, **kwargs) def _index_with_skipping_already_done( self, partition_id: int, nb_partitions: int ) -> Iterator[TResult]: """Index not already indexed contents within the partition partition_id Args: partition_id: Index of the partition to fetch nb_partitions: Total number of partitions to split into Yields: indexing result as dict to persist in the indexer backend """ next_page_token = None contents = set() while True: indexed_page = self.indexed_contents_in_partition( partition_id, nb_partitions, page_token=next_page_token ) for sha1 in indexed_page.results: contents.add(sha1) yield from self._index_contents(partition_id, nb_partitions, contents) next_page_token = indexed_page.next_page_token if next_page_token is None: break def run( self, partition_id: int, nb_partitions: int, skip_existing: bool = True, **kwargs, ) -> Dict: """Given a partition of content ids, index the contents within. Either the indexer is incremental (filter out existing computed data) or it computes everything from scratch. Args: partition_id: Index of the partition to fetch nb_partitions: Total number of partitions to split into skip_existing: Skip existing indexed data (default) or not **kwargs: passed to the `index` method Returns: dict with the indexing task status """ summary: Dict[str, Any] = {"status": "uneventful"} count = 0 try: if skip_existing: gen = self._index_with_skipping_already_done( partition_id, nb_partitions ) else: gen = self._index_contents(partition_id, nb_partitions, indexed=set([])) count_object_added_key: Optional[str] = None for contents in utils.grouper(gen, n=self.config["write_batch_size"]): - res = self.persist_index_computations( - list(contents), policy_update="update-dups" - ) + res = self.persist_index_computations(list(contents)) if not count_object_added_key: count_object_added_key = list(res.keys())[0] count += res[count_object_added_key] if count > 0: summary["status"] = "eventful" except Exception: if not self.catch_exceptions: raise self.log.exception("Problem when computing metadata.") summary["status"] = "failed" if count > 0 and count_object_added_key: summary[count_object_added_key] = count return summary class OriginIndexer(BaseIndexer[str, None, TResult], Generic[TResult]): """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: List[str], policy_update: str = "update-dups", **kwargs - ) -> Dict: + def run(self, origin_urls: List[str], **kwargs) -> Dict: """Given a list of origin urls: - retrieve origins from storage - execute the indexing computations - - store the results (according to policy_update) + - store the results Args: origin_urls: list of origin urls. - policy_update: either 'update-dups' or 'ignore-dups' to - respectively update duplicates (default) or ignore them **kwargs: passed to the `index` method """ + if "policy_update" in kwargs: + warnings.warn( + "'policy_update' argument is deprecated and ignored.", + DeprecationWarning, + ) + del kwargs["policy_update"] summary: Dict[str, Any] = {"status": "uneventful"} try: results = self.index_list(origin_urls, **kwargs) except Exception: if not self.catch_exceptions: raise summary["status"] = "failed" return summary - summary_persist = self.persist_index_computations(results, policy_update) + summary_persist = self.persist_index_computations(results) self.results = results if summary_persist: for value in summary_persist.values(): if value > 0: summary["status"] = "eventful" summary.update(summary_persist) return summary def index_list(self, origin_urls: List[str], **kwargs) -> List[TResult]: results = [] for origin_url in origin_urls: try: results.extend(self.index(origin_url, **kwargs)) except Exception: self.log.exception("Problem when processing origin %s", origin_url) raise return results class RevisionIndexer(BaseIndexer[Sha1Git, Revision, TResult], Generic[TResult]): """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: List[Sha1Git], policy_update: str) -> Dict: + def run(self, ids: List[Sha1Git], **kwargs) -> Dict: """Given a list of sha1_gits: - retrieve revisions from storage - execute the indexing computations - - store the results (according to policy_update) + - store the results Args: ids: sha1_git's identifier list - policy_update: either 'update-dups' or 'ignore-dups' to - respectively update duplicates or ignore them """ + if "policy_update" in kwargs: + warnings.warn( + "'policy_update' argument is deprecated and ignored.", + DeprecationWarning, + ) + del kwargs["policy_update"] summary: Dict[str, Any] = {"status": "uneventful"} results = [] revision_ids = [ hashutil.hash_to_bytes(id_) if isinstance(id_, str) else id_ for id_ in ids ] for (rev_id, rev) in zip(revision_ids, self.storage.revision_get(revision_ids)): if not rev: # TODO: call self.index() with rev=None? self.log.warning( "Revision %s not found in storage", hashutil.hash_to_hex(rev_id) ) continue try: results.extend(self.index(rev_id, rev)) except Exception: if not self.catch_exceptions: raise self.log.exception("Problem when processing revision") summary["status"] = "failed" return summary - summary_persist = self.persist_index_computations(results, policy_update) + summary_persist = self.persist_index_computations(results) if summary_persist: for value in summary_persist.values(): if value > 0: summary["status"] = "eventful" summary.update(summary_persist) self.results = results return summary diff --git a/swh/indexer/journal_client.py b/swh/indexer/journal_client.py index 9331e1e..06842a8 100644 --- a/swh/indexer/journal_client.py +++ b/swh/indexer/journal_client.py @@ -1,45 +1,44 @@ # Copyright (C) 2018-2020 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 logging from swh.core.utils import grouper from swh.scheduler.utils import create_task_dict MAX_ORIGINS_PER_TASK = 100 def process_journal_objects(messages, *, scheduler, task_names): """Worker function for `JournalClient.process(worker_fn)`, after currification of `scheduler` and `task_names`.""" assert set(messages) == {"origin_visit"}, set(messages) process_origin_visits(messages["origin_visit"], scheduler, task_names) def process_origin_visits(visits, scheduler, task_names): task_dicts = [] logging.debug("processing origin visits %r", visits) if task_names.get("origin_metadata"): visits = [visit for visit in visits if visit["status"] == "full"] visit_batches = grouper(visits, MAX_ORIGINS_PER_TASK) for visit_batch in visit_batches: visit_urls = [] for visit in visit_batch: if isinstance(visit["origin"], str): visit_urls.append(visit["origin"]) else: visit_urls.append(visit["origin"]["url"]) task_dicts.append( create_task_dict( task_names["origin_metadata"], "oneshot", visit_urls, - policy_update="update-dups", retries_left=1, ) ) if task_dicts: scheduler.create_tasks(task_dicts) diff --git a/swh/indexer/metadata.py b/swh/indexer/metadata.py index 0e37963..e81466c 100644 --- a/swh/indexer/metadata.py +++ b/swh/indexer/metadata.py @@ -1,432 +1,378 @@ # Copyright (C) 2017-2020 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 typing import ( Any, Callable, Dict, Iterable, Iterator, List, Optional, Tuple, TypeVar, ) from swh.core.config import merge_configs from swh.core.utils import grouper from swh.indexer.codemeta import merge_documents from swh.indexer.indexer import ContentIndexer, OriginIndexer, RevisionIndexer from swh.indexer.metadata_detector import detect_metadata from swh.indexer.metadata_dictionary import MAPPINGS from swh.indexer.origin_head import OriginHeadIndexer from swh.indexer.storage import INDEXER_CFG_KEY, Sha1 from swh.indexer.storage.model import ( ContentMetadataRow, OriginIntrinsicMetadataRow, RevisionIntrinsicMetadataRow, ) from swh.model import hashutil from swh.model.model import Revision, Sha1Git REVISION_GET_BATCH_SIZE = 10 ORIGIN_GET_BATCH_SIZE = 10 T1 = TypeVar("T1") T2 = TypeVar("T2") def call_with_batches( f: Callable[[List[T1]], Iterable[T2]], args: List[T1], batch_size: int, ) -> Iterator[T2]: """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[ContentMetadataRow]): """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: Sha1, data: Optional[bytes] = None, log_suffix="unknown revision", **kwargs, ) -> List[ContentMetadataRow]: """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 """ assert isinstance(id, bytes) assert data is not None try: mapping_name = self.tool["tool_configuration"]["context"] log_suffix += ", content_id=%s" % hashutil.hash_to_hex(id) 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 metadata is None: return [] return [ ContentMetadataRow( id=id, indexer_configuration_id=self.tool["id"], metadata=metadata, ) ] def persist_index_computations( - self, results: List[ContentMetadataRow], policy_update: str + self, results: List[ContentMetadataRow] ) -> Dict[str, int]: """Persist the results in storage. Args: results: list of content_metadata, dict with the following keys: - id (bytes): content's identifier (sha1) - metadata (jsonb): detected metadata - policy_update: either 'update-dups' or 'ignore-dups' to - respectively update duplicates or ignore them """ - return self.idx_storage.content_metadata_add( - results, conflict_update=(policy_update == "update-dups") - ) + return self.idx_storage.content_metadata_add(results) DEFAULT_CONFIG: Dict[str, Any] = { "tools": { "name": "swh-metadata-detector", "version": "0.0.2", "configuration": {}, }, } class RevisionMetadataIndexer(RevisionIndexer[RevisionIntrinsicMetadataRow]): """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 """ def __init__(self, *args, **kwargs): super().__init__(*args, **kwargs) self.config = merge_configs(DEFAULT_CONFIG, self.config) 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, id: Sha1Git, data: Optional[Revision], **kwargs ) -> List[RevisionIntrinsicMetadataRow]: """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: id: sha1_git of the revision data: revision model object 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 """ rev = data assert isinstance(rev, Revision) 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 = list(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), ) except Exception as e: self.log.exception("Problem when indexing rev: %r", e) return [ RevisionIntrinsicMetadataRow( id=rev.id, indexer_configuration_id=self.tool["id"], mappings=mappings, metadata=metadata, ) ] def persist_index_computations( - self, results: List[RevisionIntrinsicMetadataRow], policy_update: str + self, results: List[RevisionIntrinsicMetadataRow] ) -> Dict[str, int]: """Persist the results in storage. Args: results: 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: 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 - return self.idx_storage.revision_intrinsic_metadata_add( - results, conflict_update=(policy_update == "update-dups") - ) + return self.idx_storage.revision_intrinsic_metadata_add(results) def translate_revision_intrinsic_metadata( self, detected_files: Dict[str, List[Any]], log_suffix: str ) -> Tuple[List[Any], Any]: """ Determine plan of action to translate metadata when containing one or multiple detected files: Args: detected_files: 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, + sha1s_filtered, 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[Tuple[OriginIntrinsicMetadataRow, RevisionIntrinsicMetadataRow]] ): USE_TOOLS = False def __init__(self, config=None, **kwargs) -> None: 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: List[str], **kwargs ) -> List[Tuple[OriginIntrinsicMetadataRow, RevisionIntrinsicMetadataRow]]: head_rev_ids = [] origins_with_head = [] origins = list( call_with_batches( self.storage.origin_get, origin_urls, ORIGIN_GET_BATCH_SIZE, ) ) for origin in origins: if origin is None: continue head_results = self.origin_head_indexer.index(origin.url) if head_results: (head_result,) = head_results 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 for rev_metadata in self.revision_metadata_indexer.index(rev.id, rev): # There is at most one rev_metadata orig_metadata = OriginIntrinsicMetadataRow( from_revision=rev_metadata.id, 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: List[Tuple[OriginIntrinsicMetadataRow, RevisionIntrinsicMetadataRow]], - policy_update: str, ) -> Dict[str, int]: - conflict_update = policy_update == "update-dups" - # Deduplicate revisions rev_metadata: List[RevisionIntrinsicMetadataRow] = [] orig_metadata: List[OriginIntrinsicMetadataRow] = [] - revs_to_delete: List[Dict] = [] - origs_to_delete: List[Dict] = [] summary: Dict = {} 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( - { - "id": rev_item.id, - "indexer_configuration_id": ( - rev_item.indexer_configuration_id - ), - } - ) - if orig_item not in origs_to_delete: - origs_to_delete.append( - { - "id": orig_item.id, - "indexer_configuration_id": ( - orig_item.indexer_configuration_id - ), - } - ) - else: + if rev_item.metadata and not (rev_item.metadata.keys() <= {"@context"}): + # Only store non-empty metadata sets 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: - summary_rev = self.idx_storage.revision_intrinsic_metadata_add( - rev_metadata, conflict_update=conflict_update - ) + summary_rev = self.idx_storage.revision_intrinsic_metadata_add(rev_metadata) summary.update(summary_rev) if orig_metadata: - summary_ori = self.idx_storage.origin_intrinsic_metadata_add( - orig_metadata, conflict_update=conflict_update - ) - summary.update(summary_ori) - - # 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: - summary_ori = self.idx_storage.origin_intrinsic_metadata_delete( - origs_to_delete - ) + summary_ori = self.idx_storage.origin_intrinsic_metadata_add(orig_metadata) summary.update(summary_ori) - if revs_to_delete: - summary_rev = self.idx_storage.revision_intrinsic_metadata_delete( - revs_to_delete - ) - summary.update(summary_rev) return summary diff --git a/swh/indexer/mimetype.py b/swh/indexer/mimetype.py index fa78f3c..3185534 100644 --- a/swh/indexer/mimetype.py +++ b/swh/indexer/mimetype.py @@ -1,169 +1,164 @@ # Copyright (C) 2016-2020 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 typing import Any, Dict, List, Optional import magic from swh.core.config import merge_configs from swh.indexer.storage.interface import IndexerStorageInterface, PagedResult, Sha1 from swh.indexer.storage.model import ContentMimetypeRow from .indexer import ContentIndexer, ContentPartitionIndexer 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: bytes) -> Dict[str, str]: """Determine mimetype and encoding from the raw content. Args: raw_content: content's raw data Returns: dict: mimetype and encoding key and corresponding values. """ m = magic.Magic(mime=True, mime_encoding=True) res = m.from_buffer(raw_content) try: mimetype, encoding = res.split("; charset=") except ValueError: mimetype, encoding = res, "" return { "mimetype": mimetype, "encoding": encoding, } DEFAULT_CONFIG: Dict[str, Any] = { "tools": { "name": "file", "version": "1:5.30-1+deb9u1", "configuration": {"type": "library", "debian-package": "python3-magic"}, }, "write_batch_size": 1000, } class MixinMimetypeIndexer: """Mixin mimetype indexer. See :class:`MimetypeIndexer` and :class:`MimetypePartitionIndexer` """ tool: Any idx_storage: IndexerStorageInterface def __init__(self, *args, **kwargs): super().__init__(*args, **kwargs) self.config = merge_configs(DEFAULT_CONFIG, self.config) def index( self, id: Sha1, data: Optional[bytes] = None, **kwargs ) -> List[ContentMimetypeRow]: """Index sha1s' content and store result. Args: id: content's identifier data: raw content in bytes Returns: dict: content's mimetype; dict keys being - id: content's identifier (sha1) - mimetype: mimetype in bytes - encoding: encoding in bytes """ assert data is not None properties = compute_mimetype_encoding(data) return [ ContentMimetypeRow( id=id, indexer_configuration_id=self.tool["id"], mimetype=properties["mimetype"], encoding=properties["encoding"], ) ] def persist_index_computations( - self, results: List[ContentMimetypeRow], policy_update: str + self, results: List[ContentMimetypeRow] ) -> Dict[str, int]: """Persist the results in storage. Args: results: list of content's mimetype dicts (see :meth:`.index`) - policy_update: either 'update-dups' or 'ignore-dups' to - respectively update duplicates or ignore them - """ - return self.idx_storage.content_mimetype_add( - results, conflict_update=(policy_update == "update-dups") - ) + return self.idx_storage.content_mimetype_add(results) class MimetypeIndexer(MixinMimetypeIndexer, ContentIndexer[ContentMimetypeRow]): """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 MimetypePartitionIndexer( MixinMimetypeIndexer, ContentPartitionIndexer[ContentMimetypeRow] ): """Mimetype Range Indexer working on range of content identifiers. It: - (optionally) filters out content already indexed (cf :meth:`.indexed_contents_in_partition`) - reads content from objstorage per the content's id (sha1) - computes {mimetype, encoding} from that content - stores result in storage """ def indexed_contents_in_partition( self, partition_id: int, nb_partitions: int, page_token: Optional[str] = None, ) -> PagedResult[Sha1]: """Retrieve indexed content ids within partition_id. Args: partition_id: Index of the partition to fetch nb_partitions: Total number of partitions to split into page_token: opaque token used for pagination Returns: PagedResult of Sha1. If next_page_token is None, there is no more data to fetch """ return self.idx_storage.content_mimetype_get_partition( self.tool["id"], partition_id, nb_partitions, page_token=page_token ) diff --git a/swh/indexer/origin_head.py b/swh/indexer/origin_head.py index 9107e6e..d1c42b2 100644 --- a/swh/indexer/origin_head.py +++ b/swh/indexer/origin_head.py @@ -1,157 +1,155 @@ # Copyright (C) 2018-2020 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 logging import re from typing import Any, Dict, List, Tuple, Union import click from swh.indexer.indexer import OriginIndexer from swh.model.model import SnapshotBranch, TargetType from swh.storage.algos.origin import origin_get_latest_visit_status from swh.storage.algos.snapshot import snapshot_get_all_branches class OriginHeadIndexer(OriginIndexer[Dict]): """Origin-level indexer. This indexer is in charge of looking up the revision that acts as the "head" of an origin. In git, this is usually the commit pointed to by the 'master' branch.""" USE_TOOLS = False - def persist_index_computations( - self, results: Any, policy_update: str - ) -> Dict[str, int]: + def persist_index_computations(self, results: Any) -> Dict[str, int]: """Do nothing. The indexer's results are not persistent, they should only be piped to another indexer.""" return {} # Dispatch def index(self, id: str, data: None = None, **kwargs) -> List[Dict]: origin_url = id visit_and_status = origin_get_latest_visit_status( self.storage, origin_url, allowed_statuses=["full"], require_snapshot=True ) if not visit_and_status: return [] visit, visit_status = visit_and_status assert visit_status.snapshot is not None snapshot = snapshot_get_all_branches(self.storage, visit_status.snapshot) if snapshot is None: return [] method = getattr( self, "_try_get_%s_head" % visit.type, self._try_get_head_generic ) rev_id = method(snapshot.branches) if rev_id is not None: return [{"origin_url": origin_url, "revision_id": rev_id,}] # could not find a head revision return [] # Tarballs _archive_filename_re = re.compile( rb"^" rb"(?P.*)[-_]" rb"(?P[0-9]+(\.[0-9])*)" rb"(?P[-+][a-zA-Z0-9.~]+?)?" rb"(?P(\.[a-zA-Z0-9]+)+)" rb"$" ) @classmethod def _parse_version(cls: Any, filename: bytes) -> Tuple[Union[float, int], ...]: """Extracts the release version from an archive filename, to get an ordering whose maximum is likely to be the last version of the software >>> OriginHeadIndexer._parse_version(b'foo') (-inf,) >>> OriginHeadIndexer._parse_version(b'foo.tar.gz') (-inf,) >>> OriginHeadIndexer._parse_version(b'gnu-hello-0.0.1.tar.gz') (0, 0, 1, 0) >>> OriginHeadIndexer._parse_version(b'gnu-hello-0.0.1-beta2.tar.gz') (0, 0, 1, -1, 'beta2') >>> OriginHeadIndexer._parse_version(b'gnu-hello-0.0.1+foobar.tar.gz') (0, 0, 1, 1, 'foobar') """ res = cls._archive_filename_re.match(filename) if res is None: return (float("-infinity"),) version = [int(n) for n in res.group("version").decode().split(".")] if res.group("preversion") is None: version.append(0) else: preversion = res.group("preversion").decode() if preversion.startswith("-"): version.append(-1) version.append(preversion[1:]) elif preversion.startswith("+"): version.append(1) version.append(preversion[1:]) else: assert False, res.group("preversion") return tuple(version) def _try_get_ftp_head(self, branches: Dict[bytes, SnapshotBranch]) -> Any: archive_names = list(branches) max_archive_name = max(archive_names, key=self._parse_version) r = self._try_resolve_target(branches, max_archive_name) return r # Generic def _try_get_head_generic(self, branches: Dict[bytes, SnapshotBranch]) -> Any: # Works on 'deposit', 'pypi', and VCSs. return self._try_resolve_target(branches, b"HEAD") or self._try_resolve_target( branches, b"master" ) def _try_resolve_target( self, branches: Dict[bytes, SnapshotBranch], branch_name: bytes ) -> Any: try: branch = branches[branch_name] if branch is None: return None while branch.target_type == TargetType.ALIAS: branch = branches[branch.target] if branch is None: return None if branch.target_type == TargetType.REVISION: return branch.target elif branch.target_type == TargetType.CONTENT: return None # TODO elif branch.target_type == TargetType.DIRECTORY: return None # TODO elif branch.target_type == TargetType.RELEASE: return None # TODO else: assert False, branch except KeyError: return None @click.command() @click.option( "--origins", "-i", help='Origins to lookup, in the "type+url" format', multiple=True ) def main(origins: List[str]) -> None: rev_metadata_indexer = OriginHeadIndexer() rev_metadata_indexer.run(origins) if __name__ == "__main__": logging.basicConfig(level=logging.INFO) main() diff --git a/swh/indexer/sql/30-schema.sql b/swh/indexer/sql/30-schema.sql index acdf2e0..bb0f672 100644 --- a/swh/indexer/sql/30-schema.sql +++ b/swh/indexer/sql/30-schema.sql @@ -1,145 +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(132, now(), 'Work In Progress'); + values(133, 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 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 '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/50-func.sql b/swh/indexer/sql/50-func.sql index e6601d0..44c4fa1 100644 --- a/swh/indexer/sql/50-func.sql +++ b/swh/indexer/sql/50-func.sql @@ -1,472 +1,414 @@ -- 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 mimic create or replace function swh_mktemp(tblname regclass) returns void language plpgsql as $$ begin execute format(' create temporary table if not exists tmp_%1$I (like %1$I including defaults) on commit delete rows; alter table tmp_%1$I drop column if exists object_id; ', tblname); return; end $$; -- create a temporary table for content_mimetype tmp_content_mimetype, create or replace function swh_mktemp_content_mimetype() returns void language sql as $$ create temporary table if not exists tmp_content_mimetype ( like content_mimetype including defaults ) on commit delete rows; $$; 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. +-- add tmp_content_mimetype entries to content_mimetype, overwriting duplicates. -- -- 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) +create or replace function swh_content_mimetype_add() returns bigint language plpgsql as $$ declare res bigint; begin - if conflict_update then - insert into content_mimetype (id, mimetype, encoding, indexer_configuration_id) - select id, mimetype, encoding, indexer_configuration_id - from tmp_content_mimetype tcm - on conflict(id, indexer_configuration_id) - do update set mimetype = excluded.mimetype, - encoding = excluded.encoding; - else - insert into content_mimetype (id, mimetype, encoding, indexer_configuration_id) - select id, mimetype, encoding, indexer_configuration_id - from tmp_content_mimetype tcm - on conflict(id, indexer_configuration_id) - do nothing; - end if; + insert into content_mimetype (id, mimetype, encoding, indexer_configuration_id) + select id, mimetype, encoding, indexer_configuration_id + from tmp_content_mimetype tcm + on conflict(id, indexer_configuration_id) + do update set mimetype = excluded.mimetype, + encoding = excluded.encoding; + get diagnostics res = ROW_COUNT; return res; end $$; -comment on function swh_content_mimetype_add(boolean) IS 'Add new content mimetypes'; +comment on function swh_content_mimetype_add() IS 'Add new content mimetypes'; --- add tmp_content_language entries to content_language, overwriting --- duplicates if conflict_update is true, skipping duplicates otherwise. +-- add tmp_content_language entries to content_language, overwriting duplicates. -- -- 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) +create or replace function swh_content_language_add() returns bigint language plpgsql as $$ declare res bigint; begin - if conflict_update then - insert into content_language (id, lang, indexer_configuration_id) - select id, lang, indexer_configuration_id - from tmp_content_language tcl - on conflict(id, indexer_configuration_id) - do update set lang = excluded.lang; - else - insert into content_language (id, lang, indexer_configuration_id) - select id, lang, indexer_configuration_id - from tmp_content_language tcl - on conflict(id, indexer_configuration_id) - do nothing; - end if; + insert into content_language (id, lang, indexer_configuration_id) + select id, lang, indexer_configuration_id + from tmp_content_language tcl + on conflict(id, indexer_configuration_id) + do update set lang = excluded.lang; + get diagnostics res = ROW_COUNT; return res; end $$; -comment on function swh_content_language_add(boolean) IS 'Add new content languages'; +comment on function swh_content_language_add() 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 $$ create temporary table if not exists tmp_content_language ( like content_language including defaults ) on commit delete rows; $$; 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 $$ create temporary table if not exists tmp_content_ctags ( like content_ctags including defaults ) on commit delete rows; $$; 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. +-- add tmp_content_ctags entries to content_ctags, overwriting duplicates -- -- 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) +create or replace function swh_content_ctags_add() returns bigint language plpgsql as $$ declare res bigint; begin - if conflict_update then - delete from content_ctags - where id in (select tmp.id - from tmp_content_ctags tmp - inner join indexer_configuration i on i.id=tmp.indexer_configuration_id); - end if; - insert into content_ctags (id, name, kind, line, lang, indexer_configuration_id) select id, name, kind, line, lang, indexer_configuration_id from tmp_content_ctags tct on conflict(id, hash_sha1(name), kind, line, lang, indexer_configuration_id) do nothing; + get diagnostics res = ROW_COUNT; return res; end $$; -comment on function swh_content_ctags_add(boolean) IS 'Add new ctags symbols per content'; +comment on function swh_content_ctags_add() 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 $$ create temporary table if not exists tmp_content_fossology_license ( id sha1, license text, indexer_configuration_id integer ) on commit delete rows; $$; 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. +-- add tmp_content_fossology_license entries to content_fossology_license, +-- overwriting duplicates. -- -- 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) +create or replace function swh_content_fossology_license_add() returns bigint language plpgsql as $$ declare res bigint; begin -- insert unknown licenses first insert into fossology_license (name) select distinct license from tmp_content_fossology_license tmp where not exists (select 1 from fossology_license where name=tmp.license) on conflict(name) do nothing; - if conflict_update then - insert into content_fossology_license (id, license_id, indexer_configuration_id) - select tcl.id, - (select id from fossology_license where name = tcl.license) as license, - indexer_configuration_id - from tmp_content_fossology_license tcl - on conflict(id, license_id, indexer_configuration_id) - do update set license_id = excluded.license_id; - else - insert into content_fossology_license (id, license_id, indexer_configuration_id) - select tcl.id, - (select id from fossology_license where name = tcl.license) as license, - indexer_configuration_id - from tmp_content_fossology_license tcl - on conflict(id, license_id, indexer_configuration_id) - do nothing; - end if; + insert into content_fossology_license (id, license_id, indexer_configuration_id) + select tcl.id, + (select id from fossology_license where name = tcl.license) as license, + indexer_configuration_id + from tmp_content_fossology_license tcl + on conflict(id, license_id, indexer_configuration_id) + do update set license_id = excluded.license_id; get diagnostics res = ROW_COUNT; return res; end $$; -comment on function swh_content_fossology_license_add(boolean) IS 'Add new content licenses'; +comment on function swh_content_fossology_license_add() 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. +-- add tmp_content_metadata entries to content_metadata, overwriting duplicates -- -- 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) +create or replace function swh_content_metadata_add() returns bigint language plpgsql as $$ declare res bigint; begin - if conflict_update then - insert into content_metadata (id, metadata, indexer_configuration_id) - select id, metadata, indexer_configuration_id - from tmp_content_metadata tcm - on conflict(id, indexer_configuration_id) - do update set metadata = excluded.metadata; - else - insert into content_metadata (id, metadata, indexer_configuration_id) - select id, metadata, indexer_configuration_id - from tmp_content_metadata tcm - on conflict(id, indexer_configuration_id) - do nothing; - end if; + insert into content_metadata (id, metadata, indexer_configuration_id) + select id, metadata, indexer_configuration_id + from tmp_content_metadata tcm + on conflict(id, indexer_configuration_id) + do update set metadata = excluded.metadata; + get diagnostics res = ROW_COUNT; return res; end $$; -comment on function swh_content_metadata_add(boolean) IS 'Add new content metadata'; +comment on function swh_content_metadata_add() 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 $$ create temporary table if not exists tmp_content_metadata ( like content_metadata including defaults ) on commit delete rows; $$; 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. +-- overwriting duplicates. -- -- 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) +create or replace function swh_revision_intrinsic_metadata_add() returns bigint language plpgsql as $$ declare res bigint; begin - if conflict_update then - insert into revision_intrinsic_metadata (id, metadata, mappings, indexer_configuration_id) - select id, metadata, mappings, indexer_configuration_id - from tmp_revision_intrinsic_metadata tcm - on conflict(id, indexer_configuration_id) - do update set - metadata = excluded.metadata, - mappings = excluded.mappings; - else - insert into revision_intrinsic_metadata (id, metadata, mappings, indexer_configuration_id) - select id, metadata, mappings, indexer_configuration_id - from tmp_revision_intrinsic_metadata tcm - on conflict(id, indexer_configuration_id) - do nothing; - end if; + insert into revision_intrinsic_metadata (id, metadata, mappings, indexer_configuration_id) + select id, metadata, mappings, indexer_configuration_id + from tmp_revision_intrinsic_metadata tcm + on conflict(id, indexer_configuration_id) + do update set + metadata = excluded.metadata, + mappings = excluded.mappings; + get diagnostics res = ROW_COUNT; return res; end $$; -comment on function swh_revision_intrinsic_metadata_add(boolean) IS 'Add new revision intrinsic metadata'; +comment on function swh_revision_intrinsic_metadata_add() 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 $$ create temporary table if not exists tmp_revision_intrinsic_metadata ( like revision_intrinsic_metadata including defaults ) on commit delete rows; $$; 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 $$ create temporary table if not exists tmp_origin_intrinsic_metadata ( like origin_intrinsic_metadata including defaults ) on commit delete rows; $$; 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 $$ create temporary table if not exists tmp_indexer_configuration ( like indexer_configuration including defaults ) on commit delete rows; alter table tmp_indexer_configuration drop column if exists id; $$; -- add tmp_indexer_configuration entries to indexer_configuration, --- skipping duplicates if any. +-- overwriting 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. +-- overwriting duplicates. -- -- 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) +create or replace function swh_origin_intrinsic_metadata_add() returns bigint language plpgsql as $$ declare res bigint; begin perform swh_origin_intrinsic_metadata_compute_tsvector(); - if conflict_update then - insert into origin_intrinsic_metadata (id, metadata, indexer_configuration_id, from_revision, metadata_tsvector, mappings) - select id, metadata, indexer_configuration_id, from_revision, - metadata_tsvector, mappings - from tmp_origin_intrinsic_metadata - on conflict(id, indexer_configuration_id) - do update set - metadata = excluded.metadata, - metadata_tsvector = excluded.metadata_tsvector, - mappings = excluded.mappings, - from_revision = excluded.from_revision; - else - insert into origin_intrinsic_metadata (id, metadata, indexer_configuration_id, from_revision, metadata_tsvector, mappings) - select id, metadata, indexer_configuration_id, from_revision, - metadata_tsvector, mappings - from tmp_origin_intrinsic_metadata - on conflict(id, indexer_configuration_id) - do nothing; - end if; + + insert into origin_intrinsic_metadata (id, metadata, indexer_configuration_id, from_revision, metadata_tsvector, mappings) + select id, metadata, indexer_configuration_id, from_revision, + metadata_tsvector, mappings + from tmp_origin_intrinsic_metadata + on conflict(id, indexer_configuration_id) + do update set + metadata = excluded.metadata, + metadata_tsvector = excluded.metadata_tsvector, + mappings = excluded.mappings, + from_revision = excluded.from_revision; + get diagnostics res = ROW_COUNT; return res; end $$; -comment on function swh_origin_intrinsic_metadata_add(boolean) IS 'Add new origin intrinsic metadata'; +comment on function swh_origin_intrinsic_metadata_add() 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 ab5b80d..422ed19 100644 --- a/swh/indexer/storage/__init__.py +++ b/swh/indexer/storage/__init__.py @@ -1,745 +1,697 @@ # Copyright (C) 2015-2020 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 collections import Counter from importlib import import_module import json from typing import Dict, Iterable, List, Optional, Tuple, Union import warnings import psycopg2 import psycopg2.pool from swh.core.db.common import db_transaction from swh.indexer.storage.interface import IndexerStorageInterface from swh.model.hashutil import hash_to_bytes, hash_to_hex from swh.model.model import SHA1_SIZE from swh.storage.exc import StorageDBError from swh.storage.utils import get_partition_bounds_bytes from . import converters from .db import Db from .exc import DuplicateId, IndexerStorageArgumentException from .interface import PagedResult, Sha1 from .metrics import process_metrics, send_metric, timed from .model import ( ContentCtagsRow, ContentLanguageRow, ContentLicenseRow, ContentMetadataRow, ContentMimetypeRow, OriginIntrinsicMetadataRow, RevisionIntrinsicMetadataRow, ) INDEXER_CFG_KEY = "indexer_storage" MAPPING_NAMES = ["codemeta", "gemspec", "maven", "npm", "pkg-info"] SERVER_IMPLEMENTATIONS: Dict[str, str] = { "local": ".IndexerStorage", "remote": ".api.client.RemoteStorage", "memory": ".in_memory.IndexerStorage", } def get_indexer_storage(cls: str, **kwargs) -> IndexerStorageInterface: """Instantiate an indexer storage implementation of class `cls` with arguments `kwargs`. Args: cls: indexer storage class (local, remote or memory) kwargs: dictionary of arguments passed to the indexer storage class constructor Returns: an instance of swh.indexer.storage Raises: ValueError if passed an unknown storage class. """ if "args" in kwargs: warnings.warn( 'Explicit "args" key is deprecated, use keys directly instead.', DeprecationWarning, ) kwargs = kwargs["args"] class_path = SERVER_IMPLEMENTATIONS.get(cls) if class_path is None: raise ValueError( f"Unknown indexer storage class `{cls}`. " f"Supported: {', '.join(SERVER_IMPLEMENTATIONS)}" ) (module_path, class_name) = class_path.rsplit(".", 1) module = import_module(module_path if module_path else ".", package=__package__) BackendClass = getattr(module, class_name) check_config = kwargs.pop("check_config", {}) idx_storage = BackendClass(**kwargs) if check_config: if not idx_storage.check_config(**check_config): raise EnvironmentError("Indexer storage check config failed") return idx_storage def check_id_duplicates(data): """ If any two row models in `data` have the same unique key, raises a `ValueError`. Values associated to the key must be hashable. Args: data (List[dict]): List of dictionaries to be inserted >>> check_id_duplicates([ ... ContentLanguageRow(id=b'foo', indexer_configuration_id=42, lang="python"), ... ContentLanguageRow(id=b'foo', indexer_configuration_id=32, lang="python"), ... ]) >>> check_id_duplicates([ ... ContentLanguageRow(id=b'foo', indexer_configuration_id=42, lang="python"), ... ContentLanguageRow(id=b'foo', indexer_configuration_id=42, lang="python"), ... ]) Traceback (most recent call last): ... swh.indexer.storage.exc.DuplicateId: [{'id': b'foo', 'indexer_configuration_id': 42}] """ # noqa counter = Counter(tuple(sorted(item.unique_key().items())) for item in data) duplicates = [id_ for (id_, count) in counter.items() if count >= 2] if duplicates: raise DuplicateId(list(map(dict, duplicates))) 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() @timed @db_transaction() def check_config(self, *, check_write, db=None, cur=None): # 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] @timed @db_transaction() def content_mimetype_missing( self, mimetypes: Iterable[Dict], db=None, cur=None ) -> List[Tuple[Sha1, int]]: return [obj[0] for obj in db.content_mimetype_missing_from_list(mimetypes, cur)] @timed @db_transaction() def get_partition( self, indexer_type: str, indexer_configuration_id: int, partition_id: int, nb_partitions: int, page_token: Optional[str] = None, limit: int = 1000, with_textual_data=False, db=None, cur=None, ) -> PagedResult[Sha1]: """Retrieve ids of content with `indexer_type` within within partition partition_id bound by limit. Args: **indexer_type**: Type of data content to index (mimetype, language, etc...) **indexer_configuration_id**: The tool used to index data **partition_id**: index of the partition to fetch **nb_partitions**: total number of partitions to split into **page_token**: opaque token used for pagination **limit**: Limit result (default to 1000) **with_textual_data** (bool): Deal with only textual content (True) or all content (all contents by defaults, False) Raises: IndexerStorageArgumentException for; - limit to None - wrong indexer_type provided Returns: PagedResult of Sha1. If next_page_token is None, there is no more data to fetch """ if limit is None: raise IndexerStorageArgumentException("limit should not be None") if indexer_type not in db.content_indexer_names: err = f"Wrong type. Should be one of [{','.join(db.content_indexer_names)}]" raise IndexerStorageArgumentException(err) start, end = get_partition_bounds_bytes(partition_id, nb_partitions, SHA1_SIZE) if page_token is not None: start = hash_to_bytes(page_token) if end is None: end = b"\xff" * SHA1_SIZE next_page_token: Optional[str] = None ids = [ row[0] for row in db.content_get_range( indexer_type, start, end, indexer_configuration_id, limit=limit + 1, with_textual_data=with_textual_data, cur=cur, ) ] if len(ids) >= limit: next_page_token = hash_to_hex(ids[-1]) ids = ids[:limit] assert len(ids) <= limit return PagedResult(results=ids, next_page_token=next_page_token) @timed @db_transaction() def content_mimetype_get_partition( self, indexer_configuration_id: int, partition_id: int, nb_partitions: int, page_token: Optional[str] = None, limit: int = 1000, db=None, cur=None, ) -> PagedResult[Sha1]: return self.get_partition( "mimetype", indexer_configuration_id, partition_id, nb_partitions, page_token=page_token, limit=limit, db=db, cur=cur, ) @timed @process_metrics @db_transaction() def content_mimetype_add( - self, - mimetypes: List[ContentMimetypeRow], - conflict_update: bool = False, - db=None, - cur=None, + self, mimetypes: List[ContentMimetypeRow], db=None, cur=None, ) -> Dict[str, int]: check_id_duplicates(mimetypes) mimetypes.sort(key=lambda m: m.id) db.mktemp_content_mimetype(cur) db.copy_to( [m.to_dict() for m in mimetypes], "tmp_content_mimetype", ["id", "mimetype", "encoding", "indexer_configuration_id"], cur, ) - count = db.content_mimetype_add_from_temp(conflict_update, cur) + count = db.content_mimetype_add_from_temp(cur) return {"content_mimetype:add": count} @timed @db_transaction() def content_mimetype_get( self, ids: Iterable[Sha1], db=None, cur=None ) -> List[ContentMimetypeRow]: return [ ContentMimetypeRow.from_dict( converters.db_to_mimetype(dict(zip(db.content_mimetype_cols, c))) ) for c in db.content_mimetype_get_from_list(ids, cur) ] @timed @db_transaction() def content_language_missing( self, languages: Iterable[Dict], db=None, cur=None ) -> List[Tuple[Sha1, int]]: return [obj[0] for obj in db.content_language_missing_from_list(languages, cur)] @timed @db_transaction() def content_language_get( self, ids: Iterable[Sha1], db=None, cur=None ) -> List[ContentLanguageRow]: return [ ContentLanguageRow.from_dict( converters.db_to_language(dict(zip(db.content_language_cols, c))) ) for c in db.content_language_get_from_list(ids, cur) ] @timed @process_metrics @db_transaction() def content_language_add( - self, - languages: List[ContentLanguageRow], - conflict_update: bool = False, - db=None, - cur=None, + self, languages: List[ContentLanguageRow], db=None, cur=None, ) -> Dict[str, int]: 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": lang.id, "lang": lang.lang or "unknown", "indexer_configuration_id": lang.indexer_configuration_id, } for lang in languages ), "tmp_content_language", ["id", "lang", "indexer_configuration_id"], cur, ) - count = db.content_language_add_from_temp(conflict_update, cur) + count = db.content_language_add_from_temp(cur) return {"content_language:add": count} @timed @db_transaction() def content_ctags_missing( self, ctags: Iterable[Dict], db=None, cur=None ) -> List[Tuple[Sha1, int]]: return [obj[0] for obj in db.content_ctags_missing_from_list(ctags, cur)] @timed @db_transaction() def content_ctags_get( self, ids: Iterable[Sha1], db=None, cur=None ) -> List[ContentCtagsRow]: return [ ContentCtagsRow.from_dict( converters.db_to_ctags(dict(zip(db.content_ctags_cols, c))) ) for c in db.content_ctags_get_from_list(ids, cur) ] @timed @process_metrics @db_transaction() def content_ctags_add( - self, - ctags: List[ContentCtagsRow], - conflict_update: bool = False, - db=None, - cur=None, + self, ctags: List[ContentCtagsRow], db=None, cur=None, ) -> Dict[str, int]: check_id_duplicates(ctags) ctags.sort(key=lambda m: m.id) db.mktemp_content_ctags(cur) db.copy_to( [ctag.to_dict() for ctag in ctags], tblname="tmp_content_ctags", columns=["id", "name", "kind", "line", "lang", "indexer_configuration_id"], cur=cur, ) - count = db.content_ctags_add_from_temp(conflict_update, cur) + count = db.content_ctags_add_from_temp(cur) return {"content_ctags:add": count} @timed @db_transaction() def content_ctags_search( self, expression: str, limit: int = 10, last_sha1: Optional[Sha1] = None, db=None, cur=None, ) -> List[ContentCtagsRow]: return [ ContentCtagsRow.from_dict( converters.db_to_ctags(dict(zip(db.content_ctags_cols, obj))) ) for obj in db.content_ctags_search(expression, last_sha1, limit, cur=cur) ] @timed @db_transaction() def content_fossology_license_get( self, ids: Iterable[Sha1], db=None, cur=None ) -> List[ContentLicenseRow]: return [ ContentLicenseRow.from_dict( converters.db_to_fossology_license( dict(zip(db.content_fossology_license_cols, c)) ) ) for c in db.content_fossology_license_get_from_list(ids, cur) ] @timed @process_metrics @db_transaction() def content_fossology_license_add( - self, - licenses: List[ContentLicenseRow], - conflict_update: bool = False, - db=None, - cur=None, + self, licenses: List[ContentLicenseRow], db=None, cur=None, ) -> Dict[str, int]: check_id_duplicates(licenses) licenses.sort(key=lambda m: m.id) db.mktemp_content_fossology_license(cur) db.copy_to( [license.to_dict() for license in licenses], tblname="tmp_content_fossology_license", columns=["id", "license", "indexer_configuration_id"], cur=cur, ) - count = db.content_fossology_license_add_from_temp(conflict_update, cur) + count = db.content_fossology_license_add_from_temp(cur) return {"content_fossology_license:add": count} @timed @db_transaction() def content_fossology_license_get_partition( self, indexer_configuration_id: int, partition_id: int, nb_partitions: int, page_token: Optional[str] = None, limit: int = 1000, db=None, cur=None, ) -> PagedResult[Sha1]: return self.get_partition( "fossology_license", indexer_configuration_id, partition_id, nb_partitions, page_token=page_token, limit=limit, with_textual_data=True, db=db, cur=cur, ) @timed @db_transaction() def content_metadata_missing( self, metadata: Iterable[Dict], db=None, cur=None ) -> List[Tuple[Sha1, int]]: return [obj[0] for obj in db.content_metadata_missing_from_list(metadata, cur)] @timed @db_transaction() def content_metadata_get( self, ids: Iterable[Sha1], db=None, cur=None ) -> List[ContentMetadataRow]: return [ ContentMetadataRow.from_dict( converters.db_to_metadata(dict(zip(db.content_metadata_cols, c))) ) for c in db.content_metadata_get_from_list(ids, cur) ] @timed @process_metrics @db_transaction() def content_metadata_add( - self, - metadata: List[ContentMetadataRow], - conflict_update: bool = False, - db=None, - cur=None, + self, metadata: List[ContentMetadataRow], db=None, cur=None, ) -> Dict[str, int]: check_id_duplicates(metadata) metadata.sort(key=lambda m: m.id) db.mktemp_content_metadata(cur) db.copy_to( [m.to_dict() for m in metadata], "tmp_content_metadata", ["id", "metadata", "indexer_configuration_id"], cur, ) - count = db.content_metadata_add_from_temp(conflict_update, cur) + count = db.content_metadata_add_from_temp(cur) return { "content_metadata:add": count, } @timed @db_transaction() def revision_intrinsic_metadata_missing( self, metadata: Iterable[Dict], db=None, cur=None ) -> List[Tuple[Sha1, int]]: return [ obj[0] for obj in db.revision_intrinsic_metadata_missing_from_list(metadata, cur) ] @timed @db_transaction() def revision_intrinsic_metadata_get( self, ids: Iterable[Sha1], db=None, cur=None ) -> List[RevisionIntrinsicMetadataRow]: return [ RevisionIntrinsicMetadataRow.from_dict( converters.db_to_metadata( dict(zip(db.revision_intrinsic_metadata_cols, c)) ) ) for c in db.revision_intrinsic_metadata_get_from_list(ids, cur) ] @timed @process_metrics @db_transaction() def revision_intrinsic_metadata_add( - self, - metadata: List[RevisionIntrinsicMetadataRow], - conflict_update: bool = False, - db=None, - cur=None, + self, metadata: List[RevisionIntrinsicMetadataRow], db=None, cur=None, ) -> Dict[str, int]: check_id_duplicates(metadata) metadata.sort(key=lambda m: m.id) db.mktemp_revision_intrinsic_metadata(cur) db.copy_to( [m.to_dict() for m in metadata], "tmp_revision_intrinsic_metadata", ["id", "metadata", "mappings", "indexer_configuration_id"], cur, ) - count = db.revision_intrinsic_metadata_add_from_temp(conflict_update, cur) + count = db.revision_intrinsic_metadata_add_from_temp(cur) return { "revision_intrinsic_metadata:add": count, } - @timed - @process_metrics - @db_transaction() - def revision_intrinsic_metadata_delete( - self, entries: List[Dict], db=None, cur=None - ) -> Dict: - count = db.revision_intrinsic_metadata_delete(entries, cur) - return {"revision_intrinsic_metadata:del": count} - @timed @db_transaction() def origin_intrinsic_metadata_get( self, urls: Iterable[str], db=None, cur=None ) -> List[OriginIntrinsicMetadataRow]: return [ OriginIntrinsicMetadataRow.from_dict( converters.db_to_metadata( dict(zip(db.origin_intrinsic_metadata_cols, c)) ) ) for c in db.origin_intrinsic_metadata_get_from_list(urls, cur) ] @timed @process_metrics @db_transaction() def origin_intrinsic_metadata_add( - self, - metadata: List[OriginIntrinsicMetadataRow], - conflict_update: bool = False, - db=None, - cur=None, + self, metadata: List[OriginIntrinsicMetadataRow], db=None, cur=None, ) -> Dict[str, int]: check_id_duplicates(metadata) metadata.sort(key=lambda m: m.id) db.mktemp_origin_intrinsic_metadata(cur) db.copy_to( [m.to_dict() for m in metadata], "tmp_origin_intrinsic_metadata", ["id", "metadata", "indexer_configuration_id", "from_revision", "mappings"], cur, ) - count = db.origin_intrinsic_metadata_add_from_temp(conflict_update, cur) + count = db.origin_intrinsic_metadata_add_from_temp(cur) return { "origin_intrinsic_metadata:add": count, } - @timed - @process_metrics - @db_transaction() - def origin_intrinsic_metadata_delete( - self, entries: List[Dict], db=None, cur=None - ) -> Dict: - count = db.origin_intrinsic_metadata_delete(entries, cur) - return { - "origin_intrinsic_metadata:del": count, - } - @timed @db_transaction() def origin_intrinsic_metadata_search_fulltext( self, conjunction: List[str], limit: int = 100, db=None, cur=None ) -> List[OriginIntrinsicMetadataRow]: return [ OriginIntrinsicMetadataRow.from_dict( converters.db_to_metadata( dict(zip(db.origin_intrinsic_metadata_cols, c)) ) ) for c in db.origin_intrinsic_metadata_search_fulltext( conjunction, limit=limit, cur=cur ) ] @timed @db_transaction() def origin_intrinsic_metadata_search_by_producer( self, page_token: str = "", limit: int = 100, ids_only: bool = False, mappings: Optional[List[str]] = None, tool_ids: Optional[List[int]] = None, db=None, cur=None, ) -> PagedResult[Union[str, OriginIntrinsicMetadataRow]]: assert isinstance(page_token, str) # we go to limit+1 to check whether we should add next_page_token in # the response rows = db.origin_intrinsic_metadata_search_by_producer( page_token, limit + 1, ids_only, mappings, tool_ids, cur ) next_page_token = None if ids_only: results = [origin for (origin,) in rows] if len(results) > limit: results[limit:] = [] next_page_token = results[-1] else: results = [ OriginIntrinsicMetadataRow.from_dict( converters.db_to_metadata( dict(zip(db.origin_intrinsic_metadata_cols, row)) ) ) for row in rows ] if len(results) > limit: results[limit:] = [] next_page_token = results[-1].id return PagedResult(results=results, next_page_token=next_page_token,) @timed @db_transaction() def origin_intrinsic_metadata_stats(self, db=None, cur=None): 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, } @timed @db_transaction() def indexer_configuration_add(self, tools, db=None, cur=None): 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) results = [dict(zip(db.indexer_configuration_cols, line)) for line in tools] send_metric( "indexer_configuration:add", len(results), method_name="indexer_configuration_add", ) return results @timed @db_transaction() def indexer_configuration_get(self, tool, db=None, cur=None): 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 c5ea770..b2cb63b 100644 --- a/swh/indexer/storage/db.py +++ b/swh/indexer/storage/db.py @@ -1,566 +1,538 @@ # 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 typing import Dict, Iterable, Iterator, List from swh.core.db import BaseDb from swh.core.db.db_utils import execute_values_generator, stored_procedure from swh.model import hashutil from .interface import Sha1 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: str, data: Iterable[Dict], hash_keys: List[str], cur=None ): """Read from table the data with hash_keys that are missing. Args: table: Table name (e.g content_mimetype, content_language, etc...) data: Dict of data to read from hash_keys: 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: Iterable[Dict], cur=None ) -> Iterator[Sha1]: """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): + def content_mimetype_add_from_temp(self, cur=None): cur = self._cursor(cur) - cur.execute("select * from swh_content_mimetype_add(%s)", (conflict_update,)) + cur.execute("select * from swh_content_mimetype_add()") return cur.fetchone()[0] 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 == "license": return ( """ ( select name from fossology_license where id = %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` parameter 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/%%' and %(start)s <= cm.id and cm.id <= %(end)s) """ else: extra = "" query = f"""select t.id from {table} t {extra} where t.indexer_configuration_id=%(tool_id)s and %(start)s <= t.id and t.id <= %(end)s order by t.indexer_configuration_id, t.id limit %(limit)s""" cur.execute( query, { "start": start, "end": end, "tool_id": indexer_configuration_id, "limit": 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): + def content_language_add_from_temp(self, cur=None): cur = self._cursor(cur) - cur.execute("select * from swh_content_language_add(%s)", (conflict_update,)) + cur.execute("select * from swh_content_language_add()") return cur.fetchone()[0] 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): + def content_ctags_add_from_temp(self, cur=None): cur = self._cursor(cur) - cur.execute("select * from swh_content_ctags_add(%s)", (conflict_update,)) + cur.execute("select * from swh_content_ctags_add()") return cur.fetchone()[0] 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", "license", ] @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): + def content_fossology_license_add_from_temp(self, cur=None): """Add new licenses per content. """ cur = self._cursor(cur) - cur.execute( - "select * from swh_content_fossology_license_add(%s)", (conflict_update,) - ) + cur.execute("select * from swh_content_fossology_license_add()") return cur.fetchone()[0] 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 """ % ", ".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): + def content_metadata_add_from_temp(self, cur=None): cur = self._cursor(cur) - cur.execute("select * from swh_content_metadata_add(%s)", (conflict_update,)) + cur.execute("select * from swh_content_metadata_add()") return cur.fetchone()[0] 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): + def revision_intrinsic_metadata_add_from_temp(self, cur=None): cur = self._cursor(cur) - cur.execute( - "select * from swh_revision_intrinsic_metadata_add(%s)", (conflict_update,) - ) + cur.execute("select * from swh_revision_intrinsic_metadata_add()") return cur.fetchone()[0] - 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) " - "RETURNING id" % (", ".join("%s" for _ in entries)), - tuple((e["id"], e["indexer_configuration_id"]) for e in entries), - ) - return len(cur.fetchall()) - 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", "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): + def origin_intrinsic_metadata_add_from_temp(self, cur=None): cur = self._cursor(cur) - cur.execute( - "select * from swh_origin_intrinsic_metadata_add(%s)", (conflict_update,) - ) + cur.execute("select * from swh_origin_intrinsic_metadata_add()") return cur.fetchone()[0] - 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) " - "RETURNING id" % (", ".join("%s" for _ in entries)), - tuple((e["id"], e["indexer_configuration_id"]) for e in entries), - ) - return len(cur.fetchall()) - def origin_intrinsic_metadata_get_from_list(self, ids, cur=None): yield from self._get_from_list( "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), tsquery_template=tsquery_template) cur.execute(query, tsquery_args + [limit]) yield from cur def origin_intrinsic_metadata_search_by_producer( self, last, 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 last: where.append("oim.id > %s") args.append(last) 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 5f8c517..792535d 100644 --- a/swh/indexer/storage/in_memory.py +++ b/swh/indexer/storage/in_memory.py @@ -1,520 +1,486 @@ # Copyright (C) 2018-2020 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 collections import Counter, defaultdict import itertools import json import math import operator import re from typing import ( Any, Dict, Generic, Iterable, List, Optional, Set, Tuple, Type, TypeVar, Union, ) from swh.core.collections import SortedList from swh.model.hashutil import hash_to_bytes, hash_to_hex from swh.model.model import SHA1_SIZE, Sha1Git from swh.storage.utils import get_partition_bounds_bytes from . import MAPPING_NAMES, check_id_duplicates from .exc import IndexerStorageArgumentException from .interface import PagedResult, Sha1 from .model import ( BaseRow, ContentCtagsRow, ContentLanguageRow, ContentLicenseRow, ContentMetadataRow, ContentMimetypeRow, OriginIntrinsicMetadataRow, RevisionIntrinsicMetadataRow, ) SHA1_DIGEST_SIZE = 160 def _transform_tool(tool): return { "id": tool["id"], "name": tool["tool_name"], "version": tool["tool_version"], "configuration": tool["tool_configuration"], } def check_id_types(data: List[Dict[str, Any]]): """Checks all elements of the list have an 'id' whose type is 'bytes'.""" if not all(isinstance(item.get("id"), bytes) for item in data): raise IndexerStorageArgumentException("identifiers must be bytes.") def _key_from_dict(d): return tuple(sorted(d.items())) ToolId = int TValue = TypeVar("TValue", bound=BaseRow) class SubStorage(Generic[TValue]): """Implements common missing/get/add logic for each indexer type.""" _data: Dict[Sha1, Dict[Tuple, Dict[str, Any]]] _tools_per_id: Dict[Sha1, Set[ToolId]] def __init__(self, row_class: Type[TValue], tools): self.row_class = row_class self._tools = tools self._sorted_ids = SortedList[bytes, Sha1]() self._data = defaultdict(dict) self._tools_per_id = defaultdict(set) def _key_from_dict(self, d) -> Tuple: """Like the global _key_from_dict, but filters out dict keys that don't belong in the unique key.""" return _key_from_dict({k: d[k] for k in self.row_class.UNIQUE_KEY_FIELDS}) def missing(self, keys: Iterable[Dict]) -> List[Sha1]: """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 """ results = [] for key in keys: tool_id = key["indexer_configuration_id"] id_ = key["id"] if tool_id not in self._tools_per_id.get(id_, set()): results.append(id_) return results def get(self, ids: Iterable[Sha1]) -> List[TValue]: """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`) """ results = [] for id_ in ids: for entry in self._data[id_].values(): entry = entry.copy() tool_id = entry.pop("indexer_configuration_id") results.append( self.row_class( id=id_, tool=_transform_tool(self._tools[tool_id]), **entry, ) ) return results def get_all(self) -> List[TValue]: return self.get(self._sorted_ids) def get_partition( self, indexer_configuration_id: int, partition_id: int, nb_partitions: int, page_token: Optional[str] = None, limit: int = 1000, ) -> PagedResult[Sha1]: """Retrieve ids of content with `indexer_type` within partition partition_id bound by limit. Args: **indexer_type**: Type of data content to index (mimetype, language, etc...) **indexer_configuration_id**: The tool used to index data **partition_id**: index of the partition to fetch **nb_partitions**: total number of partitions to split into **page_token**: opaque token used for pagination **limit**: Limit result (default to 1000) **with_textual_data** (bool): Deal with only textual content (True) or all content (all contents by defaults, False) Raises: IndexerStorageArgumentException for; - limit to None - wrong indexer_type provided Returns: PagedResult of Sha1. If next_page_token is None, there is no more data to fetch """ if limit is None: raise IndexerStorageArgumentException("limit should not be None") (start, end) = get_partition_bounds_bytes( partition_id, nb_partitions, SHA1_SIZE ) if page_token: start = hash_to_bytes(page_token) if end is None: end = b"\xff" * SHA1_SIZE next_page_token: Optional[str] = None ids: List[Sha1] = [] sha1s = (sha1 for sha1 in self._sorted_ids.iter_from(start)) for counter, sha1 in enumerate(sha1s): if sha1 > end: break if counter >= limit: next_page_token = hash_to_hex(sha1) break ids.append(sha1) assert len(ids) <= limit return PagedResult(results=ids, next_page_token=next_page_token) - def add(self, data: Iterable[TValue], conflict_update: bool) -> int: + def add(self, data: Iterable[TValue]) -> int: """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) check_id_duplicates(data) count = 0 for obj in data: item = obj.to_dict() id_ = item.pop("id") tool_id = item["indexer_configuration_id"] key = _key_from_dict(obj.unique_key()) - if not conflict_update and key in self._data[id_]: - # Duplicate, should not be updated - continue self._data[id_][key] = item self._tools_per_id[id_].add(tool_id) count += 1 if id_ not in self._sorted_ids: self._sorted_ids.add(id_) return count - def delete(self, entries: List[Dict]) -> int: - """Delete entries and return the number of entries deleted. - - """ - deleted = 0 - for entry in entries: - (id_, tool_id) = (entry["id"], entry["indexer_configuration_id"]) - if tool_id in self._tools_per_id[id_]: - self._tools_per_id[id_].remove(tool_id) - if id_ in self._data: - key = self._key_from_dict(entry) - if key in self._data[id_]: - deleted += 1 - del self._data[id_][key] - return deleted - class IndexerStorage: """In-memory SWH indexer storage.""" def __init__(self): self._tools = {} self._mimetypes = SubStorage(ContentMimetypeRow, self._tools) self._languages = SubStorage(ContentLanguageRow, self._tools) self._content_ctags = SubStorage(ContentCtagsRow, self._tools) self._licenses = SubStorage(ContentLicenseRow, self._tools) self._content_metadata = SubStorage(ContentMetadataRow, self._tools) self._revision_intrinsic_metadata = SubStorage( RevisionIntrinsicMetadataRow, self._tools ) self._origin_intrinsic_metadata = SubStorage( OriginIntrinsicMetadataRow, self._tools ) def check_config(self, *, check_write): return True def content_mimetype_missing( self, mimetypes: Iterable[Dict] ) -> List[Tuple[Sha1, int]]: return self._mimetypes.missing(mimetypes) def content_mimetype_get_partition( self, indexer_configuration_id: int, partition_id: int, nb_partitions: int, page_token: Optional[str] = None, limit: int = 1000, ) -> PagedResult[Sha1]: return self._mimetypes.get_partition( indexer_configuration_id, partition_id, nb_partitions, page_token, limit ) def content_mimetype_add( - self, mimetypes: List[ContentMimetypeRow], conflict_update: bool = False + self, mimetypes: List[ContentMimetypeRow] ) -> Dict[str, int]: - added = self._mimetypes.add(mimetypes, conflict_update) + added = self._mimetypes.add(mimetypes) return {"content_mimetype:add": added} def content_mimetype_get(self, ids: Iterable[Sha1]) -> List[ContentMimetypeRow]: return self._mimetypes.get(ids) def content_language_missing( self, languages: Iterable[Dict] ) -> List[Tuple[Sha1, int]]: return self._languages.missing(languages) def content_language_get(self, ids: Iterable[Sha1]) -> List[ContentLanguageRow]: return self._languages.get(ids) def content_language_add( - self, languages: List[ContentLanguageRow], conflict_update: bool = False + self, languages: List[ContentLanguageRow] ) -> Dict[str, int]: - added = self._languages.add(languages, conflict_update) + added = self._languages.add(languages) return {"content_language:add": added} def content_ctags_missing(self, ctags: Iterable[Dict]) -> List[Tuple[Sha1, int]]: return self._content_ctags.missing(ctags) def content_ctags_get(self, ids: Iterable[Sha1]) -> List[ContentCtagsRow]: return self._content_ctags.get(ids) - def content_ctags_add( - self, ctags: List[ContentCtagsRow], conflict_update: bool = False - ) -> Dict[str, int]: - added = self._content_ctags.add(ctags, conflict_update,) + def content_ctags_add(self, ctags: List[ContentCtagsRow]) -> Dict[str, int]: + added = self._content_ctags.add(ctags) return {"content_ctags:add": added} def content_ctags_search( self, expression: str, limit: int = 10, last_sha1: Optional[Sha1] = None ) -> List[ContentCtagsRow]: nb_matches = 0 items_per_id: Dict[Tuple[Sha1Git, ToolId], List[ContentCtagsRow]] = {} for item in sorted(self._content_ctags.get_all()): if item.id <= (last_sha1 or bytes(0 for _ in range(SHA1_DIGEST_SIZE))): continue items_per_id.setdefault( (item.id, item.indexer_configuration_id), [] ).append(item) results = [] for items in items_per_id.values(): for item in items: if item.name != expression: continue nb_matches += 1 if nb_matches > limit: break results.append(item) return results def content_fossology_license_get( self, ids: Iterable[Sha1] ) -> List[ContentLicenseRow]: return self._licenses.get(ids) def content_fossology_license_add( - self, licenses: List[ContentLicenseRow], conflict_update: bool = False + self, licenses: List[ContentLicenseRow] ) -> Dict[str, int]: - added = self._licenses.add(licenses, conflict_update) + added = self._licenses.add(licenses) return {"content_fossology_license:add": added} def content_fossology_license_get_partition( self, indexer_configuration_id: int, partition_id: int, nb_partitions: int, page_token: Optional[str] = None, limit: int = 1000, ) -> PagedResult[Sha1]: return self._licenses.get_partition( indexer_configuration_id, partition_id, nb_partitions, page_token, limit ) def content_metadata_missing( self, metadata: Iterable[Dict] ) -> List[Tuple[Sha1, int]]: return self._content_metadata.missing(metadata) def content_metadata_get(self, ids: Iterable[Sha1]) -> List[ContentMetadataRow]: return self._content_metadata.get(ids) def content_metadata_add( - self, metadata: List[ContentMetadataRow], conflict_update: bool = False + self, metadata: List[ContentMetadataRow] ) -> Dict[str, int]: - added = self._content_metadata.add(metadata, conflict_update) + added = self._content_metadata.add(metadata) return {"content_metadata:add": added} def revision_intrinsic_metadata_missing( self, metadata: Iterable[Dict] ) -> List[Tuple[Sha1, int]]: return self._revision_intrinsic_metadata.missing(metadata) def revision_intrinsic_metadata_get( self, ids: Iterable[Sha1] ) -> List[RevisionIntrinsicMetadataRow]: return self._revision_intrinsic_metadata.get(ids) def revision_intrinsic_metadata_add( - self, - metadata: List[RevisionIntrinsicMetadataRow], - conflict_update: bool = False, + self, metadata: List[RevisionIntrinsicMetadataRow] ) -> Dict[str, int]: - added = self._revision_intrinsic_metadata.add(metadata, conflict_update) + added = self._revision_intrinsic_metadata.add(metadata) return {"revision_intrinsic_metadata:add": added} - def revision_intrinsic_metadata_delete(self, entries: List[Dict]) -> Dict: - deleted = self._revision_intrinsic_metadata.delete(entries) - return {"revision_intrinsic_metadata:del": deleted} - def origin_intrinsic_metadata_get( self, urls: Iterable[str] ) -> List[OriginIntrinsicMetadataRow]: return self._origin_intrinsic_metadata.get(urls) def origin_intrinsic_metadata_add( - self, metadata: List[OriginIntrinsicMetadataRow], conflict_update: bool = False + self, metadata: List[OriginIntrinsicMetadataRow] ) -> Dict[str, int]: - added = self._origin_intrinsic_metadata.add(metadata, conflict_update) + added = self._origin_intrinsic_metadata.add(metadata) return {"origin_intrinsic_metadata:add": added} - def origin_intrinsic_metadata_delete(self, entries: List[Dict]) -> Dict: - deleted = self._origin_intrinsic_metadata.delete(entries) - return {"origin_intrinsic_metadata:del": deleted} - def origin_intrinsic_metadata_search_fulltext( self, conjunction: List[str], limit: int = 100 ) -> List[OriginIntrinsicMetadataRow]: # 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), reverse=True # Don't try to order 'data' ) return [result for (rank_, result) in results[:limit]] def origin_intrinsic_metadata_search_by_producer( self, page_token: str = "", limit: int = 100, ids_only: bool = False, mappings: Optional[List[str]] = None, tool_ids: Optional[List[int]] = None, ) -> PagedResult[Union[str, OriginIntrinsicMetadataRow]]: assert isinstance(page_token, str) nb_results = 0 if mappings is not None: mapping_set = frozenset(mappings) if tool_ids is not None: tool_id_set = frozenset(tool_ids) rows = [] # we go to limit+1 to check whether we should add next_page_token in # the response for entry in self._origin_intrinsic_metadata.get_all(): if entry.id <= page_token: continue if nb_results >= (limit + 1): break if mappings and mapping_set.isdisjoint(entry.mappings): continue if tool_ids and entry.tool["id"] not in tool_id_set: continue rows.append(entry) nb_results += 1 if len(rows) > limit: rows = rows[:limit] next_page_token = rows[-1].id else: next_page_token = None if ids_only: rows = [row.id for row in rows] return PagedResult(results=rows, next_page_token=next_page_token,) def origin_intrinsic_metadata_stats(self): 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): 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): 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/storage/interface.py b/swh/indexer/storage/interface.py index e4563c6..7a7dc2f 100644 --- a/swh/indexer/storage/interface.py +++ b/swh/indexer/storage/interface.py @@ -1,572 +1,519 @@ # Copyright (C) 2015-2020 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 typing import Dict, Iterable, List, Optional, Tuple, TypeVar, Union from typing_extensions import Protocol, runtime_checkable from swh.core.api import remote_api_endpoint from swh.core.api.classes import PagedResult as CorePagedResult from swh.indexer.storage.model import ( ContentCtagsRow, ContentLanguageRow, ContentLicenseRow, ContentMetadataRow, ContentMimetypeRow, OriginIntrinsicMetadataRow, RevisionIntrinsicMetadataRow, ) TResult = TypeVar("TResult") PagedResult = CorePagedResult[TResult, str] Sha1 = bytes @runtime_checkable class IndexerStorageInterface(Protocol): @remote_api_endpoint("check_config") def check_config(self, *, check_write): """Check that the storage is configured and ready to go.""" ... @remote_api_endpoint("content_mimetype/missing") def content_mimetype_missing( self, mimetypes: Iterable[Dict] ) -> List[Tuple[Sha1, int]]: """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 Returns: list of tuple (id, indexer_configuration_id) missing """ ... @remote_api_endpoint("content_mimetype/range") def content_mimetype_get_partition( self, indexer_configuration_id: int, partition_id: int, nb_partitions: int, page_token: Optional[str] = None, limit: int = 1000, ) -> PagedResult[Sha1]: """Retrieve mimetypes within partition partition_id bound by limit. Args: **indexer_configuration_id**: The tool used to index data **partition_id**: index of the partition to fetch **nb_partitions**: total number of partitions to split into **page_token**: opaque token used for pagination **limit**: Limit result (default to 1000) Raises: IndexerStorageArgumentException for; - limit to None - wrong indexer_type provided Returns: PagedResult of Sha1. If next_page_token is None, there is no more data to fetch """ ... @remote_api_endpoint("content_mimetype/add") def content_mimetype_add( - self, mimetypes: List[ContentMimetypeRow], conflict_update: bool = False + self, mimetypes: List[ContentMimetypeRow] ) -> Dict[str, int]: """Add mimetypes not present in storage. Args: mimetypes: mimetype rows to be added, with their `tool` attribute set to None. - conflict_update: Flag to determine if we want to overwrite (``True``) or skip duplicates (``False``, the default) Returns: Dict summary of number of rows added """ ... @remote_api_endpoint("content_mimetype") def content_mimetype_get(self, ids: Iterable[Sha1]) -> List[ContentMimetypeRow]: """Retrieve full content mimetype per ids. Args: ids: sha1 identifiers Returns: mimetype row objects """ ... @remote_api_endpoint("content_language/missing") def content_language_missing( self, languages: Iterable[Dict] ) -> List[Tuple[Sha1, int]]: """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 Returns: list of tuple (id, indexer_configuration_id) missing """ ... @remote_api_endpoint("content_language") def content_language_get(self, ids: Iterable[Sha1]) -> List[ContentLanguageRow]: """Retrieve full content language per ids. Args: ids (iterable): sha1 identifier Returns: language row objects """ ... @remote_api_endpoint("content_language/add") def content_language_add( - self, languages: List[ContentLanguageRow], conflict_update: bool = False + self, languages: List[ContentLanguageRow] ) -> Dict[str, int]: """Add languages not present in storage. Args: languages: language row objects - conflict_update (bool): Flag to determine if we want to - overwrite (true) or skip duplicates (false, the - default) - Returns: Dict summary of number of rows added """ ... @remote_api_endpoint("content/ctags/missing") def content_ctags_missing(self, ctags: Iterable[Dict]) -> List[Tuple[Sha1, int]]: """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 Returns: list of missing id for the tuple (id, indexer_configuration_id) """ ... @remote_api_endpoint("content/ctags") def content_ctags_get(self, ids: Iterable[Sha1]) -> List[ContentCtagsRow]: """Retrieve ctags per id. Args: ids (iterable): sha1 checksums Returns: list of language rows """ ... @remote_api_endpoint("content/ctags/add") - def content_ctags_add( - self, ctags: List[ContentCtagsRow], conflict_update: bool = False - ) -> Dict[str, int]: + def content_ctags_add(self, ctags: List[ContentCtagsRow]) -> Dict[str, int]: """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 Returns: Dict summary of number of rows added """ ... @remote_api_endpoint("content/ctags/search") def content_ctags_search( self, expression: str, limit: int = 10, last_sha1: Optional[Sha1] = None ) -> List[ContentCtagsRow]: """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 ''). Returns: rows of ctags including id, name, lang, kind, line, etc... """ ... @remote_api_endpoint("content/fossology_license") def content_fossology_license_get( self, ids: Iterable[Sha1] ) -> List[ContentLicenseRow]: """Retrieve licenses per id. Args: ids: sha1 identifiers Yields: license rows; possibly more than one per (sha1, tool_id) if there are multiple licenses. """ ... @remote_api_endpoint("content/fossology_license/add") def content_fossology_license_add( - self, licenses: List[ContentLicenseRow], conflict_update: bool = False + self, licenses: List[ContentLicenseRow] ) -> Dict[str, int]: """Add licenses not present in storage. Args: license: license rows to be added, with their `tool` attribute set to None. - conflict_update: Flag to determine if we want to overwrite (true) - or skip duplicates (false, the default) - Returns: Dict summary of number of rows added """ ... @remote_api_endpoint("content/fossology_license/range") def content_fossology_license_get_partition( self, indexer_configuration_id: int, partition_id: int, nb_partitions: int, page_token: Optional[str] = None, limit: int = 1000, ) -> PagedResult[Sha1]: """Retrieve licenses within the partition partition_id bound by limit. Args: **indexer_configuration_id**: The tool used to index data **partition_id**: index of the partition to fetch **nb_partitions**: total number of partitions to split into **page_token**: opaque token used for pagination **limit**: Limit result (default to 1000) Raises: IndexerStorageArgumentException for; - limit to None - wrong indexer_type provided Returns: PagedResult of Sha1. If next_page_token is None, there is no more data to fetch """ ... @remote_api_endpoint("content_metadata/missing") def content_metadata_missing( self, metadata: Iterable[Dict] ) -> List[Tuple[Sha1, int]]: """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 """ ... @remote_api_endpoint("content_metadata") def content_metadata_get(self, ids: Iterable[Sha1]) -> List[ContentMetadataRow]: """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 """ ... @remote_api_endpoint("content_metadata/add") def content_metadata_add( - self, metadata: List[ContentMetadataRow], conflict_update: bool = False + self, metadata: List[ContentMetadataRow] ) -> Dict[str, int]: """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) - Returns: Dict summary of number of rows added """ ... @remote_api_endpoint("revision_intrinsic_metadata/missing") def revision_intrinsic_metadata_missing( self, metadata: Iterable[Dict] ) -> List[Tuple[Sha1, int]]: """List metadata missing from storage. Args: metadata (iterable): dictionaries with keys: - **id** (bytes): sha1_git revision identifier - **indexer_configuration_id** (int): tool used to compute the results Returns: missing ids """ ... @remote_api_endpoint("revision_intrinsic_metadata") def revision_intrinsic_metadata_get( self, ids: Iterable[Sha1] ) -> List[RevisionIntrinsicMetadataRow]: """Retrieve revision metadata per id. Args: ids (iterable): sha1 checksums Returns: ContentMetadataRow objects """ ... @remote_api_endpoint("revision_intrinsic_metadata/add") def revision_intrinsic_metadata_add( - self, - metadata: List[RevisionIntrinsicMetadataRow], - conflict_update: bool = False, + self, metadata: List[RevisionIntrinsicMetadataRow], ) -> Dict[str, int]: """Add metadata not present in storage. Args: metadata: ContentMetadataRow objects - conflict_update: Flag to determine if we want to overwrite (true) - or skip duplicates (false, the default) - Returns: Dict summary of number of rows added """ ... - @remote_api_endpoint("revision_intrinsic_metadata/delete") - def revision_intrinsic_metadata_delete(self, entries: List[Dict]) -> Dict: - """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 - - Returns: - Summary of number of rows deleted - """ - ... - @remote_api_endpoint("origin_intrinsic_metadata") def origin_intrinsic_metadata_get( self, urls: Iterable[str] ) -> List[OriginIntrinsicMetadataRow]: """Retrieve origin metadata per id. Args: urls (iterable): origin URLs Returns: list of OriginIntrinsicMetadataRow """ ... @remote_api_endpoint("origin_intrinsic_metadata/add") def origin_intrinsic_metadata_add( - self, metadata: List[OriginIntrinsicMetadataRow], conflict_update: bool = False + self, metadata: List[OriginIntrinsicMetadataRow] ) -> Dict[str, int]: """Add origin metadata not present in storage. Args: metadata: list of OriginIntrinsicMetadataRow objects - conflict_update: Flag to determine if we want to overwrite (true) - or skip duplicates (false, the default) - Returns: Dict summary of number of rows added """ ... - @remote_api_endpoint("origin_intrinsic_metadata/delete") - def origin_intrinsic_metadata_delete(self, entries: List[Dict]) -> Dict: - """Remove origin metadata from the storage. - - Args: - entries (dict): dictionaries with the following keys: - - - **id** (str): origin urls - - **indexer_configuration_id** (int): tool used to compute - metadata - - Returns: - Summary of number of rows deleted - """ - ... - @remote_api_endpoint("origin_intrinsic_metadata/search/fulltext") def origin_intrinsic_metadata_search_fulltext( self, conjunction: List[str], limit: int = 100 ) -> List[OriginIntrinsicMetadataRow]: """Returns the list of origins whose metadata contain all the terms. Args: conjunction: List of terms to be searched for. limit: The maximum number of results to return Returns: list of OriginIntrinsicMetadataRow """ ... @remote_api_endpoint("origin_intrinsic_metadata/search/by_producer") def origin_intrinsic_metadata_search_by_producer( self, page_token: str = "", limit: int = 100, ids_only: bool = False, mappings: Optional[List[str]] = None, tool_ids: Optional[List[int]] = None, ) -> PagedResult[Union[str, OriginIntrinsicMetadataRow]]: """Returns the list of origins whose metadata contain all the terms. Args: page_token (str): Opaque token used for pagination. limit (int): The maximum number of results to return 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. Returns: OriginIntrinsicMetadataRow objects """ ... @remote_api_endpoint("origin_intrinsic_metadata/stats") def origin_intrinsic_metadata_stats(self): """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. """ ... @remote_api_endpoint("indexer_configuration/add") 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 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. """ ... @remote_api_endpoint("indexer_configuration/data") 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. """ ... diff --git a/swh/indexer/tests/storage/test_storage.py b/swh/indexer/tests/storage/test_storage.py index 36575fa..cd55a2b 100644 --- a/swh/indexer/tests/storage/test_storage.py +++ b/swh/indexer/tests/storage/test_storage.py @@ -1,1891 +1,1705 @@ # Copyright (C) 2015-2020 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 math import threading -from typing import Any, Dict, List, Tuple, Type, cast +from typing import Any, Dict, List, Tuple, Type import attr import pytest from swh.indexer.storage.exc import DuplicateId, IndexerStorageArgumentException from swh.indexer.storage.interface import IndexerStorageInterface, PagedResult from swh.indexer.storage.model import ( BaseRow, ContentCtagsRow, ContentLanguageRow, ContentLicenseRow, ContentMetadataRow, ContentMimetypeRow, OriginIntrinsicMetadataRow, RevisionIntrinsicMetadataRow, ) from swh.model.hashutil import hash_to_bytes def prepare_mimetypes_from_licenses( fossology_licenses: List[ContentLicenseRow], ) -> List[ContentMimetypeRow]: """Fossology license needs some consistent data in db to run. """ mimetypes = [] for c in fossology_licenses: mimetypes.append( ContentMimetypeRow( id=c.id, mimetype="text/plain", # for filtering on textual data to work encoding="utf-8", indexer_configuration_id=c.indexer_configuration_id, ) ) return mimetypes def endpoint_name(etype: str, ename: str) -> str: """Compute the storage's endpoint's name >>> endpoint_name('content_mimetype', 'add') 'content_mimetype_add' >>> endpoint_name('content_fosso_license', 'delete') 'content_fosso_license_delete' """ return f"{etype}_{ename}" def endpoint(storage, etype: str, ename: str): return getattr(storage, endpoint_name(etype, ename)) def expected_summary(count: int, etype: str, ename: str = "add") -> Dict[str, int]: """Compute the expected summary The key is determine according to etype and ename >>> expected_summary(10, 'content_mimetype', 'add') {'content_mimetype:add': 10} >>> expected_summary(9, 'origin_intrinsic_metadata', 'delete') {'origin_intrinsic_metadata:del': 9} """ pattern = ename[0:3] key = endpoint_name(etype, ename).replace(f"_{ename}", f":{pattern}") return {key: count} def test_check_config(swh_indexer_storage) -> None: assert swh_indexer_storage.check_config(check_write=True) assert swh_indexer_storage.check_config(check_write=False) class StorageETypeTester: """Base class for testing a series of common behaviour between a bunch of endpoint types supported by an IndexerStorage. This is supposed to be inherited with the following class attributes: - endpoint_type - tool_name - example_data See below for example usage. """ endpoint_type: str tool_name: str example_data: List[Dict] row_class: Type[BaseRow] def test_missing( self, swh_indexer_storage_with_data: Tuple[IndexerStorageInterface, Any] ) -> None: storage, data = swh_indexer_storage_with_data etype = self.endpoint_type tool_id = data.tools[self.tool_name]["id"] # given 2 (hopefully) unknown objects query = [ {"id": data.sha1_1, "indexer_configuration_id": tool_id,}, {"id": data.sha1_2, "indexer_configuration_id": tool_id,}, ] # we expect these are both returned by the xxx_missing endpoint actual_missing = endpoint(storage, etype, "missing")(query) assert list(actual_missing) == [ data.sha1_1, data.sha1_2, ] # now, when we add one of them summary = endpoint(storage, etype, "add")( [ self.row_class.from_dict( { "id": data.sha1_2, **self.example_data[0], "indexer_configuration_id": tool_id, } ) ] ) assert summary == expected_summary(1, etype) # we expect only the other one returned actual_missing = endpoint(storage, etype, "missing")(query) assert list(actual_missing) == [data.sha1_1] - def test_add__drop_duplicate( - self, swh_indexer_storage_with_data: Tuple[IndexerStorageInterface, Any] - ) -> None: - storage, data = swh_indexer_storage_with_data - etype = self.endpoint_type - tool_id = data.tools[self.tool_name]["id"] - - # add the first object - data_v1 = { - "id": data.sha1_2, - **self.example_data[0], - "indexer_configuration_id": tool_id, - } - summary = endpoint(storage, etype, "add")([self.row_class.from_dict(data_v1)]) - assert summary == expected_summary(1, etype) - - # should be able to retrieve it - actual_data = list(endpoint(storage, etype, "get")([data.sha1_2])) - expected_data_v1 = [ - self.row_class.from_dict( - { - "id": data.sha1_2, - **self.example_data[0], - "tool": data.tools[self.tool_name], - } - ) - ] - assert actual_data == expected_data_v1 - - # now if we add a modified version of the same object (same id) - data_v2 = data_v1.copy() - data_v2.update(self.example_data[1]) - summary2 = endpoint(storage, etype, "add")([self.row_class.from_dict(data_v2)]) - assert summary2 == expected_summary(0, etype) # not added - - # we expect to retrieve the original data, not the modified one - actual_data = list(endpoint(storage, etype, "get")([data.sha1_2])) - assert actual_data == expected_data_v1 - def test_add__update_in_place_duplicate( self, swh_indexer_storage_with_data: Tuple[IndexerStorageInterface, Any] ) -> None: storage, data = swh_indexer_storage_with_data etype = self.endpoint_type tool = data.tools[self.tool_name] data_v1 = { "id": data.sha1_2, **self.example_data[0], "indexer_configuration_id": tool["id"], } # given summary = endpoint(storage, etype, "add")([self.row_class.from_dict(data_v1)]) assert summary == expected_summary(1, etype) # not added # when actual_data = list(endpoint(storage, etype, "get")([data.sha1_2])) expected_data_v1 = [ self.row_class.from_dict( {"id": data.sha1_2, **self.example_data[0], "tool": tool} ) ] # then assert actual_data == expected_data_v1 # given data_v2 = data_v1.copy() data_v2.update(self.example_data[1]) - endpoint(storage, etype, "add")( - [self.row_class.from_dict(data_v2)], conflict_update=True - ) + endpoint(storage, etype, "add")([self.row_class.from_dict(data_v2)]) assert summary == expected_summary(1, etype) # modified so counted actual_data = list(endpoint(storage, etype, "get")([data.sha1_2])) expected_data_v2 = [ self.row_class.from_dict( {"id": data.sha1_2, **self.example_data[1], "tool": tool,} ) ] # data did change as the v2 was used to overwrite v1 assert actual_data == expected_data_v2 - def test_add__update_in_place_deadlock( + def test_add_deadlock( self, swh_indexer_storage_with_data: Tuple[IndexerStorageInterface, Any] ) -> None: storage, data = swh_indexer_storage_with_data etype = self.endpoint_type tool = data.tools[self.tool_name] hashes = [ hash_to_bytes("34973274ccef6ab4dfaaf86599792fa9c3fe4{:03d}".format(i)) for i in range(1000) ] data_v1 = [ self.row_class.from_dict( { "id": hash_, **self.example_data[0], "indexer_configuration_id": tool["id"], } ) for hash_ in hashes ] data_v2 = [ self.row_class.from_dict( { "id": hash_, **self.example_data[1], "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(storage, etype, "add")(data_v1) # when - actual_data = list(endpoint(storage, etype, "get")(hashes)) + actual_data = sorted( + endpoint(storage, etype, "get")(hashes), key=lambda x: x.id, + ) expected_data_v1 = [ self.row_class.from_dict( {"id": hash_, **self.example_data[0], "tool": tool} ) for hash_ in hashes ] # then assert actual_data == expected_data_v1 # given def f1() -> None: - endpoint(storage, etype, "add")(data_v2a, conflict_update=True) + endpoint(storage, etype, "add")(data_v2a) def f2() -> None: - endpoint(storage, etype, "add")(data_v2b, conflict_update=True) + endpoint(storage, etype, "add")(data_v2b) t1 = threading.Thread(target=f1) t2 = threading.Thread(target=f2) t2.start() t1.start() t1.join() t2.join() actual_data = sorted( - (row.to_dict() for row in endpoint(storage, etype, "get")(hashes)), - key=lambda x: x["id"], + endpoint(storage, etype, "get")(hashes), key=lambda x: x.id, ) expected_data_v2 = [ - {"id": hash_, **self.example_data[1], "tool": tool} for hash_ in hashes + self.row_class.from_dict( + {"id": hash_, **self.example_data[1], "tool": tool} + ) + for hash_ in hashes ] - assert actual_data == expected_data_v2 + assert len(actual_data) == len(expected_data_v1) == len(expected_data_v2) + for (item, expected_item_v1, expected_item_v2) in zip( + actual_data, expected_data_v1, expected_data_v2 + ): + assert item in (expected_item_v1, expected_item_v2) def test_add__duplicate_twice( self, swh_indexer_storage_with_data: Tuple[IndexerStorageInterface, Any] ) -> None: storage, data = swh_indexer_storage_with_data etype = self.endpoint_type tool = data.tools[self.tool_name] data_rev1 = self.row_class.from_dict( { "id": data.revision_id_2, **self.example_data[0], "indexer_configuration_id": tool["id"], } ) data_rev2 = self.row_class.from_dict( { "id": data.revision_id_2, **self.example_data[1], "indexer_configuration_id": tool["id"], } ) # when summary = endpoint(storage, etype, "add")([data_rev1]) assert summary == expected_summary(1, etype) with pytest.raises(DuplicateId): - endpoint(storage, etype, "add")( - [data_rev2, data_rev2], conflict_update=True - ) + endpoint(storage, etype, "add")([data_rev2, data_rev2]) # then actual_data = list( endpoint(storage, etype, "get")([data.revision_id_2, data.revision_id_1]) ) expected_data = [ self.row_class.from_dict( {"id": data.revision_id_2, **self.example_data[0], "tool": tool} ) ] assert actual_data == expected_data def test_get( self, swh_indexer_storage_with_data: Tuple[IndexerStorageInterface, Any] ) -> None: storage, data = swh_indexer_storage_with_data etype = self.endpoint_type tool = data.tools[self.tool_name] query = [data.sha1_2, data.sha1_1] data1 = self.row_class.from_dict( { "id": data.sha1_2, **self.example_data[0], "indexer_configuration_id": tool["id"], } ) # when summary = endpoint(storage, etype, "add")([data1]) assert summary == expected_summary(1, etype) # then actual_data = list(endpoint(storage, etype, "get")(query)) # then expected_data = [ self.row_class.from_dict( {"id": data.sha1_2, **self.example_data[0], "tool": tool} ) ] assert actual_data == expected_data class TestIndexerStorageContentMimetypes(StorageETypeTester): """Test Indexer Storage content_mimetype related methods """ endpoint_type = "content_mimetype" tool_name = "file" example_data = [ {"mimetype": "text/plain", "encoding": "utf-8",}, {"mimetype": "text/html", "encoding": "us-ascii",}, ] row_class = ContentMimetypeRow def test_generate_content_mimetype_get_partition_failure( self, swh_indexer_storage: IndexerStorageInterface ) -> None: """get_partition call with wrong limit input should fail""" storage = swh_indexer_storage indexer_configuration_id = 42 with pytest.raises( IndexerStorageArgumentException, match="limit should not be None" ): storage.content_mimetype_get_partition( indexer_configuration_id, 0, 3, limit=None # type: ignore ) def test_generate_content_mimetype_get_partition_no_limit( self, swh_indexer_storage_with_data: Tuple[IndexerStorageInterface, Any] ) -> None: """get_partition should return result""" storage, data = swh_indexer_storage_with_data mimetypes = data.mimetypes expected_ids = set([c.id for c in mimetypes]) indexer_configuration_id = mimetypes[0].indexer_configuration_id assert len(mimetypes) == 16 nb_partitions = 16 actual_ids = [] for partition_id in range(nb_partitions): actual_result = storage.content_mimetype_get_partition( indexer_configuration_id, partition_id, nb_partitions ) assert actual_result.next_page_token is None actual_ids.extend(actual_result.results) assert len(actual_ids) == len(expected_ids) for actual_id in actual_ids: assert actual_id in expected_ids def test_generate_content_mimetype_get_partition_full( self, swh_indexer_storage_with_data: Tuple[IndexerStorageInterface, Any] ) -> None: """get_partition for a single partition should return available ids """ storage, data = swh_indexer_storage_with_data mimetypes = data.mimetypes expected_ids = set([c.id for c in mimetypes]) indexer_configuration_id = mimetypes[0].indexer_configuration_id actual_result = storage.content_mimetype_get_partition( indexer_configuration_id, 0, 1 ) assert actual_result.next_page_token is None actual_ids = actual_result.results assert len(actual_ids) == len(expected_ids) for actual_id in actual_ids: assert actual_id in expected_ids def test_generate_content_mimetype_get_partition_empty( self, swh_indexer_storage_with_data: Tuple[IndexerStorageInterface, Any] ) -> None: """get_partition when at least one of the partitions is empty""" storage, data = swh_indexer_storage_with_data mimetypes = data.mimetypes expected_ids = set([c.id for c in mimetypes]) indexer_configuration_id = mimetypes[0].indexer_configuration_id # nb_partitions = smallest power of 2 such that at least one of # the partitions is empty nb_mimetypes = len(mimetypes) nb_partitions = 1 << math.floor(math.log2(nb_mimetypes) + 1) seen_ids = [] for partition_id in range(nb_partitions): actual_result = storage.content_mimetype_get_partition( indexer_configuration_id, partition_id, nb_partitions, limit=nb_mimetypes + 1, ) for actual_id in actual_result.results: seen_ids.append(actual_id) # Limit is higher than the max number of results assert actual_result.next_page_token is None assert set(seen_ids) == expected_ids def test_generate_content_mimetype_get_partition_with_pagination( self, swh_indexer_storage_with_data: Tuple[IndexerStorageInterface, Any] ) -> None: """get_partition should return ids provided with pagination """ storage, data = swh_indexer_storage_with_data mimetypes = data.mimetypes expected_ids = set([c.id for c in mimetypes]) indexer_configuration_id = mimetypes[0].indexer_configuration_id nb_partitions = 4 actual_ids = [] for partition_id in range(nb_partitions): next_page_token = None while True: actual_result = storage.content_mimetype_get_partition( indexer_configuration_id, partition_id, nb_partitions, limit=2, page_token=next_page_token, ) actual_ids.extend(actual_result.results) next_page_token = actual_result.next_page_token if next_page_token is None: break assert len(set(actual_ids)) == len(set(expected_ids)) for actual_id in actual_ids: assert actual_id in expected_ids class TestIndexerStorageContentLanguage(StorageETypeTester): """Test Indexer Storage content_language related methods """ endpoint_type = "content_language" tool_name = "pygments" example_data = [ {"lang": "haskell",}, {"lang": "common-lisp",}, ] row_class = ContentLanguageRow class TestIndexerStorageContentCTags(StorageETypeTester): """Test Indexer Storage content_ctags related methods """ endpoint_type = "content_ctags" tool_name = "universal-ctags" example_data = [ {"name": "done", "kind": "variable", "line": 119, "lang": "OCaml",}, {"name": "done", "kind": "variable", "line": 100, "lang": "Python",}, {"name": "main", "kind": "function", "line": 119, "lang": "Python",}, ] row_class = ContentCtagsRow # the following tests are disabled because CTAGS behaves differently - @pytest.mark.skip - def test_add__drop_duplicate(self): - pass - @pytest.mark.skip def test_add__update_in_place_duplicate(self): pass @pytest.mark.skip - def test_add__update_in_place_deadlock(self): - pass - - @pytest.mark.skip - def test_add__duplicate_twice(self): - pass - - @pytest.mark.skip - def test_get(self): + def test_add_deadlock(self): pass def test_content_ctags_search( self, swh_indexer_storage_with_data: Tuple[IndexerStorageInterface, Any] ) -> None: storage, data = swh_indexer_storage_with_data # 1. given tool = data.tools["universal-ctags"] tool_id = tool["id"] ctags1 = [ ContentCtagsRow( id=data.sha1_1, indexer_configuration_id=tool_id, **kwargs, # type: ignore ) for kwargs in [ {"name": "hello", "kind": "function", "line": 133, "lang": "Python",}, {"name": "counter", "kind": "variable", "line": 119, "lang": "Python",}, {"name": "hello", "kind": "variable", "line": 210, "lang": "Python",}, ] ] ctags1_with_tool = [ attr.evolve(ctag, indexer_configuration_id=None, tool=tool) for ctag in ctags1 ] ctags2 = [ ContentCtagsRow( id=data.sha1_2, indexer_configuration_id=tool_id, **kwargs, # type: ignore ) for kwargs in [ {"name": "hello", "kind": "variable", "line": 100, "lang": "C",}, {"name": "result", "kind": "variable", "line": 120, "lang": "C",}, ] ] ctags2_with_tool = [ attr.evolve(ctag, indexer_configuration_id=None, tool=tool) for ctag in ctags2 ] storage.content_ctags_add(ctags1 + ctags2) # 1. when actual_ctags = list(storage.content_ctags_search("hello", limit=1)) # 1. then assert actual_ctags == [ctags1_with_tool[0]] # 2. when actual_ctags = list( storage.content_ctags_search("hello", limit=1, last_sha1=data.sha1_1) ) # 2. then assert actual_ctags == [ctags2_with_tool[0]] # 3. when actual_ctags = list(storage.content_ctags_search("hello")) # 3. then assert actual_ctags == [ ctags1_with_tool[0], ctags1_with_tool[2], ctags2_with_tool[0], ] # 4. when actual_ctags = list(storage.content_ctags_search("counter")) # then assert actual_ctags == [ctags1_with_tool[1]] # 5. when actual_ctags = list(storage.content_ctags_search("result", limit=1)) # then assert actual_ctags == [ctags2_with_tool[1]] def test_content_ctags_search_no_result( self, swh_indexer_storage: IndexerStorageInterface ) -> None: storage = swh_indexer_storage actual_ctags = list(storage.content_ctags_search("counter")) assert not actual_ctags def test_content_ctags_add__add_new_ctags_added( self, swh_indexer_storage_with_data: Tuple[IndexerStorageInterface, Any] ) -> None: storage, data = swh_indexer_storage_with_data # given tool = data.tools["universal-ctags"] tool_id = tool["id"] ctag1 = ContentCtagsRow( id=data.sha1_2, indexer_configuration_id=tool_id, name="done", kind="variable", line=100, lang="Scheme", ) ctag1_with_tool = attr.evolve(ctag1, indexer_configuration_id=None, tool=tool) # given storage.content_ctags_add([ctag1]) storage.content_ctags_add([ctag1]) # conflict does nothing # when actual_ctags = list(storage.content_ctags_get([data.sha1_2])) # then assert actual_ctags == [ctag1_with_tool] # given ctag2 = ContentCtagsRow( id=data.sha1_2, indexer_configuration_id=tool_id, name="defn", kind="function", line=120, lang="Scheme", ) ctag2_with_tool = attr.evolve(ctag2, indexer_configuration_id=None, tool=tool) storage.content_ctags_add([ctag2]) actual_ctags = list(storage.content_ctags_get([data.sha1_2])) assert actual_ctags == [ctag1_with_tool, ctag2_with_tool] def test_content_ctags_add__update_in_place( self, swh_indexer_storage_with_data: Tuple[IndexerStorageInterface, Any] ) -> None: storage, data = swh_indexer_storage_with_data # given tool = data.tools["universal-ctags"] tool_id = tool["id"] ctag1 = ContentCtagsRow( id=data.sha1_2, indexer_configuration_id=tool_id, name="done", kind="variable", line=100, lang="Scheme", ) ctag1_with_tool = attr.evolve(ctag1, indexer_configuration_id=None, tool=tool) # given storage.content_ctags_add([ctag1]) # when actual_ctags = list(storage.content_ctags_get([data.sha1_2])) # then assert actual_ctags == [ctag1_with_tool] # given ctag2 = ContentCtagsRow( id=data.sha1_2, indexer_configuration_id=tool_id, name="defn", kind="function", line=120, lang="Scheme", ) ctag2_with_tool = attr.evolve(ctag2, indexer_configuration_id=None, tool=tool) - storage.content_ctags_add([ctag1, ctag2], conflict_update=True) + storage.content_ctags_add([ctag1, ctag2]) actual_ctags = list(storage.content_ctags_get([data.sha1_2])) assert actual_ctags == [ctag1_with_tool, ctag2_with_tool] def test_add_empty( self, swh_indexer_storage_with_data: Tuple[IndexerStorageInterface, Any] ) -> None: (storage, data) = swh_indexer_storage_with_data etype = self.endpoint_type summary = endpoint(storage, etype, "add")([]) assert summary == {"content_ctags:add": 0} actual_ctags = list(endpoint(storage, etype, "get")([data.sha1_2])) assert actual_ctags == [] def test_get_unknown( self, swh_indexer_storage_with_data: Tuple[IndexerStorageInterface, Any] ) -> None: (storage, data) = swh_indexer_storage_with_data etype = self.endpoint_type actual_ctags = list(endpoint(storage, etype, "get")([data.sha1_2])) assert actual_ctags == [] class TestIndexerStorageContentMetadata(StorageETypeTester): """Test Indexer Storage content_metadata related methods """ tool_name = "swh-metadata-detector" endpoint_type = "content_metadata" example_data = [ { "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", }, }, {"metadata": {"other": {}, "name": "test_metadata", "version": "0.0.1"},}, ] row_class = ContentMetadataRow class TestIndexerStorageRevisionIntrinsicMetadata(StorageETypeTester): """Test Indexer Storage revision_intrinsic_metadata related methods """ tool_name = "swh-metadata-detector" endpoint_type = "revision_intrinsic_metadata" example_data = [ { "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"], }, { "metadata": {"other": {}, "name": "test_metadata", "version": "0.0.1"}, "mappings": ["mapping2"], }, ] row_class = RevisionIntrinsicMetadataRow - def test_revision_intrinsic_metadata_delete( - self, swh_indexer_storage_with_data: Tuple[IndexerStorageInterface, Any] - ) -> None: - storage, data = swh_indexer_storage_with_data - etype = self.endpoint_type - tool = data.tools[self.tool_name] - - query = [data.sha1_2, data.sha1_1] - data1 = RevisionIntrinsicMetadataRow( - id=data.sha1_2, - indexer_configuration_id=tool["id"], - **self.example_data[0], # type: ignore - ) - - # when - summary = endpoint(storage, etype, "add")([data1]) - assert summary == expected_summary(1, etype) - - summary2 = endpoint(storage, etype, "delete")( - [{"id": data.sha1_2, "indexer_configuration_id": tool["id"],}] - ) - assert summary2 == expected_summary(1, etype, "del") - - # then - actual_data = list(endpoint(storage, etype, "get")(query)) - - # then - assert not actual_data - - def test_revision_intrinsic_metadata_delete_nonexisting( - self, swh_indexer_storage_with_data: Tuple[IndexerStorageInterface, Any] - ) -> None: - storage, data = swh_indexer_storage_with_data - etype = self.endpoint_type - tool = data.tools[self.tool_name] - endpoint(storage, etype, "delete")( - [{"id": data.sha1_2, "indexer_configuration_id": tool["id"],}] - ) - -class TestIndexerStorageContentFossologyLicense: +class TestIndexerStorageContentFossologyLicense(StorageETypeTester): endpoint_type = "content_fossology_license" tool_name = "nomos" + example_data = [ + {"license": "Apache-2.0"}, + {"license": "BSD-2-Clause"}, + ] row_class = ContentLicenseRow + # the following tests are disabled because licenses behaves differently + @pytest.mark.skip + def test_add__update_in_place_duplicate(self): + pass + + @pytest.mark.skip + def test_add_deadlock(self): + pass + + # content_fossology_license_missing does not exist + @pytest.mark.skip + def test_missing(self): + pass + def test_content_fossology_license_add__new_license_added( self, swh_indexer_storage_with_data: Tuple[IndexerStorageInterface, Any] ) -> None: storage, data = swh_indexer_storage_with_data # given tool = data.tools["nomos"] tool_id = tool["id"] license1 = ContentLicenseRow( id=data.sha1_1, license="Apache-2.0", indexer_configuration_id=tool_id, ) # given storage.content_fossology_license_add([license1]) # conflict does nothing storage.content_fossology_license_add([license1]) # when actual_licenses = list(storage.content_fossology_license_get([data.sha1_1])) # then expected_licenses = [ ContentLicenseRow(id=data.sha1_1, license="Apache-2.0", tool=tool,) ] assert actual_licenses == expected_licenses # given license2 = ContentLicenseRow( id=data.sha1_1, license="BSD-2-Clause", indexer_configuration_id=tool_id, ) storage.content_fossology_license_add([license2]) actual_licenses = list(storage.content_fossology_license_get([data.sha1_1])) expected_licenses.append( ContentLicenseRow(id=data.sha1_1, license="BSD-2-Clause", tool=tool,) ) # first license was not removed when the second one was added assert sorted(actual_licenses) == sorted(expected_licenses) def test_generate_content_fossology_license_get_partition_failure( self, swh_indexer_storage_with_data: Tuple[IndexerStorageInterface, Any] ) -> None: """get_partition call with wrong limit input should fail""" storage, data = swh_indexer_storage_with_data indexer_configuration_id = 42 with pytest.raises( IndexerStorageArgumentException, match="limit should not be None" ): storage.content_fossology_license_get_partition( indexer_configuration_id, 0, 3, limit=None, # type: ignore ) def test_generate_content_fossology_license_get_partition_no_limit( self, swh_indexer_storage_with_data: Tuple[IndexerStorageInterface, Any] ) -> None: """get_partition should return results""" storage, data = swh_indexer_storage_with_data # craft some consistent mimetypes fossology_licenses = data.fossology_licenses mimetypes = prepare_mimetypes_from_licenses(fossology_licenses) indexer_configuration_id = fossology_licenses[0].indexer_configuration_id - storage.content_mimetype_add(mimetypes, conflict_update=True) + storage.content_mimetype_add(mimetypes) # add fossology_licenses to storage storage.content_fossology_license_add(fossology_licenses) # All ids from the db expected_ids = set([c.id for c in fossology_licenses]) assert len(fossology_licenses) == 10 assert len(mimetypes) == 10 nb_partitions = 4 actual_ids = [] for partition_id in range(nb_partitions): actual_result = storage.content_fossology_license_get_partition( indexer_configuration_id, partition_id, nb_partitions ) assert actual_result.next_page_token is None actual_ids.extend(actual_result.results) assert len(set(actual_ids)) == len(expected_ids) for actual_id in actual_ids: assert actual_id in expected_ids def test_generate_content_fossology_license_get_partition_full( self, swh_indexer_storage_with_data: Tuple[IndexerStorageInterface, Any] ) -> None: """get_partition for a single partition should return available ids """ storage, data = swh_indexer_storage_with_data # craft some consistent mimetypes fossology_licenses = data.fossology_licenses mimetypes = prepare_mimetypes_from_licenses(fossology_licenses) indexer_configuration_id = fossology_licenses[0].indexer_configuration_id - storage.content_mimetype_add(mimetypes, conflict_update=True) + storage.content_mimetype_add(mimetypes) # add fossology_licenses to storage storage.content_fossology_license_add(fossology_licenses) # All ids from the db expected_ids = set([c.id for c in fossology_licenses]) actual_result = storage.content_fossology_license_get_partition( indexer_configuration_id, 0, 1 ) assert actual_result.next_page_token is None actual_ids = actual_result.results assert len(set(actual_ids)) == len(expected_ids) for actual_id in actual_ids: assert actual_id in expected_ids def test_generate_content_fossology_license_get_partition_empty( self, swh_indexer_storage_with_data: Tuple[IndexerStorageInterface, Any] ) -> None: """get_partition when at least one of the partitions is empty""" storage, data = swh_indexer_storage_with_data # craft some consistent mimetypes fossology_licenses = data.fossology_licenses mimetypes = prepare_mimetypes_from_licenses(fossology_licenses) indexer_configuration_id = fossology_licenses[0].indexer_configuration_id - storage.content_mimetype_add(mimetypes, conflict_update=True) + storage.content_mimetype_add(mimetypes) # add fossology_licenses to storage storage.content_fossology_license_add(fossology_licenses) # All ids from the db expected_ids = set([c.id for c in fossology_licenses]) # nb_partitions = smallest power of 2 such that at least one of # the partitions is empty nb_licenses = len(fossology_licenses) nb_partitions = 1 << math.floor(math.log2(nb_licenses) + 1) seen_ids = [] for partition_id in range(nb_partitions): actual_result = storage.content_fossology_license_get_partition( indexer_configuration_id, partition_id, nb_partitions, limit=nb_licenses + 1, ) for actual_id in actual_result.results: seen_ids.append(actual_id) # Limit is higher than the max number of results assert actual_result.next_page_token is None assert set(seen_ids) == expected_ids def test_generate_content_fossology_license_get_partition_with_pagination( self, swh_indexer_storage_with_data: Tuple[IndexerStorageInterface, Any] ) -> None: """get_partition should return ids provided with paginationv """ storage, data = swh_indexer_storage_with_data # craft some consistent mimetypes fossology_licenses = data.fossology_licenses mimetypes = prepare_mimetypes_from_licenses(fossology_licenses) indexer_configuration_id = fossology_licenses[0].indexer_configuration_id - storage.content_mimetype_add(mimetypes, conflict_update=True) + storage.content_mimetype_add(mimetypes) # add fossology_licenses to storage storage.content_fossology_license_add(fossology_licenses) # All ids from the db expected_ids = [c.id for c in fossology_licenses] nb_partitions = 4 actual_ids = [] for partition_id in range(nb_partitions): next_page_token = None while True: actual_result = storage.content_fossology_license_get_partition( indexer_configuration_id, partition_id, nb_partitions, limit=2, page_token=next_page_token, ) actual_ids.extend(actual_result.results) next_page_token = actual_result.next_page_token if next_page_token is None: break assert len(set(actual_ids)) == len(set(expected_ids)) for actual_id in actual_ids: assert actual_id in expected_ids def test_add_empty( self, swh_indexer_storage_with_data: Tuple[IndexerStorageInterface, Any] ) -> None: (storage, data) = swh_indexer_storage_with_data etype = self.endpoint_type summary = endpoint(storage, etype, "add")([]) assert summary == {"content_fossology_license:add": 0} actual_license = list(endpoint(storage, etype, "get")([data.sha1_2])) assert actual_license == [] def test_get_unknown( self, swh_indexer_storage_with_data: Tuple[IndexerStorageInterface, Any] ) -> None: (storage, data) = swh_indexer_storage_with_data etype = self.endpoint_type actual_license = list(endpoint(storage, etype, "get")([data.sha1_2])) assert actual_license == [] class TestIndexerStorageOriginIntrinsicMetadata: def test_origin_intrinsic_metadata_get( self, swh_indexer_storage_with_data: Tuple[IndexerStorageInterface, Any] ) -> None: storage, data = swh_indexer_storage_with_data # given tool_id = data.tools["swh-metadata-detector"]["id"] metadata = { "version": None, "name": None, } metadata_rev = RevisionIntrinsicMetadataRow( id=data.revision_id_2, metadata=metadata, mappings=["mapping1"], indexer_configuration_id=tool_id, ) metadata_origin = OriginIntrinsicMetadataRow( id=data.origin_url_1, metadata=metadata, indexer_configuration_id=tool_id, mappings=["mapping1"], from_revision=data.revision_id_2, ) # when storage.revision_intrinsic_metadata_add([metadata_rev]) storage.origin_intrinsic_metadata_add([metadata_origin]) # then actual_metadata = list( storage.origin_intrinsic_metadata_get([data.origin_url_1, "no://where"]) ) expected_metadata = [ OriginIntrinsicMetadataRow( id=data.origin_url_1, metadata=metadata, tool=data.tools["swh-metadata-detector"], from_revision=data.revision_id_2, mappings=["mapping1"], ) ] assert actual_metadata == expected_metadata - def test_origin_intrinsic_metadata_delete( - self, swh_indexer_storage_with_data: Tuple[IndexerStorageInterface, Any] - ) -> None: - storage, data = swh_indexer_storage_with_data - # given - tool_id = data.tools["swh-metadata-detector"]["id"] - - metadata = { - "version": None, - "name": None, - } - metadata_rev = RevisionIntrinsicMetadataRow( - id=data.revision_id_2, - indexer_configuration_id=tool_id, - metadata=metadata, - mappings=["mapping1"], - ) - metadata_origin = OriginIntrinsicMetadataRow( - id=data.origin_url_1, - metadata=metadata, - indexer_configuration_id=tool_id, - mappings=["mapping1"], - from_revision=data.revision_id_2, - ) - metadata_origin2 = attr.evolve(metadata_origin, id=data.origin_url_2) - - # when - storage.revision_intrinsic_metadata_add([metadata_rev]) - storage.origin_intrinsic_metadata_add([metadata_origin, metadata_origin2]) - - storage.origin_intrinsic_metadata_delete( - [{"id": data.origin_url_1, "indexer_configuration_id": tool_id}] - ) - - # then - actual_metadata = list( - storage.origin_intrinsic_metadata_get( - [data.origin_url_1, data.origin_url_2, "no://where"] - ) - ) - assert [ - attr.evolve(m, indexer_configuration_id=cast(Dict, m.tool)["id"], tool=None) - for m in actual_metadata - ] == [metadata_origin2] - - def test_origin_intrinsic_metadata_delete_nonexisting( - self, swh_indexer_storage_with_data: Tuple[IndexerStorageInterface, Any] - ) -> None: - storage, data = swh_indexer_storage_with_data - tool_id = data.tools["swh-metadata-detector"]["id"] - storage.origin_intrinsic_metadata_delete( - [{"id": data.origin_url_1, "indexer_configuration_id": tool_id}] - ) - - def test_origin_intrinsic_metadata_add_drop_duplicate( - self, swh_indexer_storage_with_data: Tuple[IndexerStorageInterface, Any] - ) -> None: - storage, data = swh_indexer_storage_with_data - # given - tool_id = data.tools["swh-metadata-detector"]["id"] - - metadata_v1: Dict[str, Any] = { - "version": None, - "name": None, - } - metadata_rev_v1 = RevisionIntrinsicMetadataRow( - id=data.revision_id_1, - metadata=metadata_v1.copy(), - mappings=[], - indexer_configuration_id=tool_id, - ) - metadata_origin_v1 = OriginIntrinsicMetadataRow( - id=data.origin_url_1, - metadata=metadata_v1.copy(), - indexer_configuration_id=tool_id, - mappings=[], - from_revision=data.revision_id_1, - ) - - # given - storage.revision_intrinsic_metadata_add([metadata_rev_v1]) - storage.origin_intrinsic_metadata_add([metadata_origin_v1]) - - # when - actual_metadata = list( - storage.origin_intrinsic_metadata_get([data.origin_url_1, "no://where"]) - ) - - expected_metadata_v1 = [ - OriginIntrinsicMetadataRow( - id=data.origin_url_1, - metadata=metadata_v1, - tool=data.tools["swh-metadata-detector"], - from_revision=data.revision_id_1, - mappings=[], - ) - ] - - assert actual_metadata == expected_metadata_v1 - - # given - metadata_v2 = metadata_v1.copy() - metadata_v2.update( - {"name": "test_metadata", "author": "MG",} - ) - metadata_rev_v2 = attr.evolve(metadata_rev_v1, metadata=metadata_v2) - metadata_origin_v2 = attr.evolve(metadata_origin_v1, metadata=metadata_v2) - - storage.revision_intrinsic_metadata_add([metadata_rev_v2]) - storage.origin_intrinsic_metadata_add([metadata_origin_v2]) - - # then - actual_metadata = list( - storage.origin_intrinsic_metadata_get([data.origin_url_1]) - ) - - # metadata did not change as the v2 was dropped. - assert actual_metadata == expected_metadata_v1 - def test_origin_intrinsic_metadata_add_update_in_place_duplicate( self, swh_indexer_storage_with_data: Tuple[IndexerStorageInterface, Any] ) -> None: storage, data = swh_indexer_storage_with_data # given tool_id = data.tools["swh-metadata-detector"]["id"] metadata_v1: Dict[str, Any] = { "version": None, "name": None, } metadata_rev_v1 = RevisionIntrinsicMetadataRow( id=data.revision_id_2, metadata=metadata_v1, mappings=[], indexer_configuration_id=tool_id, ) metadata_origin_v1 = OriginIntrinsicMetadataRow( id=data.origin_url_1, metadata=metadata_v1.copy(), indexer_configuration_id=tool_id, mappings=[], from_revision=data.revision_id_2, ) # given storage.revision_intrinsic_metadata_add([metadata_rev_v1]) storage.origin_intrinsic_metadata_add([metadata_origin_v1]) # when actual_metadata = list( storage.origin_intrinsic_metadata_get([data.origin_url_1]) ) # then expected_metadata_v1 = [ OriginIntrinsicMetadataRow( id=data.origin_url_1, metadata=metadata_v1, tool=data.tools["swh-metadata-detector"], from_revision=data.revision_id_2, mappings=[], ) ] assert actual_metadata == expected_metadata_v1 # given metadata_v2 = metadata_v1.copy() metadata_v2.update( {"name": "test_update_duplicated_metadata", "author": "MG",} ) metadata_rev_v2 = attr.evolve(metadata_rev_v1, metadata=metadata_v2) metadata_origin_v2 = OriginIntrinsicMetadataRow( id=data.origin_url_1, metadata=metadata_v2.copy(), indexer_configuration_id=tool_id, mappings=["npm"], from_revision=data.revision_id_1, ) - storage.revision_intrinsic_metadata_add([metadata_rev_v2], conflict_update=True) - storage.origin_intrinsic_metadata_add( - [metadata_origin_v2], conflict_update=True - ) + storage.revision_intrinsic_metadata_add([metadata_rev_v2]) + storage.origin_intrinsic_metadata_add([metadata_origin_v2]) actual_metadata = list( storage.origin_intrinsic_metadata_get([data.origin_url_1]) ) expected_metadata_v2 = [ OriginIntrinsicMetadataRow( id=data.origin_url_1, metadata=metadata_v2, tool=data.tools["swh-metadata-detector"], from_revision=data.revision_id_1, mappings=["npm"], ) ] # metadata did change as the v2 was used to overwrite v1 assert actual_metadata == expected_metadata_v2 - def test_origin_intrinsic_metadata_add__update_in_place_deadlock( + def test_origin_intrinsic_metadata_add__deadlock( self, swh_indexer_storage_with_data: Tuple[IndexerStorageInterface, Any] ) -> None: storage, data = swh_indexer_storage_with_data # given tool_id = data.tools["swh-metadata-detector"]["id"] - ids = list(range(10)) + origins = ["file:///tmp/origin{:02d}".format(i) for i in range(100)] example_data1: Dict[str, Any] = { "metadata": {"version": None, "name": None,}, "mappings": [], } example_data2: Dict[str, Any] = { "metadata": {"version": "v1.1.1", "name": "foo",}, "mappings": [], } metadata_rev_v1 = RevisionIntrinsicMetadataRow( id=data.revision_id_2, metadata={"version": None, "name": None,}, mappings=[], indexer_configuration_id=tool_id, ) data_v1 = [ OriginIntrinsicMetadataRow( - id="file:///tmp/origin%d" % id_, + id=origin, from_revision=data.revision_id_2, indexer_configuration_id=tool_id, **example_data1, ) - for id_ in ids + for origin in origins ] data_v2 = [ OriginIntrinsicMetadataRow( - id="file:///tmp/origin%d" % id_, + id=origin, from_revision=data.revision_id_2, indexer_configuration_id=tool_id, **example_data2, ) - for id_ in ids + for origin in origins ] # 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 storage.revision_intrinsic_metadata_add([metadata_rev_v1]) storage.origin_intrinsic_metadata_add(data_v1) # when - origins = ["file:///tmp/origin%d" % i for i in ids] actual_data = list(storage.origin_intrinsic_metadata_get(origins)) expected_data_v1 = [ OriginIntrinsicMetadataRow( - id="file:///tmp/origin%d" % id_, + id=origin, from_revision=data.revision_id_2, tool=data.tools["swh-metadata-detector"], **example_data1, ) - for id_ in ids + for origin in origins ] # then assert actual_data == expected_data_v1 # given def f1() -> None: - storage.origin_intrinsic_metadata_add(data_v2a, conflict_update=True) + storage.origin_intrinsic_metadata_add(data_v2a) def f2() -> None: - storage.origin_intrinsic_metadata_add(data_v2b, conflict_update=True) + storage.origin_intrinsic_metadata_add(data_v2b) t1 = threading.Thread(target=f1) t2 = threading.Thread(target=f2) t2.start() t1.start() t1.join() t2.join() actual_data = list(storage.origin_intrinsic_metadata_get(origins)) expected_data_v2 = [ OriginIntrinsicMetadataRow( - id="file:///tmp/origin%d" % id_, + id=origin, from_revision=data.revision_id_2, tool=data.tools["swh-metadata-detector"], **example_data2, ) - for id_ in ids + for origin in origins ] - assert len(actual_data) == len(expected_data_v2) - assert sorted(actual_data, key=lambda x: x.id) == expected_data_v2 + actual_data.sort(key=lambda item: item.id) + assert len(actual_data) == len(expected_data_v1) == len(expected_data_v2) + for (item, expected_item_v1, expected_item_v2) in zip( + actual_data, expected_data_v1, expected_data_v2 + ): + assert item in (expected_item_v1, expected_item_v2) def test_origin_intrinsic_metadata_add__duplicate_twice( self, swh_indexer_storage_with_data: Tuple[IndexerStorageInterface, Any] ) -> None: storage, data = swh_indexer_storage_with_data # given tool_id = data.tools["swh-metadata-detector"]["id"] metadata = { "developmentStatus": None, "name": None, } metadata_rev = RevisionIntrinsicMetadataRow( id=data.revision_id_2, metadata=metadata, mappings=["mapping1"], indexer_configuration_id=tool_id, ) metadata_origin = OriginIntrinsicMetadataRow( id=data.origin_url_1, metadata=metadata, indexer_configuration_id=tool_id, mappings=["mapping1"], from_revision=data.revision_id_2, ) # when storage.revision_intrinsic_metadata_add([metadata_rev]) with pytest.raises(DuplicateId): storage.origin_intrinsic_metadata_add([metadata_origin, metadata_origin]) def test_origin_intrinsic_metadata_search_fulltext( self, swh_indexer_storage_with_data: Tuple[IndexerStorageInterface, Any] ) -> None: storage, data = swh_indexer_storage_with_data # given tool_id = data.tools["swh-metadata-detector"]["id"] metadata1 = { "author": "John Doe", } metadata1_rev = RevisionIntrinsicMetadataRow( id=data.revision_id_1, metadata=metadata1, mappings=[], indexer_configuration_id=tool_id, ) metadata1_origin = OriginIntrinsicMetadataRow( id=data.origin_url_1, metadata=metadata1, mappings=[], indexer_configuration_id=tool_id, from_revision=data.revision_id_1, ) metadata2 = { "author": "Jane Doe", } metadata2_rev = RevisionIntrinsicMetadataRow( id=data.revision_id_2, metadata=metadata2, mappings=[], indexer_configuration_id=tool_id, ) metadata2_origin = OriginIntrinsicMetadataRow( id=data.origin_url_2, metadata=metadata2, mappings=[], indexer_configuration_id=tool_id, from_revision=data.revision_id_2, ) # when storage.revision_intrinsic_metadata_add([metadata1_rev]) storage.origin_intrinsic_metadata_add([metadata1_origin]) storage.revision_intrinsic_metadata_add([metadata2_rev]) storage.origin_intrinsic_metadata_add([metadata2_origin]) # then search = storage.origin_intrinsic_metadata_search_fulltext assert set([res.id for res in search(["Doe"])]) == set( [data.origin_url_1, data.origin_url_2] ) assert [res.id for res in search(["John", "Doe"])] == [data.origin_url_1] assert [res.id for res in search(["John"])] == [data.origin_url_1] assert not list(search(["John", "Jane"])) def test_origin_intrinsic_metadata_search_fulltext_rank( self, swh_indexer_storage_with_data: Tuple[IndexerStorageInterface, Any] ) -> None: storage, data = swh_indexer_storage_with_data # given tool_id = data.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 = RevisionIntrinsicMetadataRow( id=data.revision_id_1, metadata=metadata1, mappings=[], indexer_configuration_id=tool_id, ) metadata1_origin = OriginIntrinsicMetadataRow( id=data.origin_url_1, metadata=metadata1, mappings=[], indexer_configuration_id=tool_id, from_revision=data.revision_id_1, ) metadata2 = {"author": ["Random Person", "Jane Doe",]} metadata2_rev = RevisionIntrinsicMetadataRow( id=data.revision_id_2, metadata=metadata2, mappings=[], indexer_configuration_id=tool_id, ) metadata2_origin = OriginIntrinsicMetadataRow( id=data.origin_url_2, metadata=metadata2, mappings=[], indexer_configuration_id=tool_id, from_revision=data.revision_id_2, ) # when storage.revision_intrinsic_metadata_add([metadata1_rev]) storage.origin_intrinsic_metadata_add([metadata1_origin]) storage.revision_intrinsic_metadata_add([metadata2_rev]) storage.origin_intrinsic_metadata_add([metadata2_origin]) # then search = storage.origin_intrinsic_metadata_search_fulltext assert [res.id for res in search(["Doe"])] == [ data.origin_url_1, data.origin_url_2, ] assert [res.id for res in search(["Doe"], limit=1)] == [data.origin_url_1] assert [res.id for res in search(["John"])] == [data.origin_url_1] assert [res.id for res in search(["Jane"])] == [ data.origin_url_2, data.origin_url_1, ] assert [res.id for res in search(["John", "Jane"])] == [data.origin_url_1] def _fill_origin_intrinsic_metadata( self, swh_indexer_storage_with_data: Tuple[IndexerStorageInterface, Any] ) -> None: storage, data = swh_indexer_storage_with_data tool1_id = data.tools["swh-metadata-detector"]["id"] tool2_id = data.tools["swh-metadata-detector2"]["id"] metadata1 = { "@context": "foo", "author": "John Doe", } metadata1_rev = RevisionIntrinsicMetadataRow( id=data.revision_id_1, metadata=metadata1, mappings=["npm"], indexer_configuration_id=tool1_id, ) metadata1_origin = OriginIntrinsicMetadataRow( id=data.origin_url_1, metadata=metadata1, mappings=["npm"], indexer_configuration_id=tool1_id, from_revision=data.revision_id_1, ) metadata2 = { "@context": "foo", "author": "Jane Doe", } metadata2_rev = RevisionIntrinsicMetadataRow( id=data.revision_id_2, metadata=metadata2, mappings=["npm", "gemspec"], indexer_configuration_id=tool2_id, ) metadata2_origin = OriginIntrinsicMetadataRow( id=data.origin_url_2, metadata=metadata2, mappings=["npm", "gemspec"], indexer_configuration_id=tool2_id, from_revision=data.revision_id_2, ) metadata3 = { "@context": "foo", } metadata3_rev = RevisionIntrinsicMetadataRow( id=data.revision_id_3, metadata=metadata3, mappings=["npm", "gemspec"], indexer_configuration_id=tool2_id, ) metadata3_origin = OriginIntrinsicMetadataRow( id=data.origin_url_3, metadata=metadata3, mappings=["pkg-info"], indexer_configuration_id=tool2_id, from_revision=data.revision_id_3, ) storage.revision_intrinsic_metadata_add([metadata1_rev]) storage.origin_intrinsic_metadata_add([metadata1_origin]) storage.revision_intrinsic_metadata_add([metadata2_rev]) storage.origin_intrinsic_metadata_add([metadata2_origin]) storage.revision_intrinsic_metadata_add([metadata3_rev]) storage.origin_intrinsic_metadata_add([metadata3_origin]) def test_origin_intrinsic_metadata_search_by_producer( self, swh_indexer_storage_with_data: Tuple[IndexerStorageInterface, Any] ) -> None: storage, data = swh_indexer_storage_with_data self._fill_origin_intrinsic_metadata(swh_indexer_storage_with_data) tool1 = data.tools["swh-metadata-detector"] tool2 = data.tools["swh-metadata-detector2"] endpoint = storage.origin_intrinsic_metadata_search_by_producer # test pagination # no 'page_token' param, return all origins result = endpoint(ids_only=True) assert result == PagedResult( results=[data.origin_url_1, data.origin_url_2, data.origin_url_3,], next_page_token=None, ) # 'page_token' is < than origin_1, return everything result = endpoint(page_token=data.origin_url_1[:-1], ids_only=True) assert result == PagedResult( results=[data.origin_url_1, data.origin_url_2, data.origin_url_3,], next_page_token=None, ) # 'page_token' is origin_3, return nothing result = endpoint(page_token=data.origin_url_3, ids_only=True) assert result == PagedResult(results=[], next_page_token=None) # test limit argument result = endpoint(page_token=data.origin_url_1[:-1], limit=2, ids_only=True) assert result == PagedResult( results=[data.origin_url_1, data.origin_url_2], next_page_token=data.origin_url_2, ) result = endpoint(page_token=data.origin_url_1, limit=2, ids_only=True) assert result == PagedResult( results=[data.origin_url_2, data.origin_url_3], next_page_token=None, ) result = endpoint(page_token=data.origin_url_2, limit=2, ids_only=True) assert result == PagedResult(results=[data.origin_url_3], next_page_token=None,) # test mappings filtering result = endpoint(mappings=["npm"], ids_only=True) assert result == PagedResult( results=[data.origin_url_1, data.origin_url_2], next_page_token=None, ) result = endpoint(mappings=["npm", "gemspec"], ids_only=True) assert result == PagedResult( results=[data.origin_url_1, data.origin_url_2], next_page_token=None, ) result = endpoint(mappings=["gemspec"], ids_only=True) assert result == PagedResult(results=[data.origin_url_2], next_page_token=None,) result = endpoint(mappings=["pkg-info"], ids_only=True) assert result == PagedResult(results=[data.origin_url_3], next_page_token=None,) result = endpoint(mappings=["foobar"], ids_only=True) assert result == PagedResult(results=[], next_page_token=None,) # test pagination + mappings result = endpoint(mappings=["npm"], limit=1, ids_only=True) assert result == PagedResult( results=[data.origin_url_1], next_page_token=data.origin_url_1, ) # test tool filtering result = endpoint(tool_ids=[tool1["id"]], ids_only=True) assert result == PagedResult(results=[data.origin_url_1], next_page_token=None,) result = endpoint(tool_ids=[tool2["id"]], ids_only=True) assert sorted(result.results) == [data.origin_url_2, data.origin_url_3] assert result.next_page_token is None result = endpoint(tool_ids=[tool1["id"], tool2["id"]], ids_only=True) assert sorted(result.results) == [ data.origin_url_1, data.origin_url_2, data.origin_url_3, ] assert result.next_page_token is None # test ids_only=False assert endpoint(mappings=["gemspec"]) == PagedResult( results=[ OriginIntrinsicMetadataRow( id=data.origin_url_2, metadata={"@context": "foo", "author": "Jane Doe",}, mappings=["npm", "gemspec"], tool=tool2, from_revision=data.revision_id_2, ) ], next_page_token=None, ) def test_origin_intrinsic_metadata_stats( self, swh_indexer_storage_with_data: Tuple[IndexerStorageInterface, Any] ) -> None: storage, data = swh_indexer_storage_with_data self._fill_origin_intrinsic_metadata(swh_indexer_storage_with_data) result = storage.origin_intrinsic_metadata_stats() assert result == { "per_mapping": { "gemspec": 1, "npm": 2, "pkg-info": 1, "codemeta": 0, "maven": 0, }, "total": 3, "non_empty": 2, } class TestIndexerStorageIndexerConfiguration: def test_indexer_configuration_add( self, swh_indexer_storage_with_data: Tuple[IndexerStorageInterface, Any] ) -> None: storage, data = swh_indexer_storage_with_data tool = { "tool_name": "some-unknown-tool", "tool_version": "some-version", "tool_configuration": {"debian-package": "some-package"}, } actual_tool = storage.indexer_configuration_get(tool) assert actual_tool is None # does not exist # add it actual_tools = list(storage.indexer_configuration_add([tool])) assert len(actual_tools) == 1 actual_tool = actual_tools[0] assert actual_tool is not None # now it exists new_id = actual_tool.pop("id") assert actual_tool == tool actual_tools2 = list(storage.indexer_configuration_add([tool])) actual_tool2 = actual_tools2[0] assert actual_tool2 is not None # now it exists new_id2 = actual_tool2.pop("id") assert new_id == new_id2 assert actual_tool == actual_tool2 def test_indexer_configuration_add_multiple( self, swh_indexer_storage_with_data: Tuple[IndexerStorageInterface, Any] ) -> None: storage, data = swh_indexer_storage_with_data tool = { "tool_name": "some-unknown-tool", "tool_version": "some-version", "tool_configuration": {"debian-package": "some-package"}, } actual_tools = list(storage.indexer_configuration_add([tool])) assert len(actual_tools) == 1 new_tools = [ tool, { "tool_name": "yet-another-tool", "tool_version": "version", "tool_configuration": {}, }, ] actual_tools = list(storage.indexer_configuration_add(new_tools)) assert len(actual_tools) == 2 # order not guaranteed, so we iterate over results to check for tool in actual_tools: _id = tool.pop("id") assert _id is not None assert tool in new_tools def test_indexer_configuration_get_missing( self, swh_indexer_storage_with_data: Tuple[IndexerStorageInterface, Any] ) -> None: storage, data = swh_indexer_storage_with_data tool = { "tool_name": "unknown-tool", "tool_version": "3.1.0rc2-31-ga2cbb8c", "tool_configuration": {"command_line": "nomossa "}, } actual_tool = storage.indexer_configuration_get(tool) assert actual_tool is None def test_indexer_configuration_get( self, swh_indexer_storage_with_data: Tuple[IndexerStorageInterface, Any] ) -> None: storage, data = swh_indexer_storage_with_data tool = { "tool_name": "nomos", "tool_version": "3.1.0rc2-31-ga2cbb8c", "tool_configuration": {"command_line": "nomossa "}, } actual_tool = storage.indexer_configuration_get(tool) assert actual_tool expected_tool = tool.copy() del actual_tool["id"] assert expected_tool == actual_tool def test_indexer_configuration_metadata_get_missing_context( self, swh_indexer_storage_with_data: Tuple[IndexerStorageInterface, Any] ) -> None: storage, data = swh_indexer_storage_with_data tool = { "tool_name": "swh-metadata-translator", "tool_version": "0.0.1", "tool_configuration": {"context": "unknown-context"}, } actual_tool = storage.indexer_configuration_get(tool) assert actual_tool is None def test_indexer_configuration_metadata_get( self, swh_indexer_storage_with_data: Tuple[IndexerStorageInterface, Any] ) -> None: storage, data = swh_indexer_storage_with_data tool = { "tool_name": "swh-metadata-translator", "tool_version": "0.0.1", "tool_configuration": {"type": "local", "context": "NpmMapping"}, } storage.indexer_configuration_add([tool]) actual_tool = storage.indexer_configuration_get(tool) assert actual_tool expected_tool = tool.copy() expected_tool["id"] = actual_tool["id"] assert expected_tool == actual_tool diff --git a/swh/indexer/tests/test_cli.py b/swh/indexer/tests/test_cli.py index 59c9528..04d1ad2 100644 --- a/swh/indexer/tests/test_cli.py +++ b/swh/indexer/tests/test_cli.py @@ -1,385 +1,385 @@ # Copyright (C) 2019-2020 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 typing import Any, Dict, List from unittest.mock import patch from click.testing import CliRunner from confluent_kafka import Consumer, Producer from swh.indexer.cli import indexer_cli_group from swh.indexer.storage.interface import IndexerStorageInterface from swh.indexer.storage.model import ( OriginIntrinsicMetadataRow, RevisionIntrinsicMetadataRow, ) from swh.journal.serializers import value_to_kafka from swh.model.hashutil import hash_to_bytes CLI_CONFIG = """ scheduler: cls: foo args: {} storage: cls: memory indexer_storage: cls: memory """ def fill_idx_storage(idx_storage: IndexerStorageInterface, nb_rows: int) -> List[int]: tools: List[Dict[str, Any]] = [ {"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 = [ OriginIntrinsicMetadataRow( 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 = [ RevisionIntrinsicMetadataRow( 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"} + expected_kwargs = {} 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(["file://dev/%04d" % i for i in origins]) def invoke(scheduler, catch_exceptions, args): runner = CliRunner() with patch( "swh.scheduler.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(indexer_cli_group, ["-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).\nDone.\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).\nDone.\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, kafka_prefix: str, kafka_server, consumer: Consumer ): """Test the 'swh indexer journal-client' cli tool.""" producer = Producer( { "bootstrap.servers": kafka_server, "client.id": "test producer", "acks": "all", } ) STATUS = {"status": "full", "origin": {"url": "file://dev/0000",}} producer.produce( topic=kafka_prefix + ".origin_visit", key=b"bogus", value=value_to_kafka(STATUS), ) result = invoke( indexer_scheduler, False, [ "journal-client", "--stop-after-objects", "1", "--broker", kafka_server, "--prefix", kafka_prefix, "--group-id", "test-consumer", ], ) # Check the output expected_output = "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, [0]) diff --git a/swh/indexer/tests/test_indexer.py b/swh/indexer/tests/test_indexer.py index f920aab..10e7155 100644 --- a/swh/indexer/tests/test_indexer.py +++ b/swh/indexer/tests/test_indexer.py @@ -1,108 +1,106 @@ # Copyright (C) 2020 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 typing import Any, Dict, List, Optional from unittest.mock import Mock import pytest from swh.indexer.indexer import ( ContentIndexer, ContentPartitionIndexer, OriginIndexer, RevisionIndexer, ) from swh.indexer.storage import PagedResult, Sha1 from .utils import BASE_TEST_CONFIG class _TestException(Exception): pass class CrashingIndexerMixin: USE_TOOLS = False def index( self, id: Any, data: Optional[Any] = None, **kwargs ) -> List[Dict[str, Any]]: raise _TestException() - def persist_index_computations(self, results, policy_update) -> Dict[str, int]: + def persist_index_computations(self, results) -> Dict[str, int]: return {} def indexed_contents_in_partition( self, partition_id: int, nb_partitions: int, page_token: Optional[str] = None ) -> PagedResult[Sha1]: raise _TestException() class CrashingContentIndexer(CrashingIndexerMixin, ContentIndexer): pass class CrashingContentPartitionIndexer(CrashingIndexerMixin, ContentPartitionIndexer): pass class CrashingRevisionIndexer(CrashingIndexerMixin, RevisionIndexer): pass class CrashingOriginIndexer(CrashingIndexerMixin, OriginIndexer): pass def test_content_indexer_catch_exceptions(): indexer = CrashingContentIndexer(config=BASE_TEST_CONFIG) indexer.objstorage = Mock() indexer.objstorage.get.return_value = b"content" - assert indexer.run([b"foo"], policy_update=True) == {"status": "failed"} + assert indexer.run([b"foo"]) == {"status": "failed"} indexer.catch_exceptions = False with pytest.raises(_TestException): - indexer.run([b"foo"], policy_update=True) + indexer.run([b"foo"]) def test_revision_indexer_catch_exceptions(): indexer = CrashingRevisionIndexer(config=BASE_TEST_CONFIG) indexer.storage = Mock() indexer.storage.revision_get.return_value = ["rev"] - assert indexer.run([b"foo"], policy_update=True) == {"status": "failed"} + assert indexer.run([b"foo"]) == {"status": "failed"} indexer.catch_exceptions = False with pytest.raises(_TestException): - indexer.run([b"foo"], policy_update=True) + indexer.run([b"foo"]) def test_origin_indexer_catch_exceptions(): indexer = CrashingOriginIndexer(config=BASE_TEST_CONFIG) - assert indexer.run(["http://example.org"], policy_update=True) == { - "status": "failed" - } + assert indexer.run(["http://example.org"]) == {"status": "failed"} indexer.catch_exceptions = False with pytest.raises(_TestException): - indexer.run(["http://example.org"], policy_update=True) + indexer.run(["http://example.org"]) def test_content_partition_indexer_catch_exceptions(): indexer = CrashingContentPartitionIndexer( config={**BASE_TEST_CONFIG, "write_batch_size": 42} ) - assert indexer.run(0, 42, policy_update=True) == {"status": "failed"} + assert indexer.run(0, 42) == {"status": "failed"} indexer.catch_exceptions = False with pytest.raises(_TestException): - indexer.run(0, 42, policy_update=True) + indexer.run(0, 42) diff --git a/swh/indexer/tests/test_journal_client.py b/swh/indexer/tests/test_journal_client.py index c27bb01..23f1a09 100644 --- a/swh/indexer/tests/test_journal_client.py +++ b/swh/indexer/tests/test_journal_client.py @@ -1,159 +1,153 @@ # 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 unittest from unittest.mock import Mock, patch from swh.indexer.journal_client import process_journal_objects class JournalClientTest(unittest.TestCase): def testOneOriginVisit(self): mock_scheduler = Mock() messages = { "origin_visit": [{"status": "full", "origin": "file:///dev/zero",},] } process_journal_objects( messages, scheduler=mock_scheduler, task_names={"origin_metadata": "task-name"}, ) self.assertTrue(mock_scheduler.create_tasks.called) call_args = mock_scheduler.create_tasks.call_args (args, kwargs) = call_args self.assertEqual(kwargs, {}) del args[0][0]["next_run"] self.assertEqual( args, ( [ { - "arguments": { - "kwargs": {"policy_update": "update-dups"}, - "args": (["file:///dev/zero"],), - }, + "arguments": {"kwargs": {}, "args": (["file:///dev/zero"],),}, "policy": "oneshot", "type": "task-name", "retries_left": 1, }, ], ), ) def testOriginVisitLegacy(self): mock_scheduler = Mock() messages = { "origin_visit": [ {"status": "full", "origin": {"url": "file:///dev/zero",}}, ] } process_journal_objects( messages, scheduler=mock_scheduler, task_names={"origin_metadata": "task-name"}, ) self.assertTrue(mock_scheduler.create_tasks.called) call_args = mock_scheduler.create_tasks.call_args (args, kwargs) = call_args self.assertEqual(kwargs, {}) del args[0][0]["next_run"] self.assertEqual( args, ( [ { - "arguments": { - "kwargs": {"policy_update": "update-dups"}, - "args": (["file:///dev/zero"],), - }, + "arguments": {"kwargs": {}, "args": (["file:///dev/zero"],),}, "policy": "oneshot", "type": "task-name", "retries_left": 1, }, ], ), ) def testOneOriginVisitBatch(self): mock_scheduler = Mock() messages = { "origin_visit": [ {"status": "full", "origin": "file:///dev/zero",}, {"status": "full", "origin": "file:///tmp/foobar",}, ] } process_journal_objects( messages, scheduler=mock_scheduler, task_names={"origin_metadata": "task-name"}, ) self.assertTrue(mock_scheduler.create_tasks.called) call_args = mock_scheduler.create_tasks.call_args (args, kwargs) = call_args self.assertEqual(kwargs, {}) del args[0][0]["next_run"] self.assertEqual( args, ( [ { "arguments": { - "kwargs": {"policy_update": "update-dups"}, + "kwargs": {}, "args": (["file:///dev/zero", "file:///tmp/foobar"],), }, "policy": "oneshot", "type": "task-name", "retries_left": 1, }, ], ), ) @patch("swh.indexer.journal_client.MAX_ORIGINS_PER_TASK", 2) def testOriginVisitBatches(self): mock_scheduler = Mock() messages = { "origin_visit": [ {"status": "full", "origin": "file:///dev/zero",}, {"status": "full", "origin": "file:///tmp/foobar",}, {"status": "full", "origin": "file:///tmp/spamegg",}, ] } process_journal_objects( messages, scheduler=mock_scheduler, task_names={"origin_metadata": "task-name"}, ) self.assertTrue(mock_scheduler.create_tasks.called) call_args = mock_scheduler.create_tasks.call_args (args, kwargs) = call_args self.assertEqual(kwargs, {}) del args[0][0]["next_run"] del args[0][1]["next_run"] self.assertEqual( args, ( [ { "arguments": { - "kwargs": {"policy_update": "update-dups"}, + "kwargs": {}, "args": (["file:///dev/zero", "file:///tmp/foobar"],), }, "policy": "oneshot", "type": "task-name", "retries_left": 1, }, { "arguments": { - "kwargs": {"policy_update": "update-dups"}, + "kwargs": {}, "args": (["file:///tmp/spamegg"],), }, "policy": "oneshot", "type": "task-name", "retries_left": 1, }, ], ), ) diff --git a/swh/indexer/tests/test_metadata.py b/swh/indexer/tests/test_metadata.py index 8fa098c..0505934 100644 --- a/swh/indexer/tests/test_metadata.py +++ b/swh/indexer/tests/test_metadata.py @@ -1,1205 +1,1205 @@ # Copyright (C) 2017-2020 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 from hypothesis import HealthCheck, given, settings, strategies from swh.indexer.codemeta import CODEMETA_TERMS from swh.indexer.metadata import ContentMetadataIndexer, RevisionMetadataIndexer from swh.indexer.metadata_detector import detect_metadata from swh.indexer.metadata_dictionary import MAPPINGS 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.storage.model import ContentMetadataRow, RevisionIntrinsicMetadataRow from swh.indexer.tests.utils import DIRECTORY2, REVISION from swh.model.hashutil import hash_to_bytes from swh.model.model import Directory, DirectoryEntry, Revision from .utils import ( BASE_TEST_CONFIG, YARN_PARSER_METADATA, fill_obj_storage, fill_storage, 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_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_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") + metadata_indexer.run(sha1s) results = list(metadata_indexer.idx_storage.content_metadata_get(sha1s)) expected_results = [ ContentMetadataRow( id=hash_to_bytes("26a9f72a7c87cc9205725cfd879f514ff4f3d8d5"), tool=TRANSLATOR_TOOL, 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", }, ), ContentMetadataRow( id=hash_to_bytes("d4c647f0fc257591cc9ba1722484229780d1c607"), tool=TRANSLATOR_TOOL, 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/", }, ), ] for result in results: del result.tool["id"] # 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": [{"type": "Person", "name": "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"), [ {"type": "Person", "name": "Ruby Coder1"}, {"type": "Person", "name": "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": [{"type": "Person", "name": "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(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(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, GemspecMapping.mapping) ), # values strategies.recursive( strategies.characters(), lambda children: strategies.lists(children, min_size=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( {f"tool_{k}": v for (k, v) in TRANSLATOR_TOOL.items()} ) assert tool is not None rev = REVISION assert rev.directory == DIRECTORY2.id metadata_indexer.idx_storage.content_metadata_add( [ ContentMetadataRow( id=DIRECTORY2.entries[0].target, indexer_configuration_id=tool["id"], metadata=YARN_PARSER_METADATA, ) ] ) - metadata_indexer.run([rev.id], "update-dups") + metadata_indexer.run([rev.id]) results = list( metadata_indexer.idx_storage.revision_intrinsic_metadata_get([REVISION.id]) ) expected_results = [ RevisionIntrinsicMetadataRow( id=rev.id, tool=TRANSLATOR_TOOL, metadata=YARN_PARSER_METADATA, mappings=["npm"], ) ] for result in results: del result.tool["id"] # then self.assertEqual(results, expected_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 = REVISION assert rev.directory == DIRECTORY2.id directory = Directory( entries=( DirectoryEntry( name=b"foobar-1.0.0", type="dir", target=rev.directory, perms=16384, ), ), ) assert directory.id is not None metadata_indexer.storage.directory_add([directory]) new_rev_dict = {**rev.to_dict(), "directory": directory.id} new_rev_dict.pop("id") new_rev = Revision.from_dict(new_rev_dict) metadata_indexer.storage.revision_add([new_rev]) tool = metadata_indexer.idx_storage.indexer_configuration_get( {f"tool_{k}": v for (k, v) in TRANSLATOR_TOOL.items()} ) assert tool is not None metadata_indexer.idx_storage.content_metadata_add( [ ContentMetadataRow( id=DIRECTORY2.entries[0].target, indexer_configuration_id=tool["id"], metadata=YARN_PARSER_METADATA, ) ] ) - metadata_indexer.run([new_rev.id], "update-dups") + metadata_indexer.run([new_rev.id]) results = list( metadata_indexer.idx_storage.revision_intrinsic_metadata_get([new_rev.id]) ) expected_results = [ RevisionIntrinsicMetadataRow( id=new_rev.id, tool=TRANSLATOR_TOOL, metadata=YARN_PARSER_METADATA, mappings=["npm"], ) ] for result in results: del result.tool["id"] # then self.assertEqual(results, expected_results) diff --git a/swh/indexer/tests/test_origin_head.py b/swh/indexer/tests/test_origin_head.py index 5faeb04..3ad457c 100644 --- a/swh/indexer/tests/test_origin_head.py +++ b/swh/indexer/tests/test_origin_head.py @@ -1,190 +1,190 @@ # Copyright (C) 2017-2020 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 copy from datetime import datetime, timezone import unittest import pytest from swh.indexer.origin_head import OriginHeadIndexer from swh.indexer.tests.utils import fill_storage from swh.model.model import ( Origin, OriginVisit, OriginVisitStatus, Snapshot, SnapshotBranch, TargetType, ) from swh.storage.utils import now @pytest.fixture def swh_indexer_config(swh_indexer_config): config = copy.deepcopy(swh_indexer_config) config.update( { "tools": { "name": "origin-metadata", "version": "0.0.1", "configuration": {}, }, "tasks": { "revision_intrinsic_metadata": None, "origin_intrinsic_metadata": None, }, } ) return config class OriginHeadTestIndexer(OriginHeadIndexer): """Specific indexer whose configuration is enough to satisfy the indexing tests. """ - def persist_index_computations(self, results, policy_update): + def persist_index_computations(self, results): self.results = results class OriginHead(unittest.TestCase): @pytest.fixture(autouse=True) def init(self, swh_config): super().setUp() self.indexer = OriginHeadTestIndexer() self.indexer.catch_exceptions = False fill_storage(self.indexer.storage) def test_git(self): origin_url = "https://github.com/SoftwareHeritage/swh-storage" self.indexer.run([origin_url]) rev_id = b"8K\x12\x00d\x03\xcc\xe4]bS\xe3\x8f{\xd7}\xac\xefrm" self.assertEqual( self.indexer.results, [{"revision_id": rev_id, "origin_url": origin_url,}], ) def test_git_partial_snapshot(self): """Checks partial snapshots are ignored.""" origin_url = "https://github.com/SoftwareHeritage/swh-core" self.indexer.storage.origin_add([Origin(url=origin_url)]) visit = self.indexer.storage.origin_visit_add( [ OriginVisit( origin=origin_url, date=datetime(2019, 2, 27, tzinfo=timezone.utc), type="git", ) ] )[0] self.indexer.storage.snapshot_add( [ Snapshot( branches={ b"foo": None, b"HEAD": SnapshotBranch( target_type=TargetType.ALIAS, target=b"foo", ), }, ), ] ) visit_status = OriginVisitStatus( origin=origin_url, visit=visit.visit, date=now(), status="partial", snapshot=b"foo", ) self.indexer.storage.origin_visit_status_add([visit_status]) self.indexer.run([origin_url]) self.assertEqual(self.indexer.results, []) def test_vcs_missing_snapshot(self): origin_url = "https://github.com/SoftwareHeritage/swh-indexer" self.indexer.storage.origin_add([Origin(url=origin_url)]) self.indexer.run([origin_url]) self.assertEqual(self.indexer.results, []) def test_pypi_missing_branch(self): origin_url = "https://pypi.org/project/abcdef/" self.indexer.storage.origin_add([Origin(url=origin_url,)]) visit = self.indexer.storage.origin_visit_add( [ OriginVisit( origin=origin_url, date=datetime(2019, 2, 27, tzinfo=timezone.utc), type="pypi", ) ] )[0] self.indexer.storage.snapshot_add( [ Snapshot( branches={ b"foo": None, b"HEAD": SnapshotBranch( target_type=TargetType.ALIAS, target=b"foo", ), }, ) ] ) visit_status = OriginVisitStatus( origin=origin_url, visit=visit.visit, date=now(), status="full", snapshot=b"foo", ) self.indexer.storage.origin_visit_status_add([visit_status]) self.indexer.run(["https://pypi.org/project/abcdef/"]) self.assertEqual(self.indexer.results, []) def test_ftp(self): origin_url = "rsync://ftp.gnu.org/gnu/3dldf" self.indexer.run([origin_url]) rev_id = b"\x8e\xa9\x8e/\xea}\x9feF\xf4\x9f\xfd\xee\xcc\x1a\xb4`\x8c\x8by" self.assertEqual( self.indexer.results, [{"revision_id": rev_id, "origin_url": origin_url,}], ) def test_ftp_missing_snapshot(self): origin_url = "rsync://ftp.gnu.org/gnu/foobar" self.indexer.storage.origin_add([Origin(url=origin_url)]) self.indexer.run([origin_url]) self.assertEqual(self.indexer.results, []) def test_deposit(self): origin_url = "https://forge.softwareheritage.org/source/jesuisgpl/" self.indexer.storage.origin_add([Origin(url=origin_url)]) self.indexer.run([origin_url]) rev_id = b"\xe7n\xa4\x9c\x9f\xfb\xb7\xf76\x11\x08{\xa6\xe9\x99\xb1\x9e]q\xeb" self.assertEqual( self.indexer.results, [{"revision_id": rev_id, "origin_url": origin_url,}], ) def test_deposit_missing_snapshot(self): origin_url = "https://forge.softwareheritage.org/source/foobar" self.indexer.storage.origin_add([Origin(url=origin_url,)]) self.indexer.run([origin_url]) self.assertEqual(self.indexer.results, []) def test_pypi(self): origin_url = "https://pypi.org/project/limnoria/" self.indexer.run([origin_url]) rev_id = b"\x83\xb9\xb6\xc7\x05\xb1%\xd0\xfem\xd8kA\x10\x9d\xc5\xfa2\xf8t" self.assertEqual( self.indexer.results, [{"revision_id": rev_id, "origin_url": origin_url}], ) def test_svn(self): origin_url = "http://0-512-md.googlecode.com/svn/" self.indexer.run([origin_url]) rev_id = b"\xe4?r\xe1,\x88\xab\xec\xe7\x9a\x87\xb8\xc9\xad#.\x1bw=\x18" self.assertEqual( self.indexer.results, [{"revision_id": rev_id, "origin_url": origin_url,}], ) diff --git a/swh/indexer/tests/test_origin_metadata.py b/swh/indexer/tests/test_origin_metadata.py index 65e8af2..63ce2aa 100644 --- a/swh/indexer/tests/test_origin_metadata.py +++ b/swh/indexer/tests/test_origin_metadata.py @@ -1,246 +1,220 @@ # Copyright (C) 2018-2020 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.indexer.metadata import OriginMetadataIndexer from swh.indexer.storage.interface import IndexerStorageInterface from swh.indexer.storage.model import ( OriginIntrinsicMetadataRow, RevisionIntrinsicMetadataRow, ) from swh.model.model import Origin from swh.storage.interface import StorageInterface from .test_metadata import REVISION_METADATA_CONFIG from .utils import REVISION, YARN_PARSER_METADATA def test_origin_metadata_indexer( idx_storage: IndexerStorageInterface, storage: StorageInterface, obj_storage ) -> None: indexer = OriginMetadataIndexer(config=REVISION_METADATA_CONFIG) origin = "https://github.com/librariesio/yarn-parser" indexer.run([origin]) tool = { "name": "swh-metadata-translator", "version": "0.0.2", "configuration": {"context": "NpmMapping", "type": "local"}, } rev_id = REVISION.id rev_metadata = RevisionIntrinsicMetadataRow( id=rev_id, tool=tool, metadata=YARN_PARSER_METADATA, mappings=["npm"], ) origin_metadata = OriginIntrinsicMetadataRow( id=origin, tool=tool, from_revision=rev_id, metadata=YARN_PARSER_METADATA, mappings=["npm"], ) rev_results = list(indexer.idx_storage.revision_intrinsic_metadata_get([rev_id])) for rev_result in rev_results: assert rev_result.tool del rev_result.tool["id"] assert rev_results == [rev_metadata] orig_results = list(indexer.idx_storage.origin_intrinsic_metadata_get([origin])) for orig_result in orig_results: assert orig_result.tool del orig_result.tool["id"] assert orig_results == [origin_metadata] def test_origin_metadata_indexer_duplicate_origin( idx_storage: IndexerStorageInterface, storage: StorageInterface, obj_storage ) -> None: 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 = "https://github.com/librariesio/yarn-parser" rev_id = REVISION.id rev_results = list(indexer.idx_storage.revision_intrinsic_metadata_get([rev_id])) assert len(rev_results) == 1 orig_results = list(indexer.idx_storage.origin_intrinsic_metadata_get([origin])) assert len(orig_results) == 1 def test_origin_metadata_indexer_missing_head( idx_storage: IndexerStorageInterface, storage: StorageInterface, obj_storage ) -> None: storage.origin_add([Origin(url="https://example.com")]) indexer = OriginMetadataIndexer(config=REVISION_METADATA_CONFIG) indexer.run(["https://example.com"]) origin = "https://example.com" results = list(indexer.idx_storage.origin_intrinsic_metadata_get([origin])) assert results == [] def test_origin_metadata_indexer_partial_missing_head( idx_storage: IndexerStorageInterface, storage: StorageInterface, obj_storage ) -> None: origin1 = "https://example.com" origin2 = "https://github.com/librariesio/yarn-parser" storage.origin_add([Origin(url=origin1)]) indexer = OriginMetadataIndexer(config=REVISION_METADATA_CONFIG) indexer.run([origin1, origin2]) rev_id = REVISION.id rev_results = list(indexer.idx_storage.revision_intrinsic_metadata_get([rev_id])) assert rev_results == [ RevisionIntrinsicMetadataRow( id=rev_id, metadata=YARN_PARSER_METADATA, mappings=["npm"], tool=rev_results[0].tool, ) ] orig_results = list( indexer.idx_storage.origin_intrinsic_metadata_get([origin1, origin2]) ) for orig_result in orig_results: assert orig_results == [ OriginIntrinsicMetadataRow( id=origin2, from_revision=rev_id, metadata=YARN_PARSER_METADATA, mappings=["npm"], tool=orig_results[0].tool, ) ] def test_origin_metadata_indexer_duplicate_revision( idx_storage: IndexerStorageInterface, storage: StorageInterface, obj_storage ) -> None: indexer = OriginMetadataIndexer(config=REVISION_METADATA_CONFIG) indexer.storage = storage indexer.idx_storage = idx_storage indexer.catch_exceptions = False origin1 = "https://github.com/librariesio/yarn-parser" origin2 = "https://github.com/librariesio/yarn-parser.git" indexer.run([origin1, origin2]) rev_id = REVISION.id rev_results = list(indexer.idx_storage.revision_intrinsic_metadata_get([rev_id])) assert len(rev_results) == 1 orig_results = list( indexer.idx_storage.origin_intrinsic_metadata_get([origin1, origin2]) ) assert len(orig_results) == 2 def test_origin_metadata_indexer_no_metadata_file( idx_storage: IndexerStorageInterface, storage: StorageInterface, obj_storage ) -> None: indexer = OriginMetadataIndexer(config=REVISION_METADATA_CONFIG) origin = "https://github.com/librariesio/yarn-parser" with patch("swh.indexer.metadata_dictionary.npm.NpmMapping.filename", b"foo.json"): indexer.run([origin]) rev_id = REVISION.id rev_results = list(indexer.idx_storage.revision_intrinsic_metadata_get([rev_id])) assert rev_results == [] orig_results = list(indexer.idx_storage.origin_intrinsic_metadata_get([origin])) assert orig_results == [] def test_origin_metadata_indexer_no_metadata( idx_storage: IndexerStorageInterface, storage: StorageInterface, obj_storage ) -> None: indexer = OriginMetadataIndexer(config=REVISION_METADATA_CONFIG) origin = "https://github.com/librariesio/yarn-parser" with patch( "swh.indexer.metadata.RevisionMetadataIndexer" ".translate_revision_intrinsic_metadata", return_value=(["npm"], {"@context": "foo"}), ): indexer.run([origin]) rev_id = REVISION.id rev_results = list(indexer.idx_storage.revision_intrinsic_metadata_get([rev_id])) assert rev_results == [] orig_results = list(indexer.idx_storage.origin_intrinsic_metadata_get([origin])) assert orig_results == [] def test_origin_metadata_indexer_error( idx_storage: IndexerStorageInterface, storage: StorageInterface, obj_storage ) -> None: indexer = OriginMetadataIndexer(config=REVISION_METADATA_CONFIG) origin = "https://github.com/librariesio/yarn-parser" with patch( "swh.indexer.metadata.RevisionMetadataIndexer" ".translate_revision_intrinsic_metadata", return_value=None, ): indexer.run([origin]) rev_id = REVISION.id rev_results = list(indexer.idx_storage.revision_intrinsic_metadata_get([rev_id])) assert rev_results == [] orig_results = list(indexer.idx_storage.origin_intrinsic_metadata_get([origin])) assert orig_results == [] -def test_origin_metadata_indexer_delete_metadata( - idx_storage: IndexerStorageInterface, storage: StorageInterface, obj_storage -) -> None: - - indexer = OriginMetadataIndexer(config=REVISION_METADATA_CONFIG) - origin = "https://github.com/librariesio/yarn-parser" - indexer.run([origin]) - - rev_id = REVISION.id - - rev_results = list(indexer.idx_storage.revision_intrinsic_metadata_get([rev_id])) - assert rev_results != [] - - orig_results = list(indexer.idx_storage.origin_intrinsic_metadata_get([origin])) - assert orig_results != [] - - with patch("swh.indexer.metadata_dictionary.npm.NpmMapping.filename", b"foo.json"): - indexer.run([origin]) - - rev_results = list(indexer.idx_storage.revision_intrinsic_metadata_get([rev_id])) - assert rev_results == [] - - orig_results = list(indexer.idx_storage.origin_intrinsic_metadata_get([origin])) - assert orig_results == [] - - def test_origin_metadata_indexer_unknown_origin( idx_storage: IndexerStorageInterface, storage: StorageInterface, obj_storage ) -> None: indexer = OriginMetadataIndexer(config=REVISION_METADATA_CONFIG) result = indexer.index_list(["https://unknown.org/foo"]) assert not result diff --git a/swh/indexer/tests/utils.py b/swh/indexer/tests/utils.py index c8e1f0c..fdbc86f 100644 --- a/swh/indexer/tests/utils.py +++ b/swh/indexer/tests/utils.py @@ -1,720 +1,719 @@ # Copyright (C) 2017-2020 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 functools from typing import Any, Dict import unittest from hypothesis import strategies from swh.core.api.classes import stream_results from swh.indexer.storage import INDEXER_CFG_KEY from swh.model import hashutil from swh.model.hashutil import hash_to_bytes from swh.model.model import ( Content, Directory, DirectoryEntry, Origin, OriginVisit, OriginVisitStatus, Person, Revision, RevisionType, Snapshot, SnapshotBranch, TargetType, Timestamp, TimestampWithTimezone, ) from swh.storage.utils import now BASE_TEST_CONFIG: Dict[str, Dict[str, Any]] = { "storage": {"cls": "memory"}, "objstorage": {"cls": "memory", "args": {},}, INDEXER_CFG_KEY: {"cls": "memory", "args": {},}, } ORIGINS = [ Origin(url="https://github.com/SoftwareHeritage/swh-storage"), Origin(url="rsync://ftp.gnu.org/gnu/3dldf"), Origin(url="https://forge.softwareheritage.org/source/jesuisgpl/"), Origin(url="https://pypi.org/project/limnoria/"), Origin(url="http://0-512-md.googlecode.com/svn/"), Origin(url="https://github.com/librariesio/yarn-parser"), Origin(url="https://github.com/librariesio/yarn-parser.git"), ] ORIGIN_VISITS = [ {"type": "git", "origin": ORIGINS[0].url}, {"type": "ftp", "origin": ORIGINS[1].url}, {"type": "deposit", "origin": ORIGINS[2].url}, {"type": "pypi", "origin": ORIGINS[3].url}, {"type": "svn", "origin": ORIGINS[4].url}, {"type": "git", "origin": ORIGINS[5].url}, {"type": "git", "origin": ORIGINS[6].url}, ] DIRECTORY = Directory( id=hash_to_bytes("34f335a750111ca0a8b64d8034faec9eedc396be"), entries=( DirectoryEntry( name=b"index.js", type="file", target=hash_to_bytes("01c9379dfc33803963d07c1ccc748d3fe4c96bb5"), perms=0o100644, ), DirectoryEntry( name=b"package.json", type="file", target=hash_to_bytes("26a9f72a7c87cc9205725cfd879f514ff4f3d8d5"), perms=0o100644, ), DirectoryEntry( name=b".github", type="dir", target=Directory(entries=()).id, perms=0o040000, ), ), ) DIRECTORY2 = Directory( id=b"\xf8zz\xa1\x12`<1$\xfav\xf9\x01\xfd5\x85F`\xf2\xb6", entries=( DirectoryEntry( name=b"package.json", type="file", target=hash_to_bytes("f5305243b3ce7ef8dc864ebc73794da304025beb"), perms=0o100644, ), ), ) REVISION = Revision( id=hash_to_bytes("c6201cb1b9b9df9a7542f9665c3b5dfab85e9775"), message=b"Improve search functionality", author=Person( name=b"Andrew Nesbitt", fullname=b"Andrew Nesbitt ", email=b"andrewnez@gmail.com", ), committer=Person( name=b"Andrew Nesbitt", fullname=b"Andrew Nesbitt ", email=b"andrewnez@gmail.com", ), committer_date=TimestampWithTimezone( timestamp=Timestamp(seconds=1380883849, microseconds=0,), offset=120, negative_utc=False, ), type=RevisionType.GIT, synthetic=False, date=TimestampWithTimezone( timestamp=Timestamp(seconds=1487596456, microseconds=0,), offset=0, negative_utc=False, ), directory=DIRECTORY2.id, parents=(), ) REVISIONS = [REVISION] SNAPSHOTS = [ Snapshot( id=hash_to_bytes("a50fde72265343b7d28cecf6db20d98a81d21965"), branches={ b"refs/heads/add-revision-origin-cache": SnapshotBranch( target=b'L[\xce\x1c\x88\x8eF\t\xf1"\x19\x1e\xfb\xc0s\xe7/\xe9l\x1e', target_type=TargetType.REVISION, ), b"refs/head/master": SnapshotBranch( target=b"8K\x12\x00d\x03\xcc\xe4]bS\xe3\x8f{\xd7}\xac\xefrm", target_type=TargetType.REVISION, ), b"HEAD": SnapshotBranch( target=b"refs/head/master", target_type=TargetType.ALIAS ), b"refs/tags/v0.0.103": SnapshotBranch( target=b'\xb6"Im{\xfdLb\xb0\x94N\xea\x96m\x13x\x88+\x0f\xdd', target_type=TargetType.RELEASE, ), }, ), Snapshot( id=hash_to_bytes("2c67f69a416bca4e1f3fcd848c588fab88ad0642"), branches={ b"3DLDF-1.1.4.tar.gz": SnapshotBranch( target=b'dJ\xfb\x1c\x91\xf4\x82B%]6\xa2\x90|\xd3\xfc"G\x99\x11', target_type=TargetType.REVISION, ), b"3DLDF-2.0.2.tar.gz": SnapshotBranch( target=b"\xb6\x0e\xe7\x9e9\xac\xaa\x19\x9e=\xd1\xc5\x00\\\xc6\xfc\xe0\xa6\xb4V", # noqa target_type=TargetType.REVISION, ), b"3DLDF-2.0.3-examples.tar.gz": SnapshotBranch( target=b"!H\x19\xc0\xee\x82-\x12F1\xbd\x97\xfe\xadZ\x80\x80\xc1\x83\xff", # noqa target_type=TargetType.REVISION, ), b"3DLDF-2.0.3.tar.gz": SnapshotBranch( target=b"\x8e\xa9\x8e/\xea}\x9feF\xf4\x9f\xfd\xee\xcc\x1a\xb4`\x8c\x8by", # noqa target_type=TargetType.REVISION, ), b"3DLDF-2.0.tar.gz": SnapshotBranch( target=b"F6*\xff(?\x19a\xef\xb6\xc2\x1fv$S\xe3G\xd3\xd1m", target_type=TargetType.REVISION, ), }, ), Snapshot( id=hash_to_bytes("68c0d26104d47e278dd6be07ed61fafb561d0d20"), branches={ b"master": SnapshotBranch( target=b"\xe7n\xa4\x9c\x9f\xfb\xb7\xf76\x11\x08{\xa6\xe9\x99\xb1\x9e]q\xeb", # noqa target_type=TargetType.REVISION, ) }, ), Snapshot( id=hash_to_bytes("f255245269e15fc99d284affd79f766668de0b67"), branches={ b"HEAD": SnapshotBranch( target=b"releases/2018.09.09", target_type=TargetType.ALIAS ), b"releases/2018.09.01": SnapshotBranch( target=b"<\xee1(\xe8\x8d_\xc1\xc9\xa6rT\xf1\x1d\xbb\xdfF\xfdw\xcf", target_type=TargetType.REVISION, ), b"releases/2018.09.09": SnapshotBranch( target=b"\x83\xb9\xb6\xc7\x05\xb1%\xd0\xfem\xd8kA\x10\x9d\xc5\xfa2\xf8t", # noqa target_type=TargetType.REVISION, ), }, ), Snapshot( id=hash_to_bytes("a1a28c0ab387a8f9e0618cb705eab81fc448f473"), branches={ b"master": SnapshotBranch( target=b"\xe4?r\xe1,\x88\xab\xec\xe7\x9a\x87\xb8\xc9\xad#.\x1bw=\x18", target_type=TargetType.REVISION, ) }, ), Snapshot( id=hash_to_bytes("bb4fd3a836930ce629d912864319637040ff3040"), branches={ b"HEAD": SnapshotBranch( target=REVISION.id, target_type=TargetType.REVISION, ) }, ), Snapshot( id=hash_to_bytes("bb4fd3a836930ce629d912864319637040ff3040"), branches={ b"HEAD": SnapshotBranch( target=REVISION.id, target_type=TargetType.REVISION, ) }, ), ] SHA1_TO_LICENSES = { "01c9379dfc33803963d07c1ccc748d3fe4c96bb5": ["GPL"], "02fb2c89e14f7fab46701478c83779c7beb7b069": ["Apache2.0"], "103bc087db1d26afc3a0283f38663d081e9b01e6": ["MIT"], "688a5ef812c53907562fe379d4b3851e69c7cb15": ["AGPL"], "da39a3ee5e6b4b0d3255bfef95601890afd80709": [], } SHA1_TO_CTAGS = { "01c9379dfc33803963d07c1ccc748d3fe4c96bb5": [ {"name": "foo", "kind": "str", "line": 10, "lang": "bar",} ], "d4c647f0fc257591cc9ba1722484229780d1c607": [ {"name": "let", "kind": "int", "line": 100, "lang": "haskell",} ], "688a5ef812c53907562fe379d4b3851e69c7cb15": [ {"name": "symbol", "kind": "float", "line": 99, "lang": "python",} ], } 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"", # was 626364 / b'bcd' "e3e40fee6ff8a52f06c3b428bfe7c0ed2ef56e92": b"unimportant content for bcd", # was 636465 / b'cde' now yarn-parser package.json "f5305243b3ce7ef8dc864ebc73794da304025beb": 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(), 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, min_size=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): storage.origin_add(ORIGINS) storage.directory_add([DIRECTORY, DIRECTORY2]) storage.revision_add(REVISIONS) storage.snapshot_add(SNAPSHOTS) for visit, snapshot in zip(ORIGIN_VISITS, SNAPSHOTS): assert snapshot.id is not None visit = storage.origin_visit_add( [OriginVisit(origin=visit["origin"], date=now(), type=visit["type"])] )[0] visit_status = OriginVisitStatus( origin=visit.origin, visit=visit.visit, date=now(), status="full", snapshot=snapshot.id, ) storage.origin_visit_status_add([visit_status]) contents = [] for (obj_id, content) in OBJ_STORAGE_DATA.items(): content_hashes = hashutil.MultiHash.from_data(content).digest() contents.append( Content( 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) class CommonContentIndexerTest(metaclass=abc.ABCMeta): 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_results_ok(self, sha1s, expected_results=None): 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(expected_results, actual_results) 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.indexer.run(sha1s) self.assert_results_ok(sha1s) # 2nd pass - self.indexer.run(sha1s, policy_update="ignore-dups") + self.indexer.run(sha1s) 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") + self.indexer.run(sha1s) # then expected_results = [ res for res in self.expected_results if hashutil.hash_to_hex(res.id) in sha1s ] self.assert_results_ok(sha1s, expected_results) class CommonContentIndexerPartitionTest: """Allows to factorize tests on range indexer. """ def setUp(self): self.contents = sorted(OBJ_STORAGE_DATA) def assert_results_ok(self, partition_id, nb_partitions, actual_results): expected_ids = [ c.sha1 for c in stream_results( self.indexer.storage.content_get_partition, partition_id=partition_id, nb_partitions=nb_partitions, ) ] actual_results = list(actual_results) for indexed_data in actual_results: _id = indexed_data.id assert _id in expected_ids _tool_id = indexed_data.indexer_configuration_id assert _tool_id == self.indexer.tool["id"] def test__index_contents(self): """Indexing contents without existing data results in indexed data """ partition_id = 0 nb_partitions = 4 actual_results = list( self.indexer._index_contents(partition_id, nb_partitions, indexed={}) ) self.assert_results_ok(partition_id, nb_partitions, actual_results) def test__index_contents_with_indexed_data(self): """Indexing contents with existing data results in less indexed data """ partition_id = 3 nb_partitions = 4 # first pass actual_results = list( self.indexer._index_contents(partition_id, nb_partitions, indexed={}), ) self.assert_results_ok(partition_id, nb_partitions, actual_results) indexed_ids = {res.id for res in actual_results} actual_results = list( self.indexer._index_contents( partition_id, nb_partitions, indexed=indexed_ids ) ) # already indexed, so nothing new assert actual_results == [] def test_generate_content_get(self): """Optimal indexing should result in indexed data """ partition_id = 0 nb_partitions = 1 actual_results = self.indexer.run( partition_id, nb_partitions, skip_existing=False ) assert actual_results["status"] == "eventful", actual_results def test_generate_content_get_no_result(self): """No result indexed returns False""" actual_results = self.indexer.run(1, 2 ** 512, incremental=False) assert actual_results == {"status": "uneventful"}