diff --git a/swh/storage/api/client.py b/swh/storage/api/client.py index 4bca5f3a..b2736eb1 100644 --- a/swh/storage/api/client.py +++ b/swh/storage/api/client.py @@ -1,261 +1,266 @@ # Copyright (C) 2015-2017 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import warnings from swh.core.api import SWHRemoteAPI from ..exc import StorageAPIError class RemoteStorage(SWHRemoteAPI): """Proxy to a remote storage API""" def __init__(self, url, timeout=None): super().__init__( api_exception=StorageAPIError, url=url, timeout=timeout) def check_config(self, *, check_write): return self.post('check_config', {'check_write': check_write}) def content_add(self, content): return self.post('content/add', {'content': content}) def content_update(self, content, keys=[]): return self.post('content/update', {'content': content, 'keys': keys}) def content_missing(self, content, key_hash='sha1'): return self.post('content/missing', {'content': content, 'key_hash': key_hash}) def content_missing_per_sha1(self, contents): return self.post('content/missing/sha1', {'contents': contents}) def content_get(self, content): return self.post('content/data', {'content': content}) def content_get_metadata(self, content): return self.post('content/metadata', {'content': content}) def content_get_range(self, start, end, limit=1000): return self.post('content/range', {'start': start, 'end': end, 'limit': limit}) def content_find(self, content): return self.post('content/present', {'content': content}) def directory_add(self, directories): return self.post('directory/add', {'directories': directories}) def directory_missing(self, directories): return self.post('directory/missing', {'directories': directories}) def directory_ls(self, directory, recursive=False): return self.get('directory/ls', {'directory': directory, 'recursive': recursive}) def revision_get(self, revisions): return self.post('revision', {'revisions': revisions}) def revision_log(self, revisions, limit=None): return self.post('revision/log', {'revisions': revisions, 'limit': limit}) def revision_shortlog(self, revisions, limit=None): return self.post('revision/shortlog', {'revisions': revisions, 'limit': limit}) def revision_add(self, revisions): return self.post('revision/add', {'revisions': revisions}) def revision_missing(self, revisions): return self.post('revision/missing', {'revisions': revisions}) def release_add(self, releases): return self.post('release/add', {'releases': releases}) def release_get(self, releases): return self.post('release', {'releases': releases}) def release_missing(self, releases): return self.post('release/missing', {'releases': releases}) def object_find_by_sha1_git(self, ids): return self.post('object/find_by_sha1_git', {'ids': ids}) def snapshot_add(self, origin, visit, snapshot): return self.post('snapshot/add', { 'origin': origin, 'visit': visit, 'snapshot': snapshot, }) def snapshot_get(self, snapshot_id): return self.post('snapshot', { 'snapshot_id': snapshot_id }) def snapshot_get_by_origin_visit(self, origin, visit): return self.post('snapshot/by_origin_visit', { 'origin': origin, 'visit': visit }) def snapshot_get_latest(self, origin, allowed_statuses=None): return self.post('snapshot/latest', { 'origin': origin, 'allowed_statuses': allowed_statuses }) def snapshot_count_branches(self, snapshot_id): return self.post('snapshot/count_branches', { 'snapshot_id': snapshot_id }) def snapshot_get_branches(self, snapshot_id, branches_from=b'', branches_count=1000, target_types=None): return self.post('snapshot/get_branches', { 'snapshot_id': snapshot_id, 'branches_from': branches_from, 'branches_count': branches_count, 'target_types': target_types }) def origin_get(self, origins=None, *, origin=None): if origin is None: if origins is None: raise TypeError('origin_get expected 1 argument') else: assert origins is None origins = origin warnings.warn("argument 'origin' of origin_get was renamed " "to 'origins' in v0.0.123.", DeprecationWarning) return self.post('origin/get', {'origins': origins}) def origin_search(self, url_pattern, offset=0, limit=50, regexp=False, with_visit=False): return self.post('origin/search', {'url_pattern': url_pattern, 'offset': offset, 'limit': limit, 'regexp': regexp, 'with_visit': with_visit}) + def origin_count(self, url_pattern, regexp=False, with_visit=False): + return self.post('origin/count', {'url_pattern': url_pattern, + 'regexp': regexp, + 'with_visit': with_visit}) + def origin_get_range(self, origin_from=1, origin_count=100): return self.post('origin/get_range', {'origin_from': origin_from, 'origin_count': origin_count}) def origin_add(self, origins): return self.post('origin/add_multi', {'origins': origins}) def origin_add_one(self, origin): return self.post('origin/add', {'origin': origin}) def origin_visit_add(self, origin, date, *, ts=None): if ts is None: if date is None: raise TypeError('origin_visit_add expected 2 arguments.') else: assert date is None warnings.warn("argument 'ts' of origin_visit_add was renamed " "to 'date' in v0.0.109.", DeprecationWarning) date = ts return self.post('origin/visit/add', {'origin': origin, 'date': date}) def origin_visit_update(self, origin, visit_id, status, metadata=None): return self.post('origin/visit/update', {'origin': origin, 'visit_id': visit_id, 'status': status, 'metadata': metadata}) def origin_visit_get(self, origin, last_visit=None, limit=None): return self.post('origin/visit/get', { 'origin': origin, 'last_visit': last_visit, 'limit': limit}) def origin_visit_get_by(self, origin, visit): return self.post('origin/visit/getby', {'origin': origin, 'visit': visit}) def person_get(self, person): return self.post('person', {'person': person}) def fetch_history_start(self, origin_id): return self.post('fetch_history/start', {'origin_id': origin_id}) def fetch_history_end(self, fetch_history_id, data): return self.post('fetch_history/end', {'fetch_history_id': fetch_history_id, 'data': data}) def fetch_history_get(self, fetch_history_id): return self.get('fetch_history', {'id': fetch_history_id}) def entity_add(self, entities): return self.post('entity/add', {'entities': entities}) def entity_get(self, uuid): return self.post('entity/get', {'uuid': uuid}) def entity_get_one(self, uuid): return self.get('entity', {'uuid': uuid}) def entity_get_from_lister_metadata(self, entities): return self.post('entity/from_lister_metadata', {'entities': entities}) def stat_counters(self): return self.get('stat/counters') def directory_entry_get_by_path(self, directory, paths): return self.post('directory/path', dict(directory=directory, paths=paths)) def tool_add(self, tools): return self.post('tool/add', {'tools': tools}) def tool_get(self, tool): return self.post('tool/data', {'tool': tool}) def origin_metadata_add(self, origin_id, ts, provider, tool, metadata): return self.post('origin/metadata/add', {'origin_id': origin_id, 'ts': ts, 'provider': provider, 'tool': tool, 'metadata': metadata}) def origin_metadata_get_by(self, origin_id, provider_type=None): return self.post('origin/metadata/get', { 'origin_id': origin_id, 'provider_type': provider_type }) def metadata_provider_add(self, provider_name, provider_type, provider_url, metadata): return self.post('provider/add', {'provider_name': provider_name, 'provider_type': provider_type, 'provider_url': provider_url, 'metadata': metadata}) def metadata_provider_get(self, provider_id): return self.post('provider/get', {'provider_id': provider_id}) def metadata_provider_get_by(self, provider): return self.post('provider/getby', {'provider': provider}) def diff_directories(self, from_dir, to_dir, track_renaming=False): return self.post('algos/diff_directories', {'from_dir': from_dir, 'to_dir': to_dir, 'track_renaming': track_renaming}) def diff_revisions(self, from_rev, to_rev, track_renaming=False): return self.post('algos/diff_revisions', {'from_rev': from_rev, 'to_rev': to_rev, 'track_renaming': track_renaming}) def diff_revision(self, revision, track_renaming=False): return self.post('algos/diff_revision', {'revision': revision, 'track_renaming': track_renaming}) diff --git a/swh/storage/api/server.py b/swh/storage/api/server.py index 996d2ae1..3ab7b7ed 100644 --- a/swh/storage/api/server.py +++ b/swh/storage/api/server.py @@ -1,404 +1,409 @@ # Copyright (C) 2015-2017 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import json import logging import click from flask import request from swh.core import config from swh.storage import get_storage as get_swhstorage from swh.core.api import (SWHServerAPIApp, decode_request, error_handler, encode_data_server as encode_data) DEFAULT_CONFIG_PATH = 'storage/storage' DEFAULT_CONFIG = { 'storage': ('dict', { 'cls': 'local', 'args': { 'db': 'dbname=softwareheritage-dev', 'objstorage': { 'cls': 'pathslicing', 'args': { 'root': '/srv/softwareheritage/objects', 'slicing': '0:2/2:4/4:6', }, }, }, }) } app = SWHServerAPIApp(__name__) storage = None @app.errorhandler(Exception) def my_error_handler(exception): return error_handler(exception, encode_data) def get_storage(): global storage if not storage: storage = get_swhstorage(**app.config['storage']) return storage @app.route('/') def index(): return ''' Software Heritage storage server

You have reached the Software Heritage storage server.
See its documentation and API for more information

''' @app.route('/check_config', methods=['POST']) def check_config(): return encode_data(get_storage().check_config(**decode_request(request))) @app.route('/content/missing', methods=['POST']) def content_missing(): return encode_data(get_storage().content_missing( **decode_request(request))) @app.route('/content/missing/sha1', methods=['POST']) def content_missing_per_sha1(): return encode_data(get_storage().content_missing_per_sha1( **decode_request(request))) @app.route('/content/present', methods=['POST']) def content_find(): return encode_data(get_storage().content_find(**decode_request(request))) @app.route('/content/add', methods=['POST']) def content_add(): return encode_data(get_storage().content_add(**decode_request(request))) @app.route('/content/update', methods=['POST']) def content_update(): return encode_data(get_storage().content_update(**decode_request(request))) @app.route('/content/data', methods=['POST']) def content_get(): return encode_data(get_storage().content_get(**decode_request(request))) @app.route('/content/metadata', methods=['POST']) def content_get_metadata(): return encode_data(get_storage().content_get_metadata( **decode_request(request))) @app.route('/content/range', methods=['POST']) def content_get_range(): return encode_data(get_storage().content_get_range( **decode_request(request))) @app.route('/directory/missing', methods=['POST']) def directory_missing(): return encode_data(get_storage().directory_missing( **decode_request(request))) @app.route('/directory/add', methods=['POST']) def directory_add(): return encode_data(get_storage().directory_add(**decode_request(request))) @app.route('/directory/path', methods=['POST']) def directory_entry_get_by_path(): return encode_data(get_storage().directory_entry_get_by_path( **decode_request(request))) @app.route('/directory/ls', methods=['GET']) def directory_ls(): dir = request.args['directory'].encode('utf-8', 'surrogateescape') rec = json.loads(request.args.get('recursive', 'False').lower()) return encode_data(get_storage().directory_ls(dir, recursive=rec)) @app.route('/revision/add', methods=['POST']) def revision_add(): return encode_data(get_storage().revision_add(**decode_request(request))) @app.route('/revision', methods=['POST']) def revision_get(): return encode_data(get_storage().revision_get(**decode_request(request))) @app.route('/revision/log', methods=['POST']) def revision_log(): return encode_data(get_storage().revision_log(**decode_request(request))) @app.route('/revision/shortlog', methods=['POST']) def revision_shortlog(): return encode_data(get_storage().revision_shortlog( **decode_request(request))) @app.route('/revision/missing', methods=['POST']) def revision_missing(): return encode_data(get_storage().revision_missing( **decode_request(request))) @app.route('/release/add', methods=['POST']) def release_add(): return encode_data(get_storage().release_add(**decode_request(request))) @app.route('/release', methods=['POST']) def release_get(): return encode_data(get_storage().release_get(**decode_request(request))) @app.route('/release/missing', methods=['POST']) def release_missing(): return encode_data(get_storage().release_missing( **decode_request(request))) @app.route('/object/find_by_sha1_git', methods=['POST']) def object_find_by_sha1_git(): return encode_data(get_storage().object_find_by_sha1_git( **decode_request(request))) @app.route('/snapshot/add', methods=['POST']) def snapshot_add(): return encode_data(get_storage().snapshot_add(**decode_request(request))) @app.route('/snapshot', methods=['POST']) def snapshot_get(): return encode_data(get_storage().snapshot_get(**decode_request(request))) @app.route('/snapshot/by_origin_visit', methods=['POST']) def snapshot_get_by_origin_visit(): return encode_data(get_storage().snapshot_get_by_origin_visit( **decode_request(request))) @app.route('/snapshot/latest', methods=['POST']) def snapshot_get_latest(): return encode_data(get_storage().snapshot_get_latest( **decode_request(request))) @app.route('/snapshot/count_branches', methods=['POST']) def snapshot_count_branches(): return encode_data(get_storage().snapshot_count_branches( **decode_request(request))) @app.route('/snapshot/get_branches', methods=['POST']) def snapshot_get_branches(): return encode_data(get_storage().snapshot_get_branches( **decode_request(request))) @app.route('/origin/get', methods=['POST']) def origin_get(): return encode_data(get_storage().origin_get(**decode_request(request))) @app.route('/origin/get_range', methods=['POST']) def origin_get_range(): return encode_data(get_storage().origin_get_range( **decode_request(request))) @app.route('/origin/search', methods=['POST']) def origin_search(): return encode_data(get_storage().origin_search(**decode_request(request))) +@app.route('/origin/count', methods=['POST']) +def origin_count(): + return encode_data(get_storage().origin_count(**decode_request(request))) + + @app.route('/origin/add_multi', methods=['POST']) def origin_add(): return encode_data(get_storage().origin_add(**decode_request(request))) @app.route('/origin/add', methods=['POST']) def origin_add_one(): return encode_data(get_storage().origin_add_one(**decode_request(request))) @app.route('/origin/visit/get', methods=['POST']) def origin_visit_get(): return encode_data(get_storage().origin_visit_get( **decode_request(request))) @app.route('/origin/visit/getby', methods=['POST']) def origin_visit_get_by(): return encode_data( get_storage().origin_visit_get_by(**decode_request(request))) @app.route('/origin/visit/add', methods=['POST']) def origin_visit_add(): return encode_data(get_storage().origin_visit_add( **decode_request(request))) @app.route('/origin/visit/update', methods=['POST']) def origin_visit_update(): return encode_data(get_storage().origin_visit_update( **decode_request(request))) @app.route('/person', methods=['POST']) def person_get(): return encode_data(get_storage().person_get(**decode_request(request))) @app.route('/fetch_history', methods=['GET']) def fetch_history_get(): return encode_data(get_storage().fetch_history_get(request.args['id'])) @app.route('/fetch_history/start', methods=['POST']) def fetch_history_start(): return encode_data( get_storage().fetch_history_start(**decode_request(request))) @app.route('/fetch_history/end', methods=['POST']) def fetch_history_end(): return encode_data( get_storage().fetch_history_end(**decode_request(request))) @app.route('/entity/add', methods=['POST']) def entity_add(): return encode_data( get_storage().entity_add(**decode_request(request))) @app.route('/entity/get', methods=['POST']) def entity_get(): return encode_data( get_storage().entity_get(**decode_request(request))) @app.route('/entity', methods=['GET']) def entity_get_one(): return encode_data(get_storage().entity_get_one(request.args['uuid'])) @app.route('/entity/from_lister_metadata', methods=['POST']) def entity_from_lister_metadata(): return encode_data(get_storage().entity_get_from_lister_metadata( **decode_request(request))) @app.route('/tool/data', methods=['POST']) def tool_get(): return encode_data(get_storage().tool_get( **decode_request(request))) @app.route('/tool/add', methods=['POST']) def tool_add(): return encode_data(get_storage().tool_add( **decode_request(request))) @app.route('/origin/metadata/add', methods=['POST']) def origin_metadata_add(): return encode_data(get_storage().origin_metadata_add(**decode_request( request))) @app.route('/origin/metadata/get', methods=['POST']) def origin_metadata_get_by(): return encode_data(get_storage().origin_metadata_get_by(**decode_request( request))) @app.route('/provider/add', methods=['POST']) def metadata_provider_add(): return encode_data(get_storage().metadata_provider_add(**decode_request( request))) @app.route('/provider/get', methods=['POST']) def metadata_provider_get(): return encode_data(get_storage().metadata_provider_get(**decode_request( request))) @app.route('/provider/getby', methods=['POST']) def metadata_provider_get_by(): return encode_data(get_storage().metadata_provider_get_by(**decode_request( request))) @app.route('/stat/counters', methods=['GET']) def stat_counters(): return encode_data(get_storage().stat_counters()) @app.route('/algos/diff_directories', methods=['POST']) def diff_directories(): return encode_data(get_storage().diff_directories( **decode_request(request))) @app.route('/algos/diff_revisions', methods=['POST']) def diff_revisions(): return encode_data(get_storage().diff_revisions(**decode_request(request))) @app.route('/algos/diff_revision', methods=['POST']) def diff_revision(): return encode_data(get_storage().diff_revision(**decode_request(request))) def run_from_webserver(environ, start_response, config_path=DEFAULT_CONFIG_PATH): """Run the WSGI app from the webserver, loading the configuration.""" cfg = config.load_named_config(config_path, DEFAULT_CONFIG) app.config.update(cfg) handler = logging.StreamHandler() app.logger.addHandler(handler) return app(environ, start_response) @click.command() @click.argument('config-path', required=1) @click.option('--host', default='0.0.0.0', help="Host to run the server") @click.option('--port', default=5002, 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 launch(config_path, host, port, debug): app.config.update(config.read(config_path, DEFAULT_CONFIG)) app.run(host, port=int(port), debug=bool(debug)) if __name__ == '__main__': launch() diff --git a/swh/storage/db.py b/swh/storage/db.py index e4e65704..91d5249b 100644 --- a/swh/storage/db.py +++ b/swh/storage/db.py @@ -1,833 +1,865 @@ # Copyright (C) 2015-2019 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 select from swh.core.db import BaseDb from swh.core.db.db_utils import stored_procedure, jsonize from swh.core.db.db_utils import execute_values_generator class Db(BaseDb): """Proxy to the SWH DB, with wrappers around stored procedures """ def mktemp_dir_entry(self, entry_type, cur=None): self._cursor(cur).execute('SELECT swh_mktemp_dir_entry(%s)', (('directory_entry_%s' % entry_type),)) @stored_procedure('swh_mktemp_revision') def mktemp_revision(self, cur=None): pass @stored_procedure('swh_mktemp_release') def mktemp_release(self, cur=None): pass @stored_procedure('swh_mktemp_snapshot_branch') def mktemp_snapshot_branch(self, cur=None): pass def register_listener(self, notify_queue, cur=None): """Register a listener for NOTIFY queue `notify_queue`""" self._cursor(cur).execute("LISTEN %s" % notify_queue) def listen_notifies(self, timeout): """Listen to notifications for `timeout` seconds""" if select.select([self.conn], [], [], timeout) == ([], [], []): return else: self.conn.poll() while self.conn.notifies: yield self.conn.notifies.pop(0) @stored_procedure('swh_content_add') def content_add_from_temp(self, cur=None): pass @stored_procedure('swh_directory_add') def directory_add_from_temp(self, cur=None): pass @stored_procedure('swh_skipped_content_add') def skipped_content_add_from_temp(self, cur=None): pass @stored_procedure('swh_revision_add') def revision_add_from_temp(self, cur=None): pass @stored_procedure('swh_release_add') def release_add_from_temp(self, cur=None): pass def content_update_from_temp(self, keys_to_update, cur=None): cur = self._cursor(cur) cur.execute("""select swh_content_update(ARRAY[%s] :: text[])""" % keys_to_update) content_get_metadata_keys = [ 'sha1', 'sha1_git', 'sha256', 'blake2s256', 'length', 'status'] skipped_content_keys = [ 'sha1', 'sha1_git', 'sha256', 'blake2s256', 'length', 'reason', 'status', 'origin'] def content_get_metadata_from_sha1s(self, sha1s, cur=None): cur = self._cursor(cur) yield from execute_values_generator( cur, """ select t.sha1, %s from (values %%s) as t (sha1) left join content using (sha1) """ % ', '.join(self.content_get_metadata_keys[1:]), ((sha1,) for sha1 in sha1s), ) def content_get_range(self, start, end, limit=None, cur=None): """Retrieve contents within range [start, end]. """ cur = self._cursor(cur) query = """select %s from content where %%s <= sha1 and sha1 <= %%s order by sha1 limit %%s""" % ', '.join(self.content_get_metadata_keys) cur.execute(query, (start, end, limit)) yield from cur content_hash_keys = ['sha1', 'sha1_git', 'sha256', 'blake2s256'] def content_missing_from_list(self, contents, cur=None): cur = self._cursor(cur) keys = ', '.join(self.content_hash_keys) equality = ' AND '.join( ('t.%s = c.%s' % (key, key)) for key in self.content_hash_keys ) yield from execute_values_generator( cur, """ SELECT %s FROM (VALUES %%s) as t(%s) WHERE NOT EXISTS ( SELECT 1 FROM content c WHERE %s ) """ % (keys, keys, equality), (tuple(c[key] for key in self.content_hash_keys) for c in contents) ) def content_missing_per_sha1(self, sha1s, cur=None): cur = self._cursor(cur) yield from execute_values_generator(cur, """ SELECT t.sha1 FROM (VALUES %s) AS t(sha1) WHERE NOT EXISTS ( SELECT 1 FROM content c WHERE c.sha1 = t.sha1 )""", ((sha1,) for sha1 in sha1s)) def skipped_content_missing_from_temp(self, cur=None): cur = self._cursor(cur) cur.execute("""SELECT sha1, sha1_git, sha256, blake2s256 FROM swh_skipped_content_missing()""") yield from cur def snapshot_exists(self, snapshot_id, cur=None): """Check whether a snapshot with the given id exists""" cur = self._cursor(cur) cur.execute("""SELECT 1 FROM snapshot where id=%s""", (snapshot_id,)) return bool(cur.fetchone()) def snapshot_add(self, origin, visit, snapshot_id, cur=None): """Add a snapshot for origin/visit from the temporary table""" cur = self._cursor(cur) cur.execute("""SELECT swh_snapshot_add(%s, %s, %s)""", (origin, visit, snapshot_id)) snapshot_count_cols = ['target_type', 'count'] def snapshot_count_branches(self, snapshot_id, cur=None): cur = self._cursor(cur) query = """\ SELECT %s FROM swh_snapshot_count_branches(%%s) """ % ', '.join(self.snapshot_count_cols) cur.execute(query, (snapshot_id,)) yield from cur snapshot_get_cols = ['snapshot_id', 'name', 'target', 'target_type'] def snapshot_get_by_id(self, snapshot_id, branches_from=b'', branches_count=None, target_types=None, cur=None): cur = self._cursor(cur) query = """\ SELECT %s FROM swh_snapshot_get_by_id(%%s, %%s, %%s, %%s :: snapshot_target[]) """ % ', '.join(self.snapshot_get_cols) cur.execute(query, (snapshot_id, branches_from, branches_count, target_types)) yield from cur def snapshot_get_by_origin_visit(self, origin_id, visit_id, cur=None): cur = self._cursor(cur) query = """\ SELECT swh_snapshot_get_by_origin_visit(%s, %s) """ cur.execute(query, (origin_id, visit_id)) ret = cur.fetchone() if ret: return ret[0] content_find_cols = ['sha1', 'sha1_git', 'sha256', 'blake2s256', 'length', 'ctime', 'status'] def content_find(self, sha1=None, sha1_git=None, sha256=None, blake2s256=None, cur=None): """Find the content optionally on a combination of the following checksums sha1, sha1_git, sha256 or blake2s256. Args: sha1: sha1 content git_sha1: the sha1 computed `a la git` sha1 of the content sha256: sha256 content blake2s256: blake2s256 content Returns: The tuple (sha1, sha1_git, sha256, blake2s256) if found or None. """ cur = self._cursor(cur) cur.execute("""SELECT %s FROM swh_content_find(%%s, %%s, %%s, %%s) LIMIT 1""" % ','.join(self.content_find_cols), (sha1, sha1_git, sha256, blake2s256)) content = cur.fetchone() if set(content) == {None}: return None else: return content def directory_missing_from_list(self, directories, cur=None): cur = self._cursor(cur) yield from execute_values_generator( cur, """ SELECT id FROM (VALUES %s) as t(id) WHERE NOT EXISTS ( SELECT 1 FROM directory d WHERE d.id = t.id ) """, ((id,) for id in directories)) directory_ls_cols = ['dir_id', 'type', 'target', 'name', 'perms', 'status', 'sha1', 'sha1_git', 'sha256', 'length'] def directory_walk_one(self, directory, cur=None): cur = self._cursor(cur) cols = ', '.join(self.directory_ls_cols) query = 'SELECT %s FROM swh_directory_walk_one(%%s)' % cols cur.execute(query, (directory,)) yield from cur def directory_walk(self, directory, cur=None): cur = self._cursor(cur) cols = ', '.join(self.directory_ls_cols) query = 'SELECT %s FROM swh_directory_walk(%%s)' % cols cur.execute(query, (directory,)) yield from cur def directory_entry_get_by_path(self, directory, paths, cur=None): """Retrieve a directory entry by path. """ cur = self._cursor(cur) cols = ', '.join(self.directory_ls_cols) query = ( 'SELECT %s FROM swh_find_directory_entry_by_path(%%s, %%s)' % cols) cur.execute(query, (directory, paths)) data = cur.fetchone() if set(data) == {None}: return None return data def revision_missing_from_list(self, revisions, cur=None): cur = self._cursor(cur) yield from execute_values_generator( cur, """ SELECT id FROM (VALUES %s) as t(id) WHERE NOT EXISTS ( SELECT 1 FROM revision r WHERE r.id = t.id ) """, ((id,) for id in revisions)) revision_add_cols = [ 'id', 'date', 'date_offset', 'date_neg_utc_offset', 'committer_date', 'committer_date_offset', 'committer_date_neg_utc_offset', 'type', 'directory', 'message', 'author_fullname', 'author_name', 'author_email', 'committer_fullname', 'committer_name', 'committer_email', 'metadata', 'synthetic', ] revision_get_cols = revision_add_cols + [ 'author_id', 'committer_id', 'parents'] def origin_visit_add(self, origin, ts, cur=None): """Add a new origin_visit for origin origin at timestamp ts with status 'ongoing'. Args: origin: origin concerned by the visit ts: the date of the visit Returns: The new visit index step for that origin """ cur = self._cursor(cur) self._cursor(cur).execute('SELECT swh_origin_visit_add(%s, %s)', (origin, ts)) return cur.fetchone()[0] def origin_visit_update(self, origin, visit_id, status, metadata, cur=None): """Update origin_visit's status.""" cur = self._cursor(cur) update = """UPDATE origin_visit SET status=%s, metadata=%s WHERE origin=%s AND visit=%s""" cur.execute(update, (status, jsonize(metadata), origin, visit_id)) origin_visit_get_cols = ['origin', 'visit', 'date', 'status', 'metadata', 'snapshot'] def origin_visit_get_all(self, origin_id, last_visit=None, limit=None, cur=None): """Retrieve all visits for origin with id origin_id. Args: origin_id: The occurrence's origin Yields: The occurrence's history visits """ cur = self._cursor(cur) if last_visit: extra_condition = 'and visit > %s' args = (origin_id, last_visit, limit) else: extra_condition = '' args = (origin_id, limit) query = """\ SELECT %s, (select id from snapshot where object_id = snapshot_id) as snapshot FROM origin_visit WHERE origin=%%s %s order by visit asc limit %%s""" % ( ', '.join(self.origin_visit_get_cols[:-1]), extra_condition ) cur.execute(query, args) yield from cur def origin_visit_get(self, origin_id, visit_id, cur=None): """Retrieve information on visit visit_id of origin origin_id. Args: origin_id: the origin concerned visit_id: The visit step for that origin Returns: The origin_visit information """ cur = self._cursor(cur) query = """\ SELECT %s, (select id from snapshot where object_id = snapshot_id) as snapshot FROM origin_visit WHERE origin = %%s AND visit = %%s """ % (', '.join(self.origin_visit_get_cols[:-1])) cur.execute(query, (origin_id, visit_id)) r = cur.fetchall() if not r: return None return r[0] def origin_visit_exists(self, origin_id, visit_id, cur=None): """Check whether an origin visit with the given ids exists""" cur = self._cursor(cur) query = "SELECT 1 FROM origin_visit where origin = %s AND visit = %s" cur.execute(query, (origin_id, visit_id)) return bool(cur.fetchone()) def origin_visit_get_latest_snapshot(self, origin_id, allowed_statuses=None, cur=None): """Retrieve the most recent origin_visit which references a snapshot Args: origin_id: the origin concerned allowed_statuses: the visit statuses allowed for the returned visit Returns: The origin_visit information, or None if no visit matches. """ cur = self._cursor(cur) extra_clause = "" if allowed_statuses: extra_clause = cur.mogrify("AND status IN %s", (tuple(allowed_statuses),)).decode() query = """\ SELECT %s, (select id from snapshot where object_id = snapshot_id) as snapshot FROM origin_visit WHERE origin = %%s AND snapshot_id is not null %s ORDER BY date DESC, visit DESC LIMIT 1 """ % (', '.join(self.origin_visit_get_cols[:-1]), extra_clause) cur.execute(query, (origin_id,)) r = cur.fetchone() if not r: return None return r @staticmethod def mangle_query_key(key, main_table): if key == 'id': return 't.id' if key == 'parents': return ''' ARRAY( SELECT rh.parent_id::bytea FROM revision_history rh WHERE rh.id = t.id ORDER BY rh.parent_rank )''' if '_' not in key: return '%s.%s' % (main_table, key) head, tail = key.split('_', 1) if (head in ('author', 'committer') and tail in ('name', 'email', 'id', 'fullname')): return '%s.%s' % (head, tail) return '%s.%s' % (main_table, key) def revision_get_from_list(self, revisions, cur=None): cur = self._cursor(cur) query_keys = ', '.join( self.mangle_query_key(k, 'revision') for k in self.revision_get_cols ) yield from execute_values_generator( cur, """ SELECT %s FROM (VALUES %%s) as t(id) LEFT JOIN revision ON t.id = revision.id LEFT JOIN person author ON revision.author = author.id LEFT JOIN person committer ON revision.committer = committer.id """ % query_keys, ((id,) for id in revisions)) def revision_log(self, root_revisions, limit=None, cur=None): cur = self._cursor(cur) query = """SELECT %s FROM swh_revision_log(%%s, %%s) """ % ', '.join(self.revision_get_cols) cur.execute(query, (root_revisions, limit)) yield from cur revision_shortlog_cols = ['id', 'parents'] def revision_shortlog(self, root_revisions, limit=None, cur=None): cur = self._cursor(cur) query = """SELECT %s FROM swh_revision_list(%%s, %%s) """ % ', '.join(self.revision_shortlog_cols) cur.execute(query, (root_revisions, limit)) yield from cur def release_missing_from_list(self, releases, cur=None): cur = self._cursor(cur) yield from execute_values_generator( cur, """ SELECT id FROM (VALUES %s) as t(id) WHERE NOT EXISTS ( SELECT 1 FROM release r WHERE r.id = t.id ) """, ((id,) for id in releases)) object_find_by_sha1_git_cols = ['sha1_git', 'type', 'id', 'object_id'] def object_find_by_sha1_git(self, ids, cur=None): cur = self._cursor(cur) yield from execute_values_generator( cur, """ WITH t (id) AS (VALUES %s), known_objects as (( select id as sha1_git, 'release'::object_type as type, id, object_id from release r where exists (select 1 from t where t.id = r.id) ) union all ( select id as sha1_git, 'revision'::object_type as type, id, object_id from revision r where exists (select 1 from t where t.id = r.id) ) union all ( select id as sha1_git, 'directory'::object_type as type, id, object_id from directory d where exists (select 1 from t where t.id = d.id) ) union all ( select sha1_git as sha1_git, 'content'::object_type as type, sha1 as id, object_id from content c where exists (select 1 from t where t.id = c.sha1_git) )) select t.id as sha1_git, k.type, k.id, k.object_id from t left join known_objects k on t.id = k.sha1_git """, ((id,) for id in ids) ) def stat_counters(self, cur=None): cur = self._cursor(cur) cur.execute('SELECT * FROM swh_stat_counters()') yield from cur fetch_history_cols = ['origin', 'date', 'status', 'result', 'stdout', 'stderr', 'duration'] def create_fetch_history(self, fetch_history, cur=None): """Create a fetch_history entry with the data in fetch_history""" cur = self._cursor(cur) query = '''INSERT INTO fetch_history (%s) VALUES (%s) RETURNING id''' % ( ','.join(self.fetch_history_cols), ','.join(['%s'] * len(self.fetch_history_cols)) ) cur.execute(query, [fetch_history.get(col) for col in self.fetch_history_cols]) return cur.fetchone()[0] def get_fetch_history(self, fetch_history_id, cur=None): """Get a fetch_history entry with the given id""" cur = self._cursor(cur) query = '''SELECT %s FROM fetch_history WHERE id=%%s''' % ( ', '.join(self.fetch_history_cols), ) cur.execute(query, (fetch_history_id,)) data = cur.fetchone() if not data: return None ret = {'id': fetch_history_id} for i, col in enumerate(self.fetch_history_cols): ret[col] = data[i] return ret def update_fetch_history(self, fetch_history, cur=None): """Update the fetch_history entry from the data in fetch_history""" cur = self._cursor(cur) query = '''UPDATE fetch_history SET %s WHERE id=%%s''' % ( ','.join('%s=%%s' % col for col in self.fetch_history_cols) ) cur.execute(query, [jsonize(fetch_history.get(col)) for col in self.fetch_history_cols + ['id']]) def origin_add(self, type, url, cur=None): """Insert a new origin and return the new identifier.""" insert = """INSERT INTO origin (type, url) values (%s, %s) RETURNING id""" cur.execute(insert, (type, url)) return cur.fetchone()[0] origin_cols = ['id', 'type', 'url'] def origin_get_with(self, origins, cur=None): """Retrieve the origin id from its type and url if found.""" cur = self._cursor(cur) query = """SELECT %s FROM (VALUES %%s) as t(type, url) LEFT JOIN origin ON (t.type=origin.type AND t.url=origin.url) """ % ','.join('origin.' + col for col in self.origin_cols) yield from execute_values_generator( cur, query, origins) def origin_get(self, ids, cur=None): """Retrieve the origin per its identifier. """ cur = self._cursor(cur) query = """SELECT %s FROM (VALUES %%s) as t(id) LEFT JOIN origin ON t.id = origin.id """ % ','.join('origin.' + col for col in self.origin_cols) yield from execute_values_generator( cur, query, ((id,) for id in ids)) - def origin_search(self, url_pattern, offset=0, limit=50, + def _origin_query(self, url_pattern, count=False, offset=0, limit=50, regexp=False, with_visit=False, cur=None): - """Search for origins whose urls contain a provided string pattern - or match a provided regular expression. - The search is performed in a case insensitive way. - - Args: - url_pattern (str): the string pattern to search for in origin urls - offset (int): number of found origins to skip before returning - results - limit (int): the maximum number of found origins to return - regexp (bool): if True, consider the provided pattern as a regular - expression and returns origins whose urls match it - with_visit (bool): if True, filter out origins with no visit - + """ + Method factorizing query creation for searching and counting origins. """ cur = self._cursor(cur) - origin_cols = ','.join(self.origin_cols) + + if count: + origin_cols = 'COUNT(*)' + else: + origin_cols = ','.join(self.origin_cols) + query = """SELECT %s FROM origin WHERE """ if with_visit: query += """ EXISTS (SELECT 1 from origin_visit WHERE origin=origin.id) AND """ - query += """ - url %s %%s - ORDER BY id - OFFSET %%s LIMIT %%s""" + query += 'url %s %%s ' + if not count: + query += 'ORDER BY id OFFSET %%s LIMIT %%s' if not regexp: query = query % (origin_cols, 'ILIKE') query_params = ('%'+url_pattern+'%', offset, limit) else: query = query % (origin_cols, '~*') query_params = (url_pattern, offset, limit) + if count: + query_params = (query_params[0],) + cur.execute(query, query_params) + + def origin_search(self, url_pattern, offset=0, limit=50, + regexp=False, with_visit=False, cur=None): + """Search for origins whose urls contain a provided string pattern + or match a provided regular expression. + The search is performed in a case insensitive way. + + Args: + url_pattern (str): the string pattern to search for in origin urls + offset (int): number of found origins to skip before returning + results + limit (int): the maximum number of found origins to return + regexp (bool): if True, consider the provided pattern as a regular + expression and returns origins whose urls match it + with_visit (bool): if True, filter out origins with no visit + + """ + self._origin_query(url_pattern, offset=offset, limit=limit, + regexp=regexp, with_visit=with_visit, cur=cur) yield from cur + def origin_count(self, url_pattern, regexp=False, + with_visit=False, cur=None): + """Count origins whose urls contain a provided string pattern + or match a provided regular expression. + The pattern search in origin urls is performed in a case insensitive + way. + + Args: + url_pattern (str): the string pattern to search for in origin urls + regexp (bool): if True, consider the provided pattern as a regular + expression and returns origins whose urls match it + with_visit (bool): if True, filter out origins with no visit + """ + self._origin_query(url_pattern, count=True, + regexp=regexp, with_visit=with_visit, cur=cur) + return cur.fetchone()[0] + person_cols = ['fullname', 'name', 'email'] person_get_cols = person_cols + ['id'] def origin_get_range(self, origin_from=1, origin_count=100, cur=None): """Retrieve ``origin_count`` origins whose ids are greater or equal than ``origin_from``. Origins are sorted by id before retrieving them. Args: origin_from (int): the minimum id of origins to retrieve origin_count (int): the maximum number of origins to retrieve """ cur = self._cursor(cur) query = """SELECT %s FROM origin WHERE id >= %%s ORDER BY id LIMIT %%s """ % ','.join(self.origin_cols) cur.execute(query, (origin_from, origin_count)) yield from cur def person_get(self, ids, cur=None): """Retrieve the persons identified by the list of ids. """ cur = self._cursor(cur) query = """SELECT %s FROM person WHERE id IN %%s""" % ', '.join(self.person_get_cols) cur.execute(query, (tuple(ids),)) yield from cur release_add_cols = [ 'id', 'target', 'target_type', 'date', 'date_offset', 'date_neg_utc_offset', 'name', 'comment', 'synthetic', 'author_fullname', 'author_name', 'author_email', ] release_get_cols = release_add_cols + ['author_id'] def release_get_from_list(self, releases, cur=None): cur = self._cursor(cur) query_keys = ', '.join( self.mangle_query_key(k, 'release') for k in self.release_get_cols ) yield from execute_values_generator( cur, """ SELECT %s FROM (VALUES %%s) as t(id) LEFT JOIN release ON t.id = release.id LEFT JOIN person author ON release.author = author.id """ % query_keys, ((id,) for id in releases)) def origin_metadata_add(self, origin, ts, provider, tool, metadata, cur=None): """ Add an origin_metadata for the origin at ts with provider, tool and metadata. Args: origin (int): the origin's id for which the metadata is added ts (datetime): time when the metadata was found provider (int): the metadata provider identifier tool (int): the tool's identifier used to extract metadata metadata (jsonb): the metadata retrieved at the time and location Returns: id (int): the origin_metadata unique id """ cur = self._cursor(cur) insert = """INSERT INTO origin_metadata (origin_id, discovery_date, provider_id, tool_id, metadata) values (%s, %s, %s, %s, %s) RETURNING id""" cur.execute(insert, (origin, ts, provider, tool, jsonize(metadata))) return cur.fetchone()[0] origin_metadata_get_cols = ['origin_id', 'discovery_date', 'tool_id', 'metadata', 'provider_id', 'provider_name', 'provider_type', 'provider_url'] def origin_metadata_get_by(self, origin_id, provider_type=None, cur=None): """Retrieve all origin_metadata entries for one origin_id """ cur = self._cursor(cur) if not provider_type: query = '''SELECT %s FROM swh_origin_metadata_get_by_origin( %%s)''' % (','.join( self.origin_metadata_get_cols)) cur.execute(query, (origin_id, )) else: query = '''SELECT %s FROM swh_origin_metadata_get_by_provider_type( %%s, %%s)''' % (','.join( self.origin_metadata_get_cols)) cur.execute(query, (origin_id, provider_type)) yield from cur tool_cols = ['id', 'name', 'version', 'configuration'] @stored_procedure('swh_mktemp_tool') def mktemp_tool(self, cur=None): pass def tool_add_from_temp(self, cur=None): cur = self._cursor(cur) cur.execute("SELECT %s from swh_tool_add()" % ( ','.join(self.tool_cols), )) yield from cur def tool_get(self, name, version, configuration, cur=None): cur = self._cursor(cur) cur.execute('''select %s from tool where name=%%s and version=%%s and configuration=%%s''' % ( ','.join(self.tool_cols)), (name, version, configuration)) return cur.fetchone() metadata_provider_cols = ['id', 'provider_name', 'provider_type', 'provider_url', 'metadata'] def metadata_provider_add(self, provider_name, provider_type, provider_url, metadata, cur=None): """Insert a new provider and return the new identifier.""" cur = self._cursor(cur) insert = """INSERT INTO metadata_provider (provider_name, provider_type, provider_url, metadata) values (%s, %s, %s, %s) RETURNING id""" cur.execute(insert, (provider_name, provider_type, provider_url, jsonize(metadata))) return cur.fetchone()[0] def metadata_provider_get(self, provider_id, cur=None): cur = self._cursor(cur) cur.execute('''select %s from metadata_provider where id=%%s ''' % ( ','.join(self.metadata_provider_cols)), (provider_id, )) return cur.fetchone() def metadata_provider_get_by(self, provider_name, provider_url, cur=None): cur = self._cursor(cur) cur.execute('''select %s from metadata_provider where provider_name=%%s and provider_url=%%s''' % ( ','.join(self.metadata_provider_cols)), (provider_name, provider_url)) return cur.fetchone() diff --git a/swh/storage/in_memory.py b/swh/storage/in_memory.py index 1ada5020..3fd755a5 100644 --- a/swh/storage/in_memory.py +++ b/swh/storage/in_memory.py @@ -1,1314 +1,1335 @@ # Copyright (C) 2015-2018 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import re import bisect import dateutil import collections from collections import defaultdict import copy import datetime import itertools import random import warnings from swh.model.hashutil import DEFAULT_ALGORITHMS from swh.model.identifiers import normalize_timestamp from swh.objstorage import get_objstorage from swh.objstorage.exc import ObjNotFoundError # Max block size of contents to return BULK_BLOCK_CONTENT_LEN_MAX = 10000 def now(): return datetime.datetime.now(tz=datetime.timezone.utc) class Storage: def __init__(self): self._contents = {} self._content_indexes = defaultdict(lambda: defaultdict(set)) self._directories = {} self._revisions = {} self._releases = {} self._snapshots = {} self._origins = [] self._origin_visits = [] self._persons = [] self._origin_metadata = defaultdict(list) self._tools = {} self._metadata_providers = {} self._objects = defaultdict(list) # ideally we would want a skip list for both fast inserts and searches self._sorted_sha1s = [] self.objstorage = get_objstorage('memory', {}) def check_config(self, *, check_write): """Check that the storage is configured and ready to go.""" return True def content_add(self, contents): """Add content blobs to the storage Args: content (iterable): iterable of dictionaries representing individual pieces of content to add. Each dictionary has the following keys: - data (bytes): the actual content - length (int): content length (default: -1) - one key for each checksum algorithm in :data:`swh.model.hashutil.DEFAULT_ALGORITHMS`, mapped to the corresponding checksum - status (str): one of visible, hidden, absent - reason (str): if status = absent, the reason why - origin (int): if status = absent, the origin we saw the content in """ for content in contents: key = self._content_key(content) if key in self._contents: continue for algorithm in DEFAULT_ALGORITHMS: if content[algorithm] in self._content_indexes[algorithm]: from . import HashCollision raise HashCollision(algorithm, content[algorithm], key) for algorithm in DEFAULT_ALGORITHMS: self._content_indexes[algorithm][content[algorithm]].add(key) self._objects[content['sha1_git']].append( ('content', content['sha1'])) self._contents[key] = copy.deepcopy(content) self._contents[key]['ctime'] = now() bisect.insort(self._sorted_sha1s, content['sha1']) if self._contents[key]['status'] == 'visible': content_data = self._contents[key].pop('data') self.objstorage.add(content_data, content['sha1']) def content_get(self, ids): """Retrieve in bulk contents and their data. This function may yield more blobs than provided sha1 identifiers, in case they collide. Args: content: iterables of sha1 Yields: Dict[str, bytes]: Generates streams of contents as dict with their raw data: - sha1 (bytes): content id - data (bytes): content's raw data Raises: ValueError in case of too much contents are required. cf. BULK_BLOCK_CONTENT_LEN_MAX """ # FIXME: Make this method support slicing the `data`. if len(ids) > BULK_BLOCK_CONTENT_LEN_MAX: raise ValueError( "Sending at most %s contents." % BULK_BLOCK_CONTENT_LEN_MAX) for obj_id in ids: try: data = self.objstorage.get(obj_id) except ObjNotFoundError: yield None continue yield {'sha1': obj_id, 'data': data} def content_get_range(self, start, end, limit=1000, db=None, cur=None): """Retrieve contents within range [start, end] bound by limit. Note that this function may return more than one blob per hash. The limit is enforced with multiplicity (ie. two blobs with the same hash will count twice toward the limit). Args: **start** (bytes): Starting identifier range (expected smaller than end) **end** (bytes): Ending identifier range (expected larger than start) **limit** (int): Limit result (default to 1000) Returns: a dict with keys: - contents [dict]: iterable of contents in between the range. - next (bytes): There remains content in the range starting from this next sha1 """ if limit is None: raise ValueError('Development error: limit should not be None') from_index = bisect.bisect_left(self._sorted_sha1s, start) sha1s = itertools.islice(self._sorted_sha1s, from_index, None) sha1s = ((sha1, content_key) for sha1 in sha1s for content_key in self._content_indexes['sha1'][sha1]) matched = [] next_content = None for sha1, key in sha1s: if sha1 > end: break if len(matched) >= limit: next_content = sha1 break matched.append({ **self._contents[key], }) return { 'contents': matched, 'next': next_content, } def content_get_metadata(self, sha1s): """Retrieve content metadata in bulk Args: content: iterable of content identifiers (sha1) Returns: an iterable with content metadata corresponding to the given ids """ # FIXME: the return value should be a mapping from search key to found # content*s* for sha1 in sha1s: if sha1 in self._content_indexes['sha1']: objs = self._content_indexes['sha1'][sha1] # FIXME: rather than selecting one of the objects with that # hash, we should return all of them. See: # https://forge.softwareheritage.org/D645?id=1994#inline-3389 key = random.sample(objs, 1)[0] data = copy.deepcopy(self._contents[key]) data.pop('ctime') yield data else: # FIXME: should really be None yield { 'sha1': sha1, 'sha1_git': None, 'sha256': None, 'blake2s256': None, 'length': None, 'status': None, } def content_find(self, content): if not set(content).intersection(DEFAULT_ALGORITHMS): raise ValueError('content keys must contain at least one of: ' '%s' % ', '.join(sorted(DEFAULT_ALGORITHMS))) found = [] for algo in DEFAULT_ALGORITHMS: hash = content.get(algo) if hash and hash in self._content_indexes[algo]: found.append(self._content_indexes[algo][hash]) if not found: return keys = list(set.intersection(*found)) # FIXME: should really be a list of all the objects found return copy.deepcopy(self._contents[keys[0]]) def content_missing(self, contents, key_hash='sha1'): """List content missing from storage Args: contents ([dict]): iterable of dictionaries whose keys are either 'length' or an item of :data:`swh.model.hashutil.ALGORITHMS`; mapped to the corresponding checksum (or length). key_hash (str): name of the column to use as hash id result (default: 'sha1') Returns: iterable ([bytes]): missing content ids (as per the key_hash column) """ for content in contents: for (algo, hash_) in content.items(): if algo not in DEFAULT_ALGORITHMS: continue if hash_ not in self._content_indexes.get(algo, []): yield content[key_hash] break else: # content_find cannot return None here, because we checked # above that there is a content with matching hashes. if self.content_find(content)['status'] == 'missing': yield content[key_hash] def content_missing_per_sha1(self, contents): """List content missing from storage based only on sha1. Args: contents: Iterable of sha1 to check for absence. Returns: iterable: missing ids Raises: TODO: an exception when we get a hash collision. """ for content in contents: if content not in self._content_indexes['sha1']: yield content def directory_add(self, directories): """Add directories to the storage Args: directories (iterable): iterable of dictionaries representing the individual directories to add. Each dict has the following keys: - id (sha1_git): the id of the directory to add - entries (list): list of dicts for each entry in the directory. Each dict has the following keys: - name (bytes) - type (one of 'file', 'dir', 'rev'): type of the directory entry (file, directory, revision) - target (sha1_git): id of the object pointed at by the directory entry - perms (int): entry permissions """ for directory in directories: if directory['id'] not in self._directories: self._directories[directory['id']] = copy.deepcopy(directory) self._objects[directory['id']].append( ('directory', directory['id'])) def directory_missing(self, directory_ids): """List directories missing from storage Args: directories (iterable): an iterable of directory ids Yields: missing directory ids """ for id in directory_ids: if id not in self._directories: yield id def _join_dentry_to_content(self, dentry): keys = ( 'status', 'sha1', 'sha1_git', 'sha256', 'length', ) ret = dict.fromkeys(keys) ret.update(dentry) if ret['type'] == 'file': content = self.content_find({'sha1_git': ret['target']}) if content: for key in keys: ret[key] = content[key] return ret def _directory_ls(self, directory_id, recursive, prefix=b''): if directory_id in self._directories: for entry in self._directories[directory_id]['entries']: ret = self._join_dentry_to_content(entry) ret['name'] = prefix + ret['name'] ret['dir_id'] = directory_id yield ret if recursive and ret['type'] == 'dir': yield from self._directory_ls( ret['target'], True, prefix + ret['name'] + b'/') def directory_ls(self, directory_id, recursive=False): """Get entries for one directory. Args: - directory: the directory to list entries from. - recursive: if flag on, this list recursively from this directory. Returns: List of entries for such directory. If `recursive=True`, names in the path of a dir/file not at the root are concatenated with a slash (`/`). """ yield from self._directory_ls(directory_id, recursive) def directory_entry_get_by_path(self, directory, paths): """Get the directory entry (either file or dir) from directory with path. Args: - directory: sha1 of the top level directory - paths: path to lookup from the top level directory. From left (top) to right (bottom). Returns: The corresponding directory entry if found, None otherwise. """ if not paths: return contents = list(self.directory_ls(directory)) if not contents: return def _get_entry(entries, name): for entry in entries: if entry['name'] == name: return entry first_item = _get_entry(contents, paths[0]) if len(paths) == 1: return first_item if not first_item or first_item['type'] != 'dir': return return self.directory_entry_get_by_path( first_item['target'], paths[1:]) def revision_add(self, revisions): """Add revisions to the storage Args: revisions (Iterable[dict]): iterable of dictionaries representing the individual revisions to add. Each dict has the following keys: - **id** (:class:`sha1_git`): id of the revision to add - **date** (:class:`dict`): date the revision was written - **committer_date** (:class:`dict`): date the revision got added to the origin - **type** (one of 'git', 'tar'): type of the revision added - **directory** (:class:`sha1_git`): the directory the revision points at - **message** (:class:`bytes`): the message associated with the revision - **author** (:class:`Dict[str, bytes]`): dictionary with keys: name, fullname, email - **committer** (:class:`Dict[str, bytes]`): dictionary with keys: name, fullname, email - **metadata** (:class:`jsonb`): extra information as dictionary - **synthetic** (:class:`bool`): revision's nature (tarball, directory creates synthetic revision`) - **parents** (:class:`list[sha1_git]`): the parents of this revision date dictionaries have the form defined in :mod:`swh.model`. """ for revision in revisions: if revision['id'] not in self._revisions: self._revisions[revision['id']] = rev = copy.deepcopy(revision) self._person_add(rev['committer']) self._person_add(rev['author']) rev['date'] = normalize_timestamp(rev.get('date')) rev['committer_date'] = normalize_timestamp( rev.get('committer_date')) self._objects[revision['id']].append( ('revision', revision['id'])) def revision_missing(self, revision_ids): """List revisions missing from storage Args: revisions (iterable): revision ids Yields: missing revision ids """ for id in revision_ids: if id not in self._revisions: yield id def revision_get(self, revision_ids): for id in revision_ids: yield copy.deepcopy(self._revisions.get(id)) def _get_parent_revs(self, rev_id, seen, limit): if limit and len(seen) >= limit: return if rev_id in seen or rev_id not in self._revisions: return seen.add(rev_id) yield self._revisions[rev_id] for parent in self._revisions[rev_id]['parents']: yield from self._get_parent_revs(parent, seen, limit) def revision_log(self, revision_ids, limit=None): """Fetch revision entry from the given root revisions. Args: revisions: array of root revision to lookup limit: limitation on the output result. Default to None. Yields: List of revision log from such revisions root. """ seen = set() for rev_id in revision_ids: yield from self._get_parent_revs(rev_id, seen, limit) def revision_shortlog(self, revisions, limit=None): """Fetch the shortlog for the given revisions Args: revisions: list of root revisions to lookup limit: depth limitation for the output Yields: a list of (id, parents) tuples. """ yield from ((rev['id'], rev['parents']) for rev in self.revision_log(revisions, limit)) def release_add(self, releases): """Add releases to the storage Args: releases (Iterable[dict]): iterable of dictionaries representing the individual releases to add. Each dict has the following keys: - **id** (:class:`sha1_git`): id of the release to add - **revision** (:class:`sha1_git`): id of the revision the release points to - **date** (:class:`dict`): the date the release was made - **name** (:class:`bytes`): the name of the release - **comment** (:class:`bytes`): the comment associated with the release - **author** (:class:`Dict[str, bytes]`): dictionary with keys: name, fullname, email the date dictionary has the form defined in :mod:`swh.model`. """ for rel in releases: rel = copy.deepcopy(rel) rel['date'] = normalize_timestamp(rel['date']) self._person_add(rel['author']) self._objects[rel['id']].append( ('release', rel['id'])) self._releases[rel['id']] = rel def release_missing(self, releases): """List releases missing from storage Args: releases: an iterable of release ids Returns: a list of missing release ids """ yield from (rel for rel in releases if rel not in self._releases) def release_get(self, releases): """Given a list of sha1, return the releases's information Args: releases: list of sha1s Yields: dicts with the same keys as those given to `release_add` (or ``None`` if a release does not exist) """ for rel_id in releases: yield copy.deepcopy(self._releases.get(rel_id)) def snapshot_add(self, origin, visit, snapshot): """Add a snapshot for the given origin/visit couple Args: origin (int): id of the origin visit (int): id of the visit snapshot (dict): the snapshot to add to the visit, containing the following keys: - **id** (:class:`bytes`): id of the snapshot - **branches** (:class:`dict`): branches the snapshot contains, mapping the branch name (:class:`bytes`) to the branch target, itself a :class:`dict` (or ``None`` if the branch points to an unknown object) - **target_type** (:class:`str`): one of ``content``, ``directory``, ``revision``, ``release``, ``snapshot``, ``alias`` - **target** (:class:`bytes`): identifier of the target (currently a ``sha1_git`` for all object kinds, or the name of the target branch for aliases) Raises: ValueError: if the origin's or visit's identifier does not exist. """ snapshot_id = snapshot['id'] if snapshot_id not in self._snapshots: self._snapshots[snapshot_id] = { 'origin': origin, 'visit': visit, 'id': snapshot_id, 'branches': copy.deepcopy(snapshot['branches']), '_sorted_branch_names': sorted(snapshot['branches']) } self._objects[snapshot_id].append(('snapshot', snapshot_id)) if origin <= len(self._origin_visits) and \ visit <= len(self._origin_visits[origin-1]): self._origin_visits[origin-1][visit-1]['snapshot'] = snapshot_id else: raise ValueError('Origin with id %s does not exist or has no visit' ' with id %s' % (origin, visit)) def snapshot_get(self, snapshot_id): """Get the content, possibly partial, of a snapshot with the given id The branches of the snapshot are iterated in the lexicographical order of their names. .. warning:: At most 1000 branches contained in the snapshot will be returned for performance reasons. In order to browse the whole set of branches, the method :meth:`snapshot_get_branches` should be used instead. Args: snapshot_id (bytes): identifier of the snapshot Returns: dict: a dict with three keys: * **id**: identifier of the snapshot * **branches**: a dict of branches contained in the snapshot whose keys are the branches' names. * **next_branch**: the name of the first branch not returned or :const:`None` if the snapshot has less than 1000 branches. """ return self.snapshot_get_branches(snapshot_id) def snapshot_get_by_origin_visit(self, origin, visit): """Get the content, possibly partial, of a snapshot for the given origin visit The branches of the snapshot are iterated in the lexicographical order of their names. .. warning:: At most 1000 branches contained in the snapshot will be returned for performance reasons. In order to browse the whole set of branches, the method :meth:`snapshot_get_branches` should be used instead. Args: origin (int): the origin's identifier visit (int): the visit's identifier Returns: dict: None if the snapshot does not exist; a dict with three keys otherwise: * **id**: identifier of the snapshot * **branches**: a dict of branches contained in the snapshot whose keys are the branches' names. * **next_branch**: the name of the first branch not returned or :const:`None` if the snapshot has less than 1000 branches. """ if origin > len(self._origins) or \ visit > len(self._origin_visits[origin-1]): return None snapshot_id = self._origin_visits[origin-1][visit-1]['snapshot'] if snapshot_id: return self.snapshot_get(snapshot_id) else: return None def snapshot_get_latest(self, origin, allowed_statuses=None): """Get the content, possibly partial, of the latest snapshot for the given origin, optionally only from visits that have one of the given allowed_statuses The branches of the snapshot are iterated in the lexicographical order of their names. .. warning:: At most 1000 branches contained in the snapshot will be returned for performance reasons. In order to browse the whole set of branches, the method :meth:`snapshot_get_branches` should be used instead. Args: origin (int): the origin's identifier allowed_statuses (list of str): list of visit statuses considered to find the latest snapshot for the visit. For instance, ``allowed_statuses=['full']`` will only consider visits that have successfully run to completion. Returns: dict: a dict with three keys: * **id**: identifier of the snapshot * **branches**: a dict of branches contained in the snapshot whose keys are the branches' names. * **next_branch**: the name of the first branch not returned or :const:`None` if the snapshot has less than 1000 branches. """ visits = self._origin_visits[origin-1] if allowed_statuses is not None: visits = [visit for visit in visits if visit['status'] in allowed_statuses] snapshot = None for visit in sorted(visits, key=lambda v: (v['date'], v['visit']), reverse=True): snapshot_id = visit['snapshot'] snapshot = self.snapshot_get(snapshot_id) if snapshot: break return snapshot def snapshot_count_branches(self, snapshot_id, db=None, cur=None): """Count the number of branches in the snapshot with the given id Args: snapshot_id (bytes): identifier of the snapshot Returns: dict: A dict whose keys are the target types of branches and values their corresponding amount """ branches = list(self._snapshots[snapshot_id]['branches'].values()) return collections.Counter(branch['target_type'] if branch else None for branch in branches) def snapshot_get_branches(self, snapshot_id, branches_from=b'', branches_count=1000, target_types=None): """Get the content, possibly partial, of a snapshot with the given id The branches of the snapshot are iterated in the lexicographical order of their names. Args: snapshot_id (bytes): identifier of the snapshot branches_from (bytes): optional parameter used to skip branches whose name is lesser than it before returning them branches_count (int): optional parameter used to restrain the amount of returned branches target_types (list): optional parameter used to filter the target types of branch to return (possible values that can be contained in that list are `'content', 'directory', 'revision', 'release', 'snapshot', 'alias'`) Returns: dict: None if the snapshot does not exist; a dict with three keys otherwise: * **id**: identifier of the snapshot * **branches**: a dict of branches contained in the snapshot whose keys are the branches' names. * **next_branch**: the name of the first branch not returned or :const:`None` if the snapshot has less than `branches_count` branches after `branches_from` included. """ snapshot = self._snapshots.get(snapshot_id) if snapshot is None: return None sorted_branch_names = snapshot['_sorted_branch_names'] from_index = bisect.bisect_left( sorted_branch_names, branches_from) if target_types: next_branch = None branches = {} for branch_name in sorted_branch_names[from_index:]: branch = snapshot['branches'][branch_name] if branch and branch['target_type'] in target_types: if len(branches) < branches_count: branches[branch_name] = branch else: next_branch = branch_name break else: # As there is no 'target_types', we can do that much faster to_index = from_index + branches_count returned_branch_names = sorted_branch_names[from_index:to_index] branches = {branch_name: snapshot['branches'][branch_name] for branch_name in returned_branch_names} if to_index >= len(sorted_branch_names): next_branch = None else: next_branch = sorted_branch_names[to_index] return { 'id': snapshot_id, 'branches': branches, 'next_branch': next_branch, } def object_find_by_sha1_git(self, ids, db=None, cur=None): """Return the objects found with the given ids. Args: ids: a generator of sha1_gits Returns: dict: a mapping from id to the list of objects found. Each object found is itself a dict with keys: - sha1_git: the input id - type: the type of object found - id: the id of the object found - object_id: the numeric id of the object found. """ ret = {} for id_ in ids: objs = self._objects.get(id_, []) ret[id_] = [{ 'sha1_git': id_, 'type': obj[0], 'id': obj[1], 'object_id': id_, } for obj in objs] return ret def origin_get(self, origins): """Return origins, either all identified by their ids or all identified by tuples (type, url). Args: origin: a list of dictionaries representing the individual origins to find. These dicts have either the keys type and url: - type (FIXME: enum TBD): the origin type ('git', 'wget', ...) - url (bytes): the url the origin points to or the id: - id (int): the origin's identifier Returns: dict: the origin dictionary with the keys: - id: origin's id - type: origin's type - url: origin's url Raises: ValueError: if the keys does not match (url and type) nor id. """ if isinstance(origins, dict): # Old API return_single = True origins = [origins] else: return_single = False # Sanity check to be error-compatible with the pgsql backend if any('id' in origin for origin in origins) \ and not all('id' in origin for origin in origins): raise ValueError( 'Either all origins or none at all should have an "id".') if any('type' in origin and 'url' in origin for origin in origins) \ and not all('type' in origin and 'url' in origin for origin in origins): raise ValueError( 'Either all origins or none at all should have a ' '"type" and an "url".') results = [] for origin in origins: if 'id' in origin: origin_id = origin['id'] elif 'type' in origin and 'url' in origin: origin_id = self._origin_id(origin) else: raise ValueError( 'Origin must have either id or (type and url).') origin = None # self._origin_id can return None if origin_id is not None and origin_id <= len(self._origins): origin = copy.deepcopy(self._origins[origin_id-1]) origin['id'] = origin_id results.append(origin) if return_single: assert len(results) == 1 return results[0] else: return results def origin_get_range(self, origin_from=1, origin_count=100): """Retrieve ``origin_count`` origins whose ids are greater or equal than ``origin_from``. Origins are sorted by id before retrieving them. Args: origin_from (int): the minimum id of origins to retrieve origin_count (int): the maximum number of origins to retrieve Yields: dicts containing origin information as returned by :meth:`swh.storage.in_memory.Storage.origin_get`. """ origin_from = max(origin_from, 1) if origin_from <= len(self._origins): max_idx = origin_from + origin_count - 1 if max_idx > len(self._origins): max_idx = len(self._origins) for idx in range(origin_from-1, max_idx): yield copy.deepcopy(self._origins[idx]) def origin_search(self, url_pattern, offset=0, limit=50, regexp=False, with_visit=False, db=None, cur=None): """Search for origins whose urls contain a provided string pattern or match a provided regular expression. The search is performed in a case insensitive way. Args: url_pattern (str): the string pattern to search for in origin urls offset (int): number of found origins to skip before returning results limit (int): the maximum number of found origins to return regexp (bool): if True, consider the provided pattern as a regular expression and return origins whose urls match it with_visit (bool): if True, filter out origins with no visit Returns: An iterable of dict containing origin information as returned by :meth:`swh.storage.storage.Storage.origin_get`. """ origins = self._origins if regexp: pat = re.compile(url_pattern) origins = [orig for orig in origins if pat.match(orig['url'])] else: origins = [orig for orig in origins if url_pattern in orig['url']] if with_visit: origins = [orig for orig in origins if len(self._origin_visits[orig['id']-1]) > 0] + origins = copy.deepcopy(origins[offset:offset+limit]) return origins + def origin_count(self, url_pattern, regexp=False, with_visit=False, + db=None, cur=None): + """Count origins whose urls contain a provided string pattern + or match a provided regular expression. + The pattern search in origin urls is performed in a case insensitive + way. + + Args: + url_pattern (str): the string pattern to search for in origin urls + regexp (bool): if True, consider the provided pattern as a regular + expression and return origins whose urls match it + with_visit (bool): if True, filter out origins with no visit + + Returns: + int: The number of origins matching the search criterion. + """ + return len(self.origin_search(url_pattern, regexp=regexp, + with_visit=with_visit, + limit=len(self._origins))) + def origin_add(self, origins): """Add origins to the storage Args: origins: list of dictionaries representing the individual origins, with the following keys: - type: the origin type ('git', 'svn', 'deb', ...) - url (bytes): the url the origin points to Returns: list: given origins as dict updated with their id """ origins = copy.deepcopy(origins) for origin in origins: origin['id'] = self.origin_add_one(origin) return origins def origin_add_one(self, origin): """Add origin to the storage Args: origin: dictionary representing the individual origin to add. This dict has the following keys: - type (FIXME: enum TBD): the origin type ('git', 'wget', ...) - url (bytes): the url the origin points to Returns: the id of the added origin, or of the identical one that already exists. """ origin = copy.deepcopy(origin) assert 'id' not in origin origin_id = self._origin_id(origin) if origin_id is None: # origin ids are in the range [1, +inf[ origin_id = len(self._origins) + 1 origin['id'] = origin_id self._origins.append(origin) self._origin_visits.append([]) key = (origin['type'], origin['url']) self._objects[key].append(('origin', origin_id)) return origin_id def fetch_history_start(self, origin_id): """Add an entry for origin origin_id in fetch_history. Returns the id of the added fetch_history entry """ pass def fetch_history_end(self, fetch_history_id, data): """Close the fetch_history entry with id `fetch_history_id`, replacing its data with `data`. """ pass def fetch_history_get(self, fetch_history_id): """Get the fetch_history entry with id `fetch_history_id`. """ raise NotImplementedError('fetch_history_get is deprecated, use ' 'origin_visit_get instead.') def origin_visit_add(self, origin, date=None, *, ts=None): """Add an origin_visit for the origin at date with status 'ongoing'. Args: origin (int): visited origin's identifier date: timestamp of such visit Returns: dict: dictionary with keys origin and visit where: - origin: origin's identifier - visit: the visit's identifier for the new visit occurrence """ if ts is None: if date is None: raise TypeError('origin_visit_add expected 2 arguments.') else: assert date is None warnings.warn("argument 'ts' of origin_visit_add was renamed " "to 'date' in v0.0.109.", DeprecationWarning) date = ts if isinstance(date, str): date = dateutil.parser.parse(date) visit_ret = None if origin <= len(self._origin_visits): # visit ids are in the range [1, +inf[ visit_id = len(self._origin_visits[origin-1]) + 1 status = 'ongoing' visit = { 'origin': origin, 'date': date, 'status': status, 'snapshot': None, 'metadata': None, 'visit': visit_id } self._origin_visits[origin-1].append(visit) visit_ret = { 'origin': origin, 'visit': visit_id, } return visit_ret def origin_visit_update(self, origin, visit_id, status, metadata=None): """Update an origin_visit's status. Args: origin (int): visited origin's identifier visit_id (int): visit's identifier status: visit's new status metadata: data associated to the visit Returns: None """ if origin > len(self._origin_visits) or \ visit_id > len(self._origin_visits[origin-1]): return self._origin_visits[origin-1][visit_id-1].update({ 'status': status, 'metadata': metadata}) def origin_visit_get(self, origin, last_visit=None, limit=None): """Retrieve all the origin's visit's information. Args: origin (int): the origin's identifier last_visit (int): visit's id from which listing the next ones, default to None limit (int): maximum number of results to return, default to None Yields: List of visits. """ if origin <= len(self._origin_visits): visits = self._origin_visits[origin-1] if last_visit is not None: visits = visits[last_visit:] if limit is not None: visits = visits[:limit] for visit in visits: visit_id = visit['visit'] yield copy.deepcopy(self._origin_visits[origin-1][visit_id-1]) def origin_visit_get_by(self, origin, visit): """Retrieve origin visit's information. Args: origin (int): the origin's identifier Returns: The information on that particular (origin, visit) or None if it does not exist """ origin_visit = None if origin <= len(self._origin_visits) and \ visit <= len(self._origin_visits[origin-1]): origin_visit = self._origin_visits[origin-1][visit-1] return copy.deepcopy(origin_visit) def person_get(self, person): """Return the persons identified by their ids. Args: person: array of ids. Returns: The array of persons corresponding of the ids. """ for p in person: if 0 <= (p - 1) < len(self._persons): yield dict(self._persons[p - 1], id=p) else: yield None def stat_counters(self): """compute statistics about the number of tuples in various tables Returns: dict: a dictionary mapping textual labels (e.g., content) to integer values (e.g., the number of tuples in table content) """ keys = ( 'content', 'directory', 'origin', 'origin_visit', 'person', 'release', 'revision', 'skipped_content', 'snapshot' ) stats = {key: 0 for key in keys} stats.update(collections.Counter( obj_type for (obj_type, obj_id) in itertools.chain(*self._objects.values()))) return stats def refresh_stat_counters(self): """Recomputes the statistics for `stat_counters`.""" pass def origin_metadata_add(self, origin_id, ts, provider, tool, metadata, db=None, cur=None): """ Add an origin_metadata for the origin at ts with provenance and metadata. Args: origin_id (int): the origin's id for which the metadata is added ts (datetime): timestamp of the found metadata provider: id of the provider of metadata (ex:'hal') tool: id of the tool used to extract metadata metadata (jsonb): the metadata retrieved at the time and location """ if isinstance(ts, str): ts = dateutil.parser.parse(ts) origin_metadata = { 'origin_id': origin_id, 'discovery_date': ts, 'tool_id': tool, 'metadata': metadata, 'provider_id': provider, } self._origin_metadata[origin_id].append(origin_metadata) return None def origin_metadata_get_by(self, origin_id, provider_type=None, db=None, cur=None): """Retrieve list of all origin_metadata entries for the origin_id Args: origin_id (int): the unique origin's identifier provider_type (str): (optional) type of provider Returns: list of dicts: the origin_metadata dictionary with the keys: - origin_id (int): origin's identifier - discovery_date (datetime): timestamp of discovery - tool_id (int): metadata's extracting tool - metadata (jsonb) - provider_id (int): metadata's provider - provider_name (str) - provider_type (str) - provider_url (str) """ metadata = [] for item in self._origin_metadata[origin_id]: item = copy.deepcopy(item) provider = self.metadata_provider_get(item['provider_id']) for attr in ('name', 'type', 'url'): item['provider_' + attr] = provider[attr] metadata.append(item) return metadata def tool_add(self, tools): """Add new tools to the storage. Args: tools (iterable of :class:`dict`): Tool information to add to storage. Each tool is a :class:`dict` with the following keys: - name (:class:`str`): name of the tool - version (:class:`str`): version of the tool - configuration (:class:`dict`): configuration of the tool, must be json-encodable Yields: :class:`dict`: All the tools inserted in storage (including the internal ``id``). The order of the list is not guaranteed to match the order of the initial list. """ inserted = [] for tool in tools: key = self._tool_key(tool) assert 'id' not in tool record = copy.deepcopy(tool) record['id'] = key # TODO: remove this if key not in self._tools: self._tools[key] = record inserted.append(copy.deepcopy(self._tools[key])) yield from inserted def tool_get(self, tool): """Retrieve tool information. Args: tool (dict): Tool information we want to retrieve from storage. The dicts have the same keys as those used in :func:`tool_add`. Returns: dict: The full tool information if it exists (``id`` included), None otherwise. """ return self._tools.get(self._tool_key(tool)) def metadata_provider_add(self, provider_name, provider_type, provider_url, metadata): """Add a metadata provider. Args: provider_name (str): Its name provider_type (str): Its type provider_url (str): Its URL metadata: JSON-encodable object Returns: an identifier of the provider """ provider = { 'name': provider_name, 'type': provider_type, 'url': provider_url, 'metadata': metadata, } key = self._metadata_provider_key(provider) provider['id'] = key self._metadata_providers[key] = provider return key def metadata_provider_get(self, provider_id, db=None, cur=None): """Get a metadata provider Args: provider_id: Its identifier, as given by `metadata_provider_add`. Returns: dict: same as `metadata_provider_add`; or None if it does not exist. """ return self._metadata_providers.get(provider_id) def metadata_provider_get_by(self, provider, db=None, cur=None): """Get a metadata provider Args: provider_name: Its name provider_url: Its URL Returns: dict: same as `metadata_provider_add`; or None if it does not exist. """ key = self._metadata_provider_key({ 'name': provider['provider_name'], 'url': provider['provider_url']}) return self._metadata_providers.get(key) def _origin_id(self, origin): origin_id = None for stored_origin in self._origins: if stored_origin['type'] == origin['type'] and \ stored_origin['url'] == origin['url']: origin_id = stored_origin['id'] break return origin_id def _person_add(self, person): """Add a person in storage. Note: Private method, do not use outside of this class. Args: person: dictionary with keys fullname, name and email. """ key = ('person', person['fullname']) if key not in self._objects: person_id = len(self._persons) + 1 self._persons.append(dict(person)) self._objects[key].append(('person', person_id)) else: person_id = self._objects[key][0][1] p = next(self.person_get([person_id])) person.update(p.items()) person['id'] = person_id @staticmethod def _content_key(content): """A stable key for a content""" return tuple(content.get(key) for key in sorted(DEFAULT_ALGORITHMS)) @staticmethod def _tool_key(tool): return (tool['name'], tool['version'], tuple(sorted(tool['configuration'].items()))) @staticmethod def _metadata_provider_key(provider): return (provider['name'], provider['url']) diff --git a/swh/storage/storage.py b/swh/storage/storage.py index 3b8dca48..d9d6c356 100644 --- a/swh/storage/storage.py +++ b/swh/storage/storage.py @@ -1,1516 +1,1535 @@ # 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 collections import defaultdict from concurrent.futures import ThreadPoolExecutor import datetime import itertools import json import warnings import dateutil.parser import psycopg2 import psycopg2.pool from . import converters from .common import db_transaction_generator, db_transaction from .db import Db from .exc import StorageDBError from .algos import diff from swh.model.hashutil import ALGORITHMS, hash_to_bytes from swh.objstorage import get_objstorage from swh.objstorage.exc import ObjNotFoundError # Max block size of contents to return BULK_BLOCK_CONTENT_LEN_MAX = 10000 EMPTY_SNAPSHOT_ID = hash_to_bytes('1a8893e6a86f444e8be8e7bda6cb34fb1735a00e') """Identifier for the empty snapshot""" class Storage(): """SWH storage proxy, encompassing DB and object storage """ def __init__(self, db, objstorage, min_pool_conns=1, max_pool_conns=10): """ Args: db_conn: either a libpq connection string, or a psycopg2 connection obj_root: path to the root of the object storage """ 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) self.objstorage = get_objstorage(**objstorage) def get_db(self): if self._db: return self._db else: return Db.from_pool(self._pool) def check_config(self, *, check_write): """Check that the storage is configured and ready to go.""" if not self.objstorage.check_config(check_write=check_write): return False # Check permissions on one of the tables with self.get_db().transaction() as cur: if check_write: check = 'INSERT' else: check = 'SELECT' cur.execute( "select has_table_privilege(current_user, 'content', %s)", (check,) ) return cur.fetchone()[0] return True def content_add(self, content): """Add content blobs to the storage Note: in case of DB errors, objects might have already been added to the object storage and will not be removed. Since addition to the object storage is idempotent, that should not be a problem. Args: content (iterable): iterable of dictionaries representing individual pieces of content to add. Each dictionary has the following keys: - data (bytes): the actual content - length (int): content length (default: -1) - one key for each checksum algorithm in :data:`swh.model.hashutil.ALGORITHMS`, mapped to the corresponding checksum - status (str): one of visible, hidden, absent - reason (str): if status = absent, the reason why - origin (int): if status = absent, the origin we saw the content in """ db = self.get_db() def _unique_key(hash, keys=db.content_hash_keys): """Given a hash (tuple or dict), return a unique key from the aggregation of keys. """ if isinstance(hash, tuple): return hash return tuple([hash[k] for k in keys]) content_by_status = defaultdict(list) for d in content: if 'status' not in d: d['status'] = 'visible' if 'length' not in d: d['length'] = -1 content_by_status[d['status']].append(d) content_with_data = content_by_status['visible'] content_without_data = content_by_status['absent'] missing_content = set(self.content_missing(content_with_data)) missing_skipped = set(_unique_key(hashes) for hashes in self.skipped_content_missing( content_without_data)) def add_to_objstorage(): data = { cont['sha1']: cont['data'] for cont in content_with_data if cont['sha1'] in missing_content } self.objstorage.add_batch(data) with db.transaction() as cur: with ThreadPoolExecutor(max_workers=1) as executor: added_to_objstorage = executor.submit(add_to_objstorage) if missing_content: # create temporary table for metadata injection db.mktemp('content', cur) content_filtered = (cont for cont in content_with_data if cont['sha1'] in missing_content) db.copy_to(content_filtered, 'tmp_content', db.content_get_metadata_keys, cur) # move metadata in place try: db.content_add_from_temp(cur) except psycopg2.IntegrityError as e: from . import HashCollision if e.diag.sqlstate == '23505' and \ e.diag.table_name == 'content': constaint_to_hash_name = { 'content_pkey': 'sha1', 'content_sha1_git_idx': 'sha1_git', 'content_sha256_idx': 'sha256', } colliding_hash_name = constaint_to_hash_name \ .get(e.diag.constraint_name) raise HashCollision(colliding_hash_name) else: raise if missing_skipped: missing_filtered = ( cont for cont in content_without_data if _unique_key(cont) in missing_skipped ) db.mktemp('skipped_content', cur) db.copy_to(missing_filtered, 'tmp_skipped_content', db.skipped_content_keys, cur) # move metadata in place db.skipped_content_add_from_temp(cur) # Wait for objstorage addition before returning from the # transaction, bubbling up any exception added_to_objstorage.result() @db_transaction() def content_update(self, content, keys=[], db=None, cur=None): """Update content blobs to the storage. Does nothing for unknown contents or skipped ones. Args: content (iterable): iterable of dictionaries representing individual pieces of content to update. Each dictionary has the following keys: - data (bytes): the actual content - length (int): content length (default: -1) - one key for each checksum algorithm in :data:`swh.model.hashutil.ALGORITHMS`, mapped to the corresponding checksum - status (str): one of visible, hidden, absent keys (list): List of keys (str) whose values needs an update, e.g., new hash column """ # TODO: Add a check on input keys. How to properly implement # this? We don't know yet the new columns. db.mktemp('content', cur) select_keys = list(set(db.content_get_metadata_keys).union(set(keys))) db.copy_to(content, 'tmp_content', select_keys, cur) db.content_update_from_temp(keys_to_update=keys, cur=cur) def content_get(self, content): """Retrieve in bulk contents and their data. This generator yields exactly as many items than provided sha1 identifiers, but callers should not assume this will always be true. It may also yield `None` values in case an object was not found. Args: content: iterables of sha1 Yields: Dict[str, bytes]: Generates streams of contents as dict with their raw data: - sha1 (bytes): content id - data (bytes): content's raw data Raises: ValueError in case of too much contents are required. cf. BULK_BLOCK_CONTENT_LEN_MAX """ # FIXME: Make this method support slicing the `data`. if len(content) > BULK_BLOCK_CONTENT_LEN_MAX: raise ValueError( "Send at maximum %s contents." % BULK_BLOCK_CONTENT_LEN_MAX) for obj_id in content: try: data = self.objstorage.get(obj_id) except ObjNotFoundError: yield None continue yield {'sha1': obj_id, 'data': data} @db_transaction() def content_get_range(self, start, end, limit=1000, db=None, cur=None): """Retrieve contents within range [start, end] bound by limit. Note that this function may return more than one blob per hash. The limit is enforced with multiplicity (ie. two blobs with the same hash will count twice toward the limit). Args: **start** (bytes): Starting identifier range (expected smaller than end) **end** (bytes): Ending identifier range (expected larger than start) **limit** (int): Limit result (default to 1000) Returns: a dict with keys: - contents [dict]: iterable of contents in between the range. - next (bytes): There remains content in the range starting from this next sha1 """ if limit is None: raise ValueError('Development error: limit should not be None') contents = [] next_content = None for counter, content_row in enumerate( db.content_get_range(start, end, limit+1, cur)): content = dict(zip(db.content_get_metadata_keys, content_row)) if counter >= limit: # take the last commit for the next page starting from this next_content = content['sha1'] break contents.append(content) return { 'contents': contents, 'next': next_content, } @db_transaction_generator(statement_timeout=500) def content_get_metadata(self, content, db=None, cur=None): """Retrieve content metadata in bulk Args: content: iterable of content identifiers (sha1) Returns: an iterable with content metadata corresponding to the given ids """ for metadata in db.content_get_metadata_from_sha1s(content, cur): yield dict(zip(db.content_get_metadata_keys, metadata)) @db_transaction_generator() def content_missing(self, content, key_hash='sha1', db=None, cur=None): """List content missing from storage Args: content ([dict]): iterable of dictionaries whose keys are either 'length' or an item of :data:`swh.model.hashutil.ALGORITHMS`; mapped to the corresponding checksum (or length). key_hash (str): name of the column to use as hash id result (default: 'sha1') Returns: iterable ([bytes]): missing content ids (as per the key_hash column) Raises: TODO: an exception when we get a hash collision. """ keys = db.content_hash_keys if key_hash not in keys: raise ValueError("key_hash should be one of %s" % keys) key_hash_idx = keys.index(key_hash) if not content: return for obj in db.content_missing_from_list(content, cur): yield obj[key_hash_idx] @db_transaction_generator() def content_missing_per_sha1(self, contents, db=None, cur=None): """List content missing from storage based only on sha1. Args: contents: Iterable of sha1 to check for absence. Returns: iterable: missing ids Raises: TODO: an exception when we get a hash collision. """ for obj in db.content_missing_per_sha1(contents, cur): yield obj[0] @db_transaction_generator() def skipped_content_missing(self, content, db=None, cur=None): """List skipped_content missing from storage Args: content: iterable of dictionaries containing the data for each checksum algorithm. Returns: iterable: missing signatures """ keys = db.content_hash_keys db.mktemp('skipped_content', cur) db.copy_to(content, 'tmp_skipped_content', keys + ['length', 'reason'], cur) yield from db.skipped_content_missing_from_temp(cur) @db_transaction() def content_find(self, content, db=None, cur=None): """Find a content hash in db. Args: content: a dictionary representing one content hash, mapping checksum algorithm names (see swh.model.hashutil.ALGORITHMS) to checksum values Returns: a triplet (sha1, sha1_git, sha256) if the content exist or None otherwise. Raises: ValueError: in case the key of the dictionary is not sha1, sha1_git nor sha256. """ if not set(content).intersection(ALGORITHMS): raise ValueError('content keys must contain at least one of: ' 'sha1, sha1_git, sha256, blake2s256') c = db.content_find(sha1=content.get('sha1'), sha1_git=content.get('sha1_git'), sha256=content.get('sha256'), blake2s256=content.get('blake2s256'), cur=cur) if c: return dict(zip(db.content_find_cols, c)) return None def directory_add(self, directories): """Add directories to the storage Args: directories (iterable): iterable of dictionaries representing the individual directories to add. Each dict has the following keys: - id (sha1_git): the id of the directory to add - entries (list): list of dicts for each entry in the directory. Each dict has the following keys: - name (bytes) - type (one of 'file', 'dir', 'rev'): type of the directory entry (file, directory, revision) - target (sha1_git): id of the object pointed at by the directory entry - perms (int): entry permissions """ dirs = set() dir_entries = { 'file': defaultdict(list), 'dir': defaultdict(list), 'rev': defaultdict(list), } for cur_dir in directories: dir_id = cur_dir['id'] dirs.add(dir_id) for src_entry in cur_dir['entries']: entry = src_entry.copy() entry['dir_id'] = dir_id dir_entries[entry['type']][dir_id].append(entry) dirs_missing = set(self.directory_missing(dirs)) if not dirs_missing: return db = self.get_db() with db.transaction() as cur: # Copy directory ids dirs_missing_dict = ({'id': dir} for dir in dirs_missing) db.mktemp('directory', cur) db.copy_to(dirs_missing_dict, 'tmp_directory', ['id'], cur) # Copy entries for entry_type, entry_list in dir_entries.items(): entries = itertools.chain.from_iterable( entries_for_dir for dir_id, entries_for_dir in entry_list.items() if dir_id in dirs_missing) db.mktemp_dir_entry(entry_type) db.copy_to( entries, 'tmp_directory_entry_%s' % entry_type, ['target', 'name', 'perms', 'dir_id'], cur, ) # Do the final copy db.directory_add_from_temp(cur) @db_transaction_generator() def directory_missing(self, directories, db=None, cur=None): """List directories missing from storage Args: directories (iterable): an iterable of directory ids Yields: missing directory ids """ for obj in db.directory_missing_from_list(directories, cur): yield obj[0] @db_transaction_generator(statement_timeout=20000) def directory_ls(self, directory, recursive=False, db=None, cur=None): """Get entries for one directory. Args: - directory: the directory to list entries from. - recursive: if flag on, this list recursively from this directory. Returns: List of entries for such directory. If `recursive=True`, names in the path of a dir/file not at the root are concatenated with a slash (`/`). """ if recursive: res_gen = db.directory_walk(directory, cur=cur) else: res_gen = db.directory_walk_one(directory, cur=cur) for line in res_gen: yield dict(zip(db.directory_ls_cols, line)) @db_transaction(statement_timeout=2000) def directory_entry_get_by_path(self, directory, paths, db=None, cur=None): """Get the directory entry (either file or dir) from directory with path. Args: - directory: sha1 of the top level directory - paths: path to lookup from the top level directory. From left (top) to right (bottom). Returns: The corresponding directory entry if found, None otherwise. """ res = db.directory_entry_get_by_path(directory, paths, cur) if res: return dict(zip(db.directory_ls_cols, res)) def revision_add(self, revisions): """Add revisions to the storage Args: revisions (Iterable[dict]): iterable of dictionaries representing the individual revisions to add. Each dict has the following keys: - **id** (:class:`sha1_git`): id of the revision to add - **date** (:class:`dict`): date the revision was written - **committer_date** (:class:`dict`): date the revision got added to the origin - **type** (one of 'git', 'tar'): type of the revision added - **directory** (:class:`sha1_git`): the directory the revision points at - **message** (:class:`bytes`): the message associated with the revision - **author** (:class:`Dict[str, bytes]`): dictionary with keys: name, fullname, email - **committer** (:class:`Dict[str, bytes]`): dictionary with keys: name, fullname, email - **metadata** (:class:`jsonb`): extra information as dictionary - **synthetic** (:class:`bool`): revision's nature (tarball, directory creates synthetic revision`) - **parents** (:class:`list[sha1_git]`): the parents of this revision date dictionaries have the form defined in :mod:`swh.model`. """ db = self.get_db() revisions_missing = set(self.revision_missing( set(revision['id'] for revision in revisions))) if not revisions_missing: return with db.transaction() as cur: db.mktemp_revision(cur) revisions_filtered = ( converters.revision_to_db(revision) for revision in revisions if revision['id'] in revisions_missing) parents_filtered = [] db.copy_to( revisions_filtered, 'tmp_revision', db.revision_add_cols, cur, lambda rev: parents_filtered.extend(rev['parents'])) db.revision_add_from_temp(cur) db.copy_to(parents_filtered, 'revision_history', ['id', 'parent_id', 'parent_rank'], cur) @db_transaction_generator() def revision_missing(self, revisions, db=None, cur=None): """List revisions missing from storage Args: revisions (iterable): revision ids Yields: missing revision ids """ if not revisions: return for obj in db.revision_missing_from_list(revisions, cur): yield obj[0] @db_transaction_generator(statement_timeout=500) def revision_get(self, revisions, db=None, cur=None): """Get all revisions from storage Args: revisions: an iterable of revision ids Returns: iterable: an iterable of revisions as dictionaries (or None if the revision doesn't exist) """ for line in db.revision_get_from_list(revisions, cur): data = converters.db_to_revision( dict(zip(db.revision_get_cols, line)) ) if not data['type']: yield None continue yield data @db_transaction_generator(statement_timeout=2000) def revision_log(self, revisions, limit=None, db=None, cur=None): """Fetch revision entry from the given root revisions. Args: revisions: array of root revision to lookup limit: limitation on the output result. Default to None. Yields: List of revision log from such revisions root. """ for line in db.revision_log(revisions, limit, cur): data = converters.db_to_revision( dict(zip(db.revision_get_cols, line)) ) if not data['type']: yield None continue yield data @db_transaction_generator(statement_timeout=2000) def revision_shortlog(self, revisions, limit=None, db=None, cur=None): """Fetch the shortlog for the given revisions Args: revisions: list of root revisions to lookup limit: depth limitation for the output Yields: a list of (id, parents) tuples. """ yield from db.revision_shortlog(revisions, limit, cur) def release_add(self, releases): """Add releases to the storage Args: releases (Iterable[dict]): iterable of dictionaries representing the individual releases to add. Each dict has the following keys: - **id** (:class:`sha1_git`): id of the release to add - **revision** (:class:`sha1_git`): id of the revision the release points to - **date** (:class:`dict`): the date the release was made - **name** (:class:`bytes`): the name of the release - **comment** (:class:`bytes`): the comment associated with the release - **author** (:class:`Dict[str, bytes]`): dictionary with keys: name, fullname, email the date dictionary has the form defined in :mod:`swh.model`. """ db = self.get_db() release_ids = set(release['id'] for release in releases) releases_missing = set(self.release_missing(release_ids)) if not releases_missing: return with db.transaction() as cur: db.mktemp_release(cur) releases_filtered = ( converters.release_to_db(release) for release in releases if release['id'] in releases_missing ) db.copy_to(releases_filtered, 'tmp_release', db.release_add_cols, cur) db.release_add_from_temp(cur) @db_transaction_generator() def release_missing(self, releases, db=None, cur=None): """List releases missing from storage Args: releases: an iterable of release ids Returns: a list of missing release ids """ if not releases: return for obj in db.release_missing_from_list(releases, cur): yield obj[0] @db_transaction_generator(statement_timeout=500) def release_get(self, releases, db=None, cur=None): """Given a list of sha1, return the releases's information Args: releases: list of sha1s Yields: dicts with the same keys as those given to `release_add` (or ``None`` if a release does not exist) """ for release in db.release_get_from_list(releases, cur): data = converters.db_to_release( dict(zip(db.release_get_cols, release)) ) yield data if data['target_type'] else None @db_transaction() def snapshot_add(self, origin, visit, snapshot, db=None, cur=None): """Add a snapshot for the given origin/visit couple Args: origin (int): id of the origin visit (int): id of the visit snapshot (dict): the snapshot to add to the visit, containing the following keys: - **id** (:class:`bytes`): id of the snapshot - **branches** (:class:`dict`): branches the snapshot contains, mapping the branch name (:class:`bytes`) to the branch target, itself a :class:`dict` (or ``None`` if the branch points to an unknown object) - **target_type** (:class:`str`): one of ``content``, ``directory``, ``revision``, ``release``, ``snapshot``, ``alias`` - **target** (:class:`bytes`): identifier of the target (currently a ``sha1_git`` for all object kinds, or the name of the target branch for aliases) Raises: ValueError: if the origin or visit id does not exist. """ if not db.snapshot_exists(snapshot['id'], cur): db.mktemp_snapshot_branch(cur) db.copy_to( ( { 'name': name, 'target': info['target'] if info else None, 'target_type': info['target_type'] if info else None, } for name, info in snapshot['branches'].items() ), 'tmp_snapshot_branch', ['name', 'target', 'target_type'], cur, ) if not db.origin_visit_exists(origin, visit): raise ValueError('Not origin visit with ids (%s, %s)' % (origin, visit)) db.snapshot_add(origin, visit, snapshot['id'], cur) @db_transaction(statement_timeout=2000) def snapshot_get(self, snapshot_id, db=None, cur=None): """Get the content, possibly partial, of a snapshot with the given id The branches of the snapshot are iterated in the lexicographical order of their names. .. warning:: At most 1000 branches contained in the snapshot will be returned for performance reasons. In order to browse the whole set of branches, the method :meth:`snapshot_get_branches` should be used instead. Args: snapshot_id (bytes): identifier of the snapshot Returns: dict: a dict with three keys: * **id**: identifier of the snapshot * **branches**: a dict of branches contained in the snapshot whose keys are the branches' names. * **next_branch**: the name of the first branch not returned or :const:`None` if the snapshot has less than 1000 branches. """ return self.snapshot_get_branches(snapshot_id, db=db, cur=cur) @db_transaction(statement_timeout=2000) def snapshot_get_by_origin_visit(self, origin, visit, db=None, cur=None): """Get the content, possibly partial, of a snapshot for the given origin visit The branches of the snapshot are iterated in the lexicographical order of their names. .. warning:: At most 1000 branches contained in the snapshot will be returned for performance reasons. In order to browse the whole set of branches, the method :meth:`snapshot_get_branches` should be used instead. Args: origin (int): the origin identifier visit (int): the visit identifier Returns: dict: None if the snapshot does not exist; a dict with three keys otherwise: * **id**: identifier of the snapshot * **branches**: a dict of branches contained in the snapshot whose keys are the branches' names. * **next_branch**: the name of the first branch not returned or :const:`None` if the snapshot has less than 1000 branches. """ snapshot_id = db.snapshot_get_by_origin_visit(origin, visit, cur) if snapshot_id: return self.snapshot_get(snapshot_id, db=db, cur=cur) return None @db_transaction(statement_timeout=2000) def snapshot_get_latest(self, origin, allowed_statuses=None, db=None, cur=None): """Get the content, possibly partial, of the latest snapshot for the given origin, optionally only from visits that have one of the given allowed_statuses The branches of the snapshot are iterated in the lexicographical order of their names. .. warning:: At most 1000 branches contained in the snapshot will be returned for performance reasons. In order to browse the whole set of branches, the method :meth:`snapshot_get_branches` should be used instead. Args: origin (int): the origin identifier allowed_statuses (list of str): list of visit statuses considered to find the latest snapshot for the visit. For instance, ``allowed_statuses=['full']`` will only consider visits that have successfully run to completion. Returns: dict: a dict with three keys: * **id**: identifier of the snapshot * **branches**: a dict of branches contained in the snapshot whose keys are the branches' names. * **next_branch**: the name of the first branch not returned or :const:`None` if the snapshot has less than 1000 branches. """ origin_visit = db.origin_visit_get_latest_snapshot( origin, allowed_statuses=allowed_statuses, cur=cur) if origin_visit: origin_visit = dict(zip(db.origin_visit_get_cols, origin_visit)) return self.snapshot_get(origin_visit['snapshot'], db=db, cur=cur) @db_transaction(statement_timeout=2000) def snapshot_count_branches(self, snapshot_id, db=None, cur=None): """Count the number of branches in the snapshot with the given id Args: snapshot_id (bytes): identifier of the snapshot Returns: dict: A dict whose keys are the target types of branches and values their corresponding amount """ return dict([bc for bc in db.snapshot_count_branches(snapshot_id, cur)]) @db_transaction(statement_timeout=2000) def snapshot_get_branches(self, snapshot_id, branches_from=b'', branches_count=1000, target_types=None, db=None, cur=None): """Get the content, possibly partial, of a snapshot with the given id The branches of the snapshot are iterated in the lexicographical order of their names. Args: snapshot_id (bytes): identifier of the snapshot branches_from (bytes): optional parameter used to skip branches whose name is lesser than it before returning them branches_count (int): optional parameter used to restrain the amount of returned branches target_types (list): optional parameter used to filter the target types of branch to return (possible values that can be contained in that list are `'content', 'directory', 'revision', 'release', 'snapshot', 'alias'`) Returns: dict: None if the snapshot does not exist; a dict with three keys otherwise: * **id**: identifier of the snapshot * **branches**: a dict of branches contained in the snapshot whose keys are the branches' names. * **next_branch**: the name of the first branch not returned or :const:`None` if the snapshot has less than `branches_count` branches after `branches_from` included. """ if snapshot_id == EMPTY_SNAPSHOT_ID: return { 'id': snapshot_id, 'branches': {}, 'next_branch': None, } branches = {} next_branch = None fetched_branches = list(db.snapshot_get_by_id( snapshot_id, branches_from=branches_from, branches_count=branches_count+1, target_types=target_types, cur=cur, )) for branch in fetched_branches[:branches_count]: branch = dict(zip(db.snapshot_get_cols, branch)) del branch['snapshot_id'] name = branch.pop('name') if branch == {'target': None, 'target_type': None}: branch = None branches[name] = branch if len(fetched_branches) > branches_count: branch = dict(zip(db.snapshot_get_cols, fetched_branches[-1])) next_branch = branch['name'] if branches: return { 'id': snapshot_id, 'branches': branches, 'next_branch': next_branch, } return None @db_transaction() def origin_visit_add(self, origin, date=None, db=None, cur=None, *, ts=None): """Add an origin_visit for the origin at ts with status 'ongoing'. Args: origin: Visited Origin id date: timestamp of such visit Returns: dict: dictionary with keys origin and visit where: - origin: origin identifier - visit: the visit identifier for the new visit occurrence """ if ts is None: if date is None: raise TypeError('origin_visit_add expected 2 arguments.') else: assert date is None warnings.warn("argument 'ts' of origin_visit_add was renamed " "to 'date' in v0.0.109.", DeprecationWarning) date = ts if isinstance(date, str): date = dateutil.parser.parse(date) return { 'origin': origin, 'visit': db.origin_visit_add(origin, date, cur) } @db_transaction() def origin_visit_update(self, origin, visit_id, status, metadata=None, db=None, cur=None): """Update an origin_visit's status. Args: origin: Visited Origin id visit_id: Visit's id status: Visit's new status metadata: Data associated to the visit Returns: None """ return db.origin_visit_update(origin, visit_id, status, metadata, cur) @db_transaction_generator(statement_timeout=500) def origin_visit_get(self, origin, last_visit=None, limit=None, db=None, cur=None): """Retrieve all the origin's visit's information. Args: origin (int): The occurrence's origin (identifier). last_visit: Starting point from which listing the next visits Default to None limit (int): Number of results to return from the last visit. Default to None Yields: List of visits. """ for line in db.origin_visit_get_all( origin, last_visit=last_visit, limit=limit, cur=cur): data = dict(zip(db.origin_visit_get_cols, line)) yield data @db_transaction(statement_timeout=500) def origin_visit_get_by(self, origin, visit, db=None, cur=None): """Retrieve origin visit's information. Args: origin: The occurrence's origin (identifier). Returns: The information on that particular (origin, visit) or None if it does not exist """ ori_visit = db.origin_visit_get(origin, visit, cur) if not ori_visit: return None return dict(zip(db.origin_visit_get_cols, ori_visit)) @db_transaction(statement_timeout=2000) def object_find_by_sha1_git(self, ids, db=None, cur=None): """Return the objects found with the given ids. Args: ids: a generator of sha1_gits Returns: dict: a mapping from id to the list of objects found. Each object found is itself a dict with keys: - sha1_git: the input id - type: the type of object found - id: the id of the object found - object_id: the numeric id of the object found. """ ret = {id: [] for id in ids} for retval in db.object_find_by_sha1_git(ids, cur=cur): if retval[1]: ret[retval[0]].append(dict(zip(db.object_find_by_sha1_git_cols, retval))) return ret origin_keys = ['id', 'type', 'url'] @db_transaction(statement_timeout=500) def origin_get(self, origins, db=None, cur=None): """Return origins, either all identified by their ids or all identified by tuples (type, url). Args: origin: a list of dictionaries representing the individual origins to find. These dicts have either the keys type and url: - type (FIXME: enum TBD): the origin type ('git', 'wget', ...) - url (bytes): the url the origin points to or the id: - id: the origin id Returns: dict: the origin dictionary with the keys: - id: origin's id - type: origin's type - url: origin's url Raises: ValueError: if the keys does not match (url and type) nor id. """ if isinstance(origins, dict): # Old API return_single = True origins = [origins] elif len(origins) == 0: return [] else: return_single = False origin_ids = [origin.get('id') for origin in origins] origin_types_and_urls = [(origin.get('type'), origin.get('url')) for origin in origins] if any(origin_ids): # Lookup per ID if all(origin_ids): results = db.origin_get(origin_ids, cur) else: raise ValueError( 'Either all origins or none at all should have an "id".') elif any(type_ and url for (type_, url) in origin_types_and_urls): # Lookup per type + URL if all(type_ and url for (type_, url) in origin_types_and_urls): results = db.origin_get_with(origin_types_and_urls, cur) else: raise ValueError( 'Either all origins or none at all should have a ' '"type" and an "url".') else: # unsupported lookup raise ValueError('Origin must have either id or (type and url).') results = [dict(zip(self.origin_keys, result)) for result in results] if return_single: assert len(results) == 1 if results[0]['id'] is not None: return results[0] else: return None else: return [None if res['id'] is None else res for res in results] @db_transaction_generator() def origin_search(self, url_pattern, offset=0, limit=50, regexp=False, with_visit=False, db=None, cur=None): """Search for origins whose urls contain a provided string pattern or match a provided regular expression. The search is performed in a case insensitive way. Args: url_pattern (str): the string pattern to search for in origin urls offset (int): number of found origins to skip before returning results limit (int): the maximum number of found origins to return regexp (bool): if True, consider the provided pattern as a regular expression and return origins whose urls match it with_visit (bool): if True, filter out origins with no visit Yields: dicts containing origin information as returned by :meth:`swh.storage.storage.Storage.origin_get`. """ for origin in db.origin_search(url_pattern, offset, limit, regexp, with_visit, cur): yield dict(zip(self.origin_keys, origin)) + @db_transaction() + def origin_count(self, url_pattern, regexp=False, + with_visit=False, db=None, cur=None): + """Count origins whose urls contain a provided string pattern + or match a provided regular expression. + The pattern search in origin urls is performed in a case insensitive + way. + + Args: + url_pattern (str): the string pattern to search for in origin urls + regexp (bool): if True, consider the provided pattern as a regular + expression and return origins whose urls match it + with_visit (bool): if True, filter out origins with no visit + + Returns: + int: The number of origins matching the search criterion. + """ + return db.origin_count(url_pattern, regexp, with_visit, cur) + @db_transaction_generator() def origin_get_range(self, origin_from=1, origin_count=100, db=None, cur=None): """Retrieve ``origin_count`` origins whose ids are greater or equal than ``origin_from``. Origins are sorted by id before retrieving them. Args: origin_from (int): the minimum id of origins to retrieve origin_count (int): the maximum number of origins to retrieve Yields: dicts containing origin information as returned by :meth:`swh.storage.storage.Storage.origin_get`. """ for origin in db.origin_get_range(origin_from, origin_count, cur): yield dict(zip(self.origin_keys, origin)) @db_transaction_generator(statement_timeout=500) def person_get(self, person, db=None, cur=None): """Return the persons identified by their ids. Args: person: array of ids. Returns: The array of persons corresponding of the ids. """ for person in db.person_get(person): yield dict(zip(db.person_get_cols, person)) @db_transaction() def origin_add(self, origins, db=None, cur=None): """Add origins to the storage Args: origins: list of dictionaries representing the individual origins, with the following keys: - type: the origin type ('git', 'svn', 'deb', ...) - url (bytes): the url the origin points to Returns: list: given origins as dict updated with their id """ for origin in origins: origin['id'] = self.origin_add_one(origin, db=db, cur=cur) return origins @db_transaction() def origin_add_one(self, origin, db=None, cur=None): """Add origin to the storage Args: origin: dictionary representing the individual origin to add. This dict has the following keys: - type (FIXME: enum TBD): the origin type ('git', 'wget', ...) - url (bytes): the url the origin points to Returns: the id of the added origin, or of the identical one that already exists. """ origin_id = list(db.origin_get_with( [(origin['type'], origin['url'])], cur))[0][0] if origin_id: return origin_id return db.origin_add(origin['type'], origin['url'], cur) @db_transaction() def fetch_history_start(self, origin_id, db=None, cur=None): """Add an entry for origin origin_id in fetch_history. Returns the id of the added fetch_history entry """ fetch_history = { 'origin': origin_id, 'date': datetime.datetime.now(tz=datetime.timezone.utc), } return db.create_fetch_history(fetch_history, cur) @db_transaction() def fetch_history_end(self, fetch_history_id, data, db=None, cur=None): """Close the fetch_history entry with id `fetch_history_id`, replacing its data with `data`. """ now = datetime.datetime.now(tz=datetime.timezone.utc) fetch_history = db.get_fetch_history(fetch_history_id, cur) if not fetch_history: raise ValueError('No fetch_history with id %d' % fetch_history_id) fetch_history['duration'] = now - fetch_history['date'] fetch_history.update(data) db.update_fetch_history(fetch_history, cur) @db_transaction() def fetch_history_get(self, fetch_history_id, db=None, cur=None): """Get the fetch_history entry with id `fetch_history_id`. """ return db.get_fetch_history(fetch_history_id, cur) @db_transaction(statement_timeout=500) def stat_counters(self, db=None, cur=None): """compute statistics about the number of tuples in various tables Returns: dict: a dictionary mapping textual labels (e.g., content) to integer values (e.g., the number of tuples in table content) """ return {k: v for (k, v) in db.stat_counters()} @db_transaction() def refresh_stat_counters(self, db=None, cur=None): """Recomputes the statistics for `stat_counters`.""" keys = [ 'content', 'directory', 'directory_entry_dir', 'directory_entry_file', 'directory_entry_rev', 'origin', 'origin_visit', 'person', 'release', 'revision', 'revision_history', 'skipped_content', 'snapshot'] for key in keys: cur.execute('select * from swh_update_counter(%s)', (key,)) @db_transaction() def origin_metadata_add(self, origin_id, ts, provider, tool, metadata, db=None, cur=None): """ Add an origin_metadata for the origin at ts with provenance and metadata. Args: origin_id (int): the origin's id for which the metadata is added ts (datetime): timestamp of the found metadata provider (int): the provider of metadata (ex:'hal') tool (int): tool used to extract metadata metadata (jsonb): the metadata retrieved at the time and location Returns: id (int): the origin_metadata unique id """ if isinstance(ts, str): ts = dateutil.parser.parse(ts) return db.origin_metadata_add(origin_id, ts, provider, tool, metadata, cur) @db_transaction_generator(statement_timeout=500) def origin_metadata_get_by(self, origin_id, provider_type=None, db=None, cur=None): """Retrieve list of all origin_metadata entries for the origin_id Args: origin_id (int): the unique origin identifier provider_type (str): (optional) type of provider Returns: list of dicts: the origin_metadata dictionary with the keys: - origin_id (int): origin's id - discovery_date (datetime): timestamp of discovery - tool_id (int): metadata's extracting tool - metadata (jsonb) - provider_id (int): metadata's provider - provider_name (str) - provider_type (str) - provider_url (str) """ for line in db.origin_metadata_get_by(origin_id, provider_type, cur): yield dict(zip(db.origin_metadata_get_cols, line)) @db_transaction_generator() def tool_add(self, tools, db=None, cur=None): """Add new tools to the storage. Args: tools (iterable of :class:`dict`): Tool information to add to storage. Each tool is a :class:`dict` with the following keys: - name (:class:`str`): name of the tool - version (:class:`str`): version of the tool - configuration (:class:`dict`): configuration of the tool, must be json-encodable Yields: :class:`dict`: All the tools inserted in storage (including the internal ``id``). The order of the list is not guaranteed to match the order of the initial list. """ db.mktemp_tool(cur) db.copy_to(tools, 'tmp_tool', ['name', 'version', 'configuration'], cur) tools = db.tool_add_from_temp(cur) for line in tools: yield dict(zip(db.tool_cols, line)) @db_transaction(statement_timeout=500) def tool_get(self, tool, db=None, cur=None): """Retrieve tool information. Args: tool (dict): Tool information we want to retrieve from storage. The dicts have the same keys as those used in :func:`tool_add`. Returns: dict: The full tool information if it exists (``id`` included), None otherwise. """ tool_conf = tool['configuration'] if isinstance(tool_conf, dict): tool_conf = json.dumps(tool_conf) idx = db.tool_get(tool['name'], tool['version'], tool_conf) if not idx: return None return dict(zip(db.tool_cols, idx)) @db_transaction() def metadata_provider_add(self, provider_name, provider_type, provider_url, metadata, db=None, cur=None): """Add a metadata provider. Args: provider_name (str): Its name provider_type (str): Its type (eg. `'deposit-client'`) provider_url (str): Its URL metadata: JSON-encodable object Returns: int: an identifier of the provider """ return db.metadata_provider_add(provider_name, provider_type, provider_url, metadata, cur) @db_transaction() def metadata_provider_get(self, provider_id, db=None, cur=None): """Get a metadata provider Args: provider_id: Its identifier, as given by `metadata_provider_add`. Returns: dict: same as `metadata_provider_add`; or None if it does not exist. """ result = db.metadata_provider_get(provider_id) if not result: return None return dict(zip(db.metadata_provider_cols, result)) @db_transaction() def metadata_provider_get_by(self, provider, db=None, cur=None): """Get a metadata provider Args: provider (dict): A dictionary with keys: * provider_name: Its name * provider_url: Its URL Returns: dict: same as `metadata_provider_add`; or None if it does not exist. """ result = db.metadata_provider_get_by(provider['provider_name'], provider['provider_url']) if not result: return None return dict(zip(db.metadata_provider_cols, result)) def diff_directories(self, from_dir, to_dir, track_renaming=False): """Compute the list of file changes introduced between two arbitrary directories (insertion / deletion / modification / renaming of files). Args: from_dir (bytes): identifier of the directory to compare from to_dir (bytes): identifier of the directory to compare to track_renaming (bool): whether or not to track files renaming Returns: A list of dict describing the introduced file changes (see :func:`swh.storage.algos.diff.diff_directories` for more details). """ return diff.diff_directories(self, from_dir, to_dir, track_renaming) def diff_revisions(self, from_rev, to_rev, track_renaming=False): """Compute the list of file changes introduced between two arbitrary revisions (insertion / deletion / modification / renaming of files). Args: from_rev (bytes): identifier of the revision to compare from to_rev (bytes): identifier of the revision to compare to track_renaming (bool): whether or not to track files renaming Returns: A list of dict describing the introduced file changes (see :func:`swh.storage.algos.diff.diff_directories` for more details). """ return diff.diff_revisions(self, from_rev, to_rev, track_renaming) def diff_revision(self, revision, track_renaming=False): """Compute the list of file changes introduced by a specific revision (insertion / deletion / modification / renaming of files) by comparing it against its first parent. Args: revision (bytes): identifier of the revision from which to compute the list of files changes track_renaming (bool): whether or not to track files renaming Returns: A list of dict describing the introduced file changes (see :func:`swh.storage.algos.diff.diff_directories` for more details). """ return diff.diff_revision(self, revision, track_renaming) diff --git a/swh/storage/tests/test_storage.py b/swh/storage/tests/test_storage.py index aab82bed..92ebbd79 100644 --- a/swh/storage/tests/test_storage.py +++ b/swh/storage/tests/test_storage.py @@ -1,2333 +1,2371 @@ # Copyright (C) 2015-2018 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import copy import datetime import itertools import random import unittest from collections import defaultdict from unittest.mock import Mock, patch import pytest from hypothesis import given, strategies from swh.model import from_disk, identifiers from swh.model.hashutil import hash_to_bytes from swh.storage.tests.storage_testing import StorageTestFixture from swh.storage import HashCollision from .generate_data_test import gen_contents, gen_origins @pytest.mark.db class StorageTestDbFixture(StorageTestFixture): def setUp(self): super().setUp() db = self.test_db[self.TEST_DB_NAME] self.conn = db.conn self.cursor = db.cursor self.maxDiff = None def tearDown(self): self.reset_storage_tables() super().tearDown() class TestStorageData: def setUp(self): super().setUp() self.cont = { 'data': b'42\n', 'length': 3, 'sha1': hash_to_bytes( '34973274ccef6ab4dfaaf86599792fa9c3fe4689'), 'sha1_git': hash_to_bytes( 'd81cc0710eb6cf9efd5b920a8453e1e07157b6cd'), 'sha256': hash_to_bytes( '673650f936cb3b0a2f93ce09d81be107' '48b1b203c19e8176b4eefc1964a0cf3a'), 'blake2s256': hash_to_bytes('d5fe1939576527e42cfd76a9455a2' '432fe7f56669564577dd93c4280e76d661d'), 'status': 'visible', } self.cont2 = { 'data': b'4242\n', 'length': 5, 'sha1': hash_to_bytes( '61c2b3a30496d329e21af70dd2d7e097046d07b7'), 'sha1_git': hash_to_bytes( '36fade77193cb6d2bd826161a0979d64c28ab4fa'), 'sha256': hash_to_bytes( '859f0b154fdb2d630f45e1ecae4a8629' '15435e663248bb8461d914696fc047cd'), 'blake2s256': hash_to_bytes('849c20fad132b7c2d62c15de310adfe87be' '94a379941bed295e8141c6219810d'), 'status': 'visible', } self.cont3 = { 'data': b'424242\n', 'length': 7, 'sha1': hash_to_bytes( '3e21cc4942a4234c9e5edd8a9cacd1670fe59f13'), 'sha1_git': hash_to_bytes( 'c932c7649c6dfa4b82327d121215116909eb3bea'), 'sha256': hash_to_bytes( '92fb72daf8c6818288a35137b72155f5' '07e5de8d892712ab96277aaed8cf8a36'), 'blake2s256': hash_to_bytes('76d0346f44e5a27f6bafdd9c2befd304af' 'f83780f93121d801ab6a1d4769db11'), 'status': 'visible', } self.missing_cont = { 'data': b'missing\n', 'length': 8, 'sha1': hash_to_bytes( 'f9c24e2abb82063a3ba2c44efd2d3c797f28ac90'), 'sha1_git': hash_to_bytes( '33e45d56f88993aae6a0198013efa80716fd8919'), 'sha256': hash_to_bytes( '6bbd052ab054ef222c1c87be60cd191a' 'ddedd24cc882d1f5f7f7be61dc61bb3a'), 'blake2s256': hash_to_bytes('306856b8fd879edb7b6f1aeaaf8db9bbecc9' '93cd7f776c333ac3a782fa5c6eba'), 'status': 'absent', } self.skipped_cont = { 'length': 1024 * 1024 * 200, 'sha1_git': hash_to_bytes( '33e45d56f88993aae6a0198013efa80716fd8920'), 'sha1': hash_to_bytes( '43e45d56f88993aae6a0198013efa80716fd8920'), 'sha256': hash_to_bytes( '7bbd052ab054ef222c1c87be60cd191a' 'ddedd24cc882d1f5f7f7be61dc61bb3a'), 'blake2s256': hash_to_bytes( 'ade18b1adecb33f891ca36664da676e1' '2c772cc193778aac9a137b8dc5834b9b'), 'reason': 'Content too long', 'status': 'absent', } self.skipped_cont2 = { 'length': 1024 * 1024 * 300, 'sha1_git': hash_to_bytes( '44e45d56f88993aae6a0198013efa80716fd8921'), 'sha1': hash_to_bytes( '54e45d56f88993aae6a0198013efa80716fd8920'), 'sha256': hash_to_bytes( '8cbd052ab054ef222c1c87be60cd191a' 'ddedd24cc882d1f5f7f7be61dc61bb3a'), 'blake2s256': hash_to_bytes( '9ce18b1adecb33f891ca36664da676e1' '2c772cc193778aac9a137b8dc5834b9b'), 'reason': 'Content too long', 'status': 'absent', } self.dir = { 'id': b'4\x013\x422\x531\x000\xf51\xe62\xa73\xff7\xc3\xa90', 'entries': [ { 'name': b'foo', 'type': 'file', 'target': self.cont['sha1_git'], 'perms': from_disk.DentryPerms.content, }, { 'name': b'bar\xc3', 'type': 'dir', 'target': b'12345678901234567890', 'perms': from_disk.DentryPerms.directory, }, ], } self.dir2 = { 'id': b'4\x013\x422\x531\x000\xf51\xe62\xa73\xff7\xc3\xa95', 'entries': [ { 'name': b'oof', 'type': 'file', 'target': self.cont2['sha1_git'], 'perms': from_disk.DentryPerms.content, } ], } self.dir3 = { 'id': hash_to_bytes('33e45d56f88993aae6a0198013efa80716fd8921'), 'entries': [ { 'name': b'foo', 'type': 'file', 'target': self.cont['sha1_git'], 'perms': from_disk.DentryPerms.content, }, { 'name': b'subdir', 'type': 'dir', 'target': self.dir['id'], 'perms': from_disk.DentryPerms.directory, }, { 'name': b'hello', 'type': 'file', 'target': b'12345678901234567890', 'perms': from_disk.DentryPerms.content, }, ], } self.minus_offset = datetime.timezone(datetime.timedelta(minutes=-120)) self.plus_offset = datetime.timezone(datetime.timedelta(minutes=120)) self.revision = { 'id': b'56789012345678901234', 'message': b'hello', 'author': { 'name': b'Nicolas Dandrimont', 'email': b'nicolas@example.com', 'fullname': b'Nicolas Dandrimont ', }, 'date': { 'timestamp': 1234567890, 'offset': 120, 'negative_utc': None, }, 'committer': { 'name': b'St\xc3fano Zacchiroli', 'email': b'stefano@example.com', 'fullname': b'St\xc3fano Zacchiroli ' }, 'committer_date': { 'timestamp': 1123456789, 'offset': 0, 'negative_utc': True, }, 'parents': [b'01234567890123456789', b'23434512345123456789'], 'type': 'git', 'directory': self.dir['id'], 'metadata': { 'checksums': { 'sha1': 'tarball-sha1', 'sha256': 'tarball-sha256', }, 'signed-off-by': 'some-dude', 'extra_headers': [ ['gpgsig', b'test123'], ['mergetags', [b'foo\\bar', b'\x22\xaf\x89\x80\x01\x00']], ], }, 'synthetic': True } self.revision2 = { 'id': b'87659012345678904321', 'message': b'hello again', 'author': { 'name': b'Roberto Dicosmo', 'email': b'roberto@example.com', 'fullname': b'Roberto Dicosmo ', }, 'date': { 'timestamp': { 'seconds': 1234567843, 'microseconds': 220000, }, 'offset': -720, 'negative_utc': None, }, 'committer': { 'name': b'tony', 'email': b'ar@dumont.fr', 'fullname': b'tony ', }, 'committer_date': { 'timestamp': 1123456789, 'offset': 0, 'negative_utc': False, }, 'parents': [b'01234567890123456789'], 'type': 'git', 'directory': self.dir2['id'], 'metadata': None, 'synthetic': False } self.revision3 = { 'id': hash_to_bytes('7026b7c1a2af56521e951c01ed20f255fa054238'), 'message': b'a simple revision with no parents this time', 'author': { 'name': b'Roberto Dicosmo', 'email': b'roberto@example.com', 'fullname': b'Roberto Dicosmo ', }, 'date': { 'timestamp': { 'seconds': 1234567843, 'microseconds': 220000, }, 'offset': -720, 'negative_utc': None, }, 'committer': { 'name': b'tony', 'email': b'ar@dumont.fr', 'fullname': b'tony ', }, 'committer_date': { 'timestamp': 1127351742, 'offset': 0, 'negative_utc': False, }, 'parents': [], 'type': 'git', 'directory': self.dir2['id'], 'metadata': None, 'synthetic': True } self.revision4 = { 'id': hash_to_bytes('368a48fe15b7db2383775f97c6b247011b3f14f4'), 'message': b'parent of self.revision2', 'author': { 'name': b'me', 'email': b'me@soft.heri', 'fullname': b'me ', }, 'date': { 'timestamp': { 'seconds': 1244567843, 'microseconds': 220000, }, 'offset': -720, 'negative_utc': None, }, 'committer': { 'name': b'committer-dude', 'email': b'committer@dude.com', 'fullname': b'committer-dude ', }, 'committer_date': { 'timestamp': { 'seconds': 1244567843, 'microseconds': 220000, }, 'offset': -720, 'negative_utc': None, }, 'parents': [self.revision3['id']], 'type': 'git', 'directory': self.dir['id'], 'metadata': None, 'synthetic': False } self.origin = { 'url': 'file:///dev/null', 'type': 'git', } self.origin2 = { 'url': 'file:///dev/zero', 'type': 'git', } self.provider = { 'name': 'hal', 'type': 'deposit-client', 'url': 'http:///hal/inria', 'metadata': { 'location': 'France' } } self.metadata_tool = { 'name': 'swh-deposit', 'version': '0.0.1', 'configuration': { 'sword_version': '2' } } self.origin_metadata = { 'origin': self.origin, 'discovery_date': datetime.datetime(2015, 1, 1, 23, 0, 0, tzinfo=datetime.timezone.utc), 'provider': self.provider, 'tool': 'swh-deposit', 'metadata': { 'name': 'test_origin_metadata', 'version': '0.0.1' } } self.origin_metadata2 = { 'origin': self.origin, 'discovery_date': datetime.datetime(2017, 1, 1, 23, 0, 0, tzinfo=datetime.timezone.utc), 'provider': self.provider, 'tool': 'swh-deposit', 'metadata': { 'name': 'test_origin_metadata', 'version': '0.0.1' } } self.date_visit1 = datetime.datetime(2015, 1, 1, 23, 0, 0, tzinfo=datetime.timezone.utc) self.date_visit2 = datetime.datetime(2017, 1, 1, 23, 0, 0, tzinfo=datetime.timezone.utc) self.date_visit3 = datetime.datetime(2018, 1, 1, 23, 0, 0, tzinfo=datetime.timezone.utc) self.release = { 'id': b'87659012345678901234', 'name': b'v0.0.1', 'author': { 'name': b'olasd', 'email': b'nic@olasd.fr', 'fullname': b'olasd ', }, 'date': { 'timestamp': 1234567890, 'offset': 42, 'negative_utc': None, }, 'target': b'43210987654321098765', 'target_type': 'revision', 'message': b'synthetic release', 'synthetic': True, } self.release2 = { 'id': b'56789012348765901234', 'name': b'v0.0.2', 'author': { 'name': b'tony', 'email': b'ar@dumont.fr', 'fullname': b'tony ', }, 'date': { 'timestamp': 1634366813, 'offset': -120, 'negative_utc': None, }, 'target': b'432109\xa9765432\xc309\x00765', 'target_type': 'revision', 'message': b'v0.0.2\nMisc performance improvements + bug fixes', 'synthetic': False } self.release3 = { 'id': b'87659012345678904321', 'name': b'v0.0.2', 'author': { 'name': b'tony', 'email': b'tony@ardumont.fr', 'fullname': b'tony ', }, 'date': { 'timestamp': 1634336813, 'offset': 0, 'negative_utc': False, }, 'target': self.revision2['id'], 'target_type': 'revision', 'message': b'yet another synthetic release', 'synthetic': True, } self.fetch_history_date = datetime.datetime( 2015, 1, 2, 21, 0, 0, tzinfo=datetime.timezone.utc) self.fetch_history_end = datetime.datetime( 2015, 1, 2, 23, 0, 0, tzinfo=datetime.timezone.utc) self.fetch_history_duration = (self.fetch_history_end - self.fetch_history_date) self.fetch_history_data = { 'status': True, 'result': {'foo': 'bar'}, 'stdout': 'blabla', 'stderr': 'blablabla', } self.snapshot = { 'id': hash_to_bytes('2498dbf535f882bc7f9a18fb16c9ad27fda7bab7'), 'branches': { b'master': { 'target': self.revision['id'], 'target_type': 'revision', }, }, 'next_branch': None } self.empty_snapshot = { 'id': hash_to_bytes('1a8893e6a86f444e8be8e7bda6cb34fb1735a00e'), 'branches': {}, 'next_branch': None } self.complete_snapshot = { 'id': hash_to_bytes('6e65b86363953b780d92b0a928f3e8fcdd10db36'), 'branches': { b'directory': { 'target': hash_to_bytes( '1bd0e65f7d2ff14ae994de17a1e7fe65111dcad8'), 'target_type': 'directory', }, b'content': { 'target': hash_to_bytes( 'fe95a46679d128ff167b7c55df5d02356c5a1ae1'), 'target_type': 'content', }, b'alias': { 'target': b'revision', 'target_type': 'alias', }, b'revision': { 'target': hash_to_bytes( 'aafb16d69fd30ff58afdd69036a26047f3aebdc6'), 'target_type': 'revision', }, b'release': { 'target': hash_to_bytes( '7045404f3d1c54e6473c71bbb716529fbad4be24'), 'target_type': 'release', }, b'snapshot': { 'target': hash_to_bytes( '1a8893e6a86f444e8be8e7bda6cb34fb1735a00e'), 'target_type': 'snapshot', }, b'dangling': None, }, 'next_branch': None } class CommonTestStorage(TestStorageData): """Base class for Storage testing. This class is used as-is to test local storage (see TestLocalStorage below) and remote storage (see TestRemoteStorage in test_remote_storage.py. We need to have the two classes inherit from this base class separately to avoid nosetests running the tests from the base class twice. """ @staticmethod def normalize_entity(entity): entity = copy.deepcopy(entity) for key in ('date', 'committer_date'): if key in entity: entity[key] = identifiers.normalize_timestamp(entity[key]) return entity def test_check_config(self): self.assertTrue(self.storage.check_config(check_write=True)) self.assertTrue(self.storage.check_config(check_write=False)) def test_content_add(self): cont = self.cont self.storage.content_add([cont]) if hasattr(self.storage, 'objstorage'): self.assertIn(cont['sha1'], self.storage.objstorage) self.cursor.execute('SELECT sha1, sha1_git, sha256, length, status' ' FROM content WHERE sha1 = %s', (cont['sha1'],)) datum = self.cursor.fetchone() self.assertEqual( (datum[0].tobytes(), datum[1].tobytes(), datum[2].tobytes(), datum[3], datum[4]), (cont['sha1'], cont['sha1_git'], cont['sha256'], cont['length'], 'visible')) def test_content_add_collision(self): cont1 = self.cont # create (corrupted) content with same sha1{,_git} but != sha256 cont1b = cont1.copy() sha256_array = bytearray(cont1b['sha256']) sha256_array[0] += 1 cont1b['sha256'] = bytes(sha256_array) with self.assertRaises(HashCollision) as cm: self.storage.content_add([cont1, cont1b]) self.assertIn(cm.exception.args[0], ['sha1', 'sha1_git', 'blake2s256']) def test_skipped_content_add(self): cont = self.skipped_cont.copy() cont2 = self.skipped_cont2.copy() cont2['blake2s256'] = None self.storage.content_add([cont, cont, cont2]) self.cursor.execute('SELECT sha1, sha1_git, sha256, blake2s256, ' 'length, status, reason ' 'FROM skipped_content ORDER BY sha1_git') datums = self.cursor.fetchall() self.assertEqual(2, len(datums)) datum = datums[0] self.assertEqual( (datum[0].tobytes(), datum[1].tobytes(), datum[2].tobytes(), datum[3].tobytes(), datum[4], datum[5], datum[6]), (cont['sha1'], cont['sha1_git'], cont['sha256'], cont['blake2s256'], cont['length'], 'absent', 'Content too long') ) datum2 = datums[1] self.assertEqual( (datum2[0].tobytes(), datum2[1].tobytes(), datum2[2].tobytes(), datum2[3], datum2[4], datum2[5], datum2[6]), (cont2['sha1'], cont2['sha1_git'], cont2['sha256'], cont2['blake2s256'], cont2['length'], 'absent', 'Content too long') ) @pytest.mark.property_based @given(strategies.sets( elements=strategies.sampled_from( ['sha256', 'sha1_git', 'blake2s256']), min_size=0)) def test_content_missing(self, algos): algos |= {'sha1'} cont2 = self.cont2 missing_cont = self.missing_cont self.storage.content_add([cont2]) test_contents = [cont2] missing_per_hash = defaultdict(list) for i in range(256): test_content = missing_cont.copy() for hash in algos: test_content[hash] = bytes([i]) + test_content[hash][1:] missing_per_hash[hash].append(test_content[hash]) test_contents.append(test_content) self.assertCountEqual( self.storage.content_missing(test_contents), missing_per_hash['sha1'] ) for hash in algos: self.assertCountEqual( self.storage.content_missing(test_contents, key_hash=hash), missing_per_hash[hash] ) def test_content_missing_per_sha1(self): # given cont2 = self.cont2 missing_cont = self.missing_cont self.storage.content_add([cont2]) # when gen = self.storage.content_missing_per_sha1([cont2['sha1'], missing_cont['sha1']]) # then self.assertEqual(list(gen), [missing_cont['sha1']]) def test_content_get_metadata(self): cont1 = self.cont.copy() cont2 = self.cont2.copy() self.storage.content_add([cont1, cont2]) gen = self.storage.content_get_metadata([cont1['sha1'], cont2['sha1']]) # we only retrieve the metadata cont1.pop('data') cont2.pop('data') self.assertCountEqual(list(gen), [cont1, cont2]) def test_content_get_metadata_missing_sha1(self): cont1 = self.cont.copy() cont2 = self.cont2.copy() missing_cont = self.missing_cont.copy() self.storage.content_add([cont1, cont2]) gen = self.storage.content_get_metadata([missing_cont['sha1']]) # All the metadata keys are None missing_cont.pop('data') for key in list(missing_cont): if key != 'sha1': missing_cont[key] = None self.assertEqual(list(gen), [missing_cont]) @staticmethod def _transform_entries(dir_, *, prefix=b''): for ent in dir_['entries']: yield { 'dir_id': dir_['id'], 'type': ent['type'], 'target': ent['target'], 'name': prefix + ent['name'], 'perms': ent['perms'], 'status': None, 'sha1': None, 'sha1_git': None, 'sha256': None, 'length': None, } def test_directory_add(self): init_missing = list(self.storage.directory_missing([self.dir['id']])) self.assertEqual([self.dir['id']], init_missing) self.storage.directory_add([self.dir]) actual_data = list(self.storage.directory_ls(self.dir['id'])) expected_data = list(self._transform_entries(self.dir)) self.assertCountEqual(expected_data, actual_data) after_missing = list(self.storage.directory_missing([self.dir['id']])) self.assertEqual([], after_missing) def test_directory_get_recursive(self): init_missing = list(self.storage.directory_missing([self.dir['id']])) self.assertEqual([self.dir['id']], init_missing) self.storage.directory_add([self.dir, self.dir2, self.dir3]) actual_data = list(self.storage.directory_ls( self.dir['id'], recursive=True)) expected_data = list(self._transform_entries(self.dir)) self.assertCountEqual(expected_data, actual_data) actual_data = list(self.storage.directory_ls( self.dir2['id'], recursive=True)) expected_data = list(self._transform_entries(self.dir2)) self.assertCountEqual(expected_data, actual_data) actual_data = list(self.storage.directory_ls( self.dir3['id'], recursive=True)) expected_data = list(itertools.chain( self._transform_entries(self.dir3), self._transform_entries(self.dir, prefix=b'subdir/'))) self.assertCountEqual(expected_data, actual_data) def test_directory_entry_get_by_path(self): # given init_missing = list(self.storage.directory_missing([self.dir3['id']])) self.assertEqual([self.dir3['id']], init_missing) self.storage.directory_add([self.dir3]) expected_entries = [ { 'dir_id': self.dir3['id'], 'name': b'foo', 'type': 'file', 'target': self.cont['sha1_git'], 'sha1': None, 'sha1_git': None, 'sha256': None, 'status': None, 'perms': from_disk.DentryPerms.content, 'length': None, }, { 'dir_id': self.dir3['id'], 'name': b'subdir', 'type': 'dir', 'target': self.dir['id'], 'sha1': None, 'sha1_git': None, 'sha256': None, 'status': None, 'perms': from_disk.DentryPerms.directory, 'length': None, }, { 'dir_id': self.dir3['id'], 'name': b'hello', 'type': 'file', 'target': b'12345678901234567890', 'sha1': None, 'sha1_git': None, 'sha256': None, 'status': None, 'perms': from_disk.DentryPerms.content, 'length': None, }, ] # when (all must be found here) for entry, expected_entry in zip(self.dir3['entries'], expected_entries): actual_entry = self.storage.directory_entry_get_by_path( self.dir3['id'], [entry['name']]) self.assertEqual(actual_entry, expected_entry) # when (nothing should be found here since self.dir is not persisted.) for entry in self.dir['entries']: actual_entry = self.storage.directory_entry_get_by_path( self.dir['id'], [entry['name']]) self.assertIsNone(actual_entry) def test_revision_add(self): init_missing = self.storage.revision_missing([self.revision['id']]) self.assertEqual([self.revision['id']], list(init_missing)) self.storage.revision_add([self.revision]) end_missing = self.storage.revision_missing([self.revision['id']]) self.assertEqual([], list(end_missing)) def test_revision_log(self): # given # self.revision4 -is-child-of-> self.revision3 self.storage.revision_add([self.revision3, self.revision4]) # when actual_results = list(self.storage.revision_log( [self.revision4['id']])) # hack: ids generated for actual_result in actual_results: if 'id' in actual_result['author']: del actual_result['author']['id'] if 'id' in actual_result['committer']: del actual_result['committer']['id'] self.assertEqual(len(actual_results), 2) # rev4 -child-> rev3 self.assertEqual(actual_results[0], self.normalize_entity(self.revision4)) self.assertEqual(actual_results[1], self.normalize_entity(self.revision3)) def test_revision_log_with_limit(self): # given # self.revision4 -is-child-of-> self.revision3 self.storage.revision_add([self.revision3, self.revision4]) actual_results = list(self.storage.revision_log( [self.revision4['id']], 1)) # hack: ids generated for actual_result in actual_results: if 'id' in actual_result['author']: del actual_result['author']['id'] if 'id' in actual_result['committer']: del actual_result['committer']['id'] self.assertEqual(len(actual_results), 1) self.assertEqual(actual_results[0], self.revision4) def test_revision_log_unknown_revision(self): rev_log = list(self.storage.revision_log([self.revision['id']])) self.assertEqual(rev_log, []) @staticmethod def _short_revision(revision): return [revision['id'], revision['parents']] def test_revision_shortlog(self): # given # self.revision4 -is-child-of-> self.revision3 self.storage.revision_add([self.revision3, self.revision4]) # when actual_results = list(self.storage.revision_shortlog( [self.revision4['id']])) self.assertEqual(len(actual_results), 2) # rev4 -child-> rev3 self.assertEqual(list(actual_results[0]), self._short_revision(self.revision4)) self.assertEqual(list(actual_results[1]), self._short_revision(self.revision3)) def test_revision_shortlog_with_limit(self): # given # self.revision4 -is-child-of-> self.revision3 self.storage.revision_add([self.revision3, self.revision4]) actual_results = list(self.storage.revision_shortlog( [self.revision4['id']], 1)) self.assertEqual(len(actual_results), 1) self.assertEqual(list(actual_results[0]), self._short_revision(self.revision4)) def test_revision_get(self): self.storage.revision_add([self.revision]) actual_revisions = list(self.storage.revision_get( [self.revision['id'], self.revision2['id']])) # when if 'id' in actual_revisions[0]['author']: del actual_revisions[0]['author']['id'] # hack: ids are generated if 'id' in actual_revisions[0]['committer']: del actual_revisions[0]['committer']['id'] self.assertEqual(len(actual_revisions), 2) self.assertEqual(actual_revisions[0], self.normalize_entity(self.revision)) self.assertIsNone(actual_revisions[1]) def test_revision_get_no_parents(self): self.storage.revision_add([self.revision3]) get = list(self.storage.revision_get([self.revision3['id']])) self.assertEqual(len(get), 1) self.assertEqual(get[0]['parents'], []) # no parents on this one def test_release_add(self): init_missing = self.storage.release_missing([self.release['id'], self.release2['id']]) self.assertEqual([self.release['id'], self.release2['id']], list(init_missing)) self.storage.release_add([self.release, self.release2]) end_missing = self.storage.release_missing([self.release['id'], self.release2['id']]) self.assertEqual([], list(end_missing)) def test_release_get(self): # given self.storage.release_add([self.release, self.release2]) # when actual_releases = list(self.storage.release_get([self.release['id'], self.release2['id']])) # then for actual_release in actual_releases: if 'id' in actual_release['author']: del actual_release['author']['id'] # hack: ids are generated self.assertEqual([self.normalize_entity(self.release), self.normalize_entity(self.release2)], [actual_releases[0], actual_releases[1]]) unknown_releases = \ list(self.storage.release_get([self.release3['id']])) self.assertIsNone(unknown_releases[0]) def test_origin_add_one(self): origin0 = self.storage.origin_get(self.origin) self.assertIsNone(origin0) id = self.storage.origin_add_one(self.origin) actual_origin = self.storage.origin_get({'url': self.origin['url'], 'type': self.origin['type']}) self.assertEqual(actual_origin['id'], id) id2 = self.storage.origin_add_one(self.origin) self.assertEqual(id, id2) def test_origin_add(self): origin0 = self.storage.origin_get([self.origin])[0] self.assertIsNone(origin0) origin1, origin2 = self.storage.origin_add([self.origin, self.origin2]) actual_origin = self.storage.origin_get([{ 'url': self.origin['url'], 'type': self.origin['type'], }])[0] self.assertEqual(actual_origin['id'], origin1['id']) actual_origin2 = self.storage.origin_get([{ 'url': self.origin2['url'], 'type': self.origin2['type'], }])[0] self.assertEqual(actual_origin2['id'], origin2['id']) def test_origin_add_twice(self): add1 = self.storage.origin_add([self.origin, self.origin2]) add2 = self.storage.origin_add([self.origin, self.origin2]) self.assertEqual(add1, add2) def test_origin_get_legacy(self): self.assertIsNone(self.storage.origin_get(self.origin)) id = self.storage.origin_add_one(self.origin) # lookup per type and url (returns id) actual_origin0 = self.storage.origin_get( {'url': self.origin['url'], 'type': self.origin['type']}) self.assertEqual(actual_origin0['id'], id) # lookup per id (returns dict) actual_origin1 = self.storage.origin_get({'id': id}) self.assertEqual(actual_origin1, {'id': id, 'type': self.origin['type'], 'url': self.origin['url']}) def test_origin_get(self): self.assertIsNone(self.storage.origin_get(self.origin)) origin_id = self.storage.origin_add_one(self.origin) # lookup per type and url (returns id) actual_origin0 = self.storage.origin_get( [{'url': self.origin['url'], 'type': self.origin['type']}]) self.assertEqual(len(actual_origin0), 1, actual_origin0) self.assertEqual(actual_origin0[0]['id'], origin_id) # lookup per id (returns dict) actual_origin1 = self.storage.origin_get([{'id': origin_id}]) self.assertEqual(len(actual_origin1), 1, actual_origin1) self.assertEqual(actual_origin1[0], {'id': origin_id, 'type': self.origin['type'], 'url': self.origin['url']}) def test_origin_get_consistency(self): self.assertIsNone(self.storage.origin_get(self.origin)) id = self.storage.origin_add_one(self.origin) with self.assertRaises(ValueError): self.storage.origin_get([ {'url': self.origin['url'], 'type': self.origin['type']}, {'id': id}]) def test_origin_search(self): found_origins = list(self.storage.origin_search(self.origin['url'])) self.assertEqual(len(found_origins), 0) found_origins = list(self.storage.origin_search(self.origin['url'], regexp=True)) self.assertEqual(len(found_origins), 0) id = self.storage.origin_add_one(self.origin) origin_data = {'id': id, 'type': self.origin['type'], 'url': self.origin['url']} found_origins = list(self.storage.origin_search(self.origin['url'])) self.assertEqual(len(found_origins), 1) self.assertEqual(found_origins[0], origin_data) found_origins = list(self.storage.origin_search( '.' + self.origin['url'][1:-1] + '.', regexp=True)) self.assertEqual(len(found_origins), 1) self.assertEqual(found_origins[0], origin_data) id2 = self.storage.origin_add_one(self.origin2) origin2_data = {'id': id2, 'type': self.origin2['type'], 'url': self.origin2['url']} found_origins = list(self.storage.origin_search(self.origin2['url'])) self.assertEqual(len(found_origins), 1) self.assertEqual(found_origins[0], origin2_data) found_origins = list(self.storage.origin_search( '.' + self.origin2['url'][1:-1] + '.', regexp=True)) self.assertEqual(len(found_origins), 1) self.assertEqual(found_origins[0], origin2_data) found_origins = list(self.storage.origin_search('/')) self.assertEqual(len(found_origins), 2) found_origins = list(self.storage.origin_search('.*/.*', regexp=True)) self.assertEqual(len(found_origins), 2) found_origins = list(self.storage.origin_search('/', offset=0, limit=1)) # noqa self.assertEqual(len(found_origins), 1) self.assertEqual(found_origins[0], origin_data) found_origins = list(self.storage.origin_search('.*/.*', offset=0, limit=1, regexp=True)) # noqa self.assertEqual(len(found_origins), 1) self.assertEqual(found_origins[0], origin_data) found_origins = list(self.storage.origin_search('/', offset=1, limit=1)) # noqa self.assertEqual(len(found_origins), 1) self.assertEqual(found_origins[0], origin2_data) found_origins = list(self.storage.origin_search('.*/.*', offset=1, limit=1, regexp=True)) # noqa self.assertEqual(len(found_origins), 1) self.assertEqual(found_origins[0], origin2_data) def test_origin_visit_add(self): # given self.assertIsNone(self.storage.origin_get([self.origin2])[0]) origin_id = self.storage.origin_add_one(self.origin2) self.assertIsNotNone(origin_id) # when origin_visit1 = self.storage.origin_visit_add( origin_id, date=self.date_visit2) # then self.assertEqual(origin_visit1['origin'], origin_id) self.assertIsNotNone(origin_visit1['visit']) actual_origin_visits = list(self.storage.origin_visit_get(origin_id)) self.assertEqual(actual_origin_visits, [{ 'origin': origin_id, 'date': self.date_visit2, 'visit': origin_visit1['visit'], 'status': 'ongoing', 'metadata': None, 'snapshot': None, }]) def test_origin_visit_update(self): # given origin_id = self.storage.origin_add_one(self.origin2) origin_id2 = self.storage.origin_add_one(self.origin) origin_visit1 = self.storage.origin_visit_add( origin_id, date=self.date_visit2) origin_visit2 = self.storage.origin_visit_add( origin_id, date=self.date_visit3) origin_visit3 = self.storage.origin_visit_add( origin_id2, date=self.date_visit3) # when visit1_metadata = { 'contents': 42, 'directories': 22, } self.storage.origin_visit_update( origin_id, origin_visit1['visit'], status='full', metadata=visit1_metadata) self.storage.origin_visit_update(origin_id2, origin_visit3['visit'], status='partial') # then actual_origin_visits = list(self.storage.origin_visit_get(origin_id)) self.assertEqual(actual_origin_visits, [{ 'origin': origin_visit2['origin'], 'date': self.date_visit2, 'visit': origin_visit1['visit'], 'status': 'full', 'metadata': visit1_metadata, 'snapshot': None, }, { 'origin': origin_visit2['origin'], 'date': self.date_visit3, 'visit': origin_visit2['visit'], 'status': 'ongoing', 'metadata': None, 'snapshot': None, }]) actual_origin_visits_bis = list(self.storage.origin_visit_get( origin_id, limit=1)) self.assertEqual(actual_origin_visits_bis, [{ 'origin': origin_visit2['origin'], 'date': self.date_visit2, 'visit': origin_visit1['visit'], 'status': 'full', 'metadata': visit1_metadata, 'snapshot': None, }]) actual_origin_visits_ter = list(self.storage.origin_visit_get( origin_id, last_visit=origin_visit1['visit'])) self.assertEqual(actual_origin_visits_ter, [{ 'origin': origin_visit2['origin'], 'date': self.date_visit3, 'visit': origin_visit2['visit'], 'status': 'ongoing', 'metadata': None, 'snapshot': None, }]) actual_origin_visits2 = list(self.storage.origin_visit_get(origin_id2)) self.assertEqual(actual_origin_visits2, [{ 'origin': origin_visit3['origin'], 'date': self.date_visit3, 'visit': origin_visit3['visit'], 'status': 'partial', 'metadata': None, 'snapshot': None, }]) def test_origin_visit_get_by(self): origin_id = self.storage.origin_add_one(self.origin2) origin_id2 = self.storage.origin_add_one(self.origin) origin_visit1 = self.storage.origin_visit_add( origin_id, date=self.date_visit2) self.storage.snapshot_add(origin_id, origin_visit1['visit'], self.snapshot) # Add some other {origin, visit} entries self.storage.origin_visit_add(origin_id, date=self.date_visit3) self.storage.origin_visit_add(origin_id2, date=self.date_visit3) # when visit1_metadata = { 'contents': 42, 'directories': 22, } self.storage.origin_visit_update( origin_id, origin_visit1['visit'], status='full', metadata=visit1_metadata) expected_origin_visit = origin_visit1.copy() expected_origin_visit.update({ 'origin': origin_id, 'visit': origin_visit1['visit'], 'date': self.date_visit2, 'metadata': visit1_metadata, 'status': 'full', 'snapshot': self.snapshot['id'], }) # when actual_origin_visit1 = self.storage.origin_visit_get_by( origin_visit1['origin'], origin_visit1['visit']) # then self.assertEqual(actual_origin_visit1, expected_origin_visit) def test_origin_visit_get_by_no_result(self): # No result actual_origin_visit = self.storage.origin_visit_get_by( 10, 999) self.assertIsNone(actual_origin_visit) def test_person_get(self): # given (person injection through revision for example) self.storage.revision_add([self.revision]) rev = list(self.storage.revision_get([self.revision['id']]))[0] id0 = rev['committer']['id'] person0 = self.revision['committer'] id1 = rev['author']['id'] person1 = self.revision['author'] # when actual_persons = self.storage.person_get([id0, id1]) # then self.assertEqual( list(actual_persons), [ { 'id': id0, 'fullname': person0['fullname'], 'name': person0['name'], 'email': person0['email'], }, { 'id': id1, 'fullname': person1['fullname'], 'name': person1['name'], 'email': person1['email'], } ]) def test_person_get_fullname_unicity(self): # given (person injection through revisions for example) revision = self.revision # create a revision with same committer fullname but wo name and email revision2 = copy.deepcopy(self.revision2) revision2['committer'] = dict(revision['committer']) revision2['committer']['email'] = None revision2['committer']['name'] = None self.storage.revision_add([revision]) self.storage.revision_add([revision2]) # when getting added revisions revisions = list( self.storage.revision_get([revision['id'], revision2['id']])) # then # check committers are the same self.assertEqual(revisions[0]['committer'], revisions[1]['committer']) # check person_get return same result person0 = list( self.storage.person_get([revisions[0]['committer']['id']]))[0] person1 = list( self.storage.person_get([revisions[1]['committer']['id']]))[0] self.assertEqual(person0, person1) def test_snapshot_add_get_empty(self): origin_id = self.storage.origin_add_one(self.origin) origin_visit1 = self.storage.origin_visit_add(origin_id, self.date_visit1) visit_id = origin_visit1['visit'] self.storage.snapshot_add(origin_id, visit_id, self.empty_snapshot) by_id = self.storage.snapshot_get(self.empty_snapshot['id']) self.assertEqual(by_id, self.empty_snapshot) by_ov = self.storage.snapshot_get_by_origin_visit(origin_id, visit_id) self.assertEqual(by_ov, self.empty_snapshot) def test_snapshot_add_get_complete(self): origin_id = self.storage.origin_add_one(self.origin) origin_visit1 = self.storage.origin_visit_add(origin_id, self.date_visit1) visit_id = origin_visit1['visit'] self.storage.snapshot_add(origin_id, visit_id, self.complete_snapshot) by_id = self.storage.snapshot_get(self.complete_snapshot['id']) self.assertEqual(by_id, self.complete_snapshot) by_ov = self.storage.snapshot_get_by_origin_visit(origin_id, visit_id) self.assertEqual(by_ov, self.complete_snapshot) def test_snapshot_add_count_branches(self): origin_id = self.storage.origin_add_one(self.origin) origin_visit1 = self.storage.origin_visit_add(origin_id, self.date_visit1) visit_id = origin_visit1['visit'] self.storage.snapshot_add(origin_id, visit_id, self.complete_snapshot) snp_id = self.complete_snapshot['id'] snp_size = self.storage.snapshot_count_branches(snp_id) expected_snp_size = { 'alias': 1, 'content': 1, 'directory': 1, 'release': 1, 'revision': 1, 'snapshot': 1, None: 1 } self.assertEqual(snp_size, expected_snp_size) def test_snapshot_add_get_paginated(self): origin_id = self.storage.origin_add_one(self.origin) origin_visit1 = self.storage.origin_visit_add(origin_id, self.date_visit1) visit_id = origin_visit1['visit'] self.storage.snapshot_add(origin_id, visit_id, self.complete_snapshot) snp_id = self.complete_snapshot['id'] branches = self.complete_snapshot['branches'] branch_names = list(sorted(branches)) snapshot = self.storage.snapshot_get_branches(snp_id, branches_from=b'release') rel_idx = branch_names.index(b'release') expected_snapshot = { 'id': snp_id, 'branches': { name: branches[name] for name in branch_names[rel_idx:] }, 'next_branch': None, } self.assertEqual(snapshot, expected_snapshot) snapshot = self.storage.snapshot_get_branches(snp_id, branches_count=1) expected_snapshot = { 'id': snp_id, 'branches': { branch_names[0]: branches[branch_names[0]], }, 'next_branch': b'content', } self.assertEqual(snapshot, expected_snapshot) snapshot = self.storage.snapshot_get_branches( snp_id, branches_from=b'directory', branches_count=3) dir_idx = branch_names.index(b'directory') expected_snapshot = { 'id': snp_id, 'branches': { name: branches[name] for name in branch_names[dir_idx:dir_idx + 3] }, 'next_branch': branch_names[dir_idx + 3], } self.assertEqual(snapshot, expected_snapshot) def test_snapshot_add_get_filtered(self): origin_id = self.storage.origin_add_one(self.origin) origin_visit1 = self.storage.origin_visit_add(origin_id, self.date_visit1) visit_id = origin_visit1['visit'] self.storage.snapshot_add(origin_id, visit_id, self.complete_snapshot) snp_id = self.complete_snapshot['id'] branches = self.complete_snapshot['branches'] snapshot = self.storage.snapshot_get_branches( snp_id, target_types=['release', 'revision']) expected_snapshot = { 'id': snp_id, 'branches': { name: tgt for name, tgt in branches.items() if tgt and tgt['target_type'] in ['release', 'revision'] }, 'next_branch': None, } self.assertEqual(snapshot, expected_snapshot) snapshot = self.storage.snapshot_get_branches(snp_id, target_types=['alias']) expected_snapshot = { 'id': snp_id, 'branches': { name: tgt for name, tgt in branches.items() if tgt and tgt['target_type'] == 'alias' }, 'next_branch': None, } self.assertEqual(snapshot, expected_snapshot) def test_snapshot_add_get(self): origin_id = self.storage.origin_add_one(self.origin) origin_visit1 = self.storage.origin_visit_add(origin_id, self.date_visit1) visit_id = origin_visit1['visit'] self.storage.snapshot_add(origin_id, visit_id, self.snapshot) by_id = self.storage.snapshot_get(self.snapshot['id']) self.assertEqual(by_id, self.snapshot) by_ov = self.storage.snapshot_get_by_origin_visit(origin_id, visit_id) self.assertEqual(by_ov, self.snapshot) origin_visit_info = self.storage.origin_visit_get_by(origin_id, visit_id) self.assertEqual(origin_visit_info['snapshot'], self.snapshot['id']) def test_snapshot_add_nonexistent_visit(self): origin_id = self.storage.origin_add_one(self.origin) visit_id = 54164461156 with self.assertRaises(ValueError): self.storage.snapshot_add(origin_id, visit_id, self.snapshot) def test_snapshot_add_twice(self): origin_id = self.storage.origin_add_one(self.origin) origin_visit1 = self.storage.origin_visit_add(origin_id, self.date_visit1) visit1_id = origin_visit1['visit'] self.storage.snapshot_add(origin_id, visit1_id, self.snapshot) by_ov1 = self.storage.snapshot_get_by_origin_visit(origin_id, visit1_id) self.assertEqual(by_ov1, self.snapshot) origin_visit2 = self.storage.origin_visit_add(origin_id, self.date_visit2) visit2_id = origin_visit2['visit'] self.storage.snapshot_add(origin_id, visit2_id, self.snapshot) by_ov2 = self.storage.snapshot_get_by_origin_visit(origin_id, visit2_id) self.assertEqual(by_ov2, self.snapshot) def test_snapshot_get_nonexistent(self): bogus_snapshot_id = b'bogus snapshot id 00' bogus_origin_id = 1 bogus_visit_id = 1 by_id = self.storage.snapshot_get(bogus_snapshot_id) self.assertIsNone(by_id) by_ov = self.storage.snapshot_get_by_origin_visit(bogus_origin_id, bogus_visit_id) self.assertIsNone(by_ov) def test_snapshot_get_latest(self): origin_id = self.storage.origin_add_one(self.origin) origin_visit1 = self.storage.origin_visit_add(origin_id, self.date_visit1) visit1_id = origin_visit1['visit'] origin_visit2 = self.storage.origin_visit_add(origin_id, self.date_visit2) visit2_id = origin_visit2['visit'] # Add a visit with the same date as the previous one origin_visit3 = self.storage.origin_visit_add(origin_id, self.date_visit2) visit3_id = origin_visit3['visit'] # Two visits, both with no snapshot: latest snapshot is None self.assertIsNone(self.storage.snapshot_get_latest(origin_id)) # Add snapshot to visit1, latest snapshot = visit 1 snapshot self.storage.snapshot_add(origin_id, visit1_id, self.complete_snapshot) self.assertEqual(self.complete_snapshot, self.storage.snapshot_get_latest(origin_id)) # Status filter: both visits are status=ongoing, so no snapshot # returned self.assertIsNone( self.storage.snapshot_get_latest(origin_id, allowed_statuses=['full']) ) # Mark the first visit as completed and check status filter again self.storage.origin_visit_update(origin_id, visit1_id, status='full') self.assertEqual( self.complete_snapshot, self.storage.snapshot_get_latest(origin_id, allowed_statuses=['full']), ) # Add snapshot to visit2 and check that the new snapshot is returned self.storage.snapshot_add(origin_id, visit2_id, self.empty_snapshot) self.assertEqual(self.empty_snapshot, self.storage.snapshot_get_latest(origin_id)) # Check that the status filter is still working self.assertEqual( self.complete_snapshot, self.storage.snapshot_get_latest(origin_id, allowed_statuses=['full']), ) # Add snapshot to visit3 (same date as visit2) and check that # the new snapshot is returned self.storage.snapshot_add(origin_id, visit3_id, self.complete_snapshot) self.assertEqual(self.complete_snapshot, self.storage.snapshot_get_latest(origin_id)) def test_stat_counters(self): expected_keys = ['content', 'directory', 'origin', 'person', 'revision'] # Initially, all counters are 0 self.storage.refresh_stat_counters() counters = self.storage.stat_counters() self.assertTrue(set(expected_keys) <= set(counters)) for key in expected_keys: self.assertEqual(counters[key], 0) # Add a content. Only the content counter should increase. self.storage.content_add([self.cont]) self.storage.refresh_stat_counters() counters = self.storage.stat_counters() self.assertTrue(set(expected_keys) <= set(counters)) for key in expected_keys: if key != 'content': self.assertEqual(counters[key], 0) self.assertEqual(counters['content'], 1) # Add other objects. Check their counter increased as well. origin_id = self.storage.origin_add_one(self.origin2) origin_visit1 = self.storage.origin_visit_add( origin_id, date=self.date_visit2) self.storage.snapshot_add(origin_id, origin_visit1['visit'], self.snapshot) self.storage.directory_add([self.dir]) self.storage.revision_add([self.revision]) self.storage.refresh_stat_counters() counters = self.storage.stat_counters() self.assertEqual(counters['content'], 1) self.assertEqual(counters['directory'], 1) self.assertEqual(counters['snapshot'], 1) self.assertEqual(counters['origin'], 1) self.assertEqual(counters['revision'], 1) self.assertEqual(counters['person'], 2) def test_content_find_with_present_content(self): # 1. with something to find cont = self.cont self.storage.content_add([cont]) actually_present = self.storage.content_find({'sha1': cont['sha1']}) actually_present.pop('ctime') self.assertEqual(actually_present, { 'sha1': cont['sha1'], 'sha256': cont['sha256'], 'sha1_git': cont['sha1_git'], 'blake2s256': cont['blake2s256'], 'length': cont['length'], 'status': 'visible' }) # 2. with something to find actually_present = self.storage.content_find( {'sha1_git': cont['sha1_git']}) actually_present.pop('ctime') self.assertEqual(actually_present, { 'sha1': cont['sha1'], 'sha256': cont['sha256'], 'sha1_git': cont['sha1_git'], 'blake2s256': cont['blake2s256'], 'length': cont['length'], 'status': 'visible' }) # 3. with something to find actually_present = self.storage.content_find( {'sha256': cont['sha256']}) actually_present.pop('ctime') self.assertEqual(actually_present, { 'sha1': cont['sha1'], 'sha256': cont['sha256'], 'sha1_git': cont['sha1_git'], 'blake2s256': cont['blake2s256'], 'length': cont['length'], 'status': 'visible' }) # 4. with something to find actually_present = self.storage.content_find({ 'sha1': cont['sha1'], 'sha1_git': cont['sha1_git'], 'sha256': cont['sha256'], 'blake2s256': cont['blake2s256'], }) actually_present.pop('ctime') self.assertEqual(actually_present, { 'sha1': cont['sha1'], 'sha256': cont['sha256'], 'sha1_git': cont['sha1_git'], 'blake2s256': cont['blake2s256'], 'length': cont['length'], 'status': 'visible' }) def test_content_find_with_non_present_content(self): # 1. with something that does not exist missing_cont = self.missing_cont actually_present = self.storage.content_find( {'sha1': missing_cont['sha1']}) self.assertIsNone(actually_present) # 2. with something that does not exist actually_present = self.storage.content_find( {'sha1_git': missing_cont['sha1_git']}) self.assertIsNone(actually_present) # 3. with something that does not exist actually_present = self.storage.content_find( {'sha256': missing_cont['sha256']}) self.assertIsNone(actually_present) def test_content_find_bad_input(self): # 1. with bad input with self.assertRaises(ValueError): self.storage.content_find({}) # empty is bad # 2. with bad input with self.assertRaises(ValueError): self.storage.content_find( {'unknown-sha1': 'something'}) # not the right key def test_object_find_by_sha1_git(self): sha1_gits = [b'00000000000000000000'] expected = { b'00000000000000000000': [], } self.storage.content_add([self.cont]) sha1_gits.append(self.cont['sha1_git']) expected[self.cont['sha1_git']] = [{ 'sha1_git': self.cont['sha1_git'], 'type': 'content', 'id': self.cont['sha1'], }] self.storage.directory_add([self.dir]) sha1_gits.append(self.dir['id']) expected[self.dir['id']] = [{ 'sha1_git': self.dir['id'], 'type': 'directory', 'id': self.dir['id'], }] self.storage.revision_add([self.revision]) sha1_gits.append(self.revision['id']) expected[self.revision['id']] = [{ 'sha1_git': self.revision['id'], 'type': 'revision', 'id': self.revision['id'], }] self.storage.release_add([self.release]) sha1_gits.append(self.release['id']) expected[self.release['id']] = [{ 'sha1_git': self.release['id'], 'type': 'release', 'id': self.release['id'], }] ret = self.storage.object_find_by_sha1_git(sha1_gits) for val in ret.values(): for obj in val: del obj['object_id'] self.assertEqual(expected, ret) def test_tool_add(self): tool = { 'name': 'some-unknown-tool', 'version': 'some-version', 'configuration': {"debian-package": "some-package"}, } actual_tool = self.storage.tool_get(tool) self.assertIsNone(actual_tool) # does not exist # add it actual_tools = list(self.storage.tool_add([tool])) self.assertEqual(len(actual_tools), 1) actual_tool = actual_tools[0] self.assertIsNotNone(actual_tool) # now it exists new_id = actual_tool.pop('id') self.assertEqual(actual_tool, tool) actual_tools2 = list(self.storage.tool_add([tool])) actual_tool2 = actual_tools2[0] self.assertIsNotNone(actual_tool2) # now it exists new_id2 = actual_tool2.pop('id') self.assertEqual(new_id, new_id2) self.assertEqual(actual_tool, actual_tool2) def test_tool_add_multiple(self): tool = { 'name': 'some-unknown-tool', 'version': 'some-version', 'configuration': {"debian-package": "some-package"}, } actual_tools = list(self.storage.tool_add([tool])) self.assertEqual(len(actual_tools), 1) new_tools = [tool, { 'name': 'yet-another-tool', 'version': 'version', 'configuration': {}, }] actual_tools = list(self.storage.tool_add(new_tools)) self.assertEqual(len(actual_tools), 2) # order not guaranteed, so we iterate over results to check for tool in actual_tools: _id = tool.pop('id') self.assertIsNotNone(_id) self.assertIn(tool, new_tools) def test_tool_get_missing(self): tool = { 'name': 'unknown-tool', 'version': '3.1.0rc2-31-ga2cbb8c', 'configuration': {"command_line": "nomossa "}, } actual_tool = self.storage.tool_get(tool) self.assertIsNone(actual_tool) def test_tool_metadata_get_missing_context(self): tool = { 'name': 'swh-metadata-translator', 'version': '0.0.1', 'configuration': {"context": "unknown-context"}, } actual_tool = self.storage.tool_get(tool) self.assertIsNone(actual_tool) def test_tool_metadata_get(self): tool = { 'name': 'swh-metadata-translator', 'version': '0.0.1', 'configuration': {"type": "local", "context": "npm"}, } tools = list(self.storage.tool_add([tool])) expected_tool = tools[0] # when actual_tool = self.storage.tool_get(tool) # then self.assertEqual(expected_tool, actual_tool) def test_metadata_provider_get(self): # given no_provider = self.storage.metadata_provider_get(6459456445615) self.assertIsNone(no_provider) # when provider_id = self.storage.metadata_provider_add( self.provider['name'], self.provider['type'], self.provider['url'], self.provider['metadata']) actual_provider = self.storage.metadata_provider_get(provider_id) expected_provider = { 'provider_name': self.provider['name'], 'provider_url': self.provider['url'] } # then del actual_provider['id'] self.assertTrue(actual_provider, expected_provider) def test_metadata_provider_get_by(self): # given no_provider = self.storage.metadata_provider_get_by({ 'provider_name': self.provider['name'], 'provider_url': self.provider['url'] }) self.assertIsNone(no_provider) # when provider_id = self.storage.metadata_provider_add( self.provider['name'], self.provider['type'], self.provider['url'], self.provider['metadata']) actual_provider = self.storage.metadata_provider_get_by({ 'provider_name': self.provider['name'], 'provider_url': self.provider['url'] }) # then self.assertTrue(provider_id, actual_provider['id']) def test_origin_metadata_add(self): # given origin_id = self.storage.origin_add([self.origin])[0]['id'] origin_metadata0 = list(self.storage.origin_metadata_get_by(origin_id)) self.assertTrue(len(origin_metadata0) == 0) tools = list(self.storage.tool_add([self.metadata_tool])) tool = tools[0] self.storage.metadata_provider_add( self.provider['name'], self.provider['type'], self.provider['url'], self.provider['metadata']) provider = self.storage.metadata_provider_get_by({ 'provider_name': self.provider['name'], 'provider_url': self.provider['url'] }) # when adding for the same origin 2 metadatas self.storage.origin_metadata_add( origin_id, self.origin_metadata['discovery_date'], provider['id'], tool['id'], self.origin_metadata['metadata']) actual_om1 = list(self.storage.origin_metadata_get_by(origin_id)) # then self.assertEqual(len(actual_om1), 1) self.assertEqual(actual_om1[0]['origin_id'], origin_id) def test_origin_metadata_get(self): # given origin_id = self.storage.origin_add([self.origin])[0]['id'] origin_id2 = self.storage.origin_add([self.origin2])[0]['id'] self.storage.metadata_provider_add(self.provider['name'], self.provider['type'], self.provider['url'], self.provider['metadata']) provider = self.storage.metadata_provider_get_by({ 'provider_name': self.provider['name'], 'provider_url': self.provider['url'] }) tool = list(self.storage.tool_add([self.metadata_tool]))[0] # when adding for the same origin 2 metadatas self.storage.origin_metadata_add( origin_id, self.origin_metadata['discovery_date'], provider['id'], tool['id'], self.origin_metadata['metadata']) self.storage.origin_metadata_add( origin_id2, self.origin_metadata2['discovery_date'], provider['id'], tool['id'], self.origin_metadata2['metadata']) self.storage.origin_metadata_add( origin_id, self.origin_metadata2['discovery_date'], provider['id'], tool['id'], self.origin_metadata2['metadata']) all_metadatas = list(self.storage.origin_metadata_get_by(origin_id)) metadatas_for_origin2 = list(self.storage.origin_metadata_get_by( origin_id2)) expected_results = [{ 'origin_id': origin_id, 'discovery_date': datetime.datetime( 2017, 1, 1, 23, 0, tzinfo=datetime.timezone.utc), 'metadata': { 'name': 'test_origin_metadata', 'version': '0.0.1' }, 'provider_id': provider['id'], 'provider_name': 'hal', 'provider_type': 'deposit-client', 'provider_url': 'http:///hal/inria', 'tool_id': tool['id'] }, { 'origin_id': origin_id, 'discovery_date': datetime.datetime( 2015, 1, 1, 23, 0, tzinfo=datetime.timezone.utc), 'metadata': { 'name': 'test_origin_metadata', 'version': '0.0.1' }, 'provider_id': provider['id'], 'provider_name': 'hal', 'provider_type': 'deposit-client', 'provider_url': 'http:///hal/inria', 'tool_id': tool['id'] }] # then self.assertEqual(len(all_metadatas), 2) self.assertEqual(len(metadatas_for_origin2), 1) self.assertCountEqual(all_metadatas, expected_results) def test_origin_metadata_get_by_provider_type(self): # given origin_id = self.storage.origin_add([self.origin])[0]['id'] origin_id2 = self.storage.origin_add([self.origin2])[0]['id'] provider1_id = self.storage.metadata_provider_add( self.provider['name'], self.provider['type'], self.provider['url'], self.provider['metadata']) provider1 = self.storage.metadata_provider_get_by({ 'provider_name': self.provider['name'], 'provider_url': self.provider['url'] }) self.assertEqual(provider1, self.storage.metadata_provider_get(provider1_id)) provider2_id = self.storage.metadata_provider_add( 'swMATH', 'registry', 'http://www.swmath.org/', {'email': 'contact@swmath.org', 'license': 'All rights reserved'}) provider2 = self.storage.metadata_provider_get_by({ 'provider_name': 'swMATH', 'provider_url': 'http://www.swmath.org/' }) self.assertEqual(provider2, self.storage.metadata_provider_get(provider2_id)) # using the only tool now inserted in the data.sql, but for this # provider should be a crawler tool (not yet implemented) tool = list(self.storage.tool_add([self.metadata_tool]))[0] # when adding for the same origin 2 metadatas self.storage.origin_metadata_add( origin_id, self.origin_metadata['discovery_date'], provider1['id'], tool['id'], self.origin_metadata['metadata']) self.storage.origin_metadata_add( origin_id2, self.origin_metadata2['discovery_date'], provider2['id'], tool['id'], self.origin_metadata2['metadata']) provider_type = 'registry' m_by_provider = list(self.storage. origin_metadata_get_by( origin_id2, provider_type)) for item in m_by_provider: if 'id' in item: del item['id'] expected_results = [{ 'origin_id': origin_id2, 'discovery_date': datetime.datetime( 2017, 1, 1, 23, 0, tzinfo=datetime.timezone.utc), 'metadata': { 'name': 'test_origin_metadata', 'version': '0.0.1' }, 'provider_id': provider2['id'], 'provider_name': 'swMATH', 'provider_type': provider_type, 'provider_url': 'http://www.swmath.org/', 'tool_id': tool['id'] }] # then self.assertEqual(len(m_by_provider), 1) self.assertEqual(m_by_provider, expected_results) class CommonPropTestStorage: def assert_contents_ok(self, expected_contents, actual_contents, keys_to_check={'sha1', 'data'}): """Assert that a given list of contents matches on a given set of keys. """ for k in keys_to_check: expected_list = sorted([c[k] for c in expected_contents]) actual_list = sorted([c[k] for c in actual_contents]) self.assertEqual(actual_list, expected_list) @given(gen_contents(min_size=1, max_size=4)) def test_generate_content_get(self, contents): # add contents to storage self.storage.content_add(contents) # input the list of sha1s we want from storage get_sha1s = [c['sha1'] for c in contents] # retrieve contents actual_contents = list(self.storage.content_get(get_sha1s)) self.assert_contents_ok(contents, actual_contents) @given(gen_contents(min_size=1, max_size=4)) def test_generate_content_get_metadata(self, contents): # add contents to storage self.storage.content_add(contents) # input the list of sha1s we want from storage get_sha1s = [c['sha1'] for c in contents] # retrieve contents actual_contents = list(self.storage.content_get_metadata(get_sha1s)) self.assertEqual(len(actual_contents), len(contents)) # will check that all contents are retrieved correctly one_content = contents[0] # content_get_metadata does not return data keys_to_check = set(one_content.keys()) - {'data'} self.assert_contents_ok(contents, actual_contents, keys_to_check=keys_to_check) def test_generate_content_get_range_limit_none(self): """content_get_range call with wrong limit input should fail""" with self.assertRaises(ValueError) as e: self.storage.content_get_range(start=None, end=None, limit=None) self.assertEqual(e.exception.args, ( 'Development error: limit should not be None',)) @given(gen_contents(min_size=1, max_size=4)) def test_generate_content_get_range_no_limit(self, contents): """content_get_range returns contents within range provided""" self.reset_storage_tables() # add contents to storage self.storage.content_add(contents) # input the list of sha1s we want from storage get_sha1s = sorted([c['sha1'] for c in contents]) start = get_sha1s[0] end = get_sha1s[-1] # retrieve contents actual_result = self.storage.content_get_range(start, end) actual_contents = actual_result['contents'] actual_next = actual_result['next'] self.assertEqual(len(contents), len(actual_contents)) self.assertIsNone(actual_next) one_content = contents[0] keys_to_check = set(one_content.keys()) - {'data'} self.assert_contents_ok(contents, actual_contents, keys_to_check) @given(gen_contents(min_size=4, max_size=4)) def test_generate_content_get_range_limit(self, contents): """content_get_range paginates results if limit exceeded""" self.reset_storage_tables() contents_map = {c['sha1']: c for c in contents} # add contents to storage self.storage.content_add(contents) # input the list of sha1s we want from storage get_sha1s = sorted([c['sha1'] for c in contents]) start = get_sha1s[0] end = get_sha1s[-1] # retrieve contents limited to 3 results limited_results = len(contents) - 1 actual_result = self.storage.content_get_range(start, end, limit=limited_results) actual_contents = actual_result['contents'] actual_next = actual_result['next'] self.assertEqual(limited_results, len(actual_contents)) self.assertIsNotNone(actual_next) self.assertEqual(actual_next, get_sha1s[-1]) expected_contents = [contents_map[sha1] for sha1 in get_sha1s[:-1]] keys_to_check = set(contents[0].keys()) - {'data'} self.assert_contents_ok(expected_contents, actual_contents, keys_to_check) # retrieve next part actual_results2 = self.storage.content_get_range(start=end, end=end) actual_contents2 = actual_results2['contents'] actual_next2 = actual_results2['next'] self.assertEqual(1, len(actual_contents2)) self.assertIsNone(actual_next2) self.assert_contents_ok([contents_map[actual_next]], actual_contents2, keys_to_check) def test_origin_get_invalid_id_legacy(self): invalid_origin_id = 1 origin_info = self.storage.origin_get({'id': invalid_origin_id}) self.assertIsNone(origin_info) origin_visits = list(self.storage.origin_visit_get( invalid_origin_id)) self.assertEqual(origin_visits, []) def test_origin_get_invalid_id(self): origin_info = self.storage.origin_get([{'id': 1}, {'id': 2}]) self.assertEqual(origin_info, [None, None]) origin_visits = list(self.storage.origin_visit_get(1)) self.assertEqual(origin_visits, []) @given(gen_origins(min_size=100, max_size=100)) def test_origin_get_range(self, new_origins): nb_origins = len(new_origins) self.storage.origin_add(new_origins) origin_from = random.randint(1, nb_origins) origin_count = random.randint(1, nb_origins - origin_from) expected_origins = [] for i in range(origin_from, origin_from + origin_count): expected_origins.append(self.storage.origin_get({'id': i})) actual_origins = list( self.storage.origin_get_range(origin_from=origin_from, origin_count=origin_count)) self.assertEqual(actual_origins, expected_origins) origin_from = -1 origin_count = 10 origins = list( self.storage.origin_get_range(origin_from=origin_from, origin_count=origin_count)) self.assertEqual(len(origins), origin_count) origin_from = 10000 origins = list( self.storage.origin_get_range(origin_from=origin_from, origin_count=origin_count)) self.assertEqual(len(origins), 0) + def test_origin_count(self): + + new_origins = [ + { + 'type': 'git', + 'url': 'https://github.com/user1/repo1' + }, + { + 'type': 'git', + 'url': 'https://github.com/user2/repo1' + }, + { + 'type': 'git', + 'url': 'https://github.com/user3/repo1' + }, + { + 'type': 'git', + 'url': 'https://gitlab.com/user1/repo1' + }, + { + 'type': 'git', + 'url': 'https://gitlab.com/user2/repo1' + } + ] + + self.storage.origin_add(new_origins) + + self.assertEqual(self.storage.origin_count('github'), 3) + self.assertEqual(self.storage.origin_count('gitlab'), 2) + self.assertEqual( + self.storage.origin_count('.*user.*', regexp=True), 5) + self.assertEqual( + self.storage.origin_count('.*user.*', regexp=False), 0) + self.assertEqual( + self.storage.origin_count('.*user1.*', regexp=True), 2) + self.assertEqual( + self.storage.origin_count('.*user1.*', regexp=False), 0) + @pytest.mark.db class TestLocalStorage(CommonTestStorage, StorageTestDbFixture, unittest.TestCase): """Test the local storage""" # Can only be tested with local storage as you can't mock # datetimes for the remote server def test_fetch_history(self): origin = self.storage.origin_add_one(self.origin) with patch('datetime.datetime'): datetime.datetime.now.return_value = self.fetch_history_date fetch_history_id = self.storage.fetch_history_start(origin) datetime.datetime.now.assert_called_with(tz=datetime.timezone.utc) with patch('datetime.datetime'): datetime.datetime.now.return_value = self.fetch_history_end self.storage.fetch_history_end(fetch_history_id, self.fetch_history_data) fetch_history = self.storage.fetch_history_get(fetch_history_id) expected_fetch_history = self.fetch_history_data.copy() expected_fetch_history['id'] = fetch_history_id expected_fetch_history['origin'] = origin expected_fetch_history['date'] = self.fetch_history_date expected_fetch_history['duration'] = self.fetch_history_duration self.assertEqual(expected_fetch_history, fetch_history) # This test is only relevant on the local storage, with an actual # objstorage raising an exception def test_content_add_objstorage_exception(self): self.storage.objstorage.add = Mock( side_effect=Exception('mocked broken objstorage') ) with self.assertRaises(Exception) as e: self.storage.content_add([self.cont]) self.assertEqual(e.exception.args, ('mocked broken objstorage',)) missing = list(self.storage.content_missing([self.cont])) self.assertEqual(missing, [self.cont['sha1']]) @pytest.mark.db @pytest.mark.property_based class PropTestLocalStorage(CommonPropTestStorage, StorageTestDbFixture, unittest.TestCase): pass class AlteringSchemaTest(TestStorageData, StorageTestDbFixture, unittest.TestCase): """This class is dedicated for the rare case where the schema needs to be altered dynamically. Otherwise, the tests could be blocking when ran altogether. """ def test_content_update(self): cont = copy.deepcopy(self.cont) self.storage.content_add([cont]) # alter the sha1_git for example cont['sha1_git'] = hash_to_bytes( '3a60a5275d0333bf13468e8b3dcab90f4046e654') self.storage.content_update([cont], keys=['sha1_git']) with self.storage.get_db().transaction() as cur: cur.execute('SELECT sha1, sha1_git, sha256, length, status' ' FROM content WHERE sha1 = %s', (cont['sha1'],)) datum = cur.fetchone() self.assertEqual( (datum[0], datum[1], datum[2], datum[3], datum[4]), (cont['sha1'], cont['sha1_git'], cont['sha256'], cont['length'], 'visible')) def test_content_update_with_new_cols(self): with self.storage.get_db().transaction() as cur: cur.execute("""alter table content add column test text default null, add column test2 text default null""") cont = copy.deepcopy(self.cont2) self.storage.content_add([cont]) cont['test'] = 'value-1' cont['test2'] = 'value-2' self.storage.content_update([cont], keys=['test', 'test2']) with self.storage.get_db().transaction() as cur: cur.execute( 'SELECT sha1, sha1_git, sha256, length, status, test, test2' ' FROM content WHERE sha1 = %s', (cont['sha1'],)) datum = cur.fetchone() self.assertEqual( (datum[0], datum[1], datum[2], datum[3], datum[4], datum[5], datum[6]), (cont['sha1'], cont['sha1_git'], cont['sha256'], cont['length'], 'visible', cont['test'], cont['test2'])) with self.storage.get_db().transaction() as cur: cur.execute("""alter table content drop column test, drop column test2""")