diff --git a/sql/upgrades/143.sql b/sql/upgrades/143.sql new file mode 100644 index 0000000..ca9a9b0 --- /dev/null +++ b/sql/upgrades/143.sql @@ -0,0 +1,94 @@ +-- SWH DB schema upgrade +-- from_version: 142 +-- to_version: 143 +-- description: Remove origin ids + +insert into dbversion(version, release, description) + values(143, now(), 'Work In Progress'); + +create or replace function swh_origin_visit_add(origin_url text, date timestamptz, type text) + returns bigint + language sql +as $$ + with origin_id as ( + select id + from origin + where url = origin_url + ), last_known_visit as ( + select coalesce(max(visit), 0) as visit + from origin_visit + where origin = (select id from origin_id) + ) + insert into origin_visit (origin, date, type, visit, status) + values ((select id from origin_id), date, type, + (select visit from last_known_visit) + 1, 'ongoing') + returning visit; +$$; + +create or replace function swh_visit_find_by_date(origin_url text, visit_date timestamptz default NOW()) + returns setof origin_visit + language plpgsql + stable +as $$ +declare + origin_id bigint; +begin + select id into origin_id from origin where url=origin_url; + return query + with closest_two_visits as (( + select ov, (date - visit_date), visit as interval + from origin_visit ov + where ov.origin = origin_id + and ov.date >= visit_date + order by ov.date asc, ov.visit desc + limit 1 + ) union ( + select ov, (visit_date - date), visit as interval + from origin_visit ov + where ov.origin = origin_id + and ov.date < visit_date + order by ov.date desc, ov.visit desc + limit 1 + )) select (ov).* from closest_two_visits order by interval, visit limit 1; +end +$$; + +drop function swh_visit_get; + +alter type origin_metadata_signature + rename attribute origin_id to origin_url; + +alter type origin_metadata_signature + alter attribute origin_url set data type text; + +create or replace function swh_origin_metadata_get_by_origin( + origin text) + returns setof origin_metadata_signature + language sql + stable +as $$ + select om.id as id, o.url as origin_url, discovery_date, tool_id, om.metadata, + mp.id as provider_id, provider_name, provider_type, provider_url + from origin_metadata as om + inner join metadata_provider mp on om.provider_id = mp.id + inner join origin o on om.origin_id = o.id + where o.url = origin + order by discovery_date desc; +$$; + +create or replace function swh_origin_metadata_get_by_provider_type( + origin_url text, + provider_type text) + returns setof origin_metadata_signature + language sql + stable +as $$ + select om.id as id, o.url as origin_url, discovery_date, tool_id, om.metadata, + mp.id as provider_id, provider_name, provider_type, provider_url + from origin_metadata as om + inner join metadata_provider mp on om.provider_id = mp.id + inner join origin o on om.origin_id = o.id + where o.url = origin_url + and mp.provider_type = provider_type + order by discovery_date desc; +$$; diff --git a/swh/storage/algos/origin.py b/swh/storage/algos/origin.py index efecb01..e360742 100644 --- a/swh/storage/algos/origin.py +++ b/swh/storage/algos/origin.py @@ -1,33 +1,34 @@ # Copyright (C) 2019 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information def iter_origins(storage, origin_from=1, origin_to=None, batch_size=10000): """Iterates over all origins in the storage. Args: storage: the storage object used for queries. batch_size: number of origins per query Yields: dict: the origin dictionary with the keys: - - id: origin's id - type: origin's type - url: origin's url """ start = origin_from while True: if origin_to: origin_count = min(origin_to - start, batch_size) else: origin_count = batch_size origins = list(storage.origin_get_range( origin_from=start, origin_count=origin_count)) if not origins: break start = origins[-1]['id'] + 1 - yield from origins + for origin in origins: + del origin['id'] + yield origin if origin_to and start > origin_to: break diff --git a/swh/storage/api/client.py b/swh/storage/api/client.py index 5e141e1..7a716d8 100644 --- a/swh/storage/api/client.py +++ b/swh/storage/api/client.py @@ -1,257 +1,257 @@ # 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 RPCClient from ..exc import StorageAPIError class RemoteStorage(RPCClient): """Proxy to a remote storage API""" api_exception = StorageAPIError def check_config(self, *, check_write): return self.post('check_config', {'check_write': check_write}) def reset(self): return self.post('reset', {}) def content_add(self, content): return self.post('content/add', {'content': content}) def content_add_metadata(self, content): return self.post('content/add_metadata', {'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 skipped_content_missing(self, contents): return self.post('content/skipped/missing', {'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.post('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, snapshots): return self.post('snapshot/add', {'snapshots': snapshots}) 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, type): return self.post( 'origin/visit/add', {'origin': origin, 'date': date, 'type': type}) def origin_visit_update(self, origin, visit_id, status=None, metadata=None, snapshot=None): return self.post('origin/visit/update', {'origin': origin, 'visit_id': visit_id, 'status': status, 'metadata': metadata, 'snapshot': snapshot}) def origin_visit_upsert(self, visits): return self.post('origin/visit/upsert', {'visits': visits}) 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_find_by_date(self, origin, visit_date, limit=None): return self.post('origin/visit/find_by_date', { 'origin': origin, 'visit_date': visit_date}) def origin_visit_get_by(self, origin, visit): return self.post('origin/visit/getby', {'origin': origin, 'visit': visit}) def origin_visit_get_latest(self, origin, allowed_statuses=None, require_snapshot=False): return self.post( 'origin/visit/get_latest', {'origin': origin, 'allowed_statuses': allowed_statuses, 'require_snapshot': require_snapshot}) def stat_counters(self): return self.get('stat/counters') def refresh_stat_counters(self): return self.get('stat/refresh') 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, + def origin_metadata_add(self, origin_url, ts, provider, tool, metadata): + return self.post('origin/metadata/add', {'origin_url': origin_url, 'ts': ts, 'provider': provider, 'tool': tool, 'metadata': metadata}) - def origin_metadata_get_by(self, origin_id, provider_type=None): + def origin_metadata_get_by(self, origin_url, provider_type=None): return self.post('origin/metadata/get', { - 'origin_id': origin_id, + 'origin_url': origin_url, '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/db.py b/swh/storage/db.py index 4ac41f3..e924415 100644 --- a/swh/storage/db.py +++ b/swh/storage/db.py @@ -1,866 +1,877 @@ # 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'] content_add_keys = content_get_metadata_keys + ['ctime'] 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(self, contents, cur=None): if not contents: return [] cur = self._cursor(cur) query = """SELECT * FROM (VALUES %s) AS t (%s) WHERE not exists (SELECT 1 FROM skipped_content s WHERE s.sha1 is not distinct from t.sha1 and s.sha1_git is not distinct from t.sha1_git and s.sha256 is not distinct from t.sha256);""" % \ ((', '.join('%s' for _ in contents)), ', '.join(self.content_hash_keys)) cur.execute(query, [tuple(cont[key] for key in self.content_hash_keys) for cont in contents]) 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, snapshot_id, cur=None): """Add a snapshot from the temporary table""" cur = self._cursor(cur) cur.execute("""SELECT swh_snapshot_add(%s)""", (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): + def snapshot_get_by_origin_visit(self, origin_url, visit_id, cur=None): cur = self._cursor(cur) query = """\ - SELECT snapshot from origin_visit where - origin_visit.origin=%s and origin_visit.visit=%s; + SELECT snapshot FROM origin_visit + INNER JOIN origin ON origin.id = origin_visit.origin + WHERE origin.url=%s AND origin_visit.visit=%s; """ - cur.execute(query, (origin_id, visit_id)) + cur.execute(query, (origin_url, 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) checksum_dict = {'sha1': sha1, 'sha1_git': sha1_git, 'sha256': sha256, 'blake2s256': blake2s256} where_parts = [] args = [] # Adds only those keys which have value other than None for algorithm in checksum_dict: if checksum_dict[algorithm] is not None: args.append(checksum_dict[algorithm]) where_parts.append(algorithm + '= %s') query = ' AND '.join(where_parts) cur.execute("""SELECT %s FROM content WHERE %s """ % (','.join(self.content_find_cols), query), args) content = cur.fetchall() 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 + ['parents'] def origin_visit_add(self, origin, ts, type, 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 type: type of loader for 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, %s)', (origin, ts, type)) return cur.fetchone()[0] def origin_visit_update(self, origin_id, visit_id, updates, cur=None): """Update origin_visit's status.""" cur = self._cursor(cur) update_cols = [] values = [] - where = ['origin=%s AND visit=%s'] + where = ['origin.id = origin_visit.origin', + 'origin.url=%s', + 'visit=%s'] where_values = [origin_id, visit_id] - from_ = '' if 'status' in updates: update_cols.append('status=%s') values.append(updates.pop('status')) if 'metadata' in updates: update_cols.append('metadata=%s') values.append(jsonize(updates.pop('metadata'))) if 'snapshot' in updates: update_cols.append('snapshot=%s') values.append(updates.pop('snapshot')) assert not updates, 'Unknown fields: %r' % updates query = """UPDATE origin_visit - SET {update_cols} - {from} - WHERE {where}""".format(**{ + SET {update_cols} + FROM origin + WHERE {where}""".format(**{ 'update_cols': ', '.join(update_cols), - 'from': from_, 'where': ' AND '.join(where) }) cur.execute(query, (*values, *where_values)) def origin_visit_upsert(self, origin, visit, date, type, status, metadata, snapshot, cur=None): + # doing an extra query like this is way simpler than trying to join + # the origin id in the query below + origin_id = next(self.origin_id_get_by_url([origin])) + cur = self._cursor(cur) query = """INSERT INTO origin_visit ({cols}) VALUES ({values}) ON CONFLICT ON CONSTRAINT origin_visit_pkey DO UPDATE SET {updates}""".format( cols=', '.join(self.origin_visit_get_cols), values=', '.join('%s' for col in self.origin_visit_get_cols), updates=', '.join('{0}=excluded.{0}'.format(col) for col in self.origin_visit_get_cols)) cur.execute( - query, (origin, visit, date, type, status, metadata, snapshot)) + query, (origin_id, visit, date, type, status, metadata, snapshot)) - origin_visit_get_cols = ['origin', 'visit', 'date', 'type', 'status', - 'metadata', 'snapshot'] + origin_visit_get_cols = [ + 'origin', 'visit', 'date', 'type', + 'status', 'metadata', 'snapshot'] + origin_visit_select_cols = [ + 'origin.url AS origin', 'visit', 'date', 'origin_visit.type AS type', + '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 FROM origin_visit - WHERE origin=%%s %s + INNER JOIN origin ON origin.id = origin_visit.origin + WHERE origin.url=%%s %s order by visit asc limit %%s""" % ( - ', '.join(self.origin_visit_get_cols), extra_condition + ', '.join(self.origin_visit_select_cols), 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 FROM origin_visit - WHERE origin = %%s AND visit = %%s - """ % (', '.join(self.origin_visit_get_cols)) + INNER JOIN origin ON origin.id = origin_visit.origin + WHERE origin.url = %%s AND visit = %%s + """ % (', '.join(self.origin_visit_select_cols)) cur.execute(query, (origin_id, visit_id)) r = cur.fetchall() if not r: return None return r[0] def origin_visit_find_by_date(self, origin, visit_date, cur=None): cur = self._cursor(cur) cur.execute( 'SELECT * FROM swh_visit_find_by_date(%s, %s)', (origin, visit_date)) r = cur.fetchall() if r: 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( self, origin_id, allowed_statuses=None, require_snapshot=False, cur=None): """Retrieve the most recent origin_visit of the given origin, with optional filters. Args: origin_id: the origin concerned allowed_statuses: the visit statuses allowed for the returned visit require_snapshot (bool): If True, only a visit with a known snapshot will be returned. Returns: The origin_visit information, or None if no visit matches. """ cur = self._cursor(cur) query_parts = [ - 'SELECT %s' % ', '.join(self.origin_visit_get_cols), - 'FROM origin_visit'] + 'SELECT %s' % ', '.join(self.origin_visit_select_cols), + 'FROM origin_visit', + 'INNER JOIN origin ON origin.id = origin_visit.origin'] - query_parts.append('WHERE origin = %s') + query_parts.append('WHERE origin.url = %s') if require_snapshot: query_parts.append('AND snapshot is not null') if allowed_statuses: query_parts.append( cur.mogrify('AND status IN %s', (tuple(allowed_statuses),)).decode()) query_parts.append('ORDER BY date DESC, visit DESC LIMIT 1') query = '\n'.join(query_parts) 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 def origin_add(self, url, cur=None): """Insert a new origin and return the new identifier.""" insert = """INSERT INTO origin (url) values (%s) - RETURNING id""" + RETURNING url""" cur.execute(insert, (url,)) return cur.fetchone()[0] - origin_cols = ['id', 'url'] + origin_cols = ['url'] def origin_get_by_url(self, origins, cur=None): - """Retrieve origin `(id, type, url)` from urls if found.""" + """Retrieve origin `(type, url)` from urls if found.""" cur = self._cursor(cur) query = """SELECT %s FROM (VALUES %%s) as t(url) LEFT JOIN origin ON t.url = origin.url """ % ','.join('origin.' + col for col in self.origin_cols) yield from execute_values_generator( cur, query, ((url,) for url in origins)) - def origin_get_by_id(self, ids, cur=None): - """Retrieve origin `(id, type, url)` from ids if found. - - """ + def origin_id_get_by_url(self, origins, cur=None): + """Retrieve origin `(type, url)` from urls if found.""" 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) + query = """SELECT id FROM (VALUES %s) as t(url) + LEFT JOIN origin ON t.url = origin.url + """ - yield from execute_values_generator( - cur, query, ((id,) for id in ids)) + for row in execute_values_generator( + cur, query, ((url,) for url in origins)): + yield row[0] + + origin_get_range_cols = ['id', 'url'] 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) + """ % ','.join(self.origin_get_range_cols) cur.execute(query, (origin_from, origin_count)) yield from cur def _origin_query(self, url_pattern, count=False, offset=0, limit=50, regexp=False, with_visit=False, cur=None): """ Method factorizing query creation for searching and counting origins. """ cur = self._cursor(cur) 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 ' 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] 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 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] + provider_id, tool_id, metadata) + SELECT id, %s, %s, %s, %s FROM origin WHERE url = %s""" + cur.execute(insert, (ts, provider, tool, jsonize(metadata), origin)) - origin_metadata_get_cols = ['origin_id', 'discovery_date', + origin_metadata_get_cols = ['origin_url', '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 + def origin_metadata_get_by(self, origin_url, provider_type=None, cur=None): + """Retrieve all origin_metadata entries for one origin_url """ 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, )) + cur.execute(query, (origin_url, )) 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)) + cur.execute(query, (origin_url, 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 e0b8475..4e81266 100644 --- a/swh/storage/in_memory.py +++ b/swh/storage/in_memory.py @@ -1,1729 +1,1688 @@ # 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 os import re import bisect import dateutil import collections from collections import defaultdict import copy import datetime import itertools import random import attr from swh.model.model import \ Content, Directory, Revision, Release, Snapshot, OriginVisit, Origin from swh.model.hashutil import DEFAULT_ALGORITHMS from swh.objstorage import get_objstorage from swh.objstorage.exc import ObjNotFoundError from .storage import get_journal_writer # Max block size of contents to return BULK_BLOCK_CONTENT_LEN_MAX = 10000 def now(): return datetime.datetime.now(tz=datetime.timezone.utc) -ENABLE_ORIGIN_IDS = \ - os.environ.get('SWH_STORAGE_IN_MEMORY_ENABLE_ORIGIN_IDS', 'true') == 'true' - - class Storage: def __init__(self, journal_writer=None): self._contents = {} self._content_indexes = defaultdict(lambda: defaultdict(set)) self._skipped_contents = {} self._skipped_content_indexes = defaultdict(lambda: defaultdict(set)) self.reset() if journal_writer: self.journal_writer = get_journal_writer(**journal_writer) else: self.journal_writer = None def reset(self): self._directories = {} self._revisions = {} self._releases = {} self._snapshots = {} self._origins = {} self._origins_by_id = [] 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, with_data): content_with_data = [] content_without_data = [] for content in contents: if content.status is None: content.status = 'visible' if content.length is None: content.length = -1 if content.status != 'absent': if self._content_key(content) not in self._contents: content_with_data.append(content) else: if self._content_key(content) not in self._skipped_contents: content_without_data.append(content) if self.journal_writer: for content in content_with_data: content = attr.evolve(content, data=None) self.journal_writer.write_addition('content', content) for content in content_without_data: self.journal_writer.write_addition('content', content) count_content_added, count_content_bytes_added = \ self._content_add_present(content_with_data, with_data) count_skipped_content_added = self._content_add_absent( content_without_data ) summary = { 'content:add': count_content_added, 'skipped_content:add': count_skipped_content_added, } if with_data: summary['content:add:bytes'] = count_content_bytes_added return summary def _content_add_present(self, contents, with_data): count_content_added = 0 count_content_bytes_added = 0 for content in contents: key = self._content_key(content) if key in self._contents: continue for algorithm in DEFAULT_ALGORITHMS: hash_ = content.get_hash(algorithm) if hash_ in self._content_indexes[algorithm]\ and (algorithm not in {'blake2s256', 'sha256'}): from . import HashCollision raise HashCollision(algorithm, hash_, key) for algorithm in DEFAULT_ALGORITHMS: hash_ = content.get_hash(algorithm) self._content_indexes[algorithm][hash_].add(key) self._objects[content.sha1_git].append( ('content', content.sha1)) self._contents[key] = content bisect.insort(self._sorted_sha1s, content.sha1) count_content_added += 1 if with_data: content_data = self._contents[key].data self._contents[key] = attr.evolve( self._contents[key], data=None) count_content_bytes_added += len(content_data) self.objstorage.add(content_data, content.sha1) return (count_content_added, count_content_bytes_added) def _content_add_absent(self, contents): count = 0 skipped_content_missing = self.skipped_content_missing(contents) for content in skipped_content_missing: key = self._content_key(content) for algo in DEFAULT_ALGORITHMS: self._skipped_content_indexes[algo][content.get_hash(algo)] \ .add(key) self._skipped_contents[key] = content count += 1 return count def _content_to_model(self, contents): """Takes a list of content dicts, optionally with an extra 'origin' key, and yields tuples (model.Content, origin).""" for content in contents: content = content.copy() content.pop('origin', None) yield Content.from_dict(content) def content_add(self, content): """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 Raises: HashCollision in case of collision Returns: Summary dict with the following key and associated values: content:add: New contents added content_bytes:add: Sum of the contents' length data skipped_content:add: New skipped contents (no data) added """ now = datetime.datetime.now(tz=datetime.timezone.utc) content = [attr.evolve(c, ctime=now) for c in self._content_to_model(content)] return self._content_add(content, with_data=True) def content_add_metadata(self, content): """Add content metadata to the storage (like `content_add`, but without inserting to the objstorage). Args: content (iterable): iterable of dictionaries representing individual pieces of content to add. Each dictionary has the following keys: - 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 - ctime (datetime): time of insertion in the archive Raises: HashCollision in case of collision Returns: Summary dict with the following key and associated values: content:add: New contents added skipped_content:add: New skipped contents (no data) added """ content = list(self._content_to_model(content)) return self._content_add(content, with_data=False) def content_get(self, content): """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(content) > BULK_BLOCK_CONTENT_LEN_MAX: raise ValueError( "Sending at most %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} 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].to_dict()) return { 'contents': matched, 'next': next_content, } def content_get_metadata(self, content): """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 content: 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] d = self._contents[key].to_dict() del d['ctime'] yield d 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)) return [self._contents[key].to_dict() for key in keys] def content_missing(self, content, 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 cont in content: for (algo, hash_) in cont.items(): if algo not in DEFAULT_ALGORITHMS: continue if hash_ not in self._content_indexes.get(algo, []): yield cont[key_hash] break else: for result in self.content_find(cont): if result['status'] == 'missing': yield cont[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 skipped_content_missing(self, contents): """List all skipped_content missing from storage Args: contents: Iterable of sha1 to check for skipped content entry Returns: iterable: dict of skipped content entry """ for content in contents: for (key, algorithm) in self._content_key_algorithm(content): if algorithm == 'blake2s256': continue if key not in self._skipped_content_indexes[algorithm]: # index must contain hashes of algos except blake2s256 # else the content is considered skipped yield content break 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 Returns: Summary dict of keys with associated count as values: directory:add: Number of directories actually added """ if self.journal_writer: self.journal_writer.write_additions( 'directory', (dir_ for dir_ in directories if dir_['id'] not in self._directories)) directories = [Directory.from_dict(d) for d in directories] count = 0 for directory in directories: if directory.id not in self._directories: count += 1 self._directories[directory.id] = directory self._objects[directory.id].append( ('directory', directory.id)) return {'directory:add': count} def directory_missing(self, directories): """List directories missing from storage Args: directories (iterable): an iterable of directory ids Yields: missing directory ids """ for id in directories: 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': # TODO: Make it able to handle more than one content content = self.content_find({'sha1_git': ret['target']}) if content: content = content[0] 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.to_dict()) 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, 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, 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. """ return self._directory_entry_get_by_path(directory, paths, b'') def _directory_entry_get_by_path(self, directory, paths, prefix): 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: entry = entry.copy() entry['name'] = prefix + entry['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:], prefix + paths[0] + b'/') 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`. Returns: Summary dict of keys with associated count as values revision_added: New objects actually stored in db """ if self.journal_writer: self.journal_writer.write_additions( 'revision', (rev for rev in revisions if rev['id'] not in self._revisions)) revisions = [Revision.from_dict(rev) for rev in revisions] count = 0 for revision in revisions: if revision.id not in self._revisions: revision = attr.evolve( revision, committer=self._person_add(revision.committer), author=self._person_add(revision.author)) self._revisions[revision.id] = revision self._objects[revision.id].append( ('revision', revision.id)) count += 1 return {'revision:add': count} def revision_missing(self, revisions): """List revisions missing from storage Args: revisions (iterable): revision ids Yields: missing revision ids """ for id in revisions: if id not in self._revisions: yield id def revision_get(self, revisions): for id in revisions: if id in self._revisions: yield self._revisions.get(id).to_dict() else: yield None 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].to_dict() for parent in self._revisions[rev_id].parents: yield from self._get_parent_revs(parent, seen, limit) def revision_log(self, revisions, 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 revisions: 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`. Returns: Summary dict of keys with associated count as values release:add: New objects contents actually stored in db """ if self.journal_writer: self.journal_writer.write_additions( 'release', (rel for rel in releases if rel['id'] not in self._releases)) releases = [Release.from_dict(rel) for rel in releases] count = 0 for rel in releases: if rel.id not in self._releases: if rel.author: self._person_add(rel.author) self._objects[rel.id].append( ('release', rel.id)) self._releases[rel.id] = rel count += 1 return {'release:add': count} 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: if rel_id in self._releases: yield self._releases[rel_id].to_dict() else: yield None def snapshot_add(self, snapshots): """Add a snapshot to the storage Args: snapshot ([dict]): the snapshots to add, 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. Returns: Summary dict of keys with associated count as values snapshot_added: Count of object actually stored in db """ count = 0 snapshots = (Snapshot.from_dict(d) for d in snapshots) snapshots = (snap for snap in snapshots if snap.id not in self._snapshots) for snapshot in snapshots: if self.journal_writer: self.journal_writer.write_addition('snapshot', snapshot) sorted_branch_names = sorted(snapshot.branches) self._snapshots[snapshot.id] = (snapshot, sorted_branch_names) self._objects[snapshot.id].append(('snapshot', snapshot.id)) count += 1 return {'snapshot:add': count} 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. """ origin_url = self._get_origin_url(origin) if not origin_url: return if origin_url not in self._origins or \ visit > len(self._origin_visits[origin_url]): return None snapshot_id = self._origin_visits[origin_url][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 methods :meth:`origin_visit_get_latest` and :meth:`snapshot_get_branches` should be used instead. Args: - origin (Union[str,int]): the origin's URL or identifier + origin (str): the origin's URL allowed_statuses (list of str): list of visit statuses considered to find the latest snapshot for the origin. 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_url = self._get_origin_url(origin) if not origin_url: return visit = self.origin_visit_get_latest( origin_url, allowed_statuses=allowed_statuses, require_snapshot=True) if visit and visit['snapshot']: snapshot = self.snapshot_get(visit['snapshot']) if not snapshot: raise ValueError( 'last origin visit references an unknown snapshot') 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 """ (snapshot, _) = self._snapshots[snapshot_id] return collections.Counter(branch.target_type.value if branch else None for branch in snapshot.branches.values()) 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. """ res = self._snapshots.get(snapshot_id) if res is None: return None (snapshot, sorted_branch_names) = res 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.value 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] branches = {name: branch.to_dict() if branch else None for (name, branch) in branches.items()} 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 _convert_origin(self, t): if t is None: return None - (origin_id, origin) = t - origin = origin.to_dict() - if ENABLE_ORIGIN_IDS: - origin['id'] = origin_id - if 'type' in origin: - del origin['type'] - - return origin + return t.to_dict() def origin_get(self, origins): """Return origins, either all identified by their ids or all identified by urls. Args: origin: a list of dictionaries representing the individual origins to find. These dicts have either the key url (and optionally type): - 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 - 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('url' in origin for origin in origins) \ and not all('url' in origin for origin in origins): raise ValueError( 'Either all origins or none at all should have ' 'an "url" key.') results = [] for origin in origins: result = None - if 'id' in origin: - assert ENABLE_ORIGIN_IDS, 'origin ids are disabled' - if origin['id'] <= len(self._origins_by_id): - result = self._origins[self._origins_by_id[origin['id']-1]] - elif 'url' in origin: + if 'url' in origin: if origin['url'] in self._origins: result = self._origins[origin['url']] else: raise ValueError( - 'Origin must have either id or url.') + 'Origin must have an url.') results.append(self._convert_origin(result)) 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`. + by :meth:`swh.storage.in_memory.Storage.origin_get`, plus + an 'id' key. """ origin_from = max(origin_from, 1) if origin_from <= len(self._origins_by_id): max_idx = origin_from + origin_count - 1 if max_idx > len(self._origins_by_id): max_idx = len(self._origins_by_id) for idx in range(origin_from-1, max_idx): - yield self._convert_origin( + origin = self._convert_origin( self._origins[self._origins_by_id[idx]]) + yield {'id': idx+1, **origin} 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 = map(self._convert_origin, self._origins.values()) if regexp: pat = re.compile(url_pattern) origins = [orig for orig in origins if pat.search(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['url']]) > 0] - if ENABLE_ORIGIN_IDS: - origins.sort(key=lambda origin: origin['id']) - return origins[offset:offset+limit] 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: - 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: - if ENABLE_ORIGIN_IDS: - origin['id'] = self.origin_add_one(origin) - else: - self.origin_add_one(origin) + 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: - url (bytes): the url the origin points to Returns: the id of the added origin, or of the identical one that already exists. """ origin = Origin.from_dict(origin) - - if origin.url in self._origins: - if ENABLE_ORIGIN_IDS: - (origin_id, _) = self._origins[origin.url] - else: + if origin.url not in self._origins: if self.journal_writer: self.journal_writer.write_addition('origin', origin) - if ENABLE_ORIGIN_IDS: - # origin ids are in the range [1, +inf[ - origin_id = len(self._origins) + 1 - self._origins_by_id.append(origin.url) - assert len(self._origins_by_id) == origin_id - else: - origin_id = None - self._origins[origin.url] = (origin_id, origin) + + # generate an origin_id because it is needed by origin_get_range. + # TODO: remove this when we remove origin_get_range + origin_id = len(self._origins) + 1 + self._origins_by_id.append(origin.url) + assert len(self._origins_by_id) == origin_id + + self._origins[origin.url] = origin self._origin_visits[origin.url] = [] self._objects[origin.url].append(('origin', origin.url)) - if ENABLE_ORIGIN_IDS: - return origin_id - else: - return origin.url + return origin.url def origin_visit_add(self, origin, date, type): """Add an origin_visit for the origin at date with status 'ongoing'. Args: - origin (Union[int,str]): visited origin's identifier or URL + origin (str): visited origin's identifier or URL date (Union[str,datetime]): timestamp of such visit type (str): the type of loader used for the visit (hg, git, ...) Returns: dict: dictionary with keys origin and visit where: - origin: origin's identifier - visit: the visit's identifier for the new visit occurrence """ - origin_url = self._get_origin_url(origin) + origin_url = origin if origin_url is None: raise ValueError('Unknown origin.') if isinstance(date, str): # FIXME: Converge on iso8601 at some point date = dateutil.parser.parse(date) elif not isinstance(date, datetime.datetime): raise TypeError('date must be a datetime or a string.') visit_ret = None if origin_url in self._origins: - (origin_id, origin) = self._origins[origin_url] + origin = self._origins[origin_url] # visit ids are in the range [1, +inf[ visit_id = len(self._origin_visits[origin_url]) + 1 status = 'ongoing' visit = OriginVisit( - origin=origin, + origin=origin.url, date=date, type=type, status=status, snapshot=None, metadata=None, visit=visit_id, ) self._origin_visits[origin_url].append(visit) visit_ret = { - 'origin': origin_id if ENABLE_ORIGIN_IDS else origin.url, + 'origin': origin.url, 'visit': visit_id, } self._objects[(origin_url, visit_id)].append( ('origin_visit', None)) if self.journal_writer: + visit = attr.evolve(visit, origin=origin) self.journal_writer.write_addition('origin_visit', visit) return visit_ret def origin_visit_update(self, origin, visit_id, status=None, metadata=None, snapshot=None): """Update an origin_visit's status. Args: - origin (Union[int,str]): visited origin's identifier or URL + origin (str): visited origin's URL visit_id (int): visit's identifier status: visit's new status metadata: data associated to the visit snapshot (sha1_git): identifier of the snapshot to add to the visit Returns: None """ origin_url = self._get_origin_url(origin) if origin_url is None: raise ValueError('Unknown origin.') try: visit = self._origin_visits[origin_url][visit_id-1] except IndexError: raise ValueError('Unknown visit_id for this origin') \ from None updates = {} if status: updates['status'] = status if metadata: updates['metadata'] = metadata if snapshot: updates['snapshot'] = snapshot visit = attr.evolve(visit, **updates) if self.journal_writer: - (_, origin) = self._origins[origin_url] - self.journal_writer.write_update('origin_visit', visit) + origin = self._origins[origin_url] + journal_visit = attr.evolve(visit, origin=origin) + self.journal_writer.write_update('origin_visit', journal_visit) self._origin_visits[origin_url][visit_id-1] = visit if origin_url not in self._origin_visits or \ visit_id > len(self._origin_visits[origin_url]): return def origin_visit_upsert(self, visits): """Add a origin_visits with a specific id and with all its data. If there is already an origin_visit with the same `(origin_url, visit_id)`, updates it instead of inserting a new one. Args: visits: iterable of dicts with keys: origin: dict with keys either `id` or `url` visit: origin visit id type: type of loader used for the visit date: timestamp of such visit status: Visit's new status metadata: Data associated to the visit snapshot (sha1_git): identifier of the snapshot to add to the visit """ visits = [OriginVisit.from_dict(d) for d in visits] if self.journal_writer: for visit in visits: visit = attr.evolve( visit, - origin=self._origins[visit.origin.url][1]) + origin=self._origins[visit.origin.url]) self.journal_writer.write_addition('origin_visit', visit) for visit in visits: visit_id = visit.visit origin_url = visit.origin.url + visit = attr.evolve(visit, origin=origin_url) + self._objects[(origin_url, visit_id)].append( ('origin_visit', None)) while len(self._origin_visits[origin_url]) <= visit_id: self._origin_visits[origin_url].append(None) self._origin_visits[origin_url][visit_id-1] = visit def _convert_visit(self, visit): if visit is None: return - (origin_id, origin) = self._origins[visit.origin.url] visit = visit.to_dict() - if ENABLE_ORIGIN_IDS: - visit['origin'] = origin_id - else: - visit['origin'] = origin.url return visit 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. """ origin_url = self._get_origin_url(origin) if origin_url in self._origin_visits: visits = self._origin_visits[origin_url] if last_visit is not None: visits = visits[last_visit:] if limit is not None: visits = visits[:limit] for visit in visits: if not visit: continue visit_id = visit.visit yield self._convert_visit( self._origin_visits[origin_url][visit_id-1]) def origin_visit_find_by_date(self, origin, visit_date): """Retrieves the origin visit whose date is closest to the provided timestamp. In case of a tie, the visit with largest id is selected. Args: origin (str): The occurrence's origin (URL). target (datetime): target timestamp Returns: A visit. """ origin_url = self._get_origin_url(origin) if origin_url in self._origin_visits: visits = self._origin_visits[origin_url] visit = min( visits, key=lambda v: (abs(v.date - visit_date), -v.visit)) return self._convert_visit(visit) 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_url = self._get_origin_url(origin) if origin_url in self._origin_visits and \ visit <= len(self._origin_visits[origin_url]): return self._convert_visit( self._origin_visits[origin_url][visit-1]) def origin_visit_get_latest( self, origin, allowed_statuses=None, require_snapshot=False): """Get the latest origin visit for the given origin, optionally looking only for those with one of the given allowed_statuses or for those with a known snapshot. Args: origin (str): the origin's URL allowed_statuses (list of str): list of visit statuses considered to find the latest visit. For instance, ``allowed_statuses=['full']`` will only consider visits that have successfully run to completion. require_snapshot (bool): If True, only a visit with a snapshot will be returned. Returns: dict: a dict with the following keys: origin: the URL of the origin visit: origin visit id type: type of loader used for the visit date: timestamp of such visit status: Visit's new status metadata: Data associated to the visit snapshot (Optional[sha1_git]): identifier of the snapshot associated to the visit """ - res = self._origins.get(origin) - if not res: + origin = self._origins.get(origin) + if not origin: return - (_, origin) = res visits = self._origin_visits[origin.url] if allowed_statuses is not None: visits = [visit for visit in visits if visit.status in allowed_statuses] if require_snapshot: visits = [visit for visit in visits if visit.snapshot] visit = max( visits, key=lambda v: (v.date, v.visit), default=None) return self._convert_visit(visit) 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, + def origin_metadata_add(self, origin_url, 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 + origin_url (str): the origin url 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(origin_id, str): - origin = self.origin_get({'url': origin_id}) - if not origin: - return - origin_id = origin['id'] + if not isinstance(origin_url, str): + raise TypeError('origin_id must be str, not %r' % (origin_url,)) if isinstance(ts, str): ts = dateutil.parser.parse(ts) origin_metadata = { - 'origin_id': origin_id, + 'origin_url': origin_url, 'discovery_date': ts, 'tool_id': tool, 'metadata': metadata, 'provider_id': provider, } - self._origin_metadata[origin_id].append(origin_metadata) + self._origin_metadata[origin_url].append(origin_metadata) return None - def origin_metadata_get_by(self, origin_id, provider_type=None, db=None, + def origin_metadata_get_by(self, origin_url, provider_type=None, db=None, cur=None): - """Retrieve list of all origin_metadata entries for the origin_id + """Retrieve list of all origin_metadata entries for the origin_url Args: - origin_id (int): the unique origin's identifier + origin_url (str): the origin's url provider_type (str): (optional) type of provider Returns: list of dicts: the origin_metadata dictionary with the keys: - - origin_id (int): origin's identifier + - origin_url (int): origin's URL - 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) """ - if isinstance(origin_id, str): - origin = self.origin_get({'url': origin_id}) - if not origin: - return - origin_id = origin['id'] - + if not isinstance(origin_url, str): + raise TypeError('origin_url must be str, not %r' % (origin_url,)) metadata = [] - for item in self._origin_metadata[origin_id]: + for item in self._origin_metadata[origin_url]: item = copy.deepcopy(item) provider = self.metadata_provider_get(item['provider_id']) for attr_name in ('name', 'type', 'url'): item['provider_' + attr_name] = \ provider['provider_' + attr_name] 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 Returns: :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])) return 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 = { 'provider_name': provider_name, 'provider_type': provider_type, 'provider_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(provider) return self._metadata_providers.get(key) def _get_origin_url(self, origin): if isinstance(origin, str): return origin - elif isinstance(origin, int): - if origin <= len(self._origins_by_id): - return self._origins_by_id[origin-1] - else: - return None else: - raise TypeError('origin must be a string or an integer.') + raise TypeError('origin must be a string.') 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(person) self._objects[key].append(('person', person_id)) else: person_id = self._objects[key][0][1] person = self._persons[person_id-1] return person @staticmethod def _content_key(content): """A stable key for a content""" return tuple(getattr(content, key) for key in sorted(DEFAULT_ALGORITHMS)) @staticmethod def _content_key_algorithm(content): """ A stable key and the algorithm for a content""" if isinstance(content, Content): content = content.to_dict() return tuple((content.get(key), key) for key in sorted(DEFAULT_ALGORITHMS)) @staticmethod def _tool_key(tool): return '%r %r %r' % (tool['name'], tool['version'], tuple(sorted(tool['configuration'].items()))) @staticmethod def _metadata_provider_key(provider): return '%r %r' % (provider['provider_name'], provider['provider_url']) diff --git a/swh/storage/sql/30-swh-schema.sql b/swh/storage/sql/30-swh-schema.sql index 31ae3a6..dca2434 100644 --- a/swh/storage/sql/30-swh-schema.sql +++ b/swh/storage/sql/30-swh-schema.sql @@ -1,469 +1,469 @@ --- --- SQL implementation of the Software Heritage data model --- -- schema versions create table dbversion ( version int primary key, release timestamptz, description text ); comment on table dbversion is 'Details of current db version'; comment on column dbversion.version is 'SQL schema version'; comment on column dbversion.release is 'Version deployment timestamp'; comment on column dbversion.description is 'Release description'; -- latest schema version insert into dbversion(version, release, description) - values(142, now(), 'Work In Progress'); + values(143, now(), 'Work In Progress'); -- a SHA1 checksum create domain sha1 as bytea check (length(value) = 20); -- a Git object ID, i.e., a Git-style salted SHA1 checksum create domain sha1_git as bytea check (length(value) = 20); -- a SHA256 checksum create domain sha256 as bytea check (length(value) = 32); -- a blake2 checksum create domain blake2s256 as bytea check (length(value) = 32); -- UNIX path (absolute, relative, individual path component, etc.) create domain unix_path as bytea; -- a set of UNIX-like access permissions, as manipulated by, e.g., chmod create domain file_perms as int; -- Checksums about actual file content. Note that the content itself is not -- stored in the DB, but on external (key-value) storage. A single checksum is -- used as key there, but the other can be used to verify that we do not inject -- content collisions not knowingly. create table content ( sha1 sha1 not null, sha1_git sha1_git not null, sha256 sha256 not null, blake2s256 blake2s256, length bigint not null, ctime timestamptz not null default now(), -- creation time, i.e. time of (first) injection into the storage status content_status not null default 'visible', object_id bigserial ); comment on table content is 'Checksums of file content which is actually stored externally'; comment on column content.sha1 is 'Content sha1 hash'; comment on column content.sha1_git is 'Git object sha1 hash'; comment on column content.sha256 is 'Content Sha256 hash'; comment on column content.blake2s256 is 'Content blake2s hash'; comment on column content.length is 'Content length'; comment on column content.ctime is 'First seen time'; comment on column content.status is 'Content status (absent, visible, hidden)'; comment on column content.object_id is 'Content identifier'; -- An origin is a place, identified by an URL, where software source code -- artifacts can be found. We support different kinds of origins, e.g., git and -- other VCS repositories, web pages that list tarballs URLs (e.g., -- http://www.kernel.org), indirect tarball URLs (e.g., -- http://www.example.org/latest.tar.gz), etc. The key feature of an origin is -- that it can be *fetched* from (wget, git clone, svn checkout, etc.) to -- retrieve all the contained software. create table origin ( id bigserial not null, url text not null ); comment on column origin.id is 'Artifact origin id'; comment on column origin.url is 'URL of origin'; -- Content blobs observed somewhere, but not ingested into the archive for -- whatever reason. This table is separate from the content table as we might -- not have the sha1 checksum of skipped contents (for instance when we inject -- git repositories, objects that are too big will be skipped here, and we will -- only know their sha1_git). 'reason' contains the reason the content was -- skipped. origin is a nullable column allowing to find out which origin -- contains that skipped content. create table skipped_content ( sha1 sha1, sha1_git sha1_git, sha256 sha256, blake2s256 blake2s256, length bigint not null, ctime timestamptz not null default now(), status content_status not null default 'absent', reason text not null, origin bigint, object_id bigserial ); comment on table skipped_content is 'Content blobs observed, but not ingested in the archive'; comment on column skipped_content.sha1 is 'Skipped content sha1 hash'; comment on column skipped_content.sha1_git is 'Git object sha1 hash'; comment on column skipped_content.sha256 is 'Skipped content sha256 hash'; comment on column skipped_content.blake2s256 is 'Skipped content blake2s hash'; comment on column skipped_content.length is 'Skipped content length'; comment on column skipped_content.ctime is 'First seen time'; comment on column skipped_content.status is 'Skipped content status (absent, visible, hidden)'; comment on column skipped_content.reason is 'Reason for skipping'; comment on column skipped_content.origin is 'Origin table identifier'; comment on column skipped_content.object_id is 'Skipped content identifier'; -- A file-system directory. A directory is a list of directory entries (see -- tables: directory_entry_{dir,file}). -- -- To list the contents of a directory: -- 1. list the contained directory_entry_dir using array dir_entries -- 2. list the contained directory_entry_file using array file_entries -- 3. list the contained directory_entry_rev using array rev_entries -- 4. UNION -- -- Synonyms/mappings: -- * git: tree create table directory ( id sha1_git not null, dir_entries bigint[], -- sub-directories, reference directory_entry_dir file_entries bigint[], -- contained files, reference directory_entry_file rev_entries bigint[], -- mounted revisions, reference directory_entry_rev object_id bigserial -- short object identifier ); comment on table directory is 'Contents of a directory, synonymous to tree (git)'; comment on column directory.id is 'Git object sha1 hash'; comment on column directory.dir_entries is 'Sub-directories, reference directory_entry_dir'; comment on column directory.file_entries is 'Contained files, reference directory_entry_file'; comment on column directory.rev_entries is 'Mounted revisions, reference directory_entry_rev'; comment on column directory.object_id is 'Short object identifier'; -- A directory entry pointing to a (sub-)directory. create table directory_entry_dir ( id bigserial, target sha1_git not null, -- id of target directory name unix_path not null, -- path name, relative to containing dir perms file_perms not null -- unix-like permissions ); comment on table directory_entry_dir is 'Directory entry for directory'; comment on column directory_entry_dir.id is 'Directory identifier'; comment on column directory_entry_dir.target is 'Target directory identifier'; comment on column directory_entry_dir.name is 'Path name, relative to containing directory'; comment on column directory_entry_dir.perms is 'Unix-like permissions'; -- A directory entry pointing to a file content. create table directory_entry_file ( id bigserial, target sha1_git not null, -- id of target file name unix_path not null, -- path name, relative to containing dir perms file_perms not null -- unix-like permissions ); comment on table directory_entry_file is 'Directory entry for file'; comment on column directory_entry_file.id is 'File identifier'; comment on column directory_entry_file.target is 'Target file identifier'; comment on column directory_entry_file.name is 'Path name, relative to containing directory'; comment on column directory_entry_file.perms is 'Unix-like permissions'; -- A directory entry pointing to a revision. create table directory_entry_rev ( id bigserial, target sha1_git not null, -- id of target revision name unix_path not null, -- path name, relative to containing dir perms file_perms not null -- unix-like permissions ); comment on table directory_entry_rev is 'Directory entry for revision'; comment on column directory_entry_dir.id is 'Revision identifier'; comment on column directory_entry_dir.target is 'Target revision in identifier'; comment on column directory_entry_dir.name is 'Path name, relative to containing directory'; comment on column directory_entry_dir.perms is 'Unix-like permissions'; -- A person referenced by some source code artifacts, e.g., a VCS revision or -- release metadata. create table person ( id bigserial, name bytea, -- advisory: not null if we managed to parse a name email bytea, -- advisory: not null if we managed to parse an email fullname bytea not null -- freeform specification; what is actually used in the checksums -- will usually be of the form 'name ' ); comment on table person is 'Person referenced in code artifact release metadata'; comment on column person.id is 'Person identifier'; comment on column person.name is 'Name'; comment on column person.email is 'Email'; comment on column person.fullname is 'Full name (raw name)'; -- The state of a source code tree at a specific point in time. -- -- Synonyms/mappings: -- * git / subversion / etc: commit -- * tarball: a specific tarball -- -- Revisions are organized as DAGs. Each revision points to 0, 1, or more (in -- case of merges) parent revisions. Each revision points to a directory, i.e., -- a file-system tree containing files and directories. create table revision ( id sha1_git not null, date timestamptz, date_offset smallint, committer_date timestamptz, committer_date_offset smallint, type revision_type not null, directory sha1_git, -- source code 'root' directory message bytea, author bigint, committer bigint, synthetic boolean not null default false, -- true iff revision has been created by Software Heritage metadata jsonb, -- extra metadata (tarball checksums, extra commit information, etc...) object_id bigserial, date_neg_utc_offset boolean, committer_date_neg_utc_offset boolean ); comment on table revision is 'Revision represents the state of a source code tree at a specific point in time'; comment on column revision.id is 'Git id of sha1 checksum'; comment on column revision.date is 'Timestamp when revision was authored'; comment on column revision.date_offset is 'Authored timestamp offset from UTC'; comment on column revision.committer_date is 'Timestamp when revision was committed'; comment on column revision.committer_date_offset is 'Committed timestamp offset from UTC'; comment on column revision.type is 'Possible revision types (''git'', ''tar'', ''dsc'', ''svn'', ''hg'')'; comment on column revision.directory is 'Directory identifier'; comment on column revision.message is 'Revision message'; comment on column revision.author is 'Author identifier'; comment on column revision.committer is 'Committer identifier'; comment on column revision.synthetic is 'true iff revision has been created by Software Heritage'; comment on column revision.metadata is 'extra metadata (tarball checksums, extra commit information, etc...)'; comment on column revision.object_id is 'Object identifier'; comment on column revision.date_neg_utc_offset is 'True indicates -0 UTC offset for author timestamp'; comment on column revision.committer_date_neg_utc_offset is 'True indicates -0 UTC offset for committer timestamp'; -- either this table or the sha1_git[] column on the revision table create table revision_history ( id sha1_git not null, parent_id sha1_git not null, parent_rank int not null default 0 -- parent position in merge commits, 0-based ); comment on table revision_history is 'Sequence of revision history with parent and position in history'; comment on column revision_history.id is 'Revision history git object sha1 checksum'; comment on column revision_history.parent_id is 'Parent revision git object identifier'; comment on column revision_history.parent_rank is 'Parent position in merge commits, 0-based'; -- Crawling history of software origins visited by Software Heritage. Each -- visit is a 3-way mapping between a software origin, a timestamp, and a -- snapshot object capturing the full-state of the origin at visit time. create table origin_visit ( origin bigint not null, visit bigint not null, date timestamptz not null, type text not null, status origin_visit_status not null, metadata jsonb, snapshot sha1_git ); comment on column origin_visit.origin is 'Visited origin'; comment on column origin_visit.visit is 'Sequential visit number for the origin'; comment on column origin_visit.date is 'Visit timestamp'; comment on column origin_visit.type is 'Type of loader that did the visit (hg, git, ...)'; comment on column origin_visit.status is 'Visit result'; comment on column origin_visit.metadata is 'Origin metadata at visit time'; comment on column origin_visit.snapshot is 'Origin snapshot at visit time'; -- A snapshot represents the entire state of a software origin as crawled by -- Software Heritage. This table is a simple mapping between (public) intrinsic -- snapshot identifiers and (private) numeric sequential identifiers. create table snapshot ( object_id bigserial not null, -- PK internal object identifier id sha1_git not null -- snapshot intrinsic identifier ); comment on table snapshot is 'State of a software origin as crawled by Software Heritage'; comment on column snapshot.object_id is 'Internal object identifier'; comment on column snapshot.id is 'Intrinsic snapshot identifier'; -- Each snapshot associate "branch" names to other objects in the Software -- Heritage Merkle DAG. This table describes branches as mappings between names -- and target typed objects. create table snapshot_branch ( object_id bigserial not null, -- PK internal object identifier name bytea not null, -- branch name, e.g., "master" or "feature/drag-n-drop" target bytea, -- target object identifier, e.g., a revision identifier target_type snapshot_target -- target object type, e.g., "revision" ); comment on table snapshot_branch is 'Associates branches with objects in Heritage Merkle DAG'; comment on column snapshot_branch.object_id is 'Internal object identifier'; comment on column snapshot_branch.name is 'Branch name'; comment on column snapshot_branch.target is 'Target object identifier'; comment on column snapshot_branch.target_type is 'Target object type'; -- Mapping between snapshots and their branches. create table snapshot_branches ( snapshot_id bigint not null, -- snapshot identifier, ref. snapshot.object_id branch_id bigint not null -- branch identifier, ref. snapshot_branch.object_id ); comment on table snapshot_branches is 'Mapping between snapshot and their branches'; comment on column snapshot_branches.snapshot_id is 'Snapshot identifier'; comment on column snapshot_branches.branch_id is 'Branch identifier'; -- A "memorable" point in time in the development history of a software -- project. -- -- Synonyms/mappings: -- * git: tag (of the annotated kind, otherwise they are just references) -- * tarball: the release version number create table release ( id sha1_git not null, target sha1_git, date timestamptz, date_offset smallint, name bytea, comment bytea, author bigint, synthetic boolean not null default false, -- true iff release has been created by Software Heritage object_id bigserial, target_type object_type not null, date_neg_utc_offset boolean ); comment on table release is 'Details of a software release, synonymous with a tag (git) or version number (tarball)'; comment on column release.id is 'Release git identifier'; comment on column release.target is 'Target git identifier'; comment on column release.date is 'Release timestamp'; comment on column release.date_offset is 'Timestamp offset from UTC'; comment on column release.name is 'Name'; comment on column release.comment is 'Comment'; comment on column release.author is 'Author'; comment on column release.synthetic is 'Indicates if created by Software Heritage'; comment on column release.object_id is 'Object identifier'; comment on column release.target_type is 'Object type (''content'', ''directory'', ''revision'', ''release'', ''snapshot'')'; comment on column release.date_neg_utc_offset is 'True indicates -0 UTC offset for release timestamp'; -- Tools create table tool ( id serial not null, name text not null, version text not null, configuration jsonb ); comment on table tool is 'Tool information'; comment on column tool.id is 'Tool identifier'; comment on column tool.version is 'Tool name'; comment on column tool.version is 'Tool version'; comment on column tool.configuration is 'Tool configuration: command line, flags, etc...'; create table metadata_provider ( id serial not null, provider_name text not null, provider_type text not null, provider_url text, metadata jsonb ); comment on table metadata_provider is 'Metadata provider information'; comment on column metadata_provider.id is 'Provider''s identifier'; comment on column metadata_provider.provider_name is 'Provider''s name'; comment on column metadata_provider.provider_url is 'Provider''s url'; comment on column metadata_provider.metadata is 'Other metadata about provider'; -- Discovery of metadata during a listing, loading, deposit or external_catalog of an origin -- also provides a translation to a defined json schema using a translation tool (tool_id) create table origin_metadata ( id bigserial not null, -- PK internal object identifier origin_id bigint not null, -- references origin(id) discovery_date timestamptz not null, -- when it was extracted provider_id bigint not null, -- ex: 'hal', 'lister-github', 'loader-github' tool_id bigint not null, metadata jsonb not null ); comment on table origin_metadata is 'keeps all metadata found concerning an origin'; comment on column origin_metadata.id is 'the origin_metadata object''s id'; comment on column origin_metadata.origin_id is 'the origin id for which the metadata was found'; comment on column origin_metadata.discovery_date is 'the date of retrieval'; comment on column origin_metadata.provider_id is 'the metadata provider: github, openhub, deposit, etc.'; comment on column origin_metadata.tool_id is 'the tool used for extracting metadata: lister-github, etc.'; comment on column origin_metadata.metadata is 'metadata in json format but with original terms'; -- Keep a cache of object counts create table object_counts ( object_type text, -- table for which we're counting objects (PK) value bigint, -- count of objects in the table last_update timestamptz, -- last update for the object count in this table single_update boolean -- whether we update this table standalone (true) or through bucketed counts (false) ); comment on table object_counts is 'Cache of object counts'; comment on column object_counts.object_type is 'Object type (''content'', ''directory'', ''revision'', ''release'', ''snapshot'')'; comment on column object_counts.value is 'Count of objects in the table'; comment on column object_counts.last_update is 'Last update for object count'; comment on column object_counts.single_update is 'standalone (true) or bucketed counts (false)'; create table object_counts_bucketed ( line serial not null, -- PK object_type text not null, -- table for which we're counting objects identifier text not null, -- identifier across which we're bucketing objects bucket_start bytea, -- lower bound (inclusive) for the bucket bucket_end bytea, -- upper bound (exclusive) for the bucket value bigint, -- count of objects in the bucket last_update timestamptz -- last update for the object count in this bucket ); comment on table object_counts_bucketed is 'Bucketed count for objects ordered by type'; comment on column object_counts_bucketed.line is 'Auto incremented idenitfier value'; comment on column object_counts_bucketed.object_type is 'Object type (''content'', ''directory'', ''revision'', ''release'', ''snapshot'')'; comment on column object_counts_bucketed.identifier is 'Common identifier for bucketed objects'; comment on column object_counts_bucketed.bucket_start is 'Lower bound (inclusive) for the bucket'; comment on column object_counts_bucketed.bucket_end is 'Upper bound (exclusive) for the bucket'; comment on column object_counts_bucketed.value is 'Count of objects in the bucket'; comment on column object_counts_bucketed.last_update is 'Last update for the object count in this bucket'; diff --git a/swh/storage/sql/40-swh-func.sql b/swh/storage/sql/40-swh-func.sql index e525ba1..7c1a88d 100644 --- a/swh/storage/sql/40-swh-func.sql +++ b/swh/storage/sql/40-swh-func.sql @@ -1,1120 +1,1121 @@ create or replace function hash_sha1(text) returns text as $$ select encode(digest($1, 'sha1'), 'hex') $$ language sql strict immutable; comment on function hash_sha1(text) is 'Compute SHA1 hash as text'; -- create a temporary table called tmp_TBLNAME, mimicking existing table -- TBLNAME -- -- Args: -- tblname: name of the table to mimick create or replace function swh_mktemp(tblname regclass) returns void language plpgsql as $$ begin execute format(' create temporary table tmp_%1$I (like %1$I including defaults) on commit drop; alter table tmp_%1$I drop column if exists object_id; ', tblname); return; end $$; -- create a temporary table for directory entries called tmp_TBLNAME, -- mimicking existing table TBLNAME with an extra dir_id (sha1_git) -- column, and dropping the id column. -- -- This is used to create the tmp_directory_entry_ tables. -- -- Args: -- tblname: name of the table to mimick create or replace function swh_mktemp_dir_entry(tblname regclass) returns void language plpgsql as $$ begin execute format(' create temporary table tmp_%1$I (like %1$I including defaults, dir_id sha1_git) on commit drop; alter table tmp_%1$I drop column id; ', tblname); return; end $$; -- create a temporary table for revisions called tmp_revisions, -- mimicking existing table revision, replacing the foreign keys to -- people with an email and name field -- create or replace function swh_mktemp_revision() returns void language sql as $$ create temporary table tmp_revision ( like revision including defaults, author_fullname bytea, author_name bytea, author_email bytea, committer_fullname bytea, committer_name bytea, committer_email bytea ) on commit drop; alter table tmp_revision drop column author; alter table tmp_revision drop column committer; alter table tmp_revision drop column object_id; $$; -- create a temporary table for releases called tmp_release, -- mimicking existing table release, replacing the foreign keys to -- people with an email and name field -- create or replace function swh_mktemp_release() returns void language sql as $$ create temporary table tmp_release ( like release including defaults, author_fullname bytea, author_name bytea, author_email bytea ) on commit drop; alter table tmp_release drop column author; alter table tmp_release drop column object_id; $$; -- create a temporary table for the branches of a snapshot create or replace function swh_mktemp_snapshot_branch() returns void language sql as $$ create temporary table tmp_snapshot_branch ( name bytea not null, target bytea, target_type snapshot_target ) on commit drop; $$; create or replace function swh_mktemp_tool() returns void language sql as $$ create temporary table tmp_tool ( like tool including defaults ) on commit drop; alter table tmp_tool drop column id; $$; -- a content signature is a set of cryptographic checksums that we use to -- uniquely identify content, for the purpose of verifying if we already have -- some content or not during content injection create type content_signature as ( sha1 sha1, sha1_git sha1_git, sha256 sha256, blake2s256 blake2s256 ); -- check which entries of tmp_skipped_content are missing from skipped_content -- -- operates in bulk: 0. swh_mktemp(skipped_content), 1. COPY to tmp_skipped_content, -- 2. call this function create or replace function swh_skipped_content_missing() returns setof content_signature language plpgsql as $$ begin return query select sha1, sha1_git, sha256, blake2s256 from tmp_skipped_content t where not exists (select 1 from skipped_content s where s.sha1 is not distinct from t.sha1 and s.sha1_git is not distinct from t.sha1_git and s.sha256 is not distinct from t.sha256); return; end $$; -- Look up content based on one or several different checksums. Return all -- content information if the content is found; a NULL row otherwise. -- -- At least one checksum should be not NULL. If several are not NULL, they will -- be AND-ed together in the lookup query. -- -- Note: this function is meant to be used to look up individual contents -- (e.g., for the web app), for batch lookup of missing content (e.g., to be -- added) see swh_content_missing create or replace function swh_content_find( sha1 sha1 default NULL, sha1_git sha1_git default NULL, sha256 sha256 default NULL, blake2s256 blake2s256 default NULL ) returns content language plpgsql as $$ declare con content; filters text[] := array[] :: text[]; -- AND-clauses used to filter content q text; begin if sha1 is not null then filters := filters || format('sha1 = %L', sha1); end if; if sha1_git is not null then filters := filters || format('sha1_git = %L', sha1_git); end if; if sha256 is not null then filters := filters || format('sha256 = %L', sha256); end if; if blake2s256 is not null then filters := filters || format('blake2s256 = %L', blake2s256); end if; if cardinality(filters) = 0 then return null; else q = format('select * from content where %s', array_to_string(filters, ' and ')); execute q into con; return con; end if; end $$; -- add tmp_content entries to content, skipping duplicates -- -- operates in bulk: 0. swh_mktemp(content), 1. COPY to tmp_content, -- 2. call this function create or replace function swh_content_add() returns void language plpgsql as $$ begin insert into content (sha1, sha1_git, sha256, blake2s256, length, status, ctime) select distinct sha1, sha1_git, sha256, blake2s256, length, status, ctime from tmp_content; return; end $$; -- add tmp_skipped_content entries to skipped_content, skipping duplicates -- -- operates in bulk: 0. swh_mktemp(skipped_content), 1. COPY to tmp_skipped_content, -- 2. call this function create or replace function swh_skipped_content_add() returns void language plpgsql as $$ begin insert into skipped_content (sha1, sha1_git, sha256, blake2s256, length, status, reason, origin) select distinct sha1, sha1_git, sha256, blake2s256, length, status, reason, origin from tmp_skipped_content where (coalesce(sha1, ''), coalesce(sha1_git, ''), coalesce(sha256, '')) in ( select coalesce(sha1, ''), coalesce(sha1_git, ''), coalesce(sha256, '') from swh_skipped_content_missing() ); -- TODO XXX use postgres 9.5 "UPSERT" support here, when available. -- Specifically, using "INSERT .. ON CONFLICT IGNORE" we can avoid -- the extra swh_content_missing() query here. return; end $$; -- Update content entries from temporary table. -- (columns are potential new columns added to the schema, this cannot be empty) -- create or replace function swh_content_update(columns_update text[]) returns void language plpgsql as $$ declare query text; tmp_array text[]; begin if array_length(columns_update, 1) = 0 then raise exception 'Please, provide the list of column names to update.'; end if; tmp_array := array(select format('%1$s=t.%1$s', unnest) from unnest(columns_update)); query = format('update content set %s from tmp_content t where t.sha1 = content.sha1', array_to_string(tmp_array, ', ')); execute query; return; end $$; comment on function swh_content_update(text[]) IS 'Update existing content''s columns'; -- check which entries of tmp_directory are missing from directory -- -- operates in bulk: 0. swh_mktemp(directory), 1. COPY to tmp_directory, -- 2. call this function create or replace function swh_directory_missing() returns setof sha1_git language plpgsql as $$ begin return query select id from tmp_directory t where not exists ( select 1 from directory d where d.id = t.id); return; end $$; create type directory_entry_type as enum('file', 'dir', 'rev'); -- Add tmp_directory_entry_* entries to directory_entry_* and directory, -- skipping duplicates in directory_entry_*. This is a generic function that -- works on all kind of directory entries. -- -- operates in bulk: 0. swh_mktemp_dir_entry('directory_entry_*'), 1 COPY to -- tmp_directory_entry_*, 2. call this function -- -- Assumption: this function is used in the same transaction that inserts the -- context directory in table "directory". create or replace function swh_directory_entry_add(typ directory_entry_type) returns void language plpgsql as $$ begin execute format(' insert into directory_entry_%1$s (target, name, perms) select distinct t.target, t.name, t.perms from tmp_directory_entry_%1$s t where not exists ( select 1 from directory_entry_%1$s i where t.target = i.target and t.name = i.name and t.perms = i.perms) ', typ); execute format(' with new_entries as ( select t.dir_id, array_agg(i.id) as entries from tmp_directory_entry_%1$s t inner join directory_entry_%1$s i using (target, name, perms) group by t.dir_id ) update tmp_directory as d set %1$s_entries = new_entries.entries from new_entries where d.id = new_entries.dir_id ', typ); return; end $$; -- Insert the data from tmp_directory, tmp_directory_entry_file, -- tmp_directory_entry_dir, tmp_directory_entry_rev into their final -- tables. -- -- Prerequisites: -- directory ids in tmp_directory -- entries in tmp_directory_entry_{file,dir,rev} -- create or replace function swh_directory_add() returns void language plpgsql as $$ begin perform swh_directory_entry_add('file'); perform swh_directory_entry_add('dir'); perform swh_directory_entry_add('rev'); insert into directory select * from tmp_directory t where not exists ( select 1 from directory d where d.id = t.id); return; end $$; -- a directory listing entry with all the metadata -- -- can be used to list a directory, and retrieve all the data in one go. create type directory_entry as ( dir_id sha1_git, -- id of the parent directory type directory_entry_type, -- type of entry target sha1_git, -- id of target name unix_path, -- path name, relative to containing dir perms file_perms, -- unix-like permissions status content_status, -- visible or absent sha1 sha1, -- content if sha1 if type is not dir sha1_git sha1_git, -- content's sha1 git if type is not dir sha256 sha256, -- content's sha256 if type is not dir length bigint -- content length if type is not dir ); -- List a single level of directory walked_dir_id -- FIXME: order by name is not correct. For git, we need to order by -- lexicographic order but as if a trailing / is present in directory -- name create or replace function swh_directory_walk_one(walked_dir_id sha1_git) returns setof directory_entry language sql stable as $$ with dir as ( select id as dir_id, dir_entries, file_entries, rev_entries from directory where id = walked_dir_id), ls_d as (select dir_id, unnest(dir_entries) as entry_id from dir), ls_f as (select dir_id, unnest(file_entries) as entry_id from dir), ls_r as (select dir_id, unnest(rev_entries) as entry_id from dir) (select dir_id, 'dir'::directory_entry_type as type, e.target, e.name, e.perms, NULL::content_status, NULL::sha1, NULL::sha1_git, NULL::sha256, NULL::bigint from ls_d left join directory_entry_dir e on ls_d.entry_id = e.id) union (select dir_id, 'file'::directory_entry_type as type, e.target, e.name, e.perms, c.status, c.sha1, c.sha1_git, c.sha256, c.length from ls_f left join directory_entry_file e on ls_f.entry_id = e.id left join content c on e.target = c.sha1_git) union (select dir_id, 'rev'::directory_entry_type as type, e.target, e.name, e.perms, NULL::content_status, NULL::sha1, NULL::sha1_git, NULL::sha256, NULL::bigint from ls_r left join directory_entry_rev e on ls_r.entry_id = e.id) order by name; $$; -- List recursively the revision directory arborescence create or replace function swh_directory_walk(walked_dir_id sha1_git) returns setof directory_entry language sql stable as $$ with recursive entries as ( select dir_id, type, target, name, perms, status, sha1, sha1_git, sha256, length from swh_directory_walk_one(walked_dir_id) union all select dir_id, type, target, (dirname || '/' || name)::unix_path as name, perms, status, sha1, sha1_git, sha256, length from (select (swh_directory_walk_one(dirs.target)).*, dirs.name as dirname from (select target, name from entries where type = 'dir') as dirs) as with_parent ) select dir_id, type, target, name, perms, status, sha1, sha1_git, sha256, length from entries $$; create or replace function swh_revision_walk(revision_id sha1_git) returns setof directory_entry language sql stable as $$ select dir_id, type, target, name, perms, status, sha1, sha1_git, sha256, length from swh_directory_walk((select directory from revision where id=revision_id)) $$; COMMENT ON FUNCTION swh_revision_walk(sha1_git) IS 'Recursively list the revision targeted directory arborescence'; -- Find a directory entry by its path create or replace function swh_find_directory_entry_by_path( walked_dir_id sha1_git, dir_or_content_path bytea[]) returns directory_entry language plpgsql as $$ declare end_index integer; paths bytea default ''; path bytea; res bytea[]; r record; begin end_index := array_upper(dir_or_content_path, 1); res[1] := walked_dir_id; for i in 1..end_index loop path := dir_or_content_path[i]; -- concatenate path for patching the name in the result record (if we found it) if i = 1 then paths = path; else paths := paths || '/' || path; -- concatenate paths end if; if i <> end_index then select * from swh_directory_walk_one(res[i] :: sha1_git) where name=path and type = 'dir' limit 1 into r; else select * from swh_directory_walk_one(res[i] :: sha1_git) where name=path limit 1 into r; end if; -- find the path if r is null then return null; else -- store the next dir to lookup the next local path from res[i+1] := r.target; end if; end loop; -- at this moment, r is the result. Patch its 'name' with the full path before returning it. r.name := paths; return r; end $$; -- List all revision IDs starting from a given revision, going back in time -- -- TODO ordering: should be breadth-first right now (what do we want?) -- TODO ordering: ORDER BY parent_rank somewhere? create or replace function swh_revision_list(root_revisions bytea[], num_revs bigint default NULL) returns table (id sha1_git, parents bytea[]) language sql stable as $$ with recursive full_rev_list(id) as ( (select id from revision where id = ANY(root_revisions)) union (select h.parent_id from revision_history as h join full_rev_list on h.id = full_rev_list.id) ), rev_list as (select id from full_rev_list limit num_revs) select rev_list.id as id, array(select rh.parent_id::bytea from revision_history rh where rh.id = rev_list.id order by rh.parent_rank ) as parent from rev_list; $$; -- List all the children of a given revision create or replace function swh_revision_list_children(root_revisions bytea[], num_revs bigint default NULL) returns table (id sha1_git, parents bytea[]) language sql stable as $$ with recursive full_rev_list(id) as ( (select id from revision where id = ANY(root_revisions)) union (select h.id from revision_history as h join full_rev_list on h.parent_id = full_rev_list.id) ), rev_list as (select id from full_rev_list limit num_revs) select rev_list.id as id, array(select rh.parent_id::bytea from revision_history rh where rh.id = rev_list.id order by rh.parent_rank ) as parent from rev_list; $$; -- Detailed entry for a revision create type revision_entry as ( id sha1_git, date timestamptz, date_offset smallint, date_neg_utc_offset boolean, committer_date timestamptz, committer_date_offset smallint, committer_date_neg_utc_offset boolean, type revision_type, directory sha1_git, message bytea, author_id bigint, author_fullname bytea, author_name bytea, author_email bytea, committer_id bigint, committer_fullname bytea, committer_name bytea, committer_email bytea, metadata jsonb, synthetic boolean, parents bytea[], object_id bigint ); -- "git style" revision log. Similar to swh_revision_list(), but returning all -- information associated to each revision, and expanding authors/committers create or replace function swh_revision_log(root_revisions bytea[], num_revs bigint default NULL) returns setof revision_entry language sql stable as $$ select t.id, r.date, r.date_offset, r.date_neg_utc_offset, r.committer_date, r.committer_date_offset, r.committer_date_neg_utc_offset, r.type, r.directory, r.message, a.id, a.fullname, a.name, a.email, c.id, c.fullname, c.name, c.email, r.metadata, r.synthetic, t.parents, r.object_id from swh_revision_list(root_revisions, num_revs) as t left join revision r on t.id = r.id left join person a on a.id = r.author left join person c on c.id = r.committer; $$; -- Detailed entry for a release create type release_entry as ( id sha1_git, target sha1_git, target_type object_type, date timestamptz, date_offset smallint, date_neg_utc_offset boolean, name bytea, comment bytea, synthetic boolean, author_id bigint, author_fullname bytea, author_name bytea, author_email bytea, object_id bigint ); -- Create entries in person from tmp_revision create or replace function swh_person_add_from_revision() returns void language plpgsql as $$ begin with t as ( select author_fullname as fullname, author_name as name, author_email as email from tmp_revision union select committer_fullname as fullname, committer_name as name, committer_email as email from tmp_revision ) insert into person (fullname, name, email) select distinct on (fullname) fullname, name, email from t where not exists ( select 1 from person p where t.fullname = p.fullname ); return; end $$; -- Create entries in revision from tmp_revision create or replace function swh_revision_add() returns void language plpgsql as $$ begin perform swh_person_add_from_revision(); insert into revision (id, date, date_offset, date_neg_utc_offset, committer_date, committer_date_offset, committer_date_neg_utc_offset, type, directory, message, author, committer, metadata, synthetic) select t.id, t.date, t.date_offset, t.date_neg_utc_offset, t.committer_date, t.committer_date_offset, t.committer_date_neg_utc_offset, t.type, t.directory, t.message, a.id, c.id, t.metadata, t.synthetic from tmp_revision t left join person a on a.fullname = t.author_fullname left join person c on c.fullname = t.committer_fullname; return; end $$; -- Create entries in person from tmp_release create or replace function swh_person_add_from_release() returns void language plpgsql as $$ begin with t as ( select distinct author_fullname as fullname, author_name as name, author_email as email from tmp_release where author_fullname is not null ) insert into person (fullname, name, email) select distinct on (fullname) fullname, name, email from t where not exists ( select 1 from person p where t.fullname = p.fullname ); return; end $$; -- Create entries in release from tmp_release create or replace function swh_release_add() returns void language plpgsql as $$ begin perform swh_person_add_from_release(); insert into release (id, target, target_type, date, date_offset, date_neg_utc_offset, name, comment, author, synthetic) select t.id, t.target, t.target_type, t.date, t.date_offset, t.date_neg_utc_offset, t.name, t.comment, a.id, t.synthetic from tmp_release t left join person a on a.fullname = t.author_fullname; return; end $$; -- add a new origin_visit for origin origin_id at date. -- -- Returns the new visit id. -create or replace function swh_origin_visit_add(origin_id bigint, date timestamptz, type text) +create or replace function swh_origin_visit_add(origin_url text, date timestamptz, type text) returns bigint language sql as $$ - with last_known_visit as ( + with origin_id as ( + select id + from origin + where url = origin_url + ), last_known_visit as ( select coalesce(max(visit), 0) as visit from origin_visit - where origin = origin_id + where origin = (select id from origin_id) ) insert into origin_visit (origin, date, type, visit, status) - values (origin_id, date, type, (select visit from last_known_visit) + 1, 'ongoing') + values ((select id from origin_id), date, type, + (select visit from last_known_visit) + 1, 'ongoing') returning visit; $$; create or replace function swh_snapshot_add(snapshot_id sha1_git) returns void language plpgsql as $$ declare snapshot_object_id snapshot.object_id%type; begin select object_id from snapshot where id = snapshot_id into snapshot_object_id; if snapshot_object_id is null then insert into snapshot (id) values (snapshot_id) returning object_id into snapshot_object_id; insert into snapshot_branch (name, target_type, target) select name, target_type, target from tmp_snapshot_branch tmp where not exists ( select 1 from snapshot_branch sb where sb.name = tmp.name and sb.target = tmp.target and sb.target_type = tmp.target_type ) on conflict do nothing; insert into snapshot_branches (snapshot_id, branch_id) select snapshot_object_id, sb.object_id as branch_id from tmp_snapshot_branch tmp join snapshot_branch sb using (name, target, target_type) where tmp.target is not null and tmp.target_type is not null union select snapshot_object_id, sb.object_id as branch_id from tmp_snapshot_branch tmp join snapshot_branch sb using (name) where tmp.target is null and tmp.target_type is null and sb.target is null and sb.target_type is null; end if; truncate table tmp_snapshot_branch; end; $$; create type snapshot_result as ( snapshot_id sha1_git, name bytea, target bytea, target_type snapshot_target ); create or replace function swh_snapshot_get_by_id(id sha1_git, branches_from bytea default '', branches_count bigint default null, target_types snapshot_target[] default NULL) returns setof snapshot_result language sql stable as $$ select swh_snapshot_get_by_id.id as snapshot_id, name, target, target_type from snapshot_branches inner join snapshot_branch on snapshot_branches.branch_id = snapshot_branch.object_id where snapshot_id = (select object_id from snapshot where snapshot.id = swh_snapshot_get_by_id.id) and (target_types is null or target_type = any(target_types)) and name >= branches_from order by name limit branches_count $$; create type snapshot_size as ( target_type snapshot_target, count bigint ); create or replace function swh_snapshot_count_branches(id sha1_git) returns setof snapshot_size language sql stable as $$ SELECT target_type, count(name) from swh_snapshot_get_by_id(swh_snapshot_count_branches.id) group by target_type; $$; -- Absolute path: directory reference + complete path relative to it create type content_dir as ( directory sha1_git, path unix_path ); -- Find the containing directory of a given content, specified by sha1 -- (note: *not* sha1_git). -- -- Return a pair (dir_it, path) where path is a UNIX path that, from the -- directory root, reach down to a file with the desired content. Return NULL -- if no match is found. -- -- In case of multiple paths (i.e., pretty much always), an arbitrary one is -- chosen. create or replace function swh_content_find_directory(content_id sha1) returns content_dir language sql stable as $$ with recursive path as ( -- Recursively build a path from the requested content to a root -- directory. Each iteration returns a pair (dir_id, filename) where -- filename is relative to dir_id. Stops when no parent directory can -- be found. (select dir.id as dir_id, dir_entry_f.name as name, 0 as depth from directory_entry_file as dir_entry_f join content on content.sha1_git = dir_entry_f.target join directory as dir on dir.file_entries @> array[dir_entry_f.id] where content.sha1 = content_id limit 1) union all (select dir.id as dir_id, (dir_entry_d.name || '/' || path.name)::unix_path as name, path.depth + 1 from path join directory_entry_dir as dir_entry_d on dir_entry_d.target = path.dir_id join directory as dir on dir.dir_entries @> array[dir_entry_d.id] limit 1) ) select dir_id, name from path order by depth desc limit 1; $$; --- Find the visit of origin id closest to date visit_date +-- Find the visit of origin closest to date visit_date -- Breaks ties by selecting the largest visit id -create or replace function swh_visit_find_by_date(origin bigint, visit_date timestamptz default NOW()) - returns origin_visit - language sql +create or replace function swh_visit_find_by_date(origin_url text, visit_date timestamptz default NOW()) + returns setof origin_visit + language plpgsql stable as $$ +declare + origin_id bigint; +begin + select id into origin_id from origin where url=origin_url; + return query with closest_two_visits as (( select ov, (date - visit_date), visit as interval from origin_visit ov - where ov.origin = origin + where ov.origin = origin_id and ov.date >= visit_date order by ov.date asc, ov.visit desc limit 1 ) union ( select ov, (visit_date - date), visit as interval from origin_visit ov - where ov.origin = origin + where ov.origin = origin_id and ov.date < visit_date order by ov.date desc, ov.visit desc limit 1 - )) select (ov).* from closest_two_visits order by interval, visit limit 1 -$$; - --- Find the visit of origin id closest to date visit_date -create or replace function swh_visit_get(origin bigint) - returns origin_visit - language sql - stable -as $$ - select * - from origin_visit - where origin=origin - order by date desc + )) select (ov).* from closest_two_visits order by interval, visit limit 1; +end $$; -- Object listing by object_id create or replace function swh_content_list_by_object_id( min_excl bigint, max_incl bigint ) returns setof content language sql stable as $$ select * from content where object_id > min_excl and object_id <= max_incl order by object_id; $$; create or replace function swh_revision_list_by_object_id( min_excl bigint, max_incl bigint ) returns setof revision_entry language sql stable as $$ with revs as ( select * from revision where object_id > min_excl and object_id <= max_incl ) select r.id, r.date, r.date_offset, r.date_neg_utc_offset, r.committer_date, r.committer_date_offset, r.committer_date_neg_utc_offset, r.type, r.directory, r.message, a.id, a.fullname, a.name, a.email, c.id, c.fullname, c.name, c.email, r.metadata, r.synthetic, array(select rh.parent_id::bytea from revision_history rh where rh.id = r.id order by rh.parent_rank) as parents, r.object_id from revs r left join person a on a.id = r.author left join person c on c.id = r.committer order by r.object_id; $$; create or replace function swh_release_list_by_object_id( min_excl bigint, max_incl bigint ) returns setof release_entry language sql stable as $$ with rels as ( select * from release where object_id > min_excl and object_id <= max_incl ) select r.id, r.target, r.target_type, r.date, r.date_offset, r.date_neg_utc_offset, r.name, r.comment, r.synthetic, p.id as author_id, p.fullname as author_fullname, p.name as author_name, p.email as author_email, r.object_id from rels r left join person p on p.id = r.author order by r.object_id; $$; -- end revision_metadata functions -- origin_metadata functions create type origin_metadata_signature as ( id bigint, - origin_id bigint, + origin_url text, discovery_date timestamptz, tool_id bigint, metadata jsonb, provider_id integer, provider_name text, provider_type text, provider_url text ); create or replace function swh_origin_metadata_get_by_origin( - origin integer) + origin text) returns setof origin_metadata_signature language sql stable as $$ - select om.id as id, origin_id, discovery_date, tool_id, om.metadata, + select om.id as id, o.url as origin_url, discovery_date, tool_id, om.metadata, mp.id as provider_id, provider_name, provider_type, provider_url from origin_metadata as om inner join metadata_provider mp on om.provider_id = mp.id - where om.origin_id = origin + inner join origin o on om.origin_id = o.id + where o.url = origin order by discovery_date desc; $$; create or replace function swh_origin_metadata_get_by_provider_type( - origin integer, - type text) + origin_url text, + provider_type text) returns setof origin_metadata_signature language sql stable as $$ - select om.id as id, origin_id, discovery_date, tool_id, om.metadata, + select om.id as id, o.url as origin_url, discovery_date, tool_id, om.metadata, mp.id as provider_id, provider_name, provider_type, provider_url from origin_metadata as om inner join metadata_provider mp on om.provider_id = mp.id - where om.origin_id = origin - and mp.provider_type = type + inner join origin o on om.origin_id = o.id + where o.url = origin_url + and mp.provider_type = provider_type order by discovery_date desc; $$; -- end origin_metadata functions -- add tmp_tool entries to tool, -- skipping duplicates if any. -- -- operates in bulk: 0. create temporary tmp_tool, 1. COPY to -- it, 2. call this function to insert and filtering out duplicates create or replace function swh_tool_add() returns setof tool language plpgsql as $$ begin insert into tool(name, version, configuration) select name, version, configuration from tmp_tool tmp on conflict(name, version, configuration) do nothing; return query select id, name, version, configuration from tmp_tool join tool using(name, version, configuration); return; end $$; -- simple counter mapping a textual label to an integer value create type counter as ( label text, value bigint ); -- return statistics about the number of tuples in various SWH tables -- -- Note: the returned values are based on postgres internal statistics -- (pg_class table), which are only updated daily (by autovacuum) or so create or replace function swh_stat_counters() returns setof counter language sql stable as $$ select object_type as label, value as value from object_counts where object_type in ( 'content', 'directory', 'directory_entry_dir', 'directory_entry_file', 'directory_entry_rev', 'origin', 'origin_visit', 'person', 'release', 'revision', 'revision_history', 'skipped_content', 'snapshot' ); $$; create or replace function swh_update_counter(object_type text) returns void language plpgsql as $$ begin execute format(' insert into object_counts (value, last_update, object_type) values ((select count(*) from %1$I), NOW(), %1$L) on conflict (object_type) do update set value = excluded.value, last_update = excluded.last_update', object_type); return; end; $$; create or replace function swh_update_counter_bucketed() returns void language plpgsql as $$ declare query text; line_to_update int; new_value bigint; begin select object_counts_bucketed.line, format( 'select count(%I) from %I where %s', coalesce(identifier, '*'), object_type, coalesce( concat_ws( ' and ', case when bucket_start is not null then format('%I >= %L', identifier, bucket_start) -- lower bound condition, inclusive end, case when bucket_end is not null then format('%I < %L', identifier, bucket_end) -- upper bound condition, exclusive end ), 'true' ) ) from object_counts_bucketed order by coalesce(last_update, now() - '1 month'::interval) asc limit 1 into line_to_update, query; execute query into new_value; update object_counts_bucketed set value = new_value, last_update = now() where object_counts_bucketed.line = line_to_update; END $$; create or replace function swh_update_counters_from_buckets() returns trigger language plpgsql as $$ begin with to_update as ( select object_type, sum(value) as value, max(last_update) as last_update from object_counts_bucketed ob1 where not exists ( select 1 from object_counts_bucketed ob2 where ob1.object_type = ob2.object_type and value is null ) group by object_type ) update object_counts set value = to_update.value, last_update = to_update.last_update from to_update where object_counts.object_type = to_update.object_type and object_counts.value != to_update.value; return null; end $$; create trigger update_counts_from_bucketed after insert or update on object_counts_bucketed for each row when (NEW.line % 256 = 0) execute procedure swh_update_counters_from_buckets(); diff --git a/swh/storage/storage.py b/swh/storage/storage.py index 7abc58d..e544b7f 100644 --- a/swh/storage/storage.py +++ b/swh/storage/storage.py @@ -1,1899 +1,1830 @@ # 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 from collections import defaultdict import copy from concurrent.futures import ThreadPoolExecutor from contextlib import contextmanager import datetime import itertools import json 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 try: from swh.journal.writer import get_journal_writer except ImportError: get_journal_writer = None # type: ignore # mypy limitation, see https://github.com/python/mypy/issues/1153 # 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, journal_writer=None): """ 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) if journal_writer: if get_journal_writer is None: raise EnvironmentError( 'You need the swh.journal package to use the ' 'journal_writer feature') self.journal_writer = get_journal_writer(**journal_writer) else: self.journal_writer = None def get_db(self): if self._db: return self._db else: return Db.from_pool(self._pool) def put_db(self, db): if db is not self._db: db.put_conn() @contextmanager def db(self): db = None try: db = self.get_db() yield db finally: if db: self.put_db(db) @db_transaction() def check_config(self, *, check_write, db, cur): """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 if check_write: check = 'INSERT' else: check = 'SELECT' cur.execute( "select has_table_privilege(current_user, 'content', %s)", (check,) ) return cur.fetchone()[0] def _content_unique_key(self, hash, db): """Given a hash (tuple or dict), return a unique key from the aggregation of keys. """ keys = db.content_hash_keys if isinstance(hash, tuple): return hash return tuple([hash[k] for k in keys]) @staticmethod def _normalize_content(d): d = d.copy() if 'status' not in d: d['status'] = 'visible' if 'length' not in d: d['length'] = -1 return d @staticmethod def _validate_content(d): """Sanity checks on status / reason / length, that postgresql doesn't enforce.""" if d['status'] not in ('visible', 'absent', 'hidden'): raise ValueError('Invalid content status: {}'.format(d['status'])) if d['status'] != 'absent' and d.get('reason') is not None: raise ValueError( 'Must not provide a reason if content is not absent.') if d['length'] < -1: raise ValueError('Content length must be positive or -1.') def _filter_new_content(self, content, db, cur): """Sort contents into buckets 'with data' and 'without data', and filter out those already in the database.""" content_by_status = defaultdict(list) for d in content: content_by_status[d['status']].append(d) content_with_data = content_by_status['visible'] \ + content_by_status['hidden'] content_without_data = content_by_status['absent'] missing_content = set(self.content_missing(content_with_data, db=db, cur=cur)) missing_skipped = set(self._content_unique_key(hashes, db) for hashes in self.skipped_content_missing( content_without_data, db=db, cur=cur)) content_with_data = [ cont for cont in content_with_data if cont['sha1'] in missing_content] content_without_data = [ cont for cont in content_without_data if self._content_unique_key(cont, db) in missing_skipped] summary = { 'content:add': len(missing_content), 'skipped_content:add': len(missing_skipped), } return (content_with_data, content_without_data, summary) def _content_add_metadata(self, db, cur, content_with_data, content_without_data): """Add content to the postgresql database but not the object storage. """ if content_with_data: # create temporary table for metadata injection db.mktemp('content', cur) db.copy_to(content_with_data, 'tmp_content', db.content_add_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': constraint_to_hash_name = { 'content_pkey': 'sha1', 'content_sha1_git_idx': 'sha1_git', 'content_sha256_idx': 'sha256', } colliding_hash_name = constraint_to_hash_name \ .get(e.diag.constraint_name) raise HashCollision(colliding_hash_name) from None else: raise if content_without_data: content_without_data = \ [cont.copy() for cont in content_without_data] - origins = db.origin_get_by_url( + origin_ids = db.origin_id_get_by_url( [cont.get('origin') for cont in content_without_data], cur=cur) - for (cont, origin) in zip(content_without_data, origins): - origin = dict(zip(db.origin_cols, origin)) + for (cont, origin_id) in zip(content_without_data, origin_ids): if 'origin' in cont: - cont['origin'] = origin['id'] + cont['origin'] = origin_id db.mktemp('skipped_content', cur) db.copy_to(content_without_data, 'tmp_skipped_content', db.skipped_content_keys, cur) # move metadata in place db.skipped_content_add_from_temp(cur) @db_transaction() def content_add(self, content, db, cur): """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: contents (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 Raises: In case of errors, nothing is stored in the db (in the objstorage, it could though). The following exceptions can occur: - HashCollision in case of collision - Any other exceptions raise by the db Returns: Summary dict with the following key and associated values: content:add: New contents added content:add:bytes: Sum of the contents' length data skipped_content:add: New skipped contents (no data) added """ content = [dict(c.items()) for c in content] # semi-shallow copy now = datetime.datetime.now(tz=datetime.timezone.utc) for item in content: item['ctime'] = now content = [self._normalize_content(c) for c in content] for c in content: self._validate_content(c) (content_with_data, content_without_data, summary) = \ self._filter_new_content(content, db, cur) if self.journal_writer: for item in content_with_data: if 'data' in item: item = item.copy() del item['data'] self.journal_writer.write_addition('content', item) for item in content_without_data: self.journal_writer.write_addition('content', item) def add_to_objstorage(): """Add to objstorage the new missing_content Returns: Sum of all the content's data length pushed to the objstorage. Content present twice is only sent once. """ content_bytes_added = 0 data = {} for cont in content_with_data: if cont['sha1'] not in data: data[cont['sha1']] = cont['data'] content_bytes_added += max(0, cont['length']) # FIXME: Since we do the filtering anyway now, we might as # well make the objstorage's add_batch call return what we # want here (real bytes added)... that'd simplify this... self.objstorage.add_batch(data) return content_bytes_added with ThreadPoolExecutor(max_workers=1) as executor: added_to_objstorage = executor.submit(add_to_objstorage) self._content_add_metadata( db, cur, content_with_data, content_without_data) # Wait for objstorage addition before returning from the # transaction, bubbling up any exception content_bytes_added = added_to_objstorage.result() summary['content:add:bytes'] = content_bytes_added return summary @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. if self.journal_writer: raise NotImplementedError( 'content_update is not yet support with a journal_writer.') 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) @db_transaction() def content_add_metadata(self, content, db, cur): """Add content metadata to the storage (like `content_add`, but without inserting to the objstorage). Args: content (iterable): iterable of dictionaries representing individual pieces of content to add. Each dictionary has the following keys: - 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 - ctime (datetime): time of insertion in the archive Returns: Summary dict with the following key and associated values: content:add: New contents added skipped_content:add: New skipped contents (no data) added """ content = [self._normalize_content(c) for c in content] for c in content: self._validate_content(c) (content_with_data, content_without_data, summary) = \ self._filter_new_content(content, db, cur) if self.journal_writer: for item in itertools.chain(content_with_data, content_without_data): assert 'data' not in content self.journal_writer.write_addition('content', item) self._content_add_metadata( db, cur, content_with_data, content_without_data) return summary 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, contents, 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 """ for content in db.skipped_content_missing(contents, cur): yield dict(zip(db.content_hash_keys, content)) @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') contents = db.content_find(sha1=content.get('sha1'), sha1_git=content.get('sha1_git'), sha256=content.get('sha256'), blake2s256=content.get('blake2s256'), cur=cur) return [dict(zip(db.content_find_cols, content)) for content in contents] @db_transaction() def directory_add(self, directories, db, cur): """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 Returns: Summary dict of keys with associated count as values: directory:add: Number of directories actually added """ summary = {'directory:add': 0} 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 if entry['type'] not in ('file', 'dir', 'rev'): raise ValueError( 'Entry type must be file, dir, or rev; not %s' % entry['type']) dir_entries[entry['type']][dir_id].append(entry) dirs_missing = set(self.directory_missing(dirs, db=db, cur=cur)) if not dirs_missing: return summary if self.journal_writer: self.journal_writer.write_additions( 'directory', (dir_ for dir_ in directories if dir_['id'] in dirs_missing)) # 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) summary['directory:add'] = len(dirs_missing) return summary @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)) @db_transaction() def revision_add(self, revisions, db, cur): """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`. Returns: Summary dict of keys with associated count as values revision:add: New objects actually stored in db """ summary = {'revision:add': 0} revisions_missing = set(self.revision_missing( set(revision['id'] for revision in revisions), db=db, cur=cur)) if not revisions_missing: return summary db.mktemp_revision(cur) revisions_filtered = [ revision for revision in revisions if revision['id'] in revisions_missing] if self.journal_writer: self.journal_writer.write_additions('revision', revisions_filtered) revisions_filtered = map(converters.revision_to_db, revisions_filtered) 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) return {'revision:add': len(revisions_missing)} @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=1000) 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) @db_transaction() def release_add(self, releases, db, cur): """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`. Returns: Summary dict of keys with associated count as values release:add: New objects contents actually stored in db """ summary = {'release:add': 0} release_ids = set(release['id'] for release in releases) releases_missing = set(self.release_missing(release_ids, db=db, cur=cur)) if not releases_missing: return summary db.mktemp_release(cur) releases_missing = list(releases_missing) releases_filtered = [ release for release in releases if release['id'] in releases_missing ] if self.journal_writer: self.journal_writer.write_additions('release', releases_filtered) releases_filtered = map(converters.release_to_db, releases_filtered) db.copy_to(releases_filtered, 'tmp_release', db.release_add_cols, cur) db.release_add_from_temp(cur) return {'release:add': len(releases_missing)} @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, snapshots, db=None, cur=None): """Add snapshots to the storage. Args: snapshot ([dict]): the snapshots to add, 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. Returns: Summary dict of keys with associated count as values snapshot:add: Count of object actually stored in db """ created_temp_table = False count = 0 for snapshot in snapshots: if not db.snapshot_exists(snapshot['id'], cur): if not created_temp_table: db.mktemp_snapshot_branch(cur) created_temp_table = True 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 self.journal_writer: self.journal_writer.write_addition('snapshot', snapshot) db.snapshot_add(snapshot['id'], cur) count += 1 return {'snapshot:add': count} @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=4000) 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 (Union[str,int]): the origin's URL or identifier + origin (str): the origin's URL 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. """ if isinstance(origin, int): origin = self.origin_get({'id': origin}, db=db, cur=cur) if not origin: return origin = origin['url'] origin_visit = self.origin_visit_get_latest( origin, allowed_statuses=allowed_statuses, require_snapshot=True, db=db, cur=cur) if origin_visit and origin_visit['snapshot']: snapshot = self.snapshot_get( origin_visit['snapshot'], db=db, cur=cur) if not snapshot: raise ValueError( 'last origin visit references an unknown snapshot') return snapshot @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, type, db=None, cur=None): """Add an origin_visit for the origin at ts with status 'ongoing'. Args: - origin (Union[int,str]): visited origin's identifier or URL + origin (str): visited origin's identifier or URL date (Union[str,datetime]): timestamp of such visit type (str): the type of loader used for the visit (hg, git, ...) Returns: dict: dictionary with keys origin and visit where: - origin: origin identifier - visit: the visit identifier for the new visit occurrence """ - if isinstance(origin, str): - origin = self.origin_get({'url': origin}, db=db, cur=cur) - origin_id = origin['id'] - else: - origin = self.origin_get({'id': origin}, db=db, cur=cur) - origin_id = origin['id'] + origin_url = origin + origin = self.origin_get({'url': origin_url}, db=db, cur=cur) if isinstance(date, str): # FIXME: Converge on iso8601 at some point date = dateutil.parser.parse(date) - visit_id = db.origin_visit_add(origin_id, date, type, cur) + visit_id = db.origin_visit_add(origin_url, date, type, cur) if self.journal_writer: # We can write to the journal only after inserting to the # DB, because we want the id of the visit - del origin['id'] self.journal_writer.write_addition('origin_visit', { 'origin': origin, 'date': date, 'type': type, 'visit': visit_id, 'status': 'ongoing', 'metadata': None, 'snapshot': None}) return { - 'origin': origin_id, + 'origin': origin_url, 'visit': visit_id, } @db_transaction() def origin_visit_update(self, origin, visit_id, status=None, metadata=None, snapshot=None, db=None, cur=None): """Update an origin_visit's status. Args: - origin (Union[int,str]): visited origin's identifier or URL + origin (str): visited origin's URL visit_id: Visit's id status: Visit's new status metadata: Data associated to the visit snapshot (sha1_git): identifier of the snapshot to add to the visit Returns: None """ - if isinstance(origin, str): - origin_id = self.origin_get({'url': origin}, db=db, cur=cur)['id'] - else: - origin_id = origin - - visit = db.origin_visit_get(origin_id, visit_id, cur=cur) + origin_url = origin + visit = db.origin_visit_get(origin_url, visit_id, cur=cur) if not visit: raise ValueError('Invalid visit_id for this origin.') visit = dict(zip(db.origin_visit_get_cols, visit)) updates = {} if status and status != visit['status']: updates['status'] = status if metadata and metadata != visit['metadata']: updates['metadata'] = metadata if snapshot and snapshot != visit['snapshot']: updates['snapshot'] = snapshot if updates: if self.journal_writer: origin = self.origin_get( - [{'id': origin_id}], db=db, cur=cur)[0] - del origin['id'] + [{'url': origin_url}], db=db, cur=cur)[0] self.journal_writer.write_update('origin_visit', { **visit, **updates, 'origin': origin}) - db.origin_visit_update(origin_id, visit_id, updates, cur) + db.origin_visit_update(origin_url, visit_id, updates, cur) @db_transaction() def origin_visit_upsert(self, visits, db=None, cur=None): """Add a origin_visits with a specific id and with all its data. If there is already an origin_visit with the same `(origin_id, visit_id)`, overwrites it. Args: visits: iterable of dicts with keys: origin: dict with keys either `id` or `url` visit: origin visit id date: timestamp of such visit status: Visit's new status metadata: Data associated to the visit snapshot (sha1_git): identifier of the snapshot to add to the visit """ visits = copy.deepcopy(visits) for visit in visits: if isinstance(visit['date'], str): visit['date'] = dateutil.parser.parse(visit['date']) visit['origin'] = \ self.origin_get([visit['origin']], db=db, cur=cur)[0] if self.journal_writer: for visit in visits: visit = copy.deepcopy(visit) if visit.get('type') is None: visit['type'] = visit['origin']['type'] - del visit['origin']['id'] self.journal_writer.write_addition('origin_visit', visit) for visit in visits: - visit['origin'] = visit['origin']['id'] + visit['origin'] = visit['origin']['url'] # TODO: upsert them all in a single query db.origin_visit_upsert(**visit, cur=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 (Union[int,str]): The occurrence's origin (identifier/URL). + origin (str): The visited origin 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. """ - if isinstance(origin, str): - origin = self.origin_get([{'url': origin}], db=db, cur=cur)[0] - if not origin: - return - origin = origin['id'] 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_find_by_date(self, origin, visit_date, db=None, cur=None): """Retrieves the origin visit whose date is closest to the provided timestamp. In case of a tie, the visit with largest id is selected. Args: origin (str): The occurrence's origin (URL). target (datetime): target timestamp Returns: A visit. """ - origin = self.origin_get([{'url': origin}], db=db, cur=cur)[0] - if not origin: - return - origin = origin['id'] line = db.origin_visit_find_by_date(origin, visit_date, cur=cur) if line: return dict(zip(db.origin_visit_get_cols, line)) @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 """ - if isinstance(origin, str): - origin = self.origin_get({'url': origin}, db=db, cur=cur) - if not origin: - return - origin = origin['id'] 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=4000) def origin_visit_get_latest( self, origin, allowed_statuses=None, require_snapshot=False, db=None, cur=None): """Get the latest origin visit for the given origin, optionally looking only for those with one of the given allowed_statuses or for those with a known snapshot. Args: origin (str): the origin's URL allowed_statuses (list of str): list of visit statuses considered to find the latest visit. For instance, ``allowed_statuses=['full']`` will only consider visits that have successfully run to completion. require_snapshot (bool): If True, only a visit with a snapshot will be returned. Returns: dict: a dict with the following keys: origin: the URL of the origin visit: origin visit id type: type of loader used for the visit date: timestamp of such visit status: Visit's new status metadata: Data associated to the visit snapshot (Optional[sha1_git]): identifier of the snapshot associated to the visit """ - origin = self.origin_get({'url': origin}, db=db, cur=cur) - if not origin: - return - origin = origin['id'] - origin_visit = db.origin_visit_get_latest( origin, allowed_statuses=allowed_statuses, require_snapshot=require_snapshot, cur=cur) if origin_visit: return dict(zip(db.origin_visit_get_cols, origin_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', '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). If the url is given and the type is omitted, one of the origins with that url is returned. Args: origin: a list of dictionaries representing the individual origins to find. - These dicts have either the key url: + These dicts have the key url: - 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 - url: origin's url Raises: ValueError: if the url or the id don't exist. """ 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_urls = [origin.get('url') for origin in origins] - if any(origin_ids): - # Lookup per ID - if all(origin_ids): - results = db.origin_get_by_id(origin_ids, cur) - else: - raise ValueError( - 'Either all origins or none at all should have an "id".') - elif any(origin_urls): - # Lookup per type + URL - if all(origin_urls): - results = db.origin_get_by_url(origin_urls, cur) - else: - raise ValueError( - 'Either all origins or none at all should have ' - 'an "url" key.') - else: # unsupported lookup - raise ValueError('Origin must have either id or url.') + origin_urls = [origin['url'] for origin in origins] + results = db.origin_get_by_url(origin_urls, cur) - results = [dict(zip(self.origin_keys, result)) + results = [dict(zip(db.origin_cols, result)) for result in results] if return_single: assert len(results) == 1 - if results[0]['id'] is not None: + if results[0]['url'] is not None: return results[0] else: return None else: - return [None if res['id'] is None else res for res in results] + return [None if res['url'] is None else res for res in results] @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)) + yield dict(zip(db.origin_get_range_cols, origin)) @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)) + yield dict(zip(db.origin_cols, 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() 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 """ origins = copy.deepcopy(origins) for origin in origins: - origin['id'] = self.origin_add_one(origin, db=db, cur=cur) + 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_by_url( - [origin['url']], cur))[0][0] - if origin_id: - return origin_id + origin_row = list(db.origin_get_by_url([origin['url']], cur))[0] + origin_url = dict(zip(db.origin_cols, origin_row))['url'] + if origin_url: + return origin_url if self.journal_writer: self.journal_writer.write_addition('origin', origin) return db.origin_add(origin['url'], 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, + def origin_metadata_add(self, origin_url, 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 + origin_url (str): the origin url 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(origin_id, str): - origin = self.origin_get({'url': origin_id}, db=db, cur=cur) - if not origin: - return - origin_id = origin['id'] - if isinstance(ts, str): ts = dateutil.parser.parse(ts) - return db.origin_metadata_add(origin_id, ts, provider, tool, - metadata, cur) + db.origin_metadata_add(origin_url, ts, provider, tool, + metadata, cur) @db_transaction_generator(statement_timeout=500) - def origin_metadata_get_by(self, origin_id, provider_type=None, db=None, + def origin_metadata_get_by(self, origin_url, 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 + origin_url (str): the origin's URL 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) """ - if isinstance(origin_id, str): - origin = self.origin_get({'url': origin_id}, db=db, cur=cur) - if not origin: - return - origin_id = origin['id'] - - for line in db.origin_metadata_get_by(origin_id, provider_type, cur): + for line in db.origin_metadata_get_by(origin_url, provider_type, cur): yield dict(zip(db.origin_metadata_get_cols, line)) @db_transaction() 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 Returns: :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) return [dict(zip(db.tool_cols, line)) for line in tools] @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_in_memory.py b/swh/storage/tests/test_in_memory.py index 37f9842..0fd7c94 100644 --- a/swh/storage/tests/test_in_memory.py +++ b/swh/storage/tests/test_in_memory.py @@ -1,33 +1,28 @@ # Copyright (C) 2018 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import pytest from swh.storage import get_storage from swh.storage.tests.test_storage import ( # noqa TestStorage, TestStorageGeneratedData) -from swh.storage.in_memory import ENABLE_ORIGIN_IDS - - -TestStorage._test_origin_ids = ENABLE_ORIGIN_IDS -TestStorageGeneratedData._test_origin_ids = ENABLE_ORIGIN_IDS # tests are executed using imported classes (TestStorage and # TestStorageGeneratedData) using overloaded swh_storage fixture # below @pytest.fixture def swh_storage(): storage_config = { 'cls': 'memory', 'args': { 'journal_writer': { 'cls': 'memory', }, }, } storage = get_storage(**storage_config) return storage diff --git a/swh/storage/tests/test_storage.py b/swh/storage/tests/test_storage.py index 0ad2ecf..8831136 100644 --- a/swh/storage/tests/test_storage.py +++ b/swh/storage/tests/test_storage.py @@ -1,3511 +1,3424 @@ # 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 copy from contextlib import contextmanager import datetime import itertools import queue import threading from collections import defaultdict from unittest.mock import Mock import psycopg2 import pytest from hypothesis import given, strategies, settings, HealthCheck from typing import ClassVar, Optional from swh.model import from_disk, identifiers from swh.model.hashutil import hash_to_bytes from swh.model.hypothesis_strategies import objects from swh.storage import HashCollision from .storage_data import data @contextmanager def db_transaction(storage): with storage.db() as db: with db.transaction() as cur: yield db, cur 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 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 cmpdir(directory): return (directory['type'], directory['dir_id']) def short_revision(revision): return [revision['id'], revision['parents']] class TestStorage: """Main 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. """ maxDiff = None # type: ClassVar[Optional[int]] - _test_origin_ids = True def test_check_config(self, swh_storage): assert swh_storage.check_config(check_write=True) assert swh_storage.check_config(check_write=False) def test_content_add(self, swh_storage): cont = data.cont insertion_start_time = datetime.datetime.now(tz=datetime.timezone.utc) actual_result = swh_storage.content_add([cont]) insertion_end_time = datetime.datetime.now(tz=datetime.timezone.utc) assert actual_result == { 'content:add': 1, 'content:add:bytes': cont['length'], 'skipped_content:add': 0 } assert list(swh_storage.content_get([cont['sha1']])) == \ [{'sha1': cont['sha1'], 'data': cont['data']}] expected_cont = data.cont del expected_cont['data'] journal_objects = list(swh_storage.journal_writer.objects) for (obj_type, obj) in journal_objects: assert insertion_start_time <= obj['ctime'] assert obj['ctime'] <= insertion_end_time del obj['ctime'] assert journal_objects == [('content', expected_cont)] def test_content_add_validation(self, swh_storage): cont = data.cont with pytest.raises(ValueError, match='status'): swh_storage.content_add([{**cont, 'status': 'foobar'}]) with pytest.raises(ValueError, match="(?i)length"): swh_storage.content_add([{**cont, 'length': -2}]) with pytest.raises((ValueError, psycopg2.IntegrityError), match='reason') as cm: swh_storage.content_add([{**cont, 'status': 'absent'}]) if type(cm.value) == psycopg2.IntegrityError: assert cm.exception.pgcode == \ psycopg2.errorcodes.NOT_NULL_VIOLATION with pytest.raises( ValueError, match="^Must not provide a reason if content is not absent.$"): swh_storage.content_add([{**cont, 'reason': 'foobar'}]) def test_content_get_missing(self, swh_storage): cont = data.cont swh_storage.content_add([cont]) # Query a single missing content results = list(swh_storage.content_get( [data.cont2['sha1']])) assert results == [None] # Check content_get does not abort after finding a missing content results = list(swh_storage.content_get( [data.cont['sha1'], data.cont2['sha1']])) assert results == [{'sha1': cont['sha1'], 'data': cont['data']}, None] # Check content_get does not discard found countent when it finds # a missing content. results = list(swh_storage.content_get( [data.cont2['sha1'], data.cont['sha1']])) assert results == [None, {'sha1': cont['sha1'], 'data': cont['data']}] def test_content_add_same_input(self, swh_storage): cont = data.cont actual_result = swh_storage.content_add([cont, cont]) assert actual_result == { 'content:add': 1, 'content:add:bytes': cont['length'], 'skipped_content:add': 0 } def test_content_add_different_input(self, swh_storage): cont = data.cont cont2 = data.cont2 actual_result = swh_storage.content_add([cont, cont2]) assert actual_result == { 'content:add': 2, 'content:add:bytes': cont['length'] + cont2['length'], 'skipped_content:add': 0 } def test_content_add_twice(self, swh_storage): actual_result = swh_storage.content_add([data.cont]) assert actual_result == { 'content:add': 1, 'content:add:bytes': data.cont['length'], 'skipped_content:add': 0 } assert len(swh_storage.journal_writer.objects) == 1 actual_result = swh_storage.content_add([data.cont, data.cont2]) assert actual_result == { 'content:add': 1, 'content:add:bytes': data.cont2['length'], 'skipped_content:add': 0 } assert len(swh_storage.journal_writer.objects) == 2 assert len(swh_storage.content_find(data.cont)) == 1 assert len(swh_storage.content_find(data.cont2)) == 1 def test_content_add_collision(self, swh_storage): cont1 = data.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 pytest.raises(HashCollision) as cm: swh_storage.content_add([cont1, cont1b]) assert cm.value.args[0] in ['sha1', 'sha1_git', 'blake2s256'] def test_content_add_metadata(self, swh_storage): cont = data.cont del cont['data'] cont['ctime'] = datetime.datetime.now() actual_result = swh_storage.content_add_metadata([cont]) assert actual_result == { 'content:add': 1, 'skipped_content:add': 0 } expected_cont = cont.copy() del expected_cont['ctime'] assert list(swh_storage.content_get_metadata([cont['sha1']])) == \ [expected_cont] assert list(swh_storage.journal_writer.objects) == [('content', cont)] def test_content_add_metadata_same_input(self, swh_storage): cont = data.cont del cont['data'] cont['ctime'] = datetime.datetime.now() actual_result = swh_storage.content_add_metadata([cont, cont]) assert actual_result == { 'content:add': 1, 'skipped_content:add': 0 } def test_content_add_metadata_different_input(self, swh_storage): cont = data.cont del cont['data'] cont['ctime'] = datetime.datetime.now() cont2 = data.cont2 del cont2['data'] cont2['ctime'] = datetime.datetime.now() actual_result = swh_storage.content_add_metadata([cont, cont2]) assert actual_result == { 'content:add': 2, 'skipped_content:add': 0 } def test_content_add_metadata_collision(self, swh_storage): cont1 = data.cont del cont1['data'] cont1['ctime'] = datetime.datetime.now() # 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 pytest.raises(HashCollision) as cm: swh_storage.content_add_metadata([cont1, cont1b]) assert cm.value.args[0] in ['sha1', 'sha1_git', 'blake2s256'] def test_skipped_content_add(self, swh_storage): cont = data.skipped_cont cont2 = data.skipped_cont2 cont2['blake2s256'] = None missing = list(swh_storage.skipped_content_missing([cont, cont2])) assert len(missing) == 2 actual_result = swh_storage.content_add([cont, cont, cont2]) assert actual_result == { 'content:add': 0, 'content:add:bytes': 0, 'skipped_content:add': 2, } missing = list(swh_storage.skipped_content_missing([cont, cont2])) assert missing == [] @pytest.mark.property_based @settings(deadline=None) # this test is very slow @given(strategies.sets( elements=strategies.sampled_from( ['sha256', 'sha1_git', 'blake2s256']), min_size=0)) def test_content_missing(self, swh_storage, algos): algos |= {'sha1'} cont2 = data.cont2 missing_cont = data.missing_cont swh_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) assert set(swh_storage.content_missing(test_contents)) == \ set(missing_per_hash['sha1']) for hash in algos: assert set(swh_storage.content_missing( test_contents, key_hash=hash)) == set(missing_per_hash[hash]) @pytest.mark.property_based @given(strategies.sets( elements=strategies.sampled_from( ['sha256', 'sha1_git', 'blake2s256']), min_size=0)) def test_content_missing_unknown_algo(self, swh_storage, algos): algos |= {'sha1'} cont2 = data.cont2 missing_cont = data.missing_cont swh_storage.content_add([cont2]) test_contents = [cont2] missing_per_hash = defaultdict(list) for i in range(16): 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_content['nonexisting_algo'] = b'\x00' test_contents.append(test_content) assert set( swh_storage.content_missing(test_contents)) == set( missing_per_hash['sha1']) for hash in algos: assert set(swh_storage.content_missing( test_contents, key_hash=hash)) == set( missing_per_hash[hash]) def test_content_missing_per_sha1(self, swh_storage): # given cont2 = data.cont2 missing_cont = data.missing_cont swh_storage.content_add([cont2]) # when gen = swh_storage.content_missing_per_sha1([cont2['sha1'], missing_cont['sha1']]) # then assert list(gen) == [missing_cont['sha1']] def test_content_get_metadata(self, swh_storage): cont1 = data.cont cont2 = data.cont2 swh_storage.content_add([cont1, cont2]) actual_md = list(swh_storage.content_get_metadata( [cont1['sha1'], cont2['sha1']])) # we only retrieve the metadata cont1.pop('data') cont2.pop('data') assert actual_md in ([cont1, cont2], [cont2, cont1]) def test_content_get_metadata_missing_sha1(self, swh_storage): cont1 = data.cont cont2 = data.cont2 missing_cont = data.missing_cont swh_storage.content_add([cont1, cont2]) gen = swh_storage.content_get_metadata([missing_cont['sha1']]) # All the metadata keys are None missing_cont.pop('data') for key in missing_cont: if key != 'sha1': missing_cont[key] = None assert list(gen) == [missing_cont] def test_directory_add(self, swh_storage): init_missing = list(swh_storage.directory_missing([data.dir['id']])) assert [data.dir['id']] == init_missing actual_result = swh_storage.directory_add([data.dir]) assert actual_result == {'directory:add': 1} assert list(swh_storage.journal_writer.objects) == \ [('directory', data.dir)] actual_data = list(swh_storage.directory_ls(data.dir['id'])) expected_data = list(transform_entries(data.dir)) assert sorted(expected_data, key=cmpdir) \ == sorted(actual_data, key=cmpdir) after_missing = list(swh_storage.directory_missing([data.dir['id']])) assert after_missing == [] def test_directory_add_validation(self, swh_storage): dir_ = copy.deepcopy(data.dir) dir_['entries'][0]['type'] = 'foobar' with pytest.raises(ValueError, match='type.*foobar'): swh_storage.directory_add([dir_]) dir_ = copy.deepcopy(data.dir) del dir_['entries'][0]['target'] with pytest.raises((TypeError, psycopg2.IntegrityError), match='target') as cm: swh_storage.directory_add([dir_]) if type(cm.value) == psycopg2.IntegrityError: assert cm.value.pgcode == psycopg2.errorcodes.NOT_NULL_VIOLATION def test_directory_add_twice(self, swh_storage): actual_result = swh_storage.directory_add([data.dir]) assert actual_result == {'directory:add': 1} assert list(swh_storage.journal_writer.objects) \ == [('directory', data.dir)] actual_result = swh_storage.directory_add([data.dir]) assert actual_result == {'directory:add': 0} assert list(swh_storage.journal_writer.objects) \ == [('directory', data.dir)] def test_directory_get_recursive(self, swh_storage): init_missing = list(swh_storage.directory_missing([data.dir['id']])) assert init_missing == [data.dir['id']] actual_result = swh_storage.directory_add( [data.dir, data.dir2, data.dir3]) assert actual_result == {'directory:add': 3} assert list(swh_storage.journal_writer.objects) == [ ('directory', data.dir), ('directory', data.dir2), ('directory', data.dir3)] # List directory containing a file and an unknown subdirectory actual_data = list(swh_storage.directory_ls( data.dir['id'], recursive=True)) expected_data = list(transform_entries(data.dir)) assert sorted(expected_data, key=cmpdir) \ == sorted(actual_data, key=cmpdir) # List directory containing a file and an unknown subdirectory actual_data = list(swh_storage.directory_ls( data.dir2['id'], recursive=True)) expected_data = list(transform_entries(data.dir2)) assert sorted(expected_data, key=cmpdir) \ == sorted(actual_data, key=cmpdir) # List directory containing a known subdirectory, entries should # be both those of the directory and of the subdir actual_data = list(swh_storage.directory_ls( data.dir3['id'], recursive=True)) expected_data = list(itertools.chain( transform_entries(data.dir3), transform_entries(data.dir, prefix=b'subdir/'))) assert sorted(expected_data, key=cmpdir) \ == sorted(actual_data, key=cmpdir) def test_directory_get_non_recursive(self, swh_storage): init_missing = list(swh_storage.directory_missing([data.dir['id']])) assert init_missing == [data.dir['id']] actual_result = swh_storage.directory_add( [data.dir, data.dir2, data.dir3]) assert actual_result == {'directory:add': 3} assert list(swh_storage.journal_writer.objects) == [ ('directory', data.dir), ('directory', data.dir2), ('directory', data.dir3)] # List directory containing a file and an unknown subdirectory actual_data = list(swh_storage.directory_ls(data.dir['id'])) expected_data = list(transform_entries(data.dir)) assert sorted(expected_data, key=cmpdir) \ == sorted(actual_data, key=cmpdir) # List directory contaiining a single file actual_data = list(swh_storage.directory_ls(data.dir2['id'])) expected_data = list(transform_entries(data.dir2)) assert sorted(expected_data, key=cmpdir) \ == sorted(actual_data, key=cmpdir) # List directory containing a known subdirectory, entries should # only be those of the parent directory, not of the subdir actual_data = list(swh_storage.directory_ls(data.dir3['id'])) expected_data = list(transform_entries(data.dir3)) assert sorted(expected_data, key=cmpdir) \ == sorted(actual_data, key=cmpdir) def test_directory_entry_get_by_path(self, swh_storage): # given init_missing = list(swh_storage.directory_missing([data.dir3['id']])) assert [data.dir3['id']] == init_missing actual_result = swh_storage.directory_add([data.dir3, data.dir4]) assert actual_result == {'directory:add': 2} expected_entries = [ { 'dir_id': data.dir3['id'], 'name': b'foo', 'type': 'file', 'target': data.cont['sha1_git'], 'sha1': None, 'sha1_git': None, 'sha256': None, 'status': None, 'perms': from_disk.DentryPerms.content, 'length': None, }, { 'dir_id': data.dir3['id'], 'name': b'subdir', 'type': 'dir', 'target': data.dir['id'], 'sha1': None, 'sha1_git': None, 'sha256': None, 'status': None, 'perms': from_disk.DentryPerms.directory, 'length': None, }, { 'dir_id': data.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( data.dir3['entries'], expected_entries): actual_entry = swh_storage.directory_entry_get_by_path( data.dir3['id'], [entry['name']]) assert actual_entry == expected_entry # same, but deeper for entry, expected_entry in zip( data.dir3['entries'], expected_entries): actual_entry = swh_storage.directory_entry_get_by_path( data.dir4['id'], [b'subdir1', entry['name']]) expected_entry = expected_entry.copy() expected_entry['name'] = b'subdir1/' + expected_entry['name'] assert actual_entry == expected_entry # when (nothing should be found here since data.dir is not persisted.) for entry in data.dir['entries']: actual_entry = swh_storage.directory_entry_get_by_path( data.dir['id'], [entry['name']]) assert actual_entry is None def test_revision_add(self, swh_storage): init_missing = swh_storage.revision_missing([data.revision['id']]) assert list(init_missing) == [data.revision['id']] actual_result = swh_storage.revision_add([data.revision]) assert actual_result == {'revision:add': 1} end_missing = swh_storage.revision_missing([data.revision['id']]) assert list(end_missing) == [] assert list(swh_storage.journal_writer.objects) \ == [('revision', data.revision)] # already there so nothing added actual_result = swh_storage.revision_add([data.revision]) assert actual_result == {'revision:add': 0} def test_revision_add_validation(self, swh_storage): rev = copy.deepcopy(data.revision) rev['date']['offset'] = 2**16 with pytest.raises((ValueError, psycopg2.DataError), match='offset') as cm: swh_storage.revision_add([rev]) if type(cm.value) == psycopg2.DataError: assert cm.value.pgcode \ == psycopg2.errorcodes.NUMERIC_VALUE_OUT_OF_RANGE rev = copy.deepcopy(data.revision) rev['committer_date']['offset'] = 2**16 with pytest.raises((ValueError, psycopg2.DataError), match='offset') as cm: swh_storage.revision_add([rev]) if type(cm.value) == psycopg2.DataError: assert cm.value.pgcode \ == psycopg2.errorcodes.NUMERIC_VALUE_OUT_OF_RANGE rev = copy.deepcopy(data.revision) rev['type'] = 'foobar' with pytest.raises((ValueError, psycopg2.DataError), match='(?i)type') as cm: swh_storage.revision_add([rev]) if type(cm.value) == psycopg2.DataError: assert cm.value.pgcode == \ psycopg2.errorcodes.INVALID_TEXT_REPRESENTATION def test_revision_add_twice(self, swh_storage): actual_result = swh_storage.revision_add([data.revision]) assert actual_result == {'revision:add': 1} assert list(swh_storage.journal_writer.objects) \ == [('revision', data.revision)] actual_result = swh_storage.revision_add( [data.revision, data.revision2]) assert actual_result == {'revision:add': 1} assert list(swh_storage.journal_writer.objects) \ == [('revision', data.revision), ('revision', data.revision2)] def test_revision_add_name_clash(self, swh_storage): revision1 = data.revision revision2 = data.revision2 revision1['author'] = { 'fullname': b'John Doe ', 'name': b'John Doe', 'email': b'john.doe@example.com' } revision2['author'] = { 'fullname': b'John Doe ', 'name': b'John Doe ', 'email': b'john.doe@example.com ' } actual_result = swh_storage.revision_add([revision1, revision2]) assert actual_result == {'revision:add': 2} def test_revision_log(self, swh_storage): # given # data.revision4 -is-child-of-> data.revision3 swh_storage.revision_add([data.revision3, data.revision4]) # when actual_results = list(swh_storage.revision_log( [data.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'] assert len(actual_results) == 2 # rev4 -child-> rev3 assert actual_results[0] == normalize_entity(data.revision4) assert actual_results[1] == normalize_entity(data.revision3) assert list(swh_storage.journal_writer.objects) == [ ('revision', data.revision3), ('revision', data.revision4)] def test_revision_log_with_limit(self, swh_storage): # given # data.revision4 -is-child-of-> data.revision3 swh_storage.revision_add([data.revision3, data.revision4]) actual_results = list(swh_storage.revision_log( [data.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'] assert len(actual_results) == 1 assert actual_results[0] == data.revision4 def test_revision_log_unknown_revision(self, swh_storage): rev_log = list(swh_storage.revision_log([data.revision['id']])) assert rev_log == [] def test_revision_shortlog(self, swh_storage): # given # data.revision4 -is-child-of-> data.revision3 swh_storage.revision_add([data.revision3, data.revision4]) # when actual_results = list(swh_storage.revision_shortlog( [data.revision4['id']])) assert len(actual_results) == 2 # rev4 -child-> rev3 assert list(actual_results[0]) == short_revision(data.revision4) assert list(actual_results[1]) == short_revision(data.revision3) def test_revision_shortlog_with_limit(self, swh_storage): # given # data.revision4 -is-child-of-> data.revision3 swh_storage.revision_add([data.revision3, data.revision4]) actual_results = list(swh_storage.revision_shortlog( [data.revision4['id']], 1)) assert len(actual_results) == 1 assert list(actual_results[0]) == short_revision(data.revision4) def test_revision_get(self, swh_storage): swh_storage.revision_add([data.revision]) actual_revisions = list(swh_storage.revision_get( [data.revision['id'], data.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'] assert len(actual_revisions) == 2 assert actual_revisions[0] == normalize_entity(data.revision) assert actual_revisions[1] is None def test_revision_get_no_parents(self, swh_storage): swh_storage.revision_add([data.revision3]) get = list(swh_storage.revision_get([data.revision3['id']])) assert len(get) == 1 assert get[0]['parents'] == [] # no parents on this one def test_release_add(self, swh_storage): init_missing = swh_storage.release_missing([data.release['id'], data.release2['id']]) assert [data.release['id'], data.release2['id']] == list(init_missing) actual_result = swh_storage.release_add([data.release, data.release2]) assert actual_result == {'release:add': 2} end_missing = swh_storage.release_missing([data.release['id'], data.release2['id']]) assert list(end_missing) == [] assert list(swh_storage.journal_writer.objects) == [ ('release', data.release), ('release', data.release2)] # already present so nothing added actual_result = swh_storage.release_add([data.release, data.release2]) assert actual_result == {'release:add': 0} def test_release_add_no_author_date(self, swh_storage): release = data.release release['author'] = None release['date'] = None actual_result = swh_storage.release_add([release]) assert actual_result == {'release:add': 1} end_missing = swh_storage.release_missing([data.release['id']]) assert list(end_missing) == [] assert list(swh_storage.journal_writer.objects) \ == [('release', release)] def test_release_add_validation(self, swh_storage): rel = copy.deepcopy(data.release) rel['date']['offset'] = 2**16 with pytest.raises((ValueError, psycopg2.DataError), match='offset') as cm: swh_storage.release_add([rel]) if type(cm.value) == psycopg2.DataError: assert cm.value.pgcode \ == psycopg2.errorcodes.NUMERIC_VALUE_OUT_OF_RANGE rel = copy.deepcopy(data.release) rel['author'] = None with pytest.raises((ValueError, psycopg2.IntegrityError), match='date') as cm: swh_storage.release_add([rel]) if type(cm.value) == psycopg2.IntegrityError: assert cm.value.pgcode == psycopg2.errorcodes.CHECK_VIOLATION def test_release_add_twice(self, swh_storage): actual_result = swh_storage.release_add([data.release]) assert actual_result == {'release:add': 1} assert list(swh_storage.journal_writer.objects) \ == [('release', data.release)] actual_result = swh_storage.release_add([data.release, data.release2]) assert actual_result == {'release:add': 1} assert list(swh_storage.journal_writer.objects) \ == [('release', data.release), ('release', data.release2)] def test_release_add_name_clash(self, swh_storage): release1 = data.release.copy() release2 = data.release2.copy() release1['author'] = { 'fullname': b'John Doe ', 'name': b'John Doe', 'email': b'john.doe@example.com' } release2['author'] = { 'fullname': b'John Doe ', 'name': b'John Doe ', 'email': b'john.doe@example.com ' } actual_result = swh_storage.release_add([release1, release2]) assert actual_result == {'release:add': 2} def test_release_get(self, swh_storage): # given swh_storage.release_add([data.release, data.release2]) # when actual_releases = list(swh_storage.release_get([data.release['id'], data.release2['id']])) # then for actual_release in actual_releases: if 'id' in actual_release['author']: del actual_release['author']['id'] # hack: ids are generated assert [ normalize_entity(data.release), normalize_entity(data.release2)] \ == [actual_releases[0], actual_releases[1]] unknown_releases = \ list(swh_storage.release_get([data.release3['id']])) assert unknown_releases[0] is None def test_origin_add_one(self, swh_storage): origin0 = swh_storage.origin_get(data.origin) assert origin0 is None id = swh_storage.origin_add_one(data.origin) actual_origin = swh_storage.origin_get({'url': data.origin['url']}) - if self._test_origin_ids: - assert actual_origin['id'] == id assert actual_origin['url'] == data.origin['url'] id2 = swh_storage.origin_add_one(data.origin) assert id == id2 def test_origin_add(self, swh_storage): origin0 = swh_storage.origin_get([data.origin])[0] assert origin0 is None origin1, origin2 = swh_storage.origin_add([data.origin, data.origin2]) actual_origin = swh_storage.origin_get([{ 'url': data.origin['url'], }])[0] - if self._test_origin_ids: - assert actual_origin['id'] == origin1['id'] assert actual_origin['url'] == origin1['url'] actual_origin2 = swh_storage.origin_get([{ 'url': data.origin2['url'], }])[0] - if self._test_origin_ids: - assert actual_origin2['id'] == origin2['id'] assert actual_origin2['url'] == origin2['url'] if 'id' in actual_origin: del actual_origin['id'] del actual_origin2['id'] assert list(swh_storage.journal_writer.objects) \ == [('origin', actual_origin), ('origin', actual_origin2)] def test_origin_add_twice(self, swh_storage): add1 = swh_storage.origin_add([data.origin, data.origin2]) assert list(swh_storage.journal_writer.objects) \ == [('origin', data.origin), ('origin', data.origin2)] add2 = swh_storage.origin_add([data.origin, data.origin2]) assert list(swh_storage.journal_writer.objects) \ == [('origin', data.origin), ('origin', data.origin2)] assert add1 == add2 def test_origin_add_validation(self, swh_storage): with pytest.raises((TypeError, KeyError), match='url'): swh_storage.origin_add([{'type': 'git'}]) def test_origin_get_legacy(self, swh_storage): assert swh_storage.origin_get(data.origin) is None - id = swh_storage.origin_add_one(data.origin) + swh_storage.origin_add_one(data.origin) - # lookup per url (returns id) actual_origin0 = swh_storage.origin_get( {'url': data.origin['url']}) - if self._test_origin_ids: - assert actual_origin0['id'] == id assert actual_origin0['url'] == data.origin['url'] - # lookup per id (returns dict) - if self._test_origin_ids: - actual_origin1 = swh_storage.origin_get({'id': id}) - - assert actual_origin1 == {'id': id, - 'url': data.origin['url']} - def test_origin_get(self, swh_storage): assert swh_storage.origin_get(data.origin) is None - origin_id = swh_storage.origin_add_one(data.origin) + swh_storage.origin_add_one(data.origin) - # lookup per url (returns id) actual_origin0 = swh_storage.origin_get( [{'url': data.origin['url']}]) assert len(actual_origin0) == 1 assert actual_origin0[0]['url'] == data.origin['url'] - if self._test_origin_ids: - # lookup per id (returns dict) - actual_origin1 = swh_storage.origin_get([{'id': origin_id}]) - - assert len(actual_origin1) == 1 - assert actual_origin1[0] == {'id': origin_id, - 'url': data.origin['url']} - - def test_origin_get_consistency(self, swh_storage): - assert swh_storage.origin_get(data.origin) is None - id = swh_storage.origin_add_one(data.origin) - - with pytest.raises(ValueError): - swh_storage.origin_get([ - {'url': data.origin['url']}, - {'id': id}]) - def test_origin_search_single_result(self, swh_storage): found_origins = list(swh_storage.origin_search(data.origin['url'])) assert len(found_origins) == 0 found_origins = list(swh_storage.origin_search(data.origin['url'], regexp=True)) assert len(found_origins) == 0 swh_storage.origin_add_one(data.origin) origin_data = { 'url': data.origin['url']} found_origins = list(swh_storage.origin_search(data.origin['url'])) assert len(found_origins) == 1 if 'id' in found_origins[0]: del found_origins[0]['id'] assert found_origins[0] == origin_data found_origins = list(swh_storage.origin_search( '.' + data.origin['url'][1:-1] + '.', regexp=True)) assert len(found_origins) == 1 if 'id' in found_origins[0]: del found_origins[0]['id'] assert found_origins[0] == origin_data swh_storage.origin_add_one(data.origin2) origin2_data = {'url': data.origin2['url']} found_origins = list(swh_storage.origin_search(data.origin2['url'])) assert len(found_origins) == 1 if 'id' in found_origins[0]: del found_origins[0]['id'] assert found_origins[0] == origin2_data found_origins = list(swh_storage.origin_search( '.' + data.origin2['url'][1:-1] + '.', regexp=True)) assert len(found_origins) == 1 if 'id' in found_origins[0]: del found_origins[0]['id'] assert found_origins[0] == origin2_data def test_origin_search_no_regexp(self, swh_storage): swh_storage.origin_add_one(data.origin) swh_storage.origin_add_one(data.origin2) origin = swh_storage.origin_get({'url': data.origin['url']}) origin2 = swh_storage.origin_get({'url': data.origin2['url']}) # no pagination found_origins = list(swh_storage.origin_search('/')) assert len(found_origins) == 2 # offset=0 found_origins0 = list(swh_storage.origin_search('/', offset=0, limit=1)) # noqa assert len(found_origins0) == 1 assert found_origins0[0] in [origin, origin2] # offset=1 found_origins1 = list(swh_storage.origin_search('/', offset=1, limit=1)) # noqa assert len(found_origins1) == 1 assert found_origins1[0] in [origin, origin2] # check both origins were returned assert found_origins0 != found_origins1 def test_origin_search_regexp_substring(self, swh_storage): swh_storage.origin_add_one(data.origin) swh_storage.origin_add_one(data.origin2) origin = swh_storage.origin_get({'url': data.origin['url']}) origin2 = swh_storage.origin_get({'url': data.origin2['url']}) # no pagination found_origins = list(swh_storage.origin_search('/', regexp=True)) assert len(found_origins) == 2 # offset=0 found_origins0 = list(swh_storage.origin_search('/', offset=0, limit=1, regexp=True)) # noqa assert len(found_origins0) == 1 assert found_origins0[0] in [origin, origin2] # offset=1 found_origins1 = list(swh_storage.origin_search('/', offset=1, limit=1, regexp=True)) # noqa assert len(found_origins1) == 1 assert found_origins1[0] in [origin, origin2] # check both origins were returned assert found_origins0 != found_origins1 def test_origin_search_regexp_fullstring(self, swh_storage): swh_storage.origin_add_one(data.origin) swh_storage.origin_add_one(data.origin2) origin = swh_storage.origin_get({'url': data.origin['url']}) origin2 = swh_storage.origin_get({'url': data.origin2['url']}) # no pagination found_origins = list(swh_storage.origin_search('.*/.*', regexp=True)) assert len(found_origins) == 2 # offset=0 found_origins0 = list(swh_storage.origin_search('.*/.*', offset=0, limit=1, regexp=True)) # noqa assert len(found_origins0) == 1 assert found_origins0[0] in [origin, origin2] # offset=1 found_origins1 = list(swh_storage.origin_search('.*/.*', offset=1, limit=1, regexp=True)) # noqa assert len(found_origins1) == 1 assert found_origins1[0] in [origin, origin2] # check both origins were returned assert found_origins0 != found_origins1 - @pytest.mark.parametrize('use_url', [True, False]) - def test_origin_visit_add(self, swh_storage, use_url): - if not self._test_origin_ids and not use_url: - return + def test_origin_visit_add(self, swh_storage): # given - origin_id = swh_storage.origin_add_one(data.origin2) - assert origin_id is not None + swh_storage.origin_add_one(data.origin2) - origin_id_or_url = data.origin2['url'] if use_url else origin_id + origin_url = data.origin2['url'] # when date_visit = datetime.datetime.now(datetime.timezone.utc) origin_visit1 = swh_storage.origin_visit_add( - origin_id_or_url, + origin_url, type=data.type_visit1, date=date_visit) actual_origin_visits = list(swh_storage.origin_visit_get( - origin_id_or_url)) + origin_url)) assert { - 'origin': origin_id, + 'origin': origin_url, 'date': date_visit, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'ongoing', 'metadata': None, 'snapshot': None, } in actual_origin_visits expected_origin = data.origin2 origin_visit = { 'origin': expected_origin, 'date': date_visit, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'ongoing', 'metadata': None, 'snapshot': None, } objects = list(swh_storage.journal_writer.objects) assert ('origin', expected_origin) in objects assert ('origin_visit', origin_visit) in objects def test_origin_visit_get__unknown_origin(self, swh_storage): assert [] == list(swh_storage.origin_visit_get('foo')) - if self._test_origin_ids: - assert list(swh_storage.origin_visit_get(10)) == [] - @pytest.mark.parametrize('use_url', [True, False]) - def test_origin_visit_add_default_type(self, swh_storage, use_url): - if not self._test_origin_ids and not use_url: - return + def test_origin_visit_add_default_type(self, swh_storage): # given - origin_id = swh_storage.origin_add_one(data.origin2) - origin_id_or_url = data.origin2['url'] if use_url else origin_id - assert origin_id is not None + swh_storage.origin_add_one(data.origin2) + origin_url = data.origin2['url'] # when date_visit = datetime.datetime.now(datetime.timezone.utc) date_visit2 = date_visit + datetime.timedelta(minutes=1) origin_visit1 = swh_storage.origin_visit_add( - origin_id_or_url, + origin_url, date=date_visit, type=data.type_visit1, ) origin_visit2 = swh_storage.origin_visit_add( - origin_id_or_url, + origin_url, date=date_visit2, type=data.type_visit2, ) # then - assert origin_visit1['origin'] == origin_id + assert origin_visit1['origin'] == origin_url assert origin_visit1['visit'] is not None actual_origin_visits = list(swh_storage.origin_visit_get( - origin_id_or_url)) + origin_url)) expected_visits = [ { - 'origin': origin_id, + 'origin': origin_url, 'date': date_visit, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'ongoing', 'metadata': None, 'snapshot': None, }, { - 'origin': origin_id, + 'origin': origin_url, 'date': date_visit2, 'visit': origin_visit2['visit'], 'type': data.type_visit2, 'status': 'ongoing', 'metadata': None, 'snapshot': None, }, ] for visit in expected_visits: assert visit in actual_origin_visits objects = list(swh_storage.journal_writer.objects) assert ('origin', data.origin2) in objects for visit in expected_visits: visit['origin'] = data.origin2 assert ('origin_visit', visit) in objects def test_origin_visit_add_validation(self, swh_storage): - origin_id_or_url = swh_storage.origin_add_one(data.origin2) + origin_url = swh_storage.origin_add_one(data.origin2) with pytest.raises((TypeError, psycopg2.ProgrammingError)) as cm: - swh_storage.origin_visit_add(origin_id_or_url, date=[b'foo'], - type=data.type_visit1) + swh_storage.origin_visit_add(origin_url, date=[b'foo']) if type(cm.value) == psycopg2.ProgrammingError: assert cm.value.pgcode \ == psycopg2.errorcodes.UNDEFINED_FUNCTION - @pytest.mark.parametrize('use_url', [True, False]) - def test_origin_visit_update(self, swh_storage, use_url): - if not self._test_origin_ids and not use_url: - return + def test_origin_visit_update(self, swh_storage): # given swh_storage.origin_add_one(data.origin) origin_url = data.origin['url'] date_visit = datetime.datetime.now(datetime.timezone.utc) origin_visit1 = swh_storage.origin_visit_add( origin_url, date=date_visit, type=data.type_visit1, ) date_visit2 = date_visit + datetime.timedelta(minutes=1) origin_visit2 = swh_storage.origin_visit_add( origin_url, date=date_visit2, type=data.type_visit2 ) swh_storage.origin_add_one(data.origin2) origin_url2 = data.origin2['url'] origin_visit3 = swh_storage.origin_visit_add( origin_url2, date=date_visit2, type=data.type_visit3 ) # when visit1_metadata = { 'contents': 42, 'directories': 22, } swh_storage.origin_visit_update( origin_url, origin_visit1['visit'], status='full', metadata=visit1_metadata) swh_storage.origin_visit_update( origin_url2, origin_visit3['visit'], status='partial') # then actual_origin_visits = list(swh_storage.origin_visit_get( origin_url)) expected_visits = [{ 'origin': origin_visit2['origin'], 'date': date_visit, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'full', 'metadata': visit1_metadata, 'snapshot': None, }, { 'origin': origin_visit2['origin'], 'date': date_visit2, 'visit': origin_visit2['visit'], 'type': data.type_visit2, 'status': 'ongoing', 'metadata': None, 'snapshot': None, }] for visit in expected_visits: assert visit in actual_origin_visits actual_origin_visits_bis = list(swh_storage.origin_visit_get( origin_url, limit=1)) assert actual_origin_visits_bis == [ { 'origin': origin_visit2['origin'], 'date': date_visit, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'full', 'metadata': visit1_metadata, 'snapshot': None, }] actual_origin_visits_ter = list(swh_storage.origin_visit_get( origin_url, last_visit=origin_visit1['visit'])) assert actual_origin_visits_ter == [ { 'origin': origin_visit2['origin'], 'date': date_visit2, 'visit': origin_visit2['visit'], 'type': data.type_visit2, 'status': 'ongoing', 'metadata': None, 'snapshot': None, }] actual_origin_visits2 = list(swh_storage.origin_visit_get( origin_url2)) assert actual_origin_visits2 == [ { 'origin': origin_visit3['origin'], 'date': date_visit2, 'visit': origin_visit3['visit'], 'type': data.type_visit3, 'status': 'partial', 'metadata': None, 'snapshot': None, }] expected_origin = data.origin.copy() expected_origin2 = data.origin2.copy() data1 = { 'origin': expected_origin, 'date': date_visit, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'ongoing', 'metadata': None, 'snapshot': None, } data2 = { 'origin': expected_origin, 'date': date_visit2, 'visit': origin_visit2['visit'], 'type': data.type_visit2, 'status': 'ongoing', 'metadata': None, 'snapshot': None, } data3 = { 'origin': expected_origin2, 'date': date_visit2, 'visit': origin_visit3['visit'], 'type': data.type_visit3, 'status': 'ongoing', 'metadata': None, 'snapshot': None, } data4 = { 'origin': expected_origin, 'date': date_visit, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'metadata': visit1_metadata, 'status': 'full', 'snapshot': None, } data5 = { 'origin': expected_origin2, 'date': date_visit2, 'visit': origin_visit3['visit'], 'type': data.type_visit3, 'status': 'partial', 'metadata': None, 'snapshot': None, } objects = list(swh_storage.journal_writer.objects) assert ('origin', expected_origin) in objects assert ('origin', expected_origin2) in objects assert ('origin_visit', data1) in objects assert ('origin_visit', data2) in objects assert ('origin_visit', data3) in objects assert ('origin_visit', data4) in objects assert ('origin_visit', data5) in objects def test_origin_visit_update_validation(self, swh_storage): - origin_id = swh_storage.origin_add_one(data.origin) + origin_url = data.origin['url'] + swh_storage.origin_add_one(data.origin) visit = swh_storage.origin_visit_add( - origin_id, + origin_url, date=data.date_visit2, type=data.type_visit2, ) with pytest.raises((ValueError, psycopg2.DataError), match='status') as cm: swh_storage.origin_visit_update( - origin_id, visit['visit'], status='foobar') + origin_url, visit['visit'], status='foobar') if type(cm.value) == psycopg2.DataError: assert cm.value.pgcode == \ psycopg2.errorcodes.INVALID_TEXT_REPRESENTATION def test_origin_visit_find_by_date(self, swh_storage): # given swh_storage.origin_add_one(data.origin) swh_storage.origin_visit_add( data.origin['url'], date=data.date_visit2, type=data.type_visit1, ) origin_visit2 = swh_storage.origin_visit_add( data.origin['url'], date=data.date_visit3, type=data.type_visit2, ) origin_visit3 = swh_storage.origin_visit_add( data.origin['url'], date=data.date_visit2, type=data.type_visit3, ) # Simple case visit = swh_storage.origin_visit_find_by_date( data.origin['url'], data.date_visit3) assert visit['visit'] == origin_visit2['visit'] # There are two visits at the same date, the latest must be returned visit = swh_storage.origin_visit_find_by_date( data.origin['url'], data.date_visit2) assert visit['visit'] == origin_visit3['visit'] def test_origin_visit_find_by_date__unknown_origin(self, swh_storage): swh_storage.origin_visit_find_by_date('foo', data.date_visit2) - @pytest.mark.parametrize('use_url', [True, False]) - def test_origin_visit_update_missing_snapshot(self, swh_storage, use_url): - if not self._test_origin_ids and not use_url: - return + def test_origin_visit_update_missing_snapshot(self, swh_storage): # given - origin_id = swh_storage.origin_add_one(data.origin) - origin_id_or_url = data.origin['url'] if use_url else origin_id + swh_storage.origin_add_one(data.origin) + origin_url = data.origin['url'] origin_visit = swh_storage.origin_visit_add( - origin_id_or_url, + origin_url, date=data.date_visit1, type=data.type_visit1, ) # when swh_storage.origin_visit_update( - origin_id_or_url, + origin_url, origin_visit['visit'], snapshot=data.snapshot['id']) # then actual_origin_visit = swh_storage.origin_visit_get_by( - origin_id_or_url, + origin_url, origin_visit['visit']) assert actual_origin_visit['snapshot'] == data.snapshot['id'] # when swh_storage.snapshot_add([data.snapshot]) assert actual_origin_visit['snapshot'] == data.snapshot['id'] - @pytest.mark.parametrize('use_url', [True, False]) - def test_origin_visit_get_by(self, swh_storage, use_url): - if not self._test_origin_ids and not use_url: - return - origin_id = swh_storage.origin_add_one(data.origin) - origin_id2 = swh_storage.origin_add_one(data.origin2) + def test_origin_visit_get_by(self, swh_storage): + swh_storage.origin_add_one(data.origin) + swh_storage.origin_add_one(data.origin2) - origin_id_or_url = data.origin['url'] if use_url else origin_id - origin2_id_or_url = data.origin2['url'] if use_url else origin_id2 + origin_url = data.origin['url'] + origin2_url = data.origin2['url'] origin_visit1 = swh_storage.origin_visit_add( - origin_id_or_url, + origin_url, date=data.date_visit2, type=data.type_visit2, ) swh_storage.snapshot_add([data.snapshot]) swh_storage.origin_visit_update( - origin_id_or_url, + origin_url, origin_visit1['visit'], snapshot=data.snapshot['id']) # Add some other {origin, visit} entries swh_storage.origin_visit_add( - origin_id_or_url, + origin_url, date=data.date_visit3, type=data.type_visit3, ) swh_storage.origin_visit_add( - origin2_id_or_url, + origin2_url, date=data.date_visit3, type=data.type_visit3, ) # when visit1_metadata = { 'contents': 42, 'directories': 22, } swh_storage.origin_visit_update( - origin_id_or_url, + origin_url, origin_visit1['visit'], status='full', metadata=visit1_metadata) expected_origin_visit = origin_visit1.copy() expected_origin_visit.update({ - 'origin': origin_id, + 'origin': origin_url, 'visit': origin_visit1['visit'], 'date': data.date_visit2, 'type': data.type_visit2, 'metadata': visit1_metadata, 'status': 'full', 'snapshot': data.snapshot['id'], }) # when actual_origin_visit1 = swh_storage.origin_visit_get_by( - origin_id_or_url, + origin_url, origin_visit1['visit']) # then assert actual_origin_visit1 == expected_origin_visit def test_origin_visit_get_by__unknown_origin(self, swh_storage): - if self._test_origin_ids: - assert swh_storage.origin_visit_get_by(2, 10) is None assert swh_storage.origin_visit_get_by('foo', 10) is None - @pytest.mark.parametrize('use_url', [True, False]) - def test_origin_visit_upsert_new(self, swh_storage, use_url): - if not self._test_origin_ids and not use_url: - return + def test_origin_visit_upsert_new(self, swh_storage): # given - origin_id = swh_storage.origin_add_one(data.origin2) + swh_storage.origin_add_one(data.origin2) origin_url = data.origin2['url'] - assert origin_id is not None # when swh_storage.origin_visit_upsert([ { 'origin': data.origin2, 'date': data.date_visit2, 'visit': 123, 'type': data.type_visit2, 'status': 'full', 'metadata': None, 'snapshot': None, }, { 'origin': data.origin2, 'date': '2018-01-01 23:00:00+00', 'visit': 1234, 'type': data.type_visit2, 'status': 'full', 'metadata': None, 'snapshot': None, }, ]) # then actual_origin_visits = list(swh_storage.origin_visit_get( origin_url)) assert actual_origin_visits == [ { - 'origin': origin_id, + 'origin': origin_url, 'date': data.date_visit2, 'visit': 123, 'type': data.type_visit2, 'status': 'full', 'metadata': None, 'snapshot': None, }, { - 'origin': origin_id, + 'origin': origin_url, 'date': data.date_visit3, 'visit': 1234, 'type': data.type_visit2, 'status': 'full', 'metadata': None, 'snapshot': None, }, ] expected_origin = data.origin2 data1 = { 'origin': expected_origin, 'date': data.date_visit2, 'visit': 123, 'type': data.type_visit2, 'status': 'full', 'metadata': None, 'snapshot': None, } data2 = { 'origin': expected_origin, 'date': data.date_visit3, 'visit': 1234, 'type': data.type_visit2, 'status': 'full', 'metadata': None, 'snapshot': None, } assert list(swh_storage.journal_writer.objects) == [ ('origin', expected_origin), ('origin_visit', data1), ('origin_visit', data2)] - @pytest.mark.parametrize('use_url', [True, False]) - def test_origin_visit_upsert_existing(self, swh_storage, use_url): - if not self._test_origin_ids and not use_url: - return + def test_origin_visit_upsert_existing(self, swh_storage): # given - origin_id = swh_storage.origin_add_one(data.origin2) + swh_storage.origin_add_one(data.origin2) origin_url = data.origin2['url'] - assert origin_id is not None # when origin_visit1 = swh_storage.origin_visit_add( origin_url, date=data.date_visit2, type=data.type_visit1, ) swh_storage.origin_visit_upsert([{ 'origin': data.origin2, 'date': data.date_visit2, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'full', 'metadata': None, 'snapshot': None, }]) # then - assert origin_visit1['origin'] == origin_id + assert origin_visit1['origin'] == origin_url assert origin_visit1['visit'] is not None actual_origin_visits = list(swh_storage.origin_visit_get( origin_url)) assert actual_origin_visits == [ { - 'origin': origin_id, + 'origin': origin_url, 'date': data.date_visit2, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'full', 'metadata': None, 'snapshot': None, }] expected_origin = data.origin2 data1 = { 'origin': expected_origin, 'date': data.date_visit2, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'ongoing', 'metadata': None, 'snapshot': None, } data2 = { 'origin': expected_origin, 'date': data.date_visit2, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'full', 'metadata': None, 'snapshot': None, } assert list(swh_storage.journal_writer.objects) == [ ('origin', expected_origin), ('origin_visit', data1), ('origin_visit', data2)] def test_origin_visit_get_by_no_result(self, swh_storage): - if self._test_origin_ids: - actual_origin_visit = swh_storage.origin_visit_get_by( - 10, 999) - assert actual_origin_visit is None - swh_storage.origin_add([data.origin]) actual_origin_visit = swh_storage.origin_visit_get_by( data.origin['url'], 999) assert actual_origin_visit is None - @pytest.mark.parametrize('use_url', [True, False]) - def test_origin_visit_get_latest(self, swh_storage, use_url): - if not self._test_origin_ids and not use_url: - return + def test_origin_visit_get_latest(self, swh_storage): swh_storage.origin_add_one(data.origin) origin_url = data.origin['url'] origin_visit1 = swh_storage.origin_visit_add( origin=origin_url, date=data.date_visit1, type=data.type_visit1, ) visit1_id = origin_visit1['visit'] origin_visit2 = swh_storage.origin_visit_add( origin=origin_url, date=data.date_visit2, type=data.type_visit2, ) visit2_id = origin_visit2['visit'] # Add a visit with the same date as the previous one origin_visit3 = swh_storage.origin_visit_add( origin=origin_url, date=data.date_visit2, type=data.type_visit2, ) visit3_id = origin_visit3['visit'] origin_visit1 = swh_storage.origin_visit_get_by(origin_url, visit1_id) origin_visit2 = swh_storage.origin_visit_get_by(origin_url, visit2_id) origin_visit3 = swh_storage.origin_visit_get_by(origin_url, visit3_id) # Two visits, both with no snapshot assert origin_visit3 == swh_storage.origin_visit_get_latest(origin_url) assert swh_storage.origin_visit_get_latest( origin_url, require_snapshot=True) is None # Add snapshot to visit1; require_snapshot=True makes it return # visit1 and require_snapshot=False still returns visit2 swh_storage.snapshot_add([data.complete_snapshot]) swh_storage.origin_visit_update( origin_url, visit1_id, snapshot=data.complete_snapshot['id']) assert {**origin_visit1, 'snapshot': data.complete_snapshot['id']} \ == swh_storage.origin_visit_get_latest( origin_url, require_snapshot=True) assert origin_visit3 == swh_storage.origin_visit_get_latest(origin_url) # Status filter: all three visits are status=ongoing, so no visit # returned assert swh_storage.origin_visit_get_latest( origin_url, allowed_statuses=['full']) is None # Mark the first visit as completed and check status filter again swh_storage.origin_visit_update( origin_url, visit1_id, status='full') assert { **origin_visit1, 'snapshot': data.complete_snapshot['id'], 'status': 'full'} == swh_storage.origin_visit_get_latest( origin_url, allowed_statuses=['full']) assert origin_visit3 == swh_storage.origin_visit_get_latest(origin_url) # Add snapshot to visit2 and check that the new snapshot is returned swh_storage.snapshot_add([data.empty_snapshot]) swh_storage.origin_visit_update( origin_url, visit2_id, snapshot=data.empty_snapshot['id']) assert {**origin_visit2, 'snapshot': data.empty_snapshot['id']} == \ swh_storage.origin_visit_get_latest( origin_url, require_snapshot=True) assert origin_visit3 == swh_storage.origin_visit_get_latest(origin_url) # Check that the status filter is still working assert { **origin_visit1, 'snapshot': data.complete_snapshot['id'], 'status': 'full'} == swh_storage.origin_visit_get_latest( origin_url, allowed_statuses=['full']) # Add snapshot to visit3 (same date as visit2) swh_storage.snapshot_add([data.complete_snapshot]) swh_storage.origin_visit_update( origin_url, visit3_id, snapshot=data.complete_snapshot['id']) assert { **origin_visit1, 'snapshot': data.complete_snapshot['id'], 'status': 'full'} == swh_storage.origin_visit_get_latest( origin_url, allowed_statuses=['full']) assert { **origin_visit1, 'snapshot': data.complete_snapshot['id'], 'status': 'full'} == swh_storage.origin_visit_get_latest( origin_url, allowed_statuses=['full'], require_snapshot=True) assert { **origin_visit3, 'snapshot': data.complete_snapshot['id'] } == swh_storage.origin_visit_get_latest(origin_url) assert { **origin_visit3, 'snapshot': data.complete_snapshot['id'] } == swh_storage.origin_visit_get_latest( origin_url, require_snapshot=True) def test_person_fullname_unicity(self, swh_storage): # given (person injection through revisions for example) revision = data.revision # create a revision with same committer fullname but wo name and email revision2 = copy.deepcopy(data.revision2) revision2['committer'] = dict(revision['committer']) revision2['committer']['email'] = None revision2['committer']['name'] = None swh_storage.revision_add([revision]) swh_storage.revision_add([revision2]) # when getting added revisions revisions = list( swh_storage.revision_get([revision['id'], revision2['id']])) # then # check committers are the same assert revisions[0]['committer'] == revisions[1]['committer'] def test_snapshot_add_get_empty(self, swh_storage): - origin_id = swh_storage.origin_add_one(data.origin) + origin_url = data.origin['url'] + swh_storage.origin_add_one(data.origin) origin_visit1 = swh_storage.origin_visit_add( - origin=origin_id, + origin=origin_url, date=data.date_visit1, type=data.type_visit1, ) visit_id = origin_visit1['visit'] actual_result = swh_storage.snapshot_add([data.empty_snapshot]) assert actual_result == {'snapshot:add': 1} swh_storage.origin_visit_update( - origin_id, visit_id, snapshot=data.empty_snapshot['id']) + origin_url, visit_id, snapshot=data.empty_snapshot['id']) by_id = swh_storage.snapshot_get(data.empty_snapshot['id']) assert by_id == {**data.empty_snapshot, 'next_branch': None} - by_ov = swh_storage.snapshot_get_by_origin_visit(origin_id, visit_id) + by_ov = swh_storage.snapshot_get_by_origin_visit(origin_url, visit_id) assert by_ov == {**data.empty_snapshot, 'next_branch': None} expected_origin = data.origin.copy() data1 = { 'origin': expected_origin, 'date': data.date_visit1, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'ongoing', 'metadata': None, 'snapshot': None, } data2 = { 'origin': expected_origin, 'date': data.date_visit1, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'ongoing', 'metadata': None, 'snapshot': data.empty_snapshot['id'], } assert list(swh_storage.journal_writer.objects) == \ [('origin', expected_origin), ('origin_visit', data1), ('snapshot', data.empty_snapshot), ('origin_visit', data2)] def test_snapshot_add_get_complete(self, swh_storage): - origin_id = swh_storage.origin_add_one(data.origin) + origin_url = data.origin['url'] + swh_storage.origin_add_one(data.origin) origin_visit1 = swh_storage.origin_visit_add( - origin=origin_id, + origin=origin_url, date=data.date_visit1, type=data.type_visit1, ) visit_id = origin_visit1['visit'] actual_result = swh_storage.snapshot_add([data.complete_snapshot]) swh_storage.origin_visit_update( - origin_id, visit_id, snapshot=data.complete_snapshot['id']) + origin_url, visit_id, snapshot=data.complete_snapshot['id']) assert actual_result == {'snapshot:add': 1} by_id = swh_storage.snapshot_get(data.complete_snapshot['id']) assert by_id == {**data.complete_snapshot, 'next_branch': None} - by_ov = swh_storage.snapshot_get_by_origin_visit(origin_id, visit_id) + by_ov = swh_storage.snapshot_get_by_origin_visit(origin_url, visit_id) assert by_ov == {**data.complete_snapshot, 'next_branch': None} def test_snapshot_add_many(self, swh_storage): actual_result = swh_storage.snapshot_add( [data.snapshot, data.complete_snapshot]) assert actual_result == {'snapshot:add': 2} assert {**data.complete_snapshot, 'next_branch': None} \ == swh_storage.snapshot_get(data.complete_snapshot['id']) assert {**data.snapshot, 'next_branch': None} \ == swh_storage.snapshot_get(data.snapshot['id']) def test_snapshot_add_many_incremental(self, swh_storage): actual_result = swh_storage.snapshot_add([data.complete_snapshot]) assert actual_result == {'snapshot:add': 1} actual_result2 = swh_storage.snapshot_add( [data.snapshot, data.complete_snapshot]) assert actual_result2 == {'snapshot:add': 1} assert {**data.complete_snapshot, 'next_branch': None} \ == swh_storage.snapshot_get(data.complete_snapshot['id']) assert {**data.snapshot, 'next_branch': None} \ == swh_storage.snapshot_get(data.snapshot['id']) def test_snapshot_add_twice(self, swh_storage): actual_result = swh_storage.snapshot_add([data.empty_snapshot]) assert actual_result == {'snapshot:add': 1} assert list(swh_storage.journal_writer.objects) \ == [('snapshot', data.empty_snapshot)] actual_result = swh_storage.snapshot_add([data.snapshot]) assert actual_result == {'snapshot:add': 1} assert list(swh_storage.journal_writer.objects) \ == [('snapshot', data.empty_snapshot), ('snapshot', data.snapshot)] def test_snapshot_add_validation(self, swh_storage): snap = copy.deepcopy(data.snapshot) snap['branches'][b'foo'] = {'target_type': 'revision'} with pytest.raises(KeyError, match='target'): swh_storage.snapshot_add([snap]) snap = copy.deepcopy(data.snapshot) snap['branches'][b'foo'] = {'target': b'\x42'*20} with pytest.raises(KeyError, match='target_type'): swh_storage.snapshot_add([snap]) def test_snapshot_add_count_branches(self, swh_storage): actual_result = swh_storage.snapshot_add([data.complete_snapshot]) assert actual_result == {'snapshot:add': 1} snp_id = data.complete_snapshot['id'] snp_size = swh_storage.snapshot_count_branches(snp_id) expected_snp_size = { 'alias': 1, 'content': 1, 'directory': 2, 'release': 1, 'revision': 1, 'snapshot': 1, None: 1 } assert snp_size == expected_snp_size def test_snapshot_add_get_paginated(self, swh_storage): swh_storage.snapshot_add([data.complete_snapshot]) snp_id = data.complete_snapshot['id'] branches = data.complete_snapshot['branches'] branch_names = list(sorted(branches)) # Test branch_from snapshot = swh_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, } assert snapshot == expected_snapshot # Test branches_count snapshot = swh_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', } assert snapshot == expected_snapshot # test branch_from + branches_count snapshot = swh_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], } assert snapshot == expected_snapshot def test_snapshot_add_get_filtered(self, swh_storage): - origin_id = swh_storage.origin_add_one(data.origin) + origin_url = data.origin['url'] + swh_storage.origin_add_one(data.origin) origin_visit1 = swh_storage.origin_visit_add( - origin=origin_id, + origin=origin_url, date=data.date_visit1, type=data.type_visit1, ) visit_id = origin_visit1['visit'] swh_storage.snapshot_add([data.complete_snapshot]) swh_storage.origin_visit_update( - origin_id, visit_id, snapshot=data.complete_snapshot['id']) + origin_url, visit_id, snapshot=data.complete_snapshot['id']) snp_id = data.complete_snapshot['id'] branches = data.complete_snapshot['branches'] snapshot = swh_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, } assert snapshot == expected_snapshot snapshot = swh_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, } assert snapshot == expected_snapshot def test_snapshot_add_get_filtered_and_paginated(self, swh_storage): swh_storage.snapshot_add([data.complete_snapshot]) snp_id = data.complete_snapshot['id'] branches = data.complete_snapshot['branches'] branch_names = list(sorted(branches)) # Test branch_from snapshot = swh_storage.snapshot_get_branches( snp_id, target_types=['directory', 'release'], branches_from=b'directory2') expected_snapshot = { 'id': snp_id, 'branches': { name: branches[name] for name in (b'directory2', b'release') }, 'next_branch': None, } assert snapshot == expected_snapshot # Test branches_count snapshot = swh_storage.snapshot_get_branches( snp_id, target_types=['directory', 'release'], branches_count=1) expected_snapshot = { 'id': snp_id, 'branches': { b'directory': branches[b'directory'] }, 'next_branch': b'directory2', } assert snapshot == expected_snapshot # Test branches_count snapshot = swh_storage.snapshot_get_branches( snp_id, target_types=['directory', 'release'], branches_count=2) expected_snapshot = { 'id': snp_id, 'branches': { name: branches[name] for name in (b'directory', b'directory2') }, 'next_branch': b'release', } assert snapshot == expected_snapshot # test branch_from + branches_count snapshot = swh_storage.snapshot_get_branches( snp_id, target_types=['directory', 'release'], branches_from=b'directory2', branches_count=1) dir_idx = branch_names.index(b'directory2') expected_snapshot = { 'id': snp_id, 'branches': { branch_names[dir_idx]: branches[branch_names[dir_idx]], }, 'next_branch': b'release', } assert snapshot == expected_snapshot def test_snapshot_add_get(self, swh_storage): - origin_id = swh_storage.origin_add_one(data.origin) + origin_url = data.origin['url'] + swh_storage.origin_add_one(data.origin) origin_visit1 = swh_storage.origin_visit_add( - origin=origin_id, + origin=origin_url, date=data.date_visit1, type=data.type_visit1, ) visit_id = origin_visit1['visit'] swh_storage.snapshot_add([data.snapshot]) swh_storage.origin_visit_update( - origin_id, visit_id, snapshot=data.snapshot['id']) + origin_url, visit_id, snapshot=data.snapshot['id']) by_id = swh_storage.snapshot_get(data.snapshot['id']) assert by_id == {**data.snapshot, 'next_branch': None} - by_ov = swh_storage.snapshot_get_by_origin_visit(origin_id, visit_id) + by_ov = swh_storage.snapshot_get_by_origin_visit(origin_url, visit_id) assert by_ov == {**data.snapshot, 'next_branch': None} origin_visit_info = swh_storage.origin_visit_get_by( - origin_id, visit_id) + origin_url, visit_id) assert origin_visit_info['snapshot'] == data.snapshot['id'] def test_snapshot_add_nonexistent_visit(self, swh_storage): - origin_id = swh_storage.origin_add_one(data.origin) + origin_url = data.origin['url'] + swh_storage.origin_add_one(data.origin) visit_id = 54164461156 swh_storage.journal_writer.objects[:] = [] swh_storage.snapshot_add([data.snapshot]) with pytest.raises(ValueError): swh_storage.origin_visit_update( - origin_id, visit_id, snapshot=data.snapshot['id']) + origin_url, visit_id, snapshot=data.snapshot['id']) assert list(swh_storage.journal_writer.objects) == [ ('snapshot', data.snapshot)] def test_snapshot_add_twice__by_origin_visit(self, swh_storage): - origin_id = swh_storage.origin_add_one(data.origin) + origin_url = data.origin['url'] + swh_storage.origin_add_one(data.origin) origin_visit1 = swh_storage.origin_visit_add( - origin=origin_id, + origin=origin_url, date=data.date_visit1, type=data.type_visit1, ) visit1_id = origin_visit1['visit'] swh_storage.snapshot_add([data.snapshot]) swh_storage.origin_visit_update( - origin_id, visit1_id, snapshot=data.snapshot['id']) + origin_url, visit1_id, snapshot=data.snapshot['id']) by_ov1 = swh_storage.snapshot_get_by_origin_visit( - origin_id, visit1_id) + origin_url, visit1_id) assert by_ov1 == {**data.snapshot, 'next_branch': None} origin_visit2 = swh_storage.origin_visit_add( - origin=origin_id, + origin=origin_url, date=data.date_visit2, type=data.type_visit2, ) visit2_id = origin_visit2['visit'] swh_storage.snapshot_add([data.snapshot]) swh_storage.origin_visit_update( - origin_id, visit2_id, snapshot=data.snapshot['id']) + origin_url, visit2_id, snapshot=data.snapshot['id']) by_ov2 = swh_storage.snapshot_get_by_origin_visit( - origin_id, visit2_id) + origin_url, visit2_id) assert by_ov2 == {**data.snapshot, 'next_branch': None} expected_origin = data.origin.copy() data1 = { 'origin': expected_origin, 'date': data.date_visit1, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'ongoing', 'metadata': None, 'snapshot': None, } data2 = { 'origin': expected_origin, 'date': data.date_visit1, 'visit': origin_visit1['visit'], 'type': data.type_visit1, 'status': 'ongoing', 'metadata': None, 'snapshot': data.snapshot['id'], } data3 = { 'origin': expected_origin, 'date': data.date_visit2, 'visit': origin_visit2['visit'], 'type': data.type_visit2, 'status': 'ongoing', 'metadata': None, 'snapshot': None, } data4 = { 'origin': expected_origin, 'date': data.date_visit2, 'visit': origin_visit2['visit'], 'type': data.type_visit2, 'status': 'ongoing', 'metadata': None, 'snapshot': data.snapshot['id'], } assert list(swh_storage.journal_writer.objects) \ == [('origin', expected_origin), ('origin_visit', data1), ('snapshot', data.snapshot), ('origin_visit', data2), ('origin_visit', data3), ('origin_visit', data4)] - @pytest.mark.parametrize('use_url', [True, False]) - def test_snapshot_get_latest(self, swh_storage, use_url): - if not self._test_origin_ids and not use_url: - return - origin_id = swh_storage.origin_add_one(data.origin) + def test_snapshot_get_latest(self, swh_storage): + origin_url = data.origin['url'] + swh_storage.origin_add_one(data.origin) origin_url = data.origin['url'] origin_visit1 = swh_storage.origin_visit_add( - origin=origin_id, + origin=origin_url, date=data.date_visit1, type=data.type_visit1, ) visit1_id = origin_visit1['visit'] origin_visit2 = swh_storage.origin_visit_add( - origin=origin_id, + origin=origin_url, date=data.date_visit2, type=data.type_visit2, ) visit2_id = origin_visit2['visit'] # Add a visit with the same date as the previous one origin_visit3 = swh_storage.origin_visit_add( - origin=origin_id, + origin=origin_url, date=data.date_visit2, type=data.type_visit3, ) visit3_id = origin_visit3['visit'] # Two visits, both with no snapshot: latest snapshot is None assert swh_storage.snapshot_get_latest(origin_url) is None # Add snapshot to visit1, latest snapshot = visit 1 snapshot swh_storage.snapshot_add([data.complete_snapshot]) swh_storage.origin_visit_update( - origin_id, visit1_id, snapshot=data.complete_snapshot['id']) + origin_url, visit1_id, snapshot=data.complete_snapshot['id']) assert {**data.complete_snapshot, 'next_branch': None} \ == swh_storage.snapshot_get_latest(origin_url) # Status filter: all three visits are status=ongoing, so no snapshot # returned assert swh_storage.snapshot_get_latest( origin_url, allowed_statuses=['full']) is None # Mark the first visit as completed and check status filter again - swh_storage.origin_visit_update(origin_id, visit1_id, status='full') + swh_storage.origin_visit_update(origin_url, visit1_id, status='full') assert {**data.complete_snapshot, 'next_branch': None} \ == swh_storage.snapshot_get_latest( origin_url, allowed_statuses=['full']) # Add snapshot to visit2 and check that the new snapshot is returned swh_storage.snapshot_add([data.empty_snapshot]) swh_storage.origin_visit_update( - origin_id, visit2_id, snapshot=data.empty_snapshot['id']) + origin_url, visit2_id, snapshot=data.empty_snapshot['id']) assert {**data.empty_snapshot, 'next_branch': None} \ - == swh_storage.snapshot_get_latest(origin_id) + == swh_storage.snapshot_get_latest(origin_url) # Check that the status filter is still working assert {**data.complete_snapshot, 'next_branch': None} \ == swh_storage.snapshot_get_latest( origin_url, allowed_statuses=['full']) # Add snapshot to visit3 (same date as visit2) and check that # the new snapshot is returned swh_storage.snapshot_add([data.complete_snapshot]) swh_storage.origin_visit_update( - origin_id, visit3_id, snapshot=data.complete_snapshot['id']) + origin_url, visit3_id, snapshot=data.complete_snapshot['id']) assert {**data.complete_snapshot, 'next_branch': None} \ == swh_storage.snapshot_get_latest(origin_url) - @pytest.mark.parametrize('use_url', [True, False]) - def test_snapshot_get_latest__missing_snapshot(self, swh_storage, use_url): - if not self._test_origin_ids and not use_url: - return + def test_snapshot_get_latest__missing_snapshot(self, swh_storage): # Origin does not exist origin_url = data.origin['url'] assert swh_storage.snapshot_get_latest(origin_url) is None swh_storage.origin_add_one(data.origin) origin_visit1 = swh_storage.origin_visit_add( origin=origin_url, date=data.date_visit1, type=data.type_visit1, ) visit1_id = origin_visit1['visit'] origin_visit2 = swh_storage.origin_visit_add( origin=origin_url, date=data.date_visit2, type=data.type_visit2, ) visit2_id = origin_visit2['visit'] # Two visits, both with no snapshot: latest snapshot is None assert swh_storage.snapshot_get_latest(origin_url) is None # Add unknown snapshot to visit1, check that the inconsistency is # detected swh_storage.origin_visit_update( origin_url, visit1_id, snapshot=data.complete_snapshot['id']) with pytest.raises(ValueError): swh_storage.snapshot_get_latest( origin_url) # Status filter: both visits are status=ongoing, so no snapshot # returned assert swh_storage.snapshot_get_latest( origin_url, allowed_statuses=['full']) is None # Mark the first visit as completed and check status filter again swh_storage.origin_visit_update( origin_url, visit1_id, status='full') with pytest.raises(ValueError): swh_storage.snapshot_get_latest( origin_url, allowed_statuses=['full']), # Actually add the snapshot and check status filter again swh_storage.snapshot_add([data.complete_snapshot]) assert {**data.complete_snapshot, 'next_branch': None} \ == swh_storage.snapshot_get_latest(origin_url) # Add unknown snapshot to visit2 and check that the inconsistency # is detected swh_storage.origin_visit_update( origin_url, visit2_id, snapshot=data.snapshot['id']) with pytest.raises(ValueError): swh_storage.snapshot_get_latest( origin_url) # Actually add that snapshot and check that the new one is returned swh_storage.snapshot_add([data.snapshot]) assert{**data.snapshot, 'next_branch': None} \ == swh_storage.snapshot_get_latest(origin_url) def test_stat_counters(self, swh_storage): expected_keys = ['content', 'directory', 'origin', 'revision'] # Initially, all counters are 0 swh_storage.refresh_stat_counters() counters = swh_storage.stat_counters() assert set(expected_keys) <= set(counters) for key in expected_keys: assert counters[key] == 0 # Add a content. Only the content counter should increase. swh_storage.content_add([data.cont]) swh_storage.refresh_stat_counters() counters = swh_storage.stat_counters() assert set(expected_keys) <= set(counters) for key in expected_keys: if key != 'content': assert counters[key] == 0 assert counters['content'] == 1 # Add other objects. Check their counter increased as well. swh_storage.origin_add_one(data.origin2) origin_visit1 = swh_storage.origin_visit_add( origin=data.origin2['url'], date=data.date_visit2, type=data.type_visit2, ) swh_storage.snapshot_add([data.snapshot]) swh_storage.origin_visit_update( data.origin2['url'], origin_visit1['visit'], snapshot=data.snapshot['id']) swh_storage.directory_add([data.dir]) swh_storage.revision_add([data.revision]) swh_storage.release_add([data.release]) swh_storage.refresh_stat_counters() counters = swh_storage.stat_counters() assert counters['content'] == 1 assert counters['directory'] == 1 assert counters['snapshot'] == 1 assert counters['origin'] == 1 assert counters['origin_visit'] == 1 assert counters['revision'] == 1 assert counters['release'] == 1 assert counters['snapshot'] == 1 if 'person' in counters: assert counters['person'] == 3 def test_content_find_ctime(self, swh_storage): cont = data.cont.copy() del cont['data'] now = datetime.datetime.now(tz=datetime.timezone.utc) cont['ctime'] = now swh_storage.content_add_metadata([cont]) actually_present = swh_storage.content_find({'sha1': cont['sha1']}) # check ctime up to one second dt = actually_present[0]['ctime'] - now assert abs(dt.total_seconds()) <= 1 del actually_present[0]['ctime'] assert actually_present[0] == { 'sha1': cont['sha1'], 'sha256': cont['sha256'], 'sha1_git': cont['sha1_git'], 'blake2s256': cont['blake2s256'], 'length': cont['length'], 'status': 'visible' } def test_content_find_with_present_content(self, swh_storage): # 1. with something to find cont = data.cont swh_storage.content_add([cont, data.cont2]) actually_present = swh_storage.content_find( {'sha1': cont['sha1']} ) assert 1 == len(actually_present) actually_present[0].pop('ctime') assert actually_present[0] == { '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 = swh_storage.content_find( {'sha1_git': cont['sha1_git']}) assert 1 == len(actually_present) actually_present[0].pop('ctime') assert actually_present[0] == { '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 = swh_storage.content_find( {'sha256': cont['sha256']}) assert 1 == len(actually_present) actually_present[0].pop('ctime') assert actually_present[0] == { '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 = swh_storage.content_find({ 'sha1': cont['sha1'], 'sha1_git': cont['sha1_git'], 'sha256': cont['sha256'], 'blake2s256': cont['blake2s256'], }) assert 1 == len(actually_present) actually_present[0].pop('ctime') assert actually_present[0] == { '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, swh_storage): # 1. with something that does not exist missing_cont = data.missing_cont actually_present = swh_storage.content_find( {'sha1': missing_cont['sha1']}) assert actually_present == [] # 2. with something that does not exist actually_present = swh_storage.content_find( {'sha1_git': missing_cont['sha1_git']}) assert actually_present == [] # 3. with something that does not exist actually_present = swh_storage.content_find( {'sha256': missing_cont['sha256']}) assert actually_present == [] def test_content_find_with_duplicate_input(self, swh_storage): cont1 = data.cont duplicate_cont = cont1.copy() # Create fake data with colliding sha256 and blake2s256 sha1_array = bytearray(duplicate_cont['sha1']) sha1_array[0] += 1 duplicate_cont['sha1'] = bytes(sha1_array) sha1git_array = bytearray(duplicate_cont['sha1_git']) sha1git_array[0] += 1 duplicate_cont['sha1_git'] = bytes(sha1git_array) # Inject the data swh_storage.content_add([cont1, duplicate_cont]) finder = {'blake2s256': duplicate_cont['blake2s256'], 'sha256': duplicate_cont['sha256']} actual_result = list(swh_storage.content_find(finder)) cont1.pop('data') duplicate_cont.pop('data') actual_result[0].pop('ctime') actual_result[1].pop('ctime') expected_result = [ cont1, duplicate_cont ] for result in expected_result: assert result in actual_result def test_content_find_with_duplicate_sha256(self, swh_storage): cont1 = data.cont duplicate_cont = cont1.copy() # Create fake data with colliding sha256 for hashalgo in ('sha1', 'sha1_git', 'blake2s256'): value = bytearray(duplicate_cont[hashalgo]) value[0] += 1 duplicate_cont[hashalgo] = bytes(value) swh_storage.content_add([cont1, duplicate_cont]) finder = { 'sha256': duplicate_cont['sha256'] } actual_result = list(swh_storage.content_find(finder)) assert len(actual_result) == 2 cont1.pop('data') duplicate_cont.pop('data') actual_result[0].pop('ctime') actual_result[1].pop('ctime') expected_result = [ cont1, duplicate_cont ] assert expected_result == sorted(actual_result, key=lambda x: x['sha1']) # Find with both sha256 and blake2s256 finder = { 'sha256': duplicate_cont['sha256'], 'blake2s256': duplicate_cont['blake2s256'] } actual_result = list(swh_storage.content_find(finder)) assert len(actual_result) == 1 actual_result[0].pop('ctime') expected_result = [duplicate_cont] assert actual_result[0] == duplicate_cont def test_content_find_with_duplicate_blake2s256(self, swh_storage): cont1 = data.cont duplicate_cont = cont1.copy() # Create fake data with colliding sha256 and blake2s256 sha1_array = bytearray(duplicate_cont['sha1']) sha1_array[0] += 1 duplicate_cont['sha1'] = bytes(sha1_array) sha1git_array = bytearray(duplicate_cont['sha1_git']) sha1git_array[0] += 1 duplicate_cont['sha1_git'] = bytes(sha1git_array) sha256_array = bytearray(duplicate_cont['sha256']) sha256_array[0] += 1 duplicate_cont['sha256'] = bytes(sha256_array) swh_storage.content_add([cont1, duplicate_cont]) finder = { 'blake2s256': duplicate_cont['blake2s256'] } actual_result = list(swh_storage.content_find(finder)) cont1.pop('data') duplicate_cont.pop('data') actual_result[0].pop('ctime') actual_result[1].pop('ctime') expected_result = [ cont1, duplicate_cont ] for result in expected_result: assert result in actual_result # Find with both sha256 and blake2s256 finder = { 'sha256': duplicate_cont['sha256'], 'blake2s256': duplicate_cont['blake2s256'] } actual_result = list(swh_storage.content_find(finder)) actual_result[0].pop('ctime') expected_result = [ duplicate_cont ] assert expected_result == actual_result def test_content_find_bad_input(self, swh_storage): # 1. with bad input with pytest.raises(ValueError): swh_storage.content_find({}) # empty is bad # 2. with bad input with pytest.raises(ValueError): swh_storage.content_find( {'unknown-sha1': 'something'}) # not the right key def test_object_find_by_sha1_git(self, swh_storage): sha1_gits = [b'00000000000000000000'] expected = { b'00000000000000000000': [], } swh_storage.content_add([data.cont]) sha1_gits.append(data.cont['sha1_git']) expected[data.cont['sha1_git']] = [{ 'sha1_git': data.cont['sha1_git'], 'type': 'content', 'id': data.cont['sha1'], }] swh_storage.directory_add([data.dir]) sha1_gits.append(data.dir['id']) expected[data.dir['id']] = [{ 'sha1_git': data.dir['id'], 'type': 'directory', 'id': data.dir['id'], }] swh_storage.revision_add([data.revision]) sha1_gits.append(data.revision['id']) expected[data.revision['id']] = [{ 'sha1_git': data.revision['id'], 'type': 'revision', 'id': data.revision['id'], }] swh_storage.release_add([data.release]) sha1_gits.append(data.release['id']) expected[data.release['id']] = [{ 'sha1_git': data.release['id'], 'type': 'release', 'id': data.release['id'], }] ret = swh_storage.object_find_by_sha1_git(sha1_gits) for val in ret.values(): for obj in val: if 'object_id' in obj: del obj['object_id'] assert expected == ret def test_tool_add(self, swh_storage): tool = { 'name': 'some-unknown-tool', 'version': 'some-version', 'configuration': {"debian-package": "some-package"}, } actual_tool = swh_storage.tool_get(tool) assert actual_tool is None # does not exist # add it actual_tools = swh_storage.tool_add([tool]) assert len(actual_tools) == 1 actual_tool = actual_tools[0] assert actual_tool is not None # now it exists new_id = actual_tool.pop('id') assert actual_tool == tool actual_tools2 = swh_storage.tool_add([tool]) actual_tool2 = actual_tools2[0] assert actual_tool2 is not None # now it exists new_id2 = actual_tool2.pop('id') assert new_id == new_id2 assert actual_tool == actual_tool2 def test_tool_add_multiple(self, swh_storage): tool = { 'name': 'some-unknown-tool', 'version': 'some-version', 'configuration': {"debian-package": "some-package"}, } actual_tools = list(swh_storage.tool_add([tool])) assert len(actual_tools) == 1 new_tools = [tool, { 'name': 'yet-another-tool', 'version': 'version', 'configuration': {}, }] actual_tools = swh_storage.tool_add(new_tools) assert len(actual_tools) == 2 # order not guaranteed, so we iterate over results to check for tool in actual_tools: _id = tool.pop('id') assert _id is not None assert tool in new_tools def test_tool_get_missing(self, swh_storage): tool = { 'name': 'unknown-tool', 'version': '3.1.0rc2-31-ga2cbb8c', 'configuration': {"command_line": "nomossa "}, } actual_tool = swh_storage.tool_get(tool) assert actual_tool is None def test_tool_metadata_get_missing_context(self, swh_storage): tool = { 'name': 'swh-metadata-translator', 'version': '0.0.1', 'configuration': {"context": "unknown-context"}, } actual_tool = swh_storage.tool_get(tool) assert actual_tool is None def test_tool_metadata_get(self, swh_storage): tool = { 'name': 'swh-metadata-translator', 'version': '0.0.1', 'configuration': {"type": "local", "context": "npm"}, } expected_tool = swh_storage.tool_add([tool])[0] # when actual_tool = swh_storage.tool_get(tool) # then assert expected_tool == actual_tool def test_metadata_provider_get(self, swh_storage): # given no_provider = swh_storage.metadata_provider_get(6459456445615) assert no_provider is None # when provider_id = swh_storage.metadata_provider_add( data.provider['name'], data.provider['type'], data.provider['url'], data.provider['metadata']) actual_provider = swh_storage.metadata_provider_get(provider_id) expected_provider = { 'provider_name': data.provider['name'], 'provider_url': data.provider['url'] } # then del actual_provider['id'] assert actual_provider, expected_provider def test_metadata_provider_get_by(self, swh_storage): # given no_provider = swh_storage.metadata_provider_get_by({ 'provider_name': data.provider['name'], 'provider_url': data.provider['url'] }) assert no_provider is None # when provider_id = swh_storage.metadata_provider_add( data.provider['name'], data.provider['type'], data.provider['url'], data.provider['metadata']) actual_provider = swh_storage.metadata_provider_get_by({ 'provider_name': data.provider['name'], 'provider_url': data.provider['url'] }) # then assert provider_id, actual_provider['id'] - @pytest.mark.parametrize('use_url', [True, False]) - def test_origin_metadata_add(self, swh_storage, use_url): - if not self._test_origin_ids: - pytest.skip('requires origin id') - + def test_origin_metadata_add(self, swh_storage): # given - origin = swh_storage.origin_add([data.origin])[0] + origin = data.origin + swh_storage.origin_add([origin])[0] tools = swh_storage.tool_add([data.metadata_tool]) tool = tools[0] swh_storage.metadata_provider_add( data.provider['name'], data.provider['type'], data.provider['url'], data.provider['metadata']) provider = swh_storage.metadata_provider_get_by({ 'provider_name': data.provider['name'], 'provider_url': data.provider['url'] }) # when adding for the same origin 2 metadatas - origin = origin['url' if use_url else 'id'] - - n_om = len(list(swh_storage.origin_metadata_get_by(origin))) + n_om = len(list(swh_storage.origin_metadata_get_by(origin['url']))) swh_storage.origin_metadata_add( - origin, + origin['url'], data.origin_metadata['discovery_date'], provider['id'], tool['id'], data.origin_metadata['metadata']) swh_storage.origin_metadata_add( - origin, + origin['url'], '2015-01-01 23:00:00+00', provider['id'], tool['id'], data.origin_metadata2['metadata']) - n_actual_om = len(list(swh_storage.origin_metadata_get_by(origin))) + n_actual_om = len(list( + swh_storage.origin_metadata_get_by(origin['url']))) # then assert n_actual_om == n_om + 2 def test_origin_metadata_get(self, swh_storage): - if not self._test_origin_ids: - pytest.skip('requires origin id') - # given - origin_id = swh_storage.origin_add([data.origin])[0]['id'] - origin_id2 = swh_storage.origin_add([data.origin2])[0]['id'] + origin_url = data.origin['url'] + origin_url2 = data.origin2['url'] + swh_storage.origin_add([data.origin]) + swh_storage.origin_add([data.origin2]) swh_storage.metadata_provider_add(data.provider['name'], data.provider['type'], data.provider['url'], data.provider['metadata']) provider = swh_storage.metadata_provider_get_by({ 'provider_name': data.provider['name'], 'provider_url': data.provider['url'] }) tool = swh_storage.tool_add([data.metadata_tool])[0] # when adding for the same origin 2 metadatas swh_storage.origin_metadata_add( - origin_id, + origin_url, data.origin_metadata['discovery_date'], provider['id'], tool['id'], data.origin_metadata['metadata']) swh_storage.origin_metadata_add( - origin_id2, + origin_url2, data.origin_metadata2['discovery_date'], provider['id'], tool['id'], data.origin_metadata2['metadata']) swh_storage.origin_metadata_add( - origin_id, + origin_url, data.origin_metadata2['discovery_date'], provider['id'], tool['id'], data.origin_metadata2['metadata']) all_metadatas = list(sorted(swh_storage.origin_metadata_get_by( - origin_id), key=lambda x: x['discovery_date'])) + origin_url), key=lambda x: x['discovery_date'])) metadatas_for_origin2 = list(swh_storage.origin_metadata_get_by( - origin_id2)) + origin_url2)) expected_results = [{ - 'origin_id': origin_id, + 'origin_url': origin_url, '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'] }, { - 'origin_id': origin_id, + 'origin_url': origin_url, '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'] }] # then assert len(all_metadatas) == 2 assert len(metadatas_for_origin2) == 1 assert all_metadatas == expected_results def test_metadata_provider_add(self, swh_storage): provider = { 'provider_name': 'swMATH', 'provider_type': 'registry', 'provider_url': 'http://www.swmath.org/', 'metadata': { 'email': 'contact@swmath.org', 'license': 'All rights reserved' } } provider['id'] = provider_id = swh_storage.metadata_provider_add( **provider) assert provider == swh_storage.metadata_provider_get_by( {'provider_name': 'swMATH', 'provider_url': 'http://www.swmath.org/'}) assert provider == swh_storage.metadata_provider_get(provider_id) def test_origin_metadata_get_by_provider_type(self, swh_storage): # given - if not self._test_origin_ids: - pytest.skip('reauires origin id') - - origin_id = swh_storage.origin_add([data.origin])[0]['id'] - origin_id2 = swh_storage.origin_add([data.origin2])[0]['id'] + origin_url = data.origin['url'] + origin_url2 = data.origin2['url'] + swh_storage.origin_add([data.origin]) + swh_storage.origin_add([data.origin2]) provider1_id = swh_storage.metadata_provider_add( data.provider['name'], data.provider['type'], data.provider['url'], data.provider['metadata']) provider1 = swh_storage.metadata_provider_get_by({ 'provider_name': data.provider['name'], 'provider_url': data.provider['url'] }) assert provider1 == swh_storage.metadata_provider_get(provider1_id) provider2_id = swh_storage.metadata_provider_add( 'swMATH', 'registry', 'http://www.swmath.org/', {'email': 'contact@swmath.org', 'license': 'All rights reserved'}) provider2 = swh_storage.metadata_provider_get_by({ 'provider_name': 'swMATH', 'provider_url': 'http://www.swmath.org/' }) assert provider2 == swh_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 = swh_storage.tool_add([data.metadata_tool])[0] # when adding for the same origin 2 metadatas swh_storage.origin_metadata_add( - origin_id, + origin_url, data.origin_metadata['discovery_date'], provider1['id'], tool['id'], data.origin_metadata['metadata']) swh_storage.origin_metadata_add( - origin_id2, + origin_url2, data.origin_metadata2['discovery_date'], provider2['id'], tool['id'], data.origin_metadata2['metadata']) provider_type = 'registry' m_by_provider = list(swh_storage.origin_metadata_get_by( - origin_id2, + origin_url2, provider_type)) for item in m_by_provider: if 'id' in item: del item['id'] expected_results = [{ - 'origin_id': origin_id2, + 'origin_url': origin_url2, '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 assert len(m_by_provider) == 1 assert m_by_provider == expected_results class TestStorageGeneratedData: - _test_origin_ids = True - 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 = set([c.get(k) for c in expected_contents]) actual_list = set([c.get(k) for c in actual_contents]) assert actual_list == expected_list, k def test_generate_content_get(self, swh_storage, swh_contents): contents_with_data = [c for c in swh_contents if c['status'] != 'absent'] # input the list of sha1s we want from storage get_sha1s = [c['sha1'] for c in contents_with_data] # retrieve contents actual_contents = list(swh_storage.content_get(get_sha1s)) assert None not in actual_contents self.assert_contents_ok(contents_with_data, actual_contents) def test_generate_content_get_metadata(self, swh_storage, swh_contents): # input the list of sha1s we want from storage expected_contents = [c for c in swh_contents if c['status'] != 'absent'] get_sha1s = [c['sha1'] for c in expected_contents] # retrieve contents actual_contents = list(swh_storage.content_get_metadata(get_sha1s)) assert len(actual_contents) == len(get_sha1s) keys_to_check = {'length', 'status', 'sha1', 'sha1_git', 'sha256', 'blake2s256'} self.assert_contents_ok(expected_contents, actual_contents, keys_to_check=keys_to_check) def test_generate_content_get_range(self, swh_storage, swh_contents): """content_get_range paginates results if limit exceeded""" # add contents to storage present_contents = [c for c in swh_contents if c['status'] != 'absent'] get_sha1s = sorted([c['sha1'] for c in swh_contents if c['status'] != 'absent']) start = get_sha1s[2] end = get_sha1s[-2] actual_result = swh_storage.content_get_range(start, end) assert actual_result['next'] is None actual_contents = actual_result['contents'] expected_contents = [c for c in present_contents if start <= c['sha1'] <= end] if expected_contents: self.assert_contents_ok( expected_contents, actual_contents, ['sha1']) else: assert actual_contents == [] def test_generate_content_get_range_full(self, swh_storage, swh_contents): """content_get_range for a full range returns all available contents""" present_contents = [c for c in swh_contents if c['status'] != 'absent'] start = b'0' * 40 end = b'f' * 40 actual_result = swh_storage.content_get_range(start, end) assert actual_result['next'] is None actual_contents = actual_result['contents'] expected_contents = [c for c in present_contents if start <= c['sha1'] <= end] if expected_contents: self.assert_contents_ok( expected_contents, actual_contents, ['sha1']) else: assert actual_contents == [] def test_generate_content_get_range_empty(self, swh_storage, swh_contents): """content_get_range for an empty range returns nothing""" start = b'0' * 40 end = b'f' * 40 actual_result = swh_storage.content_get_range(end, start) assert actual_result['next'] is None assert len(actual_result['contents']) == 0 def test_generate_content_get_range_limit_none(self, swh_storage): """content_get_range call with wrong limit input should fail""" with pytest.raises(ValueError) as e: swh_storage.content_get_range(start=None, end=None, limit=None) assert e.value.args == ('Development error: limit should not be None',) def test_generate_content_get_range_no_limit( self, swh_storage, swh_contents): """content_get_range returns contents within range provided""" # add contents to storage # input the list of sha1s we want from storage get_sha1s = sorted([c['sha1'] for c in swh_contents if c['status'] != 'absent']) start = get_sha1s[0] end = get_sha1s[-1] # retrieve contents actual_result = swh_storage.content_get_range(start, end) actual_contents = actual_result['contents'] assert actual_result['next'] is None assert len(actual_contents) == len(get_sha1s) expected_contents = [c for c in swh_contents if c['status'] != 'absent'] self.assert_contents_ok( expected_contents, actual_contents, ['sha1']) def test_generate_content_get_range_limit(self, swh_storage, swh_contents): """content_get_range paginates results if limit exceeded""" contents_map = {c['sha1']: c for c in swh_contents} # input the list of sha1s we want from storage get_sha1s = sorted([c['sha1'] for c in swh_contents if c['status'] != 'absent']) start = get_sha1s[0] end = get_sha1s[-1] # retrieve contents limited to n-1 results limited_results = len(get_sha1s) - 1 actual_result = swh_storage.content_get_range( start, end, limit=limited_results) actual_contents = actual_result['contents'] assert actual_result['next'] == get_sha1s[-1] assert len(actual_contents) == limited_results expected_contents = [contents_map[sha1] for sha1 in get_sha1s[:-1]] self.assert_contents_ok( expected_contents, actual_contents, ['sha1']) # retrieve next part actual_results2 = swh_storage.content_get_range(start=end, end=end) assert actual_results2['next'] is None actual_contents2 = actual_results2['contents'] assert len(actual_contents2) == 1 self.assert_contents_ok( [contents_map[get_sha1s[-1]]], actual_contents2, ['sha1']) - def test_origin_get_invalid_id_legacy(self, swh_storage): - if self._test_origin_ids: - invalid_origin_id = 1 - origin_info = swh_storage.origin_get({'id': invalid_origin_id}) - assert origin_info is None - - origin_visits = list(swh_storage.origin_visit_get( - invalid_origin_id)) - assert origin_visits == [] - - def test_origin_get_invalid_id(self, swh_storage): - if self._test_origin_ids: - origin_info = swh_storage.origin_get([{'id': 1}, {'id': 2}]) - assert origin_info == [None, None] - - origin_visits = list(swh_storage.origin_visit_get(1)) - assert origin_visits == [] - def test_origin_get_range(self, swh_storage, swh_origins): - if not self._test_origin_ids: - pytest.skip('requires origin id') - actual_origins = list( swh_storage.origin_get_range(origin_from=0, origin_count=0)) assert len(actual_origins) == 0 actual_origins = list( swh_storage.origin_get_range(origin_from=0, origin_count=1)) assert len(actual_origins) == 1 assert actual_origins[0]['id'] == 1 + assert actual_origins[0]['url'] == swh_origins[0]['url'] actual_origins = list( swh_storage.origin_get_range(origin_from=1, origin_count=1)) assert len(actual_origins) == 1 assert actual_origins[0]['id'] == 1 + assert actual_origins[0]['url'] == swh_origins[0]['url'] actual_origins = list( swh_storage.origin_get_range(origin_from=1, origin_count=10)) assert len(actual_origins) == 10 assert actual_origins[0]['id'] == 1 + assert actual_origins[0]['url'] == swh_origins[0]['url'] assert actual_origins[-1]['id'] == 10 + assert actual_origins[-1]['url'] == swh_origins[9]['url'] actual_origins = list( swh_storage.origin_get_range(origin_from=1, origin_count=20)) assert len(actual_origins) == 20 assert actual_origins[0]['id'] == 1 + assert actual_origins[0]['url'] == swh_origins[0]['url'] assert actual_origins[-1]['id'] == 20 + assert actual_origins[-1]['url'] == swh_origins[19]['url'] actual_origins = list( swh_storage.origin_get_range(origin_from=1, origin_count=101)) assert len(actual_origins) == 100 assert actual_origins[0]['id'] == 1 + assert actual_origins[0]['url'] == swh_origins[0]['url'] assert actual_origins[-1]['id'] == 100 + assert actual_origins[-1]['url'] == swh_origins[99]['url'] actual_origins = list( swh_storage.origin_get_range(origin_from=11, origin_count=0)) assert len(actual_origins) == 0 actual_origins = list( swh_storage.origin_get_range(origin_from=11, origin_count=10)) assert len(actual_origins) == 10 assert actual_origins[0]['id'] == 11 + assert actual_origins[0]['url'] == swh_origins[10]['url'] assert actual_origins[-1]['id'] == 20 + assert actual_origins[-1]['url'] == swh_origins[19]['url'] actual_origins = list( swh_storage.origin_get_range(origin_from=91, origin_count=11)) assert len(actual_origins) == 10 assert actual_origins[0]['id'] == 91 assert actual_origins[-1]['id'] == 100 + assert actual_origins[0]['id'] == 91 + assert actual_origins[0]['url'] == swh_origins[90]['url'] + assert actual_origins[-1]['id'] == 100 + assert actual_origins[-1]['url'] == swh_origins[99]['url'] def test_origin_count(self, swh_storage): 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' } ] swh_storage.origin_add(new_origins) assert swh_storage.origin_count('github') == 3 assert swh_storage.origin_count('gitlab') == 2 assert swh_storage.origin_count('.*user.*', regexp=True) == 5 assert swh_storage.origin_count('.*user.*', regexp=False) == 0 assert swh_storage.origin_count('.*user1.*', regexp=True) == 2 assert swh_storage.origin_count('.*user1.*', regexp=False) == 0 @settings(suppress_health_check=[HealthCheck.too_slow]) @given(strategies.lists(objects(), max_size=2)) def test_add_arbitrary(self, swh_storage, objects): for (obj_type, obj) in objects: obj = obj.to_dict() if obj_type == 'origin_visit': - origin_id = swh_storage.origin_add_one(obj.pop('origin')) + origin = obj.pop('origin') + swh_storage.origin_add_one(origin) if 'visit' in obj: del obj['visit'] swh_storage.origin_visit_add( - origin_id, obj['date'], obj['type']) + origin['url'], obj['date'], obj['type']) else: method = getattr(swh_storage, obj_type + '_add') try: method([obj]) except HashCollision: pass @pytest.mark.db class TestLocalStorage: """Test the local storage""" - _test_origin_ids = True - # This test is only relevant on the local storage, with an actual # objstorage raising an exception def test_content_add_objstorage_exception(self, swh_storage): swh_storage.objstorage.add = Mock( side_effect=Exception('mocked broken objstorage') ) with pytest.raises(Exception) as e: swh_storage.content_add([data.cont]) assert e.value.args == ('mocked broken objstorage',) missing = list(swh_storage.content_missing([data.cont])) assert missing == [data.cont['sha1']] @pytest.mark.db class TestStorageRaceConditions: @pytest.mark.xfail def test_content_add_race(self, swh_storage): results = queue.Queue() def thread(): try: with db_transaction(swh_storage) as (db, cur): ret = swh_storage.content_add([data.cont], db=db, cur=cur) results.put((threading.get_ident(), 'data', ret)) except Exception as e: results.put((threading.get_ident(), 'exc', e)) t1 = threading.Thread(target=thread) t2 = threading.Thread(target=thread) t1.start() # this avoids the race condition # import time # time.sleep(1) t2.start() t1.join() t2.join() r1 = results.get(block=False) r2 = results.get(block=False) with pytest.raises(queue.Empty): results.get(block=False) assert r1[0] != r2[0] assert r1[1] == 'data', 'Got exception %r in Thread%s' % (r1[2], r1[0]) assert r2[1] == 'data', 'Got exception %r in Thread%s' % (r2[2], r2[0]) @pytest.mark.db class TestPgStorage: """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, swh_storage): swh_storage.journal_writer = None # TODO, not supported cont = copy.deepcopy(data.cont) swh_storage.content_add([cont]) # alter the sha1_git for example cont['sha1_git'] = hash_to_bytes( '3a60a5275d0333bf13468e8b3dcab90f4046e654') swh_storage.content_update([cont], keys=['sha1_git']) with db_transaction(swh_storage) as (_, cur): cur.execute('SELECT sha1, sha1_git, sha256, length, status' ' FROM content WHERE sha1 = %s', (cont['sha1'],)) datum = cur.fetchone() assert datum == (cont['sha1'], cont['sha1_git'], cont['sha256'], cont['length'], 'visible') def test_content_update_with_new_cols(self, swh_storage): swh_storage.journal_writer = None # TODO, not supported with db_transaction(swh_storage) as (_, cur): cur.execute("""alter table content add column test text default null, add column test2 text default null""") cont = copy.deepcopy(data.cont2) swh_storage.content_add([cont]) cont['test'] = 'value-1' cont['test2'] = 'value-2' swh_storage.content_update([cont], keys=['test', 'test2']) with db_transaction(swh_storage) as (_, cur): cur.execute( '''SELECT sha1, sha1_git, sha256, length, status, test, test2 FROM content WHERE sha1 = %s''', (cont['sha1'],)) datum = cur.fetchone() assert datum == (cont['sha1'], cont['sha1_git'], cont['sha256'], cont['length'], 'visible', cont['test'], cont['test2']) with db_transaction(swh_storage) as (_, cur): cur.execute("""alter table content drop column test, drop column test2""") def test_content_add_db(self, swh_storage): cont = data.cont actual_result = swh_storage.content_add([cont]) assert actual_result == { 'content:add': 1, 'content:add:bytes': cont['length'], 'skipped_content:add': 0 } if hasattr(swh_storage, 'objstorage'): assert cont['sha1'] in swh_storage.objstorage with db_transaction(swh_storage) as (_, cur): cur.execute('SELECT sha1, sha1_git, sha256, length, status' ' FROM content WHERE sha1 = %s', (cont['sha1'],)) datum = cur.fetchone() assert datum == (cont['sha1'], cont['sha1_git'], cont['sha256'], cont['length'], 'visible') expected_cont = cont.copy() del expected_cont['data'] journal_objects = list(swh_storage.journal_writer.objects) for (obj_type, obj) in journal_objects: del obj['ctime'] assert journal_objects == [('content', expected_cont)] def test_content_add_metadata_db(self, swh_storage): cont = data.cont del cont['data'] cont['ctime'] = datetime.datetime.now() actual_result = swh_storage.content_add_metadata([cont]) assert actual_result == { 'content:add': 1, 'skipped_content:add': 0 } if hasattr(swh_storage, 'objstorage'): assert cont['sha1'] not in swh_storage.objstorage with db_transaction(swh_storage) as (_, cur): cur.execute('SELECT sha1, sha1_git, sha256, length, status' ' FROM content WHERE sha1 = %s', (cont['sha1'],)) datum = cur.fetchone() assert datum == (cont['sha1'], cont['sha1_git'], cont['sha256'], cont['length'], 'visible') assert list(swh_storage.journal_writer.objects) == [('content', cont)] def test_skipped_content_add_db(self, swh_storage): cont = data.skipped_cont cont2 = data.skipped_cont2 cont2['blake2s256'] = None actual_result = swh_storage.content_add([cont, cont, cont2]) assert actual_result == { 'content:add': 0, 'content:add:bytes': 0, 'skipped_content:add': 2, } with db_transaction(swh_storage) as (_, cur): cur.execute('SELECT sha1, sha1_git, sha256, blake2s256, ' 'length, status, reason ' 'FROM skipped_content ORDER BY sha1_git') dbdata = cur.fetchall() assert len(dbdata) == 2 assert dbdata[0] == (cont['sha1'], cont['sha1_git'], cont['sha256'], cont['blake2s256'], cont['length'], 'absent', 'Content too long') assert dbdata[1] == (cont2['sha1'], cont2['sha1_git'], cont2['sha256'], cont2['blake2s256'], cont2['length'], 'absent', 'Content too long') diff --git a/tox.ini b/tox.ini index 78178f4..4cca042 100644 --- a/tox.ini +++ b/tox.ini @@ -1,48 +1,39 @@ [tox] -envlist=flake8,mypy,py3-no-origin-ids,py3 +envlist=flake8,mypy,py3 [testenv:py3] deps = .[testing] .[listener] pytest-cov commands = pytest --hypothesis-profile=fast \ --cov={envsitepackagesdir}/swh/storage \ {envsitepackagesdir}/swh/storage \ --cov-branch {posargs} [testenv:py3-slow] deps = .[testing] .[listener] pytest-cov commands = pytest --hypothesis-profile=slow \ --cov={envsitepackagesdir}/swh/storage \ {envsitepackagesdir}/swh/storage \ --cov-branch {posargs} -[testenv:py3-no-origin-ids] -deps = - .[testing] - pytest-cov -setenv = - SWH_STORAGE_IN_MEMORY_ENABLE_ORIGIN_IDS=false -commands = - pytest --hypothesis-profile=fast {posargs} {envsitepackagesdir}/swh/storage/tests/test_in_memory.py - [testenv:flake8] skip_install = true deps = flake8 commands = {envpython} -m flake8 [testenv:mypy] skip_install = true deps = .[testing] mypy commands = mypy swh