diff --git a/sql/upgrades/148.sql b/sql/upgrades/148.sql new file mode 100644 index 00000000..dad2a3c9 --- /dev/null +++ b/sql/upgrades/148.sql @@ -0,0 +1,45 @@ +-- SWH DB schema upgrade +-- from_version: 147 +-- to_version: 148 +-- description: Fix origin_metadata values and migration schema to use correct primary key +-- 1. Fix existing duplicated entries in origin_metadata and metadata_provider +-- 2. Fix primary key on metadata_provider + +-- latest schema version +insert into dbversion(version, release, description) + values(148, now(), 'Work In Progress'); + +-- Clean up duplicated provider references in origin_metadata + +-- Lookup provider with the most minimal id already matching the future +-- composite key (provider_type, provider_url) +update origin_metadata om set provider_id=( + select min(mp1.id) as min_provider_id + from metadata_provider mp1 inner join metadata_provider mp2 + on (mp1.provider_type = mp2.provider_type and mp1.provider_url = mp2.provider_url) + where mp2.id=om.provider_id +); + +-- QUERY PLAN +-- ------------------------------------------------------------------------------------------------------------------------------------- +-- Update on origin_metadata om (cost=0.00..7506.94 rows=554 width=1157) +-- -> Seq Scan on origin_metadata om (cost=0.00..7506.94 rows=554 width=1157) +-- SubPlan 1 +-- -> Aggregate (cost=13.37..13.38 rows=1 width=4) +-- -> Hash Join (cost=2.18..12.90 rows=190 width=4) +-- Hash Cond: ((mp1.provider_type = mp2.provider_type) AND (mp1.provider_url = mp2.provider_url)) +-- -> Seq Scan on metadata_provider mp1 (cost=0.00..6.88 rows=288 width=51) +-- -> Hash (cost=2.17..2.17 rows=1 width=47) +-- -> Index Scan using metadata_provider_pkey on metadata_provider mp2 (cost=0.15..2.17 rows=1 width=47) +-- Index Cond: (id = om.provider_id) +-- (10 rows) + +-- Cleanup duplicated provider entries + +delete from metadata_provider +where id not in (select distinct provider_id from origin_metadata); + +-- Create unique index on table + +create unique index metadata_provider_type_url + on metadata_provider(provider_type, provider_url); diff --git a/swh/storage/db.py b/swh/storage/db.py index edbcb06a..9564ba58 100644 --- a/swh/storage/db.py +++ b/swh/storage/db.py @@ -1,1207 +1,1232 @@ # Copyright (C) 2015-2020 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import random import select from typing import Any, Dict, Optional, Tuple 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 from swh.model.model import OriginVisit, OriginVisitStatus, SHA1_SIZE 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) inner 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 content_missing_per_sha1_git(self, contents, cur=None): cur = self._cursor(cur) yield from execute_values_generator( cur, """ SELECT t.sha1_git FROM (VALUES %s) AS t(sha1_git) WHERE NOT EXISTS ( SELECT 1 FROM content c WHERE c.sha1_git = t.sha1_git )""", ((sha1,) for sha1 in contents), ) 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::sha1 and s.sha1_git is not distinct from t.sha1_git::sha1 and s.sha256 is not distinct from t.sha256::bytea);""" % ( (", ".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_missing_from_list(self, snapshots, 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 snapshot d WHERE d.id = t.id ) """, ((id,) for id in snapshots), ) 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_url, visit_id, cur=None): cur = self._cursor(cur) query = """\ 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_url, visit_id)) ret = cur.fetchone() if ret: return ret[0] def snapshot_get_random(self, cur=None): return self._get_random_row_from_table("snapshot", ["id"], "id", cur) 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 content_get_random(self, cur=None): return self._get_random_row_from_table("content", ["sha1_git"], "sha1_git", cur) 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 directory_get_random(self, cur=None): return self._get_random_row_from_table("directory", ["id"], "id", cur) 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] origin_visit_status_cols = [ "origin", "visit", "date", "status", "snapshot", "metadata", ] def origin_visit_status_add( self, visit_status: OriginVisitStatus, cur=None ) -> None: """Add new origin visit status """ assert self.origin_visit_status_cols[0] == "origin" assert self.origin_visit_status_cols[-1] == "metadata" cols = self.origin_visit_status_cols[1:-1] cur = self._cursor(cur) cur.execute( f"WITH origin_id as (select id from origin where url=%s) " f"INSERT INTO origin_visit_status " f"(origin, {', '.join(cols)}, metadata) " f"VALUES ((select id from origin_id), " f"{', '.join(['%s']*len(cols))}, %s) " f"ON CONFLICT (origin, visit, date) do nothing", [visit_status.origin] + [getattr(visit_status, key) for key in cols] + [jsonize(visit_status.metadata)], ) 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.id = origin_visit.origin", "origin.url=%s", "visit=%s"] where_values = [origin_id, visit_id] 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 origin WHERE {where}""".format( **{"update_cols": ", ".join(update_cols), "where": " AND ".join(where)} ) cur.execute(query, (*values, *where_values)) def origin_visit_upsert(self, origin_visit: OriginVisit, cur=None) -> None: # doing an extra query like this is way simpler than trying to join # the origin id in the query below ov = origin_visit origin_id = next(self.origin_id_get_by_url([ov.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_id, ov.visit, ov.date, ov.type, ov.status, ov.metadata, ov.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 _make_origin_visit_status(self, row: Tuple[Any]) -> Optional[Dict[str, Any]]: """Make an origin_visit_status dict out of a row """ if not row: return None return dict(zip(self.origin_visit_status_cols, row)) def origin_visit_status_get_latest( self, origin: str, visit: int, cur=None ) -> Optional[Dict[str, Any]]: """Given an origin visit id, return its latest origin_visit_status """ cols = self.origin_visit_status_cols cur = self._cursor(cur) cur.execute( f"SELECT {', '.join(cols)} " f"FROM origin_visit_status ovs " f"INNER JOIN origin o on o.id=ovs.origin " f"WHERE o.url=%s AND ovs.visit=%s" f"ORDER BY ovs.date DESC LIMIT 1", (origin, visit), ) row = cur.fetchone() return self._make_origin_visit_status(row) 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 visits for that origin """ 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 INNER JOIN origin ON origin.id = origin_visit.origin WHERE origin.url=%%s %s order by visit asc limit %%s""" % ( ", ".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 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) ) rows = cur.fetchall() if rows: visit = dict(zip(self.origin_visit_get_cols, rows[0])) visit["origin"] = origin return visit 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_select_cols), "FROM origin_visit", "INNER JOIN origin ON origin.id = origin_visit.origin", ] 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 def origin_visit_get_random(self, type, cur=None): """Randomly select one origin visit that was full and in the last 3 months """ cur = self._cursor(cur) columns = ",".join(self.origin_visit_select_cols) query = f"""with visits as ( select * from origin_visit where origin_visit.status='full' and origin_visit.type=%s and origin_visit.date > now() - '3 months'::interval ) select {columns} from visits as origin_visit inner join origin on origin_visit.origin=origin.id where random() < 0.1 limit 1 """ cur.execute(query, (type,)) return cur.fetchone() @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(sortkey, 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 ORDER BY sortkey """ % query_keys, ((sortkey, id) for sortkey, id in enumerate(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 revision_get_random(self, cur=None): return self._get_random_row_from_table("revision", ["id"], "id", 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"] def object_find_by_sha1_git(self, ids, cur=None): cur = self._cursor(cur) yield from execute_values_generator( cur, """ WITH t (sha1_git) AS (VALUES %s), known_objects as (( select id as sha1_git, 'release'::object_type as type, object_id from release r where exists (select 1 from t where t.sha1_git = r.id) ) union all ( select id as sha1_git, 'revision'::object_type as type, object_id from revision r where exists (select 1 from t where t.sha1_git = r.id) ) union all ( select id as sha1_git, 'directory'::object_type as type, object_id from directory d where exists (select 1 from t where t.sha1_git = d.id) ) union all ( select sha1_git as sha1_git, 'content'::object_type as type, object_id from content c where exists (select 1 from t where t.sha1_git = c.sha1_git) )) select t.sha1_git as sha1_git, k.type from t left join known_objects k on t.sha1_git = 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 url""" cur.execute(insert, (url,)) return cur.fetchone()[0] origin_cols = ["url"] def origin_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(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_sha1(self, sha1s, cur=None): """Retrieve origin urls from sha1s if found.""" cur = self._cursor(cur) query = """SELECT %s FROM (VALUES %%s) as t(sha1) LEFT JOIN origin ON t.sha1 = digest(origin.url, 'sha1') """ % ",".join( "origin." + col for col in self.origin_cols ) yield from execute_values_generator(cur, query, ((sha1,) for sha1 in sha1s)) def origin_id_get_by_url(self, origins, cur=None): """Retrieve origin `(type, url)` from urls if found.""" cur = self._cursor(cur) query = """SELECT id FROM (VALUES %s) as t(url) LEFT JOIN origin ON t.url = origin.url """ 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_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 INNER JOIN snapshot ON snapshot=snapshot.id 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(sortkey, id) LEFT JOIN release ON t.id = release.id LEFT JOIN person author ON release.author = author.id ORDER BY sortkey """ % query_keys, ((sortkey, id) for sortkey, id in enumerate(releases)), ) def release_get_random(self, cur=None): return self._get_random_row_from_table("release", ["id"], "id", cur) 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) 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_url", "discovery_date", "tool_id", "metadata", "provider_id", "provider_name", "provider_type", "provider_url", ] 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_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_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 - ): + self, + provider_name: str, + provider_type: str, + provider_url: str, + metadata: Dict, + cur=None, + ) -> int: """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""" - + insert = """ + INSERT INTO metadata_provider (provider_name, provider_type, + provider_url, metadata) values (%s, %s, %s, %s) + ON CONFLICT(provider_type, provider_url) do nothing + """ cur.execute( insert, (provider_name, provider_type, provider_url, jsonize(metadata)) ) - return cur.fetchone()[0] + row = self.metadata_provider_get_by_composite_key( + provider_type, provider_url, cur=cur + ) + return row[0] + + def metadata_provider_get_by_composite_key( + self, provider_type: str, provider_url: str, cur=None + ) -> Tuple: + """Retrieve metadata provider by its composite primary key. + + """ + cur = self._cursor(cur) + cur.execute( + """select %s + from metadata_provider + where provider_type=%%s and provider_url=%%s""" + % (",".join(self.metadata_provider_cols)), + (provider_type, provider_url,), + ) + return cur.fetchone() 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() def _get_random_row_from_table(self, table_name, cols, id_col, cur=None): random_sha1 = bytes(random.randint(0, 255) for _ in range(SHA1_SIZE)) cur = self._cursor(cur) query = """ (SELECT {cols} FROM {table} WHERE {id_col} >= %s ORDER BY {id_col} LIMIT 1) UNION (SELECT {cols} FROM {table} WHERE {id_col} < %s ORDER BY {id_col} DESC LIMIT 1) LIMIT 1 """.format( cols=", ".join(cols), table=table_name, id_col=id_col ) cur.execute(query, (random_sha1, random_sha1)) row = cur.fetchone() if row: return row[0] diff --git a/swh/storage/sql/30-swh-schema.sql b/swh/storage/sql/30-swh-schema.sql index 69ae248f..b9b74293 100644 --- a/swh/storage/sql/30-swh-schema.sql +++ b/swh/storage/sql/30-swh-schema.sql @@ -1,488 +1,488 @@ --- --- 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(147, now(), 'Work In Progress'); + values(148, 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 'A revision represents the state of a source code tree at a specific point in time'; comment on column revision.id is 'Git-style SHA1 commit identifier'; comment on column revision.date is 'Author timestamp as UNIX epoch'; comment on column revision.date_offset is 'Author timestamp timezone, as minute offsets from UTC'; comment on column revision.date_neg_utc_offset is 'True indicates a -0 UTC offset on author timestamp'; comment on column revision.committer_date is 'Committer timestamp as UNIX epoch'; comment on column revision.committer_date_offset is 'Committer timestamp timezone, as minute offsets from UTC'; comment on column revision.committer_date_neg_utc_offset is 'True indicates a -0 UTC offset on committer timestamp'; comment on column revision.type is 'Type of revision'; comment on column revision.directory is 'Directory identifier'; comment on column revision.message is 'Commit message'; comment on column revision.author is 'Author identity'; comment on column revision.committer is 'Committer identity'; comment on column revision.synthetic is 'True iff revision has been synthesized by Software Heritage'; comment on column revision.metadata is 'Extra revision metadata'; comment on column revision.object_id is 'Non-intrinsic, sequential object identifier'; -- 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, -- remove those when done migrating the schema status origin_visit_state 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 '(Deprecated) Visit status'; comment on column origin_visit.metadata is '(Deprecated) Optional origin visit metadata'; comment on column origin_visit.snapshot is '(Deprecated) Optional snapshot of the origin visit. It can be partial.'; -- Crawling history of software origin visits by Software Heritage. Each -- visit see its history change through new origin visit status updates create table origin_visit_status ( origin bigint not null, visit bigint not null, date timestamptz not null, status origin_visit_state not null, metadata jsonb, snapshot sha1_git ); comment on column origin_visit_status.origin is 'Origin concerned by the visit update'; comment on column origin_visit_status.visit is 'Visit concerned by the visit update'; comment on column origin_visit_status.date is 'Visit update timestamp'; comment on column origin_visit_status.status is 'Visit status (ongoing, failed, full)'; comment on column origin_visit_status.metadata is 'Optional origin visit metadata'; comment on column origin_visit_status.snapshot is 'Optional, possibly partial, snapshot of the origin visit. It can be partial.'; -- 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/60-swh-indexes.sql b/swh/storage/sql/60-swh-indexes.sql index 2db526e9..2f3e49f1 100644 --- a/swh/storage/sql/60-swh-indexes.sql +++ b/swh/storage/sql/60-swh-indexes.sql @@ -1,191 +1,194 @@ -- content create unique index concurrently content_pkey on content(sha1); create unique index concurrently on content(sha1_git); create index concurrently on content(sha256); create index concurrently on content(blake2s256); create index concurrently on content(ctime); -- TODO use a BRIN index here (postgres >= 9.5) create unique index concurrently on content(object_id); alter table content add primary key using index content_pkey; -- origin create unique index concurrently origin_pkey on origin(id); alter table origin add primary key using index origin_pkey; create index concurrently on origin using gin (url gin_trgm_ops); create index concurrently on origin using hash (url); create index concurrently on origin using btree(digest(url, 'sha1')); -- skipped_content alter table skipped_content add constraint skipped_content_sha1_sha1_git_sha256_key unique (sha1, sha1_git, sha256); create index concurrently on skipped_content(sha1); create index concurrently on skipped_content(sha1_git); create index concurrently on skipped_content(sha256); create index concurrently on skipped_content(blake2s256); create unique index concurrently on skipped_content(object_id); alter table skipped_content add constraint skipped_content_origin_fkey foreign key (origin) references origin(id) not valid; alter table skipped_content validate constraint skipped_content_origin_fkey; -- directory create unique index concurrently directory_pkey on directory(id); alter table directory add primary key using index directory_pkey; create index concurrently on directory using gin (dir_entries); create index concurrently on directory using gin (file_entries); create index concurrently on directory using gin (rev_entries); create unique index concurrently on directory(object_id); -- directory_entry_dir create unique index concurrently directory_entry_dir_pkey on directory_entry_dir(id); alter table directory_entry_dir add primary key using index directory_entry_dir_pkey; create unique index concurrently on directory_entry_dir(target, name, perms); -- directory_entry_file create unique index concurrently directory_entry_file_pkey on directory_entry_file(id); alter table directory_entry_file add primary key using index directory_entry_file_pkey; create unique index concurrently on directory_entry_file(target, name, perms); -- directory_entry_rev create unique index concurrently directory_entry_rev_pkey on directory_entry_rev(id); alter table directory_entry_rev add primary key using index directory_entry_rev_pkey; create unique index concurrently on directory_entry_rev(target, name, perms); -- person create unique index concurrently person_pkey on person(id); alter table person add primary key using index person_pkey; create unique index concurrently on person(fullname); create index concurrently on person(name); create index concurrently on person(email); -- revision create unique index concurrently revision_pkey on revision(id); alter table revision add primary key using index revision_pkey; alter table revision add constraint revision_author_fkey foreign key (author) references person(id) not valid; alter table revision validate constraint revision_author_fkey; alter table revision add constraint revision_committer_fkey foreign key (committer) references person(id) not valid; alter table revision validate constraint revision_committer_fkey; create index concurrently on revision(directory); create unique index concurrently on revision(object_id); -- revision_history create unique index concurrently revision_history_pkey on revision_history(id, parent_rank); alter table revision_history add primary key using index revision_history_pkey; create index concurrently on revision_history(parent_id); alter table revision_history add constraint revision_history_id_fkey foreign key (id) references revision(id) not valid; alter table revision_history validate constraint revision_history_id_fkey; -- snapshot create unique index concurrently snapshot_pkey on snapshot(object_id); alter table snapshot add primary key using index snapshot_pkey; create unique index concurrently on snapshot(id); -- snapshot_branch create unique index concurrently snapshot_branch_pkey on snapshot_branch(object_id); alter table snapshot_branch add primary key using index snapshot_branch_pkey; create unique index concurrently on snapshot_branch (target_type, target, name); alter table snapshot_branch add constraint snapshot_branch_target_check check ((target_type is null) = (target is null)) not valid; alter table snapshot_branch validate constraint snapshot_branch_target_check; alter table snapshot_branch add constraint snapshot_target_check check (target_type not in ('content', 'directory', 'revision', 'release', 'snapshot') or length(target) = 20) not valid; alter table snapshot_branch validate constraint snapshot_target_check; create unique index concurrently on snapshot_branch (name) where target_type is null and target is null; -- snapshot_branches create unique index concurrently snapshot_branches_pkey on snapshot_branches(snapshot_id, branch_id); alter table snapshot_branches add primary key using index snapshot_branches_pkey; alter table snapshot_branches add constraint snapshot_branches_snapshot_id_fkey foreign key (snapshot_id) references snapshot(object_id) not valid; alter table snapshot_branches validate constraint snapshot_branches_snapshot_id_fkey; alter table snapshot_branches add constraint snapshot_branches_branch_id_fkey foreign key (branch_id) references snapshot_branch(object_id) not valid; alter table snapshot_branches validate constraint snapshot_branches_branch_id_fkey; -- origin_visit create unique index concurrently origin_visit_pkey on origin_visit(origin, visit); alter table origin_visit add primary key using index origin_visit_pkey; create index concurrently on origin_visit(date); create index concurrently on origin_visit(type, status, date); alter table origin_visit add constraint origin_visit_origin_fkey foreign key (origin) references origin(id) not valid; alter table origin_visit validate constraint origin_visit_origin_fkey; -- origin_visit_status create unique index concurrently origin_visit_status_pkey on origin_visit_status(origin, visit, date); alter table origin_visit_status add primary key using index origin_visit_status_pkey; alter table origin_visit_status add constraint origin_visit_status_origin_visit_fkey foreign key (origin, visit) references origin_visit(origin, visit) not valid; alter table origin_visit_status validate constraint origin_visit_status_origin_visit_fkey; -- release create unique index concurrently release_pkey on release(id); alter table release add primary key using index release_pkey; create index concurrently on release(target, target_type); create unique index concurrently on release(object_id); alter table release add constraint release_author_fkey foreign key (author) references person(id) not valid; alter table release validate constraint release_author_fkey; -- if the author is null, then the date must be null alter table release add constraint release_author_date_check check ((date is null) or (author is not null)) not valid; alter table release validate constraint release_author_date_check; -- tool create unique index tool_pkey on tool(id); alter table tool add primary key using index tool_pkey; create unique index on tool(name, version, configuration); -- metadata_provider create unique index concurrently metadata_provider_pkey on metadata_provider(id); alter table metadata_provider add primary key using index metadata_provider_pkey; create index concurrently on metadata_provider(provider_name, provider_url); +create unique index metadata_provider_type_url + on metadata_provider(provider_type, provider_url); -- origin_metadata create unique index concurrently origin_metadata_pkey on origin_metadata(id); alter table origin_metadata add primary key using index origin_metadata_pkey; + create index concurrently on origin_metadata(origin_id, provider_id, tool_id); alter table origin_metadata add constraint origin_metadata_origin_fkey foreign key (origin_id) references origin(id) not valid; alter table origin_metadata validate constraint origin_metadata_origin_fkey; alter table origin_metadata add constraint origin_metadata_provider_fkey foreign key (provider_id) references metadata_provider(id) not valid; alter table origin_metadata validate constraint origin_metadata_provider_fkey; alter table origin_metadata add constraint origin_metadata_tool_fkey foreign key (tool_id) references tool(id) not valid; alter table origin_metadata validate constraint origin_metadata_tool_fkey; -- object_counts create unique index concurrently object_counts_pkey on object_counts(object_type); alter table object_counts add primary key using index object_counts_pkey; -- object_counts_bucketed create unique index concurrently object_counts_bucketed_pkey on object_counts_bucketed(line); alter table object_counts_bucketed add primary key using index object_counts_bucketed_pkey; diff --git a/swh/storage/tests/test_cassandra.py b/swh/storage/tests/test_cassandra.py index cacdabaa..fb541288 100644 --- a/swh/storage/tests/test_cassandra.py +++ b/swh/storage/tests/test_cassandra.py @@ -1,415 +1,419 @@ # Copyright (C) 2018-2019 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information from collections import namedtuple import datetime import os import signal import socket import subprocess import time import pytest from swh.storage import get_storage from swh.storage.cassandra import create_keyspace from swh.storage.cassandra.schema import TABLES, HASH_ALGORITHMS from swh.storage.tests.test_storage import TestStorage as _TestStorage from swh.storage.tests.test_storage import ( TestStorageGeneratedData as _TestStorageGeneratedData, ) from .storage_data import data CONFIG_TEMPLATE = """ data_file_directories: - {data_dir}/data commitlog_directory: {data_dir}/commitlog hints_directory: {data_dir}/hints saved_caches_directory: {data_dir}/saved_caches commitlog_sync: periodic commitlog_sync_period_in_ms: 1000000 partitioner: org.apache.cassandra.dht.Murmur3Partitioner endpoint_snitch: SimpleSnitch seed_provider: - class_name: org.apache.cassandra.locator.SimpleSeedProvider parameters: - seeds: "127.0.0.1" storage_port: {storage_port} native_transport_port: {native_transport_port} start_native_transport: true listen_address: 127.0.0.1 enable_user_defined_functions: true # speed-up by disabling period saving to disk key_cache_save_period: 0 row_cache_save_period: 0 trickle_fsync: false commitlog_sync_period_in_ms: 100000 """ def free_port(): sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM) sock.bind(("127.0.0.1", 0)) port = sock.getsockname()[1] sock.close() return port def wait_for_peer(addr, port): wait_until = time.time() + 20 while time.time() < wait_until: try: sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM) sock.connect((addr, port)) except ConnectionRefusedError: time.sleep(0.1) else: sock.close() return True return False @pytest.fixture(scope="session") def cassandra_cluster(tmpdir_factory): cassandra_conf = tmpdir_factory.mktemp("cassandra_conf") cassandra_data = tmpdir_factory.mktemp("cassandra_data") cassandra_log = tmpdir_factory.mktemp("cassandra_log") native_transport_port = free_port() storage_port = free_port() jmx_port = free_port() with open(str(cassandra_conf.join("cassandra.yaml")), "w") as fd: fd.write( CONFIG_TEMPLATE.format( data_dir=str(cassandra_data), storage_port=storage_port, native_transport_port=native_transport_port, ) ) if os.environ.get("LOG_CASSANDRA"): stdout = stderr = None else: stdout = stderr = subprocess.DEVNULL proc = subprocess.Popen( [ "/usr/sbin/cassandra", "-Dcassandra.config=file://%s/cassandra.yaml" % cassandra_conf, "-Dcassandra.logdir=%s" % cassandra_log, "-Dcassandra.jmx.local.port=%d" % jmx_port, "-Dcassandra-foreground=yes", ], start_new_session=True, env={ "MAX_HEAP_SIZE": "300M", "HEAP_NEWSIZE": "50M", "JVM_OPTS": "-Xlog:gc=error:file=%s/gc.log" % cassandra_log, }, stdout=stdout, stderr=stderr, ) running = wait_for_peer("127.0.0.1", native_transport_port) if running: yield (["127.0.0.1"], native_transport_port) if not running or os.environ.get("LOG_CASSANDRA"): with open(str(cassandra_log.join("debug.log"))) as fd: print(fd.read()) if not running: raise Exception("cassandra process stopped unexpectedly.") pgrp = os.getpgid(proc.pid) os.killpg(pgrp, signal.SIGKILL) class RequestHandler: def on_request(self, rf): if hasattr(rf.message, "query"): print() print(rf.message.query) @pytest.fixture(scope="session") def keyspace(cassandra_cluster): (hosts, port) = cassandra_cluster keyspace = os.urandom(10).hex() create_keyspace(hosts, keyspace, port) return keyspace # tests are executed using imported classes (TestStorage and # TestStorageGeneratedData) using overloaded swh_storage fixture # below @pytest.fixture def swh_storage_backend_config(cassandra_cluster, keyspace): (hosts, port) = cassandra_cluster storage_config = dict( cls="cassandra", hosts=hosts, port=port, keyspace=keyspace, journal_writer={"cls": "memory",}, objstorage={"cls": "memory", "args": {},}, ) yield storage_config storage = get_storage(**storage_config) for table in TABLES: storage._cql_runner._session.execute('TRUNCATE TABLE "%s"' % table) storage._cql_runner._cluster.shutdown() @pytest.mark.cassandra class TestCassandraStorage(_TestStorage): def test_content_add_murmur3_collision(self, swh_storage, mocker): """The Murmur3 token is used as link from index tables to the main table; and non-matching contents with colliding murmur3-hash are filtered-out when reading the main table. This test checks the content methods do filter out these collision. """ called = 0 # always return a token def mock_cgtfsh(algo, hash_): nonlocal called called += 1 assert algo in ("sha1", "sha1_git") return [123456] mocker.patch.object( swh_storage.storage._cql_runner, "content_get_tokens_from_single_hash", mock_cgtfsh, ) # For all tokens, always return data.cont Row = namedtuple("Row", HASH_ALGORITHMS) def mock_cgft(token): nonlocal called called += 1 return [Row(**{algo: data.cont[algo] for algo in HASH_ALGORITHMS})] mocker.patch.object( swh_storage.storage._cql_runner, "content_get_from_token", mock_cgft ) actual_result = swh_storage.content_add([data.cont2]) assert called == 4 assert actual_result == { "content:add": 1, "content:add:bytes": data.cont2["length"], } def test_content_get_metadata_murmur3_collision(self, swh_storage, mocker): """The Murmur3 token is used as link from index tables to the main table; and non-matching contents with colliding murmur3-hash are filtered-out when reading the main table. This test checks the content methods do filter out these collision. """ called = 0 # always return a token def mock_cgtfsh(algo, hash_): nonlocal called called += 1 assert algo in ("sha1", "sha1_git") return [123456] mocker.patch.object( swh_storage.storage._cql_runner, "content_get_tokens_from_single_hash", mock_cgtfsh, ) # For all tokens, always return data.cont and data.cont2 cols = list(set(data.cont) - {"data"}) Row = namedtuple("Row", cols + ["ctime"]) def mock_cgft(token): nonlocal called called += 1 return [ Row(ctime=42, **{col: cont[col] for col in cols}) for cont in [data.cont, data.cont2] ] mocker.patch.object( swh_storage.storage._cql_runner, "content_get_from_token", mock_cgft ) expected_cont = data.cont.copy() del expected_cont["data"] actual_result = swh_storage.content_get_metadata([data.cont["sha1"]]) assert called == 2 # but data.cont2 should be filtered out assert actual_result == {data.cont["sha1"]: [expected_cont]} def test_content_find_murmur3_collision(self, swh_storage, mocker): """The Murmur3 token is used as link from index tables to the main table; and non-matching contents with colliding murmur3-hash are filtered-out when reading the main table. This test checks the content methods do filter out these collision. """ called = 0 # always return a token def mock_cgtfsh(algo, hash_): nonlocal called called += 1 assert algo in ("sha1", "sha1_git") return [123456] mocker.patch.object( swh_storage.storage._cql_runner, "content_get_tokens_from_single_hash", mock_cgtfsh, ) # For all tokens, always return data.cont and data.cont2 cols = list(set(data.cont) - {"data"}) Row = namedtuple("Row", cols + ["ctime"]) def mock_cgft(token): nonlocal called called += 1 return [ Row(ctime=datetime.datetime.now(), **{col: cont[col] for col in cols}) for cont in [data.cont, data.cont2] ] mocker.patch.object( swh_storage.storage._cql_runner, "content_get_from_token", mock_cgft ) expected_cont = data.cont.copy() del expected_cont["data"] actual_result = swh_storage.content_find({"sha1": data.cont["sha1"]}) assert called == 2 # but data.cont2 should be filtered out del actual_result[0]["ctime"] assert actual_result == [expected_cont] @pytest.mark.skip("content_update is not yet implemented for Cassandra") def test_content_update(self): pass @pytest.mark.skip( 'The "person" table of the pgsql is a legacy thing, and not ' "supported by the cassandra backend." ) def test_person_fullname_unicity(self): pass @pytest.mark.skip( 'The "person" table of the pgsql is a legacy thing, and not ' "supported by the cassandra backend." ) def test_person_get(self): pass @pytest.mark.skip("Not yet implemented") def test_metadata_provider_add(self): pass + @pytest.mark.skip("Not yet implemented") + def test_metadata_provider_add_idempotent(self): + pass + @pytest.mark.skip("Not yet implemented") def test_metadata_provider_get(self): pass @pytest.mark.skip("Not yet implemented") def test_metadata_provider_get_by(self): pass @pytest.mark.skip("Not yet implemented") def test_origin_metadata_add(self): pass @pytest.mark.skip("Not yet implemented") def test_origin_metadata_get(self): pass @pytest.mark.skip("Not yet implemented") def test_origin_metadata_get_by_provider_type(self): pass @pytest.mark.skip("Not supported by Cassandra") def test_origin_count(self): pass @pytest.mark.cassandra class TestCassandraStorageGeneratedData(_TestStorageGeneratedData): @pytest.mark.skip("Not supported by Cassandra") def test_origin_count(self): pass @pytest.mark.skip("Not supported by Cassandra") def test_origin_get_range(self): pass @pytest.mark.skip("Not supported by Cassandra") def test_origin_get_range_from_zero(self): pass @pytest.mark.skip("Not supported by Cassandra") def test_generate_content_get_range_limit(self): pass @pytest.mark.skip("Not supported by Cassandra") def test_generate_content_get_range_no_limit(self): pass @pytest.mark.skip("Not supported by Cassandra") def test_generate_content_get_range(self): pass @pytest.mark.skip("Not supported by Cassandra") def test_generate_content_get_range_empty(self): pass @pytest.mark.skip("Not supported by Cassandra") def test_generate_content_get_range_limit_none(self): pass @pytest.mark.skip("Not supported by Cassandra") def test_generate_content_get_range_full(self): pass @pytest.mark.skip("Not supported by Cassandra") def test_origin_count_with_visit_no_visits(self): pass @pytest.mark.skip("Not supported by Cassandra") def test_origin_count_with_visit_with_visits_and_snapshot(self): pass @pytest.mark.skip("Not supported by Cassandra") def test_origin_count_with_visit_with_visits_no_snapshot(self): pass diff --git a/swh/storage/tests/test_storage.py b/swh/storage/tests/test_storage.py index 801a84be..29b426b7 100644 --- a/swh/storage/tests/test_storage.py +++ b/swh/storage/tests/test_storage.py @@ -1,4047 +1,4068 @@ # Copyright (C) 2015-2020 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import copy from contextlib import contextmanager import datetime import inspect import itertools import math import queue import random import threading from collections import defaultdict from datetime import timedelta 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.model import ( Content, Directory, Origin, OriginVisit, Release, Revision, Snapshot, ) from swh.model.hypothesis_strategies import objects from swh.model.hashutil import hash_to_hex from swh.storage import get_storage from swh.storage.converters import origin_url_to_sha1 as sha1 from swh.storage.exc import HashCollision, StorageArgumentException from swh.storage.interface import StorageInterface from swh.storage.utils import content_hex_hashes 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"]] def assert_contents_ok( 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 class LazyContent(Content): def with_data(self): return Content.from_dict({**self.to_dict(), "data": data.cont["data"]}) def now(): return datetime.datetime.now(tz=datetime.timezone.utc) 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]] def test_types(self, swh_storage_backend_config): """Checks all methods of StorageInterface are implemented by this backend, and that they have the same signature.""" # Create an instance of the protocol (which cannot be instantiated # directly, so this creates a subclass, then instantiates it) interface = type("_", (StorageInterface,), {})() storage = get_storage(**swh_storage_backend_config) assert "content_add" in dir(interface) missing_methods = [] for meth_name in dir(interface): if meth_name.startswith("_"): continue interface_meth = getattr(interface, meth_name) try: concrete_meth = getattr(storage, meth_name) except AttributeError: if not getattr(interface_meth, "deprecated_endpoint", False): # The backend is missing a (non-deprecated) endpoint missing_methods.append(meth_name) continue expected_signature = inspect.signature(interface_meth) actual_signature = inspect.signature(concrete_meth) assert expected_signature == actual_signature, meth_name assert missing_methods == [] 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 = now() actual_result = swh_storage.content_add([cont]) insertion_end_time = now() assert actual_result == { "content:add": 1, "content:add:bytes": cont["length"], } assert list(swh_storage.content_get([cont["sha1"]])) == [ {"sha1": cont["sha1"], "data": cont["data"]} ] expected_cont = data.cont del expected_cont["data"] contents = [ obj for (obj_type, obj) in swh_storage.journal_writer.journal.objects if obj_type == "content" ] assert len(contents) == 1 for obj in contents: assert insertion_start_time <= obj.ctime assert obj.ctime <= insertion_end_time obj_d = obj.to_dict() del obj_d["ctime"] assert obj_d == expected_cont swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["content"] == 1 def test_content_add_from_generator(self, swh_storage): def _cnt_gen(): yield data.cont actual_result = swh_storage.content_add(_cnt_gen()) assert actual_result == { "content:add": 1, "content:add:bytes": data.cont["length"], } swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["content"] == 1 def test_content_add_from_lazy_content(self, swh_storage): lazy_content = LazyContent.from_dict({**data.cont, "data": b"nope",}) insertion_start_time = now() # bypass the validation proxy for now, to directly put a dict actual_result = swh_storage.storage.content_add([lazy_content]) insertion_end_time = now() assert actual_result == { "content:add": 1, "content:add:bytes": data.cont["length"], } # the fact that we retrieve the content object from the storage with # the correct 'data' field ensures it has been 'called' assert list(swh_storage.content_get([data.cont["sha1"]])) == [ {"sha1": data.cont["sha1"], "data": data.cont["data"]} ] expected_cont = data.cont del expected_cont["data"] contents = [ obj for (obj_type, obj) in swh_storage.journal_writer.journal.objects if obj_type == "content" ] assert len(contents) == 1 for obj in contents: assert insertion_start_time <= obj.ctime assert obj.ctime <= insertion_end_time obj_d = obj.to_dict() del obj_d["ctime"] assert obj_d == expected_cont swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["content"] == 1 def test_content_add_validation(self, swh_storage): cont = data.cont with pytest.raises(StorageArgumentException, match="status"): swh_storage.content_add([{**cont, "status": "absent"}]) with pytest.raises(StorageArgumentException, match="status"): swh_storage.content_add([{**cont, "status": "foobar"}]) with pytest.raises(StorageArgumentException, match="(?i)length"): swh_storage.content_add([{**cont, "length": -2}]) with pytest.raises(StorageArgumentException, match="reason"): swh_storage.content_add([{**cont, "reason": "foobar"}]) def test_skipped_content_add_validation(self, swh_storage): cont = data.cont.copy() del cont["data"] with pytest.raises(StorageArgumentException, match="status"): swh_storage.skipped_content_add([{**cont, "status": "visible"}]) with pytest.raises(StorageArgumentException, match="reason") as cm: swh_storage.skipped_content_add([{**cont, "status": "absent"}]) if type(cm.value) == psycopg2.IntegrityError: assert cm.exception.pgcode == psycopg2.errorcodes.NOT_NULL_VIOLATION 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_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"], } 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"], } assert len(swh_storage.journal_writer.journal.objects) == 1 actual_result = swh_storage.content_add([data.cont, data.cont2]) assert actual_result == { "content:add": 1, "content:add:bytes": data.cont2["length"], } assert 2 <= len(swh_storage.journal_writer.journal.objects) <= 3 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]) exc = cm.value actual_algo = exc.algo assert actual_algo in ["sha1", "sha1_git", "blake2s256"] actual_id = exc.hash_id assert actual_id == hash_to_hex(cont1[actual_algo]) collisions = exc.args[2] assert len(collisions) == 2 assert collisions == [ content_hex_hashes(Content.from_dict(cont1).hashes()), content_hex_hashes(Content.from_dict(cont1b).hashes()), ] assert exc.colliding_content_hashes() == [ Content.from_dict(cont1).hashes(), Content.from_dict(cont1b).hashes(), ] def test_content_add_duplicate(self, swh_storage): swh_storage.content_add([data.cont, data.cont]) assert list(swh_storage.content_get([data.cont["sha1"]])) == [ {"sha1": data.cont["sha1"], "data": data.cont["data"]} ] def test_content_update(self, swh_storage): if hasattr(swh_storage, "storage"): swh_storage.journal_writer.journal = 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"]) results = swh_storage.content_get_metadata([cont["sha1"]]) del cont["data"] assert results == {cont["sha1"]: [cont]} def test_content_add_metadata(self, swh_storage): cont = data.cont del cont["data"] cont["ctime"] = now() actual_result = swh_storage.content_add_metadata([cont]) assert actual_result == { "content:add": 1, } expected_cont = cont.copy() del expected_cont["ctime"] assert swh_storage.content_get_metadata([cont["sha1"]]) == { cont["sha1"]: [expected_cont] } contents = [ obj for (obj_type, obj) in swh_storage.journal_writer.journal.objects if obj_type == "content" ] assert len(contents) == 1 for obj in contents: obj_d = obj.to_dict() del obj_d["ctime"] assert obj_d == expected_cont def test_content_add_metadata_different_input(self, swh_storage): cont = data.cont del cont["data"] cont["ctime"] = now() cont2 = data.cont2 del cont2["data"] cont2["ctime"] = now() actual_result = swh_storage.content_add_metadata([cont, cont2]) assert actual_result == { "content:add": 2, } def test_content_add_metadata_collision(self, swh_storage): cont1 = data.cont del cont1["data"] cont1["ctime"] = now() # create (corrupted) content with same sha1{,_git} but != sha256 cont1b = cont1.copy() sha1_git_array = bytearray(cont1b["sha256"]) sha1_git_array[0] += 1 cont1b["sha256"] = bytes(sha1_git_array) with pytest.raises(HashCollision) as cm: swh_storage.content_add_metadata([cont1, cont1b]) exc = cm.value actual_algo = exc.algo assert actual_algo in ["sha1", "sha1_git", "blake2s256"] actual_id = exc.hash_id assert actual_id == hash_to_hex(cont1[actual_algo]) collisions = exc.args[2] assert len(collisions) == 2 assert collisions == [ content_hex_hashes(Content.from_dict(cont1).hashes()), content_hex_hashes(Content.from_dict(cont1b).hashes()), ] assert exc.colliding_content_hashes() == [ Content.from_dict(cont1).hashes(), Content.from_dict(cont1b).hashes(), ] 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 missing == [ { "sha1": cont["sha1"], "sha1_git": cont["sha1_git"], "blake2s256": cont["blake2s256"], "sha256": cont["sha256"], }, { "sha1": cont2["sha1"], "sha1_git": cont2["sha1_git"], "blake2s256": cont2["blake2s256"], "sha256": cont2["sha256"], }, ] actual_result = swh_storage.skipped_content_add([cont, cont, cont2]) assert 2 <= actual_result.pop("skipped_content:add") <= 3 assert actual_result == {} missing = list(swh_storage.skipped_content_missing([cont, cont2])) assert missing == [] def test_skipped_content_add_missing_hashes(self, swh_storage): cont = data.skipped_cont cont2 = data.skipped_cont2 cont["sha1_git"] = cont2["sha1_git"] = None missing = list(swh_storage.skipped_content_missing([cont, cont2])) assert len(missing) == 2 actual_result = swh_storage.skipped_content_add([cont, cont, cont2]) assert 2 <= actual_result.pop("skipped_content:add") <= 3 assert actual_result == {} missing = list(swh_storage.skipped_content_missing([cont, cont2])) assert missing == [] def test_skipped_content_missing_partial_hash(self, swh_storage): cont = data.skipped_cont cont2 = cont.copy() cont2["sha1_git"] = None missing = list(swh_storage.skipped_content_missing([cont, cont2])) assert len(missing) == 2 actual_result = swh_storage.skipped_content_add([cont]) assert actual_result.pop("skipped_content:add") == 1 assert actual_result == {} missing = list(swh_storage.skipped_content_missing([cont, cont2])) assert missing == [ { "sha1": cont2["sha1"], "sha1_git": cont2["sha1_git"], "blake2s256": cont2["blake2s256"], "sha256": cont2["sha256"], } ] @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_missing_per_sha1_git(self, swh_storage): cont = data.cont cont2 = data.cont2 missing_cont = data.missing_cont swh_storage.content_add([cont, cont2]) contents = [cont["sha1_git"], cont2["sha1_git"], missing_cont["sha1_git"]] missing_contents = swh_storage.content_missing_per_sha1_git(contents) assert list(missing_contents) == [missing_cont["sha1_git"]] def test_content_get_partition(self, swh_storage, swh_contents): """content_get_partition paginates results if limit exceeded""" expected_contents = [c for c in swh_contents if c["status"] != "absent"] actual_contents = [] for i in range(16): actual_result = swh_storage.content_get_partition(i, 16) assert actual_result["next_page_token"] is None actual_contents.extend(actual_result["contents"]) assert_contents_ok(expected_contents, actual_contents, ["sha1"]) def test_content_get_partition_full(self, swh_storage, swh_contents): """content_get_partition for a single partition returns all available contents""" expected_contents = [c for c in swh_contents if c["status"] != "absent"] actual_result = swh_storage.content_get_partition(0, 1) assert actual_result["next_page_token"] is None actual_contents = actual_result["contents"] assert_contents_ok(expected_contents, actual_contents, ["sha1"]) def test_content_get_partition_empty(self, swh_storage, swh_contents): """content_get_partition when at least one of the partitions is empty""" expected_contents = { cont["sha1"] for cont in swh_contents if cont["status"] != "absent" } # nb_partitions = smallest power of 2 such that at least one of # the partitions is empty nb_partitions = 1 << math.floor(math.log2(len(swh_contents)) + 1) seen_sha1s = [] for i in range(nb_partitions): actual_result = swh_storage.content_get_partition( i, nb_partitions, limit=len(swh_contents) + 1 ) for cont in actual_result["contents"]: seen_sha1s.append(cont["sha1"]) # Limit is higher than the max number of results assert actual_result["next_page_token"] is None assert set(seen_sha1s) == expected_contents def test_content_get_partition_limit_none(self, swh_storage): """content_get_partition call with wrong limit input should fail""" with pytest.raises(StorageArgumentException) as e: swh_storage.content_get_partition(1, 16, limit=None) assert e.value.args == ("limit should not be None",) def test_generate_content_get_partition_pagination(self, swh_storage, swh_contents): """content_get_partition returns contents within range provided""" expected_contents = [c for c in swh_contents if c["status"] != "absent"] # retrieve contents actual_contents = [] for i in range(4): page_token = None while True: actual_result = swh_storage.content_get_partition( i, 4, limit=3, page_token=page_token ) actual_contents.extend(actual_result["contents"]) page_token = actual_result["next_page_token"] if page_token is None: break assert_contents_ok(expected_contents, actual_contents, ["sha1"]) def test_content_get_metadata(self, swh_storage): cont1 = data.cont cont2 = data.cont2 swh_storage.content_add([cont1, cont2]) actual_md = swh_storage.content_get_metadata([cont1["sha1"], cont2["sha1"]]) # we only retrieve the metadata cont1.pop("data") cont2.pop("data") assert actual_md[cont1["sha1"]] == [cont1] assert actual_md[cont2["sha1"]] == [cont2] assert len(actual_md.keys()) == 2 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]) actual_contents = swh_storage.content_get_metadata([missing_cont["sha1"]]) assert actual_contents == {missing_cont["sha1"]: []} def test_content_get_random(self, swh_storage): swh_storage.content_add([data.cont, data.cont2, data.cont3]) assert swh_storage.content_get_random() in { data.cont["sha1_git"], data.cont2["sha1_git"], data.cont3["sha1_git"], } 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.journal.objects) == [ ("directory", Directory.from_dict(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 == [] swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["directory"] == 1 def test_directory_add_from_generator(self, swh_storage): def _dir_gen(): yield data.dir actual_result = swh_storage.directory_add(directories=_dir_gen()) assert actual_result == {"directory:add": 1} assert list(swh_storage.journal_writer.journal.objects) == [ ("directory", Directory.from_dict(data.dir)) ] swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["directory"] == 1 def test_directory_add_validation(self, swh_storage): dir_ = copy.deepcopy(data.dir) dir_["entries"][0]["type"] = "foobar" with pytest.raises(StorageArgumentException, match="type.*foobar"): swh_storage.directory_add([dir_]) dir_ = copy.deepcopy(data.dir) del dir_["entries"][0]["target"] with pytest.raises(StorageArgumentException, 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.journal.objects) == [ ("directory", Directory.from_dict(data.dir)) ] actual_result = swh_storage.directory_add([data.dir]) assert actual_result == {"directory:add": 0} assert list(swh_storage.journal_writer.journal.objects) == [ ("directory", Directory.from_dict(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.journal.objects) == [ ("directory", Directory.from_dict(data.dir)), ("directory", Directory.from_dict(data.dir2)), ("directory", Directory.from_dict(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.journal.objects) == [ ("directory", Directory.from_dict(data.dir)), ("directory", Directory.from_dict(data.dir2)), ("directory", Directory.from_dict(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_directory_get_random(self, swh_storage): swh_storage.directory_add([data.dir, data.dir2, data.dir3]) assert swh_storage.directory_get_random() in { data.dir["id"], data.dir2["id"], data.dir3["id"], } 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.journal.objects) == [ ("revision", Revision.from_dict(data.revision)) ] # already there so nothing added actual_result = swh_storage.revision_add([data.revision]) assert actual_result == {"revision:add": 0} swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["revision"] == 1 def test_revision_add_from_generator(self, swh_storage): def _rev_gen(): yield data.revision actual_result = swh_storage.revision_add(_rev_gen()) assert actual_result == {"revision:add": 1} swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["revision"] == 1 def test_revision_add_validation(self, swh_storage): rev = copy.deepcopy(data.revision) rev["date"]["offset"] = 2 ** 16 with pytest.raises(StorageArgumentException, 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(StorageArgumentException, 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(StorageArgumentException, 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.journal.objects) == [ ("revision", Revision.from_dict(data.revision)) ] actual_result = swh_storage.revision_add([data.revision, data.revision2]) assert actual_result == {"revision:add": 1} assert list(swh_storage.journal_writer.journal.objects) == [ ("revision", Revision.from_dict(data.revision)), ("revision", Revision.from_dict(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_get_order(self, swh_storage): add_result = swh_storage.revision_add([data.revision, data.revision2]) assert add_result == {"revision:add": 2} # order 1 res1 = swh_storage.revision_get([data.revision["id"], data.revision2["id"]]) assert list(res1) == [data.revision, data.revision2] # order 2 res2 = swh_storage.revision_get([data.revision2["id"], data.revision["id"]]) assert list(res2) == [data.revision2, data.revision] 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.journal.objects) == [ ("revision", Revision.from_dict(data.revision3)), ("revision", Revision.from_dict(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_revision_get_random(self, swh_storage): swh_storage.revision_add([data.revision, data.revision2, data.revision3]) assert swh_storage.revision_get_random() in { data.revision["id"], data.revision2["id"], data.revision3["id"], } 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.journal.objects) == [ ("release", Release.from_dict(data.release)), ("release", Release.from_dict(data.release2)), ] # already present so nothing added actual_result = swh_storage.release_add([data.release, data.release2]) assert actual_result == {"release:add": 0} swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["release"] == 2 def test_release_add_from_generator(self, swh_storage): def _rel_gen(): yield data.release yield data.release2 actual_result = swh_storage.release_add(_rel_gen()) assert actual_result == {"release:add": 2} assert list(swh_storage.journal_writer.journal.objects) == [ ("release", Release.from_dict(data.release)), ("release", Release.from_dict(data.release2)), ] swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["release"] == 2 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.journal.objects) == [ ("release", Release.from_dict(release)) ] def test_release_add_validation(self, swh_storage): rel = copy.deepcopy(data.release) rel["date"]["offset"] = 2 ** 16 with pytest.raises(StorageArgumentException, 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(StorageArgumentException, 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_validation_type(self, swh_storage): rel = copy.deepcopy(data.release) rel["date"]["offset"] = "toto" with pytest.raises(StorageArgumentException): swh_storage.release_add([rel]) 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.journal.objects) == [ ("release", Release.from_dict(data.release)) ] actual_result = swh_storage.release_add([data.release, data.release2]) assert actual_result == {"release:add": 1} assert list(swh_storage.journal_writer.journal.objects) == [ ("release", Release.from_dict(data.release)), ("release", Release.from_dict(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_release_get_order(self, swh_storage): add_result = swh_storage.release_add([data.release, data.release2]) assert add_result == {"release:add": 2} # order 1 res1 = swh_storage.release_get([data.release["id"], data.release2["id"]]) assert list(res1) == [data.release, data.release2] # order 2 res2 = swh_storage.release_get([data.release2["id"], data.release["id"]]) assert list(res2) == [data.release2, data.release] def test_release_get_random(self, swh_storage): swh_storage.release_add([data.release, data.release2, data.release3]) assert swh_storage.release_get_random() in { data.release["id"], data.release2["id"], data.release3["id"], } 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"]}) 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] assert actual_origin["url"] == origin1["url"] actual_origin2 = swh_storage.origin_get([{"url": data.origin2["url"],}])[0] 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.journal.objects) == [ ("origin", Origin.from_dict(actual_origin)), ("origin", Origin.from_dict(actual_origin2)), ] swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["origin"] == 2 def test_origin_add_from_generator(self, swh_storage): def _ori_gen(): yield data.origin yield data.origin2 origin1, origin2 = swh_storage.origin_add(_ori_gen()) actual_origin = swh_storage.origin_get([{"url": data.origin["url"],}])[0] assert actual_origin["url"] == origin1["url"] actual_origin2 = swh_storage.origin_get([{"url": data.origin2["url"],}])[0] 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.journal.objects) == [ ("origin", Origin.from_dict(actual_origin)), ("origin", Origin.from_dict(actual_origin2)), ] swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["origin"] == 2 def test_origin_add_twice(self, swh_storage): add1 = swh_storage.origin_add([data.origin, data.origin2]) assert list(swh_storage.journal_writer.journal.objects) == [ ("origin", Origin.from_dict(data.origin)), ("origin", Origin.from_dict(data.origin2)), ] add2 = swh_storage.origin_add([data.origin, data.origin2]) assert list(swh_storage.journal_writer.journal.objects) == [ ("origin", Origin.from_dict(data.origin)), ("origin", Origin.from_dict(data.origin2)), ] assert add1 == add2 def test_origin_add_validation(self, swh_storage): """Incorrect formatted origin should fail the validation """ with pytest.raises(StorageArgumentException, match="url"): swh_storage.origin_add([{}]) with pytest.raises( StorageArgumentException, match="unexpected keyword argument" ): swh_storage.origin_add([{"ul": "mistyped url key"}]) def test_origin_get_legacy(self, swh_storage): assert swh_storage.origin_get(data.origin) is None swh_storage.origin_add_one(data.origin) actual_origin0 = swh_storage.origin_get({"url": data.origin["url"]}) assert actual_origin0["url"] == data.origin["url"] def test_origin_get(self, swh_storage): assert swh_storage.origin_get(data.origin) is None swh_storage.origin_add_one(data.origin) actual_origin0 = swh_storage.origin_get([{"url": data.origin["url"]}]) assert len(actual_origin0) == 1 assert actual_origin0[0]["url"] == data.origin["url"] def _generate_random_visits(self, nb_visits=100, start=0, end=7): """Generate random visits within the last 2 months (to avoid computations) """ visits = [] today = now() for weeks in range(nb_visits, 0, -1): hours = random.randint(0, 24) minutes = random.randint(0, 60) seconds = random.randint(0, 60) days = random.randint(0, 28) weeks = random.randint(start, end) date_visit = today - timedelta( weeks=weeks, hours=hours, minutes=minutes, seconds=seconds, days=days ) visits.append(date_visit) return visits def test_origin_visit_get_random(self, swh_storage): swh_storage.origin_add(data.origins) # Add some random visits within the selection range visits = self._generate_random_visits() visit_type = "git" # Add visits to those origins for origin in data.origins: origin_url = origin["url"] for date_visit in visits: visit = swh_storage.origin_visit_add( origin_url, date=date_visit, type=visit_type ) swh_storage.origin_visit_update( origin_url, visit_id=visit.visit, status="full" ) swh_storage.refresh_stat_counters() stats = swh_storage.stat_counters() assert stats["origin"] == len(data.origins) assert stats["origin_visit"] == len(data.origins) * len(visits) random_origin_visit = swh_storage.origin_visit_get_random(visit_type) assert random_origin_visit assert random_origin_visit["origin"] is not None original_urls = [o["url"] for o in data.origins] assert random_origin_visit["origin"] in original_urls def test_origin_visit_get_random_nothing_found(self, swh_storage): swh_storage.origin_add(data.origins) visit_type = "hg" # Add some visits outside of the random generation selection so nothing # will be found by the random selection visits = self._generate_random_visits(nb_visits=3, start=13, end=24) for origin in data.origins: origin_url = origin["url"] for date_visit in visits: visit = swh_storage.origin_visit_add( origin_url, date=date_visit, type=visit_type ) swh_storage.origin_visit_update(origin_url, visit.visit, status="full") random_origin_visit = swh_storage.origin_visit_get_random(visit_type) assert random_origin_visit is None def test_origin_get_by_sha1(self, swh_storage): assert swh_storage.origin_get(data.origin) is None swh_storage.origin_add_one(data.origin) origins = list(swh_storage.origin_get_by_sha1([sha1(data.origin["url"])])) assert len(origins) == 1 assert origins[0]["url"] == data.origin["url"] def test_origin_get_by_sha1_not_found(self, swh_storage): assert swh_storage.origin_get(data.origin) is None origins = list(swh_storage.origin_get_by_sha1([sha1(data.origin["url"])])) assert len(origins) == 1 assert origins[0] is None 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 def test_origin_visit_add(self, swh_storage): # given origin_url = swh_storage.origin_add_one(data.origin2) date_visit = now() # Round to milliseconds before insertion, so equality doesn't fail # after a round-trip through a DB (eg. Cassandra) date_visit = date_visit.replace(microsecond=round(date_visit.microsecond, -3)) # when origin_visit = swh_storage.origin_visit_add( origin_url, type=data.type_visit1, date=date_visit ) expected_origin_visit = { "origin": origin_url, "date": date_visit, "visit": origin_visit.visit, "type": data.type_visit1, "status": "ongoing", "metadata": None, "snapshot": None, } assert origin_visit == OriginVisit.from_dict(expected_origin_visit) actual_origin_visits = list(swh_storage.origin_visit_get(origin_url)) assert expected_origin_visit in actual_origin_visits objects = list(swh_storage.journal_writer.journal.objects) assert ("origin", Origin.from_dict(data.origin2)) in objects assert ("origin_visit", OriginVisit.from_dict(expected_origin_visit)) in objects def test_origin_visit_get__unknown_origin(self, swh_storage): assert [] == list(swh_storage.origin_visit_get("foo")) def test_origin_visit_add_default_type(self, swh_storage): # given origin_url = swh_storage.origin_add_one(data.origin2) # when date_visit = now() date_visit2 = date_visit + datetime.timedelta(minutes=1) # Round to milliseconds before insertion, so equality doesn't fail # after a round-trip through a DB (eg. Cassandra) date_visit = date_visit.replace(microsecond=round(date_visit.microsecond, -3)) date_visit2 = date_visit2.replace( microsecond=round(date_visit2.microsecond, -3) ) origin_visit1 = swh_storage.origin_visit_add( origin_url, date=date_visit, type=data.type_visit1 ) origin_visit2 = swh_storage.origin_visit_add( origin_url, date=date_visit2, type=data.type_visit2 ) # then assert origin_visit1.origin == origin_url assert origin_visit1.visit is not None actual_origin_visits = list(swh_storage.origin_visit_get(origin_url)) expected_visits = [ { "origin": origin_url, "date": date_visit, "visit": origin_visit1.visit, "type": data.type_visit1, "status": "ongoing", "metadata": None, "snapshot": None, }, { "origin": origin_url, "date": date_visit2, "visit": origin_visit2.visit, "type": data.type_visit2, "status": "ongoing", "metadata": None, "snapshot": None, }, ] assert len(expected_visits) == len(actual_origin_visits) for visit in expected_visits: assert visit in actual_origin_visits objects = list(swh_storage.journal_writer.journal.objects) assert ("origin", Origin.from_dict(data.origin2)) in objects for visit in expected_visits: assert ("origin_visit", OriginVisit.from_dict(visit)) in objects def test_origin_visit_add_validation(self, swh_storage): origin_url = swh_storage.origin_add_one(data.origin2) with pytest.raises(StorageArgumentException) as cm: swh_storage.origin_visit_add(origin_url, date=[b"foo"], type="git") if type(cm.value) == psycopg2.ProgrammingError: assert cm.value.pgcode == psycopg2.errorcodes.UNDEFINED_FUNCTION def test_origin_visit_update(self, swh_storage): # given origin_url = swh_storage.origin_add_one(data.origin) origin_url2 = swh_storage.origin_add_one(data.origin2) # date_visit < date_visit2 date_visit = data.date_visit1 date_visit2 = data.date_visit2 # Round to milliseconds before insertion, so equality doesn't fail # after a round-trip through a DB (eg. Cassandra) date_visit = date_visit.replace(microsecond=round(date_visit.microsecond, -3)) date_visit2 = date_visit2.replace( microsecond=round(date_visit2.microsecond, -3) ) origin_visit1 = swh_storage.origin_visit_add( origin_url, date=date_visit, type=data.type_visit1 ) origin_visit2 = swh_storage.origin_visit_add( origin_url, date=date_visit2, type=data.type_visit2 ) 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_url, "date": date_visit, "visit": origin_visit1.visit, "type": data.type_visit1, "status": "full", "metadata": visit1_metadata, "snapshot": None, }, { "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 actual_origin_visits_bis = list( swh_storage.origin_visit_get(origin_url, limit=1) ) assert actual_origin_visits_bis == [ { "origin": origin_url, "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_url, "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_url2, "date": date_visit2, "visit": origin_visit3.visit, "type": data.type_visit3, "status": "partial", "metadata": None, "snapshot": None, } ] data1 = { "origin": origin_url, "date": date_visit, "visit": origin_visit1.visit, "type": data.type_visit1, "status": "ongoing", "metadata": None, "snapshot": None, } data2 = { "origin": origin_url, "date": date_visit2, "visit": origin_visit2.visit, "type": data.type_visit2, "status": "ongoing", "metadata": None, "snapshot": None, } data3 = { "origin": origin_url2, "date": date_visit2, "visit": origin_visit3.visit, "type": data.type_visit3, "status": "ongoing", "metadata": None, "snapshot": None, } data4 = { "origin": origin_url, "date": date_visit, "visit": origin_visit1.visit, "type": data.type_visit1, "metadata": visit1_metadata, "status": "full", "snapshot": None, } data5 = { "origin": origin_url2, "date": date_visit2, "visit": origin_visit3.visit, "type": data.type_visit3, "status": "partial", "metadata": None, "snapshot": None, } objects = list(swh_storage.journal_writer.journal.objects) assert ("origin", Origin.from_dict(data.origin)) in objects assert ("origin", Origin.from_dict(data.origin2)) in objects assert ("origin_visit", OriginVisit.from_dict(data1)) in objects assert ("origin_visit", OriginVisit.from_dict(data2)) in objects assert ("origin_visit", OriginVisit.from_dict(data3)) in objects assert ("origin_visit", OriginVisit.from_dict(data4)) in objects assert ("origin_visit", OriginVisit.from_dict(data5)) in objects def test_origin_visit_update_validation(self, swh_storage): origin_url = swh_storage.origin_add_one(data.origin) visit = swh_storage.origin_visit_add( origin_url, date=data.date_visit2, type=data.type_visit2 ) with pytest.raises( (StorageArgumentException, ValueError), match="status" ) as cm: swh_storage.origin_visit_update(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 origin_url = swh_storage.origin_add_one(data.origin) swh_storage.origin_visit_add( origin_url, date=data.date_visit2, type=data.type_visit1 ) origin_visit2 = swh_storage.origin_visit_add( origin_url, date=data.date_visit3, type=data.type_visit2 ) origin_visit3 = swh_storage.origin_visit_add( origin_url, date=data.date_visit2, type=data.type_visit3 ) # Simple case visit = swh_storage.origin_visit_find_by_date(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(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) def test_origin_visit_update_missing_snapshot(self, swh_storage): # given origin_url = swh_storage.origin_add_one(data.origin) origin_visit = swh_storage.origin_visit_add( origin_url, date=data.date_visit1, type=data.type_visit1 ) # when swh_storage.origin_visit_update( origin_url, origin_visit.visit, status="ongoing", snapshot=data.snapshot["id"], ) # snapshot does not exist yet # then actual_origin_visit = swh_storage.origin_visit_get_by( 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"] def test_origin_visit_get_by(self, swh_storage): origin_url = swh_storage.origin_add_one(data.origin) origin_url2 = swh_storage.origin_add_one(data.origin2) origin_visit1 = swh_storage.origin_visit_add( origin_url, date=data.date_visit2, type=data.type_visit2 ) swh_storage.snapshot_add([data.snapshot]) swh_storage.origin_visit_update( origin_url, origin_visit1.visit, status="ongoing", snapshot=data.snapshot["id"], ) # Add some other {origin, visit} entries swh_storage.origin_visit_add( origin_url, date=data.date_visit3, type=data.type_visit3 ) swh_storage.origin_visit_add( origin_url2, date=data.date_visit3, 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 ) expected_origin_visit = origin_visit1.to_dict() expected_origin_visit.update( { "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_url, origin_visit1.visit ) # then assert actual_origin_visit1 == expected_origin_visit def test_origin_visit_get_by__unknown_origin(self, swh_storage): assert swh_storage.origin_visit_get_by("foo", 10) is None def test_origin_visit_upsert_new(self, swh_storage): # given origin_url = swh_storage.origin_add_one(data.origin2) # when swh_storage.origin_visit_upsert( [ OriginVisit.from_dict( { "origin": origin_url, "date": data.date_visit2, "visit": 123, "type": data.type_visit2, "status": "full", "metadata": None, "snapshot": None, } ), OriginVisit.from_dict( { "origin": origin_url, "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_url, "date": data.date_visit2, "visit": 123, "type": data.type_visit2, "status": "full", "metadata": None, "snapshot": None, }, { "origin": origin_url, "date": data.date_visit3, "visit": 1234, "type": data.type_visit2, "status": "full", "metadata": None, "snapshot": None, }, ] data1 = { "origin": origin_url, "date": data.date_visit2, "visit": 123, "type": data.type_visit2, "status": "full", "metadata": None, "snapshot": None, } data2 = { "origin": origin_url, "date": data.date_visit3, "visit": 1234, "type": data.type_visit2, "status": "full", "metadata": None, "snapshot": None, } assert list(swh_storage.journal_writer.journal.objects) == [ ("origin", Origin.from_dict(data.origin2)), ("origin_visit", OriginVisit.from_dict(data1)), ("origin_visit", OriginVisit.from_dict(data2)), ] def test_origin_visit_upsert_existing(self, swh_storage): # given origin_url = swh_storage.origin_add_one(data.origin2) # when origin_visit1 = swh_storage.origin_visit_add( origin_url, date=data.date_visit2, type=data.type_visit1 ) swh_storage.origin_visit_upsert( [ OriginVisit.from_dict( { "origin": origin_url, "date": data.date_visit2, "visit": origin_visit1.visit, "type": data.type_visit1, "status": "full", "metadata": None, "snapshot": None, } ) ] ) # then 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_url, "date": data.date_visit2, "visit": origin_visit1.visit, "type": data.type_visit1, "status": "full", "metadata": None, "snapshot": None, } ] data1 = { "origin": origin_url, "date": data.date_visit2, "visit": origin_visit1.visit, "type": data.type_visit1, "status": "ongoing", "metadata": None, "snapshot": None, } data2 = { "origin": origin_url, "date": data.date_visit2, "visit": origin_visit1.visit, "type": data.type_visit1, "status": "full", "metadata": None, "snapshot": None, } assert list(swh_storage.journal_writer.journal.objects) == [ ("origin", Origin.from_dict(data.origin2)), ("origin_visit", OriginVisit.from_dict(data1)), ("origin_visit", OriginVisit.from_dict(data2)), ] def test_origin_visit_upsert_missing_visit_id(self, swh_storage): # given origin_url = swh_storage.origin_add_one(data.origin2) # then with pytest.raises(StorageArgumentException, match="Missing visit id"): swh_storage.origin_visit_upsert( [ OriginVisit.from_dict( { "origin": origin_url, "date": data.date_visit2, "visit": None, # <- make the test raise "type": data.type_visit1, "status": "full", "metadata": None, "snapshot": None, } ) ] ) assert list(swh_storage.journal_writer.journal.objects) == [ ("origin", Origin.from_dict(data.origin2)) ] def test_origin_visit_get_by_no_result(self, swh_storage): 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 def test_origin_visit_get_latest(self, swh_storage): origin_url = swh_storage.origin_add_one(data.origin) ov1 = swh_storage.origin_visit_add( origin_url, date=data.date_visit1, type=data.type_visit1 ) ov2 = swh_storage.origin_visit_add( origin_url, date=data.date_visit2, type=data.type_visit2 ) # Add a visit with the same date as the previous one ov3 = swh_storage.origin_visit_add( origin_url, date=data.date_visit2, type=data.type_visit2 ) origin_visit1 = swh_storage.origin_visit_get_by(origin_url, ov1.visit) origin_visit2 = swh_storage.origin_visit_get_by(origin_url, ov2.visit) origin_visit3 = swh_storage.origin_visit_get_by(origin_url, ov3.visit) # 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, ov1.visit, status="ongoing", 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, ov1.visit, 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, ov2.visit, status="ongoing", 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, ov3.visit, status="ongoing", 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_url = swh_storage.origin_add_one(data.origin) origin_visit1 = swh_storage.origin_visit_add( 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_url, origin_visit1.visit, status="ongoing", 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_url, visit_id) assert by_ov == {**data.empty_snapshot, "next_branch": None} data1 = { "origin": origin_url, "date": data.date_visit1, "visit": origin_visit1.visit, "type": data.type_visit1, "status": "ongoing", "metadata": None, "snapshot": None, } data2 = { "origin": origin_url, "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.journal.objects) == [ ("origin", Origin.from_dict(data.origin)), ("origin_visit", OriginVisit.from_dict(data1)), ("snapshot", Snapshot.from_dict(data.empty_snapshot)), ("origin_visit", OriginVisit.from_dict(data2)), ] def test_snapshot_add_get_complete(self, swh_storage): origin_url = data.origin["url"] origin_url = swh_storage.origin_add_one(data.origin) origin_visit1 = swh_storage.origin_visit_add( 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_url, origin_visit1.visit, status="ongoing", 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_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"] ) swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["snapshot"] == 2 def test_snapshot_add_many_from_generator(self, swh_storage): def _snp_gen(): yield data.snapshot yield data.complete_snapshot actual_result = swh_storage.snapshot_add(_snp_gen()) assert actual_result == {"snapshot:add": 2} swh_storage.refresh_stat_counters() assert swh_storage.stat_counters()["snapshot"] == 2 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.journal.objects) == [ ("snapshot", Snapshot.from_dict(data.empty_snapshot)) ] actual_result = swh_storage.snapshot_add([data.snapshot]) assert actual_result == {"snapshot:add": 1} assert list(swh_storage.journal_writer.journal.objects) == [ ("snapshot", Snapshot.from_dict(data.empty_snapshot)), ("snapshot", Snapshot.from_dict(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(StorageArgumentException, match="target"): swh_storage.snapshot_add([snap]) snap = copy.deepcopy(data.snapshot) snap["branches"][b"foo"] = {"target": b"\x42" * 20} with pytest.raises(StorageArgumentException, 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_url = swh_storage.origin_add_one(data.origin) origin_visit1 = swh_storage.origin_visit_add( origin_url, date=data.date_visit1, type=data.type_visit1 ) swh_storage.snapshot_add([data.complete_snapshot]) swh_storage.origin_visit_update( origin_url, origin_visit1.visit, status="ongoing", 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_url = swh_storage.origin_add_one(data.origin) origin_visit1 = swh_storage.origin_visit_add( 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_url, origin_visit1.visit, status="ongoing", 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_url, visit_id) assert by_ov == {**data.snapshot, "next_branch": None} origin_visit_info = swh_storage.origin_visit_get_by(origin_url, visit_id) assert origin_visit_info["snapshot"] == data.snapshot["id"] def test_snapshot_add_nonexistent_visit(self, swh_storage): origin_url = swh_storage.origin_add_one(data.origin) # unknown visit visit_id = 54164461156 swh_storage.journal_writer.journal.objects[:] = [] swh_storage.snapshot_add([data.snapshot]) with pytest.raises(StorageArgumentException): swh_storage.origin_visit_update( origin_url, visit_id, status="ongoing", snapshot=data.snapshot["id"] ) assert list(swh_storage.journal_writer.journal.objects) == [ ("snapshot", Snapshot.from_dict(data.snapshot)) ] def test_snapshot_add_twice__by_origin_visit(self, swh_storage): origin_url = swh_storage.origin_add_one(data.origin) origin_visit1 = swh_storage.origin_visit_add( 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_url, origin_visit1.visit, status="ongoing", snapshot=data.snapshot["id"], ) by_ov1 = swh_storage.snapshot_get_by_origin_visit(origin_url, visit1_id) assert by_ov1 == {**data.snapshot, "next_branch": None} origin_visit2 = swh_storage.origin_visit_add( 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_url, origin_visit2.visit, status="ongoing", snapshot=data.snapshot["id"], ) by_ov2 = swh_storage.snapshot_get_by_origin_visit(origin_url, visit2_id) assert by_ov2 == {**data.snapshot, "next_branch": None} data1 = { "origin": origin_url, "date": data.date_visit1, "visit": origin_visit1.visit, "type": data.type_visit1, "status": "ongoing", "metadata": None, "snapshot": None, } data2 = { "origin": origin_url, "date": data.date_visit1, "visit": origin_visit1.visit, "type": data.type_visit1, "status": "ongoing", "metadata": None, "snapshot": data.snapshot["id"], } data3 = { "origin": origin_url, "date": data.date_visit2, "visit": origin_visit2.visit, "type": data.type_visit2, "status": "ongoing", "metadata": None, "snapshot": None, } data4 = { "origin": origin_url, "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.journal.objects) == [ ("origin", Origin.from_dict(data.origin)), ("origin_visit", OriginVisit.from_dict(data1)), ("snapshot", Snapshot.from_dict(data.snapshot)), ("origin_visit", OriginVisit.from_dict(data2)), ("origin_visit", OriginVisit.from_dict(data3)), ("origin_visit", OriginVisit.from_dict(data4)), ] def test_snapshot_get_latest(self, swh_storage): origin_url = swh_storage.origin_add_one(data.origin) origin_visit1 = swh_storage.origin_visit_add( origin_url, date=data.date_visit1, type=data.type_visit1 ) origin_visit2 = swh_storage.origin_visit_add( origin_url, date=data.date_visit2, type=data.type_visit2 ) # Add a visit with the same date as the previous one origin_visit3 = swh_storage.origin_visit_add( origin_url, date=data.date_visit2, type=data.type_visit3 ) # 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_url, origin_visit1.visit, status="ongoing", 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_url, origin_visit1.visit, 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_url, origin_visit2.visit, status="ongoing", snapshot=data.empty_snapshot["id"], ) assert { **data.empty_snapshot, "next_branch": None, } == 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_url, origin_visit3.visit, status="ongoing", snapshot=data.complete_snapshot["id"], ) assert { **data.complete_snapshot, "next_branch": None, } == swh_storage.snapshot_get_latest(origin_url) def test_snapshot_get_latest__missing_snapshot(self, swh_storage): origin_url = swh_storage.origin_add_one(data.origin) assert swh_storage.snapshot_get_latest(origin_url) is None origin_visit1 = swh_storage.origin_visit_add( origin_url, date=data.date_visit1, type=data.type_visit1 ) origin_visit2 = swh_storage.origin_visit_add( origin_url, date=data.date_visit2, type=data.type_visit2 ) # 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, origin_visit1.visit, status="ongoing", snapshot=data.complete_snapshot["id"], ) with pytest.raises(Exception): # XXX: should the exception be more specific than this? 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, origin_visit1.visit, status="full") with pytest.raises(Exception): # XXX: should the exception be more specific than this? 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, origin_visit2.visit, status="ongoing", snapshot=data.snapshot["id"], ) with pytest.raises(Exception): # XXX: should the exception be more specific than this? 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_snapshot_get_random(self, swh_storage): swh_storage.snapshot_add( [data.snapshot, data.empty_snapshot, data.complete_snapshot] ) assert swh_storage.snapshot_get_random() in { data.snapshot["id"], data.empty_snapshot["id"], data.complete_snapshot["id"], } def test_snapshot_missing(self, swh_storage): snap = data.snapshot missing_snap = data.empty_snapshot snapshots = [snap["id"], missing_snap["id"]] swh_storage.snapshot_add([snap]) missing_snapshots = swh_storage.snapshot_missing(snapshots) assert list(missing_snapshots) == [missing_snap["id"]] 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. origin_url = swh_storage.origin_add_one(data.origin2) origin_visit1 = swh_storage.origin_visit_add( origin_url, date=data.date_visit2, type=data.type_visit2 ) swh_storage.snapshot_add([data.snapshot]) swh_storage.origin_visit_update( origin_url, origin_visit1.visit, status="ongoing", 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"] ctime = now() cont["ctime"] = ctime 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"] - ctime 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(StorageArgumentException): swh_storage.content_find({}) # empty is bad # 2. with bad input with pytest.raises(StorageArgumentException): 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",} ] swh_storage.directory_add([data.dir]) sha1_gits.append(data.dir["id"]) expected[data.dir["id"]] = [{"sha1_git": data.dir["id"], "type": "directory",}] swh_storage.revision_add([data.revision]) sha1_gits.append(data.revision["id"]) expected[data.revision["id"]] = [ {"sha1_git": data.revision["id"], "type": "revision",} ] swh_storage.release_add([data.release]) sha1_gits.append(data.release["id"]) expected[data.release["id"]] = [ {"sha1_git": data.release["id"], "type": "release",} ] ret = swh_storage.object_find_by_sha1_git(sha1_gits) 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"] def test_origin_metadata_add(self, swh_storage): # given 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 n_om = len(list(swh_storage.origin_metadata_get_by(origin["url"]))) swh_storage.origin_metadata_add( origin["url"], data.origin_metadata["discovery_date"], provider["id"], tool["id"], data.origin_metadata["metadata"], ) swh_storage.origin_metadata_add( 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["url"]))) # then assert n_actual_om == n_om + 2 def test_origin_metadata_get(self, swh_storage): # given 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_url, data.origin_metadata["discovery_date"], provider["id"], tool["id"], data.origin_metadata["metadata"], ) swh_storage.origin_metadata_add( origin_url2, data.origin_metadata2["discovery_date"], provider["id"], tool["id"], data.origin_metadata2["metadata"], ) swh_storage.origin_metadata_add( 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_url), key=lambda x: x["discovery_date"], ) ) metadatas_for_origin2 = list(swh_storage.origin_metadata_get_by(origin_url2)) expected_results = [ { "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_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_metadata_provider_add_idempotent(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 = swh_storage.metadata_provider_add(**provider) + + expected_provider = {**provider, "id": provider_id} + assert expected_provider == swh_storage.metadata_provider_get_by( + {"provider_name": "swMATH", "provider_url": "http://www.swmath.org/"} + ) + assert expected_provider == swh_storage.metadata_provider_get(provider_id) + + provider_id2 = swh_storage.metadata_provider_add(**provider) + assert provider_id2 == provider_id + def test_origin_metadata_get_by_provider_type(self, swh_storage): # given 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_url, data.origin_metadata["discovery_date"], provider1["id"], tool["id"], data.origin_metadata["metadata"], ) swh_storage.origin_metadata_add( 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_url2, provider_type) ) for item in m_by_provider: if "id" in item: del item["id"] expected_results = [ { "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: 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 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 meta_contents = swh_storage.content_get_metadata(get_sha1s) assert len(list(meta_contents)) == len(get_sha1s) actual_contents = [] for contents in meta_contents.values(): actual_contents.extend(contents) keys_to_check = {"length", "status", "sha1", "sha1_git", "sha256", "blake2s256"} 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 returns complete range""" 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: 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: 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(StorageArgumentException) as e: swh_storage.content_get_range(start=None, end=None, limit=None) assert e.value.args == ("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""" # 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"] 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]] 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 assert_contents_ok([contents_map[get_sha1s[-1]]], actual_contents2, ["sha1"]) def test_origin_get_range_from_zero(self, swh_storage, swh_origins): 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"] @pytest.mark.parametrize( "origin_from,origin_count", [(1, 1), (1, 10), (1, 20), (1, 101), (11, 0), (11, 10), (91, 11)], ) def test_origin_get_range( self, swh_storage, swh_origins, origin_from, origin_count ): actual_origins = list( swh_storage.origin_get_range( origin_from=origin_from, origin_count=origin_count ) ) origins_with_id = list(enumerate(swh_origins, start=1)) expected_origins = [ {"url": origin["url"], "id": origin_id,} for (origin_id, origin) in origins_with_id[ origin_from - 1 : origin_from + origin_count - 1 ] ] assert actual_origins == expected_origins @pytest.mark.parametrize("limit", [1, 7, 10, 100, 1000]) def test_origin_list(self, swh_storage, swh_origins, limit): returned_origins = [] page_token = None i = 0 while True: result = swh_storage.origin_list(page_token=page_token, limit=limit) assert len(result["origins"]) <= limit returned_origins.extend(origin["url"] for origin in result["origins"]) i += 1 page_token = result.get("next_page_token") if page_token is None: assert i * limit >= len(swh_origins) break else: assert len(result["origins"]) == limit expected_origins = [origin["url"] for origin in swh_origins] assert sorted(returned_origins) == sorted(expected_origins) ORIGINS = [ "https://github.com/user1/repo1", "https://github.com/user2/repo1", "https://github.com/user3/repo1", "https://gitlab.com/user1/repo1", "https://gitlab.com/user2/repo1", "https://forge.softwareheritage.org/source/repo1", ] def test_origin_count(self, swh_storage): swh_storage.origin_add([{"url": url} for url in self.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 def test_origin_count_with_visit_no_visits(self, swh_storage): swh_storage.origin_add([{"url": url} for url in self.ORIGINS]) # none of them have visits, so with_visit=True => 0 assert swh_storage.origin_count("github", with_visit=True) == 0 assert swh_storage.origin_count("gitlab", with_visit=True) == 0 assert swh_storage.origin_count(".*user.*", regexp=True, with_visit=True) == 0 assert swh_storage.origin_count(".*user.*", regexp=False, with_visit=True) == 0 assert swh_storage.origin_count(".*user1.*", regexp=True, with_visit=True) == 0 assert swh_storage.origin_count(".*user1.*", regexp=False, with_visit=True) == 0 def test_origin_count_with_visit_with_visits_no_snapshot(self, swh_storage): swh_storage.origin_add([{"url": url} for url in self.ORIGINS]) origin_url = "https://github.com/user1/repo1" swh_storage.origin_visit_add(origin_url, date=now(), type="git") assert swh_storage.origin_count("github", with_visit=False) == 3 # it has a visit, but no snapshot, so with_visit=True => 0 assert swh_storage.origin_count("github", with_visit=True) == 0 assert swh_storage.origin_count("gitlab", with_visit=False) == 2 # these gitlab origins have no visit assert swh_storage.origin_count("gitlab", with_visit=True) == 0 assert ( swh_storage.origin_count("github.*user1", regexp=True, with_visit=False) == 1 ) assert ( swh_storage.origin_count("github.*user1", regexp=True, with_visit=True) == 0 ) assert swh_storage.origin_count("github", regexp=True, with_visit=True) == 0 def test_origin_count_with_visit_with_visits_and_snapshot(self, swh_storage): swh_storage.origin_add([{"url": url} for url in self.ORIGINS]) swh_storage.snapshot_add([data.snapshot]) origin_url = "https://github.com/user1/repo1" visit = swh_storage.origin_visit_add(origin_url, date=now(), type="git") swh_storage.origin_visit_update( origin_url, visit.visit, status="ongoing", snapshot=data.snapshot["id"] ) assert swh_storage.origin_count("github", with_visit=False) == 3 # github/user1 has a visit and a snapshot, so with_visit=True => 1 assert swh_storage.origin_count("github", with_visit=True) == 1 assert ( swh_storage.origin_count("github.*user1", regexp=True, with_visit=False) == 1 ) assert ( swh_storage.origin_count("github.*user1", regexp=True, with_visit=True) == 1 ) assert swh_storage.origin_count("github", regexp=True, with_visit=True) == 1 @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_url = obj.pop("origin") swh_storage.origin_add_one({"url": origin_url}) if "visit" in obj: del obj["visit"] swh_storage.origin_visit_add(origin_url, obj["date"], obj["type"]) elif obj_type == "origin_visit_update": # internal object for now, they don't have a storage # endpoint yet continue else: if obj_type == "content" and obj["status"] == "absent": obj_type = "skipped_content" method = getattr(swh_storage, obj_type + "_add") try: method([obj]) except HashCollision: pass @pytest.mark.db class TestLocalStorage: """Test the local storage""" # 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.content_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_with_new_cols(self, swh_storage): swh_storage.journal_writer.journal = 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"], } if hasattr(swh_storage, "objstorage"): assert cont["sha1"] in swh_storage.objstorage.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"] contents = [ obj for (obj_type, obj) in swh_storage.journal_writer.journal.objects if obj_type == "content" ] assert len(contents) == 1 for obj in contents: obj_d = obj.to_dict() del obj_d["ctime"] assert obj_d == expected_cont def test_content_add_metadata_db(self, swh_storage): cont = data.cont del cont["data"] cont["ctime"] = now() actual_result = swh_storage.content_add_metadata([cont]) assert actual_result == { "content:add": 1, } if hasattr(swh_storage, "objstorage"): assert cont["sha1"] not in swh_storage.objstorage.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", ) contents = [ obj for (obj_type, obj) in swh_storage.journal_writer.journal.objects if obj_type == "content" ] assert len(contents) == 1 for obj in contents: obj_d = obj.to_dict() assert obj_d == 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.skipped_content_add([cont, cont, cont2]) assert 2 <= actual_result.pop("skipped_content:add") <= 3 assert actual_result == {} 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", ) def test_clear_buffers(self, swh_storage): """Calling clear buffers on real storage does nothing """ assert swh_storage.clear_buffers() is None def test_flush(self, swh_storage): """Calling clear buffers on real storage does nothing """ assert swh_storage.flush() == {}