diff --git a/sql/upgrades/133.sql b/sql/upgrades/133.sql
new file mode 100644
index 000000000..34c4931c8
--- /dev/null
+++ b/sql/upgrades/133.sql
@@ -0,0 +1,12 @@
+-- SWH DB schema upgrade
+-- from_version: 132
+-- to_version: 133
+-- description: Use sha1 instead of bigint as FK from origin_visit to snapshot (part 3: remove old column)
+
+insert into dbversion(version, release, description)
+      values(133, now(), 'Work In Progress');
+
+drop index constraint origin_visit_snapshot_id_fkey;
+alter table origin_visit drop column snapshot_id;
+
+drop function swh_snapshot_get_by_origin_visit;
diff --git a/swh/storage/db.py b/swh/storage/db.py
index 018d9a868..9bb3cd711 100644
--- a/swh/storage/db.py
+++ b/swh/storage/db.py
@@ -1,886 +1,880 @@
 # Copyright (C) 2015-2019  The Software Heritage developers
 # See the AUTHORS file at the top-level directory of this distribution
 # License: GNU General Public License version 3, or any later version
 # See top-level LICENSE file for more information
 
 import select
 
 from swh.core.db import BaseDb
 from swh.core.db.db_utils import stored_procedure, jsonize
 from swh.core.db.db_utils import execute_values_generator
 
 
 class Db(BaseDb):
     """Proxy to the SWH DB, with wrappers around stored procedures
 
     """
     def mktemp_dir_entry(self, entry_type, cur=None):
         self._cursor(cur).execute('SELECT swh_mktemp_dir_entry(%s)',
                                   (('directory_entry_%s' % entry_type),))
 
     @stored_procedure('swh_mktemp_revision')
     def mktemp_revision(self, cur=None): pass
 
     @stored_procedure('swh_mktemp_release')
     def mktemp_release(self, cur=None): pass
 
     @stored_procedure('swh_mktemp_snapshot_branch')
     def mktemp_snapshot_branch(self, cur=None): pass
 
     def register_listener(self, notify_queue, cur=None):
         """Register a listener for NOTIFY queue `notify_queue`"""
         self._cursor(cur).execute("LISTEN %s" % notify_queue)
 
     def listen_notifies(self, timeout):
         """Listen to notifications for `timeout` seconds"""
         if select.select([self.conn], [], [], timeout) == ([], [], []):
             return
         else:
             self.conn.poll()
             while self.conn.notifies:
                 yield self.conn.notifies.pop(0)
 
     @stored_procedure('swh_content_add')
     def content_add_from_temp(self, cur=None): pass
 
     @stored_procedure('swh_directory_add')
     def directory_add_from_temp(self, cur=None): pass
 
     @stored_procedure('swh_skipped_content_add')
     def skipped_content_add_from_temp(self, cur=None): pass
 
     @stored_procedure('swh_revision_add')
     def revision_add_from_temp(self, cur=None): pass
 
     @stored_procedure('swh_release_add')
     def release_add_from_temp(self, cur=None): pass
 
     def content_update_from_temp(self, keys_to_update, cur=None):
         cur = self._cursor(cur)
         cur.execute("""select swh_content_update(ARRAY[%s] :: text[])""" %
                     keys_to_update)
 
     content_get_metadata_keys = [
         'sha1', 'sha1_git', 'sha256', 'blake2s256', 'length', 'status']
 
     skipped_content_keys = [
         'sha1', 'sha1_git', 'sha256', 'blake2s256',
         'length', 'reason', 'status', 'origin']
 
     def content_get_metadata_from_sha1s(self, sha1s, cur=None):
         cur = self._cursor(cur)
 
         yield from execute_values_generator(
             cur, """
             select t.sha1, %s from (values %%s) as t (sha1)
             left join content using (sha1)
             """ % ', '.join(self.content_get_metadata_keys[1:]),
             ((sha1,) for sha1 in sha1s),
         )
 
     def content_get_range(self, start, end, limit=None, cur=None):
         """Retrieve contents within range [start, end].
 
         """
         cur = self._cursor(cur)
         query = """select %s from content
                    where %%s <= sha1 and sha1 <= %%s
                    order by sha1
                    limit %%s""" % ', '.join(self.content_get_metadata_keys)
         cur.execute(query, (start, end, limit))
         yield from cur
 
     content_hash_keys = ['sha1', 'sha1_git', 'sha256', 'blake2s256']
 
     def content_missing_from_list(self, contents, cur=None):
         cur = self._cursor(cur)
 
         keys = ', '.join(self.content_hash_keys)
         equality = ' AND '.join(
             ('t.%s = c.%s' % (key, key))
             for key in self.content_hash_keys
         )
 
         yield from execute_values_generator(
             cur, """
             SELECT %s
             FROM (VALUES %%s) as t(%s)
             WHERE NOT EXISTS (
                 SELECT 1 FROM content c
                 WHERE %s
             )
             """ % (keys, keys, equality),
             (tuple(c[key] for key in self.content_hash_keys) for c in contents)
         )
 
     def content_missing_per_sha1(self, sha1s, cur=None):
         cur = self._cursor(cur)
 
         yield from execute_values_generator(cur, """
         SELECT t.sha1 FROM (VALUES %s) AS t(sha1)
         WHERE NOT EXISTS (
             SELECT 1 FROM content c WHERE c.sha1 = t.sha1
         )""", ((sha1,) for sha1 in sha1s))
 
     def skipped_content_missing_from_temp(self, cur=None):
         cur = self._cursor(cur)
 
         cur.execute("""SELECT sha1, sha1_git, sha256, blake2s256
                        FROM swh_skipped_content_missing()""")
 
         yield from cur
 
     def snapshot_exists(self, snapshot_id, cur=None):
         """Check whether a snapshot with the given id exists"""
         cur = self._cursor(cur)
 
         cur.execute("""SELECT 1 FROM snapshot where id=%s""", (snapshot_id,))
 
         return bool(cur.fetchone())
 
     def snapshot_add(self, snapshot_id, cur=None):
         """Add a snapshot from the temporary table"""
         cur = self._cursor(cur)
 
         cur.execute("""SELECT swh_snapshot_add(%s)""", (snapshot_id,))
 
     snapshot_count_cols = ['target_type', 'count']
 
     def snapshot_count_branches(self, snapshot_id, cur=None):
         cur = self._cursor(cur)
         query = """\
            SELECT %s FROM swh_snapshot_count_branches(%%s)
         """ % ', '.join(self.snapshot_count_cols)
 
         cur.execute(query, (snapshot_id,))
 
         yield from cur
 
     snapshot_get_cols = ['snapshot_id', 'name', 'target', 'target_type']
 
     def snapshot_get_by_id(self, snapshot_id, branches_from=b'',
                            branches_count=None, target_types=None,
                            cur=None):
         cur = self._cursor(cur)
         query = """\
            SELECT %s
            FROM swh_snapshot_get_by_id(%%s, %%s, %%s, %%s :: snapshot_target[])
         """ % ', '.join(self.snapshot_get_cols)
 
         cur.execute(query, (snapshot_id, branches_from, branches_count,
                             target_types))
 
         yield from cur
 
     def snapshot_get_by_origin_visit(self, origin_id, visit_id, cur=None):
         cur = self._cursor(cur)
         query = """\
            SELECT snapshot from origin_visit where
            origin_visit.origin=%s and origin_visit.visit=%s;
         """
 
         cur.execute(query, (origin_id, visit_id))
         ret = cur.fetchone()
         if ret:
             return ret[0]
 
     content_find_cols = ['sha1', 'sha1_git', 'sha256', 'blake2s256', 'length',
                          'ctime', 'status']
 
     def content_find(self, sha1=None, sha1_git=None, sha256=None,
                      blake2s256=None, cur=None):
         """Find the content optionally on a combination of the following
         checksums sha1, sha1_git, sha256 or blake2s256.
 
         Args:
             sha1: sha1 content
             git_sha1: the sha1 computed `a la git` sha1 of the content
             sha256: sha256 content
             blake2s256: blake2s256 content
 
         Returns:
             The tuple (sha1, sha1_git, sha256, blake2s256) if found or None.
 
         """
         cur = self._cursor(cur)
 
         cur.execute("""SELECT %s
                        FROM swh_content_find(%%s, %%s, %%s, %%s)
                        LIMIT 1""" % ','.join(self.content_find_cols),
                     (sha1, sha1_git, sha256, blake2s256))
 
         content = cur.fetchone()
         if set(content) == {None}:
             return None
         else:
             return content
 
     def directory_missing_from_list(self, directories, cur=None):
         cur = self._cursor(cur)
         yield from execute_values_generator(
             cur, """
             SELECT id FROM (VALUES %s) as t(id)
             WHERE NOT EXISTS (
                 SELECT 1 FROM directory d WHERE d.id = t.id
             )
             """, ((id,) for id in directories))
 
     directory_ls_cols = ['dir_id', 'type', 'target', 'name', 'perms',
                          'status', 'sha1', 'sha1_git', 'sha256', 'length']
 
     def directory_walk_one(self, directory, cur=None):
         cur = self._cursor(cur)
         cols = ', '.join(self.directory_ls_cols)
         query = 'SELECT %s FROM swh_directory_walk_one(%%s)' % cols
         cur.execute(query, (directory,))
         yield from cur
 
     def directory_walk(self, directory, cur=None):
         cur = self._cursor(cur)
         cols = ', '.join(self.directory_ls_cols)
         query = 'SELECT %s FROM swh_directory_walk(%%s)' % cols
         cur.execute(query, (directory,))
         yield from cur
 
     def directory_entry_get_by_path(self, directory, paths, cur=None):
         """Retrieve a directory entry by path.
 
         """
         cur = self._cursor(cur)
 
         cols = ', '.join(self.directory_ls_cols)
         query = (
             'SELECT %s FROM swh_find_directory_entry_by_path(%%s, %%s)' % cols)
         cur.execute(query, (directory, paths))
 
         data = cur.fetchone()
         if set(data) == {None}:
             return None
         return data
 
     def revision_missing_from_list(self, revisions, cur=None):
         cur = self._cursor(cur)
 
         yield from execute_values_generator(
             cur, """
             SELECT id FROM (VALUES %s) as t(id)
             WHERE NOT EXISTS (
                 SELECT 1 FROM revision r WHERE r.id = t.id
             )
             """, ((id,) for id in revisions))
 
     revision_add_cols = [
         'id', 'date', 'date_offset', 'date_neg_utc_offset', 'committer_date',
         'committer_date_offset', 'committer_date_neg_utc_offset', 'type',
         'directory', 'message', 'author_fullname', 'author_name',
         'author_email', 'committer_fullname', 'committer_name',
         'committer_email', 'metadata', 'synthetic',
     ]
 
     revision_get_cols = revision_add_cols + [
         'author_id', 'committer_id', 'parents']
 
     def origin_visit_add(self, origin, ts, cur=None):
         """Add a new origin_visit for origin origin at timestamp ts with
         status 'ongoing'.
 
         Args:
             origin: origin concerned by the visit
             ts: the date of the visit
 
         Returns:
             The new visit index step for that origin
 
         """
         cur = self._cursor(cur)
         self._cursor(cur).execute('SELECT swh_origin_visit_add(%s, %s)',
                                   (origin, ts))
         return cur.fetchone()[0]
 
     def origin_visit_update(self, origin_id, visit_id, updates, cur=None):
         """Update origin_visit's status."""
         cur = self._cursor(cur)
         update_cols = []
         values = []
         where = ['origin=%s AND visit=%s']
         where_values = [origin_id, visit_id]
         from_ = ''
         if 'status' in updates:
             update_cols.append('status=%s')
             values.append(updates.pop('status'))
         if 'metadata' in updates:
             update_cols.append('metadata=%s')
             values.append(jsonize(updates.pop('metadata')))
         if 'snapshot' in updates:
-            # New 'snapshot' column
             update_cols.append('snapshot=%s')
             values.append(updates.pop('snapshot'))
-
-            # Old 'snapshot_id' column
-            update_cols.append('snapshot_id=snapshot.object_id')
-            from_ = 'FROM snapshot'
-            where.append('snapshot.id=%s')
-            where_values.append()
         assert not updates, 'Unknown fields: %r' % updates
         query = """UPDATE origin_visit
                     SET {update_cols}
                     {from}
                     WHERE {where}""".format(**{
             'update_cols': ', '.join(update_cols),
             'from': from_,
             'where': ' AND '.join(where)
         })
         cur.execute(query, (*values, *where_values))
 
     origin_visit_get_cols = ['origin', 'visit', 'date', 'status', 'metadata',
                              'snapshot']
 
     def origin_visit_get_all(self, origin_id,
                              last_visit=None, limit=None, cur=None):
         """Retrieve all visits for origin with id origin_id.
 
         Args:
             origin_id: The occurrence's origin
 
         Yields:
             The occurrence's history visits
 
         """
         cur = self._cursor(cur)
 
         if last_visit:
             extra_condition = 'and visit > %s'
             args = (origin_id, last_visit, limit)
         else:
             extra_condition = ''
             args = (origin_id, limit)
 
         query = """\
         SELECT %s
         FROM origin_visit
         WHERE origin=%%s %s
         order by visit asc
         limit %%s""" % (
             ', '.join(self.origin_visit_get_cols), extra_condition
         )
 
         cur.execute(query, args)
 
         yield from cur
 
     def origin_visit_get(self, origin_id, visit_id, cur=None):
         """Retrieve information on visit visit_id of origin origin_id.
 
         Args:
             origin_id: the origin concerned
             visit_id: The visit step for that origin
 
         Returns:
             The origin_visit information
 
         """
         cur = self._cursor(cur)
 
         query = """\
             SELECT %s
             FROM origin_visit
             WHERE origin = %%s AND visit = %%s
             """ % (', '.join(self.origin_visit_get_cols))
 
         cur.execute(query, (origin_id, visit_id))
         r = cur.fetchall()
         if not r:
             return None
         return r[0]
 
     def origin_visit_exists(self, origin_id, visit_id, cur=None):
         """Check whether an origin visit with the given ids exists"""
         cur = self._cursor(cur)
 
         query = "SELECT 1 FROM origin_visit where origin = %s AND visit = %s"
 
         cur.execute(query, (origin_id, visit_id))
 
         return bool(cur.fetchone())
 
     def origin_visit_get_latest_snapshot(self, origin_id,
                                          allowed_statuses=None,
                                          cur=None):
         """Retrieve the most recent origin_visit which references a snapshot
 
         Args:
             origin_id: the origin concerned
             allowed_statuses: the visit statuses allowed for the returned visit
 
         Returns:
             The origin_visit information, or None if no visit matches.
         """
         cur = self._cursor(cur)
 
         extra_clause = ""
         if allowed_statuses:
             extra_clause = cur.mogrify("AND status IN %s",
                                        (tuple(allowed_statuses),)).decode()
 
         query = """\
             SELECT %s
             FROM origin_visit
+            INNER JOIN snapshot ON (origin_visit.snapshot=snapshot.id)
             WHERE
                 origin = %%s AND snapshot is not null %s
             ORDER BY date DESC, visit DESC
             LIMIT 1
             """ % (', '.join(self.origin_visit_get_cols), extra_clause)
 
         cur.execute(query, (origin_id,))
         r = cur.fetchone()
         if not r:
             return None
         return r
 
     @staticmethod
     def mangle_query_key(key, main_table):
         if key == 'id':
             return 't.id'
         if key == 'parents':
             return '''
             ARRAY(
             SELECT rh.parent_id::bytea
             FROM revision_history rh
             WHERE rh.id = t.id
             ORDER BY rh.parent_rank
             )'''
         if '_' not in key:
             return '%s.%s' % (main_table, key)
 
         head, tail = key.split('_', 1)
         if (head in ('author', 'committer')
                 and tail in ('name', 'email', 'id', 'fullname')):
             return '%s.%s' % (head, tail)
 
         return '%s.%s' % (main_table, key)
 
     def revision_get_from_list(self, revisions, cur=None):
         cur = self._cursor(cur)
 
         query_keys = ', '.join(
             self.mangle_query_key(k, 'revision')
             for k in self.revision_get_cols
         )
 
         yield from execute_values_generator(
             cur, """
             SELECT %s FROM (VALUES %%s) as t(id)
             LEFT JOIN revision ON t.id = revision.id
             LEFT JOIN person author ON revision.author = author.id
             LEFT JOIN person committer ON revision.committer = committer.id
             """ % query_keys,
             ((id,) for id in revisions))
 
     def revision_log(self, root_revisions, limit=None, cur=None):
         cur = self._cursor(cur)
 
         query = """SELECT %s
                    FROM swh_revision_log(%%s, %%s)
                 """ % ', '.join(self.revision_get_cols)
 
         cur.execute(query, (root_revisions, limit))
         yield from cur
 
     revision_shortlog_cols = ['id', 'parents']
 
     def revision_shortlog(self, root_revisions, limit=None, cur=None):
         cur = self._cursor(cur)
 
         query = """SELECT %s
                    FROM swh_revision_list(%%s, %%s)
                 """ % ', '.join(self.revision_shortlog_cols)
 
         cur.execute(query, (root_revisions, limit))
         yield from cur
 
     def release_missing_from_list(self, releases, cur=None):
         cur = self._cursor(cur)
         yield from execute_values_generator(
             cur, """
             SELECT id FROM (VALUES %s) as t(id)
             WHERE NOT EXISTS (
                 SELECT 1 FROM release r WHERE r.id = t.id
             )
             """, ((id,) for id in releases))
 
     object_find_by_sha1_git_cols = ['sha1_git', 'type', 'id', 'object_id']
 
     def object_find_by_sha1_git(self, ids, cur=None):
         cur = self._cursor(cur)
 
         yield from execute_values_generator(
             cur, """
             WITH t (id) AS (VALUES %s),
             known_objects as ((
                 select
                   id as sha1_git,
                   'release'::object_type as type,
                   id,
                   object_id
                 from release r
                 where exists (select 1 from t where t.id = r.id)
             ) union all (
                 select
                   id as sha1_git,
                   'revision'::object_type as type,
                   id,
                   object_id
                 from revision r
                 where exists (select 1 from t where t.id = r.id)
             ) union all (
                 select
                   id as sha1_git,
                   'directory'::object_type as type,
                   id,
                   object_id
                 from directory d
                 where exists (select 1 from t where t.id = d.id)
             ) union all (
                 select
                   sha1_git as sha1_git,
                   'content'::object_type as type,
                   sha1 as id,
                   object_id
                 from content c
                 where exists (select 1 from t where t.id = c.sha1_git)
             ))
             select t.id as sha1_git, k.type, k.id, k.object_id
             from t
             left join known_objects k on t.id = k.sha1_git
             """,
             ((id,) for id in ids)
         )
 
     def stat_counters(self, cur=None):
         cur = self._cursor(cur)
         cur.execute('SELECT * FROM swh_stat_counters()')
         yield from cur
 
     fetch_history_cols = ['origin', 'date', 'status', 'result', 'stdout',
                           'stderr', 'duration']
 
     def create_fetch_history(self, fetch_history, cur=None):
         """Create a fetch_history entry with the data in fetch_history"""
         cur = self._cursor(cur)
         query = '''INSERT INTO fetch_history (%s)
                    VALUES (%s) RETURNING id''' % (
             ','.join(self.fetch_history_cols),
             ','.join(['%s'] * len(self.fetch_history_cols))
         )
         cur.execute(query, [fetch_history.get(col) for col in
                             self.fetch_history_cols])
 
         return cur.fetchone()[0]
 
     def get_fetch_history(self, fetch_history_id, cur=None):
         """Get a fetch_history entry with the given id"""
         cur = self._cursor(cur)
         query = '''SELECT %s FROM fetch_history WHERE id=%%s''' % (
             ', '.join(self.fetch_history_cols),
         )
         cur.execute(query, (fetch_history_id,))
 
         data = cur.fetchone()
 
         if not data:
             return None
 
         ret = {'id': fetch_history_id}
         for i, col in enumerate(self.fetch_history_cols):
             ret[col] = data[i]
 
         return ret
 
     def update_fetch_history(self, fetch_history, cur=None):
         """Update the fetch_history entry from the data in fetch_history"""
         cur = self._cursor(cur)
         query = '''UPDATE fetch_history
                    SET %s
                    WHERE id=%%s''' % (
             ','.join('%s=%%s' % col for col in self.fetch_history_cols)
         )
         cur.execute(query, [jsonize(fetch_history.get(col)) for col in
                             self.fetch_history_cols + ['id']])
 
     def origin_add(self, type, url, cur=None):
         """Insert a new origin and return the new identifier."""
         insert = """INSERT INTO origin (type, url) values (%s, %s)
                     RETURNING id"""
 
         cur.execute(insert, (type, url))
         return cur.fetchone()[0]
 
     origin_cols = ['id', 'type', 'url']
 
     def origin_get_with(self, origins, cur=None):
         """Retrieve the origin id from its type and url if found."""
         cur = self._cursor(cur)
 
         query = """SELECT %s FROM (VALUES %%s) as t(type, url)
                    LEFT JOIN origin
                        ON (t.type=origin.type AND t.url=origin.url)
                 """ % ','.join('origin.' + col for col in self.origin_cols)
 
         yield from execute_values_generator(
             cur, query, origins)
 
     def origin_get(self, ids, cur=None):
         """Retrieve the origin per its identifier.
 
         """
         cur = self._cursor(cur)
 
         query = """SELECT %s FROM (VALUES %%s) as t(id)
                    LEFT JOIN origin ON t.id = origin.id
                 """ % ','.join('origin.' + col for col in self.origin_cols)
 
         yield from execute_values_generator(
             cur, query, ((id,) for id in ids))
 
     def origin_get_range(self, origin_from=1, origin_count=100, cur=None):
         """Retrieve ``origin_count`` origins whose ids are greater
         or equal than ``origin_from``.
 
         Origins are sorted by id before retrieving them.
 
         Args:
             origin_from (int): the minimum id of origins to retrieve
             origin_count (int): the maximum number of origins to retrieve
         """
         cur = self._cursor(cur)
 
         query = """SELECT %s
                    FROM origin WHERE id >= %%s
                    ORDER BY id LIMIT %%s
                 """ % ','.join(self.origin_cols)
 
         cur.execute(query, (origin_from, origin_count))
         yield from cur
 
     def _origin_query(self, url_pattern, count=False, offset=0, limit=50,
                       regexp=False, with_visit=False, cur=None):
         """
         Method factorizing query creation for searching and counting origins.
         """
         cur = self._cursor(cur)
 
         if count:
             origin_cols = 'COUNT(*)'
         else:
             origin_cols = ','.join(self.origin_cols)
 
         query = """SELECT %s
                    FROM origin
                    WHERE """
         if with_visit:
             query += """
                    EXISTS (SELECT 1 from origin_visit WHERE origin=origin.id)
                    AND """
         query += 'url %s %%s '
         if not count:
             query += 'ORDER BY id OFFSET %%s LIMIT %%s'
 
         if not regexp:
             query = query % (origin_cols, 'ILIKE')
             query_params = ('%'+url_pattern+'%', offset, limit)
         else:
             query = query % (origin_cols, '~*')
             query_params = (url_pattern, offset, limit)
 
         if count:
             query_params = (query_params[0],)
 
         cur.execute(query, query_params)
 
     def origin_search(self, url_pattern, offset=0, limit=50,
                       regexp=False, with_visit=False, cur=None):
         """Search for origins whose urls contain a provided string pattern
         or match a provided regular expression.
         The search is performed in a case insensitive way.
 
         Args:
             url_pattern (str): the string pattern to search for in origin urls
             offset (int): number of found origins to skip before returning
                 results
             limit (int): the maximum number of found origins to return
             regexp (bool): if True, consider the provided pattern as a regular
                 expression and returns origins whose urls match it
             with_visit (bool): if True, filter out origins with no visit
 
         """
         self._origin_query(url_pattern, offset=offset, limit=limit,
                            regexp=regexp, with_visit=with_visit, cur=cur)
         yield from cur
 
     def origin_count(self, url_pattern, regexp=False,
                      with_visit=False, cur=None):
         """Count origins whose urls contain a provided string pattern
         or match a provided regular expression.
         The pattern search in origin urls is performed in a case insensitive
         way.
 
         Args:
             url_pattern (str): the string pattern to search for in origin urls
             regexp (bool): if True, consider the provided pattern as a regular
                 expression and returns origins whose urls match it
             with_visit (bool): if True, filter out origins with no visit
         """
         self._origin_query(url_pattern, count=True,
                            regexp=regexp, with_visit=with_visit, cur=cur)
         return cur.fetchone()[0]
 
     person_cols = ['fullname', 'name', 'email']
     person_get_cols = person_cols + ['id']
 
     def person_get(self, ids, cur=None):
         """Retrieve the persons identified by the list of ids.
 
         """
         cur = self._cursor(cur)
 
         query = """SELECT %s
                    FROM person
                    WHERE id IN %%s""" % ', '.join(self.person_get_cols)
 
         cur.execute(query, (tuple(ids),))
         yield from cur
 
     release_add_cols = [
         'id', 'target', 'target_type', 'date', 'date_offset',
         'date_neg_utc_offset', 'name', 'comment', 'synthetic',
         'author_fullname', 'author_name', 'author_email',
     ]
     release_get_cols = release_add_cols + ['author_id']
 
     def release_get_from_list(self, releases, cur=None):
         cur = self._cursor(cur)
         query_keys = ', '.join(
             self.mangle_query_key(k, 'release')
             for k in self.release_get_cols
         )
 
         yield from execute_values_generator(
             cur, """
             SELECT %s FROM (VALUES %%s) as t(id)
             LEFT JOIN release ON t.id = release.id
             LEFT JOIN person author ON release.author = author.id
             """ % query_keys,
             ((id,) for id in releases))
 
     def origin_metadata_add(self, origin, ts, provider, tool,
                             metadata, cur=None):
         """ Add an origin_metadata for the origin at ts with provider, tool and
         metadata.
 
         Args:
             origin (int): the origin's id for which the metadata is added
             ts (datetime): time when the metadata was found
             provider (int): the metadata provider identifier
             tool (int): the tool's identifier used to extract metadata
             metadata (jsonb): the metadata retrieved at the time and location
 
         Returns:
             id (int): the origin_metadata unique id
 
         """
         cur = self._cursor(cur)
         insert = """INSERT INTO origin_metadata (origin_id, discovery_date,
                     provider_id, tool_id, metadata) values (%s, %s, %s, %s, %s)
                     RETURNING id"""
         cur.execute(insert, (origin, ts, provider, tool, jsonize(metadata)))
 
         return cur.fetchone()[0]
 
     origin_metadata_get_cols = ['origin_id', 'discovery_date',
                                 'tool_id', 'metadata', 'provider_id',
                                 'provider_name', 'provider_type',
                                 'provider_url']
 
     def origin_metadata_get_by(self, origin_id, provider_type=None, cur=None):
         """Retrieve all origin_metadata entries for one origin_id
 
         """
         cur = self._cursor(cur)
         if not provider_type:
             query = '''SELECT %s
                        FROM swh_origin_metadata_get_by_origin(
                             %%s)''' % (','.join(
                                           self.origin_metadata_get_cols))
 
             cur.execute(query, (origin_id, ))
 
         else:
             query = '''SELECT %s
                        FROM swh_origin_metadata_get_by_provider_type(
                             %%s, %%s)''' % (','.join(
                                           self.origin_metadata_get_cols))
 
             cur.execute(query, (origin_id, provider_type))
 
         yield from cur
 
     tool_cols = ['id', 'name', 'version', 'configuration']
 
     @stored_procedure('swh_mktemp_tool')
     def mktemp_tool(self, cur=None):
         pass
 
     def tool_add_from_temp(self, cur=None):
         cur = self._cursor(cur)
         cur.execute("SELECT %s from swh_tool_add()" % (
             ','.join(self.tool_cols), ))
         yield from cur
 
     def tool_get(self, name, version, configuration, cur=None):
         cur = self._cursor(cur)
         cur.execute('''select %s
                        from tool
                        where name=%%s and
                              version=%%s and
                              configuration=%%s''' % (
                                  ','.join(self.tool_cols)),
                     (name, version, configuration))
 
         return cur.fetchone()
 
     metadata_provider_cols = ['id', 'provider_name', 'provider_type',
                               'provider_url', 'metadata']
 
     def metadata_provider_add(self, provider_name, provider_type,
                               provider_url, metadata, cur=None):
         """Insert a new provider and return the new identifier."""
         cur = self._cursor(cur)
         insert = """INSERT INTO metadata_provider (provider_name, provider_type,
                     provider_url, metadata) values (%s, %s, %s, %s)
                     RETURNING id"""
 
         cur.execute(insert, (provider_name, provider_type, provider_url,
                     jsonize(metadata)))
         return cur.fetchone()[0]
 
     def metadata_provider_get(self, provider_id, cur=None):
         cur = self._cursor(cur)
         cur.execute('''select %s
                        from metadata_provider
                        where id=%%s ''' % (
                                  ','.join(self.metadata_provider_cols)),
                     (provider_id, ))
 
         return cur.fetchone()
 
     def metadata_provider_get_by(self, provider_name, provider_url,
                                  cur=None):
         cur = self._cursor(cur)
         cur.execute('''select %s
                        from metadata_provider
                        where provider_name=%%s and
                              provider_url=%%s''' % (
                                  ','.join(self.metadata_provider_cols)),
                     (provider_name, provider_url))
 
         return cur.fetchone()
diff --git a/swh/storage/sql/30-swh-schema.sql b/swh/storage/sql/30-swh-schema.sql
index 24e5d6352..8c9fd7e96 100644
--- a/swh/storage/sql/30-swh-schema.sql
+++ b/swh/storage/sql/30-swh-schema.sql
@@ -1,348 +1,346 @@
 ---
 --- SQL implementation of the Software Heritage data model
 ---
 
 -- schema versions
 create table dbversion
 (
   version     int primary key,
   release     timestamptz,
   description text
 );
 
 -- latest schema version
 insert into dbversion(version, release, description)
-      values(132, now(), 'Work In Progress');
+      values(133, 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
 );
 
 
 -- 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,
   type     text, -- TODO use an enum here (?)
   url      text not null
 );
 
 
 -- 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
 );
 
 
 -- Log of all origin fetches (i.e., origin crawling) that have been done in the
 -- past, or are still ongoing. Similar to list_history, but for origins.
 create table fetch_history
 (
   id        bigserial,
   origin    bigint,
   date      timestamptz not null,
   status    boolean,  -- true if and only if the fetch has been successful
   result    jsonb,     -- more detailed returned values, times, etc...
   stdout    text,
   stderr    text,     -- null when status is true, filled otherwise
   duration  interval  -- fetch duration of NULL if still ongoing
 );
 
 
 -- 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
 );
 
 -- A directory entry pointing to a (sub-)directory.
 create table directory_entry_dir
 (
   id      bigserial,
   target  sha1_git,   -- id of target directory
   name    unix_path,  -- path name, relative to containing dir
   perms   file_perms  -- unix-like permissions
 );
 
 -- A directory entry pointing to a file content.
 create table directory_entry_file
 (
   id      bigserial,
   target  sha1_git,   -- id of target file
   name    unix_path,  -- path name, relative to containing dir
   perms   file_perms  -- unix-like permissions
 );
 
 -- A directory entry pointing to a revision.
 create table directory_entry_rev
 (
   id      bigserial,
   target  sha1_git,   -- id of target revision
   name    unix_path,  -- path name, relative to containing dir
   perms   file_perms  -- 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 <email>'
 );
 
 
 -- 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
 );
 
 -- 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
 );
 
 
 -- 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,
   status       origin_visit_status not null,
   metadata     jsonb,
-  snapshot_id  bigint,
   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.status is 'Visit result';
 comment on column origin_visit.metadata is 'Origin metadata at visit time';
-comment on column origin_visit.snapshot_id is 'Origin snapshot at visit time';
 comment on column origin_visit.snapshot is 'Origin snapshot at visit time';
 
 
 -- A snapshot represents the entire state of a software origin as crawled by
 -- Software Heritage. This table is a simple mapping between (public) intrinsic
 -- snapshot identifiers and (private) numeric sequential identifiers.
 create table snapshot
 (
   object_id  bigserial not null,  -- PK internal object identifier
   id         sha1_git not null    -- snapshot intrinsic identifier
 );
 
 -- 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"
 );
 
 -- 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
 );
 
 
 -- 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
 );
 
 
 -- 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)
 );
 
 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
 );
diff --git a/swh/storage/sql/40-swh-func.sql b/swh/storage/sql/40-swh-func.sql
index 29254d845..aab1d8cda 100644
--- a/swh/storage/sql/40-swh-func.sql
+++ b/swh/storage/sql/40-swh-func.sql
@@ -1,1129 +1,1117 @@
 create or replace function hash_sha1(text)
        returns text
 as $$
    select encode(digest($1, 'sha1'), 'hex')
 $$ language sql strict immutable;
 
 comment on function hash_sha1(text) is 'Compute SHA1 hash as text';
 
 -- create a temporary table called tmp_TBLNAME, mimicking existing table
 -- TBLNAME
 --
 -- Args:
 --     tblname: name of the table to mimick
 create or replace function swh_mktemp(tblname regclass)
     returns void
     language plpgsql
 as $$
 begin
     execute format('
 	create temporary table tmp_%1$I
 	    (like %1$I including defaults)
 	    on commit drop;
       alter table tmp_%1$I drop column if exists object_id;
 	', tblname);
     return;
 end
 $$;
 
 -- create a temporary table for directory entries called tmp_TBLNAME,
 -- mimicking existing table TBLNAME with an extra dir_id (sha1_git)
 -- column, and dropping the id column.
 --
 -- This is used to create the tmp_directory_entry_<foo> tables.
 --
 -- Args:
 --     tblname: name of the table to mimick
 create or replace function swh_mktemp_dir_entry(tblname regclass)
     returns void
     language plpgsql
 as $$
 begin
     execute format('
 	create temporary table tmp_%1$I
 	    (like %1$I including defaults, dir_id sha1_git)
 	    on commit drop;
         alter table tmp_%1$I drop column id;
 	', tblname);
     return;
 end
 $$;
 
 
 -- create a temporary table for revisions called tmp_revisions,
 -- mimicking existing table revision, replacing the foreign keys to
 -- people with an email and name field
 --
 create or replace function swh_mktemp_revision()
     returns void
     language sql
 as $$
     create temporary table tmp_revision (
         like revision including defaults,
         author_fullname bytea,
         author_name bytea,
         author_email bytea,
         committer_fullname bytea,
         committer_name bytea,
         committer_email bytea
     ) on commit drop;
     alter table tmp_revision drop column author;
     alter table tmp_revision drop column committer;
     alter table tmp_revision drop column object_id;
 $$;
 
 
 -- create a temporary table for releases called tmp_release,
 -- mimicking existing table release, replacing the foreign keys to
 -- people with an email and name field
 --
 create or replace function swh_mktemp_release()
     returns void
     language sql
 as $$
     create temporary table tmp_release (
         like release including defaults,
         author_fullname bytea,
         author_name bytea,
         author_email bytea
     ) on commit drop;
     alter table tmp_release drop column author;
     alter table tmp_release drop column object_id;
 $$;
 
 -- create a temporary table for the branches of a snapshot
 create or replace function swh_mktemp_snapshot_branch()
     returns void
     language sql
 as $$
   create temporary table tmp_snapshot_branch (
       name bytea not null,
       target bytea,
       target_type snapshot_target
   ) on commit drop;
 $$;
 
 create or replace function swh_mktemp_tool()
     returns void
     language sql
 as $$
     create temporary table tmp_tool (
       like tool including defaults
     ) on commit drop;
     alter table tmp_tool drop column id;
 $$;
 
 
 -- a content signature is a set of cryptographic checksums that we use to
 -- uniquely identify content, for the purpose of verifying if we already have
 -- some content or not during content injection
 create type content_signature as (
     sha1       sha1,
     sha1_git   sha1_git,
     sha256     sha256,
     blake2s256 blake2s256
 );
 
 
 -- check which entries of tmp_skipped_content are missing from skipped_content
 --
 -- operates in bulk: 0. swh_mktemp(skipped_content), 1. COPY to tmp_skipped_content,
 -- 2. call this function
 create or replace function swh_skipped_content_missing()
     returns setof content_signature
     language plpgsql
 as $$
 begin
     return query
 	select sha1, sha1_git, sha256, blake2s256 from tmp_skipped_content t
 	where not exists
 	(select 1 from skipped_content s where
 	    s.sha1 is not distinct from t.sha1 and
 	    s.sha1_git is not distinct from t.sha1_git and
 	    s.sha256 is not distinct from t.sha256);
     return;
 end
 $$;
 
 
 -- Look up content based on one or several different checksums. Return all
 -- content information if the content is found; a NULL row otherwise.
 --
 -- At least one checksum should be not NULL. If several are not NULL, they will
 -- be AND-ed together in the lookup query.
 --
 -- Note: this function is meant to be used to look up individual contents
 -- (e.g., for the web app), for batch lookup of missing content (e.g., to be
 -- added) see swh_content_missing
 create or replace function swh_content_find(
     sha1       sha1       default NULL,
     sha1_git   sha1_git   default NULL,
     sha256     sha256     default NULL,
     blake2s256 blake2s256 default NULL
 )
     returns content
     language plpgsql
 as $$
 declare
     con content;
     filters text[] := array[] :: text[];  -- AND-clauses used to filter content
     q text;
 begin
     if sha1 is not null then
         filters := filters || format('sha1 = %L', sha1);
     end if;
     if sha1_git is not null then
         filters := filters || format('sha1_git = %L', sha1_git);
     end if;
     if sha256 is not null then
         filters := filters || format('sha256 = %L', sha256);
     end if;
     if blake2s256 is not null then
         filters := filters || format('blake2s256 = %L', blake2s256);
     end if;
 
     if cardinality(filters) = 0 then
         return null;
     else
         q = format('select * from content where %s',
                    array_to_string(filters, ' and '));
         execute q into con;
 	return con;
     end if;
 end
 $$;
 
 
 -- add tmp_content entries to content, skipping duplicates
 --
 -- operates in bulk: 0. swh_mktemp(content), 1. COPY to tmp_content,
 -- 2. call this function
 create or replace function swh_content_add()
     returns void
     language plpgsql
 as $$
 begin
     insert into content (sha1, sha1_git, sha256, blake2s256, length, status)
         select distinct sha1, sha1_git, sha256, blake2s256, length, status from tmp_content;
     return;
 end
 $$;
 
 
 -- add tmp_skipped_content entries to skipped_content, skipping duplicates
 --
 -- operates in bulk: 0. swh_mktemp(skipped_content), 1. COPY to tmp_skipped_content,
 -- 2. call this function
 create or replace function swh_skipped_content_add()
     returns void
     language plpgsql
 as $$
 begin
     insert into skipped_content (sha1, sha1_git, sha256, blake2s256, length, status, reason, origin)
         select distinct sha1, sha1_git, sha256, blake2s256, length, status, reason, origin
 	from tmp_skipped_content
 	where (coalesce(sha1, ''), coalesce(sha1_git, ''), coalesce(sha256, '')) in (
             select coalesce(sha1, ''), coalesce(sha1_git, ''), coalesce(sha256, '')
             from swh_skipped_content_missing()
         );
         -- TODO XXX use postgres 9.5 "UPSERT" support here, when available.
         -- Specifically, using "INSERT .. ON CONFLICT IGNORE" we can avoid
         -- the extra swh_content_missing() query here.
     return;
 end
 $$;
 
 -- Update content entries from temporary table.
 -- (columns are potential new columns added to the schema, this cannot be empty)
 --
 create or replace function swh_content_update(columns_update text[])
     returns void
     language plpgsql
 as $$
 declare
    query text;
    tmp_array text[];
 begin
     if array_length(columns_update, 1) = 0 then
         raise exception 'Please, provide the list of column names to update.';
     end if;
 
     tmp_array := array(select format('%1$s=t.%1$s', unnest) from unnest(columns_update));
 
     query = format('update content set %s
                     from tmp_content t where t.sha1 = content.sha1',
                     array_to_string(tmp_array, ', '));
 
     execute query;
 
     return;
 end
 $$;
 
 comment on function swh_content_update(text[]) IS 'Update existing content''s columns';
 
 -- check which entries of tmp_directory are missing from directory
 --
 -- operates in bulk: 0. swh_mktemp(directory), 1. COPY to tmp_directory,
 -- 2. call this function
 create or replace function swh_directory_missing()
     returns setof sha1_git
     language plpgsql
 as $$
 begin
     return query
 	select id from tmp_directory t
 	where not exists (
 	    select 1 from directory d
 	    where d.id = t.id);
     return;
 end
 $$;
 
 
 create type directory_entry_type as enum('file', 'dir', 'rev');
 
 
 -- Add tmp_directory_entry_* entries to directory_entry_* and directory,
 -- skipping duplicates in directory_entry_*.  This is a generic function that
 -- works on all kind of directory entries.
 --
 -- operates in bulk: 0. swh_mktemp_dir_entry('directory_entry_*'), 1 COPY to
 -- tmp_directory_entry_*, 2. call this function
 --
 -- Assumption: this function is used in the same transaction that inserts the
 -- context directory in table "directory".
 create or replace function swh_directory_entry_add(typ directory_entry_type)
     returns void
     language plpgsql
 as $$
 begin
     execute format('
     insert into directory_entry_%1$s (target, name, perms)
     select distinct t.target, t.name, t.perms
     from tmp_directory_entry_%1$s t
     where not exists (
     select 1
     from directory_entry_%1$s i
     where t.target = i.target and t.name = i.name and t.perms = i.perms)
    ', typ);
 
     execute format('
     with new_entries as (
 	select t.dir_id, array_agg(i.id) as entries
 	from tmp_directory_entry_%1$s t
 	inner join directory_entry_%1$s i
 	using (target, name, perms)
 	group by t.dir_id
     )
     update tmp_directory as d
     set %1$s_entries = new_entries.entries
     from new_entries
     where d.id = new_entries.dir_id
     ', typ);
 
     return;
 end
 $$;
 
 -- Insert the data from tmp_directory, tmp_directory_entry_file,
 -- tmp_directory_entry_dir, tmp_directory_entry_rev into their final
 -- tables.
 --
 -- Prerequisites:
 --  directory ids in tmp_directory
 --  entries in tmp_directory_entry_{file,dir,rev}
 --
 create or replace function swh_directory_add()
     returns void
     language plpgsql
 as $$
 begin
     perform swh_directory_entry_add('file');
     perform swh_directory_entry_add('dir');
     perform swh_directory_entry_add('rev');
 
     insert into directory
     select * from tmp_directory t
     where not exists (
         select 1 from directory d
 	where d.id = t.id);
 
     return;
 end
 $$;
 
 -- a directory listing entry with all the metadata
 --
 -- can be used to list a directory, and retrieve all the data in one go.
 create type directory_entry as
 (
   dir_id   sha1_git,     -- id of the parent directory
   type     directory_entry_type,  -- type of entry
   target   sha1_git,     -- id of target
   name     unix_path,    -- path name, relative to containing dir
   perms    file_perms,   -- unix-like permissions
   status   content_status,  -- visible or absent
   sha1     sha1,            -- content if sha1 if type is not dir
   sha1_git sha1_git,        -- content's sha1 git if type is not dir
   sha256   sha256,          -- content's sha256 if type is not dir
   length   bigint           -- content length if type is not dir
 );
 
 
 -- List a single level of directory walked_dir_id
 -- FIXME: order by name is not correct. For git, we need to order by
 -- lexicographic order but as if a trailing / is present in directory
 -- name
 create or replace function swh_directory_walk_one(walked_dir_id sha1_git)
     returns setof directory_entry
     language sql
     stable
 as $$
     with dir as (
 	select id as dir_id, dir_entries, file_entries, rev_entries
 	from directory
 	where id = walked_dir_id),
     ls_d as (select dir_id, unnest(dir_entries) as entry_id from dir),
     ls_f as (select dir_id, unnest(file_entries) as entry_id from dir),
     ls_r as (select dir_id, unnest(rev_entries) as entry_id from dir)
     (select dir_id, 'dir'::directory_entry_type as type,
             e.target, e.name, e.perms, NULL::content_status,
             NULL::sha1, NULL::sha1_git, NULL::sha256, NULL::bigint
      from ls_d
      left join directory_entry_dir e on ls_d.entry_id = e.id)
     union
     (select dir_id, 'file'::directory_entry_type as type,
             e.target, e.name, e.perms, c.status,
             c.sha1, c.sha1_git, c.sha256, c.length
      from ls_f
      left join directory_entry_file e on ls_f.entry_id = e.id
      left join content c on e.target = c.sha1_git)
     union
     (select dir_id, 'rev'::directory_entry_type as type,
             e.target, e.name, e.perms, NULL::content_status,
             NULL::sha1, NULL::sha1_git, NULL::sha256, NULL::bigint
      from ls_r
      left join directory_entry_rev e on ls_r.entry_id = e.id)
     order by name;
 $$;
 
 -- List recursively the revision directory arborescence
 create or replace function swh_directory_walk(walked_dir_id sha1_git)
     returns setof directory_entry
     language sql
     stable
 as $$
     with recursive entries as (
         select dir_id, type, target, name, perms, status, sha1, sha1_git,
                sha256, length
         from swh_directory_walk_one(walked_dir_id)
         union all
         select dir_id, type, target, (dirname || '/' || name)::unix_path as name,
                perms, status, sha1, sha1_git, sha256, length
         from (select (swh_directory_walk_one(dirs.target)).*, dirs.name as dirname
               from (select target, name from entries where type = 'dir') as dirs) as with_parent
     )
     select dir_id, type, target, name, perms, status, sha1, sha1_git, sha256, length
     from entries
 $$;
 
 create or replace function swh_revision_walk(revision_id sha1_git)
   returns setof directory_entry
   language sql
   stable
 as $$
   select dir_id, type, target, name, perms, status, sha1, sha1_git, sha256, length
   from swh_directory_walk((select directory from revision where id=revision_id))
 $$;
 
 COMMENT ON FUNCTION swh_revision_walk(sha1_git) IS 'Recursively list the revision targeted directory arborescence';
 
 
 -- Find a directory entry by its path
 create or replace function swh_find_directory_entry_by_path(
     walked_dir_id sha1_git,
     dir_or_content_path bytea[])
     returns directory_entry
     language plpgsql
 as $$
 declare
     end_index integer;
     paths bytea default '';
     path bytea;
     res bytea[];
     r record;
 begin
     end_index := array_upper(dir_or_content_path, 1);
     res[1] := walked_dir_id;
 
     for i in 1..end_index
     loop
         path := dir_or_content_path[i];
         -- concatenate path for patching the name in the result record (if we found it)
         if i = 1 then
             paths = path;
         else
             paths := paths || '/' || path;  -- concatenate paths
         end if;
 
         if i <> end_index then
             select *
             from swh_directory_walk_one(res[i] :: sha1_git)
             where name=path
             and type = 'dir'
             limit 1 into r;
         else
             select *
             from swh_directory_walk_one(res[i] :: sha1_git)
             where name=path
             limit 1 into r;
         end if;
 
         -- find the path
         if r is null then
            return null;
         else
             -- store the next dir to lookup the next local path from
             res[i+1] := r.target;
         end if;
     end loop;
 
     -- at this moment, r is the result. Patch its 'name' with the full path before returning it.
     r.name := paths;
     return r;
 end
 $$;
 
 -- List all revision IDs starting from a given revision, going back in time
 --
 -- TODO ordering: should be breadth-first right now (what do we want?)
 -- TODO ordering: ORDER BY parent_rank somewhere?
 create or replace function swh_revision_list(root_revisions bytea[], num_revs bigint default NULL)
     returns table (id sha1_git, parents bytea[])
     language sql
     stable
 as $$
     with recursive full_rev_list(id) as (
         (select id from revision where id = ANY(root_revisions))
         union
         (select h.parent_id
          from revision_history as h
          join full_rev_list on h.id = full_rev_list.id)
     ),
     rev_list as (select id from full_rev_list limit num_revs)
     select rev_list.id as id,
            array(select rh.parent_id::bytea
                  from revision_history rh
                  where rh.id = rev_list.id
                  order by rh.parent_rank
                 ) as parent
     from rev_list;
 $$;
 
 -- List all the children of a given revision
 create or replace function swh_revision_list_children(root_revisions bytea[], num_revs bigint default NULL)
     returns table (id sha1_git, parents bytea[])
     language sql
     stable
 as $$
     with recursive full_rev_list(id) as (
         (select id from revision where id = ANY(root_revisions))
         union
         (select h.id
          from revision_history as h
          join full_rev_list on h.parent_id = full_rev_list.id)
     ),
     rev_list as (select id from full_rev_list limit num_revs)
     select rev_list.id as id,
            array(select rh.parent_id::bytea
                  from revision_history rh
                  where rh.id = rev_list.id
                  order by rh.parent_rank
                 ) as parent
     from rev_list;
 $$;
 
 
 -- Detailed entry for a revision
 create type revision_entry as
 (
   id                             sha1_git,
   date                           timestamptz,
   date_offset                    smallint,
   date_neg_utc_offset            boolean,
   committer_date                 timestamptz,
   committer_date_offset          smallint,
   committer_date_neg_utc_offset  boolean,
   type                           revision_type,
   directory                      sha1_git,
   message                        bytea,
   author_id                      bigint,
   author_fullname                bytea,
   author_name                    bytea,
   author_email                   bytea,
   committer_id                   bigint,
   committer_fullname             bytea,
   committer_name                 bytea,
   committer_email                bytea,
   metadata                       jsonb,
   synthetic                      boolean,
   parents                        bytea[],
   object_id                      bigint
 );
 
 
 -- "git style" revision log. Similar to swh_revision_list(), but returning all
 -- information associated to each revision, and expanding authors/committers
 create or replace function swh_revision_log(root_revisions bytea[], num_revs bigint default NULL)
     returns setof revision_entry
     language sql
     stable
 as $$
     select t.id, r.date, r.date_offset, r.date_neg_utc_offset,
            r.committer_date, r.committer_date_offset, r.committer_date_neg_utc_offset,
            r.type, r.directory, r.message,
            a.id, a.fullname, a.name, a.email,
            c.id, c.fullname, c.name, c.email,
            r.metadata, r.synthetic, t.parents, r.object_id
     from swh_revision_list(root_revisions, num_revs) as t
     left join revision r on t.id = r.id
     left join person a on a.id = r.author
     left join person c on c.id = r.committer;
 $$;
 
 
 -- Detailed entry for a release
 create type release_entry as
 (
   id                   sha1_git,
   target               sha1_git,
   target_type          object_type,
   date                 timestamptz,
   date_offset          smallint,
   date_neg_utc_offset  boolean,
   name                 bytea,
   comment              bytea,
   synthetic            boolean,
   author_id            bigint,
   author_fullname      bytea,
   author_name          bytea,
   author_email         bytea,
   object_id            bigint
 );
 
 -- Create entries in person from tmp_revision
 create or replace function swh_person_add_from_revision()
     returns void
     language plpgsql
 as $$
 begin
     with t as (
         select author_fullname as fullname, author_name as name, author_email as email from tmp_revision
     union
         select committer_fullname as fullname, committer_name as name, committer_email as email from tmp_revision
     ) insert into person (fullname, name, email)
     select distinct fullname, name, email from t
     where not exists (
         select 1
         from person p
         where t.fullname = p.fullname
     );
     return;
 end
 $$;
 
 
 -- Create entries in revision from tmp_revision
 create or replace function swh_revision_add()
     returns void
     language plpgsql
 as $$
 begin
     perform swh_person_add_from_revision();
 
     insert into revision (id, date, date_offset, date_neg_utc_offset, committer_date, committer_date_offset, committer_date_neg_utc_offset, type, directory, message, author, committer, metadata, synthetic)
     select t.id, t.date, t.date_offset, t.date_neg_utc_offset, t.committer_date, t.committer_date_offset, t.committer_date_neg_utc_offset, t.type, t.directory, t.message, a.id, c.id, t.metadata, t.synthetic
     from tmp_revision t
     left join person a on a.fullname = t.author_fullname
     left join person c on c.fullname = t.committer_fullname;
     return;
 end
 $$;
 
 
 -- Create entries in person from tmp_release
 create or replace function swh_person_add_from_release()
     returns void
     language plpgsql
 as $$
 begin
     with t as (
         select distinct author_fullname as fullname, author_name as name, author_email as email from tmp_release
     ) insert into person (fullname, name, email)
     select fullname, name, email from t
     where not exists (
         select 1
         from person p
         where t.fullname = p.fullname
     );
     return;
 end
 $$;
 
 
 -- Create entries in release from tmp_release
 create or replace function swh_release_add()
     returns void
     language plpgsql
 as $$
 begin
     perform swh_person_add_from_release();
 
     insert into release (id, target, target_type, date, date_offset, date_neg_utc_offset, name, comment, author, synthetic)
     select t.id, t.target, t.target_type, t.date, t.date_offset, t.date_neg_utc_offset, t.name, t.comment, a.id, t.synthetic
     from tmp_release t
     left join person a on a.fullname = t.author_fullname;
     return;
 end
 $$;
 
 
 -- add a new origin_visit for origin origin_id at date.
 --
 -- Returns the new visit id.
 create or replace function swh_origin_visit_add(origin_id bigint, date timestamptz)
     returns bigint
     language sql
 as $$
   with last_known_visit as (
     select coalesce(max(visit), 0) as visit
     from origin_visit
     where origin = origin_id
   )
   insert into origin_visit (origin, date, visit, status)
   values (origin_id, date, (select visit from last_known_visit) + 1, 'ongoing')
   returning visit;
 $$;
 
 create or replace function swh_snapshot_add(snapshot_id snapshot.id%type)
   returns void
   language plpgsql
 as $$
 declare
   snapshot_object_id snapshot.object_id%type;
 begin
   select object_id from snapshot where id = snapshot_id into snapshot_object_id;
   if snapshot_object_id is null then
      insert into snapshot (id) values (snapshot_id) returning object_id into snapshot_object_id;
      insert into snapshot_branch (name, target_type, target)
        select name, target_type, target from tmp_snapshot_branch tmp
        where not exists (
          select 1
          from snapshot_branch sb
          where sb.name = tmp.name
            and sb.target = tmp.target
            and sb.target_type = tmp.target_type
        )
        on conflict do nothing;
      insert into snapshot_branches (snapshot_id, branch_id)
      select snapshot_object_id, sb.object_id as branch_id
        from tmp_snapshot_branch tmp
        join snapshot_branch sb
        using (name, target, target_type)
        where tmp.target is not null and tmp.target_type is not null
      union
      select snapshot_object_id, sb.object_id as branch_id
        from tmp_snapshot_branch tmp
        join snapshot_branch sb
        using (name)
        where tmp.target is null and tmp.target_type is null
          and sb.target is null and sb.target_type is null;
   end if;
 end;
 $$;
 
 create type snapshot_result as (
   snapshot_id  sha1_git,
   name         bytea,
   target       bytea,
   target_type  snapshot_target
 );
 
 create or replace function swh_snapshot_get_by_id(id snapshot.id%type,
     branches_from bytea default '', branches_count bigint default null,
     target_types snapshot_target[] default NULL)
   returns setof snapshot_result
   language sql
   stable
 as $$
   select
     swh_snapshot_get_by_id.id as snapshot_id, name, target, target_type
   from snapshot_branches
   inner join snapshot_branch on snapshot_branches.branch_id = snapshot_branch.object_id
   where snapshot_id = (select object_id from snapshot where snapshot.id = swh_snapshot_get_by_id.id)
     and (target_types is null or target_type = any(target_types))
     and name >= branches_from
   order by name limit branches_count
 $$;
 
 create type snapshot_size as (
   target_type snapshot_target,
   count bigint
 );
 
 create or replace function swh_snapshot_count_branches(id snapshot.id%type)
   returns setof snapshot_size
   language sql
   stable
 as $$
   SELECT target_type, count(name)
   from swh_snapshot_get_by_id(swh_snapshot_count_branches.id)
   group by target_type;
 $$;
 
-create or replace function swh_snapshot_get_by_origin_visit(origin_id bigint, visit_id bigint)
-  returns snapshot.id%type
-  language sql
-  stable
-as $$
-  select snapshot.id
-  from origin_visit
-  left join snapshot
-  on snapshot.object_id = origin_visit.snapshot_id
-  where origin_visit.origin=origin_id and origin_visit.visit=visit_id;
-$$;
-
 -- Absolute path: directory reference + complete path relative to it
 create type content_dir as (
     directory  sha1_git,
     path       unix_path
 );
 
 
 -- Find the containing directory of a given content, specified by sha1
 -- (note: *not* sha1_git).
 --
 -- Return a pair (dir_it, path) where path is a UNIX path that, from the
 -- directory root, reach down to a file with the desired content. Return NULL
 -- if no match is found.
 --
 -- In case of multiple paths (i.e., pretty much always), an arbitrary one is
 -- chosen.
 create or replace function swh_content_find_directory(content_id sha1)
     returns content_dir
     language sql
     stable
 as $$
     with recursive path as (
 	-- Recursively build a path from the requested content to a root
 	-- directory. Each iteration returns a pair (dir_id, filename) where
 	-- filename is relative to dir_id. Stops when no parent directory can
 	-- be found.
 	(select dir.id as dir_id, dir_entry_f.name as name, 0 as depth
 	 from directory_entry_file as dir_entry_f
 	 join content on content.sha1_git = dir_entry_f.target
 	 join directory as dir on dir.file_entries @> array[dir_entry_f.id]
 	 where content.sha1 = content_id
 	 limit 1)
 	union all
 	(select dir.id as dir_id,
 		(dir_entry_d.name || '/' || path.name)::unix_path as name,
 		path.depth + 1
 	 from path
 	 join directory_entry_dir as dir_entry_d on dir_entry_d.target = path.dir_id
 	 join directory as dir on dir.dir_entries @> array[dir_entry_d.id]
 	 limit 1)
     )
     select dir_id, name from path order by depth desc limit 1;
 $$;
 
 -- Find the visit of origin id closest to date visit_date
 create or replace function swh_visit_find_by_date(origin bigint, visit_date timestamptz default NOW())
     returns origin_visit
     language sql
     stable
 as $$
   with closest_two_visits as ((
     select ov, (date - visit_date) as interval
     from origin_visit ov
     where ov.origin = origin
           and ov.date >= visit_date
     order by ov.date asc
     limit 1
   ) union (
     select ov, (visit_date - date) as interval
     from origin_visit ov
     where ov.origin = origin
           and ov.date < visit_date
     order by ov.date desc
     limit 1
   )) select (ov).* from closest_two_visits order by interval limit 1
 $$;
 
 -- Find the visit of origin id closest to date visit_date
 create or replace function swh_visit_get(origin bigint)
     returns origin_visit
     language sql
     stable
 as $$
     select *
     from origin_visit
     where origin=origin
     order by date desc
 $$;
 
 -- Object listing by object_id
 
 create or replace function swh_content_list_by_object_id(
     min_excl bigint,
     max_incl bigint
 )
     returns setof content
     language sql
     stable
 as $$
     select * from content
     where object_id > min_excl and object_id <= max_incl
     order by object_id;
 $$;
 
 create or replace function swh_revision_list_by_object_id(
     min_excl bigint,
     max_incl bigint
 )
     returns setof revision_entry
     language sql
     stable
 as $$
     with revs as (
         select * from revision
         where object_id > min_excl and object_id <= max_incl
     )
     select r.id, r.date, r.date_offset, r.date_neg_utc_offset,
            r.committer_date, r.committer_date_offset, r.committer_date_neg_utc_offset,
            r.type, r.directory, r.message,
            a.id, a.fullname, a.name, a.email, c.id, c.fullname, c.name, c.email, r.metadata, r.synthetic,
            array(select rh.parent_id::bytea from revision_history rh where rh.id = r.id order by rh.parent_rank)
                as parents, r.object_id
     from revs r
     left join person a on a.id = r.author
     left join person c on c.id = r.committer
     order by r.object_id;
 $$;
 
 create or replace function swh_release_list_by_object_id(
     min_excl bigint,
     max_incl bigint
 )
     returns setof release_entry
     language sql
     stable
 as $$
     with rels as (
         select * from release
         where object_id > min_excl and object_id <= max_incl
     )
     select r.id, r.target, r.target_type, r.date, r.date_offset, r.date_neg_utc_offset, r.name, r.comment,
            r.synthetic, p.id as author_id, p.fullname as author_fullname, p.name as author_name, p.email as author_email, r.object_id
     from rels r
     left join person p on p.id = r.author
     order by r.object_id;
 $$;
 
 
 -- end revision_metadata functions
 -- origin_metadata functions
 create type origin_metadata_signature as (
     id bigint,
     origin_id bigint,
     discovery_date timestamptz,
     tool_id bigint,
     metadata jsonb,
     provider_id integer,
     provider_name text,
     provider_type text,
     provider_url  text
 );
 create or replace function swh_origin_metadata_get_by_origin(
        origin integer)
     returns setof origin_metadata_signature
     language sql
     stable
 as $$
     select om.id as id, origin_id, discovery_date, tool_id, om.metadata,
            mp.id as provider_id, provider_name, provider_type, provider_url
     from origin_metadata as om
     inner join metadata_provider mp on om.provider_id = mp.id
     where om.origin_id = origin
     order by discovery_date desc;
 $$;
 
 create or replace function swh_origin_metadata_get_by_provider_type(
        origin integer,
        type text)
     returns setof origin_metadata_signature
     language sql
     stable
 as $$
     select om.id as id, origin_id, discovery_date, tool_id, om.metadata,
            mp.id as provider_id, provider_name, provider_type, provider_url
     from origin_metadata as om
     inner join metadata_provider mp on om.provider_id = mp.id
     where om.origin_id = origin
     and mp.provider_type = type
     order by discovery_date desc;
 $$;
 -- end origin_metadata functions
 
 -- add tmp_tool entries to tool,
 -- skipping duplicates if any.
 --
 -- operates in bulk: 0. create temporary tmp_tool, 1. COPY to
 -- it, 2. call this function to insert and filtering out duplicates
 create or replace function swh_tool_add()
     returns setof tool
     language plpgsql
 as $$
 begin
       insert into tool(name, version, configuration)
       select name, version, configuration from tmp_tool tmp
       on conflict(name, version, configuration) do nothing;
 
       return query
           select id, name, version, configuration
           from tmp_tool join tool
               using(name, version, configuration);
 
       return;
 end
 $$;
 
 
 -- simple counter mapping a textual label to an integer value
 create type counter as (
     label  text,
     value  bigint
 );
 
 -- return statistics about the number of tuples in various SWH tables
 --
 -- Note: the returned values are based on postgres internal statistics
 -- (pg_class table), which are only updated daily (by autovacuum) or so
 create or replace function swh_stat_counters()
     returns setof counter
     language sql
     stable
 as $$
     select object_type as label, value as value
     from object_counts
     where object_type in (
         'content',
         'directory',
         'directory_entry_dir',
         'directory_entry_file',
         'directory_entry_rev',
         'origin',
         'origin_visit',
         'person',
         'release',
         'revision',
         'revision_history',
         'skipped_content',
         'snapshot'
     );
 $$;
 
 create or replace function swh_update_counter(object_type text)
     returns void
     language plpgsql
 as $$
 begin
     execute format('
 	insert into object_counts
     (value, last_update, object_type)
   values
     ((select count(*) from %1$I), NOW(), %1$L)
   on conflict (object_type) do update set
     value = excluded.value,
     last_update = excluded.last_update',
   object_type);
     return;
 end;
 $$;
 
 create or replace function swh_update_counter_bucketed()
     returns void
     language plpgsql
 as $$
 declare
   query text;
   line_to_update int;
   new_value bigint;
 begin
   select
     object_counts_bucketed.line,
     format(
       'select count(%I) from %I where %s',
       coalesce(identifier, '*'),
       object_type,
       coalesce(
         concat_ws(
           ' and ',
           case when bucket_start is not null then
             format('%I >= %L', identifier, bucket_start) -- lower bound condition, inclusive
           end,
           case when bucket_end is not null then
             format('%I < %L', identifier, bucket_end) -- upper bound condition, exclusive
           end
         ),
         'true'
       )
     )
     from object_counts_bucketed
     order by coalesce(last_update, now() - '1 month'::interval) asc
     limit 1
     into line_to_update, query;
 
   execute query into new_value;
 
   update object_counts_bucketed
     set value = new_value,
         last_update = now()
     where object_counts_bucketed.line = line_to_update;
 
 END
 $$;
 
 create or replace function swh_update_counters_from_buckets()
   returns trigger
   language plpgsql
 as $$
 begin
 with to_update as (
   select object_type, sum(value) as value, max(last_update) as last_update
   from object_counts_bucketed ob1
   where not exists (
     select 1 from object_counts_bucketed ob2
     where ob1.object_type = ob2.object_type
     and value is null
     )
   group by object_type
 ) update object_counts
   set
     value = to_update.value,
     last_update = to_update.last_update
   from to_update
   where
     object_counts.object_type = to_update.object_type
     and object_counts.value != to_update.value;
 return null;
 end
 $$;
 
 create trigger update_counts_from_bucketed
   after insert or update
   on object_counts_bucketed
   for each row
   when (NEW.line % 256 = 0)
   execute procedure swh_update_counters_from_buckets();
diff --git a/swh/storage/sql/60-swh-indexes.sql b/swh/storage/sql/60-swh-indexes.sql
index f0e5e8b34..f3d83b87b 100644
--- a/swh/storage/sql/60-swh-indexes.sql
+++ b/swh/storage/sql/60-swh-indexes.sql
@@ -1,184 +1,181 @@
 -- 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(type, url);
 
 
 -- 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;
 
 -- fetch_history
 
 create unique index concurrently fetch_history_pkey on fetch_history(id);
 alter table fetch_history add primary key using index fetch_history_pkey;
 
 alter table fetch_history add constraint fetch_history_origin_fkey foreign key (origin) references origin(id) not valid;
 alter table fetch_history validate constraint fetch_history_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);
 
 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;
 
-alter table origin_visit add constraint origin_visit_snapshot_id_fkey foreign key (snapshot_id) references snapshot(object_id) not valid;
-alter table origin_visit validate constraint origin_visit_snapshot_id_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;
 
 -- 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);
 
 -- 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_storage.py b/swh/storage/tests/test_storage.py
index 7d50862b4..bdb6aefb1 100644
--- a/swh/storage/tests/test_storage.py
+++ b/swh/storage/tests/test_storage.py
@@ -1,2739 +1,2814 @@
 # Copyright (C) 2015-2018  The Software Heritage developers
 # See the AUTHORS file at the top-level directory of this distribution
 # License: GNU General Public License version 3, or any later version
 # See top-level LICENSE file for more information
 
 import copy
 import datetime
 import itertools
 import random
 import unittest
 from collections import defaultdict
 from unittest.mock import Mock, patch
 
 import pytest
 
 from hypothesis import given, strategies
 
 from swh.model import from_disk, identifiers
 from swh.model.hashutil import hash_to_bytes
 from swh.storage.tests.storage_testing import StorageTestFixture
 from swh.storage import HashCollision
 
 from .generate_data_test import gen_contents, gen_origins
 
 
 @pytest.mark.db
 class StorageTestDbFixture(StorageTestFixture):
     def setUp(self):
         super().setUp()
 
         db = self.test_db[self.TEST_DB_NAME]
         self.conn = db.conn
         self.cursor = db.cursor
 
         self.maxDiff = None
 
     def tearDown(self):
         self.reset_storage_tables()
         super().tearDown()
 
 
 class TestStorageData:
     def setUp(self):
         super().setUp()
 
         self.cont = {
             'data': b'42\n',
             'length': 3,
             'sha1': hash_to_bytes(
                 '34973274ccef6ab4dfaaf86599792fa9c3fe4689'),
             'sha1_git': hash_to_bytes(
                 'd81cc0710eb6cf9efd5b920a8453e1e07157b6cd'),
             'sha256': hash_to_bytes(
                 '673650f936cb3b0a2f93ce09d81be107'
                 '48b1b203c19e8176b4eefc1964a0cf3a'),
             'blake2s256': hash_to_bytes('d5fe1939576527e42cfd76a9455a2'
                                         '432fe7f56669564577dd93c4280e76d661d'),
             'status': 'visible',
         }
 
         self.cont2 = {
             'data': b'4242\n',
             'length': 5,
             'sha1': hash_to_bytes(
                 '61c2b3a30496d329e21af70dd2d7e097046d07b7'),
             'sha1_git': hash_to_bytes(
                 '36fade77193cb6d2bd826161a0979d64c28ab4fa'),
             'sha256': hash_to_bytes(
                 '859f0b154fdb2d630f45e1ecae4a8629'
                 '15435e663248bb8461d914696fc047cd'),
             'blake2s256': hash_to_bytes('849c20fad132b7c2d62c15de310adfe87be'
                                         '94a379941bed295e8141c6219810d'),
             'status': 'visible',
         }
 
         self.cont3 = {
             'data': b'424242\n',
             'length': 7,
             'sha1': hash_to_bytes(
                 '3e21cc4942a4234c9e5edd8a9cacd1670fe59f13'),
             'sha1_git': hash_to_bytes(
                 'c932c7649c6dfa4b82327d121215116909eb3bea'),
             'sha256': hash_to_bytes(
                 '92fb72daf8c6818288a35137b72155f5'
                 '07e5de8d892712ab96277aaed8cf8a36'),
             'blake2s256': hash_to_bytes('76d0346f44e5a27f6bafdd9c2befd304af'
                                         'f83780f93121d801ab6a1d4769db11'),
             'status': 'visible',
         }
 
         self.missing_cont = {
             'data': b'missing\n',
             'length': 8,
             'sha1': hash_to_bytes(
                 'f9c24e2abb82063a3ba2c44efd2d3c797f28ac90'),
             'sha1_git': hash_to_bytes(
                 '33e45d56f88993aae6a0198013efa80716fd8919'),
             'sha256': hash_to_bytes(
                 '6bbd052ab054ef222c1c87be60cd191a'
                 'ddedd24cc882d1f5f7f7be61dc61bb3a'),
             'blake2s256': hash_to_bytes('306856b8fd879edb7b6f1aeaaf8db9bbecc9'
                                         '93cd7f776c333ac3a782fa5c6eba'),
             'status': 'absent',
         }
 
         self.skipped_cont = {
             'length': 1024 * 1024 * 200,
             'sha1_git': hash_to_bytes(
                 '33e45d56f88993aae6a0198013efa80716fd8920'),
             'sha1': hash_to_bytes(
                 '43e45d56f88993aae6a0198013efa80716fd8920'),
             'sha256': hash_to_bytes(
                 '7bbd052ab054ef222c1c87be60cd191a'
                 'ddedd24cc882d1f5f7f7be61dc61bb3a'),
             'blake2s256': hash_to_bytes(
                 'ade18b1adecb33f891ca36664da676e1'
                 '2c772cc193778aac9a137b8dc5834b9b'),
             'reason': 'Content too long',
             'status': 'absent',
         }
 
         self.skipped_cont2 = {
             'length': 1024 * 1024 * 300,
             'sha1_git': hash_to_bytes(
                 '44e45d56f88993aae6a0198013efa80716fd8921'),
             'sha1': hash_to_bytes(
                 '54e45d56f88993aae6a0198013efa80716fd8920'),
             'sha256': hash_to_bytes(
                 '8cbd052ab054ef222c1c87be60cd191a'
                 'ddedd24cc882d1f5f7f7be61dc61bb3a'),
             'blake2s256': hash_to_bytes(
                 '9ce18b1adecb33f891ca36664da676e1'
                 '2c772cc193778aac9a137b8dc5834b9b'),
             'reason': 'Content too long',
             'status': 'absent',
         }
 
         self.dir = {
             'id': b'4\x013\x422\x531\x000\xf51\xe62\xa73\xff7\xc3\xa90',
             'entries': [
                 {
                     'name': b'foo',
                     'type': 'file',
                     'target': self.cont['sha1_git'],
                     'perms': from_disk.DentryPerms.content,
                 },
                 {
                     'name': b'bar\xc3',
                     'type': 'dir',
                     'target': b'12345678901234567890',
                     'perms': from_disk.DentryPerms.directory,
                 },
             ],
         }
 
         self.dir2 = {
             'id': b'4\x013\x422\x531\x000\xf51\xe62\xa73\xff7\xc3\xa95',
             'entries': [
                 {
                     'name': b'oof',
                     'type': 'file',
                     'target': self.cont2['sha1_git'],
                     'perms': from_disk.DentryPerms.content,
                 }
             ],
         }
 
         self.dir3 = {
             'id': hash_to_bytes('33e45d56f88993aae6a0198013efa80716fd8921'),
             'entries': [
                 {
                     'name': b'foo',
                     'type': 'file',
                     'target': self.cont['sha1_git'],
                     'perms': from_disk.DentryPerms.content,
                 },
                 {
                     'name': b'subdir',
                     'type': 'dir',
                     'target': self.dir['id'],
                     'perms': from_disk.DentryPerms.directory,
                 },
                 {
                     'name': b'hello',
                     'type': 'file',
                     'target': b'12345678901234567890',
                     'perms': from_disk.DentryPerms.content,
                 },
 
             ],
         }
 
         self.minus_offset = datetime.timezone(datetime.timedelta(minutes=-120))
         self.plus_offset = datetime.timezone(datetime.timedelta(minutes=120))
 
         self.revision = {
             'id': b'56789012345678901234',
             'message': b'hello',
             'author': {
                 'name': b'Nicolas Dandrimont',
                 'email': b'nicolas@example.com',
                 'fullname': b'Nicolas Dandrimont <nicolas@example.com> ',
             },
             'date': {
                 'timestamp': 1234567890,
                 'offset': 120,
                 'negative_utc': None,
             },
             'committer': {
                 'name': b'St\xc3fano Zacchiroli',
                 'email': b'stefano@example.com',
                 'fullname': b'St\xc3fano Zacchiroli <stefano@example.com>'
             },
             'committer_date': {
                 'timestamp': 1123456789,
                 'offset': 0,
                 'negative_utc': True,
             },
             'parents': [b'01234567890123456789', b'23434512345123456789'],
             'type': 'git',
             'directory': self.dir['id'],
             'metadata': {
                 'checksums': {
                     'sha1': 'tarball-sha1',
                     'sha256': 'tarball-sha256',
                 },
                 'signed-off-by': 'some-dude',
                 'extra_headers': [
                     ['gpgsig', b'test123'],
                     ['mergetags', [b'foo\\bar', b'\x22\xaf\x89\x80\x01\x00']],
                 ],
             },
             'synthetic': True
         }
 
         self.revision2 = {
             'id': b'87659012345678904321',
             'message': b'hello again',
             'author': {
                 'name': b'Roberto Dicosmo',
                 'email': b'roberto@example.com',
                 'fullname': b'Roberto Dicosmo <roberto@example.com>',
             },
             'date': {
                 'timestamp': {
                     'seconds': 1234567843,
                     'microseconds': 220000,
                 },
                 'offset': -720,
                 'negative_utc': None,
             },
             'committer': {
                 'name': b'tony',
                 'email': b'ar@dumont.fr',
                 'fullname': b'tony <ar@dumont.fr>',
             },
             'committer_date': {
                 'timestamp': 1123456789,
                 'offset': 0,
                 'negative_utc': False,
             },
             'parents': [b'01234567890123456789'],
             'type': 'git',
             'directory': self.dir2['id'],
             'metadata': None,
             'synthetic': False
         }
 
         self.revision3 = {
             'id': hash_to_bytes('7026b7c1a2af56521e951c01ed20f255fa054238'),
             'message': b'a simple revision with no parents this time',
             'author': {
                 'name': b'Roberto Dicosmo',
                 'email': b'roberto@example.com',
                 'fullname': b'Roberto Dicosmo <roberto@example.com>',
             },
             'date': {
                 'timestamp': {
                     'seconds': 1234567843,
                     'microseconds': 220000,
                 },
                 'offset': -720,
                 'negative_utc': None,
             },
             'committer': {
                 'name': b'tony',
                 'email': b'ar@dumont.fr',
                 'fullname': b'tony <ar@dumont.fr>',
             },
             'committer_date': {
                 'timestamp': 1127351742,
                 'offset': 0,
                 'negative_utc': False,
             },
             'parents': [],
             'type': 'git',
             'directory': self.dir2['id'],
             'metadata': None,
             'synthetic': True
         }
 
         self.revision4 = {
             'id': hash_to_bytes('368a48fe15b7db2383775f97c6b247011b3f14f4'),
             'message': b'parent of self.revision2',
             'author': {
                 'name': b'me',
                 'email': b'me@soft.heri',
                 'fullname': b'me <me@soft.heri>',
             },
             'date': {
                 'timestamp': {
                     'seconds': 1244567843,
                     'microseconds': 220000,
                 },
                 'offset': -720,
                 'negative_utc': None,
             },
             'committer': {
                 'name': b'committer-dude',
                 'email': b'committer@dude.com',
                 'fullname': b'committer-dude <committer@dude.com>',
             },
             'committer_date': {
                 'timestamp': {
                     'seconds': 1244567843,
                     'microseconds': 220000,
                 },
                 'offset': -720,
                 'negative_utc': None,
             },
             'parents': [self.revision3['id']],
             'type': 'git',
             'directory': self.dir['id'],
             'metadata': None,
             'synthetic': False
         }
 
         self.origin = {
             'url': 'file:///dev/null',
             'type': 'git',
         }
 
         self.origin2 = {
             'url': 'file:///dev/zero',
             'type': 'git',
         }
 
         self.provider = {
             'name': 'hal',
             'type': 'deposit-client',
             'url': 'http:///hal/inria',
             'metadata': {
                 'location': 'France'
             }
         }
 
         self.metadata_tool = {
             'name': 'swh-deposit',
             'version': '0.0.1',
             'configuration': {
                 'sword_version': '2'
             }
         }
 
         self.origin_metadata = {
             'origin': self.origin,
             'discovery_date': datetime.datetime(2015, 1, 1, 23, 0, 0,
                                                 tzinfo=datetime.timezone.utc),
             'provider': self.provider,
             'tool': 'swh-deposit',
             'metadata': {
                 'name': 'test_origin_metadata',
                 'version': '0.0.1'
              }
         }
 
         self.origin_metadata2 = {
             'origin': self.origin,
             'discovery_date': datetime.datetime(2017, 1, 1, 23, 0, 0,
                                                 tzinfo=datetime.timezone.utc),
             'provider': self.provider,
             'tool': 'swh-deposit',
             'metadata': {
                 'name': 'test_origin_metadata',
                 'version': '0.0.1'
              }
         }
 
         self.date_visit1 = datetime.datetime(2015, 1, 1, 23, 0, 0,
                                              tzinfo=datetime.timezone.utc)
 
         self.date_visit2 = datetime.datetime(2017, 1, 1, 23, 0, 0,
                                              tzinfo=datetime.timezone.utc)
 
         self.date_visit3 = datetime.datetime(2018, 1, 1, 23, 0, 0,
                                              tzinfo=datetime.timezone.utc)
 
         self.release = {
             'id': b'87659012345678901234',
             'name': b'v0.0.1',
             'author': {
                 'name': b'olasd',
                 'email': b'nic@olasd.fr',
                 'fullname': b'olasd <nic@olasd.fr>',
             },
             'date': {
                 'timestamp': 1234567890,
                 'offset': 42,
                 'negative_utc': None,
             },
             'target': b'43210987654321098765',
             'target_type': 'revision',
             'message': b'synthetic release',
             'synthetic': True,
         }
 
         self.release2 = {
             'id': b'56789012348765901234',
             'name': b'v0.0.2',
             'author': {
                 'name': b'tony',
                 'email': b'ar@dumont.fr',
                 'fullname': b'tony <ar@dumont.fr>',
             },
             'date': {
                 'timestamp': 1634366813,
                 'offset': -120,
                 'negative_utc': None,
             },
             'target': b'432109\xa9765432\xc309\x00765',
             'target_type': 'revision',
             'message': b'v0.0.2\nMisc performance improvements + bug fixes',
             'synthetic': False
         }
 
         self.release3 = {
             'id': b'87659012345678904321',
             'name': b'v0.0.2',
             'author': {
                 'name': b'tony',
                 'email': b'tony@ardumont.fr',
                 'fullname': b'tony <tony@ardumont.fr>',
             },
             'date': {
                 'timestamp': 1634336813,
                 'offset': 0,
                 'negative_utc': False,
             },
             'target': self.revision2['id'],
             'target_type': 'revision',
             'message': b'yet another synthetic release',
             'synthetic': True,
         }
 
         self.fetch_history_date = datetime.datetime(
             2015, 1, 2, 21, 0, 0,
             tzinfo=datetime.timezone.utc)
         self.fetch_history_end = datetime.datetime(
             2015, 1, 2, 23, 0, 0,
             tzinfo=datetime.timezone.utc)
 
         self.fetch_history_duration = (self.fetch_history_end -
                                        self.fetch_history_date)
 
         self.fetch_history_data = {
             'status': True,
             'result': {'foo': 'bar'},
             'stdout': 'blabla',
             'stderr': 'blablabla',
         }
 
         self.snapshot = {
             'id': hash_to_bytes('2498dbf535f882bc7f9a18fb16c9ad27fda7bab7'),
             'branches': {
                 b'master': {
                     'target': self.revision['id'],
                     'target_type': 'revision',
                 },
             },
             'next_branch': None
         }
 
         self.empty_snapshot = {
             'id': hash_to_bytes('1a8893e6a86f444e8be8e7bda6cb34fb1735a00e'),
             'branches': {},
             'next_branch': None
         }
 
         self.complete_snapshot = {
             'id': hash_to_bytes('6e65b86363953b780d92b0a928f3e8fcdd10db36'),
             'branches': {
                 b'directory': {
                     'target': hash_to_bytes(
                         '1bd0e65f7d2ff14ae994de17a1e7fe65111dcad8'),
                     'target_type': 'directory',
                 },
                 b'content': {
                     'target': hash_to_bytes(
                         'fe95a46679d128ff167b7c55df5d02356c5a1ae1'),
                     'target_type': 'content',
                 },
                 b'alias': {
                     'target': b'revision',
                     'target_type': 'alias',
                 },
                 b'revision': {
                     'target': hash_to_bytes(
                         'aafb16d69fd30ff58afdd69036a26047f3aebdc6'),
                     'target_type': 'revision',
                 },
                 b'release': {
                     'target': hash_to_bytes(
                         '7045404f3d1c54e6473c71bbb716529fbad4be24'),
                     'target_type': 'release',
                 },
                 b'snapshot': {
                     'target': hash_to_bytes(
                         '1a8893e6a86f444e8be8e7bda6cb34fb1735a00e'),
                     'target_type': 'snapshot',
                 },
                 b'dangling': None,
             },
             'next_branch': None
         }
 
 
 class CommonTestStorage(TestStorageData):
     """Base class for Storage testing.
 
     This class is used as-is to test local storage (see TestLocalStorage
     below) and remote storage (see TestRemoteStorage in
     test_remote_storage.py.
 
     We need to have the two classes inherit from this base class
     separately to avoid nosetests running the tests from the base
     class twice.
 
     """
     @staticmethod
     def normalize_entity(entity):
         entity = copy.deepcopy(entity)
         for key in ('date', 'committer_date'):
             if key in entity:
                 entity[key] = identifiers.normalize_timestamp(entity[key])
 
         return entity
 
     def test_check_config(self):
         self.assertTrue(self.storage.check_config(check_write=True))
         self.assertTrue(self.storage.check_config(check_write=False))
 
     def test_content_add(self):
         cont = self.cont
 
         self.storage.content_add([cont])
         self.assertEqual(list(self.storage.content_get([cont['sha1']])),
                          [{'sha1': cont['sha1'], 'data': cont['data']}])
 
         expected_cont = cont.copy()
         del expected_cont['data']
         self.assertEqual(list(self.journal_writer.objects),
                          [('content', expected_cont)])
 
     def test_content_add_db(self):
         cont = self.cont
 
         self.storage.content_add([cont])
         if hasattr(self.storage, 'objstorage'):
             self.assertIn(cont['sha1'], self.storage.objstorage)
         self.cursor.execute('SELECT sha1, sha1_git, sha256, length, status'
                             ' FROM content WHERE sha1 = %s',
                             (cont['sha1'],))
         datum = self.cursor.fetchone()
         self.assertEqual(
             (datum[0].tobytes(), datum[1].tobytes(), datum[2].tobytes(),
              datum[3], datum[4]),
             (cont['sha1'], cont['sha1_git'], cont['sha256'],
              cont['length'], 'visible'))
 
         expected_cont = cont.copy()
         del expected_cont['data']
         self.assertEqual(list(self.journal_writer.objects),
                          [('content', expected_cont)])
 
     def test_content_add_collision(self):
         cont1 = self.cont
 
         # create (corrupted) content with same sha1{,_git} but != sha256
         cont1b = cont1.copy()
         sha256_array = bytearray(cont1b['sha256'])
         sha256_array[0] += 1
         cont1b['sha256'] = bytes(sha256_array)
 
         with self.assertRaises(HashCollision) as cm:
             self.storage.content_add([cont1, cont1b])
 
         self.assertIn(cm.exception.args[0], ['sha1', 'sha1_git', 'blake2s256'])
 
     def test_skipped_content_add(self):
         cont = self.skipped_cont.copy()
         cont2 = self.skipped_cont2.copy()
         cont2['blake2s256'] = None
 
         self.storage.content_add([cont, cont, cont2])
 
         self.cursor.execute('SELECT sha1, sha1_git, sha256, blake2s256, '
                             'length, status, reason '
                             'FROM skipped_content ORDER BY sha1_git')
 
         datums = self.cursor.fetchall()
 
         self.assertEqual(2, len(datums))
         datum = datums[0]
         self.assertEqual(
             (datum[0].tobytes(), datum[1].tobytes(), datum[2].tobytes(),
              datum[3].tobytes(), datum[4], datum[5], datum[6]),
             (cont['sha1'], cont['sha1_git'], cont['sha256'],
              cont['blake2s256'], cont['length'], 'absent',
              'Content too long')
         )
 
         datum2 = datums[1]
         self.assertEqual(
             (datum2[0].tobytes(), datum2[1].tobytes(), datum2[2].tobytes(),
              datum2[3], datum2[4], datum2[5], datum2[6]),
             (cont2['sha1'], cont2['sha1_git'], cont2['sha256'],
              cont2['blake2s256'], cont2['length'], 'absent',
              'Content too long')
         )
 
     @pytest.mark.property_based
     @given(strategies.sets(
         elements=strategies.sampled_from(
             ['sha256', 'sha1_git', 'blake2s256']),
         min_size=0))
     def test_content_missing(self, algos):
         algos |= {'sha1'}
         cont2 = self.cont2
         missing_cont = self.missing_cont
         self.storage.content_add([cont2])
         test_contents = [cont2]
         missing_per_hash = defaultdict(list)
         for i in range(256):
             test_content = missing_cont.copy()
             for hash in algos:
                 test_content[hash] = bytes([i]) + test_content[hash][1:]
                 missing_per_hash[hash].append(test_content[hash])
             test_contents.append(test_content)
 
         self.assertCountEqual(
             self.storage.content_missing(test_contents),
             missing_per_hash['sha1']
         )
 
         for hash in algos:
             self.assertCountEqual(
                 self.storage.content_missing(test_contents, key_hash=hash),
                 missing_per_hash[hash]
             )
 
     def test_content_missing_per_sha1(self):
         # given
         cont2 = self.cont2
         missing_cont = self.missing_cont
         self.storage.content_add([cont2])
         # when
         gen = self.storage.content_missing_per_sha1([cont2['sha1'],
                                                      missing_cont['sha1']])
 
         # then
         self.assertEqual(list(gen), [missing_cont['sha1']])
 
     def test_content_get_metadata(self):
         cont1 = self.cont.copy()
         cont2 = self.cont2.copy()
 
         self.storage.content_add([cont1, cont2])
 
         gen = self.storage.content_get_metadata([cont1['sha1'], cont2['sha1']])
 
         # we only retrieve the metadata
         cont1.pop('data')
         cont2.pop('data')
 
         self.assertCountEqual(list(gen), [cont1, cont2])
 
     def test_content_get_metadata_missing_sha1(self):
         cont1 = self.cont.copy()
         cont2 = self.cont2.copy()
 
         missing_cont = self.missing_cont.copy()
 
         self.storage.content_add([cont1, cont2])
 
         gen = self.storage.content_get_metadata([missing_cont['sha1']])
 
         # All the metadata keys are None
         missing_cont.pop('data')
         for key in list(missing_cont):
             if key != 'sha1':
                 missing_cont[key] = None
 
         self.assertEqual(list(gen), [missing_cont])
 
     @staticmethod
     def _transform_entries(dir_, *, prefix=b''):
         for ent in dir_['entries']:
             yield {
                 'dir_id': dir_['id'],
                 'type': ent['type'],
                 'target': ent['target'],
                 'name': prefix + ent['name'],
                 'perms': ent['perms'],
                 'status': None,
                 'sha1': None,
                 'sha1_git': None,
                 'sha256': None,
                 'length': None,
             }
 
     def test_directory_add(self):
         init_missing = list(self.storage.directory_missing([self.dir['id']]))
         self.assertEqual([self.dir['id']], init_missing)
 
         self.storage.directory_add([self.dir])
         self.assertEqual(list(self.journal_writer.objects),
                          [('directory', self.dir)])
 
         actual_data = list(self.storage.directory_ls(self.dir['id']))
         expected_data = list(self._transform_entries(self.dir))
         self.assertCountEqual(expected_data, actual_data)
 
         after_missing = list(self.storage.directory_missing([self.dir['id']]))
         self.assertEqual([], after_missing)
 
     def test_directory_get_recursive(self):
         init_missing = list(self.storage.directory_missing([self.dir['id']]))
         self.assertEqual([self.dir['id']], init_missing)
 
         self.storage.directory_add([self.dir, self.dir2, self.dir3])
         self.assertEqual(list(self.journal_writer.objects),
                          [('directory', self.dir),
                           ('directory', self.dir2),
                           ('directory', self.dir3)])
 
         actual_data = list(self.storage.directory_ls(
             self.dir['id'], recursive=True))
         expected_data = list(self._transform_entries(self.dir))
         self.assertCountEqual(expected_data, actual_data)
 
         actual_data = list(self.storage.directory_ls(
             self.dir2['id'], recursive=True))
         expected_data = list(self._transform_entries(self.dir2))
         self.assertCountEqual(expected_data, actual_data)
 
         actual_data = list(self.storage.directory_ls(
             self.dir3['id'], recursive=True))
         expected_data = list(itertools.chain(
             self._transform_entries(self.dir3),
             self._transform_entries(self.dir, prefix=b'subdir/')))
         self.assertCountEqual(expected_data, actual_data)
 
     def test_directory_entry_get_by_path(self):
         # given
         init_missing = list(self.storage.directory_missing([self.dir3['id']]))
         self.assertEqual([self.dir3['id']], init_missing)
 
         self.storage.directory_add([self.dir3])
 
         expected_entries = [
             {
                 'dir_id': self.dir3['id'],
                 'name': b'foo',
                 'type': 'file',
                 'target': self.cont['sha1_git'],
                 'sha1': None,
                 'sha1_git': None,
                 'sha256': None,
                 'status': None,
                 'perms': from_disk.DentryPerms.content,
                 'length': None,
             },
             {
                 'dir_id': self.dir3['id'],
                 'name': b'subdir',
                 'type': 'dir',
                 'target': self.dir['id'],
                 'sha1': None,
                 'sha1_git': None,
                 'sha256': None,
                 'status': None,
                 'perms': from_disk.DentryPerms.directory,
                 'length': None,
             },
             {
                 'dir_id': self.dir3['id'],
                 'name': b'hello',
                 'type': 'file',
                 'target': b'12345678901234567890',
                 'sha1': None,
                 'sha1_git': None,
                 'sha256': None,
                 'status': None,
                 'perms': from_disk.DentryPerms.content,
                 'length': None,
             },
         ]
 
         # when (all must be found here)
         for entry, expected_entry in zip(self.dir3['entries'],
                                          expected_entries):
             actual_entry = self.storage.directory_entry_get_by_path(
                 self.dir3['id'],
                 [entry['name']])
             self.assertEqual(actual_entry, expected_entry)
 
         # when (nothing should be found here since self.dir is not persisted.)
         for entry in self.dir['entries']:
             actual_entry = self.storage.directory_entry_get_by_path(
                 self.dir['id'],
                 [entry['name']])
             self.assertIsNone(actual_entry)
 
     def test_revision_add(self):
         init_missing = self.storage.revision_missing([self.revision['id']])
         self.assertEqual([self.revision['id']], list(init_missing))
 
         self.storage.revision_add([self.revision])
 
         end_missing = self.storage.revision_missing([self.revision['id']])
         self.assertEqual([], list(end_missing))
 
         self.assertEqual(list(self.journal_writer.objects),
                          [('revision', self.revision)])
 
     def test_revision_log(self):
         # given
         # self.revision4 -is-child-of-> self.revision3
         self.storage.revision_add([self.revision3,
                                    self.revision4])
 
         # when
         actual_results = list(self.storage.revision_log(
             [self.revision4['id']]))
 
         # hack: ids generated
         for actual_result in actual_results:
             if 'id' in actual_result['author']:
                 del actual_result['author']['id']
             if 'id' in actual_result['committer']:
                 del actual_result['committer']['id']
 
         self.assertEqual(len(actual_results), 2)  # rev4 -child-> rev3
         self.assertEqual(actual_results[0],
                          self.normalize_entity(self.revision4))
         self.assertEqual(actual_results[1],
                          self.normalize_entity(self.revision3))
 
         self.assertEqual(list(self.journal_writer.objects),
                          [('revision', self.revision3),
                           ('revision', self.revision4)])
 
     def test_revision_log_with_limit(self):
         # given
         # self.revision4 -is-child-of-> self.revision3
         self.storage.revision_add([self.revision3,
                                    self.revision4])
         actual_results = list(self.storage.revision_log(
             [self.revision4['id']], 1))
 
         # hack: ids generated
         for actual_result in actual_results:
             if 'id' in actual_result['author']:
                 del actual_result['author']['id']
             if 'id' in actual_result['committer']:
                 del actual_result['committer']['id']
 
         self.assertEqual(len(actual_results), 1)
         self.assertEqual(actual_results[0], self.revision4)
 
     def test_revision_log_unknown_revision(self):
         rev_log = list(self.storage.revision_log([self.revision['id']]))
         self.assertEqual(rev_log, [])
 
     @staticmethod
     def _short_revision(revision):
         return [revision['id'], revision['parents']]
 
     def test_revision_shortlog(self):
         # given
         # self.revision4 -is-child-of-> self.revision3
         self.storage.revision_add([self.revision3,
                                    self.revision4])
 
         # when
         actual_results = list(self.storage.revision_shortlog(
             [self.revision4['id']]))
 
         self.assertEqual(len(actual_results), 2)  # rev4 -child-> rev3
         self.assertEqual(list(actual_results[0]),
                          self._short_revision(self.revision4))
         self.assertEqual(list(actual_results[1]),
                          self._short_revision(self.revision3))
 
     def test_revision_shortlog_with_limit(self):
         # given
         # self.revision4 -is-child-of-> self.revision3
         self.storage.revision_add([self.revision3,
                                    self.revision4])
         actual_results = list(self.storage.revision_shortlog(
             [self.revision4['id']], 1))
 
         self.assertEqual(len(actual_results), 1)
         self.assertEqual(list(actual_results[0]),
                          self._short_revision(self.revision4))
 
     def test_revision_get(self):
         self.storage.revision_add([self.revision])
 
         actual_revisions = list(self.storage.revision_get(
             [self.revision['id'], self.revision2['id']]))
 
         # when
         if 'id' in actual_revisions[0]['author']:
             del actual_revisions[0]['author']['id']  # hack: ids are generated
         if 'id' in actual_revisions[0]['committer']:
             del actual_revisions[0]['committer']['id']
 
         self.assertEqual(len(actual_revisions), 2)
         self.assertEqual(actual_revisions[0],
                          self.normalize_entity(self.revision))
         self.assertIsNone(actual_revisions[1])
 
     def test_revision_get_no_parents(self):
         self.storage.revision_add([self.revision3])
 
         get = list(self.storage.revision_get([self.revision3['id']]))
 
         self.assertEqual(len(get), 1)
         self.assertEqual(get[0]['parents'], [])  # no parents on this one
 
     def test_release_add(self):
         init_missing = self.storage.release_missing([self.release['id'],
                                                      self.release2['id']])
         self.assertEqual([self.release['id'], self.release2['id']],
                          list(init_missing))
 
         self.storage.release_add([self.release, self.release2])
 
         end_missing = self.storage.release_missing([self.release['id'],
                                                     self.release2['id']])
         self.assertEqual([], list(end_missing))
 
         self.assertEqual(list(self.journal_writer.objects),
                          [('release', self.release),
                           ('release', self.release2)])
 
     def test_release_get(self):
         # given
         self.storage.release_add([self.release, self.release2])
 
         # when
         actual_releases = list(self.storage.release_get([self.release['id'],
                                                          self.release2['id']]))
 
         # then
         for actual_release in actual_releases:
             if 'id' in actual_release['author']:
                 del actual_release['author']['id']  # hack: ids are generated
 
         self.assertEqual([self.normalize_entity(self.release),
                           self.normalize_entity(self.release2)],
                          [actual_releases[0], actual_releases[1]])
 
         unknown_releases = \
             list(self.storage.release_get([self.release3['id']]))
 
         self.assertIsNone(unknown_releases[0])
 
     def test_origin_add_one(self):
         origin0 = self.storage.origin_get(self.origin)
         self.assertIsNone(origin0)
 
         id = self.storage.origin_add_one(self.origin)
 
         actual_origin = self.storage.origin_get({'url': self.origin['url'],
                                                  'type': self.origin['type']})
         self.assertEqual(actual_origin['id'], id)
 
         id2 = self.storage.origin_add_one(self.origin)
 
         self.assertEqual(id, id2)
 
     def test_origin_add(self):
         origin0 = self.storage.origin_get([self.origin])[0]
         self.assertIsNone(origin0)
 
         origin1, origin2 = self.storage.origin_add([self.origin, self.origin2])
 
         actual_origin = self.storage.origin_get([{
             'url': self.origin['url'],
             'type': self.origin['type'],
         }])[0]
         self.assertEqual(actual_origin['id'], origin1['id'])
 
         actual_origin2 = self.storage.origin_get([{
             'url': self.origin2['url'],
             'type': self.origin2['type'],
         }])[0]
         self.assertEqual(actual_origin2['id'], origin2['id'])
 
         self.assertEqual(list(self.journal_writer.objects),
                          [('origin', actual_origin),
                           ('origin', actual_origin2)])
 
     def test_origin_add_twice(self):
         add1 = self.storage.origin_add([self.origin, self.origin2])
         add2 = self.storage.origin_add([self.origin, self.origin2])
 
         self.assertEqual(add1, add2)
 
     def test_origin_get_legacy(self):
         self.assertIsNone(self.storage.origin_get(self.origin))
         id = self.storage.origin_add_one(self.origin)
 
         # lookup per type and url (returns id)
         actual_origin0 = self.storage.origin_get(
             {'url': self.origin['url'], 'type': self.origin['type']})
         self.assertEqual(actual_origin0['id'], id)
 
         # lookup per id (returns dict)
         actual_origin1 = self.storage.origin_get({'id': id})
 
         self.assertEqual(actual_origin1, {'id': id,
                                           'type': self.origin['type'],
                                           'url': self.origin['url']})
 
     def test_origin_get(self):
         self.assertIsNone(self.storage.origin_get(self.origin))
         origin_id = self.storage.origin_add_one(self.origin)
 
         # lookup per type and url (returns id)
         actual_origin0 = self.storage.origin_get(
             [{'url': self.origin['url'], 'type': self.origin['type']}])
         self.assertEqual(len(actual_origin0), 1, actual_origin0)
         self.assertEqual(actual_origin0[0]['id'], origin_id)
 
         # lookup per id (returns dict)
         actual_origin1 = self.storage.origin_get([{'id': origin_id}])
 
         self.assertEqual(len(actual_origin1), 1, actual_origin1)
         self.assertEqual(actual_origin1[0], {'id': origin_id,
                                              'type': self.origin['type'],
                                              'url': self.origin['url']})
 
     def test_origin_get_consistency(self):
         self.assertIsNone(self.storage.origin_get(self.origin))
         id = self.storage.origin_add_one(self.origin)
 
         with self.assertRaises(ValueError):
             self.storage.origin_get([
                 {'url': self.origin['url'], 'type': self.origin['type']},
                 {'id': id}])
 
     def test_origin_search(self):
         found_origins = list(self.storage.origin_search(self.origin['url']))
         self.assertEqual(len(found_origins), 0)
 
         found_origins = list(self.storage.origin_search(self.origin['url'],
                                                         regexp=True))
         self.assertEqual(len(found_origins), 0)
 
         id = self.storage.origin_add_one(self.origin)
         origin_data = {'id': id,
                        'type': self.origin['type'],
                        'url': self.origin['url']}
         found_origins = list(self.storage.origin_search(self.origin['url']))
         self.assertEqual(len(found_origins), 1)
         self.assertEqual(found_origins[0], origin_data)
 
         found_origins = list(self.storage.origin_search(
             '.' + self.origin['url'][1:-1] + '.', regexp=True))
         self.assertEqual(len(found_origins), 1)
         self.assertEqual(found_origins[0], origin_data)
 
         id2 = self.storage.origin_add_one(self.origin2)
         origin2_data = {'id': id2,
                         'type': self.origin2['type'],
                         'url': self.origin2['url']}
         found_origins = list(self.storage.origin_search(self.origin2['url']))
         self.assertEqual(len(found_origins), 1)
         self.assertEqual(found_origins[0], origin2_data)
 
         found_origins = list(self.storage.origin_search(
             '.' + self.origin2['url'][1:-1] + '.', regexp=True))
         self.assertEqual(len(found_origins), 1)
         self.assertEqual(found_origins[0], origin2_data)
 
         found_origins = list(self.storage.origin_search('/'))
         self.assertEqual(len(found_origins), 2)
 
         found_origins = list(self.storage.origin_search('.*/.*', regexp=True))
         self.assertEqual(len(found_origins), 2)
 
         found_origins = list(self.storage.origin_search('/', offset=0, limit=1)) # noqa
         self.assertEqual(len(found_origins), 1)
         self.assertEqual(found_origins[0], origin_data)
 
         found_origins = list(self.storage.origin_search('.*/.*', offset=0, limit=1, regexp=True)) # noqa
         self.assertEqual(len(found_origins), 1)
         self.assertEqual(found_origins[0], origin_data)
 
         found_origins = list(self.storage.origin_search('/', offset=1, limit=1)) # noqa
         self.assertEqual(len(found_origins), 1)
         self.assertEqual(found_origins[0], origin2_data)
 
         found_origins = list(self.storage.origin_search('.*/.*', offset=1, limit=1, regexp=True)) # noqa
         self.assertEqual(len(found_origins), 1)
         self.assertEqual(found_origins[0], origin2_data)
 
     def test_origin_visit_add(self):
         # given
         self.assertIsNone(self.storage.origin_get([self.origin2])[0])
 
         origin_id = self.storage.origin_add_one(self.origin2)
         self.assertIsNotNone(origin_id)
 
         # when
         origin_visit1 = self.storage.origin_visit_add(
             origin_id,
             date=self.date_visit2)
 
         # then
         self.assertEqual(origin_visit1['origin'], origin_id)
         self.assertIsNotNone(origin_visit1['visit'])
 
         actual_origin_visits = list(self.storage.origin_visit_get(origin_id))
         self.assertEqual(actual_origin_visits,
                          [{
                              'origin': origin_id,
                              'date': self.date_visit2,
                              'visit': origin_visit1['visit'],
                              'status': 'ongoing',
                              'metadata': None,
                              'snapshot': None,
                          }])
 
         expected_origin = self.origin2.copy()
         expected_origin['id'] = origin_id
         data = {
             'origin': expected_origin,
             'date': self.date_visit2,
             'visit': origin_visit1['visit'],
             'status': 'ongoing',
             'metadata': None,
             'snapshot': None,
         }
         self.assertEqual(list(self.journal_writer.objects),
                          [('origin', expected_origin),
                           ('origin_visit', data)])
 
     def test_origin_visit_update(self):
         # given
         origin_id = self.storage.origin_add_one(self.origin2)
         origin_id2 = self.storage.origin_add_one(self.origin)
 
         origin_visit1 = self.storage.origin_visit_add(
             origin_id,
             date=self.date_visit2)
 
         origin_visit2 = self.storage.origin_visit_add(
             origin_id,
             date=self.date_visit3)
 
         origin_visit3 = self.storage.origin_visit_add(
             origin_id2,
             date=self.date_visit3)
 
         # when
         visit1_metadata = {
             'contents': 42,
             'directories': 22,
         }
         self.storage.origin_visit_update(
             origin_id, origin_visit1['visit'], status='full',
             metadata=visit1_metadata)
         self.storage.origin_visit_update(origin_id2, origin_visit3['visit'],
                                          status='partial')
 
         # then
         actual_origin_visits = list(self.storage.origin_visit_get(origin_id))
         self.assertEqual(actual_origin_visits, [{
             'origin': origin_visit2['origin'],
             'date': self.date_visit2,
             'visit': origin_visit1['visit'],
             'status': 'full',
             'metadata': visit1_metadata,
             'snapshot': None,
         }, {
             'origin': origin_visit2['origin'],
             'date': self.date_visit3,
             'visit': origin_visit2['visit'],
             'status': 'ongoing',
             'metadata': None,
             'snapshot': None,
         }])
 
         actual_origin_visits_bis = list(self.storage.origin_visit_get(
             origin_id, limit=1))
         self.assertEqual(actual_origin_visits_bis,
                          [{
                              'origin': origin_visit2['origin'],
                              'date': self.date_visit2,
                              'visit': origin_visit1['visit'],
                              'status': 'full',
                              'metadata': visit1_metadata,
                              'snapshot': None,
                          }])
 
         actual_origin_visits_ter = list(self.storage.origin_visit_get(
             origin_id, last_visit=origin_visit1['visit']))
         self.assertEqual(actual_origin_visits_ter,
                          [{
                              'origin': origin_visit2['origin'],
                              'date': self.date_visit3,
                              'visit': origin_visit2['visit'],
                              'status': 'ongoing',
                              'metadata': None,
                              'snapshot': None,
                          }])
 
         actual_origin_visits2 = list(self.storage.origin_visit_get(origin_id2))
         self.assertEqual(actual_origin_visits2,
                          [{
                              'origin': origin_visit3['origin'],
                              'date': self.date_visit3,
                              'visit': origin_visit3['visit'],
                              'status': 'partial',
                              'metadata': None,
                              'snapshot': None,
                          }])
 
         expected_origin = self.origin2.copy()
         expected_origin['id'] = origin_id
         expected_origin2 = self.origin.copy()
         expected_origin2['id'] = origin_id2
         data1 = {
             'origin': expected_origin,
             'date': self.date_visit2,
             'visit': origin_visit1['visit'],
             'status': 'ongoing',
             'metadata': None,
             'snapshot': None,
         }
         data2 = {
             'origin': expected_origin,
             'date': self.date_visit3,
             'visit': origin_visit2['visit'],
             'status': 'ongoing',
             'metadata': None,
             'snapshot': None,
         }
         data3 = {
             'origin': expected_origin2,
             'date': self.date_visit3,
             'visit': origin_visit3['visit'],
             'status': 'ongoing',
             'metadata': None,
             'snapshot': None,
         }
         data4 = {
             'origin': expected_origin,
             'date': self.date_visit2,
             'visit': origin_visit1['visit'],
             'metadata': visit1_metadata,
             'status': 'full',
             'snapshot': None,
         }
         data5 = {
             'origin': expected_origin2,
             'date': self.date_visit3,
             'visit': origin_visit3['visit'],
             'status': 'partial',
             'metadata': None,
             'snapshot': None,
         }
         self.assertEqual(list(self.journal_writer.objects),
                          [('origin', expected_origin),
                           ('origin', expected_origin2),
                           ('origin_visit', data1),
                           ('origin_visit', data2),
                           ('origin_visit', data3),
                           ('origin_visit', data4),
                           ('origin_visit', data5)])
 
+    def test_origin_visit_update_missing_snapshot(self):
+        # given
+        origin_id = self.storage.origin_add_one(self.origin)
+
+        origin_visit = self.storage.origin_visit_add(
+            origin_id,
+            date=self.date_visit1)
+
+        # when
+        self.storage.origin_visit_update(
+            origin_id, origin_visit['visit'],
+            snapshot=self.snapshot['id'])
+
+        # then
+        actual_origin_visit = self.storage.origin_visit_get_by(
+            origin_visit['origin'], origin_visit['visit'])
+        self.assertEqual(actual_origin_visit['snapshot'], self.snapshot['id'])
+
+        # when
+        self.storage.snapshot_add(self.snapshot)
+        self.assertEqual(actual_origin_visit['snapshot'], self.snapshot['id'])
+
     def test_origin_visit_get_by(self):
         origin_id = self.storage.origin_add_one(self.origin2)
         origin_id2 = self.storage.origin_add_one(self.origin)
 
         origin_visit1 = self.storage.origin_visit_add(
             origin_id,
             date=self.date_visit2)
 
         self.storage.snapshot_add(origin_id, origin_visit1['visit'],
                                   self.snapshot)
 
         # Add some other {origin, visit} entries
         self.storage.origin_visit_add(origin_id, date=self.date_visit3)
         self.storage.origin_visit_add(origin_id2, date=self.date_visit3)
 
         # when
         visit1_metadata = {
             'contents': 42,
             'directories': 22,
         }
 
         self.storage.origin_visit_update(
             origin_id, origin_visit1['visit'], status='full',
             metadata=visit1_metadata)
 
         expected_origin_visit = origin_visit1.copy()
         expected_origin_visit.update({
             'origin': origin_id,
             'visit': origin_visit1['visit'],
             'date': self.date_visit2,
             'metadata': visit1_metadata,
             'status': 'full',
             'snapshot': self.snapshot['id'],
         })
 
         # when
         actual_origin_visit1 = self.storage.origin_visit_get_by(
             origin_visit1['origin'], origin_visit1['visit'])
 
         # then
         self.assertEqual(actual_origin_visit1, expected_origin_visit)
 
     def test_origin_visit_get_by_no_result(self):
         # No result
         actual_origin_visit = self.storage.origin_visit_get_by(
             10, 999)
 
         self.assertIsNone(actual_origin_visit)
 
     def test_person_get(self):
         # given (person injection through revision for example)
         self.storage.revision_add([self.revision])
         rev = list(self.storage.revision_get([self.revision['id']]))[0]
 
         id0 = rev['committer']['id']
         person0 = self.revision['committer']
 
         id1 = rev['author']['id']
         person1 = self.revision['author']
 
         # when
         actual_persons = self.storage.person_get([id0, id1])
 
         # then
         self.assertEqual(
             list(actual_persons), [
                 {
                     'id': id0,
                     'fullname': person0['fullname'],
                     'name': person0['name'],
                     'email': person0['email'],
                 },
                 {
                     'id': id1,
                     'fullname': person1['fullname'],
                     'name': person1['name'],
                     'email': person1['email'],
                 }
             ])
 
     def test_person_get_fullname_unicity(self):
         # given (person injection through revisions for example)
         revision = self.revision
 
         # create a revision with same committer fullname but wo name and email
         revision2 = copy.deepcopy(self.revision2)
         revision2['committer'] = dict(revision['committer'])
         revision2['committer']['email'] = None
         revision2['committer']['name'] = None
 
         self.storage.revision_add([revision])
         self.storage.revision_add([revision2])
 
         # when getting added revisions
         revisions = list(
             self.storage.revision_get([revision['id'], revision2['id']]))
 
         # then
         # check committers are the same
         self.assertEqual(revisions[0]['committer'],
                          revisions[1]['committer'])
 
         # check person_get return same result
         person0 = list(
             self.storage.person_get([revisions[0]['committer']['id']]))[0]
 
         person1 = list(
             self.storage.person_get([revisions[1]['committer']['id']]))[0]
 
         self.assertEqual(person0, person1)
 
     def test_snapshot_add_get_empty(self):
         origin_id = self.storage.origin_add_one(self.origin)
         origin_visit1 = self.storage.origin_visit_add(origin_id,
                                                       self.date_visit1)
         visit_id = origin_visit1['visit']
 
         self.storage.snapshot_add(self.empty_snapshot)
         self.storage.origin_visit_update(
             origin_id, visit_id, snapshot=self.empty_snapshot['id'])
 
         by_id = self.storage.snapshot_get(self.empty_snapshot['id'])
         self.assertEqual(by_id, self.empty_snapshot)
 
         by_ov = self.storage.snapshot_get_by_origin_visit(origin_id, visit_id)
         self.assertEqual(by_ov, self.empty_snapshot)
 
         expected_origin = self.origin.copy()
         expected_origin['id'] = origin_id
         data1 = {
             'origin': expected_origin,
             'date': self.date_visit1,
             'visit': origin_visit1['visit'],
             'status': 'ongoing',
             'metadata': None,
             'snapshot': None,
         }
         data2 = {
             'origin': expected_origin,
             'date': self.date_visit1,
             'visit': origin_visit1['visit'],
             'status': 'ongoing',
             'metadata': None,
             'snapshot': self.empty_snapshot['id'],
         }
         self.assertEqual(list(self.journal_writer.objects),
                          [('origin', expected_origin),
                           ('origin_visit', data1),
                           ('snapshot', self.empty_snapshot),
                           ('origin_visit', data2)])
 
     def test_snapshot_add_get_empty__legacy_add(self):
         origin_id = self.storage.origin_add_one(self.origin)
         origin_visit1 = self.storage.origin_visit_add(origin_id,
                                                       self.date_visit1)
         visit_id = origin_visit1['visit']
 
         self.storage.snapshot_add(origin_id, visit_id, self.empty_snapshot)
 
         by_id = self.storage.snapshot_get(self.empty_snapshot['id'])
         self.assertEqual(by_id, self.empty_snapshot)
 
         by_ov = self.storage.snapshot_get_by_origin_visit(origin_id, visit_id)
         self.assertEqual(by_ov, self.empty_snapshot)
 
         expected_origin = self.origin.copy()
         expected_origin['id'] = origin_id
         data1 = {
             'origin': expected_origin,
             'date': self.date_visit1,
             'visit': origin_visit1['visit'],
             'status': 'ongoing',
             'metadata': None,
             'snapshot': None,
         }
         data2 = {
             'origin': expected_origin,
             'date': self.date_visit1,
             'visit': origin_visit1['visit'],
             'status': 'ongoing',
             'metadata': None,
             'snapshot': self.empty_snapshot['id'],
         }
         self.assertEqual(list(self.journal_writer.objects),
                          [('origin', expected_origin),
                           ('origin_visit', data1),
                           ('snapshot', self.empty_snapshot),
                           ('origin_visit', data2)])
 
     def test_snapshot_add_get_complete(self):
         origin_id = self.storage.origin_add_one(self.origin)
         origin_visit1 = self.storage.origin_visit_add(origin_id,
                                                       self.date_visit1)
         visit_id = origin_visit1['visit']
 
         self.storage.snapshot_add(origin_id, visit_id, self.complete_snapshot)
 
         by_id = self.storage.snapshot_get(self.complete_snapshot['id'])
         self.assertEqual(by_id, self.complete_snapshot)
 
         by_ov = self.storage.snapshot_get_by_origin_visit(origin_id, visit_id)
         self.assertEqual(by_ov, self.complete_snapshot)
 
     def test_snapshot_add_count_branches(self):
         origin_id = self.storage.origin_add_one(self.origin)
         origin_visit1 = self.storage.origin_visit_add(origin_id,
                                                       self.date_visit1)
         visit_id = origin_visit1['visit']
 
         self.storage.snapshot_add(origin_id, visit_id, self.complete_snapshot)
 
         snp_id = self.complete_snapshot['id']
         snp_size = self.storage.snapshot_count_branches(snp_id)
 
         expected_snp_size = {
             'alias': 1,
             'content': 1,
             'directory': 1,
             'release': 1,
             'revision': 1,
             'snapshot': 1,
             None: 1
         }
 
         self.assertEqual(snp_size, expected_snp_size)
 
     def test_snapshot_add_get_paginated(self):
         origin_id = self.storage.origin_add_one(self.origin)
         origin_visit1 = self.storage.origin_visit_add(origin_id,
                                                       self.date_visit1)
         visit_id = origin_visit1['visit']
 
         self.storage.snapshot_add(origin_id, visit_id, self.complete_snapshot)
 
         snp_id = self.complete_snapshot['id']
         branches = self.complete_snapshot['branches']
         branch_names = list(sorted(branches))
 
         snapshot = self.storage.snapshot_get_branches(snp_id,
                                                       branches_from=b'release')
 
         rel_idx = branch_names.index(b'release')
         expected_snapshot = {
             'id': snp_id,
             'branches': {
                 name: branches[name]
                 for name in branch_names[rel_idx:]
             },
             'next_branch': None,
         }
 
         self.assertEqual(snapshot, expected_snapshot)
 
         snapshot = self.storage.snapshot_get_branches(snp_id,
                                                       branches_count=1)
 
         expected_snapshot = {
             'id': snp_id,
             'branches': {
                  branch_names[0]: branches[branch_names[0]],
             },
             'next_branch': b'content',
         }
         self.assertEqual(snapshot, expected_snapshot)
 
         snapshot = self.storage.snapshot_get_branches(
             snp_id, branches_from=b'directory', branches_count=3)
 
         dir_idx = branch_names.index(b'directory')
         expected_snapshot = {
             'id': snp_id,
             'branches': {
                 name: branches[name]
                 for name in branch_names[dir_idx:dir_idx + 3]
             },
             'next_branch': branch_names[dir_idx + 3],
         }
 
         self.assertEqual(snapshot, expected_snapshot)
 
     def test_snapshot_add_get_filtered(self):
         origin_id = self.storage.origin_add_one(self.origin)
         origin_visit1 = self.storage.origin_visit_add(origin_id,
                                                       self.date_visit1)
         visit_id = origin_visit1['visit']
 
         self.storage.snapshot_add(origin_id, visit_id, self.complete_snapshot)
 
         snp_id = self.complete_snapshot['id']
         branches = self.complete_snapshot['branches']
 
         snapshot = self.storage.snapshot_get_branches(
             snp_id, target_types=['release', 'revision'])
 
         expected_snapshot = {
             'id': snp_id,
             'branches': {
                 name: tgt
                 for name, tgt in branches.items()
                 if tgt and tgt['target_type'] in ['release', 'revision']
             },
             'next_branch': None,
         }
 
         self.assertEqual(snapshot, expected_snapshot)
 
         snapshot = self.storage.snapshot_get_branches(snp_id,
                                                       target_types=['alias'])
 
         expected_snapshot = {
             'id': snp_id,
             'branches': {
                 name: tgt
                 for name, tgt in branches.items()
                 if tgt and tgt['target_type'] == 'alias'
             },
             'next_branch': None,
         }
 
         self.assertEqual(snapshot, expected_snapshot)
 
     def test_snapshot_add_get(self):
         origin_id = self.storage.origin_add_one(self.origin)
         origin_visit1 = self.storage.origin_visit_add(origin_id,
                                                       self.date_visit1)
         visit_id = origin_visit1['visit']
 
         self.storage.snapshot_add(origin_id, visit_id, self.snapshot)
 
         by_id = self.storage.snapshot_get(self.snapshot['id'])
         self.assertEqual(by_id, self.snapshot)
 
         by_ov = self.storage.snapshot_get_by_origin_visit(origin_id, visit_id)
         self.assertEqual(by_ov, self.snapshot)
 
         origin_visit_info = self.storage.origin_visit_get_by(origin_id,
                                                              visit_id)
         self.assertEqual(origin_visit_info['snapshot'], self.snapshot['id'])
 
     def test_snapshot_add_nonexistent_visit(self):
         origin_id = self.storage.origin_add_one(self.origin)
         visit_id = 54164461156
 
         self.journal_writer.objects[:] = []
 
         self.storage.snapshot_add(self.snapshot)
 
         with self.assertRaises(ValueError):
             self.storage.origin_visit_update(
                 origin_id, visit_id, snapshot=self.snapshot['id'])
 
         self.assertEqual(list(self.journal_writer.objects), [
             ('snapshot', self.snapshot)])
 
     def test_snapshot_add_nonexistent_visit__legacy_add(self):
         origin_id = self.storage.origin_add_one(self.origin)
         visit_id = 54164461156
 
         self.journal_writer.objects[:] = []
 
         with self.assertRaises(ValueError):
             self.storage.snapshot_add(origin_id, visit_id, self.snapshot)
 
         # Note: the actual legacy behavior was to abort before adding
         # the snapshot; but delaying non-existence checks makes the
         # compatibility code simpler
         self.assertEqual(list(self.journal_writer.objects), [
             ('snapshot', self.snapshot)])
 
     def test_snapshot_add_twice(self):
         origin_id = self.storage.origin_add_one(self.origin)
         origin_visit1 = self.storage.origin_visit_add(origin_id,
                                                       self.date_visit1)
         visit1_id = origin_visit1['visit']
         self.storage.snapshot_add(self.snapshot)
         self.storage.origin_visit_update(
             origin_id, visit1_id, snapshot=self.snapshot['id'])
 
         by_ov1 = self.storage.snapshot_get_by_origin_visit(origin_id,
                                                            visit1_id)
         self.assertEqual(by_ov1, self.snapshot)
 
         origin_visit2 = self.storage.origin_visit_add(origin_id,
                                                       self.date_visit2)
         visit2_id = origin_visit2['visit']
 
         self.storage.snapshot_add(self.snapshot)
         self.storage.origin_visit_update(
             origin_id, visit2_id, snapshot=self.snapshot['id'])
 
         by_ov2 = self.storage.snapshot_get_by_origin_visit(origin_id,
                                                            visit2_id)
         self.assertEqual(by_ov2, self.snapshot)
 
         expected_origin = self.origin.copy()
         expected_origin['id'] = origin_id
         data1 = {
             'origin': expected_origin,
             'date': self.date_visit1,
             'visit': origin_visit1['visit'],
             'status': 'ongoing',
             'metadata': None,
             'snapshot': None,
         }
         data2 = {
             'origin': expected_origin,
             'date': self.date_visit1,
             'visit': origin_visit1['visit'],
             'status': 'ongoing',
             'metadata': None,
             'snapshot': self.snapshot['id'],
         }
         data3 = {
             'origin': expected_origin,
             'date': self.date_visit2,
             'visit': origin_visit2['visit'],
             'status': 'ongoing',
             'metadata': None,
             'snapshot': None,
         }
         data4 = {
             'origin': expected_origin,
             'date': self.date_visit2,
             'visit': origin_visit2['visit'],
             'status': 'ongoing',
             'metadata': None,
             'snapshot': self.snapshot['id'],
         }
         self.assertEqual(list(self.journal_writer.objects),
                          [('origin', expected_origin),
                           ('origin_visit', data1),
                           ('snapshot', self.snapshot),
                           ('origin_visit', data2),
                           ('origin_visit', data3),
                           ('snapshot', self.snapshot),
                           ('origin_visit', data4)])
 
     def test_snapshot_add_twice__legacy_add(self):
         origin_id = self.storage.origin_add_one(self.origin)
         origin_visit1 = self.storage.origin_visit_add(origin_id,
                                                       self.date_visit1)
         visit1_id = origin_visit1['visit']
         self.storage.snapshot_add(origin_id, visit1_id, self.snapshot)
 
         by_ov1 = self.storage.snapshot_get_by_origin_visit(origin_id,
                                                            visit1_id)
         self.assertEqual(by_ov1, self.snapshot)
 
         origin_visit2 = self.storage.origin_visit_add(origin_id,
                                                       self.date_visit2)
         visit2_id = origin_visit2['visit']
 
         self.storage.snapshot_add(origin_id, visit2_id, self.snapshot)
 
         by_ov2 = self.storage.snapshot_get_by_origin_visit(origin_id,
                                                            visit2_id)
         self.assertEqual(by_ov2, self.snapshot)
 
         expected_origin = self.origin.copy()
         expected_origin['id'] = origin_id
         data1 = {
             'origin': expected_origin,
             'date': self.date_visit1,
             'visit': origin_visit1['visit'],
             'status': 'ongoing',
             'metadata': None,
             'snapshot': None,
         }
         data2 = {
             'origin': expected_origin,
             'date': self.date_visit1,
             'visit': origin_visit1['visit'],
             'status': 'ongoing',
             'metadata': None,
             'snapshot': self.snapshot['id'],
         }
         data3 = {
             'origin': expected_origin,
             'date': self.date_visit2,
             'visit': origin_visit2['visit'],
             'status': 'ongoing',
             'metadata': None,
             'snapshot': None,
         }
         data4 = {
             'origin': expected_origin,
             'date': self.date_visit2,
             'visit': origin_visit2['visit'],
             'status': 'ongoing',
             'metadata': None,
             'snapshot': self.snapshot['id'],
         }
         self.assertEqual(list(self.journal_writer.objects),
                          [('origin', expected_origin),
                           ('origin_visit', data1),
                           ('snapshot', self.snapshot),
                           ('origin_visit', data2),
                           ('origin_visit', data3),
                           ('snapshot', self.snapshot),
                           ('origin_visit', data4)])
 
     def test_snapshot_get_nonexistent(self):
         bogus_snapshot_id = b'bogus snapshot id 00'
         bogus_origin_id = 1
         bogus_visit_id = 1
 
         by_id = self.storage.snapshot_get(bogus_snapshot_id)
         self.assertIsNone(by_id)
 
         by_ov = self.storage.snapshot_get_by_origin_visit(bogus_origin_id,
                                                           bogus_visit_id)
         self.assertIsNone(by_ov)
 
     def test_snapshot_get_latest(self):
         origin_id = self.storage.origin_add_one(self.origin)
         origin_visit1 = self.storage.origin_visit_add(origin_id,
                                                       self.date_visit1)
         visit1_id = origin_visit1['visit']
         origin_visit2 = self.storage.origin_visit_add(origin_id,
                                                       self.date_visit2)
         visit2_id = origin_visit2['visit']
 
         # Add a visit with the same date as the previous one
         origin_visit3 = self.storage.origin_visit_add(origin_id,
                                                       self.date_visit2)
         visit3_id = origin_visit3['visit']
 
         # Two visits, both with no snapshot: latest snapshot is None
         self.assertIsNone(self.storage.snapshot_get_latest(origin_id))
 
         # Add snapshot to visit1, latest snapshot = visit 1 snapshot
         self.storage.snapshot_add(self.complete_snapshot)
         self.storage.origin_visit_update(
             origin_id, visit1_id, snapshot=self.complete_snapshot['id'])
         self.assertEqual(self.complete_snapshot,
                          self.storage.snapshot_get_latest(origin_id))
 
         # Status filter: both visits are status=ongoing, so no snapshot
         # returned
         self.assertIsNone(
             self.storage.snapshot_get_latest(origin_id,
                                              allowed_statuses=['full'])
         )
 
         # Mark the first visit as completed and check status filter again
         self.storage.origin_visit_update(origin_id, visit1_id, status='full')
         self.assertEqual(
             self.complete_snapshot,
             self.storage.snapshot_get_latest(origin_id,
                                              allowed_statuses=['full']),
         )
 
         # Add snapshot to visit2 and check that the new snapshot is returned
         self.storage.snapshot_add(self.empty_snapshot)
         self.storage.origin_visit_update(
             origin_id, visit2_id, snapshot=self.empty_snapshot['id'])
         self.assertEqual(self.empty_snapshot,
                          self.storage.snapshot_get_latest(origin_id))
 
         # Check that the status filter is still working
         self.assertEqual(
             self.complete_snapshot,
             self.storage.snapshot_get_latest(origin_id,
                                              allowed_statuses=['full']),
         )
 
         # Add snapshot to visit3 (same date as visit2) and check that
         # the new snapshot is returned
         self.storage.snapshot_add(self.complete_snapshot)
         self.storage.origin_visit_update(
             origin_id, visit3_id, snapshot=self.complete_snapshot['id'])
         self.assertEqual(self.complete_snapshot,
                          self.storage.snapshot_get_latest(origin_id))
 
+    def test_snapshot_get_latest__missing_snapshot(self):
+        origin_id = self.storage.origin_add_one(self.origin)
+        origin_visit1 = self.storage.origin_visit_add(origin_id,
+                                                      self.date_visit1)
+        visit1_id = origin_visit1['visit']
+        origin_visit2 = self.storage.origin_visit_add(origin_id,
+                                                      self.date_visit2)
+        visit2_id = origin_visit2['visit']
+
+        # Two visits, both with no snapshot: latest snapshot is None
+        self.assertIsNone(self.storage.snapshot_get_latest(origin_id))
+
+        # Add unknown snapshot to visit1, latest snapshot = None
+        self.storage.origin_visit_update(
+            origin_id, visit1_id, snapshot=self.complete_snapshot['id'])
+        self.assertIsNone(self.storage.snapshot_get_latest(origin_id))
+
+        # Status filter: both visits are status=ongoing, so no snapshot
+        # returned
+        self.assertIsNone(
+            self.storage.snapshot_get_latest(origin_id,
+                                             allowed_statuses=['full'])
+        )
+
+        # Mark the first visit as completed and check status filter again
+        self.storage.origin_visit_update(origin_id, visit1_id, status='full')
+        self.assertIsNone(
+            self.storage.snapshot_get_latest(origin_id,
+                                             allowed_statuses=['full']),
+        )
+
+        # Actually add the snapshot and check status filter again
+        self.storage.snapshot_add(self.complete_snapshot)
+        self.assertEqual(
+            self.complete_snapshot,
+            self.storage.snapshot_get_latest(origin_id)
+        )
+
+        # Add unknown snapshot to visit2 and check that the old snapshot
+        # is still returned
+        self.storage.origin_visit_update(
+            origin_id, visit2_id, snapshot=self.empty_snapshot['id'])
+        self.assertEqual(
+            self.complete_snapshot,
+            self.storage.snapshot_get_latest(origin_id))
+
+        # Actually add that snapshot and check that the new one is returned
+        self.storage.snapshot_add(self.empty_snapshot)
+        self.assertEqual(
+            self.empty_snapshot,
+            self.storage.snapshot_get_latest(origin_id)
+        )
+
     def test_snapshot_get_latest__legacy_add(self):
         origin_id = self.storage.origin_add_one(self.origin)
         origin_visit1 = self.storage.origin_visit_add(origin_id,
                                                       self.date_visit1)
         visit1_id = origin_visit1['visit']
         origin_visit2 = self.storage.origin_visit_add(origin_id,
                                                       self.date_visit2)
         visit2_id = origin_visit2['visit']
 
         # Add a visit with the same date as the previous one
         origin_visit3 = self.storage.origin_visit_add(origin_id,
                                                       self.date_visit2)
         visit3_id = origin_visit3['visit']
 
         # Two visits, both with no snapshot: latest snapshot is None
         self.assertIsNone(self.storage.snapshot_get_latest(origin_id))
 
         # Add snapshot to visit1, latest snapshot = visit 1 snapshot
         self.storage.snapshot_add(origin_id, visit1_id, self.complete_snapshot)
         self.assertEqual(self.complete_snapshot,
                          self.storage.snapshot_get_latest(origin_id))
 
         # Status filter: both visits are status=ongoing, so no snapshot
         # returned
         self.assertIsNone(
             self.storage.snapshot_get_latest(origin_id,
                                              allowed_statuses=['full'])
         )
 
         # Mark the first visit as completed and check status filter again
         self.storage.origin_visit_update(origin_id, visit1_id, status='full')
         self.assertEqual(
             self.complete_snapshot,
             self.storage.snapshot_get_latest(origin_id,
                                              allowed_statuses=['full']),
         )
 
         # Add snapshot to visit2 and check that the new snapshot is returned
         self.storage.snapshot_add(origin_id, visit2_id, self.empty_snapshot)
         self.assertEqual(self.empty_snapshot,
                          self.storage.snapshot_get_latest(origin_id))
 
         # Check that the status filter is still working
         self.assertEqual(
             self.complete_snapshot,
             self.storage.snapshot_get_latest(origin_id,
                                              allowed_statuses=['full']),
         )
 
         # Add snapshot to visit3 (same date as visit2) and check that
         # the new snapshot is returned
         self.storage.snapshot_add(origin_id, visit3_id, self.complete_snapshot)
         self.assertEqual(self.complete_snapshot,
                          self.storage.snapshot_get_latest(origin_id))
 
     def test_stat_counters(self):
         expected_keys = ['content', 'directory',
                          'origin', 'person', 'revision']
 
         # Initially, all counters are 0
 
         self.storage.refresh_stat_counters()
         counters = self.storage.stat_counters()
         self.assertTrue(set(expected_keys) <= set(counters))
         for key in expected_keys:
             self.assertEqual(counters[key], 0)
 
         # Add a content. Only the content counter should increase.
 
         self.storage.content_add([self.cont])
 
         self.storage.refresh_stat_counters()
         counters = self.storage.stat_counters()
 
         self.assertTrue(set(expected_keys) <= set(counters))
         for key in expected_keys:
             if key != 'content':
                 self.assertEqual(counters[key], 0)
         self.assertEqual(counters['content'], 1)
 
         # Add other objects. Check their counter increased as well.
 
         origin_id = self.storage.origin_add_one(self.origin2)
         origin_visit1 = self.storage.origin_visit_add(
             origin_id,
             date=self.date_visit2)
         self.storage.snapshot_add(origin_id, origin_visit1['visit'],
                                   self.snapshot)
         self.storage.directory_add([self.dir])
         self.storage.revision_add([self.revision])
 
         self.storage.refresh_stat_counters()
         counters = self.storage.stat_counters()
         self.assertEqual(counters['content'], 1)
         self.assertEqual(counters['directory'], 1)
         self.assertEqual(counters['snapshot'], 1)
         self.assertEqual(counters['origin'], 1)
         self.assertEqual(counters['revision'], 1)
         self.assertEqual(counters['person'], 2)
 
     def test_content_find_with_present_content(self):
         # 1. with something to find
         cont = self.cont
         self.storage.content_add([cont])
 
         actually_present = self.storage.content_find({'sha1': cont['sha1']})
 
         actually_present.pop('ctime')
         self.assertEqual(actually_present, {
             'sha1': cont['sha1'],
             'sha256': cont['sha256'],
             'sha1_git': cont['sha1_git'],
             'blake2s256': cont['blake2s256'],
             'length': cont['length'],
             'status': 'visible'
         })
 
         # 2. with something to find
         actually_present = self.storage.content_find(
             {'sha1_git': cont['sha1_git']})
 
         actually_present.pop('ctime')
         self.assertEqual(actually_present, {
             'sha1': cont['sha1'],
             'sha256': cont['sha256'],
             'sha1_git': cont['sha1_git'],
             'blake2s256': cont['blake2s256'],
             'length': cont['length'],
             'status': 'visible'
         })
 
         # 3. with something to find
         actually_present = self.storage.content_find(
             {'sha256': cont['sha256']})
 
         actually_present.pop('ctime')
         self.assertEqual(actually_present, {
             'sha1': cont['sha1'],
             'sha256': cont['sha256'],
             'sha1_git': cont['sha1_git'],
             'blake2s256': cont['blake2s256'],
             'length': cont['length'],
             'status': 'visible'
         })
 
         # 4. with something to find
         actually_present = self.storage.content_find({
             'sha1': cont['sha1'],
             'sha1_git': cont['sha1_git'],
             'sha256': cont['sha256'],
             'blake2s256': cont['blake2s256'],
         })
 
         actually_present.pop('ctime')
         self.assertEqual(actually_present, {
             'sha1': cont['sha1'],
             'sha256': cont['sha256'],
             'sha1_git': cont['sha1_git'],
             'blake2s256': cont['blake2s256'],
             'length': cont['length'],
             'status': 'visible'
         })
 
     def test_content_find_with_non_present_content(self):
         # 1. with something that does not exist
         missing_cont = self.missing_cont
 
         actually_present = self.storage.content_find(
             {'sha1': missing_cont['sha1']})
 
         self.assertIsNone(actually_present)
 
         # 2. with something that does not exist
         actually_present = self.storage.content_find(
             {'sha1_git': missing_cont['sha1_git']})
 
         self.assertIsNone(actually_present)
 
         # 3. with something that does not exist
         actually_present = self.storage.content_find(
             {'sha256': missing_cont['sha256']})
 
         self.assertIsNone(actually_present)
 
     def test_content_find_bad_input(self):
         # 1. with bad input
         with self.assertRaises(ValueError):
             self.storage.content_find({})  # empty is bad
 
         # 2. with bad input
         with self.assertRaises(ValueError):
             self.storage.content_find(
                 {'unknown-sha1': 'something'})  # not the right key
 
     def test_object_find_by_sha1_git(self):
         sha1_gits = [b'00000000000000000000']
         expected = {
             b'00000000000000000000': [],
         }
 
         self.storage.content_add([self.cont])
         sha1_gits.append(self.cont['sha1_git'])
         expected[self.cont['sha1_git']] = [{
             'sha1_git': self.cont['sha1_git'],
             'type': 'content',
             'id': self.cont['sha1'],
         }]
 
         self.storage.directory_add([self.dir])
         sha1_gits.append(self.dir['id'])
         expected[self.dir['id']] = [{
             'sha1_git': self.dir['id'],
             'type': 'directory',
             'id': self.dir['id'],
         }]
 
         self.storage.revision_add([self.revision])
         sha1_gits.append(self.revision['id'])
         expected[self.revision['id']] = [{
             'sha1_git': self.revision['id'],
             'type': 'revision',
             'id': self.revision['id'],
         }]
 
         self.storage.release_add([self.release])
         sha1_gits.append(self.release['id'])
         expected[self.release['id']] = [{
             'sha1_git': self.release['id'],
             'type': 'release',
             'id': self.release['id'],
         }]
 
         ret = self.storage.object_find_by_sha1_git(sha1_gits)
         for val in ret.values():
             for obj in val:
                 del obj['object_id']
 
         self.assertEqual(expected, ret)
 
     def test_tool_add(self):
         tool = {
             'name': 'some-unknown-tool',
             'version': 'some-version',
             'configuration': {"debian-package": "some-package"},
         }
 
         actual_tool = self.storage.tool_get(tool)
         self.assertIsNone(actual_tool)  # does not exist
 
         # add it
         actual_tools = list(self.storage.tool_add([tool]))
 
         self.assertEqual(len(actual_tools), 1)
         actual_tool = actual_tools[0]
         self.assertIsNotNone(actual_tool)  # now it exists
         new_id = actual_tool.pop('id')
         self.assertEqual(actual_tool, tool)
 
         actual_tools2 = list(self.storage.tool_add([tool]))
         actual_tool2 = actual_tools2[0]
         self.assertIsNotNone(actual_tool2)  # now it exists
         new_id2 = actual_tool2.pop('id')
 
         self.assertEqual(new_id, new_id2)
         self.assertEqual(actual_tool, actual_tool2)
 
     def test_tool_add_multiple(self):
         tool = {
             'name': 'some-unknown-tool',
             'version': 'some-version',
             'configuration': {"debian-package": "some-package"},
         }
 
         actual_tools = list(self.storage.tool_add([tool]))
         self.assertEqual(len(actual_tools), 1)
 
         new_tools = [tool, {
             'name': 'yet-another-tool',
             'version': 'version',
             'configuration': {},
         }]
 
         actual_tools = list(self.storage.tool_add(new_tools))
         self.assertEqual(len(actual_tools), 2)
 
         # order not guaranteed, so we iterate over results to check
         for tool in actual_tools:
             _id = tool.pop('id')
             self.assertIsNotNone(_id)
             self.assertIn(tool, new_tools)
 
     def test_tool_get_missing(self):
         tool = {
             'name': 'unknown-tool',
             'version': '3.1.0rc2-31-ga2cbb8c',
             'configuration': {"command_line": "nomossa <filepath>"},
         }
 
         actual_tool = self.storage.tool_get(tool)
 
         self.assertIsNone(actual_tool)
 
     def test_tool_metadata_get_missing_context(self):
         tool = {
             'name': 'swh-metadata-translator',
             'version': '0.0.1',
             'configuration': {"context": "unknown-context"},
         }
 
         actual_tool = self.storage.tool_get(tool)
 
         self.assertIsNone(actual_tool)
 
     def test_tool_metadata_get(self):
         tool = {
             'name': 'swh-metadata-translator',
             'version': '0.0.1',
             'configuration': {"type": "local", "context": "npm"},
         }
 
         tools = list(self.storage.tool_add([tool]))
         expected_tool = tools[0]
 
         # when
         actual_tool = self.storage.tool_get(tool)
 
         # then
         self.assertEqual(expected_tool, actual_tool)
 
     def test_metadata_provider_get(self):
         # given
         no_provider = self.storage.metadata_provider_get(6459456445615)
         self.assertIsNone(no_provider)
         # when
         provider_id = self.storage.metadata_provider_add(
             self.provider['name'],
             self.provider['type'],
             self.provider['url'],
             self.provider['metadata'])
 
         actual_provider = self.storage.metadata_provider_get(provider_id)
         expected_provider = {
             'provider_name': self.provider['name'],
             'provider_url': self.provider['url']
         }
         # then
         del actual_provider['id']
         self.assertTrue(actual_provider, expected_provider)
 
     def test_metadata_provider_get_by(self):
         # given
         no_provider = self.storage.metadata_provider_get_by({
             'provider_name': self.provider['name'],
             'provider_url': self.provider['url']
         })
         self.assertIsNone(no_provider)
         # when
         provider_id = self.storage.metadata_provider_add(
             self.provider['name'],
             self.provider['type'],
             self.provider['url'],
             self.provider['metadata'])
 
         actual_provider = self.storage.metadata_provider_get_by({
             'provider_name': self.provider['name'],
             'provider_url': self.provider['url']
         })
         # then
         self.assertTrue(provider_id, actual_provider['id'])
 
     def test_origin_metadata_add(self):
         # given
         origin_id = self.storage.origin_add([self.origin])[0]['id']
         origin_metadata0 = list(self.storage.origin_metadata_get_by(origin_id))
         self.assertTrue(len(origin_metadata0) == 0)
 
         tools = list(self.storage.tool_add([self.metadata_tool]))
         tool = tools[0]
 
         self.storage.metadata_provider_add(
                            self.provider['name'],
                            self.provider['type'],
                            self.provider['url'],
                            self.provider['metadata'])
         provider = self.storage.metadata_provider_get_by({
                             'provider_name': self.provider['name'],
                             'provider_url': self.provider['url']
                       })
 
         # when adding for the same origin 2 metadatas
         self.storage.origin_metadata_add(
                     origin_id,
                     self.origin_metadata['discovery_date'],
                     provider['id'],
                     tool['id'],
                     self.origin_metadata['metadata'])
         actual_om1 = list(self.storage.origin_metadata_get_by(origin_id))
         # then
         self.assertEqual(len(actual_om1), 1)
         self.assertEqual(actual_om1[0]['origin_id'], origin_id)
 
     def test_origin_metadata_get(self):
         # given
         origin_id = self.storage.origin_add([self.origin])[0]['id']
         origin_id2 = self.storage.origin_add([self.origin2])[0]['id']
 
         self.storage.metadata_provider_add(self.provider['name'],
                                            self.provider['type'],
                                            self.provider['url'],
                                            self.provider['metadata'])
         provider = self.storage.metadata_provider_get_by({
                             'provider_name': self.provider['name'],
                             'provider_url': self.provider['url']
                    })
         tool = list(self.storage.tool_add([self.metadata_tool]))[0]
         # when adding for the same origin 2 metadatas
         self.storage.origin_metadata_add(
                     origin_id,
                     self.origin_metadata['discovery_date'],
                     provider['id'],
                     tool['id'],
                     self.origin_metadata['metadata'])
         self.storage.origin_metadata_add(
                     origin_id2,
                     self.origin_metadata2['discovery_date'],
                     provider['id'],
                     tool['id'],
                     self.origin_metadata2['metadata'])
         self.storage.origin_metadata_add(
                     origin_id,
                     self.origin_metadata2['discovery_date'],
                     provider['id'],
                     tool['id'],
                     self.origin_metadata2['metadata'])
         all_metadatas = list(self.storage.origin_metadata_get_by(origin_id))
         metadatas_for_origin2 = list(self.storage.origin_metadata_get_by(
                                           origin_id2))
         expected_results = [{
             'origin_id': origin_id,
             'discovery_date': datetime.datetime(
                                 2017, 1, 1, 23, 0,
                                 tzinfo=datetime.timezone.utc),
             'metadata': {
                 'name': 'test_origin_metadata',
                 'version': '0.0.1'
             },
             'provider_id': provider['id'],
             'provider_name': 'hal',
             'provider_type': 'deposit-client',
             'provider_url': 'http:///hal/inria',
             'tool_id': tool['id']
         }, {
             'origin_id': origin_id,
             'discovery_date': datetime.datetime(
                                 2015, 1, 1, 23, 0,
                                 tzinfo=datetime.timezone.utc),
             'metadata': {
                 'name': 'test_origin_metadata',
                 'version': '0.0.1'
             },
             'provider_id': provider['id'],
             'provider_name': 'hal',
             'provider_type': 'deposit-client',
             'provider_url': 'http:///hal/inria',
             'tool_id': tool['id']
         }]
 
         # then
         self.assertEqual(len(all_metadatas), 2)
         self.assertEqual(len(metadatas_for_origin2), 1)
         self.assertCountEqual(all_metadatas, expected_results)
 
     def test_origin_metadata_get_by_provider_type(self):
         # given
         origin_id = self.storage.origin_add([self.origin])[0]['id']
         origin_id2 = self.storage.origin_add([self.origin2])[0]['id']
         provider1_id = self.storage.metadata_provider_add(
                            self.provider['name'],
                            self.provider['type'],
                            self.provider['url'],
                            self.provider['metadata'])
         provider1 = self.storage.metadata_provider_get_by({
                             'provider_name': self.provider['name'],
                             'provider_url': self.provider['url']
                    })
         self.assertEqual(provider1,
                          self.storage.metadata_provider_get(provider1_id))
 
         provider2_id = self.storage.metadata_provider_add(
                             'swMATH',
                             'registry',
                             'http://www.swmath.org/',
                             {'email': 'contact@swmath.org',
                              'license': 'All rights reserved'})
         provider2 = self.storage.metadata_provider_get_by({
                             'provider_name': 'swMATH',
                             'provider_url': 'http://www.swmath.org/'
                    })
         self.assertEqual(provider2,
                          self.storage.metadata_provider_get(provider2_id))
 
         # using the only tool now inserted in the data.sql, but for this
         # provider should be a crawler tool (not yet implemented)
         tool = list(self.storage.tool_add([self.metadata_tool]))[0]
 
         # when adding for the same origin 2 metadatas
         self.storage.origin_metadata_add(
                     origin_id,
                     self.origin_metadata['discovery_date'],
                     provider1['id'],
                     tool['id'],
                     self.origin_metadata['metadata'])
         self.storage.origin_metadata_add(
                     origin_id2,
                     self.origin_metadata2['discovery_date'],
                     provider2['id'],
                     tool['id'],
                     self.origin_metadata2['metadata'])
         provider_type = 'registry'
         m_by_provider = list(self.storage.
                              origin_metadata_get_by(
                                 origin_id2,
                                 provider_type))
         for item in m_by_provider:
             if 'id' in item:
                 del item['id']
         expected_results = [{
             'origin_id': origin_id2,
             'discovery_date': datetime.datetime(
                                 2017, 1, 1, 23, 0,
                                 tzinfo=datetime.timezone.utc),
             'metadata': {
                 'name': 'test_origin_metadata',
                 'version': '0.0.1'
             },
             'provider_id': provider2['id'],
             'provider_name': 'swMATH',
             'provider_type': provider_type,
             'provider_url': 'http://www.swmath.org/',
             'tool_id': tool['id']
         }]
         # then
 
         self.assertEqual(len(m_by_provider), 1)
         self.assertEqual(m_by_provider, expected_results)
 
 
 class CommonPropTestStorage:
     def assert_contents_ok(self, expected_contents, actual_contents,
                            keys_to_check={'sha1', 'data'}):
         """Assert that a given list of contents matches on a given set of keys.
 
         """
         for k in keys_to_check:
             expected_list = sorted([c[k] for c in expected_contents])
             actual_list = sorted([c[k] for c in actual_contents])
             self.assertEqual(actual_list, expected_list)
 
     @given(gen_contents(min_size=1, max_size=4))
     def test_generate_content_get(self, contents):
         # add contents to storage
         self.storage.content_add(contents)
 
         # input the list of sha1s we want from storage
         get_sha1s = [c['sha1'] for c in contents]
 
         # retrieve contents
         actual_contents = list(self.storage.content_get(get_sha1s))
 
         self.assert_contents_ok(contents, actual_contents)
 
     @given(gen_contents(min_size=1, max_size=4))
     def test_generate_content_get_metadata(self, contents):
         # add contents to storage
         self.storage.content_add(contents)
 
         # input the list of sha1s we want from storage
         get_sha1s = [c['sha1'] for c in contents]
 
         # retrieve contents
         actual_contents = list(self.storage.content_get_metadata(get_sha1s))
 
         self.assertEqual(len(actual_contents), len(contents))
 
         # will check that all contents are retrieved correctly
         one_content = contents[0]
         # content_get_metadata does not return data
         keys_to_check = set(one_content.keys()) - {'data'}
         self.assert_contents_ok(contents, actual_contents,
                                 keys_to_check=keys_to_check)
 
     def test_generate_content_get_range_limit_none(self):
         """content_get_range call with wrong limit input should fail"""
         with self.assertRaises(ValueError) as e:
             self.storage.content_get_range(start=None, end=None, limit=None)
 
         self.assertEqual(e.exception.args, (
             'Development error: limit should not be None',))
 
     @given(gen_contents(min_size=1, max_size=4))
     def test_generate_content_get_range_no_limit(self, contents):
         """content_get_range returns contents within range provided"""
         self.reset_storage_tables()
         # add contents to storage
         self.storage.content_add(contents)
 
         # input the list of sha1s we want from storage
         get_sha1s = sorted([c['sha1'] for c in contents])
         start = get_sha1s[0]
         end = get_sha1s[-1]
 
         # retrieve contents
         actual_result = self.storage.content_get_range(start, end)
 
         actual_contents = actual_result['contents']
         actual_next = actual_result['next']
 
         self.assertEqual(len(contents), len(actual_contents))
         self.assertIsNone(actual_next)
 
         one_content = contents[0]
         keys_to_check = set(one_content.keys()) - {'data'}
         self.assert_contents_ok(contents, actual_contents, keys_to_check)
 
     @given(gen_contents(min_size=4, max_size=4))
     def test_generate_content_get_range_limit(self, contents):
         """content_get_range paginates results if limit exceeded"""
         self.reset_storage_tables()
         contents_map = {c['sha1']: c for c in contents}
 
         # add contents to storage
         self.storage.content_add(contents)
 
         # input the list of sha1s we want from storage
         get_sha1s = sorted([c['sha1'] for c in contents])
         start = get_sha1s[0]
         end = get_sha1s[-1]
 
         # retrieve contents limited to 3 results
         limited_results = len(contents) - 1
         actual_result = self.storage.content_get_range(start, end,
                                                        limit=limited_results)
 
         actual_contents = actual_result['contents']
         actual_next = actual_result['next']
 
         self.assertEqual(limited_results, len(actual_contents))
         self.assertIsNotNone(actual_next)
         self.assertEqual(actual_next, get_sha1s[-1])
 
         expected_contents = [contents_map[sha1] for sha1 in get_sha1s[:-1]]
         keys_to_check = set(contents[0].keys()) - {'data'}
         self.assert_contents_ok(expected_contents, actual_contents,
                                 keys_to_check)
 
         # retrieve next part
         actual_results2 = self.storage.content_get_range(start=end, end=end)
         actual_contents2 = actual_results2['contents']
         actual_next2 = actual_results2['next']
 
         self.assertEqual(1, len(actual_contents2))
         self.assertIsNone(actual_next2)
 
         self.assert_contents_ok([contents_map[actual_next]], actual_contents2,
 
                                 keys_to_check)
 
     def test_origin_get_invalid_id_legacy(self):
         invalid_origin_id = 1
 
         origin_info = self.storage.origin_get({'id': invalid_origin_id})
         self.assertIsNone(origin_info)
 
         origin_visits = list(self.storage.origin_visit_get(
             invalid_origin_id))
         self.assertEqual(origin_visits, [])
 
     def test_origin_get_invalid_id(self):
         origin_info = self.storage.origin_get([{'id': 1}, {'id': 2}])
         self.assertEqual(origin_info, [None, None])
 
         origin_visits = list(self.storage.origin_visit_get(1))
         self.assertEqual(origin_visits, [])
 
     @given(gen_origins(min_size=100, max_size=100))
     def test_origin_get_range(self, new_origins):
 
         nb_origins = len(new_origins)
 
         self.storage.origin_add(new_origins)
 
         origin_from = random.randint(1, nb_origins)
         origin_count = random.randint(1, nb_origins - origin_from)
 
         expected_origins = []
         for i in range(origin_from, origin_from + origin_count):
             expected_origins.append(self.storage.origin_get({'id': i}))
 
         actual_origins = list(
             self.storage.origin_get_range(origin_from=origin_from,
                                           origin_count=origin_count))
 
         self.assertEqual(actual_origins, expected_origins)
 
         origin_from = -1
         origin_count = 10
         origins = list(
             self.storage.origin_get_range(origin_from=origin_from,
                                           origin_count=origin_count))
         self.assertEqual(len(origins), origin_count)
 
         origin_from = 10000
         origins = list(
             self.storage.origin_get_range(origin_from=origin_from,
                                           origin_count=origin_count))
         self.assertEqual(len(origins), 0)
 
     def test_origin_count(self):
 
         new_origins = [
             {
                 'type': 'git',
                 'url': 'https://github.com/user1/repo1'
             },
             {
                 'type': 'git',
                 'url': 'https://github.com/user2/repo1'
             },
             {
                 'type': 'git',
                 'url': 'https://github.com/user3/repo1'
             },
             {
                 'type': 'git',
                 'url': 'https://gitlab.com/user1/repo1'
             },
             {
                 'type': 'git',
                 'url': 'https://gitlab.com/user2/repo1'
             }
         ]
 
         self.storage.origin_add(new_origins)
 
         self.assertEqual(self.storage.origin_count('github'), 3)
         self.assertEqual(self.storage.origin_count('gitlab'), 2)
         self.assertEqual(
             self.storage.origin_count('.*user.*', regexp=True), 5)
         self.assertEqual(
             self.storage.origin_count('.*user.*', regexp=False), 0)
         self.assertEqual(
             self.storage.origin_count('.*user1.*', regexp=True), 2)
         self.assertEqual(
             self.storage.origin_count('.*user1.*', regexp=False), 0)
 
 
 @pytest.mark.db
 class TestLocalStorage(CommonTestStorage, StorageTestDbFixture,
                        unittest.TestCase):
     """Test the local storage"""
 
     # Can only be tested with local storage as you can't mock
     # datetimes for the remote server
     def test_fetch_history(self):
         origin = self.storage.origin_add_one(self.origin)
         with patch('datetime.datetime'):
             datetime.datetime.now.return_value = self.fetch_history_date
             fetch_history_id = self.storage.fetch_history_start(origin)
             datetime.datetime.now.assert_called_with(tz=datetime.timezone.utc)
 
         with patch('datetime.datetime'):
             datetime.datetime.now.return_value = self.fetch_history_end
             self.storage.fetch_history_end(fetch_history_id,
                                            self.fetch_history_data)
 
         fetch_history = self.storage.fetch_history_get(fetch_history_id)
         expected_fetch_history = self.fetch_history_data.copy()
 
         expected_fetch_history['id'] = fetch_history_id
         expected_fetch_history['origin'] = origin
         expected_fetch_history['date'] = self.fetch_history_date
         expected_fetch_history['duration'] = self.fetch_history_duration
 
         self.assertEqual(expected_fetch_history, fetch_history)
 
     # This test is only relevant on the local storage, with an actual
     # objstorage raising an exception
     def test_content_add_objstorage_exception(self):
         self.storage.objstorage.add = Mock(
             side_effect=Exception('mocked broken objstorage')
         )
 
         with self.assertRaises(Exception) as e:
             self.storage.content_add([self.cont])
 
         self.assertEqual(e.exception.args, ('mocked broken objstorage',))
         missing = list(self.storage.content_missing([self.cont]))
         self.assertEqual(missing, [self.cont['sha1']])
 
 
 @pytest.mark.db
 @pytest.mark.property_based
 class PropTestLocalStorage(CommonPropTestStorage, StorageTestDbFixture,
                            unittest.TestCase):
     pass
 
 
 class AlteringSchemaTest(TestStorageData, StorageTestDbFixture,
                          unittest.TestCase):
     """This class is dedicated for the rare case where the schema needs to
        be altered dynamically.
 
        Otherwise, the tests could be blocking when ran altogether.
 
     """
     def test_content_update(self):
         self.storage.journal_writer = None  # TODO, not supported
 
         cont = copy.deepcopy(self.cont)
 
         self.storage.content_add([cont])
         # alter the sha1_git for example
         cont['sha1_git'] = hash_to_bytes(
             '3a60a5275d0333bf13468e8b3dcab90f4046e654')
 
         self.storage.content_update([cont], keys=['sha1_git'])
 
         with self.storage.get_db().transaction() as cur:
             cur.execute('SELECT sha1, sha1_git, sha256, length, status'
                         ' FROM content WHERE sha1 = %s',
                         (cont['sha1'],))
             datum = cur.fetchone()
 
         self.assertEqual(
             (datum[0], datum[1], datum[2],
              datum[3], datum[4]),
             (cont['sha1'], cont['sha1_git'], cont['sha256'],
              cont['length'], 'visible'))
 
     def test_content_update_with_new_cols(self):
         self.storage.journal_writer = None  # TODO, not supported
 
         with self.storage.get_db().transaction() as cur:
             cur.execute("""alter table content
                            add column test text default null,
                            add column test2 text default null""")
 
         cont = copy.deepcopy(self.cont2)
         self.storage.content_add([cont])
         cont['test'] = 'value-1'
         cont['test2'] = 'value-2'
 
         self.storage.content_update([cont], keys=['test', 'test2'])
         with self.storage.get_db().transaction() as cur:
             cur.execute(
                 'SELECT sha1, sha1_git, sha256, length, status, test, test2'
                 ' FROM content WHERE sha1 = %s',
                 (cont['sha1'],))
 
             datum = cur.fetchone()
 
         self.assertEqual(
             (datum[0], datum[1], datum[2],
              datum[3], datum[4], datum[5], datum[6]),
             (cont['sha1'], cont['sha1_git'], cont['sha256'],
              cont['length'], 'visible', cont['test'], cont['test2']))
 
         with self.storage.get_db().transaction() as cur:
             cur.execute("""alter table content drop column test,
                            drop column test2""")