diff --git a/sql/swh-func.sql b/sql/swh-func.sql
index 4d1c54e7d..273f74dff 100644
--- a/sql/swh-func.sql
+++ b/sql/swh-func.sql
@@ -1,2204 +1,2222 @@
 -- 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 with a single "bytea" column for fast object lookup.
 create or replace function swh_mktemp_bytea()
     returns void
     language sql
 as $$
     create temporary table tmp_bytea (
       id bytea
     ) on commit drop;
 $$;
 
 -- create a temporary table for occurrence_history
 create or replace function swh_mktemp_occurrence_history()
     returns void
     language sql
 as $$
     create temporary table tmp_occurrence_history(
         like occurrence_history including defaults,
         visit bigint not null
     ) on commit drop;
     alter table tmp_occurrence_history
       drop column visits,
       drop column object_id;
 $$;
 
 -- create a temporary table for entity_history, sans id
 create or replace function swh_mktemp_entity_history()
     returns void
     language sql
 as $$
     create temporary table tmp_entity_history (
         like entity_history including defaults) on commit drop;
     alter table tmp_entity_history drop column id;
 $$;
 
 -- create a temporary table for entities called tmp_entity_lister,
 -- with only the columns necessary for retrieving the uuid of a listed
 -- entity.
 create or replace function swh_mktemp_entity_lister()
     returns void
     language sql
 as $$
   create temporary table tmp_entity_lister (
     id              bigint,
     lister_metadata jsonb
   ) on commit drop;
 $$;
 
 
 -- 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_content are missing from content
 --
 -- operates in bulk: 0. swh_mktemp(content), 1. COPY to tmp_content,
 -- 2. call this function
 create or replace function swh_content_missing()
     returns setof content_signature
     language plpgsql
 as $$
 begin
     return query (
       select sha1, sha1_git, sha256, blake2s256 from tmp_content as tmp
       where not exists (
         select 1 from content as c
         where c.sha1 = tmp.sha1 and
               c.sha1_git = tmp.sha1_git and
               c.sha256 = tmp.sha256
       )
     );
     return;
 end
 $$;
 
 -- check which entries of tmp_content_sha1 are missing from content
 --
 -- operates in bulk: 0. swh_mktemp_content_sha1(), 1. COPY to tmp_content_sha1,
 -- 2. call this function
 create or replace function swh_content_missing_per_sha1()
     returns setof sha1
     language plpgsql
 as $$
 begin
     return query
            (select id::sha1
             from tmp_bytea as tmp
             where not exists
             (select 1 from content as c where c.sha1=tmp.id));
 end
 $$;
 
 
 -- 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 $$
 begin
     insert into content (sha1, sha1_git, sha256, blake2s256, length, status)
         select distinct sha1, sha1_git, sha256, blake2s256, length, status
 	from tmp_content
 	where (sha1, sha1_git, sha256) in (
             select sha1, sha1_git, sha256
             from swh_content_missing()
         );
         -- TODO XXX use postgres 9.5 "UPSERT" support here, when available.
         -- Specifically, using "INSERT .. ON CONFLICT IGNORE" we can avoid
         -- the extra swh_content_missing() query here.
     return;
 end
 $$;
 
 
 -- 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 $$
 begin
     return query
 	select id from tmp_directory t
 	where not exists (
 	    select 1 from directory d
 	    where d.id = t.id);
     return;
 end
 $$;
 
 
 -- Retrieve information on directory from temporary table
 create or replace function swh_directory_get()
     returns setof directory
     language plpgsql
 as $$
 begin
     return query
 	select d.*
         from tmp_directory t
         inner join directory d on t.id = d.id;
     return;
 end
 $$;
 
 
 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 $$
     select t.id, r.date, r.date_offset, r.date_neg_utc_offset,
            r.committer_date, r.committer_date_offset, r.committer_date_neg_utc_offset,
            r.type, r.directory, r.message,
            a.id, a.fullname, a.name, a.email,
            c.id, c.fullname, c.name, c.email,
            r.metadata, r.synthetic, t.parents, r.object_id
     from swh_revision_list(root_revisions, num_revs) as t
     left join revision r on t.id = r.id
     left join person a on a.id = r.author
     left join person c on c.id = r.committer;
 $$;
 
 
 -- Retrieve revisions from tmp_bytea in bulk
 create or replace function swh_revision_get()
     returns setof revision_entry
     language plpgsql
 as $$
 begin
     return query
         select r.id, r.date, r.date_offset, r.date_neg_utc_offset,
                r.committer_date, r.committer_date_offset, r.committer_date_neg_utc_offset,
                r.type, r.directory, r.message,
                a.id, a.fullname, a.name, a.email, c.id, c.fullname, c.name, c.email, r.metadata, r.synthetic,
          array(select rh.parent_id::bytea from revision_history rh where rh.id = t.id order by rh.parent_rank)
                    as parents, r.object_id
         from tmp_bytea t
         left join revision r on t.id = r.id
         left join person a on a.id = r.author
         left join person c on c.id = r.committer;
     return;
 end
 $$;
 
 -- List missing revisions from tmp_bytea
 create or replace function swh_revision_missing()
     returns setof sha1_git
     language plpgsql
 as $$
 begin
     return query
         select id::sha1_git from tmp_bytea t
 	where not exists (
 	    select 1 from revision r
 	    where r.id = t.id);
     return;
 end
 $$;
 
 -- 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
 );
 
 -- Detailed entry for release
 create or replace function swh_release_get()
     returns setof release_entry
     language plpgsql
 as $$
 begin
     return query
         select r.id, r.target, r.target_type, r.date, r.date_offset, r.date_neg_utc_offset, r.name, r.comment,
                r.synthetic, p.id as author_id, p.fullname as author_fullname, p.name as author_name, p.email as author_email, r.object_id
         from tmp_bytea t
         inner join release r on t.id = r.id
         inner join person p on p.id = r.author;
     return;
 end
 $$;
 
 -- 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
 $$;
 
 
 -- List missing releases from tmp_bytea
 create or replace function swh_release_missing()
     returns setof sha1_git
     language plpgsql
 as $$
 begin
   return query
     select id::sha1_git from tmp_bytea t
     where not exists (
       select 1 from release r
       where r.id = t.id);
 end
 $$;
 
 
 -- 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
 $$;
 
 create or replace function swh_occurrence_update_for_origin(origin_id bigint)
   returns void
   language sql
 as $$
   delete from occurrence where origin = origin_id;
   insert into occurrence (origin, branch, target, target_type)
     select origin, branch, target, target_type
     from occurrence_history
     where origin = origin_id and
           (select visit from origin_visit
            where origin = origin_id
            order by date desc
            limit 1) = any(visits);
 $$;
 
 create or replace function swh_occurrence_update_all()
   returns void
   language plpgsql
 as $$
 declare
   origin_id origin.id%type;
 begin
   for origin_id in
     select distinct id from origin
   loop
     perform swh_occurrence_update_for_origin(origin_id);
   end loop;
   return;
 end;
 $$;
 
 -- 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 $$
   with last_known_visit as (
     select coalesce(max(visit), 0) as visit
     from origin_visit
     where origin = origin_id
   )
   insert into origin_visit (origin, date, visit, status)
   values (origin_id, date, (select visit from last_known_visit) + 1, 'ongoing')
   returning visit;
 $$;
 
 -- add tmp_occurrence_history entries to occurrence_history
 --
 -- operates in bulk: 0. swh_mktemp(occurrence_history), 1. COPY to tmp_occurrence_history,
 -- 2. call this function
 create or replace function swh_occurrence_history_add()
     returns void
     language plpgsql
 as $$
 declare
   origin_id origin.id%type;
 begin
   -- Create or update occurrence_history
   with occurrence_history_id_visit as (
     select tmp_occurrence_history.*, object_id, visits from tmp_occurrence_history
     left join occurrence_history using(origin, branch, target, target_type)
   ),
   occurrences_to_update as (
     select object_id, visit from occurrence_history_id_visit where object_id is not null
   ),
   update_occurrences as (
     update occurrence_history
     set visits = array(select unnest(occurrence_history.visits) as e
                         union
                        select occurrences_to_update.visit as e
                        order by e)
     from occurrences_to_update
     where occurrence_history.object_id = occurrences_to_update.object_id
   )
   insert into occurrence_history (origin, branch, target, target_type, visits)
     select origin, branch, target, target_type, ARRAY[visit]
       from occurrence_history_id_visit
       where object_id is null;
 
   -- update occurrence
   for origin_id in
     select distinct origin from tmp_occurrence_history
   loop
     perform swh_occurrence_update_for_origin(origin_id);
   end loop;
   return;
 end
 $$;
 
 
 -- 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 $$
     with recursive path as (
 	-- Recursively build a path from the requested content to a root
 	-- directory. Each iteration returns a pair (dir_id, filename) where
 	-- filename is relative to dir_id. Stops when no parent directory can
 	-- be found.
 	(select dir.id as dir_id, dir_entry_f.name as name, 0 as depth
 	 from directory_entry_file as dir_entry_f
 	 join content on content.sha1_git = dir_entry_f.target
 	 join directory as dir on dir.file_entries @> array[dir_entry_f.id]
 	 where content.sha1 = content_id
 	 limit 1)
 	union all
 	(select dir.id as dir_id,
 		(dir_entry_d.name || '/' || path.name)::unix_path as name,
 		path.depth + 1
 	 from path
 	 join directory_entry_dir as dir_entry_d on dir_entry_d.target = path.dir_id
 	 join directory as dir on dir.dir_entries @> array[dir_entry_d.id]
 	 limit 1)
     )
     select dir_id, name from path order by depth desc limit 1;
 $$;
 
 
 -- Walk the revision history starting from a given revision, until a matching
 -- occurrence is found. Return all occurrence information if one is found, NULL
 -- otherwise.
 create or replace function swh_revision_find_occurrence(revision_id sha1_git)
     returns occurrence
     language sql
     stable
 as $$
 	select origin, branch, target, target_type
   from swh_revision_list_children(ARRAY[revision_id] :: bytea[]) as rev_list
 	left join occurrence_history occ_hist
   on rev_list.id = occ_hist.target
 	where occ_hist.origin is not null and
         occ_hist.target_type = 'revision'
 	limit 1;
 $$;
 
 -- 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 $$
     select *
     from origin_visit
     where origin=origin
     order by date desc
 $$;
 
 
 -- Retrieve occurrence by filtering on origin_id and optionally on
 -- branch_name and/or validity range
 create or replace function swh_occurrence_get_by(
        origin_id bigint,
        branch_name bytea default NULL,
        date timestamptz default NULL)
     returns setof occurrence_history
     language plpgsql
 as $$
 declare
     filters text[] := array[] :: text[];  -- AND-clauses used to filter content
     visit_id bigint;
     q text;
 begin
     if origin_id is null then
         raise exception 'Needs an origin_id to get an occurrence.';
     end if;
     filters := filters || format('origin = %L', origin_id);
     if branch_name is not null then
         filters := filters || format('branch = %L', branch_name);
     end if;
     if date is not null then
         select visit from swh_visit_find_by_date(origin_id, date) into visit_id;
     else
         select visit from origin_visit where origin = origin_id order by origin_visit.date desc limit 1 into visit_id;
     end if;
     if visit_id is null then
         return;
     end if;
     filters := filters || format('%L = any(visits)', visit_id);
 
     q = format('select * from occurrence_history where %s',
                array_to_string(filters, ' and '));
     return query execute q;
 end
 $$;
 
 
 -- Retrieve revisions by occurrence criterion filtering
 create or replace function swh_revision_get_by(
        origin_id bigint,
        branch_name bytea default NULL,
        date timestamptz default NULL)
     returns setof revision_entry
     language sql
     stable
 as $$
     select r.id, r.date, r.date_offset, r.date_neg_utc_offset,
         r.committer_date, r.committer_date_offset, r.committer_date_neg_utc_offset,
         r.type, r.directory, r.message,
         a.id, a.fullname, a.name, a.email, c.id, c.fullname, c.name, c.email, r.metadata, r.synthetic,
         array(select rh.parent_id::bytea
             from revision_history rh
             where rh.id = r.id
             order by rh.parent_rank
         ) as parents, r.object_id
     from swh_occurrence_get_by(origin_id, branch_name, date) as occ
     inner join revision r on occ.target = r.id
     left join person a on a.id = r.author
     left join person c on c.id = r.committer;
 $$;
 
 -- Retrieve a release by occurrence criterion
 create or replace function swh_release_get_by(
        origin_id bigint)
     returns setof release_entry
     language sql
     stable
 as $$
    select r.id, r.target, r.target_type, r.date, r.date_offset, r.date_neg_utc_offset,
         r.name, r.comment, r.synthetic, a.id as author_id, a.fullname as author_fullname,
         a.name as author_name, a.email as author_email, r.object_id
     from release r
     inner join occurrence_history occ on occ.target = r.target
     left join person a on a.id = r.author
     where occ.origin = origin_id and occ.target_type = 'revision' and r.target_type = 'revision';
 $$;
 
 
 create type content_provenance as (
   content  sha1_git,
   revision sha1_git,
   origin   bigint,
   visit    bigint,
   path     unix_path
 );
 
 COMMENT ON TYPE content_provenance IS 'Provenance information on content';
 
 create or replace function swh_content_find_provenance(content_id sha1_git)
     returns setof content_provenance
     language sql
 as $$
     with subscripted_paths as (
         select content, revision_paths, generate_subscripts(revision_paths, 1) as s
         from cache_content_revision
         where content = content_id
     ),
     cleaned_up_contents as (
         select content, revision_paths[s][1]::sha1_git as revision, revision_paths[s][2]::unix_path as path
         from subscripted_paths
     )
     select cuc.content, cuc.revision, cro.origin, cro.visit, cuc.path
     from cleaned_up_contents cuc
     inner join cache_revision_origin cro using(revision)
 $$;
 
 COMMENT ON FUNCTION swh_content_find_provenance(sha1_git) IS 'Given a content, provide provenance information on it';
 
 
 create type object_found as (
     sha1_git   sha1_git,
     type       object_type,
     id         bytea,       -- sha1 or sha1_git depending on object_type
     object_id  bigint
 );
 
 -- Find objects by sha1_git, return their type and their main identifier
 create or replace function swh_object_find_by_sha1_git()
     returns setof object_found
     language plpgsql
 as $$
 begin
     return query
     with known_objects as ((
         select id as sha1_git, 'release'::object_type as type, id, object_id from release r
         where exists (select 1 from tmp_bytea t where t.id = r.id)
     ) union all (
         select id as sha1_git, 'revision'::object_type as type, id, object_id from revision r
         where exists (select 1 from tmp_bytea t where t.id = r.id)
     ) union all (
         select id as sha1_git, 'directory'::object_type as type, id, object_id from directory d
         where exists (select 1 from tmp_bytea t where t.id = d.id)
     ) union all (
         select sha1_git as sha1_git, 'content'::object_type as type, sha1 as id, object_id from content c
         where exists (select 1 from tmp_bytea t where t.id = c.sha1_git)
     ))
     select t.id::sha1_git as sha1_git, k.type, k.id, k.object_id from tmp_bytea t
       left join known_objects k on t.id = k.sha1_git;
 end
 $$;
 
 -- Create entries in entity_history from tmp_entity_history
 --
 -- TODO: do something smarter to compress the entries if the data
 -- didn't change.
 create or replace function swh_entity_history_add()
     returns void
     language plpgsql
 as $$
 begin
     insert into entity_history (
         uuid, parent, name, type, description, homepage, active, generated, lister_metadata, metadata, validity
     ) select * from tmp_entity_history;
     return;
 end
 $$;
 
 
 create or replace function swh_update_entity_from_entity_history()
     returns trigger
     language plpgsql
 as $$
 begin
     insert into entity (uuid, parent, name, type, description, homepage, active, generated,
       lister_metadata, metadata, last_seen, last_id)
       select uuid, parent, name, type, description, homepage, active, generated,
              lister_metadata, metadata, unnest(validity), id
       from entity_history
       where uuid = NEW.uuid
       order by unnest(validity) desc limit 1
     on conflict (uuid) do update set
       parent = EXCLUDED.parent,
       name = EXCLUDED.name,
       type = EXCLUDED.type,
       description = EXCLUDED.description,
       homepage = EXCLUDED.homepage,
       active = EXCLUDED.active,
       generated = EXCLUDED.generated,
       lister_metadata = EXCLUDED.lister_metadata,
       metadata = EXCLUDED.metadata,
       last_seen = EXCLUDED.last_seen,
       last_id = EXCLUDED.last_id;
 
     return null;
 end
 $$;
 
 create trigger update_entity
   after insert or update
   on entity_history
   for each row
   execute procedure swh_update_entity_from_entity_history();
 
 -- map an id of tmp_entity_lister to a full entity
 create type entity_id as (
     id               bigint,
     uuid             uuid,
     parent           uuid,
     name             text,
     type             entity_type,
     description      text,
     homepage         text,
     active           boolean,
     generated        boolean,
     lister_metadata  jsonb,
     metadata         jsonb,
     last_seen        timestamptz,
     last_id          bigint
 );
 
 -- find out the uuid of the entries of entity with the metadata
 -- contained in tmp_entity_lister
 create or replace function swh_entity_from_tmp_entity_lister()
     returns setof entity_id
     language plpgsql
 as $$
 begin
   return query
     select t.id, e.*
     from tmp_entity_lister t
     left join entity e
     on e.lister_metadata @> t.lister_metadata;
   return;
 end
 $$;
 
 create or replace function swh_entity_get(entity_uuid uuid)
     returns setof entity
     language sql
     stable
 as $$
   with recursive entity_hierarchy as (
   select e.*
     from entity e where uuid = entity_uuid
     union
     select p.*
     from entity_hierarchy e
     join entity p on e.parent = p.uuid
   )
   select *
   from entity_hierarchy;
 $$;
 
 
 -- 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 $$
     with rels as (
         select * from release
         where object_id > min_excl and object_id <= max_incl
     )
     select r.id, r.target, r.target_type, r.date, r.date_offset, r.date_neg_utc_offset, r.name, r.comment,
            r.synthetic, p.id as author_id, p.fullname as author_fullname, p.name as author_name, p.email as author_email, r.object_id
     from rels r
     left join person p on p.id = r.author
     order by r.object_id;
 $$;
 
 
 create or replace function swh_cache_content_revision_add()
     returns void
     language plpgsql
 as $$
 declare
   cnt bigint;
   d sha1_git;
 begin
   delete from tmp_bytea t where exists (select 1 from cache_content_revision_processed ccrp where t.id = ccrp.revision);
 
   select count(*) from tmp_bytea into cnt;
   if cnt <> 0 then
     create temporary table tmp_ccr (
         content sha1_git,
         directory sha1_git,
         path unix_path
     ) on commit drop;
 
     create temporary table tmp_ccrd (
         directory sha1_git,
         revision sha1_git
     ) on commit drop;
 
     insert into tmp_ccrd
       select directory, id as revision
       from tmp_bytea
       inner join revision using(id);
 
     insert into cache_content_revision_processed
       select distinct id from tmp_bytea order by id;
 
     for d in
       select distinct directory from tmp_ccrd
     loop
       insert into tmp_ccr
         select sha1_git as content, d as directory, name as path
         from swh_directory_walk(d)
         where type='file';
     end loop;
 
     with revision_contents as (
       select content, false as blacklisted, array_agg(ARRAY[revision::bytea, path::bytea]) as revision_paths
       from tmp_ccr
       inner join tmp_ccrd using (directory)
       group by content
       order by content
     ), updated_cache_entries as (
       update cache_content_revision ccr
       set revision_paths = ccr.revision_paths || rc.revision_paths
       from revision_contents rc
       where ccr.content = rc.content and ccr.blacklisted = false
       returning ccr.content
     ) insert into cache_content_revision
         select * from revision_contents rc
         where not exists (select 1 from updated_cache_entries uce where uce.content = rc.content)
         order by rc.content
       on conflict (content) do update
         set revision_paths = cache_content_revision.revision_paths || EXCLUDED.revision_paths
         where cache_content_revision.blacklisted = false;
     return;
   else
     return;
   end if;
 end
 $$;
 
 COMMENT ON FUNCTION swh_cache_content_revision_add() IS 'Cache the revisions from tmp_bytea into cache_content_revision';
 
 
 create or replace function swh_occurrence_by_origin_visit(origin_id bigint, visit_id bigint)
     returns setof occurrence
     language sql
     stable
 as $$
   select origin, branch, target, target_type from occurrence_history
   where origin = origin_id and visit_id = ANY(visits);
 $$;
 
 create type cache_content_signature as (
   sha1      sha1,
   sha1_git  sha1_git,
   sha256    sha256,
   revision_paths  bytea[][]
 );
 
 create or replace function swh_cache_content_get_all()
        returns setof cache_content_signature
        language sql
        stable
 as $$
     SELECT c.sha1, c.sha1_git, c.sha256, ccr.revision_paths
     FROM cache_content_revision ccr
     INNER JOIN content as c
     ON ccr.content = c.sha1_git
 $$;
 
 COMMENT ON FUNCTION swh_cache_content_get_all() IS 'Retrieve batch of contents';
 
 
 create or replace function swh_cache_content_get(target sha1_git)
        returns setof cache_content_signature
        language sql
        stable
 as $$
     SELECT c.sha1, c.sha1_git, c.sha256, ccr.revision_paths
     FROM cache_content_revision ccr
     INNER JOIN content as c
     ON ccr.content = c.sha1_git
     where ccr.content = target
 $$;
 
 COMMENT ON FUNCTION swh_cache_content_get(sha1_git) IS 'Retrieve cache content information';
 
 create or replace function swh_revision_from_target(target sha1_git, target_type object_type)
     returns sha1_git
     language plpgsql
 as $$
 #variable_conflict use_variable
 begin
    while target_type = 'release' loop
        select r.target, r.target_type from release r where r.id = target into target, target_type;
    end loop;
    if target_type = 'revision' then
        return target;
    else
        return null;
    end if;
 end
 $$;
 
 create or replace function swh_cache_revision_origin_add(origin_id bigint, visit_id bigint)
     returns setof sha1_git
     language plpgsql
 as $$
 declare
     visit_exists bool;
 begin
   select true from origin_visit where origin = origin_id and visit = visit_id into visit_exists;
 
   if not visit_exists then
       return;
   end if;
 
   visit_exists := null;
 
   select true from cache_revision_origin where origin = origin_id and visit = visit_id limit 1 into visit_exists;
 
   if visit_exists then
       return;
   end if;
 
   return query with new_pointed_revs as (
     select swh_revision_from_target(target, target_type) as id
     from swh_occurrence_by_origin_visit(origin_id, visit_id)
   ),
   old_pointed_revs as (
     select swh_revision_from_target(target, target_type) as id
     from swh_occurrence_by_origin_visit(origin_id,
       (select visit from origin_visit where origin = origin_id and visit < visit_id order by visit desc limit 1))
   ),
   new_revs as (
     select distinct id
     from swh_revision_list(array(select id::bytea from new_pointed_revs where id is not null))
   ),
   old_revs as (
     select distinct id
     from swh_revision_list(array(select id::bytea from old_pointed_revs where id is not null))
   )
   insert into cache_revision_origin (revision, origin, visit)
   select n.id as revision, origin_id, visit_id from new_revs n
     where not exists (
     select 1 from old_revs o
     where o.id = n.id)
    returning revision;
 end
 $$;
 
 -- create a temporary table for content_ctags tmp_content_mimetype_missing,
 create or replace function swh_mktemp_content_mimetype_missing()
     returns void
     language sql
 as $$
   create temporary table tmp_content_mimetype_missing (
     id sha1,
     indexer_configuration_id bigint
   ) on commit drop;
 $$;
 
 comment on function swh_mktemp_content_mimetype_missing() IS 'Helper table to filter existing mimetype information';
 
 -- check which entries of tmp_bytea are missing from content_mimetype
 --
 -- operates in bulk: 0. swh_mktemp_bytea(), 1. COPY to tmp_bytea,
 -- 2. call this function
 create or replace function swh_content_mimetype_missing()
     returns setof sha1
     language plpgsql
 as $$
 begin
     return query
 	(select id::sha1 from tmp_content_mimetype_missing as tmp
 	 where not exists
 	     (select 1 from content_mimetype as c
               where c.id = tmp.id and c.indexer_configuration_id = tmp.indexer_configuration_id));
     return;
 end
 $$;
 
 comment on function swh_content_mimetype_missing() is 'Filter existing mimetype information';
 
 -- create a temporary table for content_mimetype tmp_content_mimetype,
 create or replace function swh_mktemp_content_mimetype()
     returns void
     language sql
 as $$
   create temporary table tmp_content_mimetype (
     like content_mimetype including defaults
   ) on commit drop;
 $$;
 
 comment on function swh_mktemp_content_mimetype() IS 'Helper table to add mimetype information';
 
 -- add tmp_content_mimetype entries to content_mimetype, overwriting
 -- duplicates if conflict_update is true, skipping duplicates otherwise.
 --
 -- If filtering duplicates is in order, the call to
 -- swh_content_mimetype_missing must take place before calling this
 -- function.
 --
 --
 -- operates in bulk: 0. swh_mktemp(content_mimetype), 1. COPY to tmp_content_mimetype,
 -- 2. call this function
 create or replace function swh_content_mimetype_add(conflict_update boolean)
     returns void
     language plpgsql
 as $$
 begin
     if conflict_update then
         insert into content_mimetype (id, mimetype, encoding, indexer_configuration_id)
         select id, mimetype, encoding, indexer_configuration_id
         from tmp_content_mimetype tcm
             on conflict(id, indexer_configuration_id)
                 do update set mimetype = excluded.mimetype,
                               encoding = excluded.encoding;
 
     else
         insert into content_mimetype (id, mimetype, encoding, indexer_configuration_id)
         select id, mimetype, encoding, indexer_configuration_id
         from tmp_content_mimetype tcm
             on conflict(id, indexer_configuration_id) do nothing;
     end if;
     return;
 end
 $$;
 
 comment on function swh_content_mimetype_add(boolean) IS 'Add new content mimetypes';
 
 create type content_mimetype_signature as(
     id sha1,
     mimetype bytea,
     encoding bytea,
     tool_id integer,
     tool_name text,
     tool_version text,
     tool_configuration jsonb
 );
 
 -- Retrieve list of content mimetype from the temporary table.
 --
 -- operates in bulk: 0. mktemp(tmp_bytea), 1. COPY to tmp_bytea,
 -- 2. call this function
 create or replace function swh_content_mimetype_get()
     returns setof content_mimetype_signature
     language plpgsql
 as $$
 begin
     return query
         select c.id, mimetype, encoding,
                i.id as tool_id, tool_name, tool_version, tool_configuration
         from tmp_bytea t
         inner join content_mimetype c on c.id=t.id
         inner join indexer_configuration i on c.indexer_configuration_id=i.id;
     return;
 end
 $$;
 
 comment on function swh_content_mimetype_get() IS 'List content''s mimetypes';
 
 -- create a temporary table for content_language tmp_content_language,
 create or replace function swh_mktemp_content_language_missing()
     returns void
     language sql
 as $$
   create temporary table tmp_content_language_missing (
     id sha1,
     indexer_configuration_id integer
   ) on commit drop;
 $$;
 
 comment on function swh_mktemp_content_language_missing() is 'Helper table to filter missing language';
 
 -- check which entries of tmp_bytea are missing from content_language
 --
 -- operates in bulk: 0. swh_mktemp_bytea(), 1. COPY to tmp_bytea,
 -- 2. call this function
 create or replace function swh_content_language_missing()
     returns setof sha1
     language plpgsql
 as $$
 begin
     return query
 	select id::sha1 from tmp_content_language_missing as tmp
 	where not exists
 	    (select 1 from content_language as c
              where c.id = tmp.id and c.indexer_configuration_id = tmp.indexer_configuration_id);
     return;
 end
 $$;
 
 comment on function swh_content_language_missing() IS 'Filter missing content languages';
 
 -- add tmp_content_language entries to content_language, overwriting
 -- duplicates if conflict_update is true, skipping duplicates otherwise.
 --
 -- If filtering duplicates is in order, the call to
 -- swh_content_language_missing must take place before calling this
 -- function.
 --
 -- operates in bulk: 0. swh_mktemp(content_language), 1. COPY to
 -- tmp_content_language, 2. call this function
 create or replace function swh_content_language_add(conflict_update boolean)
     returns void
     language plpgsql
 as $$
 begin
     if conflict_update then
       insert into content_language (id, lang, indexer_configuration_id)
       select id, lang, indexer_configuration_id
     	from tmp_content_language tcl
             on conflict(id, indexer_configuration_id)
                 do update set lang = excluded.lang;
 
     else
         insert into content_language (id, lang, indexer_configuration_id)
         select id, lang, indexer_configuration_id
     	  from tmp_content_language tcl
             on conflict(id, indexer_configuration_id)
             do nothing;
     end if;
     return;
 end
 $$;
 
 comment on function swh_content_language_add(boolean) IS 'Add new content languages';
 
 -- create a temporary table for retrieving content_language
 create or replace function swh_mktemp_content_language()
     returns void
     language sql
 as $$
   create temporary table tmp_content_language (
     like content_language including defaults
   ) on commit drop;
 $$;
 
 comment on function swh_mktemp_content_language() is 'Helper table to add content language';
 
 create type content_language_signature as (
     id sha1,
     lang languages,
     tool_id integer,
     tool_name text,
     tool_version text,
     tool_configuration jsonb
 );
 
 -- Retrieve list of content language from the temporary table.
 --
 -- operates in bulk: 0. mktemp(tmp_bytea), 1. COPY to tmp_bytea, 2. call this function
 create or replace function swh_content_language_get()
     returns setof content_language_signature
     language plpgsql
 as $$
 begin
     return query
         select c.id, lang, i.id as tool_id, tool_name, tool_version, tool_configuration
         from tmp_bytea t
         inner join content_language c on c.id = t.id
         inner join indexer_configuration i on i.id=c.indexer_configuration_id;
     return;
 end
 $$;
 
 comment on function swh_content_language_get() is 'List content''s language';
 
 
 -- create a temporary table for content_ctags tmp_content_ctags,
 create or replace function swh_mktemp_content_ctags()
     returns void
     language sql
 as $$
   create temporary table tmp_content_ctags (
     like content_ctags including defaults
   ) on commit drop;
 $$;
 
 comment on function swh_mktemp_content_ctags() is 'Helper table to add content ctags';
 
 
 -- add tmp_content_ctags entries to content_ctags, overwriting
 -- duplicates if conflict_update is true, skipping duplicates otherwise.
 --
 -- operates in bulk: 0. swh_mktemp(content_ctags), 1. COPY to tmp_content_ctags,
 -- 2. call this function
 create or replace function swh_content_ctags_add(conflict_update boolean)
     returns void
     language plpgsql
 as $$
 begin
     if conflict_update then
         delete from content_ctags
         where id in (select tmp.id
                      from tmp_content_ctags tmp
                      inner join indexer_configuration i on i.id=tmp.indexer_configuration_id);
     end if;
 
     insert into content_ctags (id, name, kind, line, lang, indexer_configuration_id)
     select id, name, kind, line, lang, indexer_configuration_id
     from tmp_content_ctags tct
         on conflict(id, hash_sha1(name), kind, line, lang, indexer_configuration_id)
         do nothing;
     return;
 end
 $$;
 
 comment on function swh_content_ctags_add(boolean) IS 'Add new ctags symbols per content';
 
 -- create a temporary table for content_ctags missing routine
 create or replace function swh_mktemp_content_ctags_missing()
     returns void
     language sql
 as $$
   create temporary table tmp_content_ctags_missing (
     id           sha1,
     indexer_configuration_id    integer
   ) on commit drop;
 $$;
 
 comment on function swh_mktemp_content_ctags_missing() is 'Helper table to filter missing content ctags';
 
 -- check which entries of tmp_bytea are missing from content_ctags
 --
 -- operates in bulk: 0. swh_mktemp_bytea(), 1. COPY to tmp_bytea,
 -- 2. call this function
 create or replace function swh_content_ctags_missing()
     returns setof sha1
     language plpgsql
 as $$
 begin
     return query
 	(select id::sha1 from tmp_content_ctags_missing as tmp
 	 where not exists
 	     (select 1 from content_ctags as c
               where c.id = tmp.id and c.indexer_configuration_id=tmp.indexer_configuration_id
               limit 1));
     return;
 end
 $$;
 
 comment on function swh_content_ctags_missing() IS 'Filter missing content ctags';
 
 create type content_ctags_signature as (
   id sha1,
   name text,
   kind text,
   line bigint,
   lang ctags_languages,
   tool_id integer,
   tool_name text,
   tool_version text,
   tool_configuration jsonb
 );
 
 -- Retrieve list of content ctags from the temporary table.
 --
 -- operates in bulk: 0. mktemp(tmp_bytea), 1. COPY to tmp_bytea, 2. call this function
 create or replace function swh_content_ctags_get()
     returns setof content_ctags_signature
     language plpgsql
 as $$
 begin
     return query
         select c.id, c.name, c.kind, c.line, c.lang,
                i.id as tool_id, i.tool_name, i.tool_version, i.tool_configuration
         from tmp_bytea t
         inner join content_ctags c using(id)
         inner join indexer_configuration i on i.id = c.indexer_configuration_id
         order by line;
     return;
 end
 $$;
 
 comment on function swh_content_ctags_get() IS 'List content ctags';
 
 -- Search within ctags content.
 --
 create or replace function swh_content_ctags_search(
        expression text,
        l integer default 10,
        last_sha1 sha1 default '\x0000000000000000000000000000000000000000')
     returns setof content_ctags_signature
     language sql
 as $$
     select c.id, name, kind, line, lang,
            i.id as tool_id, tool_name, tool_version, tool_configuration
     from content_ctags c
     inner join indexer_configuration i on i.id = c.indexer_configuration_id
     where hash_sha1(name) = hash_sha1(expression)
     and c.id > last_sha1
     order by id
     limit l;
 $$;
 
 comment on function swh_content_ctags_search(text, integer, sha1) IS 'Equality search through ctags'' symbols';
 
 
 -- create a temporary table for content_fossology_license tmp_content_fossology_license,
 create or replace function swh_mktemp_content_fossology_license()
     returns void
     language sql
 as $$
   create temporary table tmp_content_fossology_license (
     id                       sha1,
     license                  text,
     indexer_configuration_id integer
   ) on commit drop;
 $$;
 
 comment on function swh_mktemp_content_fossology_license() is 'Helper table to add content license';
 
 -- add tmp_content_fossology_license entries to content_fossology_license, overwriting
 -- duplicates if conflict_update is true, skipping duplicates otherwise.
 --
 -- operates in bulk: 0. swh_mktemp(content_fossology_license), 1. COPY to
 -- tmp_content_fossology_license, 2. call this function
 create or replace function swh_content_fossology_license_add(conflict_update boolean)
     returns void
     language plpgsql
 as $$
 begin
     -- insert unknown licenses first
     insert into fossology_license (name)
     select distinct license from tmp_content_fossology_license tmp
     where not exists (select 1 from fossology_license where name=tmp.license)
     on conflict(name) do nothing;
 
     if conflict_update then
         -- delete from content_fossology_license c
         --   using tmp_content_fossology_license tmp, indexer_configuration i
         --   where c.id = tmp.id and i.id=tmp.indexer_configuration_id
         delete from content_fossology_license
         where id in (select tmp.id
                      from tmp_content_fossology_license tmp
                      inner join indexer_configuration i on i.id=tmp.indexer_configuration_id);
     end if;
 
     insert into content_fossology_license (id, license_id, indexer_configuration_id)
     select tcl.id,
           (select id from fossology_license where name = tcl.license) as license,
           indexer_configuration_id
     from tmp_content_fossology_license tcl
         on conflict(id, license_id, indexer_configuration_id)
         do nothing;
     return;
 end
 $$;
 
 comment on function swh_content_fossology_license_add(boolean) IS 'Add new content licenses';
 
 create type content_fossology_license_signature as (
   id                 sha1,
   tool_id            integer,
   tool_name          text,
   tool_version       text,
   tool_configuration jsonb,
   licenses           text[]
 );
 
 -- Retrieve list of content license from the temporary table.
 --
 -- operates in bulk: 0. mktemp(tmp_bytea), 1. COPY to tmp_bytea,
 -- 2. call this function
 create or replace function swh_content_fossology_license_get()
     returns setof content_fossology_license_signature
     language plpgsql
 as $$
 begin
     return query
       select cl.id,
              ic.id as tool_id,
              ic.tool_name,
              ic.tool_version,
              ic.tool_configuration,
              array(select name
                    from fossology_license
                    where id = ANY(array_agg(cl.license_id))) as licenses
       from tmp_bytea tcl
       inner join content_fossology_license cl using(id)
       inner join indexer_configuration ic on ic.id=cl.indexer_configuration_id
       group by cl.id, ic.id, ic.tool_name, ic.tool_version, ic.tool_configuration;
     return;
 end
 $$;
 
 comment on function swh_content_fossology_license_get() IS 'List content licenses';
 
 -- content_metadata functions
 --
 -- create a temporary table for content_metadata tmp_content_metadata,
 create or replace function swh_mktemp_content_metadata_missing()
     returns void
     language sql
 as $$
   create temporary table tmp_content_metadata_missing (
     id sha1,
     indexer_configuration_id integer
   ) on commit drop;
 $$;
 
 comment on function swh_mktemp_content_metadata_missing() is 'Helper table to filter missing metadata in content_metadata';
 
 -- check which entries of tmp_bytea are missing from content_metadata
 --
 -- operates in bulk: 0. swh_mktemp_bytea(), 1. COPY to tmp_bytea,
 -- 2. call this function
 create or replace function swh_content_metadata_missing()
     returns setof sha1
     language plpgsql
 as $$
 begin
     return query
 	select id::sha1 from tmp_content_metadata_missing as tmp
 	where not exists
 	    (select 1 from content_metadata as c
              where c.id = tmp.id and c.indexer_configuration_id = tmp.indexer_configuration_id);
     return;
 end
 $$;
 
 comment on function swh_content_metadata_missing() IS 'Filter missing content metadata';
 
 -- add tmp_content_metadata entries to content_metadata, overwriting
 -- duplicates if conflict_update is true, skipping duplicates otherwise.
 --
 -- If filtering duplicates is in order, the call to
 -- swh_content_metadata_missing must take place before calling this
 -- function.
 --
 -- operates in bulk: 0. swh_mktemp(content_language), 1. COPY to
 -- tmp_content_metadata, 2. call this function
 create or replace function swh_content_metadata_add(conflict_update boolean)
     returns void
     language plpgsql
 as $$
 begin
     if conflict_update then
       insert into content_metadata (id, translated_metadata, indexer_configuration_id)
       select id, translated_metadata, indexer_configuration_id
     	from tmp_content_metadata tcm
             on conflict(id, indexer_configuration_id)
                 do update set translated_metadata = excluded.translated_metadata;
 
     else
         insert into content_metadata (id, translated_metadata, indexer_configuration_id)
         select id, translated_metadata, indexer_configuration_id
     	from tmp_content_metadata tcm
             on conflict(id, indexer_configuration_id)
             do nothing;
     end if;
     return;
 end
 $$;
 
 comment on function swh_content_metadata_add(boolean) IS 'Add new content metadata';
 
 -- create a temporary table for retrieving content_metadata
 create or replace function swh_mktemp_content_metadata()
     returns void
     language sql
 as $$
   create temporary table tmp_content_metadata (
     like content_metadata including defaults
   ) on commit drop;
 $$;
 
 comment on function swh_mktemp_content_metadata() is 'Helper table to add content metadata';
 
 --
 create type content_metadata_signature as (
     id sha1,
     translated_metadata jsonb,
     tool_id integer,
     tool_name text,
     tool_version text,
     tool_configuration jsonb
 );
 
 -- Retrieve list of content metadata from the temporary table.
 --
 -- operates in bulk: 0. mktemp(tmp_bytea), 1. COPY to tmp_bytea, 2. call this function
 create or replace function swh_content_metadata_get()
     returns setof content_metadata_signature
     language plpgsql
 as $$
 begin
     return query
         select c.id, translated_metadata, i.id as tool_id, tool_name, tool_version, tool_configuration
         from tmp_bytea t
         inner join content_metadata c on c.id = t.id
         inner join indexer_configuration i on i.id=c.indexer_configuration_id;
     return;
 end
 $$;
 
 comment on function swh_content_metadata_get() is 'List content''s metadata';
 -- end content_metadata functions
 
 -- revision_metadata functions
 --
 -- create a temporary table for revision_metadata tmp_revision_metadata,
 create or replace function swh_mktemp_revision_metadata_missing()
     returns void
     language sql
 as $$
   create temporary table tmp_revision_metadata_missing (
     id sha1_git,
     indexer_configuration_id integer
   ) on commit drop;
 $$;
 
 comment on function swh_mktemp_revision_metadata_missing() is 'Helper table to filter missing metadata in revision_metadata';
 
 -- check which entries of tmp_bytea are missing from revision_metadata
 --
 -- operates in bulk: 0. swh_mktemp_bytea(), 1. COPY to tmp_bytea,
 -- 2. call this function
 create or replace function swh_revision_metadata_missing()
     returns setof sha1
     language plpgsql
 as $$
 begin
     return query
 	select id::sha1 from tmp_revision_metadata_missing as tmp
 	where not exists
 	    (select 1 from revision_metadata as c
              where c.id = tmp.id and c.indexer_configuration_id = tmp.indexer_configuration_id);
     return;
 end
 $$;
 
 comment on function swh_revision_metadata_missing() IS 'Filter missing content metadata';
 
 -- add tmp_revision_metadata entries to revision_metadata, overwriting
 -- duplicates if conflict_update is true, skipping duplicates otherwise.
 --
 -- If filtering duplicates is in order, the call to
 -- swh_revision_metadata_missing must take place before calling this
 -- function.
 --
 -- operates in bulk: 0. swh_mktemp(content_language), 1. COPY to
 -- tmp_revision_metadata, 2. call this function
 create or replace function swh_revision_metadata_add(conflict_update boolean)
     returns void
     language plpgsql
 as $$
 begin
     if conflict_update then
       insert into revision_metadata (id, translated_metadata, indexer_configuration_id)
       select id, translated_metadata, indexer_configuration_id
     	from tmp_revision_metadata tcm
             on conflict(id, indexer_configuration_id)
                 do update set translated_metadata = excluded.translated_metadata;
 
     else
         insert into revision_metadata (id, translated_metadata, indexer_configuration_id)
         select id, translated_metadata, indexer_configuration_id
     	from tmp_revision_metadata tcm
             on conflict(id, indexer_configuration_id)
             do nothing;
     end if;
     return;
 end
 $$;
 
 comment on function swh_revision_metadata_add(boolean) IS 'Add new revision metadata';
 
 -- create a temporary table for retrieving revision_metadata
 create or replace function swh_mktemp_revision_metadata()
     returns void
     language sql
 as $$
   create temporary table tmp_revision_metadata (
     like revision_metadata including defaults
   ) on commit drop;
 $$;
 
 comment on function swh_mktemp_revision_metadata() is 'Helper table to add revision metadata';
 
 --
 create type revision_metadata_signature as (
     id sha1_git,
     translated_metadata jsonb,
     tool_id integer,
     tool_name text,
     tool_version text,
     tool_configuration jsonb
 );
 
 -- Retrieve list of revision metadata from the temporary table.
 --
 -- operates in bulk: 0. mktemp(tmp_bytea), 1. COPY to tmp_bytea, 2. call this function
 create or replace function swh_revision_metadata_get()
     returns setof revision_metadata_signature
     language plpgsql
 as $$
 begin
     return query
         select c.id, translated_metadata, i.id as tool_id, tool_name, tool_version, tool_configuration
         from tmp_bytea t
         inner join revision_metadata c on c.id = t.id
         inner join indexer_configuration i on i.id=c.indexer_configuration_id;
     return;
 end
 $$;
 
 comment on function swh_revision_metadata_get() is 'List revision''s metadata';
 -- end revision_metadata functions
 
 -- 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 $$
-    select relname::text as label, n_live_tup::bigint - n_dead_tup::bigint as value
-    from pg_stat_user_tables
-    where relid in (
-        'public.content'::regclass,
-        'public.directory'::regclass,
-        'public.directory_entry_dir'::regclass,
-        'public.directory_entry_file'::regclass,
-        'public.directory_entry_rev'::regclass,
-        'public.occurrence'::regclass,
-        'public.occurrence_history'::regclass,
-        'public.origin'::regclass,
-        'public.person'::regclass,
-        'public.entity'::regclass,
-        'public.entity_history'::regclass,
-        'public.release'::regclass,
-        'public.revision'::regclass,
-        'public.revision_history'::regclass,
-        'public.skipped_content'::regclass
+    select object_type as label, value as value
+    from object_counts
+    where object_type in (
+        'content',
+        'directory',
+        'directory_entry_dir',
+        'directory_entry_file',
+        'directory_entry_rev',
+        'occurrence',
+        'occurrence_history',
+        'origin',
+        'person',
+        'entity',
+        'entity_history',
+        'release',
+        'revision',
+        'revision_history',
+        'skipped_content'
     );
 $$;
+
+create or replace function swh_update_counter(object_type text)
+    returns void
+    language plpgsql
+as $$
+begin
+    execute format('
+	insert into object_counts
+    (value, last_update, object_type)
+  values
+    ((select count(*) from %1$I), NOW(), %1$L)
+  on conflict (object_type) do update set
+    value = excluded.value,
+    last_update = excluded.last_update',
+  object_type);
+    return;
+end;
+$$;
diff --git a/sql/swh-indexes.sql b/sql/swh-indexes.sql
index b119c6ddc..e53db6517 100644
--- a/sql/swh-indexes.sql
+++ b/sql/swh-indexes.sql
@@ -1,295 +1,299 @@
 -- 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 index concurrently on content(object_id);
 
 alter table content add primary key using index content_pkey;
 
 
 -- entity_history
 
 create unique index concurrently entity_history_pkey on entity_history(id);
 create index concurrently on entity_history(uuid);
 create index concurrently on entity_history(name);
 
 alter table entity_history add primary key using index entity_history_pkey;
 
 -- entity
 
 create unique index concurrently entity_pkey on entity(uuid);
 
 create index concurrently on entity(name);
 create index concurrently on entity using gin(lister_metadata jsonb_path_ops);
 
 alter table entity add primary key using index entity_pkey;
 alter table entity add constraint entity_parent_fkey foreign key (parent) references entity(uuid) deferrable initially deferred not valid;
 alter table entity validate constraint entity_parent_fkey;
 alter table entity add constraint entity_last_id_fkey foreign key (last_id) references entity_history(id) not valid;
 alter table entity validate constraint entity_last_id_fkey;
 
 -- entity_equivalence
 
 create unique index concurrently entity_equivalence_pkey on entity_equivalence(entity1, entity2);
 alter table entity_equivalence add primary key using index entity_equivalence_pkey;
 
 
 alter table entity_equivalence add constraint "entity_equivalence_entity1_fkey" foreign key (entity1) references entity(uuid) not valid;
 alter table entity_equivalence validate constraint entity_equivalence_entity1_fkey;
 alter table entity_equivalence add constraint "entity_equivalence_entity2_fkey" foreign key (entity2) references entity(uuid) not valid;
 alter table entity_equivalence validate constraint entity_equivalence_entity2_fkey;
 alter table entity_equivalence add constraint "order_entities" check (entity1 < entity2) not valid;
 alter table entity_equivalence validate constraint order_entities;
 
 -- listable_entity
 
 create unique index concurrently listable_entity_pkey on listable_entity(uuid);
 alter table listable_entity add primary key using index listable_entity_pkey;
 
 alter table listable_entity add constraint listable_entity_uuid_fkey foreign key (uuid) references entity(uuid) not valid;
 alter table listable_entity validate constraint listable_entity_uuid_fkey;
 
 -- list_history
 
 create unique index concurrently list_history_pkey on list_history(id);
 alter table list_history add primary key using index list_history_pkey;
 
 alter table list_history add constraint list_history_entity_fkey foreign key (entity) references listable_entity(uuid) not valid;
 alter table list_history validate constraint list_history_entity_fkey;
 
 -- 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);
 
 alter table origin add constraint origin_lister_fkey foreign key (lister) references listable_entity(uuid) not valid;
 alter table origin validate constraint origin_lister_fkey;
 
 alter table origin add constraint origin_project_fkey foreign key (project) references entity(uuid) not valid;
 alter table origin validate constraint origin_project_fkey;
 
 -- skipped_content
 
 alter table skipped_content add constraint skipped_content_sha1_sha1_git_sha256_key unique (sha1, sha1_git, sha256);
 
 create unique index concurrently on skipped_content(sha1);
 create unique index concurrently on skipped_content(sha1_git);
 create index concurrently on skipped_content(sha256);
 create index concurrently on skipped_content(blake2s256);
 create 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 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 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;
 
 -- 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;
 
 -- occurrence_history
 create unique index concurrently occurrence_history_pkey on occurrence_history(object_id);
 alter table occurrence_history add primary key using index occurrence_history_pkey;
 
 create index concurrently on occurrence_history(target, target_type);
 create index concurrently on occurrence_history(origin, branch);
 create unique index concurrently on occurrence_history(origin, branch, target, target_type);
 
 alter table occurrence_history add constraint occurrence_history_origin_fkey foreign key (origin) references origin(id) not valid;
 alter table occurrence_history validate constraint occurrence_history_origin_fkey;
 
 -- occurrence
 create unique index concurrently occurrence_pkey on occurrence(origin, branch);
 alter table occurrence add primary key using index occurrence_pkey;
 
 alter table occurrence add constraint occurrence_origin_fkey foreign key (origin) references origin(id) not valid;
 alter table occurrence validate constraint occurrence_origin_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 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;
 
 -- cache_content_revision
 create unique index concurrently cache_content_revision_pkey on cache_content_revision(content);
 alter table cache_content_revision add primary key using index cache_content_revision_pkey;
 
 alter table cache_content_revision add constraint cache_content_revision_content_fkey foreign key (content) references content(sha1_git) not valid;
 alter table cache_content_revision validate constraint cache_content_revision_content_fkey;
 
 -- cache_content_revision_processed
 create unique index concurrently cache_content_revision_processed_pkey on cache_content_revision_processed(revision);
 alter table cache_content_revision_processed add primary key using index cache_content_revision_processed_pkey;
 
 alter table cache_content_revision_processed add constraint cache_content_revision_processed_revision_fkey foreign key (revision) references revision(id) not valid;
 alter table cache_content_revision_processed validate constraint cache_content_revision_processed_revision_fkey;
 
 -- cache_revision_origin
 create unique index concurrently cache_revision_origin_pkey on cache_revision_origin(revision, origin, visit);
 alter table cache_revision_origin add primary key using index cache_revision_origin_pkey;
 
 alter table cache_revision_origin add constraint cache_revision_origin_revision_fkey foreign key (revision) references revision(id) not valid;
 alter table cache_revision_origin validate constraint cache_revision_origin_revision_fkey;
 
 alter table cache_revision_origin add constraint cache_revision_origin_origin_fkey foreign key (origin, visit) references origin_visit(origin, visit) not valid;
 alter table cache_revision_origin validate constraint cache_revision_origin_origin_fkey;
 
 create index concurrently on cache_revision_origin(revision);
 
 -- indexer_configuration
 create unique index concurrently indexer_configuration_pkey on indexer_configuration(id);
 alter table indexer_configuration add primary key using index indexer_configuration_pkey;
 
 create unique index on indexer_configuration(tool_name, tool_version, tool_configuration);
 
 -- content_mimetype
 create unique index concurrently content_mimetype_pkey on content_mimetype(id, indexer_configuration_id);
 alter table content_mimetype add primary key using index content_mimetype_pkey;
 
 alter table content_mimetype add constraint content_mimetype_id_fkey foreign key (id) references content(sha1) not valid;
 alter table content_mimetype validate constraint content_mimetype_id_fkey;
 
 alter table content_mimetype add constraint content_mimetype_indexer_configuration_id_fkey foreign key (indexer_configuration_id) references indexer_configuration(id) not valid;
 alter table content_mimetype validate constraint content_mimetype_indexer_configuration_id_fkey;
 
 -- content_language
 create unique index concurrently content_language_pkey on content_language(id, indexer_configuration_id);
 alter table content_language add primary key using index content_language_pkey;
 
 alter table content_language add constraint content_language_id_fkey foreign key (id) references content(sha1) not valid;
 alter table content_language validate constraint content_language_id_fkey;
 
 alter table content_language add constraint content_language_indexer_configuration_id_fkey foreign key (indexer_configuration_id) references indexer_configuration(id) not valid;
 alter table content_language validate constraint content_language_indexer_configuration_id_fkey;
 
 -- content_ctags
 create index concurrently on content_ctags(id);
 create index concurrently on content_ctags(hash_sha1(name));
 create unique index concurrently on content_ctags(id, hash_sha1(name), kind, line, lang, indexer_configuration_id);
 
 alter table content_ctags add constraint content_ctags_id_fkey foreign key (id) references content(sha1) not valid;
 alter table content_ctags validate constraint content_ctags_id_fkey;
 
 alter table content_ctags add constraint content_ctags_indexer_configuration_id_fkey foreign key (indexer_configuration_id) references indexer_configuration(id) not valid;
 alter table content_ctags validate constraint content_ctags_indexer_configuration_id_fkey;
 
 -- fossology_license
 create unique index concurrently fossology_license_pkey on fossology_license(id);
 alter table fossology_license add primary key using index fossology_license_pkey;
 
 create unique index on fossology_license(name);
 
 -- content_fossology_license
 create unique index concurrently content_fossology_license_pkey on content_fossology_license(id, license_id, indexer_configuration_id);
 alter table content_fossology_license add primary key using index content_fossology_license_pkey;
 
 alter table content_fossology_license add constraint content_fossology_license_id_fkey foreign key (id) references content(sha1) not valid;
 alter table content_fossology_license validate constraint content_fossology_license_id_fkey;
 
 alter table content_fossology_license add constraint content_fossology_license_license_id_fkey foreign key (license_id) references fossology_license(id) not valid;
 alter table content_fossology_license validate constraint content_fossology_license_license_id_fkey;
 
 alter table content_fossology_license add constraint content_fossology_license_indexer_configuration_id_fkey foreign key (indexer_configuration_id) references indexer_configuration(id) not valid;
 alter table content_fossology_license validate constraint content_fossology_license_indexer_configuration_id_fkey;
 
 -- content_metadata
 create unique index concurrently content_metadata_pkey on content_metadata(id, indexer_configuration_id);
 alter table content_metadata add primary key using index content_metadata_pkey;
 
 alter table content_metadata add constraint content_metadata_id_fkey foreign key (id) references content(sha1) not valid;
 alter table content_metadata validate constraint content_metadata_id_fkey;
 
 alter table content_metadata add constraint content_metadata_indexer_configuration_id_fkey foreign key (indexer_configuration_id) references indexer_configuration(id) not valid;
 alter table content_metadata validate constraint content_metadata_indexer_configuration_id_fkey;
 
 
 -- revision_metadata
 create unique index concurrently revision_metadata_pkey on revision_metadata(id, indexer_configuration_id);
 alter table revision_metadata add primary key using index revision_metadata_pkey;
 
 alter table revision_metadata add constraint revision_metadata_id_fkey foreign key (id) references revision(id) not valid;
 alter table revision_metadata validate constraint revision_metadata_id_fkey;
 
 alter table revision_metadata add constraint revision_metadata_indexer_configuration_id_fkey foreign key (indexer_configuration_id) references indexer_configuration(id) not valid;
 alter table revision_metadata validate constraint revision_metadata_indexer_configuration_id_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;
diff --git a/sql/swh-schema.sql b/sql/swh-schema.sql
index ddae2a25b..107282ec5 100644
--- a/sql/swh-schema.sql
+++ b/sql/swh-schema.sql
@@ -1,493 +1,500 @@
 ---
 --- Software Heritage Data Model
 ---
 
 -- drop schema if exists swh cascade;
 -- create schema swh;
 -- set search_path to swh;
 
 create table dbversion
 (
   version     int primary key,
   release     timestamptz,
   description text
 );
 
 insert into dbversion(version, release, description)
-      values(107, now(), 'Work In Progress');
+      values(108, now(), 'Work In Progress');
 
 -- a SHA1 checksum (not necessarily originating from Git)
 create domain sha1 as bytea check (length(value) = 20);
 
 -- a Git object ID, i.e., a SHA1 checksum
 create domain sha1_git as bytea check (length(value) = 20);
 
 -- 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
 );
 
 
 -- Entities constitute a typed hierarchy of organization, hosting
 -- facilities, groups, people and software projects.
 --
 -- Examples of entities: Software Heritage, Debian, GNU, GitHub,
 -- Apache, The Linux Foundation, the Debian Python Modules Team, the
 -- torvalds GitHub user, the torvalds/linux GitHub project.
 --
 -- The data model is hierarchical (via the parent attribute) and might
 -- store sub-branches of existing entities. The key feature of an
 -- entity is might be *listed* (if it is available in listable_entity)
 -- to retrieve information about its content, i.e: sub-entities,
 -- projects, origins.
 
 -- The history of entities. Allows us to keep historical metadata
 -- about entities.  The temporal invariant is the uuid. Root
 -- organization uuids are manually generated (and available in
 -- swh-data.sql).
 --
 -- For generated entities (generated = true), we can provide
 -- generation_metadata to allow listers to retrieve the uuids of previous
 -- iterations of the entity.
 --
 -- Inactive entities that have been active in the past (active =
 -- false) should register the timestamp at which we saw them
 -- deactivate, in a new entry of entity_history.
 create table entity_history
 (
   id               bigserial not null,
   uuid             uuid,
   parent           uuid,             -- should reference entity_history(uuid)
   name             text not null,
   type             entity_type not null,
   description      text,
   homepage         text,
   active           boolean not null, -- whether the entity was seen on the last listing
   generated        boolean not null, -- whether this entity has been generated by a lister
   lister_metadata  jsonb,            -- lister-specific metadata, used for queries
   metadata         jsonb,
   validity         timestamptz[]     -- timestamps at which we have seen this entity
 );
 
 -- The entity table provides a view of the latest information on a
 -- given entity. It is updated via a trigger on entity_history.
 create table entity
 (
   uuid             uuid not null,
   parent           uuid,
   name             text not null,
   type             entity_type not null,
   description      text,
   homepage         text,
   active           boolean not null, -- whether the entity was seen on the last listing
   generated        boolean not null, -- whether this entity has been generated by a lister
   lister_metadata  jsonb,            -- lister-specific metadata, used for queries
   metadata         jsonb,
   last_seen        timestamptz,      -- last listing time or disappearance time for active=false
   last_id          bigint            -- last listing id
 );
 
 -- Register the equivalence between two entities. Allows sideways
 -- navigation in the entity table
 create table entity_equivalence
 (
   entity1 uuid,
   entity2 uuid
 );
 
 -- Register a lister for a specific entity.
 create table listable_entity
 (
   uuid         uuid,
   enabled      boolean not null default true, -- do we list this entity automatically?
   list_engine  text,  -- crawler to be used to list entity's content
   list_url     text,  -- root URL to start the listing
   list_params  jsonb,  -- org-specific listing parameter
   latest_list  timestamptz  -- last time the entity's content has been listed
 );
 
 -- Log of all entity listings (i.e., entity crawling) that have been
 -- done in the past, or are still ongoing.
 create table list_history
 (
   id        bigserial not null,
   date      timestamptz not null,
   status    boolean,   -- true if and only if the listing has been successful
   result    jsonb,     -- more detailed return value, depending on status
   stdout    text,
   stderr    text,
   duration  interval,  -- fetch duration of NULL if still ongoing
   entity    uuid
 );
 
 
 -- An origin is a place, identified by an URL, where software 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* (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,
   lister   uuid,
   project  uuid
 );
 
 -- Content we have seen but skipped for some reason. This table is
 -- separate from the content table as we might not have the sha1
 -- checksum of that data (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,
   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.
 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
 );
 
 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>'
 );
 
 -- A snapshot of a software project 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,
   date                  timestamptz,
   date_offset           smallint,
   committer_date        timestamptz,
   committer_date_offset smallint,
   type                  revision_type not null,
   directory             sha1_git,  -- file-system tree
   message               bytea,
   author                bigint,
   committer             bigint,
   synthetic             boolean not null default false,  -- true if synthetic (cf. swh-loader-tar)
   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,
   parent_id    sha1_git,
   parent_rank  int not null default 0
     -- parent position in merge commits, 0-based
 );
 
 -- The timestamps at which Software Heritage has made a visit of the given origin.
 create table origin_visit
 (
   origin    bigint not null,
   visit     bigint not null,
   date      timestamptz not null,
   status    origin_visit_status not null,
   metadata  jsonb
 );
 
 comment on column origin_visit.origin is 'Visited origin';
 comment on column origin_visit.visit is 'Visit number the visit occurred for that origin';
 comment on column origin_visit.date is 'Visit date for that origin';
 comment on column origin_visit.status is 'Visit status for that origin';
 comment on column origin_visit.metadata is 'Metadata associated with the visit';
 
 
 -- The content of software origins is indexed starting from top-level pointers
 -- called "branches". Every time we fetch some origin we store in this table
 -- where the branches pointed to at fetch time.
 --
 -- Synonyms/mappings:
 -- * git: ref (in the "git update-ref" sense)
 create table occurrence_history
 (
   origin       bigint not null,
   branch       bytea not null,        -- e.g., b"master" (for VCS), or b"sid" (for Debian)
   target       sha1_git not null,     -- ref target, e.g., commit id
   target_type  object_type not null,  -- ref target type
   visits       bigint[] not null,     -- the visits where that occurrence was valid. References
                                       -- origin_visit(visit), where o_h.origin = origin_visit.origin.
   object_id    bigserial not null     -- short object identifier
 );
 
 -- Materialized view of occurrence_history, storing the *current* value of each
 -- branch, as last seen by SWH.
 create table occurrence
 (
   origin    bigint,
   branch    bytea not null,
   target    sha1_git not null,
   target_type object_type not null
 );
 
 -- A "memorable" point in the development history of a 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 if synthetic (cf. swh-loader-tar)
   object_id   bigserial,
   target_type object_type not null,
   date_neg_utc_offset  boolean
 );
 
 
 -- Content provenance information caches
 -- https://forge.softwareheritage.org/T547
 --
 -- Those tables aren't expected to be exhaustive, and get filled on a case by
 -- case basis: absence of data doesn't mean the data is not there
 
 -- content <-> revision mapping cache
 --
 -- semantics: "we have seen the content with given id in the given path inside
 -- the given revision"
 
 create table cache_content_revision (
     content         sha1_git not null,
     blacklisted     boolean default false,
     revision_paths  bytea[][]
 );
 
 create table cache_content_revision_processed (
     revision  sha1_git not null
 );
 
 -- revision <-> origin_visit mapping cache
 --
 -- semantics: "we have seen the given revision in the given origin during the
 -- given visit"
 
 create table cache_revision_origin (
    revision  sha1_git not null,
    origin    bigint not null,
    visit     bigint not null
 );
 
 -- Computing metadata on sha1's contents
 
 create table indexer_configuration (
   id serial not null,
   tool_name text not null,
   tool_version text not null,
   tool_configuration jsonb
 );
 
 comment on table indexer_configuration is 'Indexer''s configuration version';
 comment on column indexer_configuration.id is 'Tool identifier';
 comment on column indexer_configuration.tool_version is 'Tool name';
 comment on column indexer_configuration.tool_version is 'Tool version';
 comment on column indexer_configuration.tool_configuration is 'Tool configuration: command line, flags, etc...';
 
 -- Properties (mimetype, encoding, etc...)
 create table content_mimetype (
   id sha1 not null,
   mimetype bytea not null,
   encoding bytea not null,
   indexer_configuration_id bigint not null
 );
 
 comment on table content_mimetype is 'Metadata associated to a raw content';
 comment on column content_mimetype.mimetype is 'Raw content Mimetype';
 comment on column content_mimetype.encoding is 'Raw content encoding';
 comment on column content_mimetype.indexer_configuration_id is 'Tool used to compute the information';
 
 -- Language metadata
 create table content_language (
   id sha1 not null,
   lang languages not null,
   indexer_configuration_id bigint not null
 );
 
 comment on table content_language is 'Language information on a raw content';
 comment on column content_language.lang is 'Language information';
 comment on column content_language.indexer_configuration_id is 'Tool used to compute the information';
 
 -- ctags information per content
 create table content_ctags (
   id sha1 not null,
   name text not null,
   kind text not null,
   line bigint not null,
   lang ctags_languages not null,
   indexer_configuration_id bigint not null
 );
 
 comment on table content_ctags is 'Ctags information on a raw content';
 comment on column content_ctags.id is 'Content identifier';
 comment on column content_ctags.name is 'Symbol name';
 comment on column content_ctags.kind is 'Symbol kind (function, class, variable, const...)';
 comment on column content_ctags.line is 'Symbol line';
 comment on column content_ctags.lang is 'Language information for that content';
 comment on column content_ctags.indexer_configuration_id is 'Tool used to compute the information';
 
 create table fossology_license(
   id smallserial,
   name text not null
 );
 
 comment on table fossology_license is 'Possible license recognized by license indexer';
 comment on column fossology_license.id is 'License identifier';
 comment on column fossology_license.name is 'License name';
 
 create table content_fossology_license (
   id sha1 not null,
   license_id smallserial not null,
   indexer_configuration_id bigint not null
 );
 
 comment on table content_fossology_license is 'license associated to a raw content';
 comment on column content_fossology_license.id is 'Raw content identifier';
 comment on column content_fossology_license.license_id is 'One of the content''s license identifier';
 comment on column content_fossology_license.indexer_configuration_id is 'Tool used to compute the information';
 
 
 -- The table content_metadata provides a translation to files
 -- identified as potentially containning metadata with a translation tool (indexer_configuration_id)
 create table content_metadata(
   id                       sha1   not null,
   translated_metadata      jsonb  not null,
   indexer_configuration_id bigint not null
 );
 
 comment on table content_metadata is 'metadata semantically translated from a content file';
 comment on column content_metadata.id is 'sha1 of content file';
 comment on column content_metadata.translated_metadata is 'result of translation with defined format';
 comment on column content_metadata.indexer_configuration_id is 'tool used for translation';
 
 -- The table revision_metadata provides a minimal set of intrinsic metadata
 -- detected with the detection  tool (indexer_configuration_id) and aggregated
 -- from the content_metadata translation.
 create table revision_metadata(
   id                       sha1_git   not null,
   translated_metadata      jsonb      not null,
   indexer_configuration_id bigint     not null
 );
 
 comment on table revision_metadata is 'metadata semantically detected and translated in a revision';
 comment on column revision_metadata.id is 'sha1_git of revision';
 comment on column revision_metadata.translated_metadata is 'result of detection and translation with defined format';
 comment on column revision_metadata.indexer_configuration_id is 'tool used for detection';
+
+-- Keep a cache of object counts
+create table object_counts (
+  object_type text,
+  value bigint,
+  last_update timestamptz
+);
diff --git a/swh/storage/tests/test_storage.py b/swh/storage/tests/test_storage.py
index 95bd2b56b..33b676645 100644
--- a/swh/storage/tests/test_storage.py
+++ b/swh/storage/tests/test_storage.py
@@ -1,3549 +1,3554 @@
 # Copyright (C) 2015-2017  The Software Heritage developers
 # See the AUTHORS file at the top-level directory of this distribution
 # License: GNU General Public License version 3, or any later version
 # See top-level LICENSE file for more information
 
 import copy
 import datetime
 from operator import itemgetter
 import psycopg2
 import unittest
 from uuid import UUID
 
 from unittest.mock import patch
 
 from nose.tools import istest
 from nose.plugins.attrib import attr
 
 from swh.model import identifiers
 from swh.model.hashutil import hash_to_bytes
 from swh.storage.db import cursor_to_bytes
 from swh.core.tests.db_testing import DbTestFixture
 from swh.storage.tests.storage_testing import StorageTestFixture
 
 
 @attr('db')
 class BaseTestStorage(StorageTestFixture, DbTestFixture):
     def setUp(self):
         super().setUp()
 
         db = self.test_db[self.TEST_STORAGE_DB_NAME]
         self.conn = db.conn
         self.cursor = db.cursor
 
         self.maxDiff = None
 
         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': 0o644,
                 },
                 {
                     'name': b'bar\xc3',
                     'type': 'dir',
                     'target': b'12345678901234567890',
                     'perms': 0o2000,
                 },
             ],
         }
 
         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': 0o644,
                 }
             ],
         }
 
         self.dir3 = {
             'id': hash_to_bytes('33e45d56f88993aae6a0198013efa80716fd8921'),
             'entries': [
                 {
                     'name': b'foo',
                     'type': 'file',
                     'target': self.cont['sha1_git'],
                     'perms': 0o644,
                 },
                 {
                     'name': b'bar',
                     'type': 'dir',
                     'target': b'12345678901234560000',
                     'perms': 0o2000,
                 },
                 {
                     'name': b'hello',
                     'type': 'file',
                     'target': b'12345678901234567890',
                     'perms': 0o644,
                 },
 
             ],
         }
 
         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.date_visit1 = datetime.datetime(2015, 1, 1, 23, 0, 0,
                                              tzinfo=datetime.timezone.utc)
 
         self.occurrence = {
             'branch': b'master',
             'target': b'67890123456789012345',
             'target_type': 'revision',
         }
 
         self.date_visit2 = datetime.datetime(2015, 1, 1, 23, 0, 0,
                                              tzinfo=datetime.timezone.utc)
 
         self.occurrence2 = {
             'branch': b'master',
             'target': self.revision2['id'],
             'target_type': 'revision',
         }
 
         self.date_visit3 = datetime.datetime(2015, 1, 1, 23, 0, 0,
                                              tzinfo=datetime.timezone.utc)
 
         # template occurrence to be filled in test (cf. revision_log_by)
         self.occurrence3 = {
             'branch': b'master',
             'target_type': 'revision',
         }
 
         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 improvments + 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.entity1 = {
             'uuid': UUID('f96a7ec1-0058-4920-90cc-7327e4b5a4bf'),
             # GitHub users
             'parent': UUID('ad6df473-c1d2-4f40-bc58-2b091d4a750e'),
             'name': 'github:user:olasd',
             'type': 'person',
             'description': 'Nicolas Dandrimont',
             'homepage': 'http://example.com',
             'active': True,
             'generated': True,
             'lister_metadata': {
                 # swh.lister.github
                 'lister': '34bd6b1b-463f-43e5-a697-785107f598e4',
                 'id': 12877,
                 'type': 'user',
                 'last_activity': '2015-11-03',
             },
             'metadata': None,
             'validity': [
                 datetime.datetime(2015, 11, 3, 11, 0, 0,
                                   tzinfo=datetime.timezone.utc),
             ]
         }
 
         self.entity1_query = {
             'lister': '34bd6b1b-463f-43e5-a697-785107f598e4',
             'id': 12877,
             'type': 'user',
         }
 
         self.entity2 = {
             'uuid': UUID('3903d075-32d6-46d4-9e29-0aef3612c4eb'),
             # GitHub users
             'parent': UUID('ad6df473-c1d2-4f40-bc58-2b091d4a750e'),
             'name': 'github:user:zacchiro',
             'type': 'person',
             'description': 'Stefano Zacchiroli',
             'homepage': 'http://example.com',
             'active': True,
             'generated': True,
             'lister_metadata': {
                 # swh.lister.github
                 'lister': '34bd6b1b-463f-43e5-a697-785107f598e4',
                 'id': 216766,
                 'type': 'user',
                 'last_activity': '2015-11-03',
             },
             'metadata': None,
             'validity': [
                 datetime.datetime(2015, 11, 3, 11, 0, 0,
                                   tzinfo=datetime.timezone.utc),
             ]
         }
 
         self.entity3 = {
             'uuid': UUID('111df473-c1d2-4f40-bc58-2b091d4a7111'),
             # GitHub users
             'parent': UUID('222df473-c1d2-4f40-bc58-2b091d4a7222'),
             'name': 'github:user:ardumont',
             'type': 'person',
             'description': 'Antoine R. Dumont a.k.a tony',
             'homepage': 'https://ardumont.github.io',
             'active': True,
             'generated': True,
             'lister_metadata': {
                 'lister': '34bd6b1b-463f-43e5-a697-785107f598e4',
                 'id': 666,
                 'type': 'user',
                 'last_activity': '2016-01-15',
             },
             'metadata': None,
             'validity': [
                 datetime.datetime(2015, 11, 3, 11, 0, 0,
                                   tzinfo=datetime.timezone.utc),
             ]
         }
 
         self.entity4 = {
             'uuid': UUID('222df473-c1d2-4f40-bc58-2b091d4a7222'),
             # GitHub users
             'parent': None,
             'name': 'github:user:ToNyX',
             'type': 'person',
             'description': 'ToNyX',
             'homepage': 'https://ToNyX.github.io',
             'active': True,
             'generated': True,
             'lister_metadata': {
                 'lister': '34bd6b1b-463f-43e5-a697-785107f598e4',
                 'id': 999,
                 'type': 'user',
                 'last_activity': '2015-12-24',
             },
             'metadata': None,
             'validity': [
                 datetime.datetime(2015, 11, 3, 11, 0, 0,
                                   tzinfo=datetime.timezone.utc),
             ]
         }
 
         self.entity2_query = {
             'lister_metadata': {
                 'lister': '34bd6b1b-463f-43e5-a697-785107f598e4',
                 'id': 216766,
                 'type': 'user',
             },
         }
 
     def tearDown(self):
         self.reset_storage_tables()
         super().tearDown()
 
     def fetch_tools(self):
         tools = {}
         self.cursor.execute('''select tool_name, id, tool_version,
                                       tool_configuration
                                from indexer_configuration''')
         for row in self.cursor.fetchall():
             tools[row[0]] = {
                 'id': row[1],
                 'name': row[0],
                 'version': row[2],
                 'configuration': row[3]
             }
 
         return tools
 
 
 class CommonTestStorage(BaseTestStorage):
     """Base class for Storage testing.
 
     This class is used as-is to test local storage (see TestStorage
     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
 
     @istest
     def check_config(self):
         self.assertTrue(self.storage.check_config(check_write=True))
         self.assertTrue(self.storage.check_config(check_write=False))
 
     @istest
     def content_add(self):
         cont = self.cont
 
         self.storage.content_add([cont])
         if hasattr(self.storage, 'objstorage'):
             self.assertIn(cont['sha1'], self.storage.objstorage)
         self.cursor.execute('SELECT sha1, sha1_git, sha256, length, status'
                             ' FROM content WHERE sha1 = %s',
                             (cont['sha1'],))
         datum = self.cursor.fetchone()
         self.assertEqual(
             (datum[0].tobytes(), datum[1].tobytes(), datum[2].tobytes(),
              datum[3], datum[4]),
             (cont['sha1'], cont['sha1_git'], cont['sha256'],
              cont['length'], 'visible'))
 
     @istest
     def 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(psycopg2.IntegrityError):
             self.storage.content_add([cont1, cont1b])
 
     @istest
     def 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.assertEquals(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')
         )
 
     @istest
     def content_missing(self):
         cont2 = self.cont2
         missing_cont = self.missing_cont
         self.storage.content_add([cont2])
         gen = self.storage.content_missing([cont2, missing_cont])
 
         self.assertEqual(list(gen), [missing_cont['sha1']])
 
     @istest
     def 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']])
 
     @istest
     def 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.assertEqual(list(gen), [cont1, cont2])
 
     @istest
     def 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])
 
     @istest
     def directory_get(self):
         # given
         init_missing = list(self.storage.directory_missing([self.dir['id']]))
         self.assertEqual([self.dir['id']], init_missing)
 
         self.storage.directory_add([self.dir])
 
         # when
         actual_dirs = list(self.storage.directory_get([self.dir['id']]))
 
         self.assertEqual(len(actual_dirs), 1)
 
         dir0 = actual_dirs[0]
         self.assertEqual(dir0['id'], self.dir['id'])
         # ids are generated so non deterministic value
         self.assertEqual(len(dir0['file_entries']), 1)
         self.assertEqual(len(dir0['dir_entries']), 1)
         self.assertIsNone(dir0['rev_entries'])
 
         after_missing = list(self.storage.directory_missing([self.dir['id']]))
         self.assertEqual([], after_missing)
 
     @istest
     def 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])
 
         stored_data = list(self.storage.directory_ls(self.dir['id']))
 
         data_to_store = []
         for ent in sorted(self.dir['entries'], key=itemgetter('name')):
             data_to_store.append({
                 'dir_id': self.dir['id'],
                 'type': ent['type'],
                 'target': ent['target'],
                 'name': ent['name'],
                 'perms': ent['perms'],
                 'status': None,
                 'sha1': None,
                 'sha1_git': None,
                 'sha256': None,
                 'length': None,
             })
 
         self.assertEqual(data_to_store, stored_data)
 
         after_missing = list(self.storage.directory_missing([self.dir['id']]))
         self.assertEqual([], after_missing)
 
     @istest
     def 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': 0o644,
                 'length': None,
             },
             {
                 'dir_id': self.dir3['id'],
                 'name': b'bar',
                 'type': 'dir',
                 'target': b'12345678901234560000',
                 'sha1': None,
                 'sha1_git': None,
                 'sha256': None,
                 'status': None,
                 'perms': 0o2000,
                 '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': 0o644,
                 '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)
 
     @istest
     def revision_add(self):
         init_missing = self.storage.revision_missing([self.revision['id']])
         self.assertEqual([self.revision['id']], list(init_missing))
 
         self.storage.revision_add([self.revision])
 
         end_missing = self.storage.revision_missing([self.revision['id']])
         self.assertEqual([], list(end_missing))
 
     def cache_content_revision_objects(self):
         self.storage.content_add([self.cont, self.cont2, self.cont3])
         directory = {
             'id': b'4\x013\x422\x531\x000\xf51\xe62\xa73\xff7\xc3\xa90',
             'entries': [
                 {
                     'name': b'bar',
                     'type': 'file',
                     'target': self.cont2['sha1_git'],
                     'perms': 0o644,
                 },
                 {
                     'name': b'foo',
                     'type': 'file',
                     'target': self.cont['sha1_git'],
                     'perms': 0o644,
                 },
                 {
                     'name': b'bar\xc3',
                     'type': 'dir',
                     'target': b'12345678901234567890',
                     'perms': 0o2000,
                 },
             ],
         }
         directory2 = copy.deepcopy(directory)
         directory2['id'] = (directory2['id'][:-1] +
                             bytes([(directory2['id'][-1] + 1) % 256]))
         directory2['entries'][1] = {
             'name': b'foo',
             'type': 'file',
             'target': self.cont3['sha1_git'],
             'perms': 0o644,
         }
 
         self.storage.directory_add([directory, directory2])
         revision = self.revision.copy()
         revision['directory'] = directory['id']
         revision2 = copy.deepcopy(revision)
         revision2['parents'] = [revision['id']]
         revision2['directory'] = directory2['id']
         revision2['id'] = (revision2['id'][:-1] +
                            bytes([(revision2['id'][-1] + 1) % 256]))
         self.storage.revision_add([revision, revision2])
         return (directory, directory2, revision, revision2)
 
     @istest
     def cache_content_revision_add(self):
         # Create a real arborescence tree (contents + directory) and a
         # revision targeting that directory.
         # Assert the cache is empty for that revision
         # Then create that revision
         # Trigger the cache population for that revision
         # Assert the cache now contains information for that revision
         # Trigger again the cache population for that revision
         # Assert the cache is not modified
 
         # given ()
         (directory, directory2,
          revision, revision2) = self.cache_content_revision_objects()
 
         # assert nothing in cache yet
         count_query = '''select count(*)
                          from cache_content_revision'''
         self.cursor.execute(count_query)
         ret = self.cursor.fetchone()
         self.assertEqual(ret, (0, ))
 
         # when, triggered the first time, we cache the revision
         self.storage.cache_content_revision_add([revision['id']])
         # the second time, we do nothing as this is already done
         self.storage.cache_content_revision_add([revision['id']])
 
         # then
         self.cursor.execute(count_query)
         ret = self.cursor.fetchone()
         # only 2 contents exists for that revision (the second call to
         # revision_cache discards as the revision is already cached)
         self.assertEqual(ret, (2, ))
 
         self.cursor.execute('select * from cache_content_revision')
         ret = self.cursor.fetchall()
 
         expected_cache_entries = [
             (directory['entries'][0]['target'], False,
              [[revision['id'], directory['entries'][0]['name']]]),
             (directory['entries'][1]['target'], False,
              [[revision['id'], directory['entries'][1]['name']]])
         ]
         for i, expected_entry in enumerate(expected_cache_entries):
             ret_entry = (ret[i][0].tobytes(), ret[i][1],
                          [[ret[i][2][0][0].tobytes(),
                            ret[i][2][0][1].tobytes()]])
             self.assertEquals(ret_entry, expected_entry)
 
     @istest
     def cache_content_revision_add_twice(self):
         # given ()
         (directory, directory2,
          revision, revision2) = self.cache_content_revision_objects()
 
         # assert nothing in cache yet
         count_query = '''select count(*)
                          from cache_content_revision'''
         self.cursor.execute(count_query)
         ret = self.cursor.fetchone()
         self.assertEqual(ret, (0, ))
 
         # when, triggered the first time, we cache the revision
         self.storage.cache_content_revision_add([revision['id']])
         # the second time, we do nothing as this is already done
         self.storage.cache_content_revision_add([revision2['id']])
 
         # then
         self.cursor.execute('select * from cache_content_revision')
         cache_entries = {
             content.tobytes(): [[rev.tobytes(), path.tobytes()]
                                 for rev, path in rev_paths]
             for content, blacklisted, rev_paths in self.cursor.fetchall()
         }
 
         self.assertEquals(len(cache_entries), 3)
         self.assertEquals(len(cache_entries[self.cont['sha1_git']]), 1)
         self.assertEquals(len(cache_entries[self.cont2['sha1_git']]), 2)
         self.assertEquals(len(cache_entries[self.cont3['sha1_git']]), 1)
 
     @istest
     def cache_content_get_all(self):
         # given
         (directory, directory2,
          revision, revision2) = self.cache_content_revision_objects()
 
         # assert nothing in cache yet
         test_query = '''select sha1, sha1_git, sha256, ccr.revision_paths
                         from cache_content_revision ccr
                         inner join content c on c.sha1_git=ccr.content'''
 
         self.storage.cache_content_revision_add([revision['id']])
         self.cursor.execute(test_query, (revision['id'],))
         ret = list(cursor_to_bytes(self.cursor))
 
         self.assertEqual(len(ret), 2)
 
         expected_contents = []
         for entry in ret:
             expected_contents.append(dict(
                 zip(['sha1', 'sha1_git', 'sha256', 'revision_paths'], entry)))
 
         # 1. default filters gives everything
         actual_cache_contents = list(self.storage.cache_content_get_all())
 
         self.assertEquals(actual_cache_contents, expected_contents)
 
     @istest
     def cache_content_get(self):
         # given
         (directory, directory2,
          revision, revision2) = self.cache_content_revision_objects()
 
         # assert nothing in cache yet
         test_query = '''select c.sha1, c.sha1_git, c.sha256, ccr.revision_paths
                         from cache_content_revision ccr
                         inner join content c on c.sha1_git=ccr.content
                         where ccr.content=%s'''
 
         self.storage.cache_content_revision_add([revision['id']])
         self.cursor.execute(test_query, (self.cont2['sha1_git'],))
         ret = list(cursor_to_bytes(self.cursor))[0]
 
         self.assertIsNotNone(ret)
 
         expected_content = dict(
             zip(['sha1', 'sha1_git', 'sha256', 'revision_paths'], ret))
 
         # when
         actual_cache_content = self.storage.cache_content_get(self.cont2)
 
         # then
         self.assertEquals(actual_cache_content, expected_content)
 
     @istest
     def 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:
             del actual_result['author']['id']
             del actual_result['committer']['id']
 
         self.assertEqual(len(actual_results), 2)  # rev4 -child-> rev3
         self.assertEquals(actual_results[0],
                           self.normalize_entity(self.revision4))
         self.assertEquals(actual_results[1],
                           self.normalize_entity(self.revision3))
 
     @istest
     def 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:
             del actual_result['author']['id']
             del actual_result['committer']['id']
 
         self.assertEqual(len(actual_results), 1)
         self.assertEquals(actual_results[0], self.revision4)
 
     @istest
     def revision_log_by(self):
         # given
         origin_id = self.storage.origin_add_one(self.origin2)
         self.storage.revision_add([self.revision3,
                                    self.revision4])
 
         # occurrence3 targets 'revision4'
         # with branch 'master' and origin origin_id
         occurrence3 = self.occurrence3.copy()
         date_visit1 = self.date_visit3
         origin_visit1 = self.storage.origin_visit_add(origin_id,
                                                       date_visit1)
         occurrence3.update({
             'origin': origin_id,
             'target': self.revision4['id'],
             'visit': origin_visit1['visit'],
         })
 
         self.storage.occurrence_add([occurrence3])
 
         # self.revision4 -is-child-of-> self.revision3
         # when
         actual_results = list(self.storage.revision_log_by(
             origin_id,
             branch_name=occurrence3['branch'],
             timestamp=date_visit1))
 
         # hack: ids generated
         for actual_result in actual_results:
             del actual_result['author']['id']
             del actual_result['committer']['id']
 
         self.assertEqual(len(actual_results), 2)
         self.assertEquals(actual_results[0],
                           self.normalize_entity(self.revision4))
         self.assertEquals(actual_results[1],
                           self.normalize_entity(self.revision3))
 
         # when - 2
         actual_results = list(self.storage.revision_log_by(
             origin_id,
             branch_name=None,
             timestamp=None,
             limit=1))
 
         # then
         for actual_result in actual_results:
             del actual_result['author']['id']
             del actual_result['committer']['id']
 
         self.assertEqual(len(actual_results), 1)
         self.assertEquals(actual_results[0], self.revision4)
 
         # when - 3 (revision not found)
 
         actual_res = list(self.storage.revision_log_by(
             origin_id,
             branch_name='inexistant-branch',
             timestamp=None))
 
         self.assertEquals(actual_res, [])
 
     @staticmethod
     def _short_revision(revision):
         return [revision['id'], revision['parents']]
 
     @istest
     def 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.assertEquals(list(actual_results[0]),
                           self._short_revision(self.revision4))
         self.assertEquals(list(actual_results[1]),
                           self._short_revision(self.revision3))
 
     @istest
     def 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.assertEquals(list(actual_results[0]),
                           self._short_revision(self.revision4))
 
     @istest
     def revision_get(self):
         self.storage.revision_add([self.revision])
 
         actual_revisions = list(self.storage.revision_get(
             [self.revision['id'], self.revision2['id']]))
 
         # when
         del actual_revisions[0]['author']['id']  # hack: ids are generated
         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])
 
     @istest
     def 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
 
     @istest
     def revision_get_by(self):
         # given
         self.storage.content_add([self.cont2])
         self.storage.directory_add([self.dir2])  # point to self.cont
         self.storage.revision_add([self.revision2])  # points to self.dir
         origin_id = self.storage.origin_add_one(self.origin2)
 
         # occurrence2 points to 'revision2' with branch 'master', we
         # need to point to the right origin
         occurrence2 = self.occurrence2.copy()
         date_visit1 = self.date_visit2
         origin_visit1 = self.storage.origin_visit_add(origin_id, date_visit1)
         occurrence2.update({
             'origin': origin_id,
             'visit': origin_visit1['visit'],
         })
         self.storage.occurrence_add([occurrence2])
 
         # we want only revision 2
         expected_revisions = list(self.storage.revision_get(
             [self.revision2['id']]))
 
         # when
         actual_results = list(self.storage.revision_get_by(
             origin_id,
             occurrence2['branch'],
             None))
 
         self.assertEqual(actual_results[0], expected_revisions[0])
 
         # when (with no branch filtering, it's still ok)
         actual_results = list(self.storage.revision_get_by(
             origin_id,
             None,
             None))
 
         self.assertEqual(actual_results[0], expected_revisions[0])
 
     @istest
     def revision_get_by_multiple_occurrence(self):
         # 2 occurrences pointing to 2 different revisions
         # each occurence have 1 day delta
         # the api must return the revision whose occurrence is the nearest.
 
         # given
         self.storage.content_add([self.cont2])
         self.storage.directory_add([self.dir2])
         self.storage.revision_add([self.revision2, self.revision3])
         origin_id = self.storage.origin_add_one(self.origin2)
 
         # occurrence2 points to 'revision2' with branch 'master', we
         # need to point to the right origin
         date_visit1 = self.date_visit2
         origin_visit1 = self.storage.origin_visit_add(origin_id, date_visit1)
         occurrence2 = self.occurrence2.copy()
         occurrence2.update({
             'origin': origin_id,
             'visit': origin_visit1['visit']
         })
 
         dt = datetime.timedelta(days=1)
         date_visit2 = date_visit1 + dt
         origin_visit2 = self.storage.origin_visit_add(origin_id, date_visit2)
         occurrence3 = self.occurrence2.copy()
         occurrence3.update({
             'origin': origin_id,
             'visit': origin_visit2['visit'],
             'target': self.revision3['id'],
         })
         # 2 occurrences on same revision with lower validity date with 1 day
         # delta
         self.storage.occurrence_add([occurrence2])
         self.storage.occurrence_add([occurrence3])
 
         # when
         actual_results0 = list(self.storage.revision_get_by(
             origin_id,
             occurrence2['branch'],
             date_visit1))
 
         # hack: ids are generated
         del actual_results0[0]['author']['id']
         del actual_results0[0]['committer']['id']
 
         self.assertEquals(len(actual_results0), 1)
         self.assertEqual(actual_results0,
                          [self.normalize_entity(self.revision2)])
 
         # when
         actual_results1 = list(self.storage.revision_get_by(
             origin_id,
             occurrence2['branch'],
             date_visit1 + dt/3))  # closer to first visit
 
         # hack: ids are generated
         del actual_results1[0]['author']['id']
         del actual_results1[0]['committer']['id']
 
         self.assertEquals(len(actual_results1), 1)
         self.assertEqual(actual_results1,
                          [self.normalize_entity(self.revision2)])
 
         # when
         actual_results2 = list(self.storage.revision_get_by(
             origin_id,
             occurrence2['branch'],
             date_visit1 + 2*dt/3))  # closer to second visit
 
         del actual_results2[0]['author']['id']
         del actual_results2[0]['committer']['id']
 
         self.assertEquals(len(actual_results2), 1)
         self.assertEqual(actual_results2,
                          [self.normalize_entity(self.revision3)])
 
         # when
         actual_results3 = list(self.storage.revision_get_by(
             origin_id,
             occurrence3['branch'],
             date_visit2))
 
         # hack: ids are generated
         del actual_results3[0]['author']['id']
         del actual_results3[0]['committer']['id']
 
         self.assertEquals(len(actual_results3), 1)
         self.assertEqual(actual_results3,
                          [self.normalize_entity(self.revision3)])
 
         # when
         actual_results4 = list(self.storage.revision_get_by(
             origin_id,
             None,
             None))
 
         for actual_result in actual_results4:
             del actual_result['author']['id']
             del actual_result['committer']['id']
 
         self.assertEquals(len(actual_results4), 1)
         self.assertCountEqual(actual_results4,
                               [self.normalize_entity(self.revision3)])
 
     @istest
     def 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))
 
     @istest
     def 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:
             del actual_release['author']['id']  # hack: ids are generated
 
         self.assertEquals([self.normalize_entity(self.release),
                            self.normalize_entity(self.release2)],
                           [actual_releases[0], actual_releases[1]])
 
     @istest
     def release_get_by(self):
         # given
         self.storage.revision_add([self.revision2])  # points to self.dir
         self.storage.release_add([self.release3])
         origin_id = self.storage.origin_add_one(self.origin2)
 
         # occurrence2 points to 'revision2' with branch 'master', we
         # need to point to the right origin
         origin_visit = self.storage.origin_visit_add(origin_id,
                                                      self.date_visit2)
         occurrence2 = self.occurrence2.copy()
         occurrence2.update({
             'origin': origin_id,
             'visit': origin_visit['visit'],
         })
 
         self.storage.occurrence_add([occurrence2])
 
         # we want only revision 2
         expected_releases = list(self.storage.release_get(
             [self.release3['id']]))
 
         # when
         actual_results = list(self.storage.release_get_by(
             occurrence2['origin']))
 
         # then
         self.assertEqual(actual_results[0], expected_releases[0])
 
     @istest
     def 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)
 
     @istest
     def origin_add(self):
         origin0 = self.storage.origin_get(self.origin)
         self.assertIsNone(origin0)
 
         id1, id2 = self.storage.origin_add([self.origin, self.origin2])
 
         actual_origin = self.storage.origin_get({
             'url': self.origin['url'],
             'type': self.origin['type'],
         })
         self.assertEqual(actual_origin['id'], id1)
 
         actual_origin2 = self.storage.origin_get({
             'url': self.origin2['url'],
             'type': self.origin2['type'],
         })
         self.assertEqual(actual_origin2['id'], id2)
 
     @istest
     def 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)
 
     @istest
     def origin_get(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'],
                                           'lister': None,
                                           'project': None})
 
     @istest
     def origin_visit_add(self):
         # given
         self.assertIsNone(self.storage.origin_get(self.origin2))
 
         origin_id = self.storage.origin_add_one(self.origin2)
         self.assertIsNotNone(origin_id)
 
         # when
         origin_visit1 = self.storage.origin_visit_add(
             origin_id,
             ts=self.date_visit2)
 
         # then
         self.assertEquals(origin_visit1['origin'], origin_id)
         self.assertIsNotNone(origin_visit1['visit'])
         self.assertTrue(origin_visit1['visit'] > 0)
 
         actual_origin_visits = list(self.storage.origin_visit_get(origin_id))
         self.assertEquals(actual_origin_visits,
                           [{
                               'origin': origin_id,
                               'date': self.date_visit2,
                               'visit': origin_visit1['visit'],
                               'status': 'ongoing',
                               'metadata': None,
                           }])
 
     @istest
     def 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,
             ts=self.date_visit2)
 
         origin_visit2 = self.storage.origin_visit_add(
             origin_id,
             ts=self.date_visit3)
 
         origin_visit3 = self.storage.origin_visit_add(
             origin_id2,
             ts=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.assertEquals(actual_origin_visits,
                           [{
                               'origin': origin_visit2['origin'],
                               'date': self.date_visit2,
                               'visit': origin_visit1['visit'],
                               'status': 'full',
                               'metadata': visit1_metadata,
                           },
                            {
                                'origin': origin_visit2['origin'],
                                'date': self.date_visit3,
                                'visit': origin_visit2['visit'],
                                'status': 'ongoing',
                                'metadata': None,
                            }])
 
         actual_origin_visits_bis = list(self.storage.origin_visit_get(
             origin_id, limit=1))
         self.assertEquals(actual_origin_visits_bis,
                           [{
                               'origin': origin_visit2['origin'],
                               'date': self.date_visit2,
                               'visit': origin_visit1['visit'],
                               'status': 'full',
                               'metadata': visit1_metadata,
                           }])
 
         actual_origin_visits_ter = list(self.storage.origin_visit_get(
             origin_id, last_visit=origin_visit1['visit']))
         self.assertEquals(actual_origin_visits_ter,
                           [{
                                'origin': origin_visit2['origin'],
                                'date': self.date_visit3,
                                'visit': origin_visit2['visit'],
                                'status': 'ongoing',
                                'metadata': None,
                            }])
 
         actual_origin_visits2 = list(self.storage.origin_visit_get(origin_id2))
         self.assertEquals(actual_origin_visits2,
                           [{
                               'origin': origin_visit3['origin'],
                               'date': self.date_visit3,
                               'visit': origin_visit3['visit'],
                               'status': 'partial',
                               'metadata': None,
                           }])
 
     @istest
     def 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,
             ts=self.date_visit2)
 
         occurrence2 = self.occurrence2.copy()
         occurrence2.update({
             'origin': origin_id,
             'visit': origin_visit1['visit'],
         })
 
         self.storage.occurrence_add([occurrence2])
 
         # Add some other {origin, visit} entries
         self.storage.origin_visit_add(origin_id, ts=self.date_visit3)
         self.storage.origin_visit_add(origin_id2, ts=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',
             'occurrences': {
                 occurrence2['branch']: {
                     'target': occurrence2['target'],
                     'target_type': occurrence2['target_type'],
                 }
             }
         })
 
         # when
         actual_origin_visit1 = self.storage.origin_visit_get_by(
             origin_visit1['origin'], origin_visit1['visit'])
 
         # then
         self.assertEquals(actual_origin_visit1, expected_origin_visit)
 
     @istest
     def 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)
 
     @istest
     def occurrence_add(self):
         occur = self.occurrence.copy()
 
         origin_id = self.storage.origin_add_one(self.origin2)
         date_visit1 = self.date_visit1
         origin_visit1 = self.storage.origin_visit_add(origin_id, date_visit1)
 
         revision = self.revision.copy()
         revision['id'] = occur['target']
         self.storage.revision_add([revision])
 
         occur.update({
             'origin': origin_id,
             'visit': origin_visit1['visit'],
         })
         self.storage.occurrence_add([occur])
 
         test_query = '''
         with indiv_occurrences as (
           select origin, branch, target, target_type, unnest(visits) as visit
           from occurrence_history
         )
         select origin, branch, target, target_type, date
         from indiv_occurrences
         left join origin_visit using(origin, visit)
         order by origin, date'''
 
         self.cursor.execute(test_query)
         ret = self.cursor.fetchall()
         self.assertEqual(len(ret), 1)
         self.assertEqual(
             (ret[0][0], ret[0][1].tobytes(), ret[0][2].tobytes(),
              ret[0][3], ret[0][4]),
             (occur['origin'], occur['branch'], occur['target'],
              occur['target_type'], self.date_visit1))
 
         date_visit2 = date_visit1 + datetime.timedelta(hours=10)
 
         origin_visit2 = self.storage.origin_visit_add(origin_id, date_visit2)
         occur2 = occur.copy()
         occur2.update({
             'visit': origin_visit2['visit'],
         })
         self.storage.occurrence_add([occur2])
 
         self.cursor.execute(test_query)
         ret = self.cursor.fetchall()
         self.assertEqual(len(ret), 2)
         self.assertEqual(
             (ret[0][0], ret[0][1].tobytes(), ret[0][2].tobytes(),
              ret[0][3], ret[0][4]),
             (occur['origin'], occur['branch'], occur['target'],
              occur['target_type'], date_visit1))
         self.assertEqual(
             (ret[1][0], ret[1][1].tobytes(), ret[1][2].tobytes(),
              ret[1][3], ret[1][4]),
             (occur2['origin'], occur2['branch'], occur2['target'],
              occur2['target_type'], date_visit2))
 
     @istest
     def occurrence_get(self):
         # given
         occur = self.occurrence.copy()
         origin_id = self.storage.origin_add_one(self.origin2)
         origin_visit1 = self.storage.origin_visit_add(origin_id,
                                                       self.date_visit1)
 
         revision = self.revision.copy()
         revision['id'] = occur['target']
         self.storage.revision_add([revision])
 
         occur.update({
             'origin': origin_id,
             'visit': origin_visit1['visit'],
         })
         self.storage.occurrence_add([occur])
         self.storage.occurrence_add([occur])
 
         # when
         actual_occurrence = list(self.storage.occurrence_get(origin_id))
 
         # then
         expected_occurrence = self.occurrence.copy()
         expected_occurrence.update({
             'origin': origin_id
         })
         self.assertEquals(len(actual_occurrence), 1)
         self.assertEquals(actual_occurrence[0], expected_occurrence)
 
     def _trigger_cache_provenance(self, origin_visit):
         """Trigger cache population for cache_content_revision.
 
         """
         ret = list(self.storage.cache_revision_origin_add(
                 origin_visit['origin'],
                 origin_visit['visit'],
         ))
 
         for revision_id in ret:
             self.storage.cache_content_revision_add([revision_id])
 
         return ret
 
     @istest
     def content_find_provenance_with_present_content(self):
         # 1. with something to find
         # given
         origin_id = self.storage.origin_add_one(self.origin2)
         self.storage.content_add([self.cont2])
         self.storage.directory_add([self.dir2])  # point to self.cont
         self.storage.revision_add([self.revision3])  # points to self.dir
 
         occurrence = self.occurrence3.copy()
         occurrence['target'] = self.revision3['id']
         origin_visit1 = self.storage.origin_visit_add(origin_id,
                                                       self.date_visit2)
         occurrence.update({
             'origin': origin_id,
             'visit': origin_visit1['visit'],
         })
 
         self.storage.occurrence_add([occurrence])
 
         # Trigger cache population for cache_content_revision
         cached_revisions = self._trigger_cache_provenance(origin_visit1)
 
         self.assertIn(self.revision3['id'], cached_revisions)
 
         # when
         occs = list(self.storage.content_find_provenance(
             {'sha1': self.cont2['sha1']}))
 
         # then
         self.assertEquals(len(occs), 1)
         self.assertEquals(occs[0]['origin'], origin_visit1['origin'])
         self.assertEquals(occs[0]['visit'], origin_visit1['visit'])
         self.assertEquals(occs[0]['revision'], self.revision3['id'])
         self.assertEquals(occs[0]['path'], self.dir2['entries'][0]['name'])
 
         occs2 = list(self.storage.content_find_provenance(
             {'sha1_git': self.cont2['sha1_git']}))
 
         self.assertEquals(len(occs2), 1)
         self.assertEquals(occs2[0]['origin'], origin_visit1['origin'])
         self.assertEquals(occs2[0]['visit'], origin_visit1['visit'])
         self.assertEquals(occs2[0]['revision'], self.revision3['id'])
         self.assertEquals(occs2[0]['path'], self.dir2['entries'][0]['name'])
 
         occs3 = list(self.storage.content_find_provenance(
             {'sha256': self.cont2['sha256']}))
 
         self.assertEquals(len(occs3), 1)
         self.assertEquals(occs3[0]['origin'], origin_visit1['origin'])
         self.assertEquals(occs3[0]['visit'], origin_visit1['visit'])
         self.assertEquals(occs3[0]['revision'], self.revision3['id'])
         self.assertEquals(occs3[0]['path'], self.dir2['entries'][0]['name'])
 
     @istest
     def content_find_provenance_with_non_present_content(self):
         # 1. with something that does not exist
         missing_cont = self.missing_cont
 
         occ = list(self.storage.content_find_provenance(
             {'sha1': missing_cont['sha1']}))
 
         self.assertEquals(occ, [],
                           "Content does not exist so no occurrence")
 
         # 2. with something that does not exist
         occ = list(self.storage.content_find_provenance(
             {'sha1_git': missing_cont['sha1_git']}))
 
         self.assertEquals(occ, [],
                           "Content does not exist so no occurrence")
 
         # 3. with something that does not exist
         occ = list(self.storage.content_find_provenance(
             {'sha256': missing_cont['sha256']}))
 
         self.assertEquals(occ, [],
                           "Content does not exist so no occurrence")
 
     @istest
     def content_find_occurrence_bad_input(self):
         # 1. with bad input
         with self.assertRaises(ValueError) as cm:
             list(self.storage.content_find_provenance({}))  # empty is bad
         self.assertIn('content keys', cm.exception.args[0])
 
         # 2. with bad input
         with self.assertRaises(ValueError) as cm:
             list(self.storage.content_find_provenance(
                 {'unknown-sha1': 'something'}))  # not the right key
         self.assertIn('content keys', cm.exception.args[0])
 
     @istest
     def entity_get_from_lister_metadata(self):
         self.storage.entity_add([self.entity1])
 
         fetched_entities = list(
             self.storage.entity_get_from_lister_metadata(
                 [self.entity1_query, self.entity2_query]))
 
         # Entity 1 should have full metadata, with last_seen/last_id instead
         # of validity
         entity1 = self.entity1.copy()
         entity1['last_seen'] = entity1['validity'][0]
         del fetched_entities[0]['last_id']
         del entity1['validity']
         # Entity 2 should have no metadata
         entity2 = {
             'uuid': None,
             'lister_metadata': self.entity2_query.copy(),
         }
 
         self.assertEquals(fetched_entities, [entity1, entity2])
 
     @istest
     def entity_get_from_lister_metadata_twice(self):
         self.storage.entity_add([self.entity1])
 
         fetched_entities1 = list(
             self.storage.entity_get_from_lister_metadata(
                 [self.entity1_query]))
         fetched_entities2 = list(
             self.storage.entity_get_from_lister_metadata(
                 [self.entity1_query]))
 
         self.assertEquals(fetched_entities1, fetched_entities2)
 
     @istest
     def entity_get(self):
         # given
         self.storage.entity_add([self.entity4])
         self.storage.entity_add([self.entity3])
 
         # when: entity3 -child-of-> entity4
         actual_entity3 = list(self.storage.entity_get(self.entity3['uuid']))
 
         self.assertEquals(len(actual_entity3), 2)
         # remove dynamic data (modified by db)
         entity3 = self.entity3.copy()
         entity4 = self.entity4.copy()
         del entity3['validity']
         del entity4['validity']
         del actual_entity3[0]['last_seen']
         del actual_entity3[0]['last_id']
         del actual_entity3[1]['last_seen']
         del actual_entity3[1]['last_id']
         self.assertEquals(actual_entity3, [entity3, entity4])
 
         # when: entity4 only child
         actual_entity4 = list(self.storage.entity_get(self.entity4['uuid']))
 
         self.assertEquals(len(actual_entity4), 1)
         # remove dynamic data (modified by db)
         entity4 = self.entity4.copy()
         del entity4['validity']
         del actual_entity4[0]['last_id']
         del actual_entity4[0]['last_seen']
 
         self.assertEquals(actual_entity4, [entity4])
 
     @istest
     def entity_get_one(self):
         # given
         self.storage.entity_add([self.entity3, self.entity4])
 
         # when: entity3 -child-of-> entity4
         actual_entity3 = self.storage.entity_get_one(self.entity3['uuid'])
 
         # remove dynamic data (modified by db)
         entity3 = self.entity3.copy()
         del entity3['validity']
         del actual_entity3['last_seen']
         del actual_entity3['last_id']
         self.assertEquals(actual_entity3, entity3)
 
     @istest
     def stat_counters(self):
         expected_keys = ['content', 'directory', 'directory_entry_dir',
                          'occurrence', 'origin', 'person', 'revision']
+
+        for key in expected_keys:
+            self.cursor.execute('select * from swh_update_counter(%s)', (key,))
+        self.conn.commit()
+
         counters = self.storage.stat_counters()
 
         self.assertTrue(set(expected_keys) <= set(counters))
         self.assertIsInstance(counters[expected_keys[0]], int)
 
     @istest
     def 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'
         })
 
     @istest
     def 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)
 
     @istest
     def 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
 
     @istest
     def 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)
 
     @istest
     def content_mimetype_missing(self):
         # given
         tools = self.fetch_tools()
         tool_id = tools['file']['id']
 
         cont2 = self.cont2
         self.storage.content_add([cont2])
 
         mimetypes = [
             {
                 'id': self.cont2['sha1'],
                 'indexer_configuration_id': tool_id,
             },
             {
                 'id': self.missing_cont['sha1'],
                 'indexer_configuration_id': tool_id,
             }]
 
         # when
         actual_missing = self.storage.content_mimetype_missing(mimetypes)
 
         # then
         self.assertEqual(list(actual_missing), [
             self.cont2['sha1'],
             self.missing_cont['sha1']
         ])
 
         # given
         self.storage.content_mimetype_add([{
             'id': self.cont2['sha1'],
             'mimetype': b'text/plain',
             'encoding': b'utf-8',
             'indexer_configuration_id': tool_id,
         }])
 
         # when
         actual_missing = self.storage.content_mimetype_missing(mimetypes)
 
         # then
         self.assertEqual(list(actual_missing), [self.missing_cont['sha1']])
 
     @istest
     def content_mimetype_add__drop_duplicate(self):
         # given
         tools = self.fetch_tools()
         tool_id = tools['file']['id']
 
         cont2 = self.cont2
         self.storage.content_add([cont2])
 
         mimetype_v1 = {
             'id': self.cont2['sha1'],
             'mimetype': b'text/plain',
             'encoding': b'utf-8',
             'indexer_configuration_id': tool_id,
         }
 
         # given
         self.storage.content_mimetype_add([mimetype_v1])
 
         # when
         actual_mimetypes = list(self.storage.content_mimetype_get(
             [self.cont2['sha1']]))
 
         # then
         expected_mimetypes_v1 = [{
             'id': self.cont2['sha1'],
             'mimetype': b'text/plain',
             'encoding': b'utf-8',
             'tool': tools['file'],
         }]
         self.assertEqual(actual_mimetypes, expected_mimetypes_v1)
 
         # given
         mimetype_v2 = mimetype_v1.copy()
         mimetype_v2.update({
             'mimetype': b'text/html',
             'encoding': b'us-ascii',
         })
 
         self.storage.content_mimetype_add([mimetype_v2])
 
         actual_mimetypes = list(self.storage.content_mimetype_get(
             [self.cont2['sha1']]))
 
         # mimetype did not change as the v2 was dropped.
         self.assertEqual(actual_mimetypes, expected_mimetypes_v1)
 
     @istest
     def content_mimetype_add__update_in_place_duplicate(self):
         # given
         tools = self.fetch_tools()
         tool_id = tools['file']['id']
         cont2 = self.cont2
         self.storage.content_add([cont2])
 
         mimetype_v1 = {
             'id': self.cont2['sha1'],
             'mimetype': b'text/plain',
             'encoding': b'utf-8',
             'indexer_configuration_id': tool_id,
         }
 
         # given
         self.storage.content_mimetype_add([mimetype_v1])
 
         # when
         actual_mimetypes = list(self.storage.content_mimetype_get(
             [self.cont2['sha1']]))
 
         expected_mimetypes_v1 = [{
             'id': self.cont2['sha1'],
             'mimetype': b'text/plain',
             'encoding': b'utf-8',
             'tool': tools['file'],
         }]
 
         # then
         self.assertEqual(actual_mimetypes, expected_mimetypes_v1)
 
         # given
         mimetype_v2 = mimetype_v1.copy()
         mimetype_v2.update({
             'mimetype': b'text/html',
             'encoding': b'us-ascii',
         })
 
         self.storage.content_mimetype_add([mimetype_v2], conflict_update=True)
 
         actual_mimetypes = list(self.storage.content_mimetype_get(
             [self.cont2['sha1']]))
 
         expected_mimetypes_v2 = [{
             'id': self.cont2['sha1'],
             'mimetype': b'text/html',
             'encoding': b'us-ascii',
             'tool': {
                 'id': 2,
                 'name': 'file',
                 'version': '5.22',
                 'configuration': {'command_line': 'file --mime <filepath>'}
             }
         }]
 
         # mimetype did change as the v2 was used to overwrite v1
         self.assertEqual(actual_mimetypes, expected_mimetypes_v2)
 
     @istest
     def content_mimetype_get(self):
         # given
         tools = self.fetch_tools()
         tool_id = tools['file']['id']
         cont2 = self.cont2
         self.storage.content_add([cont2])
 
         mimetypes = [self.cont2['sha1'], self.missing_cont['sha1']]
 
         mimetype1 = {
             'id': self.cont2['sha1'],
             'mimetype': b'text/plain',
             'encoding': b'utf-8',
             'indexer_configuration_id': tool_id,
         }
 
         # when
         self.storage.content_mimetype_add([mimetype1])
 
         # then
         actual_mimetypes = list(self.storage.content_mimetype_get(mimetypes))
 
         # then
         expected_mimetypes = [{
             'id': self.cont2['sha1'],
             'mimetype': b'text/plain',
             'encoding': b'utf-8',
             'tool': tools['file']
         }]
 
         self.assertEqual(actual_mimetypes, expected_mimetypes)
 
     @istest
     def content_language_missing(self):
         # given
         tools = self.fetch_tools()
         tool_id = tools['pygments']['id']
 
         cont2 = self.cont2
         self.storage.content_add([cont2])
 
         languages = [
             {
                 'id': self.cont2['sha1'],
                 'indexer_configuration_id': tool_id,
             },
             {
                 'id': self.missing_cont['sha1'],
                 'indexer_configuration_id': tool_id,
             }
         ]
 
         # when
         actual_missing = list(self.storage.content_language_missing(languages))
 
         # then
         self.assertEqual(list(actual_missing), [
             self.cont2['sha1'],
             self.missing_cont['sha1'],
         ])
 
         # given
         self.storage.content_language_add([{
             'id': self.cont2['sha1'],
             'lang': 'haskell',
             'indexer_configuration_id': tool_id,
         }])
 
         # when
         actual_missing = list(self.storage.content_language_missing(languages))
 
         # then
         self.assertEqual(actual_missing, [self.missing_cont['sha1']])
 
     @istest
     def content_language_get(self):
         # given
         tools = self.fetch_tools()
         tool_id = tools['pygments']['id']
         cont2 = self.cont2
         self.storage.content_add([cont2])
 
         language1 = {
             'id': self.cont2['sha1'],
             'lang': 'common-lisp',
             'indexer_configuration_id': tool_id,
         }
 
         # when
         self.storage.content_language_add([language1])
 
         # then
         actual_languages = list(self.storage.content_language_get(
             [self.cont2['sha1'], self.missing_cont['sha1']]))
 
         # then
         expected_languages = [{
             'id': self.cont2['sha1'],
             'lang': 'common-lisp',
             'tool': tools['pygments']
         }]
 
         self.assertEqual(actual_languages, expected_languages)
 
     @istest
     def content_language_add__drop_duplicate(self):
         # given
         tools = self.fetch_tools()
         tool_id = tools['pygments']['id']
         cont2 = self.cont2
         self.storage.content_add([cont2])
 
         language_v1 = {
             'id': self.cont2['sha1'],
             'lang': 'emacslisp',
             'indexer_configuration_id': tool_id,
         }
 
         # given
         self.storage.content_language_add([language_v1])
 
         # when
         actual_languages = list(self.storage.content_language_get(
             [self.cont2['sha1']]))
 
         # then
         expected_languages_v1 = [{
             'id': self.cont2['sha1'],
             'lang': 'emacslisp',
             'tool': tools['pygments']
         }]
         self.assertEqual(actual_languages, expected_languages_v1)
 
         # given
         language_v2 = language_v1.copy()
         language_v2.update({
             'lang': 'common-lisp',
         })
 
         self.storage.content_language_add([language_v2])
 
         actual_languages = list(self.storage.content_language_get(
             [self.cont2['sha1']]))
 
         # language did not change as the v2 was dropped.
         self.assertEqual(actual_languages, expected_languages_v1)
 
     @istest
     def content_language_add__update_in_place_duplicate(self):
         # given
         tools = self.fetch_tools()
         tool_id = tools['pygments']['id']
         cont2 = self.cont2
         self.storage.content_add([cont2])
 
         language_v1 = {
             'id': self.cont2['sha1'],
             'lang': 'common-lisp',
             'indexer_configuration_id': tool_id,
         }
 
         # given
         self.storage.content_language_add([language_v1])
 
         # when
         actual_languages = list(self.storage.content_language_get(
             [self.cont2['sha1']]))
 
         # then
         expected_languages_v1 = [{
             'id': self.cont2['sha1'],
             'lang': 'common-lisp',
             'tool': tools['pygments']
         }]
         self.assertEqual(actual_languages, expected_languages_v1)
 
         # given
         language_v2 = language_v1.copy()
         language_v2.update({
             'lang': 'emacslisp',
         })
 
         self.storage.content_language_add([language_v2], conflict_update=True)
 
         actual_languages = list(self.storage.content_language_get(
             [self.cont2['sha1']]))
 
         # language did not change as the v2 was dropped.
         expected_languages_v2 = [{
             'id': self.cont2['sha1'],
             'lang': 'emacslisp',
             'tool': tools['pygments']
         }]
 
         # language did change as the v2 was used to overwrite v1
         self.assertEqual(actual_languages, expected_languages_v2)
 
     @istest
     def content_ctags_missing(self):
         # given
         tools = self.fetch_tools()
         tool_id = tools['universal-ctags']['id']
 
         cont2 = self.cont2
         self.storage.content_add([cont2])
 
         ctags = [
             {
                 'id': self.cont2['sha1'],
                 'indexer_configuration_id': tool_id,
             },
             {
                 'id': self.missing_cont['sha1'],
                 'indexer_configuration_id': tool_id,
             }
         ]
 
         # when
         actual_missing = self.storage.content_ctags_missing(ctags)
 
         # then
         self.assertEqual(list(actual_missing), [
             self.cont2['sha1'],
             self.missing_cont['sha1']
         ])
 
         # given
         self.storage.content_ctags_add([
             {
                 'id': self.cont2['sha1'],
                 'indexer_configuration_id': tool_id,
                 'ctags': [{
                     'name': 'done',
                     'kind': 'variable',
                     'line': 119,
                     'lang': 'OCaml',
                 }]
             },
         ])
 
         # when
         actual_missing = self.storage.content_ctags_missing(ctags)
 
         # then
         self.assertEqual(list(actual_missing), [self.missing_cont['sha1']])
 
     @istest
     def content_ctags_get(self):
         # given
         tools = self.fetch_tools()
         tool_id = tools['universal-ctags']['id']
 
         cont2 = self.cont2
         self.storage.content_add([cont2])
 
         ctags = [self.cont2['sha1'], self.missing_cont['sha1']]
 
         ctag1 = {
             'id': self.cont2['sha1'],
             'indexer_configuration_id': tool_id,
             'ctags': [
                 {
                     'name': 'done',
                     'kind': 'variable',
                     'line': 100,
                     'lang': 'Python',
                 },
                 {
                     'name': 'main',
                     'kind': 'function',
                     'line': 119,
                     'lang': 'Python',
                 }]
         }
 
         # when
         self.storage.content_ctags_add([ctag1])
 
         # then
         actual_ctags = list(self.storage.content_ctags_get(ctags))
 
         # then
 
         expected_ctags = [
             {
                 'id': self.cont2['sha1'],
                 'tool': tools['universal-ctags'],
                 'name': 'done',
                 'kind': 'variable',
                 'line': 100,
                 'lang': 'Python',
             },
             {
                 'id': self.cont2['sha1'],
                 'tool': tools['universal-ctags'],
                 'name': 'main',
                 'kind': 'function',
                 'line': 119,
                 'lang': 'Python',
             }
         ]
 
         self.assertEqual(actual_ctags, expected_ctags)
 
     @istest
     def content_ctags_search(self):
         # 1. given
         tools = self.fetch_tools()
         tool = tools['universal-ctags']
         tool_id = tool['id']
 
         cont = self.cont
         cont2 = self.cont2
         self.storage.content_add([cont, cont2])
 
         ctag1 = {
             'id': cont['sha1'],
             'indexer_configuration_id': tool_id,
             'ctags': [
                 {
                     'name': 'hello',
                     'kind': 'function',
                     'line': 133,
                     'lang': 'Python',
                 },
                 {
                     'name': 'counter',
                     'kind': 'variable',
                     'line': 119,
                     'lang': 'Python',
                 },
             ]
         }
 
         ctag2 = {
             'id': cont2['sha1'],
             'indexer_configuration_id': tool_id,
             'ctags': [
                 {
                     'name': 'hello',
                     'kind': 'variable',
                     'line': 100,
                     'lang': 'C',
                 },
             ]
         }
 
         self.storage.content_ctags_add([ctag1, ctag2])
 
         # 1. when
         actual_ctags = list(self.storage.content_ctags_search('hello',
                                                               limit=1))
 
         # 1. then
         self.assertEqual(actual_ctags, [
             {
                 'id': ctag1['id'],
                 'tool': tool,
                 'name': 'hello',
                 'kind': 'function',
                 'line': 133,
                 'lang': 'Python',
             }
         ])
 
         # 2. when
         actual_ctags = list(self.storage.content_ctags_search(
             'hello',
             limit=1,
             last_sha1=ctag1['id']))
 
         # 2. then
         self.assertEqual(actual_ctags, [
             {
                 'id': ctag2['id'],
                 'tool': tool,
                 'name': 'hello',
                 'kind': 'variable',
                 'line': 100,
                 'lang': 'C',
             }
         ])
 
         # 3. when
         actual_ctags = list(self.storage.content_ctags_search('hello'))
 
         # 3. then
         self.assertEqual(actual_ctags, [
             {
                 'id': ctag1['id'],
                 'tool': tool,
                 'name': 'hello',
                 'kind': 'function',
                 'line': 133,
                 'lang': 'Python',
             },
             {
                 'id': ctag2['id'],
                 'tool': tool,
                 'name': 'hello',
                 'kind': 'variable',
                 'line': 100,
                 'lang': 'C',
             },
         ])
 
         # 4. when
         actual_ctags = list(self.storage.content_ctags_search('counter'))
 
         # then
         self.assertEqual(actual_ctags, [{
             'id': ctag1['id'],
             'tool': tool,
             'name': 'counter',
             'kind': 'variable',
             'line': 119,
             'lang': 'Python',
         }])
 
     @istest
     def content_ctags_search_no_result(self):
         actual_ctags = list(self.storage.content_ctags_search('counter'))
 
         self.assertEquals(actual_ctags, [])
 
     @istest
     def content_ctags_add__add_new_ctags_added(self):
         # given
         tools = self.fetch_tools()
         tool = tools['universal-ctags']
         tool_id = tool['id']
         cont2 = self.cont2
         self.storage.content_add([cont2])
 
         ctag_v1 = {
             'id': self.cont2['sha1'],
             'indexer_configuration_id': tool_id,
             'ctags': [{
                 'name': 'done',
                 'kind': 'variable',
                 'line': 100,
                 'lang': 'Scheme',
             }]
         }
 
         # given
         self.storage.content_ctags_add([ctag_v1])
         self.storage.content_ctags_add([ctag_v1])  # conflict does nothing
 
         # when
         actual_ctags = list(self.storage.content_ctags_get(
             [self.cont2['sha1']]))
 
         # then
         expected_ctags = [{
             'id': self.cont2['sha1'],
             'name': 'done',
             'kind': 'variable',
             'line': 100,
             'lang': 'Scheme',
             'tool': tool,
         }]
 
         self.assertEqual(actual_ctags, expected_ctags)
 
         # given
         ctag_v2 = ctag_v1.copy()
         ctag_v2.update({
             'ctags': [
                 {
                     'name': 'defn',
                     'kind': 'function',
                     'line': 120,
                     'lang': 'Scheme',
                 }
             ]
         })
 
         self.storage.content_ctags_add([ctag_v2])
 
         expected_ctags = [
             {
                 'id': self.cont2['sha1'],
                 'name': 'done',
                 'kind': 'variable',
                 'line': 100,
                 'lang': 'Scheme',
                 'tool': tool,
             }, {
                 'id': self.cont2['sha1'],
                 'name': 'defn',
                 'kind': 'function',
                 'line': 120,
                 'lang': 'Scheme',
                 'tool': tool,
             }
         ]
 
         actual_ctags = list(self.storage.content_ctags_get(
             [self.cont2['sha1']]))
 
         self.assertEqual(actual_ctags, expected_ctags)
 
     @istest
     def content_ctags_add__update_in_place(self):
         # given
         tools = self.fetch_tools()
         tool = tools['universal-ctags']
         tool_id = tool['id']
 
         cont2 = self.cont2
         self.storage.content_add([cont2])
 
         ctag_v1 = {
             'id': self.cont2['sha1'],
             'indexer_configuration_id': tool_id,
             'ctags': [{
                 'name': 'done',
                 'kind': 'variable',
                 'line': 100,
                 'lang': 'Scheme',
             }]
         }
 
         # given
         self.storage.content_ctags_add([ctag_v1])
 
         # when
         actual_ctags = list(self.storage.content_ctags_get(
             [self.cont2['sha1']]))
 
         # then
         expected_ctags = [
             {
                 'id': self.cont2['sha1'],
                 'name': 'done',
                 'kind': 'variable',
                 'line': 100,
                 'lang': 'Scheme',
                 'tool': tool
             }
         ]
         self.assertEqual(actual_ctags, expected_ctags)
 
         # given
         ctag_v2 = ctag_v1.copy()
         ctag_v2.update({
             'ctags': [
                 {
                     'name': 'done',
                     'kind': 'variable',
                     'line': 100,
                     'lang': 'Scheme',
                 },
                 {
                     'name': 'defn',
                     'kind': 'function',
                     'line': 120,
                     'lang': 'Scheme',
                 }
             ]
         })
 
         self.storage.content_ctags_add([ctag_v2], conflict_update=True)
 
         actual_ctags = list(self.storage.content_ctags_get(
             [self.cont2['sha1']]))
 
         # ctag did change as the v2 was used to overwrite v1
         expected_ctags = [
             {
                 'id': self.cont2['sha1'],
                 'name': 'done',
                 'kind': 'variable',
                 'line': 100,
                 'lang': 'Scheme',
                 'tool': tool,
             },
             {
                 'id': self.cont2['sha1'],
                 'name': 'defn',
                 'kind': 'function',
                 'line': 120,
                 'lang': 'Scheme',
                 'tool': tool,
             }
         ]
         self.assertEqual(actual_ctags, expected_ctags)
 
     @istest
     def content_fossology_license_get(self):
         # given
         tools = self.fetch_tools()
         tool = tools['nomos']
         tool_id = tool['id']
 
         cont = self.cont
         self.storage.content_add([cont])
 
         license1 = {
             'id': cont['sha1'],
             'licenses': ['GPL-2.0+'],
             'indexer_configuration_id': tool_id,
         }
 
         # when
         self.storage.content_fossology_license_add([license1])
 
         # then
         actual_licenses = list(self.storage.content_fossology_license_get(
             [cont['sha1'], self.missing_cont['sha1']]))
 
         expected_license = {
             'id': cont['sha1'],
             'licenses': ['GPL-2.0+'],
             'tool': tool,
         }
 
         # then
         self.assertEqual(actual_licenses, [expected_license])
 
     @istest
     def content_fossology_license_add__new_license_added(self):
         # given
         tools = self.fetch_tools()
         tool = tools['nomos']
         tool_id = tool['id']
 
         cont = self.cont
         self.storage.content_add([cont])
 
         license_v1 = {
             'id': cont['sha1'],
             'licenses': ['Apache-2.0'],
             'indexer_configuration_id': tool_id,
         }
 
         # given
         self.storage.content_fossology_license_add([license_v1])
         # conflict does nothing
         self.storage.content_fossology_license_add([license_v1])
 
         # when
         actual_licenses = list(self.storage.content_fossology_license_get(
             [cont['sha1']]))
 
         # then
         expected_license = {
             'id': cont['sha1'],
             'licenses': ['Apache-2.0'],
             'tool': tool,
         }
         self.assertEqual(actual_licenses, [expected_license])
 
         # given
         license_v2 = license_v1.copy()
         license_v2.update({
             'licenses': ['BSD-2-Clause'],
         })
 
         self.storage.content_fossology_license_add([license_v2])
 
         actual_licenses = list(self.storage.content_fossology_license_get(
             [cont['sha1']]))
 
         expected_license.update({
             'licenses': ['Apache-2.0', 'BSD-2-Clause'],
         })
 
         # license did not change as the v2 was dropped.
         self.assertEqual(actual_licenses, [expected_license])
 
     @istest
     def content_fossology_license_add__update_in_place_duplicate(self):
         # given
         tools = self.fetch_tools()
         tool = tools['nomos']
         tool_id = tool['id']
 
         cont = self.cont
         self.storage.content_add([cont])
 
         license_v1 = {
             'id': cont['sha1'],
             'licenses': ['CECILL'],
             'indexer_configuration_id': tool_id,
         }
 
         # given
         self.storage.content_fossology_license_add([license_v1])
         # conflict does nothing
         self.storage.content_fossology_license_add([license_v1])
 
         # when
         actual_licenses = list(self.storage.content_fossology_license_get(
             [cont['sha1']]))
 
         # then
         expected_license = {
             'id': cont['sha1'],
             'licenses': ['CECILL'],
             'tool': tool,
         }
         self.assertEqual(actual_licenses, [expected_license])
 
         # given
         license_v2 = license_v1.copy()
         license_v2.update({
             'licenses': ['CECILL-2.0']
         })
 
         self.storage.content_fossology_license_add([license_v2],
                                                    conflict_update=True)
 
         actual_licenses = list(self.storage.content_fossology_license_get(
             [cont['sha1']]))
 
         # license did change as the v2 was used to overwrite v1
         expected_license.update({
             'licenses': ['CECILL-2.0']
         })
         self.assertEqual(actual_licenses, [expected_license])
 
     @istest
     def content_metadata_missing(self):
         # given
         tools = self.fetch_tools()
         tool_id = tools['swh-metadata-translator']['id']
 
         cont2 = self.cont2
         self.storage.content_add([cont2])
 
         metadatas = [
             {
                 'id': self.cont2['sha1'],
                 'indexer_configuration_id': tool_id,
             },
             {
                 'id': self.missing_cont['sha1'],
                 'indexer_configuration_id': tool_id,
             }
         ]
 
         # when
         actual_missing = list(self.storage.content_metadata_missing(metadatas))
 
         # then
         self.assertEqual(list(actual_missing), [
             self.cont2['sha1'],
             self.missing_cont['sha1'],
         ])
 
         # given
         self.storage.content_metadata_add([{
             'id': self.cont2['sha1'],
             'translated_metadata': {
                 'other': {},
                 'codeRepository': {
                     'type': 'git',
                     'url': 'https://github.com/moranegg/metadata_test'
                 },
                 'description': 'Simple package.json test for indexer',
                 'name': 'test_metadata',
                 'version': '0.0.1'
             },
             'indexer_configuration_id': tool_id
         }])
 
         # when
         actual_missing = list(self.storage.content_metadata_missing(metadatas))
 
         # then
         self.assertEqual(actual_missing, [self.missing_cont['sha1']])
 
     @istest
     def content_metadata_get(self):
         # given
         tools = self.fetch_tools()
         tool_id = tools['swh-metadata-translator']['id']
         cont2 = self.cont2
         self.storage.content_add([cont2])
 
         metadata1 = {
             'id': self.cont2['sha1'],
             'translated_metadata': {
                 'other': {},
                 'codeRepository': {
                     'type': 'git',
                     'url': 'https://github.com/moranegg/metadata_test'
                 },
                 'description': 'Simple package.json test for indexer',
                 'name': 'test_metadata',
                 'version': '0.0.1'
             },
             'indexer_configuration_id': tool_id,
         }
 
         # when
         self.storage.content_metadata_add([metadata1])
 
         # then
         actual_metadatas = list(self.storage.content_metadata_get(
             [self.cont2['sha1'], self.missing_cont['sha1']]))
 
         expected_metadatas = [{
             'id': self.cont2['sha1'],
             'translated_metadata': {
                 'other': {},
                 'codeRepository': {
                     'type': 'git',
                     'url': 'https://github.com/moranegg/metadata_test'
                 },
                 'description': 'Simple package.json test for indexer',
                 'name': 'test_metadata',
                 'version': '0.0.1'
             },
             'tool': tools['swh-metadata-translator']
         }]
 
         self.assertEqual(actual_metadatas, expected_metadatas)
 
     @istest
     def content_metadata_add_drop_duplicate(self):
         # given
         tools = self.fetch_tools()
         tool_id = tools['swh-metadata-translator']['id']
         cont2 = self.cont2
         self.storage.content_add([cont2])
 
         metadata_v1 = {
             'id': self.cont2['sha1'],
             'translated_metadata': {
                 'other': {},
                 'name': 'test_metadata',
                 'version': '0.0.1'
             },
             'indexer_configuration_id': tool_id,
         }
 
         # given
         self.storage.content_metadata_add([metadata_v1])
 
         # when
         actual_metadatas = list(self.storage.content_metadata_get(
             [self.cont2['sha1']]))
 
         expected_metadatas_v1 = [{
             'id': self.cont2['sha1'],
             'translated_metadata': {
                 'other': {},
                 'name': 'test_metadata',
                 'version': '0.0.1'
             },
             'tool': tools['swh-metadata-translator']
         }]
 
         self.assertEqual(actual_metadatas, expected_metadatas_v1)
 
         # given
         metadata_v2 = metadata_v1.copy()
         metadata_v2.update({
             'translated_metadata': {
                 'other': {},
                 'name': 'test_drop_duplicated_metadata',
                 'version': '0.0.1'
             },
         })
 
         self.storage.content_metadata_add([metadata_v2])
 
         # then
         actual_metadatas = list(self.storage.content_metadata_get(
             [self.cont2['sha1']]))
 
         # metadata did not change as the v2 was dropped.
         self.assertEqual(actual_metadatas, expected_metadatas_v1)
 
     @istest
     def content_metadata_add_update_in_place_duplicate(self):
         # given
         tools = self.fetch_tools()
         tool_id = tools['swh-metadata-translator']['id']
         cont2 = self.cont2
         self.storage.content_add([cont2])
 
         metadata_v1 = {
             'id': self.cont2['sha1'],
             'translated_metadata': {
                 'other': {},
                 'name': 'test_metadata',
                 'version': '0.0.1'
             },
             'indexer_configuration_id': tool_id,
         }
 
         # given
         self.storage.content_metadata_add([metadata_v1])
 
         # when
         actual_metadatas = list(self.storage.content_metadata_get(
             [self.cont2['sha1']]))
 
         # then
         expected_metadatas_v1 = [{
             'id': self.cont2['sha1'],
             'translated_metadata': {
                 'other': {},
                 'name': 'test_metadata',
                 'version': '0.0.1'
             },
             'tool': tools['swh-metadata-translator']
         }]
         self.assertEqual(actual_metadatas, expected_metadatas_v1)
 
         # given
         metadata_v2 = metadata_v1.copy()
         metadata_v2.update({
             'translated_metadata': {
                 'other': {},
                 'name': 'test_update_duplicated_metadata',
                 'version': '0.0.1'
             },
         })
         self.storage.content_metadata_add([metadata_v2], conflict_update=True)
 
         actual_metadatas = list(self.storage.content_metadata_get(
             [self.cont2['sha1']]))
 
         # language did not change as the v2 was dropped.
         expected_metadatas_v2 = [{
             'id': self.cont2['sha1'],
             'translated_metadata': {
                 'other': {},
                 'name': 'test_update_duplicated_metadata',
                 'version': '0.0.1'
             },
             'tool': tools['swh-metadata-translator']
         }]
 
         # metadata did change as the v2 was used to overwrite v1
         self.assertEqual(actual_metadatas, expected_metadatas_v2)
 
     @istest
     def revision_metadata_missing(self):
         # given
         tools = self.fetch_tools()
         tool_id = tools['swh-metadata-detector']['id']
 
         rev = self.revision
         missing_rev = self.revision2
         self.storage.revision_add([rev])
 
         metadatas = [
             {
                 'id': rev['id'],
                 'indexer_configuration_id': tool_id,
             },
             {
                 'id': missing_rev['id'],
                 'indexer_configuration_id': tool_id,
             }
         ]
 
         # when
         actual_missing = list(self.storage.revision_metadata_missing(
                               metadatas))
 
         # then
         self.assertEqual(list(actual_missing), [
             rev['id'],
             missing_rev['id'],
         ])
 
         # given
         self.storage.revision_metadata_add([{
             'id': rev['id'],
             'translated_metadata': {
                 'developmentStatus': None,
                 'version': None,
                 'operatingSystem': None,
                 'description': None,
                 'keywords': None,
                 'issueTracker': None,
                 'name': None,
                 'author': None,
                 'relatedLink': None,
                 'url': None,
                 'type': None,
                 'license': None,
                 'maintainer': None,
                 'email': None,
                 'softwareRequirements': None,
                 'identifier': None
             },
             'indexer_configuration_id': tool_id
         }])
 
         # when
         actual_missing = list(self.storage.revision_metadata_missing(
                               metadatas))
 
         # then
         self.assertEqual(actual_missing, [missing_rev['id']])
 
     @istest
     def revision_metadata_get(self):
         # given
         tools = self.fetch_tools()
         tool_id = tools['swh-metadata-detector']['id']
         rev = self.revision2
         self.storage.revision_add([rev])
 
         metadata_rev = {
             'id': rev['id'],
             'translated_metadata': {
                 'developmentStatus': None,
                 'version': None,
                 'operatingSystem': None,
                 'description': None,
                 'keywords': None,
                 'issueTracker': None,
                 'name': None,
                 'author': None,
                 'relatedLink': None,
                 'url': None,
                 'type': None,
                 'license': None,
                 'maintainer': None,
                 'email': None,
                 'softwareRequirements': None,
                 'identifier': None
             },
             'indexer_configuration_id': tool_id
         }
 
         # when
         self.storage.revision_metadata_add([metadata_rev])
 
         # then
         actual_metadatas = list(self.storage.revision_metadata_get(
             [self.revision2['id'], self.revision['id']]))
 
         expected_metadatas = [{
             'id': rev['id'],
             'translated_metadata': metadata_rev['translated_metadata'],
             'tool': tools['swh-metadata-detector']
         }]
 
         self.assertEqual(actual_metadatas, expected_metadatas)
 
     @istest
     def revision_metadata_add_drop_duplicate(self):
         # given
         tools = self.fetch_tools()
         tool_id = tools['swh-metadata-detector']['id']
         revision = self.revision
         self.storage.revision_add([revision])
 
         metadata_v1 = {
             'id': self.revision['id'],
             'translated_metadata':  {
                 'developmentStatus': None,
                 'version': None,
                 'operatingSystem': None,
                 'description': None,
                 'keywords': None,
                 'issueTracker': None,
                 'name': None,
                 'author': None,
                 'relatedLink': None,
                 'url': None,
                 'type': None,
                 'license': None,
                 'maintainer': None,
                 'email': None,
                 'softwareRequirements': None,
                 'identifier': None
             },
             'indexer_configuration_id': tool_id,
         }
 
         # given
         self.storage.revision_metadata_add([metadata_v1])
 
         # when
         actual_metadatas = list(self.storage.revision_metadata_get(
             [self.revision['id']]))
 
         expected_metadatas_v1 = [{
             'id': self.revision['id'],
             'translated_metadata':  metadata_v1['translated_metadata'],
             'tool': tools['swh-metadata-detector']
         }]
 
         self.assertEqual(actual_metadatas, expected_metadatas_v1)
 
         # given
         metadata_v2 = metadata_v1.copy()
         metadata_v2.update({
             'translated_metadata':  {
                 'name': 'test_metadata',
                 'author': 'MG',
             },
         })
 
         self.storage.revision_metadata_add([metadata_v2])
 
         # then
         actual_metadatas = list(self.storage.revision_metadata_get(
             [self.revision['id']]))
 
         # metadata did not change as the v2 was dropped.
         self.assertEqual(actual_metadatas, expected_metadatas_v1)
 
     @istest
     def revision_metadata_add_update_in_place_duplicate(self):
         # given
         tools = self.fetch_tools()
         tool_id = tools['swh-metadata-detector']['id']
         revision = self.revision2
         self.storage.revision_add([revision])
 
         metadata_v1 = {
             'id': self.revision2['id'],
             'translated_metadata': {
                 'developmentStatus': None,
                 'version': None,
                 'operatingSystem': None,
                 'description': None,
                 'keywords': None,
                 'issueTracker': None,
                 'name': None,
                 'author': None,
                 'relatedLink': None,
                 'url': None,
                 'type': None,
                 'license': None,
                 'maintainer': None,
                 'email': None,
                 'softwareRequirements': None,
                 'identifier': None
             },
             'indexer_configuration_id': tool_id,
         }
 
         # given
         self.storage.revision_metadata_add([metadata_v1])
 
         # when
         actual_metadatas = list(self.storage.revision_metadata_get(
             [self.revision2['id']]))
 
         # then
         expected_metadatas_v1 = [{
             'id': self.revision2['id'],
             'translated_metadata':  metadata_v1['translated_metadata'],
             'tool': tools['swh-metadata-detector']
         }]
         self.assertEqual(actual_metadatas, expected_metadatas_v1)
 
         # given
         metadata_v2 = metadata_v1.copy()
         metadata_v2.update({
             'translated_metadata':  {
                 'name': 'test_update_duplicated_metadata',
                 'author': 'MG'
             },
         })
         self.storage.revision_metadata_add([metadata_v2], conflict_update=True)
 
         actual_metadatas = list(self.storage.revision_metadata_get(
             [self.revision2['id']]))
 
         # language did not change as the v2 was dropped.
         expected_metadatas_v2 = [{
             'id': self.revision2['id'],
             'translated_metadata': metadata_v2['translated_metadata'],
             'tool': tools['swh-metadata-detector']
         }]
 
         # metadata did change as the v2 was used to overwrite v1
         self.assertEqual(actual_metadatas, expected_metadatas_v2)
 
     @istest
     def indexer_configuration_get_missing(self):
         tool = {
             'tool_name': 'unknown-tool',
             'tool_version': '3.1.0rc2-31-ga2cbb8c',
             'tool_configuration': {"command_line": "nomossa <filepath>"},
         }
 
         actual_tool = self.storage.indexer_configuration_get(tool)
 
         self.assertIsNone(actual_tool)
 
     @istest
     def indexer_configuration_get(self):
         tool = {
             'tool_name': 'nomos',
             'tool_version': '3.1.0rc2-31-ga2cbb8c',
             'tool_configuration': {"command_line": "nomossa <filepath>"},
         }
 
         actual_tool = self.storage.indexer_configuration_get(tool)
 
         expected_tool = tool.copy()
         expected_tool['id'] = 1
 
         self.assertEqual(expected_tool, actual_tool)
 
     @istest
     def indexer_configuration_metadata_get_missing_context(self):
         tool = {
             'tool_name': 'swh-metadata-translator',
             'tool_version': '0.0.1',
             'tool_configuration': {"context": "unknown-context"},
         }
 
         actual_tool = self.storage.indexer_configuration_get(tool)
 
         self.assertIsNone(actual_tool)
 
     @istest
     def indexer_configuration_metadata_get(self):
         tool = {
             'tool_name': 'swh-metadata-translator',
             'tool_version': '0.0.1',
             'tool_configuration': {"type": "local", "context": "npm"},
         }
 
         actual_tool = self.storage.indexer_configuration_get(tool)
 
         expected_tool = tool.copy()
         expected_tool['id'] = actual_tool['id']
 
         self.assertEqual(expected_tool, actual_tool)
 
 
 class TestLocalStorage(CommonTestStorage, unittest.TestCase):
     """Test the local storage"""
 
     # Can only be tested with local storage as you can't mock
     # datetimes for the remote server
     @istest
     def 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)
 
     # The remote API doesn't expose _person_add
     @istest
     def person_get(self):
         # given
         person0 = {
             'fullname': b'bob <alice@bob>',
             'name': b'bob',
             'email': b'alice@bob',
         }
         id0 = self.storage._person_add(person0)
 
         person1 = {
             'fullname': b'tony <tony@bob>',
             'name': b'tony',
             'email': b'tony@bob',
         }
         id1 = self.storage._person_add(person1)
 
         # when
         actual_persons = self.storage.person_get([id0, id1])
 
         # given (person injection through release for example)
         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'],
                 },
             ])
 
 
 class AlteringSchemaTest(BaseTestStorage, 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.
 
     """
     @istest
     def content_update(self):
         cont = copy.deepcopy(self.cont)
 
         self.storage.content_add([cont])
         # alter the sha1_git for example
         cont['sha1_git'] = hash_to_bytes(
             '3a60a5275d0333bf13468e8b3dcab90f4046e654')
 
         self.storage.content_update([cont], keys=['sha1_git'])
 
         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'))
 
     @istest
     def content_update_with_new_cols(self):
         self.cursor.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'])
 
         self.cursor.execute(
             'SELECT sha1, sha1_git, sha256, length, status, test, test2'
             ' 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], datum[5], datum[6]),
             (cont['sha1'], cont['sha1_git'], cont['sha256'],
              cont['length'], 'visible', cont['test'], cont['test2']))
 
         self.cursor.execute("""alter table content drop column test,
                                                    drop column test2""")