diff --git a/sql/swh-schema.sql b/sql/swh-schema.sql
index e7360796..f05c73a8 100644
--- a/sql/swh-schema.sql
+++ b/sql/swh-schema.sql
@@ -1,652 +1,652 @@
 ---
 --- 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(97, 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);
 
 -- 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 primary key,
   sha1_git  sha1_git not null,
   sha256    sha256 not null,
   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
 );
 
 create unique index on content(sha1_git);
 create unique index on content(sha256);
 create index on content(ctime);  -- TODO use a BRIN index here (postgres >= 9.5)
 create index on content(object_id);
 
 -- Asynchronous notification of new content insertions
 create function notify_new_content()
   returns trigger
   language plpgsql
 as $$
   begin
     perform pg_notify('new_content', encode(new.sha1, 'hex'));
     return null;
   end;
 $$;
 
 create trigger notify_new_content
   after insert on content
   for each row
   execute procedure notify_new_content();
 
 
 -- 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 primary key,
   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
 );
 
 create index on entity_history(uuid);
 create index on entity_history(name);
 
 -- 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 primary key,
   parent           uuid references entity(uuid) deferrable initially deferred,
   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 references entity_history(id) -- last listing id
 );
 
 create index on entity(name);
 create index on entity using gin(lister_metadata jsonb_path_ops);
 
 -- Register the equivalence between two entities. Allows sideways
 -- navigation in the entity table
 create table entity_equivalence
 (
   entity1 uuid references entity(uuid),
   entity2 uuid references entity(uuid),
   primary key (entity1, entity2),
   constraint order_entities check (entity1 < entity2)
 );
 
 -- Register a lister for a specific entity.
 create table listable_entity
 (
   uuid         uuid references entity(uuid) primary key,
   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 primary key,
   entity    uuid references listable_entity(uuid),
   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
 );
 
 
 -- 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 primary key,
   type     text, -- TODO use an enum here (?)
   url      text not null,
   lister   uuid references listable_entity(uuid),
   project  uuid references entity(uuid)
 );
 
 create index on origin(type, url);
 
 -- Asynchronous notification of new origin insertions
 create function notify_new_origin()
   returns trigger
   language plpgsql
 as $$
   begin
     perform pg_notify('new_origin', new.id::text);
     return null;
   end;
 $$;
 
 create trigger notify_new_origin
   after insert on origin
   for each row
   execute procedure notify_new_origin();
 
 -- 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,
   length    bigint not null,
   ctime     timestamptz not null default now(),
   status    content_status not null default 'absent',
   reason    text not null,
   origin    bigint references origin(id),
   object_id bigserial,
   unique (sha1, sha1_git, sha256)
 );
 
 -- Those indexes support multiple NULL values.
 create unique index on skipped_content(sha1);
 create unique index on skipped_content(sha1_git);
 create unique index on skipped_content(sha256);
 create index on skipped_content(object_id);
 
 -- Asynchronous notification of new skipped content insertions
 create function notify_new_skipped_content()
   returns trigger
   language plpgsql
 as $$
   begin
   perform pg_notify('new_skipped_content', json_build_object(
       'sha1', encode(new.sha1, 'hex'),
       'sha1_git', encode(new.sha1_git, 'hex'),
       'sha256', encode(new.sha256, 'hex')
     )::text);
     return null;
   end;
 $$;
 
 create trigger notify_new_skipped_content
   after insert on skipped_content
   for each row
   execute procedure notify_new_skipped_content();
 
 
 -- 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 primary key,
   origin    bigint references origin(id),
   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 primary key,
   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
 );
 
 create index on directory using gin (dir_entries);
 create index on directory using gin (file_entries);
 create index on directory using gin (rev_entries);
 create index on directory(object_id);
 
 -- Asynchronous notification of new directory insertions
 create function notify_new_directory()
   returns trigger
   language plpgsql
 as $$
   begin
     perform pg_notify('new_directory', encode(new.id, 'hex'));
     return null;
   end;
 $$;
 
 create trigger notify_new_directory
   after insert on directory
   for each row
   execute procedure notify_new_directory();
 
 
 -- A directory entry pointing to a sub-directory.
 create table directory_entry_dir
 (
   id      bigserial primary key,
   target  sha1_git,   -- id of target directory
   name    unix_path,  -- path name, relative to containing dir
   perms   file_perms  -- unix-like permissions
 );
 
 create unique index on directory_entry_dir(target, name, perms);
 
 -- A directory entry pointing to a file.
 create table directory_entry_file
 (
   id      bigserial primary key,
   target  sha1_git,   -- id of target file
   name    unix_path,  -- path name, relative to containing dir
   perms   file_perms  -- unix-like permissions
 );
 
 create unique index on directory_entry_file(target, name, perms);
 
 -- A directory entry pointing to a revision.
 create table directory_entry_rev
 (
   id      bigserial primary key,
   target  sha1_git,   -- id of target revision
   name    unix_path,  -- path name, relative to containing dir
   perms   file_perms  -- unix-like permissions
 );
 
 create unique index on directory_entry_rev(target, name, perms);
 
 create table person
 (
   id        bigserial primary key,
   fullname  bytea not null, -- freeform specification; what is actually used in the checksums
                             --     will usually be of the form 'name <email>'
   name      bytea,          -- advisory: not null if we managed to parse a name
   email     bytea           -- advisory: not null if we managed to parse an email
 );
 
 create unique index on person(fullname);
 create index on person(name);
 create index on person(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 primary key,
   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 not null,
   directory             sha1_git,  -- file-system tree
   message               bytea,
   author                bigint references person(id),
   committer             bigint references person(id),
   metadata              jsonb, -- extra metadata (tarball checksums, extra commit information, etc...)
   synthetic             boolean not null default false,  -- true if synthetic (cf. swh-loader-tar)
   object_id             bigserial
 );
 
 create index on revision(directory);
 create index on revision(object_id);
 
 -- Asynchronous notification of new revision insertions
 create function notify_new_revision()
   returns trigger
   language plpgsql
 as $$
   begin
     perform pg_notify('new_revision', encode(new.id, 'hex'));
     return null;
   end;
 $$;
 
 create trigger notify_new_revision
   after insert on revision
   for each row
   execute procedure notify_new_revision();
 
 
 -- either this table or the sha1_git[] column on the revision table
 create table revision_history
 (
   id           sha1_git references revision(id),
   parent_id    sha1_git,
   parent_rank  int not null default 0,
     -- parent position in merge commits, 0-based
   primary key (id, parent_rank)
 );
 
 create index on revision_history(parent_id);
 
 -- The timestamps at which Software Heritage has made a visit of the given origin.
 create table origin_visit
 (
   origin    bigint not null references origin(id),
   visit     bigint not null,
   date      timestamptz not null,
   status    origin_visit_status not null,
   metadata  jsonb,
   primary key (origin, visit)
 );
 
 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';
 
 create index on origin_visit(date);
 
 -- Asynchronous notification of new origin visits
 create function notify_new_origin_visit()
   returns trigger
   language plpgsql
 as $$
   begin
     perform pg_notify('new_origin_visit', json_build_object(
       'origin', new.origin,
       'visit', new.visit
     )::text);
     return null;
   end;
 $$;
 
 create trigger notify_new_origin_visit
   after insert on origin_visit
   for each row
   execute procedure notify_new_origin_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 references origin(id) 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
   object_id    bigserial not null,    -- short object identifier
   visits       bigint[] not null,     -- the visits where that occurrence was valid. References
                                       -- origin_visit(visit), where o_h.origin = origin_visit.origin.
   primary key (object_id)
 );
 
 create index on occurrence_history(target, target_type);
 create index on occurrence_history(origin, branch);
 create unique index on occurrence_history(origin, branch, target, target_type);
 create index on occurrence_history(object_id);
 
 -- Materialized view of occurrence_history, storing the *current* value of each
 -- branch, as last seen by SWH.
 create table occurrence
 (
   origin    bigint references origin(id) not null,
   branch    bytea not null,
   target    sha1_git not null,
   target_type object_type not null,
   primary key(origin, branch)
 );
 
 -- 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 primary key,
   target      sha1_git,
   target_type object_type,
   date        timestamptz,
   date_offset smallint,
   date_neg_utc_offset  boolean,
   name        bytea,
   comment     bytea,
   author      bigint references person(id),
   synthetic   boolean not null default false,  -- true if synthetic (cf. swh-loader-tar)
   object_id   bigserial
 );
 
 create index on release(target, target_type);
 create index on release(object_id);
 
 -- Asynchronous notification of new release insertions
 create function notify_new_release()
   returns trigger
   language plpgsql
 as $$
   begin
     perform pg_notify('new_release', encode(new.id, 'hex'));
     return null;
   end;
 $$;
 
 create trigger notify_new_release
   after insert on release
   for each row
   execute procedure notify_new_release();
 
 
 -- 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 primary key references content(sha1_git),
     blacklisted     boolean default false,
     revision_paths  bytea[][]
 );
 
 create table cache_content_revision_processed (
     revision  sha1_git not null primary key references revision(id)
 );
 
 -- 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 references revision(id),
    origin    bigint not null,
    visit     bigint not null,
    primary key (revision, origin, visit),
    foreign key (origin, visit) references origin_visit (origin, visit)
 );
 
 create index on cache_revision_origin(revision);
 
 -- Computing metadata on sha1's contents
 
 create table indexer_configuration (
   id serial primary key 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...';
 
 create unique index on indexer_configuration(tool_name, tool_version);
 
 -- Properties (mimetype, encoding, etc...)
 create table content_mimetype (
   id sha1 references content(sha1) not null,
   mimetype bytea not null,
   encoding bytea not null,
   indexer_configuration_id bigserial references indexer_configuration(id) not null,
   primary key(id, indexer_configuration_id)
 );
 
 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 references content(sha1) not null,
   lang languages not null,
   indexer_configuration_id bigserial references indexer_configuration(id) not null,
   primary key(id, indexer_configuration_id)
 );
 
 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 references content(sha1) not null,
   name text not null,
   kind text not null,
   line bigint not null,
   lang ctags_languages not null,
   indexer_configuration_id bigserial references indexer_configuration(id) 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 index on content_ctags(id);
-create index on content_ctags(name);
-create unique index on content_ctags(id, md5(name), kind, line, lang, indexer_configuration_id);
+create index on content_ctags(hash_sha1(name));
+create unique index on content_ctags(id, hash_sha1(name), kind, line, lang, indexer_configuration_id);
 
 create table fossology_license(
   id smallserial primary key,
   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 unique index on fossology_license(name);
 
 create table content_fossology_license (
   id sha1 references content(sha1) not null,
   license_id smallserial references fossology_license(id) not null,
   indexer_configuration_id bigserial references indexer_configuration(id) not null,
   primary key(id, license_id, indexer_configuration_id)
 );
 
 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';
diff --git a/sql/upgrades/097.sql b/sql/upgrades/097.sql
index 7d3a315a..d124f06d 100644
--- a/sql/upgrades/097.sql
+++ b/sql/upgrades/097.sql
@@ -1,551 +1,568 @@
 -- SWH DB schema upgrade
 -- from_version: 96
 -- to_version: 97
 -- description: Update indexer configuration
 
 insert into dbversion(version, release, description)
       values(97, now(), 'Work In Progress');
 
 ------------------------
 -- Update Schema + data
 ------------------------
 
 update indexer_configuration
 set tool_configuration='{"command_line": "nomossa <filepath>"}'
 where tool_name='nomos' and tool_version='3.1.0rc2-31-ga2cbb8c';
 
 insert into indexer_configuration(tool_name, tool_version, tool_configuration)
 values ('universal-ctags', '~git7859817b', '{"command_line": "ctags --fields=+lnz --sort=no --links=no --output-format=json <filepath>"}');
 
 insert into indexer_configuration(tool_name, tool_version, tool_configuration)
 values ('pygments', '2.0.1+dfsg-1.1+deb8u1', '{"type": "library", "debian-package": "python3-pygments"}');
 
 insert into indexer_configuration(tool_name, tool_version, tool_configuration)
 values ('file', '5.22', '{"command_line": "file --mime <filepath>"}');
 
 -- ctags
 
-alter table content_ctags
-  add column indexer_configuration_id bigserial;
+create table content_ctags_new (
+  id sha1 not null,
+  name text not null,
+  kind text not null,
+  line bigint not null,
+  lang ctags_languages not null,
+  indexer_configuration_id bigserial not null
+);
 
-comment on column content_ctags.indexer_configuration_id is 'Tool used to compute the information';
+comment on table content_ctags_new is 'Ctags information on a raw content';
+comment on column content_ctags_new.id is 'Content identifier';
+comment on column content_ctags_new.name is 'Symbol name';
+comment on column content_ctags_new.kind is 'Symbol kind (function, class, variable, const...)';
+comment on column content_ctags_new.line is 'Symbol line';
+comment on column content_ctags_new.lang is 'Language information for that content';
+comment on column content_ctags_new.indexer_configuration_id is 'Tool used to compute the information';
 
-update content_ctags
-set indexer_configuration_id = (select id
-                                from indexer_configuration
-                                where tool_name='universal-ctags');
+insert into content_ctags_new(id, name, kind, line, lang, indexer_configuration_id)
+select id, name, kind, line, lang, (select id from indexer_configuration where tool_name='universal-ctags' limit 1)
+from content_ctags;
 
-alter table content_ctags
-  alter column indexer_configuration_id set not null;
+alter table content_ctags_new
+add constraint content_ctags_id_idx
+foreign key (id) references content(sha1);
 
-alter table content_ctags
-  add constraint content_ctags_indexer_configuration_id_idx
-  foreign key (indexer_configuration_id) references indexer_configuration(id);
+alter table content_ctags_new
+add constraint content_ctags_indexer_configuration_id_idx
+foreign key (indexer_configuration_id) references indexer_configuration(id);
+
+create index on content_ctags_new(id);
+create unique index on content_ctags_new(id, hash_sha1(name), kind, line, lang, indexer_configuration_id);
+create index on content_ctags_new(hash_sha1(name));
 
-drop index content_ctags_id_md5_kind_line_lang_idx;
-create unique index on content_ctags(id, md5(name), kind, line, lang, indexer_configuration_id);
+alter table content_ctags rename to content_ctags_old;
+alter table content_ctags_new rename to content_ctags;
+drop table content_ctags_old;
 
 -- language
 
 alter table content_language
   add column indexer_configuration_id bigserial;
 
 comment on column content_language.indexer_configuration_id is 'Tool used to compute the information';
 
 update content_language
 set indexer_configuration_id = (select id from indexer_configuration where tool_name='pygments');
 
 alter table content_language
   alter column indexer_configuration_id set not null;
 
 alter table content_language
   add constraint content_language_indexer_configuration_id_idx
   foreign key (indexer_configuration_id) references indexer_configuration(id);
 
 alter table content_language
   drop constraint content_language_pkey;
 
 alter table content_language
   add primary key(id, indexer_configuration_id);
 
 -- mimetype
 
 alter table content_mimetype
   add column indexer_configuration_id bigserial;
 
 comment on column content_mimetype.indexer_configuration_id is 'Tool used to compute the information';
 
 update content_mimetype
 set indexer_configuration_id = (select id from indexer_configuration where tool_name='file');
 
 alter table content_mimetype
   alter column indexer_configuration_id
   set not null;
 
 alter table content_mimetype
   add constraint content_mimetype_indexer_configuration_id_idx
   foreign key (indexer_configuration_id) references indexer_configuration(id);
 
 alter table content_mimetype
   drop constraint content_mimetype_pkey;
 
 alter table content_mimetype
   add primary key(id, indexer_configuration_id);
 
 -- fossology-license
 
 comment on column content_fossology_license.indexer_configuration_id is 'Tool used to compute the information';
 
 alter table content_fossology_license
   alter column indexer_configuration_id
   set not null;
 
 alter table content_fossology_license
   add primary key using index content_fossology_license_id_license_id_indexer_configurati_idx;
 
 ---------------------
 -- Update functions
 ---------------------
 
 -- ctags
 
 -- create a temporary table for content_ctags missing routine
 create or replace function swh_mktemp_content_ctags_missing()
     returns void
     language sql
 as $$
   create temporary table tmp_content_ctags_missing (
     id           sha1,
     tool_name    text,
     tool_version text
   ) on commit drop;
 $$;
 
 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 $$
 begin
     return query
 	(select id::sha1 from tmp_content_ctags_missing as tmp
 	 where not exists
 	     (select 1 from content_ctags as c
               inner join indexer_configuration i
               on (tmp.tool_name = i.tool_name and tmp.tool_version = i.tool_version)
               where c.id = tmp.id limit 1));
     return;
 end
 $$;
 
 -- create a temporary table for content_ctags tmp_content_ctags,
 create or replace function swh_mktemp_content_ctags()
     returns void
     language sql
 as $$
   create temporary table tmp_content_ctags (
     like content_ctags including defaults
   ) on commit drop;
   alter table tmp_content_ctags
     drop column indexer_configuration_id,
     add column tool_name text,
     add column tool_version text;
 $$;
 
 comment on function swh_mktemp_content_ctags() is 'Helper table to add content ctags';
 
 create or replace function swh_content_ctags_get()
     returns setof content_ctags_signature
     language plpgsql
 as $$
 begin
     return query
         select c.id, c.name, c.kind, c.line, c.lang, i.tool_name, i.tool_version
         from tmp_bytea t
         inner join content_ctags c using(id)
         inner join indexer_configuration i on i.id = c.indexer_configuration_id
         order by line;
     return;
 end
 $$;
 
 comment on function swh_content_ctags_get() IS 'List content ctags';
 
 
 -- 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 distinct id from tmp_content_ctags);
     end if;
 
     insert into content_ctags (id, name, kind, line, lang, indexer_configuration_id)
     select id, name, kind, line, lang,
            (select id from indexer_configuration
             where tool_name=tct.tool_name
             and tool_version=tct.tool_version)
     from tmp_content_ctags tct
-        on conflict(id, md5(name), kind, line, lang, indexer_configuration_id)
+        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';
 
 drop type content_ctags_signature cascade;
 create type content_ctags_signature as (
   id sha1,
   name text,
   kind text,
   line bigint,
   lang ctags_languages,
   tool_name text,
   tool_version text
 );
 
 
 -- 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 $$
 begin
     return query
         select c.id, c.name, c.kind, c.line, c.lang, i.tool_name, i.tool_version
         from tmp_bytea t
         inner join content_ctags c using(id)
         inner join indexer_configuration i on i.id = c.indexer_configuration_id
         order by line;
     return;
 end
 $$;
 
 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 $$
     select c.id, name, kind, line, lang, tool_name, tool_version
     from content_ctags c
     inner join indexer_configuration i on i.id = c.indexer_configuration_id
     where hash_sha1(name) = hash_sha1(expression)
     and c.id > last_sha1
     order by id
     limit l;
 $$;
 
 comment on function swh_content_ctags_search(text, integer, sha1) IS 'Equality search through ctags'' symbols';
 
 -- mimetype
 
 -- 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 $$
   create temporary table tmp_content_mimetype_missing (
     id sha1 references content(sha1) not null,
     tool_name text not null,
     tool_version text not null
   ) on commit drop;
 $$;
 
 comment on function swh_mktemp_content_mimetype_missing() IS 'Helper table to filter existing mimetype information';
 
 -- create a temporary table for content_ctags tmp_content_mimetype,
 create or replace function swh_mktemp_content_mimetype()
     returns void
     language sql
 as $$
   create temporary table tmp_content_mimetype (
     like content_mimetype including defaults
   ) on commit drop;
   alter table tmp_content_mimetype
     drop column indexer_configuration_id,
     add column tool_name text,
     add column tool_version text;
 $$;
 
 comment on function swh_mktemp_content_mimetype() is 'Helper table to add content ctags';
 
 create or replace function swh_content_mimetype_missing()
     returns setof sha1
     language plpgsql
 as $$
 begin
     return query
 	(select id::sha1 from tmp_content_mimetype_missing as tmp
 	 where not exists
 	     (select 1 from content_mimetype as c
               inner join indexer_configuration i
               on (tmp.tool_name = i.tool_name and tmp.tool_version = i.tool_version)
               where c.id = tmp.id));
     return;
 end
 $$;
 
 comment on function swh_content_mimetype_missing() is 'Filter existing mimetype information';
 
 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,
                (select id from indexer_configuration
                where tool_name=tcm.tool_name
                and tool_version=tcm.tool_version)
         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,
                (select id from indexer_configuration
                where tool_name=tcm.tool_name
                and tool_version=tcm.tool_version)
          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_name text,
   tool_version text
 );
 
 drop function swh_content_mimetype_get();
 
 create or replace function swh_content_mimetype_get()
     returns setof content_mimetype_signature
     language plpgsql
 as $$
 begin
     return query
         select c.id, mimetype, encoding, tool_name, tool_version
         from tmp_bytea t
         inner join content_mimetype c on c.id=t.id
         inner join indexer_configuration i on c.indexer_configuration_id=i.id;
     return;
 end
 $$;
 
 comment on function swh_content_mimetype_get() IS 'List content''s mimetype';
 
 -- language
 
 -- create a temporary table for content_language tmp_content_language,
 create or replace function swh_mktemp_content_language_missing()
     returns void
     language sql
 as $$
   create temporary table tmp_content_language_missing (
     id sha1,
     lang languages,
     tool_name text,
     tool_version text
   ) on commit drop;
 $$;
 
 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 $$
 begin
     return query
 	select id::sha1 from tmp_content_language_missing as tmp
 	where not exists
 	    (select 1 from content_language as c
             inner join indexer_configuration i
             on (tmp.tool_name = i.tool_name and tmp.tool_version = i.tool_version)
             where c.id = tmp.id);
     return;
 end
 $$;
 
 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,
                (select id from indexer_configuration
                where tool_name=tcl.tool_name
                and tool_version=tcl.tool_version)
     	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,
                (select id from indexer_configuration
                where tool_name=tcl.tool_name
                and tool_version=tcl.tool_version)
     	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 $$
   create temporary table tmp_content_language (
     like content_language including defaults
   ) on commit drop;
   alter table tmp_content_language
     drop column indexer_configuration_id,
     add column tool_name text,
     add column tool_version text;
 $$;
 
 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_name text,
     tool_version text
 );
 
 drop function swh_content_language_get();
 
 -- 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 $$
 begin
     return query
         select c.id, lang, tool_name, tool_version
         from tmp_bytea t
         inner join content_language c on c.id = t.id
         inner join indexer_configuration i on i.id=c.indexer_configuration_id;
     return;
 end
 $$;
 
 comment on function swh_content_language_get() IS 'List content''s language';
 
 -- license
 
 -- create a temporary table for content_fossology_license_missing
 create or replace function swh_mktemp_content_fossology_license_missing()
     returns void
     language sql
 as $$
   create temporary table tmp_content_fossology_license_missing (
     id bytea,
     tool_name text,
     tool_version text
   ) on commit drop;
 $$;
 
 comment on function swh_mktemp_content_fossology_license_missing() is 'Helper table to add content license';
 
 -- check which entries of tmp_content_fossology_license are missing from content_fossology_license
 create or replace function swh_content_fossology_license_missing()
     returns setof sha1
     language plpgsql
 as $$
 begin
     return query
 	(select id::sha1 from tmp_content_fossology_license_missing as tmp
 	 where not exists
 	     (select 1 from content_fossology_license as c
               inner join indexer_configuration i on i.id=c.indexer_configuration_id
               where c.id = tmp.id));
     return;
 end
 $$;
 
 comment on function swh_content_fossology_license_missing() IS 'Filter missing content licenses';
 
 -- 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 $$
   create temporary table tmp_content_fossology_license (
     id           sha1,
     tool_name    text,
     tool_version text,
     license      text
   ) on commit drop;
 $$;
 
 comment on function swh_mktemp_content_fossology_license() is 'Helper table to add content license';
 
 -- create a temporary table for checking licenses' name
 create or replace function swh_mktemp_content_fossology_license_unknown()
     returns void
     language sql
 as $$
   create temporary table tmp_content_fossology_license_unknown (
     name       text not null
   ) on commit drop;
 $$;
 
 comment on function swh_mktemp_content_fossology_license_unknown() is 'Helper table to list unknown licenses';