-- #222. DESIGN.md §15, as amended: a language is satisfied by exactly one
-- sidecar. No filename segment distinguishes forced from plain from SDH, so
-- two sidecar rows for one (media file, language) describe two files
-- competing for one name. The schema says so now rather than leaving it to
-- the API's path check.
--
-- Embedded rows are deliberately untouched. They describe tracks inside the
-- video, not files on disk, and several can legitimately coexist for one
-- language — a plain track and a forced one, say. Their key stays
-- `(media_file_id, language, forced, sdh)`.

-- A database that predates the constraint may already hold a duplicate from
-- a manual grab that beat the path check: a fetched `.pt-PT.srt` beside a
-- translated `.pt-PT.mt.srt`, for instance. Resolve rather than fail. Of the
-- rows for one (media file, language): keep a real subtitle over a machine
-- translation, and of two of the same kind the newest.
--
-- The files stay on disk. Deleting a viewer's subtitle during a migration is
-- worse than leaving an orphan, and the manual delete (#218, #223) cleans one
-- up on request.
DELETE FROM subtitle_files
WHERE  path IS NOT NULL
  AND  id NOT IN (
           SELECT id
           FROM   (
               SELECT id,
                      ROW_NUMBER() OVER (
                          PARTITION BY media_file_id, language
                          ORDER BY (origin = 'translated') ASC,
                                   created_at DESC,
                                   id DESC
                      ) AS place
               FROM   subtitle_files
               WHERE  path IS NOT NULL
           )
           WHERE place = 1
       );

CREATE UNIQUE INDEX subtitle_files_one_sidecar
    ON subtitle_files (media_file_id, language)
    WHERE path IS NOT NULL;