import db from '@adonisjs/lucid/services/db'

/**
 * Twins by content (LOG.md (130)): a probed file's first 16 KiB and size (file_hashes, what the par2 merge and the
 * repeated verdict match) in a catalog release that has a name, readable or found inside. The same film posted
 * under scrambles by other tools gets that name without another fetch. Releases with a junk verdict don't count.
 */
/** Twins read per pair: the hottest pairs have 131k. */
const TWIN_SCAN = 500

export async function twinNames(
  pairs: { hash16k: string; size: number }[],
  trx: { rawQuery: typeof db.rawQuery } = db
): Promise<Map<string, string>> {
  const out = new Map<string, string>()
  if (pairs.length === 0) return out
  // Per pair the first named twin among its lowest TWIN_SCAN release ids. hash16k is typed as the column
  // (char(32)): as text the join cast the column and scanned all of file_hashes, 4 s a call; and with the index
  // the hottest pairs (55 with over 500 twins, up to 131k, all readable) made a call walk every twin, 37 s inside
  // the flush's transaction (LOG.md (138)). One name is all a pair needs.
  const { rows } = await trx.rawQuery(
    `SELECT v.hash16k, v.size, t.name
     FROM jsonb_to_recordset(?::jsonb) AS v(hash16k char(32), size bigint)
     CROSS JOIN LATERAL (
       SELECT coalesce(r.inner_name, r.name) AS name
       FROM (SELECT release_id FROM file_hashes h WHERE h.hash16k = v.hash16k AND h.size = v.size ORDER BY release_id LIMIT ?) h
       JOIN releases r ON r.id = h.release_id AND (r.readable OR r.inner_name IS NOT NULL)
       WHERE NOT EXISTS (SELECT 1 FROM release_verdicts x WHERE x.release_id = r.id)
       ORDER BY r.readable DESC, r.id LIMIT 1) t`,
    [JSON.stringify(pairs), TWIN_SCAN]
  )
  for (const r of rows) out.set(`${r.hash16k}\t${r.size}`, r.name)
  return out
}

export const twinKey = (hash16k: string, size: number) => `${hash16k}\t${size}`