#!/usr/bin/env tsx
// On-demand duplicate detection. Runs AFTER build:index + build:stats (it reads
// the cues + statsByPath those populate), so it is deliberately not chained into
// build:data.
//
// Flags:
//   --threshold N      duration cutoff in seconds (default 180)
//   --all-durations    no length filter; enables the containment sweep
//   --blocking S       how candidate pairs are nominated: title | duration |
//                      both. Defaults to `title` corpus-wide and `duration` in
//                      shorts mode. Nomination is never evidence — every pair is
//                      then judged on transcript content — so this trades recall
//                      against runtime, not correctness.
//   --near F           Jaccard near-duplicate threshold (default 0.6)
//   --tolerance N      duration bucketing window in seconds (default 2)
import { getPaths } from "../lib/paths";
import { detectDuplicateShorts } from "../controller/duplicateShorts";
import type { DuplicateBlocking } from "../lib/duplicates";
import { parseFlags } from "./_parseFlags";

const flags = parseFlags(process.argv.slice(2));

const thresholdSeconds =
  flags["all-durations"] === "true"
    ? null
    : flags.threshold !== undefined
      ? Number(flags.threshold)
      : undefined;

const BLOCKING: ReadonlyArray<DuplicateBlocking> = ["title", "duration", "both"];
const blockingFlag = flags.blocking;
if (
  blockingFlag !== undefined &&
  !BLOCKING.includes(blockingFlag as DuplicateBlocking)
) {
  console.error(
    `--blocking must be one of: ${BLOCKING.join(", ")} (got "${blockingFlag}")`,
  );
  process.exit(1);
}

detectDuplicateShorts({
  paths: getPaths(),
  thresholdSeconds,
  blocking: blockingFlag as DuplicateBlocking | undefined,
  nearThreshold: flags.near !== undefined ? Number(flags.near) : undefined,
  durationToleranceSeconds:
    flags.tolerance !== undefined ? Number(flags.tolerance) : undefined,
}).catch((err) => {
  console.error(err);
  process.exit(1);
});