Files
usenet-indexer/config/indexer.ts
T

48 lines
2.1 KiB
TypeScript

import env from '#start/env'
export default {
/** How often `index:scheduler` checks the groups for new articles. */
intervalMs: env.get('INDEX_INTERVAL_MS', 60 * 1000),
/** Articles per fetch job (one XOVER call). */
batchSize: BigInt(env.get('INDEX_BATCH_SIZE', 20_000)),
/** Upper bound on fetch jobs queued per group per tick, so catching up is spread out. */
maxBatchesPerTick: env.get('INDEX_MAX_BATCHES_PER_TICK', 5),
/**
* Where a group that was never indexed starts: this many articles before
* the newest one. The server's low-water mark can be years back.
*/
initialBackfill: BigInt(env.get('INDEX_INITIAL_BACKFILL', 50_000)),
/**
* Obfuscated articles whose message-id matches one of these are not sent
* to the body queue: their uploader spreads every file over many groups,
* so identifying them would take far more bandwidth than there is
* (see LOG.md, 2026-09-28 (9)). Normal-subject articles are unaffected.
*/
skipBodyMessageIds: [
// hex7$hex7$hex7@hex10.hex5, ~60k articles/min over 10+ groups
/^<?[0-9a-f]{7}\$[0-9a-f]{7}\$[0-9a-f]{7}@[0-9a-f]{10}\.[0-9a-f]{5}>?$/,
],
/**
* Obfuscated articles whose message-id matches one of these don't go to
* the body queue. Instead they're recorded per file in `deferred_files`
* (their subject keeps the file name, only the part counter is missing).
* `worker:deferred` later fetches one body per file (CONCEPT.md D28).
*/
deferBodyMessageIds: [
// ngPost: <hex32@ngPost>. Mostly RAR5 with encrypted headers (LOG.md 2026-09-28 (14)).
/^<?[0-9a-f]{32}@ngPost>?$/,
],
/**
* Spotnet header groups (CONCEPT.md D29): their headers are spots, not
* binaries. Add one with `group:add free.pt --backfill 5000`.
*/
spotGroups: ['free.pt'],
/** worker:deferred leaves a file alone until it has had no new articles for this long. */
deferredSettleMs: env.get('DEFERRED_SETTLE_MS', 15 * 60 * 1000),
/** Files of at most this many parts are downloaded completely (small archives, NZBs, par2 index files). */
deferredExpandMaxParts: env.get('DEFERRED_EXPAND_MAX_PARTS', 8),
}