Files
usenet-indexer/commands/workers/Spots.ts
T
Daan MeijerandClaude Opus 5.5 be8a3d4580 Spotnet import, header backfill, staging and counter grouping, faster search
Spotnet (CONCEPT D29):
- Index free.pt fully and import spots with their descriptions, categories
  and NZBs; a spot renames its release, since Spotnet names are more
  trustworthy than names derived from subjects.
- Find passwords in spot descriptions too, and tell "needs a password we
  have" from "needs a password we don't have".

Content inspection:
- List the contents of 7z (.7z.001) archives, SFV sets, nicovideo uploads
  and other archive-like files; mark yEncBin .bin containers as encrypted.
- Take real names from yEnc headers for randomly named files, and merge
  uploads that were split across posts.

Storage (D31, D32):
- Store segment lists zstd-compressed behind the FileStore accessor.
- group:backfill indexes older headers at low priority and pauses when
  the NVMe or HDD part of the database gets too large.

Grouping (D35, D36):
- Lone header segments wait in staged_segments until a second segment of
  their file arrives, which drops the per-article junk binaries.
- Counter grouping joins random-subject uploads by poster, [i/M] counter,
  part count and day.

Search and maintenance (D33, D34):
- A trigram-indexed search_text column, smaller indexes, estimated stats.
- Passes that clean up nonsense names; weekly index maintenance; GC budgets
  per kind.
- Web UI: grey out stale results while a search runs and cancel superseded
  requests. Count only up to 1,000 matches for the page, which made filter
  clicks take seconds (Newznab keeps the 10,000 cap).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-03 19:59:23 +02:00

64 lines
2.5 KiB
TypeScript

import { BaseCommand, flags } from '@adonisjs/core/ace'
import { CommandOptions } from '@adonisjs/core/types/ace'
import env from '#start/env'
import Shutdown from '#services/Shutdown'
import NntpService from '#services/NntpService'
import SpotService from '#services/SpotService'
const IDLE_MS = 30_000
/** Spots claimed at a time; most of a history backfill is listed in bulk. */
const BATCH = 500
/** Imported spots whose details are read per idle round. */
const DETAILS_BATCH = 50
/**
* Works through queued Spotnet spots (CONCEPT.md D29): verifies each one,
* downloads its compressed NZB (a few KB to a few MB) and imports it.
*/
export default class SpotsWorker extends BaseCommand {
public static commandName = 'worker:spots'
public static description = 'Reads Spotnet spots: verifies them and imports their NZBs.'
public static options: CommandOptions = {
startApp: true,
}
@flags.number({ description: 'Stop after this many spots (default: keep running)' })
declare limit?: number
public async run() {
const concurrency = env.get('SPOT_CONCURRENCY', 4)
this.logger.info(`Spot worker started (concurrency ${concurrency}).`)
const counts: Record<string, number> = {}
let done = 0
try {
while (!Shutdown.requested && (!this.limit || done < this.limit)) {
const batch = await SpotService.claim(Math.min(BATCH, this.limit ? this.limit - done : Infinity))
if (batch.length === 0) {
if (this.limit) break
// Idle: read the details of imported spots that don't have them yet (newest first).
if ((await SpotService.fillDetails(DETAILS_BATCH)) === 0) await Shutdown.sleep(IDLE_MS)
continue
}
// Old, verified spots are listed in bulk; the rest need their header (and maybe NZB) read.
const listable = batch.filter((spot) => SpotService.isListable(spot))
const single = batch.filter((spot) => !SpotService.isListable(spot))
counts.listed = (counts.listed ?? 0) + (await SpotService.list(listable))
let next = 0
await Promise.all(
Array.from({ length: concurrency }, async () => {
while (next < single.length) {
const status = await SpotService.process(single[next++])
counts[status] = (counts[status] ?? 0) + 1
}
})
)
done += batch.length
this.logger.info(`${done} spots: ${Object.entries(counts).map(([k, v]) => `${v} ${k}`).join(', ')}.`)
}
} finally {
await NntpService.shutdown()
}
}
}