Daan MeijerandClaude Opus 5.5
f4ded062df
Inspection lists only the entries whose headers are in the first segment of a first volume. A walk hops from header to header, fetching one segment per entry and volume, in its own queue (one job per collection worker) on NNTP connections inspection isn't waiting for. content:walk-archives queues releases inspected earlier (CONCEPT D40). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
71 lines
2.8 KiB
TypeScript
71 lines
2.8 KiB
TypeScript
import { BaseCommand, args, flags } from '@adonisjs/core/ace'
|
|
import { CommandOptions } from '@adonisjs/core/types/ace'
|
|
import db from '@adonisjs/lucid/services/db'
|
|
import QueueService from '#services/QueueService'
|
|
import NntpService from '#services/NntpService'
|
|
import ArchiveWalkService from '#services/ArchiveWalkService'
|
|
|
|
const BATCH = 5000
|
|
|
|
/**
|
|
* Complete archive listings for releases inspected before archive walks
|
|
* existed (CONCEPT.md D40): queues those whose listing leaves most of the
|
|
* release unaccounted for. worker:collection walks them, one at a time and
|
|
* behind inspection. With release ids, walks those right here instead.
|
|
*/
|
|
export default class ArchiveWalk extends BaseCommand {
|
|
public static commandName = 'content:walk-archives'
|
|
public static description = 'Queues releases with partial archive listings for a (low priority) header walk.'
|
|
|
|
public static options: CommandOptions = {
|
|
startApp: true,
|
|
}
|
|
|
|
@args.spread({ description: 'Release ids to walk now (instead of queueing)', required: false })
|
|
declare releaseIds?: string[]
|
|
|
|
@flags.number({ description: 'Queue at most this many releases' })
|
|
declare limit?: number
|
|
|
|
@flags.boolean({ description: 'Also releases that were walked before' })
|
|
declare again: boolean
|
|
|
|
public async run() {
|
|
try {
|
|
if (this.releaseIds?.length) {
|
|
for (const id of this.releaseIds) {
|
|
this.logger.info(JSON.stringify(await ArchiveWalkService.walk(Number(id))))
|
|
}
|
|
return
|
|
}
|
|
let lastId = 0
|
|
let queued = 0
|
|
while (!this.limit || queued < this.limit) {
|
|
const query = db
|
|
.from('releases as r')
|
|
.where('r.id', '>', lastId)
|
|
.whereNotNull('r.contents')
|
|
.orderBy('r.id')
|
|
.limit(BATCH)
|
|
.select('r.id', 'r.size', 'r.contents_walked_at', db.raw(`(
|
|
SELECT count(*) FROM jsonb_array_elements(r.contents)) AS n`), db.raw(`(
|
|
SELECT coalesce(sum((e->>'size')::bigint), 0) FROM jsonb_array_elements(r.contents) e) AS listed`))
|
|
const rows = await query
|
|
if (rows.length === 0) break
|
|
lastId = Number(rows.at(-1).id)
|
|
const jobs = rows
|
|
.filter((r) => this.again || !r.contents_walked_at)
|
|
.filter((r) => ArchiveWalkService.worthWalking(Number(r.n), Number(r.listed), Number(r.size)))
|
|
.slice(0, this.limit ? this.limit - queued : undefined)
|
|
.map((r) => ({ name: 'walk', data: { releaseId: Number(r.id) }, opts: { jobId: `walk-${r.id}-${Date.now()}` } }))
|
|
if (jobs.length > 0) await QueueService.archiveWalkQueue.addBulk(jobs)
|
|
queued += jobs.length
|
|
}
|
|
this.logger.info(`Queued ${queued} releases for an archive walk.`)
|
|
} finally {
|
|
await QueueService.closeAll()
|
|
await NntpService.shutdown()
|
|
}
|
|
}
|
|
}
|