Files
usenet-indexer/commands/workers/File.ts
T

118 lines
4.4 KiB
TypeScript

import { BaseCommand } from '@adonisjs/core/ace'
import { CommandOptions } from '@adonisjs/core/types/ace'
import { Worker } from 'bullmq'
import db from '@adonisjs/lucid/services/db'
import queueConfig from '#config/queue'
import Shutdown from '#services/Shutdown'
import QueueService from '#services/QueueService'
export default class FileWorker extends BaseCommand {
public static commandName = 'worker:file'
public static description = 'Starts a worker that turns completed binaries into files.'
public static options: CommandOptions = {
startApp: true,
}
public async run() {
this.logger.info('Starting file worker...')
const collectionQueue = QueueService.collectionQueue
const worker = new Worker('file-queue', async (job) => {
const { binaryId } = job.data
const binary = await db.from('binaries').where('id', binaryId).first()
if (!binary) {
this.logger.warning(`Binary ${binaryId} no longer exists (garbage collected?).`)
return
}
if (binary.conflicted_at) {
this.logger.warning(`Binary ${binaryId} ("${binary.name}") has conflicting parts, skipping.`)
return
}
const parts = await db
.from('parts')
.where('binary_id', binaryId)
.orderBy('number')
.select('number', 'message_id', 'bytes')
if (parts.length < binary.total_parts) {
throw new Error(`Binary ${binaryId} has ${parts.length}/${binary.total_parts} parts.`)
}
const messageIds = Object.fromEntries(
parts.map((part) => [part.number, { id: part.message_id, size: part.bytes }])
)
// Already known as a file, e.g. added from a posted NZB before its own articles completed.
const existing = await db
.from('files')
.whereRaw(`(message_ids->'1'->>'id') = ?`, [messageIds['1']?.id ?? ''])
.first()
if (existing) {
await db.from('binaries').where('id', binaryId).update({ file_id: existing.id })
await dropCopiedParts(binary)
this.logger.debug(`File "${binary.name}" already exists as ID ${existing.id} (same first segment).`)
return
}
// file_key is unique: a second completion of the same upload inserts nothing.
const knex = db.connection().getWriteClient()
const now = new Date()
const [inserted] = await knex('files')
.insert({
file_key: binary.file_key,
filename: binary.name,
poster: binary.poster,
date: binary.posted_at ? new Date(binary.posted_at).getTime() : now.getTime(),
parts: parts.length,
message_ids: JSON.stringify(messageIds),
groups: JSON.stringify(binary.groups),
release_id: binary.release_id,
real_name: binary.real_name,
size: parts.reduce((sum, part) => sum + Number(part.bytes), 0),
created_at: now,
updated_at: now,
})
.onConflict('file_key')
.ignore()
.returning('id')
const fileId =
inserted?.id ?? (await db.from('files').where('file_key', binary.file_key).first())?.id
await db.from('binaries').where('id', binaryId).update({ file_id: fileId })
await dropCopiedParts(binary)
if (!inserted) {
this.logger.debug(`File "${binary.name}" (${binary.file_key}) already exists as ID ${fileId}.`)
return
}
this.logger.info(`Saved file "${binary.name}" (${parts.length} parts) as ID ${fileId}.`)
await collectionQueue.add('process-collection', { fileId }, { jobId: `file-${fileId}` })
}, { connection: queueConfig.connection })
worker.on('failed', (job, err) => {
this.logger.error(`File job ${job?.id} failed: ${err.message}`)
})
this.logger.info('File worker started and listening for jobs.')
await Shutdown.wait()
this.logger.info('Shutting down: finishing active jobs...')
await worker.close()
await QueueService.closeAll()
}
}
/**
* The file holds every message id now. Binaries identified by their subject
* (no size: header-derived) don't need their parts any more; body-derived
* ones keep them, so articles of an equal-sized next volume are recognised
* as a conflict and split off (CONCEPT.md D20). LOG.md 2026-09-28 (17).
*/
async function dropCopiedParts(binary: { id: number; size: number | null }) {
if (binary.size === null) await db.from('parts').where('binary_id', binary.id).delete()
}