Daan MeijerandClaude Opus 5.5
2dd5b4cd81
Sets stored in one batch share created_at, so paging on created_at < last skipped ~10k of 61k sets; the timestamp now also stays text so microseconds survive the round trip. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
66 lines
2.9 KiB
TypeScript
66 lines
2.9 KiB
TypeScript
import { BaseCommand, flags } from '@adonisjs/core/ace'
|
|
import type { CommandOptions } from '@adonisjs/core/types/ace'
|
|
import db from '@adonisjs/lucid/services/db'
|
|
import { Par2Merger } from '#services/par2_merger'
|
|
|
|
/**
|
|
* The par2 merger's name pass over sets found before it was built (2026-10-23): every set with its file list, newest
|
|
* first, by set row. --dry-run counts what it would merge and shows examples, merging nothing.
|
|
*/
|
|
export default class ReleasesMergeNames extends BaseCommand {
|
|
static commandName = 'releases:merge-names'
|
|
static description = "Merges releases by their par2 set's file names, for sets found before the name pass; --dry-run shows only"
|
|
static options: CommandOptions = { startApp: true }
|
|
|
|
@flags.number({ description: 'Sets to look at (newest first); all without' })
|
|
declare sets: number
|
|
|
|
@flags.boolean({ description: 'Count and show, merge nothing' })
|
|
declare dryRun: boolean
|
|
|
|
async run() {
|
|
const merger = new Par2Merger()
|
|
// Keyset on (newest created_at, set_id): sets stored in one batch share created_at, and the timestamp stays text
|
|
// so microseconds survive the round trip.
|
|
let before = ['9999-12-31', '']
|
|
let looked = 0
|
|
let merges = 0
|
|
let releases = 0
|
|
const examples: string[] = []
|
|
while (this.sets === undefined || looked < this.sets) {
|
|
const { rows } = await db.rawQuery(
|
|
`SELECT set_id, at::text AS at FROM (
|
|
SELECT s.set_id, max(s.created_at) AS at FROM par2_sets s WHERE EXISTS (SELECT 1 FROM par2_files f WHERE f.set_id = s.set_id)
|
|
GROUP BY s.set_id) x
|
|
WHERE (at, set_id) < (?::timestamptz, ?) ORDER BY at DESC, set_id DESC LIMIT ${this.dryRun ? 50 : 500}`,
|
|
before
|
|
)
|
|
if (rows.length === 0) break
|
|
for (const { set_id: setId } of rows) {
|
|
looked++
|
|
if (this.dryRun) {
|
|
const found = await db.transaction(async (trx) => merger.nameMatches(trx, setId.trim()))
|
|
if (found) {
|
|
merges++
|
|
releases += found.size
|
|
if (examples.length < 15) {
|
|
const { rows: names } = await db.rawQuery(`SELECT id, name, files FROM releases WHERE id = ANY(?) ORDER BY id`, [[...found.keys()]])
|
|
examples.push(names.map((n: any) => `${n.name.slice(0, 50)} [${n.files}]`).join(' + '))
|
|
}
|
|
}
|
|
} else {
|
|
const merged = await merger.mergeByName(setId.trim())
|
|
if (merged > 0) {
|
|
merges++
|
|
releases += merged + 1
|
|
}
|
|
}
|
|
}
|
|
before = [rows.at(-1).at, rows.at(-1).set_id]
|
|
if (this.dryRun || looked % 20_000 < 500) this.logger.info(`${looked} sets looked at: ${releases} releases ${this.dryRun ? 'would merge' : 'merged'} into ${merges}.`)
|
|
}
|
|
this.logger.info(`Done: ${looked} sets looked at, ${releases} releases ${this.dryRun ? 'would merge' : 'merged'} into ${merges}.`)
|
|
for (const e of examples) this.logger.info(` ${e.slice(0, 300)}`)
|
|
}
|
|
}
|