Daan MeijerandClaude Opus 5.5
95f1d427df
Of 5,000 waiting inspection jobs, 3,212 were queued only because their stem looked random, and 2,044 of those were later RAR volumes (xyz.part47.rar, .r00) or par2 recovery volumes (.vol03+04.par2). Their first segment adds nothing: the set is listed from its first volume and named from its index .par2, as for readable names already. Each one cost a ~700 KB download; inspection pulled ~85 MB/s and fell behind the backfill. - isCandidate() rejects later volumes (isLaterVolume) before the random- name rule. - worker:file only queues files that are candidates, so the ~30% that inspection skips anyway no longer take queue slots. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
26 lines
1.0 KiB
TypeScript
26 lines
1.0 KiB
TypeScript
import { sevenZipVolume } from '../sevenzip/index.js'
|
|
|
|
/**
|
|
* Files whose first segment says what an archive holds: named first RAR
|
|
* volumes (.part01.rar, .rar), 7z (.7z, .7z.001) and `.bin`, an extension
|
|
* uploaders use for archive volumes too (sniffed by content).
|
|
*/
|
|
export function isArchiveStart(name: string): boolean {
|
|
if (/\.bin$/i.test(name)) return true
|
|
const volume = sevenZipVolume(name)
|
|
if (volume === 0 || volume === 1) return true
|
|
return /\.part0*1\.rar$/i.test(name) || (/\.rar$/i.test(name) && !/\.part\d+\.rar$/i.test(name))
|
|
}
|
|
|
|
/**
|
|
* A later RAR volume (.part02.rar, .r00) or a par2 recovery volume
|
|
* (.vol03+04.par2): the volume number is readable even under a random stem.
|
|
* The set is listed from its first volume and named from its index .par2,
|
|
* so the first segment of these says nothing new (LOG.md 2026-10-04).
|
|
*/
|
|
export function isLaterVolume(name: string): boolean {
|
|
const part = /\.part(\d+)\.rar$/i.exec(name)
|
|
if (part) return Number(part[1]) > 1
|
|
return /\.r\d{2,3}$/i.test(name) || /\.vol\d+[+-]\d+\.par2$/i.test(name)
|
|
}
|