Files
usenet-indexer/lib/content/archive_names.ts
T
Daan MeijerandClaude Opus 5.5 f4ded062df
Test and deploy / test (push) Successful in 1m24s
Test and deploy / deploy (push) Successful in 1m58s
Complete archive listings by walking RAR headers, at low priority
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>
2026-10-05 23:32:52 +02:00

41 lines
1.7 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$/i.test(name)
}
/**
* The set and 1-based number of a RAR volume: `x.part03.rar` is volume 3 of
* `x`, and in the old naming `x.rar` is 1, `x.r00` 2, `x.r01` 3. Null for
* other names.
*/
export function rarVolume(name: string): { base: string; number: number } | null {
const part = /^(.*)\.part(\d+)\.rar$/i.exec(name)
if (part) return { base: part[1].toLowerCase(), number: Number(part[2]) }
const old = /^(.*)\.r(\d{2,3})$/i.exec(name)
if (old) return { base: old[1].toLowerCase(), number: Number(old[2]) + 2 }
const first = /^(.*)\.rar$/i.exec(name)
if (first) return { base: first[1].toLowerCase(), number: 1 }
return null
}