Daan MeijerandClaude Opus 5.5
be8a3d4580
Spotnet (CONCEPT D29): - Index free.pt fully and import spots with their descriptions, categories and NZBs; a spot renames its release, since Spotnet names are more trustworthy than names derived from subjects. - Find passwords in spot descriptions too, and tell "needs a password we have" from "needs a password we don't have". Content inspection: - List the contents of 7z (.7z.001) archives, SFV sets, nicovideo uploads and other archive-like files; mark yEncBin .bin containers as encrypted. - Take real names from yEnc headers for randomly named files, and merge uploads that were split across posts. Storage (D31, D32): - Store segment lists zstd-compressed behind the FileStore accessor. - group:backfill indexes older headers at low priority and pauses when the NVMe or HDD part of the database gets too large. Grouping (D35, D36): - Lone header segments wait in staged_segments until a second segment of their file arrives, which drops the per-article junk binaries. - Counter grouping joins random-subject uploads by poster, [i/M] counter, part count and day. Search and maintenance (D33, D34): - A trigram-indexed search_text column, smaller indexes, estimated stats. - Passes that clean up nonsense names; weekly index maintenance; GC budgets per kind. - Web UI: grey out stale results while a search runs and cancel superseded requests. Count only up to 1,000 matches for the page, which made filter clicks take seconds (Newznab keeps the 10,000 cap). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
51 lines
2.3 KiB
TypeScript
51 lines
2.3 KiB
TypeScript
/**
|
|
* Archive passwords that spotters put in the title or description instead of
|
|
* the NZB's `<meta type="password">`:
|
|
* `Title{{secret}}` (the newznab/SABnzbd convention),
|
|
* `Wachtwoord: KKKK2`, `[b]Password[/b]: x`, `WW: p3IU5Rz9R`, `ww= 0112358`,
|
|
* `WW FC0401` (abbreviation without separator: only with a digit in it).
|
|
* The value must be the rest of its line and a single token, so sentences
|
|
* such as "Wachtwoord: deze download is zonder wachtwoord geplaatst" or
|
|
* "met een password beschermd" don't count.
|
|
*/
|
|
const KEYWORD = String.raw`wachtwoord|wachtw|password|passwort|passwd|pwd|pass|ww|pw`
|
|
const WITH_SEPARATOR = new RegExp(String.raw`(?:^|[^a-z0-9])(?:${KEYWORD})\s*(?:is\s*)?[:=]\s*(.*)$`, 'i')
|
|
const ABBREVIATION = /(?:^|[^a-z0-9])(?:ww|pw)\s+(\S+)\s*$/i
|
|
const NO_PASSWORD = /\b(zonder|geen|no|without|none|niet|kein|ohne)\b.{0,20}\b(wachtwoord|password|passwort|ww|pw)\b|\b(wachtwoord|password|passwort)\b.{0,20}\b(niet nodig|not needed|none|geen|nvt|n\/a)\b/i
|
|
const NOT_A_VALUE = /^(?:-+|geen|none|no|nee|nvt|n\/a|niet|not|leeg|empty|zonder|without|onbekend|unknown|zie|see|in|staat|volgt|nzb|spot)$/i
|
|
|
|
/** Lines of a spot description: UBB/HTML line breaks split, other tags dropped. */
|
|
function lines(description: string): string[] {
|
|
return description
|
|
.replace(/\[br\]|<br\s*\/?>/gi, '\n')
|
|
.replace(/\[\/?[a-z]+(?:=[^\]]*)?\]|<\/?[a-z][^>]*>/gi, '')
|
|
.split(/\r?\n/)
|
|
.map((line) => line.trim())
|
|
}
|
|
|
|
function clean(value: string): string | null {
|
|
const token = value.trim().replace(/^["'“‘«(<]+|["'”’»)>.,;!]+$/g, '')
|
|
if (!token || /\s/.test(token) || token.length < 2 || token.length > 64 || NOT_A_VALUE.test(token)) return null
|
|
return token
|
|
}
|
|
|
|
export function passwordFromSpot(title: string, description?: string | null): string | null {
|
|
const braces = /\{\{([^{}]{1,64})\}\}/.exec(title)
|
|
if (braces && clean(braces[1])) return clean(braces[1])
|
|
for (const line of lines(description ?? '')) {
|
|
if (!line || NO_PASSWORD.test(line)) continue
|
|
const separated = WITH_SEPARATOR.exec(line)
|
|
if (separated) {
|
|
const value = clean(separated[1])
|
|
if (value) return value
|
|
continue
|
|
}
|
|
const abbreviated = ABBREVIATION.exec(line)
|
|
if (abbreviated && /\d/.test(abbreviated[1])) {
|
|
const value = clean(abbreviated[1])
|
|
if (value) return value
|
|
}
|
|
}
|
|
return null
|
|
}
|