Files
usenet-indexer/tests/functional/names.spec.ts
T
Daan MeijerandClaude Opus 5.5 be8a3d4580 Spotnet import, header backfill, staging and counter grouping, faster search
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- Web UI: grey out stale results while a search runs and cancel superseded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>
2026-10-03 19:59:23 +02:00

95 lines
4.8 KiB
TypeScript

import { test } from '@japa/runner'
import db from '@adonisjs/lucid/services/db'
import FileStore from '#services/FileStore'
import testUtils from '@adonisjs/core/services/test_utils'
import NameService from '#services/NameService'
async function release(name: string, files: { name: string; size: number; md5_16k: string }[]) {
const now = new Date()
const [row] = await db
.table('releases')
.insert({ release_key: `${name}`.padEnd(40, 'x').slice(0, 40), name, source: 'par2', groups: '[]', posted_at: now, first_seen_at: now, last_seen_at: now })
.returning('id')
for (const [i, f] of files.entries()) {
await db.table('release_files').insert({ release_id: row.id, par2_file_id: String(i).padStart(32, '0'), name: f.name, size: f.size, md5_16k: f.md5_16k })
}
return Number(row.id)
}
async function binary(key: string, fields: Record<string, unknown>) {
const now = new Date()
const [row] = await db
.table('binaries')
.insert({ file_key: key.padEnd(40, '0'), poster: 'x', subject: '"x" yEnc', name: 'Xq8r2KdLm3Zw91PqA7', total_parts: 1, groups: '[]', first_seen_at: now, last_seen_at: now, ...fields })
.returning('id')
return Number(row.id)
}
test.group('NameService', (group) => {
group.each.setup(() => testUtils.db().withGlobalTransaction())
test('an exact match leaves a random-named single-file release for the par2 set', async ({ assert }) => {
const season = await release('SEAL.Team.S03', [
{ name: 'SEAL.Team.S03E18.1080p.WEB-DL-nitrato.mkv', size: 939_684_767, md5_16k: 'd'.repeat(32) },
])
const now = new Date()
const [weak] = await db
.table('releases')
.insert({ release_key: 'w'.repeat(40), name: 'mOzyyxCyYUjAbCdEf12', source: 'stem', groups: '[]', first_seen_at: now, last_seen_at: now })
.returning('id')
const [file] = await FileStore.insert([
{ filename: 'mOzyyxCyYUjAbCdEf12', poster: 'x', date: now.getTime(), parts: 1, size: 1, groups: '[]', segments: [], release_id: weak.id, created_at: now, updated_at: now },
])
const episode = await binary('ep18', { size: 939_684_767, md5_16k: 'd'.repeat(32), release_id: weak.id, file_id: file.id })
await NameService.resolve([episode])
const moved = await db.from('binaries').where('id', episode).first()
assert.equal(Number(moved.release_id), season)
assert.equal(moved.real_name, 'SEAL.Team.S03E18.1080p.WEB-DL-nitrato.mkv')
assert.equal(Number((await db.from('files').where('id', file.id).first()).release_id), season)
})
test('a file in a real grouping keeps it', async ({ assert }) => {
await release('Other.Set', [{ name: 'Other.Show.S01E01.mkv', size: 5_000_000, md5_16k: 'e'.repeat(32) }])
const now = new Date()
const [nzb] = await db
.table('releases')
.insert({ release_key: 'n'.repeat(40), name: 'Qz8r2KdLm3Zw91PqA7x', source: 'nzb', groups: '[]', first_seen_at: now, last_seen_at: now })
.returning('id')
const id = await binary('nzbfile', { size: 5_000_000, md5_16k: 'e'.repeat(32), release_id: nzb.id })
await NameService.resolve([id])
assert.equal(Number((await db.from('binaries').where('id', id).first()).release_id), Number(nzb.id))
})
test('names equal-sized volumes exactly by their first-16k fingerprint', async ({ assert }) => {
const releaseId = await release('Some.Movie', [
{ name: 'Some.Movie.part1.rar', size: 50_000_000, md5_16k: 'a'.repeat(32) },
{ name: 'Some.Movie.part2.rar', size: 50_000_000, md5_16k: 'b'.repeat(32) },
])
const one = await binary('one', { size: 50_000_000, md5_16k: 'b'.repeat(32) })
const two = await binary('two', { size: 50_000_000, md5_16k: 'a'.repeat(32) })
const stranger = await binary('three', { size: 50_000_000, md5_16k: 'c'.repeat(32) })
await NameService.resolve([one, two, stranger])
const rows = await db.from('binaries').whereIn('id', [one, two, stranger]).orderBy('id')
assert.deepEqual(rows.map((r) => [r.real_name, r.release_id && Number(r.release_id)]), [
['Some.Movie.part2.rar', releaseId],
['Some.Movie.part1.rar', releaseId],
[null, null],
])
})
test('without a fingerprint, names by size only when the size is unique in the release', async ({ assert }) => {
const releaseId = await release('Other', [
{ name: 'Other.mkv', size: 700_000_000, md5_16k: 'd'.repeat(32) },
{ name: 'Other.part1.rar', size: 10_000_000, md5_16k: 'e'.repeat(32) },
{ name: 'Other.part2.rar', size: 10_000_000, md5_16k: 'f'.repeat(32) },
])
const video = await binary('video', { size: 700_000_000, release_id: releaseId })
const volume = await binary('volume', { size: 10_000_000, release_id: releaseId })
await NameService.resolve([video, volume])
assert.equal((await db.from('binaries').where('id', video).first()).real_name, 'Other.mkv')
assert.isNull((await db.from('binaries').where('id', volume).first()).real_name)
})
})