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 - Web UI: grey out stale results while a search runs and cancel superseded requests.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>
71 lines
3.6 KiB
TypeScript
71 lines
3.6 KiB
TypeScript
import { test } from '@japa/runner'
|
|
import db from '@adonisjs/lucid/services/db'
|
|
import testUtils from '@adonisjs/core/services/test_utils'
|
|
import StagingService from '#services/StagingService'
|
|
import IngestService, { segmentFromHeader } from '#services/IngestService'
|
|
|
|
const segment = (name: string, k: number, n: number, id = `${name}-${k}@x`) =>
|
|
segmentFromHeader(
|
|
{ 'subject': `"${name}" yEnc (${k}/${n})`, 'from': 'poster@x', 'message-id': `<${id}>`, 'date': 'Thu, 01 Oct 2026 12:00:00 GMT', ':bytes': '700000' },
|
|
'alt.binaries.test',
|
|
k
|
|
)!
|
|
|
|
async function binary(name: string) {
|
|
return db.from('binaries').where('name', name).first()
|
|
}
|
|
|
|
test.group('Staging', (group) => {
|
|
group.each.setup(() => testUtils.db().withGlobalTransaction())
|
|
|
|
test('a lone segment waits; its second segment brings both in', async ({ assert }) => {
|
|
let r = await StagingService.filter([segment('rnd1.bin', 3, 50)])
|
|
assert.equal(r.staged, 1)
|
|
assert.lengthOf(r.ingest, 0)
|
|
await IngestService.ingest(r.ingest)
|
|
assert.isNull(await binary('rnd1.bin'))
|
|
|
|
// The same article again (a re-fetched range) is no second segment.
|
|
r = await StagingService.filter([segment('rnd1.bin', 3, 50)])
|
|
assert.lengthOf(r.ingest, 0)
|
|
|
|
// Nor is the same article crossposted to another group (other group, other article number).
|
|
const crosspost = { ...segment('rnd1.bin', 3, 50), groups: ['alt.binaries.boneless'], articleNumber: 160154327571 }
|
|
r = await StagingService.filter([crosspost])
|
|
assert.lengthOf(r.ingest, 0)
|
|
r = await StagingService.filter([segment('dup.bin', 2, 9), { ...segment('dup.bin', 2, 9), groups: ['alt.binaries.boneless'] }])
|
|
assert.equal(r.staged, 1)
|
|
|
|
r = await StagingService.filter([segment('rnd1.bin', 4, 50)])
|
|
assert.deepEqual(r.ingest.map((s) => s.number).sort(), [3, 4])
|
|
await IngestService.ingest(r.ingest)
|
|
const b = await binary('rnd1.bin')
|
|
assert.equal(Number((await db.from('parts').where('binary_id', b.id).count('* as n'))[0].n), 2)
|
|
assert.lengthOf(await db.from('staged_segments').where('file_key', segment('rnd1.bin', 3, 50).fileKey), 0)
|
|
|
|
// Later segments of a known file go straight in.
|
|
r = await StagingService.filter([segment('rnd1.bin', 9, 50)])
|
|
assert.lengthOf(r.ingest, 1)
|
|
})
|
|
|
|
test('single-part files and files with two segments in the batch go straight in; staged ones join them', async ({ assert }) => {
|
|
// Part 1 arrived alone at the end of the previous batch.
|
|
await StagingService.filter([segment('real.part01.rar', 1, 3)])
|
|
const r = await StagingService.filter([segment('real.part01.rar', 2, 3), segment('real.part01.rar', 3, 3), segment('one.nfo', 1, 1)])
|
|
assert.equal(r.staged, 0)
|
|
assert.sameMembers(r.ingest.map((s) => `${s.name}:${s.number}`), ['real.part01.rar:1', 'real.part01.rar:2', 'real.part01.rar:3', 'one.nfo:1'])
|
|
})
|
|
|
|
test('GC adopts segments whose file got a binary, and drops old ones', async ({ assert }) => {
|
|
await StagingService.filter([segment('late.bin', 7, 10)])
|
|
await StagingService.filter([segment('old.bin', 2, 10)])
|
|
await db.from('staged_segments').where('file_key', segment('old.bin', 2, 10).fileKey).update({ staged_at: new Date(Date.now() - 3 * 3600_000) })
|
|
// Another job created the binary meanwhile.
|
|
await IngestService.ingest([segment('late.bin', 1, 10), segment('late.bin', 2, 10)])
|
|
const result = await StagingService.sweep(2 * 3600, Date.now() + 10_000)
|
|
assert.deepEqual(result, { adopted: 1, expired: 1 })
|
|
const b = await binary('late.bin')
|
|
assert.equal(Number((await db.from('parts').where('binary_id', b.id).count('* as n'))[0].n), 3)
|
|
})
|
|
})
|