Daan MeijerandClaude Opus 5.5
2c14315f94
Measured on two neighbouring boneless ranges (merging their fragments): - 99.8% of fragment files were single articles of a random-named 'file' of >100 parts: a random subject per article, which never completes from headers. They now count as per-article. - A file is kept as a fragment when its first part seen is above 1 and comes within the start window (the idle window: uploads in busy groups spread over minutes, and a 50k-article edge zone is ~30 s of boneless), or when it was still open at the range's end with later parts missing. Anything else missing parts is incomplete and only counted. Per range: 70,308 → 130 fragment files; merged, 47 of the 48 files met complete (57,558 segments, ~8% of the range's kept segments). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
85 lines
5.0 KiB
TypeScript
85 lines
5.0 KiB
TypeScript
import { test } from '@japa/runner'
|
||
import { RangeIndexer } from '#lib/edge/index'
|
||
import { decodeChunk } from '#lib/chunks/index'
|
||
import { DEFAULT_RULES } from '#lib/rules/index'
|
||
import type { Overview } from '#lib/nntp/index'
|
||
|
||
const GROUP = 'alt.binaries.test'
|
||
const rules = { ...DEFAULT_RULES, samplePercent: 0, droppedSignatures: [], priorities: { 'alt.binaries.boneless': 1, [GROUP]: 2, 'alt.binaries.x': 3 } }
|
||
let id = 0
|
||
|
||
/** Overview lines of one posted file: all its parts, from article number `at` on. */
|
||
function post(at: number, name: string, parts: number, opts: { counter?: string; groups?: string[]; tool?: 'ngPost' | 'nyuu'; poster?: string } = {}): Overview[] {
|
||
return Array.from({ length: parts }, (_, i) => {
|
||
id++
|
||
const mid = opts.tool === 'ngPost' ? `${id.toString(16).padStart(32, '0')}@ngPost` : `art${id}@test`
|
||
const groups = opts.groups ?? [GROUP]
|
||
return [at + i, {
|
||
'subject': `${opts.counter ? `${opts.counter} - ` : ''}"${name}" yEnc (${i + 1}/${parts})`,
|
||
'from': opts.poster ?? 'poster <p@x>',
|
||
'date': 'Mon, 05 Oct 2026 10:00:00 +0000',
|
||
'message-id': `<${mid}>`,
|
||
':bytes': '700000',
|
||
'xref': `news.example ${groups.map((g, k) => `${g}:${at + i + k}`).join(' ')}`,
|
||
}] as Overview
|
||
})
|
||
}
|
||
|
||
test.group('edge / RangeIndexer', () => {
|
||
test('groups files into releases with probe candidates, and counts what the rules dropped', ({ assert }) => {
|
||
const indexer = new RangeIndexer({ group: GROUP, start: 1, end: 1_000_000, rules, edgeArticles: 10 })
|
||
indexer.add([
|
||
...post(100_000, 'Some.Show.S01E01.1080p.WEB.part1.rar', 3, { counter: 'Some.Show.S01E01 [1/3]' }),
|
||
...post(100_010, 'Some.Show.S01E01.1080p.WEB.part2.rar', 3, { counter: 'Some.Show.S01E01 [2/3]' }),
|
||
...post(100_020, 'Some.Show.S01E01.1080p.WEB.par2', 1, { counter: 'Some.Show.S01E01 [3/3]' }),
|
||
// A crosspost whose owner is boneless (priority 1): skipped here.
|
||
...post(100_030, 'Other.Release.2020.mkv', 2, { groups: [GROUP, 'alt.binaries.boneless'] }),
|
||
// Random-named ngPost upload: garbage everywhere.
|
||
...post(100_040, 'Hs7dKq2LmZ9xWv3RtYp1Qa.part01.rar', 4, { tool: 'ngPost' }),
|
||
// A random subject per article: per-article.
|
||
...post(100_050, 'Pq4ZmXc8VbN2LkJh6GfDs3', 1),
|
||
], 200_000)
|
||
indexer.add([[100_060, { 'subject': 'obfuscated', 'from': 'x', 'message-id': '<obf@test>', 'date': '', ':bytes': '1', 'xref': `news.example ${GROUP}:100060` }]], 300_000)
|
||
indexer.finish()
|
||
const batch = indexer.take()
|
||
|
||
assert.equal(batch.headers, 3 + 3 + 1 + 2 + 4 + 1 + 1)
|
||
assert.lengthOf(batch.releases, 1)
|
||
const [release] = batch.releases
|
||
assert.include(release, { files: 3, segments: 7, firstArticle: 100_000, lastArticle: 100_020 })
|
||
assert.deepEqual(decodeChunk(release.payload).map((f) => f.name).sort(), ['Some.Show.S01E01.1080p.WEB.par2', 'Some.Show.S01E01.1080p.WEB.part1.rar', 'Some.Show.S01E01.1080p.WEB.part2.rar'])
|
||
assert.deepEqual(batch.candidates.map((c) => [c.kind, c.file]).sort(), [['archive', 'Some.Show.S01E01.1080p.WEB.part1.rar'], ['par2', 'Some.Show.S01E01.1080p.WEB.par2']])
|
||
|
||
const counts = Object.fromEntries(batch.counts.map((c) => [`${c.rule} ${c.key}`.trim(), [c.articles, c.files]]))
|
||
assert.deepEqual(counts, { 'crosspost alt.binaries.boneless': [2, 0], 'garbage ngPost alt.binaries.test': [4, 1], 'per-article other': [1, 1], 'obfuscated': [1, 0] })
|
||
assert.equal(batch.next, 1_000_001)
|
||
})
|
||
|
||
test('files the edges cut leave as fragments; one missing parts in the middle is only counted', ({ assert }) => {
|
||
const indexer = new RangeIndexer({ group: GROUP, start: 1, end: 1_000_000, rules, edgeArticles: 1000 })
|
||
indexer.add([
|
||
// Parts 2–3 right after the start: part 1 is in the previous range.
|
||
...post(5, 'Start.Cut.2020.part1.rar', 3).slice(1),
|
||
// Parts 1–2 seen, part 3 never: incomplete on the server.
|
||
...post(500_000, 'Middle.Hole.2020.part1.rar', 3).slice(0, 2),
|
||
], 600_000)
|
||
// Chunks without its part 3: the hole file is given up (idle) long before the end.
|
||
for (let at = 650_000; at < 950_000; at += 50_000) indexer.add([], at)
|
||
// Parts 1–2 near the end, still open when the range ends: part 3 is in the next range.
|
||
indexer.add(post(999_990, 'End.Cut.2020.part1.rar', 3).slice(0, 2), 1_000_001)
|
||
indexer.finish()
|
||
const batch = indexer.take()
|
||
assert.deepEqual(batch.fragments.map((f) => [f.name, f.segments.map((s) => s[0])]).sort(), [['End.Cut.2020.part1.rar', [1, 2]], ['Start.Cut.2020.part1.rar', [2, 3]]])
|
||
assert.deepEqual(batch.counts.map((c) => [c.rule, c.articles, c.files]), [['incomplete', 2, 1]])
|
||
assert.lengthOf(batch.releases, 0)
|
||
})
|
||
})
|
||
|
||
test.group('edge / taking over a range', () => {
|
||
test("a worker that resumes a range midway starts its first batch at the range's resume point", ({ assert }) => {
|
||
const indexer = new RangeIndexer({ group: GROUP, start: 1, end: 1_000_000, resumeAt: 500_001, rules })
|
||
indexer.add(post(500_001, 'A.Release.2020.mkv', 1), 600_000)
|
||
assert.deepEqual([indexer.take().from, indexer.take().from], [500_001, 600_000])
|
||
})
|
||
})
|