Files
usenet-indexer/tests/unit/probe/yenc.spec.ts
T
Daan MeijerandClaude Opus 5.5 8bd6d6aa5f
Test and deploy / test (push) Successful in 50s
Test and deploy / deploy (push) Successful in 1m46s
Rebuild: phase 2's prober reads the probe queue
probe:run (compose service prober, PROBE_CONNECTIONS, default 6) claims
waiting candidates of settled releases (lone, then par2, then archive),
fetches each article with BODY over connections of its own (no
compression) and inspects it: the yEnc name and size, the content type
from the first bytes, a par2 set's files, a RAR volume's entries and
whether they're encrypted. Results per release and kind in
release_inspections (CHUNK_TABLESPACE, the HDD); on the release
passworded, inner_name (the largest content name) and inspected_at.
430 = missing, not yEnc = error, both final; connection trouble puts
the candidate back.

Fetch and parse in one process: an article takes ~0.1 s per connection,
parsing a few ms (no queue in between). Parsers from voyager 1 (lib/yenc,
lib/rar, lib/par2, lib/content sniff) with their tests; XoverClient.body;
yencode.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-11 15:32:49 +02:00

108 lines
4.0 KiB
TypeScript

import { test } from '@japa/runner'
import yencode from 'yencode'
import {
YencCrcError,
YencError,
crc32Hex,
decodeSegment,
parseYencMeta,
} from '#lib/yenc/index'
/** Builds an article body as a yEnc poster would send it. */
function article(
data: Buffer,
opts: { name: string; fileSize?: number; part?: number; total?: number; begin?: number; fileCrc?: string }
) {
const fileSize = opts.fileSize ?? data.length
const encoded = yencode.encode(data).toString('latin1')
const lines: string[] = []
if (opts.part) {
lines.push(`=ybegin part=${opts.part} total=${opts.total} line=128 size=${fileSize} name=${opts.name}`)
const begin = opts.begin ?? 1
lines.push(`=ypart begin=${begin} end=${begin + data.length - 1}`)
lines.push(encoded)
const fileCrc = opts.fileCrc ? ` crc32=${opts.fileCrc}` : ''
lines.push(`=yend size=${data.length} part=${opts.part} pcrc32=${crc32Hex(data)}${fileCrc}`)
} else {
lines.push(`=ybegin line=128 size=${fileSize} name=${opts.name}`)
lines.push(encoded)
lines.push(`=yend size=${data.length} crc32=${crc32Hex(data)}`)
}
return Buffer.from(lines.join('\r\n'), 'latin1')
}
function randomBytes(length: number, seed = 1) {
const buf = Buffer.alloc(length)
let x = seed
for (let i = 0; i < length; i++) {
x = (x * 1103515245 + 12345) & 0x7fffffff
buf[i] = x & 0xff
}
return buf
}
test.group('yenc / parseYencMeta', () => {
test('parses a multi-part header as seen on alt.binaries.test', ({ assert }) => {
const body = Buffer.from(
'=ybegin part=56 line=128 size=104857600 name=obrMkrDeLmbhaouwYO34.part08.rar\r\n' +
'=ypart begin=21120001 end=21504000\r\n' +
'xyz\r\n' +
'=yend size=384000 part=56 pcrc32=B6339AFC',
'latin1'
)
const meta = parseYencMeta(body)
assert.deepEqual(meta.begin, {
part: 56,
total: undefined,
line: 128,
size: 104857600,
name: 'obrMkrDeLmbhaouwYO34.part08.rar',
})
assert.deepEqual(meta.part, { begin: 21120001, end: 21504000 })
assert.deepEqual(meta.end, { size: 384000, part: 56, pcrc32: 'b6339afc', crc32: undefined })
assert.equal(body.subarray(meta.dataStart, meta.dataEnd).toString(), 'xyz')
})
test('keeps spaces and "=" in the filename', ({ assert }) => {
const body = article(Buffer.from('hi'), { name: 'My File = v2 (final).nfo' })
assert.equal(parseYencMeta(body).begin.name, 'My File = v2 (final).nfo')
})
test('ignores leading blank lines before =ybegin', ({ assert }) => {
const body = Buffer.concat([Buffer.from('\r\n\r\n'), article(Buffer.from('hi'), { name: 'a.txt' })])
assert.equal(parseYencMeta(body).begin.name, 'a.txt')
})
test('rejects bodies without yEnc markers', ({ assert }) => {
assert.throws(() => parseYencMeta(Buffer.from('plain text\r\n')), /=ybegin/)
assert.throws(() => parseYencMeta(Buffer.from('=ybegin line=128 size=2 name=a\r\nxx')), /=yend/)
})
})
test.group('yenc / decodeSegment', () => {
test('round-trips a single-part post and checks crc32', ({ assert }) => {
const data = randomBytes(5000)
const segment = decodeSegment(article(data, { name: 'single.bin' }))
assert.isTrue(segment.data.equals(data))
assert.equal(segment.offset, 0)
})
test('throws YencCrcError on a corrupted part', ({ assert }) => {
const body = article(randomBytes(1000), { name: 'x.bin', part: 1, total: 1 })
const index = body.indexOf('\r\n=ypart') + 60
body[index] = body[index] === 0x41 ? 0x42 : 0x41
assert.throws(() => decodeSegment(body), YencCrcError as any)
})
test('undoes NNTP dot-stuffing', ({ assert }) => {
// Byte 4 encodes to "." (4 + 42 = 46). An unescaped leading "." is dot-stuffed to "..".
const data = Buffer.from([4, 5, 6])
const body = Buffer.from(
`=ybegin line=128 size=3 name=dot.bin\r\n../0\r\n=yend size=3 crc32=${crc32Hex(data)}`,
'latin1'
)
assert.isTrue(decodeSegment(body).data.equals(data))
assert.throws(() => decodeSegment(body, { stripDots: false }), YencError as any)
})
})