Daan MeijerandClaude Opus 5.5
95f1d427df
Of 5,000 waiting inspection jobs, 3,212 were queued only because their stem looked random, and 2,044 of those were later RAR volumes (xyz.part47.rar, .r00) or par2 recovery volumes (.vol03+04.par2). Their first segment adds nothing: the set is listed from its first volume and named from its index .par2, as for readable names already. Each one cost a ~700 KB download; inspection pulled ~85 MB/s and fell behind the backfill. - isCandidate() rejects later volumes (isLaterVolume) before the random- name rule. - worker:file only queues files that are candidates, so the ~30% that inspection skips anyway no longer take queue slots. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
66 lines
3.7 KiB
TypeScript
66 lines
3.7 KiB
TypeScript
import { test } from '@japa/runner'
|
|
import yencode from 'yencode'
|
|
import { isLaterVolume, sniffContentType } from '#lib/content/index'
|
|
import { crc32Hex, decodeSegment, YencError } from '#lib/yenc/index'
|
|
|
|
test.group('content / sniffContentType', () => {
|
|
test('recognises containers and media by magic bytes', ({ assert }) => {
|
|
const magic = (hex: string, pad = 16) => Buffer.concat([Buffer.from(hex, 'hex'), Buffer.alloc(pad)])
|
|
assert.equal(sniffContentType(Buffer.concat([Buffer.from('nzbe'), Buffer.alloc(40)])), 'nzbe')
|
|
assert.equal(sniffContentType(magic('5041523200504b54')), 'par2')
|
|
assert.equal(sniffContentType(magic('526172211a070100')), 'rar5')
|
|
assert.equal(sniffContentType(magic('526172211a0700')), 'rar4')
|
|
assert.equal(sniffContentType(magic('1a45dfa3')), 'matroska')
|
|
assert.equal(sniffContentType(magic('0000001866747970')), 'mp4')
|
|
assert.equal(sniffContentType(magic('28b52ffd')), 'zstd')
|
|
assert.equal(sniffContentType(Buffer.from('<?xml version="1.0"?>\n<!DOCTYPE nzb PUBLIC "x">')), 'nzb')
|
|
assert.isNull(sniffContentType(Buffer.from('plain text')))
|
|
assert.equal(sniffContentType(magic('ffd8ffe0')), 'jpeg')
|
|
assert.equal(sniffContentType(magic('89504e470d0a1a0a')), 'png')
|
|
assert.equal(sniffContentType(Buffer.concat([Buffer.from('ID3'), Buffer.alloc(16)])), 'mp3')
|
|
assert.equal(sniffContentType(Buffer.concat([Buffer.from('fLaC'), Buffer.alloc(16)])), 'flac')
|
|
assert.equal(sniffContentType(Buffer.from('RIFF\x00\x00\x00\x00AVI LIST', 'latin1')), 'avi')
|
|
|
|
// UDF (Blu-ray) volume recognition sequence at 32 KiB
|
|
const udf = Buffer.alloc(0x9000)
|
|
udf.write('BEA01', 0x8001, 'latin1')
|
|
udf.write('NSR03', 0x8801, 'latin1')
|
|
assert.equal(sniffContentType(udf), 'udf')
|
|
})
|
|
})
|
|
|
|
test.group('yenc / lenientSize', () => {
|
|
test("recognises yEncBin's encrypted .bin container by its header", ({ assert }) => {
|
|
// The first 48 bytes of 2141406641.bin (yEncBin@Poster.com).
|
|
const data = Buffer.from('54f399d117c492696e4dc4ef5b60c11d7f83e92dfdf23450e79370b048123da81e4c8013091b682fb22478daed2ae981', 'hex')
|
|
assert.equal(sniffContentType(data), 'yencbin')
|
|
// The second variant (1060238685.bin).
|
|
assert.equal(sniffContentType(Buffer.from('54f399e917c492696a4e9fb05b60c31d7f83e92df9f16f5086e3c3d9480d66ef1e48d915', 'hex')), 'yencbin')
|
|
assert.isNull(sniffContentType(Buffer.from('54f399d117c492696e4dc4ef5b60c11e7f83e92d', 'hex')))
|
|
})
|
|
|
|
test('decodes a part whose declared size leaves out a header, still checking the CRC', ({ assert }) => {
|
|
const data = Buffer.concat([Buffer.from('nzbe'), Buffer.alloc(16, 7), Buffer.from('ciphertext-here')])
|
|
const declared = data.length - 20
|
|
const body = Buffer.from(
|
|
`=ybegin part=1 line=128 size=${declared} name=f6dd6b156692a52b.bin\r\n=ypart begin=1 end=${declared}\r\n` +
|
|
yencode.encode(data).toString('latin1') +
|
|
`\r\n=yend size=${declared} part=1 pcrc32=${crc32Hex(data)}`,
|
|
'latin1'
|
|
)
|
|
assert.throws(() => decodeSegment(body), YencError as any)
|
|
assert.isTrue(decodeSegment(body, { lenientSize: true }).data.equals(data))
|
|
})
|
|
})
|
|
|
|
test.group('content / isLaterVolume', () => {
|
|
test('recognises later RAR volumes and par2 recovery volumes, also under a random stem', ({ assert }) => {
|
|
for (const name of ['P8vttYaPec1mL4nDZHPZo7Nd6iEWj8lP.part47.rar', 'Show.S01E01.part002.rar', 'abc.r00', 'abc.r123', 'x7Kq9.vol03+04.par2', 'Show.vol127-128.par2']) {
|
|
assert.isTrue(isLaterVolume(name), name)
|
|
}
|
|
for (const name of ['P8vttYaPec1mL4nDZHPZo7Nd6iEWj8lP.part01.rar', 'abc.part1.rar', 'abc.rar', 'x7Kq9.par2', '6e13186238ab54ca498e46d2d77da099', 'abc.7z.002', 'abc.mkv']) {
|
|
assert.isFalse(isLaterVolume(name), name)
|
|
}
|
|
})
|
|
})
|