168 lines
8.4 KiB
JavaScript
168 lines
8.4 KiB
JavaScript
const test = require('node:test');
|
||
const assert = require('node:assert');
|
||
const { buildTitleKeywords } = require('../lib/ytdlp.js');
|
||
|
||
// The keywords become `title ~= (?i)<kw>` match-filters in yt-dlp, i.e. every keyword must match
|
||
// the candidate title case-insensitively. This mirrors that check.
|
||
const accepts = (title, candidate) =>
|
||
buildTitleKeywords(title).every(kw => new RegExp(kw, 'i').test(candidate));
|
||
|
||
test('a number in the title is always required, however short', () => {
|
||
const kws = buildTitleKeywords('700 Main Street');
|
||
assert.ok(kws.some(k => k.includes('700')), `700 fehlt in ${JSON.stringify(kws)}`);
|
||
});
|
||
|
||
test('rejects a same-shaped title with a different number', () => {
|
||
// The real regression: "777 Main Street" (Release - Topic) was downloaded for DAT ADAM's
|
||
// "700 Main Street", because only the two longest words (Street, Main) were required.
|
||
assert.equal(accepts('700 Main Street', '777 Main Street'), false);
|
||
assert.equal(accepts('700 Main Street', '700 Main Street'), true);
|
||
});
|
||
|
||
test('accepts the abbreviated spelling uploaders use', () => {
|
||
assert.equal(accepts('700 Main Street', '700 Main st (cr-Version)'), true);
|
||
assert.equal(accepts('700 Main Street', 'DAT ADAM - 700 Main St [FULL SONG]'), true);
|
||
});
|
||
|
||
test('the abbreviation does not match inside another word', () => {
|
||
assert.equal(accepts('700 Main Street', '700 Main Stuff'), false);
|
||
});
|
||
|
||
test('titles without numbers keep the previous two-longest-words behaviour', () => {
|
||
assert.deepEqual(buildTitleKeywords('Bohemian Rhapsody'), ['Bohemian', 'Rhapsody']);
|
||
assert.equal(accepts('Bohemian Rhapsody', 'Queen - Bohemian Rhapsody (Official Video)'), true);
|
||
assert.equal(accepts('Bohemian Rhapsody', 'Queen - Another One Bites The Dust'), false);
|
||
});
|
||
|
||
test('a remaster year is not required — YouTube titles never carry it', () => {
|
||
// "… - 2020 Remaster" steht auf der Veröffentlichung, der Upload heißt schlicht
|
||
// "Take Me Home, Country Roads". Vor dieser Ausnahme hätte die 2020 ihn abgelehnt.
|
||
assert.equal(accepts('Take Me Home, Country Roads - 2020 Remaster',
|
||
'John Denver - Take Me Home, Country Roads'), true);
|
||
});
|
||
|
||
test('a year that IS the title stays required', () => {
|
||
assert.equal(accepts('1999', 'Prince - 1999 (Official Music Video)'), true);
|
||
assert.equal(accepts('1999', 'Prince - 1984 (Official Music Video)'), false);
|
||
});
|
||
|
||
const { buildVariantFilter } = require('../lib/ytdlp.js');
|
||
|
||
// Der Variantenfilter ist eine yt-dlp-Ausdruckskette "title !~= (?i)\bx\b & …".
|
||
// Diese Hilfsfunktion wertet sie so aus, wie yt-dlp es tut.
|
||
const variantAccepts = (searchTitle, candidate) => {
|
||
const f = buildVariantFilter(searchTitle);
|
||
if (!f) return true;
|
||
return f.split(' & ').every(part => {
|
||
const m = /^title !~= \(\?i\)(.+)$/.exec(part);
|
||
return !new RegExp(m[1], 'i').test(candidate);
|
||
});
|
||
};
|
||
|
||
test('rejects a live recording — is_live only covers running streams', () => {
|
||
// Der echte Fall: auf dem Kuenstlerkanal, Dauer im Fenster, Titel passend.
|
||
assert.equal(variantAccepts('UFO', 'Dat Adam - Ufo Video Days 2015 Live'), false);
|
||
assert.equal(variantAccepts('UFO', 'DAT ADAM - 700 Main St | ROCK AM RING 2017 [LIVE]'), false);
|
||
assert.equal(variantAccepts('UFO', 'UFO'), true);
|
||
});
|
||
|
||
test('a deliberately live title keeps its live results', () => {
|
||
assert.equal(variantAccepts('Live Forever', 'Oasis - Live Forever'), true);
|
||
assert.equal(variantAccepts('Unplugged in New York (Live)', 'Nirvana - All Apologies (Live)'), true);
|
||
});
|
||
|
||
test('"live" inside another word does not disable the rule', () => {
|
||
// "deliver" enthaelt "live" als Teilstring — die Regel muss trotzdem greifen.
|
||
assert.equal(variantAccepts('Deliver', 'Artist - Deliver (Live at Wembley)'), false);
|
||
assert.equal(variantAccepts('Deliver', 'Artist - Deliver'), true);
|
||
});
|
||
|
||
const { pickYtmVideoUrls } = require('../lib/ytdlp.js');
|
||
|
||
// Echte Ausgabe der YTM-Suche "DAT ADAM UFO": Songs, ein Album (MPREb_) und der
|
||
// Kuenstlerkanal (UC…) auf Platz 9.
|
||
const YTM_OUT = [
|
||
'https://music.youtube.com/watch?v=ZG4XhPn3Yb4',
|
||
'https://music.youtube.com/watch?v=2KVU6aikZF0',
|
||
'https://music.youtube.com/browse/MPREb_IhxJPixC1QT',
|
||
'https://music.youtube.com/watch?v=phLOTtJaqZk',
|
||
'https://music.youtube.com/watch?v=p935nH6aj8Y',
|
||
'https://music.youtube.com/watch?v=Pb2YcDBm5fA',
|
||
'https://music.youtube.com/browse/MPREb_S7MMKVMduma',
|
||
'https://music.youtube.com/watch?v=mNfsX2RbZ2M',
|
||
'https://music.youtube.com/browse/UC5hilNPCUHEPf4VpG5_YpYA',
|
||
'https://music.youtube.com/watch?v=O034JUlf1J4',
|
||
].join('\n');
|
||
|
||
test('a channel hit no longer discards the whole result list', () => {
|
||
const { urls, skipped } = pickYtmVideoUrls(YTM_OUT);
|
||
assert.equal(urls.length, 7);
|
||
assert.equal(skipped, 3); // 2 Alben + 1 Kanal
|
||
assert.match(urls[0], /ZG4XhPn3Yb4/); // der offizielle Art Track
|
||
assert.ok(!urls.some(u => u.includes('/browse/')));
|
||
});
|
||
|
||
test('nothing but list entries yields no candidates', () => {
|
||
const only = 'https://music.youtube.com/browse/UC5hilNPCUHEPf4VpG5_YpYA';
|
||
assert.deepEqual(pickYtmVideoUrls(only).urls, []);
|
||
assert.deepEqual(pickYtmVideoUrls('').urls, []);
|
||
});
|
||
|
||
// ─── Japanische Titel bekommen wieder eine Titelpruefung ────────────────────
|
||
// Regression zum 24.9.2026: "銀髪の少年" (HUNTER×HUNTER, Yoshihisa Hirano) lieferte ein anderes
|
||
// Stueck desselben Komponisten. Ursache: fuer japanische Titel gab buildTitleKeywords eine LEERE
|
||
// Liste zurueck, und die Kaskadenschritte 3/4 lassen die Kuenstlerpruefung fallen — uebrig blieb
|
||
// allein das Dauerfenster, in das auf einem Soundtrack-Album fast jeder Titel passt.
|
||
|
||
test('japanischer Titel liefert jetzt ein Muster statt gar nichts', () => {
|
||
const kws = buildTitleKeywords('銀髪の少年');
|
||
assert.equal(kws.length, 1);
|
||
assert.ok(new RegExp(kws[0], 'i').test('銀髪の少年'), 'Originaltitel muss passen');
|
||
assert.ok(!new RegExp(kws[0], 'i').test('闘う者たち'), 'anderes Stueck darf NICHT passen');
|
||
});
|
||
|
||
test('Romaji-Fassung wird als Alternative akzeptiert', () => {
|
||
const kws = buildTitleKeywords('銀髪の少年', 'ginpatsu no shounen');
|
||
const re = new RegExp(kws[0], 'i');
|
||
assert.ok(re.test('銀髪の少年'), 'Original');
|
||
assert.ok(re.test('Ginpatsu no Shounen'), 'Romaji mit Leerzeichen');
|
||
assert.ok(re.test('Ginpatsu-no-Shounen'), 'Romaji mit Bindestrichen');
|
||
assert.ok(re.test('Hunter x Hunter OST - Ginpatsu no Shounen'), 'als Teil eines laengeren Titels');
|
||
assert.ok(!re.test('Requiem Aranea'), 'anderes Stueck desselben Albums');
|
||
});
|
||
|
||
test('Romaji, die gar keine sind, werden nicht als Alternative genommen', () => {
|
||
// romajiForStorage gibt den Text unveraendert zurueck, wenn der Tokenizer fehlt
|
||
const kws = buildTitleKeywords('銀髪の少年', '銀髪の少年');
|
||
assert.equal(kws.length, 1);
|
||
assert.ok(!kws[0].includes('|'), 'keine doppelte Alternative');
|
||
});
|
||
|
||
test('Sonderzeichen im japanischen Titel bleiben woertlich', () => {
|
||
const kws = buildTitleKeywords('君の名は。(Movie ver.)');
|
||
const re = new RegExp(kws[0], 'i');
|
||
assert.ok(re.test('君の名は。(Movie ver.)'));
|
||
assert.ok(!re.test('君の名はX Movie verY'), 'Punkt darf nicht als Platzhalter wirken');
|
||
});
|
||
|
||
test('lateinische Titel bleiben unveraendert', () => {
|
||
assert.deepEqual(buildTitleKeywords('Bohemian Rhapsody'), ['Bohemian', 'Rhapsody']);
|
||
assert.deepEqual(buildTitleKeywords('Dearly Beloved'), ['Beloved', 'Dearly']);
|
||
});
|
||
|
||
test('Umschrift toleriert die ueblichen Schreibvarianten', () => {
|
||
const re = new RegExp(buildTitleKeywords('銀髪の少年', 'Ginpatsu No Shounen')[0], 'i');
|
||
assert.ok(re.test('Ginpatsu no Shounen'), 'wie der Tokenizer schreibt');
|
||
assert.ok(re.test('Ginpatsu no Shonen'), 'ohne langes o — die haeufigste Variante');
|
||
assert.ok(re.test('Ginpatsu-no-Shonen'), 'mit Bindestrichen');
|
||
assert.ok(re.test('GINPATSU NO SHŌNEN'), 'mit Makron');
|
||
assert.ok(!re.test('Ginpatsu no Otona'), 'anderer Titel faellt weiterhin durch');
|
||
});
|
||
|
||
test('Katakana-Laengungsstrich faellt aus der Umschrift', () => {
|
||
// romajiForStorage laesst "ー" stehen ("TeーZe"); in einem lateinischen Titel steht es nie.
|
||
const re = new RegExp(buildTitleKeywords('残酷な天使のテーゼ', 'Zankoku Na Tenshi No TeーZe')[0], 'i');
|
||
assert.ok(re.test('Zankoku na Tenshi no Teze'), 'ohne Strich geschrieben');
|
||
assert.ok(re.test('残酷な天使のテーゼ'), 'Originaltitel weiterhin');
|
||
});
|