import assert from 'node:assert/strict';
import test from 'node:test';
import { convertYoutubeTimedTextToVtt, normalizeYoutubeAutoVtt } from './timedtext';
test('convertYoutubeTimedTextToVtt leaves malformed numeric entities literal', () => {
const result = convertYoutubeTimedTextToVtt(
'� � A
',
);
assert.equal(
result,
['WEBVTT', '', '00:00:00.000 --> 00:00:01.000', '� � A', ''].join('\n'),
);
});
test('convertYoutubeTimedTextToVtt does not swallow text after zero-length overlap rows', () => {
const result = convertYoutubeTimedTextToVtt(
[
'',
'今日は
',
'今日はいい天気ですね
',
'今日はいい天気ですね
',
'',
].join(''),
);
assert.equal(
result,
[
'WEBVTT',
'',
'00:00:00.000 --> 00:00:00.999',
'今日は',
'',
'00:00:01.000 --> 00:00:03.000',
'いい天気ですね',
'',
].join('\n'),
);
});
test('convertYoutubeTimedTextToVtt extends rolling captions to the next window event', () => {
// Real-world shape of YouTube's sentence-level auto captions: window-append
// filler rows (a="1", sometimes without d) mark the display timeline, while
// long text rows carry a placeholder d="3000" far shorter than the speech.
const result = convertYoutubeTimedTextToVtt(
[
'',
'\n
',
'ありがとうって言えないよね。こんなんじゃ。
',
'\n
',
'私だったら無理だよ。
',
'',
].join('\n'),
);
assert.equal(
result,
[
'WEBVTT',
'',
'00:01:38.560 --> 00:01:46.950',
'ありがとうって言えないよね。こんなんじゃ。',
'',
'00:01:46.960 --> 00:01:50.759',
'私だったら無理だよ。',
'',
].join('\n'),
);
});
test('normalizeYoutubeAutoVtt strips cumulative rolling-caption prefixes', () => {
const result = normalizeYoutubeAutoVtt(
[
'WEBVTT',
'',
'00:00:01.000 --> 00:00:02.000',
'今日は',
'',
'00:00:02.000 --> 00:00:03.000',
'今日はいい天気ですね',
'',
'00:00:03.000 --> 00:00:04.000',
'今日はいい天気ですね本当に',
'',
].join('\n'),
);
assert.equal(
result,
[
'WEBVTT',
'',
'00:00:01.000 --> 00:00:02.000',
'今日は',
'',
'00:00:02.000 --> 00:00:03.000',
'いい天気ですね',
'',
'00:00:03.000 --> 00:00:04.000',
'本当に',
'',
].join('\n'),
);
});