Repository navigation
Expand file tree
/
Copy pathwebvtt.js
More file actions
689 lines (642 loc) · 18.1 KB
/
Copy pathwebvtt.js
File metadata and controls
689 lines (642 loc) · 18.1 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
import $ from 'jquery';
function addWebvttFunctions(AblePlayer) {
// See section 4.1 of dev.w3.org/html5/webvtt for format details.
AblePlayer.prototype.parseWebVTT = function(data) {
let srcFile = data.src;
let text = data.text;
// Normalize line ends to \n.
text = text.replace(/(\r\n|\n|\r)/g,'\n');
var parserState = {
src: srcFile,
text: text,
error: null,
metadata: {},
cues: [],
line: 1,
column: 1
};
try {
act(parserState, parseFileBody);
}
catch (err) {
var errString = 'Invalid WebVTT file: ' + parserState.src + '\n';
errString += 'Line: ' + parserState.line + ', ';
errString += 'Column: ' + parserState.column + '\n';
errString += err;
if (console.warn) {
console.warn(errString);
} else if (console.log) {
console.log(errString);
}
}
return parserState;
}
function actList(state, list) {
var results = [];
for (var ii = 0; ii < list.length; ii++) {
results.push(act(state, list[ii]));
}
return results;
}
// Applies the action and checks for errors.
function act(state, action) {
var val = action(state);
if (state.error !== null) {
throw state.error;
}
return val;
}
function updatePosition(state, cutText) {
for (var ii = 0; ii < cutText.length; ii++) {
if (cutText[ii] === '\n') {
state.column = 1;
state.line += 1;
} else {
state.column += 1;
}
}
}
function cut(state, length) {
var returnText = state.text.substring(0, length);
updatePosition(state, returnText);
state.text = state.text.substring(length);
return returnText;
}
function cutLine(state) {
var nextEOL = state.text.indexOf('\n');
var returnText;
if (nextEOL === -1) {
returnText = state.text;
updatePosition(state, returnText);
state.text = '';
} else {
returnText = state.text.substring(0, nextEOL);
updatePosition(state, returnText + '\n');
state.text = state.text.substring(nextEOL + 1);
}
return returnText;
}
function peekLine(state) {
var nextEOL = state.text.indexOf('\n');
return (nextEOL === -1) ? state.text : state.text.substring(0, nextEOL);
}
function parseFileBody(state) {
actList(state, [
eatOptionalBOM,
eatSignature]);
var c = state.text[0];
if (c === ' ' || c === '\t' || c === '\n') {
actList(state, [
eatUntilEOLInclusive,
parseMetadataHeaders,
eatAtLeast1EmptyLines,
parseCuesAndComments]);
} else {
state.error = "WEBVTT signature not followed by whitespace.";
}
}
// Parses all metadata headers until a cue is discovered.
function parseMetadataHeaders(state) {
while (true) {
var nextLine = peekLine(state);
if (nextLine.indexOf('-->') !== -1) {
return;
} else if (nextLine.length === 0) {
return;
} else {
var keyValue = act(state, getMetadataKeyValue);
state.metadata[keyValue[0]] = keyValue[1];
act(state, eatUntilEOLInclusive);
}
}
}
function nextSpaceOrNewline(s) {
var possible = [];
var spaceIndex = s.indexOf(' ');
if (spaceIndex >= 0) {
possible.push(spaceIndex);
}
var tabIndex = s.indexOf('\t');
if (tabIndex >= 0) {
possible.push(tabIndex);
}
var lineIndex = s.indexOf('\n');
if (lineIndex >= 0) {
possible.push(lineIndex);
}
return Math.min.apply(null, possible);
}
function getMetadataKeyValue(state) {
var next = state.text.indexOf('\n');
var pair = cut(state, next);
var colon = pair.indexOf(':');
if (colon === -1) {
state.error = 'Missing colon.';
return;
} else {
var pairName = pair.substring(0, colon);
var pairValue = pair.substring(colon + 1);
return [pairName, pairValue];
}
}
function getSettingsKeyValue(state) {
var next = nextSpaceOrNewline(state.text);
var pair = cut(state, next);
var colon = pair.indexOf(':');
if (colon === -1) {
state.error = 'Missing colon.';
return;
} else {
var pairName = pair.substring(0, colon);
var pairValue = pair.substring(colon + 1);
return [pairName, pairValue];
}
}
function parseCuesAndComments(state) {
while (true) {
var nextLine = peekLine(state);
// If NOTE is not on a line all its own, it must be followed by a space or tab.
if (nextLine.indexOf('NOTE') === 0 && ((nextLine.length === 4) || (nextLine[4] === ' ') || (nextLine[4] === '\t'))) {
actList(state, [eatComment, eatEmptyLines]);
} else if (nextLine.trim().length === 0 && state.text.length > 0) {
act(state, eatEmptyLines);
} else if (nextLine.trim().length > 0) {
act(state, parseCue);
} else {
// Everythings parsed!
return;
}
}
}
function parseCue(state) {
var nextLine = peekLine(state);
var cueId;
var errString;
if(nextLine.indexOf('-->') === -1) {
cueId = cutLine(state);
nextLine = peekLine(state);
if(nextLine.indexOf('-->') === -1) {
errString = 'Invalid WebVTT file: ' + state.src + '\n';
errString += 'Line: ' + state.line + ', ';
errString += 'Column: ' + state.column + '\n';
errString += 'Expected cue timing for cueId \''+cueId+'\' but found: ' + nextLine + '\n';
if (console.warn) {
console.warn(errString);
} else if (console.log) {
console.log(errString);
}
return; // Return leaving line for parseCuesAndComments to handle
}
}
var cueTimings = actList(state, [getTiming,
eatAtLeast1SpacesOrTabs,
eatArrow,
eatAtLeast1SpacesOrTabs,
getTiming]);
var startTime = cueTimings[0];
var endTime = cueTimings[4];
if (startTime >= endTime) {
state.error = 'Start time is not sooner than end time.';
return;
}
act(state, eatSpacesOrTabs);
var cueSettings = act(state, getCueSettings);
// Cut the newline.
cut(state, 1);
var components = act(state, getCuePayload);
if (typeof cueId === 'undefined') {
cueId = state.cues.length + 1;
}
state.cues.push({
id: cueId,
start: startTime,
end: endTime,
settings: cueSettings,
components: components
});
}
function getCueSettings(state) {
var cueSettings = {};
while (state.text.length > 0 && state.text[0] !== '\n') {
var keyValue = act(state, getSettingsKeyValue);
cueSettings[keyValue[0]] = keyValue[1];
act(state, eatSpacesOrTabs);
}
return cueSettings;
}
function getCuePayload(state) {
// Parser based on instructions in draft.
var result = {type: 'internal', tagName: '', value: '', classes: [], annotation: '', parent: null, children: [], language: ''};
var current = result;
var languageStack = [];
while (state.text.length > 0) {
var nextLine = peekLine(state);
if (nextLine.indexOf('-->') !== -1) {
break; // Reached next cue timing line; definitely end of payload
} else if (nextLine.length === 0) {
// peekLine returns '' when state.text starts with '\n'.
// A true blank line (end of cue) is two consecutive newlines, so we'll check for that here
if (state.text.length === 1 || state.text[1] === '\n') {
break; // True blank line or solitary trailing newline — end of cue
}
// If we get here we had a single newline left in state.text because the previous "line" ended with a tag;
// We'll consume it and keep parsing the rest of the cue.
cut(state, 1); // Consume the lone newline
current.children.push({type: 'string', value: '\n'}); // preserve as newline in output
continue;
}
var token = getCueToken(state);
// We'll use the tokens themselves as objects where possible.
if (token.type === 'string') {
current.children.push(token);
} else if (token.type === 'startTag') {
token.type = token.tagName;
// Define token.parent; added by Terrill to fix bug end 'endTag' loop
token.parent = current;
if ($.inArray(token.tagName, ['i', 'b', 'u', 'ruby']) !== -1) {
if (languageStack.length > 0) {
current.language = languageStack[languageStack.length - 1];
}
current.children.push(token);
current = token;
} else if (token.tagName === 'rt' && current.tagName === 'ruby') {
if (languageStack.length > 0) {
current.language = languageStack[languageStack.length - 1];
}
current.children.push(token);
current = token;
} else if (token.tagName === 'c') {
token.value = token.annotation;
if (languageStack.length > 0) {
current.language = languageStack[languageStack.length - 1];
}
current.children.push(token);
current = token;
} else if (token.tagName === 'v') {
token.value = token.annotation;
if (languageStack.length > 0) {
current.language = languageStack[languageStack.length - 1];
}
current.children.push(token);
current = token;
} else if (token.tagName === 'lang') {
languageStack.push(token.annotation);
if (languageStack.length > 0) {
current.language = languageStack[languageStack.length - 1];
}
current.children.push(token);
current = token;
}
} else if (token.type === 'endTag') {
if (token.tagName === current.type && $.inArray(token.tagName, ['c', 'i', 'b', 'u', 'ruby', 'rt', 'v']) !== -1) {
// NOTE from Terrill: This was resulting in an error because current.parent was undefined
// Fixed (I think) by assigning current token to token.parent in 'startTag' loop
current = current.parent;
} else if (token.tagName === 'lang' && current.type === 'lang') {
current = current.parent;
languageStack.pop();
} else if (token.tagName === 'ruby' && current.type === 'rt') {
current = current.parent.parent;
}
} else if (token.type === 'timestampTag') {
var tempState = {
text: token.value,
error: null,
metadata: {},
cues: [],
line: 1,
column: 1
};
try {
var timing = act(tempState, getTiming);
if (tempState.text.length === 0) {
token.value = timing;
current.push(token);
}
}
catch (e) {
// Errors are suppressed here, not sure why - VP 2026-03-02
}
}
}
return result;
}
// Gets a single cue token; uses the method in the w3 specification.
function getCueToken(state) {
var tokenState = 'data';
var result = [];
var buffer = '';
var token = {type: '', tagName: '', value: '', classes: [], annotation: '', children: []}
while (true) {
var c;
// Double newlines indicate end of token.
if (state.text.length >= 2 && state.text[0] === '\n' && state.text[1] === '\n') {
c = '\u0004';
} else if (state.text.length > 0) {
c = state.text[0];
} else {
// End of file.
c = '\u0004';
}
if (tokenState === 'data') {
if (c === '&') {
buffer = '&';
tokenState = 'escape';
} else if (c === '<') {
if (result.length === 0) {
tokenState = 'tag';
} else {
token.type = 'string';
token.value = result.join('');
return token;
}
} else if (c === '\u0004') {
return {type: 'string', value: result.join('')};
} else {
result.push(c);
}
} else if (tokenState === 'escape') {
if (c === '&') {
result.push(buffer);
buffer = '&';
} else if (c.match(/[0-9a-z]/)) {
buffer += c;
} else if (c === ';') {
if (buffer === '&') {
result.push('&');
} else if (buffer === '<') {
result.push('<');
} else if (buffer === '>') {
result.push('>');
} else if (buffer === '&lrm') {
result.push('\u200e');
} else if (buffer === '&rlm') {
result.push('\u200f');
} else if (buffer === ' ') {
result.push('\u00a0');
} else {
result.push(buffer);
result.push(';');
}
tokenState = 'data';
} else if (c === '<' || c === '\u0004') {
result.push(buffer);
token.type = 'string';
token.value = result.join('');
return token;
} else if (c === '\t' || c === '\n' || c === '\u000c' || c === ' ') { // Handle unescaped & chars as strings
result.push(buffer);
token.type = 'string';
token.value = result.join('');
return token;
} else {
result.push(buffer);
tokenState = 'data';
}
} else if (tokenState === 'tag') {
if (c === '\t' || c === '\n' || c === '\u000c' || c === ' ') {
tokenState = 'startTagAnnotation';
} else if (c === '.') {
tokenState = 'startTagClass';
} else if (c === '/') {
tokenState = 'endTag';
} else if (c.match('[0-9]')) {
tokenState = 'timestampTag';
result.push(c);
} else if (c === '>') {
cut(state, 1);
break;
} else if (c === '\u0004') {
token.tagName = '';
token.type = 'startTag';
return token;
} else {
result.push(c);
tokenState = 'startTag';
}
} else if (tokenState === 'startTag') {
if (c === '\t' || c === '\u000c' || c === ' ') {
tokenState = 'startTagAnnotation';
} else if (c === '\n') {
buffer = c;
tokenState = 'startTagAnnotation';
} else if (c === '.') {
tokenState = 'startTagClass';
} else if (c === '>') {
cut(state, 1);
token.tagName = result.join('');
token.type = 'startTag';
return token;
} else if (c === '\u0004') {
token.tagName = result.join('');
token.type = 'startTag';
return token;
} else {
result.push(c);
}
} else if (tokenState === 'startTagClass') {
if (c === '\t' || c === '\u000c' || c === ' ') {
token.classes.push(buffer);
buffer = '';
tokenState = 'startTagAnnotation';
} else if (c === '\n') {
token.classes.push(buffer);
buffer = c;
tokenState = 'startTagAnnotation';
} else if (c === '.') {
token.classes.push(buffer);
buffer = "";
} else if (c === '>') {
cut(state, 1);
token.classes.push(buffer);
token.type = 'startTag';
token.tagName = result.join('');
return token;
} else if (c === '\u0004') {
token.classes.push(buffer);
token.type = 'startTag';
token.tagName = result.join('');
return token;
} else {
buffer += 'c';
}
} else if (tokenState === 'startTagAnnotation') {
if (c === '>') {
cut(state, 1);
buffer = buffer.trim().replace(/ +/, ' ');
token.type = 'startTag';
token.tagName = result.join('');
token.annotation = buffer;
return token;
} else if (c === '\u0004') {
buffer = buffer.trim().replace(/ +/, ' ');
token.type = 'startTag';
token.tagName = result.join('');
token.annotation = buffer;
return token;
} else {
buffer += c;
}
} else if (tokenState === 'endTag') {
if (c === '>') {
cut(state, 1);
token.type = 'endTag';
token.tagName = result.join('');
return token;
} else if (c === '\u0004') {
token.type = 'endTag';
token.tagName = result.join('');
return token;
} else {
result.push(c);
}
} else if (tokenState === 'timestampTag') {
if (c === '>') {
cut(state, 1);
token.type = 'timestampTag';
token.name = result.join('');
return token;
} else if (c === '\u0004') {
token.type = 'timestampTag';
token.name = result.join('');
return token;
} else {
result.push(c);
}
} else {
throw 'Unknown tokenState ' + tokenState;
}
cut(state, 1);
}
}
function eatComment(state) {
// Cut the NOTE line.
var noteLine = cutLine(state);
if (noteLine.indexOf('-->') !== -1) {
state.error = 'Invalid syntax: --> in NOTE line.';
return;
}
while (true) {
var nextLine = peekLine(state);
if ( nextLine.trim().length === 0) {
// End of comment.
return;
} else if (nextLine.indexOf('-->') !== -1) {
state.error = 'Invalid syntax: --> in comment.';
return;
} else {
cutLine(state);
}
}
}
// Initial byte order mark.
function eatOptionalBOM(state) {
if (state.text[0] === '\ufeff') {
cut(state, 1);
}
}
// "WEBVTT" string.
function eatSignature(state) {
if (state.text.substring(0,6) === 'WEBVTT') {
cut(state, 6);
} else {
state.error = 'Invalid signature.';
}
}
function eatArrow(state) {
if (state.text.length < 3 || state.text.substring(0,3) !== '-->') {
state.error = 'Missing -->';
} else {
cut(state, 3);
}
}
function eatSpacesOrTabs(state) {
while (state.text[0] === '\t' || state.text[0] === ' ') {
cut(state, 1);
}
}
function eatAtLeast1SpacesOrTabs(state) {
var numEaten = 0;
while (state.text[0] === '\t' || state.text[0] === ' ') {
cut(state, 1);
numEaten += 1;
}
if (numEaten === 0) {
state.error = 'Missing space.';
}
}
function eatUntilEOLInclusive(state) {
var nextEOL = state.text.indexOf('\n');
if (nextEOL === -1) {
state.error = 'Missing EOL.';
} else {
cut(state, nextEOL + 1);
}
}
function eatEmptyLines(state) {
while (state.text.length > 0) {
var nextLine = peekLine(state);
if ( nextLine.trim().length === 0) {
cutLine(state);
} else {
break;
}
}
}
// Eats empty lines, but throws an error if there's not at least one.
function eatAtLeast1EmptyLines(state) {
var linesEaten = 0;
while (state.text.length > 0) {
var nextLine = peekLine(state);
if ( nextLine.trim().length === 0) {
cutLine(state);
linesEaten += 1;
} else {
break;
}
}
if (linesEaten === 0) {
state.error = 'Missing empty line.';
}
}
function getTiming(state) {
var nextSpace = nextSpaceOrNewline(state.text);
if (nextSpace === -1) {
state.error('Missing timing.');
return;
}
var timestamp = cut(state, nextSpace);
// The spec requires exactly 2 characters for minutes and seconds, and 2+ for hours,
// but some VTT generation creates 1 digit hour times (e.g. "1:02:24.000 --> 1:04:48.000") and it seems harmless to allow that here
var results = /((\d+):)?((\d\d):)(\d\d).(\d\d\d)|(\d+).(\d\d\d)/.exec(timestamp);
if (!results) {
state.error = 'Unable to parse timestamp';
return;
}
var time = 0;
var hours = results[2];
var minutes = results[4];
if (minutes) {
if (parseInt(minutes, 10) > 59) {
state.error = 'Invalid minute range';
return;
}
if (hours) {
time += 3600 * parseInt(hours, 10);
}
time += 60 * parseInt(minutes, 10);
var seconds = results[5];
if (parseInt(seconds, 10) > 59) {
state.error = 'Invalid second range';
return;
}
time += parseInt(seconds, 10);
time += parseInt(results[6], 10) / 1000;
} else {
time += parseInt(results[7], 10);
time += parseInt(results[8], 10) / 1000;
}
return time;
}
}
export default addWebvttFunctions;