File: WebVTTParser.cpp

package info (click to toggle)
qtwebkit 2.3.4.dfsg-10
  • links: PTS, VCS
  • area: main
  • in suites: buster
  • size: 290,632 kB
  • sloc: cpp: 1,417,515; python: 85,048; ansic: 39,357; perl: 38,862; ruby: 10,313; objc: 9,505; xml: 8,679; asm: 3,864; yacc: 2,458; sh: 1,237; lex: 813; makefile: 592; java: 228; php: 79
file content (427 lines) | stat: -rw-r--r-- 14,986 bytes parent folder | download | duplicates (3)
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
/*
 * Copyright (C) 2011 Google Inc.  All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions are
 * met:
 *
 *     * Redistributions of source code must retain the above copyright
 * notice, this list of conditions and the following disclaimer.
 *     * Redistributions in binary form must reproduce the above
 * copyright notice, this list of conditions and the following disclaimer
 * in the documentation and/or other materials provided with the
 * distribution.
 *     * Neither the name of Google Inc. nor the names of its
 * contributors may be used to endorse or promote products derived from
 * this software without specific prior written permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
 * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
 * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
 * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
 * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
 * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
 * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 */

#include "config.h"

#if ENABLE(VIDEO_TRACK)

#include "WebVTTParser.h"

#include "HTMLElement.h"
#include "ProcessingInstruction.h"
#include "SegmentedString.h"
#include "Text.h"
#include <wtf/text/WTFString.h>

namespace WebCore {

const double secondsPerHour = 3600;
const double secondsPerMinute = 60;
const double secondsPerMillisecond = 0.001;
const double malformedTime = -1;
const unsigned bomLength = 3;
const unsigned fileIdentifierLength = 6;

String WebVTTParser::collectDigits(const String& input, unsigned* position)
{
    StringBuilder digits;
    while (*position < input.length() && isASCIIDigit(input[*position]))
        digits.append(input[(*position)++]);
    return digits.toString();
}

String WebVTTParser::collectWord(const String& input, unsigned* position)
{
    StringBuilder string;
    while (*position < input.length() && !isASpace(input[*position]))
        string.append(input[(*position)++]);
    return string.toString();
}

WebVTTParser::WebVTTParser(WebVTTParserClient* client, ScriptExecutionContext* context)
    : m_scriptExecutionContext(context)
    , m_state(Initial)
    , m_currentStartTime(0)
    , m_currentEndTime(0)
    , m_tokenizer(WebVTTTokenizer::create())
    , m_client(client)
{
}

void WebVTTParser::getNewCues(Vector<RefPtr<TextTrackCue> >& outputCues)
{
    outputCues = m_cuelist;
    m_cuelist.clear();
}

void WebVTTParser::parseBytes(const char* data, unsigned length)
{
    // 4.8.10.13.3 WHATWG WebVTT Parser algorithm.
    // 1-3 - Initial setup.
    unsigned position = 0;

    while (position < length) {
        String line = collectNextLine(data, length, &position);
        
        switch (m_state) {
        case Initial:
            // Buffer up at least 9 bytes before proceeding with checking for the file identifier.
            m_identifierData.append(data, length);
            if (m_identifierData.size() < bomLength + fileIdentifierLength)
                return;

            // 4-12 - Collect the first line and check for "WEBVTT".
            if (!hasRequiredFileIdentifier()) {
                if (m_client)
                    m_client->fileFailedToParse();
                return;
            }

            m_state = Header;
            m_identifierData.clear();
            break;
        
        case Header:
            // 13-18 - Allow a header (comment area) under the WEBVTT line.
            if (line.isEmpty())
                m_state = Id;
            break;
        
        case Id:
            // 19-29 - Allow any number of line terminators, then initialize new cue values.
            if (line.isEmpty())
                break;
            resetCueValues();
            
            // 30-39 - Check if this line contains an optional identifier or timing data.
            m_state = collectCueId(line);
            break;
        
        case TimingsAndSettings:
            // 40 - Collect cue timings and settings.
            m_state = collectTimingsAndSettings(line);
            break;
        
        case CueText:
            // 41-53 - Collect the cue text, create a cue, and add it to the output.
            m_state = collectCueText(line, length, position);
            break;

        case BadCue:
            // 54-62 - Collect and discard the remaining cue.
            m_state = ignoreBadCue(line);
            break;
        }
    }
}

bool WebVTTParser::hasRequiredFileIdentifier()
{
    // A WebVTT file identifier consists of an optional BOM character,
    // the string "WEBVTT" followed by an optional space or tab character,
    // and any number of characters that are not line terminators ...
    unsigned position = 0;
    if (m_identifierData.size() >= bomLength && m_identifierData[0] == '\xEF' && m_identifierData[1] == '\xBB' && m_identifierData[2] == '\xBF')
        position += bomLength;
    String line = collectNextLine(m_identifierData.data(), m_identifierData.size(), &position);

    if (line.length() < fileIdentifierLength)
        return false;
    if (line.substring(0, fileIdentifierLength) != "WEBVTT")
        return false;
    if (line.length() > fileIdentifierLength && line[fileIdentifierLength] != ' ' && line[fileIdentifierLength] != '\t')
        return false;

    return true;
}

WebVTTParser::ParseState WebVTTParser::collectCueId(const String& line)
{
    if (line.contains("-->"))
        return collectTimingsAndSettings(line);
    m_currentId = line;
    return TimingsAndSettings;
}

WebVTTParser::ParseState WebVTTParser::collectTimingsAndSettings(const String& line)
{
    // 4.8.10.13.3 Collect WebVTT cue timings and settings.
    // 1-3 - Let input be the string being parsed and position be a pointer into input
    unsigned position = 0;
    skipWhiteSpace(line, &position);

    // 4-5 - Collect a WebVTT timestamp. If that fails, then abort and return failure. Otherwise, let cue's text track cue start time be the collected time.
    m_currentStartTime = collectTimeStamp(line, &position);
    if (m_currentStartTime == malformedTime)
        return BadCue;
    if (position >= line.length())
        return BadCue;
    char nextChar = line[position++];
    if (nextChar != ' ' && nextChar != '\t')
        return BadCue;
    skipWhiteSpace(line, &position);

    // 6-9 - If the next three characters are not "-->", abort and return failure.
    if (line.find("-->", position) == notFound)
        return BadCue;
    position += 3;
    if (position >= line.length())
        return BadCue;
    nextChar = line[position++];
    if (nextChar != ' ' && nextChar != '\t')
        return BadCue;
    skipWhiteSpace(line, &position);

    // 10-11 - Collect a WebVTT timestamp. If that fails, then abort and return failure. Otherwise, let cue's text track cue end time be the collected time.
    m_currentEndTime = collectTimeStamp(line, &position);
    if (m_currentEndTime == malformedTime)
        return BadCue;
    skipWhiteSpace(line, &position);

    // 12 - Parse the WebVTT settings for the cue (conducted in TextTrackCue).
    m_currentSettings = line.substring(position, line.length()-1);
    return CueText;
}

WebVTTParser::ParseState WebVTTParser::collectCueText(const String& line, unsigned length, unsigned position)
{
    if (line.isEmpty()) {
        createNewCue();
        return Id;
    }
    if (!m_currentContent.isEmpty())
        m_currentContent.append("\n");
    m_currentContent.append(line);

    if (position >= length)
        createNewCue();
                
    return CueText;
}

WebVTTParser::ParseState WebVTTParser::ignoreBadCue(const String& line)
{
    if (!line.isEmpty())
        return BadCue;
    return Id;
}

PassRefPtr<DocumentFragment>  WebVTTParser::createDocumentFragmentFromCueText(const String& text)
{
    // Cue text processing based on
    // 4.8.10.13.4 WebVTT cue text parsing rules and
    // 4.8.10.13.5 WebVTT cue text DOM construction rules.

    if (!text.length())
        return 0;

    ASSERT(m_scriptExecutionContext->isDocument());
    Document* document = static_cast<Document*>(m_scriptExecutionContext);
    
    RefPtr<DocumentFragment> fragment = DocumentFragment::create(document);
    m_currentNode = fragment;
    m_tokenizer->reset();
    m_token.clear();
    
    SegmentedString content(text);
    while (m_tokenizer->nextToken(content, m_token))
        constructTreeFromToken(document);
    
    return fragment.release();
}

void WebVTTParser::createNewCue()
{
    if (!m_currentContent.length())
        return;

    RefPtr<TextTrackCue> cue = TextTrackCue::create(m_scriptExecutionContext, m_currentStartTime, m_currentEndTime, m_currentContent.toString());
    cue->setId(m_currentId);
    cue->setCueSettings(m_currentSettings);

    m_cuelist.append(cue);
    if (m_client)
        m_client->newCuesParsed();
}

void WebVTTParser::resetCueValues()
{
    m_currentId = emptyString();
    m_currentSettings = emptyString();
    m_currentStartTime = 0;
    m_currentEndTime = 0;
    m_currentContent.clear();
}

double WebVTTParser::collectTimeStamp(const String& line, unsigned* position)
{
    // 4.8.10.13.3 Collect a WebVTT timestamp.
    // 1-4 - Initial checks, let most significant units be minutes.
    enum Mode { minutes, hours };
    Mode mode = minutes;
    if (*position >= line.length() || !isASCIIDigit(line[*position]))
        return malformedTime;

    // 5-6 - Collect a sequence of characters that are 0-9.
    String digits1 = collectDigits(line, position);
    int value1 = digits1.toInt();

    // 7 - If not 2 characters or value is greater than 59, interpret as hours.
    if (digits1.length() != 2 || value1 > 59)
        mode = hours;

    // 8-12 - Collect the next sequence of 0-9 after ':' (must be 2 chars).
    if (*position >= line.length() || line[(*position)++] != ':')
        return malformedTime;
    if (*position >= line.length() || !isASCIIDigit(line[(*position)]))
        return malformedTime;
    String digits2 = collectDigits(line, position);
    int value2 = digits2.toInt();
    if (digits2.length() != 2) 
        return malformedTime;

    // 13 - Detect whether this timestamp includes hours.
    int value3;
    if (mode == hours || (*position < line.length() && line[*position] == ':')) {
        if (*position >= line.length() || line[(*position)++] != ':')
            return malformedTime;
        if (*position >= line.length() || !isASCIIDigit(line[*position]))
            return malformedTime;
        String digits3 = collectDigits(line, position);
        if (digits3.length() != 2)
            return malformedTime;
        value3 = digits3.toInt();
    } else {
        value3 = value2;
        value2 = value1;
        value1 = 0;
    }

    // 14-19 - Collect next sequence of 0-9 after '.' (must be 3 chars).
    if (*position >= line.length() || line[(*position)++] != '.')
        return malformedTime;
    if (*position >= line.length() || !isASCIIDigit(line[*position]))
        return malformedTime;
    String digits4 = collectDigits(line, position);
    if (digits4.length() != 3)
        return malformedTime;
    int value4 = digits4.toInt();
    if (value2 > 59 || value3 > 59)
        return malformedTime;

    // 20-21 - Calculate result.
    return (value1 * secondsPerHour) + (value2 * secondsPerMinute) + value3 + (value4 * secondsPerMillisecond);
}

void WebVTTParser::constructTreeFromToken(Document* document)
{
    AtomicString tokenTagName(m_token.name().data(), m_token.name().size());
    QualifiedName tagName(nullAtom, tokenTagName, xhtmlNamespaceURI);

    // http://dev.w3.org/html5/webvtt/#webvtt-cue-text-dom-construction-rules
    
    switch (m_token.type()) {
    case WebVTTTokenTypes::Character: {
        String content(m_token.characters().data(), m_token.characters().size());
        RefPtr<Text> child = Text::create(document, content);
        m_currentNode->parserAppendChild(child);
        break;
    }
    case WebVTTTokenTypes::StartTag: {
        RefPtr<HTMLElement> child;
        if (isRecognizedTag(tokenTagName))
            child = HTMLElement::create(tagName, document);
        else if (m_token.name().size() == 1 && m_token.name()[0] == 'c')
            child = HTMLElement::create(spanTag, document);
        else if (m_token.name().size() == 1 && m_token.name()[0] == 'v')
            child = HTMLElement::create(qTag, document);

        if (child) {
            if (m_token.classes().size() > 0)
                child->setAttribute(classAttr, AtomicString(m_token.classes().data(), m_token.classes().size()));
            if (child->hasTagName(qTag))
                child->setAttribute(titleAttr, AtomicString(m_token.annotation().data(), m_token.annotation().size()));
            m_currentNode->parserAppendChild(child);
            m_currentNode = child;
        }
        break;
    }
    case WebVTTTokenTypes::EndTag:
        if (isRecognizedTag(tokenTagName)
            || (m_token.name().size() == 1 && m_token.name()[0] == 'c')
            || (m_token.name().size() == 1 && m_token.name()[0] == 'v')) {
            if (m_currentNode->parentNode())
                m_currentNode = m_currentNode->parentNode();
        }
        break;
    case WebVTTTokenTypes::TimestampTag: {
        unsigned position = 0;
        double time = collectTimeStamp(m_token.characters().data(), &position);
        if (time != malformedTime)
            m_currentNode->parserAppendChild(ProcessingInstruction::create(document, "timestamp", String(m_token.characters().data(), m_token.characters().size())));
        break;
    }
    default:
        break;
    }
    m_token.clear();
}

void WebVTTParser::skipWhiteSpace(const String& line, unsigned* position)
{
    while (*position < line.length() && isASpace(line[*position]))
        (*position)++;
}

void WebVTTParser::skipLineTerminator(const char* data, unsigned length, unsigned* position)
{
    if (*position >= length)
        return;
    if (data[*position] == '\r')
        (*position)++;
    if (*position >= length)
        return;
    if (data[*position] == '\n')
        (*position)++;
}

String WebVTTParser::collectNextLine(const char* data, unsigned length, unsigned* position)
{
    unsigned oldPosition = *position;
    while (*position < length && data[*position] != '\r' && data[*position] != '\n')
        (*position)++;
    String line = String::fromUTF8(data + oldPosition, *position - oldPosition);
    skipLineTerminator(data, length, position);
    return line;
}

}

#endif