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
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
|
/* decsrtsub.c
Copyright (c) 2003-2019 HandBrake Team
This file is part of the HandBrake source code
Homepage: <http://handbrake.fr/>.
It may be used under the terms of the GNU General Public License v2.
For full terms see the file COPYING file or visit http://www.gnu.org/licenses/gpl-2.0.html
*/
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <iconv.h>
#include <errno.h>
#include "hb.h"
#include "colormap.h"
#include "decsrtsub.h"
struct start_and_end {
unsigned long start, end;
};
enum
{
k_state_inEntry,
k_state_inEntry_or_new,
k_state_potential_new_entry,
k_state_timecode,
};
typedef struct srt_entry_s {
long offset, duration;
long start, stop;
char text[1024];
int pos;
} srt_entry_t;
/*
* Store all context in the work private struct,
*/
struct hb_work_private_s
{
hb_job_t * job;
FILE * file;
char buf[1024];
int pos;
int end;
char utf8_buf[2048];
int utf8_pos;
int utf8_end;
int utf8_bom_skipped;
unsigned long current_time;
unsigned long number_of_entries;
unsigned long last_entry_number;
unsigned long current_state;
srt_entry_t current_entry;
iconv_t *iconv_context;
hb_subtitle_t *subtitle;
uint64_t start_time; // In HB time
uint64_t stop_time; // In HB time
int line; // SSA line number
};
static char* srt_markup_to_ssa(char *srt, int *len)
{
char terminator;
char color[40];
uint32_t rgb;
*len = 0;
if (srt[0] != '<' && srt[0] != '{')
return NULL;
if (srt[0] == '<')
terminator = '>';
else
terminator = '}';
if (srt[1] == 'i' && srt[2] == terminator)
{
*len = 3;
return hb_strdup_printf("{\\i1}");
}
else if (srt[1] == 'b' && srt[2] == terminator)
{
*len = 3;
return hb_strdup_printf("{\\b1}");
}
else if (srt[1] == 'u' && srt[2] == terminator)
{
*len = 3;
return hb_strdup_printf("{\\u1}");
}
else if (srt[1] == '/' && srt[2] == 'i' && srt[3] == terminator)
{
*len = 4;
return hb_strdup_printf("{\\i0}");
}
else if (srt[1] == '/' && srt[2] == 'b' && srt[3] == terminator)
{
*len = 4;
return hb_strdup_printf("{\\b0}");
}
else if (srt[1] == '/' && srt[2] == 'u' && srt[3] == terminator)
{
*len = 4;
return hb_strdup_printf("{\\u0}");
}
else if (srt[0] == '<' && !strncmp(srt + 1, "font", 4))
{
int match;
match = sscanf(srt + 1, "font color=\"%39[^\"]\">", color);
if (match != 1)
{
return NULL;
}
while (srt[*len] != '>') (*len)++;
(*len)++;
if (color[0] == '#')
rgb = strtol(color + 1, NULL, 16);
else
rgb = hb_rgb_lookup_by_name(color);
return hb_strdup_printf("{\\1c&H%X&}", HB_RGB_TO_BGR(rgb));
}
else if (srt[0] == '<' && srt[1] == '/' && !strncmp(srt + 2, "font", 4) &&
srt[6] == '>')
{
*len = 7;
return hb_strdup_printf("{\\1c&HFFFFFF&}");
}
return NULL;
}
void hb_srt_to_ssa(hb_buffer_t *sub_in, int line)
{
if (sub_in->size == 0)
return;
// null terminate input if not already terminated
if (sub_in->data[sub_in->size-1] != 0)
{
hb_buffer_realloc(sub_in, ++sub_in->size);
sub_in->data[sub_in->size - 1] = 0;
}
char * srt = (char*)sub_in->data;
// SSA markup expands a little over SRT, so allocate a bit of extra
// space. More will be realloc'd if needed.
hb_buffer_t * sub = hb_buffer_init(sub_in->size + 80);
char * ssa, *ssa_markup;
int skip, len, pos, ii;
// Exchange data between input sub and new ssa_sub
// After this, sub_in contains ssa data
hb_buffer_swap_copy(sub_in, sub);
ssa = (char*)sub_in->data;
sprintf((char*)sub_in->data, "%d,,Default,,0,0,0,,", line);
pos = strlen((char*)sub_in->data);
ii = 0;
while (srt[ii] != '\0')
{
if ((ssa_markup = srt_markup_to_ssa(srt + ii, &skip)) != NULL)
{
len = strlen(ssa_markup);
hb_buffer_realloc(sub_in, pos + len + 1);
// After realloc, sub_in->data may change
ssa = (char*)sub_in->data;
sprintf(ssa + pos, "%s", ssa_markup);
free(ssa_markup);
pos += len;
ii += skip;
}
else
{
hb_buffer_realloc(sub_in, pos + 4);
// After realloc, sub_in->data may change
ssa = (char*)sub_in->data;
if (srt[ii] == '\r')
{
if (srt[ii + 1] == '\n')
{
ii++;
}
if (srt[ii + 1] != 0)
{
ssa[pos++] = '\\';
ssa[pos++] = 'N';
}
ii++;
}
else if (srt[ii] == '\n')
{
if (srt[ii + 1] != 0)
{
ssa[pos++] = '\\';
ssa[pos++] = 'N';
}
ii++;
}
else
{
ssa[pos++] = srt[ii++];
}
}
}
ssa[pos] = '\0';
sub_in->size = pos + 1;
hb_buffer_close(&sub);
}
static int
read_time_from_string( const char* timeString, struct start_and_end *result )
{
// for ex. 00:00:15,248 --> 00:00:16,545
long houres1, minutes1, seconds1, milliseconds1,
houres2, minutes2, seconds2, milliseconds2;
int scanned;
scanned = sscanf(timeString, "%ld:%ld:%ld,%ld --> %ld:%ld:%ld,%ld\n",
&houres1, &minutes1, &seconds1, &milliseconds1,
&houres2, &minutes2, &seconds2, &milliseconds2);
if (scanned != 8)
{
scanned = sscanf(timeString, "%ld:%ld:%ld.%ld --> %ld:%ld:%ld.%ld\n",
&houres1, &minutes1, &seconds1, &milliseconds1,
&houres2, &minutes2, &seconds2, &milliseconds2);
if (scanned != 8)
{
return 0;
}
}
result->start =
milliseconds1 + seconds1*1000 + minutes1*60*1000 + houres1*60*60*1000;
result->end =
milliseconds2 + seconds2*1000 + minutes2*60*1000 + houres2*60*60*1000;
return 1;
}
static int utf8_fill( hb_work_private_t * pv )
{
int bytes, conversion = 0;
size_t out_size;
/* Align utf8 data to beginning of the buffer so that we can
* fill the buffer to its maximum */
memmove( pv->utf8_buf, pv->utf8_buf + pv->utf8_pos, pv->utf8_end - pv->utf8_pos );
pv->utf8_end -= pv->utf8_pos;
pv->utf8_pos = 0;
out_size = 2048 - pv->utf8_end;
while( out_size )
{
char *p, *q;
size_t in_size, retval;
if( pv->end == pv->pos )
{
bytes = fread( pv->buf, 1, 1024, pv->file );
pv->pos = 0;
pv->end = bytes;
if( bytes == 0 )
{
return conversion;
}
}
p = pv->buf + pv->pos;
q = pv->utf8_buf + pv->utf8_end;
in_size = pv->end - pv->pos;
retval = iconv( pv->iconv_context, &p, &in_size, &q, &out_size);
if (q != pv->utf8_buf + pv->utf8_end)
{
conversion = 1;
}
pv->utf8_end = q - pv->utf8_buf;
pv->pos = p - pv->buf;
if ( !pv->utf8_bom_skipped )
{
uint8_t *buf = (uint8_t*)pv->utf8_buf;
if (buf[0] == 0xef && buf[1] == 0xbb && buf[2] == 0xbf)
{
pv->utf8_pos = 3;
if (pv->utf8_pos == pv->utf8_end)
{
// If only the bom was converted, indicate no conversion
conversion = 0;
}
}
pv->utf8_bom_skipped = 1;
}
if( ( retval == -1 ) && ( errno == EINVAL ) )
{
/* Incomplete multibyte sequence, read more data */
memmove( pv->buf, p, pv->end - pv->pos );
pv->end -= pv->pos;
pv->pos = 0;
bytes = fread( pv->buf + pv->end, 1, 1024 - pv->end, pv->file );
if( bytes == 0 )
{
return conversion;
}
pv->end += bytes;
} else if ( ( retval == -1 ) && ( errno == EILSEQ ) )
{
hb_error( "Invalid byte for codeset in input, discard byte" );
/* Try the next byte of the input */
pv->pos++;
} else if ( ( retval == -1 ) && ( errno == E2BIG ) )
{
/* buffer full */
return conversion;
}
}
return 1;
}
static int get_line( hb_work_private_t * pv, char *buf, int size )
{
int i;
char c;
// clear remnants of the previous line before progessing a new one
memset(buf, '\0', size);
/* Find newline in converted UTF-8 buffer */
for( i = 0; i < size - 1; i++ )
{
if( pv->utf8_pos >= pv->utf8_end )
{
if( !utf8_fill( pv ) )
{
if( i )
return 1;
else
return 0;
}
}
c = pv->utf8_buf[pv->utf8_pos++];
if( c == '\n' )
{
buf[i] = '\n';
buf[i+1] = '\0';
return 1;
}
buf[i] = c;
}
buf[0] = '\0';
return 1;
}
/*
* Read the SRT file and put the entries into the subtitle fifo for all to read
*/
static hb_buffer_t *srt_read( hb_work_private_t *pv )
{
char line_buffer[1024];
int reprocess = 0, resync = 0;
if( !pv->file )
{
return NULL;
}
while( reprocess || get_line( pv, line_buffer, sizeof( line_buffer ) ) )
{
reprocess = 0;
switch (pv->current_state)
{
case k_state_timecode:
{
struct start_and_end timing;
int result;
result = read_time_from_string( line_buffer, &timing );
if (!result)
{
resync = 1;
pv->current_state = k_state_potential_new_entry;
continue;
}
pv->current_entry.duration = timing.end - timing.start;
pv->current_entry.offset = timing.start - pv->current_time;
pv->current_time = timing.end;
pv->current_entry.start = timing.start;
pv->current_entry.stop = timing.end;
pv->current_state = k_state_inEntry;
continue;
}
case k_state_inEntry_or_new:
{
char *endpoint;
/*
* Is this really new next entry begin?
* Look for entry number.
*/
strtol(line_buffer, &endpoint, 10);
if (endpoint == line_buffer ||
(endpoint && *endpoint != '\n' && *endpoint != '\r'))
{
/*
* Doesn't resemble an entry number
* must still be in an entry
*/
if (!resync)
{
reprocess = 1;
pv->current_state = k_state_inEntry;
}
continue;
}
reprocess = 1;
pv->current_state = k_state_potential_new_entry;
break;
}
case k_state_inEntry:
{
char *q;
int size, len;
// If the current line is empty, we assume this is the
// separation between two entries. In case we are wrong,
// the mistake is corrected in the next state.
if (strcmp(line_buffer, "\n") == 0 || strcmp(line_buffer, "\r\n") == 0) {
pv->current_state = k_state_potential_new_entry;
continue;
}
q = pv->current_entry.text + pv->current_entry.pos;
len = strlen( line_buffer );
size = MIN(1024 - pv->current_entry.pos - 1, len );
memcpy(q, line_buffer, size);
pv->current_entry.pos += size;
pv->current_entry.text[pv->current_entry.pos] = '\0';
break;
}
case k_state_potential_new_entry:
{
char *endpoint;
long entry_number;
hb_buffer_t *buffer = NULL;
/*
* Is this really new next entry begin?
*/
entry_number = strtol(line_buffer, &endpoint, 10);
if (!resync && (*line_buffer == '\n' || *line_buffer == '\r'))
{
/*
* Well.. looks like we are in the wrong mode.. lets add the
* newline we misinterpreted...
*/
strncat(pv->current_entry.text, " ", sizeof(pv->current_entry.text) - strlen(pv->current_entry.text) - 1);
pv->current_state = k_state_inEntry_or_new;
continue;
}
if (endpoint == line_buffer ||
(endpoint && *endpoint != '\n' && *endpoint != '\r'))
{
/*
* Well.. looks like we are in the wrong mode.. lets add the
* line we misinterpreted...
*/
if (!resync)
{
reprocess = 1;
pv->current_state = k_state_inEntry;
}
continue;
}
/*
* We found the next entry - or a really rare error condition
*/
pv->last_entry_number = entry_number;
resync = 0;
if (*pv->current_entry.text != '\0')
{
long length = 0;
char *p, *q;
uint64_t start_time = ( pv->current_entry.start +
pv->subtitle->config.offset ) * 90;
uint64_t stop_time = ( pv->current_entry.stop +
pv->subtitle->config.offset ) * 90;
if( !( start_time >= pv->start_time && stop_time < pv->stop_time ) )
{
hb_deep_log( 3, "Discarding SRT at time start %"PRId64", stop %"PRId64, start_time, stop_time);
memset( &pv->current_entry, 0, sizeof( srt_entry_t ) );
++(pv->number_of_entries);
pv->current_state = k_state_timecode;
continue;
}
for (q = p = pv->current_entry.text; *p != '\0'; p++)
{
if (*p == '\r' || *p == '\n')
{
// sanitize newline codes to a single '\n'
// and delete any newline at the end of the subtitle
if (*(p + 1) != '\n' && *(p + 1) != '\r' &&
*(p + 1) != '\0')
{
*q = '\n';
q++;
length++;
}
}
else
{
*q = *p;
q++;
length++;
}
}
*q = '\0';
buffer = hb_buffer_init( length + 1 );
if( buffer )
{
buffer->s.start = start_time - pv->start_time;
buffer->s.stop = stop_time - pv->start_time;
memcpy( buffer->data, pv->current_entry.text, length + 1 );
}
}
memset( &pv->current_entry, 0, sizeof( srt_entry_t ) );
++(pv->number_of_entries);
pv->current_state = k_state_timecode;
if( buffer )
{
return buffer;
}
continue;
}
}
}
hb_buffer_t *buffer = NULL;
if (*pv->current_entry.text != '\0')
{
long length = 0;
char *p, *q;
uint64_t start_time = ( pv->current_entry.start +
pv->subtitle->config.offset ) * 90;
uint64_t stop_time = ( pv->current_entry.stop +
pv->subtitle->config.offset ) * 90;
if( !( start_time >= pv->start_time && stop_time < pv->stop_time ) )
{
hb_deep_log( 3, "Discarding SRT at time start %"PRId64", stop %"PRId64, start_time, stop_time);
memset( &pv->current_entry, 0, sizeof( srt_entry_t ) );
return NULL;
}
for (q = p = pv->current_entry.text; *p != '\0'; p++)
{
if (*p == '\r' || *p == '\n')
{
// sanitize newline codes to a single '\n'
// and delete any newline at the end of the subtitle
if (*(p + 1) != '\n' && *(p + 1) != '\r' && *(p + 1) != '\0')
{
*q = '\n';
q++;
length++;
}
}
else
{
*q = *p;
q++;
length++;
}
}
*q = '\0';
buffer = hb_buffer_init( length + 1 );
if( buffer )
{
buffer->s.start = start_time - pv->start_time;
buffer->s.stop = stop_time - pv->start_time;
memcpy( buffer->data, pv->current_entry.text, length + 1 );
}
}
memset( &pv->current_entry, 0, sizeof( srt_entry_t ) );
if( buffer )
{
return buffer;
}
return NULL;
}
static int decsrtInit( hb_work_object_t * w, hb_job_t * job )
{
hb_work_private_t * pv;
int i;
hb_chapter_t * chapter;
pv = calloc( 1, sizeof( hb_work_private_t ) );
if (pv == NULL)
{
goto fail;
}
w->private_data = pv;
pv->job = job;
pv->current_state = k_state_potential_new_entry;
pv->number_of_entries = 0;
pv->last_entry_number = 0;
pv->current_time = 0;
pv->subtitle = w->subtitle;
/*
* Figure out the start and stop times from the chapters being
* encoded - drop subtitle not in this range.
*/
pv->start_time = 0;
for( i = 1; i < job->chapter_start; ++i )
{
chapter = hb_list_item( job->list_chapter, i - 1 );
if( chapter )
{
pv->start_time += chapter->duration;
} else {
hb_error( "Could not locate chapter %d for SRT start time", i );
}
}
pv->stop_time = pv->start_time;
for( i = job->chapter_start; i <= job->chapter_end; ++i )
{
chapter = hb_list_item( job->list_chapter, i - 1 );
if( chapter )
{
pv->stop_time += chapter->duration;
} else {
hb_error( "Could not locate chapter %d for SRT start time", i );
}
}
hb_deep_log(3, "SRT Start time %"PRId64", stop time %"PRId64,
pv->start_time, pv->stop_time);
if (job->pts_to_start != 0)
{
pv->start_time = AV_NOPTS_VALUE;
}
pv->iconv_context = iconv_open( "utf-8", pv->subtitle->config.src_codeset );
if( pv->iconv_context == (iconv_t) -1 )
{
hb_error("Could not open the iconv library with those file formats\n");
goto fail;
} else {
memset( &pv->current_entry, 0, sizeof( srt_entry_t ) );
pv->file = hb_fopen(w->subtitle->config.src_filename, "r");
if( !pv->file )
{
hb_error("Could not open the SRT subtitle file '%s'\n",
w->subtitle->config.src_filename);
goto fail;
}
}
// Generate generic SSA Script Info.
int height = job->title->geometry.height - job->crop[0] - job->crop[1];
int width = job->title->geometry.width - job->crop[2] - job->crop[3];
hb_subtitle_add_ssa_header(w->subtitle, HB_FONT_SANS,
.066 * job->title->geometry.height,
width, height);
return 0;
fail:
if (pv != NULL)
{
if (pv->iconv_context != (iconv_t) -1)
{
iconv_close(pv->iconv_context);
}
if (pv->file != NULL)
{
fclose(pv->file);
}
free(pv);
w->private_data = NULL;
}
return 1;
}
static int decsrtWork( hb_work_object_t * w, hb_buffer_t ** buf_in,
hb_buffer_t ** buf_out )
{
hb_work_private_t * pv = w->private_data;
hb_buffer_t * out = NULL;
if (pv->job->reader_pts_offset == AV_NOPTS_VALUE)
{
// We need to wait for reader to initialize it's pts offset so that
// we know where to start reading SRTs.
*buf_out = NULL;
return HB_WORK_OK;
}
if (pv->start_time == AV_NOPTS_VALUE)
{
pv->start_time = pv->job->reader_pts_offset;
if (pv->job->pts_to_stop > 0)
{
pv->stop_time = pv->job->pts_to_start + pv->job->pts_to_stop;
}
}
out = srt_read( pv );
if (out != NULL)
{
hb_srt_to_ssa(out, ++pv->line);
*buf_out = out;
return HB_WORK_OK;
} else {
*buf_out = hb_buffer_eof_init();
return HB_WORK_DONE;
}
}
static void decsrtClose( hb_work_object_t * w )
{
hb_work_private_t * pv = w->private_data;
if (pv != NULL)
{
fclose( pv->file );
iconv_close(pv->iconv_context);
free( w->private_data );
}
}
hb_work_object_t hb_decsrtsub =
{
WORK_DECSRTSUB,
"SRT Subtitle Decoder",
decsrtInit,
decsrtWork,
decsrtClose
};
|