forked from kripken/speak.js
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathreadclause.cpp
executable file
·2763 lines (2384 loc) · 62.9 KB
/
readclause.cpp
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
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/***************************************************************************
* Copyright (C) 2005 to 2011 by Jonathan Duddington *
* email: [email protected] *
* *
* This program is free software; you can redistribute it and/or modify *
* it under the terms of the GNU General Public License as published by *
* the Free Software Foundation; either version 3 of the License, or *
* (at your option) any later version. *
* *
* This program is distributed in the hope that it will be useful, *
* but WITHOUT ANY WARRANTY; without even the implied warranty of *
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the *
* GNU General Public License for more details. *
* *
* You should have received a copy of the GNU General Public License *
* along with this program; if not, write see: *
* <http://www.gnu.org/licenses/>. *
***************************************************************************/
#include "StdAfx.h"
#include <stdio.h>
#include <ctype.h>
#include <stdlib.h>
#include <string.h>
#include <wctype.h>
//#include <wchar.h>
#include <math.h>
#include "speak_lib.h"
#include "speech.h"
#include "phoneme.h"
#include "synthesize.h"
#include "voice.h"
#include "translate.h"
#ifdef PLATFORM_POSIX
#include <unistd.h>
#endif
#include <locale.h>
#define N_XML_BUF 256
static const char *xmlbase = ""; // base URL from <speak>
static int namedata_ix=0;
static int n_namedata = 0;
char *namedata = NULL;
static FILE *f_input = NULL;
static int ungot_char2 = 0;
unsigned char *p_textinput;
wchar_t *p_wchar_input;
static int ungot_char;
static const char *ungot_word = NULL;
static int end_of_input;
static int ignore_text=0; // set during <sub> ... </sub> to ignore text which has been replaced by an alias
static int audio_text=0; // set during <audio> ... </audio>
static int clear_skipping_text = 0; // next clause should clear the skipping_text flag
int count_characters = 0;
static int sayas_mode;
static int sayas_start;
static int ssml_ignore_l_angle = 0;
// alter tone for announce punctuation or capitals
//static const char *tone_punct_on = "\0016T"; // add reverberation, lower pitch
//static const char *tone_punct_off = "\001T\001P";
// ignore these characters
static const unsigned short chars_ignore[] = {
0x200c, // zero width non-joiner
0x200d, // zero width joiner
0 };
// punctuations symbols that can end a clause
static const unsigned short punct_chars[] = {',','.','?','!',':',';',
0x2013, // en-dash
0x2014, // em-dash
0x2026, // elipsis
0x037e, // Greek question mark (looks like semicolon)
0x0387, // Greek semicolon, ano teleia
0x0964, // Devanagari Danda (fullstop)
0x0589, // Armenian period
0x055d, // Armenian comma
0x055c, // Armenian exclamation
0x055e, // Armenian question
0x055b, // Armenian emphasis mark
0x0b1b, // Arabic ;
0x061f, // Arabic ?
0x1362, // Ethiopic period
0x1363,
0x1364,
0x1365,
0x1366,
0x1367,
0x1368,
0x10fb, // Georgian paragraph
0x3001, // ideograph comma
0x3002, // ideograph period
0xff01, // fullwidth exclamation
0xff0c, // fullwidth comma
0xff0e, // fullwidth period
0xff1a, // fullwidth colon
0xff1b, // fullwidth semicolon
0xff1f, // fullwidth question mark
0};
// indexed by (entry num. in punct_chars) + 1
// bits 0-7 pause x 10mS, bits 12-14 intonation type, bit 15 don't need following space or bracket
static const unsigned int punct_attributes [] = { 0,
CLAUSE_COMMA, CLAUSE_PERIOD, CLAUSE_QUESTION, CLAUSE_EXCLAMATION, CLAUSE_COLON, CLAUSE_SEMICOLON,
CLAUSE_SEMICOLON, // en-dash
CLAUSE_SEMICOLON, // em-dash
CLAUSE_SEMICOLON | PUNCT_SAY_NAME | 0x8000, // elipsis
CLAUSE_QUESTION, // Greek question mark
CLAUSE_SEMICOLON, // Greek semicolon
CLAUSE_PERIOD | 0x8000, // Devanagari Danda (fullstop)
CLAUSE_PERIOD | 0x8000, // Armenian period
CLAUSE_COMMA, // Armenian comma
CLAUSE_EXCLAMATION | PUNCT_IN_WORD, // Armenian exclamation
CLAUSE_QUESTION | PUNCT_IN_WORD, // Armenian question
CLAUSE_PERIOD | PUNCT_IN_WORD, // Armenian emphasis mark
CLAUSE_SEMICOLON, // Arabic ;
CLAUSE_QUESTION, // Arabic question mark
CLAUSE_PERIOD, // Ethiopic period
CLAUSE_COMMA, // Ethiopic comma
CLAUSE_SEMICOLON, // Ethiopic semicolon
CLAUSE_COLON, // Ethiopic colon
CLAUSE_COLON, // Ethiopic preface colon
CLAUSE_QUESTION, // Ethiopic question mark
CLAUSE_PARAGRAPH, // Ethiopic paragraph
CLAUSE_PARAGRAPH, // Georgian paragraph
CLAUSE_COMMA+0x8000, // ideograph comma
CLAUSE_PERIOD+0x8000, // ideograph period
CLAUSE_EXCLAMATION+0x8000, // fullwidth
CLAUSE_COMMA+0x8000,
CLAUSE_PERIOD+0x8000,
CLAUSE_COLON+0x8000,
CLAUSE_SEMICOLON+0x8000,
CLAUSE_QUESTION+0x8000,
CLAUSE_SEMICOLON, // spare
0 };
// stack for language and voice properties
// frame 0 is for the defaults, before any ssml tags.
typedef struct {
int tag_type;
int voice_variant;
int voice_gender;
int voice_age;
char voice_name[40];
char language[20];
} SSML_STACK;
#define N_SSML_STACK 20
static int n_ssml_stack;
static SSML_STACK ssml_stack[N_SSML_STACK];
static char current_voice_id[40] = {0};
#define N_PARAM_STACK 20
static int n_param_stack;
PARAM_STACK param_stack[N_PARAM_STACK];
static int speech_parameters[N_SPEECH_PARAM]; // current values, from param_stack
const int param_defaults[N_SPEECH_PARAM] = {
0, // silence (internal use)
175, // rate wpm
100, // volume
50, // pitch
50, // range
0, // punctuation
0, // capital letters
0, // wordgap
0, // options
0, // intonation
0,
0,
0, // emphasis
0, // line length
0, // voice type
};
#ifdef NEED_WCHAR_FUNCTIONS
extern "C" {
// additional Latin characters beyond the Latin1 character set
#define MAX_WALPHA 0x233
// indexed by character - 0x100
// 0=not alphabetic, 0xff=lower case, 0xfe=special case
// other=value to add to upper case to convert to lower case
static unsigned char walpha_tab[MAX_WALPHA-0xff] = {
1,0xff, 1,0xff, 1,0xff, 1,0xff, 1,0xff, 1,0xff, 1,0xff, 1,0xff, // 100
1,0xff, 1,0xff, 1,0xff, 1,0xff, 1,0xff, 1,0xff, 1,0xff, 1,0xff, // 110
1,0xff, 1,0xff, 1,0xff, 1,0xff, 1,0xff, 1,0xff, 1,0xff, 1,0xff, // 120
0xfe,0xff, 1,0xff, 1,0xff, 1,0xff,0xff, 1,0xff, 1,0xff, 1,0xff, 1, // 130
0xff, 1,0xff, 1,0xff, 1,0xff, 1,0xff,0xff, 1,0xff, 1,0xff, 1,0xff, // 140
1,0xff, 1,0xff, 1,0xff, 1,0xff, 1,0xff, 1,0xff, 1,0xff, 1,0xff, // 150
1,0xff, 1,0xff, 1,0xff, 1,0xff, 1,0xff, 1,0xff, 1,0xff, 1,0xff, // 160
1,0xff, 1,0xff, 1,0xff, 1,0xff,0xff, 1,0xff, 1,0xff, 1,0xff,0xff, // 170
0xff, 210, 1,0xff, 1,0xff, 206, 1,0xff, 205, 205, 1,0xff,0xff, 79, 202, // 180
203, 1,0xff, 205, 207,0xff, 211, 209, 1,0xff,0xff,0xff, 211, 213,0xff, 214, // 190
1,0xff, 1,0xff, 1,0xff, 218, 1,0xff, 218,0xff,0xff, 1,0xff, 218, 1, // 1a0
0xff, 217, 217, 1,0xff, 1,0xff, 219, 1,0xff,0xff,0xff, 1,0xff,0xff,0xff, // 1b0
0xff,0xff,0xff,0xff, 2, 1,0xff, 2, 1,0xff, 2, 1,0xff, 1,0xff, 1, // 1c0
0xff, 1,0xff, 1,0xff, 1,0xff, 1,0xff, 1,0xff, 1,0xff,0xff, 1,0xff, // 1d0
1,0xff, 1,0xff, 1,0xff, 1,0xff, 1,0xff, 1,0xff, 1,0xff, 1,0xff, // 1e0
0xff, 2, 1,0xff, 1,0xff,0xff,0xff, 1,0xff, 1,0xff, 1,0xff, 1,0xff, // 1f0
1,0xff, 1,0xff, 1,0xff, 1,0xff, 1,0xff, 1,0xff, 1,0xff, 1,0xff, // 200
1,0xff, 1,0xff, 1,0xff, 1,0xff, 1,0xff, 1,0xff, 1,0xff, 1,0xff, // 210
0xff, 0, 1,0xff, 1,0xff, 1,0xff, 1,0xff, 1,0xff, 1,0xff, 1,0xff, // 220
1,0xff, 1,0xff }; // 230
// use ctype.h functions for Latin1 (character < 0x100)
int iswalpha(wint_t c)
{
if(c < 0x100)
return(isalpha(c));
if((c > 0x3040) && (c <= 0xa700))
return(1); // japanese, chinese characters
if(c > MAX_WALPHA)
return(0);
return(walpha_tab[c-0x100]);
}
int iswdigit(wint_t c)
{
if(c < 0x100)
return(isdigit(c));
return(0);
}
int iswalnum(wint_t c)
{
if(iswdigit(c))
return(1);
return(iswalpha(c));
}
wint_t towlower(wint_t c)
{
int x;
if(c < 0x100)
return(tolower(c));
if((c > MAX_WALPHA) || ((x = walpha_tab[c-0x100])==0xff))
return(c); // already lower case
if(x == 0xfe)
{
// special cases
if(c == 0x130) // uppercase i-dot
return('i');
}
return(c + x); // convert to lower case
}
wint_t towupper(wint_t c)
{
// check whether the previous character code is the upper-case equivalent of this character
if(tolower(c-1) == c)
return(c-1); // yes, use it
return(c); // no
}
int iswupper(wint_t c)
{
int x;
if(c < 0x100)
return(isupper(c));
if(((c > MAX_WALPHA) || (x = walpha_tab[c-0x100])==0) || (x == 0xff))
return(0);
return(1);
}
int iswlower(wint_t c)
{
if(c < 0x100)
return(islower(c));
if((c > MAX_WALPHA) || (walpha_tab[c-0x100] != 0xff))
return(0);
return(1);
}
int iswspace(wint_t c)
{
if(c < 0x100)
return(isspace(c));
return(0);
}
int iswpunct(wint_t c)
{
if(c < 0x100)
return(ispunct(c));
return(0);
}
const wchar_t *wcschr(const wchar_t *str, int c)
{
while(*str != 0)
{
if(*str == c)
return(str);
str++;
}
return(NULL);
}
#ifndef WINCE
// wcslen() is provided by WINCE, but not the other wchar functions
const int wcslen(const wchar_t *str)
{
int ix=0;
while(*str != 0)
{
ix++;
}
return(ix);
}
#endif
float wcstod(const wchar_t *str, wchar_t **tailptr)
{
int ix;
char buf[80];
while(isspace(*str)) str++;
for(ix=0; ix<80; ix++)
{
buf[ix] = str[ix];
if(isspace(buf[ix]))
break;
}
*tailptr = (wchar_t *)&str[ix];
return(atof(buf));
}
}
#endif // NEED_WCHAR_FUNCTIONS
int towlower2(unsigned int c)
{
// check for non-standard upper to lower case conversions
if(c == 'I')
{
if(translator->translator_name == L('t','r'))
{
c = 0x131; // I -> ı
}
}
#ifdef __WIN32__
if(c == 0x130) // uppercase i-dot
return('i');
#endif
return(towlower(c));
}
static int IsRomanU(unsigned int c)
{//================================
if((c=='I') || (c=='V') || (c=='X') || (c=='L'))
return(1);
return(0);
}
static void GetC_unget(int c)
{//==========================
// This is only called with UTF8 input, not wchar input
if(f_input != NULL)
ungetc(c,f_input);
else
{
p_textinput--;
*p_textinput = c;
end_of_input = 0;
}
}
int Eof(void)
{//==========
if(ungot_char != 0)
return(0);
if(f_input != 0)
return(feof(f_input));
return(end_of_input);
}
static int GetC_get(void)
{//======================
unsigned int c;
unsigned int c2;
if(f_input != NULL)
{
c = fgetc(f_input);
if(feof(f_input)) c = ' ';
if(option_multibyte == espeakCHARS_16BIT)
{
c2 = fgetc(f_input);
if(feof(f_input)) c2 = 0;
c = c + (c2 << 8);
}
return(c);
}
if(option_multibyte == espeakCHARS_WCHAR)
{
if(*p_wchar_input == 0)
{
end_of_input = 1;
return(0);
}
if(!end_of_input)
return(*p_wchar_input++);
}
else
{
if(*p_textinput == 0)
{
end_of_input = 1;
return(0);
}
if(!end_of_input)
{
if(option_multibyte == espeakCHARS_16BIT)
{
c = p_textinput[0] + (p_textinput[1] << 8);
p_textinput += 2;
return(c);
}
return(*p_textinput++ & 0xff);
}
}
return(0);
}
static int GetC(void)
{//==================
// Returns a unicode wide character
// Performs UTF8 checking and conversion
int c;
int c1;
int c2;
int cbuf[4];
int ix;
int n_bytes;
unsigned char m;
static int ungot2 = 0;
static const unsigned char mask[4] = {0xff,0x1f,0x0f,0x07};
static const unsigned char mask2[4] = {0,0x80,0x20,0x30};
if((c1 = ungot_char) != 0)
{
ungot_char = 0;
return(c1);
}
if(ungot2 != 0)
{
c1 = ungot2;
ungot2 = 0;
}
else
{
c1 = GetC_get();
}
if((option_multibyte == espeakCHARS_WCHAR) || (option_multibyte == espeakCHARS_16BIT))
{
count_characters++;
return(c1); // wchar_t text
}
if((option_multibyte < 2) && (c1 & 0x80))
{
// multi-byte utf8 encoding, convert to unicode
n_bytes = 0;
if(((c1 & 0xe0) == 0xc0) && ((c1 & 0x1e) != 0))
n_bytes = 1;
else
if((c1 & 0xf0) == 0xe0)
n_bytes = 2;
else
if(((c1 & 0xf8) == 0xf0) && ((c1 & 0x0f) <= 4))
n_bytes = 3;
if((ix = n_bytes) > 0)
{
c = c1 & mask[ix];
m = mask2[ix];
while(ix > 0)
{
if((c2 = cbuf[ix] = GetC_get()) == 0)
{
if(option_multibyte==espeakCHARS_AUTO)
option_multibyte=espeakCHARS_8BIT; // change "auto" option to "no"
GetC_unget(' ');
break;
}
if((c2 & 0xc0) != 0x80)
{
// This is not UTF8. Change to 8-bit characterset.
if((n_bytes == 2) && (ix == 1))
ungot2 = cbuf[2];
GetC_unget(c2);
break;
}
m = 0x80;
c = (c << 6) + (c2 & 0x3f);
ix--;
}
if(ix == 0)
{
count_characters++;
return(c);
}
}
// top-bit-set character is not utf8, drop through to 8bit charset case
if((option_multibyte==espeakCHARS_AUTO) && !Eof())
option_multibyte=espeakCHARS_8BIT; // change "auto" option to "no"
}
// 8 bit character set, convert to unicode if
count_characters++;
if(c1 >= 0xa0)
return(translator->charset_a0[c1-0xa0]);
return(c1);
} // end of GetC
static void UngetC(int c)
{//======================
ungot_char = c;
}
static const char *WordToString2(unsigned int word)
{//================================================
// Convert a language mnemonic word into a string
int ix;
static char buf[5];
char *p;
p = buf;
for(ix=3; ix>=0; ix--)
{
if((*p = word >> (ix*8)) != 0)
p++;
}
*p = 0;
return(buf);
}
static const char *LookupSpecial(Translator *tr, const char *string, char* text_out)
{//=================================================================================
unsigned int flags[2];
char phonemes[55];
char phonemes2[55];
char *string1 = (char *)string;
flags[0] = flags[1] = 0;
if(LookupDictList(tr,&string1,phonemes,flags,0,NULL))
{
SetWordStress(tr, phonemes, flags, -1, 0);
DecodePhonemes(phonemes,phonemes2);
sprintf(text_out,"[\002%s]]",phonemes2);
return(text_out);
}
return(NULL);
}
static const char *LookupCharName(Translator *tr, int c, int only)
{//===============================================================
// Find the phoneme string (in ascii) to speak the name of character c
// Used for punctuation characters and symbols
int ix;
unsigned int flags[2];
char single_letter[24];
char phonemes[60];
char phonemes2[60];
const char *lang_name = NULL;
char *string;
static char buf[60];
buf[0] = 0;
flags[0] = 0;
flags[1] = 0;
single_letter[0] = 0;
single_letter[1] = '_';
ix = utf8_out(c,&single_letter[2]);
single_letter[2+ix]=0;
if(only)
{
string = &single_letter[2];
LookupDictList(tr, &string, phonemes, flags, 0, NULL);
}
else
{
string = &single_letter[1];
if(LookupDictList(tr, &string, phonemes, flags, 0, NULL) == 0)
{
// try _* then *
string = &single_letter[2];
if(LookupDictList(tr, &string, phonemes, flags, 0, NULL) == 0)
{
// now try the rules
single_letter[1] = ' ';
TranslateRules(tr, &single_letter[2], phonemes, sizeof(phonemes), NULL,0,NULL);
}
}
}
if((only==0) && (phonemes[0] == 0) && (tr->translator_name != L('e','n')))
{
// not found, try English
SetTranslator2("en");
string = &single_letter[1];
single_letter[1] = '_';
if(LookupDictList(translator2, &string, phonemes, flags, 0, NULL) == 0)
{
string = &single_letter[2];
LookupDictList(translator2, &string, phonemes, flags, 0, NULL);
}
if(phonemes[0])
{
lang_name = "en";
}
else
{
SelectPhonemeTable(voice->phoneme_tab_ix); // revert to original phoneme table
}
}
if(phonemes[0])
{
if(lang_name)
{
SetWordStress(translator2, phonemes, flags, -1, 0);
DecodePhonemes(phonemes,phonemes2);
sprintf(buf,"[\002_^_%s %s _^_%s]]","en",phonemes2,WordToString2(tr->translator_name));
SelectPhonemeTable(voice->phoneme_tab_ix); // revert to original phoneme table
}
else
{
SetWordStress(tr, phonemes, flags, -1, 0);
DecodePhonemes(phonemes,phonemes2);
sprintf(buf,"[\002%s]] ",phonemes2);
}
}
else
if(only == 0)
{
strcpy(buf,"[\002(X1)(X1)(X1)]]");
}
return(buf);
}
int Read4Bytes(FILE *f)
{//====================
// Read 4 bytes (least significant first) into a word
int ix;
unsigned char c;
int acc=0;
for(ix=0; ix<4; ix++)
{
c = fgetc(f) & 0xff;
acc += (c << (ix*8));
}
return(acc);
}
static int LoadSoundFile(const char *fname, int index)
{//===================================================
FILE *f;
char *p;
int *ip;
int length;
char fname_temp[100];
char fname2[sizeof(path_home)+13+40];
if(fname == NULL)
{
// filename is already in the table
fname = soundicon_tab[index].filename;
}
if(fname==NULL)
return(1);
if(fname[0] != '/')
{
// a relative path, look in espeak-data/soundicons
sprintf(fname2,"%s%csoundicons%c%s",path_home,PATHSEP,PATHSEP,fname);
fname = fname2;
}
f = NULL;
#ifdef PLATFORM_POSIX
if((f = fopen(fname,"rb")) != NULL)
{
int ix;
int fd_temp;
const char *resample;
int header[3];
char command[sizeof(fname2)+sizeof(fname2)+40];
fseek(f,20,SEEK_SET);
for(ix=0; ix<3; ix++)
header[ix] = Read4Bytes(f);
// if the sound file is not mono, 16 bit signed, at the correct sample rate, then convert it
if((header[0] != 0x10001) || (header[1] != samplerate) || (header[2] != samplerate*2))
{
fclose(f);
f = NULL;
if(header[2] == samplerate)
resample = "";
else
resample = "polyphase";
strcpy(fname_temp,"/tmp/espeakXXXXXX");
if((fd_temp = mkstemp(fname_temp)) >= 0)
{
close(fd_temp);
// sprintf(fname_temp,"%s.wav",tmpnam(NULL));
sprintf(command,"sox \"%s\" -r %d -w -s -c1 %s %s\n", fname, samplerate, fname_temp, resample);
if(system(command) == 0)
{
fname = fname_temp;
}
}
}
}
#endif
if(f == NULL)
{
f = fopen(fname,"rb");
if(f == NULL)
{
// fprintf(stderr,"Can't read temp file: %s\n",fname);
return(3);
}
}
length = GetFileLength(fname);
fseek(f,0,SEEK_SET);
if((p = (char *)realloc(soundicon_tab[index].data, length)) == NULL)
{
fclose(f);
return(4);
}
length = fread(p,1,length,f);
fclose(f);
remove(fname_temp);
ip = (int *)(&p[40]);
soundicon_tab[index].length = (*ip) / 2; // length in samples
soundicon_tab[index].data = p;
return(0);
} // end of LoadSoundFile
static int LookupSoundicon(int c)
{//==============================
// Find the sound icon number for a punctuation chatacter
int ix;
for(ix=N_SOUNDICON_SLOTS; ix<n_soundicon_tab; ix++)
{
if(soundicon_tab[ix].name == c)
{
if(soundicon_tab[ix].length == 0)
{
if(LoadSoundFile(NULL,ix)!=0)
return(-1); // sound file is not available
}
return(ix);
}
}
return(-1);
}
static int LoadSoundFile2(const char *fname)
{//=========================================
// Load a sound file into one of the reserved slots in the sound icon table
// (if it'snot already loaded)
int ix;
static int slot = -1;
for(ix=0; ix<n_soundicon_tab; ix++)
{
if(((soundicon_tab[ix].filename != NULL) && strcmp(fname, soundicon_tab[ix].filename) == 0))
return(ix); // already loaded
}
// load the file into the next slot
slot++;
if(slot >= N_SOUNDICON_SLOTS)
slot = 0;
if(LoadSoundFile(fname, slot) != 0)
return(-1);
soundicon_tab[slot].filename = (char *)realloc(soundicon_tab[ix].filename, strlen(fname)+1);
strcpy(soundicon_tab[slot].filename, fname);
return(slot);
}
static int AnnouncePunctuation(Translator *tr, int c1, int *c2_ptr, char *output, int *bufix, int end_clause)
{//==========================================================================================================
// announce punctuation names
// c1: the punctuation character
// c2: the following character
int punct_count;
const char *punctname;
int found = 0;
int soundicon;
int attributes;
int short_pause;
int c2;
int len;
int bufix1;
char buf[200];
char buf2[80];
c2 = *c2_ptr;
buf[0] = 0;
if((soundicon = LookupSoundicon(c1)) >= 0)
{
// add an embedded command to play the soundicon
sprintf(buf,"\001%dI ",soundicon);
UngetC(c2);
found = 1;
}
else
if((punctname = LookupCharName(tr, c1, 0)) != NULL)
{
found = 1;
if((*bufix==0) || (end_clause ==0) || (tr->langopts.param[LOPT_ANNOUNCE_PUNCT] & 2))
{
punct_count=1;
while((c2 == c1) && (c1 != '<')) // don't eat extra '<', it can miss XML tags
{
punct_count++;
c2 = GetC();
}
*c2_ptr = c2;
if(end_clause)
{
UngetC(c2);
}
if(punct_count==1)
{
// sprintf(buf,"%s %s %s",tone_punct_on,punctname,tone_punct_off);
sprintf(buf," %s",punctname); // we need the space before punctname, to ensure it doesn't merge with the previous word (eg. "2.-a")
}
else
if(punct_count < 4)
{
buf[0] = 0;
if(embedded_value[EMBED_S] < 300)
sprintf(buf,"\001+10S"); // Speak punctuation name faster, unless we are already speaking fast. It would upset Sonic SpeedUp
while(punct_count-- > 0)
{
sprintf(buf2," %s",punctname);
strcat(buf, buf2);
}
if(embedded_value[EMBED_S] < 300)
{
sprintf(buf2," \001-10S");
strcat(buf, buf2);
}
}
else
{
sprintf(buf," %s %d %s",
punctname,punct_count,punctname);
}
}
else
{
// end the clause now and pick up the punctuation next time
UngetC(c2);
if(option_ssml)
{
if((c1 == '<') || (c1 == '&'))
ssml_ignore_l_angle = c1; // this was < which was converted to <, don't pick it up again as <
}
ungot_char2 = c1;
buf[0] = ' ';
buf[1] = 0;
}
}
if(found == 0)
return(-1);
bufix1 = *bufix;
len = strlen(buf);
strcpy(&output[*bufix],buf);
*bufix += len;
if(end_clause==0)
return(-1);
if(c1 == '-')
return(CLAUSE_NONE); // no pause
attributes = punct_attributes[lookupwchar(punct_chars,c1)];
short_pause = CLAUSE_SHORTFALL;
if((attributes & CLAUSE_BITS_INTONATION) == 0x1000)
short_pause = CLAUSE_SHORTCOMMA;
if((bufix1 > 0) && !(tr->langopts.param[LOPT_ANNOUNCE_PUNCT] & 2))
{
if((attributes & ~0x8000) == CLAUSE_SEMICOLON)
return(CLAUSE_SHORTFALL);
return(short_pause);
}
if(attributes & CLAUSE_BIT_SENTENCE)
return(attributes);
return(short_pause);
} // end of AnnouncePunctuation
#define SSML_SPEAK 1
#define SSML_VOICE 2
#define SSML_PROSODY 3
#define SSML_SAYAS 4
#define SSML_MARK 5
#define SSML_SENTENCE 6
#define SSML_PARAGRAPH 7
#define SSML_PHONEME 8
#define SSML_SUB 9
#define SSML_STYLE 10
#define SSML_AUDIO 11
#define SSML_EMPHASIS 12
#define SSML_BREAK 13
#define SSML_IGNORE_TEXT 14
#define HTML_BREAK 15
#define HTML_NOSPACE 16 // don't insert a space for this element, so it doesn't break a word
#define SSML_CLOSE 0x20 // for a closing tag, OR this with the tag type
// these tags have no effect if they are self-closing, eg. <voice />
static char ignore_if_self_closing[] = {0,1,1,1,1,0,0,0,0,1,1,0,1,0,1,0,0,0,0};