Skip to content
Navigation Menu
{{ message }}
forked from hansonrobotics/ChatScript-engine
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathtextUtilities.cpp
More file actions
3181 lines (2962 loc) · 98.8 KB
/
Copy pathtextUtilities.cpp
File metadata and controls
3181 lines (2962 loc) · 98.8 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
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
#include "common.h"
int startSentence;
int endSentence;
bool fullfloat = false; // 2 float digits or all
int numberStyle = AMERICAN_NUMBERS;
FILE* docOut = NULL;
bool showBadUTF = false; // log bad utf8 characer words
static bool blockComment = false;
bool singleSource = false; // in ReadDocument treat each line as an independent sentence
bool newline = false;
int docSampleRate = 0;
int docSample = 0;
int docVolleyStartTime = 0;
bool hasHighChar = false;
char conditionalCompile[MAX_CONDITIONALS+1][50];
int conditionalCompiledIndex = 0;
char numberComma = ',';
char numberPeriod = '.';
char tmpWord[MAX_WORD_SIZE]; // globally visible scratch word
char* userRecordSourceBuffer = 0; // input source for reading is this text stream of user file
int BOM = NOBOM; // current ByteOrderMark
static char holdc = 0; // holds extra character from readahead
unsigned char utf82extendedascii[128];
unsigned char extendedascii2utf8[128] =
{
0,0xbc,0xa9,0xa2,0xa4,0xa0,0xa5, 0xa7,0xaa,0xab, 0xa8,0xaf,0xae,0xac,0x84,0x85,0x89,0xa6,0x86,0xb4,
0xb6,0xb2,0xbb,0xb9,0xbf,0x96,0x9c,0xa2,0xa3,0xa5, 0x00,0xa1,0xad,0xb3,0xba,0xb1,0x91,
};
typedef struct NUMBERDECODE
{
int word; // word of a number index
unsigned int length; // length of word
int64 value; // value of word
int realNumber; // the type, one two are real, third is fraction
} NUMBERDECODE;
static NUMBERDECODE* numberValues;
typedef struct CURRENCYDECODE
{
int word; // word index of currency abbrev
int concept; // word index of concept to mark it
} CURRENCYDECODE;
static CURRENCYDECODE* currencies;
char toHex[16] = {
'0','1','2','3','4','5','6','7','8','9','A','B','C','D','E','F'};
unsigned char toLowercaseData[256] = // convert upper to lower case
{
0,1,2,3,4,5,6,7,8,9, 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,'a','b','c','d','e',
'f','g','h','i','j','k','l','m','n','o',
'p','q','r','s','t','u','v','w','x','y',
'z',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
};
unsigned char toUppercaseData[256] = // convert lower to upper case
{
0,1,2,3,4,5,6,7,8,9, 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,'A','B','C','D','E',
'F','G','H','I','J','K','L','M','N','O',
'P','Q','R','S','T','U','V','W','X','Y',
'Z',91,92,93,94,95,96,'A','B','C', 'D','E','F','G','H','I','J','K','L','M',
'N','O','P','Q','R','S','T','U','V','W', 'X','Y','Z',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
};
unsigned char isVowelData[256] = // english vowels
{
0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,'a',0,0,0,'e', 0,0,0,'i',0,0,0,0,0,'o',
0,0,0,0,0,'u',0,0,0,'y', 0,0,0,0,0,0,0,'a',0,0,
0,'e',0,0,0,'i',0,0,0,0, 0,'o',0,0,0,0,0,'u',0,0,
0,'y',0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0
};
signed char nestingData[256] = // the matching bracket things: () [] {}
{
0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,
1,-1,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0, // ()
0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0, 0,1,0,-1,0,0,0,0,0,0, // [ ]
0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,
0,0,0,1,0,-1,0,0,0,0, // { }
0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0
};
unsigned char legalNaming[256] = // what we allow in script-created names (like ~topicname or $uservar)
{
0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,'\'',
0,0,0,0,0,'-','.',0,'0','1', '2','3','4','5','6','7','8','9',0,0,
0,0,0,0,0,'A','B','C','D','E', 'F','G','H','I','J','K','L','M','N','O',
'P','Q','R','S','T','U','V','W','X','Y', 'Z',0,0,0,0,'_',0,'A','B','C',
'D','E','F','G','H','I','J','K','L','M',
'N','O','P','Q','R','S','T','U','V','W', 'X','Y','Z',0,0,0,0,0,1,1,
1,1,1,1,1,1,1,1,1,1, 1,1,1,1,1,1,1,1,1,1,
1,1,1,1,1,1,1,1,1,1, 1,1,1,1,1,1,1,1,1,1,
1,1,1,1,1,1,1,1,1,1, 1,1,1,1,1,1,1,1,1,1,
1,1,1,1,1,1,1,1,1,1, 1,1,1,1,1,1,1,1,1,1,
1,1,1,1,1,1,1,1,1,1, 1,1,1,1,1,1,1,1,1,1,
1,1,1,1,1,1,1,1,1,1, 1,1,1,1,1,1,1,1,1,1,
1,1,1,1,1,1,
};
unsigned char punctuation[256] = // direct lookup of punctuation -- // / is normal because can be a numeric fraction
{
ENDERS,0,0,0,0,0,0,0,0,SPACES, // 10 null \t
SPACES,0,0,SPACES,0,0,0,0,0,0, // 20 \n \r
0,0,0,0,0,0,0,0,0,0, // 30
0,0,SPACES,ENDERS,QUOTERS,SYMBOLS,SYMBOLS,ARITHMETICS,CONVERTERS,QUOTERS, // 40 space ! " # $ % & '
BRACKETS,BRACKETS,ARITHMETICS|QUOTERS , ARITHMETICS,PUNCTUATIONS, ARITHMETICS|ENDERS,ARITHMETICS|ENDERS,ARITHMETICS,0,0, // () * + , - . /
0,0,0,0,0,0,0,0,ENDERS,ENDERS, // 60 : ;
BRACKETS,ARITHMETICS,BRACKETS,ENDERS,SYMBOLS,0,0,0,0,0, // 70 < = > ? @
0,0,0,0,0,0,0,0,0,0, // 80
0,0,0,0,0,0,0,0,0,0, // 90
0,BRACKETS,0,BRACKETS,ARITHMETICS,0,CONVERTERS,0,0,0, // 100 [ \ ] ^ ` _ is normal \ is unusual
0,0,0,0,0,0,0,0,0,0, // 110
0,0,0,0,0,0,0,0,0,0, // 120
0,0,0,BRACKETS,PUNCTUATIONS,BRACKETS,SYMBOLS,0,0,0, // 130 { | } ~
0,0,0,0,0,0,0,0,0,0, // 140
0,0,0,0,0,0,0,0,0,0, // 150
0,0,0,0,0,0,0,0,0,0, // 160
0,0,0,0,0,0,0,0,0,0, // 170
0,0,0,0,0,0,0,0,0,0, // 180
0,0,0,0,0,0,0,0,0,0, // 190
0,0,0,0,0,0,0,0,0,0, // 200
0,0,0,0,0,0,0,0,0,0, // 210
0,0,0,0,0,0,0,0,0,0, // 220
0,0,0,0,0,0,0,0,0,0, // 230
0,0,0,0,0,0,0,0,0,0, // 240
0,0,0,0,0,0,0,0,0,0, // 250
0,0,0,0,0,0,
};
unsigned char realPunctuation[256] = // punctuation characters
{
0,0,0,0,0,0,0,0,0,0, // 10
0,0,0,0,0,0,0,0,0,0, // 20
0,0,0,0,0,0,0,0,0,0, // 30
0,0,0,PUNCTUATIONS,0,0,0,0,0,0, // 40 !
0,0,0 , 0,PUNCTUATIONS, 0,PUNCTUATIONS,0,0,0, // , .
0,0,0,0,0,0,0,0,PUNCTUATIONS,PUNCTUATIONS, // 60 : ;
0,0,0,PUNCTUATIONS,0,0,0,0,0,0, // ?
0,0,0,0,0,0,0,0,0,0, // 80
0,0,0,0,0,0,0,0,0,0, // 90
0,0,0,0,0,0,0,0,0,0, // 100
0,0,0,0,0,0,0,0,0,0, // 110
0,0,0,0,0,0,0,0,0,0, // 120
0,0,0,0,0,0,0,0,0,0, // 130
0,0,0,0,0,0,0,0,0,0, // 140
0,0,0,0,0,0,0,0,0,0, // 150
0,0,0,0,0,0,0,0,0,0, // 160
0,0,0,0,0,0,0,0,0,0, // 170
0,0,0,0,0,0,0,0,0,0, // 180
0,0,0,0,0,0,0,0,0,0, // 190
0,0,0,0,0,0,0,0,0,0, // 200
0,0,0,0,0,0,0,0,0,0, // 210
0,0,0,0,0,0,0,0,0,0, // 220
0,0,0,0,0,0,0,0,0,0, // 230
0,0,0,0,0,0,0,0,0,0, // 240
0,0,0,0,0,0,0,0,0,0, // 250
0,0,0,0,0,0,
};
unsigned char isAlphabeticDigitData[256] = // non-digit number starter (+-.) == 1 isdigit == 2 isupper == 3 islower == 4 isletter >= 3 utf8 == 5
{
0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,1,1,0,0,0, // # and $
0,0,0,VALIDNONDIGIT,0,VALIDNONDIGIT,VALIDNONDIGIT,0,VALIDDIGIT,VALIDDIGIT, VALIDDIGIT,VALIDDIGIT,VALIDDIGIT,VALIDDIGIT,VALIDDIGIT,VALIDDIGIT,VALIDDIGIT,VALIDDIGIT,0,0, // + and . and -
0,0,0,0,0,VALIDUPPER,VALIDUPPER,VALIDUPPER,VALIDUPPER,VALIDUPPER,
VALIDUPPER,VALIDUPPER,VALIDUPPER,VALIDUPPER,VALIDUPPER,VALIDUPPER,VALIDUPPER,VALIDUPPER,VALIDUPPER,VALIDUPPER,
VALIDUPPER,VALIDUPPER,VALIDUPPER,VALIDUPPER,VALIDUPPER,VALIDUPPER,VALIDUPPER,VALIDUPPER,VALIDUPPER,VALIDUPPER,
VALIDUPPER,0,0,0,0,0,0,4,4,4,
VALIDLOWER,VALIDLOWER,VALIDLOWER,VALIDLOWER,VALIDLOWER,VALIDLOWER,VALIDLOWER,VALIDLOWER,VALIDLOWER,VALIDLOWER,
VALIDLOWER,VALIDLOWER,VALIDLOWER,VALIDLOWER,VALIDLOWER,VALIDLOWER,VALIDLOWER,VALIDLOWER,VALIDLOWER,VALIDLOWER,
VALIDLOWER,VALIDLOWER,VALIDLOWER,0,0,0,0,0, VALIDUTF8,VALIDUTF8,
VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8, VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,
VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8, VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,
VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8, VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,
VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8, VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,
VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8, VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,
VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8, VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,
VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8,VALIDUTF8
};
unsigned int roman[256] = // values of roman numerals
{
0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0, //20
0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0, //40
0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0, //60
0,0,0,0,0,0,0,100,500,0, 0,0,0,1,0,0,50,1000,0,0, //80 C(67)=100 D(68)=500 I(73)=1 L(76)=50 M(77)=1000
0,0,0,0,0,0,5,0,10,0, 0,0,0,0,0,0,0,0,0,0, //100 V(86)=5 X(88)=10
0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,
};
unsigned char isComparatorData[256] = // = < > & ? ! %
{
0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0, //20
0,0,0,0,0,0,0,0,0,0, 0,0,0,1,0,0,0,0,1,0, //40 33=! 38=&
0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0, //60
1,1,1,1,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0, //80 < = > ?
0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0, //100
0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0, //120
0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0
};
/////////////////////////////////////////////
// STARTUP
/////////////////////////////////////////////
void InitTextUtilities()
{
memset(utf82extendedascii, 0, 128);
extendedascii2utf8[0xe1 - 128] = 0x9f; // german fancy ss
for (unsigned int i = 0; i < 128; ++i)
{
unsigned char c = extendedascii2utf8[i];
if (c) c -= 128; // remove top bit
utf82extendedascii[c] = (unsigned char)i;
}
}
void ClearNumbers()
{
numberValues = 0; // heap is discarded, need to discard this
currencies = 0;
}
char* ReadTokenMass(char* ptr, char* word)
{
ptr = SkipWhitespace(ptr);
while (*ptr && *ptr != ' ') *word++ = *ptr++; // find end of word
*word = 0;
return ptr;
}
void InitTextUtilities1()
{
char file[SMALL_WORD_SIZE];
sprintf(file, (char*)"%s/%s/numbers.txt", livedata, language);
FILE* in = FopenStaticReadOnly(file); // LIVEDATA substitutes or from script TOPIC world
if (!in) return;
char word[MAX_WORD_SIZE];
char value[MAX_WORD_SIZE];
char kind[MAX_WORD_SIZE];
char* limit;
char* stack = InfiniteStack64(limit,"initnumbers");
int* data = (int*)stack;
while (ReadALine(readBuffer, in) >= 0) // once 1 REALNUMBER
{
if (*readBuffer == '#' || *readBuffer == 0) continue;
char* ptr = ReadCompiledWord(readBuffer, word);
ptr = ReadCompiledWord(ptr, value);
ptr = ReadCompiledWord(ptr, kind);
int64 val;
ReadInt64(value, val);
int kindval = 0;
if (!stricmp(kind, "DIGIT_NUMBER")) kindval = DIGIT_NUMBER;
else if (!stricmp(kind, "FRACTION_NUMBER")) kindval = FRACTION_NUMBER;
else if (!stricmp(kind, "WORD_NUMBER")) kindval = WORD_NUMBER;
else if (!stricmp(kind, "REAL_NUMBER")) kindval = WORD_NUMBER;
else myexit("Bad number table");
char* w = StoreWord(word,AS_IS)->word;
int index = Heap2Index(w);
*data++ = index;
*data++ = strlen(word);
*(int64*)data = val; // int64 value
data += 2;
*data++ = kindval;
*data++ = 0; // alignment to keep block at int64 style
}
*data++ = 0; // terminal value for end detection
size_t size = (char*)data - stack;
size /= 8; // 64bit chunks
numberValues = (NUMBERDECODE*)AllocateHeap(stack, size+1,8);
ReleaseInfiniteStack();
fclose(in);
sprintf(file, (char*)"%s/%s/currencies.txt", livedata, language);
in = FopenStaticReadOnly(file); // LIVEDATA substitutes or from script TOPIC world
if (!in) return;
stack = InfiniteStack64(limit, "initcurrency");
data = (int*)stack;
while (ReadALine(readBuffer, in) >= 0) // $ ~dollar
{
if (*readBuffer == '#' || *readBuffer == 0) continue;
char* ptr = ReadCompiledWord(readBuffer, word);
MakeLowerCase(word);
ptr = ReadCompiledWord(ptr, kind);
MakeLowerCase(kind);
if (*kind != '~') myexit("Bad currency table");
char* w = StoreWord(word, AS_IS | CURRENCY)->word; // currency name
int index = Heap2Index(w);
*data++ = index;
w = StoreWord(kind, AS_IS)->word; // currency name
index = Heap2Index(w);
*data++ = index;
}
*data++ = 0; // terminal value for end detection
size = (char*)data - stack;
size /= 8; // 64bit chunks
currencies = (CURRENCYDECODE*)AllocateHeap(stack, size + 1, 8);
ReleaseInfiniteStack();
fclose(in);
}
void CloseTextUtilities()
{
}
bool IsFraction(char* token)
{
if (IsDigit(token[0])) // fraction?
{
char* at = strchr(token,'/');
if (at)
{
at = token;
while (IsDigit(*++at)) {;}
if (*at == '/')
{
while (IsDigit(*++at)) {;}
if (!*at) return true;
}
}
}
return false;
}
char* RemoveEscapesWeAdded(char* at)
{
if (!at || !*at) return at;
char* startScan = at;
while ((at = strchr(at,'\\'))) // we always add ESCAPE_FLAG backslash
{
if (*(at-1) == ESCAPE_FLAG) // alter the escape in some way
{
if (at[1] == 't') at[1] = '\t'; // legal
else if (at[1] == 'n') at[1] = '\n'; // legal
else if (at[1] == 'r') at[1] = '\r'; // legal
// other choices dont translate, eg double quote
memmove(at-1,at+1,strlen(at)); // remove the escape flag and the escape
}
else ++at; // we dont mark " with ESCAPE_FLAG, we are not protecting it.
}
return startScan;
}
char* CopyRemoveEscapes(char* to, char* at,int limit,bool all) // all includes ones we didnt add as well
{
*to = 0;
char* start = to;
if (!at || !*at) return to;
// need to remove escapes we put there
--at;
while (*++at)
{
if (*at == ESCAPE_FLAG && at[1] == '\\') // we added an escape here
{
at += 2; // move to escaped item
if (*(at-1) == ESCAPE_FLAG) // dual escape is special marker, there is no escaped item
{
*to++ = '\r'; // legal
*to++ = '\n'; // legal
--at; // rescan the item
}
else if (*at == 't') *to++ = '\t'; // legal
else if (*at == 'n') *to++ = '\n'; // legal
else if (*at == 'r') *to++ = '\r'; // legal
else *to++ = *at; // remove our escape pair and pass the item
}
else if (*at == '\\' && all) // remove ALL other escapes in addition to ones we put there
{
++at; // move to escaped item
if (*at == 't') *to++ = '\t';
else if (*at == 'n') *to++ = '\n'; // legal
else if (*at == 'r') *to++ = '\r'; // legal
else {*to++ = *at; } // just pass along untranslated
}
else *to++ = *at;
if ((to-start) >= limit) // too much, kill it
{
*to = 0;
break;
}
}
*to = 0;
return start;
}
void RemoveImpure(char* buffer)
{
char* p;
while ((p = strchr(buffer,'\r'))) *p = ' '; // legal
while ((p = strchr(buffer,'\n'))) *p = ' '; // legal
while ((p = strchr(buffer,'\t'))) *p = ' '; // legal
}
void ChangeSpecial(char* buffer)
{
char* limit;
char* buf = InfiniteStack(limit,"ChangeSpecial");
AddEscapes(buf,buffer,true,MAX_BUFFER_SIZE);
strcpy(buffer,buf);
ReleaseInfiniteStack();
}
char* AddEscapes(char* to, char* from, bool normal,int limit) // normal true means dont flag with extra markers
{
limit -= 200; // dont get close to limit
char* start = to;
char* at = from - 1;
// if we NEED to add an escape, we have to mark it as such so we know to remove them later.
while (*++at)
{
// convert these
if (*at == '\n') { // not expected to see
if (!normal) *to++ = ESCAPE_FLAG;
*to++ = '\\';
*to++ = 'n'; // legal
}
else if (*at == '\r') {// not expected to see
if (!normal) *to++ = ESCAPE_FLAG;
*to++ = '\\';
*to++ = 'r';// legal
}
else if (*at == '\t') {// not expected to see
if (!normal) *to++ = ESCAPE_FLAG;
*to++ = '\\';
*to++ = 't'; // legal
}
else if (*at == '"') { // we need to preserve that it was escaped, though we always escape it in json anyway, because writeuservars needs to know
if (!normal) *to++ = ESCAPE_FLAG;
*to++ = '\\';
*to++ = '"';
}
// detect it is already escaped
else if (*at == '\\')
{
char* at1 = at + 1;
if (*at1 && (*at1 == 'n' || *at1 == 'r' || *at1 == 't' || *at1 == '"' || *at1 == 'u' || *at1 == '\\')) // just pass it along
{
*to++ = *at;
*to++ = *++at;
}
else {
if (!normal) *to++ = ESCAPE_FLAG;
*to++ = '\\';
*to++ = '\\';
}
}
// no escape needed
else *to++ = *at;
if ((to-start) > limit && false) // dont overflow just abort silently
{
ReportBug((char*)"AddEscapes overflowing buffer");
break;
}
}
*to = 0;
return to; // return where we ended
}
double Convert2Float(char* original)
{
char num[MAX_WORD_SIZE];
strcpy(num, original);
char* comma;
while ((comma = strchr(num, numberComma))) memmove(comma, comma + 1, strlen(comma));
char* period = strchr(num, numberPeriod);
if (period) *period = '.'; // force us period
double val = atof(num);
if (IsDigitWithNumberSuffix(num)) // 10K 10M 10B
{
size_t len = strlen(num);
char d = num[len - 1];
if (d == 'k' || d == 'K') val *= 1000;
else if (d == 'm' || d == 'M') val *= 1000000;
else if (d == 'B' || d == 'b' || d == 'G' || d == 'g') val *= 1000000000;
}
return val;
}
void AcquireDefines(char* fileName)
{ // dictionary entries: `xxxx (property names) ``xxxx (systemflag names) ``` (parse flags values) -- and flipped: `nxxxx and ``nnxxxx and ```nnnxxx with infermrak being ptr to original name
FILE* in = FopenStaticReadOnly(fileName); // SRC/dictionarySystem.h
if (!in)
{
printf((char*)"%s",(char*)"Unable to read dictionarySystem.h\r\n");
return;
}
char label[MAX_WORD_SIZE];
char word[MAX_WORD_SIZE];
bool orop = false;
bool shiftop = false;
bool plusop = false;
bool minusop = false;
bool timesop = false;
bool excludeop = false;
int offset = 1;
word[0] = ENDUNIT;
bool endsystem = false;
while (ReadALine(readBuffer, in) >= 0)
{
uint64 result = NOPROBLEM_BIT;
int64 value;
if (!strnicmp(readBuffer,(char*)"// system flags",15)) // end of property flags seen
{
word[1] = ENDUNIT; // system flag words have `` in front
offset = 2;
}
else if (!strnicmp(readBuffer,(char*)"// end system flags",19)) // end of system flags seen
{
offset = 1;
}
else if (!strnicmp(readBuffer,(char*)"// parse flags",14)) // start of parse flags seen
{
word[1] = ENDUNIT; // parse flag words have ``` in front
word[2] = ENDUNIT; // parse flag words have ``` in front
offset = 3;
}
else if (!strnicmp(readBuffer,(char*)"// end parse flags",18)) // end of parse flags seen
{
word[1] = ENDUNIT; // misc flag words have ```` in front and do not xref from number to word
word[2] = ENDUNIT; // misc flag words have ```` in front
word[3] = ENDUNIT; // misc flag words have ```` in front
offset = 4;
endsystem = true;
}
char* ptr = ReadCompiledWord(readBuffer,word+offset);
if (stricmp(word+offset,(char*)"#define")) continue;
// accept lines line #define NAME 0x...
ptr = ReadCompiledWord(ptr,word+offset); // the #define name
if (ptr == 0 || *ptr == 0 || strchr(word+offset,'(')) continue; // if a paren is IMMEDIATELY attached to the name, its a macro, ignore it.
while (ptr) // read value of the define
{
ptr = SkipWhitespace(ptr);
if (ptr == 0) break;
char c = *ptr++;
if (!c) break;
if (c == ')' || c == '/') break; // a form of ending
if (c == '+' && *ptr == ' ') plusop = true;
else if (c == '-' && *ptr == ' ') minusop = true;
else if (c == '*' && *ptr == ' ') timesop = true;
else if (c == '^' && *ptr == ' ') excludeop = true;
else if (IsDigit(c))
{
ptr = (*ptr == 'x' || *ptr == 'X') ? ReadHex(ptr-1,(uint64&)value) : ReadInt64(ptr-1,value);
if (plusop) result += value;
else if (minusop) result -= value;
else if (timesop) result *= value;
else if (excludeop) result ^= value;
else if (orop) result |= value;
else if (shiftop) result <<= value;
else result = value;
excludeop = plusop = minusop = orop = shiftop = timesop = false;
}
else if (c == '('); // start of a (expression in a define, ignore it
else if (c == '|') orop = true;
else if (c == '<') // <<
{
++ptr;
shiftop = true;
}
else // reusing word
{
ptr = ReadCompiledWord(ptr-1,label);
value = FindValueByName(label);
bool olddict = xbuildDictionary;
xbuildDictionary = false;
if (!value) value = FindSystemValueByName(label);
if (!value) value = FindMiscValueByName(label);
if (!value) value = FindParseValueByName(label);
xbuildDictionary = olddict;
if (!value) ReportBug((char*)"missing modifier value for %s\r\n",label)
if (orop) result |= value;
else if (shiftop) result <<= value;
else if (plusop) result += value;
else if (minusop) result -= value;
else if (timesop) result *= value;
else if (excludeop) result ^= value;
else result = value;
excludeop = plusop = minusop = orop = shiftop = timesop = false;
}
}
WORDP D = StoreWord(word,AS_IS | result);
AddInternalFlag(D,DEFINES);
#ifdef WIN32
sprintf(word+offset,(char*)"%I64d",result);
#else
sprintf(word+offset,(char*)"%lld",result);
#endif
if (!endsystem) // cross ref from number to value only for properties and system flags and parsemarks for decoding bits back to words for marking
{
WORDP E = StoreWord(word);
AddInternalFlag(E,DEFINES);
if (!E->inferMark) E->inferMark = MakeMeaning(D); // if number value NOT already defined, use this definition
}
}
FClose(in);
}
static MEANING ConceptFact(char* word, MEANING M, bool facts)
{
MEANING X = MakeMeaning(BUILDCONCEPT(word));
if (facts) CreateFact(X, Mmember, M);
return X;
}
void AcquirePosMeanings(bool facts)
{
// create pos meanings and sets
// if (buildDictionary) return; // dont add these into dictionary
uint64 bit = START_BIT;
char name[MAX_WORD_SIZE];
*name = '~';
MEANING pos = ConceptFact((char*)"~pos", 0, false);
MEANING sys = ConceptFact((char*)"~sys", 0, false);
for (int i = 63; i >= 0; --i) // properties get named concepts
{
char* word = FindNameByValue(bit);
if (word)
{
MakeLowerCopy(name+1,word); // all pos names start with `
posMeanings[i] = ConceptFact(name,pos,facts);
}
word = FindSystemNameByValue(bit);
if (word)
{
MakeLowerCopy(name+1,word); // all sys names start with ``
sysMeanings[i] = ConceptFact(name, sys, facts);
}
bit >>= 1;
}
MEANING M = ConceptFact((char*)"~aux_verb", pos, facts);
ConceptFact((char*)"~aux_verb_future", M, facts);
ConceptFact((char*)"~aux_verb_past", M, facts);
ConceptFact((char*)"~aux_verb_present", M, facts);
ConceptFact((char*)"~aux_be", M, facts);
ConceptFact((char*)"~aux_have", M, facts);
ConceptFact((char*)"~aux_do", M, facts);
M = ConceptFact((char*)"~aux_verb_tenses",pos,facts);
ConceptFact((char*)"~aux_verb_future",M,facts);
ConceptFact((char*)"~aux_verb_past",M, facts);
ConceptFact((char*)"~aux_verb_present",M, facts);
M = ConceptFact((char*)"~conjunction",pos,facts);
ConceptFact((char*)"~conjunction_subordinate",M,facts);
ConceptFact((char*)"~conjunction_coordinate",M,facts);
M = ConceptFact((char*)"~determiner_bits", pos, facts);
ConceptFact((char*)"~determiner", M, facts);
ConceptFact((char*)"~predeterminer", M, facts);
M = ConceptFact((char*)"~possessive_bits", pos, facts);
ConceptFact((char*)"~possessive", M, facts);
ConceptFact((char*)"~pronoun_possessive", M, facts);
M = ConceptFact((char*)"~noun_bits", pos, facts);
ConceptFact((char*)"~noun_singular", M, facts);
ConceptFact((char*)"~noun_plural", M, facts);
ConceptFact((char*)"~noun_proper_singular", M, facts);
ConceptFact((char*)"~noun_proper_plural", M, facts);
ConceptFact((char*)"~noun_number", M, facts);
ConceptFact((char*)"~noun_adjective", M, facts);
ConceptFact((char*)"~noun_gerund", M, facts);
M = ConceptFact((char*)"~normal_noun_bits", pos, facts);
ConceptFact((char*)"~noun_singular", M, facts);
ConceptFact((char*)"~noun_plural", M, facts);
ConceptFact((char*)"~noun_proper_singular", M, facts);
ConceptFact((char*)"~noun_proper_plural", M, facts);
M = ConceptFact((char*)"~pronoun_bits", pos, facts);
ConceptFact((char*)"~pronoun_subject", M, facts);
ConceptFact((char*)"~pronoun_object", M, facts);
M = ConceptFact((char*)"~verb_bits", pos, facts);
ConceptFact((char*)"~verb_present", M, facts);
ConceptFact((char*)"~verb_present_3ps", M, facts);
ConceptFact((char*)"~verb_past", M, facts);
ConceptFact((char*)"~verb_past_participle", M, facts);
ConceptFact((char*)"~verb_present_participle", M, facts);
M = ConceptFact((char*)"~punctuation", pos, facts);
ConceptFact((char*)"~paren", M, facts);
ConceptFact((char*)"~comma", M, facts);
ConceptFact((char*)"~quote", M, facts);
ConceptFact((char*)"~currency", M, facts);
MEANING role = ConceptFact((char*)"~grammar_role", 0, false);
unsigned int i = 0;
char* ptr;
while ((ptr = roleSets[i++]) != 0)
{
ConceptFact(ptr, role, facts);
}
}
uint64 FindValueByName(char* name)
{
if (!*name || *name == '?') return 0; // ? is the default argument to call
char word[MAX_WORD_SIZE];
word[0] = ENDUNIT;
MakeUpperCopy(word+1,name);
WORDP D = FindWord(word);
if (!D|| !(D->internalBits & DEFINES)) return 0;
return D->properties;
}
char* FindNameByValue(uint64 val) // works for invertable pos bits only
{
char word[MAX_WORD_SIZE];
word[0] = ENDUNIT;
#ifdef WIN32
sprintf(word+1,(char*)"%I64d",val);
#else
sprintf(word+1,(char*)"%lld",val);
#endif
WORDP D = FindWord(word);
if (!D || !(D->internalBits & DEFINES)) return 0;
D = Meaning2Word(D->inferMark);
return D->word+1;
}
bool IsModelNumber(char* word)
{
int alphanumeric = 0;
--word;
while (*++word)
{
if (IsAlphaUTF8(*word)) alphanumeric |= 1;
else if (IsDigit(*word)) alphanumeric |= 2;
}
return (alphanumeric == 3);
}
uint64 FindSystemValueByName(char* name)
{
if (!*name || *name == '?') return 0; // ? is the default argument to call
char word[MAX_WORD_SIZE];
word[0] = ENDUNIT;
word[1] = ENDUNIT;
MakeUpperCopy(word+2,name);
WORDP D = FindWord(word);
if (!D || !(D->internalBits & DEFINES))
{
if (xbuildDictionary)
ReportBug((char*)"Failed to find system value %s",name);
return 0;
}
return D->properties;
}
char* FindSystemNameByValue(uint64 val) // works for invertable system bits only
{
char word[MAX_WORD_SIZE];
word[0] = ENDUNIT;
word[1] = ENDUNIT;
#ifdef WIN32
sprintf(word+2,(char*)"%I64d",val);
#else
sprintf(word+2,(char*)"%lld",val);
#endif
WORDP D = FindWord(word);
if (!D || !(D->internalBits & DEFINES)) return 0;
return Meaning2Word(D->inferMark)->word+2;
}
char* FindParseNameByValue(uint64 val)
{
char word[MAX_WORD_SIZE];
word[0] = ENDUNIT;
word[1] = ENDUNIT;
word[2] = ENDUNIT;
#ifdef WIN32
sprintf(word+3,(char*)"%I64d",val);
#else
sprintf(word+3,(char*)"%lld",val);
#endif
WORDP D = FindWord(word);
if (!D || !(D->internalBits & DEFINES)) return 0;
return Meaning2Word(D->inferMark)->word+3;
}
uint64 FindParseValueByName(char* name)
{
if (!*name || *name == '?') return 0; // ? is the default argument to call
char word[MAX_WORD_SIZE];
word[0] = ENDUNIT;
word[1] = ENDUNIT;
word[2] = ENDUNIT;
MakeUpperCopy(word+3,name);
WORDP D = FindWord(word);
if (!D || !(D->internalBits & DEFINES))
{
if (xbuildDictionary) ReportBug((char*)"Failed to find parse value %s",name);
return 0;
}
return D->properties;
}
uint64 FindMiscValueByName(char* name)
{
if (!*name || *name == '?') return 0; // ? is the default argument to call
char word[MAX_WORD_SIZE];
word[0] = ENDUNIT;
word[1] = ENDUNIT;
word[2] = ENDUNIT;
word[3] = ENDUNIT;
MakeUpperCopy(word+4,name);
WORDP D = FindWord(word);
if (!D || !(D->internalBits & DEFINES))
{
if (xbuildDictionary) ReportBug((char*)"Failed to find misc value %s",name);
return 0;
}
return D->properties;
}
/////////////////////////////////////////////
// BOOLEAN-STYLE QUESTIONS
/////////////////////////////////////////////
bool IsArithmeticOperator(char* word)
{
word = SkipWhitespace(word);
char c = *word;
if (c == '+' || c == '-' || c == '*' || c == '/' || c == '&')
{
if (IsDigit(word[1]) || word[1] == ' ' || word[1] == '=') return true;
return false;
}
return
((c == '|' && (word[1] == ' ' || word[1] == '^' || word[1] == '=')) ||
(c == '%' && !word[1]) ||
(c == '%' && word[1] == ' ') ||
(c == '%' && word[1] == '=') ||
(c == '^' && !word[1]) ||
(c == '^' && word[1] == ' ') ||
(c == '^' && word[1] == '=') ||
(c == '<' && word[1] == '<') ||
(c == '>' && word[1] == '>')
);
}
char* IsUTF8(char* buffer,char* character) // swallow a single utf8 character (ptr past it) or return null
{
*character = *buffer;
character[1] = 0; // simple ascii character
if (*buffer == 0) return buffer; // dont walk past end
if (((unsigned char)*buffer) < 127) return buffer+1; // not utf8
char* start = buffer;
unsigned int count = UTFCharSize(buffer) - 1; // bytes beyond first
if (count == 0) count = 300; // not real?
// does count of extenders match requested count
unsigned int n = 0;
while (*++buffer && *(unsigned char*) buffer >= 128 && *(unsigned char*) buffer <= 191) ++n;
if (n == count)
{
strncpy(character,start,count+1);
character[count+1] = 0;
return buffer;
}
return start+1;
}
char GetTemperatureLetter(char* ptr)
{
if (!ptr || !ptr[1] || !IsDigit(*ptr)) return 0; // format must be like 1C or 19F
size_t len = strlen(ptr) - 1;
char lastc = GetUppercaseData(ptr[len]);
if (lastc == 'F' || lastc == 'C' || lastc == 'K') // ends in a temp letter
{
// prove rest of prefix is a number
char* p = ptr-1;
while (IsDigit(*++p)); // find end of number prefix
if (len == (size_t)(p - ptr)) return lastc;
}
return 0;
}
char* IsTextCurrency(char* ptr,char* end)
{
if (!end)
{
end = ptr;
while (*++end && !IsDigit(*end)); // locate nominal end of text
}
// look up direct word numbers
WORDP D = FindWord(ptr, (end - ptr), LOWERCASE_LOOKUP);
if ( D && D->properties & CURRENCY && currencies) for (unsigned int i = 0; i < 10000; ++i)
{
size_t len = end - ptr;
int index = currencies[i].word;
if (!index) break;
char* w = Index2Heap(index);
if (!strnicmp(ptr, Index2Heap(index), len))
{
if (ptr[len] == 0 || IsDigit(ptr[len])) return Index2Heap(currencies[i].concept); // a match
}
}
return NULL;
}
char* IsSymbolCurrency(char* ptr)
{
char* end = ptr;
while (*++end && !IsDigit(*end)); // locate nominal end of text
if (*ptr == 0xe2 && ptr[1] == 0x82 && ptr[2] == 0xac) return end;// euro is prefix
else if (*ptr == 0xC2 && ptr[1] == 0xA2) return end; // cent sign
else if (*ptr == 0xc2) // yen is prefix
{
char c = ptr[1];
if (c == 0xa2 || c == 0xa3 || c == 0xa4 || c == 0xa5) return end;
}
else if (*ptr == 0xc3 && ptr[1] == 0xb1) return end; // british pound
else if (*ptr == 0xe2 && ptr[1] == 0x82 && ptr[2] == 0xb9) return end; // rupee
else if (IsTextCurrency(ptr,end) != NULL) return end;
return NULL;
}
unsigned char* GetCurrency(unsigned char* ptr,char* &number) // does this point to a currency token, return currency and point to number (NOT PROVEN its a number)
{
char* prefixEnd = IsSymbolCurrency((char*)ptr); // is it at start
if (prefixEnd)
You can’t perform that action at this time.