This repository was archived by the owner on Aug 31, 2021. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 223
Expand file tree
/
Copy pathfoundation-chunk.cpp
More file actions
940 lines (764 loc) · 34.5 KB
/
Copy pathfoundation-chunk.cpp
File metadata and controls
940 lines (764 loc) · 34.5 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
/* Copyright (C) 2003-2015 LiveCode Ltd.
This file is part of LiveCode.
LiveCode is free software; you can redistribute it and/or modify it under
the terms of the GNU General Public License v3 as published by the Free
Software Foundation.
LiveCode 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 LiveCode. If not see <http://www.gnu.org/licenses/>. */
#include <foundation.h>
#include <foundation-locale.h>
#include <foundation-unicode.h>
#include "foundation-chunk.h"
////////////////////////////////////////////////////////////////////////////////
uinteger_t MCChunkCountByteChunkCallback(void *context, MCRange *p_range)
{
uinteger_t t_length;
t_length = MCDataGetLength(*(MCDataRef *)context);
if (p_range == nil)
return t_length;
MCRange t_range;
t_range = *p_range;
return t_range . offset + t_range . length > t_length ? t_length - t_range . offset : t_range . length;
}
uinteger_t MCChunkCountCodeunitChunkCallback(void *context, MCRange *p_range)
{
uinteger_t t_length;
t_length = MCStringGetLength(*(MCStringRef *)context);
if (p_range == nil)
return t_length;
MCRange t_range;
t_range = *p_range;
return t_range . offset + t_range . length > t_length ? t_length - t_range . offset : t_range . length;
}
uinteger_t MCChunkCountGraphemeChunkCallback(void *context, MCRange *p_range)
{
MCRange t_range;
if (p_range == nil)
t_range = MCRangeMake(0, MCStringGetLength(*(MCStringRef *)context));
else
t_range = *p_range;
MCRange t_grapheme_range;
MCStringUnmapGraphemeIndices(*(MCStringRef *)context, t_range, t_grapheme_range);
return t_grapheme_range . length;
}
uinteger_t MCChunkCountElementChunkCallback(void *context, MCRange *p_range)
{
uinteger_t t_length;
t_length = MCProperListGetLength(*(MCProperListRef *)context);
if (p_range == nil)
return t_length;
MCRange t_range;
t_range = *p_range;
return t_range . offset + t_range . length > t_length ? t_length - t_range . offset : t_range . length;
}
////////////////////////////////////////////////////////////////////////////////
// AL-2015-02-10: [[ Bug 14532 ]] Allow chunk extents to be counted in a
// given range, to prevent substring copying in text chunk resolution.
// Note the returned r_first and r_chunk count *are* allowed to overrun
// the given range - MCStringsMarkTextChunkInRange does the work of
// ensuring the absolute indices are restricted accordingly.
bool MCChunkGetExtentsByRangeInRange(bool p_strict, bool p_boundary_start, bool p_boundary_end, integer_t p_first, integer_t p_last, MCChunkCountCallback p_callback, void *p_context, MCRange *p_range, uindex_t& r_first, uindex_t& r_chunk_count)
{
int32_t t_chunk_count;
uinteger_t t_count;
bool t_counted;
t_counted = false;
// If the first index is negative, count chunks and adjust accordingly.
// Resolved index should be the index *before* the target first chunk.
if (p_first < 0)
{
t_count = p_callback(p_context, p_range);
t_counted = true;
p_first += t_count;
}
else
p_first--;
// If the last index is negative, count chunks and adjust accordingly.
// Resolved index should be the index of the target last chunk.
if (p_last < 0)
{
if (!t_counted)
{
t_count = p_callback(p_context, p_range);
t_counted = true;
}
p_last += t_count + 1;
}
t_chunk_count = p_last - p_first;
if (p_first < 0)
t_chunk_count += p_first;
if (p_strict)
{
// If we counted back too far, the start index is out of range unless we are looking for a start
// boundary, in which case p_first can be -1 (before the 0-indexed first chunk)
if (p_first < -1 || (!p_boundary_start && p_first == -1))
return false;
// If there are no chunks in this range, the range was invalid
if (t_chunk_count == 0)
return false;
if (!t_counted)
t_count = p_callback(p_context, p_range);
// If the range extends beyond the number of chunks, the end index is out of range unless we are
// looking for an end boundary, in which case it can exceed the end index by 1.
if (p_first + t_chunk_count > t_count + 1 || (!p_boundary_end && p_first + t_chunk_count == t_count + 1))
return false;
}
if (p_first < 0)
p_first = 0;
if (t_chunk_count < 0)
t_chunk_count = 0;
r_chunk_count = (uindex_t)t_chunk_count;
r_first = (uindex_t)p_first;
return true;
}
// AL-2015-03-03: Add booleans to allow chunk ranges to be out of range by 1 in strict mode.
// This is so that executing things like 'the offset of x after 0 in x' doesn't throw an error.
bool MCChunkGetExtentsByExpressionInRange(bool p_strict, bool p_boundary_start, bool p_boundary_end, integer_t p_first, MCChunkCountCallback p_callback, void *p_context, MCRange *p_range, uindex_t& r_first, uindex_t& r_chunk_count)
{
int32_t t_chunk_count;
t_chunk_count = 1;
uinteger_t t_count;
bool t_counted;
t_counted = false;
if (p_first < 0 || p_range != nil)
{
t_count = p_callback(p_context, p_range);
t_counted = true;
p_first += t_count;
}
else
p_first--;
if (p_strict)
{
// If we counted back too far, the start index is out of range unless we are looking for a start
// boundary, in which case p_first can be -1 (before the 0-indexed first chunk)
if (p_first < -1 || (!p_boundary_start && p_first == -1))
return false;
if (!t_counted)
t_count = p_callback(p_context, p_range);
// If the range extends beyond the number of chunks, the end index is out of range unless we are
// looking for an end boundary, in which case it can exceed the end index by 1.
if (p_first + t_chunk_count > t_count + 1 || (!p_boundary_end && p_first + t_chunk_count == t_count + 1))
return false;
}
if (p_first < 0)
{
t_chunk_count = 0;
p_first = 0;
}
r_first = p_first;
r_chunk_count = t_chunk_count;
return true;
}
////////////////////////////////////////////////////////////////////////////////
bool MCChunkGetExtentsOfByteChunkByRangeInRange(MCDataRef p_data, MCRange *p_range, integer_t p_first, integer_t p_last, bool p_strict, bool p_boundary_start, bool p_boundary_end, uindex_t& r_first, uindex_t& r_chunk_count)
{
return MCChunkGetExtentsByRangeInRange(p_strict, p_boundary_start, p_boundary_end, p_first, p_last, MCChunkCountByteChunkCallback, &p_data, p_range, r_first, r_chunk_count);
}
bool MCChunkGetExtentsOfByteChunkByExpressionInRange(MCDataRef p_data, MCRange *p_range, integer_t p_first, bool p_strict, bool p_boundary_start, bool p_boundary_end, uindex_t& r_first, uindex_t& r_chunk_count)
{
return MCChunkGetExtentsByExpressionInRange(p_strict, p_boundary_start, p_boundary_end, p_first, MCChunkCountByteChunkCallback, &p_data, p_range, r_first, r_chunk_count);
}
bool MCChunkGetExtentsOfCodeunitChunkByRangeInRange(MCStringRef p_string, MCRange *p_range, integer_t p_first, integer_t p_last, bool p_strict, bool p_boundary_start, bool p_boundary_end, uindex_t& r_first, uindex_t& r_chunk_count)
{
return MCChunkGetExtentsByRangeInRange(p_strict, p_boundary_start, p_boundary_end, p_first, p_last, MCChunkCountCodeunitChunkCallback, &p_string, p_range, r_first, r_chunk_count);
}
bool MCChunkGetExtentsOfCodeunitChunkByExpressionInRange(MCStringRef p_string, MCRange *p_range, integer_t p_first, bool p_strict, bool p_boundary_start, bool p_boundary_end, uindex_t& r_first, uindex_t& r_chunk_count)
{
return MCChunkGetExtentsByExpressionInRange(p_strict, p_boundary_start, p_boundary_end, p_first, MCChunkCountCodeunitChunkCallback, &p_string, p_range, r_first, r_chunk_count);
}
bool MCChunkGetExtentsOfGraphemeChunkByRangeInRange(MCStringRef p_string, MCRange *p_range, integer_t p_first, integer_t p_last, bool p_strict, bool p_boundary_start, bool p_boundary_end, uindex_t& r_first, uindex_t& r_chunk_count)
{
return MCChunkGetExtentsByRangeInRange(p_strict, p_boundary_start, p_boundary_end, p_first, p_last, MCChunkCountGraphemeChunkCallback, &p_string, p_range, r_first, r_chunk_count);
}
bool MCChunkGetExtentsOfGraphemeChunkByExpressionInRange(MCStringRef p_string, MCRange *p_range, integer_t p_first, bool p_strict, bool p_boundary_start, bool p_boundary_end, uindex_t& r_first, uindex_t& r_chunk_count)
{
return MCChunkGetExtentsByExpressionInRange(p_strict, p_boundary_start, p_boundary_end, p_first, MCChunkCountGraphemeChunkCallback, &p_string, p_range, r_first, r_chunk_count);
}
bool MCChunkGetExtentsOfElementChunkByRangeInRange(MCProperListRef p_list, MCRange *p_range, integer_t p_first, integer_t p_last, bool p_strict, bool p_boundary_start, bool p_boundary_end, uindex_t& r_first, uindex_t& r_chunk_count)
{
return MCChunkGetExtentsByRangeInRange(p_strict, p_boundary_start, p_boundary_end, p_first, p_last, MCChunkCountElementChunkCallback, &p_list, p_range, r_first, r_chunk_count);
}
bool MCChunkGetExtentsOfElementChunkByExpressionInRange(MCProperListRef p_list, MCRange *p_range, integer_t p_first, bool p_strict, bool p_boundary_start, bool p_boundary_end, uindex_t& r_first, uindex_t& r_chunk_count)
{
return MCChunkGetExtentsByExpressionInRange(p_strict, p_boundary_start, p_boundary_end, p_first, MCChunkCountElementChunkCallback, &p_list, p_range, r_first, r_chunk_count);
}
////////////////////////////////////////////////////////////////////////////////
bool MCChunkIsAmongTheChunksOfRange(MCStringRef p_chunk, MCStringRef p_string, MCStringRef p_delimiter, MCStringOptions p_options, MCRange p_range)
{
MCRange t_range;
if (!MCStringFind(p_string, p_range, p_chunk, p_options, &t_range))
return false;
uindex_t t_length;
// if there is no delimiter to the left then continue searching the string.
if (t_range . offset != 0 &&
!MCStringSharedSuffix(p_string, MCRangeMake(0, t_range . offset), p_delimiter, p_options, t_length))
return MCChunkIsAmongTheChunksOfRange(p_chunk, p_string, p_delimiter, p_options, MCRangeMake(t_range . offset + t_range . length, p_range . length));
// if there is no delimiter to the right then continue searching the string.
if (t_range . offset + t_range . length != MCStringGetLength(p_string) &&
!MCStringSharedPrefix(p_string, MCRangeMake(t_range . offset + t_range . length, UINDEX_MAX), p_delimiter, p_options, t_length))
return MCChunkIsAmongTheChunksOfRange(p_chunk, p_string, p_delimiter, p_options, MCRangeMake(t_range . offset + t_range . length, p_range . length));
return true;
}
bool MCChunkOffsetOfChunkInRange(MCStringRef p_string, MCStringRef p_needle, MCStringRef p_delimiter, bool p_whole_matches, MCStringOptions p_options, MCRange p_range, uindex_t& r_offset)
{
// If we can't find the chunk in the remainder of the string, we are done.
MCRange t_range;
if (!MCStringFind(p_string, p_range, p_needle, p_options, &t_range))
return false;
uindex_t t_length;
// If we are in wholeMatches mode, ensure the delimiter is either side.
if (p_whole_matches)
{
if (t_range . offset > 0 &&
!MCStringSharedSuffix(p_string, MCRangeMake(0, t_range . offset), p_delimiter, p_options, t_length))
return MCChunkOffsetOfChunkInRange(p_string, p_needle, p_delimiter, p_whole_matches, p_options, MCRangeMake(t_range . offset + t_range . length, p_range . length), r_offset);
if (t_range . offset + t_range . length < MCStringGetLength(p_string) &&
!MCStringSharedPrefix(p_string, MCRangeMake(t_range . offset + t_range . length, UINDEX_MAX), p_delimiter, p_options, t_length))
return MCChunkOffsetOfChunkInRange(p_string, p_needle, p_delimiter, p_whole_matches, p_options, MCRangeMake(t_range . offset + t_range . length + 1, p_range . length), r_offset);
}
r_offset = t_range . offset;
return true;
}
void MCChunkSkipWord(MCStringRef p_string, MCStringRef p_line_delimiter, MCStringOptions p_options, bool p_skip_spaces, uindex_t& x_offset)
{
uindex_t t_length = MCStringGetLength(p_string);
uindex_t t_end_quote_offset = t_length;
uindex_t t_end_line_offset = t_length;
if (MCStringGetCharAtIndex(p_string, x_offset) == '"')
{
// then bump the offset up to the next quotation mark + 1, or the beginning of the next line
// if neither of these are present then set offset to string length.
if (!MCStringFirstIndexOfChar(p_string, '"', x_offset + 1, kMCStringOptionCompareExact, t_end_quote_offset))
t_end_quote_offset = t_length;
if (!MCStringFirstIndexOf(p_string, p_line_delimiter, x_offset + 1, p_options, t_end_line_offset))
t_end_line_offset = t_length;
if (t_end_quote_offset < t_end_line_offset)
x_offset = t_end_quote_offset + 1;
else if (t_end_line_offset < t_end_quote_offset)
x_offset = t_end_line_offset + MCStringGetLength(p_line_delimiter);
else
x_offset = t_length;
}
else
{
while (!MCUnicodeIsWhitespace(MCStringGetCharAtIndex(p_string, x_offset)) && x_offset < t_length)
x_offset++;
}
if (p_skip_spaces)
{
while (MCUnicodeIsWhitespace(MCStringGetCharAtIndex(p_string, x_offset)) && x_offset < t_length)
x_offset++;
}
}
////////////////////////////////////////////////////////////////////////////////
MCTextChunkIterator::MCTextChunkIterator(MCStringRef p_text, MCChunkType p_chunk_type)
{
m_text = MCValueRetain(p_text);
m_length = MCStringGetLength(p_text);
m_chunk_type = p_chunk_type;
m_range = MCRangeMake(0, 0);
// AL-2014-10-24: [[ Bug 13783 ]] Set exhausted to true if the string is immediately exhausted
m_exhausted = MCStringIsEmpty(p_text);
m_options = kMCStringOptionCompareCaseless;
}
// AL-2015-02-10: [[ Bug 14532 ]] Add text chunk iterator constructor for restricted range chunk operations.
MCTextChunkIterator::MCTextChunkIterator(MCStringRef p_text, MCChunkType p_chunk_type, MCRange p_restriction)
{
m_text = MCValueRetain(p_text);
m_length = p_restriction . length == UINDEX_MAX ? MCStringGetLength(m_text) : p_restriction . offset + p_restriction . length;
m_chunk_type = p_chunk_type;
m_range = MCRangeMake(p_restriction . offset, 0);
// AL-2014-10-24: [[ Bug 13783 ]] Set exhausted to true if the string is immediately exhausted
m_exhausted = (p_restriction . length == 0 || p_restriction . offset>= MCStringGetLength(m_text));
m_options = kMCStringOptionCompareCaseless;
}
MCTextChunkIterator::~MCTextChunkIterator()
{
MCValueRelease(m_text);
}
////////////////////////////////////////////////////////////////////////////////
MCTextChunkIterator_Grapheme::MCTextChunkIterator_Grapheme(MCStringRef p_text, MCChunkType p_chunk_type) : MCTextChunkIterator(p_text, p_chunk_type)
{
;
}
MCTextChunkIterator_Grapheme::MCTextChunkIterator_Grapheme(MCStringRef p_text, MCChunkType p_chunk_type, MCRange p_restriction) : MCTextChunkIterator(p_text, p_chunk_type, p_restriction)
{
;
}
MCTextChunkIterator_Grapheme::~MCTextChunkIterator_Grapheme()
{
;
}
bool MCTextChunkIterator_Grapheme::Next()
{
m_range . offset = m_range . offset + m_range . length;
if (m_range . offset >= m_length)
return false;
uindex_t t_next;
t_next = MCStringGraphemeBreakIteratorAdvance(m_text, m_range . offset);
if (t_next == kMCLocaleBreakIteratorDone)
{
m_exhausted = true;
t_next = m_length;
}
m_range . length = t_next - m_range . offset;
return true;
}
bool MCTextChunkIterator_Grapheme::IsAmong(MCStringRef p_needle)
{
if (MCStringIsEmpty(p_needle))
return false;
while (Next())
if (MCStringSubstringIsEqualTo(m_text, m_range, p_needle, m_options))
return true;
return false;
}
////////////////////////////////////////////////////////////////////////////////
MCTextChunkIterator_Codepoint::MCTextChunkIterator_Codepoint(MCStringRef p_text, MCChunkType p_chunk_type) : MCTextChunkIterator(p_text, p_chunk_type)
{
;
}
MCTextChunkIterator_Codepoint::MCTextChunkIterator_Codepoint(MCStringRef p_text, MCChunkType p_chunk_type, MCRange p_restriction) : MCTextChunkIterator(p_text, p_chunk_type, p_restriction)
{
;
}
MCTextChunkIterator_Codepoint::~MCTextChunkIterator_Codepoint()
{
;
}
bool MCTextChunkIterator_Codepoint::Next()
{
m_range . offset = m_range . offset + m_range . length;
if (m_range . offset >= m_length)
return false;
if (MCStringIsValidSurrogatePair(m_text, m_range . offset))
m_range . length = 2;
else
m_range . length = 1;
if (m_range . offset + m_range . length == m_length)
m_exhausted = true;
return true;
}
bool MCTextChunkIterator_Codepoint::IsAmong(MCStringRef p_needle)
{
if (MCStringIsEmpty(p_needle))
return false;
while (Next())
if (MCStringSubstringIsEqualTo(m_text, m_range, p_needle, m_options))
return true;
return false;
}
////////////////////////////////////////////////////////////////////////////////
MCTextChunkIterator_Codeunit::MCTextChunkIterator_Codeunit(MCStringRef p_text, MCChunkType p_chunk_type) : MCTextChunkIterator(p_text, p_chunk_type)
{
;
}
MCTextChunkIterator_Codeunit::MCTextChunkIterator_Codeunit(MCStringRef p_text, MCChunkType p_chunk_type, MCRange p_restriction) : MCTextChunkIterator(p_text, p_chunk_type, p_restriction)
{
;
}
MCTextChunkIterator_Codeunit::~MCTextChunkIterator_Codeunit()
{
;
}
bool MCTextChunkIterator_Codeunit::Next()
{
m_range . offset = m_range . offset + m_range . length;
if (m_range . offset == m_length - 1)
m_exhausted = true;
else if (m_range . offset >= m_length)
return false;
m_range . length = 1;
return true;
}
bool MCTextChunkIterator_Codeunit::IsAmong(MCStringRef p_needle)
{
if (MCStringIsEmpty(p_needle))
return false;
return MCStringFind(m_text, MCRangeMake(0, m_length), p_needle, m_options, nil);
}
uindex_t MCTextChunkIterator_Codeunit::ChunkOffset(MCStringRef p_needle, uindex_t p_start_offset, uindex_t *p_end_offset, bool p_whole_matches)
{
// AL-2015-07-20: [[ Bug 15618 ]] Search for the codeunit within the specified range
MCRange t_in_range;
t_in_range = MCRangeMake(p_start_offset, p_end_offset != nil ? *p_end_offset : m_length);
MCRange t_range;
if (MCStringFind(m_text, t_in_range, p_needle, m_options, &t_range))
{
if (!p_whole_matches || t_range . length == 1)
return t_range . offset + 1;
}
return 0;
}
uindex_t MCTextChunkIterator_Codeunit::CountChunks()
{
return m_length;
}
////////////////////////////////////////////////////////////////////////////////
MCTextChunkIterator_Delimited::MCTextChunkIterator_Delimited(MCStringRef p_text, MCChunkType p_chunk_type, MCStringRef p_delimiter) : MCTextChunkIterator(p_text, p_chunk_type)
{
m_delimiter = MCValueRetain(p_delimiter);
m_delimiter_length = MCStringGetLength(p_delimiter);
m_first_chunk = true;
}
MCTextChunkIterator_Delimited::MCTextChunkIterator_Delimited(MCStringRef p_text, MCChunkType p_chunk_type, MCStringRef p_delimiter, MCRange p_restriction) : MCTextChunkIterator(p_text, p_chunk_type, p_restriction)
{
m_delimiter = MCValueRetain(p_delimiter);
m_delimiter_length = MCStringGetLength(p_delimiter);
m_first_chunk = true;
}
MCTextChunkIterator_Delimited::~MCTextChunkIterator_Delimited()
{
MCValueRelease(m_delimiter);
}
bool MCTextChunkIterator_Delimited::Next()
{
uindex_t t_offset = m_range . offset + m_range . length;
if (!m_first_chunk)
t_offset += m_delimiter_length;
if (t_offset >= m_length)
return false;
m_range . offset = t_offset;
m_first_chunk = false;
MCRange t_found_range;
// calculate the length of the line / item
// AL-2015-02-10: [[ Bug 14532 ]] Use restricted range for delimiter search
if (!MCStringFind(m_text, MCRangeMake(t_offset, m_length - t_offset), m_delimiter, m_options, &t_found_range))
{
m_range . length = m_length - m_range . offset;
m_exhausted = true;
}
else
{
m_range . length = t_found_range . offset - m_range . offset;
// AL-2014-10-15: [[ Bug 13671 ]] Keep track of matched delimiter length to increment offset correctly
m_delimiter_length = t_found_range . length;
if (t_found_range . offset + t_found_range . length == m_length)
m_exhausted = true;
}
return true;
}
bool MCTextChunkIterator_Delimited::IsAmong(MCStringRef p_needle)
{
// if the pattern is empty, we use the default behavior -
// i.e. go through chunk by chunk to find an empty one.
if (!MCStringIsEmpty(p_needle))
{
// Otherwise we need to find p_needle and check to see if there is a delimiter either side.
// This is because of the case where the delimiter is within p_needle - e.g.
// "a,b" is among the items of "a,b,c,d" should return true.
return MCChunkIsAmongTheChunksOfRange(p_needle, m_text, m_delimiter, m_options, MCRangeMake(m_range . offset, m_length - m_range . offset));
}
while (Next())
if (MCStringSubstringIsEqualTo(m_text, m_range, p_needle, m_options))
return true;
// AL-2014-09-10: [[ Bug 13356 ]] If we were not 'exhausted', then there was a trailing delimiter
// which means empty is considered to be among the chunks.
if (MCStringIsEmpty(p_needle) && !m_exhausted)
return true;
return false;
}
uindex_t MCTextChunkIterator_Delimited::ChunkOffset(MCStringRef p_needle, uindex_t p_start_offset, uindex_t *p_end_offset, bool p_whole_matches)
{
// Ensure that when no item is skipped, the offset starts from the first item - without skipping it
uindex_t t_chunk_offset;
t_chunk_offset = 1;
// Skip ahead to the first (1-indexed) chunk of interest.
p_start_offset += 1;
while (p_start_offset)
{
if (!Next())
break;
p_start_offset--;
}
// If we skip past the last chunk, we are done.
if (p_start_offset > 0)
return 0;
// MW-2013-01-21: item/line/paragraph offset do not currently operate on a 'split' basis.
// Instead, they return the index of the chunk in which p_chunk starts and if
// wholeMatches is true, then before and after the found range must be the del
// or eos. e.g.
// itemOffset("a,b", "aa,b,cc") => 1 if wholeMatches false, 0 otherwise
// itemOffset("b,c", "a,b,c") => 2
// If we're looking for empty, then we have to iterate through the chunks.
if (!MCStringIsEmpty(p_needle))
{
uindex_t t_found_offset;
if (!MCChunkOffsetOfChunkInRange(m_text, p_needle, m_delimiter, p_whole_matches, m_options, MCRangeMake(m_range . offset, m_length - m_range . offset), t_found_offset))
return 0;
// Count the number of delimiters between the start of the first chunk
// and the start of the found string.
t_chunk_offset += MCStringCount(m_text, MCRangeMake(m_range . offset, t_found_offset - m_range . offset), m_delimiter, m_options);
// AL-2015-07-20: [[ Bug 15618 ]] If the chunk found is outside the specified range, return 0 (not found)
if (p_end_offset != nil && t_chunk_offset > *p_end_offset)
return 0;
return t_chunk_offset;
}
// Otherwise, just iterate through the chunks.
do
{
// AL-2015-07-20: [[ Bug 15618 ]] If there is an end offset, don't exceed it.
if (p_end_offset != nil && t_chunk_offset > *p_end_offset)
break;
if (p_whole_matches)
{
if (MCStringSubstringIsEqualTo(m_text, MCRangeMake(m_range . offset, m_length - m_range . offset), p_needle, m_options))
return t_chunk_offset;
}
else
{
if (MCStringSubstringContains(m_text, MCRangeMake(m_range . offset, m_length - m_range . offset), p_needle, m_options))
return t_chunk_offset;
}
t_chunk_offset++;
}
while (Next());
// if not found then return 0.
return 0;
}
////////////////////////////////////////////////////////////////////////////////
MCTextChunkIterator_ICU::MCTextChunkIterator_ICU(MCStringRef p_text, MCChunkType p_chunk_type) : MCTextChunkIterator(p_text, p_chunk_type)
{
m_break_position = 0;
MCBreakIteratorRef break_iterator;
break_iterator = nil;
switch (p_chunk_type)
{
case kMCChunkTypeSentence:
{
MCRange t_range;
uindex_t t_end;
/* UNCHECKED */ MCLocaleBreakIteratorCreate(kMCLocaleBasic, kMCBreakIteratorTypeSentence, break_iterator);
/* UNCHECKED */ MCLocaleBreakIteratorSetText(break_iterator, m_text);
t_range . length = 0;
t_range . offset = 0;
while ((t_end = MCLocaleBreakIteratorAdvance(break_iterator)) != kMCLocaleBreakIteratorDone)
{
t_range . offset += t_range . length;
t_range . length = t_end - t_range . offset;
m_breaks . Push(t_range);
}
}
break;
case kMCChunkTypeTrueWord:
{
MCAutoArray<uindex_t> t_breaks;
/* UNCHECKED */ MCLocaleBreakIteratorCreate(kMCLocaleBasic, kMCBreakIteratorTypeWord, break_iterator);
/* UNCHECKED */ MCLocaleBreakIteratorSetText(break_iterator, m_text);
MCRange t_range = MCRangeMake(0, 0);
while (MCLocaleWordBreakIteratorAdvance(m_text, break_iterator, t_range)
&& t_range . offset + t_range . length != kMCLocaleBreakIteratorDone)
{
m_breaks . Push(t_range);
}
}
break;
default:
MCUnreachable();
}
if (break_iterator != nil)
MCLocaleBreakIteratorRelease(break_iterator);
}
MCTextChunkIterator_ICU::MCTextChunkIterator_ICU(MCStringRef p_text, MCChunkType p_chunk_type, MCRange p_restriction) : MCTextChunkIterator(p_text, p_chunk_type, p_restriction)
{
m_break_position = 0;
MCBreakIteratorRef break_iterator;
break_iterator = nil;
switch (p_chunk_type)
{
case kMCChunkTypeSentence:
{
MCAutoStringRef t_substring;
MCStringCopySubstring(m_text, p_restriction, &t_substring);
MCRange t_range;
uindex_t t_end;
/* UNCHECKED */ MCLocaleBreakIteratorCreate(kMCLocaleBasic, kMCBreakIteratorTypeSentence, break_iterator);
/* UNCHECKED */ MCLocaleBreakIteratorSetText(break_iterator, *t_substring);
// PM-2015-05-26: [[ Bug 15422 ]] Start with zero length to make sure the first trueWord is counted
t_range . length = 0;
t_range . offset = p_restriction . offset;
while ((t_end = MCLocaleBreakIteratorAdvance(break_iterator)) != kMCLocaleBreakIteratorDone)
{
t_range . offset += t_range . length;
t_range . length = t_end - t_range . offset;
m_breaks . Push(t_range);
}
}
break;
case kMCChunkTypeTrueWord:
{
MCAutoStringRef t_substring;
MCStringCopySubstring(m_text, p_restriction, &t_substring);
MCAutoArray<uindex_t> t_breaks;
/* UNCHECKED */ MCLocaleBreakIteratorCreate(kMCLocaleBasic, kMCBreakIteratorTypeWord, break_iterator);
/* UNCHECKED */ MCLocaleBreakIteratorSetText(break_iterator, *t_substring);
MCRange t_rel_range;
t_rel_range = MCRangeMake(0, 0);
while (MCLocaleWordBreakIteratorAdvance(*t_substring, break_iterator, t_rel_range)
&& t_rel_range . offset + t_rel_range . length != kMCLocaleBreakIteratorDone)
{
m_breaks . Push(MCRangeMake(t_rel_range . offset + p_restriction . offset,
t_rel_range . length + p_restriction . length));
}
}
break;
default:
MCUnreachable();
}
if (break_iterator != nil)
MCLocaleBreakIteratorRelease(break_iterator);
}
MCTextChunkIterator_ICU::~MCTextChunkIterator_ICU()
{
}
bool MCTextChunkIterator_ICU::Next()
{
// We have a word, sentence or character delimiter, we just have to get the range stored from the constructor
if (m_break_position < m_breaks . Size())
{
m_range = m_breaks[m_break_position++];
if (m_break_position == m_breaks . Size())
m_exhausted = true;
return true;
}
return false;
}
////////////////////////////////////////////////////////////////////////////////
MCTextChunkIterator_Word::MCTextChunkIterator_Word(MCStringRef p_text, MCChunkType p_chunk_type, MCStringRef p_line_delimiter) : MCTextChunkIterator(p_text, p_chunk_type)
{
m_line_delimiter = MCValueRetain(p_line_delimiter);
}
MCTextChunkIterator_Word::MCTextChunkIterator_Word(MCStringRef p_text, MCChunkType p_chunk_type, MCStringRef p_line_delimiter, MCRange p_range) : MCTextChunkIterator(p_text, p_chunk_type, p_range)
{
m_line_delimiter = MCValueRetain(p_line_delimiter);
}
MCTextChunkIterator_Word::~MCTextChunkIterator_Word()
{
MCValueRelease(m_line_delimiter);
}
bool MCTextChunkIterator_Word::Next()
{
uindex_t t_offset = m_range . offset + m_range . length;
if (t_offset >= m_length)
return false;
m_range . offset = t_offset;
// if there are consecutive spaces at the beginning, skip them
while (t_offset < m_length && MCUnicodeIsWhitespace(MCStringGetCharAtIndex(m_text, t_offset)))
t_offset++;
if (t_offset >= m_length)
return false;
m_range . offset = t_offset;
MCChunkSkipWord(m_text, m_line_delimiter, m_options, false, t_offset);
// AL-2015-02-10: [[ Bug 14532 ]] Use restricted range for exhaustion check
if (t_offset >= m_length)
m_exhausted = true;
m_range . length = t_offset - m_range . offset;
return true;
}
////////////////////////////////////////////////////////////////////////////////
MCTextChunkIterator *MCChunkCreateTextChunkIterator(MCStringRef p_text, MCRange *p_range, MCChunkType p_chunk_type, MCStringRef p_line_delimiter, MCStringRef p_item_delimiter, MCStringOptions p_options)
{
p_chunk_type = MCChunkTypeSimplify(p_text, p_chunk_type);
MCTextChunkIterator *t_iterator = nil;
switch (p_chunk_type)
{
case kMCChunkTypeSentence:
case kMCChunkTypeTrueWord:
if (p_range != nil)
t_iterator = new MCTextChunkIterator_ICU(p_text, p_chunk_type, *p_range);
else
t_iterator = new MCTextChunkIterator_ICU(p_text, p_chunk_type);
break;
case kMCChunkTypeLine:
case kMCChunkTypeItem:
MCStringRef t_delimiter;
if (p_chunk_type == kMCChunkTypeLine)
t_delimiter = p_line_delimiter;
else
t_delimiter = p_item_delimiter;
if (p_range != nil)
t_iterator = new MCTextChunkIterator_Delimited(p_text, p_chunk_type, t_delimiter, *p_range);
else
t_iterator = new MCTextChunkIterator_Delimited(p_text, p_chunk_type, t_delimiter);
break;
break;
case kMCChunkTypeParagraph:
if (p_range != nil)
t_iterator = new MCTextChunkIterator_Delimited(p_text, p_chunk_type, MCSTR("\n"), *p_range);
else
t_iterator = new MCTextChunkIterator_Delimited(p_text, p_chunk_type, MCSTR("\n"));
break;
break;
case kMCChunkTypeWord:
// AL-2015-10-08: [[ Bug 16161 ]] Word chunk needs to be passed line delimiter
// as words are also delimited by line breaks.
if (p_range != nil)
t_iterator = new MCTextChunkIterator_Word(p_text, p_chunk_type, p_line_delimiter, *p_range);
else
t_iterator = new MCTextChunkIterator_Word(p_text, p_chunk_type, p_line_delimiter);
break;
case kMCChunkTypeCharacter:
if (p_range != nil)
t_iterator = new MCTextChunkIterator_Grapheme(p_text, p_chunk_type, *p_range);
else
t_iterator = new MCTextChunkIterator_Grapheme(p_text, p_chunk_type);
break;
case kMCChunkTypeCodepoint:
if (p_range != nil)
t_iterator = new MCTextChunkIterator_Codepoint(p_text, p_chunk_type, *p_range);
else
t_iterator = new MCTextChunkIterator_Codepoint(p_text, p_chunk_type);
break;
case kMCChunkTypeCodeunit:
if (p_range != nil)
t_iterator = new MCTextChunkIterator_Codeunit(p_text, p_chunk_type, *p_range);
else
t_iterator = new MCTextChunkIterator_Codeunit(p_text, p_chunk_type);
break;
default:
MCAssert(false);
}
t_iterator -> SetOptions(p_options);
return t_iterator;
}
////////////////////////////////////////////////////////////////////////////////
MCChunkType MCChunkTypeSimplify(MCStringRef p_string, MCChunkType p_type)
{
switch (p_type)
{
case kMCChunkTypeCharacter:
{
if (MCStringIsTrivial(p_string))
return kMCChunkTypeCodeunit;
break;
}
case kMCChunkTypeCodepoint:
{
if (MCStringIsBasic(p_string))
return kMCChunkTypeCodeunit;
break;
}
default:
break;
}
return p_type;
}
MCChunkType MCChunkTypeFromCharChunkType(MCCharChunkType p_char_type)
{
switch (p_char_type)
{
case kMCCharChunkTypeCodeunit:
return kMCChunkTypeCodeunit;
case kMCCharChunkTypeCodepoint:
return kMCChunkTypeCodepoint;
case kMCCharChunkTypeGrapheme:
return kMCChunkTypeCharacter;
default:
MCUnreachableReturn(kMCChunkTypeCharacter);
}
}