forked from python/cpython
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathunicodedata.c
1377 lines (1218 loc) · 40.9 KB
/
unicodedata.c
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
/* ------------------------------------------------------------------------
unicodedata -- Provides access to the Unicode database.
Data was extracted from the UnicodeData.txt file.
The current version number is reported in the unidata_version constant.
Written by Marc-Andre Lemburg (mal@lemburg.com).
Modified for Python 2.0 by Fredrik Lundh (fredrik@pythonware.com)
Modified by Martin v. Löwis (martin@v.loewis.de)
Copyright (c) Corporation for National Research Initiatives.
------------------------------------------------------------------------ */
#define PY_SSIZE_T_CLEAN
#include "Python.h"
#include "ucnhash.h"
#include "structmember.h"
/*[clinic input]
module unicodedata
class unicodedata.UCD 'PreviousDBVersion *' '&UCD_Type'
[clinic start generated code]*/
/*[clinic end generated code: output=da39a3ee5e6b4b0d input=6dac153082d150bc]*/
/* character properties */
typedef struct {
const unsigned char category; /* index into
_PyUnicode_CategoryNames */
const unsigned char combining; /* combining class value 0 - 255 */
const unsigned char bidirectional; /* index into
_PyUnicode_BidirectionalNames */
const unsigned char mirrored; /* true if mirrored in bidir mode */
const unsigned char east_asian_width; /* index into
_PyUnicode_EastAsianWidth */
const unsigned char normalization_quick_check; /* see is_normalized() */
} _PyUnicode_DatabaseRecord;
typedef struct change_record {
/* sequence of fields should be the same as in merge_old_version */
const unsigned char bidir_changed;
const unsigned char category_changed;
const unsigned char decimal_changed;
const unsigned char mirrored_changed;
const unsigned char east_asian_width_changed;
const double numeric_changed;
} change_record;
/* data file generated by Tools/unicode/makeunicodedata.py */
#include "unicodedata_db.h"
static const _PyUnicode_DatabaseRecord*
_getrecord_ex(Py_UCS4 code)
{
int index;
if (code >= 0x110000)
index = 0;
else {
index = index1[(code>>SHIFT)];
index = index2[(index<<SHIFT)+(code&((1<<SHIFT)-1))];
}
return &_PyUnicode_Database_Records[index];
}
/* ------------- Previous-version API ------------------------------------- */
typedef struct previous_version {
PyObject_HEAD
const char *name;
const change_record* (*getrecord)(Py_UCS4);
Py_UCS4 (*normalization)(Py_UCS4);
} PreviousDBVersion;
#include "clinic/unicodedata.c.h"
#define get_old_record(self, v) ((((PreviousDBVersion*)self)->getrecord)(v))
static PyMemberDef DB_members[] = {
{"unidata_version", T_STRING, offsetof(PreviousDBVersion, name), READONLY},
{NULL}
};
/* forward declaration */
static PyTypeObject UCD_Type;
#define UCD_Check(o) (Py_TYPE(o)==&UCD_Type)
static PyObject*
new_previous_version(const char*name, const change_record* (*getrecord)(Py_UCS4),
Py_UCS4 (*normalization)(Py_UCS4))
{
PreviousDBVersion *self;
self = PyObject_New(PreviousDBVersion, &UCD_Type);
if (self == NULL)
return NULL;
self->name = name;
self->getrecord = getrecord;
self->normalization = normalization;
return (PyObject*)self;
}
/* --- Module API --------------------------------------------------------- */
/*[clinic input]
unicodedata.UCD.decimal
self: self
chr: int(accept={str})
default: object=NULL
/
Converts a Unicode character into its equivalent decimal value.
Returns the decimal value assigned to the character chr as integer.
If no such value is defined, default is returned, or, if not given,
ValueError is raised.
[clinic start generated code]*/
static PyObject *
unicodedata_UCD_decimal_impl(PyObject *self, int chr,
PyObject *default_value)
/*[clinic end generated code: output=be23376e1a185231 input=933f8107993f23d0]*/
{
int have_old = 0;
long rc;
Py_UCS4 c = (Py_UCS4)chr;
if (self && UCD_Check(self)) {
const change_record *old = get_old_record(self, c);
if (old->category_changed == 0) {
/* unassigned */
have_old = 1;
rc = -1;
}
else if (old->decimal_changed != 0xFF) {
have_old = 1;
rc = old->decimal_changed;
}
}
if (!have_old)
rc = Py_UNICODE_TODECIMAL(c);
if (rc < 0) {
if (default_value == NULL) {
PyErr_SetString(PyExc_ValueError,
"not a decimal");
return NULL;
}
else {
Py_INCREF(default_value);
return default_value;
}
}
return PyLong_FromLong(rc);
}
/*[clinic input]
unicodedata.UCD.digit
self: self
chr: int(accept={str})
default: object=NULL
/
Converts a Unicode character into its equivalent digit value.
Returns the digit value assigned to the character chr as integer.
If no such value is defined, default is returned, or, if not given,
ValueError is raised.
[clinic start generated code]*/
static PyObject *
unicodedata_UCD_digit_impl(PyObject *self, int chr, PyObject *default_value)
/*[clinic end generated code: output=96e18c950171fd2f input=e27d6e4565cd29f2]*/
{
long rc;
Py_UCS4 c = (Py_UCS4)chr;
rc = Py_UNICODE_TODIGIT(c);
if (rc < 0) {
if (default_value == NULL) {
PyErr_SetString(PyExc_ValueError, "not a digit");
return NULL;
}
else {
Py_INCREF(default_value);
return default_value;
}
}
return PyLong_FromLong(rc);
}
/*[clinic input]
unicodedata.UCD.numeric
self: self
chr: int(accept={str})
default: object=NULL
/
Converts a Unicode character into its equivalent numeric value.
Returns the numeric value assigned to the character chr as float.
If no such value is defined, default is returned, or, if not given,
ValueError is raised.
[clinic start generated code]*/
static PyObject *
unicodedata_UCD_numeric_impl(PyObject *self, int chr,
PyObject *default_value)
/*[clinic end generated code: output=53ce281fe85b10c4 input=fdf5871a5542893c]*/
{
int have_old = 0;
double rc;
Py_UCS4 c = (Py_UCS4)chr;
if (self && UCD_Check(self)) {
const change_record *old = get_old_record(self, c);
if (old->category_changed == 0) {
/* unassigned */
have_old = 1;
rc = -1.0;
}
else if (old->decimal_changed != 0xFF) {
have_old = 1;
rc = old->decimal_changed;
}
}
if (!have_old)
rc = Py_UNICODE_TONUMERIC(c);
if (rc == -1.0) {
if (default_value == NULL) {
PyErr_SetString(PyExc_ValueError, "not a numeric character");
return NULL;
}
else {
Py_INCREF(default_value);
return default_value;
}
}
return PyFloat_FromDouble(rc);
}
/*[clinic input]
unicodedata.UCD.category
self: self
chr: int(accept={str})
/
Returns the general category assigned to the character chr as string.
[clinic start generated code]*/
static PyObject *
unicodedata_UCD_category_impl(PyObject *self, int chr)
/*[clinic end generated code: output=8571539ee2e6783a input=27d6f3d85050bc06]*/
{
int index;
Py_UCS4 c = (Py_UCS4)chr;
index = (int) _getrecord_ex(c)->category;
if (self && UCD_Check(self)) {
const change_record *old = get_old_record(self, c);
if (old->category_changed != 0xFF)
index = old->category_changed;
}
return PyUnicode_FromString(_PyUnicode_CategoryNames[index]);
}
/*[clinic input]
unicodedata.UCD.bidirectional
self: self
chr: int(accept={str})
/
Returns the bidirectional class assigned to the character chr as string.
If no such value is defined, an empty string is returned.
[clinic start generated code]*/
static PyObject *
unicodedata_UCD_bidirectional_impl(PyObject *self, int chr)
/*[clinic end generated code: output=d36310ce2039bb92 input=b3d8f42cebfcf475]*/
{
int index;
Py_UCS4 c = (Py_UCS4)chr;
index = (int) _getrecord_ex(c)->bidirectional;
if (self && UCD_Check(self)) {
const change_record *old = get_old_record(self, c);
if (old->category_changed == 0)
index = 0; /* unassigned */
else if (old->bidir_changed != 0xFF)
index = old->bidir_changed;
}
return PyUnicode_FromString(_PyUnicode_BidirectionalNames[index]);
}
/*[clinic input]
unicodedata.UCD.combining -> int
self: self
chr: int(accept={str})
/
Returns the canonical combining class assigned to the character chr as integer.
Returns 0 if no combining class is defined.
[clinic start generated code]*/
static int
unicodedata_UCD_combining_impl(PyObject *self, int chr)
/*[clinic end generated code: output=cad056d0cb6a5920 input=9f2d6b2a95d0a22a]*/
{
int index;
Py_UCS4 c = (Py_UCS4)chr;
index = (int) _getrecord_ex(c)->combining;
if (self && UCD_Check(self)) {
const change_record *old = get_old_record(self, c);
if (old->category_changed == 0)
index = 0; /* unassigned */
}
return index;
}
/*[clinic input]
unicodedata.UCD.mirrored -> int
self: self
chr: int(accept={str})
/
Returns the mirrored property assigned to the character chr as integer.
Returns 1 if the character has been identified as a "mirrored"
character in bidirectional text, 0 otherwise.
[clinic start generated code]*/
static int
unicodedata_UCD_mirrored_impl(PyObject *self, int chr)
/*[clinic end generated code: output=2532dbf8121b50e6 input=5dd400d351ae6f3b]*/
{
int index;
Py_UCS4 c = (Py_UCS4)chr;
index = (int) _getrecord_ex(c)->mirrored;
if (self && UCD_Check(self)) {
const change_record *old = get_old_record(self, c);
if (old->category_changed == 0)
index = 0; /* unassigned */
else if (old->mirrored_changed != 0xFF)
index = old->mirrored_changed;
}
return index;
}
/*[clinic input]
unicodedata.UCD.east_asian_width
self: self
chr: int(accept={str})
/
Returns the east asian width assigned to the character chr as string.
[clinic start generated code]*/
static PyObject *
unicodedata_UCD_east_asian_width_impl(PyObject *self, int chr)
/*[clinic end generated code: output=484e8537d9ee8197 input=c4854798aab026e0]*/
{
int index;
Py_UCS4 c = (Py_UCS4)chr;
index = (int) _getrecord_ex(c)->east_asian_width;
if (self && UCD_Check(self)) {
const change_record *old = get_old_record(self, c);
if (old->category_changed == 0)
index = 0; /* unassigned */
else if (old->east_asian_width_changed != 0xFF)
index = old->east_asian_width_changed;
}
return PyUnicode_FromString(_PyUnicode_EastAsianWidthNames[index]);
}
/*[clinic input]
unicodedata.UCD.decomposition
self: self
chr: int(accept={str})
/
Returns the character decomposition mapping assigned to the character chr as string.
An empty string is returned in case no such mapping is defined.
[clinic start generated code]*/
static PyObject *
unicodedata_UCD_decomposition_impl(PyObject *self, int chr)
/*[clinic end generated code: output=7d699f3ec7565d27 input=e4c12459ad68507b]*/
{
char decomp[256];
int code, index, count;
size_t i;
unsigned int prefix_index;
Py_UCS4 c = (Py_UCS4)chr;
code = (int)c;
if (self && UCD_Check(self)) {
const change_record *old = get_old_record(self, c);
if (old->category_changed == 0)
return PyUnicode_FromString(""); /* unassigned */
}
if (code < 0 || code >= 0x110000)
index = 0;
else {
index = decomp_index1[(code>>DECOMP_SHIFT)];
index = decomp_index2[(index<<DECOMP_SHIFT)+
(code&((1<<DECOMP_SHIFT)-1))];
}
/* high byte is number of hex bytes (usually one or two), low byte
is prefix code (from*/
count = decomp_data[index] >> 8;
/* XXX: could allocate the PyString up front instead
(strlen(prefix) + 5 * count + 1 bytes) */
/* Based on how index is calculated above and decomp_data is generated
from Tools/unicode/makeunicodedata.py, it should not be possible
to overflow decomp_prefix. */
prefix_index = decomp_data[index] & 255;
assert(prefix_index < Py_ARRAY_LENGTH(decomp_prefix));
/* copy prefix */
i = strlen(decomp_prefix[prefix_index]);
memcpy(decomp, decomp_prefix[prefix_index], i);
while (count-- > 0) {
if (i)
decomp[i++] = ' ';
assert(i < sizeof(decomp));
PyOS_snprintf(decomp + i, sizeof(decomp) - i, "%04X",
decomp_data[++index]);
i += strlen(decomp + i);
}
return PyUnicode_FromStringAndSize(decomp, i);
}
static void
get_decomp_record(PyObject *self, Py_UCS4 code, int *index, int *prefix, int *count)
{
if (code >= 0x110000) {
*index = 0;
} else if (self && UCD_Check(self) &&
get_old_record(self, code)->category_changed==0) {
/* unassigned in old version */
*index = 0;
}
else {
*index = decomp_index1[(code>>DECOMP_SHIFT)];
*index = decomp_index2[(*index<<DECOMP_SHIFT)+
(code&((1<<DECOMP_SHIFT)-1))];
}
/* high byte is number of hex bytes (usually one or two), low byte
is prefix code (from*/
*count = decomp_data[*index] >> 8;
*prefix = decomp_data[*index] & 255;
(*index)++;
}
#define SBase 0xAC00
#define LBase 0x1100
#define VBase 0x1161
#define TBase 0x11A7
#define LCount 19
#define VCount 21
#define TCount 28
#define NCount (VCount*TCount)
#define SCount (LCount*NCount)
static PyObject*
nfd_nfkd(PyObject *self, PyObject *input, int k)
{
PyObject *result;
Py_UCS4 *output;
Py_ssize_t i, o, osize;
int kind;
void *data;
/* Longest decomposition in Unicode 3.2: U+FDFA */
Py_UCS4 stack[20];
Py_ssize_t space, isize;
int index, prefix, count, stackptr;
unsigned char prev, cur;
stackptr = 0;
isize = PyUnicode_GET_LENGTH(input);
space = isize;
/* Overallocate at most 10 characters. */
if (space > 10) {
if (space <= PY_SSIZE_T_MAX - 10)
space += 10;
}
else {
space *= 2;
}
osize = space;
output = PyMem_NEW(Py_UCS4, space);
if (!output) {
PyErr_NoMemory();
return NULL;
}
i = o = 0;
kind = PyUnicode_KIND(input);
data = PyUnicode_DATA(input);
while (i < isize) {
stack[stackptr++] = PyUnicode_READ(kind, data, i++);
while(stackptr) {
Py_UCS4 code = stack[--stackptr];
/* Hangul Decomposition adds three characters in
a single step, so we need at least that much room. */
if (space < 3) {
Py_UCS4 *new_output;
osize += 10;
space += 10;
new_output = PyMem_Realloc(output, osize*sizeof(Py_UCS4));
if (new_output == NULL) {
PyMem_Free(output);
PyErr_NoMemory();
return NULL;
}
output = new_output;
}
/* Hangul Decomposition. */
if (SBase <= code && code < (SBase+SCount)) {
int SIndex = code - SBase;
int L = LBase + SIndex / NCount;
int V = VBase + (SIndex % NCount) / TCount;
int T = TBase + SIndex % TCount;
output[o++] = L;
output[o++] = V;
space -= 2;
if (T != TBase) {
output[o++] = T;
space --;
}
continue;
}
/* normalization changes */
if (self && UCD_Check(self)) {
Py_UCS4 value = ((PreviousDBVersion*)self)->normalization(code);
if (value != 0) {
stack[stackptr++] = value;
continue;
}
}
/* Other decompositions. */
get_decomp_record(self, code, &index, &prefix, &count);
/* Copy character if it is not decomposable, or has a
compatibility decomposition, but we do NFD. */
if (!count || (prefix && !k)) {
output[o++] = code;
space--;
continue;
}
/* Copy decomposition onto the stack, in reverse
order. */
while(count) {
code = decomp_data[index + (--count)];
stack[stackptr++] = code;
}
}
}
result = PyUnicode_FromKindAndData(PyUnicode_4BYTE_KIND,
output, o);
PyMem_Free(output);
if (!result)
return NULL;
/* result is guaranteed to be ready, as it is compact. */
kind = PyUnicode_KIND(result);
data = PyUnicode_DATA(result);
/* Sort canonically. */
i = 0;
prev = _getrecord_ex(PyUnicode_READ(kind, data, i))->combining;
for (i++; i < PyUnicode_GET_LENGTH(result); i++) {
cur = _getrecord_ex(PyUnicode_READ(kind, data, i))->combining;
if (prev == 0 || cur == 0 || prev <= cur) {
prev = cur;
continue;
}
/* Non-canonical order. Need to switch *i with previous. */
o = i - 1;
while (1) {
Py_UCS4 tmp = PyUnicode_READ(kind, data, o+1);
PyUnicode_WRITE(kind, data, o+1,
PyUnicode_READ(kind, data, o));
PyUnicode_WRITE(kind, data, o, tmp);
o--;
if (o < 0)
break;
prev = _getrecord_ex(PyUnicode_READ(kind, data, o))->combining;
if (prev == 0 || prev <= cur)
break;
}
prev = _getrecord_ex(PyUnicode_READ(kind, data, i))->combining;
}
return result;
}
static int
find_nfc_index(PyObject *self, struct reindex* nfc, Py_UCS4 code)
{
unsigned int index;
for (index = 0; nfc[index].start; index++) {
unsigned int start = nfc[index].start;
if (code < start)
return -1;
if (code <= start + nfc[index].count) {
unsigned int delta = code - start;
return nfc[index].index + delta;
}
}
return -1;
}
static PyObject*
nfc_nfkc(PyObject *self, PyObject *input, int k)
{
PyObject *result;
int kind;
void *data;
Py_UCS4 *output;
Py_ssize_t i, i1, o, len;
int f,l,index,index1,comb;
Py_UCS4 code;
Py_ssize_t skipped[20];
int cskipped = 0;
result = nfd_nfkd(self, input, k);
if (!result)
return NULL;
/* result will be "ready". */
kind = PyUnicode_KIND(result);
data = PyUnicode_DATA(result);
len = PyUnicode_GET_LENGTH(result);
/* We allocate a buffer for the output.
If we find that we made no changes, we still return
the NFD result. */
output = PyMem_NEW(Py_UCS4, len);
if (!output) {
PyErr_NoMemory();
Py_DECREF(result);
return 0;
}
i = o = 0;
again:
while (i < len) {
for (index = 0; index < cskipped; index++) {
if (skipped[index] == i) {
/* *i character is skipped.
Remove from list. */
skipped[index] = skipped[cskipped-1];
cskipped--;
i++;
goto again; /* continue while */
}
}
/* Hangul Composition. We don't need to check for <LV,T>
pairs, since we always have decomposed data. */
code = PyUnicode_READ(kind, data, i);
if (LBase <= code && code < (LBase+LCount) &&
i + 1 < len &&
VBase <= PyUnicode_READ(kind, data, i+1) &&
PyUnicode_READ(kind, data, i+1) < (VBase+VCount)) {
/* check L character is a modern leading consonant (0x1100 ~ 0x1112)
and V character is a modern vowel (0x1161 ~ 0x1175). */
int LIndex, VIndex;
LIndex = code - LBase;
VIndex = PyUnicode_READ(kind, data, i+1) - VBase;
code = SBase + (LIndex*VCount+VIndex)*TCount;
i+=2;
if (i < len &&
TBase < PyUnicode_READ(kind, data, i) &&
PyUnicode_READ(kind, data, i) < (TBase+TCount)) {
/* check T character is a modern trailing consonant
(0x11A8 ~ 0x11C2). */
code += PyUnicode_READ(kind, data, i)-TBase;
i++;
}
output[o++] = code;
continue;
}
/* code is still input[i] here */
f = find_nfc_index(self, nfc_first, code);
if (f == -1) {
output[o++] = code;
i++;
continue;
}
/* Find next unblocked character. */
i1 = i+1;
comb = 0;
/* output base character for now; might be updated later. */
output[o] = PyUnicode_READ(kind, data, i);
while (i1 < len) {
Py_UCS4 code1 = PyUnicode_READ(kind, data, i1);
int comb1 = _getrecord_ex(code1)->combining;
if (comb) {
if (comb1 == 0)
break;
if (comb >= comb1) {
/* Character is blocked. */
i1++;
continue;
}
}
l = find_nfc_index(self, nfc_last, code1);
/* i1 cannot be combined with i. If i1
is a starter, we don't need to look further.
Otherwise, record the combining class. */
if (l == -1) {
not_combinable:
if (comb1 == 0)
break;
comb = comb1;
i1++;
continue;
}
index = f*TOTAL_LAST + l;
index1 = comp_index[index >> COMP_SHIFT];
code = comp_data[(index1<<COMP_SHIFT)+
(index&((1<<COMP_SHIFT)-1))];
if (code == 0)
goto not_combinable;
/* Replace the original character. */
output[o] = code;
/* Mark the second character unused. */
assert(cskipped < 20);
skipped[cskipped++] = i1;
i1++;
f = find_nfc_index(self, nfc_first, output[o]);
if (f == -1)
break;
}
/* Output character was already written.
Just advance the indices. */
o++; i++;
}
if (o == len) {
/* No changes. Return original string. */
PyMem_Free(output);
return result;
}
Py_DECREF(result);
result = PyUnicode_FromKindAndData(PyUnicode_4BYTE_KIND,
output, o);
PyMem_Free(output);
return result;
}
/* Return 1 if the input is certainly normalized, 0 if it might not be. */
static int
is_normalized(PyObject *self, PyObject *input, int nfc, int k)
{
Py_ssize_t i, len;
int kind;
void *data;
unsigned char prev_combining = 0, quickcheck_mask;
/* An older version of the database is requested, quickchecks must be
disabled. */
if (self && UCD_Check(self))
return 0;
/* The two quickcheck bits at this shift mean 0=Yes, 1=Maybe, 2=No,
as described in http://unicode.org/reports/tr15/#Annex8. */
quickcheck_mask = 3 << ((nfc ? 4 : 0) + (k ? 2 : 0));
i = 0;
kind = PyUnicode_KIND(input);
data = PyUnicode_DATA(input);
len = PyUnicode_GET_LENGTH(input);
while (i < len) {
Py_UCS4 ch = PyUnicode_READ(kind, data, i++);
const _PyUnicode_DatabaseRecord *record = _getrecord_ex(ch);
unsigned char combining = record->combining;
unsigned char quickcheck = record->normalization_quick_check;
if (quickcheck & quickcheck_mask)
return 0; /* this string might need normalization */
if (combining && prev_combining > combining)
return 0; /* non-canonical sort order, not normalized */
prev_combining = combining;
}
return 1; /* certainly normalized */
}
/*[clinic input]
unicodedata.UCD.normalize
self: self
form: str
unistr as input: unicode
/
Return the normal form 'form' for the Unicode string unistr.
Valid values for form are 'NFC', 'NFKC', 'NFD', and 'NFKD'.
[clinic start generated code]*/
static PyObject *
unicodedata_UCD_normalize_impl(PyObject *self, const char *form,
PyObject *input)
/*[clinic end generated code: output=62d1f8870027efdc input=1744c55f4ab79bf0]*/
{
if (PyUnicode_GET_LENGTH(input) == 0) {
/* Special case empty input strings, since resizing
them later would cause internal errors. */
Py_INCREF(input);
return input;
}
if (strcmp(form, "NFC") == 0) {
if (is_normalized(self, input, 1, 0)) {
Py_INCREF(input);
return input;
}
return nfc_nfkc(self, input, 0);
}
if (strcmp(form, "NFKC") == 0) {
if (is_normalized(self, input, 1, 1)) {
Py_INCREF(input);
return input;
}
return nfc_nfkc(self, input, 1);
}
if (strcmp(form, "NFD") == 0) {
if (is_normalized(self, input, 0, 0)) {
Py_INCREF(input);
return input;
}
return nfd_nfkd(self, input, 0);
}
if (strcmp(form, "NFKD") == 0) {
if (is_normalized(self, input, 0, 1)) {
Py_INCREF(input);
return input;
}
return nfd_nfkd(self, input, 1);
}
PyErr_SetString(PyExc_ValueError, "invalid normalization form");
return NULL;
}
/* -------------------------------------------------------------------- */
/* unicode character name tables */
/* data file generated by Tools/unicode/makeunicodedata.py */
#include "unicodename_db.h"
/* -------------------------------------------------------------------- */
/* database code (cut and pasted from the unidb package) */
static unsigned long
_gethash(const char *s, int len, int scale)
{
int i;
unsigned long h = 0;
unsigned long ix;
for (i = 0; i < len; i++) {
h = (h * scale) + (unsigned char) Py_TOUPPER(Py_CHARMASK(s[i]));
ix = h & 0xff000000;
if (ix)
h = (h ^ ((ix>>24) & 0xff)) & 0x00ffffff;
}
return h;
}
static const char * const hangul_syllables[][3] = {
{ "G", "A", "" },
{ "GG", "AE", "G" },
{ "N", "YA", "GG" },
{ "D", "YAE", "GS" },
{ "DD", "EO", "N", },
{ "R", "E", "NJ" },
{ "M", "YEO", "NH" },
{ "B", "YE", "D" },
{ "BB", "O", "L" },
{ "S", "WA", "LG" },
{ "SS", "WAE", "LM" },
{ "", "OE", "LB" },
{ "J", "YO", "LS" },
{ "JJ", "U", "LT" },
{ "C", "WEO", "LP" },
{ "K", "WE", "LH" },
{ "T", "WI", "M" },
{ "P", "YU", "B" },
{ "H", "EU", "BS" },
{ 0, "YI", "S" },
{ 0, "I", "SS" },
{ 0, 0, "NG" },
{ 0, 0, "J" },
{ 0, 0, "C" },
{ 0, 0, "K" },
{ 0, 0, "T" },
{ 0, 0, "P" },
{ 0, 0, "H" }
};
/* These ranges need to match makeunicodedata.py:cjk_ranges. */
static int
is_unified_ideograph(Py_UCS4 code)
{
return
(0x3400 <= code && code <= 0x4DB5) || /* CJK Ideograph Extension A */
(0x4E00 <= code && code <= 0x9FEF) || /* CJK Ideograph */
(0x20000 <= code && code <= 0x2A6D6) || /* CJK Ideograph Extension B */
(0x2A700 <= code && code <= 0x2B734) || /* CJK Ideograph Extension C */
(0x2B740 <= code && code <= 0x2B81D) || /* CJK Ideograph Extension D */
(0x2B820 <= code && code <= 0x2CEA1) || /* CJK Ideograph Extension E */
(0x2CEB0 <= code && code <= 0x2EBEF); /* CJK Ideograph Extension F */
}
/* macros used to determine if the given code point is in the PUA range that
* we are using to store aliases and named sequences */
#define IS_ALIAS(cp) ((cp >= aliases_start) && (cp < aliases_end))
#define IS_NAMED_SEQ(cp) ((cp >= named_sequences_start) && \
(cp < named_sequences_end))
static int
_getucname(PyObject *self, Py_UCS4 code, char* buffer, int buflen,
int with_alias_and_seq)
{
/* Find the name associated with the given code point.
* If with_alias_and_seq is 1, check for names in the Private Use Area 15
* that we are using for aliases and named sequences. */
int offset;
int i;
int word;
unsigned char* w;
if (code >= 0x110000)
return 0;
/* XXX should we just skip all the code points in the PUAs here? */
if (!with_alias_and_seq && (IS_ALIAS(code) || IS_NAMED_SEQ(code)))
return 0;
if (self && UCD_Check(self)) {
/* in 3.2.0 there are no aliases and named sequences */
const change_record *old;
if (IS_ALIAS(code) || IS_NAMED_SEQ(code))
return 0;
old = get_old_record(self, code);
if (old->category_changed == 0) {
/* unassigned */
return 0;
}
}
if (SBase <= code && code < SBase+SCount) {
/* Hangul syllable. */
int SIndex = code - SBase;
int L = SIndex / NCount;
int V = (SIndex % NCount) / TCount;
int T = SIndex % TCount;
if (buflen < 27)
/* Worst case: HANGUL SYLLABLE <10chars>. */
return 0;
strcpy(buffer, "HANGUL SYLLABLE ");
buffer += 16;
strcpy(buffer, hangul_syllables[L][0]);
buffer += strlen(hangul_syllables[L][0]);
strcpy(buffer, hangul_syllables[V][1]);
buffer += strlen(hangul_syllables[V][1]);
strcpy(buffer, hangul_syllables[T][2]);
buffer += strlen(hangul_syllables[T][2]);
*buffer = '\0';
return 1;
}
if (is_unified_ideograph(code)) {
if (buflen < 28)
/* Worst case: CJK UNIFIED IDEOGRAPH-20000 */
return 0;
sprintf(buffer, "CJK UNIFIED IDEOGRAPH-%X", code);
return 1;