Repository navigation
Expand file tree
/
Copy pathcodecs.h
More file actions
828 lines (781 loc) · 27.4 KB
/
Copy pathcodecs.h
File metadata and controls
828 lines (781 loc) · 27.4 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
/* stringlib: codec implementations */
#if !STRINGLIB_IS_UNICODE
# error "codecs.h is specific to Unicode"
#endif
/* Mask to quickly check whether a C 'long' contains a
non-ASCII, UTF8-encoded char. */
#if (SIZEOF_LONG == 8)
# define ASCII_CHAR_MASK 0x8080808080808080UL
#elif (SIZEOF_LONG == 4)
# define ASCII_CHAR_MASK 0x80808080UL
#else
# error C 'long' size should be either 4 or 8!
#endif
/* 10xxxxxx */
#define IS_CONTINUATION_BYTE(ch) ((ch) >= 0x80 && (ch) < 0xC0)
Py_LOCAL_INLINE(Py_UCS4)
STRINGLIB(utf8_decode)(const char **inptr, const char *end,
STRINGLIB_CHAR *dest,
Py_ssize_t *outpos)
{
Py_UCS4 ch;
const char *s = *inptr;
const char *aligned_end = (const char *) _Py_ALIGN_DOWN(end, SIZEOF_LONG);
STRINGLIB_CHAR *p = dest + *outpos;
while (s < end) {
ch = (unsigned char)*s;
if (ch < 0x80) {
/* Fast path for runs of ASCII characters. Given that common UTF-8
input will consist of an overwhelming majority of ASCII
characters, we try to optimize for this case by checking
as many characters as a C 'long' can contain.
First, check if we can do an aligned read, as most CPUs have
a penalty for unaligned reads.
*/
if (_Py_IS_ALIGNED(s, SIZEOF_LONG)) {
/* Help register allocation */
const char *_s = s;
STRINGLIB_CHAR *_p = p;
while (_s < aligned_end) {
/* Read a whole long at a time (either 4 or 8 bytes),
and do a fast unrolled copy if it only contains ASCII
characters. */
unsigned long value = *(unsigned long *) _s;
if (value & ASCII_CHAR_MASK)
break;
#if PY_LITTLE_ENDIAN
_p[0] = (STRINGLIB_CHAR)(value & 0xFFu);
_p[1] = (STRINGLIB_CHAR)((value >> 8) & 0xFFu);
_p[2] = (STRINGLIB_CHAR)((value >> 16) & 0xFFu);
_p[3] = (STRINGLIB_CHAR)((value >> 24) & 0xFFu);
# if SIZEOF_LONG == 8
_p[4] = (STRINGLIB_CHAR)((value >> 32) & 0xFFu);
_p[5] = (STRINGLIB_CHAR)((value >> 40) & 0xFFu);
_p[6] = (STRINGLIB_CHAR)((value >> 48) & 0xFFu);
_p[7] = (STRINGLIB_CHAR)((value >> 56) & 0xFFu);
# endif
#else
# if SIZEOF_LONG == 8
_p[0] = (STRINGLIB_CHAR)((value >> 56) & 0xFFu);
_p[1] = (STRINGLIB_CHAR)((value >> 48) & 0xFFu);
_p[2] = (STRINGLIB_CHAR)((value >> 40) & 0xFFu);
_p[3] = (STRINGLIB_CHAR)((value >> 32) & 0xFFu);
_p[4] = (STRINGLIB_CHAR)((value >> 24) & 0xFFu);
_p[5] = (STRINGLIB_CHAR)((value >> 16) & 0xFFu);
_p[6] = (STRINGLIB_CHAR)((value >> 8) & 0xFFu);
_p[7] = (STRINGLIB_CHAR)(value & 0xFFu);
# else
_p[0] = (STRINGLIB_CHAR)((value >> 24) & 0xFFu);
_p[1] = (STRINGLIB_CHAR)((value >> 16) & 0xFFu);
_p[2] = (STRINGLIB_CHAR)((value >> 8) & 0xFFu);
_p[3] = (STRINGLIB_CHAR)(value & 0xFFu);
# endif
#endif
_s += SIZEOF_LONG;
_p += SIZEOF_LONG;
}
s = _s;
p = _p;
if (s == end)
break;
ch = (unsigned char)*s;
}
if (ch < 0x80) {
s++;
*p++ = ch;
continue;
}
}
if (ch < 0xE0) {
/* \xC2\x80-\xDF\xBF -- 0080-07FF */
Py_UCS4 ch2;
if (ch < 0xC2) {
/* invalid sequence
\x80-\xBF -- continuation byte
\xC0-\xC1 -- fake 0000-007F */
goto InvalidStart;
}
if (end - s < 2) {
/* unexpected end of data: the caller will decide whether
it's an error or not */
break;
}
ch2 = (unsigned char)s[1];
if (!IS_CONTINUATION_BYTE(ch2))
/* invalid continuation byte */
goto InvalidContinuation1;
ch = (ch << 6) + ch2 -
((0xC0 << 6) + 0x80);
assert ((ch > 0x007F) && (ch <= 0x07FF));
s += 2;
if (STRINGLIB_MAX_CHAR <= 0x007F ||
(STRINGLIB_MAX_CHAR < 0x07FF && ch > STRINGLIB_MAX_CHAR))
/* Out-of-range */
goto Return;
*p++ = ch;
continue;
}
if (ch < 0xF0) {
/* \xE0\xA0\x80-\xEF\xBF\xBF -- 0800-FFFF */
Py_UCS4 ch2, ch3;
if (end - s < 3) {
/* unexpected end of data: the caller will decide whether
it's an error or not */
if (end - s < 2)
break;
ch2 = (unsigned char)s[1];
if (!IS_CONTINUATION_BYTE(ch2) ||
(ch2 < 0xA0 ? ch == 0xE0 : ch == 0xED))
/* for clarification see comments below */
goto InvalidContinuation1;
break;
}
ch2 = (unsigned char)s[1];
ch3 = (unsigned char)s[2];
if (!IS_CONTINUATION_BYTE(ch2)) {
/* invalid continuation byte */
goto InvalidContinuation1;
}
if (ch == 0xE0) {
if (ch2 < 0xA0)
/* invalid sequence
\xE0\x80\x80-\xE0\x9F\xBF -- fake 0000-0800 */
goto InvalidContinuation1;
} else if (ch == 0xED && ch2 >= 0xA0) {
/* Decoding UTF-8 sequences in range \xED\xA0\x80-\xED\xBF\xBF
will result in surrogates in range D800-DFFF. Surrogates are
not valid UTF-8 so they are rejected.
See http://www.unicode.org/versions/Unicode5.2.0/ch03.pdf
(table 3-7) and http://www.rfc-editor.org/rfc/rfc3629.txt */
goto InvalidContinuation1;
}
if (!IS_CONTINUATION_BYTE(ch3)) {
/* invalid continuation byte */
goto InvalidContinuation2;
}
ch = (ch << 12) + (ch2 << 6) + ch3 -
((0xE0 << 12) + (0x80 << 6) + 0x80);
assert ((ch > 0x07FF) && (ch <= 0xFFFF));
s += 3;
if (STRINGLIB_MAX_CHAR <= 0x07FF ||
(STRINGLIB_MAX_CHAR < 0xFFFF && ch > STRINGLIB_MAX_CHAR))
/* Out-of-range */
goto Return;
*p++ = ch;
continue;
}
if (ch < 0xF5) {
/* \xF0\x90\x80\x80-\xF4\x8F\xBF\xBF -- 10000-10FFFF */
Py_UCS4 ch2, ch3, ch4;
if (end - s < 4) {
/* unexpected end of data: the caller will decide whether
it's an error or not */
if (end - s < 2)
break;
ch2 = (unsigned char)s[1];
if (!IS_CONTINUATION_BYTE(ch2) ||
(ch2 < 0x90 ? ch == 0xF0 : ch == 0xF4))
/* for clarification see comments below */
goto InvalidContinuation1;
if (end - s < 3)
break;
ch3 = (unsigned char)s[2];
if (!IS_CONTINUATION_BYTE(ch3))
goto InvalidContinuation2;
break;
}
ch2 = (unsigned char)s[1];
ch3 = (unsigned char)s[2];
ch4 = (unsigned char)s[3];
if (!IS_CONTINUATION_BYTE(ch2)) {
/* invalid continuation byte */
goto InvalidContinuation1;
}
if (ch == 0xF0) {
if (ch2 < 0x90)
/* invalid sequence
\xF0\x80\x80\x80-\xF0\x8F\xBF\xBF -- fake 0000-FFFF */
goto InvalidContinuation1;
} else if (ch == 0xF4 && ch2 >= 0x90) {
/* invalid sequence
\xF4\x90\x80\80- -- 110000- overflow */
goto InvalidContinuation1;
}
if (!IS_CONTINUATION_BYTE(ch3)) {
/* invalid continuation byte */
goto InvalidContinuation2;
}
if (!IS_CONTINUATION_BYTE(ch4)) {
/* invalid continuation byte */
goto InvalidContinuation3;
}
ch = (ch << 18) + (ch2 << 12) + (ch3 << 6) + ch4 -
((0xF0 << 18) + (0x80 << 12) + (0x80 << 6) + 0x80);
assert ((ch > 0xFFFF) && (ch <= 0x10FFFF));
s += 4;
if (STRINGLIB_MAX_CHAR <= 0xFFFF ||
(STRINGLIB_MAX_CHAR < 0x10FFFF && ch > STRINGLIB_MAX_CHAR))
/* Out-of-range */
goto Return;
*p++ = ch;
continue;
}
goto InvalidStart;
}
ch = 0;
Return:
*inptr = s;
*outpos = p - dest;
return ch;
InvalidStart:
ch = 1;
goto Return;
InvalidContinuation1:
ch = 2;
goto Return;
InvalidContinuation2:
ch = 3;
goto Return;
InvalidContinuation3:
ch = 4;
goto Return;
}
#undef ASCII_CHAR_MASK
/* UTF-8 encoder specialized for a Unicode kind to avoid the slow
PyUnicode_READ() macro. Delete some parts of the code depending on the kind:
UCS-1 strings don't need to handle surrogates for example. */
Py_LOCAL_INLINE(PyObject *)
STRINGLIB(utf8_encoder)(PyObject *unicode,
STRINGLIB_CHAR *data,
Py_ssize_t size,
const char *errors)
{
#define MAX_SHORT_UNICHARS 300 /* largest size we'll do on the stack */
Py_ssize_t i; /* index into s of next input byte */
char *p; /* next free byte in output buffer */
#if STRINGLIB_SIZEOF_CHAR > 1
PyObject *error_handler_obj = NULL;
PyObject *exc = NULL;
PyObject *rep = NULL;
_Py_error_handler error_handler = _Py_ERROR_UNKNOWN;
#endif
#if STRINGLIB_SIZEOF_CHAR == 1
const Py_ssize_t max_char_size = 2;
#elif STRINGLIB_SIZEOF_CHAR == 2
const Py_ssize_t max_char_size = 3;
#else /* STRINGLIB_SIZEOF_CHAR == 4 */
const Py_ssize_t max_char_size = 4;
#endif
_PyBytesWriter writer;
assert(size >= 0);
_PyBytesWriter_Init(&writer);
if (size > PY_SSIZE_T_MAX / max_char_size) {
/* integer overflow */
return PyErr_NoMemory();
}
p = _PyBytesWriter_Alloc(&writer, size * max_char_size);
if (p == NULL)
return NULL;
for (i = 0; i < size;) {
Py_UCS4 ch = data[i++];
if (ch < 0x80) {
/* Encode ASCII */
*p++ = (char) ch;
}
else
#if STRINGLIB_SIZEOF_CHAR > 1
if (ch < 0x0800)
#endif
{
/* Encode Latin-1 */
*p++ = (char)(0xc0 | (ch >> 6));
*p++ = (char)(0x80 | (ch & 0x3f));
}
#if STRINGLIB_SIZEOF_CHAR > 1
else if (Py_UNICODE_IS_SURROGATE(ch)) {
Py_ssize_t startpos, endpos, newpos;
Py_ssize_t k;
if (error_handler == _Py_ERROR_UNKNOWN) {
error_handler = get_error_handler(errors);
}
startpos = i-1;
endpos = startpos+1;
while ((endpos < size) && Py_UNICODE_IS_SURROGATE(data[endpos]))
endpos++;
/* Only overallocate the buffer if it's not the last write */
writer.overallocate = (endpos < size);
switch (error_handler)
{
case _Py_ERROR_REPLACE:
memset(p, '?', endpos - startpos);
p += (endpos - startpos);
/* fall through the ignore handler */
case _Py_ERROR_IGNORE:
i += (endpos - startpos - 1);
break;
case _Py_ERROR_SURROGATEPASS:
for (k=startpos; k<endpos; k++) {
ch = data[k];
*p++ = (char)(0xe0 | (ch >> 12));
*p++ = (char)(0x80 | ((ch >> 6) & 0x3f));
*p++ = (char)(0x80 | (ch & 0x3f));
}
i += (endpos - startpos - 1);
break;
case _Py_ERROR_BACKSLASHREPLACE:
/* subtract preallocated bytes */
writer.min_size -= max_char_size * (endpos - startpos);
p = backslashreplace(&writer, p,
unicode, startpos, endpos);
if (p == NULL)
goto error;
i += (endpos - startpos - 1);
break;
case _Py_ERROR_XMLCHARREFREPLACE:
/* subtract preallocated bytes */
writer.min_size -= max_char_size * (endpos - startpos);
p = xmlcharrefreplace(&writer, p,
unicode, startpos, endpos);
if (p == NULL)
goto error;
i += (endpos - startpos - 1);
break;
case _Py_ERROR_SURROGATEESCAPE:
for (k=startpos; k<endpos; k++) {
ch = data[k];
if (!(0xDC80 <= ch && ch <= 0xDCFF))
break;
*p++ = (char)(ch & 0xff);
}
if (k >= endpos) {
i += (endpos - startpos - 1);
break;
}
startpos = k;
assert(startpos < endpos);
/* fall through the default handler */
default:
rep = unicode_encode_call_errorhandler(
errors, &error_handler_obj, "utf-8", "surrogates not allowed",
unicode, &exc, startpos, endpos, &newpos);
if (!rep)
goto error;
/* subtract preallocated bytes */
writer.min_size -= max_char_size;
if (PyBytes_Check(rep)) {
p = _PyBytesWriter_WriteBytes(&writer, p,
PyBytes_AS_STRING(rep),
PyBytes_GET_SIZE(rep));
}
else {
/* rep is unicode */
if (PyUnicode_READY(rep) < 0)
goto error;
if (!PyUnicode_IS_ASCII(rep)) {
raise_encode_exception(&exc, "utf-8",
unicode,
i-1, i,
"surrogates not allowed");
goto error;
}
assert(PyUnicode_KIND(rep) == PyUnicode_1BYTE_KIND);
p = _PyBytesWriter_WriteBytes(&writer, p,
PyUnicode_DATA(rep),
PyUnicode_GET_LENGTH(rep));
}
if (p == NULL)
goto error;
Py_CLEAR(rep);
i = newpos;
}
/* If overallocation was disabled, ensure that it was the last
write. Otherwise, we missed an optimization */
assert(writer.overallocate || i == size);
}
else
#if STRINGLIB_SIZEOF_CHAR > 2
if (ch < 0x10000)
#endif
{
*p++ = (char)(0xe0 | (ch >> 12));
*p++ = (char)(0x80 | ((ch >> 6) & 0x3f));
*p++ = (char)(0x80 | (ch & 0x3f));
}
#if STRINGLIB_SIZEOF_CHAR > 2
else /* ch >= 0x10000 */
{
assert(ch <= MAX_UNICODE);
/* Encode UCS4 Unicode ordinals */
*p++ = (char)(0xf0 | (ch >> 18));
*p++ = (char)(0x80 | ((ch >> 12) & 0x3f));
*p++ = (char)(0x80 | ((ch >> 6) & 0x3f));
*p++ = (char)(0x80 | (ch & 0x3f));
}
#endif /* STRINGLIB_SIZEOF_CHAR > 2 */
#endif /* STRINGLIB_SIZEOF_CHAR > 1 */
}
#if STRINGLIB_SIZEOF_CHAR > 1
Py_XDECREF(error_handler_obj);
Py_XDECREF(exc);
#endif
return _PyBytesWriter_Finish(&writer, p);
#if STRINGLIB_SIZEOF_CHAR > 1
error:
Py_XDECREF(rep);
Py_XDECREF(error_handler_obj);
Py_XDECREF(exc);
_PyBytesWriter_Dealloc(&writer);
return NULL;
#endif
#undef MAX_SHORT_UNICHARS
}
/* The pattern for constructing UCS2-repeated masks. */
#if SIZEOF_LONG == 8
# define UCS2_REPEAT_MASK 0x0001000100010001ul
#elif SIZEOF_LONG == 4
# define UCS2_REPEAT_MASK 0x00010001ul
#else
# error C 'long' size should be either 4 or 8!
#endif
/* The mask for fast checking. */
#if STRINGLIB_SIZEOF_CHAR == 1
/* The mask for fast checking of whether a C 'long' contains a
non-ASCII or non-Latin1 UTF16-encoded characters. */
# define FAST_CHAR_MASK (UCS2_REPEAT_MASK * (0xFFFFu & ~STRINGLIB_MAX_CHAR))
#else
/* The mask for fast checking of whether a C 'long' may contain
UTF16-encoded surrogate characters. This is an efficient heuristic,
assuming that non-surrogate characters with a code point >= 0x8000 are
rare in most input.
*/
# define FAST_CHAR_MASK (UCS2_REPEAT_MASK * 0x8000u)
#endif
/* The mask for fast byte-swapping. */
#define STRIPPED_MASK (UCS2_REPEAT_MASK * 0x00FFu)
/* Swap bytes. */
#define SWAB(value) ((((value) >> 8) & STRIPPED_MASK) | \
(((value) & STRIPPED_MASK) << 8))
Py_LOCAL_INLINE(Py_UCS4)
STRINGLIB(utf16_decode)(const unsigned char **inptr, const unsigned char *e,
STRINGLIB_CHAR *dest, Py_ssize_t *outpos,
int native_ordering)
{
Py_UCS4 ch;
const unsigned char *aligned_end =
(const unsigned char *) _Py_ALIGN_DOWN(e, SIZEOF_LONG);
const unsigned char *q = *inptr;
STRINGLIB_CHAR *p = dest + *outpos;
/* Offsets from q for retrieving byte pairs in the right order. */
#if PY_LITTLE_ENDIAN
int ihi = !!native_ordering, ilo = !native_ordering;
#else
int ihi = !native_ordering, ilo = !!native_ordering;
#endif
--e;
while (q < e) {
Py_UCS4 ch2;
/* First check for possible aligned read of a C 'long'. Unaligned
reads are more expensive, better to defer to another iteration. */
if (_Py_IS_ALIGNED(q, SIZEOF_LONG)) {
/* Fast path for runs of in-range non-surrogate chars. */
const unsigned char *_q = q;
while (_q < aligned_end) {
unsigned long block = * (unsigned long *) _q;
if (native_ordering) {
/* Can use buffer directly */
if (block & FAST_CHAR_MASK)
break;
}
else {
/* Need to byte-swap */
if (block & SWAB(FAST_CHAR_MASK))
break;
#if STRINGLIB_SIZEOF_CHAR == 1
block >>= 8;
#else
block = SWAB(block);
#endif
}
#if PY_LITTLE_ENDIAN
# if SIZEOF_LONG == 4
p[0] = (STRINGLIB_CHAR)(block & 0xFFFFu);
p[1] = (STRINGLIB_CHAR)(block >> 16);
# elif SIZEOF_LONG == 8
p[0] = (STRINGLIB_CHAR)(block & 0xFFFFu);
p[1] = (STRINGLIB_CHAR)((block >> 16) & 0xFFFFu);
p[2] = (STRINGLIB_CHAR)((block >> 32) & 0xFFFFu);
p[3] = (STRINGLIB_CHAR)(block >> 48);
# endif
#else
# if SIZEOF_LONG == 4
p[0] = (STRINGLIB_CHAR)(block >> 16);
p[1] = (STRINGLIB_CHAR)(block & 0xFFFFu);
# elif SIZEOF_LONG == 8
p[0] = (STRINGLIB_CHAR)(block >> 48);
p[1] = (STRINGLIB_CHAR)((block >> 32) & 0xFFFFu);
p[2] = (STRINGLIB_CHAR)((block >> 16) & 0xFFFFu);
p[3] = (STRINGLIB_CHAR)(block & 0xFFFFu);
# endif
#endif
_q += SIZEOF_LONG;
p += SIZEOF_LONG / 2;
}
q = _q;
if (q >= e)
break;
}
ch = (q[ihi] << 8) | q[ilo];
q += 2;
if (!Py_UNICODE_IS_SURROGATE(ch)) {
#if STRINGLIB_SIZEOF_CHAR < 2
if (ch > STRINGLIB_MAX_CHAR)
/* Out-of-range */
goto Return;
#endif
*p++ = (STRINGLIB_CHAR)ch;
continue;
}
/* UTF-16 code pair: */
if (q >= e)
goto UnexpectedEnd;
if (!Py_UNICODE_IS_HIGH_SURROGATE(ch))
goto IllegalEncoding;
ch2 = (q[ihi] << 8) | q[ilo];
q += 2;
if (!Py_UNICODE_IS_LOW_SURROGATE(ch2))
goto IllegalSurrogate;
ch = Py_UNICODE_JOIN_SURROGATES(ch, ch2);
#if STRINGLIB_SIZEOF_CHAR < 4
/* Out-of-range */
goto Return;
#else
*p++ = (STRINGLIB_CHAR)ch;
#endif
}
ch = 0;
Return:
*inptr = q;
*outpos = p - dest;
return ch;
UnexpectedEnd:
ch = 1;
goto Return;
IllegalEncoding:
ch = 2;
goto Return;
IllegalSurrogate:
ch = 3;
goto Return;
}
#undef UCS2_REPEAT_MASK
#undef FAST_CHAR_MASK
#undef STRIPPED_MASK
#undef SWAB
#if STRINGLIB_MAX_CHAR >= 0x80
Py_LOCAL_INLINE(Py_ssize_t)
STRINGLIB(utf16_encode)(const STRINGLIB_CHAR *in,
Py_ssize_t len,
unsigned short **outptr,
int native_ordering)
{
unsigned short *out = *outptr;
const STRINGLIB_CHAR *end = in + len;
#if STRINGLIB_SIZEOF_CHAR == 1
if (native_ordering) {
const STRINGLIB_CHAR *unrolled_end = in + _Py_SIZE_ROUND_DOWN(len, 4);
while (in < unrolled_end) {
out[0] = in[0];
out[1] = in[1];
out[2] = in[2];
out[3] = in[3];
in += 4; out += 4;
}
while (in < end) {
*out++ = *in++;
}
} else {
# define SWAB2(CH) ((CH) << 8) /* high byte is zero */
const STRINGLIB_CHAR *unrolled_end = in + _Py_SIZE_ROUND_DOWN(len, 4);
while (in < unrolled_end) {
out[0] = SWAB2(in[0]);
out[1] = SWAB2(in[1]);
out[2] = SWAB2(in[2]);
out[3] = SWAB2(in[3]);
in += 4; out += 4;
}
while (in < end) {
Py_UCS4 ch = *in++;
*out++ = SWAB2((Py_UCS2)ch);
}
#undef SWAB2
}
*outptr = out;
return len;
#else
if (native_ordering) {
#if STRINGLIB_MAX_CHAR < 0x10000
const STRINGLIB_CHAR *unrolled_end = in + _Py_SIZE_ROUND_DOWN(len, 4);
while (in < unrolled_end) {
/* check if any character is a surrogate character */
if (((in[0] ^ 0xd800) &
(in[1] ^ 0xd800) &
(in[2] ^ 0xd800) &
(in[3] ^ 0xd800) & 0xf800) == 0)
break;
out[0] = in[0];
out[1] = in[1];
out[2] = in[2];
out[3] = in[3];
in += 4; out += 4;
}
#endif
while (in < end) {
Py_UCS4 ch;
ch = *in++;
if (ch < 0xd800)
*out++ = ch;
else if (ch < 0xe000)
/* reject surrogate characters (U+D800-U+DFFF) */
goto fail;
#if STRINGLIB_MAX_CHAR >= 0x10000
else if (ch >= 0x10000) {
out[0] = Py_UNICODE_HIGH_SURROGATE(ch);
out[1] = Py_UNICODE_LOW_SURROGATE(ch);
out += 2;
}
#endif
else
*out++ = ch;
}
} else {
#define SWAB2(CH) (((CH) << 8) | ((CH) >> 8))
#if STRINGLIB_MAX_CHAR < 0x10000
const STRINGLIB_CHAR *unrolled_end = in + _Py_SIZE_ROUND_DOWN(len, 4);
while (in < unrolled_end) {
/* check if any character is a surrogate character */
if (((in[0] ^ 0xd800) &
(in[1] ^ 0xd800) &
(in[2] ^ 0xd800) &
(in[3] ^ 0xd800) & 0xf800) == 0)
break;
out[0] = SWAB2(in[0]);
out[1] = SWAB2(in[1]);
out[2] = SWAB2(in[2]);
out[3] = SWAB2(in[3]);
in += 4; out += 4;
}
#endif
while (in < end) {
Py_UCS4 ch = *in++;
if (ch < 0xd800)
*out++ = SWAB2((Py_UCS2)ch);
else if (ch < 0xe000)
/* reject surrogate characters (U+D800-U+DFFF) */
goto fail;
#if STRINGLIB_MAX_CHAR >= 0x10000
else if (ch >= 0x10000) {
Py_UCS2 ch1 = Py_UNICODE_HIGH_SURROGATE(ch);
Py_UCS2 ch2 = Py_UNICODE_LOW_SURROGATE(ch);
out[0] = SWAB2(ch1);
out[1] = SWAB2(ch2);
out += 2;
}
#endif
else
*out++ = SWAB2((Py_UCS2)ch);
}
#undef SWAB2
}
*outptr = out;
return len;
fail:
*outptr = out;
return len - (end - in + 1);
#endif
}
#if STRINGLIB_SIZEOF_CHAR == 1
# define SWAB4(CH, tmp) ((CH) << 24) /* high bytes are zero */
#elif STRINGLIB_SIZEOF_CHAR == 2
# define SWAB4(CH, tmp) (tmp = (CH), \
((tmp & 0x00FFu) << 24) + ((tmp & 0xFF00u) << 8))
/* high bytes are zero */
#else
# define SWAB4(CH, tmp) (tmp = (CH), \
tmp = ((tmp & 0x00FF00FFu) << 8) + ((tmp >> 8) & 0x00FF00FFu), \
((tmp & 0x0000FFFFu) << 16) + ((tmp >> 16) & 0x0000FFFFu))
#endif
Py_LOCAL_INLINE(Py_ssize_t)
STRINGLIB(utf32_encode)(const STRINGLIB_CHAR *in,
Py_ssize_t len,
PY_UINT32_T **outptr,
int native_ordering)
{
PY_UINT32_T *out = *outptr;
const STRINGLIB_CHAR *end = in + len;
if (native_ordering) {
const STRINGLIB_CHAR *unrolled_end = in + _Py_SIZE_ROUND_DOWN(len, 4);
while (in < unrolled_end) {
#if STRINGLIB_SIZEOF_CHAR > 1
/* check if any character is a surrogate character */
if (((in[0] ^ 0xd800) &
(in[1] ^ 0xd800) &
(in[2] ^ 0xd800) &
(in[3] ^ 0xd800) & 0xf800) == 0)
break;
#endif
out[0] = in[0];
out[1] = in[1];
out[2] = in[2];
out[3] = in[3];
in += 4; out += 4;
}
while (in < end) {
Py_UCS4 ch;
ch = *in++;
#if STRINGLIB_SIZEOF_CHAR > 1
if (Py_UNICODE_IS_SURROGATE(ch)) {
/* reject surrogate characters (U+D800-U+DFFF) */
goto fail;
}
#endif
*out++ = ch;
}
} else {
const STRINGLIB_CHAR *unrolled_end = in + _Py_SIZE_ROUND_DOWN(len, 4);
while (in < unrolled_end) {
#if STRINGLIB_SIZEOF_CHAR > 1
Py_UCS4 ch1, ch2, ch3, ch4;
/* check if any character is a surrogate character */
if (((in[0] ^ 0xd800) &
(in[1] ^ 0xd800) &
(in[2] ^ 0xd800) &
(in[3] ^ 0xd800) & 0xf800) == 0)
break;
#endif
out[0] = SWAB4(in[0], ch1);
out[1] = SWAB4(in[1], ch2);
out[2] = SWAB4(in[2], ch3);
out[3] = SWAB4(in[3], ch4);
in += 4; out += 4;
}
while (in < end) {
Py_UCS4 ch = *in++;
#if STRINGLIB_SIZEOF_CHAR > 1
if (Py_UNICODE_IS_SURROGATE(ch)) {
/* reject surrogate characters (U+D800-U+DFFF) */
goto fail;
}
#endif
*out++ = SWAB4(ch, ch);
}
}
*outptr = out;
return len;
#if STRINGLIB_SIZEOF_CHAR > 1
fail:
*outptr = out;
return len - (end - in + 1);
#endif
}
#undef SWAB4
#endif