This repository was archived by the owner on Feb 13, 2025. It is now read-only.
forked from python/cpython
-
Notifications
You must be signed in to change notification settings - Fork 64
Expand file tree
/
Copy pathfileutils.c
More file actions
2921 lines (2565 loc) · 80.6 KB
/
fileutils.c
File metadata and controls
2921 lines (2565 loc) · 80.6 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 "Python.h"
#include "pycore_fileutils.h" // fileutils definitions
#include "pycore_runtime.h" // _PyRuntime
#include "osdefs.h" // SEP
#include <locale.h>
#include <stdlib.h> // mbstowcs()
#ifdef MS_WINDOWS
# include <malloc.h>
# include <windows.h>
# include <winioctl.h> // FILE_DEVICE_* constants
# include "pycore_fileutils_windows.h" // FILE_STAT_BASIC_INFORMATION
# if defined(MS_WINDOWS_GAMES) && !defined(MS_WINDOWS_DESKTOP)
# define PATHCCH_ALLOW_LONG_PATHS 0x01
# else
# include <pathcch.h> // PathCchCombineEx
# endif
extern int winerror_to_errno(int);
#endif
#ifdef HAVE_LANGINFO_H
#include <langinfo.h>
#endif
#ifdef HAVE_SYS_IOCTL_H
#include <sys/ioctl.h>
#endif
#ifdef HAVE_NON_UNICODE_WCHAR_T_REPRESENTATION
#include <iconv.h>
#endif
#ifdef HAVE_FCNTL_H
#include <fcntl.h>
#endif /* HAVE_FCNTL_H */
#ifdef O_CLOEXEC
/* Does open() support the O_CLOEXEC flag? Possible values:
-1: unknown
0: open() ignores O_CLOEXEC flag, ex: Linux kernel older than 2.6.23
1: open() supports O_CLOEXEC flag, close-on-exec is set
The flag is used by _Py_open(), _Py_open_noraise(), io.FileIO
and os.open(). */
int _Py_open_cloexec_works = -1;
#endif
// The value must be the same in unicodeobject.c.
#define MAX_UNICODE 0x10ffff
// mbstowcs() and mbrtowc() errors
static const size_t DECODE_ERROR = ((size_t)-1);
static const size_t INCOMPLETE_CHARACTER = (size_t)-2;
static int
get_surrogateescape(_Py_error_handler errors, int *surrogateescape)
{
switch (errors)
{
case _Py_ERROR_STRICT:
*surrogateescape = 0;
return 0;
case _Py_ERROR_SURROGATEESCAPE:
*surrogateescape = 1;
return 0;
default:
return -1;
}
}
PyObject *
_Py_device_encoding(int fd)
{
int valid;
Py_BEGIN_ALLOW_THREADS
_Py_BEGIN_SUPPRESS_IPH
valid = isatty(fd);
_Py_END_SUPPRESS_IPH
Py_END_ALLOW_THREADS
if (!valid)
Py_RETURN_NONE;
#ifdef MS_WINDOWS
#ifdef HAVE_WINDOWS_CONSOLE_IO
UINT cp;
if (fd == 0)
cp = GetConsoleCP();
else if (fd == 1 || fd == 2)
cp = GetConsoleOutputCP();
else
cp = 0;
/* GetConsoleCP() and GetConsoleOutputCP() return 0 if the application
has no console */
if (cp == 0) {
Py_RETURN_NONE;
}
return PyUnicode_FromFormat("cp%u", (unsigned int)cp);
#else
Py_RETURN_NONE;
#endif /* HAVE_WINDOWS_CONSOLE_IO */
#else
if (_PyRuntime.preconfig.utf8_mode) {
_Py_DECLARE_STR(utf_8, "utf-8");
return Py_NewRef(&_Py_STR(utf_8));
}
return _Py_GetLocaleEncodingObject();
#endif
}
static size_t
is_valid_wide_char(wchar_t ch)
{
#ifdef HAVE_NON_UNICODE_WCHAR_T_REPRESENTATION
/* Oracle Solaris doesn't use Unicode code points as wchar_t encoding
for non-Unicode locales, which makes values higher than MAX_UNICODE
possibly valid. */
return 1;
#endif
if (Py_UNICODE_IS_SURROGATE(ch)) {
// Reject lone surrogate characters
return 0;
}
if (ch > MAX_UNICODE) {
// bpo-35883: Reject characters outside [U+0000; U+10ffff] range.
// The glibc mbstowcs() UTF-8 decoder does not respect the RFC 3629,
// it creates characters outside the [U+0000; U+10ffff] range:
// https://sourceware.org/bugzilla/show_bug.cgi?id=2373
return 0;
}
return 1;
}
static size_t
_Py_mbstowcs(wchar_t *dest, const char *src, size_t n)
{
size_t count = mbstowcs(dest, src, n);
if (dest != NULL && count != DECODE_ERROR) {
for (size_t i=0; i < count; i++) {
wchar_t ch = dest[i];
if (!is_valid_wide_char(ch)) {
return DECODE_ERROR;
}
}
}
return count;
}
#ifdef HAVE_MBRTOWC
static size_t
_Py_mbrtowc(wchar_t *pwc, const char *str, size_t len, mbstate_t *pmbs)
{
assert(pwc != NULL);
size_t count = mbrtowc(pwc, str, len, pmbs);
if (count != 0 && count != DECODE_ERROR && count != INCOMPLETE_CHARACTER) {
if (!is_valid_wide_char(*pwc)) {
return DECODE_ERROR;
}
}
return count;
}
#endif
#if !defined(_Py_FORCE_UTF8_FS_ENCODING) && !defined(MS_WINDOWS)
#define USE_FORCE_ASCII
extern int _Py_normalize_encoding(const char *, char *, size_t);
/* Workaround FreeBSD and OpenIndiana locale encoding issue with the C locale
and POSIX locale. nl_langinfo(CODESET) announces an alias of the
ASCII encoding, whereas mbstowcs() and wcstombs() functions use the
ISO-8859-1 encoding. The problem is that os.fsencode() and os.fsdecode() use
locale.getpreferredencoding() codec. For example, if command line arguments
are decoded by mbstowcs() and encoded back by os.fsencode(), we get a
UnicodeEncodeError instead of retrieving the original byte string.
The workaround is enabled if setlocale(LC_CTYPE, NULL) returns "C",
nl_langinfo(CODESET) announces "ascii" (or an alias to ASCII), and at least
one byte in range 0x80-0xff can be decoded from the locale encoding. The
workaround is also enabled on error, for example if getting the locale
failed.
On HP-UX with the C locale or the POSIX locale, nl_langinfo(CODESET)
announces "roman8" but mbstowcs() uses Latin1 in practice. Force also the
ASCII encoding in this case.
Values of force_ascii:
1: the workaround is used: Py_EncodeLocale() uses
encode_ascii_surrogateescape() and Py_DecodeLocale() uses
decode_ascii()
0: the workaround is not used: Py_EncodeLocale() uses wcstombs() and
Py_DecodeLocale() uses mbstowcs()
-1: unknown, need to call check_force_ascii() to get the value
*/
#define force_ascii (_PyRuntime.fileutils.force_ascii)
static int
check_force_ascii(void)
{
char *loc = setlocale(LC_CTYPE, NULL);
if (loc == NULL) {
goto error;
}
if (strcmp(loc, "C") != 0 && strcmp(loc, "POSIX") != 0) {
/* the LC_CTYPE locale is different than C and POSIX */
return 0;
}
#if defined(HAVE_LANGINFO_H) && defined(CODESET)
const char *codeset = nl_langinfo(CODESET);
if (!codeset || codeset[0] == '\0') {
/* CODESET is not set or empty */
goto error;
}
char encoding[20]; /* longest name: "iso_646.irv_1991\0" */
if (!_Py_normalize_encoding(codeset, encoding, sizeof(encoding))) {
goto error;
}
#ifdef __hpux
if (strcmp(encoding, "roman8") == 0) {
unsigned char ch;
wchar_t wch;
size_t res;
ch = (unsigned char)0xA7;
res = _Py_mbstowcs(&wch, (char*)&ch, 1);
if (res != DECODE_ERROR && wch == L'\xA7') {
/* On HP-UX with C locale or the POSIX locale,
nl_langinfo(CODESET) announces "roman8", whereas mbstowcs() uses
Latin1 encoding in practice. Force ASCII in this case.
Roman8 decodes 0xA7 to U+00CF. Latin1 decodes 0xA7 to U+00A7. */
return 1;
}
}
#else
const char* ascii_aliases[] = {
"ascii",
/* Aliases from Lib/encodings/aliases.py */
"646",
"ansi_x3.4_1968",
"ansi_x3.4_1986",
"ansi_x3_4_1968",
"cp367",
"csascii",
"ibm367",
"iso646_us",
"iso_646.irv_1991",
"iso_ir_6",
"us",
"us_ascii",
NULL
};
int is_ascii = 0;
for (const char **alias=ascii_aliases; *alias != NULL; alias++) {
if (strcmp(encoding, *alias) == 0) {
is_ascii = 1;
break;
}
}
if (!is_ascii) {
/* nl_langinfo(CODESET) is not "ascii" or an alias of ASCII */
return 0;
}
for (unsigned int i=0x80; i<=0xff; i++) {
char ch[1];
wchar_t wch[1];
size_t res;
unsigned uch = (unsigned char)i;
ch[0] = (char)uch;
res = _Py_mbstowcs(wch, ch, 1);
if (res != DECODE_ERROR) {
/* decoding a non-ASCII character from the locale encoding succeed:
the locale encoding is not ASCII, force ASCII */
return 1;
}
}
/* None of the bytes in the range 0x80-0xff can be decoded from the locale
encoding: the locale encoding is really ASCII */
#endif /* !defined(__hpux) */
return 0;
#else
/* nl_langinfo(CODESET) is not available: always force ASCII */
return 1;
#endif /* defined(HAVE_LANGINFO_H) && defined(CODESET) */
error:
/* if an error occurred, force the ASCII encoding */
return 1;
}
int
_Py_GetForceASCII(void)
{
if (force_ascii == -1) {
force_ascii = check_force_ascii();
}
return force_ascii;
}
void
_Py_ResetForceASCII(void)
{
force_ascii = -1;
}
static int
encode_ascii(const wchar_t *text, char **str,
size_t *error_pos, const char **reason,
int raw_malloc, _Py_error_handler errors)
{
char *result = NULL, *out;
size_t len, i;
wchar_t ch;
int surrogateescape;
if (get_surrogateescape(errors, &surrogateescape) < 0) {
return -3;
}
len = wcslen(text);
/* +1 for NULL byte */
if (raw_malloc) {
result = PyMem_RawMalloc(len + 1);
}
else {
result = PyMem_Malloc(len + 1);
}
if (result == NULL) {
return -1;
}
out = result;
for (i=0; i<len; i++) {
ch = text[i];
if (ch <= 0x7f) {
/* ASCII character */
*out++ = (char)ch;
}
else if (surrogateescape && 0xdc80 <= ch && ch <= 0xdcff) {
/* UTF-8b surrogate */
*out++ = (char)(ch - 0xdc00);
}
else {
if (raw_malloc) {
PyMem_RawFree(result);
}
else {
PyMem_Free(result);
}
if (error_pos != NULL) {
*error_pos = i;
}
if (reason) {
*reason = "encoding error";
}
return -2;
}
}
*out = '\0';
*str = result;
return 0;
}
#else
int
_Py_GetForceASCII(void)
{
return 0;
}
void
_Py_ResetForceASCII(void)
{
/* nothing to do */
}
#endif /* !defined(_Py_FORCE_UTF8_FS_ENCODING) && !defined(MS_WINDOWS) */
#if !defined(HAVE_MBRTOWC) || defined(USE_FORCE_ASCII)
static int
decode_ascii(const char *arg, wchar_t **wstr, size_t *wlen,
const char **reason, _Py_error_handler errors)
{
wchar_t *res;
unsigned char *in;
wchar_t *out;
size_t argsize = strlen(arg) + 1;
int surrogateescape;
if (get_surrogateescape(errors, &surrogateescape) < 0) {
return -3;
}
if (argsize > PY_SSIZE_T_MAX / sizeof(wchar_t)) {
return -1;
}
res = PyMem_RawMalloc(argsize * sizeof(wchar_t));
if (!res) {
return -1;
}
out = res;
for (in = (unsigned char*)arg; *in; in++) {
unsigned char ch = *in;
if (ch < 128) {
*out++ = ch;
}
else {
if (!surrogateescape) {
PyMem_RawFree(res);
if (wlen) {
*wlen = in - (unsigned char*)arg;
}
if (reason) {
*reason = "decoding error";
}
return -2;
}
*out++ = 0xdc00 + ch;
}
}
*out = 0;
if (wlen != NULL) {
*wlen = out - res;
}
*wstr = res;
return 0;
}
#endif /* !HAVE_MBRTOWC */
static int
decode_current_locale(const char* arg, wchar_t **wstr, size_t *wlen,
const char **reason, _Py_error_handler errors)
{
wchar_t *res;
size_t argsize;
size_t count;
#ifdef HAVE_MBRTOWC
unsigned char *in;
wchar_t *out;
mbstate_t mbs;
#endif
int surrogateescape;
if (get_surrogateescape(errors, &surrogateescape) < 0) {
return -3;
}
#ifdef HAVE_BROKEN_MBSTOWCS
/* Some platforms have a broken implementation of
* mbstowcs which does not count the characters that
* would result from conversion. Use an upper bound.
*/
argsize = strlen(arg);
#else
argsize = _Py_mbstowcs(NULL, arg, 0);
#endif
if (argsize != DECODE_ERROR) {
if (argsize > PY_SSIZE_T_MAX / sizeof(wchar_t) - 1) {
return -1;
}
res = (wchar_t *)PyMem_RawMalloc((argsize + 1) * sizeof(wchar_t));
if (!res) {
return -1;
}
count = _Py_mbstowcs(res, arg, argsize + 1);
if (count != DECODE_ERROR) {
*wstr = res;
if (wlen != NULL) {
*wlen = count;
}
return 0;
}
PyMem_RawFree(res);
}
/* Conversion failed. Fall back to escaping with surrogateescape. */
#ifdef HAVE_MBRTOWC
/* Try conversion with mbrtwoc (C99), and escape non-decodable bytes. */
/* Overallocate; as multi-byte characters are in the argument, the
actual output could use less memory. */
argsize = strlen(arg) + 1;
if (argsize > PY_SSIZE_T_MAX / sizeof(wchar_t)) {
return -1;
}
res = (wchar_t*)PyMem_RawMalloc(argsize * sizeof(wchar_t));
if (!res) {
return -1;
}
in = (unsigned char*)arg;
out = res;
memset(&mbs, 0, sizeof mbs);
while (argsize) {
size_t converted = _Py_mbrtowc(out, (char*)in, argsize, &mbs);
if (converted == 0) {
/* Reached end of string; null char stored. */
break;
}
if (converted == INCOMPLETE_CHARACTER) {
/* Incomplete character. This should never happen,
since we provide everything that we have -
unless there is a bug in the C library, or I
misunderstood how mbrtowc works. */
goto decode_error;
}
if (converted == DECODE_ERROR) {
if (!surrogateescape) {
goto decode_error;
}
/* Decoding error. Escape as UTF-8b, and start over in the initial
shift state. */
*out++ = 0xdc00 + *in++;
argsize--;
memset(&mbs, 0, sizeof mbs);
continue;
}
// _Py_mbrtowc() reject lone surrogate characters
assert(!Py_UNICODE_IS_SURROGATE(*out));
/* successfully converted some bytes */
in += converted;
argsize -= converted;
out++;
}
if (wlen != NULL) {
*wlen = out - res;
}
*wstr = res;
return 0;
decode_error:
PyMem_RawFree(res);
if (wlen) {
*wlen = in - (unsigned char*)arg;
}
if (reason) {
*reason = "decoding error";
}
return -2;
#else /* HAVE_MBRTOWC */
/* Cannot use C locale for escaping; manually escape as if charset
is ASCII (i.e. escape all bytes > 128. This will still roundtrip
correctly in the locale's charset, which must be an ASCII superset. */
return decode_ascii(arg, wstr, wlen, reason, errors);
#endif /* HAVE_MBRTOWC */
}
/* Decode a byte string from the locale encoding.
Use the strict error handler if 'surrogateescape' is zero. Use the
surrogateescape error handler if 'surrogateescape' is non-zero: undecodable
bytes are decoded as characters in range U+DC80..U+DCFF. If a byte sequence
can be decoded as a surrogate character, escape the bytes using the
surrogateescape error handler instead of decoding them.
On success, return 0 and write the newly allocated wide character string into
*wstr (use PyMem_RawFree() to free the memory). If wlen is not NULL, write
the number of wide characters excluding the null character into *wlen.
On memory allocation failure, return -1.
On decoding error, return -2. If wlen is not NULL, write the start of
invalid byte sequence in the input string into *wlen. If reason is not NULL,
write the decoding error message into *reason.
Return -3 if the error handler 'errors' is not supported.
Use the Py_EncodeLocaleEx() function to encode the character string back to
a byte string. */
int
_Py_DecodeLocaleEx(const char* arg, wchar_t **wstr, size_t *wlen,
const char **reason,
int current_locale, _Py_error_handler errors)
{
if (current_locale) {
#ifdef _Py_FORCE_UTF8_LOCALE
return _Py_DecodeUTF8Ex(arg, strlen(arg), wstr, wlen, reason,
errors);
#else
return decode_current_locale(arg, wstr, wlen, reason, errors);
#endif
}
#ifdef _Py_FORCE_UTF8_FS_ENCODING
return _Py_DecodeUTF8Ex(arg, strlen(arg), wstr, wlen, reason,
errors);
#else
int use_utf8 = (_PyRuntime.preconfig.utf8_mode >= 1);
#ifdef MS_WINDOWS
use_utf8 |= (_PyRuntime.preconfig.legacy_windows_fs_encoding == 0);
#endif
if (use_utf8) {
return _Py_DecodeUTF8Ex(arg, strlen(arg), wstr, wlen, reason,
errors);
}
#ifdef USE_FORCE_ASCII
if (force_ascii == -1) {
force_ascii = check_force_ascii();
}
if (force_ascii) {
/* force ASCII encoding to workaround mbstowcs() issue */
return decode_ascii(arg, wstr, wlen, reason, errors);
}
#endif
return decode_current_locale(arg, wstr, wlen, reason, errors);
#endif /* !_Py_FORCE_UTF8_FS_ENCODING */
}
/* Decode a byte string from the locale encoding with the
surrogateescape error handler: undecodable bytes are decoded as characters
in range U+DC80..U+DCFF. If a byte sequence can be decoded as a surrogate
character, escape the bytes using the surrogateescape error handler instead
of decoding them.
Return a pointer to a newly allocated wide character string, use
PyMem_RawFree() to free the memory. If size is not NULL, write the number of
wide characters excluding the null character into *size
Return NULL on decoding error or memory allocation error. If *size* is not
NULL, *size is set to (size_t)-1 on memory error or set to (size_t)-2 on
decoding error.
Decoding errors should never happen, unless there is a bug in the C
library.
Use the Py_EncodeLocale() function to encode the character string back to a
byte string. */
wchar_t*
Py_DecodeLocale(const char* arg, size_t *wlen)
{
wchar_t *wstr;
int res = _Py_DecodeLocaleEx(arg, &wstr, wlen,
NULL, 0,
_Py_ERROR_SURROGATEESCAPE);
if (res != 0) {
assert(res != -3);
if (wlen != NULL) {
*wlen = (size_t)res;
}
return NULL;
}
return wstr;
}
static int
encode_current_locale(const wchar_t *text, char **str,
size_t *error_pos, const char **reason,
int raw_malloc, _Py_error_handler errors)
{
const size_t len = wcslen(text);
char *result = NULL, *bytes = NULL;
size_t i, size, converted;
wchar_t c, buf[2];
int surrogateescape;
if (get_surrogateescape(errors, &surrogateescape) < 0) {
return -3;
}
/* The function works in two steps:
1. compute the length of the output buffer in bytes (size)
2. outputs the bytes */
size = 0;
buf[1] = 0;
while (1) {
for (i=0; i < len; i++) {
c = text[i];
if (c >= 0xdc80 && c <= 0xdcff) {
if (!surrogateescape) {
goto encode_error;
}
/* UTF-8b surrogate */
if (bytes != NULL) {
*bytes++ = c - 0xdc00;
size--;
}
else {
size++;
}
continue;
}
else {
buf[0] = c;
if (bytes != NULL) {
converted = wcstombs(bytes, buf, size);
}
else {
converted = wcstombs(NULL, buf, 0);
}
if (converted == DECODE_ERROR) {
goto encode_error;
}
if (bytes != NULL) {
bytes += converted;
size -= converted;
}
else {
size += converted;
}
}
}
if (result != NULL) {
*bytes = '\0';
break;
}
size += 1; /* nul byte at the end */
if (raw_malloc) {
result = PyMem_RawMalloc(size);
}
else {
result = PyMem_Malloc(size);
}
if (result == NULL) {
return -1;
}
bytes = result;
}
*str = result;
return 0;
encode_error:
if (raw_malloc) {
PyMem_RawFree(result);
}
else {
PyMem_Free(result);
}
if (error_pos != NULL) {
*error_pos = i;
}
if (reason) {
*reason = "encoding error";
}
return -2;
}
/* Encode a string to the locale encoding.
Parameters:
* raw_malloc: if non-zero, allocate memory using PyMem_RawMalloc() instead
of PyMem_Malloc().
* current_locale: if non-zero, use the current LC_CTYPE, otherwise use
Python filesystem encoding.
* errors: error handler like "strict" or "surrogateescape".
Return value:
0: success, *str is set to a newly allocated decoded string.
-1: memory allocation failure
-2: encoding error, set *error_pos and *reason (if set).
-3: the error handler 'errors' is not supported.
*/
static int
encode_locale_ex(const wchar_t *text, char **str, size_t *error_pos,
const char **reason,
int raw_malloc, int current_locale, _Py_error_handler errors)
{
if (current_locale) {
#ifdef _Py_FORCE_UTF8_LOCALE
return _Py_EncodeUTF8Ex(text, str, error_pos, reason,
raw_malloc, errors);
#else
return encode_current_locale(text, str, error_pos, reason,
raw_malloc, errors);
#endif
}
#ifdef _Py_FORCE_UTF8_FS_ENCODING
return _Py_EncodeUTF8Ex(text, str, error_pos, reason,
raw_malloc, errors);
#else
int use_utf8 = (_PyRuntime.preconfig.utf8_mode >= 1);
#ifdef MS_WINDOWS
use_utf8 |= (_PyRuntime.preconfig.legacy_windows_fs_encoding == 0);
#endif
if (use_utf8) {
return _Py_EncodeUTF8Ex(text, str, error_pos, reason,
raw_malloc, errors);
}
#ifdef USE_FORCE_ASCII
if (force_ascii == -1) {
force_ascii = check_force_ascii();
}
if (force_ascii) {
return encode_ascii(text, str, error_pos, reason,
raw_malloc, errors);
}
#endif
return encode_current_locale(text, str, error_pos, reason,
raw_malloc, errors);
#endif /* _Py_FORCE_UTF8_FS_ENCODING */
}
static char*
encode_locale(const wchar_t *text, size_t *error_pos,
int raw_malloc, int current_locale)
{
char *str;
int res = encode_locale_ex(text, &str, error_pos, NULL,
raw_malloc, current_locale,
_Py_ERROR_SURROGATEESCAPE);
if (res != -2 && error_pos) {
*error_pos = (size_t)-1;
}
if (res != 0) {
return NULL;
}
return str;
}
/* Encode a wide character string to the locale encoding with the
surrogateescape error handler: surrogate characters in the range
U+DC80..U+DCFF are converted to bytes 0x80..0xFF.
Return a pointer to a newly allocated byte string, use PyMem_Free() to free
the memory. Return NULL on encoding or memory allocation error.
If error_pos is not NULL, *error_pos is set to (size_t)-1 on success, or set
to the index of the invalid character on encoding error.
Use the Py_DecodeLocale() function to decode the bytes string back to a wide
character string. */
char*
Py_EncodeLocale(const wchar_t *text, size_t *error_pos)
{
return encode_locale(text, error_pos, 0, 0);
}
/* Similar to Py_EncodeLocale(), but result must be freed by PyMem_RawFree()
instead of PyMem_Free(). */
char*
_Py_EncodeLocaleRaw(const wchar_t *text, size_t *error_pos)
{
return encode_locale(text, error_pos, 1, 0);
}
int
_Py_EncodeLocaleEx(const wchar_t *text, char **str,
size_t *error_pos, const char **reason,
int current_locale, _Py_error_handler errors)
{
return encode_locale_ex(text, str, error_pos, reason, 1,
current_locale, errors);
}
// Get the current locale encoding name:
//
// - Return "utf-8" if _Py_FORCE_UTF8_LOCALE macro is defined (ex: on Android)
// - Return "utf-8" if the UTF-8 Mode is enabled
// - On Windows, return the ANSI code page (ex: "cp1250")
// - Return "utf-8" if nl_langinfo(CODESET) returns an empty string.
// - Otherwise, return nl_langinfo(CODESET).
//
// Return NULL on memory allocation failure.
//
// See also config_get_locale_encoding()
wchar_t*
_Py_GetLocaleEncoding(void)
{
#ifdef _Py_FORCE_UTF8_LOCALE
// On Android langinfo.h and CODESET are missing,
// and UTF-8 is always used in mbstowcs() and wcstombs().
return _PyMem_RawWcsdup(L"utf-8");
#else
#ifdef MS_WINDOWS
wchar_t encoding[23];
unsigned int ansi_codepage = GetACP();
swprintf(encoding, Py_ARRAY_LENGTH(encoding), L"cp%u", ansi_codepage);
encoding[Py_ARRAY_LENGTH(encoding) - 1] = 0;
return _PyMem_RawWcsdup(encoding);
#else
const char *encoding = nl_langinfo(CODESET);
if (!encoding || encoding[0] == '\0') {
// Use UTF-8 if nl_langinfo() returns an empty string. It can happen on
// macOS if the LC_CTYPE locale is not supported.
return _PyMem_RawWcsdup(L"utf-8");
}
wchar_t *wstr;
int res = decode_current_locale(encoding, &wstr, NULL,
NULL, _Py_ERROR_SURROGATEESCAPE);
if (res < 0) {
return NULL;
}
return wstr;
#endif // !MS_WINDOWS
#endif // !_Py_FORCE_UTF8_LOCALE
}
PyObject *
_Py_GetLocaleEncodingObject(void)
{
wchar_t *encoding = _Py_GetLocaleEncoding();
if (encoding == NULL) {
PyErr_NoMemory();
return NULL;
}
PyObject *str = PyUnicode_FromWideChar(encoding, -1);
PyMem_RawFree(encoding);
return str;
}
#ifdef HAVE_NON_UNICODE_WCHAR_T_REPRESENTATION
/* Check whether current locale uses Unicode as internal wchar_t form. */
int
_Py_LocaleUsesNonUnicodeWchar(void)
{
/* Oracle Solaris uses non-Unicode internal wchar_t form for
non-Unicode locales and hence needs conversion to UTF first. */
char* codeset = nl_langinfo(CODESET);
if (!codeset) {
return 0;
}
/* 646 refers to ISO/IEC 646 standard that corresponds to ASCII encoding */
return (strcmp(codeset, "UTF-8") != 0 && strcmp(codeset, "646") != 0);
}
static wchar_t *
_Py_ConvertWCharForm(const wchar_t *source, Py_ssize_t size,
const char *tocode, const char *fromcode)
{
static_assert(sizeof(wchar_t) == 4, "wchar_t must be 32-bit");
/* Ensure we won't overflow the size. */
if (size > (PY_SSIZE_T_MAX / (Py_ssize_t)sizeof(wchar_t))) {
PyErr_NoMemory();
return NULL;
}
/* the string doesn't have to be NULL terminated */
wchar_t* target = PyMem_Malloc(size * sizeof(wchar_t));
if (target == NULL) {
PyErr_NoMemory();
return NULL;
}
iconv_t cd = iconv_open(tocode, fromcode);
if (cd == (iconv_t)-1) {
PyErr_Format(PyExc_ValueError, "iconv_open() failed");
PyMem_Free(target);
return NULL;
}
char *inbuf = (char *) source;
char *outbuf = (char *) target;
size_t inbytesleft = sizeof(wchar_t) * size;
size_t outbytesleft = inbytesleft;
size_t ret = iconv(cd, &inbuf, &inbytesleft, &outbuf, &outbytesleft);
if (ret == DECODE_ERROR) {
PyErr_Format(PyExc_ValueError, "iconv() failed");
PyMem_Free(target);
iconv_close(cd);