Repository navigation
Expand file tree
/
Copy pathtokenizer.c
More file actions
3011 lines (2786 loc) · 92.2 KB
/
Copy pathtokenizer.c
File metadata and controls
3011 lines (2786 loc) · 92.2 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
/* Tokenizer implementation */
#define PY_SSIZE_T_CLEAN
#include "Python.h"
#include "pycore_call.h" // _PyObject_CallNoArgs()
#include <ctype.h>
#include <assert.h>
#include "tokenizer.h"
#include "errcode.h"
/* Alternate tab spacing */
#define ALTTABSIZE 1
#define is_potential_identifier_start(c) (\
(c >= 'a' && c <= 'z')\
|| (c >= 'A' && c <= 'Z')\
|| c == '_'\
|| (c >= 128))
#define is_potential_identifier_char(c) (\
(c >= 'a' && c <= 'z')\
|| (c >= 'A' && c <= 'Z')\
|| (c >= '0' && c <= '9')\
|| c == '_'\
|| (c >= 128))
/* Don't ever change this -- it would break the portability of Python code */
#define TABSIZE 8
#define MAKE_TOKEN(token_type) token_setup(tok, token, token_type, p_start, p_end)
#define MAKE_TYPE_COMMENT_TOKEN(token_type, col_offset, end_col_offset) (\
type_comment_token_setup(tok, token, token_type, col_offset, end_col_offset, p_start, p_end))
#define ADVANCE_LINENO() \
tok->lineno++; \
tok->col_offset = 0;
#define INSIDE_FSTRING(tok) (tok->tok_mode_stack_index > 0)
#define INSIDE_FSTRING_EXPR(tok) (tok->curly_bracket_expr_start_depth >= 0)
#ifdef Py_DEBUG
static inline tokenizer_mode* TOK_GET_MODE(struct tok_state* tok) {
assert(tok->tok_mode_stack_index >= 0);
assert(tok->tok_mode_stack_index < MAXFSTRINGLEVEL);
return &(tok->tok_mode_stack[tok->tok_mode_stack_index]);
}
static inline tokenizer_mode* TOK_NEXT_MODE(struct tok_state* tok) {
assert(tok->tok_mode_stack_index >= 0);
assert(tok->tok_mode_stack_index + 1 < MAXFSTRINGLEVEL);
return &(tok->tok_mode_stack[++tok->tok_mode_stack_index]);
}
#else
#define TOK_GET_MODE(tok) (&(tok->tok_mode_stack[tok->tok_mode_stack_index]))
#define TOK_NEXT_MODE(tok) (&(tok->tok_mode_stack[++tok->tok_mode_stack_index]))
#endif
/* Forward */
static struct tok_state *tok_new(void);
static int tok_nextc(struct tok_state *tok);
static void tok_backup(struct tok_state *tok, int c);
static int syntaxerror(struct tok_state *tok, const char *format, ...);
/* Spaces in this constant are treated as "zero or more spaces or tabs" when
tokenizing. */
static const char* type_comment_prefix = "# type: ";
/* Create and initialize a new tok_state structure */
static struct tok_state *
tok_new(void)
{
struct tok_state *tok = (struct tok_state *)PyMem_Malloc(
sizeof(struct tok_state));
if (tok == NULL)
return NULL;
tok->buf = tok->cur = tok->inp = NULL;
tok->fp_interactive = 0;
tok->interactive_src_start = NULL;
tok->interactive_src_end = NULL;
tok->start = NULL;
tok->end = NULL;
tok->done = E_OK;
tok->fp = NULL;
tok->input = NULL;
tok->tabsize = TABSIZE;
tok->indent = 0;
tok->indstack[0] = 0;
tok->atbol = 1;
tok->pendin = 0;
tok->prompt = tok->nextprompt = NULL;
tok->lineno = 0;
tok->starting_col_offset = -1;
tok->col_offset = -1;
tok->level = 0;
tok->altindstack[0] = 0;
tok->decoding_state = STATE_INIT;
tok->decoding_erred = 0;
tok->enc = NULL;
tok->encoding = NULL;
tok->cont_line = 0;
tok->filename = NULL;
tok->decoding_readline = NULL;
tok->decoding_buffer = NULL;
tok->readline = NULL;
tok->type_comments = 0;
tok->async_hacks = 0;
tok->async_def = 0;
tok->async_def_indent = 0;
tok->async_def_nl = 0;
tok->interactive_underflow = IUNDERFLOW_NORMAL;
tok->str = NULL;
tok->report_warnings = 1;
tok->tok_extra_tokens = 0;
tok->comment_newline = 0;
tok->implicit_newline = 0;
tok->tok_mode_stack[0] = (tokenizer_mode){.kind =TOK_REGULAR_MODE, .f_string_quote='\0', .f_string_quote_size = 0, .f_string_debug=0};
tok->tok_mode_stack_index = 0;
tok->tok_report_warnings = 1;
#ifdef Py_DEBUG
tok->debug = _Py_GetConfig()->parser_debug;
#endif
return tok;
}
static char *
new_string(const char *s, Py_ssize_t len, struct tok_state *tok)
{
char* result = (char *)PyMem_Malloc(len + 1);
if (!result) {
tok->done = E_NOMEM;
return NULL;
}
memcpy(result, s, len);
result[len] = '\0';
return result;
}
static char *
error_ret(struct tok_state *tok) /* XXX */
{
tok->decoding_erred = 1;
if ((tok->fp != NULL || tok->readline != NULL) && tok->buf != NULL) {/* see _PyTokenizer_Free */
PyMem_Free(tok->buf);
}
tok->buf = tok->cur = tok->inp = NULL;
tok->start = NULL;
tok->end = NULL;
tok->done = E_DECODE;
return NULL; /* as if it were EOF */
}
static const char *
get_normal_name(const char *s) /* for utf-8 and latin-1 */
{
char buf[13];
int i;
for (i = 0; i < 12; i++) {
int c = s[i];
if (c == '\0')
break;
else if (c == '_')
buf[i] = '-';
else
buf[i] = tolower(c);
}
buf[i] = '\0';
if (strcmp(buf, "utf-8") == 0 ||
strncmp(buf, "utf-8-", 6) == 0)
return "utf-8";
else if (strcmp(buf, "latin-1") == 0 ||
strcmp(buf, "iso-8859-1") == 0 ||
strcmp(buf, "iso-latin-1") == 0 ||
strncmp(buf, "latin-1-", 8) == 0 ||
strncmp(buf, "iso-8859-1-", 11) == 0 ||
strncmp(buf, "iso-latin-1-", 12) == 0)
return "iso-8859-1";
else
return s;
}
/* Return the coding spec in S, or NULL if none is found. */
static int
get_coding_spec(const char *s, char **spec, Py_ssize_t size, struct tok_state *tok)
{
Py_ssize_t i;
*spec = NULL;
/* Coding spec must be in a comment, and that comment must be
* the only statement on the source code line. */
for (i = 0; i < size - 6; i++) {
if (s[i] == '#')
break;
if (s[i] != ' ' && s[i] != '\t' && s[i] != '\014')
return 1;
}
for (; i < size - 6; i++) { /* XXX inefficient search */
const char* t = s + i;
if (memcmp(t, "coding", 6) == 0) {
const char* begin = NULL;
t += 6;
if (t[0] != ':' && t[0] != '=')
continue;
do {
t++;
} while (t[0] == ' ' || t[0] == '\t');
begin = t;
while (Py_ISALNUM(t[0]) ||
t[0] == '-' || t[0] == '_' || t[0] == '.')
t++;
if (begin < t) {
char* r = new_string(begin, t - begin, tok);
const char* q;
if (!r)
return 0;
q = get_normal_name(r);
if (r != q) {
PyMem_Free(r);
r = new_string(q, strlen(q), tok);
if (!r)
return 0;
}
*spec = r;
break;
}
}
}
return 1;
}
/* Check whether the line contains a coding spec. If it does,
invoke the set_readline function for the new encoding.
This function receives the tok_state and the new encoding.
Return 1 on success, 0 on failure. */
static int
check_coding_spec(const char* line, Py_ssize_t size, struct tok_state *tok,
int set_readline(struct tok_state *, const char *))
{
char *cs;
if (tok->cont_line) {
/* It's a continuation line, so it can't be a coding spec. */
tok->decoding_state = STATE_NORMAL;
return 1;
}
if (!get_coding_spec(line, &cs, size, tok)) {
return 0;
}
if (!cs) {
Py_ssize_t i;
for (i = 0; i < size; i++) {
if (line[i] == '#' || line[i] == '\n' || line[i] == '\r')
break;
if (line[i] != ' ' && line[i] != '\t' && line[i] != '\014') {
/* Stop checking coding spec after a line containing
* anything except a comment. */
tok->decoding_state = STATE_NORMAL;
break;
}
}
return 1;
}
tok->decoding_state = STATE_NORMAL;
if (tok->encoding == NULL) {
assert(tok->decoding_readline == NULL);
if (strcmp(cs, "utf-8") != 0 && !set_readline(tok, cs)) {
error_ret(tok);
PyErr_Format(PyExc_SyntaxError, "encoding problem: %s", cs);
PyMem_Free(cs);
return 0;
}
tok->encoding = cs;
} else { /* then, compare cs with BOM */
if (strcmp(tok->encoding, cs) != 0) {
error_ret(tok);
PyErr_Format(PyExc_SyntaxError,
"encoding problem: %s with BOM", cs);
PyMem_Free(cs);
return 0;
}
PyMem_Free(cs);
}
return 1;
}
/* See whether the file starts with a BOM. If it does,
invoke the set_readline function with the new encoding.
Return 1 on success, 0 on failure. */
static int
check_bom(int get_char(struct tok_state *),
void unget_char(int, struct tok_state *),
int set_readline(struct tok_state *, const char *),
struct tok_state *tok)
{
int ch1, ch2, ch3;
ch1 = get_char(tok);
tok->decoding_state = STATE_SEEK_CODING;
if (ch1 == EOF) {
return 1;
} else if (ch1 == 0xEF) {
ch2 = get_char(tok);
if (ch2 != 0xBB) {
unget_char(ch2, tok);
unget_char(ch1, tok);
return 1;
}
ch3 = get_char(tok);
if (ch3 != 0xBF) {
unget_char(ch3, tok);
unget_char(ch2, tok);
unget_char(ch1, tok);
return 1;
}
} else {
unget_char(ch1, tok);
return 1;
}
if (tok->encoding != NULL)
PyMem_Free(tok->encoding);
tok->encoding = new_string("utf-8", 5, tok);
if (!tok->encoding)
return 0;
/* No need to set_readline: input is already utf-8 */
return 1;
}
static int
tok_concatenate_interactive_new_line(struct tok_state *tok, const char *line) {
assert(tok->fp_interactive);
if (!line) {
return 0;
}
Py_ssize_t current_size = tok->interactive_src_end - tok->interactive_src_start;
Py_ssize_t line_size = strlen(line);
char last_char = line[line_size > 0 ? line_size - 1 : line_size];
if (last_char != '\n') {
line_size += 1;
}
char* new_str = tok->interactive_src_start;
new_str = PyMem_Realloc(new_str, current_size + line_size + 1);
if (!new_str) {
if (tok->interactive_src_start) {
PyMem_Free(tok->interactive_src_start);
}
tok->interactive_src_start = NULL;
tok->interactive_src_end = NULL;
tok->done = E_NOMEM;
return -1;
}
strcpy(new_str + current_size, line);
tok->implicit_newline = 0;
if (last_char != '\n') {
/* Last line does not end in \n, fake one */
new_str[current_size + line_size - 1] = '\n';
new_str[current_size + line_size] = '\0';
tok->implicit_newline = 1;
}
tok->interactive_src_start = new_str;
tok->interactive_src_end = new_str + current_size + line_size;
return 0;
}
/* Traverse and remember all f-string buffers, in order to be able to restore
them after reallocating tok->buf */
static void
remember_fstring_buffers(struct tok_state *tok)
{
int index;
tokenizer_mode *mode;
for (index = tok->tok_mode_stack_index; index >= 0; --index) {
mode = &(tok->tok_mode_stack[index]);
mode->f_string_start_offset = mode->f_string_start - tok->buf;
mode->f_string_multi_line_start_offset = mode->f_string_multi_line_start - tok->buf;
}
}
/* Traverse and restore all f-string buffers after reallocating tok->buf */
static void
restore_fstring_buffers(struct tok_state *tok)
{
int index;
tokenizer_mode *mode;
for (index = tok->tok_mode_stack_index; index >= 0; --index) {
mode = &(tok->tok_mode_stack[index]);
mode->f_string_start = tok->buf + mode->f_string_start_offset;
mode->f_string_multi_line_start = tok->buf + mode->f_string_multi_line_start_offset;
}
}
static int
set_fstring_expr(struct tok_state* tok, struct token *token, char c) {
assert(token != NULL);
assert(c == '}' || c == ':' || c == '!');
tokenizer_mode *tok_mode = TOK_GET_MODE(tok);
if (!tok_mode->f_string_debug || token->metadata) {
return 0;
}
PyObject *res = PyUnicode_DecodeUTF8(
tok_mode->last_expr_buffer,
tok_mode->last_expr_size - tok_mode->last_expr_end,
NULL
);
if (!res) {
return -1;
}
token->metadata = res;
return 0;
}
static int
update_fstring_expr(struct tok_state *tok, char cur)
{
assert(tok->cur != NULL);
Py_ssize_t size = strlen(tok->cur);
tokenizer_mode *tok_mode = TOK_GET_MODE(tok);
switch (cur) {
case 0:
if (!tok_mode->last_expr_buffer || tok_mode->last_expr_end >= 0) {
return 1;
}
char *new_buffer = PyMem_Realloc(
tok_mode->last_expr_buffer,
tok_mode->last_expr_size + size
);
if (new_buffer == NULL) {
PyMem_Free(tok_mode->last_expr_buffer);
goto error;
}
tok_mode->last_expr_buffer = new_buffer;
strncpy(tok_mode->last_expr_buffer + tok_mode->last_expr_size, tok->cur, size);
tok_mode->last_expr_size += size;
break;
case '{':
if (tok_mode->last_expr_buffer != NULL) {
PyMem_Free(tok_mode->last_expr_buffer);
}
tok_mode->last_expr_buffer = PyMem_Malloc(size);
if (tok_mode->last_expr_buffer == NULL) {
goto error;
}
tok_mode->last_expr_size = size;
tok_mode->last_expr_end = -1;
strncpy(tok_mode->last_expr_buffer, tok->cur, size);
break;
case '}':
case '!':
case ':':
if (tok_mode->last_expr_end == -1) {
tok_mode->last_expr_end = strlen(tok->start);
}
break;
default:
Py_UNREACHABLE();
}
return 1;
error:
tok->done = E_NOMEM;
return 0;
}
static void
free_fstring_expressions(struct tok_state *tok)
{
int index;
tokenizer_mode *mode;
for (index = tok->tok_mode_stack_index; index >= 0; --index) {
mode = &(tok->tok_mode_stack[index]);
if (mode->last_expr_buffer != NULL) {
PyMem_Free(mode->last_expr_buffer);
mode->last_expr_buffer = NULL;
mode->last_expr_size = 0;
mode->last_expr_end = -1;
}
}
}
/* Read a line of text from TOK into S, using the stream in TOK.
Return NULL on failure, else S.
On entry, tok->decoding_buffer will be one of:
1) NULL: need to call tok->decoding_readline to get a new line
2) PyUnicodeObject *: decoding_feof has called tok->decoding_readline and
stored the result in tok->decoding_buffer
3) PyByteArrayObject *: previous call to tok_readline_recode did not have enough room
(in the s buffer) to copy entire contents of the line read
by tok->decoding_readline. tok->decoding_buffer has the overflow.
In this case, tok_readline_recode is called in a loop (with an expanded buffer)
until the buffer ends with a '\n' (or until the end of the file is
reached): see tok_nextc and its calls to tok_reserve_buf.
*/
static int
tok_reserve_buf(struct tok_state *tok, Py_ssize_t size)
{
Py_ssize_t cur = tok->cur - tok->buf;
Py_ssize_t oldsize = tok->inp - tok->buf;
Py_ssize_t newsize = oldsize + Py_MAX(size, oldsize >> 1);
if (newsize > tok->end - tok->buf) {
char *newbuf = tok->buf;
Py_ssize_t start = tok->start == NULL ? -1 : tok->start - tok->buf;
Py_ssize_t line_start = tok->start == NULL ? -1 : tok->line_start - tok->buf;
Py_ssize_t multi_line_start = tok->multi_line_start - tok->buf;
remember_fstring_buffers(tok);
newbuf = (char *)PyMem_Realloc(newbuf, newsize);
if (newbuf == NULL) {
tok->done = E_NOMEM;
return 0;
}
tok->buf = newbuf;
tok->cur = tok->buf + cur;
tok->inp = tok->buf + oldsize;
tok->end = tok->buf + newsize;
tok->start = start < 0 ? NULL : tok->buf + start;
tok->line_start = line_start < 0 ? NULL : tok->buf + line_start;
tok->multi_line_start = multi_line_start < 0 ? NULL : tok->buf + multi_line_start;
restore_fstring_buffers(tok);
}
return 1;
}
static inline int
contains_null_bytes(const char* str, size_t size) {
return memchr(str, 0, size) != NULL;
}
static int
tok_readline_recode(struct tok_state *tok) {
PyObject *line;
const char *buf;
Py_ssize_t buflen;
line = tok->decoding_buffer;
if (line == NULL) {
line = PyObject_CallNoArgs(tok->decoding_readline);
if (line == NULL) {
error_ret(tok);
goto error;
}
}
else {
tok->decoding_buffer = NULL;
}
buf = PyUnicode_AsUTF8AndSize(line, &buflen);
if (buf == NULL) {
error_ret(tok);
goto error;
}
// Make room for the null terminator *and* potentially
// an extra newline character that we may need to artificially
// add.
size_t buffer_size = buflen + 2;
if (!tok_reserve_buf(tok, buffer_size)) {
goto error;
}
memcpy(tok->inp, buf, buflen);
tok->inp += buflen;
*tok->inp = '\0';
if (tok->fp_interactive &&
tok_concatenate_interactive_new_line(tok, buf) == -1) {
goto error;
}
Py_DECREF(line);
return 1;
error:
Py_XDECREF(line);
return 0;
}
/* Set the readline function for TOK to a StreamReader's
readline function. The StreamReader is named ENC.
This function is called from check_bom and check_coding_spec.
ENC is usually identical to the future value of tok->encoding,
except for the (currently unsupported) case of UTF-16.
Return 1 on success, 0 on failure. */
static int
fp_setreadl(struct tok_state *tok, const char* enc)
{
PyObject *readline, *open, *stream;
int fd;
long pos;
fd = fileno(tok->fp);
/* Due to buffering the file offset for fd can be different from the file
* position of tok->fp. If tok->fp was opened in text mode on Windows,
* its file position counts CRLF as one char and can't be directly mapped
* to the file offset for fd. Instead we step back one byte and read to
* the end of line.*/
pos = ftell(tok->fp);
if (pos == -1 ||
lseek(fd, (off_t)(pos > 0 ? pos - 1 : pos), SEEK_SET) == (off_t)-1) {
PyErr_SetFromErrnoWithFilename(PyExc_OSError, NULL);
return 0;
}
open = _PyImport_GetModuleAttrString("io", "open");
if (open == NULL) {
return 0;
}
stream = PyObject_CallFunction(open, "isisOOO",
fd, "r", -1, enc, Py_None, Py_None, Py_False);
Py_DECREF(open);
if (stream == NULL) {
return 0;
}
readline = PyObject_GetAttr(stream, &_Py_ID(readline));
Py_DECREF(stream);
if (readline == NULL) {
return 0;
}
Py_XSETREF(tok->decoding_readline, readline);
if (pos > 0) {
PyObject *bufobj = _PyObject_CallNoArgs(readline);
if (bufobj == NULL) {
return 0;
}
Py_DECREF(bufobj);
}
return 1;
}
/* Fetch the next byte from TOK. */
static int fp_getc(struct tok_state *tok) {
return getc(tok->fp);
}
/* Unfetch the last byte back into TOK. */
static void fp_ungetc(int c, struct tok_state *tok) {
ungetc(c, tok->fp);
}
/* Check whether the characters at s start a valid
UTF-8 sequence. Return the number of characters forming
the sequence if yes, 0 if not. The special cases match
those in stringlib/codecs.h:utf8_decode.
*/
static int
valid_utf8(const unsigned char* s)
{
int expected = 0;
int length;
if (*s < 0x80) {
/* single-byte code */
return 1;
}
else if (*s < 0xE0) {
/* \xC2\x80-\xDF\xBF -- 0080-07FF */
if (*s < 0xC2) {
/* invalid sequence
\x80-\xBF -- continuation byte
\xC0-\xC1 -- fake 0000-007F */
return 0;
}
expected = 1;
}
else if (*s < 0xF0) {
/* \xE0\xA0\x80-\xEF\xBF\xBF -- 0800-FFFF */
if (*s == 0xE0 && *(s + 1) < 0xA0) {
/* invalid sequence
\xE0\x80\x80-\xE0\x9F\xBF -- fake 0000-0800 */
return 0;
}
else if (*s == 0xED && *(s + 1) >= 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 https://www.unicode.org/versions/Unicode5.2.0/ch03.pdf
(table 3-7) and http://www.rfc-editor.org/rfc/rfc3629.txt */
return 0;
}
expected = 2;
}
else if (*s < 0xF5) {
/* \xF0\x90\x80\x80-\xF4\x8F\xBF\xBF -- 10000-10FFFF */
if (*(s + 1) < 0x90 ? *s == 0xF0 : *s == 0xF4) {
/* invalid sequence -- one of:
\xF0\x80\x80\x80-\xF0\x8F\xBF\xBF -- fake 0000-FFFF
\xF4\x90\x80\x80- -- 110000- overflow */
return 0;
}
expected = 3;
}
else {
/* invalid start byte */
return 0;
}
length = expected + 1;
for (; expected; expected--)
if (s[expected] < 0x80 || s[expected] >= 0xC0)
return 0;
return length;
}
static int
ensure_utf8(char *line, struct tok_state *tok)
{
int badchar = 0;
unsigned char *c;
int length;
for (c = (unsigned char *)line; *c; c += length) {
if (!(length = valid_utf8(c))) {
badchar = *c;
break;
}
}
if (badchar) {
PyErr_Format(PyExc_SyntaxError,
"Non-UTF-8 code starting with '\\x%.2x' "
"in file %U on line %i, "
"but no encoding declared; "
"see https://peps.python.org/pep-0263/ for details",
badchar, tok->filename, tok->lineno);
return 0;
}
return 1;
}
/* Fetch a byte from TOK, using the string buffer. */
static int
buf_getc(struct tok_state *tok) {
return Py_CHARMASK(*tok->str++);
}
/* Unfetch a byte from TOK, using the string buffer. */
static void
buf_ungetc(int c, struct tok_state *tok) {
tok->str--;
assert(Py_CHARMASK(*tok->str) == c); /* tok->cur may point to read-only segment */
}
/* Set the readline function for TOK to ENC. For the string-based
tokenizer, this means to just record the encoding. */
static int
buf_setreadl(struct tok_state *tok, const char* enc) {
tok->enc = enc;
return 1;
}
/* Return a UTF-8 encoding Python string object from the
C byte string STR, which is encoded with ENC. */
static PyObject *
translate_into_utf8(const char* str, const char* enc) {
PyObject *utf8;
PyObject* buf = PyUnicode_Decode(str, strlen(str), enc, NULL);
if (buf == NULL)
return NULL;
utf8 = PyUnicode_AsUTF8String(buf);
Py_DECREF(buf);
return utf8;
}
static char *
translate_newlines(const char *s, int exec_input, int preserve_crlf,
struct tok_state *tok) {
int skip_next_lf = 0;
size_t needed_length = strlen(s) + 2, final_length;
char *buf, *current;
char c = '\0';
buf = PyMem_Malloc(needed_length);
if (buf == NULL) {
tok->done = E_NOMEM;
return NULL;
}
for (current = buf; *s; s++, current++) {
c = *s;
if (skip_next_lf) {
skip_next_lf = 0;
if (c == '\n') {
c = *++s;
if (!c)
break;
}
}
if (!preserve_crlf && c == '\r') {
skip_next_lf = 1;
c = '\n';
}
*current = c;
}
/* If this is exec input, add a newline to the end of the string if
there isn't one already. */
if (exec_input && c != '\n' && c != '\0') {
*current = '\n';
current++;
}
*current = '\0';
final_length = current - buf + 1;
if (final_length < needed_length && final_length) {
/* should never fail */
char* result = PyMem_Realloc(buf, final_length);
if (result == NULL) {
PyMem_Free(buf);
}
buf = result;
}
return buf;
}
/* Decode a byte string STR for use as the buffer of TOK.
Look for encoding declarations inside STR, and record them
inside TOK. */
static char *
decode_str(const char *input, int single, struct tok_state *tok, int preserve_crlf)
{
PyObject* utf8 = NULL;
char *str;
const char *s;
const char *newl[2] = {NULL, NULL};
int lineno = 0;
tok->input = str = translate_newlines(input, single, preserve_crlf, tok);
if (str == NULL)
return NULL;
tok->enc = NULL;
tok->str = str;
if (!check_bom(buf_getc, buf_ungetc, buf_setreadl, tok))
return error_ret(tok);
str = tok->str; /* string after BOM if any */
assert(str);
if (tok->enc != NULL) {
utf8 = translate_into_utf8(str, tok->enc);
if (utf8 == NULL)
return error_ret(tok);
str = PyBytes_AsString(utf8);
}
for (s = str;; s++) {
if (*s == '\0') break;
else if (*s == '\n') {
assert(lineno < 2);
newl[lineno] = s;
lineno++;
if (lineno == 2) break;
}
}
tok->enc = NULL;
/* need to check line 1 and 2 separately since check_coding_spec
assumes a single line as input */
if (newl[0]) {
if (!check_coding_spec(str, newl[0] - str, tok, buf_setreadl)) {
return NULL;
}
if (tok->enc == NULL && tok->decoding_state != STATE_NORMAL && newl[1]) {
if (!check_coding_spec(newl[0]+1, newl[1] - newl[0],
tok, buf_setreadl))
return NULL;
}
}
if (tok->enc != NULL) {
assert(utf8 == NULL);
utf8 = translate_into_utf8(str, tok->enc);
if (utf8 == NULL)
return error_ret(tok);
str = PyBytes_AS_STRING(utf8);
}
assert(tok->decoding_buffer == NULL);
tok->decoding_buffer = utf8; /* CAUTION */
return str;
}
/* Set up tokenizer for string */
struct tok_state *
_PyTokenizer_FromString(const char *str, int exec_input, int preserve_crlf)
{
struct tok_state *tok = tok_new();
char *decoded;
if (tok == NULL)
return NULL;
decoded = decode_str(str, exec_input, tok, preserve_crlf);
if (decoded == NULL) {
_PyTokenizer_Free(tok);
return NULL;
}
tok->buf = tok->cur = tok->inp = decoded;
tok->end = decoded;
return tok;
}
struct tok_state *
_PyTokenizer_FromReadline(PyObject* readline, const char* enc,
int exec_input, int preserve_crlf)
{
struct tok_state *tok = tok_new();
if (tok == NULL)
return NULL;
if ((tok->buf = (char *)PyMem_Malloc(BUFSIZ)) == NULL) {
_PyTokenizer_Free(tok);
return NULL;
}
tok->cur = tok->inp = tok->buf;
tok->end = tok->buf + BUFSIZ;
tok->fp = NULL;
if (enc != NULL) {
tok->encoding = new_string(enc, strlen(enc), tok);
if (!tok->encoding) {
_PyTokenizer_Free(tok);
return NULL;
}
}
tok->decoding_state = STATE_NORMAL;
Py_INCREF(readline);
tok->readline = readline;
return tok;
}
/* Set up tokenizer for UTF-8 string */
struct tok_state *
_PyTokenizer_FromUTF8(const char *str, int exec_input, int preserve_crlf)
{
struct tok_state *tok = tok_new();
char *translated;
if (tok == NULL)
return NULL;
tok->input = translated = translate_newlines(str, exec_input, preserve_crlf, tok);
if (translated == NULL) {
_PyTokenizer_Free(tok);
return NULL;
}
tok->decoding_state = STATE_NORMAL;
tok->enc = NULL;
tok->str = translated;
tok->encoding = new_string("utf-8", 5, tok);
if (!tok->encoding) {
_PyTokenizer_Free(tok);
return NULL;
}
tok->buf = tok->cur = tok->inp = translated;
tok->end = translated;
return tok;
}
/* Set up tokenizer for file */
struct tok_state *
_PyTokenizer_FromFile(FILE *fp, const char* enc,
const char *ps1, const char *ps2)
{
struct tok_state *tok = tok_new();
if (tok == NULL)
return NULL;
if ((tok->buf = (char *)PyMem_Malloc(BUFSIZ)) == NULL) {
_PyTokenizer_Free(tok);
return NULL;
}
tok->cur = tok->inp = tok->buf;
tok->end = tok->buf + BUFSIZ;
tok->fp = fp;
tok->prompt = ps1;
tok->nextprompt = ps2;
if (enc != NULL) {
/* Must copy encoding declaration since it
gets copied into the parse tree. */
tok->encoding = new_string(enc, strlen(enc), tok);
if (!tok->encoding) {
_PyTokenizer_Free(tok);
return NULL;
}
tok->decoding_state = STATE_NORMAL;
}
return tok;
}
/* Free a tok_state structure */
void
_PyTokenizer_Free(struct tok_state *tok)
{
if (tok->encoding != NULL) {
PyMem_Free(tok->encoding);