forked from micropython/micropython
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathobjstr.c
2457 lines (2202 loc) · 84 KB
/
objstr.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
/*
* This file is part of the MicroPython project, http://micropython.org/
*
* The MIT License (MIT)
*
* Copyright (c) 2013, 2014 Damien P. George
* Copyright (c) 2014-2018 Paul Sokolovsky
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
#include <string.h>
#include <assert.h>
#include "py/unicode.h"
#include "py/objstr.h"
#include "py/objlist.h"
#include "py/runtime.h"
#include "py/stackctrl.h"
#if MICROPY_PY_BUILTINS_STR_OP_MODULO
STATIC mp_obj_t str_modulo_format(mp_obj_t pattern, size_t n_args, const mp_obj_t *args, mp_obj_t dict);
#endif
STATIC mp_obj_t mp_obj_new_bytes_iterator(mp_obj_t str, mp_obj_iter_buf_t *iter_buf);
STATIC NORETURN void bad_implicit_conversion(mp_obj_t self_in);
STATIC mp_obj_t mp_obj_new_str_type_from_vstr(const mp_obj_type_t *type, vstr_t *vstr);
STATIC void str_check_arg_type(const mp_obj_type_t *self_type, const mp_obj_t arg) {
// String operations generally need the args type to match the object they're called on,
// e.g. str.find(str), byte.startswith(byte)
// with the exception that bytes may be used for bytearray and vice versa.
const mp_obj_type_t *arg_type = mp_obj_get_type(arg);
#if MICROPY_PY_BUILTINS_BYTEARRAY
if (arg_type == &mp_type_bytearray) {
arg_type = &mp_type_bytes;
}
if (self_type == &mp_type_bytearray) {
self_type = &mp_type_bytes;
}
#endif
if (arg_type != self_type) {
bad_implicit_conversion(arg);
}
}
STATIC void check_is_str_or_bytes(mp_obj_t self_in) {
mp_check_self(mp_obj_is_str_or_bytes(self_in));
}
/******************************************************************************/
/* str */
void mp_str_print_quoted(const mp_print_t *print, const byte *str_data, size_t str_len, bool is_bytes) {
// this escapes characters, but it will be very slow to print (calling print many times)
bool has_single_quote = false;
bool has_double_quote = false;
for (const byte *s = str_data, *top = str_data + str_len; !has_double_quote && s < top; s++) {
if (*s == '\'') {
has_single_quote = true;
} else if (*s == '"') {
has_double_quote = true;
}
}
int quote_char = '\'';
if (has_single_quote && !has_double_quote) {
quote_char = '"';
}
mp_printf(print, "%c", quote_char);
for (const byte *s = str_data, *top = str_data + str_len; s < top; s++) {
if (*s == quote_char) {
mp_printf(print, "\\%c", quote_char);
} else if (*s == '\\') {
mp_print_str(print, "\\\\");
} else if (*s >= 0x20 && *s != 0x7f && (!is_bytes || *s < 0x80)) {
// In strings, anything which is not ascii control character
// is printed as is, this includes characters in range 0x80-0xff
// (which can be non-Latin letters, etc.)
mp_printf(print, "%c", *s);
} else if (*s == '\n') {
mp_print_str(print, "\\n");
} else if (*s == '\r') {
mp_print_str(print, "\\r");
} else if (*s == '\t') {
mp_print_str(print, "\\t");
} else {
mp_printf(print, "\\x%02x", *s);
}
}
mp_printf(print, "%c", quote_char);
}
#if MICROPY_PY_JSON
void mp_str_print_json(const mp_print_t *print, const byte *str_data, size_t str_len) {
// for JSON spec, see http://www.ietf.org/rfc/rfc4627.txt
// if we are given a valid utf8-encoded string, we will print it in a JSON-conforming way
mp_print_str(print, "\"");
for (const byte *s = str_data, *top = str_data + str_len; s < top; s++) {
if (*s == '"' || *s == '\\') {
mp_printf(print, "\\%c", *s);
} else if (*s >= 32) {
// this will handle normal and utf-8 encoded chars
mp_printf(print, "%c", *s);
} else if (*s == '\n') {
mp_print_str(print, "\\n");
} else if (*s == '\r') {
mp_print_str(print, "\\r");
} else if (*s == '\t') {
mp_print_str(print, "\\t");
} else {
// this will handle control chars
mp_printf(print, "\\u%04x", *s);
}
}
mp_print_str(print, "\"");
}
#endif
STATIC void str_print(const mp_print_t *print, mp_obj_t self_in, mp_print_kind_t kind) {
GET_STR_DATA_LEN(self_in, str_data, str_len);
#if MICROPY_PY_JSON
if (kind == PRINT_JSON) {
mp_str_print_json(print, str_data, str_len);
return;
}
#endif
#if !MICROPY_PY_BUILTINS_STR_UNICODE
bool is_bytes = mp_obj_is_type(self_in, &mp_type_bytes);
#else
bool is_bytes = true;
#endif
if (kind == PRINT_RAW || (!MICROPY_PY_BUILTINS_STR_UNICODE && kind == PRINT_STR && !is_bytes)) {
print->print_strn(print->data, (const char *)str_data, str_len);
} else {
if (is_bytes) {
print->print_strn(print->data, "b", 1);
}
mp_str_print_quoted(print, str_data, str_len, is_bytes);
}
}
mp_obj_t mp_obj_str_make_new(const mp_obj_type_t *type, size_t n_args, size_t n_kw, const mp_obj_t *args) {
#if MICROPY_CPYTHON_COMPAT
if (n_kw != 0) {
mp_arg_error_unimpl_kw();
}
#endif
mp_arg_check_num(n_args, n_kw, 0, 3, false);
switch (n_args) {
case 0:
return MP_OBJ_NEW_QSTR(MP_QSTR_);
case 1: {
vstr_t vstr;
mp_print_t print;
vstr_init_print(&vstr, 16, &print);
mp_obj_print_helper(&print, args[0], PRINT_STR);
return mp_obj_new_str_type_from_vstr(type, &vstr);
}
default: // 2 or 3 args
// TODO: validate 2nd/3rd args
if (mp_obj_is_type(args[0], &mp_type_bytes)) {
GET_STR_DATA_LEN(args[0], str_data, str_len);
GET_STR_HASH(args[0], str_hash);
if (str_hash == 0) {
str_hash = qstr_compute_hash(str_data, str_len);
}
#if MICROPY_PY_BUILTINS_STR_UNICODE_CHECK
if (!utf8_check(str_data, str_len)) {
mp_raise_msg(&mp_type_UnicodeError, NULL);
}
#endif
// Check if a qstr with this data already exists
qstr q = qstr_find_strn((const char *)str_data, str_len);
if (q != MP_QSTRnull) {
return MP_OBJ_NEW_QSTR(q);
}
mp_obj_str_t *o = MP_OBJ_TO_PTR(mp_obj_new_str_copy(type, NULL, str_len));
o->data = str_data;
o->hash = str_hash;
return MP_OBJ_FROM_PTR(o);
} else {
mp_buffer_info_t bufinfo;
mp_get_buffer_raise(args[0], &bufinfo, MP_BUFFER_READ);
// This will utf-8 check the input.
return mp_obj_new_str(bufinfo.buf, bufinfo.len);
}
}
}
STATIC mp_obj_t bytes_make_new(const mp_obj_type_t *type_in, size_t n_args, size_t n_kw, const mp_obj_t *args) {
(void)type_in;
#if MICROPY_CPYTHON_COMPAT
if (n_kw != 0) {
mp_arg_error_unimpl_kw();
}
#else
(void)n_kw;
#endif
if (n_args == 0) {
return mp_const_empty_bytes;
}
if (mp_obj_is_type(args[0], &mp_type_bytes)) {
return args[0];
}
if (mp_obj_is_str(args[0])) {
if (n_args < 2 || n_args > 3) {
#if MICROPY_ERROR_REPORTING <= MICROPY_ERROR_REPORTING_TERSE
goto wrong_args;
#else
mp_raise_TypeError(MP_ERROR_TEXT("string argument without an encoding"));
#endif
}
GET_STR_DATA_LEN(args[0], str_data, str_len);
GET_STR_HASH(args[0], str_hash);
if (str_hash == 0) {
str_hash = qstr_compute_hash(str_data, str_len);
}
mp_obj_str_t *o = MP_OBJ_TO_PTR(mp_obj_new_str_copy(&mp_type_bytes, NULL, str_len));
o->data = str_data;
o->hash = str_hash;
return MP_OBJ_FROM_PTR(o);
}
if (n_args > 1) {
goto wrong_args;
}
if (mp_obj_is_small_int(args[0])) {
mp_int_t len = MP_OBJ_SMALL_INT_VALUE(args[0]);
if (len < 0) {
mp_raise_ValueError(NULL);
}
vstr_t vstr;
vstr_init_len(&vstr, len);
memset(vstr.buf, 0, len);
return mp_obj_new_bytes_from_vstr(&vstr);
}
// check if argument has the buffer protocol
mp_buffer_info_t bufinfo;
if (mp_get_buffer(args[0], &bufinfo, MP_BUFFER_READ)) {
return mp_obj_new_bytes(bufinfo.buf, bufinfo.len);
}
vstr_t vstr;
// Try to create array of exact len if initializer len is known
mp_obj_t len_in = mp_obj_len_maybe(args[0]);
if (len_in == MP_OBJ_NULL) {
vstr_init(&vstr, 16);
} else {
mp_int_t len = MP_OBJ_SMALL_INT_VALUE(len_in);
vstr_init(&vstr, len);
}
mp_obj_iter_buf_t iter_buf;
mp_obj_t iterable = mp_getiter(args[0], &iter_buf);
mp_obj_t item;
while ((item = mp_iternext(iterable)) != MP_OBJ_STOP_ITERATION) {
mp_int_t val = mp_obj_get_int(item);
#if MICROPY_FULL_CHECKS
if (val < 0 || val > 255) {
mp_raise_ValueError(MP_ERROR_TEXT("bytes value out of range"));
}
#endif
vstr_add_byte(&vstr, val);
}
return mp_obj_new_bytes_from_vstr(&vstr);
wrong_args:
mp_raise_TypeError(MP_ERROR_TEXT("wrong number of arguments"));
}
// like strstr but with specified length and allows \0 bytes
// TODO replace with something more efficient/standard
const byte *find_subbytes(const byte *haystack, size_t hlen, const byte *needle, size_t nlen, int direction) {
if (hlen >= nlen) {
size_t str_index, str_index_end;
if (direction > 0) {
str_index = 0;
str_index_end = hlen - nlen;
} else {
str_index = hlen - nlen;
str_index_end = 0;
}
for (;;) {
if (memcmp(&haystack[str_index], needle, nlen) == 0) {
// found
return haystack + str_index;
}
if (str_index == str_index_end) {
// not found
break;
}
str_index += direction;
}
}
return NULL;
}
// Note: this function is used to check if an object is a str or bytes, which
// works because both those types use it as their binary_op method. Revisit
// mp_obj_is_str_or_bytes if this fact changes.
mp_obj_t mp_obj_str_binary_op(mp_binary_op_t op, mp_obj_t lhs_in, mp_obj_t rhs_in) {
// check for modulo
if (op == MP_BINARY_OP_MODULO) {
#if MICROPY_PY_BUILTINS_STR_OP_MODULO
mp_obj_t *args = &rhs_in;
size_t n_args = 1;
mp_obj_t dict = MP_OBJ_NULL;
if (mp_obj_is_type(rhs_in, &mp_type_tuple)) {
// TODO: Support tuple subclasses?
mp_obj_tuple_get(rhs_in, &n_args, &args);
} else if (mp_obj_is_type(rhs_in, &mp_type_dict)) {
dict = rhs_in;
}
return str_modulo_format(lhs_in, n_args, args, dict);
#else
return MP_OBJ_NULL;
#endif
}
// from now on we need lhs type and data, so extract them
const mp_obj_type_t *lhs_type = mp_obj_get_type(lhs_in);
GET_STR_DATA_LEN(lhs_in, lhs_data, lhs_len);
// check for multiply
if (op == MP_BINARY_OP_MULTIPLY) {
mp_int_t n;
if (!mp_obj_get_int_maybe(rhs_in, &n)) {
return MP_OBJ_NULL; // op not supported
}
if (n <= 0) {
if (lhs_type == &mp_type_str) {
return MP_OBJ_NEW_QSTR(MP_QSTR_); // empty str
} else {
return mp_const_empty_bytes;
}
}
vstr_t vstr;
vstr_init_len(&vstr, lhs_len * n);
mp_seq_multiply(lhs_data, sizeof(*lhs_data), lhs_len, n, vstr.buf);
return mp_obj_new_str_type_from_vstr(lhs_type, &vstr);
}
// From now on all operations allow:
// - str with str
// - bytes with bytes
// - bytes with bytearray
// - bytes with array.array
// To do this efficiently we use the buffer protocol to extract the raw
// data for the rhs, but only if the lhs is a bytes object.
//
// NOTE: CPython does not allow comparison between bytes ard array.array
// (even if the array is of type 'b'), even though it allows addition of
// such types. We are not compatible with this (we do allow comparison
// of bytes with anything that has the buffer protocol). It would be
// easy to "fix" this with a bit of extra logic below, but it costs code
// size and execution time so we don't.
const byte *rhs_data;
size_t rhs_len;
if (lhs_type == mp_obj_get_type(rhs_in)) {
GET_STR_DATA_LEN(rhs_in, rhs_data_, rhs_len_);
rhs_data = rhs_data_;
rhs_len = rhs_len_;
} else if (lhs_type == &mp_type_bytes) {
mp_buffer_info_t bufinfo;
if (!mp_get_buffer(rhs_in, &bufinfo, MP_BUFFER_READ)) {
return MP_OBJ_NULL; // op not supported
}
rhs_data = bufinfo.buf;
rhs_len = bufinfo.len;
} else {
// LHS is str and RHS has an incompatible type
// (except if operation is EQUAL, but that's handled by mp_obj_equal)
// CONTAINS must fail with a bad-implicit-conversion exception, because
// otherwise mp_binary_op() will fallback to `list(lhs).__contains__(rhs)`.
if (op == MP_BINARY_OP_CONTAINS) {
bad_implicit_conversion(rhs_in);
}
// All other operations are not supported, and may be handled by another
// type, eg for reverse operations.
return MP_OBJ_NULL;
}
switch (op) {
case MP_BINARY_OP_ADD:
case MP_BINARY_OP_INPLACE_ADD: {
if (lhs_len == 0 && mp_obj_get_type(rhs_in) == lhs_type) {
return rhs_in;
}
if (rhs_len == 0) {
return lhs_in;
}
vstr_t vstr;
vstr_init_len(&vstr, lhs_len + rhs_len);
memcpy(vstr.buf, lhs_data, lhs_len);
memcpy(vstr.buf + lhs_len, rhs_data, rhs_len);
return mp_obj_new_str_type_from_vstr(lhs_type, &vstr);
}
case MP_BINARY_OP_CONTAINS:
return mp_obj_new_bool(find_subbytes(lhs_data, lhs_len, rhs_data, rhs_len, 1) != NULL);
// case MP_BINARY_OP_NOT_EQUAL: // This is never passed here
case MP_BINARY_OP_EQUAL: // This will be passed only for bytes, str is dealt with in mp_obj_equal()
case MP_BINARY_OP_LESS:
case MP_BINARY_OP_LESS_EQUAL:
case MP_BINARY_OP_MORE:
case MP_BINARY_OP_MORE_EQUAL:
return mp_obj_new_bool(mp_seq_cmp_bytes(op, lhs_data, lhs_len, rhs_data, rhs_len));
default:
return MP_OBJ_NULL; // op not supported
}
}
#if !MICROPY_PY_BUILTINS_STR_UNICODE
// objstrunicode defines own version
const byte *str_index_to_ptr(const mp_obj_type_t *type, const byte *self_data, size_t self_len,
mp_obj_t index, bool is_slice) {
size_t index_val = mp_get_index(type, self_len, index, is_slice);
return self_data + index_val;
}
#endif
// This is used for both bytes and 8-bit strings. This is not used for unicode strings.
STATIC mp_obj_t bytes_subscr(mp_obj_t self_in, mp_obj_t index, mp_obj_t value) {
const mp_obj_type_t *type = mp_obj_get_type(self_in);
GET_STR_DATA_LEN(self_in, self_data, self_len);
if (value == MP_OBJ_SENTINEL) {
// load
#if MICROPY_PY_BUILTINS_SLICE
if (mp_obj_is_type(index, &mp_type_slice)) {
mp_bound_slice_t slice;
if (!mp_seq_get_fast_slice_indexes(self_len, index, &slice)) {
mp_raise_NotImplementedError(MP_ERROR_TEXT("only slices with step=1 (aka None) are supported"));
}
return mp_obj_new_str_of_type(type, self_data + slice.start, slice.stop - slice.start);
}
#endif
size_t index_val = mp_get_index(type, self_len, index, false);
// If we have unicode enabled the type will always be bytes, so take the short cut.
if (MICROPY_PY_BUILTINS_STR_UNICODE || type == &mp_type_bytes) {
return MP_OBJ_NEW_SMALL_INT(self_data[index_val]);
} else {
return mp_obj_new_str_via_qstr((char *)&self_data[index_val], 1);
}
} else {
return MP_OBJ_NULL; // op not supported
}
}
STATIC mp_obj_t str_join(mp_obj_t self_in, mp_obj_t arg) {
check_is_str_or_bytes(self_in);
const mp_obj_type_t *self_type = mp_obj_get_type(self_in);
const mp_obj_type_t *ret_type = self_type;
// get separation string
GET_STR_DATA_LEN(self_in, sep_str, sep_len);
// process args
size_t seq_len;
mp_obj_t *seq_items;
if (!mp_obj_is_type(arg, &mp_type_list) && !mp_obj_is_type(arg, &mp_type_tuple)) {
// arg is not a list nor a tuple, try to convert it to a list
// TODO: Try to optimize?
arg = mp_obj_list_make_new(&mp_type_list, 1, 0, &arg);
}
mp_obj_get_array(arg, &seq_len, &seq_items);
// count required length
size_t required_len = 0;
#if MICROPY_PY_BUILTINS_BYTEARRAY
if (self_type == &mp_type_bytearray) {
self_type = &mp_type_bytes;
}
#endif
for (size_t i = 0; i < seq_len; i++) {
const mp_obj_type_t *seq_type = mp_obj_get_type(seq_items[i]);
#if MICROPY_PY_BUILTINS_BYTEARRAY
if (seq_type == &mp_type_bytearray) {
seq_type = &mp_type_bytes;
}
#endif
if (seq_type != self_type) {
mp_raise_TypeError(
MP_ERROR_TEXT("join expects a list of str/bytes objects consistent with self object"));
}
if (i > 0) {
required_len += sep_len;
}
GET_STR_LEN(seq_items[i], l);
required_len += l;
}
// make joined string
vstr_t vstr;
vstr_init_len(&vstr, required_len);
byte *data = (byte *)vstr.buf;
for (size_t i = 0; i < seq_len; i++) {
if (i > 0) {
memcpy(data, sep_str, sep_len);
data += sep_len;
}
GET_STR_DATA_LEN(seq_items[i], s, l);
memcpy(data, s, l);
data += l;
}
// return joined string
return mp_obj_new_str_type_from_vstr(ret_type, &vstr);
}
MP_DEFINE_CONST_FUN_OBJ_2(str_join_obj, str_join);
mp_obj_t mp_obj_str_split(size_t n_args, const mp_obj_t *args) {
const mp_obj_type_t *self_type = mp_obj_get_type(args[0]);
mp_int_t splits = -1;
mp_obj_t sep = mp_const_none;
if (n_args > 1) {
sep = args[1];
if (n_args > 2) {
splits = mp_obj_get_int(args[2]);
}
}
mp_obj_t res = mp_obj_new_list(0, NULL);
GET_STR_DATA_LEN(args[0], s, len);
const byte *top = s + len;
if (sep == mp_const_none) {
// sep not given, so separate on whitespace
// Initial whitespace is not counted as split, so we pre-do it
while (s < top && unichar_isspace(*s)) {
s++;
}
while (s < top && splits != 0) {
const byte *start = s;
while (s < top && !unichar_isspace(*s)) {
s++;
}
mp_obj_list_append(res, mp_obj_new_str_of_type(self_type, start, s - start));
if (s >= top) {
break;
}
while (s < top && unichar_isspace(*s)) {
s++;
}
if (splits > 0) {
splits--;
}
}
if (s < top) {
mp_obj_list_append(res, mp_obj_new_str_of_type(self_type, s, top - s));
}
} else {
// sep given
str_check_arg_type(self_type, sep);
size_t sep_len;
const char *sep_str = mp_obj_str_get_data(sep, &sep_len);
if (sep_len == 0) {
mp_raise_ValueError(MP_ERROR_TEXT("empty separator"));
}
for (;;) {
const byte *start = s;
for (;;) {
if (splits == 0 || s + sep_len > top) {
s = top;
break;
} else if (memcmp(s, sep_str, sep_len) == 0) {
break;
}
s++;
}
mp_obj_list_append(res, mp_obj_new_str_of_type(self_type, start, s - start));
if (s >= top) {
break;
}
s += sep_len;
if (splits > 0) {
splits--;
}
}
}
return res;
}
MP_DEFINE_CONST_FUN_OBJ_VAR_BETWEEN(str_split_obj, 1, 3, mp_obj_str_split);
#if MICROPY_PY_BUILTINS_STR_SPLITLINES
STATIC mp_obj_t str_splitlines(size_t n_args, const mp_obj_t *pos_args, mp_map_t *kw_args) {
enum { ARG_keepends };
static const mp_arg_t allowed_args[] = {
{ MP_QSTR_keepends, MP_ARG_BOOL, {.u_bool = false} },
};
// parse args
mp_arg_val_t args[MP_ARRAY_SIZE(allowed_args)];
mp_arg_parse_all(n_args - 1, pos_args + 1, kw_args, MP_ARRAY_SIZE(allowed_args), allowed_args, args);
const mp_obj_type_t *self_type = mp_obj_get_type(pos_args[0]);
mp_obj_t res = mp_obj_new_list(0, NULL);
GET_STR_DATA_LEN(pos_args[0], s, len);
const byte *top = s + len;
while (s < top) {
const byte *start = s;
size_t match = 0;
while (s < top) {
if (*s == '\n') {
match = 1;
break;
} else if (*s == '\r') {
if (s[1] == '\n') {
match = 2;
} else {
match = 1;
}
break;
}
s++;
}
size_t sub_len = s - start;
if (args[ARG_keepends].u_bool) {
sub_len += match;
}
mp_obj_list_append(res, mp_obj_new_str_of_type(self_type, start, sub_len));
s += match;
}
return res;
}
MP_DEFINE_CONST_FUN_OBJ_KW(str_splitlines_obj, 1, str_splitlines);
#endif
STATIC mp_obj_t str_rsplit(size_t n_args, const mp_obj_t *args) {
if (n_args < 3) {
// If we don't have split limit, it doesn't matter from which side
// we split.
return mp_obj_str_split(n_args, args);
}
const mp_obj_type_t *self_type = mp_obj_get_type(args[0]);
mp_obj_t sep = args[1];
GET_STR_DATA_LEN(args[0], s, len);
mp_int_t splits = mp_obj_get_int(args[2]);
if (splits < 0) {
// Negative limit means no limit, so delegate to split().
return mp_obj_str_split(n_args, args);
}
mp_int_t org_splits = splits;
// Preallocate list to the max expected # of elements, as we
// will fill it from the end.
mp_obj_list_t *res = MP_OBJ_TO_PTR(mp_obj_new_list(splits + 1, NULL));
mp_int_t idx = splits;
if (sep == mp_const_none) {
mp_raise_NotImplementedError(MP_ERROR_TEXT("rsplit(None,n)"));
} else {
size_t sep_len;
const char *sep_str = mp_obj_str_get_data(sep, &sep_len);
if (sep_len == 0) {
mp_raise_ValueError(MP_ERROR_TEXT("empty separator"));
}
const byte *beg = s;
const byte *last = s + len;
for (;;) {
s = last - sep_len;
for (;;) {
if (splits == 0 || s < beg) {
break;
} else if (memcmp(s, sep_str, sep_len) == 0) {
break;
}
s--;
}
if (s < beg || splits == 0) {
res->items[idx] = mp_obj_new_str_of_type(self_type, beg, last - beg);
break;
}
res->items[idx--] = mp_obj_new_str_of_type(self_type, s + sep_len, last - s - sep_len);
last = s;
splits--;
}
if (idx != 0) {
// We split less parts than split limit, now go cleanup surplus
size_t used = org_splits + 1 - idx;
memmove(res->items, &res->items[idx], used * sizeof(mp_obj_t));
mp_seq_clear(res->items, used, res->alloc, sizeof(*res->items));
res->len = used;
}
}
return MP_OBJ_FROM_PTR(res);
}
MP_DEFINE_CONST_FUN_OBJ_VAR_BETWEEN(str_rsplit_obj, 1, 3, str_rsplit);
STATIC mp_obj_t str_finder(size_t n_args, const mp_obj_t *args, int direction, bool is_index) {
const mp_obj_type_t *self_type = mp_obj_get_type(args[0]);
check_is_str_or_bytes(args[0]);
// check argument type
str_check_arg_type(self_type, args[1]);
GET_STR_DATA_LEN(args[0], haystack, haystack_len);
GET_STR_DATA_LEN(args[1], needle, needle_len);
const byte *start = haystack;
const byte *end = haystack + haystack_len;
if (n_args >= 3 && args[2] != mp_const_none) {
start = str_index_to_ptr(self_type, haystack, haystack_len, args[2], true);
}
if (n_args >= 4 && args[3] != mp_const_none) {
end = str_index_to_ptr(self_type, haystack, haystack_len, args[3], true);
}
if (end < start) {
goto out_error;
}
const byte *p = find_subbytes(start, end - start, needle, needle_len, direction);
if (p == NULL) {
out_error:
// not found
if (is_index) {
mp_raise_ValueError(MP_ERROR_TEXT("substring not found"));
} else {
return MP_OBJ_NEW_SMALL_INT(-1);
}
} else {
// found
#if MICROPY_PY_BUILTINS_STR_UNICODE
if (self_type == &mp_type_str) {
return MP_OBJ_NEW_SMALL_INT(utf8_ptr_to_index(haystack, p));
}
#endif
return MP_OBJ_NEW_SMALL_INT(p - haystack);
}
}
STATIC mp_obj_t str_find(size_t n_args, const mp_obj_t *args) {
return str_finder(n_args, args, 1, false);
}
MP_DEFINE_CONST_FUN_OBJ_VAR_BETWEEN(str_find_obj, 2, 4, str_find);
STATIC mp_obj_t str_rfind(size_t n_args, const mp_obj_t *args) {
return str_finder(n_args, args, -1, false);
}
MP_DEFINE_CONST_FUN_OBJ_VAR_BETWEEN(str_rfind_obj, 2, 4, str_rfind);
STATIC mp_obj_t str_index(size_t n_args, const mp_obj_t *args) {
return str_finder(n_args, args, 1, true);
}
MP_DEFINE_CONST_FUN_OBJ_VAR_BETWEEN(str_index_obj, 2, 4, str_index);
STATIC mp_obj_t str_rindex(size_t n_args, const mp_obj_t *args) {
return str_finder(n_args, args, -1, true);
}
MP_DEFINE_CONST_FUN_OBJ_VAR_BETWEEN(str_rindex_obj, 2, 4, str_rindex);
// TODO: (Much) more variety in args
STATIC mp_obj_t str_startswith(size_t n_args, const mp_obj_t *args) {
const mp_obj_type_t *self_type = mp_obj_get_type(args[0]);
GET_STR_DATA_LEN(args[0], str, str_len);
size_t prefix_len;
const char *prefix = mp_obj_str_get_data(args[1], &prefix_len);
const byte *start = str;
if (n_args > 2) {
start = str_index_to_ptr(self_type, str, str_len, args[2], true);
}
if (prefix_len + (start - str) > str_len) {
return mp_const_false;
}
return mp_obj_new_bool(memcmp(start, prefix, prefix_len) == 0);
}
MP_DEFINE_CONST_FUN_OBJ_VAR_BETWEEN(str_startswith_obj, 2, 3, str_startswith);
STATIC mp_obj_t str_endswith(size_t n_args, const mp_obj_t *args) {
GET_STR_DATA_LEN(args[0], str, str_len);
size_t suffix_len;
const char *suffix = mp_obj_str_get_data(args[1], &suffix_len);
if (n_args > 2) {
mp_raise_NotImplementedError(MP_ERROR_TEXT("start/end indices"));
}
if (suffix_len > str_len) {
return mp_const_false;
}
return mp_obj_new_bool(memcmp(str + (str_len - suffix_len), suffix, suffix_len) == 0);
}
MP_DEFINE_CONST_FUN_OBJ_VAR_BETWEEN(str_endswith_obj, 2, 3, str_endswith);
enum { LSTRIP, RSTRIP, STRIP };
STATIC mp_obj_t str_uni_strip(int type, size_t n_args, const mp_obj_t *args) {
check_is_str_or_bytes(args[0]);
const mp_obj_type_t *self_type = mp_obj_get_type(args[0]);
const byte *chars_to_del;
uint chars_to_del_len;
static const byte whitespace[] = " \t\n\r\v\f";
if (n_args == 1) {
chars_to_del = whitespace;
chars_to_del_len = sizeof(whitespace) - 1;
} else {
str_check_arg_type(self_type, args[1]);
GET_STR_DATA_LEN(args[1], s, l);
chars_to_del = s;
chars_to_del_len = l;
}
GET_STR_DATA_LEN(args[0], orig_str, orig_str_len);
size_t first_good_char_pos = 0;
bool first_good_char_pos_set = false;
size_t last_good_char_pos = 0;
size_t i = 0;
int delta = 1;
if (type == RSTRIP) {
i = orig_str_len - 1;
delta = -1;
}
for (size_t len = orig_str_len; len > 0; len--) {
if (find_subbytes(chars_to_del, chars_to_del_len, &orig_str[i], 1, 1) == NULL) {
if (!first_good_char_pos_set) {
first_good_char_pos_set = true;
first_good_char_pos = i;
if (type == LSTRIP) {
last_good_char_pos = orig_str_len - 1;
break;
} else if (type == RSTRIP) {
first_good_char_pos = 0;
last_good_char_pos = i;
break;
}
}
last_good_char_pos = i;
}
i += delta;
}
if (!first_good_char_pos_set) {
// string is all whitespace, return ''
if (self_type == &mp_type_str) {
return MP_OBJ_NEW_QSTR(MP_QSTR_);
} else {
return mp_const_empty_bytes;
}
}
assert(last_good_char_pos >= first_good_char_pos);
// +1 to accommodate the last character
size_t stripped_len = last_good_char_pos - first_good_char_pos + 1;
if (stripped_len == orig_str_len) {
// If nothing was stripped, don't bother to dup original string
// TODO: watch out for this case when we'll get to bytearray.strip()
assert(first_good_char_pos == 0);
return args[0];
}
return mp_obj_new_str_of_type(self_type, orig_str + first_good_char_pos, stripped_len);
}
STATIC mp_obj_t str_strip(size_t n_args, const mp_obj_t *args) {
return str_uni_strip(STRIP, n_args, args);
}
MP_DEFINE_CONST_FUN_OBJ_VAR_BETWEEN(str_strip_obj, 1, 2, str_strip);
STATIC mp_obj_t str_lstrip(size_t n_args, const mp_obj_t *args) {
return str_uni_strip(LSTRIP, n_args, args);
}
MP_DEFINE_CONST_FUN_OBJ_VAR_BETWEEN(str_lstrip_obj, 1, 2, str_lstrip);
STATIC mp_obj_t str_rstrip(size_t n_args, const mp_obj_t *args) {
return str_uni_strip(RSTRIP, n_args, args);
}
MP_DEFINE_CONST_FUN_OBJ_VAR_BETWEEN(str_rstrip_obj, 1, 2, str_rstrip);
#if MICROPY_PY_BUILTINS_STR_CENTER
STATIC mp_obj_t str_center(mp_obj_t str_in, mp_obj_t width_in) {
GET_STR_DATA_LEN(str_in, str, str_len);
mp_uint_t width = mp_obj_get_int(width_in);
if (str_len >= width) {
return str_in;
}
vstr_t vstr;
vstr_init_len(&vstr, width);
memset(vstr.buf, ' ', width);
int left = (width - str_len) / 2;
memcpy(vstr.buf + left, str, str_len);
return mp_obj_new_str_type_from_vstr(mp_obj_get_type(str_in), &vstr);
}
MP_DEFINE_CONST_FUN_OBJ_2(str_center_obj, str_center);
#endif
// Takes an int arg, but only parses unsigned numbers, and only changes
// *num if at least one digit was parsed.
STATIC const char *str_to_int(const char *str, const char *top, int *num) {
if (str < top && '0' <= *str && *str <= '9') {
*num = 0;
do {
*num = *num * 10 + (*str - '0');
str++;
}
while (str < top && '0' <= *str && *str <= '9');
}
return str;
}
STATIC bool isalignment(char ch) {
return ch && strchr("<>=^", ch) != NULL;
}
STATIC bool istype(char ch) {
return ch && strchr("bcdeEfFgGnosxX%", ch) != NULL;
}
STATIC bool arg_looks_integer(mp_obj_t arg) {
return mp_obj_is_bool(arg) || mp_obj_is_int(arg);
}
STATIC bool arg_looks_numeric(mp_obj_t arg) {
return arg_looks_integer(arg)
#if MICROPY_PY_BUILTINS_FLOAT
|| mp_obj_is_float(arg)
#endif
;
}
#if MICROPY_PY_BUILTINS_STR_OP_MODULO
STATIC mp_obj_t arg_as_int(mp_obj_t arg) {
#if MICROPY_PY_BUILTINS_FLOAT
if (mp_obj_is_float(arg)) {
return mp_obj_new_int_from_float(mp_obj_float_get(arg));
}
#endif
return arg;
}
#endif
#if MICROPY_ERROR_REPORTING <= MICROPY_ERROR_REPORTING_TERSE
STATIC NORETURN void terse_str_format_value_error(void) {
mp_raise_ValueError(MP_ERROR_TEXT("bad format string"));
}
#else
// define to nothing to improve coverage
#define terse_str_format_value_error()
#endif
STATIC vstr_t mp_obj_str_format_helper(const char *str, const char *top, int *arg_i, size_t n_args, const mp_obj_t *args, mp_map_t *kwargs) {
vstr_t vstr;
mp_print_t print;
vstr_init_print(&vstr, 16, &print);
for (; str < top; str++) {