summaryrefslogtreecommitdiff
path: root/Objects/bytes_methods.c
blob: 07842f7469101365614139706d0bf2b3f35549e9 (plain)
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
#define PY_SSIZE_T_CLEAN
#include "Python.h"
#include "bytes_methods.h"

PyDoc_STRVAR_shared(_Py_isspace__doc__,
"B.isspace() -> bool\n\
\n\
Return True if all characters in B are whitespace\n\
and there is at least one character in B, False otherwise.");

PyObject*
_Py_bytes_isspace(const char *cptr, Py_ssize_t len)
{
    const unsigned char *p
        = (unsigned char *) cptr;
    const unsigned char *e;

    /* Shortcut for single character strings */
    if (len == 1 && Py_ISSPACE(*p))
        Py_RETURN_TRUE;

    /* Special case for empty strings */
    if (len == 0)
        Py_RETURN_FALSE;

    e = p + len;
    for (; p < e; p++) {
        if (!Py_ISSPACE(*p))
            Py_RETURN_FALSE;
    }
    Py_RETURN_TRUE;
}


PyDoc_STRVAR_shared(_Py_isalpha__doc__,
"B.isalpha() -> bool\n\
\n\
Return True if all characters in B are alphabetic\n\
and there is at least one character in B, False otherwise.");

PyObject*
_Py_bytes_isalpha(const char *cptr, Py_ssize_t len)
{
    const unsigned char *p
        = (unsigned char *) cptr;
    const unsigned char *e;

    /* Shortcut for single character strings */
    if (len == 1 && Py_ISALPHA(*p))
        Py_RETURN_TRUE;

    /* Special case for empty strings */
    if (len == 0)
        Py_RETURN_FALSE;

    e = p + len;
    for (; p < e; p++) {
        if (!Py_ISALPHA(*p))
            Py_RETURN_FALSE;
    }
    Py_RETURN_TRUE;
}


PyDoc_STRVAR_shared(_Py_isalnum__doc__,
"B.isalnum() -> bool\n\
\n\
Return True if all characters in B are alphanumeric\n\
and there is at least one character in B, False otherwise.");

PyObject*
_Py_bytes_isalnum(const char *cptr, Py_ssize_t len)
{
    const unsigned char *p
        = (unsigned char *) cptr;
    const unsigned char *e;

    /* Shortcut for single character strings */
    if (len == 1 && Py_ISALNUM(*p))
        Py_RETURN_TRUE;

    /* Special case for empty strings */
    if (len == 0)
        Py_RETURN_FALSE;

    e = p + len;
    for (; p < e; p++) {
        if (!Py_ISALNUM(*p))
            Py_RETURN_FALSE;
    }
    Py_RETURN_TRUE;
}


PyDoc_STRVAR_shared(_Py_isascii__doc__,
"B.isascii() -> bool\n\
\n\
Return True if B is empty or all characters in B are ASCII,\n\
False otherwise.");

// Optimization is copied from ascii_decode in unicodeobject.c
/* 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

PyObject*
_Py_bytes_isascii(const char *cptr, Py_ssize_t len)
{
    const char *p = cptr;
    const char *end = p + len;
    const char *aligned_end = (const char *) _Py_ALIGN_DOWN(end, SIZEOF_LONG);

    while (p < end) {
        /* Fast path, see in STRINGLIB(utf8_decode) in stringlib/codecs.h
           for an explanation. */
        if (_Py_IS_ALIGNED(p, SIZEOF_LONG)) {
            /* Help allocation */
            const char *_p = p;
            while (_p < aligned_end) {
                unsigned long value = *(unsigned long *) _p;
                if (value & ASCII_CHAR_MASK) {
                    Py_RETURN_FALSE;
                }
                _p += SIZEOF_LONG;
            }
            p = _p;
            if (_p == end)
                break;
        }
        if ((unsigned char)*p & 0x80) {
            Py_RETURN_FALSE;
        }
        p++;
    }
    Py_RETURN_TRUE;
}

#undef ASCII_CHAR_MASK


PyDoc_STRVAR_shared(_Py_isdigit__doc__,
"B.isdigit() -> bool\n\
\n\
Return True if all characters in B are digits\n\
and there is at least one character in B, False otherwise.");

PyObject*
_Py_bytes_isdigit(const char *cptr, Py_ssize_t len)
{
    const unsigned char *p
        = (unsigned char *) cptr;
    const unsigned char *e;

    /* Shortcut for single character strings */
    if (len == 1 && Py_ISDIGIT(*p))
        Py_RETURN_TRUE;

    /* Special case for empty strings */
    if (len == 0)
        Py_RETURN_FALSE;

    e = p + len;
    for (; p < e; p++) {
        if (!Py_ISDIGIT(*p))
            Py_RETURN_FALSE;
    }
    Py_RETURN_TRUE;
}


PyDoc_STRVAR_shared(_Py_islower__doc__,
"B.islower() -> bool\n\
\n\
Return True if all cased characters in B are lowercase and there is\n\
at least one cased character in B, False otherwise.");

PyObject*
_Py_bytes_islower(const char *cptr, Py_ssize_t len)
{
    const unsigned char *p
        = (unsigned char *) cptr;
    const unsigned char *e;
    int cased;

    /* Shortcut for single character strings */
    if (len == 1)
        return PyBool_FromLong(Py_ISLOWER(*p));

    /* Special case for empty strings */
    if (len == 0)
        Py_RETURN_FALSE;

    e = p + len;
    cased = 0;
    for (; p < e; p++) {
        if (Py_ISUPPER(*p))
            Py_RETURN_FALSE;
        else if (!cased && Py_ISLOWER(*p))
            cased = 1;
    }
    return PyBool_FromLong(cased);
}


PyDoc_STRVAR_shared(_Py_isupper__doc__,
"B.isupper() -> bool\n\
\n\
Return True if all cased characters in B are uppercase and there is\n\
at least one cased character in B, False otherwise.");

PyObject*
_Py_bytes_isupper(const char *cptr, Py_ssize_t len)
{
    const unsigned char *p
        = (unsigned char *) cptr;
    const unsigned char *e;
    int cased;

    /* Shortcut for single character strings */
    if (len == 1)
        return PyBool_FromLong(Py_ISUPPER(*p));

    /* Special case for empty strings */
    if (len == 0)
        Py_RETURN_FALSE;

    e = p + len;
    cased = 0;
    for (; p < e; p++) {
        if (Py_ISLOWER(*p))
            Py_RETURN_FALSE;
        else if (!cased && Py_ISUPPER(*p))
            cased = 1;
    }
    return PyBool_FromLong(cased);
}


PyDoc_STRVAR_shared(_Py_istitle__doc__,
"B.istitle() -> bool\n\
\n\
Return True if B is a titlecased string and there is at least one\n\
character in B, i.e. uppercase characters may only follow uncased\n\
characters and lowercase characters only cased ones. Return False\n\
otherwise.");

PyObject*
_Py_bytes_istitle(const char *cptr, Py_ssize_t len)
{
    const unsigned char *p
        = (unsigned char *) cptr;
    const unsigned char *e;
    int cased, previous_is_cased;

    /* Shortcut for single character strings */
    if (len == 1)
        return PyBool_FromLong(Py_ISUPPER(*p));

    /* Special case for empty strings */
    if (len == 0)
        Py_RETURN_FALSE;

    e = p + len;
    cased = 0;
    previous_is_cased = 0;
    for (; p < e; p++) {
        const unsigned char ch = *p;

        if (Py_ISUPPER(ch)) {
            if (previous_is_cased)
                Py_RETURN_FALSE;
            previous_is_cased = 1;
            cased = 1;
        }
        else if (Py_ISLOWER(ch)) {
            if (!previous_is_cased)
                Py_RETURN_FALSE;
            previous_is_cased = 1;
            cased = 1;
        }
        else
            previous_is_cased = 0;
    }
    return PyBool_FromLong(cased);
}


PyDoc_STRVAR_shared(_Py_lower__doc__,
"B.lower() -> copy of B\n\
\n\
Return a copy of B with all ASCII characters converted to lowercase.");

void
_Py_bytes_lower(char *result, const char *cptr, Py_ssize_t len)
{
    Py_ssize_t i;

    for (i = 0; i < len; i++) {
        result[i] = Py_TOLOWER((unsigned char) cptr[i]);
    }
}


PyDoc_STRVAR_shared(_Py_upper__doc__,
"B.upper() -> copy of B\n\
\n\
Return a copy of B with all ASCII characters converted to uppercase.");

void
_Py_bytes_upper(char *result, const char *cptr, Py_ssize_t len)
{
    Py_ssize_t i;

    for (i = 0; i < len; i++) {
        result[i] = Py_TOUPPER((unsigned char) cptr[i]);
    }
}


PyDoc_STRVAR_shared(_Py_title__doc__,
"B.title() -> copy of B\n\
\n\
Return a titlecased version of B, i.e. ASCII words start with uppercase\n\
characters, all remaining cased characters have lowercase.");

void
_Py_bytes_title(char *result, const char *s, Py_ssize_t len)
{
    Py_ssize_t i;
    int previous_is_cased = 0;

    for (i = 0; i < len; i++) {
        int c = Py_CHARMASK(*s++);
        if (Py_ISLOWER(c)) {
            if (!previous_is_cased)
                c = Py_TOUPPER(c);
            previous_is_cased = 1;
        } else if (Py_ISUPPER(c)) {
            if (previous_is_cased)
                c = Py_TOLOWER(c);
            previous_is_cased = 1;
        } else
            previous_is_cased = 0;
        *result++ = c;
    }
}


PyDoc_STRVAR_shared(_Py_capitalize__doc__,
"B.capitalize() -> copy of B\n\
\n\
Return a copy of B with only its first character capitalized (ASCII)\n\
and the rest lower-cased.");

void
_Py_bytes_capitalize(char *result, const char *s, Py_ssize_t len)
{
    Py_ssize_t i;

    if (0 < len) {
        int c = Py_CHARMASK(*s++);
        if (Py_ISLOWER(c))
            *result = Py_TOUPPER(c);
        else
            *result = c;
        result++;
    }
    for (i = 1; i < len; i++) {
        int c = Py_CHARMASK(*s++);
        if (Py_ISUPPER(c))
            *result = Py_TOLOWER(c);
        else
            *result = c;
        result++;
    }
}


PyDoc_STRVAR_shared(_Py_swapcase__doc__,
"B.swapcase() -> copy of B\n\
\n\
Return a copy of B with uppercase ASCII characters converted\n\
to lowercase ASCII and vice versa.");

void
_Py_bytes_swapcase(char *result, const char *s, Py_ssize_t len)
{
    Py_ssize_t i;

    for (i = 0; i < len; i++) {
        int c = Py_CHARMASK(*s++);
        if (Py_ISLOWER(c)) {
            *result = Py_TOUPPER(c);
        }
        else if (Py_ISUPPER(c)) {
            *result = Py_TOLOWER(c);
        }
        else
            *result = c;
        result++;
    }
}


PyDoc_STRVAR_shared(_Py_maketrans__doc__,
"B.maketrans(frm, to) -> translation table\n\
\n\
Return a translation table (a bytes object of length 256) suitable\n\
for use in the bytes or bytearray translate method where each byte\n\
in frm is mapped to the byte at the same position in to.\n\
The bytes objects frm and to must be of the same length.");

PyObject *
_Py_bytes_maketrans(Py_buffer *frm, Py_buffer *to)
{
    PyObject *res = NULL;
    Py_ssize_t i;
    char *p;

    if (frm->len != to->len) {
        PyErr_Format(PyExc_ValueError,
                     "maketrans arguments must have same length");
        return NULL;
    }
    res = PyBytes_FromStringAndSize(NULL, 256);
    if (!res)
        return NULL;
    p = PyBytes_AS_STRING(res);
    for (i = 0; i < 256; i++)
        p[i] = (char) i;
    for (i = 0; i < frm->len; i++) {
        p[((unsigned char *)frm->buf)[i]] = ((char *)to->buf)[i];
    }

    return res;
}

#define FASTSEARCH fastsearch
#define STRINGLIB(F) stringlib_##F
#define STRINGLIB_CHAR char
#define STRINGLIB_SIZEOF_CHAR 1

#include "stringlib/fastsearch.h"
#include "stringlib/count.h"
#include "stringlib/find.h"

/*
Wraps stringlib_parse_args_finds() and additionally checks the first
argument type.

In case the first argument is a bytes-like object, sets it to subobj,
and doesn't touch the byte parameter.
In case it is an integer in range(0, 256), writes the integer value
to byte, and sets subobj to NULL.

The other parameters are similar to those of
stringlib_parse_args_finds().
*/

Py_LOCAL_INLINE(int)
parse_args_finds_byte(const char *function_name, PyObject *args,
                      PyObject **subobj, char *byte,
                      Py_ssize_t *start, Py_ssize_t *end)
{
    PyObject *tmp_subobj;
    Py_ssize_t ival;

    if(!stringlib_parse_args_finds(function_name, args, &tmp_subobj,
                                   start, end))
        return 0;

    if (PyObject_CheckBuffer(tmp_subobj)) {
        *subobj = tmp_subobj;
        return 1;
    }

    if (!PyIndex_Check(tmp_subobj)) {
        PyErr_Format(PyExc_TypeError,
                     "argument should be integer or bytes-like object, "
                     "not '%.200s'",
                     Py_TYPE(tmp_subobj)->tp_name);
        return 0;
    }

    ival = PyNumber_AsSsize_t(tmp_subobj, NULL);
    if (ival == -1 && PyErr_Occurred()) {
        return 0;
    }
    if (ival < 0 || ival > 255) {
        PyErr_SetString(PyExc_ValueError, "byte must be in range(0, 256)");
        return 0;
    }

    *subobj = NULL;
    *byte = (char)ival;
    return 1;
}

/* helper macro to fixup start/end slice values */
#define ADJUST_INDICES(start, end, len)         \
    if (end > len)                          \
        end = len;                          \
    else if (end < 0) {                     \
        end += len;                         \
        if (end < 0)                        \
        end = 0;                        \
    }                                       \
    if (start < 0) {                        \
        start += len;                       \
        if (start < 0)                      \
        start = 0;                      \
    }

Py_LOCAL_INLINE(Py_ssize_t)
find_internal(const char *str, Py_ssize_t len,
              const char *function_name, PyObject *args, int dir)
{
    PyObject *subobj;
    char byte;
    Py_buffer subbuf;
    const char *sub;
    Py_ssize_t sub_len;
    Py_ssize_t start = 0, end = PY_SSIZE_T_MAX;
    Py_ssize_t res;

    if (!parse_args_finds_byte(function_name, args,
                               &subobj, &byte, &start, &end))
        return -2;

    if (subobj) {
        if (PyObject_GetBuffer(subobj, &subbuf, PyBUF_SIMPLE) != 0)
            return -2;

        sub = subbuf.buf;
        sub_len = subbuf.len;
    }
    else {
        sub = &byte;
        sub_len = 1;
    }

    ADJUST_INDICES(start, end, len);
    if (end - start < sub_len)
        res = -1;
    else if (sub_len == 1) {
        if (dir > 0)
            res = stringlib_find_char(
                str + start, end - start,
                *sub);
        else
            res = stringlib_rfind_char(
                str + start, end - start,
                *sub);
        if (res >= 0)
            res += start;
    }
    else {
        if (dir > 0)
            res = stringlib_find_slice(
                str, len,
                sub, sub_len, start, end);
        else
            res = stringlib_rfind_slice(
                str, len,
                sub, sub_len, start, end);
    }

    if (subobj)
        PyBuffer_Release(&subbuf);

    return res;
}

PyDoc_STRVAR_shared(_Py_find__doc__,
"B.find(sub[, start[, end]]) -> int\n\
\n\
Return the lowest index in B where subsection sub is found,\n\
such that sub is contained within B[start,end].  Optional\n\
arguments start and end are interpreted as in slice notation.\n\
\n\
Return -1 on failure.");

PyObject *
_Py_bytes_find(const char *str, Py_ssize_t len, PyObject *args)
{
    Py_ssize_t result = find_internal(str, len, "find", args, +1);
    if (result == -2)
        return NULL;
    return PyLong_FromSsize_t(result);
}

PyDoc_STRVAR_shared(_Py_index__doc__,
"B.index(sub[, start[, end]]) -> int\n\
\n\
Return the lowest index in B where subsection sub is found,\n\
such that sub is contained within B[start,end].  Optional\n\
arguments start and end are interpreted as in slice notation.\n\
\n\
Raises ValueError when the subsection is not found.");

PyObject *
_Py_bytes_index(const char *str, Py_ssize_t len, PyObject *args)
{
    Py_ssize_t result = find_internal(str, len, "index", args, +1);
    if (result == -2)
        return NULL;
    if (result == -1) {
        PyErr_SetString(PyExc_ValueError,
                        "subsection not found");
        return NULL;
    }
    return PyLong_FromSsize_t(result);
}

PyDoc_STRVAR_shared(_Py_rfind__doc__,
"B.rfind(sub[, start[, end]]) -> int\n\
\n\
Return the highest index in B where subsection sub is found,\n\
such that sub is contained within B[start,end].  Optional\n\
arguments start and end are interpreted as in slice notation.\n\
\n\
Return -1 on failure.");

PyObject *
_Py_bytes_rfind(const char *str, Py_ssize_t len, PyObject *args)
{
    Py_ssize_t result = find_internal(str, len, "rfind", args, -1);
    if (result == -2)
        return NULL;
    return PyLong_FromSsize_t(result);
}

PyDoc_STRVAR_shared(_Py_rindex__doc__,
"B.rindex(sub[, start[, end]]) -> int\n\
\n\
Return the highest index in B where subsection sub is found,\n\
such that sub is contained within B[start,end].  Optional\n\
arguments start and end are interpreted as in slice notation.\n\
\n\
Raise ValueError when the subsection is not found.");

PyObject *
_Py_bytes_rindex(const char *str, Py_ssize_t len, PyObject *args)
{
    Py_ssize_t result = find_internal(str, len, "rindex", args, -1);
    if (result == -2)
        return NULL;
    if (result == -1) {
        PyErr_SetString(PyExc_ValueError,
                        "subsection not found");
        return NULL;
    }
    return PyLong_FromSsize_t(result);
}

PyDoc_STRVAR_shared(_Py_count__doc__,
"B.count(sub[, start[, end]]) -> int\n\
\n\
Return the number of non-overlapping occurrences of subsection sub in\n\
bytes B[start:end].  Optional arguments start and end are interpreted\n\
as in slice notation.");

PyObject *
_Py_bytes_count(const char *str, Py_ssize_t len, PyObject *args)
{
    PyObject *sub_obj;
    const char *sub;
    Py_ssize_t sub_len;
    char byte;
    Py_ssize_t start = 0, end = PY_SSIZE_T_MAX;

    Py_buffer vsub;
    PyObject *count_obj;

    if (!parse_args_finds_byte("count", args,
                               &sub_obj, &byte, &start, &end))
        return NULL;

    if (sub_obj) {
        if (PyObject_GetBuffer(sub_obj, &vsub, PyBUF_SIMPLE) != 0)
            return NULL;

        sub = vsub.buf;
        sub_len = vsub.len;
    }
    else {
        sub = &byte;
        sub_len = 1;
    }

    ADJUST_INDICES(start, end, len);

    count_obj = PyLong_FromSsize_t(
        stringlib_count(str + start, end - start, sub, sub_len, PY_SSIZE_T_MAX)
        );

    if (sub_obj)
        PyBuffer_Release(&vsub);

    return count_obj;
}

int
_Py_bytes_contains(const char *str, Py_ssize_t len, PyObject *arg)
{
    Py_ssize_t ival = PyNumber_AsSsize_t(arg, NULL);
    if (ival == -1 && PyErr_Occurred()) {
        Py_buffer varg;
        Py_ssize_t pos;
        PyErr_Clear();
        if (PyObject_GetBuffer(arg, &varg, PyBUF_SIMPLE) != 0)
            return -1;
        pos = stringlib_find(str, len,
                             varg.buf, varg.len, 0);
        PyBuffer_Release(&varg);
        return pos >= 0;
    }
    if (ival < 0 || ival >= 256) {
        PyErr_SetString(PyExc_ValueError, "byte must be in range(0, 256)");
        return -1;
    }

    return memchr(str, (int) ival, len) != NULL;
}


/* Matches the end (direction >= 0) or start (direction < 0) of the buffer
 * against substr, using the start and end arguments. Returns
 * -1 on error, 0 if not found and 1 if found.
 */
static int
tailmatch(const char *str, Py_ssize_t len, PyObject *substr,
          Py_ssize_t start, Py_ssize_t end, int direction)
{
    Py_buffer sub_view = {NULL, NULL};
    const char *sub;
    Py_ssize_t slen;

    if (PyBytes_Check(substr)) {
        sub = PyBytes_AS_STRING(substr);
        slen = PyBytes_GET_SIZE(substr);
    }
    else {
        if (PyObject_GetBuffer(substr, &sub_view, PyBUF_SIMPLE) != 0)
            return -1;
        sub = sub_view.buf;
        slen = sub_view.len;
    }

    ADJUST_INDICES(start, end, len);

    if (direction < 0) {
        /* startswith */
        if (start + slen > len)
            goto notfound;
    } else {
        /* endswith */
        if (end - start < slen || start > len)
            goto notfound;

        if (end - slen > start)
            start = end - slen;
    }
    if (end - start < slen)
        goto notfound;
    if (memcmp(str + start, sub, slen) != 0)
        goto notfound;

    PyBuffer_Release(&sub_view);
    return 1;

notfound:
    PyBuffer_Release(&sub_view);
    return 0;
}

static PyObject *
_Py_bytes_tailmatch(const char *str, Py_ssize_t len,
                    const char *function_name, PyObject *args,
                    int direction)
{
    Py_ssize_t start = 0;
    Py_ssize_t end = PY_SSIZE_T_MAX;
    PyObject *subobj;
    int result;

    if (!stringlib_parse_args_finds(function_name, args, &subobj, &start, &end))
        return NULL;
    if (PyTuple_Check(subobj)) {
        Py_ssize_t i;
        for (i = 0; i < PyTuple_GET_SIZE(subobj); i++) {
            result = tailmatch(str, len, PyTuple_GET_ITEM(subobj, i),
                               start, end, direction);
            if (result == -1)
                return NULL;
            else if (result) {
                Py_RETURN_TRUE;
            }
        }
        Py_RETURN_FALSE;
    }
    result = tailmatch(str, len, subobj, start, end, direction);
    if (result == -1) {
        if (PyErr_ExceptionMatches(PyExc_TypeError))
            PyErr_Format(PyExc_TypeError,
                         "%s first arg must be bytes or a tuple of bytes, "
                         "not %s",
                         function_name, Py_TYPE(subobj)->tp_name);
        return NULL;
    }
    else
        return PyBool_FromLong(result);
}

PyDoc_STRVAR_shared(_Py_startswith__doc__,
"B.startswith(prefix[, start[, end]]) -> bool\n\
\n\
Return True if B starts with the specified prefix, False otherwise.\n\
With optional start, test B beginning at that position.\n\
With optional end, stop comparing B at that position.\n\
prefix can also be a tuple of bytes to try.");

PyObject *
_Py_bytes_startswith(const char *str, Py_ssize_t len, PyObject *args)
{
    return _Py_bytes_tailmatch(str, len, "startswith", args, -1);
}

PyDoc_STRVAR_shared(_Py_endswith__doc__,
"B.endswith(suffix[, start[, end]]) -> bool\n\
\n\
Return True if B ends with the specified suffix, False otherwise.\n\
With optional start, test B beginning at that position.\n\
With optional end, stop comparing B at that position.\n\
suffix can also be a tuple of bytes to try.");

PyObject *
_Py_bytes_endswith(const char *str, Py_ssize_t len, PyObject *args)
{
    return _Py_bytes_tailmatch(str, len, "endswith", args, +1);
}

PyDoc_STRVAR_shared(_Py_expandtabs__doc__,
"B.expandtabs(tabsize=8) -> copy of B\n\
\n\
Return a copy of B where all tab characters are expanded using spaces.\n\
If tabsize is not given, a tab size of 8 characters is assumed.");

PyDoc_STRVAR_shared(_Py_ljust__doc__,
"B.ljust(width[, fillchar]) -> copy of B\n"
"\n"
"Return B left justified in a string of length width. Padding is\n"
"done using the specified fill character (default is a space).");

PyDoc_STRVAR_shared(_Py_rjust__doc__,
"B.rjust(width[, fillchar]) -> copy of B\n"
"\n"
"Return B right justified in a string of length width. Padding is\n"
"done using the specified fill character (default is a space)");

PyDoc_STRVAR_shared(_Py_center__doc__,
"B.center(width[, fillchar]) -> copy of B\n"
"\n"
"Return B centered in a string of length width.  Padding is\n"
"done using the specified fill character (default is a space).");

PyDoc_STRVAR_shared(_Py_zfill__doc__,
"B.zfill(width) -> copy of B\n"
"\n"
"Pad a numeric string B with zeros on the left, to fill a field\n"
"of the specified width.  B is never truncated.");