/src/cpython/Objects/bytes_methods.c

Source
#include "Python.h"
#include "pycore_abstract.h"   // _PyIndex_Check()
#include "pycore_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
        = (const 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
        = (const 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
        = (const 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_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
        = (const 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
        = (const 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
        = (const 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
        = (const unsigned char *) cptr;
    const unsigned char *e;
    int cased, previous_is_cased;

    if (len == 1) {
        if (Py_ISUPPER(*p)) {
            Py_RETURN_TRUE;
        }
        Py_RETURN_FALSE;
    }

    /* 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)
{
    if (len > 0) {
        *result = Py_TOUPPER(*s);
        _Py_bytes_lower(result + 1, s + 1, len - 1);
    }
}


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)
{
    if (frm->len != to->len) {
        PyErr_Format(PyExc_ValueError,
                     "maketrans arguments must have same length");
        return NULL;
    }
    PyBytesWriter *writer = PyBytesWriter_Create(256);
    if (!writer) {
        return NULL;
    }
    char *p = PyBytesWriter_GetData(writer);
    Py_ssize_t i;
    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 PyBytesWriter_Finish(writer);
}

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

#include "stringlib/fastsearch.h"
#include "stringlib/count.h"
#include "stringlib/find.h"
#include "stringlib/find_max_char.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 **subobj, char *byte)
{
    if (PyObject_CheckBuffer(*subobj)) {
        return 1;
    }

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

    Py_ssize_t ival = PyNumber_AsSsize_t(*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) \
    do {                                \
        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;              \
            }                           \
        }                               \
    } while (0)

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

    if (!parse_args_finds_byte(function_name, &subobj, &byte)) {
        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;
}

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

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

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

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

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

    Py_buffer vsub;
    PyObject *count_obj;

    if (!parse_args_finds_byte("count", &sub_obj, &byte)) {
        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 > len - slen)
            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 *subobj,
                    Py_ssize_t start, Py_ssize_t end,
                    int direction)
{
    if (PyTuple_Check(subobj)) {
        Py_ssize_t i;
        for (i = 0; i < PyTuple_GET_SIZE(subobj); i++) {
            PyObject *item = PyTuple_GET_ITEM(subobj, i);
            int result = tailmatch(str, len, item, start, end, direction);
            if (result < 0) {
                return NULL;
            }
            else if (result) {
                Py_RETURN_TRUE;
            }
        }
        Py_RETURN_FALSE;
    }
    int 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;
    }
    return PyBool_FromLong(result);
}

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

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

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.");

PyObject*
_Py_bytes_isascii(const char *cptr, Py_ssize_t len)
{
    const char *p = cptr;
    const char *end = p + len;
    Py_ssize_t max_char = stringlib_find_max_char(cptr, end);
    if (max_char > 127) {
        Py_RETURN_FALSE;
    }
    Py_RETURN_TRUE;
}

Coverage Report

Created: 2026-01-10 06:41

Line	Count	Source
1		#include "Python.h"
2		#include "pycore_abstract.h" // _PyIndex_Check()
3		#include "pycore_bytes_methods.h"
4
5		PyDoc_STRVAR_shared(_Py_isspace__doc__,
6		"B.isspace() -> bool\n\
7		\n\
8		Return True if all characters in B are whitespace\n\
9		and there is at least one character in B, False otherwise.");
10
11		PyObject*
12		_Py_bytes_isspace(const char *cptr, Py_ssize_t len)
13	0	{
14	0	const unsigned char *p
15	0	= (const unsigned char *) cptr;
16	0	const unsigned char *e;
17
18		/* Shortcut for single character strings */
19	0	if (len == 1 && Py_ISSPACE(*p))
20	0	Py_RETURN_TRUE;
21
22		/* Special case for empty strings */
23	0	if (len == 0)
24	0	Py_RETURN_FALSE;
25
26	0	e = p + len;
27	0	for (; p < e; p++) {
28	0	if (!Py_ISSPACE(*p))
29	0	Py_RETURN_FALSE;
30	0	}
31	0	Py_RETURN_TRUE;
32	0	}
33
34
35		PyDoc_STRVAR_shared(_Py_isalpha__doc__,
36		"B.isalpha() -> bool\n\
37		\n\
38		Return True if all characters in B are alphabetic\n\
39		and there is at least one character in B, False otherwise.");
40
41		PyObject*
42		_Py_bytes_isalpha(const char *cptr, Py_ssize_t len)
43	0	{
44	0	const unsigned char *p
45	0	= (const unsigned char *) cptr;
46	0	const unsigned char *e;
47
48		/* Shortcut for single character strings */
49	0	if (len == 1 && Py_ISALPHA(*p))
50	0	Py_RETURN_TRUE;
51
52		/* Special case for empty strings */
53	0	if (len == 0)
54	0	Py_RETURN_FALSE;
55
56	0	e = p + len;
57	0	for (; p < e; p++) {
58	0	if (!Py_ISALPHA(*p))
59	0	Py_RETURN_FALSE;
60	0	}
61	0	Py_RETURN_TRUE;
62	0	}
63
64
65		PyDoc_STRVAR_shared(_Py_isalnum__doc__,
66		"B.isalnum() -> bool\n\
67		\n\
68		Return True if all characters in B are alphanumeric\n\
69		and there is at least one character in B, False otherwise.");
70
71		PyObject*
72		_Py_bytes_isalnum(const char *cptr, Py_ssize_t len)
73	0	{
74	0	const unsigned char *p
75	0	= (const unsigned char *) cptr;
76	0	const unsigned char *e;
77
78		/* Shortcut for single character strings */
79	0	if (len == 1 && Py_ISALNUM(*p))
80	0	Py_RETURN_TRUE;
81
82		/* Special case for empty strings */
83	0	if (len == 0)
84	0	Py_RETURN_FALSE;
85
86	0	e = p + len;
87	0	for (; p < e; p++) {
88	0	if (!Py_ISALNUM(*p))
89	0	Py_RETURN_FALSE;
90	0	}
91	0	Py_RETURN_TRUE;
92	0	}
93
94
95		PyDoc_STRVAR_shared(_Py_isdigit__doc__,
96		"B.isdigit() -> bool\n\
97		\n\
98		Return True if all characters in B are digits\n\
99		and there is at least one character in B, False otherwise.");
100
101		PyObject*
102		_Py_bytes_isdigit(const char *cptr, Py_ssize_t len)
103	0	{
104	0	const unsigned char *p
105	0	= (const unsigned char *) cptr;
106	0	const unsigned char *e;
107
108		/* Shortcut for single character strings */
109	0	if (len == 1 && Py_ISDIGIT(*p))
110	0	Py_RETURN_TRUE;
111
112		/* Special case for empty strings */
113	0	if (len == 0)
114	0	Py_RETURN_FALSE;
115
116	0	e = p + len;
117	0	for (; p < e; p++) {
118	0	if (!Py_ISDIGIT(*p))
119	0	Py_RETURN_FALSE;
120	0	}
121	0	Py_RETURN_TRUE;
122	0	}
123
124
125		PyDoc_STRVAR_shared(_Py_islower__doc__,
126		"B.islower() -> bool\n\
127		\n\
128		Return True if all cased characters in B are lowercase and there is\n\
129		at least one cased character in B, False otherwise.");
130
131		PyObject*
132		_Py_bytes_islower(const char *cptr, Py_ssize_t len)
133	0	{
134	0	const unsigned char *p
135	0	= (const unsigned char *) cptr;
136	0	const unsigned char *e;
137	0	int cased;
138
139		/* Shortcut for single character strings */
140	0	if (len == 1)
141	0	return PyBool_FromLong(Py_ISLOWER(*p));
142
143		/* Special case for empty strings */
144	0	if (len == 0)
145	0	Py_RETURN_FALSE;
146
147	0	e = p + len;
148	0	cased = 0;
149	0	for (; p < e; p++) {
150	0	if (Py_ISUPPER(*p))
151	0	Py_RETURN_FALSE;
152	0	else if (!cased && Py_ISLOWER(*p))
153	0	cased = 1;
154	0	}
155	0	return PyBool_FromLong(cased);
156	0	}
157
158
159		PyDoc_STRVAR_shared(_Py_isupper__doc__,
160		"B.isupper() -> bool\n\
161		\n\
162		Return True if all cased characters in B are uppercase and there is\n\
163		at least one cased character in B, False otherwise.");
164
165		PyObject*
166		_Py_bytes_isupper(const char *cptr, Py_ssize_t len)
167	0	{
168	0	const unsigned char *p
169	0	= (const unsigned char *) cptr;
170	0	const unsigned char *e;
171	0	int cased;
172
173		/* Shortcut for single character strings */
174	0	if (len == 1)
175	0	return PyBool_FromLong(Py_ISUPPER(*p));
176
177		/* Special case for empty strings */
178	0	if (len == 0)
179	0	Py_RETURN_FALSE;
180
181	0	e = p + len;
182	0	cased = 0;
183	0	for (; p < e; p++) {
184	0	if (Py_ISLOWER(*p))
185	0	Py_RETURN_FALSE;
186	0	else if (!cased && Py_ISUPPER(*p))
187	0	cased = 1;
188	0	}
189	0	return PyBool_FromLong(cased);
190	0	}
191
192
193		PyDoc_STRVAR_shared(_Py_istitle__doc__,
194		"B.istitle() -> bool\n\
195		\n\
196		Return True if B is a titlecased string and there is at least one\n\
197		character in B, i.e. uppercase characters may only follow uncased\n\
198		characters and lowercase characters only cased ones. Return False\n\
199		otherwise.");
200
201		PyObject*
202		_Py_bytes_istitle(const char *cptr, Py_ssize_t len)
203	0	{
204	0	const unsigned char *p
205	0	= (const unsigned char *) cptr;
206	0	const unsigned char *e;
207	0	int cased, previous_is_cased;
208
209	0	if (len == 1) {
210	0	if (Py_ISUPPER(*p)) {
211	0	Py_RETURN_TRUE;
212	0	}
213	0	Py_RETURN_FALSE;
214	0	}
215
216		/* Special case for empty strings */
217	0	if (len == 0)
218	0	Py_RETURN_FALSE;
219
220	0	e = p + len;
221	0	cased = 0;
222	0	previous_is_cased = 0;
223	0	for (; p < e; p++) {
224	0	const unsigned char ch = *p;
225
226	0	if (Py_ISUPPER(ch)) {
227	0	if (previous_is_cased)
228	0	Py_RETURN_FALSE;
229	0	previous_is_cased = 1;
230	0	cased = 1;
231	0	}
232	0	else if (Py_ISLOWER(ch)) {
233	0	if (!previous_is_cased)
234	0	Py_RETURN_FALSE;
235	0	previous_is_cased = 1;
236	0	cased = 1;
237	0	}
238	0	else
239	0	previous_is_cased = 0;
240	0	}
241	0	return PyBool_FromLong(cased);
242	0	}
243
244
245		PyDoc_STRVAR_shared(_Py_lower__doc__,
246		"B.lower() -> copy of B\n\
247		\n\
248		Return a copy of B with all ASCII characters converted to lowercase.");
249
250		void
251		_Py_bytes_lower(char result, const char cptr, Py_ssize_t len)
252	79.0M	{
253	79.0M	Py_ssize_t i;
254
255	967M	for (i = 0; i < len; i++) {
256	888M	result[i] = Py_TOLOWER((unsigned char) cptr[i]);
257	888M	}
258	79.0M	}
259
260
261		PyDoc_STRVAR_shared(_Py_upper__doc__,
262		"B.upper() -> copy of B\n\
263		\n\
264		Return a copy of B with all ASCII characters converted to uppercase.");
265
266		void
267		_Py_bytes_upper(char result, const char cptr, Py_ssize_t len)
268	20.3k	{
269	20.3k	Py_ssize_t i;
270
271	415k	for (i = 0; i < len; i++) {
272	394k	result[i] = Py_TOUPPER((unsigned char) cptr[i]);
273	394k	}
274	20.3k	}
275
276
277		PyDoc_STRVAR_shared(_Py_title__doc__,
278		"B.title() -> copy of B\n\
279		\n\
280		Return a titlecased version of B, i.e. ASCII words start with uppercase\n\
281		characters, all remaining cased characters have lowercase.");
282
283		void
284		_Py_bytes_title(char result, const char s, Py_ssize_t len)
285	0	{
286	0	Py_ssize_t i;
287	0	int previous_is_cased = 0;
288
289	0	for (i = 0; i < len; i++) {
290	0	int c = Py_CHARMASK(*s++);
291	0	if (Py_ISLOWER(c)) {
292	0	if (!previous_is_cased)
293	0	c = Py_TOUPPER(c);
294	0	previous_is_cased = 1;
295	0	} else if (Py_ISUPPER(c)) {
296	0	if (previous_is_cased)
297	0	c = Py_TOLOWER(c);
298	0	previous_is_cased = 1;
299	0	} else
300	0	previous_is_cased = 0;
301	0	*result++ = c;
302	0	}
303	0	}
304
305
306		PyDoc_STRVAR_shared(_Py_capitalize__doc__,
307		"B.capitalize() -> copy of B\n\
308		\n\
309		Return a copy of B with only its first character capitalized (ASCII)\n\
310		and the rest lower-cased.");
311
312		void
313		_Py_bytes_capitalize(char result, const char s, Py_ssize_t len)
314	0	{
315	0	if (len > 0) {
316	0	result = Py_TOUPPER(s);
317	0	_Py_bytes_lower(result + 1, s + 1, len - 1);
318	0	}
319	0	}
320
321
322		PyDoc_STRVAR_shared(_Py_swapcase__doc__,
323		"B.swapcase() -> copy of B\n\
324		\n\
325		Return a copy of B with uppercase ASCII characters converted\n\
326		to lowercase ASCII and vice versa.");
327
328		void
329		_Py_bytes_swapcase(char result, const char s, Py_ssize_t len)
330	0	{
331	0	Py_ssize_t i;
332
333	0	for (i = 0; i < len; i++) {
334	0	int c = Py_CHARMASK(*s++);
335	0	if (Py_ISLOWER(c)) {
336	0	*result = Py_TOUPPER(c);
337	0	}
338	0	else if (Py_ISUPPER(c)) {
339	0	*result = Py_TOLOWER(c);
340	0	}
341	0	else
342	0	*result = c;
343	0	result++;
344	0	}
345	0	}
346
347
348		PyDoc_STRVAR_shared(_Py_maketrans__doc__,
349		"B.maketrans(frm, to) -> translation table\n\
350		\n\
351		Return a translation table (a bytes object of length 256) suitable\n\
352		for use in the bytes or bytearray translate method where each byte\n\
353		in frm is mapped to the byte at the same position in to.\n\
354		The bytes objects frm and to must be of the same length.");
355
356		PyObject *
357		_Py_bytes_maketrans(Py_buffer frm, Py_buffer to)
358	28	{
359	28	if (frm->len != to->len) {
360	0	PyErr_Format(PyExc_ValueError,
361	0	"maketrans arguments must have same length");
362	0	return NULL;
363	0	}
364	28	PyBytesWriter *writer = PyBytesWriter_Create(256);
365	28	if (!writer) {
366	0	return NULL;
367	0	}
368	28	char *p = PyBytesWriter_GetData(writer);
369	28	Py_ssize_t i;
370	7.19k	for (i = 0; i < 256; i++)
371	7.16k	p[i] = (char) i;
372	1.28k	for (i = 0; i < frm->len; i++) {
373	1.25k	p[((unsigned char )frm->buf)[i]] = ((char )to->buf)[i];
374	1.25k	}
375
376	28	return PyBytesWriter_Finish(writer);
377	28	}
378
379	6.50M	#define FASTSEARCH fastsearch
380	6.51M	#define STRINGLIB(F) stringlib_##F
381	0	#define STRINGLIB_CHAR char
382	0	#define STRINGLIB_SIZEOF_CHAR 1
383	5.65M	#define STRINGLIB_FAST_MEMCHR memchr
384
385		#include "stringlib/fastsearch.h"
386		#include "stringlib/count.h"
387		#include "stringlib/find.h"
388		#include "stringlib/find_max_char.h"
389
390		/*
391		Wraps stringlib_parse_args_finds() and additionally checks the first
392		argument type.
393
394		In case the first argument is a bytes-like object, sets it to subobj,
395		and doesn't touch the byte parameter.
396		In case it is an integer in range(0, 256), writes the integer value
397		to byte, and sets subobj to NULL.
398
399		The other parameters are similar to those of
400		stringlib_parse_args_finds().
401		*/
402
403		Py_LOCAL_INLINE(int)
404		parse_args_finds_byte(const char function_name, PyObject subobj, char byte)
405	24.3M	{
406	24.3M	if (PyObject_CheckBuffer(*subobj)) {
407	23.3M	return 1;
408	23.3M	}
409
410	952k	if (!_PyIndex_Check(*subobj)) {
411	0	PyErr_Format(PyExc_TypeError,
412	0	"argument should be integer or bytes-like object, "
413	0	"not '%.200s'",
414	0	Py_TYPE(*subobj)->tp_name);
415	0	return 0;
416	0	}
417
418	952k	Py_ssize_t ival = PyNumber_AsSsize_t(*subobj, NULL);
419	952k	if (ival == -1 && PyErr_Occurred()) {
420	0	return 0;
421	0	}
422	952k	if (ival < 0 \|\| ival > 255) {
423	0	PyErr_SetString(PyExc_ValueError, "byte must be in range(0, 256)");
424	0	return 0;
425	0	}
426
427	952k	*subobj = NULL;
428	952k	*byte = (char)ival;
429	952k	return 1;
430	952k	}
431
432		/* helper macro to fixup start/end slice values */
433		#define ADJUST_INDICES(start, end, len) \
434	24.6M	do { \
435	24.6M	if (end > len) { \
436	24.6M	end = len; \
437	24.6M	} \
438	24.6M	else if (end < 0) { \
439	0	end += len; \
440	0	if (end < 0) { \
441	0	end = 0; \
442	0	} \
443	0	} \
444	24.6M	if (start < 0) { \
445	0	start += len; \
446	0	if (start < 0) { \
447	0	start = 0; \
448	0	} \
449	0	} \
450	24.6M	} while (0)
451
452		Py_LOCAL_INLINE(Py_ssize_t)
453		find_internal(const char *str, Py_ssize_t len,
454		const char function_name, PyObject subobj,
455		Py_ssize_t start, Py_ssize_t end,
456		int dir)
457	17.8M	{
458	17.8M	char byte;
459	17.8M	Py_buffer subbuf;
460	17.8M	const char *sub;
461	17.8M	Py_ssize_t sub_len;
462	17.8M	Py_ssize_t res;
463
464	17.8M	if (!parse_args_finds_byte(function_name, &subobj, &byte)) {
465	0	return -2;
466	0	}
467
468	17.8M	if (subobj) {
469	16.8M	if (PyObject_GetBuffer(subobj, &subbuf, PyBUF_SIMPLE) != 0)
470	0	return -2;
471
472	16.8M	sub = subbuf.buf;
473	16.8M	sub_len = subbuf.len;
474	16.8M	}
475	952k	else {
476	952k	sub = &byte;
477	952k	sub_len = 1;
478	952k	}
479
480	17.8M	ADJUST_INDICES(start, end, len);
481	17.8M	if (end - start < sub_len)
482	19	res = -1;
483	17.8M	else if (sub_len == 1) {
484	17.8M	if (dir > 0)
485	17.8M	res = stringlib_find_char(
486	17.8M	str + start, end - start,
487	17.8M	*sub);
488	20.1k	else
489	20.1k	res = stringlib_rfind_char(
490	20.1k	str + start, end - start,
491	20.1k	*sub);
492	17.8M	if (res >= 0)
493	13.2M	res += start;
494	17.8M	}
495	7.31k	else {
496	7.31k	if (dir > 0)
497	0	res = stringlib_find_slice(
498	0	str, len,
499	0	sub, sub_len, start, end);
500	7.31k	else
501	7.31k	res = stringlib_rfind_slice(
502	7.31k	str, len,
503	7.31k	sub, sub_len, start, end);
504	7.31k	}
505
506	17.8M	if (subobj)
507	16.8M	PyBuffer_Release(&subbuf);
508
509	17.8M	return res;
510	17.8M	}
511
512		PyObject *
513		_Py_bytes_find(const char str, Py_ssize_t len, PyObject sub,
514		Py_ssize_t start, Py_ssize_t end)
515	17.8M	{
516	17.8M	Py_ssize_t result = find_internal(str, len, "find", sub, start, end, +1);
517	17.8M	if (result == -2)
518	0	return NULL;
519	17.8M	return PyLong_FromSsize_t(result);
520	17.8M	}
521
522		PyObject *
523		_Py_bytes_index(const char str, Py_ssize_t len, PyObject sub,
524		Py_ssize_t start, Py_ssize_t end)
525	0	{
526	0	Py_ssize_t result = find_internal(str, len, "index", sub, start, end, +1);
527	0	if (result == -2)
528	0	return NULL;
529	0	if (result == -1) {
530	0	PyErr_SetString(PyExc_ValueError,
531	0	"subsection not found");
532	0	return NULL;
533	0	}
534	0	return PyLong_FromSsize_t(result);
535	0	}
536
537		PyObject *
538		_Py_bytes_rfind(const char str, Py_ssize_t len, PyObject sub,
539		Py_ssize_t start, Py_ssize_t end)
540	27.5k	{
541	27.5k	Py_ssize_t result = find_internal(str, len, "rfind", sub, start, end, -1);
542	27.5k	if (result == -2)
543	0	return NULL;
544	27.5k	return PyLong_FromSsize_t(result);
545	27.5k	}
546
547		PyObject *
548		_Py_bytes_rindex(const char str, Py_ssize_t len, PyObject sub,
549		Py_ssize_t start, Py_ssize_t end)
550	0	{
551	0	Py_ssize_t result = find_internal(str, len, "rindex", sub, start, end, -1);
552	0	if (result == -2)
553	0	return NULL;
554	0	if (result == -1) {
555	0	PyErr_SetString(PyExc_ValueError,
556	0	"subsection not found");
557	0	return NULL;
558	0	}
559	0	return PyLong_FromSsize_t(result);
560	0	}
561
562		PyObject *
563		_Py_bytes_count(const char str, Py_ssize_t len, PyObject sub_obj,
564		Py_ssize_t start, Py_ssize_t end)
565	6.49M	{
566	6.49M	const char *sub;
567	6.49M	Py_ssize_t sub_len;
568	6.49M	char byte;
569
570	6.49M	Py_buffer vsub;
571	6.49M	PyObject *count_obj;
572
573	6.49M	if (!parse_args_finds_byte("count", &sub_obj, &byte)) {
574	0	return NULL;
575	0	}
576
577	6.49M	if (sub_obj) {
578	6.49M	if (PyObject_GetBuffer(sub_obj, &vsub, PyBUF_SIMPLE) != 0)
579	0	return NULL;
580
581	6.49M	sub = vsub.buf;
582	6.49M	sub_len = vsub.len;
583	6.49M	}
584	0	else {
585	0	sub = &byte;
586	0	sub_len = 1;
587	0	}
588
589	6.49M	ADJUST_INDICES(start, end, len);
590
591	6.49M	count_obj = PyLong_FromSsize_t(
592	6.49M	stringlib_count(str + start, end - start, sub, sub_len, PY_SSIZE_T_MAX)
593	6.49M	);
594
595	6.49M	if (sub_obj)
596	6.49M	PyBuffer_Release(&vsub);
597
598	6.49M	return count_obj;
599	6.49M	}
600
601		int
602		_Py_bytes_contains(const char str, Py_ssize_t len, PyObject arg)
603	2.94k	{
604	2.94k	Py_ssize_t ival = PyNumber_AsSsize_t(arg, NULL);
605	2.94k	if (ival == -1 && PyErr_Occurred()) {
606	2.94k	Py_buffer varg;
607	2.94k	Py_ssize_t pos;
608	2.94k	PyErr_Clear();
609	2.94k	if (PyObject_GetBuffer(arg, &varg, PyBUF_SIMPLE) != 0)
610	0	return -1;
611	2.94k	pos = stringlib_find(str, len,
612	2.94k	varg.buf, varg.len, 0);
613	2.94k	PyBuffer_Release(&varg);
614	2.94k	return pos >= 0;
615	2.94k	}
616	0	if (ival < 0 \|\| ival >= 256) {
617	0	PyErr_SetString(PyExc_ValueError, "byte must be in range(0, 256)");
618	0	return -1;
619	0	}
620
621	0	return memchr(str, (int) ival, len) != NULL;
622	0	}
623
624
625		/* Matches the end (direction >= 0) or start (direction < 0) of the buffer
626		* against substr, using the start and end arguments. Returns
627		* -1 on error, 0 if not found and 1 if found.
628		*/
629		static int
630		tailmatch(const char str, Py_ssize_t len, PyObject substr,
631		Py_ssize_t start, Py_ssize_t end, int direction)
632	308k	{
633	308k	Py_buffer sub_view = {NULL, NULL};
634	308k	const char *sub;
635	308k	Py_ssize_t slen;
636
637	308k	if (PyBytes_Check(substr)) {
638	308k	sub = PyBytes_AS_STRING(substr);
639	308k	slen = PyBytes_GET_SIZE(substr);
640	308k	}
641	0	else {
642	0	if (PyObject_GetBuffer(substr, &sub_view, PyBUF_SIMPLE) != 0)
643	0	return -1;
644	0	sub = sub_view.buf;
645	0	slen = sub_view.len;
646	0	}
647
648	308k	ADJUST_INDICES(start, end, len);
649
650	308k	if (direction < 0) {
651		/* startswith */
652	308k	if (start > len - slen)
653	258k	goto notfound;
654	308k	} else {
655		/* endswith */
656	0	if (end - start < slen \|\| start > len)
657	0	goto notfound;
658
659	0	if (end - slen > start)
660	0	start = end - slen;
661	0	}
662	50.3k	if (end - start < slen)
663	0	goto notfound;
664	50.3k	if (memcmp(str + start, sub, slen) != 0)
665	22.8k	goto notfound;
666
667	27.5k	PyBuffer_Release(&sub_view);
668	27.5k	return 1;
669
670	281k	notfound:
671	281k	PyBuffer_Release(&sub_view);
672	281k	return 0;
673	50.3k	}
674
675		static PyObject *
676		_Py_bytes_tailmatch(const char *str, Py_ssize_t len,
677		const char function_name, PyObject subobj,
678		Py_ssize_t start, Py_ssize_t end,
679		int direction)
680	308k	{
681	308k	if (PyTuple_Check(subobj)) {
682	0	Py_ssize_t i;
683	0	for (i = 0; i < PyTuple_GET_SIZE(subobj); i++) {
684	0	PyObject *item = PyTuple_GET_ITEM(subobj, i);
685	0	int result = tailmatch(str, len, item, start, end, direction);
686	0	if (result < 0) {
687	0	return NULL;
688	0	}
689	0	else if (result) {
690	0	Py_RETURN_TRUE;
691	0	}
692	0	}
693	0	Py_RETURN_FALSE;
694	0	}
695	308k	int result = tailmatch(str, len, subobj, start, end, direction);
696	308k	if (result == -1) {
697	0	if (PyErr_ExceptionMatches(PyExc_TypeError)) {
698	0	PyErr_Format(PyExc_TypeError,
699	0	"%s first arg must be bytes or a tuple of bytes, "
700	0	"not %s",
701	0	function_name, Py_TYPE(subobj)->tp_name);
702	0	}
703	0	return NULL;
704	0	}
705	308k	return PyBool_FromLong(result);
706	308k	}
707
708		PyObject *
709		_Py_bytes_startswith(const char str, Py_ssize_t len, PyObject subobj,
710		Py_ssize_t start, Py_ssize_t end)
711	308k	{
712	308k	return _Py_bytes_tailmatch(str, len, "startswith", subobj, start, end, -1);
713	308k	}
714
715		PyObject *
716		_Py_bytes_endswith(const char str, Py_ssize_t len, PyObject subobj,
717		Py_ssize_t start, Py_ssize_t end)
718	0	{
719	0	return _Py_bytes_tailmatch(str, len, "endswith", subobj, start, end, +1);
720	0	}
721
722		PyDoc_STRVAR_shared(_Py_isascii__doc__,
723		"B.isascii() -> bool\n\
724		\n\
725		Return True if B is empty or all characters in B are ASCII,\n\
726		False otherwise.");
727
728		PyObject*
729		_Py_bytes_isascii(const char *cptr, Py_ssize_t len)
730	0	{
731	0	const char *p = cptr;
732	0	const char *end = p + len;
733	0	Py_ssize_t max_char = stringlib_find_max_char(cptr, end);
734	0	if (max_char > 127) {
735	0	Py_RETURN_FALSE;
736	0	}
737	0	Py_RETURN_TRUE;
738	0	}