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
|
/* Searching a string for a character outside a given set of characters.
Copyright (C) 1999, 2002, 2006-2024 Free Software Foundation, Inc.
Written by Bruno Haible <bruno@clisp.org>, 2007.
This file is free software: you can redistribute it and/or modify
it under the terms of the GNU Lesser General Public License as
published by the Free Software Foundation, either version 3 of the
License, or (at your option) any later version.
This file is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public License
along with this program. If not, see <https://www.gnu.org/licenses/>. */
#include <config.h>
/* Specification. */
#include <string.h>
#include <stdlib.h>
#if GNULIB_MCEL_PREFER
# include "mcel.h"
#else
# include "mbuiterf.h"
#endif
/* Find the first occurrence in the character string STRING of any character
not in the character string REJECT. Return the number of bytes from the
beginning of the string to this occurrence, or to the end of the string
if none exists. */
size_t
mbsspn (const char *string, const char *reject)
{
/* Optimize two cases. */
if (reject[0] == '\0')
return 0;
if (reject[1] == '\0')
{
unsigned char uc = (unsigned char) reject[0];
const char *iter = string;
if (MB_CUR_MAX > 1)
{
#if GNULIB_MCEL_PREFER
for (mcel_t g; *iter; iter += g.len)
{
g = mcel_scanz (iter);
if (! (g.len == 1 && (unsigned char) *iter == uc))
break;
}
#else
mbuif_state_t state;
for (mbuif_init (state); mbuif_avail (state, iter); )
{
mbchar_t cur = mbuif_next (state, iter);
if (!(mb_len (cur) == 1 && (unsigned char) *iter == uc))
break;
iter += mb_len (cur);
}
#endif
}
else
{
for (; *iter != '\0'; iter++)
if ((unsigned char) *iter != uc)
break;
}
return iter - string;
}
/* General case. */
if (MB_CUR_MAX > 1)
{
#if GNULIB_MCEL_PREFER
for (size_t i = 0; ; )
{
char c = string[i];
if (!c)
return i;
mcel_t g = mcel_scanz (string + i);
if (g.len == 1)
{
if (!mbschr (reject, c))
return i;
}
else
{
for (char const *aiter = reject; ; )
{
if (!*aiter)
return i;
mcel_t a = mcel_scanz (aiter);
if (mcel_cmp (a, g) == 0)
break;
aiter += a.len;
}
}
i += g.len;
}
#else
mbuif_state_t state;
const char *iter;
for (mbuif_init (state), iter = string; mbuif_avail (state, iter); )
{
mbchar_t cur = mbuif_next (state, iter);
if (mb_len (cur) == 1)
{
if (mbschr (reject, *iter) == NULL)
goto found;
}
else
{
mbuif_state_t astate;
const char *aiter;
for (mbuif_init (astate), aiter = reject; ; )
{
if (!mbuif_avail (astate, aiter))
goto found;
mbchar_t acur = mbuif_next (astate, aiter);
if (mb_equal (acur, cur))
break;
aiter += mb_len (acur);
}
}
iter += mb_len (cur);
}
found:
return iter - string;
#endif
}
else
return strspn (string, reject);
}
|
