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
|
/* utf8.c - Operations on UTF-8 strings.
*
* Copyright (C) 2002 Timo Sirainen
*
* Based on GLib code by
*
* Copyright (C) 1999 Tom Tromey
* Copyright (C) 2000 Red Hat, Inc.
*
* This library 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 2 of the License, or (at your option) any later version.
*
* This library 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 General Public License along
* with this program; if not, write to the Free Software Foundation, Inc.,
* 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
*/
#include "utf8.h"
#include "module.h"
#include "wcwidth.c"
/* Provide is_utf8(): */
#include "recode.h"
int string_advance(char const **str, int policy)
{
if (policy == TREAT_STRING_AS_UTF8) {
gunichar c;
c = g_utf8_get_char(*str);
*str = g_utf8_next_char(*str);
return unichar_isprint(c) ? mk_wcwidth(c) : 1;
} else {
/* Assume TREAT_STRING_AS_BYTES: */
*str += 1;
return 1;
}
}
int string_policy(const char *str)
{
if (is_utf8()) {
if (str == NULL || g_utf8_validate(str, -1, NULL)) {
/* No string provided or valid UTF-8 string: treat as UTF-8: */
return TREAT_STRING_AS_UTF8;
}
}
return TREAT_STRING_AS_BYTES;
}
int string_length(const char *str, int policy)
{
g_return_val_if_fail(str != NULL, 0);
if (policy == -1) {
policy = string_policy(str);
}
if (policy == TREAT_STRING_AS_UTF8) {
return g_utf8_strlen(str, -1);
}
else {
/* Assume TREAT_STRING_AS_BYTES: */
return strlen(str);
}
}
int string_width(const char *str, int policy)
{
int len;
g_return_val_if_fail(str != NULL, 0);
if (policy == -1) {
policy = string_policy(str);
}
len = 0;
while (*str != '\0') {
len += string_advance(&str, policy);
}
return len;
}
int string_chars_for_width(const char *str, int policy, unsigned int n, unsigned int *bytes)
{
const char *c, *previous_c;
int str_width, char_width, char_count;
g_return_val_if_fail(str != NULL, -1);
/* Handle the dummy case where n is 0: */
if (n == 0) {
if (bytes != NULL) {
*bytes = 0;
}
return 0;
}
if (policy == -1) {
policy = string_policy(str);
}
/* Iterate over characters until we reach n: */
char_count = 0;
str_width = 0;
c = str;
while (*c != '\0') {
previous_c = c;
char_width = string_advance(&c, policy);
if (str_width + char_width > n) {
/* We stepped beyond n, get one step back and stop there: */
c = previous_c;
break;
}
++ char_count;
str_width += char_width;
}
/* At this point, we know that char_count characters reach str_width
* columns, which is less than or equal to n. */
/* Optionally provide the equivalent amount of bytes: */
if (bytes != NULL) {
*bytes = c - str;
}
return char_count;
}
|
