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
|
#define _GNU_SOURCE
#include <assert.h>
#include <string.h>
#include <stdio.h>
#include <wchar.h>
#include <wctype.h>
#include "fold/fold.h"
void fold_text(const char *text,
int linelen,
int line_cb(void *arg, const char *start, int len),
void *arg)
{
const char *start, *end, *sep;
size_t sep_bytes, len;
int col, rc = 0;
mbstate_t ps;
/* start, end and sep are byte-positions in the string, and should always
* lie on the start of a multibyte sequence */
start = end = sep = text;
sep_bytes = 0;
col = 0;
len = strlen(text);
memset(&ps, 0, sizeof(ps));
while (!rc) {
size_t bytes;
wchar_t wc;
int width;
bytes = mbrtowc(&wc, end, len - (end - text), &ps);
assert(bytes >= 0);
/* we'll get a zero size for the nul terminator */
if (!bytes) {
line_cb(arg, start, end - start);
break;
}
if (wc == L'\n') {
rc = line_cb(arg, start, end - start);
start = sep = end += bytes;
sep_bytes = 0;
col = 0;
continue;
}
width = wcwidth(wc);
/* we should have caught this in the !bytes check... */
if (width == 0) {
line_cb(arg, start, end - start);
break;
}
/* unprintable character? just add it to the current line */
if (width < 0) {
end += bytes;
continue;
}
col += width;
if (col > linelen) {
if (sep != start) {
/* split on a previous word boundary, if
* possible */
rc = line_cb(arg, start, sep - start);
end = sep + sep_bytes;
} else {
/* otherwise, break the word */
rc = line_cb(arg, start, end - start);
}
sep_bytes = 0;
start = sep = end;
col = 0;
} else {
/* record our last separator */
if (wc == L' ') {
sep = end;
sep_bytes = bytes;
}
end += bytes;
}
}
}
|
