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
|
/*
* File: utf8.c
*
* Copyright (C) 2009 Jorge Arellano Cid <jcid@dillo.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 3 of the License, or
* (at your option) any later version.
*/
#include <fltk/utf.h>
#include "utf8.hh"
// C++ functions with C linkage ----------------------------------------------
/*
* Return index of the last byte of the UTF-8-encoded character that str + i
* points to or into.
*/
uint_t a_Utf8_end_of_char(const char *str, uint_t i)
{
/* We can almost get what we want from utf8fwd(p+1,...)-1, but that
* does not work for the last character in a string, and the fn makes some
* assumptions that do not suit us.
* Here's something very simpleminded instead:
*/
if (str && *str && (str[i] & 0x80)) {
int internal_bytes = (str[i] & 0x40) ? 0 : 1;
while (((str[i + 1] & 0xc0) == 0x80) && (++internal_bytes < 4))
i++;
}
return i;
}
/*
* Decode a single UTF-8-encoded character starting at p.
* The resulting Unicode value (in the range 0-0x10ffff) is returned,
* and len is set to the number of bytes in the UTF-8 encoding.
* Note that utf8decode(), if given non-UTF-8 data, will interpret
* it as ISO-8859-1 or CP1252 if possible.
*/
uint_t a_Utf8_decode(const char* str, const char* end, int* len)
{
return utf8decode(str, end, len);
}
/*
* Write UTF-8 encoding of ucs into buf and return number of bytes written.
*/
int a_Utf8_encode(unsigned int ucs, char *buf)
{
return utf8encode(ucs, buf);
}
/*
* Examine first srclen bytes of src.
* Return 0 if not legal UTF-8, 1 if all ASCII, 2 if all below 0x800,
* 3 if all below 0x10000, and 4 otherwise.
*/
int a_Utf8_test(const char* src, unsigned int srclen)
{
return utf8test(src, srclen);
}
|
