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
|
/* Compare pieces of UTF-16 strings.
Copyright (C) 1999, 2002, 2006, 2009-2011 Free Software Foundation, Inc.
Written by Bruno Haible <bruno@clisp.org>, 2002.
This program 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 program 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 <http://www.gnu.org/licenses/>. */
#include <config.h>
/* Specification. */
#include "unistr.h"
int
u16_cmp (const uint16_t *s1, const uint16_t *s2, size_t n)
{
/* Note that the UTF-16 encoding does NOT preserve lexicographic order.
Namely, if uc1 is a 16-bit character and [uc2a,uc2b] is a surrogate pair,
we must enforce uc1 < [uc2a,uc2b], even if uc1 > uc2a. */
for (; n > 0;)
{
uint16_t c1 = *s1++;
uint16_t c2 = *s2++;
if (c1 == c2)
{
n--;
continue;
}
if (c1 < 0xd800 || c1 >= 0xe000)
{
if (!(c2 < 0xd800 || c2 >= 0xe000))
/* c2 is a surrogate, but c1 is not. */
return -1;
}
else
{
if (c2 < 0xd800 || c2 >= 0xe000)
/* c1 is a surrogate, but c2 is not. */
return 1;
}
return (int)c1 - (int)c2;
/* > 0 if c1 > c2, < 0 if c1 < c2. */
}
return 0;
}
|
