1 /* Look at first character in UTF-8 string.
2 Copyright (C) 1999-2002, 2006-2007, 2009-2021 Free Software Foundation, Inc.
3 Written by Bruno Haible <bruno@clisp.org>, 2001.
5 This program is free software: you can redistribute it and/or modify it
6 under the terms of the GNU Lesser General Public License as published
7 by the Free Software Foundation; either version 3 of the License, or
8 (at your option) any later version.
10 This program is distributed in the hope that it will be useful,
11 but WITHOUT ANY WARRANTY; without even the implied warranty of
12 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
13 Lesser General Public License for more details.
15 You should have received a copy of the GNU Lesser General Public License
16 along with this program. If not, see <https://www.gnu.org/licenses/>. */
20 #if defined IN_LIBUNISTRING
21 /* Tell unistr.h to declare u8_mbtouc_unsafe as 'extern', not
23 # include "unistring-notinline.h"
32 u8_mbtouc_unsafe (ucs4_t
*puc
, const uint8_t *s
, size_t n
)
47 if ((s
[1] ^ 0x80) < 0x40)
49 *puc
= ((unsigned int) (c
& 0x1f) << 6)
50 | (unsigned int) (s
[1] ^ 0x80);
53 /* invalid multibyte character */
57 /* incomplete multibyte character */
66 if ((s
[1] ^ 0x80) < 0x40)
68 if ((s
[2] ^ 0x80) < 0x40)
70 if ((c
>= 0xe1 || s
[1] >= 0xa0)
71 && (c
!= 0xed || s
[1] < 0xa0))
73 *puc
= ((unsigned int) (c
& 0x0f) << 12)
74 | ((unsigned int) (s
[1] ^ 0x80) << 6)
75 | (unsigned int) (s
[2] ^ 0x80);
78 /* invalid multibyte character */
82 /* invalid multibyte character */
86 /* invalid multibyte character */
90 /* incomplete multibyte character */
92 if (n
== 1 || (s
[1] ^ 0x80) >= 0x40)
102 if ((s
[1] ^ 0x80) < 0x40)
104 if ((s
[2] ^ 0x80) < 0x40)
106 if ((s
[3] ^ 0x80) < 0x40)
108 if ((c
>= 0xf1 || s
[1] >= 0x90)
109 && (c
< 0xf4 || (c
== 0xf4 && s
[1] < 0x90))
112 *puc
= ((unsigned int) (c
& 0x07) << 18)
113 | ((unsigned int) (s
[1] ^ 0x80) << 12)
114 | ((unsigned int) (s
[2] ^ 0x80) << 6)
115 | (unsigned int) (s
[3] ^ 0x80);
118 /* invalid multibyte character */
122 /* invalid multibyte character */
126 /* invalid multibyte character */
130 /* invalid multibyte character */
134 /* incomplete multibyte character */
136 if (n
== 1 || (s
[1] ^ 0x80) >= 0x40)
138 else if (n
== 2 || (s
[2] ^ 0x80) >= 0x40)
145 /* invalid multibyte character */