1 /* Look at first character in UTF-8 string, returning an error code.
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/>. */
24 u8_mbtoucr (ucs4_t
*puc
, const uint8_t *s
, size_t n
)
39 if ((s
[1] ^ 0x80) < 0x40)
41 *puc
= ((unsigned int) (c
& 0x1f) << 6)
42 | (unsigned int) (s
[1] ^ 0x80);
45 /* invalid multibyte character */
49 /* incomplete multibyte character */
58 if ((s
[1] ^ 0x80) < 0x40
59 && (c
>= 0xe1 || s
[1] >= 0xa0)
60 && (c
!= 0xed || s
[1] < 0xa0))
64 if ((s
[2] ^ 0x80) < 0x40)
66 *puc
= ((unsigned int) (c
& 0x0f) << 12)
67 | ((unsigned int) (s
[1] ^ 0x80) << 6)
68 | (unsigned int) (s
[2] ^ 0x80);
71 /* invalid multibyte character */
75 /* incomplete multibyte character */
80 /* invalid multibyte character */
84 /* incomplete multibyte character */
93 if ((s
[1] ^ 0x80) < 0x40
94 && (c
>= 0xf1 || s
[1] >= 0x90)
95 && (c
< 0xf4 || (c
== 0xf4 && s
[1] < 0x90)))
99 if ((s
[2] ^ 0x80) < 0x40)
103 if ((s
[3] ^ 0x80) < 0x40)
105 *puc
= ((unsigned int) (c
& 0x07) << 18)
106 | ((unsigned int) (s
[1] ^ 0x80) << 12)
107 | ((unsigned int) (s
[2] ^ 0x80) << 6)
108 | (unsigned int) (s
[3] ^ 0x80);
111 /* invalid multibyte character */
115 /* incomplete multibyte character */
120 /* invalid multibyte character */
124 /* incomplete multibyte character */
129 /* invalid multibyte character */
133 /* incomplete multibyte character */
139 /* invalid multibyte character */