1 /* Look at first character in UTF-8 string.
2 Copyright (C) 1999-2000, 2002, 2006-2007, 2009-2021 Free Software
4 Written by Bruno Haible <bruno@clisp.org>, 2002.
6 This program is free software: you can redistribute it and/or modify it
7 under the terms of the GNU Lesser General Public License as published
8 by the Free Software Foundation; either version 3 of the License, or
9 (at your option) any later version.
11 This program is distributed in the hope that it will be useful,
12 but WITHOUT ANY WARRANTY; without even the implied warranty of
13 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
14 Lesser General Public License for more details.
16 You should have received a copy of the GNU Lesser General Public License
17 along with this program. If not, see <https://www.gnu.org/licenses/>. */
25 u8_strmbtouc (ucs4_t
*puc
, const uint8_t *s
)
27 /* Keep in sync with unistr.h and u8-mbtouc-aux.c. */
33 return (c
!= 0 ? 1 : 0);
39 if ((s
[1] ^ 0x80) < 0x40)
41 *puc
= ((unsigned int) (c
& 0x1f) << 6)
42 | (unsigned int) (s
[1] ^ 0x80);
48 if ((s
[1] ^ 0x80) < 0x40 && (s
[2] ^ 0x80) < 0x40
49 && (c
>= 0xe1 || s
[1] >= 0xa0)
50 && (c
!= 0xed || s
[1] < 0xa0))
52 *puc
= ((unsigned int) (c
& 0x0f) << 12)
53 | ((unsigned int) (s
[1] ^ 0x80) << 6)
54 | (unsigned int) (s
[2] ^ 0x80);
60 if ((s
[1] ^ 0x80) < 0x40 && (s
[2] ^ 0x80) < 0x40
61 && (s
[3] ^ 0x80) < 0x40
62 && (c
>= 0xf1 || s
[1] >= 0x90)
63 && (c
< 0xf4 || (c
== 0xf4 && s
[1] < 0x90)))
65 *puc
= ((unsigned int) (c
& 0x07) << 18)
66 | ((unsigned int) (s
[1] ^ 0x80) << 12)
67 | ((unsigned int) (s
[2] ^ 0x80) << 6)
68 | (unsigned int) (s
[3] ^ 0x80);
73 /* invalid or incomplete multibyte character */