1 /* Look at first character in UTF-8 string.
2 Copyright (C) 1999-2000, 2002, 2006-2007 Free Software Foundation, Inc.
3 Written by Bruno Haible <bruno@clisp.org>, 2002.
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 <http://www.gnu.org/licenses/>. */
24 u8_mblen (const uint8_t *s, size_t n)
28 /* Keep in sync with unistr.h and utf8-ucs4.c. */
32 return (c != 0 ? 1 : 0);
38 #if CONFIG_UNICODE_SAFETY
39 && (s[1] ^ 0x80) < 0x40
47 #if CONFIG_UNICODE_SAFETY
48 && (s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40
49 && (c >= 0xe1 || s[1] >= 0xa0)
50 && (c != 0xed || s[1] < 0xa0)
58 #if CONFIG_UNICODE_SAFETY
59 && (s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40
60 && (s[3] ^ 0x80) < 0x40
61 && (c >= 0xf1 || s[1] >= 0x90)
63 && (c < 0xf4 || (c == 0xf4 && s[1] < 0x90))
73 #if CONFIG_UNICODE_SAFETY
74 && (s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40
75 && (s[3] ^ 0x80) < 0x40 && (s[4] ^ 0x80) < 0x40
76 && (c >= 0xf9 || s[1] >= 0x88)
84 #if CONFIG_UNICODE_SAFETY
85 && (s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40
86 && (s[3] ^ 0x80) < 0x40 && (s[4] ^ 0x80) < 0x40
87 && (s[5] ^ 0x80) < 0x40
88 && (c >= 0xfd || s[1] >= 0x84)
96 /* invalid or incomplete multibyte character */