1 /* Look at first character in UTF-8 string.
2 Copyright (C) 1999-2000, 2002, 2006-2007, 2009-2014 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 <http://www.gnu.org/licenses/>. */
25 u8_mblen (const uint8_t *s, size_t n)
29 /* Keep in sync with unistr.h and u8-mbtouc-aux.c. */
33 return (c != 0 ? 1 : 0);
39 #if CONFIG_UNICODE_SAFETY
40 && (s[1] ^ 0x80) < 0x40
48 #if CONFIG_UNICODE_SAFETY
49 && (s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40
50 && (c >= 0xe1 || s[1] >= 0xa0)
51 && (c != 0xed || s[1] < 0xa0)
59 #if CONFIG_UNICODE_SAFETY
60 && (s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40
61 && (s[3] ^ 0x80) < 0x40
62 && (c >= 0xf1 || s[1] >= 0x90)
64 && (c < 0xf4 || (c == 0xf4 && s[1] < 0x90))
74 #if CONFIG_UNICODE_SAFETY
75 && (s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40
76 && (s[3] ^ 0x80) < 0x40 && (s[4] ^ 0x80) < 0x40
77 && (c >= 0xf9 || s[1] >= 0x88)
85 #if CONFIG_UNICODE_SAFETY
86 && (s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40
87 && (s[3] ^ 0x80) < 0x40 && (s[4] ^ 0x80) < 0x40
88 && (s[5] ^ 0x80) < 0x40
89 && (c >= 0xfd || s[1] >= 0x84)
97 /* invalid or incomplete multibyte character */