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 Library General Public License as published
7 by the Free Software Foundation; either version 2, or (at your option)
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 Library General Public License for more details.
15 You should have received a copy of the GNU Library General Public
16 License along with this program; if not, write to the Free Software
17 Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301,
26 u8_mblen (const uint8_t *s, size_t n)
30 /* Keep in sync with utf8-ucs4.h and utf8-ucs4.c. */
34 return (c != 0 ? 1 : 0);
40 #if CONFIG_UNICODE_SAFETY
41 && (s[1] ^ 0x80) < 0x40
49 #if CONFIG_UNICODE_SAFETY
50 && (s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40
51 && (c >= 0xe1 || s[1] >= 0xa0)
52 && (c != 0xed || s[1] < 0xa0)
60 #if CONFIG_UNICODE_SAFETY
61 && (s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40
62 && (s[3] ^ 0x80) < 0x40
63 && (c >= 0xf1 || s[1] >= 0x90)
65 && (c < 0xf4 || (c == 0xf4 && s[1] < 0x90))
75 #if CONFIG_UNICODE_SAFETY
76 && (s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40
77 && (s[3] ^ 0x80) < 0x40 && (s[4] ^ 0x80) < 0x40
78 && (c >= 0xf9 || s[1] >= 0x88)
86 #if CONFIG_UNICODE_SAFETY
87 && (s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40
88 && (s[3] ^ 0x80) < 0x40 && (s[4] ^ 0x80) < 0x40
89 && (s[5] ^ 0x80) < 0x40
90 && (c >= 0xfd || s[1] >= 0x84)
98 /* invalid or incomplete multibyte character */