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_strmblen (const uint8_t *s)
28 /* Keep in sync with unistr.h and utf8-ucs4.c. */
32 return (c != 0 ? 1 : 0);
37 #if CONFIG_UNICODE_SAFETY
38 if ((s[1] ^ 0x80) < 0x40)
46 #if CONFIG_UNICODE_SAFETY
47 if ((s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40
48 && (c >= 0xe1 || s[1] >= 0xa0)
49 && (c != 0xed || s[1] < 0xa0))
51 if (s[1] != 0 && s[2] != 0)
57 #if CONFIG_UNICODE_SAFETY
58 if ((s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40
59 && (s[3] ^ 0x80) < 0x40
60 && (c >= 0xf1 || s[1] >= 0x90)
62 && (c < 0xf4 || (c == 0xf4 && s[1] < 0x90))
66 if (s[1] != 0 && s[2] != 0 && s[3] != 0)
73 #if CONFIG_UNICODE_SAFETY
74 if ((s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40
75 && (s[3] ^ 0x80) < 0x40 && (s[4] ^ 0x80) < 0x40
76 && (c >= 0xf9 || s[1] >= 0x88))
78 if (s[1] != 0 && s[2] != 0 && s[3] != 0 && s[4] != 0)
84 #if CONFIG_UNICODE_SAFETY
85 if ((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))
90 if (s[1] != 0 && s[2] != 0 && s[3] != 0 && s[4] != 0 && s[5] != 0)
96 /* invalid or incomplete multibyte character */