1 /* Look at first character in UTF-8 string.
2 Copyright (C) 1999-2000, 2002, 2006-2007, 2009-2013 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_strmblen (const uint8_t *s)
27 /* Keep in sync with unistr.h and u8-mbtouc-aux.c. */
31 return (c != 0 ? 1 : 0);
36 #if CONFIG_UNICODE_SAFETY
37 if ((s[1] ^ 0x80) < 0x40)
45 #if CONFIG_UNICODE_SAFETY
46 if ((s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40
47 && (c >= 0xe1 || s[1] >= 0xa0)
48 && (c != 0xed || s[1] < 0xa0))
50 if (s[1] != 0 && s[2] != 0)
56 #if CONFIG_UNICODE_SAFETY
57 if ((s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40
58 && (s[3] ^ 0x80) < 0x40
59 && (c >= 0xf1 || s[1] >= 0x90)
61 && (c < 0xf4 || (c == 0xf4 && s[1] < 0x90))
65 if (s[1] != 0 && s[2] != 0 && s[3] != 0)
72 #if CONFIG_UNICODE_SAFETY
73 if ((s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40
74 && (s[3] ^ 0x80) < 0x40 && (s[4] ^ 0x80) < 0x40
75 && (c >= 0xf9 || s[1] >= 0x88))
77 if (s[1] != 0 && s[2] != 0 && s[3] != 0 && s[4] != 0)
83 #if CONFIG_UNICODE_SAFETY
84 if ((s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40
85 && (s[3] ^ 0x80) < 0x40 && (s[4] ^ 0x80) < 0x40
86 && (s[5] ^ 0x80) < 0x40
87 && (c >= 0xfd || s[1] >= 0x84))
89 if (s[1] != 0 && s[2] != 0 && s[3] != 0 && s[4] != 0 && s[5] != 0)
95 /* invalid or incomplete multibyte character */