1 /* Look at first character in UTF-8 string.
2 Copyright (C) 1999-2002, 2006-2007, 2009-2010 Free Software Foundation, Inc.
3 Written by Bruno Haible <bruno@clisp.org>, 2001.
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/>. */
20 #if defined IN_LIBUNISTRING
21 /* Tell unistr.h to declare u8_mbtouc as 'extern', not 'static inline'. */
22 # include "unistring-notinline.h"
31 u8_mbtouc (ucs4_t *puc, const uint8_t *s, size_t n)
46 if ((s[1] ^ 0x80) < 0x40)
48 *puc = ((unsigned int) (c & 0x1f) << 6)
49 | (unsigned int) (s[1] ^ 0x80);
52 /* invalid multibyte character */
56 /* incomplete multibyte character */
65 if ((s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40
66 && (c >= 0xe1 || s[1] >= 0xa0)
67 && (c != 0xed || s[1] < 0xa0))
69 *puc = ((unsigned int) (c & 0x0f) << 12)
70 | ((unsigned int) (s[1] ^ 0x80) << 6)
71 | (unsigned int) (s[2] ^ 0x80);
74 /* invalid multibyte character */
78 /* incomplete multibyte character */
87 if ((s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40
88 && (s[3] ^ 0x80) < 0x40
89 && (c >= 0xf1 || s[1] >= 0x90)
91 && (c < 0xf4 || (c == 0xf4 && s[1] < 0x90))
95 *puc = ((unsigned int) (c & 0x07) << 18)
96 | ((unsigned int) (s[1] ^ 0x80) << 12)
97 | ((unsigned int) (s[2] ^ 0x80) << 6)
98 | (unsigned int) (s[3] ^ 0x80);
101 /* invalid multibyte character */
105 /* incomplete multibyte character */
115 if ((s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40
116 && (s[3] ^ 0x80) < 0x40 && (s[4] ^ 0x80) < 0x40
117 && (c >= 0xf9 || s[1] >= 0x88))
119 *puc = ((unsigned int) (c & 0x03) << 24)
120 | ((unsigned int) (s[1] ^ 0x80) << 18)
121 | ((unsigned int) (s[2] ^ 0x80) << 12)
122 | ((unsigned int) (s[3] ^ 0x80) << 6)
123 | (unsigned int) (s[4] ^ 0x80);
126 /* invalid multibyte character */
130 /* incomplete multibyte character */
139 if ((s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40
140 && (s[3] ^ 0x80) < 0x40 && (s[4] ^ 0x80) < 0x40
141 && (s[5] ^ 0x80) < 0x40
142 && (c >= 0xfd || s[1] >= 0x84))
144 *puc = ((unsigned int) (c & 0x01) << 30)
145 | ((unsigned int) (s[1] ^ 0x80) << 24)
146 | ((unsigned int) (s[2] ^ 0x80) << 18)
147 | ((unsigned int) (s[3] ^ 0x80) << 12)
148 | ((unsigned int) (s[4] ^ 0x80) << 6)
149 | (unsigned int) (s[5] ^ 0x80);
152 /* invalid multibyte character */
156 /* incomplete multibyte character */
163 /* invalid multibyte character */