2 * fribidi-char-sets-utf8.c - UTF-8 character set conversion routines
4 * $Id: fribidi-char-sets-utf8.c,v 1.3 2005-07-30 09:06:28 behdad Exp $
6 * $Date: 2005-07-30 09:06:28 $
8 * $Source: /home/behdad/src/fdo/fribidi/togit/git/../fribidi/fribidi2/charset/fribidi-char-sets-utf8.c,v $
11 * Behdad Esfahbod, 2001, 2002, 2004
12 * Dov Grobgeld, 1999, 2000
14 * Copyright (C) 2004 Sharif FarsiWeb, Inc
15 * Copyright (C) 2001,2002 Behdad Esfahbod
16 * Copyright (C) 1999,2000 Dov Grobgeld
18 * This library is free software; you can redistribute it and/or
19 * modify it under the terms of the GNU Lesser General Public
20 * License as published by the Free Software Foundation; either
21 * version 2.1 of the License, or (at your option) any later version.
23 * This library is distributed in the hope that it will be useful,
24 * but WITHOUT ANY WARRANTY; without even the implied warranty of
25 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
26 * Lesser General Public License for more details.
28 * You should have received a copy of the GNU Lesser General Public License
29 * along with this library, in a file named COPYING; if not, write to the
30 * Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
31 * Boston, MA 02110-1301, USA
33 * For licensing issues, contact <license@farsiweb.info>.
38 #include <fribidi-char-sets-utf8.h>
40 #include <fribidi-unicode.h>
43 fribidi_utf8_to_unicode (
51 FriBidiStrIndex length;
52 const unsigned char *s = (unsigned const char *) ss;
53 const unsigned char *t = s;
56 while ((FriBidiStrIndex) (s - t) < len)
58 register unsigned char ch = *s;
59 if (ch <= 0x7f) /* one byte */
63 else if (ch <= 0xdf) /* 2 byte */
65 *us++ = ((*s & 0x1f) << 6) + (*(s + 1) & 0x3f);
68 else if (ch <= 0xef) /* 3 byte */
71 ((int) (*s & 0x0f) << 12) +
72 ((*(s + 1) & 0x3f) << 6) + (*(s + 2) & 0x3f);
78 ((int) (*s & 0x07) << 18) +
79 ((*(s + 1) & 0x3f) << 12) +
80 ((*(s + 2) & 0x3f) << 6) +
81 ((*(s + 3) & 0x3f) << 0);
90 fribidi_unicode_to_utf8 (
92 const FriBidiChar *us,
99 unsigned char *s = (unsigned char *) ss;
100 unsigned char *t = s;
102 for (i = 0; i < len; i++)
104 FriBidiChar mychar = us[i];
109 else if (mychar <= 0x7FF)
111 *t++ = 0xC0 | (unsigned char) (mychar >> 6); /* upper 5 bits */
112 *t++ = 0x80 | (unsigned char) (mychar & 0x3F); /* lower 6 bits */
114 else if (mychar <= 0xFFFF)
116 *t++ = 0xE0 | (unsigned char) (mychar >> 12); /* upper 4 bits */
117 *t++ = 0x80 | (unsigned char) ((mychar >> 6) & 0x3F); /* next 6 bits */
118 *t++ = 0x80 | (unsigned char) (mychar & 0x3F); /* lowest 6 bits */
120 else if (mychar < FRIBIDI_UNICODE_CHARS)
122 *t++ = 0xF0 | (unsigned char) ((mychar >> 18) & 0x07); /* upper 3 bits */
123 *t++ = 0x80 | (unsigned char) ((mychar >> 12) & 0x3F); /* next 6 bits */
124 *t++ = 0x80 | (unsigned char) ((mychar >> 6) & 0x3F); /* next 6 bits */
125 *t++ = 0x80 | (unsigned char) (mychar & 0x3F); /* lowest 6 bits */
133 /* Editor directions:
134 * vim:textwidth=78:tabstop=8:shiftwidth=2:autoindent:cindent