1 /* Part of SWI-Prolog
2
3 Author: Jan Wielemaker
4 E-mail: J.Wielemaker@vu.nl
5 WWW: http://www.swi-prolog.org
6 Copyright (c) 2000-2011, University of Amsterdam
7 All rights reserved.
8
9 Redistribution and use in source and binary forms, with or without
10 modification, are permitted provided that the following conditions
11 are met:
12
13 1. Redistributions of source code must retain the above copyright
14 notice, this list of conditions and the following disclaimer.
15
16 2. Redistributions in binary form must reproduce the above copyright
17 notice, this list of conditions and the following disclaimer in
18 the documentation and/or other materials provided with the
19 distribution.
20
21 THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
22 "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
23 LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
24 FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
25 COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
26 INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
27 BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
28 LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
29 CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
30 LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
31 ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
32 POSSIBILITY OF SUCH DAMAGE.
33 */
34
35 #include <stdio.h>
36 #include "utf8.h"
37
38 /* - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
39 UTF-8 Decoding, based on http://www.cl.cam.ac.uk/~mgk25/unicode.html
40 - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - */
41
42 #define CONT(i) ((in[i]&0xc0) == 0x80)
43 #define VAL(i, s) ((in[i]&0x3f) << s)
44
45 char *
sgml__utf8_get_char(const char * in,int * chr)46 sgml__utf8_get_char(const char *in, int *chr)
47 { /* 2-byte, 0x80-0x7ff */
48 if ( (in[0]&0xe0) == 0xc0 && CONT(1) )
49 { *chr = ((in[0]&0x1f) << 6)|VAL(1,0);
50 return (char *)in+2;
51 }
52 /* 3-byte, 0x800-0xffff */
53 if ( (in[0]&0xf0) == 0xe0 && CONT(1) && CONT(2) )
54 { *chr = ((in[0]&0xf) << 12)|VAL(1,6)|VAL(2,0);
55 return (char *)in+3;
56 }
57 /* 4-byte, 0x10000-0x1FFFFF */
58 if ( (in[0]&0xf8) == 0xf0 && CONT(1) && CONT(2) && CONT(3) )
59 { *chr = ((in[0]&0x7) << 18)|VAL(1,12)|VAL(2,6)|VAL(3,0);
60 return (char *)in+4;
61 }
62 /* 5-byte, 0x200000-0x3FFFFFF */
63 if ( (in[0]&0xfc) == 0xf8 && CONT(1) && CONT(2) && CONT(3) && CONT(4) )
64 { *chr = ((in[0]&0x3) << 24)|VAL(1,18)|VAL(2,12)|VAL(3,6)|VAL(4,0);
65 return (char *)in+5;
66 }
67 /* 6-byte, 0x400000-0x7FFFFFF */
68 if ( (in[0]&0xfe) == 0xfc && CONT(1) && CONT(2) && CONT(3) && CONT(4) && CONT(5) )
69 { *chr = ((in[0]&0x1) << 30)|VAL(1,24)|VAL(2,18)|VAL(3,12)|VAL(4,6)|VAL(5,0);
70 return (char *)in+4;
71 }
72
73 *chr = *in;
74
75 return (char *)in+1;
76 }
77
78
79 char *
sgml_utf8_put_char(char * out,int chr)80 sgml_utf8_put_char(char *out, int chr)
81 { if ( chr < 0x80 )
82 { *out++ = chr;
83 } else if ( chr < 0x800 )
84 { *out++ = 0xc0|((chr>>6)&0x1f);
85 *out++ = 0x80|(chr&0x3f);
86 } else if ( chr < 0x10000 )
87 { *out++ = 0xe0|((chr>>12)&0x0f);
88 *out++ = 0x80|((chr>>6)&0x3f);
89 *out++ = 0x80|(chr&0x3f);
90 } else if ( chr < 0x200000 )
91 { *out++ = 0xf0|((chr>>18)&0x07);
92 *out++ = 0x80|((chr>>12)&0x3f);
93 *out++ = 0x80|((chr>>6)&0x3f);
94 *out++ = 0x80|(chr&0x3f);
95 } else if ( chr < 0x4000000 )
96 { *out++ = 0xf8|((chr>>24)&0x03);
97 *out++ = 0x80|((chr>>18)&0x3f);
98 *out++ = 0x80|((chr>>12)&0x3f);
99 *out++ = 0x80|((chr>>6)&0x3f);
100 *out++ = 0x80|(chr&0x3f);
101 } else if ( (unsigned)chr < 0x80000000 )
102 { *out++ = 0xfc|((chr>>30)&0x01);
103 *out++ = 0x80|((chr>>24)&0x3f);
104 *out++ = 0x80|((chr>>18)&0x3f);
105 *out++ = 0x80|((chr>>12)&0x3f);
106 *out++ = 0x80|((chr>>6)&0x3f);
107 *out++ = 0x80|(chr&0x3f);
108 }
109
110 return out;
111 }
112
113
114 size_t
sgml_utf8_strlen(const char * s,size_t len)115 sgml_utf8_strlen(const char *s, size_t len)
116 { const char *e = &s[len];
117 unsigned int l = 0;
118
119 while(s<e)
120 { int chr;
121
122 s = utf8_get_char(s, &chr);
123 l++;
124 }
125
126 return l;
127 }
128