1 /* $NetBSD: unicode.h,v 1.2 2023/05/10 12:23:42 rillig Exp $ */
2
3 /*-
4 * Copyright (c) 2001, 2004 The NetBSD Foundation, Inc.
5 * All rights reserved.
6 *
7 * Redistribution and use in source and binary forms, with or without
8 * modification, are permitted provided that the following conditions
9 * are met:
10 * 1. Redistributions of source code must retain the above copyright
11 * notice, this list of conditions and the following disclaimer.
12 * 2. Redistributions in binary form must reproduce the above copyright
13 * notice, this list of conditions and the following disclaimer in the
14 * documentation and/or other materials provided with the distribution.
15 *
16 * THIS SOFTWARE IS PROVIDED BY THE NETBSD FOUNDATION, INC. AND CONTRIBUTORS
17 * ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
18 * TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
19 * PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE FOUNDATION OR CONTRIBUTORS
20 * BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
21 * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
22 * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
23 * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
24 * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
25 * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
26 * POSSIBILITY OF SUCH DAMAGE.
27 */
28
29 /*-
30 * Copyright (c) 1993
31 * The Regents of the University of California. All rights reserved.
32 *
33 * This code is derived from software contributed to Berkeley by
34 * Paul Borman at Krystal Technologies.
35 *
36 * Redistribution and use in source and binary forms, with or without
37 * modification, are permitted provided that the following conditions
38 * are met:
39 * 1. Redistributions of source code must retain the above copyright
40 * notice, this list of conditions and the following disclaimer.
41 * 2. Redistributions in binary form must reproduce the above copyright
42 * notice, this list of conditions and the following disclaimer in the
43 * documentation and/or other materials provided with the distribution.
44 * 3. All advertising materials mentioning features or use of this software
45 * must display the following acknowledgement:
46 * This product includes software developed by the University of
47 * California, Berkeley and its contributors.
48 * 4. Neither the name of the University nor the names of its contributors
49 * may be used to endorse or promote products derived from this software
50 * without specific prior written permission.
51 *
52 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
53 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
54 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
55 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
56 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
57 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
58 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
59 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
60 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
61 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
62 * SUCH DAMAGE.
63 */
64
65 /*
66 * Routines for handling Unicode encoded in UTF-8 form, code derived from
67 * src/lib/libc/locale/utf2.c.
68 */
69 static u_int16_t wget_utf8(const char **, size_t *) __unused;
70 static int wput_utf8(char *, size_t, u_int16_t) __unused;
71
72 /*
73 * Read one UTF8-encoded character off the string, shift the string pointer
74 * and return the character.
75 */
76 static u_int16_t
wget_utf8(const char ** str,size_t * sz)77 wget_utf8(const char **str, size_t *sz)
78 {
79 unsigned int c;
80 u_int16_t rune = 0;
81 const char *s = *str;
82 static const int _utf_count[16] = {
83 1, 1, 1, 1, 1, 1, 1, 1,
84 0, 0, 0, 0, 2, 2, 3, 0,
85 };
86
87 /* must be called with at least one byte remaining */
88 assert(*sz > 0);
89
90 c = _utf_count[(s[0] & 0xf0) >> 4];
91 if (c == 0 || c > *sz) {
92 decoding_error:
93 /*
94 * The first character is in range 128-255 and doesn't mark a
95 * valid UTF-8 sequence. There is not much we can do with
96 * this, so handle by returning the first byte as if it were a
97 * correctly encoded ISO-8859-1 character.
98 */
99 c = 1;
100 }
101
102 switch (c) {
103 case 1:
104 rune = s[0] & 0xff;
105 break;
106 case 2:
107 if ((s[1] & 0xc0) != 0x80)
108 goto decoding_error;
109 rune = ((s[0] & 0x1F) << 6) | (s[1] & 0x3F);
110 break;
111 case 3:
112 if ((s[1] & 0xC0) != 0x80 || (s[2] & 0xC0) != 0x80)
113 goto decoding_error;
114 rune = ((s[0] & 0x0F) << 12) | ((s[1] & 0x3F) << 6)
115 | (s[2] & 0x3F);
116 break;
117 }
118
119 *str += c;
120 *sz -= c;
121 return rune;
122 }
123
124 /*
125 * Encode wide character and write it to the string. 'n' specifies
126 * how much buffer space remains in 's'. Returns number of bytes written
127 * to the target string 's'.
128 */
129 static int
wput_utf8(char * s,size_t n,u_int16_t wc)130 wput_utf8(char *s, size_t n, u_int16_t wc)
131 {
132 if (wc & 0xf800) {
133 if (n < 3) {
134 /* bound check failure */
135 return 0;
136 }
137
138 s[0] = 0xE0 | (wc >> 12);
139 s[1] = 0x80 | ((wc >> 6) & 0x3F);
140 s[2] = 0x80 | ((wc) & 0x3F);
141 return 3;
142 } else if (wc & 0x0780) {
143 if (n < 2) {
144 /* bound check failure */
145 return 0;
146 }
147
148 s[0] = 0xC0 | (wc >> 6);
149 s[1] = 0x80 | ((wc) & 0x3F);
150 return 2;
151 } else {
152 if (n < 1) {
153 /* bound check failure */
154 return 0;
155 }
156
157 s[0] = wc;
158 return 1;
159 }
160 }
161