1/*	$OpenBSD: ntfs_conv.c,v 1.9 2013/11/24 16:02:30 jsing Exp $	*/
2/*	$NetBSD: ntfs_conv.c,v 1.1 2002/12/23 17:38:32 jdolecek Exp $	*/
3
4/*-
5 * Copyright (c) 2001 The NetBSD Foundation, Inc.
6 * All rights reserved.
7 *
8 * Redistribution and use in source and binary forms, with or without
9 * modification, are permitted provided that the following conditions
10 * are met:
11 * 1. Redistributions of source code must retain the above copyright
12 *    notice, this list of conditions and the following disclaimer.
13 * 2. Redistributions in binary form must reproduce the above copyright
14 *    notice, this list of conditions and the following disclaimer in the
15 *    documentation and/or other materials provided with the distribution.
16 *
17 * THIS SOFTWARE IS PROVIDED BY THE NETBSD FOUNDATION, INC. AND CONTRIBUTORS
18 * ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
19 * TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
20 * PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL THE FOUNDATION OR CONTRIBUTORS
21 * BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
22 * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
23 * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
24 * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
25 * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
26 * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
27 * POSSIBILITY OF SUCH DAMAGE.
28 */
29
30/*
31 * File name recode stuff.
32 *
33 * The utf-8 routines were derived from src/lib/libc/locale/utf2.c.
34 */
35
36#include <sys/param.h>
37#include <sys/systm.h>
38#include <sys/namei.h>
39#include <sys/mount.h>
40
41/* #define NTFS_DEBUG 1 */
42#include <ntfs/ntfs.h>
43#include <ntfs/ntfs_inode.h>
44#include <ntfs/ntfs_subr.h>
45
46/* UTF-8 encoding stuff */
47
48static const int _utf_count[16] = {
49        1, 1, 1, 1, 1, 1, 1, 1,
50        0, 0, 0, 0, 2, 2, 3, 0,
51};
52
53/*
54 * Read one wide character off the string, shift the string pointer
55 * and return the character.
56 */
57wchar
58ntfs_utf8_wget(const char **str)
59{
60	int c;
61	wchar rune = 0;
62	const char *s = *str;
63
64	c = _utf_count[(s[0] >> 4) & 0xf];
65	if (c == 0) {
66		c = 1;
67		goto encoding_error;
68	}
69
70	switch (c) {
71	case 1:
72		rune = s[0] & 0xff;
73		break;
74	case 2:
75		if ((s[1] & 0xc0) != 0x80)
76			goto encoding_error;
77		rune = ((s[0] & 0x1F) << 6) | (s[1] & 0x3F);
78		break;
79	case 3:
80		if ((s[1] & 0xC0) != 0x80 || (s[2] & 0xC0) != 0x80)
81			goto encoding_error;
82		rune = ((s[0] & 0x1F) << 12) | ((s[1] & 0x3F) << 6) |
83		    (s[2] & 0x3F);
84		break;
85	}
86
87encoding_error:
88	*str = *str + c;
89	return rune;
90}
91
92/*
93 * Encode wide character and write it to the string. 'n' specifies
94 * how much space there is in the string. Returns number of bytes written
95 * to the target string.
96 */
97int
98ntfs_utf8_wput(char *s, size_t n, wchar wc)
99{
100        if (wc & 0xf800) {
101                if (n < 3) {
102                        /* bound check failure */
103			DDPRINTF("ntfs_utf8_wput: need 3 bytes\n");
104                        return 0;
105                }
106
107                s[0] = 0xE0 | ((wc >> 12) & 0x0F);
108                s[1] = 0x80 | ((wc >> 6) & 0x3F);
109                s[2] = 0x80 | ((wc) & 0x3F);
110                return 3;
111        } else {
112                if (wc & 0x0780) {
113                        if (n < 2) {
114                                /* bound check failure */
115				DDPRINTF("ntfs_utf8_wput: need 2 bytes\n");
116                                return 0;
117                        }
118
119                        s[0] = 0xC0 | ((wc >> 6) & 0x1F);
120                        s[1] = 0x80 | ((wc) & 0x3F);
121                        return 2;
122                } else {
123                        if (n < 1) {
124                                /* bound check failure */
125				DDPRINTF("ntfs_utf8_wput: need 1 byte\n");
126                                return 0;
127                        }
128
129                        s[0] = wc;
130                        return 1;
131                }
132        }
133}
134
135/*
136 * Compare two wide characters, returning 1, 0, -1 if the first is
137 * bigger, equal or lower than the second.
138 */
139int
140ntfs_utf8_wcmp(wchar wc1, wchar wc2)
141{
142	/* no conversions needed for utf8 */
143
144	if (wc1 == wc2)
145		return 0;
146	else
147		return (int) wc1 - (int) wc2;
148}
149