xref: /netbsd-src/sys/fs/cd9660/cd9660_util.c (revision d48f14661dda8638fee055ba15d35bdfb29b9fa8)
1 /*	$NetBSD: cd9660_util.c,v 1.6 2005/12/11 12:24:25 christos Exp $	*/
2 
3 /*-
4  * Copyright (c) 1994
5  *	The Regents of the University of California.  All rights reserved.
6  *
7  * This code is derived from software contributed to Berkeley
8  * by Pace Willisson (pace@blitz.com).  The Rock Ridge Extension
9  * Support code is derived from software contributed to Berkeley
10  * by Atsushi Murai (amurai@spec.co.jp).
11  *
12  * Redistribution and use in source and binary forms, with or without
13  * modification, are permitted provided that the following conditions
14  * are met:
15  * 1. Redistributions of source code must retain the above copyright
16  *    notice, this list of conditions and the following disclaimer.
17  * 2. Redistributions in binary form must reproduce the above copyright
18  *    notice, this list of conditions and the following disclaimer in the
19  *    documentation and/or other materials provided with the distribution.
20  * 3. Neither the name of the University nor the names of its contributors
21  *    may be used to endorse or promote products derived from this software
22  *    without specific prior written permission.
23  *
24  * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
25  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
26  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
27  * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
28  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
29  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
30  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
31  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
32  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
33  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
34  * SUCH DAMAGE.
35  *
36  *	@(#)cd9660_util.c	8.3 (Berkeley) 12/5/94
37  */
38 
39 #include <sys/cdefs.h>
40 __KERNEL_RCSID(0, "$NetBSD: cd9660_util.c,v 1.6 2005/12/11 12:24:25 christos Exp $");
41 
42 #include <sys/param.h>
43 #include <sys/systm.h>
44 #include <sys/namei.h>
45 #include <sys/resourcevar.h>
46 #include <sys/kernel.h>
47 #include <sys/file.h>
48 #include <sys/stat.h>
49 #include <sys/buf.h>
50 #include <sys/proc.h>
51 #include <sys/mount.h>
52 #include <sys/vnode.h>
53 #include <sys/malloc.h>
54 #include <sys/dirent.h>
55 
56 #include <fs/cd9660/iso.h>
57 #include <fs/cd9660/cd9660_extern.h>
58 
59 #include <fs/unicode.h>
60 
61 static u_int16_t wget(const u_char **, size_t *, int);
62 static int wput(u_char *, size_t, u_int16_t, int);
63 
64 int cd9660_utf8_joliet = 1;
65 
66 /*
67  * Get one character out of an iso filename
68  * Return number of bytes consumed
69  */
70 int
71 isochar(isofn, isoend, joliet_level, c)
72 	const u_char *isofn;
73 	const u_char *isoend;
74 	int joliet_level;
75 	u_int16_t *c;
76 {
77 	*c = isofn[0];
78 	if (joliet_level == 0 || isofn + 1 == isoend) {
79 		/* (00) and (01) are one byte in Joliet, too */
80 		return 1;
81 	}
82 
83 	if (cd9660_utf8_joliet) {
84 		*c = (*c << 8) + isofn[1];
85 	} else {
86 		/* characters outside ISO-8859-1 subset replaced with '?' */
87 		if (*c != 0)
88 			*c = '?';
89 		else
90 			*c = isofn[1];
91 	}
92 
93 	return 2;
94 }
95 
96 /*
97  * translate and compare a filename
98  * Note: Version number plus ';' may be omitted.
99  */
100 int
101 isofncmp(fn, fnlen, isofn, isolen, joliet_level)
102 	const u_char *fn, *isofn;
103 	size_t fnlen, isolen;
104 	int joliet_level;
105 {
106 	int i, j;
107 	u_int16_t fc, ic;
108 	const u_char *isoend = isofn + isolen;
109 
110 	while (fnlen > 0) {
111 		fc = wget(&fn, &fnlen, joliet_level);
112 
113 		if (isofn == isoend)
114 			return fc;
115 		isofn += isochar(isofn, isoend, joliet_level, &ic);
116 		if (ic == ';') {
117 			switch (fc) {
118 			default:
119 				return fc;
120 			case 0:
121 				return 0;
122 			case ';':
123 				break;
124 			}
125 			fn++;
126 			for (i = 0; --fnlen >= 0; i = i * 10 + *fn++ - '0') {
127 				if (*fn < '0' || *fn > '9') {
128 					return -1;
129 				}
130 			}
131 			for (j = 0; isofn != isoend; j = j * 10 + ic - '0')
132 				isofn += isochar(isofn, isoend,
133 						 joliet_level, &ic);
134 			return i - j;
135 		}
136 		if (ic != fc) {
137 			if (ic >= 'A' && ic <= 'Z') {
138 				if (ic + ('a' - 'A') != fc) {
139 					if (fc >= 'a' && fc <= 'z')
140 						fc -= 'a' - 'A';
141 
142 					return (int) fc - (int) ic;
143 				}
144 			} else
145 				return (int) fc - (int) ic;
146 		}
147 	}
148 	if (isofn != isoend) {
149 		isofn += isochar(isofn, isoend, joliet_level, &ic);
150 		switch (ic) {
151 		default:
152 			return -1;
153 		case '.':
154 			if (isofn != isoend) {
155 				isochar(isofn, isoend, joliet_level, &ic);
156 				if (ic == ';')
157 					return 0;
158 			}
159 			return -1;
160 		case ';':
161 			return 0;
162 		}
163 	}
164 	return 0;
165 }
166 
167 /*
168  * translate a filename
169  */
170 void
171 isofntrans(infn, infnlen, outfn, outfnlen, original, casetrans, assoc, joliet_level)
172 	u_char *infn, *outfn;
173 	int infnlen;
174 	u_short *outfnlen;
175 	int original;
176 	int casetrans;
177 	int assoc;
178 	int joliet_level;
179 {
180 	int fnidx = 0;
181 	u_char *infnend = infn + infnlen;
182 	u_int16_t c;
183 	int sz;
184 
185 	if (assoc) {
186 		*outfn++ = ASSOCCHAR;
187 		fnidx++;
188 	}
189 
190 	for(; infn != infnend; fnidx += sz) {
191 		infn += isochar(infn, infnend, joliet_level, &c);
192 
193 		if (casetrans && joliet_level == 0 && c >= 'A' && c <= 'Z')
194 			c = c + ('a' - 'A');
195 		else if (!original && c == ';') {
196 			if (fnidx > 0 && outfn[-1] == '.')
197 				fnidx--;
198 			break;
199 		}
200 
201 		sz = wput(outfn, MAXNAMLEN - fnidx, c, joliet_level);
202 		if (sz == 0) {
203 			/* not enough space to write the character */
204 			if (fnidx < MAXNAMLEN) {
205 				*outfn = '?';
206 				fnidx++;
207 			}
208 			break;
209 		}
210 		outfn += sz;
211 	}
212 	*outfnlen = fnidx;
213 }
214 
215 static u_int16_t
216 wget(const u_char **str, size_t *sz, int joliet_level)
217 {
218 	if (joliet_level > 0 && cd9660_utf8_joliet) {
219 		/* decode UTF-8 sequence */
220 		return wget_utf8((const char **) str, sz);
221 	} else {
222 		/*
223 		 * Raw 8-bit characters without any conversion. For Joliet,
224 		 * this effectively assumes provided file name is using
225 		 * ISO-8859-1 subset.
226 		 */
227 		u_int16_t c = *str[0];
228 		(*str)++;
229 
230 		return c;
231 	}
232 }
233 
234 static int
235 wput(u_char *s, size_t n, u_int16_t c, int joliet_level)
236 {
237 	if (joliet_level > 0 && cd9660_utf8_joliet) {
238 		/* Store Joliet file name encoded into UTF-8 */
239 		return wput_utf8((char *)s, n, c);
240 	} else {
241 		/*
242 		 * Store raw 8-bit characters without any conversion.
243 		 * For Joliet case, this filters the Unicode characters
244 		 * to ISO-8859-1 subset.
245 		 */
246 		*s = (u_char)c;
247 		return 1;
248 	}
249 }
250