sys/fs/cd9660/cd9660_util.c

   1 /*      $NetBSD: cd9660_util.c,v 1.12 2014/11/10 18:46:33 maxv 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 1.12 2014/11/10 18:46:33 maxv 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/dirent.h>
  54
  55 #include <fs/cd9660/iso.h>
  56 #include <fs/cd9660/cd9660_extern.h>
  57
  58 #include <fs/unicode.h>
  59
  60 static u_int16_t wget(const u_char **, size_t *, int);
  61 static int wput(u_char *, size_t, u_int16_t, int);
  62
  63 int cd9660_utf8_joliet = 1;
  64
  65 /*
  66  * Get one character out of an iso filename
  67  * Return number of bytes consumed
  68  */
  69 int
  70 isochar(const u_char *isofn, const u_char *isoend, int joliet_level,
  71         u_int16_t *c)
  72 {
  73         *c = isofn[0];
  74         if (joliet_level == 0 || isofn + 1 == isoend) {
  75                 /* (00) and (01) are one byte in Joliet, too */
  76                 return 1;
  77         }
  78
  79         if (cd9660_utf8_joliet) {
  80                 *c = (*c << 8) + isofn[1];
  81         } else {
  82                 /* characters outside ISO-8859-1 subset replaced with '?' */
  83                 if (*c != 0)
  84                         *c = '?';
  85                 else
  86                         *c = isofn[1];
  87         }
  88
  89         return 2;
  90 }
  91
  92 /*
  93  * translate and compare a filename
  94  * Note: Version number plus ';' may be omitted.
  95  */
  96 int
  97 isofncmp(const u_char *fn, size_t fnlen, const u_char *isofn, size_t isolen,
  98         int joliet_level)
  99 {
 100         int i, j;
 101         u_int16_t fc, ic;
 102         const u_char *isoend = isofn + isolen;
 103
 104         while (fnlen > 0) {
 105                 fc = wget(&fn, &fnlen, joliet_level);
 106
 107                 if (isofn == isoend)
 108                         return fc;
 109                 isofn += isochar(isofn, isoend, joliet_level, &ic);
 110                 if (ic == ';') {
 111                         switch (fc) {
 112                         default:
 113                                 return fc;
 114                         case 0:
 115                                 return 0;
 116                         case ';':
 117                                 break;
 118                         }
 119                         for (i = 0; fnlen-- != 0; i = i * 10 + *fn++ - '0') {
 120                                 if (*fn < '0' || *fn > '9') {
 121                                         return -1;
 122                                 }
 123                         }
 124                         for (j = 0; isofn != isoend; j = j * 10 + ic - '0')
 125                                 isofn += isochar(isofn, isoend,
 126                                                  joliet_level, &ic);
 127                         return i - j;
 128                 }
 129                 if (ic != fc) {
 130                         if (ic >= 'A' && ic <= 'Z') {
 131                                 if (ic + ('a' - 'A') != fc) {
 132                                         if (fc >= 'a' && fc <= 'z')
 133                                                 fc -= 'a' - 'A';
 134
 135                                         return (int) fc - (int) ic;
 136                                 }
 137                         } else
 138                                 return (int) fc - (int) ic;
 139                 }
 140         }
 141         if (isofn != isoend) {
 142                 isofn += isochar(isofn, isoend, joliet_level, &ic);
 143                 switch (ic) {
 144                 default:
 145                         return -1;
 146                 case '.':
 147                         if (isofn != isoend) {
 148                                 isochar(isofn, isoend, joliet_level, &ic);
 149                                 if (ic == ';')
 150                                         return 0;
 151                         }
 152                         return -1;
 153                 case ';':
 154                         return 0;
 155                 }
 156         }
 157         return 0;
 158 }
 159
 160 /*
 161  * translate a filename
 162  */
 163 void
 164 isofntrans(const u_char *infn, int infnlen, u_char *outfn, u_short *outfnlen,
 165         int original, int casetrans, int assoc, int joliet_level)
 166 {
 167         int fnidx = 0;
 168         const u_char *infnend = infn + infnlen;
 169         u_int16_t c;
 170         int sz;
 171
 172         if (assoc) {
 173                 *outfn++ = ASSOCCHAR;
 174                 fnidx++;
 175         }
 176
 177         for(; infn != infnend; fnidx += sz) {
 178                 infn += isochar(infn, infnend, joliet_level, &c);
 179
 180                 if (casetrans && joliet_level == 0 && c >= 'A' && c <= 'Z')
 181                         c = c + ('a' - 'A');
 182                 else if (!original && c == ';') {
 183                         if (fnidx > 0 && outfn[-1] == '.')
 184                                 fnidx--;
 185                         break;
 186                 }
 187
 188                 sz = wput(outfn, ISO_MAXNAMLEN - fnidx, c, joliet_level);
 189                 if (sz == 0) {
 190                         /* not enough space to write the character */
 191                         if (fnidx < ISO_MAXNAMLEN) {
 192                                 *outfn = '?';
 193                                 fnidx++;
 194                         }
 195                         break;
 196                 }
 197                 outfn += sz;
 198         }
 199         *outfnlen = fnidx;
 200 }
 201
 202 static u_int16_t
 203 wget(const u_char **str, size_t *sz, int joliet_level)
 204 {
 205         if (joliet_level > 0 && cd9660_utf8_joliet) {
 206                 /* decode UTF-8 sequence */
 207                 return wget_utf8((const char **) str, sz);
 208         } else {
 209                 /*
 210                  * Raw 8-bit characters without any conversion. For Joliet,
 211                  * this effectively assumes provided file name is using
 212                  * ISO-8859-1 subset.
 213                  */
 214                 u_int16_t c = *str[0];
 215                 (*str)++;
 216                 (*sz)--;
 217
 218                 return c;
 219         }
 220 }
 221
 222 static int
 223 wput(u_char *s, size_t n, u_int16_t c, int joliet_level)
 224 {
 225         if (joliet_level > 0 && cd9660_utf8_joliet) {
 226                 /* Store Joliet file name encoded into UTF-8 */
 227                 return wput_utf8((char *)s, n, c);
 228         } else {
 229                 /*
 230                  * Store raw 8-bit characters without any conversion.
 231                  * For Joliet case, this filters the Unicode characters
 232                  * to ISO-8859-1 subset.
 233                  */
 234                 *s = (u_char)c;
 235                 return 1;
 236         }
 237 }