Hi,
Several days ago I got a CD with Russian filenames on it and discovered that
I'm unable to read those filenames. After some hacking I produced a patch,
which should solve this problem in the manner similar to what we have in
msdosfs module (i.e. user-provided conversion table). I have to emphasize that
it's a temporary solution until we will have iconv support in kernel.
Please somebody review attached patches.
-Maxim
Index: cd9660/cd9660_lookup.c
===================================================================
RCS file: /home/ncvs/src/sys/isofs/cd9660/cd9660_lookup.c,v
retrieving revision 1.25
diff -d -u -r1.25 cd9660_lookup.c
--- cd9660/cd9660_lookup.c 2000/10/03 04:39:50 1.25
+++ cd9660/cd9660_lookup.c 2000/12/27 10:03:04
@@ -239,7 +239,7 @@
if (namelen != 1
|| ep->name[0] != 0)
goto notfound;
- } else if (!(res = isofncmp(name, len, ep->name,
namelen, imp->joliet_level))) {
+ } else if (!(res = isofncmp(name, len, ep->name,
+namelen, imp->joliet_level, imp->ctable))) {
if (isoflags & 2)
ino = isodirino(ep, imp);
else
Index: cd9660/cd9660_mount.h
===================================================================
RCS file: /home/ncvs/src/sys/isofs/cd9660/cd9660_mount.h,v
retrieving revision 1.4
diff -d -u -r1.4 cd9660_mount.h
--- cd9660/cd9660_mount.h 2000/05/01 20:05:04 1.4
+++ cd9660/cd9660_mount.h 2000/12/27 10:03:04
@@ -47,6 +47,7 @@
struct export_args export; /* network export info */
int flags; /* mounting flags, see below */
int ssector; /* starting sector, 0 for 1st session */
+ u_char *ctable[256]; /* Table for converting unicode filenames */
};
#define ISOFSMNT_NORRIP 0x00000001 /* disable Rock Ridge Ext.*/
#define ISOFSMNT_GENS 0x00000002 /* enable generation numbers */
Index: cd9660/cd9660_rrip.c
===================================================================
RCS file: /home/ncvs/src/sys/isofs/cd9660/cd9660_rrip.c,v
retrieving revision 1.18
diff -d -u -r1.18 cd9660_rrip.c
--- cd9660/cd9660_rrip.c 2000/05/05 09:58:17 1.18
+++ cd9660/cd9660_rrip.c 2000/12/27 10:03:05
@@ -301,7 +301,7 @@
{
isofntrans(isodir->name,isonum_711(isodir->name_len),
ana->outbuf,ana->outlen,
- 1,isonum_711(isodir->flags)&4, ana->imp->joliet_level);
+ 1,isonum_711(isodir->flags)&4, ana->imp->joliet_level,
+ana->imp->ctable);
switch (*ana->outbuf) {
default:
break;
@@ -509,7 +509,7 @@
pwhead = isodir->name + isonum_711(isodir->name_len);
if (!(isonum_711(isodir->name_len)&1))
pwhead++;
- isochar(isodir->name, pwhead, ana->imp->joliet_level, &c);
+ isochar(isodir->name, pwhead, ana->imp->joliet_level, &c, ana->imp->ctable);
/* If it's not the '.' entry of the root dir obey SP field */
if (c != 0 || isonum_733(isodir->extent) != ana->imp->root_extent)
@@ -646,7 +646,7 @@
*outlen = 0;
isochar(isodir->name, isodir->name + isonum_711(isodir->name_len),
- imp->joliet_level, &c);
+ imp->joliet_level, &c, imp->ctable);
tab = rrip_table_getname;
if (c == 0 || c == 1) {
cd9660_rrip_defname(isodir,&analyze);
Index: cd9660/cd9660_util.c
===================================================================
RCS file: /home/ncvs/src/sys/isofs/cd9660/cd9660_util.c,v
retrieving revision 1.15
diff -d -u -r1.15 cd9660_util.c
--- cd9660/cd9660_util.c 2000/10/29 13:56:43 1.15
+++ cd9660/cd9660_util.c 2000/12/27 10:03:05
@@ -52,25 +52,28 @@
* Return number of bytes consumed
*/
int
-isochar(isofn, isoend, joliet_level, c)
+isochar(isofn, isoend, joliet_level, c, ctable)
u_char *isofn;
u_char *isoend;
int joliet_level;
u_char *c;
+ u_char **ctable;
{
*c = *isofn++;
if (joliet_level == 0 || isofn == isoend)
/* (00) and (01) are one byte in Joliet, too */
return 1;
- /* No Unicode support yet :-( */
+ /* Limited Unicode support yet :-( */
+ /* (requires user-supplied conversion table) */
switch (*c) {
- default:
- *c = '?';
- break;
- case '\0':
+ case '\0': /* ANSI */
*c = *isofn;
break;
+ default:
+ if ((ctable[*c] == NULL) || ((*c = ctable[*c][*isofn]) == '\0'))
+ *c = '?';
+ break;
}
return 2;
}
@@ -81,12 +84,13 @@
* Note: Version number plus ';' may be omitted.
*/
int
-isofncmp(fn, fnlen, isofn, isolen, joliet_level)
+isofncmp(fn, fnlen, isofn, isolen, joliet_level, ctable)
u_char *fn;
int fnlen;
u_char *isofn;
int isolen;
int joliet_level;
+ u_char **ctable;
{
int i, j;
u_char c, *fnend = fn + fnlen, *isoend = isofn + isolen;
@@ -94,7 +98,7 @@
for (; fn != fnend; fn++) {
if (isofn == isoend)
return *fn;
- isofn += isochar(isofn, isoend, joliet_level, &c);
+ isofn += isochar(isofn, isoend, joliet_level, &c, ctable);
if (c == ';') {
if (*fn++ != ';')
return fn[-1];
@@ -105,7 +109,7 @@
}
for (j = 0; isofn != isoend; j = j * 10 + c - '0')
isofn += isochar(isofn, isoend,
- joliet_level, &c);
+ joliet_level, &c, ctable);
return i - j;
}
if (c != *fn) {
@@ -121,13 +125,13 @@
}
}
if (isofn != isoend) {
- isofn += isochar(isofn, isoend, joliet_level, &c);
+ isofn += isochar(isofn, isoend, joliet_level, &c, ctable);
switch (c) {
default:
return -c;
case '.':
if (isofn != isoend) {
- isochar(isofn, isoend, joliet_level, &c);
+ isochar(isofn, isoend, joliet_level, &c, ctable);
if (c == ';')
return 0;
}
@@ -143,7 +147,7 @@
* translate a filename of length > 0
*/
void
-isofntrans(infn, infnlen, outfn, outfnlen, original, assoc, joliet_level)
+isofntrans(infn, infnlen, outfn, outfnlen, original, assoc, joliet_level, ctable)
u_char *infn;
int infnlen;
u_char *outfn;
@@ -151,6 +155,7 @@
int original;
int assoc;
int joliet_level;
+ u_char **ctable;
{
int fnidx = 0;
u_char c, d = '\0', *infnend = infn + infnlen;
@@ -160,7 +165,7 @@
fnidx++;
}
for (; infn != infnend; fnidx++) {
- infn += isochar(infn, infnend, joliet_level, &c);
+ infn += isochar(infn, infnend, joliet_level, &c, ctable);
if (!original && !joliet_level && c >= 'A' && c <= 'Z')
*outfn++ = c + ('a' - 'A');
Index: cd9660/cd9660_vfsops.c
===================================================================
RCS file: /home/ncvs/src/sys/isofs/cd9660/cd9660_vfsops.c,v
retrieving revision 1.81
diff -d -u -r1.81 cd9660_vfsops.c
--- cd9660/cd9660_vfsops.c 2000/12/08 21:50:31 1.81
+++ cd9660/cd9660_vfsops.c 2000/12/27 10:03:06
@@ -284,6 +284,7 @@
struct iso_supplementary_descriptor *sup = NULL;
struct iso_directory_record *rootp;
int logical_block_size;
+ int i;
if (!(mp->mnt_flag & MNT_RDONLY))
return EROFS;
@@ -502,6 +503,13 @@
supbp = NULL;
}
+ for (i = 0; i < 256; i++)
+ if (argp->ctable[i] != NULL) {
+ isomp->ctable[i] = malloc(256 * sizeof(u_char), M_ISOFSMNT,
+M_WAITOK);
+ if (error = copyin(argp->ctable[i], isomp->ctable[i], 256 *
+sizeof(u_char)))
+ goto out;
+ }
+
return 0;
out:
devvp->v_rdev->si_mountpoint = NULL;
@@ -514,6 +522,9 @@
if (needclose)
(void)VOP_CLOSE(devvp, FREAD, NOCRED, p);
if (isomp) {
+ for (i = 0; i < 256; i++)
+ if (isomp->ctable[i] != NULL)
+ free((caddr_t)isomp->ctable[i], M_ISOFSMNT);
free((caddr_t)isomp, M_ISOFSMNT);
mp->mnt_data = (qaddr_t)0;
}
@@ -530,7 +541,7 @@
struct proc *p;
{
register struct iso_mnt *isomp;
- int error, flags = 0;
+ int i, error, flags = 0;
if (mntflags & MNT_FORCE)
flags |= FORCECLOSE;
@@ -547,6 +558,9 @@
isomp->im_devvp->v_rdev->si_mountpoint = NULL;
error = VOP_CLOSE(isomp->im_devvp, FREAD, NOCRED, p);
vrele(isomp->im_devvp);
+ for (i = 0; i < 256; i++)
+ if (isomp->ctable[i] != NULL)
+ free((caddr_t)isomp->ctable[i], M_ISOFSMNT);
free((caddr_t)isomp, M_ISOFSMNT);
mp->mnt_data = (qaddr_t)0;
mp->mnt_flag &= ~MNT_LOCAL;
Index: cd9660/cd9660_vnops.c
===================================================================
RCS file: /home/ncvs/src/sys/isofs/cd9660/cd9660_vnops.c,v
retrieving revision 1.67
diff -d -u -r1.67 cd9660_vnops.c
--- cd9660/cd9660_vnops.c 2000/08/29 14:45:47 1.67
+++ cd9660/cd9660_vnops.c 2000/12/27 10:03:08
@@ -556,7 +556,7 @@
idp->current.d_name, &namelen,
imp->iso_ftype == ISO_FTYPE_9660,
isonum_711(ep->flags)&4,
- imp->joliet_level);
+ imp->joliet_level, imp->ctable);
idp->current.d_namlen = (u_char)namelen;
if (imp->iso_ftype == ISO_FTYPE_DEFAULT)
error = iso_shipdir(idp);
Index: cd9660/iso.h
===================================================================
RCS file: /home/ncvs/src/sys/isofs/cd9660/iso.h,v
retrieving revision 1.20
diff -d -u -r1.20 iso.h
--- cd9660/iso.h 2000/06/29 01:19:12 1.20
+++ cd9660/iso.h 2000/12/27 10:03:08
@@ -246,6 +246,8 @@
int rr_skip0;
int joliet_level;
+
+ u_char *ctable[256];
};
#define VFSTOISOFS(mp) ((struct iso_mnt *)((mp)->mnt_data))
@@ -266,9 +268,10 @@
extern vop_t **cd9660_specop_p;
extern vop_t **cd9660_fifoop_p;
-int isochar __P((u_char *, u_char *, int, u_char *));
-int isofncmp __P((u_char *, int, u_char *, int, int));
-void isofntrans __P((u_char *, int, u_char *, u_short *, int, int, int));
+int isochar __P((u_char *, u_char *, int, u_char *, u_char **));
+int isofncmp __P((u_char *, int, u_char *, int, int, u_char **));
+void isofntrans __P((u_char *, int, u_char *, u_short *, int, int, int, \
+ u_char **));
ino_t isodirino __P((struct iso_directory_record *, struct iso_mnt *));
#endif /* _KERNEL */
Index: mount_cd9660/Makefile
===================================================================
RCS file: /home/ncvs/src/sbin/mount_cd9660/Makefile,v
retrieving revision 1.4
diff -d -u -r1.4 Makefile
--- mount_cd9660/Makefile 1998/01/20 10:39:58 1.4
+++ mount_cd9660/Makefile 2000/12/27 10:03:08
@@ -1,11 +1,23 @@
-# @(#)Makefile 8.3 (Berkeley) 3/27/94
+#
+# $FreeBSD$
+#
PROG= mount_cd9660
SRCS= mount_cd9660.c getmntopts.c
MAN8= mount_cd9660.8
+DPADD= ${LIBUTIL}
+LDADD= -lutil
MOUNT= ${.CURDIR}/../mount
CFLAGS+= -I${MOUNT}
.PATH: ${MOUNT}
+
+TABDIR= ${DESTDIR}${LIBDATADIR}/cd9660
+TABLES= unic2koi
+
+afterinstall:
+ cd ${.CURDIR} && \
+ ${INSTALL} -c -o ${BINOWN} -g ${BINGRP} -m ${SHAREMODE} \
+ ${TABLES} ${TABDIR}
.include <bsd.prog.mk>
Index: mount_cd9660/mount_cd9660.8
===================================================================
RCS file: /home/ncvs/src/sbin/mount_cd9660/mount_cd9660.8,v
retrieving revision 1.13
diff -d -u -r1.13 mount_cd9660.8
--- mount_cd9660/mount_cd9660.8 2000/11/20 16:47:32 1.13
+++ mount_cd9660/mount_cd9660.8 2000/12/27 10:03:08
@@ -47,6 +47,7 @@
.Op Fl egjrv
.Op Fl o Ar options
.Op Fl s Ar startsector
+.Op Fl W Ar table
.Ar special | node
.Sh DESCRIPTION
The
@@ -114,6 +115,13 @@
is printing.
.It Fl v
Be verbose about the starting sector decisions made.
+.It Fl W Ar table
+Specify text file with conversion tables for Unicode filenames.
+.El
+.Sh FILES
+.Bl -tag -width /usr/libdata/cd9660 -compact
+.It Pa /usr/libdata/cd9660
+default place for character sets conversion tables
.El
.Sh SEE ALSO
.Xr cdcontrol 1 ,
Index: mount_cd9660/mount_cd9660.c
===================================================================
RCS file: /home/ncvs/src/sbin/mount_cd9660/mount_cd9660.c,v
retrieving revision 1.15
diff -d -u -r1.15 mount_cd9660.c
--- mount_cd9660/mount_cd9660.c 1999/10/09 11:54:08 1.15
+++ mount_cd9660/mount_cd9660.c 2000/12/27 10:03:09
@@ -58,12 +58,14 @@
#include <sys/mount.h>
#include <sys/../isofs/cd9660/cd9660_mount.h>
+#include <ctype.h>
#include <err.h>
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <sysexits.h>
#include <unistd.h>
+#include <libutil.h>
#include "mntopts.h"
@@ -79,6 +81,7 @@
int get_ssector(const char *dev);
void usage(void);
+int load_ctable(const char *name, u_char *ctable[256]);
int
main(int argc, char **argv)
@@ -92,7 +95,7 @@
mntflags = opts = verbose = 0;
memset(&args, 0, sizeof args);
args.ssector = -1;
- while ((ch = getopt(argc, argv, "egjo:rs:v")) != -1)
+ while ((ch = getopt(argc, argv, "egjo:rs:vW:")) != -1)
switch (ch) {
case 'e':
opts |= ISOFSMNT_EXTATT;
@@ -115,6 +118,9 @@
case 'v':
verbose++;
break;
+ case 'W':
+ load_ctable(optarg, args.ctable);
+ break;
case '?':
default:
usage();
@@ -184,7 +190,8 @@
usage(void)
{
(void)fprintf(stderr,
- "usage: mount_cd9660 [-egrv] [-o options] [-s startsector] special
node\n");
+ "usage: mount_cd9660 [-egrv] [-o options] [-s startsector] " \
+ "[-W table] special node\n");
exit(EX_USAGE);
}
@@ -228,4 +235,73 @@
return -1;
return ntohl(toc_buffer[i].addr.lba);
+}
+
+int
+load_ctable (const char *name, u_char *ctable[256])
+{
+ FILE *f;
+ int i, j, base, num;
+ int ci[16];
+ size_t line = 0;
+ char buf[128];
+ char *fn, *s, *p;
+ u_char *code, *cp;
+
+ if (*name == '/')
+ fn = (char *)name;
+ else {
+ snprintf(buf, sizeof(buf), "/usr/libdata/cd9660/%s", name);
+ buf[127] = '\0';
+ fn = buf;
+ }
+ if ((f = fopen(fn, "r")) == NULL)
+ err(EX_NOINPUT, "%s", fn);
+ p = NULL;
+ code = NULL;
+ num = 0;
+ do {
+ base = -1;
+ if (code == NULL)
+ code = malloc(256);
+ cp = code;
+ for (i = 0; i < 17; i++) {
+ do {
+ if (p != NULL) free(p);
+ p = s = fparseln(f, NULL, &line, NULL, 0);
+ if (s == NULL)
+ break;
+ while (isspace((unsigned char)*s))
+ s++;
+ } while (*s == '\0');
+ if (s == NULL)
+ break;
+ if (base == -1) {
+ if ((sscanf(s, "Base: %i", &base) != 1) || (base < 0) \
+ || (base > 255))
+ errx(EX_DATAERR, "unicode conversion table:
+missing" \
+ " or invalid base in line %d", line);
+ } else {
+ if (sscanf(s, "%i%i%i%i%i%i%i%i%i%i%i%i%i%i%i%i",
+ ci, ci + 1, ci + 2, ci + 3, ci + 4, ci + 5,
+ \
+ ci + 6, ci + 7, ci + 8, ci + 9, ci + 10, ci + 11,
+ \
+ ci + 12, ci + 13, ci + 14, ci + 15) != 16)
+ errx(EX_DATAERR, "unicode conversion table:
+missing" \
+ " or invalid item(s) in row %d, line %d", i,
+line);
+ for (j = 0; j < 16; j++)
+ *cp++ = ci[j];
+ }
+ }
+ if (cp == code + 256) {
+ ctable[base] = code;
+ code = NULL;
+ num++;
+ } else if (base != -1)
+ errx(EX_DATAERR, "truncated unicode conversion table near line
+%d", \
+ line);
+ } while (feof(f) == 0);
+ free(p);
+ fclose(f);
+
+ return num;
}
Index: mount_cd9660/unic2koi
===================================================================
RCS file: unic2koi
diff -N unic2koi
--- /dev/null Wed Dec 27 02:00:25 2000
+++ unic2koi Wed Dec 27 02:03:09 2000
@@ -0,0 +1,25 @@
+# $FreeBSD$
+#
+# unic2koi: 16 rows of Unicode -> KOI8-U conversion table
+#
+# `Base' specifies the first byte of Unicode charcode, so for example the
+# second value in the table `0xb3' means that Unicode character with code
+# `0x0401' should be maped into single byte character `0xb3'.
+
+Base: 0x04
+0x00 0xb3 0x00 0x00 0xb4 0x00 0xb6 0xb7 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00
+0xe1 0xe2 0xf7 0xe7 0xe4 0xe5 0xf6 0xfa 0xe9 0xea 0xeb 0xec 0xed 0xee 0xef 0xf0
+0xf2 0xf3 0xf4 0xf5 0xe6 0xe8 0xe3 0xfe 0xfb 0xfd 0xff 0xf9 0xf8 0xfc 0xe0 0xf1
+0xc1 0xc2 0xd7 0xc7 0xc4 0xc5 0xd6 0xda 0xc9 0xca 0xcb 0xcc 0xcd 0xce 0xcf 0xd0
+0xd2 0xd3 0xd4 0xd5 0xc6 0xc8 0xc3 0xde 0xdb 0xdd 0xdf 0xd9 0xd8 0xdc 0xc0 0xd1
+0x00 0xa3 0x00 0x00 0xa4 0x00 0xa6 0xa7 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00
+0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00
+0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00
+0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00
+0xbd 0xad 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00
+0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00
+0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00
+0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00
+0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00
+0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00
+0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00 0x00
