Updated patches to work with the current trunk.

[rsync/rsync-patches.git] / transliterate.diff

This patch adds an option --tr=BAD/GOOD to transliterate filenames.  It
can be used to remove characters illegal on the destination filesystem.
Jeff Weber expressed interest in this:

http://lists.samba.org/archive/rsync/2007-October/018996.html

This patch is a COMPLETE HACK that covers the most common cases.  Others
are welcome to improve it.

To use this patch, run these commands for a successful build:

    patch -p1 <patches/transliterate.diff
    ./configure                                 (optional if already run)
    make

based-on: 24079e988fc31af4eba56cd2701fdc5a4154980d
diff --git a/flist.c b/flist.c
--- a/flist.c
+++ b/flist.c
@@ -86,6 +86,9 @@ extern int filesfrom_convert;
 extern iconv_t ic_send, ic_recv;
 #endif
 
+extern char *tr_opt, *tr_left, *tr_right;
+extern int tr_right_len;
+
 #ifdef HAVE_UTIMENSAT
 #ifdef HAVE_STRUCT_STAT_ST_MTIM_TV_NSEC
 #define ST_MTIME_NSEC st_mtim.tv_nsec
@@ -673,6 +676,24 @@ static void send_file_entry(int f, const char *fname, struct file_struct *file,
 		stats.total_size += F_LENGTH(file);
 }
 
+static void transliterate(char *thisname)
+{
+	char *p1, *p2, *pleft;
+
+	for (p1 = p2 = thisname; *p1; p1++) {
+		/* Look up the current character in the left string. */
+		pleft = strchr(tr_left, *p1);
+		if (!pleft)
+			/* Not found: no change. */
+			*p2++ = *p1;
+		else if (pleft - tr_left < tr_right_len)
+			/* Store replacement from the right string. */
+			*p2++ = tr_right[pleft - tr_left];
+		/* Otherwise delete. */
+	}
+	*p2 = '\0';
+}
+
 static struct file_struct *recv_file_entry(int f, struct file_list *flist, int xflags)
 {
 	static int64 modtime;
@@ -741,6 +762,9 @@ static struct file_struct *recv_file_entry(int f, struct file_list *flist, int x
 	}
 #endif
 
+	if (tr_opt)
+		transliterate(thisname);
+
 	if (*thisname)
 		clean_fname(thisname, 0);
 
diff --git a/options.c b/options.c
--- a/options.c
+++ b/options.c
@@ -190,6 +190,8 @@ int logfile_format_has_i = 0;
 int logfile_format_has_o_or_i = 0;
 int always_checksum = 0;
 int list_only = 0;
+char *tr_opt = NULL, *tr_left = NULL, *tr_right = NULL;
+int tr_right_len = 0;
 
 #define MAX_BATCH_NAME_LEN 256	/* Must be less than MAXPATHLEN-13 */
 char *batch_name = NULL;
@@ -783,6 +785,7 @@ void usage(enum logcode F)
 #ifdef ICONV_OPTION
   rprintf(F,"     --iconv=CONVERT_SPEC    request charset conversion of filenames\n");
 #endif
+  rprintf(F,"     --tr=BAD/GOOD           transliterate filenames\n");
   rprintf(F," -4, --ipv4                  prefer IPv4\n");
   rprintf(F," -6, --ipv6                  prefer IPv6\n");
   rprintf(F,"     --version               print version number\n");
@@ -996,6 +999,7 @@ static struct poptOption long_options[] = {
   {"iconv",            0,  POPT_ARG_STRING, &iconv_opt, 0, 0, 0 },
   {"no-iconv",         0,  POPT_ARG_NONE,   0, OPT_NO_ICONV, 0, 0 },
 #endif
+  {"tr",               0,  POPT_ARG_STRING, &tr_opt, 0, 0, 0 },
   {"ipv4",            '4', POPT_ARG_VAL,    &default_af_hint, AF_INET, 0, 0 },
   {"ipv6",            '6', POPT_ARG_VAL,    &default_af_hint, AF_INET6, 0, 0 },
   {"8-bit-output",    '8', POPT_ARG_VAL,    &allow_8bit_chars, 1, 0, 0 },
@@ -2232,6 +2236,31 @@ int parse_arguments(int *argc_p, const char ***argv_p)
 		}
 	}
 
+	/* Easiest way to get a local server right is to do this on both sides */
+	if (tr_opt) {
+		if (*tr_opt) {
+			char *p;
+
+			need_unsorted_flist = 1;
+			/* Our mutation shouldn't interfere with transmission of the
+			 * original option to the server. */
+			tr_left = strdup(tr_opt);
+			p = strchr(tr_left, '/');
+			if (p != NULL) {
+				*p = '\0';
+				p++;
+				tr_right = p;
+				tr_right_len = strlen(tr_right);
+				if (strchr(tr_right, '/') != NULL) {
+					snprintf(err_buf, sizeof err_buf,
+						"--tr cannot transliterate slashes\n");
+					return 0;
+				}
+			}
+		} else
+			tr_opt = NULL;
+	}
+
 	am_starting_up = 0;
 
 	return 1;
@@ -2646,6 +2675,12 @@ void server_options(char **args, int *argc_p)
 	else if (remove_source_files)
 		args[ac++] = "--remove-sent-files";
 
+	if (tr_opt) {
+		if (asprintf(&arg, "--tr=%s", tr_opt) < 0)
+			goto oom;
+		args[ac++] = arg;
+	}
+
 	if (ac > MAX_SERVER_ARGS) { /* Not possible... */
 		rprintf(FERROR, "argc overflow in server_options().\n");
 		exit_cleanup(RERR_MALLOC);
diff --git a/rsync.yo b/rsync.yo
--- a/rsync.yo
+++ b/rsync.yo
@@ -436,6 +436,7 @@ to the detailed description below for a complete description.  verb(
      --read-batch=FILE       read a batched update from FILE
      --protocol=NUM          force an older protocol version to be used
      --iconv=CONVERT_SPEC    request charset conversion of filenames
+     --tr=BAD/GOOD           transliterate filenames
      --checksum-seed=NUM     set block/file checksum seed (advanced)
  -4, --ipv4                  prefer IPv4
  -6, --ipv6                  prefer IPv6
@@ -2359,6 +2360,22 @@ daemon uses the charset specified in its "charset" configuration parameter
 regardless of the remote charset you actually pass.  Thus, you may feel free to
 specify just the local charset for a daemon transfer (e.g. bf(--iconv=utf8)).
 
+dit(bf(--tr=BAD/GOOD)) Transliterates filenames on the receiver, after the
+iconv conversion (if any).  This can be used to remove characters illegal
+on the destination filesystem.  If you use this option, consider saving a
+"find . -ls" listing of the source in the destination to help you determine
+the original filenames in case of need.
+
+The argument consists of a string of characters to remove, optionally
+followed by a slash and a string of corresponding characters with which to
+replace them.  The second string may be shorter, in which case any leftover
+characters in the first string are simply deleted.  For example,
+bf(--tr=':\/!') replaces colons with exclamation marks and deletes backslashes.
+Slashes cannot be transliterated because it would cause havoc.
+
+If the receiver is invoked over a remote shell, use bf(--protect-args) to
+stop the shell from interpreting any nasty characters in the argument.
+
 dit(bf(-4, --ipv4) or bf(-6, --ipv6)) Tells rsync to prefer IPv4/IPv6
 when creating sockets.  This only affects sockets that rsync has direct
 control over, such as the outgoing socket when directly contacting an