fdupes-1.40

CHANGES

@@ -7,6 +7,17 @@ those who've otherwise worked on that item. For a list of
 contributors names and identifiers please see the CONTRIBUTORS file.
 
 
+Changes from 1.31 to 1.40
+
+- Added option to omit the first file in each group 
+  of matches. [LM, AL]
+- Added escaping of filenames containing spaces when
+  sameline option is specified. [AL]
+- Changed version indicator format from "fdupes version X.Y"
+  to the simpler "fdupes X.Y". [AL]
+- Changed ordering of options appearing in the help
+  text (--help), manpage, and README file. [AL]
+
 Changes from 1.30 to 1.31
 
 - Added interactive option to preserve all files during

CONTRIBUTORS

@@ -7,5 +7,6 @@ on their contributions. Names are listed in alphabetical order.
  [FD] Frank DENIS aka Jedi/Sector One aka DJ Chrysalis <[email protected]>
  [KK] Kresimir Kukulj <[email protected]>
  [LB] Laurent Bonnaud <[email protected]>
+ [LM] Luca Montecchiani <[email protected]>
 [SSD] Steven S. Dick <[email protected]>
 

Makefile

@@ -13,7 +13,7 @@ MANPAGEDIR = /usr/local/man
 #
 # VERSION determines the program's version number.
 #
-VERSION = "1.31"
+VERSION = "1.40"
 
 #
 # To use the md5sum program for calculating signatures (instead of the
@@ -42,7 +42,7 @@ install: fdupes
 	cp fdupes.1 $(MANPAGEDIR)/man1
 
 tarball: clean
-	tar --directory=.. -c -z -v -f ../fdupes-$(VERSION).tar.gz fdupes
+	tar --directory=.. -c -z -v -f ../fdupes-$(VERSION).tar.gz fdupes-$(VERSION)
 
 clean:
 	rm -f *.o

README

@@ -8,28 +8,33 @@ Usage
 --------------------------------------------------------------------
 Usage: fdupes [options] DIRECTORY...
 
- -r --recurse  		include files residing in subdirectories
- -q --quiet    		hide progress indicator
- -1 --sameline 		list duplicates on a single line
- -S --size     		show size of duplicate files
- -s --symlinks 		follow symlinks
- -H --hardlinks		normally, when two or more files point to the same
-               		disk area they are treated as non-duplicates; this
-               		option will change this behavior
- -n --noempty  		exclude zero-length files from consideration
- -d --delete   		prompt user for files to preserve and delete all others
-               		important: under particular circumstances, data
-               		may be lost when using this option together with -s
-               		or --symlinks, or when specifying a particular
-               		directory more than once; refer to the fdupes
-               		documentation for additional information
- -v --version  		display fdupes version
- -h --help     		display this help message
+ -r --recurse     	include files residing in subdirectories
+ -s --symlinks    	follow symlinks
+ -H --hardlinks   	normally, when two or more files point to the same
+                  	disk area they are treated as non-duplicates; this
+                  	option will change this behavior
+ -n --noempty     	exclude zero-length files from consideration
+ -f --omitfirst   	omit the first file in each set of matches
+ -1 --sameline    	list each set of matches on a single line
+ -S --size        	show size of duplicate files
+ -q --quiet       	hide progress indicator
+ -d --delete      	prompt user for files to preserve and delete all
+                  	others; important: under particular circumstances,
+                  	data may be lost when using this option together
+                  	with -s or --symlinks, or when specifying a
+                  	particular directory more than once; refer to the
+                  	fdupes documentation for additional information
+ -v --version     	display fdupes version
+ -h --help        	display this help message
 
 Unless -1 or --sameline is specified, duplicate files are listed 
 together in groups, each file displayed on a separate line. The
 groups are then separated from each other by blank lines.
 
+When -1 or --sameline is specified, spaces and backslash characters (\) 
+appearing in a filename are preceded by a backslash character. For
+instance, "with spaces" becomes "with\ spaces".
+
 When using -d or --delete, care should be taken to insure against
 accidental data loss. While no information will be immediately
 lost, using this option together with -s or --symlink can lead 

TODO

@@ -1,6 +1,5 @@
 - Add option to highlight or identify symlinked files.
 - Verify correctness of red-black tree algorithm. Optimize.
-- Add quoting of filenames containing spaces when using --sameline.
 - Fix problem where MD5 collisions will result in one of the
   files not being registered (causing it to be ignored).
 

fdupes.1

@@ -21,15 +21,6 @@ byte-by-byte comparison.
 .B -r --recurse
 include files residing in subdirectories
 .TP
-.B -q --quiet
-hide progress indicator
-.TP
-.B -1 --sameline
-list duplicates on a single line
-.TP
-.B -S --size
-show size of duplicate files
-.TP
 .B -s --symlinks
 follow symlinked directories
 .TP
@@ -40,6 +31,18 @@ treated as non-duplicates; this option will change this behavior
 .B -n --noempty
 exclude zero-length files from consideration
 .TP
+.B -f --omitfirst
+omit the first file in each set of matches
+.TP
+.B -1 --sameline
+list each set of matches on a single line
+.TP
+.B -S --size
+show size of duplicate files
+.TP
+.B -q --quiet
+hide progress indicator
+.TP
 .B -d --delete
 prompt user for files to preserve, deleting all others (see
 .B CAVEATS
@@ -61,6 +64,13 @@ or
 is specified, duplicate files are listed
 together in groups, each file displayed on a separate line. The
 groups are then separated from each other by blank lines.
+
+When
+.B -1
+or
+.B --sameline
+is specified, spaces and backslash characters  (\fB\e\fP) appearing
+in a filename are preceded by a backslash character.
 .SH CAVEATS
 If fdupes returns with an error message such as
 .B fdupes: error invoking md5sum

fdupes.c

@@ -37,14 +37,15 @@
 #define ISFLAG(a,b) ((a & b) == b)
 #define SETFLAG(a,b) (a |= b)
 
-#define F_RECURSE           0x01
-#define F_HIDEPROGRESS      0x02
-#define F_DSAMELINE         0x04
-#define F_FOLLOWLINKS       0x08
-#define F_DELETEFILES       0x10
-#define F_EXCLUDEEMPTY      0x20
-#define F_CONSIDERHARDLINKS 0x40
-#define F_SHOWSIZE          0x80
+#define F_RECURSE           0x001
+#define F_HIDEPROGRESS      0x002
+#define F_DSAMELINE         0x004
+#define F_FOLLOWLINKS       0x008
+#define F_DELETEFILES       0x010
+#define F_EXCLUDEEMPTY      0x020
+#define F_CONSIDERHARDLINKS 0x040
+#define F_SHOWSIZE          0x080
+#define F_OMITFIRST         0x100
 
 char *program_name;
 
@@ -89,6 +90,38 @@ void errormsg(char *message, ...)
   vfprintf(stderr, message, ap);
 }
 
+void escapefilename(char *escape_list, char **filename_ptr)
+{
+  int x;
+  int tx;
+  char *tmp;
+  char *filename;
+
+  filename = *filename_ptr;
+
+  tmp = (char*) malloc(strlen(filename) * 2 + 1);
+  if (tmp == NULL) {
+    errormsg("out of memory!\n");
+    exit(1);
+  }
+
+  for (x = 0, tx = 0; x < strlen(filename); x++) {
+    if (strchr(escape_list, filename[x]) != NULL) tmp[tx++] = '\\';
+    tmp[tx++] = filename[x];
+  }
+
+  tmp[tx] = '\0';
+
+  if (x != tx) {
+    *filename_ptr = realloc(*filename_ptr, strlen(tmp) + 1);
+    if (*filename_ptr == NULL) {
+      errormsg("out of memory!\n");
+      exit(1);
+    }
+    strcpy(*filename_ptr, tmp);
+  }
+}
+
 off_t filesize(char *filename) {
   struct stat s;
 
@@ -554,18 +587,22 @@ void printmatches(file_t *files)
 
   while (files != NULL) {
     if (files->hasdupes) {
-      if (ISFLAG(flags, F_SHOWSIZE)) printf("%ld byte%seach:\n", files->size,
-       (files->size != 1) ? "s " : " ");
-      printf("%s%c", files->d_name, ISFLAG(flags, F_DSAMELINE)?' ':'\n');
+      if (!ISFLAG(flags, F_OMITFIRST)) {
+	if (ISFLAG(flags, F_SHOWSIZE)) printf("%ld byte%seach:\n", files->size,
+	 (files->size != 1) ? "s " : " ");
+	if (ISFLAG(flags, F_DSAMELINE)) escapefilename("\\ ", &files->d_name);
+	printf("%s%c", files->d_name, ISFLAG(flags, F_DSAMELINE)?' ':'\n');
+      }
       tmpfile = files->duplicates;
       while (tmpfile != NULL) {
+	if (ISFLAG(flags, F_DSAMELINE)) escapefilename("\\ ", &tmpfile->d_name);
 	printf("%s%c", tmpfile->d_name, ISFLAG(flags, F_DSAMELINE)?' ':'\n');
 	tmpfile = tmpfile->duplicates;
       }
       printf("\n");
 
     }
-
+      
     files = files->next;
   }
 }
@@ -705,23 +742,24 @@ void help_text()
 {
   printf("Usage: fdupes [options] DIRECTORY...\n\n");
 
-  printf(" -r --recurse  \t\tinclude files residing in subdirectories\n");
-  printf(" -q --quiet    \t\thide progress indicator\n");
-  printf(" -1 --sameline \t\tlist duplicates on a single line\n");
-  printf(" -S --size     \t\tshow size of duplicate files\n");
-  printf(" -s --symlinks \t\tfollow symlinks\n");
-  printf(" -H --hardlinks\t\tnormally, when two or more files point to the same\n");
-  printf("               \t\tdisk area they are treated as non-duplicates; this\n"); 
-  printf("               \t\toption will change this behavior\n");
-  printf(" -n --noempty  \t\texclude zero-length files from consideration\n");
-  printf(" -d --delete   \t\tprompt user for files to preserve and delete all others\n"); 
-  printf("               \t\timportant: under particular circumstances, data\n");
-  printf("               \t\tmay be lost when using this option together with -s\n");
-  printf("               \t\tor --symlinks, or when specifying a particular\n");
-  printf("               \t\tdirectory more than once; refer to the fdupes\n");
-  printf("               \t\tdocumentation for additional information\n");
-  printf(" -v --version  \t\tdisplay fdupes version\n");
-  printf(" -h --help     \t\tdisplay this help message\n\n");
+  printf(" -r --recurse     \tinclude files residing in subdirectories\n");
+  printf(" -s --symlinks    \tfollow symlinks\n");
+  printf(" -H --hardlinks   \tnormally, when two or more files point to the same\n");
+  printf("                  \tdisk area they are treated as non-duplicates; this\n"); 
+  printf("                  \toption will change this behavior\n");
+  printf(" -n --noempty     \texclude zero-length files from consideration\n");
+  printf(" -f --omitfirst   \tomit the first file in each set of matches\n");
+  printf(" -1 --sameline    \tlist each set of matches on a single line\n");
+  printf(" -S --size        \tshow size of duplicate files\n");
+  printf(" -q --quiet       \thide progress indicator\n");
+  printf(" -d --delete      \tprompt user for files to preserve and delete all\n"); 
+  printf("                  \tothers; important: under particular circumstances,\n");
+  printf("                  \tdata may be lost when using this option together\n");
+  printf("                  \twith -s or --symlinks, or when specifying a\n");
+  printf("                  \tparticular directory more than once; refer to the\n");
+  printf("                  \tfdupes documentation for additional information\n");
+  printf(" -v --version     \tdisplay fdupes version\n");
+  printf(" -h --help        \tdisplay this help message\n\n");
 }
 
 int main(int argc, char **argv) {
@@ -738,6 +776,7 @@ int main(int argc, char **argv) {
 
   static struct option long_options[] = 
   {
+    { "omitfirst", 0, 0, 'f' },
     { "recurse", 0, 0, 'r' },
     { "quiet", 0, 0, 'q' },
     { "sameline", 0, 0, '1' },
@@ -753,8 +792,11 @@ int main(int argc, char **argv) {
 
   program_name = argv[0];
 
-  while ((opt = getopt_long(argc, argv, "rq1SsHndvh", long_options, NULL)) != EOF) {
+  while ((opt = getopt_long(argc, argv, "frq1SsHndvh", long_options, NULL)) != EOF) {
     switch (opt) {
+    case 'f':
+      SETFLAG(flags, F_OMITFIRST);
+      break;
     case 'r':
       SETFLAG(flags, F_RECURSE);
       break;
@@ -780,7 +822,7 @@ int main(int argc, char **argv) {
       SETFLAG(flags, F_DELETEFILES);
       break;
     case 'v':
-      printf("fdupes version %s\n", VERSION);
+      printf("fdupes %s\n", VERSION);
       exit(0);
     case 'h':
       help_text();

testdir/with spaces a

@@ -0,0 +1 @@
+with spaces

testdir/with spaces b

@@ -0,0 +1 @@
+with spaces