Fixed du. Now behaves just like GNU du (only less so).

 -Erik

4 files changed, 131 insertions, 27 deletions

diff --git a/Changelog b/Changelog
index 98e82df5c..a0cc13aa3 100644
--- a/Changelog
+++ b/Changelog
@@ -8,6 +8,9 @@
 		fork() for running klogd.
 	* nslookup types are now changed to u_int32_t (instead of uint32_t)
 	    changed per a patch from Pascal Bellard <pascal.bellard@ascend.com>
+	* Fixed "du" so it gives the same answers as GNU "du" (busybox du used to
+	    count hard-linked files more then once).  Many thanks to 
+	    Friedrich Vedder <fwv@myrtle.lahn.de> for the fix.
 
 	-Erik Andersen
 
@@ -75,8 +78,8 @@
 	* Fixed a bug where init could have reference already freed memory.
 	    Found and fixed by Taketoshi Sano <kgh12351@nifty.ne.jp>
 	* Several contributions from Friedrich Vedder <fwv@myrtle.lahn.de>
-	* Added (and documented) "-n" option for head - Cleanup for a number of
-	* usage messages -- also 
+	* Added (and documented) "-n" option for head
+	* Cleanup for a number of usage messages -- also 
 	    contributed Friedrich Vedder <fwv@myrtle.lahn.de>
 	* Cosmetic fix to busybox.c (Don't print a comma at the
 	    end of line if there are no more application names).
@@ -87,7 +90,7 @@
 	* Created a tiny tail implementation, removing -c, -q, -v, and making
 	    tail -f work only with a single file.  This reduced tail from 6k to
 	    2.4k.  The bigger/more featured tail can still be had by disabling
-	    BB_FEATURE_SIMPLE_TAIL in dusybox.defs.h
+	    BB_FEATURE_SIMPLE_TAIL in busybox.defs.h
 	* Ping now falls back to doing the right thing if /etc/protocols
 	    turns up missing.
 	* Fixed mount and umount.  Previously they could leak loop device 
diff --git a/TODO b/TODO
index bcba2948c..43419a09b 100644
--- a/TODO
+++ b/TODO
@@ -53,15 +53,6 @@ Some known bugs, todo items, etc...
 -----------------------
 
 
-[andersen@slag busybox]$ ./busybox du /bin
-6213    /bin
-[andersen@slag busybox]$ du /bin
-2971    /bin
-[andersen@slag busybox]$ du --block-size=512 /bin
-5943    /bin
-
------------------------
-
 -rw-r--r-- 1000/1000      4398 2000-01-06 21:55 uniq.c
 -rw-r--r-- 1000/1000      1568 1999-10-20 18:08 update.c
 -rw-r----- 0/1000         1168 2000-01-29 21:03 update.o
@@ -89,13 +80,6 @@ function without this. Will you have the time to add this soon?
 
 -----------------------
 
-
-/bin/busybox --install -s    which makes all links to commands that it
-  can support (an optionnal -s should be used for symbolic links instead
-  of hard links).
-
------------------------
-
 cd /mnt
 mkdir BACKUP
 mv * BACKUP
@@ -105,3 +89,12 @@ work properly either when renaming a directory into something else
 (it produces a lot of disk activity when doing this).
 
 
+-----------------------
+
+
+Feature request:
+
+/bin/busybox --install -s    which makes all links to commands that it
+  can support (an optionnal -s should be used for symbolic links instead
+  of hard links).
+
diff --git a/coreutils/du.c b/coreutils/du.c
index 7b5acb490..02d1d9737 100644
--- a/coreutils/du.c
+++ b/coreutils/du.c
@@ -36,18 +36,32 @@
 
 typedef void (Display) (long, char *);
 
-static const char du_usage[] =
+typedef struct inode_type {
+	struct inode_type *next;
+	ino_t ino;
+} INODETYPE;
+
+#define HASH_SIZE	311		/* Should be prime */
+#define hash_inode(i)	((i) % HASH_SIZE)
 
+static INODETYPE *inode_hash_list[HASH_SIZE];
+
+static const char du_usage[] =
 	"du [OPTION]... [FILE]...\n\n"
+	"Summarize disk space used for each FILE and/or directory.\n"
+	"Disk space is printed in units of 1024 bytes.\n\n"
+	"Options:\n"
+	"\t-l\tcount sizes many times if hard linked\n"
 	"\t-s\tdisplay only a total for each argument\n";
 
 static int du_depth = 0;
+static int count_hardlinks = 0;
 
 static Display *print;
 
 static void print_normal(long size, char *filename)
 {
-	fprintf(stdout, "%-7ld %s\n", size, filename);
+	fprintf(stdout, "%ld\t%s\n", size, filename);
 }
 
 static void print_summary(long size, char *filename)
@@ -57,6 +71,36 @@ static void print_summary(long size, char *filename)
 	}
 }
 
+/* Return 1 if inode is in inode hash list, else return 0 */
+static int is_in_list(const ino_t ino)
+{
+	INODETYPE *inode;
+
+	inode = inode_hash_list[hash_inode(ino)];
+	while (inode != NULL) {
+		if (inode->ino == ino)
+			return 1;
+		inode = inode->next;
+	}
+
+	return 0;
+}
+
+/* Add inode to inode hash list */
+static void add_inode(const ino_t ino)
+{
+	int i;
+	INODETYPE *inode;
+    
+	i = hash_inode(ino);
+	inode = malloc(sizeof(INODETYPE));
+	if (inode == NULL)
+		fatalError("du: Not enough memory.");
+
+	inode->ino = ino;
+	inode->next = inode_hash_list[i];
+	inode_hash_list[i] = inode;
+}
 
 /* tiny recursive du */
 static long du(char *filename)
@@ -72,7 +116,7 @@ static long du(char *filename)
 	du_depth++;
 	sum = (statbuf.st_blocks >> 1);
 
-	/* Don't add in stuff pointed to by links */
+	/* Don't add in stuff pointed to by symbolic links */
 	if (S_ISLNK(statbuf.st_mode)) {
 		return 0;
 	}
@@ -104,6 +148,12 @@ static long du(char *filename)
 		closedir(dir);
 		print(sum, filename);
 	}
+	else if (statbuf.st_nlink > 1 && !count_hardlinks) {
+		/* Add files with hard links only once */
+		if (is_in_list(statbuf.st_ino))
+			return 0;
+		add_inode(statbuf.st_ino);
+	}
 	du_depth--;
 	return sum;
 }
@@ -124,7 +174,11 @@ int du_main(int argc, char **argv)
 			case 's':
 				print = print_summary;
 				break;
+			case 'l':
+				count_hardlinks = 1;
+				break;
 			case 'h':
+			case '-':
 				usage(du_usage);
 				break;
 			default:
@@ -153,4 +207,4 @@ int du_main(int argc, char **argv)
 	exit(0);
 }
 
-/* $Id: du.c,v 1.13 2000/02/13 04:10:57 beppu Exp $ */
+/* $Id: du.c,v 1.14 2000/02/19 18:16:49 erik Exp $ */
diff --git a/du.c b/du.c
index 7b5acb490..02d1d9737 100644
--- a/du.c
+++ b/du.c
@@ -36,18 +36,32 @@
 
 typedef void (Display) (long, char *);
 
-static const char du_usage[] =
+typedef struct inode_type {
+	struct inode_type *next;
+	ino_t ino;
+} INODETYPE;
+
+#define HASH_SIZE	311		/* Should be prime */
+#define hash_inode(i)	((i) % HASH_SIZE)
 
+static INODETYPE *inode_hash_list[HASH_SIZE];
+
+static const char du_usage[] =
 	"du [OPTION]... [FILE]...\n\n"
+	"Summarize disk space used for each FILE and/or directory.\n"
+	"Disk space is printed in units of 1024 bytes.\n\n"
+	"Options:\n"
+	"\t-l\tcount sizes many times if hard linked\n"
 	"\t-s\tdisplay only a total for each argument\n";
 
 static int du_depth = 0;
+static int count_hardlinks = 0;
 
 static Display *print;
 
 static void print_normal(long size, char *filename)
 {
-	fprintf(stdout, "%-7ld %s\n", size, filename);
+	fprintf(stdout, "%ld\t%s\n", size, filename);
 }
 
 static void print_summary(long size, char *filename)
@@ -57,6 +71,36 @@ static void print_summary(long size, char *filename)
 	}
 }
 
+/* Return 1 if inode is in inode hash list, else return 0 */
+static int is_in_list(const ino_t ino)
+{
+	INODETYPE *inode;
+
+	inode = inode_hash_list[hash_inode(ino)];
+	while (inode != NULL) {
+		if (inode->ino == ino)
+			return 1;
+		inode = inode->next;
+	}
+
+	return 0;
+}
+
+/* Add inode to inode hash list */
+static void add_inode(const ino_t ino)
+{
+	int i;
+	INODETYPE *inode;
+    
+	i = hash_inode(ino);
+	inode = malloc(sizeof(INODETYPE));
+	if (inode == NULL)
+		fatalError("du: Not enough memory.");
+
+	inode->ino = ino;
+	inode->next = inode_hash_list[i];
+	inode_hash_list[i] = inode;
+}
 
 /* tiny recursive du */
 static long du(char *filename)
@@ -72,7 +116,7 @@ static long du(char *filename)
 	du_depth++;
 	sum = (statbuf.st_blocks >> 1);
 
-	/* Don't add in stuff pointed to by links */
+	/* Don't add in stuff pointed to by symbolic links */
 	if (S_ISLNK(statbuf.st_mode)) {
 		return 0;
 	}
@@ -104,6 +148,12 @@ static long du(char *filename)
 		closedir(dir);
 		print(sum, filename);
 	}
+	else if (statbuf.st_nlink > 1 && !count_hardlinks) {
+		/* Add files with hard links only once */
+		if (is_in_list(statbuf.st_ino))
+			return 0;
+		add_inode(statbuf.st_ino);
+	}
 	du_depth--;
 	return sum;
 }
@@ -124,7 +174,11 @@ int du_main(int argc, char **argv)
 			case 's':
 				print = print_summary;
 				break;
+			case 'l':
+				count_hardlinks = 1;
+				break;
 			case 'h':
+			case '-':
 				usage(du_usage);
 				break;
 			default:
@@ -153,4 +207,4 @@ int du_main(int argc, char **argv)
 	exit(0);
 }
 
-/* $Id: du.c,v 1.13 2000/02/13 04:10:57 beppu Exp $ */
+/* $Id: du.c,v 1.14 2000/02/19 18:16:49 erik Exp $ */