New "diff-cache" implementation.

This one is about a million times simpler, and much more likely to be
correct too.

Instead of trying to match up a tree object against the index, we just
read in the tree object side-by-side into the index, and just walk the
resulting index file. This was what all the read-tree cleanups were
all getting to.

cache.h

@@ -99,7 +99,9 @@ extern int read_cache(void);
 extern int write_cache(int newfd, struct cache_entry **cache, int entries);
 extern int cache_name_pos(const char *name, int namelen);
 extern int add_cache_entry(struct cache_entry *ce, int ok_to_add);
+extern int remove_entry_at(int pos);
 extern int remove_file_from_cache(char *path);
+extern int same_name(struct cache_entry *a, struct cache_entry *b);
 extern int cache_match_stat(struct cache_entry *ce, struct stat *st);
 
 #define MTIME_CHANGED	0x0001

diff-cache.c

@@ -1,220 +1,90 @@
 #include "cache.h"
 
 static int cached_only = 0;
-static int recursive = 0;
 static int line_termination = '\n';
 
-static int diff_cache(void *tree, unsigned long size, struct cache_entry **ac, int entries, const char *base);
-
-static void update_tree_entry(void **bufp, unsigned long *sizep)
-{
-	void *buf = *bufp;
-	unsigned long size = *sizep;
-	int len = strlen(buf) + 1 + 20;
-
-	if (size < len)
-		die("corrupt tree file 1 (%s)", size);
-	*bufp = buf + len;
-	*sizep = size - len;
-}
-
-static const unsigned char *extract(void *tree, unsigned long size, const char **pathp, unsigned int *modep)
-{
-	int len = strlen(tree)+1;
-	const unsigned char *sha1 = tree + len;
-	const char *path = strchr(tree, ' ');
-
-	if (!path || size < len + 20 || sscanf(tree, "%o", modep) != 1)
-		die("corrupt tree file 2 (%d)", size);
-	*pathp = path+1;
-	return sha1;
-}
-
-static char *malloc_base(const char *base, const char *path, int pathlen)
-{
-	int baselen = strlen(base);
-	char *newbase = malloc(baselen + pathlen + 2);
-	memcpy(newbase, base, baselen);
-	memcpy(newbase + baselen, path, pathlen);
-	memcpy(newbase + baselen + pathlen, "/", 2);
-	return newbase;
-}
-
-static void show_file(const char *prefix, const char *path, unsigned int mode, const unsigned char *sha1, const char *base);
-
-/* A whole sub-tree went away or appeared */
-static void show_tree(const char *prefix, void *tree, unsigned long size, const char *base)
-{
-	while (size) {
-		const char *path;
-		unsigned int mode;
-		const unsigned char *sha1 = extract(tree, size, &path, &mode);
-		
-		show_file(prefix, path, mode, sha1, base);
-		update_tree_entry(&tree, &size);
-	}
-}
-
 /* A file entry went away or appeared */
-static void show_file(const char *prefix, const char *path, unsigned int mode, const unsigned char *sha1, const char *base)
+static void show_file(const char *prefix, struct cache_entry *ce)
 {
-	if (recursive && S_ISDIR(mode)) {
+	printf("%s%o\t%s\t%s\t%s%c", prefix, ntohl(ce->ce_mode), "blob",
-		char type[20];
+	       sha1_to_hex(ce->sha1), ce->name, line_termination);
-		unsigned long size;
-		char *newbase = malloc_base(base, path, strlen(path));
-		void *tree;
-
-		tree = read_sha1_file(sha1, type, &size);
-		if (!tree || strcmp(type, "tree"))
-			die("corrupt tree sha %s", sha1_to_hex(sha1));
-
-		show_tree(prefix, tree, size, newbase);
-		
-		free(tree);
-		free(newbase);
-		return;
-	}
-
-	printf("%s%o\t%s\t%s\t%s%s%c", prefix, mode,
-	       S_ISDIR(mode) ? "tree" : "blob",
-	       sha1_to_hex(sha1), base, path,
-	       line_termination);
 }
 
-static int compare_tree_entry(const char *path1, unsigned int mode1, const unsigned char *sha1,
+static int show_modified(struct cache_entry *old, struct cache_entry *new)
-			      struct cache_entry **ac, int *entries, const char *base)
 {
-	int baselen = strlen(base);
+	unsigned int mode = ntohl(new->ce_mode), oldmode;
-	struct cache_entry *ce = *ac;
+	unsigned char *sha1 = new->sha1;
-	const char *path2 = ce->name + baselen;
+	unsigned char old_sha1_hex[60];
-	unsigned int mode2 = ntohl(ce->ce_mode);
-	const unsigned char *sha2 = ce->sha1;
-	int cmp, pathlen1, pathlen2;
-	char old_sha1_hex[50];
-
-	pathlen1 = strlen(path1);
-	pathlen2 = strlen(path2);
-	cmp = cache_name_compare(path1, pathlen1, path2, pathlen2);
-	if (cmp < 0) {
-		if (S_ISDIR(mode1)) {
-			char type[20];
-			unsigned long size;
-			void *tree = read_sha1_file(sha1, type, &size);
-			char *newbase = malloc(baselen + 2 + pathlen1);
-
-			memcpy(newbase, base, baselen);
-			memcpy(newbase + baselen, path1, pathlen1);
-			memcpy(newbase + baselen + pathlen1, "/", 2);
-			if (!tree || strcmp(type, "tree"))
-				die("unable to read tree object %s", sha1_to_hex(sha1));
-			*entries = diff_cache(tree, size, ac, *entries, newbase);
-			free(newbase);
-			free(tree);
-			return -1;
-		}
-		show_file("-", path1, mode1, sha1, base);
-		return -1;
-	}
 
 	if (!cached_only) {
 		static unsigned char no_sha1[20];
-		int fd, changed;
+		int changed;
 		struct stat st;
-		fd = open(ce->name, O_RDONLY);
+		if (stat(new->name, &st) < 0) {
-		if (fd < 0 || fstat(fd, &st) < 0) {
+			show_file("-", old);
-			show_file("-", path1, mode1, sha1, base);
 			return -1;
 		}
-		changed = cache_match_stat(ce, &st);
+		changed = cache_match_stat(new, &st);
-		close(fd);
 		if (changed) {
-			mode2 = st.st_mode;
+			mode = st.st_mode;
-			sha2 = no_sha1;
+			sha1 = no_sha1;
 		}
 	}
 
-	if (cmp > 0) {
+	oldmode = ntohl(old->ce_mode);
-		show_file("+", path2, mode2, sha2, base);
+	if (mode == oldmode && !memcmp(sha1, old->sha1, 20))
-		return 1;
-	}
-	if (!memcmp(sha1, sha2, 20) && mode1 == mode2)
 		return 0;
 
-	/*
+	strcpy(old_sha1_hex, sha1_to_hex(old->sha1));
-	 * If the filemode has changed to/from a directory from/to a regular
+	printf("*%o->%o\t%s\t%s->%s\t%s%c", oldmode, mode,
-	 * file, we need to consider it a remove and an add.
+	       "blob",
-	 */
+	       old_sha1_hex, sha1_to_hex(sha1),
-	if (S_ISDIR(mode1) || S_ISDIR(mode2)) {
+	       old->name, line_termination);
-		show_file("-", path1, mode1, sha1, base);
-		show_file("+", path2, mode2, sha2, base);
-		return 0;
-	}
-
-	strcpy(old_sha1_hex, sha1_to_hex(sha1));
-	printf("*%o->%o\t%s\t%s->%s\t%s%s%c", mode1, mode2,
-	       S_ISDIR(mode1) ? "tree" : "blob",
-	       old_sha1_hex, sha1_to_hex(sha2), base, path1,
-	       line_termination);
 	return 0;
 }
 
-static int diff_cache(void *tree, unsigned long size, struct cache_entry **ac, int entries, const char *base)
+static int diff_cache(struct cache_entry **ac, int entries)
 {
-	int baselen = strlen(base);
+	while (entries) {
+		struct cache_entry *ce = *ac;
 
-	for (;;) {
+		/* No matching 0-stage (current) entry? Show it as deleted */
-		struct cache_entry *ce;
+		if (ce_stage(ce)) {
-		unsigned int mode;
+			show_file("-", ce);
-		const char *path;
-		const unsigned char *sha1;
-		int left;
-
-		/*
-		 * No entries in the cache (with this base)?
-		 * Output the tree contents.
-		 */
-		if (!entries || ce_namelen(ce = *ac) < baselen || memcmp(ce->name, base, baselen)) {
-			if (!size)
-				return entries;
-			sha1 = extract(tree, size, &path, &mode);
-			show_file("-", path, mode, sha1, base);
-			update_tree_entry(&tree, &size);
-			continue;
-		}
-
-		/*
-		 * No entries in the tree? Output the cache contents
-		 */
-		if (!size) {
-			show_file("+", ce->name, ntohl(ce->ce_mode), ce->sha1, "");
 			ac++;
 			entries--;
 			continue;
 		}
-
+		/* No matching 1-stage (tree) entry? Show the current one as added */
-		sha1 = extract(tree, size, &path, &mode);
+		if (entries == 1 || !same_name(ce, ac[1])) {
-		left = entries;
+			show_file("-", ce);
-		switch (compare_tree_entry(path, mode, sha1, ac, &left, base)) {
-		case -1:
-			update_tree_entry(&tree, &size);
-			if (left < entries) {
-				ac += (entries - left);
-				entries = left;
-			}
-			continue;
-		case 0:
-			update_tree_entry(&tree, &size);
-			/* Fallthrough */
-		case 1:
 			ac++;
 			entries--;
 			continue;
 		}
-		die("diff-cache: internal error");
+		show_modified(ac[1], ce);
+		ac += 2;
+		entries -= 2;
+		continue;
 	}
 	return 0;
 }
 
+static void remove_merge_entries(void)
+{
+	int i;
+	for (i = 0; i < active_nr; i++) {
+		struct cache_entry *ce = active_cache[i];
+		if (!ce_stage(ce))
+			break;
+		printf("%s: unmerged\n", ce->name);
+		while (remove_entry_at(i)) {
+			if (!ce_stage(active_cache[i]))
+				break;
+		}
+	}
+}
+
 static char *diff_cache_usage = "diff-cache [-r] [-z] [--cached] <tree sha1>";
 
 int main(int argc, char **argv)
@@ -229,7 +99,7 @@ int main(int argc, char **argv)
 		argv++;
 		argc--;
 		if (!strcmp(arg, "-r")) {
-			recursive = 1;
+			/* We accept the -r flag just to look like diff-tree */
 			continue;
 		}
 		if (!strcmp(arg, "-z")) {
@@ -246,9 +116,13 @@ int main(int argc, char **argv)
 	if (argc != 2 || get_sha1_hex(argv[1], tree_sha1))
 		usage(diff_cache_usage);
 
+	remove_merge_entries();
+
 	tree = read_tree_with_tree_or_commit_sha1(tree_sha1, &size, 0);
 	if (!tree)
 		die("bad tree object %s", argv[1]);
+	if (read_tree(tree, size, 1))
+		die("unable to read tree object %s", argv[1]);
 
-	return diff_cache(tree, size, active_cache, active_nr, "");
+	return diff_cache(active_cache, active_nr);
 }

read-cache.c

@@ -87,7 +87,7 @@ int cache_name_pos(const char *name, int namelen)
 }
 
 /* Remove entry, return true if there are more entries to go.. */
-static int remove_entry_at(int pos)
+int remove_entry_at(int pos)
 {
 	active_nr--;
 	if (pos >= active_nr)
@@ -106,7 +106,7 @@ int remove_file_from_cache(char *path)
 	return 0;
 }
 
-static int same_name(struct cache_entry *a, struct cache_entry *b)
+int same_name(struct cache_entry *a, struct cache_entry *b)
 {
 	int len = ce_namelen(a);
 	return ce_namelen(b) == len && !memcmp(a->name, b->name, len);