Merge branch 'jc/merge-subtree'

* jc/merge-subtree:
  A new merge stragety 'subtree'.

It is safe to merge this early as this is a feature that user
explicitly needs to ask for and would not trigger otherwise.  A
known issue with the current implementation is that the subtree
matching heuristics is very stupid.  It could run ls-tree twice
and try to count intersection.

Giving it wider audience would help it to get improved by
motivated volunteers.

Signed-off-by: Junio C Hamano <junkio@cox.net>

7 files changed, 373 insertions, 3 deletions

diff --git a/.gitignore b/.gitignore
index b39f78fcdf..9229e918cd 100644
--- a/.gitignore
+++ b/.gitignore
@@ -77,6 +77,7 @@ git-merge-ours
 git-merge-recursive
 git-merge-resolve
 git-merge-stupid
+git-merge-subtree
 git-mergetool
 git-mktag
 git-mktree
@@ -148,6 +149,7 @@ test-chmtime
 test-date
 test-delta
 test-dump-cache-tree
+test-match-trees
 common-cmds.h
 *.tar.gz
 *.dsc
diff --git a/Makefile b/Makefile
index ac29c629e3..a77d31de98 100644
--- a/Makefile
+++ b/Makefile
@@ -251,6 +251,8 @@ BUILT_INS = \
 # what 'all' will build and 'install' will install, in gitexecdir
 ALL_PROGRAMS = $(PROGRAMS) $(SCRIPTS)
 
+ALL_PROGRAMS += git-merge-subtree$X
+
 # what 'all' will build but not install in gitexecdir
 OTHER_PROGRAMS = git$X gitweb/gitweb.cgi
 ifndef NO_TCLTK
@@ -299,7 +301,7 @@ LIB_OBJS = \
 	server-info.o setup.o sha1_file.o sha1_name.o strbuf.o \
 	tag.o tree.o usage.o config.o environment.o ctype.o copy.o \
 	revision.o pager.o tree-walk.o xdiff-interface.o \
-	write_or_die.o trace.o list-objects.o grep.o \
+	write_or_die.o trace.o list-objects.o grep.o match-trees.o \
 	alloc.o merge-file.o path-list.o help.o unpack-trees.o $(DIFF_OBJS) \
 	color.o wt-status.o archive-zip.o archive-tar.o shallow.o utf8.o \
 	convert.o
@@ -725,6 +727,9 @@ git$X: git.c common-cmds.h $(BUILTIN_OBJS) $(GITLIBS) GIT-CFLAGS
 
 help.o: common-cmds.h
 
+git-merge-subtree$X: git-merge-recursive$X
+	rm -f $@ && ln git-merge-recursive$X $@
+
 $(BUILT_INS): git$X
 	$(QUIET_BUILT_IN)rm -f $@ && ln git$X $@
 
@@ -942,6 +947,9 @@ test-dump-cache-tree$X: dump-cache-tree.o $(GITLIBS)
 test-sha1$X: test-sha1.o $(GITLIBS)
 	$(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) $(LIBS)
 
+test-match-trees$X: test-match-trees.o $(GITLIBS)
+	$(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $(filter %.o,$^) $(LIBS)
+
 test-chmtime$X: test-chmtime.c
 	$(CC) $(ALL_CFLAGS) -o $@ $(ALL_LDFLAGS) $<
 
diff --git a/cache.h b/cache.h
index 1b50c32b13..eb57507b80 100644
--- a/cache.h
+++ b/cache.h
@@ -496,4 +496,7 @@ extern void trace_argv_printf(const char **argv, int count, const char *format,
 extern int convert_to_git(const char *path, char **bufp, unsigned long *sizep);
 extern int convert_to_working_tree(const char *path, char **bufp, unsigned long *sizep);
 
+/* match-trees.c */
+void shift_tree(const unsigned char *, const unsigned char *, unsigned char *, int);
+
 #endif /* CACHE_H */
diff --git a/git-merge.sh b/git-merge.sh
index fa4589173f..7ebbce4bdb 100755
--- a/git-merge.sh
+++ b/git-merge.sh
@@ -16,10 +16,10 @@ test -z "$(git ls-files -u)" ||
 LF='
 '
 
-all_strategies='recur recursive octopus resolve stupid ours'
+all_strategies='recur recursive octopus resolve stupid ours subtree'
 default_twohead_strategies='recursive'
 default_octopus_strategies='octopus'
-no_trivial_merge_strategies='ours'
+no_trivial_merge_strategies='ours subtree'
 use_strategies=
 
 index_merge=t
diff --git a/match-trees.c b/match-trees.c
new file mode 100644
index 0000000000..23cafe47b4
--- /dev/null
+++ b/match-trees.c
@@ -0,0 +1,304 @@
+#include "cache.h"
+#include "tree.h"
+#include "tree-walk.h"
+
+static int score_missing(unsigned mode, const char *path)
+{
+	int score;
+
+	if (S_ISDIR(mode))
+		score = -1000;
+	else if (S_ISLNK(mode))
+		score = -500;
+	else
+		score = -50;
+	return score;
+}
+
+static int score_differs(unsigned mode1, unsigned mode2, const char *path)
+{
+	int score;
+
+	if (S_ISDIR(mode1) != S_ISDIR(mode2))
+		score = -100;
+	else if (S_ISLNK(mode1) != S_ISLNK(mode2))
+		score = -50;
+	else
+		score = -5;
+	return score;
+}
+
+static int score_matches(unsigned mode1, unsigned mode2, const char *path)
+{
+	int score;
+
+	/* Heh, we found SHA-1 collisions between different kind of objects */
+	if (S_ISDIR(mode1) != S_ISDIR(mode2))
+		score = -100;
+	else if (S_ISLNK(mode1) != S_ISLNK(mode2))
+		score = -50;
+
+	else if (S_ISDIR(mode1))
+		score = 1000;
+	else if (S_ISLNK(mode1))
+		score = 500;
+	else
+		score = 250;
+	return score;
+}
+
+/*
+ * Inspect two trees, and give a score that tells how similar they are.
+ */
+static int score_trees(const unsigned char *hash1, const unsigned char *hash2)
+{
+	struct tree_desc one;
+	struct tree_desc two;
+	void *one_buf, *two_buf;
+	int score = 0;
+	enum object_type type;
+	unsigned long size;
+
+	one_buf = read_sha1_file(hash1, &type, &size);
+	if (!one_buf)
+		die("unable to read tree (%s)", sha1_to_hex(hash1));
+	if (type != OBJ_TREE)
+		die("%s is not a tree", sha1_to_hex(hash1));
+	init_tree_desc(&one, one_buf, size);
+	two_buf = read_sha1_file(hash2, &type, &size);
+	if (!two_buf)
+		die("unable to read tree (%s)", sha1_to_hex(hash2));
+	if (type != OBJ_TREE)
+		die("%s is not a tree", sha1_to_hex(hash2));
+	init_tree_desc(&two, two_buf, size);
+	while (one.size | two.size) {
+		const unsigned char *elem1 = elem1;
+		const unsigned char *elem2 = elem2;
+		const char *path1 = path1;
+		const char *path2 = path2;
+		unsigned mode1 = mode1;
+		unsigned mode2 = mode2;
+		int cmp;
+
+		if (one.size)
+			elem1 = tree_entry_extract(&one, &path1, &mode1);
+		if (two.size)
+			elem2 = tree_entry_extract(&two, &path2, &mode2);
+
+		if (!one.size) {
+			/* two has more entries */
+			score += score_missing(mode2, path2);
+			update_tree_entry(&two);
+			continue;
+		}
+		if (!two.size) {
+			/* two lacks this entry */
+			score += score_missing(mode1, path1);
+			update_tree_entry(&one);
+			continue;
+		}
+		cmp = base_name_compare(path1, strlen(path1), mode1,
+					path2, strlen(path2), mode2);
+		if (cmp < 0) {
+			/* path1 does not appear in two */
+			score += score_missing(mode1, path1);
+			update_tree_entry(&one);
+			continue;
+		}
+		else if (cmp > 0) {
+			/* path2 does not appear in one */
+			score += score_missing(mode2, path2);
+			update_tree_entry(&two);
+			continue;
+		}
+		else if (hashcmp(elem1, elem2))
+			/* they are different */
+			score += score_differs(mode1, mode2, path1);
+		else
+			/* same subtree or blob */
+			score += score_matches(mode1, mode2, path1);
+		update_tree_entry(&one);
+		update_tree_entry(&two);
+	}
+	free(one_buf);
+	free(two_buf);
+	return score;
+}
+
+/*
+ * Match one itself and its subtrees with two and pick the best match.
+ */
+static void match_trees(const unsigned char *hash1,
+			const unsigned char *hash2,
+			int *best_score,
+			char **best_match,
+			char *base,
+			int recurse_limit)
+{
+	struct tree_desc one;
+	void *one_buf;
+	enum object_type type;
+	unsigned long size;
+
+	one_buf = read_sha1_file(hash1, &type, &size);
+	if (!one_buf)
+		die("unable to read tree (%s)", sha1_to_hex(hash1));
+	if (type != OBJ_TREE)
+		die("%s is not a tree", sha1_to_hex(hash1));
+	init_tree_desc(&one, one_buf, size);
+
+	while (one.size) {
+		const char *path;
+		const unsigned char *elem;
+		unsigned mode;
+		int score;
+
+		elem = tree_entry_extract(&one, &path, &mode);
+		if (!S_ISDIR(mode))
+			goto next;
+		score = score_trees(elem, hash2);
+		if (*best_score < score) {
+			char *newpath;
+			newpath = xmalloc(strlen(base) + strlen(path) + 1);
+			sprintf(newpath, "%s%s", base, path);
+			free(*best_match);
+			*best_match = newpath;
+			*best_score = score;
+		}
+		if (recurse_limit) {
+			char *newbase;
+			newbase = xmalloc(strlen(base) + strlen(path) + 2);
+			sprintf(newbase, "%s%s/", base, path);
+			match_trees(elem, hash2, best_score, best_match,
+				    newbase, recurse_limit - 1);
+			free(newbase);
+		}
+
+	next:
+		update_tree_entry(&one);
+	}
+	free(one_buf);
+}
+
+/*
+ * A tree "hash1" has a subdirectory at "prefix".  Come up with a
+ * tree object by replacing it with another tree "hash2".
+ */
+static int splice_tree(const unsigned char *hash1,
+		       char *prefix,
+		       const unsigned char *hash2,
+		       unsigned char *result)
+{
+	char *subpath;
+	int toplen;
+	char *buf;
+	unsigned long sz;
+	struct tree_desc desc;
+	unsigned char *rewrite_here;
+	const unsigned char *rewrite_with;
+	unsigned char subtree[20];
+	enum object_type type;
+	int status;
+
+	subpath = strchr(prefix, '/');
+	if (!subpath)
+		toplen = strlen(prefix);
+	else {
+		toplen = subpath - prefix;
+		subpath++;
+	}
+
+	buf = read_sha1_file(hash1, &type, &sz);
+	if (!buf)
+		die("cannot read tree %s", sha1_to_hex(hash1));
+	init_tree_desc(&desc, buf, sz);
+
+	rewrite_here = NULL;
+	while (desc.size) {
+		const char *name;
+		unsigned mode;
+		const unsigned char *sha1;
+
+		sha1 = tree_entry_extract(&desc, &name, &mode);
+		if (strlen(name) == toplen &&
+		    !memcmp(name, prefix, toplen)) {
+			if (!S_ISDIR(mode))
+				die("entry %s in tree %s is not a tree",
+				    name, sha1_to_hex(hash1));
+			rewrite_here = (unsigned char *) sha1;
+			break;
+		}
+		update_tree_entry(&desc);
+	}
+	if (!rewrite_here)
+		die("entry %.*s not found in tree %s",
+		    toplen, prefix, sha1_to_hex(hash1));
+	if (subpath) {
+		status = splice_tree(rewrite_here, subpath, hash2, subtree);
+		if (status)
+			return status;
+		rewrite_with = subtree;
+	}
+	else
+		rewrite_with = hash2;
+	hashcpy(rewrite_here, rewrite_with);
+	status = write_sha1_file(buf, sz, tree_type, result);
+	free(buf);
+	return status;
+}
+
+/*
+ * We are trying to come up with a merge between one and two that
+ * results in a tree shape similar to one.  The tree two might
+ * correspond to a subtree of one, in which case it needs to be
+ * shifted down by prefixing otherwise empty directories.  On the
+ * other hand, it could cover tree one and we might need to pick a
+ * subtree of it.
+ */
+void shift_tree(const unsigned char *hash1,
+		const unsigned char *hash2,
+		unsigned char *shifted,
+		int depth_limit)
+{
+	char *add_prefix;
+	char *del_prefix;
+	int add_score, del_score;
+
+	add_score = del_score = score_trees(hash1, hash2);
+	add_prefix = xcalloc(1, 1);
+	del_prefix = xcalloc(1, 1);
+
+	/*
+	 * See if one's subtree resembles two; if so we need to prefix
+	 * two with a few fake trees to match the prefix.
+	 */
+	match_trees(hash1, hash2, &add_score, &add_prefix, "", depth_limit);
+
+	/*
+	 * See if two's subtree resembles one; if so we need to
+	 * pick only subtree of two.
+	 */
+	match_trees(hash2, hash1, &del_score, &del_prefix, "", depth_limit);
+
+	/* Assume we do not have to do any shifting */
+	hashcpy(shifted, hash2);
+
+	if (add_score < del_score) {
+		/* We need to pick a subtree of two */
+		unsigned mode;
+
+		if (!*del_prefix)
+			return;
+
+		if (get_tree_entry(hash2, del_prefix, shifted, &mode))
+			die("cannot find path %s in tree %s",
+			    del_prefix, sha1_to_hex(hash2));
+		return;
+	}
+
+	if (!*add_prefix)
+		return;
+
+	splice_tree(hash1, add_prefix, hash2, shifted);
+}
+
diff --git a/merge-recursive.c b/merge-recursive.c
index 2b614b64ba..3096594b3e 100644
--- a/merge-recursive.c
+++ b/merge-recursive.c
@@ -16,6 +16,22 @@
 #include "path-list.h"
 #include "xdiff-interface.h"
 
+static int subtree_merge;
+
+static struct tree *shift_tree_object(struct tree *one, struct tree *two)
+{
+	unsigned char shifted[20];
+
+	/*
+	 * NEEDSWORK: this limits the recursion depth to hardcoded
+	 * value '2' to avoid excessive overhead.
+	 */
+	shift_tree(one->object.sha1, two->object.sha1, shifted, 2);
+	if (!hashcmp(two->object.sha1, shifted))
+		return two;
+	return lookup_tree(shifted);
+}
+
 /*
  * A virtual commit has
  * - (const char *)commit->util set to the name, and
@@ -1137,6 +1153,12 @@ static int merge_trees(struct tree *head,
 		       struct tree **result)
 {
 	int code, clean;
+
+	if (subtree_merge) {
+		merge = shift_tree_object(head, merge);
+		common = shift_tree_object(head, common);
+	}
+
 	if (sha_eq(common->object.sha1, merge->object.sha1)) {
 		output(0, "Already uptodate!");
 		*result = head;
@@ -1342,6 +1364,13 @@ int main(int argc, char *argv[])
 	struct lock_file *lock = xcalloc(1, sizeof(struct lock_file));
 	int index_fd;
 
+	if (argv[0]) {
+		int namelen = strlen(argv[0]);
+		if (8 < namelen &&
+		    !strcmp(argv[0] + namelen - 8, "-subtree"))
+			subtree_merge = 1;
+	}
+
 	git_config(merge_config);
 	if (getenv("GIT_MERGE_VERBOSITY"))
 		verbosity = strtol(getenv("GIT_MERGE_VERBOSITY"), NULL, 10);
diff --git a/test-match-trees.c b/test-match-trees.c
new file mode 100644
index 0000000000..a3c4688778
--- /dev/null
+++ b/test-match-trees.c
@@ -0,0 +1,24 @@
+#include "cache.h"
+#include "tree.h"
+
+int main(int ac, char **av)
+{
+	unsigned char hash1[20], hash2[20], shifted[20];
+	struct tree *one, *two;
+
+	if (get_sha1(av[1], hash1))
+		die("cannot parse %s as an object name", av[1]);
+	if (get_sha1(av[2], hash2))
+		die("cannot parse %s as an object name", av[2]);
+	one = parse_tree_indirect(hash1);
+	if (!one)
+		die("not a treeish %s", av[1]);
+	two = parse_tree_indirect(hash2);
+	if (!two)
+		die("not a treeish %s", av[2]);
+
+	shift_tree(one->object.sha1, two->object.sha1, shifted, -1);
+	printf("shifted: %s\n", sha1_to_hex(shifted));
+
+	exit(0);
+}