Chose better tag names in git-describe after merges.

Recently git.git itself encountered a situation on its master and
next branches where git-describe stopped reporting 'v1.5.0-rc0-gN'
and instead started reporting 'v1.4.4.4-gN'.  This appeared to be
a backward jump in version numbering.

  maint     o-------------------4
            \                    \
  master     o-o-o-o-o-o-o-5-o-C-o-W

The issue is that commit C in the diagram claims it is version
1.5.0, as the tag v1.5.0 is placed on commit 5.  Yet commit W
claims it is version 1.4.4.4 as the tag v1.5.0 has an older tag
date than the v1.4.4.4 tag.

As it turns out this situation is very common.  A bug fix applied
to maint and later merged into master occurs frequently enough that
it should Just Work Right(tm).

Rather than taking the first tag that gets found git-describe will
now generate a list of all possible tags and select the one which
has the most number of commits in common with HEAD (or whatever
revision the user requested the description of).

This rule is based on the principle shown in the diagram above.
There are a large number of commits on the primary development branch
'master' which do not appear in the 'maint' branch, and many of
these are already tagged as part of v1.5.0-rc0.  Additionally these
commits are not in v1.4.4.4, as they are part of the v1.5.0 release
still being developed.  The v1.5.0-rc0 tag is more descriptive of
W than v1.4.4.4 is, and therefore should be used.

Signed-off-by: Shawn O. Pearce <spearce@spearce.org>
Signed-off-by: Junio C Hamano <junkio@cox.net>

builtin-describe.c

@@ -2,10 +2,11 @@
 #include "commit.h"
 #include "tag.h"
 #include "refs.h"
+#include "diff.h"
+#include "diffcore.h"
+#include "revision.h"
 #include "builtin.h"
 
-#define SEEN (1u << 0)
-
 static const char describe_usage[] =
 "git-describe [--all] [--tags] [--abbrev=<n>] <committish>*";
 
@@ -16,7 +17,7 @@ static int abbrev = DEFAULT_ABBREV;
 
 static int names, allocs;
 static struct commit_name {
-	const struct commit *commit;
+	struct commit *commit;
 	int prio; /* annotated tag = 2, tag = 1, head = 0 */
 	char path[FLEX_ARRAY]; /* more */
 } **name_array = NULL;
@@ -35,7 +36,7 @@ static struct commit_name *match(struct commit *cmit)
 }
 
 static void add_to_known_names(const char *path,
-			       const struct commit *commit,
+			       struct commit *commit,
 			       int prio)
 {
 	int idx;
@@ -98,6 +99,12 @@ static int compare_names(const void *_a, const void *_b)
 	return (a_date > b_date) ? -1 : (a_date == b_date) ? 0 : 1;
 }
 
+struct possible_tag {
+	struct possible_tag *next;
+	struct commit_name *name;
+	unsigned long depth;
+};
+
 static void describe(const char *arg, int last_one)
 {
 	unsigned char sha1[20];
@@ -105,6 +112,7 @@ static void describe(const char *arg, int last_one)
 	struct commit_list *list;
 	static int initialized = 0;
 	struct commit_name *n;
+	struct possible_tag *all_matches, *min_match, *cur_match;
 
 	if (get_sha1(arg, sha1))
 		die("Not a valid object name %s", arg);
@@ -125,19 +133,67 @@ static void describe(const char *arg, int last_one)
 	}
 
 	list = NULL;
+	all_matches = NULL;
+	cur_match = NULL;
 	commit_list_insert(cmit, &list);
 	while (list) {
-		struct commit *c = pop_most_recent_commit(&list, SEEN);
+		struct commit *c = pop_commit(&list);
 		n = match(c);
 		if (n) {
-			printf("%s-g%s\n", n->path,
-			       find_unique_abbrev(cmit->object.sha1, abbrev));
-			if (!last_one)
-				clear_commit_marks(cmit, SEEN);
-			return;
+			struct possible_tag *p = xmalloc(sizeof(*p));
+			p->name = n;
+			p->next = NULL;
+			if (cur_match)
+				cur_match->next = p;
+			else
+				all_matches = p;
+			cur_match = p;
+		} else {
+			struct commit_list *parents = c->parents;
+			while (parents) {
+				struct commit *p = parents->item;
+				parse_commit(p);
+				if (!(p->object.flags & SEEN)) {
+					p->object.flags |= SEEN;
+					insert_by_date(p, &list);
+				}
+				parents = parents->next;
 			}
 		}
+	}
+
+	if (!all_matches)
 		die("cannot describe '%s'", sha1_to_hex(cmit->object.sha1));
+
+	min_match = NULL;
+	for (cur_match = all_matches; cur_match; cur_match = cur_match->next) {
+		struct rev_info revs;
+		struct commit *tagged = cur_match->name->commit;
+
+		clear_commit_marks(cmit, -1);
+		init_revisions(&revs, NULL);
+		tagged->object.flags |= UNINTERESTING;
+		add_pending_object(&revs, &tagged->object, NULL);
+		add_pending_object(&revs, &cmit->object, NULL);
+
+		prepare_revision_walk(&revs);
+		cur_match->depth = 0;
+		while ((!min_match || cur_match->depth < min_match->depth)
+			&& get_revision(&revs))
+			cur_match->depth++;
+		if (!min_match || cur_match->depth < min_match->depth)
+			min_match = cur_match;
+	}
+	printf("%s-g%s\n", min_match->name->path,
+		   find_unique_abbrev(cmit->object.sha1, abbrev));
+
+	if (!last_one) {
+		for (cur_match = all_matches; cur_match; cur_match = min_match) {
+			min_match = cur_match->next;
+			free(cur_match);
+		}
+		clear_commit_marks(cmit, SEEN);
+	}
 }
 
 int cmd_describe(int argc, const char **argv, const char *prefix)