Merge branch 'tr/filter-branch'

* tr/filter-branch:
  revision --simplify-merges: make it a no-op without pathspec
  revision --simplify-merges: do not leave commits unprocessed
  revision --simplify-merges: use decoration instead of commit->util field
  Documentation: rev-list-options: move --simplify-merges documentation
  filter-branch: use --simplify-merges
  filter-branch: fix ref rewriting with --subdirectory-filter
  filter-branch: Extend test to show rewriting bug
  Topo-sort before --simplify-merges
  revision traversal: show full history with merge simplification
  revision.c: whitespace fix

1 files changed, 181 insertions, 21 deletions

diff --git a/revision.c b/revision.c
index 36291b6..bcbc7bd 100644
--- a/revision.c
+++ b/revision.c
@@ -489,7 +489,7 @@ static int add_parents_to_list(struct rev_info *revs, struct commit *commit,
 			p->object.flags |= SEEN;
 			insert_by_date_cached(p, list, cached_base, cache_ptr);
 		}
-		if(revs->first_parent_only)
+		if (revs->first_parent_only)
 			break;
 	}
 	return 0;
@@ -1041,6 +1041,11 @@ static int handle_revision_opt(struct rev_info *revs, int argc, const char **arg
 	} else if (!strcmp(arg, "--topo-order")) {
 		revs->lifo = 1;
 		revs->topo_order = 1;
+	} else if (!strcmp(arg, "--simplify-merges")) {
+		revs->simplify_merges = 1;
+		revs->rewrite_parents = 1;
+		revs->simplify_history = 0;
+		revs->limited = 1;
 	} else if (!strcmp(arg, "--date-order")) {
 		revs->lifo = 0;
 		revs->topo_order = 1;
@@ -1368,6 +1373,179 @@ static void add_child(struct rev_info *revs, struct commit *parent, struct commi
 	l->next = add_decoration(&revs->children, &parent->object, l);
 }
 
+static int remove_duplicate_parents(struct commit *commit)
+{
+	struct commit_list **pp, *p;
+	int surviving_parents;
+
+	/* Examine existing parents while marking ones we have seen... */
+	pp = &commit->parents;
+	while ((p = *pp) != NULL) {
+		struct commit *parent = p->item;
+		if (parent->object.flags & TMP_MARK) {
+			*pp = p->next;
+			continue;
+		}
+		parent->object.flags |= TMP_MARK;
+		pp = &p->next;
+	}
+	/* count them while clearing the temporary mark */
+	surviving_parents = 0;
+	for (p = commit->parents; p; p = p->next) {
+		p->item->object.flags &= ~TMP_MARK;
+		surviving_parents++;
+	}
+	return surviving_parents;
+}
+
+struct merge_simplify_state {
+	struct commit *simplified;
+};
+
+static struct merge_simplify_state *locate_simplify_state(struct rev_info *revs, struct commit *commit)
+{
+	struct merge_simplify_state *st;
+
+	st = lookup_decoration(&revs->merge_simplification, &commit->object);
+	if (!st) {
+		st = xcalloc(1, sizeof(*st));
+		add_decoration(&revs->merge_simplification, &commit->object, st);
+	}
+	return st;
+}
+
+static struct commit_list **simplify_one(struct rev_info *revs, struct commit *commit, struct commit_list **tail)
+{
+	struct commit_list *p;
+	struct merge_simplify_state *st, *pst;
+	int cnt;
+
+	st = locate_simplify_state(revs, commit);
+
+	/*
+	 * Have we handled this one?
+	 */
+	if (st->simplified)
+		return tail;
+
+	/*
+	 * An UNINTERESTING commit simplifies to itself, so does a
+	 * root commit.  We do not rewrite parents of such commit
+	 * anyway.
+	 */
+	if ((commit->object.flags & UNINTERESTING) || !commit->parents) {
+		st->simplified = commit;
+		return tail;
+	}
+
+	/*
+	 * Do we know what commit all of our parents should be rewritten to?
+	 * Otherwise we are not ready to rewrite this one yet.
+	 */
+	for (cnt = 0, p = commit->parents; p; p = p->next) {
+		pst = locate_simplify_state(revs, p->item);
+		if (!pst->simplified) {
+			tail = &commit_list_insert(p->item, tail)->next;
+			cnt++;
+		}
+	}
+	if (cnt) {
+		tail = &commit_list_insert(commit, tail)->next;
+		return tail;
+	}
+
+	/*
+	 * Rewrite our list of parents.
+	 */
+	for (p = commit->parents; p; p = p->next) {
+		pst = locate_simplify_state(revs, p->item);
+		p->item = pst->simplified;
+	}
+	cnt = remove_duplicate_parents(commit);
+
+	/*
+	 * It is possible that we are a merge and one side branch
+	 * does not have any commit that touches the given paths;
+	 * in such a case, the immediate parents will be rewritten
+	 * to different commits.
+	 *
+	 *      o----X		X: the commit we are looking at;
+	 *     /    /		o: a commit that touches the paths;
+	 * ---o----'
+	 *
+	 * Further reduce the parents by removing redundant parents.
+	 */
+	if (1 < cnt) {
+		struct commit_list *h = reduce_heads(commit->parents);
+		cnt = commit_list_count(h);
+		free_commit_list(commit->parents);
+		commit->parents = h;
+	}
+
+	/*
+	 * A commit simplifies to itself if it is a root, if it is
+	 * UNINTERESTING, if it touches the given paths, or if it is a
+	 * merge and its parents simplifies to more than one commits
+	 * (the first two cases are already handled at the beginning of
+	 * this function).
+	 *
+	 * Otherwise, it simplifies to what its sole parent simplifies to.
+	 */
+	if (!cnt ||
+	    (commit->object.flags & UNINTERESTING) ||
+	    !(commit->object.flags & TREESAME) ||
+	    (1 < cnt))
+		st->simplified = commit;
+	else {
+		pst = locate_simplify_state(revs, commit->parents->item);
+		st->simplified = pst->simplified;
+	}
+	return tail;
+}
+
+static void simplify_merges(struct rev_info *revs)
+{
+	struct commit_list *list;
+	struct commit_list *yet_to_do, **tail;
+
+	if (!revs->topo_order)
+		sort_in_topological_order(&revs->commits, revs->lifo);
+	if (!revs->prune)
+		return;
+
+	/* feed the list reversed */
+	yet_to_do = NULL;
+	for (list = revs->commits; list; list = list->next)
+		commit_list_insert(list->item, &yet_to_do);
+	while (yet_to_do) {
+		list = yet_to_do;
+		yet_to_do = NULL;
+		tail = &yet_to_do;
+		while (list) {
+			struct commit *commit = list->item;
+			struct commit_list *next = list->next;
+			free(list);
+			list = next;
+			tail = simplify_one(revs, commit, tail);
+		}
+	}
+
+	/* clean up the result, removing the simplified ones */
+	list = revs->commits;
+	revs->commits = NULL;
+	tail = &revs->commits;
+	while (list) {
+		struct commit *commit = list->item;
+		struct commit_list *next = list->next;
+		struct merge_simplify_state *st;
+		free(list);
+		list = next;
+		st = locate_simplify_state(revs, commit);
+		if (st->simplified == commit)
+			tail = &commit_list_insert(commit, tail)->next;
+	}
+}
+
 static void set_children(struct rev_info *revs)
 {
 	struct commit_list *l;
@@ -1408,6 +1586,8 @@ int prepare_revision_walk(struct rev_info *revs)
 			return -1;
 	if (revs->topo_order)
 		sort_in_topological_order(&revs->commits, revs->lifo);
+	if (revs->simplify_merges)
+		simplify_merges(revs);
 	if (revs->children.name)
 		set_children(revs);
 	return 0;
@@ -1440,26 +1620,6 @@ static enum rewrite_result rewrite_one(struct rev_info *revs, struct commit **pp
 	}
 }
 
-static void remove_duplicate_parents(struct commit *commit)
-{
-	struct commit_list **pp, *p;
-
-	/* Examine existing parents while marking ones we have seen... */
-	pp = &commit->parents;
-	while ((p = *pp) != NULL) {
-		struct commit *parent = p->item;
-		if (parent->object.flags & TMP_MARK) {
-			*pp = p->next;
-			continue;
-		}
-		parent->object.flags |= TMP_MARK;
-		pp = &p->next;
-	}
-	/* ... and clear the temporary mark */
-	for (p = commit->parents; p; p = p->next)
-		p->item->object.flags &= ~TMP_MARK;
-}
-
 static int rewrite_parents(struct rev_info *revs, struct commit *commit)
 {
 	struct commit_list **pp = &commit->parents;