Merge branch 'js/merge-base'

1 files changed, 248 insertions, 3 deletions

diff --git a/commit.c b/commit.c
index e51ffa1c6c..c6bf10d045 100644
--- a/commit.c
+++ b/commit.c
@@ -397,12 +397,13 @@ void clear_commit_marks(struct commit *commit, unsigned int mark)
 {
 	struct commit_list *parents;
 
-	parents = commit->parents;
 	commit->object.flags &= ~mark;
+	parents = commit->parents;
 	while (parents) {
 		struct commit *parent = parents->item;
-		if (parent && parent->object.parsed &&
-		    (parent->object.flags & mark))
+
+		/* Have we already cleared this? */
+		if (mark & parent->object.flags)
 			clear_commit_marks(parent, mark);
 		parents = parents->next;
 	}
@@ -846,3 +847,247 @@ void sort_in_topological_order_fn(struct commit_list ** list, int lifo,
 	}
 	free(nodes);
 }
+
+/* merge-rebase stuff */
+
+/* bits #0..7 in revision.h */
+#define PARENT1		(1u<< 8)
+#define PARENT2		(1u<< 9)
+#define STALE		(1u<<10)
+
+static struct commit *interesting(struct commit_list *list)
+{
+	while (list) {
+		struct commit *commit = list->item;
+		list = list->next;
+		if (commit->object.flags & STALE)
+			continue;
+		return commit;
+	}
+	return NULL;
+}
+
+/*
+ * A pathological example of how this thing works.
+ *
+ * Suppose we had this commit graph, where chronologically
+ * the timestamp on the commit are A <= B <= C <= D <= E <= F
+ * and we are trying to figure out the merge base for E and F
+ * commits.
+ *
+ *                  F
+ *                 / \
+ *            E   A   D
+ *             \ /   /
+ *              B   /
+ *               \ /
+ *                C
+ *
+ * First we push E and F to list to be processed.  E gets bit 1
+ * and F gets bit 2.  The list becomes:
+ *
+ *     list=F(2) E(1), result=empty
+ *
+ * Then we pop F, the newest commit, from the list.  Its flag is 2.
+ * We scan its parents, mark them reachable from the side that F is
+ * reachable from, and push them to the list:
+ *
+ *     list=E(1) D(2) A(2), result=empty
+ *
+ * Next pop E and do the same.
+ *
+ *     list=D(2) B(1) A(2), result=empty
+ *
+ * Next pop D and do the same.
+ *
+ *     list=C(2) B(1) A(2), result=empty
+ *
+ * Next pop C and do the same.
+ *
+ *     list=B(1) A(2), result=empty
+ *
+ * Now it is B's turn.  We mark its parent, C, reachable from B's side,
+ * and push it to the list:
+ *
+ *     list=C(3) A(2), result=empty
+ *
+ * Now pop C and notice it has flags==3.  It is placed on the result list,
+ * and the list now contains:
+ *
+ *     list=A(2), result=C(3)
+ *
+ * We pop A and do the same.
+ *
+ *     list=B(3), result=C(3)
+ *
+ * Next, we pop B and something very interesting happens.  It has flags==3
+ * so it is also placed on the result list, and its parents are marked
+ * stale, retroactively, and placed back on the list:
+ *
+ *    list=C(7), result=C(7) B(3)
+ *
+ * Now, list does not have any interesting commit.  So we find the newest
+ * commit from the result list that is not marked stale.  Which is
+ * commit B.
+ *
+ *
+ * Another pathological example how this thing used to fail to mark an
+ * ancestor of a merge base as STALE before we introduced the
+ * postprocessing phase (mark_reachable_commits).
+ *
+ *		  2
+ *		  H
+ *	    1    / \
+ *	    G   A   \
+ *	    |\ /     \
+ *	    | B       \
+ *	    |  \       \
+ *	     \  C       F
+ *	      \  \     /
+ *	       \  D   /
+ *		\ |  /
+ *		 \| /
+ *		  E
+ *
+ *	 list			A B C D E F G H
+ *	 G1 H2			- - - - - - 1 2
+ *	 H2 E1 B1		- 1 - - 1 - 1 2
+ *	 F2 E1 B1 A2		2 1 - - 1 2 1 2
+ *	 E3 B1 A2		2 1 - - 3 2 1 2
+ *	 B1 A2			2 1 - - 3 2 1 2
+ *	 C1 A2			2 1 1 - 3 2 1 2
+ *	 D1 A2			2 1 1 1 3 2 1 2
+ *	 A2			2 1 1 1 3 2 1 2
+ *	 B3			2 3 1 1 3 2 1 2
+ *	 C7			2 3 7 1 3 2 1 2
+ *
+ * At this point, unfortunately, everybody in the list is
+ * stale, so we fail to complete the following two
+ * steps to fully marking stale commits.
+ *
+ *	 D7			2 3 7 7 3 2 1 2
+ *	 E7			2 3 7 7 7 2 1 2
+ *
+ * and we ended up showing E as an interesting merge base.
+ * The postprocessing phase re-injects C and continues traversal
+ * to contaminate D and E.
+ */
+
+static void mark_reachable_commits(struct commit_list *result,
+				   struct commit_list *list)
+{
+	struct commit_list *tmp;
+
+	/*
+	 * Postprocess to fully contaminate the well.
+	 */
+	for (tmp = result; tmp; tmp = tmp->next) {
+		struct commit *c = tmp->item;
+		/* Reinject stale ones to list,
+		 * so we can scan their parents.
+		 */
+		if (c->object.flags & STALE)
+			commit_list_insert(c, &list);
+	}
+	while (list) {
+		struct commit *c = list->item;
+		struct commit_list *parents;
+
+		tmp = list;
+		list = list->next;
+		free(tmp);
+
+		/* Anything taken out of the list is stale, so
+		 * mark all its parents stale.  We do not
+		 * parse new ones (we already parsed all the relevant
+		 * ones).
+		 */
+		parents = c->parents;
+		while (parents) {
+			struct commit *p = parents->item;
+			parents = parents->next;
+			if (!(p->object.flags & STALE)) {
+				p->object.flags |= STALE;
+				commit_list_insert(p, &list);
+			}
+		}
+	}
+}
+
+struct commit_list *get_merge_bases(struct commit *rev1, struct commit *rev2,
+                                    int cleanup)
+{
+	struct commit_list *list = NULL;
+	struct commit_list *result = NULL;
+	struct commit_list *tmp = NULL;
+
+	if (rev1 == rev2)
+		return commit_list_insert(rev1, &result);
+
+	parse_commit(rev1);
+	parse_commit(rev2);
+
+	rev1->object.flags |= PARENT1;
+	rev2->object.flags |= PARENT2;
+	insert_by_date(rev1, &list);
+	insert_by_date(rev2, &list);
+
+	while (interesting(list)) {
+		struct commit *commit = list->item;
+		struct commit_list *parents;
+		int flags = commit->object.flags
+			& (PARENT1 | PARENT2 | STALE);
+
+		tmp = list;
+		list = list->next;
+		free(tmp);
+		if (flags == (PARENT1 | PARENT2)) {
+			insert_by_date(commit, &result);
+
+			/* Mark parents of a found merge stale */
+			flags |= STALE;
+		}
+		parents = commit->parents;
+		while (parents) {
+			struct commit *p = parents->item;
+			parents = parents->next;
+			if ((p->object.flags & flags) == flags)
+				continue;
+			parse_commit(p);
+			p->object.flags |= flags;
+			insert_by_date(p, &list);
+		}
+	}
+
+	if (!result)
+		goto finish;
+
+	if (result->next && list)
+		mark_reachable_commits(result, list);
+
+	/* cull duplicates */
+	for (tmp = result, list = NULL; tmp; ) {
+		struct commit *commit = tmp->item;
+		struct commit_list *next = tmp->next;
+		if (commit->object.flags & STALE) {
+			if (list != NULL)
+				list->next = next;
+			free(tmp);
+		} else {
+			if (list == NULL)
+				result = tmp;
+			list = tmp;
+			commit->object.flags |= STALE;
+		}
+
+		tmp = next;
+	}
+
+ finish:
+	if (cleanup) {
+		clear_commit_marks(rev1, PARENT1 | PARENT2 | STALE);
+		clear_commit_marks(rev2, PARENT1 | PARENT2 | STALE);
+	}
+
+	return result;
+}