merge-base.c: pathological case fix.

Also add some illustration requested by Linus.

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

diff --git a/merge-base.c b/merge-base.c
index 18d81d08a5147acd09b6f1e2f57f647ea5bf1fc5..923256c821582f38daffed4fb0df2a97fe66d74b 100644 (file)
--- a/merge-base.c
+++ b/merge-base.c
@@ -6,18 +6,82 @@
 #define PARENT2 2
 #define UNINTERESTING 4
 
-static int interesting(struct commit_list *list)
+static struct commit *interesting(struct commit_list *list)
 {
        while (list) {
                struct commit *commit = list->item;
                list = list->next;
                if (commit->object.flags & UNINTERESTING)
                        continue;
-               return 1;
+               return commit;
        }
-       return 0;
+       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
+ * uninteresting, 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 uninteresting.  Which is
+ * commit B.
+ */
+
 static struct commit *common_ancestor(struct commit *rev1, struct commit *rev2)
 {
        struct commit_list *list = NULL;
@@ -58,9 +122,7 @@ static struct commit *common_ancestor(struct commit *rev1, struct commit *rev2)
                        insert_by_date(p, &list);
                }
        }
-       if (!result)
-               return NULL;
-       return result->item;
+       return interesting(result);
 }
 
 int main(int argc, char **argv)