X-Git-Url: https://git.verplant.org/?a=blobdiff_plain;f=merge-base.c;h=923256c821582f38daffed4fb0df2a97fe66d74b;hb=d5a8664ed50ad86a6cdd0c096c20e4d1e64d818b;hp=36ac42008c924e3364b51bfb27cf6ac2c5a89de2;hpb=6683463ed6b2da9eed309c305806f9393d1ae728;p=git.git

diff --git a/merge-base.c b/merge-base.c
index 36ac4200..923256c8 100644
--- a/merge-base.c
+++ b/merge-base.c
@@ -1,57 +1,147 @@
+#include <stdlib.h>
 #include "cache.h"
-#include "revision.h"
+#include "commit.h"
 
-/*
- * This is stupid. We could have much better heurstics, I bet.
- */
-static int better(struct revision *new, struct revision *old)
+#define PARENT1 1
+#define PARENT2 2
+#define UNINTERESTING 4
+
+static struct commit *interesting(struct commit_list *list)
 {
-	return new->date > old->date;
+	while (list) {
+		struct commit *commit = list->item;
+		list = list->next;
+		if (commit->object.flags & UNINTERESTING)
+			continue;
+		return commit;
+	}
+	return NULL;
 }
 
-static struct revision *common_parent(struct revision *rev1, struct revision *rev2)
+/*
+ * 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)
 {
-	int i;
-	struct revision *best = NULL;
-
-	mark_reachable(rev1, 1);
-	mark_reachable(rev2, 2);
-	for (i = 0; i < nr_revs ;i++) {
-		struct revision *rev = revs[i];
-		if ((rev->flags & 3) != 3)
-			continue;
-		if (!best) {
-			best = rev;
-			continue;
+	struct commit_list *list = NULL;
+	struct commit_list *result = NULL;
+
+	if (rev1 == rev2)
+		return rev1;
+
+	parse_commit(rev1);
+	parse_commit(rev2);
+
+	rev1->object.flags |= 1;
+	rev2->object.flags |= 2;
+	insert_by_date(rev1, &list);
+	insert_by_date(rev2, &list);
+
+	while (interesting(list)) {
+		struct commit *commit = list->item;
+		struct commit_list *tmp = list, *parents;
+		int flags = commit->object.flags & 7;
+
+		list = list->next;
+		free(tmp);
+		if (flags == 3) {
+			insert_by_date(commit, &result);
+
+			/* Mark children of a found merge uninteresting */
+			flags |= UNINTERESTING;
+		}
+		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 (better(rev, best))
-			best = rev;
 	}
-	return best;
+	return interesting(result);
 }
 
 int main(int argc, char **argv)
 {
-	unsigned char rev1[20], rev2[20];
-	struct revision *common;
-
-	if (argc != 3 || get_sha1_hex(argv[1], rev1) || get_sha1_hex(argv[2], rev2))
-		usage("merge-base <commit1> <commit2>");
-
-	/*
-	 * We will eventually want to include a revision cache file
-	 * that "rev-tree.c" has generated, since this is going to
-	 * otherwise be quite expensive for big trees..
-	 *
-	 * That's some time off, though, and in the meantime we know
-	 * that we have a solution to the eventual expense.
-	 */
-	parse_commit(rev1);
-	parse_commit(rev2);
+	struct commit *rev1, *rev2, *ret;
+	unsigned char rev1key[20], rev2key[20];
 
-	common = common_parent(lookup_rev(rev1), lookup_rev(rev2));
-	if (!common)
-		die("no common parent found");
-	printf("%s\n", sha1_to_hex(common->sha1));
+	if (argc != 3 ||
+	    get_sha1(argv[1], rev1key) ||
+	    get_sha1(argv[2], rev2key)) {
+		usage("git-merge-base <commit-id> <commit-id>");
+	}
+	rev1 = lookup_commit_reference(rev1key);
+	rev2 = lookup_commit_reference(rev2key);
+	if (!rev1 || !rev2)
+		return 1;
+	ret = common_ancestor(rev1, rev2);
+	if (!ret)
+		return 1;
+	printf("%s\n", sha1_to_hex(ret->object.sha1));
 	return 0;
 }