merge-base: teach "--fork-point" modejc/merge-base-reflog

The "git pull --rebase" command computes the fork point of the
branch being rebased using the reflog entries of the "base" branch
(typically a remote-tracking branch) the branch's work was based on,
in order to cope with the case in which the "base" branch has been
rewound and rebuilt.  For example, if the history looked like this:

                     o---B1
                    /
    ---o---o---B2--o---o---o---Base
            \
             B3
              \
               Derived

where the current tip of the "base" branch is at Base, but earlier
fetch observed that its tip used to be B3 and then B2 and then B1
before getting to the current commit, and the branch being rebased
on top of the latest "base" is based on commit B3, it tries to find
B3 by going through the output of "git rev-list --reflog base" (i.e.
Base, B1, B2, B3) until it finds a commit that is an ancestor of the
current tip "Derived".

Internally, we have get_merge_bases_many() that can compute this
with one-go.  We would want a merge-base between Derived and a
fictitious merge commit that would result by merging all the
historical tips of "base".  When such a commit exist, we should get
a single result, which exactly match one of the reflog entries of
"base".

Teach "git merge-base" a new mode, "--fork-point", to compute
exactly that.

Helped-by: Martin von Zweigbergk <martinvonz@gmail.com>
Helped-by: John Keeping <john@keeping.me.uk>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 109 insertions, 0 deletions

diff --git a/builtin/merge-base.c b/builtin/merge-base.c
index d39c91023e..a2923235e1 100644
--- a/builtin/merge-base.c
+++ b/builtin/merge-base.c
@@ -1,6 +1,9 @@
 #include "builtin.h"
 #include "cache.h"
 #include "commit.h"
+#include "refs.h"
+#include "diff.h"
+#include "revision.h"
 #include "parse-options.h"
 
 static int show_merge_base(struct commit **rev, int rev_nr, int show_all)
@@ -27,6 +30,7 @@ static const char * const merge_base_usage[] = {
 	N_("git merge-base [-a|--all] --octopus <commit>..."),
 	N_("git merge-base --independent <commit>..."),
 	N_("git merge-base --is-ancestor <commit> <commit>"),
+	N_("git merge-base --fork-point <ref> [<commit>]"),
 	NULL
 };
 
@@ -85,6 +89,103 @@ static int handle_is_ancestor(int argc, const char **argv)
 		return 1;
 }
 
+struct rev_collect {
+	struct commit **commit;
+	int nr;
+	int alloc;
+	unsigned int initial : 1;
+};
+
+static void add_one_commit(unsigned char *sha1, struct rev_collect *revs)
+{
+	struct commit *commit;
+
+	if (is_null_sha1(sha1))
+		return;
+
+	commit = lookup_commit(sha1);
+	if (!commit ||
+	    (commit->object.flags & TMP_MARK) ||
+	    parse_commit(commit))
+		return;
+
+	ALLOC_GROW(revs->commit, revs->nr + 1, revs->alloc);
+	revs->commit[revs->nr++] = commit;
+	commit->object.flags |= TMP_MARK;
+}
+
+static int collect_one_reflog_ent(unsigned char *osha1, unsigned char *nsha1,
+				  const char *ident, unsigned long timestamp,
+				  int tz, const char *message, void *cbdata)
+{
+	struct rev_collect *revs = cbdata;
+
+	if (revs->initial) {
+		revs->initial = 0;
+		add_one_commit(osha1, revs);
+	}
+	add_one_commit(nsha1, revs);
+	return 0;
+}
+
+static int handle_fork_point(int argc, const char **argv)
+{
+	unsigned char sha1[20];
+	char *refname;
+	const char *commitname;
+	struct rev_collect revs;
+	struct commit *derived;
+	struct commit_list *bases;
+	int i, ret = 0;
+
+	switch (dwim_ref(argv[0], strlen(argv[0]), sha1, &refname)) {
+	case 0:
+		die("No such ref: '%s'", argv[0]);
+	case 1:
+		break; /* good */
+	default:
+		die("Ambiguous refname: '%s'", argv[0]);
+	}
+
+	commitname = (argc == 2) ? argv[1] : "HEAD";
+	if (get_sha1(commitname, sha1))
+		die("Not a valid object name: '%s'", commitname);
+
+	derived = lookup_commit_reference(sha1);
+	memset(&revs, 0, sizeof(revs));
+	revs.initial = 1;
+	for_each_reflog_ent(refname, collect_one_reflog_ent, &revs);
+
+	for (i = 0; i < revs.nr; i++)
+		revs.commit[i]->object.flags &= ~TMP_MARK;
+
+	bases = get_merge_bases_many(derived, revs.nr, revs.commit, 0);
+
+	/*
+	 * There should be one and only one merge base, when we found
+	 * a common ancestor among reflog entries.
+	 */
+	if (!bases || bases->next) {
+		ret = 1;
+		goto cleanup_return;
+	}
+
+	/* And the found one must be one of the reflog entries */
+	for (i = 0; i < revs.nr; i++)
+		if (&bases->item->object == &revs.commit[i]->object)
+			break; /* found */
+	if (revs.nr <= i) {
+		ret = 1; /* not found */
+		goto cleanup_return;
+	}
+
+	printf("%s\n", sha1_to_hex(bases->item->object.sha1));
+
+cleanup_return:
+	free_commit_list(bases);
+	return ret;
+}
+
 int cmd_merge_base(int argc, const char **argv, const char *prefix)
 {
 	struct commit **rev;
@@ -100,6 +201,8 @@ int cmd_merge_base(int argc, const char **argv, const char *prefix)
 			    N_("list revs not reachable from others"), 'r'),
 		OPT_CMDMODE(0, "is-ancestor", &cmdmode,
 			    N_("is the first one ancestor of the other?"), 'a'),
+		OPT_CMDMODE(0, "fork-point", &cmdmode,
+			    N_("find where <commit> forked from reflog of <ref>"), 'f'),
 		OPT_END()
 	};
 
@@ -120,6 +223,12 @@ int cmd_merge_base(int argc, const char **argv, const char *prefix)
 	if (cmdmode == 'r' || cmdmode == 'o')
 		return handle_octopus(argc, argv, cmdmode == 'r', show_all);
 
+	if (cmdmode == 'f') {
+		if (argc < 1 || 2 < argc)
+			usage_with_options(merge_base_usage, options);
+		return handle_fork_point(argc, argv);
+	}
+
 	if (argc < 2)
 		usage_with_options(merge_base_usage, options);