Merge branch 'jc/rev-list-ancestry-path'

* jc/rev-list-ancestry-path:
  revision: Turn off history simplification in --ancestry-path mode
  revision: Fix typo in --ancestry-path error message
  Documentation/rev-list-options.txt: Explain --ancestry-path
  Documentation/rev-list-options.txt: Fix missing line in example history graph
  revision: --ancestry-path

4 files changed, 226 insertions, 3 deletions

diff --git a/Documentation/rev-list-options.txt b/Documentation/rev-list-options.txt
index b9fb7a86bd..73569c073e 100644
--- a/Documentation/rev-list-options.txt
+++ b/Documentation/rev-list-options.txt
@@ -384,6 +384,14 @@ Default mode::
 	merges from the resulting history, as there are no selected
 	commits contributing to this merge.
 
+--ancestry-path::
+
+	When given a range of commits to display (e.g. 'commit1..commit2'
+	or 'commit2 {caret}commit1'), only display commits that exist
+	directly on the ancestry chain between the 'commit1' and
+	'commit2', i.e. commits that are both descendants of 'commit1',
+	and ancestors of 'commit2'.
+
 A more detailed explanation follows.
 
 Suppose you specified `foo` as the <paths>.  We shall call commits
@@ -440,7 +448,7 @@ This results in:
 +
 -----------------------------------------------------------------------
 	  .-A---N---O
-	 /         /
+	 /     /   /
 	I---------D
 -----------------------------------------------------------------------
 +
@@ -511,8 +519,6 @@ Note that without '\--full-history', this still simplifies merges: if
 one of the parents is TREESAME, we follow only that one, so the other
 sides of the merge are never walked.
 
-Finally, there is a fourth simplification mode available:
-
 --simplify-merges::
 
 	First, build a history graph in the same way that
@@ -554,6 +560,46 @@ Note the major differences in `N` and `P` over '\--full-history':
   removed completely, because it had one parent and is TREESAME.
 --
 
+Finally, there is a fifth simplification mode available:
+
+--ancestry-path::
+
+	Limit the displayed commits to those directly on the ancestry
+	chain between the "from" and "to" commits in the given commit
+	range. I.e. only display commits that are ancestor of the "to"
+	commit, and descendants of the "from" commit.
++
+As an example use case, consider the following commit history:
++
+-----------------------------------------------------------------------
+	    D---E-------F
+	   /     \       \
+	  B---C---G---H---I---J
+	 /                     \
+	A-------K---------------L--M
+-----------------------------------------------------------------------
++
+A regular 'D..M' computes the set of commits that are ancestors of `M`,
+but excludes the ones that are ancestors of `D`. This is useful to see
+what happened to the history leading to `M` since `D`, in the sense
+that "what does `M` have that did not exist in `D`". The result in this
+example would be all the commits, except `A` and `B` (and `D` itself,
+of course).
++
+When we want to find out what commits in `M` are contaminated with the
+bug introduced by `D` and need fixing, however, we might want to view
+only the subset of 'D..M' that are actually descendants of `D`, i.e.
+excluding `C` and `K`. This is exactly what the '\--ancestry-path'
+option does. Applied to the 'D..M' range, it results in:
++
+-----------------------------------------------------------------------
+		E-------F
+		 \       \
+		  G---H---I---J
+			       \
+				L--M
+-----------------------------------------------------------------------
+
 The '\--simplify-by-decoration' option allows you to view only the
 big picture of the topology of the history, by omitting commits
 that are not referenced by tags.  Commits are marked as !TREESAME
diff --git a/revision.c b/revision.c
index b209d493e1..7847921658 100644
--- a/revision.c
+++ b/revision.c
@@ -646,6 +646,93 @@ static int still_interesting(struct commit_list *src, unsigned long date, int sl
 	return slop-1;
 }
 
+/*
+ * "rev-list --ancestry-path A..B" computes commits that are ancestors
+ * of B but not ancestors of A but further limits the result to those
+ * that are descendants of A.  This takes the list of bottom commits and
+ * the result of "A..B" without --ancestry-path, and limits the latter
+ * further to the ones that can reach one of the commits in "bottom".
+ */
+static void limit_to_ancestry(struct commit_list *bottom, struct commit_list *list)
+{
+	struct commit_list *p;
+	struct commit_list *rlist = NULL;
+	int made_progress;
+
+	/*
+	 * Reverse the list so that it will be likely that we would
+	 * process parents before children.
+	 */
+	for (p = list; p; p = p->next)
+		commit_list_insert(p->item, &rlist);
+
+	for (p = bottom; p; p = p->next)
+		p->item->object.flags |= TMP_MARK;
+
+	/*
+	 * Mark the ones that can reach bottom commits in "list",
+	 * in a bottom-up fashion.
+	 */
+	do {
+		made_progress = 0;
+		for (p = rlist; p; p = p->next) {
+			struct commit *c = p->item;
+			struct commit_list *parents;
+			if (c->object.flags & (TMP_MARK | UNINTERESTING))
+				continue;
+			for (parents = c->parents;
+			     parents;
+			     parents = parents->next) {
+				if (!(parents->item->object.flags & TMP_MARK))
+					continue;
+				c->object.flags |= TMP_MARK;
+				made_progress = 1;
+				break;
+			}
+		}
+	} while (made_progress);
+
+	/*
+	 * NEEDSWORK: decide if we want to remove parents that are
+	 * not marked with TMP_MARK from commit->parents for commits
+	 * in the resulting list.  We may not want to do that, though.
+	 */
+
+	/*
+	 * The ones that are not marked with TMP_MARK are uninteresting
+	 */
+	for (p = list; p; p = p->next) {
+		struct commit *c = p->item;
+		if (c->object.flags & TMP_MARK)
+			continue;
+		c->object.flags |= UNINTERESTING;
+	}
+
+	/* We are done with the TMP_MARK */
+	for (p = list; p; p = p->next)
+		p->item->object.flags &= ~TMP_MARK;
+	for (p = bottom; p; p = p->next)
+		p->item->object.flags &= ~TMP_MARK;
+	free_commit_list(rlist);
+}
+
+/*
+ * Before walking the history, keep the set of "negative" refs the
+ * caller has asked to exclude.
+ *
+ * This is used to compute "rev-list --ancestry-path A..B", as we need
+ * to filter the result of "A..B" further to the ones that can actually
+ * reach A.
+ */
+static struct commit_list *collect_bottom_commits(struct commit_list *list)
+{
+	struct commit_list *elem, *bottom = NULL;
+	for (elem = list; elem; elem = elem->next)
+		if (elem->item->object.flags & UNINTERESTING)
+			commit_list_insert(elem->item, &bottom);
+	return bottom;
+}
+
 static int limit_list(struct rev_info *revs)
 {
 	int slop = SLOP;
@@ -653,6 +740,13 @@ static int limit_list(struct rev_info *revs)
 	struct commit_list *list = revs->commits;
 	struct commit_list *newlist = NULL;
 	struct commit_list **p = &newlist;
+	struct commit_list *bottom = NULL;
+
+	if (revs->ancestry_path) {
+		bottom = collect_bottom_commits(list);
+		if (!bottom)
+			die("--ancestry-path given but there are no bottom commits");
+	}
 
 	while (list) {
 		struct commit_list *entry = list;
@@ -694,6 +788,11 @@ static int limit_list(struct rev_info *revs)
 	if (revs->cherry_pick)
 		cherry_pick_list(newlist, revs);
 
+	if (bottom) {
+		limit_to_ancestry(bottom, newlist);
+		free_commit_list(bottom);
+	}
+
 	revs->commits = newlist;
 	return 0;
 }
@@ -1089,6 +1188,10 @@ static int handle_revision_opt(struct rev_info *revs, int argc, const char **arg
 		revs->min_age = approxidate(arg + 8);
 	} else if (!strcmp(arg, "--first-parent")) {
 		revs->first_parent_only = 1;
+	} else if (!strcmp(arg, "--ancestry-path")) {
+		revs->ancestry_path = 1;
+		revs->simplify_history = 0;
+		revs->limited = 1;
 	} else if (!strcmp(arg, "-g") || !strcmp(arg, "--walk-reflogs")) {
 		init_reflog_walk(&revs->reflog_info);
 	} else if (!strcmp(arg, "--default")) {
diff --git a/revision.h b/revision.h
index 568f1c98de..855464f144 100644
--- a/revision.h
+++ b/revision.h
@@ -66,6 +66,7 @@ struct rev_info {
 			reverse_output_stage:1,
 			cherry_pick:1,
 			bisect:1,
+			ancestry_path:1,
 			first_parent_only:1;
 
 	/* Diff flags */
diff --git a/t/t6019-rev-list-ancestry-path.sh b/t/t6019-rev-list-ancestry-path.sh
new file mode 100755
index 0000000000..76410293b3
--- /dev/null
+++ b/t/t6019-rev-list-ancestry-path.sh
@@ -0,0 +1,73 @@
+#!/bin/sh
+
+test_description='--ancestry-path'
+
+#          D---E-------F
+#         /     \       \
+#    B---C---G---H---I---J
+#   /                     \
+#  A-------K---------------L--M
+#
+#  D..M                 == E F G H I J K L M
+#  --ancestry-path D..M == E F H I J L M
+#
+#  D..M -- M.t                 == M
+#  --ancestry-path D..M -- M.t == M
+
+. ./test-lib.sh
+
+test_merge () {
+	test_tick &&
+	git merge -s ours -m "$2" "$1" &&
+	git tag "$2"
+}
+
+test_expect_success setup '
+	test_commit A &&
+	test_commit B &&
+	test_commit C &&
+	test_commit D &&
+	test_commit E &&
+	test_commit F &&
+	git reset --hard C &&
+	test_commit G &&
+	test_merge E H &&
+	test_commit I &&
+	test_merge F J &&
+	git reset --hard A &&
+	test_commit K &&
+	test_merge J L &&
+	test_commit M
+'
+
+test_expect_success 'rev-list D..M' '
+	for c in E F G H I J K L M; do echo $c; done >expect &&
+	git rev-list --format=%s D..M |
+	sed -e "/^commit /d" |
+	sort >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success 'rev-list --ancestry-path D..M' '
+	for c in E F H I J L M; do echo $c; done >expect &&
+	git rev-list --ancestry-path --format=%s D..M |
+	sed -e "/^commit /d" |
+	sort >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success 'rev-list D..M -- M.t' '
+	echo M >expect &&
+	git rev-list --format=%s D..M -- M.t |
+	sed -e "/^commit /d" >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success 'rev-list --ancestry-patch D..M -- M.t' '
+	echo M >expect &&
+	git rev-list --ancestry-path --format=%s D..M -- M.t |
+	sed -e "/^commit /d" >actual &&
+	test_cmp expect actual
+'
+
+test_done