git-rev-list: add --exclude-first-parent-only flag

It is useful to know when a branch first diverged in history
from some integration branch in order to be able to enumerate
the user's local changes. However, these local changes can
include arbitrary merges, so it is necessary to ignore this
merge structure when finding the divergence point.

In order to do this, teach the "rev-list" family to accept
"--exclude-first-parent-only", which restricts the traversal
of excluded commits to only follow first parent links.

   -A-----E-F-G--main
     \   / /
      B-C-D--topic

In this example, the goal is to return the set {B, C, D} which
represents a topic branch that has been merged into main branch.
`git rev-list topic ^main` will end up returning no commits
since excluding main will end up traversing the commits on topic
as well. `git rev-list --exclude-first-parent-only topic ^main`
however will return {B, C, D} as desired.

Add docs for the new flag, and clarify the doc for --first-parent
to indicate that it applies to traversing the set of included
commits only.

Signed-off-by: Jerry Zhang <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: jerry-skydio

Documentation/rev-list-options.txt

@@ -122,19 +122,27 @@ again.  Equivalent forms are `--min-parents=0` (any commit has 0 or more
 parents) and `--max-parents=-1` (negative numbers denote no upper limit).
 
 --first-parent::
-	Follow only the first parent commit upon seeing a merge
-	commit.  This option can give a better overview when
-	viewing the evolution of a particular topic branch,
-	because merges into a topic branch tend to be only about
-	adjusting to updated upstream from time to time, and
-	this option allows you to ignore the individual commits
-	brought in to your history by such a merge.
+	When finding commits to include, follow only the first
+	parent commit upon seeing a merge commit.  This option
+	can give a better overview when viewing the evolution of
+	a particular topic branch, because merges into a topic
+	branch tend to be only about adjusting to updated upstream
+	from time to time, and this option allows you to ignore
+	the individual commits brought in to your history by such
+	a merge.
 ifdef::git-log[]
 +
 This option also changes default diff format for merge commits
 to `first-parent`, see `--diff-merges=first-parent` for details.
 endif::git-log[]
 
+--exclude-first-parent-only::
+	When finding commits to exclude (with a '{caret}'), follow only
+	the first parent commit upon seeing a merge commit.
+	This can be used to find the set of changes in a topic branch
+	from the point where it diverged from the remote branch, given
+	that arbitrary merges can be valid topic branch changes.
+
 --not::
 	Reverses the meaning of the '{caret}' prefix (or lack thereof)
 	for all following revision specifiers, up to the next `--not`.

blame.c

@@ -2615,7 +2615,7 @@ void assign_blame(struct blame_scoreboard *sb, int opt)
 		else {
 			commit->object.flags |= UNINTERESTING;
 			if (commit->object.parsed)
-				mark_parents_uninteresting(commit);
+				mark_parents_uninteresting(sb->revs, commit);
 		}
 		/* treat root commit as boundary */
 		if (!commit->parents && !sb->show_root)

revision.c

@@ -273,7 +273,7 @@ static void commit_stack_clear(struct commit_stack *stack)
 	stack->nr = stack->alloc = 0;
 }
 
-static void mark_one_parent_uninteresting(struct commit *commit,
+static void mark_one_parent_uninteresting(struct rev_info *revs, struct commit *commit,
 					  struct commit_stack *pending)
 {
 	struct commit_list *l;
@@ -290,20 +290,26 @@ static void mark_one_parent_uninteresting(struct commit *commit,
 	 * wasn't uninteresting), in which case we need
 	 * to mark its parents recursively too..
 	 */
-	for (l = commit->parents; l; l = l->next)
+	for (l = commit->parents; l; l = l->next) {
 		commit_stack_push(pending, l->item);
+		if (revs && revs->exclude_first_parent_only)
+			break;
+	}
 }
 
-void mark_parents_uninteresting(struct commit *commit)
+void mark_parents_uninteresting(struct rev_info *revs, struct commit *commit)
 {
 	struct commit_stack pending = COMMIT_STACK_INIT;
 	struct commit_list *l;
 
-	for (l = commit->parents; l; l = l->next)
-		mark_one_parent_uninteresting(l->item, &pending);
+	for (l = commit->parents; l; l = l->next) {
+		mark_one_parent_uninteresting(revs, l->item, &pending);
+		if (revs && revs->exclude_first_parent_only)
+			break;
+	}
 
 	while (pending.nr > 0)
-		mark_one_parent_uninteresting(commit_stack_pop(&pending),
+		mark_one_parent_uninteresting(revs, commit_stack_pop(&pending),
 					      &pending);
 
 	commit_stack_clear(&pending);
@@ -441,7 +447,7 @@ static struct commit *handle_commit(struct rev_info *revs,
 		if (repo_parse_commit(revs->repo, commit) < 0)
 			die("unable to parse commit %s", name);
 		if (flags & UNINTERESTING) {
-			mark_parents_uninteresting(commit);
+			mark_parents_uninteresting(revs, commit);
 
 			if (!revs->topo_order || !generation_numbers_enabled(the_repository))
 				revs->limited = 1;
@@ -1124,14 +1130,16 @@ static int process_parents(struct rev_info *revs, struct commit *commit,
 			if (repo_parse_commit_gently(revs->repo, p, 1) < 0)
 				continue;
 			if (p->parents)
-				mark_parents_uninteresting(p);
+				mark_parents_uninteresting(revs, p);
 			if (p->object.flags & SEEN)
 				continue;
 			p->object.flags |= (SEEN | NOT_USER_GIVEN);
 			if (list)
 				commit_list_insert_by_date(p, list);
 			if (queue)
 				prio_queue_put(queue, p);
+			if (revs->exclude_first_parent_only)
+				break;
 		}
 		return 0;
 	}
@@ -1422,7 +1430,7 @@ static int limit_list(struct rev_info *revs)
 		if (process_parents(revs, commit, &original_list, NULL) < 0)
 			return -1;
 		if (obj->flags & UNINTERESTING) {
-			mark_parents_uninteresting(commit);
+			mark_parents_uninteresting(revs, commit);
 			slop = still_interesting(original_list, date, slop, &interesting_cache);
 			if (slop)
 				continue;
@@ -2223,6 +2231,8 @@ static int handle_revision_opt(struct rev_info *revs, int argc, const char **arg
 		return argcount;
 	} else if (!strcmp(arg, "--first-parent")) {
 		revs->first_parent_only = 1;
+	} else if (!strcmp(arg, "--exclude-first-parent-only")) {
+		revs->exclude_first_parent_only = 1;
 	} else if (!strcmp(arg, "--ancestry-path")) {
 		revs->ancestry_path = 1;
 		revs->simplify_history = 0;
@@ -3345,7 +3355,7 @@ static void explore_walk_step(struct rev_info *revs)
 		return;
 
 	if (c->object.flags & UNINTERESTING)
-		mark_parents_uninteresting(c);
+		mark_parents_uninteresting(revs, c);
 
 	for (p = c->parents; p; p = p->next)
 		test_flag_and_insert(&info->explore_queue, p->item, TOPO_WALK_EXPLORED);

revision.h

@@ -158,6 +158,7 @@ struct rev_info {
 			bisect:1,
 			ancestry_path:1,
 			first_parent_only:1,
+			exclude_first_parent_only:1,
 			line_level_traverse:1,
 			tree_blobs_in_commit_order:1,
 
@@ -398,7 +399,7 @@ const char *get_revision_mark(const struct rev_info *revs,
 void put_revision_mark(const struct rev_info *revs,
 		       const struct commit *commit);
 
-void mark_parents_uninteresting(struct commit *commit);
+void mark_parents_uninteresting(struct rev_info *revs, struct commit *commit);
 void mark_tree_uninteresting(struct repository *r, struct tree *tree);
 void mark_trees_uninteresting_sparse(struct repository *r, struct oidset *trees);
 

shallow.c

@@ -603,7 +603,7 @@ static int mark_uninteresting(const char *refname, const struct object_id *oid,
 	if (!commit)
 		return 0;
 	commit->object.flags |= UNINTERESTING;
-	mark_parents_uninteresting(commit);
+	mark_parents_uninteresting(NULL, commit);
 	return 0;
 }
 

t/t6012-rev-list-simplify.sh

@@ -16,13 +16,12 @@ unnote () {
 }
 
 #
-# Create a test repo with interesting commit graph:
+# Create a test repo with an interesting commit graph:
 #
-# A--B----------G--H--I--K--L
-#  \  \           /     /
-#   \  \         /     /
-#    C------E---F     J
-#        \_/
+# A-----B-----G--H--I--K--L
+#  \     \      /     /
+#   \     \    /     /
+#    C--D--E--F     J
 #
 # The commits are laid out from left-to-right starting with
 # the root commit A and terminating at the tip commit L.
@@ -142,6 +141,13 @@ check_result 'I B A' --author-date-order -- file
 check_result 'H' --first-parent -- another-file
 check_result 'H' --first-parent --topo-order -- another-file
 
+check_result 'L K I H G B A' --first-parent L
+check_result 'F E D C' --exclude-first-parent-only F ^L
+check_result '' F ^L
+check_result 'L K I H G J' L ^F
+check_result 'L K I H G B J' --exclude-first-parent-only L ^F
+check_result 'L K I H G B' --exclude-first-parent-only --first-parent L ^F
+
 check_result 'E C B A' --full-history E -- lost
 test_expect_success 'full history simplification without parent' '
 	printf "%s\n" E C B A >expect &&