[PATCH v2 1/3] commit-reach: implement get_reachable_subset

From: Derrick Stolee via GitGitGadget <gitgitgadget@gmail.com>
Date: Nov 2, 2018, 13:14 UTC
Message-ID: <9e570603bda528986f425cae8a9c32ba700bc29b.1541164482.git.gitgitgadget@gmail.com>
In-Reply-To: <pull.60.v2.git.gitgitgadget@gmail.com>

From: Derrick Stolee <dstolee@microsoft.com>

The existing reachability algorithms in commit-reach.c focus on finding merge-bases or determining if all commits in a set X can reach at least one commit in a set Y. However, for two commits sets X and Y, we may also care about which commits in Y are reachable from at least one commit in X.

Implement get_reachable_subset() which answers this question. Given two arrays of commits, 'from' and 'to', return a commit_list with every commit from the 'to' array that is reachable from at least one commit in the 'from' array.

The algorithm is a simple walk starting at the 'from' commits, using the PARENT2 flag to indicate "this commit has already been added to the walk queue". By marking the 'to' commits with the PARENT1 flag, we can determine when we see a commit from the 'to' array. We remove the PARENT1 flag as we add that commit to the result list to avoid duplicates.

The order of the resulting list is a reverse of the order that the commits are discovered in the walk.

There are a couple shortcuts to avoid walking more than we need:

1. We determine the minimum generation number of commits in the
   'to' array. We do not walk commits with generation number
   below this minimum.

2. We count how many distinct commits are in the 'to' array, and
   decrement this count when we discover a 'to' commit during the
   walk. If this number reaches zero, then we can terminate the
   walk.

Tests will be added using the 'test-tool reach' helper in a subsequent commit.

Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
---
 commit-reach.c | 70 ++++++++++++++++++++++++++++++++++++++++++++++++++
 commit-reach.h | 13 ++++++++++
 2 files changed, 83 insertions(+)

diff --git a/commit-reach.c b/commit-reach.c
index 9f79ce0a22..8ad5352752 100644
--- a/commit-reach.c
+++ b/commit-reach.c
@@ -688,3 +688,73 @@ int can_all_from_reach(struct commit_list *from, struct commit_list *to,
 	object_array_clear(&from_objs);
 	return result;
 }
+
+struct commit_list *get_reachable_subset(struct commit **from, int nr_from,
+					 struct commit **to, int nr_to,
+					 unsigned int reachable_flag)
+{
+	struct commit **item;
+	struct commit *current;
+	struct commit_list *found_commits = NULL;
+	struct commit **to_last = to + nr_to;
+	struct commit **from_last = from + nr_from;
+	uint32_t min_generation = GENERATION_NUMBER_INFINITY;
+	int num_to_find = 0;
+
+	struct prio_queue queue = { compare_commits_by_gen_then_commit_date };
+
+	for (item = to; item < to_last; item++) {
+		struct commit *c = *item;
+		
+		parse_commit(c);
+		if (c->generation < min_generation)
+			min_generation = c->generation;
+
+		if (!(c->object.flags & PARENT1)) {
+			c->object.flags |= PARENT1;
+			num_to_find++;
+		}
+	}
+
+	for (item = from; item < from_last; item++) {
+		struct commit *c = *item;
+		if (!(c->object.flags & PARENT2)) {
+			c->object.flags |= PARENT2;
+			parse_commit(c);
+
+			prio_queue_put(&queue, *item);
+		}
+	}
+
+	while (num_to_find && (current = prio_queue_get(&queue)) != NULL) {
+		struct commit_list *parents;
+
+		if (current->object.flags & PARENT1) {
+			current->object.flags &= ~PARENT1;
+			current->object.flags |= reachable_flag;
+			commit_list_insert(current, &found_commits);
+			num_to_find--;
+		}
+
+		for (parents = current->parents; parents; parents = parents->next) {
+			struct commit *p = parents->item;
+
+			parse_commit(p);
+
+			if (p->generation < min_generation)
+				continue;
+
+			if (p->object.flags & PARENT2)
+				continue;
+
+			p->object.flags |= PARENT2;
+			prio_queue_put(&queue, p);
+		}
+	}
+
+	clear_commit_marks_many(nr_to, to, PARENT1);
+	clear_commit_marks_many(nr_from, from, PARENT2);
+
+	return found_commits;
+}
+
diff --git a/commit-reach.h b/commit-reach.h
index 7d313e2975..bb34af0269 100644
--- a/commit-reach.h
+++ b/commit-reach.h
@@ -74,4 +74,17 @@ int can_all_from_reach_with_flag(struct object_array *from,
 int can_all_from_reach(struct commit_list *from, struct commit_list *to,
 		       int commit_date_cutoff);
 
+
+/*
+ * Return a list of commits containing the commits in the 'to' array
+ * that are reachable from at least one commit in the 'from' array.
+ * Also add the given 'flag' to each of the commits in the returned list.
+ *
+ * This method uses the PARENT1 and PARENT2 flags during its operation,
+ * so be sure these flags are not set before calling the method.
+ */
+struct commit_list *get_reachable_subset(struct commit **from, int nr_from,
+					 struct commit **to, int nr_to,
+					 unsigned int reachable_flag);
+
 #endif

-- 
gitgitgadget