Merge branch 'kw/patch-ids-optim'

When "git rebase" tries to compare set of changes on the updated
upstream and our own branch, it computes patch-id for all of these
changes and attempts to find matches. This has been optimized by
lazily computing the full patch-id (which is expensive) to be
compared only for changes that touch the same set of paths.

* kw/patch-ids-optim:
  rebase: avoid computing unnecessary patch IDs
  patch-ids: add flag to create the diff patch id using header only data
  patch-ids: replace the seen indicator with a commit pointer
  patch-ids: stop using a hand-rolled hashmap implementation

1 files changed, 10 insertions, 6 deletions

diff --git a/diff.c b/diff.c
index b43d3dd..534c12e 100644
--- a/diff.c
+++ b/diff.c
@@ -4462,7 +4462,7 @@ static void patch_id_consume(void *priv, char *line, unsigned long len)
 }
 
 /* returns 0 upon success, and writes result into sha1 */
-static int diff_get_patch_id(struct diff_options *options, unsigned char *sha1)
+static int diff_get_patch_id(struct diff_options *options, unsigned char *sha1, int diff_header_only)
 {
 	struct diff_queue_struct *q = &diff_queued_diff;
 	int i;
@@ -4497,9 +4497,6 @@ static int diff_get_patch_id(struct diff_options *options, unsigned char *sha1)
 
 		diff_fill_sha1_info(p->one);
 		diff_fill_sha1_info(p->two);
-		if (fill_mmfile(&mf1, p->one) < 0 ||
-				fill_mmfile(&mf2, p->two) < 0)
-			return error("unable to read files to diff");
 
 		len1 = remove_space(p->one->path, strlen(p->one->path));
 		len2 = remove_space(p->two->path, strlen(p->two->path));
@@ -4534,6 +4531,13 @@ static int diff_get_patch_id(struct diff_options *options, unsigned char *sha1)
 					len2, p->two->path);
 		git_SHA1_Update(&ctx, buffer, len1);
 
+		if (diff_header_only)
+			continue;
+
+		if (fill_mmfile(&mf1, p->one) < 0 ||
+		    fill_mmfile(&mf2, p->two) < 0)
+			return error("unable to read files to diff");
+
 		if (diff_filespec_is_binary(p->one) ||
 		    diff_filespec_is_binary(p->two)) {
 			git_SHA1_Update(&ctx, oid_to_hex(&p->one->oid),
@@ -4556,11 +4560,11 @@ static int diff_get_patch_id(struct diff_options *options, unsigned char *sha1)
 	return 0;
 }
 
-int diff_flush_patch_id(struct diff_options *options, unsigned char *sha1)
+int diff_flush_patch_id(struct diff_options *options, unsigned char *sha1, int diff_header_only)
 {
 	struct diff_queue_struct *q = &diff_queued_diff;
 	int i;
-	int result = diff_get_patch_id(options, sha1);
+	int result = diff_get_patch_id(options, sha1, diff_header_only);
 
 	for (i = 0; i < q->nr; i++)
 		diff_free_filepair(q->queue[i]);