[PATCH v5 11/17] unpack-trees: hash less in cone mode

["Derrick Stolee via GitGitGadget" <gitgitgadget@xxxxxxxxx>]

From: Derrick Stolee <dstolee@xxxxxxxxxxxxx>

The sparse-checkout feature in "cone mode" can use the fact that
the recursive patterns are "connected" to the root via parent
patterns to decide if a directory is entirely contained in the
sparse-checkout or entirely removed.

In these cases, we can skip hashing the paths within those
directories and simply set the skipworktree bit to the correct
value.

Signed-off-by: Derrick Stolee <dstolee@xxxxxxxxxxxxx>
---
 dir.c          |  4 ++--
 dir.h          |  1 +
 unpack-trees.c | 38 +++++++++++++++++++++++---------------
 3 files changed, 26 insertions(+), 17 deletions(-)

diff --git a/dir.c b/dir.c
index 35c1ca9e24..2ef92a50a0 100644
--- a/dir.c
+++ b/dir.c
@@ -1270,7 +1270,7 @@ enum pattern_match_result path_matches_pattern_list(
 
 	if (hashmap_contains_path(&pl->recursive_hashmap,
 				  &parent_pathname)) {
-		result = MATCHED;
+		result = MATCHED_RECURSIVE;
 		goto done;
 	}
 
@@ -1292,7 +1292,7 @@ enum pattern_match_result path_matches_pattern_list(
 	if (hashmap_contains_parent(&pl->recursive_hashmap,
 				    pathname,
 				    &parent_pathname))
-		result = MATCHED;
+		result = MATCHED_RECURSIVE;
 
 done:
 	strbuf_release(&parent_pathname);
diff --git a/dir.h b/dir.h
index 8e232085cd..77a43dbf89 100644
--- a/dir.h
+++ b/dir.h
@@ -264,6 +264,7 @@ enum pattern_match_result {
 	UNDECIDED = -1,
 	NOT_MATCHED = 0,
 	MATCHED = 1,
+	MATCHED_RECURSIVE = 2,
 };
 
 /*
diff --git a/unpack-trees.c b/unpack-trees.c
index a90d71845d..c0dca20865 100644
--- a/unpack-trees.c
+++ b/unpack-trees.c
@@ -1283,15 +1283,17 @@ static int clear_ce_flags_dir(struct index_state *istate,
 	struct cache_entry **cache_end;
 	int dtype = DT_DIR;
 	int rc;
-	enum pattern_match_result ret;
-	ret = path_matches_pattern_list(prefix->buf, prefix->len,
-					basename, &dtype, pl, istate);
+	enum pattern_match_result ret, orig_ret;
+	orig_ret = path_matches_pattern_list(prefix->buf, prefix->len,
+					     basename, &dtype, pl, istate);
 
 	strbuf_addch(prefix, '/');
 
 	/* If undecided, use matching result of parent dir in defval */
-	if (ret == UNDECIDED)
+	if (orig_ret == UNDECIDED)
 		ret = default_match;
+	else
+		ret = orig_ret;
 
 	for (cache_end = cache; cache_end != cache + nr; cache_end++) {
 		struct cache_entry *ce = *cache_end;
@@ -1299,17 +1301,23 @@ static int clear_ce_flags_dir(struct index_state *istate,
 			break;
 	}
 
-	/*
-	 * TODO: check pl, if there are no patterns that may conflict
-	 * with ret (iow, we know in advance the incl/excl
-	 * decision for the entire directory), clear flag here without
-	 * calling clear_ce_flags_1(). That function will call
-	 * the expensive path_matches_pattern_list() on every entry.
-	 */
-	rc = clear_ce_flags_1(istate, cache, cache_end - cache,
-			      prefix,
-			      select_mask, clear_mask,
-			      pl, ret);
+	if (pl->use_cone_patterns && orig_ret == MATCHED_RECURSIVE) {
+		struct cache_entry **ce = cache;
+		rc = (cache_end - cache) / sizeof(struct cache_entry *);
+
+		while (ce < cache_end) {
+			(*ce)->ce_flags &= ~clear_mask;
+			ce++;
+		}
+	} else if (pl->use_cone_patterns && orig_ret == NOT_MATCHED) {
+		rc = (cache_end - cache) / sizeof(struct cache_entry *);
+	} else {
+		rc = clear_ce_flags_1(istate, cache, cache_end - cache,
+				      prefix,
+				      select_mask, clear_mask,
+				      pl, ret);
+	}
+
 	strbuf_setlen(prefix, prefix->len - 1);
 	return rc;
 }
-- 
gitgitgadget