microsoft · derrickstolee · Sep 7, 2021 · Sep 3, 2021 · Sep 3, 2021 · Sep 3, 2021
diff --git a/builtin/sparse-checkout.c b/builtin/sparse-checkout.c
@@ -132,7 +132,7 @@ static void clean_tracked_sparse_directories(struct repository *r)
 	 * sparse index will not delete directories that contain
 	 * conflicted entries or submodules.
 	 */
-	if (!r->index->sparse_index) {
+	if (r->index->sparse_index == COMPLETELY_FULL) {
 		/*
 		 * If something, such as a merge conflict or other concern,
 		 * prevents us from converting to a sparse index, then do
@@ -444,6 +444,9 @@ static int sparse_checkout_init(int argc, const char **argv)
 		/* force an index rewrite */
 		repo_read_index(the_repository);
 		the_repository->index->updated_workdir = 1;
+
+		if (!init_opts.sparse_index)
+			ensure_full_index(the_repository->index);
 	}
 
 	core_apply_sparse_checkout = 1;
@@ -760,6 +763,9 @@ int cmd_sparse_checkout(int argc, const char **argv, const char *prefix)
 
 	git_config(git_default_config, NULL);
 
+	prepare_repo_settings(the_repository);
+	the_repository->settings.command_requires_full_index = 0;
+
 	if (argc > 0) {
 		if (!strcmp(argv[0], "list"))
 			return sparse_checkout_list(argc, argv);

diff --git a/cache-tree.c b/cache-tree.c
@@ -101,6 +101,31 @@ struct cache_tree_sub *cache_tree_sub(struct cache_tree *it, const char *path)
 	return find_subtree(it, path, pathlen, 1);
 }
 
+struct cache_tree *cache_tree_find_path(struct cache_tree *it, const char *path)
+{
+	const char *slash;
+	int namelen;
+	struct cache_tree_sub *down;
+
+	if (!it)
+		return NULL;
+	slash = strchrnul(path, '/');
+	namelen = slash - path;
+	it->entry_count = -1;
+	if (!*slash) {
+		int pos;
+		pos = cache_tree_subtree_pos(it, path, namelen);
+		if (0 <= pos) {
+			return it->down[pos]->cache_tree;
+		}
+		return NULL;
+	}
+	down = find_subtree(it, path, namelen, 0);
+	if (down)
+		return cache_tree_find_path(down->cache_tree, slash + 1);
+	return NULL;
+}
+
 static int do_invalidate_path(struct cache_tree *it, const char *path)
 {
 	/* a/b/c

diff --git a/cache-tree.h b/cache-tree.h
@@ -29,6 +29,8 @@ struct cache_tree_sub *cache_tree_sub(struct cache_tree *, const char *);
 
 int cache_tree_subtree_pos(struct cache_tree *it, const char *path, int pathlen);
 
+struct cache_tree *cache_tree_find_path(struct cache_tree *it, const char *path);
+
 void cache_tree_write(struct strbuf *, struct cache_tree *root);
 struct cache_tree *cache_tree_read(const char *buffer, unsigned long size);
 

diff --git a/cache.h b/cache.h
@@ -311,6 +311,28 @@ struct untracked_cache;
 struct progress;
 struct pattern_list;
 
+enum sparse_index_mode {
+	/*
+	 * COMPLETELY_FULL: there are no sparse directories
+	 * in the index at all.
+	 */
+	COMPLETELY_FULL = 0,
+
+	/*
+	 * COLLAPSED: the index has already been collapsed to sparse
+	 * directories whereever possible.
+	 */
+	COLLAPSED = 1,
+
+	/*
+	 * PARTIALLY_SPARSE: the sparse directories that exist are
+	 * outside the sparse-checkout boundary, but it is possible
+	 * that some file entries could collapse to sparse directory
+	 * entries.
+	 */
+	PARTIALLY_SPARSE = 2,
+};
+
 struct index_state {
 	struct cache_entry **cache;
 	unsigned int version;
@@ -324,14 +346,8 @@ struct index_state {
 		 drop_cache_tree : 1,
 		 updated_workdir : 1,
 		 updated_skipworktree : 1,
-		 fsmonitor_has_run_once : 1,
-
-		 /*
-		  * sparse_index == 1 when sparse-directory
-		  * entries exist. Requires sparse-checkout
-		  * in cone mode.
-		  */
-		 sparse_index : 1;
+		 fsmonitor_has_run_once : 1;
+	enum sparse_index_mode sparse_index;
 	struct hashmap name_hash;
 	struct hashmap dir_hash;
 	struct object_id oid;

diff --git a/dir.c b/dir.c
@@ -1402,46 +1402,16 @@ static struct path_pattern *last_matching_pattern_from_list(const char *pathname
 	return res;
 }
 
-/*
- * Scan the list of patterns to determine if the ordered list
- * of patterns matches on 'pathname'.
- *
- * Return 1 for a match, 0 for not matched and -1 for undecided.
- */
-enum pattern_match_result path_matches_pattern_list(
+enum pattern_match_result path_matches_cone_mode_pattern_list(
 				const char *pathname, int pathlen,
-				const char *basename, int *dtype,
-				struct pattern_list *pl,
-				struct index_state *istate)
+				struct pattern_list *pl)
 {
-	struct path_pattern *pattern;
 	struct strbuf parent_pathname = STRBUF_INIT;
 	int result = NOT_MATCHED;
 	size_t slash_pos;
 
-	/*
-	 * The virtual file system data is used to prevent git from traversing
-	 * any part of the tree that is not in the virtual file system.  Return
-	 * 1 to exclude the entry if it is not found in the virtual file system,
-	 * else fall through to the regular excludes logic as it may further exclude.
-	 */
-	if (*dtype == DT_UNKNOWN)
-		*dtype = resolve_dtype(DT_UNKNOWN, istate, pathname, pathlen);
-	if (is_excluded_from_virtualfilesystem(pathname, pathlen, *dtype) > 0)
-		return 1;
-
-	if (!pl->use_cone_patterns) {
-		pattern = last_matching_pattern_from_list(pathname, pathlen, basename,
-							dtype, pl, istate);
-		if (pattern) {
-			if (pattern->flags & PATTERN_FLAG_NEGATIVE)
-				return NOT_MATCHED;
-			else
-				return MATCHED;
-		}
-
-		return UNDECIDED;
-	}
+	if (!pl->use_cone_patterns)
+		BUG("path_matches_cone_mode_pattern_list requires cone mode patterns");
 
 	if (pl->full_cone)
 		return MATCHED;
@@ -1494,6 +1464,46 @@ enum pattern_match_result path_matches_pattern_list(
 	return result;
 }
 
+/*
+ * Scan the list of patterns to determine if the ordered list
+ * of patterns matches on 'pathname'.
+ *
+ * Return 1 for a match, 0 for not matched and -1 for undecided.
+ */
+enum pattern_match_result path_matches_pattern_list(
+				const char *pathname, int pathlen,
+				const char *basename, int *dtype,
+				struct pattern_list *pl,
+				struct index_state *istate)
+{
+	/*
+	 * The virtual file system data is used to prevent git from traversing
+	 * any part of the tree that is not in the virtual file system.  Return
+	 * 1 to exclude the entry if it is not found in the virtual file system,
+	 * else fall through to the regular excludes logic as it may further exclude.
+	 */
+	if (*dtype == DT_UNKNOWN)
+		*dtype = resolve_dtype(DT_UNKNOWN, istate, pathname, pathlen);
+	if (is_excluded_from_virtualfilesystem(pathname, pathlen, *dtype) > 0)
+		return 1;
+
+	if (!pl->use_cone_patterns) {
+		struct path_pattern *pattern = last_matching_pattern_from_list(
+							pathname, pathlen, basename,
+							dtype, pl, istate);
+		if (pattern) {
+			if (pattern->flags & PATTERN_FLAG_NEGATIVE)
+				return NOT_MATCHED;
+			else
+				return MATCHED;
+		}
+
+		return UNDECIDED;
+	}
+
+	return path_matches_cone_mode_pattern_list(pathname, pathlen, pl);
+}
+
 int init_sparse_checkout_patterns(struct index_state *istate)
 {
 	if (!core_apply_sparse_checkout ||

diff --git a/dir.h b/dir.h
@@ -383,6 +383,15 @@ enum pattern_match_result {
 	MATCHED_RECURSIVE = 2,
 };
 
+/*
+ * Test if a given path is contained in the given pattern list.
+ *
+ * The given pattern list _must_ use cone mode patterns.
+ */
+enum pattern_match_result path_matches_cone_mode_pattern_list(
+				const char *pathname, int pathlen,
+				struct pattern_list *pl);
+
 /*
  * Scan the list of patterns to determine if the ordered list
  * of patterns matches on 'pathname'.

diff --git a/read-cache.c b/read-cache.c
@@ -108,7 +108,7 @@ static const char *alternate_index_output;
 static void set_index_entry(struct index_state *istate, int nr, struct cache_entry *ce)
 {
 	if (S_ISSPARSEDIR(ce->ce_mode))
-		istate->sparse_index = 1;
+		istate->sparse_index = COLLAPSED;
 
 	istate->cache[nr] = ce;
 	add_name_hash(istate, ce);
@@ -1828,7 +1828,7 @@ static int read_index_extension(struct index_state *istate,
 		break;
 	case CACHE_EXT_SPARSE_DIRECTORIES:
 		/* no content, only an indicator */
-		istate->sparse_index = 1;
+		istate->sparse_index = COLLAPSED;
 		break;
 	default:
 		if (*ext < 'A' || 'Z' < *ext)
@@ -3109,7 +3109,7 @@ static int do_write_locked_index(struct index_state *istate, struct lock_file *l
 				 unsigned flags)
 {
 	int ret;
-	int was_full = !istate->sparse_index;
+	int was_full = istate->sparse_index == COMPLETELY_FULL;
 
 	ret = convert_to_sparse(istate, 0);