reset: make sparse-aware (except --mixed)

Remove `ensure_full_index` guard on `prime_cache_tree` and update
`prime_cache_tree_rec` to correctly reconstruct sparse directory entries in
the cache tree. While processing a tree's entries, `prime_cache_tree_rec`
must determine whether a directory entry is sparse or not by searching for
it in the index (*without* expanding the index). If a matching sparse
directory index entry is found, no subtrees are added to the cache tree
entry and the entry count is set to 1 (representing the sparse directory
itself). Otherwise, the tree is assumed to not be sparse and its subtrees
are recursively added to the cache tree.

Helped-by: Elijah Newren <[email protected]>
Signed-off-by: Victoria Dye <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: vdye

cache-tree.c

@@ -740,15 +740,26 @@ int write_index_as_tree(struct object_id *oid, struct index_state *index_state,
 	return ret;
 }
 
+static void prime_cache_tree_sparse_dir(struct cache_tree *it,
+					struct tree *tree)
+{
+
+	oidcpy(&it->oid, &tree->object.oid);
+	it->entry_count = 1;
+}
+
 static void prime_cache_tree_rec(struct repository *r,
 				 struct cache_tree *it,
-				 struct tree *tree)
+				 struct tree *tree,
+				 struct strbuf *tree_path)
 {
 	struct tree_desc desc;
 	struct name_entry entry;
 	int cnt;
+	int base_path_len = tree_path->len;
 
 	oidcpy(&it->oid, &tree->object.oid);
+
 	init_tree_desc(&desc, tree->buffer, tree->size);
 	cnt = 0;
 	while (tree_entry(&desc, &entry)) {
@@ -757,27 +768,55 @@ static void prime_cache_tree_rec(struct repository *r,
 		else {
 			struct cache_tree_sub *sub;
 			struct tree *subtree = lookup_tree(r, &entry.oid);
+
 			if (!subtree->object.parsed)
 				parse_tree(subtree);
 			sub = cache_tree_sub(it, entry.path);
 			sub->cache_tree = cache_tree();
-			prime_cache_tree_rec(r, sub->cache_tree, subtree);
+
+			/*
+			 * Recursively-constructed subtree path is only needed when working
+			 * in a sparse index (where it's used to determine whether the
+			 * subtree is a sparse directory in the index).
+			 */
+			if (r->index->sparse_index) {
+				strbuf_setlen(tree_path, base_path_len);
+				strbuf_grow(tree_path, base_path_len + entry.pathlen + 1);
+				strbuf_add(tree_path, entry.path, entry.pathlen);
+				strbuf_addch(tree_path, '/');
+			}
+
+			/*
+			 * If a sparse index is in use, the directory being processed may be
+			 * sparse. To confirm that, we can check whether an entry with that
+			 * exact name exists in the index. If it does, the created subtree
+			 * should be sparse. Otherwise, cache tree expansion should continue
+			 * as normal.
+			 */
+			if (r->index->sparse_index &&
+			    index_entry_exists(r->index, tree_path->buf, tree_path->len))
+				prime_cache_tree_sparse_dir(sub->cache_tree, subtree);
+			else
+				prime_cache_tree_rec(r, sub->cache_tree, subtree, tree_path);
 			cnt += sub->cache_tree->entry_count;
 		}
 	}
+
 	it->entry_count = cnt;
 }
 
 void prime_cache_tree(struct repository *r,
 		      struct index_state *istate,
 		      struct tree *tree)
 {
+	struct strbuf tree_path = STRBUF_INIT;
+
 	trace2_region_enter("cache-tree", "prime_cache_tree", the_repository);
 	cache_tree_free(&istate->cache_tree);
 	istate->cache_tree = cache_tree();
 
-	ensure_full_index(istate);
-	prime_cache_tree_rec(r, istate->cache_tree, tree);
+	prime_cache_tree_rec(r, istate->cache_tree, tree, &tree_path);
+	strbuf_release(&tree_path);
 	istate->cache_changed |= CACHE_TREE_CHANGED;
 	trace2_region_leave("cache-tree", "prime_cache_tree", the_repository);
 }

cache.h

@@ -816,6 +816,16 @@ struct cache_entry *index_file_exists(struct index_state *istate, const char *na
  */
 int index_name_pos(struct index_state *, const char *name, int namelen);
 
+/*
+ * Determines whether an entry with the given name exists within the
+ * given index. The return value is 1 if an exact match is found, otherwise
+ * it is 0. Note that, unlike index_name_pos, this function does not expand
+ * the index if it is sparse. If an item exists within the full index but it
+ * is contained within a sparse directory (and not in the sparse index), 0 is
+ * returned.
+ */
+int index_entry_exists(struct index_state *, const char *name, int namelen);
+
 /*
  * Some functions return the negative complement of an insert position when a
  * precise match was not found but a position was found where the entry would

read-cache.c

@@ -68,6 +68,11 @@
  */
 #define CACHE_ENTRY_PATH_LENGTH 80
 
+enum index_search_mode {
+	NO_EXPAND_SPARSE = 0,
+	EXPAND_SPARSE = 1
+};
+
 static inline struct cache_entry *mem_pool__ce_alloc(struct mem_pool *mem_pool, size_t len)
 {
 	struct cache_entry *ce;
@@ -551,7 +556,10 @@ int cache_name_stage_compare(const char *name1, int len1, int stage1, const char
 	return 0;
 }
 
-static int index_name_stage_pos(struct index_state *istate, const char *name, int namelen, int stage)
+static int index_name_stage_pos(struct index_state *istate,
+				const char *name, int namelen,
+				int stage,
+				enum index_search_mode search_mode)
 {
 	int first, last;
 
@@ -570,7 +578,7 @@ static int index_name_stage_pos(struct index_state *istate, const char *name, in
 		first = next+1;
 	}
 
-	if (istate->sparse_index &&
+	if (search_mode == EXPAND_SPARSE && istate->sparse_index &&
 	    first > 0) {
 		/* Note: first <= istate->cache_nr */
 		struct cache_entry *ce = istate->cache[first - 1];
@@ -586,7 +594,7 @@ static int index_name_stage_pos(struct index_state *istate, const char *name, in
 		    ce_namelen(ce) < namelen &&
 		    !strncmp(name, ce->name, ce_namelen(ce))) {
 			ensure_full_index(istate);
-			return index_name_stage_pos(istate, name, namelen, stage);
+			return index_name_stage_pos(istate, name, namelen, stage, search_mode);
 		}
 	}
 
@@ -595,7 +603,12 @@ static int index_name_stage_pos(struct index_state *istate, const char *name, in
 
 int index_name_pos(struct index_state *istate, const char *name, int namelen)
 {
-	return index_name_stage_pos(istate, name, namelen, 0);
+	return index_name_stage_pos(istate, name, namelen, 0, EXPAND_SPARSE);
+}
+
+int index_entry_exists(struct index_state *istate, const char *name, int namelen)
+{
+	return index_name_stage_pos(istate, name, namelen, 0, NO_EXPAND_SPARSE) >= 0;
 }
 
 int remove_index_entry_at(struct index_state *istate, int pos)
@@ -1222,7 +1235,7 @@ static int has_dir_name(struct index_state *istate,
 			 */
 		}
 
-		pos = index_name_stage_pos(istate, name, len, stage);
+		pos = index_name_stage_pos(istate, name, len, stage, EXPAND_SPARSE);
 		if (pos >= 0) {
 			/*
 			 * Found one, but not so fast.  This could
@@ -1322,7 +1335,7 @@ static int add_index_entry_with_check(struct index_state *istate, struct cache_e
 		strcmp(ce->name, istate->cache[istate->cache_nr - 1]->name) > 0)
 		pos = index_pos_to_insert_pos(istate->cache_nr);
 	else
-		pos = index_name_stage_pos(istate, ce->name, ce_namelen(ce), ce_stage(ce));
+		pos = index_name_stage_pos(istate, ce->name, ce_namelen(ce), ce_stage(ce), EXPAND_SPARSE);
 
 	/* existing match? Just replace it. */
 	if (pos >= 0) {
@@ -1357,7 +1370,7 @@ static int add_index_entry_with_check(struct index_state *istate, struct cache_e
 		if (!ok_to_replace)
 			return error(_("'%s' appears as both a file and as a directory"),
 				     ce->name);
-		pos = index_name_stage_pos(istate, ce->name, ce_namelen(ce), ce_stage(ce));
+		pos = index_name_stage_pos(istate, ce->name, ce_namelen(ce), ce_stage(ce), EXPAND_SPARSE);
 		pos = -pos-1;
 	}
 	return pos + 1;

t/t1092-sparse-checkout-compatibility.sh

@@ -777,9 +777,9 @@ test_expect_success 'sparse-index is not expanded' '
 	ensure_not_expanded checkout - &&
 	ensure_not_expanded switch rename-out-to-out &&
 	ensure_not_expanded switch - &&
-	git -C sparse-index reset --hard &&
+	ensure_not_expanded reset --hard &&
 	ensure_not_expanded checkout rename-out-to-out -- deep/deeper1 &&
-	git -C sparse-index reset --hard &&
+	ensure_not_expanded reset --hard &&
 	ensure_not_expanded restore -s rename-out-to-out -- deep/deeper1 &&
 
 	echo >>sparse-index/README.md &&
@@ -789,6 +789,17 @@ test_expect_success 'sparse-index is not expanded' '
 	echo >>sparse-index/untracked.txt &&
 	ensure_not_expanded add . &&
 
+	for ref in update-deep update-folder1 update-folder2 update-deep
+	do
+		echo >>sparse-index/README.md &&
+		ensure_not_expanded reset --hard $ref || return 1
+	done &&
+
+	ensure_not_expanded reset --hard update-deep &&
+	ensure_not_expanded reset --keep base &&
+	ensure_not_expanded reset --merge update-deep &&
+	ensure_not_expanded reset --hard &&
+
 	ensure_not_expanded checkout -f update-deep &&
 	test_config -C sparse-index pull.twohead ort &&
 	(