pathspec.h: move pathspec_needs_expanded_index() from reset.c to here

Method pathspec_needs_expanded_index() in reset.c from 4d1cfc1351
(reset: make --mixed sparse-aware, 2021-11-29) is reusable when we
need to verify if the index needs to be expanded when the command
is utilizing a pathspec rather than a literal path.

Move it to pathspec.h for reusability.

Add a few items to the function so it can better serve its purpose as
a standalone public function:

* Add a check in front so if the index is not sparse, return early since
  no expansion is needed.

* It now takes an arbitrary 'struct index_state' pointer instead of
  using `the_index` and `active_cache`.

* Add documentation to the function.

Helped-by: Victoria Dye <vdye@github.com>
Helped-by: Derrick Stolee <derrickstolee@github.com>
Signed-off-by: Shaoxuan Yuan <shaoxuan.yuan02@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 89 insertions, 0 deletions

diff --git a/pathspec.c b/pathspec.c
index 84ad9c73cf..46e77a85fe 100644
--- a/pathspec.c
+++ b/pathspec.c
@@ -759,3 +759,92 @@ int match_pathspec_attrs(struct index_state *istate,
 
 	return 1;
 }
+
+int pathspec_needs_expanded_index(struct index_state *istate,
+				  const struct pathspec *pathspec)
+{
+	unsigned int i, pos;
+	int res = 0;
+	char *skip_worktree_seen = NULL;
+
+	/*
+	 * If index is not sparse, no index expansion is needed.
+	 */
+	if (!istate->sparse_index)
+		return 0;
+
+	/*
+	 * When using a magic pathspec, assume for the sake of simplicity that
+	 * the index needs to be expanded to match all matchable files.
+	 */
+	if (pathspec->magic)
+		return 1;
+
+	for (i = 0; i < pathspec->nr; i++) {
+		struct pathspec_item item = pathspec->items[i];
+
+		/*
+		 * If the pathspec item has a wildcard, the index should be expanded
+		 * if the pathspec has the possibility of matching a subset of entries inside
+		 * of a sparse directory (but not the entire directory).
+		 *
+		 * If the pathspec item is a literal path, the index only needs to be expanded
+		 * if a) the pathspec isn't in the sparse checkout cone (to make sure we don't
+		 * expand for in-cone files) and b) it doesn't match any sparse directories
+		 * (since we can reset whole sparse directories without expanding them).
+		 */
+		if (item.nowildcard_len < item.len) {
+			/*
+			 * Special case: if the pattern is a path inside the cone
+			 * followed by only wildcards, the pattern cannot match
+			 * partial sparse directories, so we know we don't need to
+			 * expand the index.
+			 *
+			 * Examples:
+			 * - in-cone/foo***: doesn't need expanded index
+			 * - not-in-cone/bar*: may need expanded index
+			 * - **.c: may need expanded index
+			 */
+			if (strspn(item.original + item.nowildcard_len, "*") == item.len - item.nowildcard_len &&
+			    path_in_cone_mode_sparse_checkout(item.original, istate))
+				continue;
+
+			for (pos = 0; pos < istate->cache_nr; pos++) {
+				struct cache_entry *ce = istate->cache[pos];
+
+				if (!S_ISSPARSEDIR(ce->ce_mode))
+					continue;
+
+				/*
+				 * If the pre-wildcard length is longer than the sparse
+				 * directory name and the sparse directory is the first
+				 * component of the pathspec, need to expand the index.
+				 */
+				if (item.nowildcard_len > ce_namelen(ce) &&
+				    !strncmp(item.original, ce->name, ce_namelen(ce))) {
+					res = 1;
+					break;
+				}
+
+				/*
+				 * If the pre-wildcard length is shorter than the sparse
+				 * directory and the pathspec does not match the whole
+				 * directory, need to expand the index.
+				 */
+				if (!strncmp(item.original, ce->name, item.nowildcard_len) &&
+				    wildmatch(item.original, ce->name, 0)) {
+					res = 1;
+					break;
+				}
+			}
+		} else if (!path_in_cone_mode_sparse_checkout(item.original, istate) &&
+			   !matches_skip_worktree(pathspec, i, &skip_worktree_seen))
+			res = 1;
+
+		if (res > 0)
+			break;
+	}
+
+	free(skip_worktree_seen);
+	return res;
+}