[v2,5/8] sparse-checkout: create helper methods

Commit Message

Derrick Stolee Aug. 10, 2021, 7:50 p.m. UTC

From: Derrick Stolee <[e-mail]>

As we integrate the sparse index into more builtins, we occasionally
need to check the sparse-checkout patterns to see if a path is within
the sparse-checkout cone. Create some helper methods that help
initialize the patterns and check for pattern matching to make this
easier.

The existing callers of commands like get_sparse_checkout_patterns() use
a custom 'struct pattern_list' that is not necessarily the one in the
'struct index_state', so there are not many previous uses that could
adopt these helpers. There are just two in builtin/add.c and
sparse-index.c that can use path_in_sparse_checkout().

Signed-off-by: Derrick Stolee <[e-mail]>
---
 builtin/add.c  |  8 ++------
 dir.c          | 29 +++++++++++++++++++++++++++++
 dir.h          |  6 ++++++
 sparse-index.c | 12 +++---------
 4 files changed, 40 insertions(+), 15 deletions(-)

Comments

Derrick Stolee Aug. 12, 2021, 5:29 p.m. UTC | #1

On 8/10/2021 3:50 PM, Derrick Stolee via GitGitGadget wrote:
...
> +enum pattern_match_result path_in_sparse_checkout(const char *path,
> +						  struct index_state *istate)
> +{
> +	int dtype = DT_REG;
> +	init_sparse_checkout_patterns(istate);
> +
> +	if (!istate->sparse_checkout_patterns)
> +		return MATCHED;
> +
> +	return path_matches_pattern_list(path, strlen(path), NULL, &dtype,
> +					 istate->sparse_checkout_patterns,
> +					 istate);

While expanding on this work to fix behavior in 'git (add|rm|mv)' around
sparse entries, I noticed a problem with this method, specifically with
non-cone-mode patterns:

1. The NULL here should be the "basename" of the path, not NULL. This doesn't
   matter for cone mode, but _does_ matter for more general patterns.

2. The return type here can be UNDECIDED with general patterns, which really
   means "not matched" but is distinct from NOT_MATCHED because of the recursive
   assumptions when a directory is returned with NOT_MATCHED. Since the usage
   pattern for path_in_sparse_checkout() is to get a boolean result, the
   return type should switch to 'int' and we should return
   "path_matches_pattern_list(...) > 0".

I'm still doing some more testing to ensure I've got the necessary tweaks in
place to work with the other changes I'm going for. Plan on me sending a v3
with the appropriate changes here.

>  	/*
>  	 * Is the current path outside of the sparse cone?
>  	 * Then check if the region can be replaced by a sparse
>  	 * directory entry (everything is sparse and merged).
>  	 */
> -	match = path_matches_pattern_list(ct_path, ct_pathlen,
> -					  NULL, &dtype, pl, istate);
> +	match = path_in_sparse_checkout(ct_path, istate);
>  	if (match != NOT_MATCHED)
>  		can_convert = 0;

We could remove the use of "match" here and use the boolean result of
path_in_sparse_checkout() instead.

Thanks,
-Stolee

Patch

diff --git a/builtin/add.c b/builtin/add.c
index 17528e8f922..f675bdeae4a 100644
--- a/builtin/add.c
+++ b/builtin/add.c
@@ -190,8 +190,6 @@  static int refresh(int verbose, const struct pathspec *pathspec)
 	struct string_list only_match_skip_worktree = STRING_LIST_INIT_NODUP;
 	int flags = REFRESH_IGNORE_SKIP_WORKTREE |
 		    (verbose ? REFRESH_IN_PORCELAIN : REFRESH_QUIET);
-	struct pattern_list pl = { 0 };
-	int sparse_checkout_enabled = !get_sparse_checkout_patterns(&pl);
 
 	seen = xcalloc(pathspec->nr, 1);
 	refresh_index(&the_index, flags, pathspec, seen,
@@ -199,12 +197,10 @@  static int refresh(int verbose, const struct pathspec *pathspec)
 	for (i = 0; i < pathspec->nr; i++) {
 		if (!seen[i]) {
 			const char *path = pathspec->items[i].original;
-			int dtype = DT_REG;
 
 			if (matches_skip_worktree(pathspec, i, &skip_worktree_seen) ||
-			    (sparse_checkout_enabled &&
-			     !path_matches_pattern_list(path, strlen(path), NULL,
-							&dtype, &pl, &the_index))) {
+			    (core_apply_sparse_checkout &&
+			     path_in_sparse_checkout(path, &the_index) == NOT_MATCHED)) {
 				string_list_append(&only_match_skip_worktree,
 						   pathspec->items[i].original);
 			} else {
diff --git a/dir.c b/dir.c
index 03c4d212672..7027bdfa068 100644
--- a/dir.c
+++ b/dir.c
@@ -1439,6 +1439,35 @@  done:
 	return result;
 }
 
+int init_sparse_checkout_patterns(struct index_state *istate)
+{
+	if (istate->sparse_checkout_patterns)
+		return 0;
+
+	CALLOC_ARRAY(istate->sparse_checkout_patterns, 1);
+
+	if (get_sparse_checkout_patterns(istate->sparse_checkout_patterns) < 0) {
+		FREE_AND_NULL(istate->sparse_checkout_patterns);
+		return -1;
+	}
+
+	return 0;
+}
+
+enum pattern_match_result path_in_sparse_checkout(const char *path,
+						  struct index_state *istate)
+{
+	int dtype = DT_REG;
+	init_sparse_checkout_patterns(istate);
+
+	if (!istate->sparse_checkout_patterns)
+		return MATCHED;
+
+	return path_matches_pattern_list(path, strlen(path), NULL, &dtype,
+					 istate->sparse_checkout_patterns,
+					 istate);
+}
+
 static struct path_pattern *last_matching_pattern_from_lists(
 		struct dir_struct *dir, struct index_state *istate,
 		const char *pathname, int pathlen,
diff --git a/dir.h b/dir.h
index b3e1a54a971..9af2e8c4ba4 100644
--- a/dir.h
+++ b/dir.h
@@ -394,6 +394,12 @@  enum pattern_match_result path_matches_pattern_list(const char *pathname,
 				const char *basename, int *dtype,
 				struct pattern_list *pl,
 				struct index_state *istate);
+
+int init_sparse_checkout_patterns(struct index_state *state);
+
+enum pattern_match_result path_in_sparse_checkout(const char *path,
+						  struct index_state *istate);
+
 struct dir_entry *dir_add_ignored(struct dir_struct *dir,
 				  struct index_state *istate,
 				  const char *pathname, int len);
diff --git a/sparse-index.c b/sparse-index.c
index b6e90417556..2efc9fd4910 100644
--- a/sparse-index.c
+++ b/sparse-index.c
@@ -34,17 +34,14 @@  static int convert_to_sparse_rec(struct index_state *istate,
 	int i, can_convert = 1;
 	int start_converted = num_converted;
 	enum pattern_match_result match;
-	int dtype = DT_UNKNOWN;
 	struct strbuf child_path = STRBUF_INIT;
-	struct pattern_list *pl = istate->sparse_checkout_patterns;
 
 	/*
 	 * Is the current path outside of the sparse cone?
 	 * Then check if the region can be replaced by a sparse
 	 * directory entry (everything is sparse and merged).
 	 */
-	match = path_matches_pattern_list(ct_path, ct_pathlen,
-					  NULL, &dtype, pl, istate);
+	match = path_in_sparse_checkout(ct_path, istate);
 	if (match != NOT_MATCHED)
 		can_convert = 0;
 
@@ -153,11 +150,8 @@  int convert_to_sparse(struct index_state *istate)
 	if (!istate->repo->settings.sparse_index)
 		return 0;
 
-	if (!istate->sparse_checkout_patterns) {
-		istate->sparse_checkout_patterns = xcalloc(1, sizeof(struct pattern_list));
-		if (get_sparse_checkout_patterns(istate->sparse_checkout_patterns) < 0)
-			return 0;
-	}
+	if (init_sparse_checkout_patterns(istate) < 0)
+		return 0;
 
 	/*
 	 * We need cone-mode patterns to use sparse-index. If a user edits