[PATCH 1/8] built-in add -i: allow filtering the modified files list

From: Johannes Schindelin via GitGitGadget <gitgitgadget@gmail.com>
Date: Nov 15, 2019, 12:36 UTC
Message-ID: <1844c4d55e21c40cbdbfdd73c82b4a1a074ff184.1573821382.git.gitgitgadget@gmail.com>
In-Reply-To: <pull.171.git.1573821382.gitgitgadget@gmail.com>

From: Johannes Schindelin <johannes.schindelin@gmx.de>

In the `update` command of `git add -i`, we are primarily interested in the list of modified files that have worktree (i.e. unstaged) changes.

At the same time, we need to determine _also_ the staged changes, to be able to produce the full added/deleted information.

The Perl script version of `git add -i` has a parameter of the `list_modified()` function for that matter. In C, we can be a lot more precise, using an `enum`.

The C implementation of the filter also has an easier time to avoid unnecessary work, simply by using an adaptive order of the `diff-index` and `diff-files` phases, and then skipping files in the second phase when they have not been seen in the first phase.

Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de>
---
 add-interactive.c | 25 ++++++++++++++++++++++---
 1 file changed, 22 insertions(+), 3 deletions(-)

diff --git a/add-interactive.c b/add-interactive.c
index 5d89863bab..8ec930ac15 100644
--- a/add-interactive.c
+++ b/add-interactive.c
@@ -347,6 +347,7 @@ struct collection_status {
 
 	const char *reference;
 
+	unsigned skip_unseen:1;
 	struct string_list *files;
 	struct hashmap file_map;
 };
@@ -374,6 +375,9 @@ static void collect_changes_cb(struct diff_queue_struct *q,
 		entry = hashmap_get_entry_from_hash(&s->file_map, hash, name,
 						    struct pathname_entry, ent);
 		if (!entry) {
+			if (s->skip_unseen)
+				continue;
+
 			add_file_item(s->files, name);
 
 			entry = xcalloc(sizeof(*entry), 1);
@@ -395,13 +399,22 @@ static void collect_changes_cb(struct diff_queue_struct *q,
 	free_diffstat_info(&stat);
 }
 
-static int get_modified_files(struct repository *r, struct string_list *files,
+enum modified_files_filter {
+	NO_FILTER = 0,
+	WORKTREE_ONLY = 1,
+	INDEX_ONLY = 2,
+};
+
+static int get_modified_files(struct repository *r,
+			      enum modified_files_filter filter,
+			      struct string_list *files,
 			      const struct pathspec *ps)
 {
 	struct object_id head_oid;
 	int is_initial = !resolve_ref_unsafe("HEAD", RESOLVE_REF_READING,
 					     &head_oid, NULL);
 	struct collection_status s = { FROM_WORKTREE };
+	int i;
 
 	if (discard_index(r->index) < 0 ||
 	    repo_read_index_preload(r, ps, 0) < 0)
@@ -411,10 +424,16 @@ static int get_modified_files(struct repository *r, struct string_list *files,
 	s.files = files;
 	hashmap_init(&s.file_map, pathname_entry_cmp, NULL, 0);
 
-	for (s.phase = FROM_WORKTREE; s.phase <= FROM_INDEX; s.phase++) {
+	for (i = 0; i < 2; i++) {
 		struct rev_info rev;
 		struct setup_revision_opt opt = { 0 };
 
+		if (filter == INDEX_ONLY)
+			s.phase = i ? FROM_WORKTREE : FROM_INDEX;
+		else
+			s.phase = i ? FROM_INDEX : FROM_WORKTREE;
+		s.skip_unseen = filter && i;
+
 		opt.def = is_initial ?
 			empty_tree_oid_hex() : oid_to_hex(&head_oid);
 
@@ -498,7 +517,7 @@ static void print_file_item(int i, struct string_list_item *item,
 static int run_status(struct add_i_state *s, const struct pathspec *ps,
 		      struct string_list *files, struct list_options *opts)
 {
-	if (get_modified_files(s->r, files, ps) < 0)
+	if (get_modified_files(s->r, NO_FILTER, files, ps) < 0)
 		return -1;
 
 	list(s, files, opts);

-- 
gitgitgadget