[PATCH v2 1/2] builtin/ls-files.c:add git ls-file --dedup option

["ZheNing Hu via GitGitGadget" <gitgitgadget@gmail.com>]

From: ZheNing Hu <adlternative@gmail.com>

1.When we use git ls-files with both -m -d,
we would find that repeated path,sometimes
it is confusing.
2.When we are performing a branch merge,
 the default git ls-files will also output
 multiple repeated file names.
Therefore, I added the --dedup option to git ls-files.
1. It can be achieved that only the deleted file name
is displayed when using -m, -d, and --dedup at the same time.
2. Add --dedup when merging branches to remove duplicate file
 names. (unless -s, -u are used)

Signed-off-by: ZheNing Hu <adlternative@gmail.com>
---
 builtin/ls-files.c | 43 ++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 38 insertions(+), 5 deletions(-)

diff --git a/builtin/ls-files.c b/builtin/ls-files.c
index c8eae899b82..66a7e251a46 100644
--- a/builtin/ls-files.c
+++ b/builtin/ls-files.c
@@ -35,6 +35,7 @@ static int line_terminator = '\n';
 static int debug_mode;
 static int show_eol;
 static int recurse_submodules;
+static int delete_dup;
 
 static const char *prefix;
 static int max_prefix_len;
@@ -301,6 +302,7 @@ static void show_files(struct repository *repo, struct dir_struct *dir)
 {
 	int i;
 	struct strbuf fullname = STRBUF_INIT;
+	const struct cache_entry *last_stage=NULL;
 
 	/* For cached/deleted files we don't need to even do the readdir */
 	if (show_others || show_killed) {
@@ -315,7 +317,20 @@ static void show_files(struct repository *repo, struct dir_struct *dir)
 	if (show_cached || show_stage) {
 		for (i = 0; i < repo->index->cache_nr; i++) {
 			const struct cache_entry *ce = repo->index->cache[i];
-
+			if(show_cached && delete_dup){
+				switch (ce_stage(ce)) {
+				case 0:
+				default:
+					break;
+				case 1:
+				case 2:
+				case 3:
+					if (last_stage &&
+					!strcmp(last_stage->name, ce->name))
+						continue;
+					last_stage=ce;
+				}
+			}
 			construct_fullname(&fullname, repo, ce);
 
 			if ((dir->flags & DIR_SHOW_IGNORED) &&
@@ -336,7 +351,20 @@ static void show_files(struct repository *repo, struct dir_struct *dir)
 			const struct cache_entry *ce = repo->index->cache[i];
 			struct stat st;
 			int err;
-
+			if(delete_dup){
+				switch (ce_stage(ce)) {
+				case 0:
+				default:
+					break;
+				case 1:
+				case 2:
+				case 3:
+					if (last_stage &&
+					!strcmp(last_stage->name, ce->name))
+						continue;
+					last_stage=ce;
+				}
+			}
 			construct_fullname(&fullname, repo, ce);
 
 			if ((dir->flags & DIR_SHOW_IGNORED) &&
@@ -347,10 +375,14 @@ static void show_files(struct repository *repo, struct dir_struct *dir)
 			if (ce_skip_worktree(ce))
 				continue;
 			err = lstat(fullname.buf, &st);
-			if (show_deleted && err)
+			if(delete_dup && show_deleted && show_modified && err)
 				show_ce(repo, dir, ce, fullname.buf, tag_removed);
-			if (show_modified && ie_modified(repo->index, ce, &st, 0))
-				show_ce(repo, dir, ce, fullname.buf, tag_modified);
+			else{
+				if (show_deleted && err)/* you can't find it,so it's actually removed at all! */
+					show_ce(repo, dir, ce, fullname.buf, tag_removed);
+				if (show_modified && ie_modified(repo->index, ce, &st, 0))
+					show_ce(repo, dir, ce, fullname.buf, tag_modified);
+			}
 		}
 	}
 
@@ -578,6 +610,7 @@ int cmd_ls_files(int argc, const char **argv, const char *cmd_prefix)
 			N_("pretend that paths removed since <tree-ish> are still present")),
 		OPT__ABBREV(&abbrev),
 		OPT_BOOL(0, "debug", &debug_mode, N_("show debugging data")),
+		OPT_BOOL(0, "dedup", &delete_dup, N_("delete duplicate entry in index")),
 		OPT_END()
 	};
 
-- 
gitgitgadget