ls-files.c: add --deduplicate option

During a merge conflict, the name of a file may appear multiple
times in "git ls-files" output, once for each stage.  If you use
both `--delete` and `--modify` at the same time, the output may
mention a deleted file twice.

When none of the '-t', '-u', or '-s' options is in use, these
duplicate entries do not add much value to the output.

Introduce a new '--deduplicate' option to suppress them.

Signed-off-by: ZheNing Hu <adlternative@gmail.com>
[jc: extended doc and rewritten commit log]
Signed-off-by: Junio C Hamano <gitster@pobox.com>

3 files changed, 102 insertions, 3 deletions

diff --git a/Documentation/git-ls-files.txt b/Documentation/git-ls-files.txt
index 0a3b5265b3..6d11ab506b 100644
--- a/Documentation/git-ls-files.txt
+++ b/Documentation/git-ls-files.txt
@@ -13,6 +13,7 @@ SYNOPSIS
 		(--[cached|deleted|others|ignored|stage|unmerged|killed|modified])*
 		(-[c|d|o|i|s|u|k|m])*
 		[--eol]
+		[--deduplicate]
 		[-x <pattern>|--exclude=<pattern>]
 		[-X <file>|--exclude-from=<file>]
 		[--exclude-per-directory=<file>]
@@ -80,6 +81,13 @@ OPTIONS
 	\0 line termination on output and do not quote filenames.
 	See OUTPUT below for more information.
 
+--deduplicate::
+	When only filenames are shown, suppress duplicates that may
+	come from having multiple stages during a merge, or giving
+	`--deleted` and `--modified` option at the same time.
+	When any of the `-t`, `--unmerged`, or `--stage` option is
+	in use, this option has no effect.
+
 -x <pattern>::
 --exclude=<pattern>::
 	Skip untracked files matching pattern.
diff --git a/builtin/ls-files.c b/builtin/ls-files.c
index e94d724aff..f6f9e483b2 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 skipping_duplicates;
 
 static const char *prefix;
 static int max_prefix_len;
@@ -328,11 +329,14 @@ static void show_files(struct repository *repo, struct dir_struct *dir)
 		if (ce->ce_flags & CE_UPDATE)
 			continue;
 		if ((show_cached || show_stage) &&
-		    (!show_unmerged || ce_stage(ce)))
+		    (!show_unmerged || ce_stage(ce))) {
 			show_ce(repo, dir, ce, fullname.buf,
 				ce_stage(ce) ? tag_unmerged :
 				(ce_skip_worktree(ce) ? tag_skip_worktree :
 				 tag_cached));
+			if (skipping_duplicates)
+				goto skip_to_next_name;
+		}
 
 		if (!(show_deleted || show_modified))
 			continue;
@@ -341,11 +345,28 @@ static void show_files(struct repository *repo, struct dir_struct *dir)
 		stat_err = lstat(fullname.buf, &st);
 		if (stat_err && (errno != ENOENT && errno != ENOTDIR))
 			error_errno("cannot lstat '%s'", fullname.buf);
-		if (stat_err && show_deleted)
+		if (stat_err && show_deleted) {
 			show_ce(repo, dir, ce, fullname.buf, tag_removed);
+			if (skipping_duplicates)
+				goto skip_to_next_name;
+		}
 		if (show_modified &&
-		    (stat_err || ie_modified(repo->index, ce, &st, 0)))
+		    (stat_err || ie_modified(repo->index, ce, &st, 0))) {
 			show_ce(repo, dir, ce, fullname.buf, tag_modified);
+			if (skipping_duplicates)
+				goto skip_to_next_name;
+		}
+		continue;
+
+skip_to_next_name:
+		{
+			int j;
+			struct cache_entry **cache = repo->index->cache;
+			for (j = i + 1; j < repo->index->cache_nr; j++)
+				if (strcmp(ce->name, cache[j]->name))
+					break;
+			i = j - 1; /* compensate for the for loop */
+		}
 	}
 
 	strbuf_release(&fullname);
@@ -572,6 +593,8 @@ 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, "deduplicate", &skipping_duplicates,
+			 N_("suppress duplicate entries")),
 		OPT_END()
 	};
 
@@ -611,6 +634,8 @@ int cmd_ls_files(int argc, const char **argv, const char *cmd_prefix)
 		 * you also show the stage information.
 		 */
 		show_stage = 1;
+	if (show_tag || show_stage)
+		skipping_duplicates = 0;
 	if (dir.exclude_per_dir)
 		exc_given = 1;
 
diff --git a/t/t3012-ls-files-dedup.sh b/t/t3012-ls-files-dedup.sh
new file mode 100755
index 0000000000..2682b1f43a
--- /dev/null
+++ b/t/t3012-ls-files-dedup.sh
@@ -0,0 +1,66 @@
+#!/bin/sh
+
+test_description='git ls-files --deduplicate test'
+
+. ./test-lib.sh
+
+test_expect_success 'setup' '
+	>a.txt &&
+	>b.txt &&
+	>delete.txt &&
+	git add a.txt b.txt delete.txt &&
+	git commit -m base &&
+	echo a >a.txt &&
+	echo b >b.txt &&
+	echo delete >delete.txt &&
+	git add a.txt b.txt delete.txt &&
+	git commit -m tip &&
+	git tag tip &&
+	git reset --hard HEAD^ &&
+	echo change >a.txt &&
+	git commit -a -m side &&
+	git tag side
+'
+
+test_expect_success 'git ls-files --deduplicate to show unique unmerged path' '
+	test_must_fail git merge tip &&
+	git ls-files --deduplicate >actual &&
+	cat >expect <<-\EOF &&
+	a.txt
+	b.txt
+	delete.txt
+	EOF
+	test_cmp expect actual &&
+	git merge --abort
+'
+
+test_expect_success 'git ls-files -d -m --deduplicate with different display options' '
+	git reset --hard side &&
+	test_must_fail git merge tip &&
+	rm delete.txt &&
+	git ls-files -d -m --deduplicate >actual &&
+	cat >expect <<-\EOF &&
+	a.txt
+	delete.txt
+	EOF
+	test_cmp expect actual &&
+	git ls-files -d -m -t --deduplicate >actual &&
+	cat >expect <<-\EOF &&
+	C a.txt
+	C a.txt
+	C a.txt
+	R delete.txt
+	C delete.txt
+	EOF
+	test_cmp expect actual &&
+	git ls-files -d -m -c --deduplicate >actual &&
+	cat >expect <<-\EOF &&
+	a.txt
+	b.txt
+	delete.txt
+	EOF
+	test_cmp expect actual &&
+	git merge --abort
+'
+
+test_done