git/list[1] front-page[2] threads[3] people[4] search[5] about
 

[PATCH v6 3/3] ls-files.c: add --deduplicate option

From
ZheNing Hu via GitGitGadget <gitgitgadget@gmail.com>
Date
Jan 23, 2021, 10:20 UTC
Message-ID
<07b603fd97c0e2d7a70407da552c3c0658a84731.1611397210.git.gitgitgadget@gmail.com>
In-Reply-To
<pull.832.v6.git.1611397210.gitgitgadget@gmail.com>
From: ZheNing Hu <adlternative@gmail.com>

In order to provide users a better experience when viewing information about files in the index and the working tree, the `--deduplicate` option will suppress some duplicate name under some conditions.

In a merge conflict, one file name of "git ls-files" output may appear multiple times. For example,now there is an unmerged path `a.c`,`a.c` will appear three times in the output of "git ls-files".We can use "git ls-files --deduplicate" to output `a.c` only one time.(unless `--stage` or `--unmerged` is used to view all the detailed information in the index)

In addition, if you use both `--delete` and `--modify` at the same time, The `--deduplicate` option can also suppress file name output.

Additional instructions: In order to display entries information,`deduplicate` suppresses the output of duplicate file names, not the output of duplicate entries information, so under the option of `-t`, `--stage`, `--unmerge`, `--deduplicate` will have no effect.

Signed-off-by: ZheNing Hu <adlternative@gmail.com>
---
 Documentation/git-ls-files.txt |  5 +++
 builtin/ls-files.c             | 30 +++++++++++++---
 t/t3012-ls-files-dedup.sh      | 66 ++++++++++++++++++++++++++++++++++
 3 files changed, 97 insertions(+), 4 deletions(-)
 create mode 100755 t/t3012-ls-files-dedup.sh
diff --git a/Documentation/git-ls-files.txt b/Documentation/git-ls-files.txt
index cbcf5263dd0..d11c8ade402 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>]
@@ -81,6 +82,10 @@ OPTIONS
 	\0 line termination on output and do not quote filenames.
 	See OUTPUT below for more information.
 
+--deduplicate::
+	Suppress duplicate entries when there are unmerged paths in index
+	or `--deleted` and `--modified` are combined.
+
 -x <pattern>::
 --exclude=<pattern>::
 	Skip untracked files matching pattern.
diff --git a/builtin/ls-files.c b/builtin/ls-files.c
index 966c0ab0296..fb9cf50d764 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;
@@ -326,12 +327,14 @@ static void show_files(struct repository *repo, struct dir_struct *dir)
 			continue;
 		if (ce->ce_flags & CE_UPDATE)
 			continue;
-		if (show_cached || show_stage) {
-			if (!show_unmerged || ce_stage(ce))
+		if ((show_cached || show_stage) &&
+			(!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;
@@ -340,11 +343,27 @@ 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 outer for loop */
+		}
 	}
 
 	strbuf_release(&fullname);
@@ -571,6 +590,7 @@ 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,"deduplicate",&skipping_duplicates,N_("suppress duplicate entries")),
 		OPT_END()
 	};
 
@@ -610,6 +630,8 @@ 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 00000000000..2682b1f43a6
--- /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

-- 
gitgitgadget
Previous: Junio C HamanoNext: Junio C Hamano
Message 54 of 65 in “builtin/ls-files.c:add git ls-file --dedup option”
  1. builtin/ls-files.c:add git ls-file --dedup option阿德烈 via GitGitGadget, Jan 6, 2021
  2. Eric SunshineJan 7, 2021
  3. Junio C HamanoJan 7, 2021
  4. 0/2 builtin/ls-files.c:add git ls-file --dedup option阿德烈 via GitGitGadget, Jan 8, 2021
  5. 1/2 builtin/ls-files.c:add git ls-file --dedup optionZheNing Hu via GitGitGadget, Jan 8, 2021
  6. 2/2 builtin:ls-files.c:add git ls-file --dedup optionZheNing Hu via GitGitGadget, Jan 8, 2021
  7. Eric SunshineJan 14, 2021
  8. 胡哲宁Jan 14, 2021
  9. ls-files.c: add --dedup option阿德烈 via GitGitGadget, Jan 14, 2021
  10. Junio C HamanoJan 15, 2021
  11. 胡哲宁Jan 17, 2021
  12. Junio C HamanoJan 17, 2021
  13. Eric SunshineJan 16, 2021
  14. 胡哲宁Jan 17, 2021
  15. Eric SunshineJan 17, 2021
  16. Junio C HamanoJan 17, 2021
  17. Eric SunshineJan 18, 2021
  18. 0/3 builtin/ls-files.c:add git ls-file --dedup option阿德烈 via GitGitGadget, Jan 17, 2021
  19. 1/3 ls_files.c: bugfix for --deleted and --modifiedZheNing Hu via GitGitGadget, Jan 17, 2021
  20. Junio C HamanoJan 17, 2021
  21. 2/3 ls_files.c: consolidate two for loops into oneZheNing Hu via GitGitGadget, Jan 17, 2021
  22. 3/3 ls-files: add --deduplicate optionZheNing Hu via GitGitGadget, Jan 17, 2021
  23. Junio C HamanoJan 17, 2021
  24. Junio C HamanoJan 17, 2021
  25. 胡哲宁Jan 18, 2021
  26. 胡哲宁Jan 18, 2021
  27. Junio C HamanoJan 18, 2021
  28. 胡哲宁Jan 19, 2021
  29. 0/3 builtin/ls-files.c:add git ls-file --dedup option阿德烈 via GitGitGadget, Jan 19, 2021
  30. 3/3 ls-files.c: add --deduplicate optionZheNing Hu via GitGitGadget, Jan 19, 2021
  31. Junio C HamanoJan 20, 2021
  32. 胡哲宁Jan 21, 2021
  33. Junio C HamanoJan 21, 2021
  34. 胡哲宁Jan 22, 2021
  35. Johannes SchindelinJan 22, 2021
  36. Junio C HamanoJan 22, 2021
  37. GitGitGadget and `next`, was Re: [PATCH v5 3/3] ls-files.c: add --deduplicate optionJohannes Schindelin, Mar 19, 2021
  38. Junio C HamanoMar 19, 2021
  39. 胡哲宁Jan 23, 2021
  40. ls-files.c: add --deduplicate optionZheNing Hu, Jan 22, 2021
  41. Junio C HamanoJan 22, 2021
  42. 胡哲宁Jan 23, 2021
  43. 2/3 ls_files.c: consolidate two for loops into oneZheNing Hu via GitGitGadget, Jan 19, 2021
  44. Junio C HamanoJan 20, 2021
  45. 胡哲宁Jan 21, 2021
  46. 1/3 ls_files.c: bugfix for --deleted and --modifiedZheNing Hu via GitGitGadget, Jan 19, 2021
  47. Junio C HamanoJan 20, 2021
  48. 胡哲宁Jan 21, 2021
  49. 0/3 builtin/ls-files.c:add git ls-file --dedup option阿德烈 via GitGitGadget, Jan 23, 2021
  50. 1/3 ls_files.c: bugfix for --deleted and --modifiedZheNing Hu via GitGitGadget, Jan 23, 2021
  51. Junio C HamanoJan 23, 2021
  52. 2/3 ls_files.c: consolidate two for loops into oneZheNing Hu via GitGitGadget, Jan 23, 2021
  53. Junio C HamanoJan 23, 2021
  54. 3/3 ls-files.c: add --deduplicate optionZheNing Hu via GitGitGadget, Jan 23, 2021
  55. Junio C HamanoJan 23, 2021
  56. 1/3 ls_files.c: bugfix for --deleted and --modifiedJunio C Hamano, Jan 23, 2021
  57. 2/3 ls_files.c: consolidate two for loops into oneJunio C Hamano, Jan 23, 2021
  58. 3/3 ls-files.c: add --deduplicate optionJunio C Hamano, Jan 23, 2021
  59. 0/3 builtin/ls-files.c:add git ls-file --dedup option阿德烈 via GitGitGadget, Jan 24, 2021
  60. 1/3 ls_files.c: bugfix for --deleted and --modifiedZheNing Hu via GitGitGadget, Jan 24, 2021
  61. Junio C HamanoJan 24, 2021
  62. 胡哲宁Jan 25, 2021
  63. Junio C HamanoJan 25, 2021
  64. 2/3 ls_files.c: consolidate two for loops into oneZheNing Hu via GitGitGadget, Jan 24, 2021
  65. 3/3 ls-files.c: add --deduplicate optionZheNing Hu via GitGitGadget, Jan 24, 2021

Read the whole thread, see it on lore, or plain text.

$ cat FOOTERMessages come from the public archive at lore.kernel.org/git, fetched every hour. The front page is chosen and written each morning by an AI editor and can be wrong; the threads themselves are the record. About and API. For agents: an MCP server at https://gitlist.dev/mcp, and any thread, story or person page as Markdown by adding .md to its URL (or sending Accept: text/markdown). Details in /llms.txt.