@matheusbsbs / matheus-bagliano / commits / cab851c2f8

ls-tree: support --object-only option for "git-ls-tree"

'--object-only' is an alias for '--format=%(objectname)'. It cannot be used together other format-altering options like '--name-only', '--long' or '--format', they are mutually exclusive. The "--name-only" option outputs <filepath> only. Likewise, <objectName> is another high frequency used field, so implement '--object-only' option will bring intuitive and clear semantics for this scenario. Using '--format=%(objectname)' we can achieve a similar effect, but the former is with a lower learning cost(without knowing the format requirement of '--format' option). Even so, if a user is prefer to use "--format=%(objectname)", this is entirely welcome because they are not only equivalent in function, but also have almost identical performance. The reason is this commit also add the specific of "--format=%(objectname)" to the current fast-pathes (builtin formats) to avoid running unnecessary parsing mechanisms. The following performance benchmarks are based on torvalds/linux.git: When hit the fast-path: Benchmark 1: /opt/git/ls-tree-oid-only/bin/git ls-tree -r --object-only HEAD Time (mean ± σ): 83.6 ms ± 2.0 ms [User: 59.4 ms, System: 24.1 ms] Range (min … max): 80.4 ms … 87.2 ms 35 runs Benchmark 1: /opt/git/ls-tree-oid-only/bin/git ls-tree -r --format='%(objectname)' HEAD Time (mean ± σ): 84.1 ms ± 1.8 ms [User: 61.7 ms, System: 22.3 ms] Range (min … max): 80.9 ms … 87.5 ms 35 runs But for a customized format, it will be slower: Benchmark 1: /opt/git/ls-tree-oid-only/bin/git ls-tree -r --format='oid: %(objectname)' HEAD Time (mean ± σ): 96.5 ms ± 2.5 ms [User: 72.9 ms, System: 23.5 ms] Range (min … max): 93.1 ms … 104.1 ms 31 runs Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Teng Long <dyroneteng@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>

Teng Long committed Mar 23, 2022 at 17:13 UTC cab851c2f8c190bed93719ca8c712fdfcc3c7182

4 files changed +36 -4

Documentation/git-ls-tree.txt

+10 -1

@@ -10,7 +10,7 @@ SYNOPSIS

10 --------

11 [verse]

12 'git ls-tree' [-d] [-r] [-t] [-l] [-z]

13 - [--name-only] [--name-status] [--full-name] [--full-tree] [--abbrev[=<n>]] [--format=<format>]

13 + [--name-only] [--name-status] [--object-only] [--full-name] [--full-tree] [--abbrev[=<n>]] [--format=<format>]

14 <tree-ish> [<path>...]

16 DESCRIPTION

@@ -59,6 +59,15 @@ OPTIONS

59 --name-only::

60 --name-status::

61 List only filenames (instead of the "long" output), one per line.

62 + Cannot be combined with `--object-only`.

63 +

64 +--object-only::

65 + List only names of the objects, one per line. Cannot be combined

66 + with `--name-only` or `--name-status`.

67 + This is equivalent to specifying `--format='%(objectname)'`, but

68 + for both this option and that exact format the command takes a

69 + hand-optimized codepath instead of going through the generic

70 + formatting mechanism.

72 --abbrev[=<n>]::

73 Instead of showing the full 40-byte hexadecimal object

builtin/ls-tree.c

+12 -1

@@ -24,7 +24,6 @@ static struct pathspec pathspec;

24 static int chomp_prefix;

25 static const char *ls_tree_prefix;

26 static const char *format;

27 -

27 struct show_tree_data {

28 unsigned mode;

29 enum object_type type;

@@ -42,6 +41,7 @@ static enum ls_tree_cmdmode {

41 MODE_DEFAULT = 0,

42 MODE_LONG,

43 MODE_NAME_ONLY,

44 + MODE_OBJECT_ONLY,

45 } cmdmode;

47 static void expand_objectsize(struct strbuf *line, const struct object_id *oid,

@@ -227,6 +227,11 @@ static int show_tree(const struct object_id *oid, struct strbuf *base,

227 return recurse;

228 }

229

230 + if (cmdmode == MODE_OBJECT_ONLY) {

231 + printf("%s%c", find_unique_abbrev(oid, abbrev), line_termination);

232 + return recurse;

233 + }

234 +

235 if (cmdmode == MODE_NAME_ONLY) {

236 baselen = base->len;

237 strbuf_addstr(base, pathname);

@@ -264,6 +269,10 @@ static struct ls_tree_cmdmode_to_fmt ls_tree_cmdmode_format[] = {

269 .mode = MODE_NAME_ONLY, /* And MODE_NAME_STATUS */

270 .fmt = "%(path)",

271 },

272 + {

273 + .mode = MODE_OBJECT_ONLY,

274 + .fmt = "%(objectname)",

275 + },

276 { 0 },

277 };

278

@@ -288,6 +297,8 @@ int cmd_ls_tree(int argc, const char **argv, const char *prefix)

297 MODE_NAME_ONLY),

298 OPT_CMDMODE(0, "name-status", &cmdmode, N_("list only filenames"),

299 MODE_NAME_ONLY),

300 + OPT_CMDMODE(0, "object-only", &cmdmode, N_("list only objects"),

301 + MODE_OBJECT_ONLY),

302 OPT_SET_INT(0, "full-name", &chomp_prefix,

303 N_("use full path names"), 0),

304 OPT_BOOL(0, "full-tree", &full_tree,

t/t3103-ls-tree-misc.sh

+5 -2

@@ -25,11 +25,14 @@ test_expect_success 'ls-tree fails with non-zero exit code on broken tree' '

26 for opts in \

27 "--name-only --long" \

28 - "--name-status --long"

28 + "--name-status --long" \

29 + "--name-only --object-only" \

30 + "--name-status --object-only" \

31 + "--object-only --long" \

32 + "--object-only --format"

33 do

34 test_expect_success "usage: incompatible options: $opts" '

35 test_expect_code 129 git ls-tree $opts $tree

36 '

37 done

34 -

38 test_done

t/t3104-ls-tree-format.sh

@@ -49,6 +49,15 @@ test_ls_tree_format \

49 "%(path)" \

50 "--name-only"

52 +test_ls_tree_format \

53 + "%(objectname)" \

54 + "--object-only"

55 +

56 +test_ls_tree_format \

57 + "%(objectname)" \

58 + "--object-only --abbrev" \

59 + "--abbrev"

60 +

61 test_ls_tree_format \

62 "%(objectmode) %(objecttype) %(objectname)%x09%(path)" \

63 "-t" \