ls-tree: introduce "--format" option

Add a --format option to ls-tree. It has an existing default output,
and then --long and --name-only options to emit the default output
along with the objectsize and, or to only emit object paths.

Rather than add --type-only, --object-only etc. we can just support a
--format using a strbuf_expand() similar to "for-each-ref
--format". We might still add such options in the future for
convenience.

The --format implementation is slower than the existing code, but this
change does not cause any performance regressions. We'll leave the
existing show_tree() unchanged, and only run show_tree_fmt() in if
a --format different than the hardcoded built-in ones corresponding to
the existing modes is provided.

I.e. something like the "--long" output would be much slower with
this, mainly due to how we need to allocate various things to do with
quote.c instead of spewing the output directly to stdout.

The new option of '--format' comes from Ævar Arnfjörð Bjarmasonn's
idea and suggestion, this commit makes modifications in terms of the
original discussion on community [1].

In [1] there was a "GIT_TEST_LS_TREE_FORMAT_BACKEND" variable to
ensure that we had test coverage for passing tests that would
otherwise use show_tree() through show_tree_fmt(), and thus that the
formatting mechanism could handle all the same cases as the
non-formatting options.

Somewhere in subsequent re-rolls of that we seem to have drifted away
from what the goal of these tests should be. We're trying to ensure
correctness of show_tree_fmt(). We can't tell if we "hit [the]
fast-path" here, and instead of having an explicit test for that, we
can just add it to something our "test_ls_tree_format" tests for.

Here is the statistics about performance tests:

1. Default format (hitten the builtin formats):

    "git ls-tree <tree-ish>" vs "--format='%(mode) %(type) %(object)%x09%(file)'"

    $hyperfine --warmup=10 "/opt/git/master/bin/git ls-tree -r HEAD"
    Benchmark 1: /opt/git/master/bin/git ls-tree -r HEAD
    Time (mean ± σ):     105.2 ms ±   3.3 ms    [User: 84.3 ms, System: 20.8 ms]
    Range (min … max):    99.2 ms … 113.2 ms    28 runs

    $hyperfine --warmup=10 "/opt/git/ls-tree-oid-only/bin/git ls-tree -r --format='%(mode) %(type) %(object)%x09%(file)'  HEAD"
    Benchmark 1: /opt/git/ls-tree-oid-only/bin/git ls-tree -r --format='%(mode) %(type) %(object)%x09%(file)'  HEAD
    Time (mean ± σ):     106.4 ms ±   2.7 ms    [User: 86.1 ms, System: 20.2 ms]
    Range (min … max):   100.2 ms … 110.5 ms    29 runs

2. Default format includes object size (hitten the builtin formats):

    "git ls-tree -l <tree-ish>" vs "--format='%(mode) %(type) %(object) %(size:padded)%x09%(file)'"

    $hyperfine --warmup=10 "/opt/git/master/bin/git ls-tree -r -l HEAD"
    Benchmark 1: /opt/git/master/bin/git ls-tree -r -l HEAD
    Time (mean ± σ):     335.1 ms ±   6.5 ms    [User: 304.6 ms, System: 30.4 ms]
    Range (min … max):   327.5 ms … 348.4 ms    10 runs

    $hyperfine --warmup=10 "/opt/git/ls-tree-oid-only/bin/git ls-tree -r --format='%(mode) %(type) %(object) %(size:padded)%x09%(file)'  HEAD"
    Benchmark 1: /opt/git/ls-tree-oid-only/bin/git ls-tree -r --format='%(mode) %(type) %(object) %(size:padded)%x09%(file)'  HEAD
    Time (mean ± σ):     337.2 ms ±   8.2 ms    [User: 309.2 ms, System: 27.9 ms]
    Range (min … max):   328.8 ms … 349.4 ms    10 runs

Links:
	[1] https://public-inbox.org/git/RFC-patch-6.7-eac299f06ff-20211217T131635Z-avarab@gmail.com/
	[2] https://lore.kernel.org/git/cb717d08be87e3239117c6c667cb32caabaad33d.1646390152.git.dyroneteng@gmail.com/

Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com>
Signed-off-by: Teng Long <dyroneteng@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 150 insertions, 3 deletions

diff --git a/builtin/ls-tree.c b/builtin/ls-tree.c
index edc8bf53a6..8a1bf2fa4d 100644
--- a/builtin/ls-tree.c
+++ b/builtin/ls-tree.c
@@ -23,6 +23,8 @@ static int ls_options;
 static struct pathspec pathspec;
 static int chomp_prefix;
 static const char *ls_tree_prefix;
+static const char *format;
+
 struct show_tree_data {
 	unsigned mode;
 	enum object_type type;
@@ -37,10 +39,77 @@ static const  char * const ls_tree_usage[] = {
 };
 
 static enum ls_tree_cmdmode {
-	MODE_LONG = 1,
+	MODE_DEFAULT = 0,
+	MODE_LONG,
 	MODE_NAME_ONLY,
 } cmdmode;
 
+static void expand_objectsize(struct strbuf *line, const struct object_id *oid,
+			      const enum object_type type, unsigned int padded)
+{
+	if (type == OBJ_BLOB) {
+		unsigned long size;
+		if (oid_object_info(the_repository, oid, &size) < 0)
+			die(_("could not get object info about '%s'"),
+			    oid_to_hex(oid));
+		if (padded)
+			strbuf_addf(line, "%7"PRIuMAX, (uintmax_t)size);
+		else
+			strbuf_addf(line, "%"PRIuMAX, (uintmax_t)size);
+	} else if (padded) {
+		strbuf_addf(line, "%7s", "-");
+	} else {
+		strbuf_addstr(line, "-");
+	}
+}
+
+static size_t expand_show_tree(struct strbuf *sb, const char *start,
+			       void *context)
+{
+	struct show_tree_data *data = context;
+	const char *end;
+	const char *p;
+	unsigned int errlen;
+	size_t len = strbuf_expand_literal_cb(sb, start, NULL);
+
+	if (len)
+		return len;
+	if (*start != '(')
+		die(_("bad ls-tree format: element '%s' does not start with '('"), start);
+
+	end = strchr(start + 1, ')');
+	if (!end)
+		die(_("bad ls-tree format: element '%s' does not end in ')'"), start);
+
+	len = end - start + 1;
+	if (skip_prefix(start, "(objectmode)", &p)) {
+		strbuf_addf(sb, "%06o", data->mode);
+	} else if (skip_prefix(start, "(objecttype)", &p)) {
+		strbuf_addstr(sb, type_name(data->type));
+	} else if (skip_prefix(start, "(objectsize:padded)", &p)) {
+		expand_objectsize(sb, data->oid, data->type, 1);
+	} else if (skip_prefix(start, "(objectsize)", &p)) {
+		expand_objectsize(sb, data->oid, data->type, 0);
+	} else if (skip_prefix(start, "(objectname)", &p)) {
+		strbuf_add_unique_abbrev(sb, data->oid, abbrev);
+	} else if (skip_prefix(start, "(path)", &p)) {
+		const char *name = data->base->buf;
+		const char *prefix = chomp_prefix ? ls_tree_prefix : NULL;
+		struct strbuf quoted = STRBUF_INIT;
+		struct strbuf sbuf = STRBUF_INIT;
+		strbuf_addstr(data->base, data->pathname);
+		name = relative_path(data->base->buf, prefix, &sbuf);
+		quote_c_style(name, &quoted, NULL, 0);
+		strbuf_addbuf(sb, &quoted);
+		strbuf_release(&sbuf);
+		strbuf_release(&quoted);
+	} else {
+		errlen = (unsigned long)len;
+		die(_("bad ls-tree format: %%%.*s"), errlen, start);
+	}
+	return len;
+}
+
 static int show_recursive(const char *base, size_t baselen, const char *pathname)
 {
 	int i;
@@ -71,6 +140,38 @@ static int show_recursive(const char *base, size_t baselen, const char *pathname
 	return 0;
 }
 
+static int show_tree_fmt(const struct object_id *oid, struct strbuf *base,
+			 const char *pathname, unsigned mode, void *context)
+{
+	size_t baselen;
+	int recurse = 0;
+	struct strbuf sb = STRBUF_INIT;
+	enum object_type type = object_type(mode);
+
+	struct show_tree_data data = {
+		.mode = mode,
+		.type = type,
+		.oid = oid,
+		.pathname = pathname,
+		.base = base,
+	};
+
+	if (type == OBJ_TREE && show_recursive(base->buf, base->len, pathname))
+		recurse = READ_TREE_RECURSIVE;
+	if (type == OBJ_TREE && recurse && !(ls_options & LS_SHOW_TREES))
+		return recurse;
+	if (type == OBJ_BLOB && (ls_options & LS_TREE_ONLY))
+		return 0;
+
+	baselen = base->len;
+	strbuf_expand(&sb, format, expand_show_tree, &data);
+	strbuf_addch(&sb, line_termination);
+	fwrite(sb.buf, sb.len, 1, stdout);
+	strbuf_release(&sb);
+	strbuf_setlen(base, baselen);
+	return recurse;
+}
+
 static int show_default(struct show_tree_data *data)
 {
 	size_t baselen = data->base->len;
@@ -145,11 +246,33 @@ static int show_tree(const struct object_id *oid, struct strbuf *base,
 	return recurse;
 }
 
+struct ls_tree_cmdmode_to_fmt {
+	enum ls_tree_cmdmode mode;
+	const char *const fmt;
+};
+
+static struct ls_tree_cmdmode_to_fmt ls_tree_cmdmode_format[] = {
+	{
+		.mode = MODE_DEFAULT,
+		.fmt = "%(objectmode) %(objecttype) %(objectname)%x09%(path)",
+	},
+	{
+		.mode = MODE_LONG,
+		.fmt = "%(objectmode) %(objecttype) %(objectname) %(objectsize:padded)%x09%(path)",
+	},
+	{
+		.mode = MODE_NAME_ONLY, /* And MODE_NAME_STATUS */
+		.fmt = "%(path)",
+	},
+	{ 0 },
+};
+
 int cmd_ls_tree(int argc, const char **argv, const char *prefix)
 {
 	struct object_id oid;
 	struct tree *tree;
 	int i, full_tree = 0;
+	read_tree_fn_t fn = show_tree;
 	const struct option ls_tree_options[] = {
 		OPT_BIT('d', NULL, &ls_options, N_("only show trees"),
 			LS_TREE_ONLY),
@@ -170,6 +293,9 @@ int cmd_ls_tree(int argc, const char **argv, const char *prefix)
 		OPT_BOOL(0, "full-tree", &full_tree,
 			 N_("list entire tree; not just current directory "
 			    "(implies --full-name)")),
+		OPT_STRING_F(0, "format", &format, N_("format"),
+					 N_("format to use for the output"),
+					 PARSE_OPT_NONEG),
 		OPT__ABBREV(&abbrev),
 		OPT_END()
 	};
@@ -190,6 +316,10 @@ int cmd_ls_tree(int argc, const char **argv, const char *prefix)
 	    ((LS_TREE_ONLY|LS_RECURSIVE) & ls_options))
 		ls_options |= LS_SHOW_TREES;
 
+	if (format && cmdmode)
+		usage_msg_opt(
+			_("--format can't be combined with other format-altering options"),
+			ls_tree_usage, ls_tree_options);
 	if (argc < 1)
 		usage_with_options(ls_tree_usage, ls_tree_options);
 	if (get_oid(argv[0], &oid))
@@ -211,6 +341,23 @@ int cmd_ls_tree(int argc, const char **argv, const char *prefix)
 	tree = parse_tree_indirect(&oid);
 	if (!tree)
 		die("not a tree object");
-	return !!read_tree(the_repository, tree,
-			   &pathspec, show_tree, NULL);
+	/*
+	 * The generic show_tree_fmt() is slower than show_tree(), so
+	 * take the fast path if possible.
+	 */
+	if (format) {
+		struct ls_tree_cmdmode_to_fmt *m2f;
+
+		fn = show_tree_fmt;
+		for (m2f = ls_tree_cmdmode_format; m2f->fmt; m2f++) {
+			if (strcmp(format, m2f->fmt))
+				continue;
+
+			cmdmode = m2f->mode;
+			fn = show_tree;
+			break;
+		}
+	}
+
+	return !!read_tree(the_repository, tree, &pathspec, fn, NULL);
 }