rev-list: support human-readable output for --disk-usage

The '--disk-usage' option for git-rev-list was introduced in 16950f8
(rev-list: add --disk-usage option for calculating disk usage, 2021-02-09).
This is very useful for people inspect their git repo's objects usage
infomation, but the resulting number is quit hard for a human to read.

Teach git rev-list to output a human readable result when using
'--disk-usage'.

Signed-off-by: Li Linchao <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: Li Linchao

Documentation/rev-list-options.txt

@@ -242,13 +242,16 @@ ifdef::git-rev-list[]
 	to `/dev/null` as the output does not have to be formatted.
 
 --disk-usage::
+--disk-usage=human::
 	Suppress normal output; instead, print the sum of the bytes used
 	for on-disk storage by the selected commits or objects. This is
 	equivalent to piping the output into `git cat-file
 	--batch-check='%(objectsize:disk)'`, except that it runs much
 	faster (especially with `--use-bitmap-index`). See the `CAVEATS`
 	section in linkgit:git-cat-file[1] for the limitations of what
 	"on-disk storage" means.
+	With the optional value `human`, on-disk storage size is shown
+	in human-readable string(e.g. 12.24 Kib, 3.50 Mib).
 endif::git-rev-list[]
 
 --cherry-mark::

builtin/rev-list.c

@@ -46,6 +46,7 @@ static const char rev_list_usage[] =
 "    --parents\n"
 "    --children\n"
 "    --objects | --objects-edge\n"
+"    --disk-usage[=human]\n"
 "    --unpacked\n"
 "    --header | --pretty\n"
 "    --[no-]object-names\n"
@@ -81,6 +82,7 @@ static int arg_show_object_names = 1;
 
 static int show_disk_usage;
 static off_t total_disk_usage;
+static int human_readable;
 
 static off_t get_object_disk_usage(struct object *obj)
 {
@@ -368,6 +370,17 @@ static int show_object_fast(
 	return 1;
 }
 
+static void print_disk_usage(off_t size)
+{
+	struct strbuf sb = STRBUF_INIT;
+	if (human_readable)
+		strbuf_humanise_bytes(&sb, size);
+	else
+		strbuf_addf(&sb, "%"PRIuMAX, (uintmax_t)size);
+	puts(sb.buf);
+	strbuf_release(&sb);
+}
+
 static inline int parse_missing_action_value(const char *value)
 {
 	if (!strcmp(value, "error")) {
@@ -473,6 +486,7 @@ static int try_bitmap_disk_usage(struct rev_info *revs,
 				 int filter_provided_objects)
 {
 	struct bitmap_index *bitmap_git;
+	off_t size_from_bitmap;
 
 	if (!show_disk_usage)
 		return -1;
@@ -481,8 +495,8 @@ static int try_bitmap_disk_usage(struct rev_info *revs,
 	if (!bitmap_git)
 		return -1;
 
-	printf("%"PRIuMAX"\n",
-	       (uintmax_t)get_disk_usage_from_bitmap(bitmap_git, revs));
+	size_from_bitmap = get_disk_usage_from_bitmap(bitmap_git, revs);
+	print_disk_usage(size_from_bitmap);
 	return 0;
 }
 
@@ -624,7 +638,21 @@ int cmd_rev_list(int argc, const char **argv, const char *prefix)
 			continue;
 		}
 
-		if (!strcmp(arg, "--disk-usage")) {
+		if (skip_prefix(arg, "--disk-usage", &arg)) {
+			if (*arg == '=') {
+				if (!strcmp(++arg, "human")) {
+					human_readable = 1;
+				} else
+					die(_("invalid value for '%s': '%s', the only allowed format is '%s'"),
+					    "--disk-usage=<format>", arg, "human");
+			} else if (*arg) {
+				/*
+				 * Arguably should goto a label to continue chain of ifs?
+				 * Doesn't matter unless we try to add --disk-usage-foo
+				 * afterwards.
+				 */
+				usage(rev_list_usage);
+			}
 			show_disk_usage = 1;
 			info.flags |= REV_LIST_QUIET;
 			continue;
@@ -753,7 +781,7 @@ int cmd_rev_list(int argc, const char **argv, const char *prefix)
 	}
 
 	if (show_disk_usage)
-		printf("%"PRIuMAX"\n", (uintmax_t)total_disk_usage);
+		print_disk_usage(total_disk_usage);
 
 cleanup:
 	release_revisions(&revs);

t/t6115-rev-list-du.sh

@@ -48,4 +48,26 @@ check_du HEAD
 check_du --objects HEAD
 check_du --objects HEAD^..HEAD
 
+# As mentioned above, don't use hardcode sizes as actual size, but use the
+# output from git cat-file.
+test_expect_success 'rev-list --disk-usage=human' '
+	git rev-list --objects HEAD --disk-usage=human >actual &&
+	disk_usage_slow --objects HEAD >actual_size &&
+	grep "$(cat actual_size) bytes" actual
+'
+
+test_expect_success 'rev-list --disk-usage=human with bitmaps' '
+	git rev-list --objects HEAD --use-bitmap-index --disk-usage=human >actual &&
+	disk_usage_slow --objects HEAD >actual_size &&
+	grep "$(cat actual_size) bytes" actual
+'
+
+test_expect_success 'rev-list use --disk-usage unproperly' '
+	test_must_fail git rev-list --objects HEAD --disk-usage=typo 2>err &&
+	cat >expect <<-\EOF &&
+	fatal: invalid value for '\''--disk-usage=<format>'\'': '\''typo'\'', the only allowed format is '\''human'\''
+	EOF
+	test_cmp err expect
+'
+
 test_done