cat-file: sort and de-dup output of --batch-all-objectsjk/cat-file-batch-all

The sorting we could probably live without, but printing
duplicates is just a hassle for the user, who must then
de-dup themselves (or risk a wrong answer if they are doing
something like counting objects with a particular property).

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

3 files changed, 18 insertions, 12 deletions

diff --git a/Documentation/git-cat-file.txt b/Documentation/git-cat-file.txt
index 6831b08efb..3105fc0720 100644
--- a/Documentation/git-cat-file.txt
+++ b/Documentation/git-cat-file.txt
@@ -74,8 +74,7 @@ OPTIONS
 	requested batch operation on all objects in the repository and
 	any alternate object stores (not just reachable objects).
 	Requires `--batch` or `--batch-check` be specified. Note that
-	the order of the objects is unspecified, and there may be
-	duplicate entries.
+	the objects are visited in order sorted by their hashes.
 
 --buffer::
 	Normally batch output is flushed after each object is output, so
diff --git a/builtin/cat-file.c b/builtin/cat-file.c
index 95604c4a63..07baad1e59 100644
--- a/builtin/cat-file.c
+++ b/builtin/cat-file.c
@@ -9,6 +9,7 @@
 #include "userdiff.h"
 #include "streaming.h"
 #include "tree-walk.h"
+#include "sha1-array.h"
 
 struct batch_options {
 	int enabled;
@@ -324,19 +325,19 @@ struct object_cb_data {
 	struct expand_data *expand;
 };
 
-static int batch_object_cb(const unsigned char *sha1,
-			   struct object_cb_data *data)
+static void batch_object_cb(const unsigned char sha1[20], void *vdata)
 {
+	struct object_cb_data *data = vdata;
 	hashcpy(data->expand->sha1, sha1);
 	batch_object_write(NULL, data->opt, data->expand);
-	return 0;
 }
 
 static int batch_loose_object(const unsigned char *sha1,
 			      const char *path,
 			      void *data)
 {
-	return batch_object_cb(sha1, data);
+	sha1_array_append(data, sha1);
+	return 0;
 }
 
 static int batch_packed_object(const unsigned char *sha1,
@@ -344,7 +345,8 @@ static int batch_packed_object(const unsigned char *sha1,
 			       uint32_t pos,
 			       void *data)
 {
-	return batch_object_cb(sha1, data);
+	sha1_array_append(data, sha1);
+	return 0;
 }
 
 static int batch_objects(struct batch_options *opt)
@@ -375,11 +377,17 @@ static int batch_objects(struct batch_options *opt)
 		data.info.typep = &data.type;
 
 	if (opt->all_objects) {
+		struct sha1_array sa = SHA1_ARRAY_INIT;
 		struct object_cb_data cb;
+
+		for_each_loose_object(batch_loose_object, &sa, 0);
+		for_each_packed_object(batch_packed_object, &sa, 0);
+
 		cb.opt = opt;
 		cb.expand = &data;
-		for_each_loose_object(batch_loose_object, &cb, 0);
-		for_each_packed_object(batch_packed_object, &cb, 0);
+		sha1_array_for_each_unique(&sa, batch_object_cb, &cb);
+
+		sha1_array_clear(&sa);
 		return 0;
 	}
 
diff --git a/t/t1006-cat-file.sh b/t/t1006-cat-file.sh
index 2b4220a604..4f38078ff3 100755
--- a/t/t1006-cat-file.sh
+++ b/t/t1006-cat-file.sh
@@ -548,7 +548,7 @@ test_expect_success 'git cat-file --batch --follow-symlink returns correct sha a
 '
 
 test_expect_success 'cat-file --batch-all-objects shows all objects' '
-	# make new repos so we now the full set of objects; we will
+	# make new repos so we know the full set of objects; we will
 	# also make sure that there are some packed and some loose
 	# objects, some referenced and some not, and that there are
 	# some available only via alternates.
@@ -569,8 +569,7 @@ test_expect_success 'cat-file --batch-all-objects shows all objects' '
 	) >>expect.unsorted &&
 	sort <expect.unsorted >expect &&
 	git -C all-two cat-file --batch-all-objects \
-				--batch-check="%(objectname)" >actual.unsorted &&
-	sort <actual.unsorted >actual &&
+				--batch-check="%(objectname)" >actual &&
 	test_cmp expect actual
 '