Merge branch 'vd/cat-file-objectmode-update' into seen

"git cat-file --batch" learns to understand %(objectmode) atom to
allow the caller to tell missing objects (due to repository
corruption) and submodules (whose commit objects are OK to be
missing) apart.

Comments?

* vd/cat-file-objectmode-update:
  cat-file.c: add batch handling for submodules
  cat-file: add %(objectmode) atom
  t1006: update 'run_tests' to test generic object specifiers

Author: gitster

Documentation/git-cat-file.adoc

@@ -307,6 +307,11 @@ newline. The available atoms are:
 `objecttype`::
 	The type of the object (the same as `cat-file -t` reports).
 
+`objectmode`::
+	If the specified object has mode information (such as a tree or
+	index entry), the mode expressed as an octal integer. Otherwise,
+	empty string.
+
 `objectsize`::
 	The size, in bytes, of the object (the same as `cat-file -s`
 	reports).
@@ -368,6 +373,14 @@ If a name is specified that might refer to more than one object (an ambiguous sh
 <object> SP ambiguous LF
 ------------
 
+If a name is specified that refers to a submodule entry in a tree and the
+target object does not exist in the repository, then `cat-file` will ignore
+any custom format and print (with the object ID of the submodule):
+
+------------
+<oid> SP submodule LF
+------------
+
 If `--follow-symlinks` is used, and a symlink in the repository points
 outside the repository, then `cat-file` will ignore any custom format
 and print:

builtin/cat-file.c

@@ -275,6 +275,7 @@ struct expand_data {
 	struct object_id oid;
 	enum object_type type;
 	unsigned long size;
+	unsigned short mode;
 	off_t disk_size;
 	const char *rest;
 	struct object_id delta_base_oid;
@@ -306,6 +307,7 @@ struct expand_data {
 	 */
 	unsigned skip_object_info : 1;
 };
+#define EXPAND_DATA_INIT  { .mode = S_IFINVALID }
 
 static int is_atom(const char *atom, const char *s, int slen)
 {
@@ -345,6 +347,9 @@ static int expand_atom(struct strbuf *sb, const char *atom, int len,
 		else
 			strbuf_addstr(sb,
 				      oid_to_hex(&data->delta_base_oid));
+	} else if (is_atom("objectmode", atom, len)) {
+		if (!data->mark_query && !(S_IFINVALID == data->mode))
+			strbuf_addf(sb, "%06o", data->mode);
 	} else
 		return 0;
 	return 1;
@@ -489,7 +494,10 @@ static void batch_object_write(const char *obj_name,
 							    &data->oid, &data->info,
 							    OBJECT_INFO_LOOKUP_REPLACE);
 		if (ret < 0) {
-			report_object_status(opt, obj_name, &data->oid, "missing");
+			if (data->mode == S_IFGITLINK)
+				report_object_status(opt, oid_to_hex(&data->oid), &data->oid, "submodule");
+			else
+				report_object_status(opt, obj_name, &data->oid, "missing");
 			return;
 		}
 
@@ -611,6 +619,7 @@ static void batch_one_object(const char *obj_name,
 		goto out;
 	}
 
+	data->mode = ctx.mode;
 	batch_object_write(obj_name, scratch, opt, data, NULL, 0);
 
 out:
@@ -864,7 +873,7 @@ static int batch_objects(struct batch_options *opt)
 {
 	struct strbuf input = STRBUF_INIT;
 	struct strbuf output = STRBUF_INIT;
-	struct expand_data data;
+	struct expand_data data = EXPAND_DATA_INIT;
 	int save_warning;
 	int retval = 0;
 
@@ -873,7 +882,6 @@ static int batch_objects(struct batch_options *opt)
 	 * object_info to be handed to odb_read_object_info_extended for each
 	 * object.
 	 */
-	memset(&data, 0, sizeof(data));
 	data.mark_query = 1;
 	expand_format(&output,
 		      opt->format ? opt->format : DEFAULT_FORMAT,

t/t1006-cat-file.sh

@@ -113,53 +113,55 @@ strlen () {
 
 run_tests () {
     type=$1
-    oid=$2
-    size=$3
-    content=$4
-    pretty_content=$5
+    object_name="$2"
+    mode=$3
+    size=$4
+    content=$5
+    pretty_content=$6
+    oid=${7:-"$object_name"}
 
     batch_output="$oid $type $size
 $content"
 
     test_expect_success "$type exists" '
-	git cat-file -e $oid
+	git cat-file -e "$object_name"
     '
 
     test_expect_success "Type of $type is correct" '
 	echo $type >expect &&
-	git cat-file -t $oid >actual &&
+	git cat-file -t "$object_name" >actual &&
 	test_cmp expect actual
     '
 
     test_expect_success "Size of $type is correct" '
 	echo $size >expect &&
-	git cat-file -s $oid >actual &&
+	git cat-file -s "$object_name" >actual &&
 	test_cmp expect actual
     '
 
     test -z "$content" ||
     test_expect_success "Content of $type is correct" '
 	echo_without_newline "$content" >expect &&
-	git cat-file $type $oid >actual &&
+	git cat-file $type "$object_name" >actual &&
 	test_cmp expect actual
     '
 
     test_expect_success "Pretty content of $type is correct" '
 	echo_without_newline "$pretty_content" >expect &&
-	git cat-file -p $oid >actual &&
+	git cat-file -p "$object_name" >actual &&
 	test_cmp expect actual
     '
 
     test -z "$content" ||
     test_expect_success "--batch output of $type is correct" '
 	echo "$batch_output" >expect &&
-	echo $oid | git cat-file --batch >actual &&
+	echo "$object_name" | git cat-file --batch >actual &&
 	test_cmp expect actual
     '
 
     test_expect_success "--batch-check output of $type is correct" '
 	echo "$oid $type $size" >expect &&
-	echo_without_newline $oid | git cat-file --batch-check >actual &&
+	echo_without_newline "$object_name" | git cat-file --batch-check >actual &&
 	test_cmp expect actual
     '
 
@@ -168,44 +170,59 @@ $content"
 	test -z "$content" ||
 		test_expect_success "--batch-command $opt output of $type content is correct" '
 		echo "$batch_output" >expect &&
-		test_write_lines "contents $oid" | git cat-file --batch-command $opt >actual &&
+		test_write_lines "contents $object_name" | git cat-file --batch-command $opt >actual &&
 		test_cmp expect actual
 	'
 
 	test_expect_success "--batch-command $opt output of $type info is correct" '
 		echo "$oid $type $size" >expect &&
-		test_write_lines "info $oid" |
+		test_write_lines "info $object_name" |
 		git cat-file --batch-command $opt >actual &&
 		test_cmp expect actual
 	'
     done
 
     test_expect_success "custom --batch-check format" '
 	echo "$type $oid" >expect &&
-	echo $oid | git cat-file --batch-check="%(objecttype) %(objectname)" >actual &&
+	echo "$object_name" | git cat-file --batch-check="%(objecttype) %(objectname)" >actual &&
 	test_cmp expect actual
     '
 
     test_expect_success "custom --batch-command format" '
 	echo "$type $oid" >expect &&
-	echo "info $oid" | git cat-file --batch-command="%(objecttype) %(objectname)" >actual &&
+	echo "info $object_name" | git cat-file --batch-command="%(objecttype) %(objectname)" >actual &&
 	test_cmp expect actual
     '
 
-    test_expect_success '--batch-check with %(rest)' '
+    # FIXME: %(rest) is incompatible with object names that include whitespace,
+    # e.g. HEAD:path/to/a/file with spaces. Use the resolved OID as input to
+    # test this instead of the raw object name.
+    if echo "$object_name" | grep " "; then
+	test_rest=test_expect_failure
+    else
+	test_rest=test_expect_success
+    fi
+
+    $test_rest '--batch-check with %(rest)' '
 	echo "$type this is some extra content" >expect &&
-	echo "$oid    this is some extra content" |
+	echo "$object_name    this is some extra content" |
 		git cat-file --batch-check="%(objecttype) %(rest)" >actual &&
 	test_cmp expect actual
     '
 
+    test_expect_success '--batch-check with %(objectmode)' '
+	echo "$mode $oid" >expect &&
+	echo $object_name | git cat-file --batch-check="%(objectmode) %(objectname)" >actual &&
+	test_cmp expect actual
+    '
+
     test -z "$content" ||
     test_expect_success "--batch without type ($type)" '
 	{
 		echo "$size" &&
 		echo "$content"
 	} >expect &&
-	echo $oid | git cat-file --batch="%(objectsize)" >actual &&
+	echo "$object_name" | git cat-file --batch="%(objectsize)" >actual &&
 	test_cmp expect actual
     '
 
@@ -215,7 +232,7 @@ $content"
 		echo "$type" &&
 		echo "$content"
 	} >expect &&
-	echo $oid | git cat-file --batch="%(objecttype)" >actual &&
+	echo "$object_name" | git cat-file --batch="%(objecttype)" >actual &&
 	test_cmp expect actual
     '
 }
@@ -230,13 +247,14 @@ test_expect_success "setup" '
 	git config extensions.compatobjectformat $test_compat_hash_algo &&
 	echo_without_newline "$hello_content" > hello &&
 	git update-index --add hello &&
+	echo_without_newline "$hello_content" > "path with spaces" &&
+	git update-index --add --chmod=+x "path with spaces" &&
 	git commit -m "add hello file"
 '
 
 run_blob_tests () {
     oid=$1
-
-    run_tests 'blob' $oid $hello_size "$hello_content" "$hello_content"
+    run_tests 'blob' $oid "" $hello_size "$hello_content" "$hello_content"
 
     test_expect_success '--batch-command --buffer with flush for blob info' '
 	echo "$oid blob $hello_size" >expect &&
@@ -269,13 +287,17 @@ test_expect_success '--batch-check without %(rest) considers whole line' '
 
 tree_oid=$(git write-tree)
 tree_compat_oid=$(git rev-parse --output-object-format=$test_compat_hash_algo $tree_oid)
-tree_size=$(($(test_oid rawsz) + 13))
-tree_compat_size=$(($(test_oid --hash=compat rawsz) + 13))
-tree_pretty_content="100644 blob $hello_oid	hello${LF}"
-tree_compat_pretty_content="100644 blob $hello_compat_oid	hello${LF}"
-
-run_tests 'tree' $tree_oid $tree_size "" "$tree_pretty_content"
-run_tests 'tree' $tree_compat_oid $tree_compat_size "" "$tree_compat_pretty_content"
+tree_size=$((2 * $(test_oid rawsz) + 13 + 24))
+tree_compat_size=$((2 * $(test_oid --hash=compat rawsz) + 13 + 24))
+tree_pretty_content="100644 blob $hello_oid	hello${LF}100755 blob $hello_oid	path with spaces${LF}"
+tree_compat_pretty_content="100644 blob $hello_compat_oid	hello${LF}100755 blob $hello_compat_oid	path with spaces${LF}"
+
+run_tests 'tree' $tree_oid "" $tree_size "" "$tree_pretty_content"
+run_tests 'tree' $tree_compat_oid "" $tree_compat_size "" "$tree_compat_pretty_content"
+run_tests 'blob' "$tree_oid:hello" "100644" $hello_size "" "$hello_content" $hello_oid
+run_tests 'blob' "$tree_compat_oid:hello" "100644" $hello_size "" "$hello_content" $hello_compat_oid
+run_tests 'blob' "$tree_oid:path with spaces" "100755" $hello_size "" "$hello_content" $hello_oid
+run_tests 'blob' "$tree_compat_oid:path with spaces" "100755" $hello_size "" "$hello_content" $hello_compat_oid
 
 commit_message="Initial commit"
 commit_oid=$(echo_without_newline "$commit_message" | git commit-tree $tree_oid)
@@ -294,8 +316,8 @@ committer $GIT_COMMITTER_NAME <$GIT_COMMITTER_EMAIL> $GIT_COMMITTER_DATE
 
 $commit_message"
 
-run_tests 'commit' $commit_oid $commit_size "$commit_content" "$commit_content"
-run_tests 'commit' $commit_compat_oid $commit_compat_size "$commit_compat_content" "$commit_compat_content"
+run_tests 'commit' $commit_oid "" $commit_size "$commit_content" "$commit_content"
+run_tests 'commit' $commit_compat_oid "" $commit_compat_size "$commit_compat_content" "$commit_compat_content"
 
 tag_header_without_oid="type blob
 tag hellotag
@@ -318,8 +340,8 @@ tag_size=$(strlen "$tag_content")
 tag_compat_oid=$(git rev-parse --output-object-format=$test_compat_hash_algo $tag_oid)
 tag_compat_size=$(strlen "$tag_compat_content")
 
-run_tests 'tag' $tag_oid $tag_size "$tag_content" "$tag_content"
-run_tests 'tag' $tag_compat_oid $tag_compat_size "$tag_compat_content" "$tag_compat_content"
+run_tests 'tag' $tag_oid "" $tag_size "$tag_content" "$tag_content"
+run_tests 'tag' $tag_compat_oid "" $tag_compat_size "$tag_compat_content" "$tag_compat_content"
 
 test_expect_success "Reach a blob from a tag pointing to it" '
 	echo_without_newline "$hello_content" >expect &&
@@ -1198,6 +1220,31 @@ test_expect_success 'cat-file --batch-check respects replace objects' '
 	test_cmp expect actual
 '
 
+test_expect_success 'batch-check with a submodule' '
+	# FIXME: this call to mktree is incompatible with compatObjectFormat
+	# because the submodule OID cannot be mapped to the compat hash algo.
+	test_unconfig extensions.compatobjectformat &&
+	printf "160000 commit $(test_oid deadbeef)\tsub\n" >tree-with-sub &&
+	tree=$(git mktree <tree-with-sub) &&
+	test_config extensions.compatobjectformat $test_compat_hash_algo &&
+
+	git cat-file --batch-check >actual <<-EOF &&
+	$tree:sub
+	EOF
+	printf "$(test_oid deadbeef) submodule\n" >expect &&
+	test_cmp expect actual
+'
+
+test_expect_success 'batch-check with a submodule, object exists' '
+	printf "160000 commit $commit_oid\tsub\n" >tree-with-sub &&
+	tree=$(git mktree <tree-with-sub) &&
+	git cat-file --batch-check >actual <<-EOF &&
+	$tree:sub
+	EOF
+	printf "$commit_oid commit $commit_size\n" >expect &&
+	test_cmp expect actual
+'
+
 # Pull the entry for object with oid "$1" out of the output of
 # "cat-file --batch", including its object content (which requires
 # parsing and reading a set amount of bytes, hence perl).