Merge branch 'jk/no-funny-object-types'

Support to create a loose object file with unknown object type has
been dropped.

* jk/no-funny-object-types:
  object-file: drop support for writing objects with unknown types
  hash-object: handle --literally with OPT_NEGBIT
  hash-object: merge HASH_* and INDEX_* flags
  hash-object: stop allowing unknown types
  t: add lib-loose.sh
  t/helper: add zlib test-tool
  oid_object_info(): drop type_name strbuf
  fsck: stop using object_info->type_name strbuf
  oid_object_info_convert(): stop using string for object type
  cat-file: use type enum instead of buffer for -t option
  object-file: drop OBJECT_INFO_ALLOW_UNKNOWN_TYPE flag
  cat-file: make --allow-unknown-type a noop
  object-file.h: fix typo in variable declaration

Author: gitster

Documentation/git-cat-file.adoc

@@ -9,8 +9,7 @@ SYNOPSIS
 --------
 [verse]
 'git cat-file' <type> <object>
-'git cat-file' (-e | -p) <object>
-'git cat-file' (-t | -s) [--allow-unknown-type] <object>
+'git cat-file' (-e | -p | -t | -s) <object>
 'git cat-file' (--textconv | --filters)
 	     [<rev>:<path|tree-ish> | --path=<path|tree-ish> <rev>]
 'git cat-file' (--batch | --batch-check | --batch-command) [--batch-all-objects]
@@ -202,9 +201,6 @@ flush::
 	only once, even if it is stored multiple times in the
 	repository.
 
---allow-unknown-type::
-	Allow `-s` or `-t` to query broken/corrupt objects of unknown type.
-
 --follow-symlinks::
 	With `--batch` or `--batch-check`, follow symlinks inside the
 	repository when requesting objects with extended SHA-1

Makefile

@@ -859,6 +859,7 @@ TEST_BUILTINS_OBJS += test-wildmatch.o
 TEST_BUILTINS_OBJS += test-windows-named-pipe.o
 TEST_BUILTINS_OBJS += test-write-cache.o
 TEST_BUILTINS_OBJS += test-xml-encode.o
+TEST_BUILTINS_OBJS += test-zlib.o
 
 # Do not add more tests here unless they have extra dependencies. Add
 # them in TEST_BUILTINS_OBJS above.

builtin/cat-file.c

@@ -100,8 +100,7 @@ static int stream_blob(const struct object_id *oid)
 	return 0;
 }
 
-static int cat_one_file(int opt, const char *exp_type, const char *obj_name,
-			int unknown_type)
+static int cat_one_file(int opt, const char *exp_type, const char *obj_name)
 {
 	int ret;
 	struct object_id oid;
@@ -110,7 +109,6 @@ static int cat_one_file(int opt, const char *exp_type, const char *obj_name,
 	unsigned long size;
 	struct object_context obj_context = {0};
 	struct object_info oi = OBJECT_INFO_INIT;
-	struct strbuf sb = STRBUF_INIT;
 	unsigned flags = OBJECT_INFO_LOOKUP_REPLACE;
 	unsigned get_oid_flags =
 		GET_OID_RECORD_PATH |
@@ -121,9 +119,6 @@ static int cat_one_file(int opt, const char *exp_type, const char *obj_name,
 	if (!path && opt_cw)
 		get_oid_flags |= GET_OID_REQUIRE_PATH;
 
-	if (unknown_type)
-		flags |= OBJECT_INFO_ALLOW_UNKNOWN_TYPE;
-
 	if (get_oid_with_context(the_repository, obj_name, get_oid_flags, &oid,
 				 &obj_context))
 		die("Not a valid object name %s", obj_name);
@@ -136,16 +131,12 @@ static int cat_one_file(int opt, const char *exp_type, const char *obj_name,
 	buf = NULL;
 	switch (opt) {
 	case 't':
-		oi.type_name = &sb;
+		oi.typep = &type;
 		if (oid_object_info_extended(the_repository, &oid, &oi, flags) < 0)
 			die("git cat-file: could not get object info");
-		if (sb.len) {
-			printf("%s\n", sb.buf);
-			strbuf_release(&sb);
-			ret = 0;
-			goto cleanup;
-		}
-		break;
+		printf("%s\n", type_name(type));
+		ret = 0;
+		goto cleanup;
 
 	case 's':
 		oi.sizep = &size;
@@ -1038,8 +1029,7 @@ int cmd_cat_file(int argc,
 
 	const char * const builtin_catfile_usage[] = {
 		N_("git cat-file <type> <object>"),
-		N_("git cat-file (-e | -p) <object>"),
-		N_("git cat-file (-t | -s) [--allow-unknown-type] <object>"),
+		N_("git cat-file (-e | -p | -t | -s) <object>"),
 		N_("git cat-file (--textconv | --filters)\n"
 		   "             [<rev>:<path|tree-ish> | --path=<path|tree-ish> <rev>]"),
 		N_("git cat-file (--batch | --batch-check | --batch-command) [--batch-all-objects]\n"
@@ -1057,8 +1047,8 @@ int cmd_cat_file(int argc,
 		OPT_GROUP(N_("Emit [broken] object attributes")),
 		OPT_CMDMODE('t', NULL, &opt, N_("show object type (one of 'blob', 'tree', 'commit', 'tag', ...)"), 't'),
 		OPT_CMDMODE('s', NULL, &opt, N_("show object size"), 's'),
-		OPT_BOOL(0, "allow-unknown-type", &unknown_type,
-			  N_("allow -s and -t to work with broken/corrupt objects")),
+		OPT_HIDDEN_BOOL(0, "allow-unknown-type", &unknown_type,
+			  N_("historical option -- no-op")),
 		OPT_BOOL(0, "use-mailmap", &use_mailmap, N_("use mail map file")),
 		OPT_ALIAS(0, "mailmap", "use-mailmap"),
 		/* Batch mode */
@@ -1209,10 +1199,7 @@ int cmd_cat_file(int argc,
 		obj_name = argv[1];
 	}
 
-	if (unknown_type && opt != 't' && opt != 's')
-		die("git cat-file --allow-unknown-type: use with -s or -t");
-
-	ret = cat_one_file(opt, exp_type, obj_name, unknown_type);
+	ret = cat_one_file(opt, exp_type, obj_name);
 
 out:
 	list_objects_filter_release(&batch.objects_filter);

builtin/fsck.c

@@ -614,12 +614,11 @@ static void get_default_heads(void)
 struct for_each_loose_cb
 {
 	struct progress *progress;
-	struct strbuf obj_type;
 };
 
-static int fsck_loose(const struct object_id *oid, const char *path, void *data)
+static int fsck_loose(const struct object_id *oid, const char *path,
+		      void *data UNUSED)
 {
-	struct for_each_loose_cb *cb_data = data;
 	struct object *obj;
 	enum object_type type = OBJ_NONE;
 	unsigned long size;
@@ -629,8 +628,6 @@ static int fsck_loose(const struct object_id *oid, const char *path, void *data)
 	struct object_id real_oid = *null_oid(the_hash_algo);
 	int err = 0;
 
-	strbuf_reset(&cb_data->obj_type);
-	oi.type_name = &cb_data->obj_type;
 	oi.sizep = &size;
 	oi.typep = &type;
 
@@ -642,10 +639,6 @@ static int fsck_loose(const struct object_id *oid, const char *path, void *data)
 			err = error(_("%s: object corrupt or missing: %s"),
 				    oid_to_hex(oid), path);
 	}
-	if (type != OBJ_NONE && type < 0)
-		err = error(_("%s: object is of unknown type '%s': %s"),
-			    oid_to_hex(&real_oid), cb_data->obj_type.buf,
-			    path);
 	if (err < 0) {
 		errors_found |= ERROR_OBJECT;
 		free(contents);
@@ -697,7 +690,6 @@ static void fsck_object_dir(const char *path)
 {
 	struct progress *progress = NULL;
 	struct for_each_loose_cb cb_data = {
-		.obj_type = STRBUF_INIT,
 		.progress = progress,
 	};
 
@@ -712,7 +704,6 @@ static void fsck_object_dir(const char *path)
 				      &cb_data);
 	display_progress(progress, 256);
 	stop_progress(&progress);
-	strbuf_release(&cb_data.obj_type);
 }
 
 static int fsck_head_link(const char *head_ref_name,

builtin/hash-object.c

@@ -19,65 +19,30 @@
 #include "strbuf.h"
 #include "write-or-die.h"
 
-enum {
-	HASH_OBJECT_CHECK = (1 << 0),
-	HASH_OBJECT_WRITE = (1 << 1),
-};
-
-/*
- * This is to create corrupt objects for debugging and as such it
- * needs to bypass the data conversion performed by, and the type
- * limitation imposed by, index_fd() and its callees.
- */
-static int hash_literally(struct object_id *oid, int fd, const char *type, unsigned flags)
+static void hash_fd(int fd, const char *type, const char *path, unsigned flags)
 {
-	struct strbuf buf = STRBUF_INIT;
-	int ret;
-
-	if (strbuf_read(&buf, fd, 4096) < 0)
-		ret = -1;
-	else
-		ret = write_object_file_literally(buf.buf, buf.len, type, oid,
-						  (flags & HASH_OBJECT_WRITE) ? WRITE_OBJECT_FILE_PERSIST : 0);
-	close(fd);
-	strbuf_release(&buf);
-	return ret;
-}
-
-static void hash_fd(int fd, const char *type, const char *path, unsigned flags,
-		    int literally)
-{
-	unsigned int index_flags = 0;
 	struct stat st;
 	struct object_id oid;
 
-	if (flags & HASH_OBJECT_WRITE)
-		index_flags |= INDEX_WRITE_OBJECT;
-	if (flags & HASH_OBJECT_CHECK)
-		index_flags |= INDEX_FORMAT_CHECK;
-
 	if (fstat(fd, &st) < 0 ||
-	    (literally
-	     ? hash_literally(&oid, fd, type, flags)
-	     : index_fd(the_repository->index, &oid, fd, &st,
-			type_from_string(type), path, index_flags)))
-		die((flags & HASH_OBJECT_WRITE)
+	    index_fd(the_repository->index, &oid, fd, &st,
+		     type_from_string(type), path, flags))
+		die((flags & INDEX_WRITE_OBJECT)
 		    ? "Unable to add %s to database"
 		    : "Unable to hash %s", path);
 	printf("%s\n", oid_to_hex(&oid));
 	maybe_flush_or_die(stdout, "hash to stdout");
 }
 
 static void hash_object(const char *path, const char *type, const char *vpath,
-			unsigned flags, int literally)
+			unsigned flags)
 {
 	int fd;
 	fd = xopen(path, O_RDONLY);
-	hash_fd(fd, type, vpath, flags, literally);
+	hash_fd(fd, type, vpath, flags);
 }
 
-static void hash_stdin_paths(const char *type, int no_filters, unsigned flags,
-			     int literally)
+static void hash_stdin_paths(const char *type, int no_filters, unsigned flags)
 {
 	struct strbuf buf = STRBUF_INIT;
 	struct strbuf unquoted = STRBUF_INIT;
@@ -89,8 +54,7 @@ static void hash_stdin_paths(const char *type, int no_filters, unsigned flags,
 				die("line is badly quoted");
 			strbuf_swap(&buf, &unquoted);
 		}
-		hash_object(buf.buf, type, no_filters ? NULL : buf.buf, flags,
-			    literally);
+		hash_object(buf.buf, type, no_filters ? NULL : buf.buf, flags);
 	}
 	strbuf_release(&buf);
 	strbuf_release(&unquoted);
@@ -111,19 +75,20 @@ int cmd_hash_object(int argc,
 	int hashstdin = 0;
 	int stdin_paths = 0;
 	int no_filters = 0;
-	int literally = 0;
 	int nongit = 0;
-	unsigned flags = HASH_OBJECT_CHECK;
+	unsigned flags = INDEX_FORMAT_CHECK;
 	const char *vpath = NULL;
 	char *vpath_free = NULL;
 	const struct option hash_object_options[] = {
 		OPT_STRING('t', NULL, &type, N_("type"), N_("object type")),
 		OPT_BIT('w', NULL, &flags, N_("write the object into the object database"),
-			HASH_OBJECT_WRITE),
+			INDEX_WRITE_OBJECT),
 		OPT_COUNTUP( 0 , "stdin", &hashstdin, N_("read the object from stdin")),
 		OPT_BOOL( 0 , "stdin-paths", &stdin_paths, N_("read file names from stdin")),
 		OPT_BOOL( 0 , "no-filters", &no_filters, N_("store file as is without filters")),
-		OPT_BOOL( 0, "literally", &literally, N_("just hash any random garbage to create corrupt objects for debugging Git")),
+		OPT_NEGBIT( 0, "literally", &flags,
+			    N_("just hash any random garbage to create corrupt objects for debugging Git"),
+			    INDEX_FORMAT_CHECK),
 		OPT_STRING( 0 , "path", &vpath, N_("file"), N_("process file as it were from this path")),
 		OPT_END()
 	};
@@ -133,7 +98,7 @@ int cmd_hash_object(int argc,
 	argc = parse_options(argc, argv, prefix, hash_object_options,
 			     hash_object_usage, 0);
 
-	if (flags & HASH_OBJECT_WRITE)
+	if (flags & INDEX_WRITE_OBJECT)
 		prefix = setup_git_directory();
 	else
 		prefix = setup_git_directory_gently(&nongit);
@@ -169,7 +134,7 @@ int cmd_hash_object(int argc,
 	}
 
 	if (hashstdin)
-		hash_fd(0, type, vpath, flags, literally);
+		hash_fd(0, type, vpath, flags);
 
 	for (i = 0 ; i < argc; i++) {
 		const char *arg = argv[i];
@@ -178,12 +143,12 @@ int cmd_hash_object(int argc,
 		if (prefix)
 			arg = to_free = prefix_filename(prefix, arg);
 		hash_object(arg, type, no_filters ? NULL : vpath ? vpath : arg,
-			    flags, literally);
+			    flags);
 		free(to_free);
 	}
 
 	if (stdin_paths)
-		hash_stdin_paths(type, no_filters, flags, literally);
+		hash_stdin_paths(type, no_filters, flags);
 
 	free(vpath_free);