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

9 files changed, 158 insertions, 201 deletions

diff --git a/t/helper/meson.build b/t/helper/meson.build
index d4e8b26df8..675e64c010 100644
--- a/t/helper/meson.build
+++ b/t/helper/meson.build
@@ -77,6 +77,7 @@ test_tool_sources = [
   'test-windows-named-pipe.c',
   'test-write-cache.c',
   'test-xml-encode.c',
+  'test-zlib.c',
 ]
 
 test_tool = executable('test-tool',
diff --git a/t/helper/test-tool.c b/t/helper/test-tool.c
index 74812ed86d..a7abc618b3 100644
--- a/t/helper/test-tool.c
+++ b/t/helper/test-tool.c
@@ -91,6 +91,7 @@ static struct test_cmd cmds[] = {
 	{ "windows-named-pipe", cmd__windows_named_pipe },
 #endif
 	{ "write-cache", cmd__write_cache },
+	{ "zlib", cmd__zlib },
 };
 
 static NORETURN void die_usage(void)
diff --git a/t/helper/test-tool.h b/t/helper/test-tool.h
index 2571a3ccfe..7f150fa1eb 100644
--- a/t/helper/test-tool.h
+++ b/t/helper/test-tool.h
@@ -84,6 +84,7 @@ int cmd__wildmatch(int argc, const char **argv);
 int cmd__windows_named_pipe(int argc, const char **argv);
 #endif
 int cmd__write_cache(int argc, const char **argv);
+int cmd__zlib(int argc, const char **argv);
 
 int cmd_hash_impl(int ac, const char **av, int algo, int unsafe);
 
diff --git a/t/helper/test-zlib.c b/t/helper/test-zlib.c
new file mode 100644
index 0000000000..de7e9edee1
--- /dev/null
+++ b/t/helper/test-zlib.c
@@ -0,0 +1,62 @@
+#include "test-tool.h"
+#include "git-zlib.h"
+#include "strbuf.h"
+
+static const char *zlib_usage = "test-tool zlib [inflate|deflate]";
+
+static void do_zlib(struct git_zstream *stream,
+		    int (*zlib_func)(git_zstream *, int),
+		    int fd_in, int fd_out)
+{
+	struct strbuf buf_in = STRBUF_INIT;
+	int status = Z_OK;
+
+	if (strbuf_read(&buf_in, fd_in, 0) < 0)
+		die_errno("read error");
+
+	stream->next_in = (unsigned char *)buf_in.buf;
+	stream->avail_in = buf_in.len;
+
+	while (status == Z_OK ||
+	       (status == Z_BUF_ERROR && !stream->avail_out)) {
+		unsigned char buf_out[4096];
+
+		stream->next_out = buf_out;
+		stream->avail_out = sizeof(buf_out);
+
+		status = zlib_func(stream, Z_FINISH);
+		if (write_in_full(fd_out, buf_out,
+				  sizeof(buf_out) - stream->avail_out) < 0)
+			die_errno("write error");
+	}
+
+	if (status != Z_STREAM_END)
+		die("zlib error %d", status);
+
+	strbuf_release(&buf_in);
+}
+
+int cmd__zlib(int argc, const char **argv)
+{
+	git_zstream stream;
+
+	if (argc != 2)
+		usage(zlib_usage);
+
+	memset(&stream, 0, sizeof(stream));
+
+	if (!strcmp(argv[1], "inflate")) {
+		git_inflate_init(&stream);
+		do_zlib(&stream, git_inflate, 0, 1);
+		git_inflate_end(&stream);
+	} else if (!strcmp(argv[1], "deflate")) {
+		git_deflate_init(&stream, Z_DEFAULT_COMPRESSION);
+		do_zlib(&stream, git_deflate, 0, 1);
+		git_deflate_end(&stream);
+	} else {
+		error("unknown mode: %s", argv[1]);
+		usage(zlib_usage);
+	}
+
+	return 0;
+}
diff --git a/t/lib-loose.sh b/t/lib-loose.sh
new file mode 100644
index 0000000000..3613631eaf
--- /dev/null
+++ b/t/lib-loose.sh
@@ -0,0 +1,30 @@
+# Support routines for hand-crafting loose objects.
+
+# Write a loose object into the odb at $1, with object type $2 and contents
+# from stdin. Writes the oid to stdout. Example:
+#
+#   oid=$(echo foo | loose_obj .git/objects blob)
+#
+loose_obj () {
+	cat >tmp_loose.content &&
+	size=$(wc -c <tmp_loose.content) &&
+	{
+		# Do not quote $size here; we want the shell
+		# to strip whitespace that "wc" adds on some platforms.
+		printf "%s %s\0" "$2" $size &&
+		cat tmp_loose.content
+	} >tmp_loose.raw &&
+
+	oid=$(test-tool $test_hash_algo <tmp_loose.raw) &&
+	suffix=${oid#??} &&
+	prefix=${oid%$suffix} &&
+	dir=$1/$prefix &&
+	file=$dir/$suffix &&
+
+	test-tool zlib deflate <tmp_loose.raw >tmp_loose.zlib &&
+	mkdir -p "$dir" &&
+	mv tmp_loose.zlib "$file" &&
+
+	rm tmp_loose.raw tmp_loose.content &&
+	echo "$oid"
+}
diff --git a/t/t1006-cat-file.sh b/t/t1006-cat-file.sh
index ce8b27bf54..317da6869c 100755
--- a/t/t1006-cat-file.sh
+++ b/t/t1006-cat-file.sh
@@ -3,6 +3,7 @@
 test_description='git cat-file'
 
 . ./test-lib.sh
+. "$TEST_DIRECTORY/lib-loose.sh"
 
 test_cmdmode_usage () {
 	test_expect_code 129 "$@" 2>err &&
@@ -136,18 +137,6 @@ $content"
 	test_cmp expect actual
     '
 
-    test_expect_success "Type of $type is correct using --allow-unknown-type" '
-	echo $type >expect &&
-	git cat-file -t --allow-unknown-type $oid >actual &&
-	test_cmp expect actual
-    '
-
-    test_expect_success "Size of $type is correct using --allow-unknown-type" '
-	echo $size >expect &&
-	git cat-file -s --allow-unknown-type $oid >actual &&
-	test_cmp expect actual
-    '
-
     test -z "$content" ||
     test_expect_success "Content of $type is correct" '
 	echo_without_newline "$content" >expect &&
@@ -669,103 +658,75 @@ test_expect_success 'setup bogus data' '
 	bogus_short_type="bogus" &&
 	bogus_short_content="bogus" &&
 	bogus_short_size=$(strlen "$bogus_short_content") &&
-	bogus_short_oid=$(echo_without_newline "$bogus_short_content" | git hash-object -t $bogus_short_type --literally -w --stdin) &&
+	bogus_short_oid=$(echo_without_newline "$bogus_short_content" | loose_obj .git/objects $bogus_short_type) &&
 
 	bogus_long_type="abcdefghijklmnopqrstuvwxyz1234679" &&
 	bogus_long_content="bogus" &&
 	bogus_long_size=$(strlen "$bogus_long_content") &&
-	bogus_long_oid=$(echo_without_newline "$bogus_long_content" | git hash-object -t $bogus_long_type --literally -w --stdin)
+	bogus_long_oid=$(echo_without_newline "$bogus_long_content" | loose_obj .git/objects $bogus_long_type)
 '
 
-for arg1 in '' --allow-unknown-type
+for arg1 in -s -t -p
 do
-	for arg2 in -s -t -p
-	do
-		if test "$arg1" = "--allow-unknown-type" && test "$arg2" = "-p"
-		then
-			continue
-		fi
+	test_expect_success "cat-file $arg1 error on bogus short OID" '
+		cat >expect <<-\EOF &&
+		fatal: invalid object type
+		EOF
 
+		test_must_fail git cat-file $arg1 $bogus_short_oid >out 2>actual &&
+		test_must_be_empty out &&
+		test_cmp expect actual
+	'
 
-		test_expect_success "cat-file $arg1 $arg2 error on bogus short OID" '
-			cat >expect <<-\EOF &&
-			fatal: invalid object type
+	test_expect_success "cat-file $arg1 error on bogus full OID" '
+		if test "$arg1" = "-p"
+		then
+			cat >expect <<-EOF
+			error: header for $bogus_long_oid too long, exceeds 32 bytes
+			fatal: Not a valid object name $bogus_long_oid
 			EOF
+		else
+			cat >expect <<-EOF
+			error: header for $bogus_long_oid too long, exceeds 32 bytes
+			fatal: git cat-file: could not get object info
+			EOF
+		fi &&
 
-			if test "$arg1" = "--allow-unknown-type"
-			then
-				git cat-file $arg1 $arg2 $bogus_short_oid
-			else
-				test_must_fail git cat-file $arg1 $arg2 $bogus_short_oid >out 2>actual &&
-				test_must_be_empty out &&
-				test_cmp expect actual
-			fi
-		'
-
-		test_expect_success "cat-file $arg1 $arg2 error on bogus full OID" '
-			if test "$arg2" = "-p"
-			then
-				cat >expect <<-EOF
-				error: header for $bogus_long_oid too long, exceeds 32 bytes
-				fatal: Not a valid object name $bogus_long_oid
-				EOF
-			else
-				cat >expect <<-EOF
-				error: header for $bogus_long_oid too long, exceeds 32 bytes
-				fatal: git cat-file: could not get object info
-				EOF
-			fi &&
+		test_must_fail git cat-file $arg1 $bogus_long_oid >out 2>actual &&
+		test_must_be_empty out &&
+		test_cmp expect actual
+	'
 
-			if test "$arg1" = "--allow-unknown-type"
-			then
-				git cat-file $arg1 $arg2 $bogus_short_oid
-			else
-				test_must_fail git cat-file $arg1 $arg2 $bogus_long_oid >out 2>actual &&
-				test_must_be_empty out &&
-				test_cmp expect actual
-			fi
-		'
+	test_expect_success "cat-file $arg1 error on missing short OID" '
+		cat >expect.err <<-EOF &&
+		fatal: Not a valid object name $(test_oid deadbeef_short)
+		EOF
+		test_must_fail git cat-file $arg1 $(test_oid deadbeef_short) >out 2>err.actual &&
+		test_must_be_empty out &&
+		test_cmp expect.err err.actual
+	'
 
-		test_expect_success "cat-file $arg1 $arg2 error on missing short OID" '
-			cat >expect.err <<-EOF &&
-			fatal: Not a valid object name $(test_oid deadbeef_short)
+	test_expect_success "cat-file $arg1 error on missing full OID" '
+		if test "$arg1" = "-p"
+		then
+			cat >expect.err <<-EOF
+			fatal: Not a valid object name $(test_oid deadbeef)
 			EOF
-			test_must_fail git cat-file $arg1 $arg2 $(test_oid deadbeef_short) >out 2>err.actual &&
-			test_must_be_empty out &&
-			test_cmp expect.err err.actual
-		'
-
-		test_expect_success "cat-file $arg1 $arg2 error on missing full OID" '
-			if test "$arg2" = "-p"
-			then
-				cat >expect.err <<-EOF
-				fatal: Not a valid object name $(test_oid deadbeef)
-				EOF
-			else
-				cat >expect.err <<-\EOF
-				fatal: git cat-file: could not get object info
-				EOF
-			fi &&
-			test_must_fail git cat-file $arg1 $arg2 $(test_oid deadbeef) >out 2>err.actual &&
-			test_must_be_empty out &&
-			test_cmp expect.err err.actual
-		'
-	done
+		else
+			cat >expect.err <<-\EOF
+			fatal: git cat-file: could not get object info
+			EOF
+		fi &&
+		test_must_fail git cat-file $arg1 $(test_oid deadbeef) >out 2>err.actual &&
+		test_must_be_empty out &&
+		test_cmp expect.err err.actual
+	'
 done
 
-test_expect_success '-e is OK with a broken object without --allow-unknown-type' '
+test_expect_success '-e is OK with a broken object' '
 	git cat-file -e $bogus_short_oid
 '
 
-test_expect_success '-e can not be combined with --allow-unknown-type' '
-	test_expect_code 128 git cat-file -e --allow-unknown-type $bogus_short_oid
-'
-
-test_expect_success '-p cannot print a broken object even with --allow-unknown-type' '
-	test_must_fail git cat-file -p $bogus_short_oid &&
-	test_expect_code 128 git cat-file -p --allow-unknown-type $bogus_short_oid
-'
-
 test_expect_success '<type> <hash> does not work with objects of broken types' '
 	cat >err.expect <<-\EOF &&
 	fatal: invalid object type "bogus"
@@ -788,60 +749,8 @@ test_expect_success 'broken types combined with --batch and --batch-check' '
 	test_cmp err.expect err.actual
 '
 
-test_expect_success 'the --batch and --batch-check options do not combine with --allow-unknown-type' '
-	test_expect_code 128 git cat-file --batch --allow-unknown-type <bogus-oid &&
-	test_expect_code 128 git cat-file --batch-check --allow-unknown-type <bogus-oid
-'
-
-test_expect_success 'the --allow-unknown-type option does not consider replacement refs' '
-	cat >expect <<-EOF &&
-	$bogus_short_type
-	EOF
-	git cat-file -t --allow-unknown-type $bogus_short_oid >actual &&
-	test_cmp expect actual &&
-
-	# Create it manually, as "git replace" will die on bogus
-	# types.
-	head=$(git rev-parse --verify HEAD) &&
-	test_when_finished "test-tool ref-store main delete-refs 0 msg refs/replace/$bogus_short_oid" &&
-	test-tool ref-store main update-ref msg "refs/replace/$bogus_short_oid" $head $ZERO_OID REF_SKIP_OID_VERIFICATION &&
-
-	cat >expect <<-EOF &&
-	commit
-	EOF
-	git cat-file -t --allow-unknown-type $bogus_short_oid >actual &&
-	test_cmp expect actual
-'
-
-test_expect_success "Type of broken object is correct" '
-	echo $bogus_short_type >expect &&
-	git cat-file -t --allow-unknown-type $bogus_short_oid >actual &&
-	test_cmp expect actual
-'
-
-test_expect_success "Size of broken object is correct" '
-	echo $bogus_short_size >expect &&
-	git cat-file -s --allow-unknown-type $bogus_short_oid >actual &&
-	test_cmp expect actual
-'
-
-test_expect_success 'clean up broken object' '
-	rm .git/objects/$(test_oid_to_path $bogus_short_oid)
-'
-
-test_expect_success "Type of broken object is correct when type is large" '
-	echo $bogus_long_type >expect &&
-	git cat-file -t --allow-unknown-type $bogus_long_oid >actual &&
-	test_cmp expect actual
-'
-
-test_expect_success "Size of large broken object is correct when type is large" '
-	echo $bogus_long_size >expect &&
-	git cat-file -s --allow-unknown-type $bogus_long_oid >actual &&
-	test_cmp expect actual
-'
-
-test_expect_success 'clean up broken object' '
+test_expect_success 'clean up broken objects' '
+	rm .git/objects/$(test_oid_to_path $bogus_short_oid) &&
 	rm .git/objects/$(test_oid_to_path $bogus_long_oid)
 '
 
@@ -903,25 +812,6 @@ test_expect_success 'cat-file -t and -s on corrupt loose object' '
 	)
 '
 
-test_expect_success 'truncated object with --allow-unknown-type' - <<\EOT
-	objtype='a really long type name that exceeds the 32-byte limit' &&
-	blob=$(git hash-object -w --literally -t "$objtype" /dev/null) &&
-	objpath=.git/objects/$(test_oid_to_path "$blob") &&
-
-	# We want to truncate the object far enough in that we don't hit the
-	# end while inflating the first 32 bytes (since we want to have to dig
-	# for the trailing NUL of the header). But we don't want to go too far,
-	# since our header isn't very big. And of course we are counting
-	# deflated zlib bytes in the on-disk file, so it's a bit of a guess.
-	# Empirically 50 seems to work.
-	mv "$objpath" obj.bak &&
-	test_when_finished 'mv obj.bak "$objpath"' &&
-	test_copy_bytes 50 <obj.bak >"$objpath" &&
-
-	test_must_fail git cat-file --allow-unknown-type -t $blob 2>err &&
-	test_grep "unable to unpack $blob header" err
-EOT
-
 test_expect_success 'object reading handles zlib dictionary' - <<\EOT
 	echo 'content that will be recompressed' >file &&
 	blob=$(git hash-object -w file) &&
diff --git a/t/t1007-hash-object.sh b/t/t1007-hash-object.sh
index b3cf53ff8c..dbbe9fb0d4 100755
--- a/t/t1007-hash-object.sh
+++ b/t/t1007-hash-object.sh
@@ -248,15 +248,8 @@ test_expect_success 'hash-object complains about truncated type name' '
 	test_must_fail git hash-object -t bl --stdin </dev/null
 '
 
-test_expect_success '--literally' '
-	t=1234567890 &&
-	echo example | git hash-object -t $t --literally --stdin
-'
-
-test_expect_success '--literally with extra-long type' '
-	t=12345678901234567890123456789012345678901234567890 &&
-	t="$t$t$t$t$t$t$t$t$t$t$t$t$t$t$t$t$t$t$t$t$t$t$t$t$t$t$t$t$t$t" &&
-	echo example | git hash-object -t $t --literally --stdin
+test_expect_success '--literally complains about non-standard types' '
+	test_must_fail git hash-object -t bogus --literally --stdin
 '
 
 test_expect_success '--stdin outside of repository (uses SHA-1)' '
diff --git a/t/t1450-fsck.sh b/t/t1450-fsck.sh
index 0105045376..5ae86c42be 100755
--- a/t/t1450-fsck.sh
+++ b/t/t1450-fsck.sh
@@ -7,6 +7,7 @@ test_description='git fsck random collection of tests
 '
 
 . ./test-lib.sh
+. "$TEST_DIRECTORY/lib-loose.sh"
 
 test_expect_success setup '
 	git config gc.auto 0 &&
@@ -71,30 +72,6 @@ test_expect_success 'object with hash mismatch' '
 	)
 '
 
-test_expect_success 'object with hash and type mismatch' '
-	git init --bare hash-type-mismatch &&
-	(
-		cd hash-type-mismatch &&
-
-		oid=$(echo blob | git hash-object -w --stdin -t garbage --literally) &&
-		oldoid=$oid &&
-		old=$(test_oid_to_path "$oid") &&
-		new=$(dirname $old)/$(test_oid ff_2) &&
-		oid="$(dirname $new)$(basename $new)" &&
-
-		mv objects/$old objects/$new &&
-		git update-index --add --cacheinfo 100644 $oid foo &&
-		tree=$(git write-tree) &&
-		cmt=$(echo bogus | git commit-tree $tree) &&
-		git update-ref refs/heads/bogus $cmt &&
-
-
-		test_must_fail git fsck 2>out &&
-		grep "^error: $oldoid: hash-path mismatch, found at: .*$new" out &&
-		grep "^error: $oldoid: object is of unknown type '"'"'garbage'"'"'" out
-	)
-'
-
 test_expect_success 'zlib corrupt loose object output ' '
 	git init --bare corrupt-loose-output &&
 	(
@@ -997,12 +974,13 @@ test_expect_success 'fsck error and recovery on invalid object type' '
 	(
 		cd garbage-type &&
 
-		garbage_blob=$(git hash-object --stdin -w -t garbage --literally </dev/null) &&
+		garbage_blob=$(loose_obj objects garbage </dev/null) &&
 
 		test_must_fail git fsck 2>err &&
 		grep -e "^error" -e "^fatal" err >errors &&
-		test_line_count = 1 errors &&
-		grep "$garbage_blob: object is of unknown type '"'"'garbage'"'"':" err
+		test_line_count = 2 errors &&
+		test_grep "unable to parse type from header .garbage" err &&
+		test_grep "$garbage_blob: object corrupt or missing:" err
 	)
 '
 
diff --git a/t/t1512-rev-parse-disambiguation.sh b/t/t1512-rev-parse-disambiguation.sh
index 70f1e0a998..1a380a4184 100755
--- a/t/t1512-rev-parse-disambiguation.sh
+++ b/t/t1512-rev-parse-disambiguation.sh
@@ -24,6 +24,7 @@ GIT_TEST_DEFAULT_INITIAL_BRANCH_NAME=main
 export GIT_TEST_DEFAULT_INITIAL_BRANCH_NAME
 
 . ./test-lib.sh
+. "$TEST_DIRECTORY/lib-loose.sh"
 
 test_cmp_failed_rev_parse () {
 	dir=$1
@@ -67,8 +68,8 @@ test_expect_success 'ambiguous loose bad object parsed as OBJ_BAD' '
 		cd blob.bad &&
 
 		# Both have the prefix "bad0"
-		echo xyzfaowcoh | git hash-object -t bad -w --stdin --literally &&
-		echo xyzhjpyvwl | git hash-object -t bad -w --stdin --literally
+		echo xyzfaowcoh | loose_obj objects bad &&
+		echo xyzhjpyvwl | loose_obj objects bad
 	) &&
 
 	test_cmp_failed_rev_parse blob.bad bad0 <<-\EOF