From: Junio C Hamano <gitster@pobox.com>
Date: Mon, 25 Oct 2021 23:06:56 +0000 (-0700)
Subject: Merge branch 'ab/fsck-unexpected-type'
X-Git-Tag: v2.34.0-rc0~43
X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=061a21d36d8;p=thirdparty%2Fgit.git

Merge branch 'ab/fsck-unexpected-type'

"git fsck" has been taught to report mismatch between expected and
actual types of an object better.

* ab/fsck-unexpected-type:
  fsck: report invalid object type-path combinations
  fsck: don't hard die on invalid object types
  object-file.c: stop dying in parse_loose_header()
  object-file.c: return ULHR_TOO_LONG on "header too long"
  object-file.c: use "enum" return type for unpack_loose_header()
  object-file.c: simplify unpack_loose_short_header()
  object-file.c: make parse_loose_header_extended() public
  object-file.c: return -1, not "status" from unpack_loose_header()
  object-file.c: don't set "typep" when returning non-zero
  cat-file tests: test for current --allow-unknown-type behavior
  cat-file tests: add corrupt loose object test
  cat-file tests: test for missing/bogus object with -t, -s and -p
  cat-file tests: move bogus_* variable declarations earlier
  fsck tests: test for garbage appended to a loose object
  fsck tests: test current hash/type mismatch behavior
  fsck tests: refactor one test to use a sub-repo
  fsck tests: add test for fsck-ing an unknown type
---

061a21d36d807bdcf996f388d5e487d5e1993bbc
diff --cc t/t1006-cat-file.sh
index 4a753705ec,fe302f2818..658628375c
--- a/t/t1006-cat-file.sh
+++ b/t/t1006-cat-file.sh
@@@ -332,18 -475,9 +475,13 @@@ test_expect_success "Size of broken obj
  	test_cmp expect actual
  '
  
 +test_expect_success 'clean up broken object' '
- 	rm .git/objects/$(test_oid_to_path $bogus_sha1)
++	rm .git/objects/$(test_oid_to_path $bogus_short_sha1)
 +'
 +
- bogus_type="abcdefghijklmnopqrstuvwxyz1234679"
- bogus_content="bogus"
- bogus_size=$(strlen "$bogus_content")
- bogus_sha1=$(echo_without_newline "$bogus_content" | git hash-object -t $bogus_type --literally -w --stdin)
- 
  test_expect_success "Type of broken object is correct when type is large" '
- 	echo $bogus_type >expect &&
- 	git cat-file -t --allow-unknown-type $bogus_sha1 >actual &&
+ 	echo $bogus_long_type >expect &&
+ 	git cat-file -t --allow-unknown-type $bogus_long_sha1 >actual &&
  	test_cmp expect actual
  '
  
@@@ -353,8 -487,56 +491,60 @@@ test_expect_success "Size of large brok
  	test_cmp expect actual
  '
  
 +test_expect_success 'clean up broken object' '
- 	rm .git/objects/$(test_oid_to_path $bogus_sha1)
++	rm .git/objects/$(test_oid_to_path $bogus_long_sha1)
++'
++
+ test_expect_success 'cat-file -t and -s on corrupt loose object' '
+ 	git init --bare corrupt-loose.git &&
+ 	(
+ 		cd corrupt-loose.git &&
+ 
+ 		# Setup and create the empty blob and its path
+ 		empty_path=$(git rev-parse --git-path objects/$(test_oid_to_path "$EMPTY_BLOB")) &&
+ 		git hash-object -w --stdin </dev/null &&
+ 
+ 		# Create another blob and its path
+ 		echo other >other.blob &&
+ 		other_blob=$(git hash-object -w --stdin <other.blob) &&
+ 		other_path=$(git rev-parse --git-path objects/$(test_oid_to_path "$other_blob")) &&
+ 
+ 		# Before the swap the size is 0
+ 		cat >out.expect <<-EOF &&
+ 		0
+ 		EOF
+ 		git cat-file -s "$EMPTY_BLOB" >out.actual 2>err.actual &&
+ 		test_must_be_empty err.actual &&
+ 		test_cmp out.expect out.actual &&
+ 
+ 		# Swap the two to corrupt the repository
+ 		mv -f "$other_path" "$empty_path" &&
+ 		test_must_fail git fsck 2>err.fsck &&
+ 		grep "hash-path mismatch" err.fsck &&
+ 
+ 		# confirm that cat-file is reading the new swapped-in
+ 		# blob...
+ 		cat >out.expect <<-EOF &&
+ 		blob
+ 		EOF
+ 		git cat-file -t "$EMPTY_BLOB" >out.actual 2>err.actual &&
+ 		test_must_be_empty err.actual &&
+ 		test_cmp out.expect out.actual &&
+ 
+ 		# ... since it has a different size now.
+ 		cat >out.expect <<-EOF &&
+ 		6
+ 		EOF
+ 		git cat-file -s "$EMPTY_BLOB" >out.actual 2>err.actual &&
+ 		test_must_be_empty err.actual &&
+ 		test_cmp out.expect out.actual &&
+ 
+ 		# So far "cat-file" has been happy to spew the found
+ 		# content out as-is. Try to make it zlib-invalid.
+ 		mv -f other.blob "$empty_path" &&
+ 		test_must_fail git fsck 2>err.fsck &&
+ 		grep "^error: inflate: data stream error (" err.fsck
+ 	)
  '
  
  # Tests for git cat-file --follow-symlinks