diff options
Diffstat (limited to 't/t1450-fsck.sh')
| -rwxr-xr-x | t/t1450-fsck.sh | 358 |
1 files changed, 348 insertions, 10 deletions
diff --git a/t/t1450-fsck.sh b/t/t1450-fsck.sh index cfb32b6242..cb4b66e29d 100755 --- a/t/t1450-fsck.sh +++ b/t/t1450-fsck.sh @@ -43,13 +43,13 @@ test_expect_success 'HEAD is part of refs, valid objects appear valid' ' test_expect_success 'setup: helpers for corruption tests' ' sha1_file() { - echo "$*" | sed "s#..#.git/objects/&/#" + remainder=${1#??} && + firsttwo=${1%$remainder} && + echo ".git/objects/$firsttwo/$remainder" } && remove_object() { - file=$(sha1_file "$*") && - test -e "$file" && - rm -f "$file" + rm "$(sha1_file "$1")" } ' @@ -77,11 +77,31 @@ test_expect_success 'object with bad sha1' ' test_expect_success 'branch pointing to non-commit' ' git rev-parse HEAD^{tree} >.git/refs/heads/invalid && test_when_finished "git update-ref -d refs/heads/invalid" && - git fsck 2>out && + test_must_fail git fsck 2>out && cat out && grep "not a commit" out ' +test_expect_success 'HEAD link pointing at a funny object' ' + test_when_finished "mv .git/SAVED_HEAD .git/HEAD" && + mv .git/HEAD .git/SAVED_HEAD && + echo 0000000000000000000000000000000000000000 >.git/HEAD && + # avoid corrupt/broken HEAD from interfering with repo discovery + test_must_fail env GIT_DIR=.git git fsck 2>out && + cat out && + grep "detached HEAD points" out +' + +test_expect_success 'HEAD link pointing at a funny place' ' + test_when_finished "mv .git/SAVED_HEAD .git/HEAD" && + mv .git/HEAD .git/SAVED_HEAD && + echo "ref: refs/funny/place" >.git/HEAD && + # avoid corrupt/broken HEAD from interfering with repo discovery + test_must_fail env GIT_DIR=.git git fsck 2>out && + cat out && + grep "HEAD points to something strange" out +' + test_expect_success 'email without @ is okay' ' git cat-file commit HEAD >basis && sed "s/@/AT/" basis >okay && @@ -156,16 +176,29 @@ test_expect_success 'integer overflow in timestamps is reported' ' grep "error in commit $new.*integer overflow" out ' -test_expect_success 'malformatted tree object' ' - test_when_finished "git update-ref -d refs/tags/wrong" && - test_when_finished "remove_object \$T" && +test_expect_success 'commit with NUL in header' ' + git cat-file commit HEAD >basis && + sed "s/author ./author Q/" <basis | q_to_nul >commit-NUL-header && + new=$(git hash-object -t commit -w --stdin <commit-NUL-header) && + test_when_finished "remove_object $new" && + git update-ref refs/heads/bogus "$new" && + test_when_finished "git update-ref -d refs/heads/bogus" && + test_must_fail git fsck 2>out && + cat out && + grep "error in commit $new.*unterminated header: NUL at offset" out +' + +test_expect_success 'tree object with duplicate entries' ' + test_when_finished "for i in \$T; do remove_object \$i; done" && T=$( GIT_INDEX_FILE=test-index && export GIT_INDEX_FILE && rm -f test-index && >x && git add x && + git rev-parse :x && T=$(git write-tree) && + echo $T && ( git cat-file tree $T && git cat-file tree $T @@ -176,6 +209,41 @@ test_expect_success 'malformatted tree object' ' grep "error in tree .*contains duplicate file entries" out ' +test_expect_success 'unparseable tree object' ' + test_when_finished "git update-ref -d refs/heads/wrong" && + test_when_finished "remove_object \$tree_sha1" && + test_when_finished "remove_object \$commit_sha1" && + tree_sha1=$(printf "100644 \0twenty-bytes-of-junk" | git hash-object -t tree --stdin -w --literally) && + commit_sha1=$(git commit-tree $tree_sha1) && + git update-ref refs/heads/wrong $commit_sha1 && + test_must_fail git fsck 2>out && + test_i18ngrep "error: empty filename in tree entry" out && + test_i18ngrep "$tree_sha1" out && + test_i18ngrep ! "fatal: empty filename in tree entry" out +' + +hex2oct() { + perl -ne 'printf "\\%03o", hex for /../g' +} + +test_expect_success 'tree entry with type mismatch' ' + test_when_finished "remove_object \$blob" && + test_when_finished "remove_object \$tree" && + test_when_finished "remove_object \$commit" && + test_when_finished "git update-ref -d refs/heads/type_mismatch" && + blob=$(echo blob | git hash-object -w --stdin) && + blob_bin=$(echo $blob | hex2oct) && + tree=$( + printf "40000 dir\0${blob_bin}100644 file\0${blob_bin}" | + git hash-object -t tree --stdin -w --literally + ) && + commit=$(git commit-tree $tree) && + git update-ref refs/heads/type_mismatch $commit && + test_must_fail git fsck >out 2>&1 && + test_i18ngrep "is a blob, not a tree" out && + test_i18ngrep ! "dangling blob" out +' + test_expect_success 'tag pointing to nonexistent' ' cat >invalid-tag <<-\EOF && object ffffffffffffffffffffffffffffffffffffffff @@ -231,8 +299,8 @@ test_expect_success 'tag with incorrect tag name & missing tagger' ' git fsck --tags 2>out && cat >expect <<-EOF && - warning in tag $tag: invalid '\''tag'\'' name: wrong name format - warning in tag $tag: invalid format - expected '\''tagger'\'' line + warning in tag $tag: badTagName: invalid '\''tag'\'' name: wrong name format + warning in tag $tag: missingTaggerEntry: invalid format - expected '\''tagger'\'' line EOF test_cmp expect out ' @@ -256,6 +324,26 @@ test_expect_success 'tag with bad tagger' ' grep "error in tag .*: invalid author/committer" out ' +test_expect_success 'tag with NUL in header' ' + sha=$(git rev-parse HEAD) && + q_to_nul >tag-NUL-header <<-EOF && + object $sha + type commit + tag contains-Q-in-header + tagger T A Gger <tagger@example.com> 1234567890 -0000 + + This is an invalid tag. + EOF + + tag=$(git hash-object --literally -t tag -w --stdin <tag-NUL-header) && + test_when_finished "remove_object $tag" && + echo $tag >.git/refs/tags/wrong && + test_when_finished "git update-ref -d refs/tags/wrong" && + test_must_fail git fsck --tags 2>out && + cat out && + grep "error in tag $tag.*unterminated header: NUL at offset" out +' + test_expect_success 'cleaned up' ' git fsck >actual 2>&1 && test_cmp empty actual @@ -287,6 +375,17 @@ test_expect_success 'rev-list --verify-objects with bad sha1' ' grep -q "error: sha1 mismatch 63ffffffffffffffffffffffffffffffffffffff" out ' +test_expect_success 'force fsck to ignore double author' ' + git cat-file commit HEAD >basis && + sed "s/^author .*/&,&/" <basis | tr , \\n >multiple-authors && + new=$(git hash-object -t commit -w --stdin <multiple-authors) && + test_when_finished "remove_object $new" && + git update-ref refs/heads/bogus "$new" && + test_when_finished "git update-ref -d refs/heads/bogus" && + test_must_fail git fsck && + git -c fsck.multipleAuthors=ignore fsck +' + _bz='\0' _bz5="$_bz$_bz$_bz$_bz$_bz" _bz20="$_bz5$_bz5$_bz5$_bz5" @@ -364,6 +463,24 @@ test_expect_success 'fsck allows .Ňit' ' ) ' +test_expect_success 'NUL in commit' ' + rm -fr nul-in-commit && + git init nul-in-commit && + ( + cd nul-in-commit && + git commit --allow-empty -m "initial commitQNUL after message" && + git cat-file commit HEAD >original && + q_to_nul <original >munged && + git hash-object -w -t commit --stdin <munged >name && + git branch bad $(cat name) && + + test_must_fail git -c fsck.nulInCommit=error fsck 2>warn.1 && + grep nulInCommit warn.1 && + git fsck 2>warn.2 && + grep nulInCommit warn.2 + ) +' + # create a static test repo which is broken by omitting # one particular object ($1, which is looked up via rev-parse # in the new repository). @@ -420,4 +537,225 @@ test_expect_success 'fsck notices ref pointing to missing tag' ' test_must_fail git -C missing fsck ' +test_expect_success 'fsck --connectivity-only' ' + rm -rf connectivity-only && + git init connectivity-only && + ( + cd connectivity-only && + touch empty && + git add empty && + test_commit empty && + + # Drop the index now; we want to be sure that we + # recursively notice the broken objects + # because they are reachable from refs, not because + # they are in the index. + rm -f .git/index && + + # corrupt the blob, but in a way that we can still identify + # its type. That lets us see that --connectivity-only is + # not actually looking at the contents, but leaves it + # free to examine the type if it chooses. + empty=.git/objects/e6/9de29bb2d1d6434b8b29ae775ad8c2e48c5391 && + blob=$(echo unrelated | git hash-object -w --stdin) && + mv -f $(sha1_file $blob) $empty && + + test_must_fail git fsck --strict && + git fsck --strict --connectivity-only && + tree=$(git rev-parse HEAD:) && + suffix=${tree#??} && + tree=.git/objects/${tree%$suffix}/$suffix && + rm -f $tree && + echo invalid >$tree && + test_must_fail git fsck --strict --connectivity-only + ) +' + +test_expect_success 'fsck --connectivity-only with explicit head' ' + rm -rf connectivity-only && + git init connectivity-only && + ( + cd connectivity-only && + test_commit foo && + rm -f .git/index && + tree=$(git rev-parse HEAD^{tree}) && + remove_object $(git rev-parse HEAD:foo.t) && + test_must_fail git fsck --connectivity-only $tree + ) +' + +test_expect_success 'fsck --name-objects' ' + rm -rf name-objects && + git init name-objects && + ( + cd name-objects && + test_commit julius caesar.t && + test_commit augustus && + test_commit caesar && + remove_object $(git rev-parse julius:caesar.t) && + test_must_fail git fsck --name-objects >out && + tree=$(git rev-parse --verify julius:) && + egrep "$tree \((refs/heads/master|HEAD)@\{[0-9]*\}:" out + ) +' + +test_expect_success 'alternate objects are correctly blamed' ' + test_when_finished "rm -rf alt.git .git/objects/info/alternates" && + git init --bare alt.git && + echo "../../alt.git/objects" >.git/objects/info/alternates && + mkdir alt.git/objects/12 && + >alt.git/objects/12/34567890123456789012345678901234567890 && + test_must_fail git fsck >out 2>&1 && + grep alt.git out +' + +test_expect_success 'fsck errors in packed objects' ' + git cat-file commit HEAD >basis && + sed "s/</one/" basis >one && + sed "s/</foo/" basis >two && + one=$(git hash-object -t commit -w one) && + two=$(git hash-object -t commit -w two) && + pack=$( + { + echo $one && + echo $two + } | git pack-objects .git/objects/pack/pack + ) && + test_when_finished "rm -f .git/objects/pack/pack-$pack.*" && + remove_object $one && + remove_object $two && + test_must_fail git fsck 2>out && + grep "error in commit $one.* - bad name" out && + grep "error in commit $two.* - bad name" out && + ! grep corrupt out +' + +test_expect_success 'fsck fails on corrupt packfile' ' + hsh=$(git commit-tree -m mycommit HEAD^{tree}) && + pack=$(echo $hsh | git pack-objects .git/objects/pack/pack) && + + # Corrupt the first byte of the first object. (It contains 3 type bits, + # at least one of which is not zero, so setting the first byte to 0 is + # sufficient.) + chmod a+w .git/objects/pack/pack-$pack.pack && + printf '\0' | dd of=.git/objects/pack/pack-$pack.pack bs=1 conv=notrunc seek=12 && + + test_when_finished "rm -f .git/objects/pack/pack-$pack.*" && + remove_object $hsh && + test_must_fail git fsck 2>out && + test_i18ngrep "checksum mismatch" out +' + +test_expect_success 'fsck finds problems in duplicate loose objects' ' + rm -rf broken-duplicate && + git init broken-duplicate && + ( + cd broken-duplicate && + test_commit duplicate && + # no "-d" here, so we end up with duplicates + git repack && + # now corrupt the loose copy + file=$(sha1_file "$(git rev-parse HEAD)") && + rm "$file" && + echo broken >"$file" && + test_must_fail git fsck + ) +' + +test_expect_success 'fsck detects trailing loose garbage (commit)' ' + git cat-file commit HEAD >basis && + echo bump-commit-sha1 >>basis && + commit=$(git hash-object -w -t commit basis) && + file=$(sha1_file $commit) && + test_when_finished "remove_object $commit" && + chmod +w "$file" && + echo garbage >>"$file" && + test_must_fail git fsck 2>out && + test_i18ngrep "garbage.*$commit" out +' + +test_expect_success 'fsck detects trailing loose garbage (blob)' ' + blob=$(echo trailing | git hash-object -w --stdin) && + file=$(sha1_file $blob) && + test_when_finished "remove_object $blob" && + chmod +w "$file" && + echo garbage >>"$file" && + test_must_fail git fsck 2>out && + test_i18ngrep "garbage.*$blob" out +' + +# for each of type, we have one version which is referenced by another object +# (and so while unreachable, not dangling), and another variant which really is +# dangling. +test_expect_success 'fsck notices dangling objects' ' + git init dangling && + ( + cd dangling && + blob=$(echo not-dangling | git hash-object -w --stdin) && + dblob=$(echo dangling | git hash-object -w --stdin) && + tree=$(printf "100644 blob %s\t%s\n" $blob one | git mktree) && + dtree=$(printf "100644 blob %s\t%s\n" $blob two | git mktree) && + commit=$(git commit-tree $tree) && + dcommit=$(git commit-tree -p $commit $tree) && + + cat >expect <<-EOF && + dangling blob $dblob + dangling commit $dcommit + dangling tree $dtree + EOF + + git fsck >actual && + # the output order is non-deterministic, as it comes from a hash + sort <actual >actual.sorted && + test_cmp expect actual.sorted + ) +' + +test_expect_success 'fsck $name notices bogus $name' ' + test_must_fail git fsck bogus && + test_must_fail git fsck $_z40 +' + +test_expect_success 'bogus head does not fallback to all heads' ' + # set up a case that will cause a reachability complaint + echo to-be-deleted >foo && + git add foo && + blob=$(git rev-parse :foo) && + test_when_finished "git rm --cached foo" && + remove_object $blob && + test_must_fail git fsck $_z40 >out 2>&1 && + ! grep $blob out +' + +# Corrupt the checksum on the index. +# Add 1 to the last byte in the SHA. +corrupt_index_checksum () { + perl -w -e ' + use Fcntl ":seek"; + open my $fh, "+<", ".git/index" or die "open: $!"; + binmode $fh; + seek $fh, -1, SEEK_END or die "seek: $!"; + read $fh, my $in_byte, 1 or die "read: $!"; + + $in_value = unpack("C", $in_byte); + $out_value = ($in_value + 1) & 255; + + $out_byte = pack("C", $out_value); + + seek $fh, -1, SEEK_END or die "seek: $!"; + print $fh $out_byte; + close $fh or die "close: $!"; + ' +} + +# Corrupt the checksum on the index and then +# verify that only fsck notices. +test_expect_success 'detect corrupt index file in fsck' ' + cp .git/index .git/index.backup && + test_when_finished "mv .git/index.backup .git/index" && + corrupt_index_checksum && + test_must_fail git fsck --cache 2>errors && + grep "bad index file" errors +' + test_done |