git/t/t5300-pack-object.sh

402 lines
10 KiB
Bash
Raw Normal View History

#!/bin/sh
#
# Copyright (c) 2005 Junio C Hamano
#
test_description='git pack-object
'
. ./test-lib.sh
TRASH=`pwd`
test_expect_success \
'setup' \
'rm -f .git/index*
perl -e "print \"a\" x 4096;" > a &&
perl -e "print \"b\" x 4096;" > b &&
perl -e "print \"c\" x 4096;" > c &&
git update-index --add a b c &&
cat c >d && echo foo >>d && git update-index --add d &&
tree=`git write-tree` &&
commit=`git commit-tree $tree </dev/null` && {
echo $tree &&
echo $commit &&
git ls-tree $tree | sed -e "s/.* \\([0-9a-f]*\\) .*/\\1/"
} >obj-list && {
git diff-tree --root -p $commit &&
while read object
do
t=`git cat-file -t $object` &&
git cat-file $t $object || return 1
done <obj-list
} >expect'
test_expect_success \
'pack without delta' \
'packname_1=$(git pack-objects --window=0 test-1 <obj-list)'
rm -fr .git2
mkdir .git2
test_expect_success \
'unpack without delta' \
"GIT_OBJECT_DIRECTORY=.git2/objects &&
export GIT_OBJECT_DIRECTORY &&
git init &&
git unpack-objects -n <test-1-${packname_1}.pack &&
git unpack-objects <test-1-${packname_1}.pack"
unset GIT_OBJECT_DIRECTORY
cd "$TRASH/.git2"
test_expect_success \
'check unpack without delta' \
'(cd ../.git && find objects -type f -print) |
while read path
do
cmp $path ../.git/$path || {
echo $path differs.
return 1
}
done'
cd "$TRASH"
test_expect_success \
'pack with REF_DELTA' \
'pwd &&
packname_2=$(git pack-objects test-2 <obj-list)'
rm -fr .git2
mkdir .git2
test_expect_success \
'unpack with REF_DELTA' \
'GIT_OBJECT_DIRECTORY=.git2/objects &&
export GIT_OBJECT_DIRECTORY &&
git init &&
git unpack-objects -n <test-2-${packname_2}.pack &&
git unpack-objects <test-2-${packname_2}.pack'
unset GIT_OBJECT_DIRECTORY
cd "$TRASH/.git2"
test_expect_success \
'check unpack with REF_DELTA' \
'(cd ../.git && find objects -type f -print) |
while read path
do
cmp $path ../.git/$path || {
echo $path differs.
return 1
}
done'
cd "$TRASH"
test_expect_success \
'pack with OFS_DELTA' \
'pwd &&
packname_3=$(git pack-objects --delta-base-offset test-3 <obj-list)'
rm -fr .git2
mkdir .git2
test_expect_success \
'unpack with OFS_DELTA' \
'GIT_OBJECT_DIRECTORY=.git2/objects &&
export GIT_OBJECT_DIRECTORY &&
git init &&
git unpack-objects -n <test-3-${packname_3}.pack &&
git unpack-objects <test-3-${packname_3}.pack'
unset GIT_OBJECT_DIRECTORY
cd "$TRASH/.git2"
test_expect_success \
'check unpack with OFS_DELTA' \
'(cd ../.git && find objects -type f -print) |
while read path
do
cmp $path ../.git/$path || {
echo $path differs.
return 1
}
done'
cd "$TRASH"
test_expect_success 'compare delta flavors' '
perl -e '\''
defined($_ = -s $_) or die for @ARGV;
exit 1 if $ARGV[0] <= $ARGV[1];
'\'' test-2-$packname_2.pack test-3-$packname_3.pack
'
rm -fr .git2
mkdir .git2
test_expect_success \
'use packed objects' \
'GIT_OBJECT_DIRECTORY=.git2/objects &&
export GIT_OBJECT_DIRECTORY &&
git init &&
cp test-1-${packname_1}.pack test-1-${packname_1}.idx .git2/objects/pack && {
git diff-tree --root -p $commit &&
while read object
do
t=`git cat-file -t $object` &&
git cat-file $t $object || return 1
done <obj-list
} >current &&
diff expect current'
test_expect_success \
'use packed deltified (REF_DELTA) objects' \
'GIT_OBJECT_DIRECTORY=.git2/objects &&
export GIT_OBJECT_DIRECTORY &&
rm -f .git2/objects/pack/test-* &&
cp test-2-${packname_2}.pack test-2-${packname_2}.idx .git2/objects/pack && {
git diff-tree --root -p $commit &&
while read object
do
t=`git cat-file -t $object` &&
git cat-file $t $object || return 1
done <obj-list
} >current &&
diff expect current'
test_expect_success \
'use packed deltified (OFS_DELTA) objects' \
'GIT_OBJECT_DIRECTORY=.git2/objects &&
export GIT_OBJECT_DIRECTORY &&
rm -f .git2/objects/pack/test-* &&
cp test-3-${packname_3}.pack test-3-${packname_3}.idx .git2/objects/pack && {
git diff-tree --root -p $commit &&
while read object
do
t=`git cat-file -t $object` &&
git cat-file $t $object || return 1
done <obj-list
} >current &&
diff expect current'
unset GIT_OBJECT_DIRECTORY
test_expect_success 'survive missing objects/pack directory' '
(
rm -fr missing-pack &&
mkdir missing-pack &&
cd missing-pack &&
git init &&
GOP=.git/objects/pack
rm -fr $GOP &&
git index-pack --stdin --keep=test <../test-3-${packname_3}.pack &&
test -f $GOP/pack-${packname_3}.pack &&
test_cmp $GOP/pack-${packname_3}.pack ../test-3-${packname_3}.pack &&
test -f $GOP/pack-${packname_3}.idx &&
test_cmp $GOP/pack-${packname_3}.idx ../test-3-${packname_3}.idx &&
test -f $GOP/pack-${packname_3}.keep
)
'
test_expect_success \
'verify pack' \
'git verify-pack test-1-${packname_1}.idx \
test-2-${packname_2}.idx \
test-3-${packname_3}.idx'
test_expect_success \
'verify pack -v' \
'git verify-pack -v test-1-${packname_1}.idx \
test-2-${packname_2}.idx \
test-3-${packname_3}.idx'
test_expect_success \
'verify-pack catches mismatched .idx and .pack files' \
'cat test-1-${packname_1}.idx >test-3.idx &&
cat test-2-${packname_2}.pack >test-3.pack &&
if git verify-pack test-3.idx
then false
else :;
fi'
test_expect_success \
'verify-pack catches a corrupted pack signature' \
'cat test-1-${packname_1}.pack >test-3.pack &&
echo | dd of=test-3.pack count=1 bs=1 conv=notrunc seek=2 &&
if git verify-pack test-3.idx
then false
else :;
fi'
test_expect_success \
'verify-pack catches a corrupted pack version' \
'cat test-1-${packname_1}.pack >test-3.pack &&
echo | dd of=test-3.pack count=1 bs=1 conv=notrunc seek=7 &&
if git verify-pack test-3.idx
then false
else :;
fi'
test_expect_success \
'verify-pack catches a corrupted type/size of the 1st packed object data' \
'cat test-1-${packname_1}.pack >test-3.pack &&
echo | dd of=test-3.pack count=1 bs=1 conv=notrunc seek=12 &&
if git verify-pack test-3.idx
then false
else :;
fi'
test_expect_success \
'verify-pack catches a corrupted sum of the index file itself' \
'l=`wc -c <test-3.idx` &&
l=`expr $l - 20` &&
cat test-1-${packname_1}.pack >test-3.pack &&
printf "%20s" "" | dd of=test-3.idx count=20 bs=1 conv=notrunc seek=$l &&
if git verify-pack test-3.pack
then false
else :;
fi'
test_expect_success \
'build pack index for an existing pack' \
'cat test-1-${packname_1}.pack >test-3.pack &&
git index-pack -o tmp.idx test-3.pack &&
cmp tmp.idx test-1-${packname_1}.idx &&
git index-pack test-3.pack &&
cmp test-3.idx test-1-${packname_1}.idx &&
cat test-2-${packname_2}.pack >test-3.pack &&
git index-pack -o tmp.idx test-2-${packname_2}.pack &&
cmp tmp.idx test-2-${packname_2}.idx &&
git index-pack test-3.pack &&
cmp test-3.idx test-2-${packname_2}.idx &&
cat test-3-${packname_3}.pack >test-3.pack &&
git index-pack -o tmp.idx test-3-${packname_3}.pack &&
cmp tmp.idx test-3-${packname_3}.idx &&
git index-pack test-3.pack &&
cmp test-3.idx test-3-${packname_3}.idx &&
:'
don't ever allow SHA1 collisions to exist by fetching a pack Waaaaaaay back Git was considered to be secure as it never overwrote an object it already had. This was ensured by always unpacking the packfile received over the network (both in fetch and receive-pack) and our already existing logic to not create a loose object for an object we already have. Lately however we keep "large-ish" packfiles on both fetch and push by running them through index-pack instead of unpack-objects. This would let an attacker perform a birthday attack. How? Assume the attacker knows a SHA-1 that has two different data streams. He knows the client is likely to have the "good" one. So he sends the "evil" variant to the other end as part of a "large-ish" packfile. The recipient keeps that packfile, and indexes it. Now since this is a birthday attack there is a SHA-1 collision; two objects exist in the repository with the same SHA-1. They have *very* different data streams. One of them is "evil". Currently the poor recipient cannot tell the two objects apart, short of by examining the timestamp of the packfiles. But lets say the recipient repacks before he realizes he's been attacked. We may wind up packing the "evil" version of the object, and deleting the "good" one. This is made *even more likely* by Junio's recent rearrange_packed_git patch (b867092f). It is extremely unlikely for a SHA1 collisions to occur, but if it ever happens with a remote (hence untrusted) object we simply must not let the fetch succeed. Normally received packs should not contain objects we already have. But when they do we must ensure duplicated objects with the same SHA1 actually contain the same data. Signed-off-by: Nicolas Pitre <nico@cam.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2007-03-20 19:32:35 +00:00
test_expect_success \
'fake a SHA1 hash collision' \
'test -f .git/objects/c8/2de19312b6c3695c0c18f70709a6c535682a67 &&
cp -f .git/objects/9d/235ed07cd19811a6ceb342de82f190e49c9f68 \
.git/objects/c8/2de19312b6c3695c0c18f70709a6c535682a67'
Sane use of test_expect_failure Originally, test_expect_failure was designed to be the opposite of test_expect_success, but this was a bad decision. Most tests run a series of commands that leads to the single command that needs to be tested, like this: test_expect_{success,failure} 'test title' ' setup1 && setup2 && setup3 && what is to be tested ' And expecting a failure exit from the whole sequence misses the point of writing tests. Your setup$N that are supposed to succeed may have failed without even reaching what you are trying to test. The only valid use of test_expect_failure is to check a trivial single command that is expected to fail, which is a minority in tests of Porcelain-ish commands. This large-ish patch rewrites all uses of test_expect_failure to use test_expect_success and rewrites the condition of what is tested, like this: test_expect_success 'test title' ' setup1 && setup2 && setup3 && ! this command should fail ' test_expect_failure is redefined to serve as a reminder that that test *should* succeed but due to a known breakage in git it currently does not pass. So if git-foo command should create a file 'bar' but you discovered a bug that it doesn't, you can write a test like this: test_expect_failure 'git-foo should create bar' ' rm -f bar && git foo && test -f bar ' This construct acts similar to test_expect_success, but instead of reporting "ok/FAIL" like test_expect_success does, the outcome is reported as "FIXED/still broken". Signed-off-by: Junio C Hamano <gitster@pobox.com>
2008-02-01 09:50:53 +00:00
test_expect_success \
don't ever allow SHA1 collisions to exist by fetching a pack Waaaaaaay back Git was considered to be secure as it never overwrote an object it already had. This was ensured by always unpacking the packfile received over the network (both in fetch and receive-pack) and our already existing logic to not create a loose object for an object we already have. Lately however we keep "large-ish" packfiles on both fetch and push by running them through index-pack instead of unpack-objects. This would let an attacker perform a birthday attack. How? Assume the attacker knows a SHA-1 that has two different data streams. He knows the client is likely to have the "good" one. So he sends the "evil" variant to the other end as part of a "large-ish" packfile. The recipient keeps that packfile, and indexes it. Now since this is a birthday attack there is a SHA-1 collision; two objects exist in the repository with the same SHA-1. They have *very* different data streams. One of them is "evil". Currently the poor recipient cannot tell the two objects apart, short of by examining the timestamp of the packfiles. But lets say the recipient repacks before he realizes he's been attacked. We may wind up packing the "evil" version of the object, and deleting the "good" one. This is made *even more likely* by Junio's recent rearrange_packed_git patch (b867092f). It is extremely unlikely for a SHA1 collisions to occur, but if it ever happens with a remote (hence untrusted) object we simply must not let the fetch succeed. Normally received packs should not contain objects we already have. But when they do we must ensure duplicated objects with the same SHA1 actually contain the same data. Signed-off-by: Nicolas Pitre <nico@cam.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2007-03-20 19:32:35 +00:00
'make sure index-pack detects the SHA1 collision' \
'test_must_fail git index-pack -o bad.idx test-3.pack 2>msg &&
grep "SHA1 COLLISION FOUND" msg'
don't ever allow SHA1 collisions to exist by fetching a pack Waaaaaaay back Git was considered to be secure as it never overwrote an object it already had. This was ensured by always unpacking the packfile received over the network (both in fetch and receive-pack) and our already existing logic to not create a loose object for an object we already have. Lately however we keep "large-ish" packfiles on both fetch and push by running them through index-pack instead of unpack-objects. This would let an attacker perform a birthday attack. How? Assume the attacker knows a SHA-1 that has two different data streams. He knows the client is likely to have the "good" one. So he sends the "evil" variant to the other end as part of a "large-ish" packfile. The recipient keeps that packfile, and indexes it. Now since this is a birthday attack there is a SHA-1 collision; two objects exist in the repository with the same SHA-1. They have *very* different data streams. One of them is "evil". Currently the poor recipient cannot tell the two objects apart, short of by examining the timestamp of the packfiles. But lets say the recipient repacks before he realizes he's been attacked. We may wind up packing the "evil" version of the object, and deleting the "good" one. This is made *even more likely* by Junio's recent rearrange_packed_git patch (b867092f). It is extremely unlikely for a SHA1 collisions to occur, but if it ever happens with a remote (hence untrusted) object we simply must not let the fetch succeed. Normally received packs should not contain objects we already have. But when they do we must ensure duplicated objects with the same SHA1 actually contain the same data. Signed-off-by: Nicolas Pitre <nico@cam.org> Signed-off-by: Junio C Hamano <junkio@cox.net>
2007-03-20 19:32:35 +00:00
test_expect_success \
'honor pack.packSizeLimit' \
'git config pack.packSizeLimit 200 &&
packname_4=$(git pack-objects test-4 <obj-list) &&
test 3 = $(ls test-4-*.pack | wc -l)'
test_expect_success 'unpacking with --strict' '
git config --unset pack.packsizelimit &&
for j in a b c d e f g
do
for i in 0 1 2 3 4 5 6 7 8 9
do
o=$(echo $j$i | git hash-object -w --stdin) &&
echo "100644 $o 0 $j$i"
done
done >LIST &&
rm -f .git/index &&
git update-index --index-info <LIST &&
LIST=$(git write-tree) &&
rm -f .git/index &&
head -n 10 LIST | git update-index --index-info &&
LI=$(git write-tree) &&
rm -f .git/index &&
tail -n 10 LIST | git update-index --index-info &&
ST=$(git write-tree) &&
PACK5=$( git rev-list --objects "$LIST" "$LI" "$ST" | \
git pack-objects test-5 ) &&
PACK6=$( (
echo "$LIST"
echo "$LI"
echo "$ST"
) | git pack-objects test-6 ) &&
test_create_repo test-5 &&
(
cd test-5 &&
git unpack-objects --strict <../test-5-$PACK5.pack &&
git ls-tree -r $LIST &&
git ls-tree -r $LI &&
git ls-tree -r $ST
) &&
test_create_repo test-6 &&
(
# tree-only into empty repo -- many unreachables
cd test-6 &&
test_must_fail git unpack-objects --strict <../test-6-$PACK6.pack
) &&
(
# already populated -- no unreachables
cd test-5 &&
git unpack-objects --strict <../test-6-$PACK6.pack
)
'
test_expect_success 'index-pack with --strict' '
for j in a b c d e f g
do
for i in 0 1 2 3 4 5 6 7 8 9
do
o=$(echo $j$i | git hash-object -w --stdin) &&
echo "100644 $o 0 $j$i"
done
done >LIST &&
rm -f .git/index &&
git update-index --index-info <LIST &&
LIST=$(git write-tree) &&
rm -f .git/index &&
head -n 10 LIST | git update-index --index-info &&
LI=$(git write-tree) &&
rm -f .git/index &&
tail -n 10 LIST | git update-index --index-info &&
ST=$(git write-tree) &&
PACK5=$( git rev-list --objects "$LIST" "$LI" "$ST" | \
git pack-objects test-5 ) &&
PACK6=$( (
echo "$LIST"
echo "$LI"
echo "$ST"
) | git pack-objects test-6 ) &&
test_create_repo test-7 &&
(
cd test-7 &&
git index-pack --strict --stdin <../test-5-$PACK5.pack &&
git ls-tree -r $LIST &&
git ls-tree -r $LI &&
git ls-tree -r $ST
) &&
test_create_repo test-8 &&
(
# tree-only into empty repo -- many unreachables
cd test-8 &&
test_must_fail git index-pack --strict --stdin <../test-6-$PACK6.pack
) &&
(
# already populated -- no unreachables
cd test-7 &&
git index-pack --strict --stdin <../test-6-$PACK6.pack
)
'
test_expect_success 'tolerate absurdly small packsizelimit' '
git config pack.packSizeLimit 2 &&
packname_9=$(git pack-objects test-9 <obj-list) &&
test $(wc -l <obj-list) = $(ls test-9-*.pack | wc -l)
'
test_done