git-commit-vandalism/t/lib-pack.sh

111 lines
2.9 KiB
Bash
Raw Normal View History

# Support routines for hand-crafting weird or malicious packs.
#
# You can make a complete pack like:
#
# pack_header 2 >foo.pack &&
# pack_obj e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 >>foo.pack &&
# pack_obj e68fe8129b546b101aee9510c5328e7f21ca1d18 >>foo.pack &&
# pack_trailer foo.pack
# Print the big-endian 4-byte octal representation of $1
uint32_octal () {
n=$1
printf '\\%o' $(($n / 16777216)); n=$((n % 16777216))
printf '\\%o' $(($n / 65536)); n=$((n % 65536))
printf '\\%o' $(($n / 256)); n=$((n % 256))
printf '\\%o' $(($n ));
}
# Print the big-endian 4-byte binary representation of $1
uint32_binary () {
printf "$(uint32_octal "$1")"
}
# Print a pack header, version 2, for a pack with $1 objects
pack_header () {
printf 'PACK' &&
printf '\0\0\0\2' &&
uint32_binary "$1"
}
# Print the pack data for object $1, as a delta against object $2 (or as a full
# object if $2 is missing or empty). The output is suitable for including
# directly in the packfile, and represents the entirety of the object entry.
# Doing this on the fly (especially picking your deltas) is quite tricky, so we
# have hardcoded some well-known objects. See the case statements below for the
# complete list.
pack_obj () {
case "$1" in
# empty blob
e69de29bb2d1d6434b8b29ae775ad8c2e48c5391)
case "$2" in
'')
printf '\060\170\234\003\0\0\0\0\1'
return
;;
esac
;;
# blob containing "\7\76"
e68fe8129b546b101aee9510c5328e7f21ca1d18)
case "$2" in
'')
printf '\062\170\234\143\267\3\0\0\116\0\106'
return
;;
01d7713666f4de822776c7622c10f1b07de280dc)
printf '\165\1\327\161\66\146\364\336\202\47\166' &&
printf '\307\142\54\20\361\260\175\342\200\334\170' &&
printf '\234\143\142\142\142\267\003\0\0\151\0\114'
return
;;
esac
;;
# blob containing "\7\0"
01d7713666f4de822776c7622c10f1b07de280dc)
case "$2" in
'')
printf '\062\170\234\143\147\0\0\0\20\0\10'
return
;;
e68fe8129b546b101aee9510c5328e7f21ca1d18)
printf '\165\346\217\350\22\233\124\153\20\32\356' &&
printf '\225\20\305\62\216\177\41\312\35\30\170\234' &&
printf '\143\142\142\142\147\0\0\0\53\0\16'
return
;;
esac
;;
esac
index-pack: check .gitmodules files with --strict Now that the internal fsck code has all of the plumbing we need, we can start checking incoming .gitmodules files. Naively, it seems like we would just need to add a call to fsck_finish() after we've processed all of the objects. And that would be enough to cover the initial test included here. But there are two extra bits: 1. We currently don't bother calling fsck_object() at all for blobs, since it has traditionally been a noop. We'd actually catch these blobs in fsck_finish() at the end, but it's more efficient to check them when we already have the object loaded in memory. 2. The second pass done by fsck_finish() needs to access the objects, but we're actually indexing the pack in this process. In theory we could give the fsck code a special callback for accessing the in-pack data, but it's actually quite tricky: a. We don't have an internal efficient index mapping oids to packfile offsets. We only generate it on the fly as part of writing out the .idx file. b. We'd still have to reconstruct deltas, which means we'd basically have to replicate all of the reading logic in packfile.c. Instead, let's avoid running fsck_finish() until after we've written out the .idx file, and then just add it to our internal packed_git list. This does mean that the objects are "in the repository" before we finish our fsck checks. But unpack-objects already exhibits this same behavior, and it's an acceptable tradeoff here for the same reason: the quarantine mechanism means that pushes will be fully protected. In addition to a basic push test in t7415, we add a sneaky pack that reverses the usual object order in the pack, requiring that index-pack access the tree and blob during the "finish" step. This already works for unpack-objects (since it will have written out loose objects), but we'll check it with this sneaky pack for good measure. Signed-off-by: Jeff King <peff@peff.net>
2018-05-05 01:45:01 +02:00
# If it's not a delta, we can convince pack-objects to generate a pack
# with just our entry, and then strip off the header (12 bytes) and
# trailer (20 bytes).
if test -z "$2"
then
echo "$1" | git pack-objects --stdout >pack_obj.tmp &&
size=$(wc -c <pack_obj.tmp) &&
dd if=pack_obj.tmp bs=1 count=$((size - 20 - 12)) skip=12 &&
rm -f pack_obj.tmp
return
fi
echo >&2 "BUG: don't know how to print $1${2:+ (from $2)}"
return 1
}
# Compute and append pack trailer to "$1"
pack_trailer () {
test-tool sha1 -b <"$1" >trailer.tmp &&
cat trailer.tmp >>"$1" &&
rm -f trailer.tmp
}
# Remove any existing packs to make sure that
# whatever we index next will be the pack that we
# actually use.
clear_packs () {
rm -f .git/objects/pack/*
}