def corrupt_share(options):
import random
from allmydata.storage.mutable import MutableShareFile
from allmydata.storage.immutable import ShareFile
from allmydata.mutable.layout import unpack_header
from allmydata.immutable.layout import ReadBucketProxy
out = options.stdout
fn = options['filename']
assert options["offset"] == "block-random", "other offsets not implemented"
# first, what kind of share is it?
def flip_bit(start, end):
offset = random.randrange(start, end)
bit = random.randrange(0, 8)
print("[%d..%d): %d.b%d" % (start, end, offset, bit), file=out)
f = open(fn, "rb+")
f.seek(offset)
d = f.read(1)
d = bchr(ord(d) ^ 0x01)
f.seek(offset)
f.write(d)
f.close()
with open(fn, "rb") as f:
prefix = f.read(32)
if MutableShareFile.is_valid_header(prefix):
# mutable
m = MutableShareFile(fn)
with open(fn, "rb") as f:
f.seek(m.DATA_OFFSET)
# Read enough data to get a mutable header to unpack.
data = f.read(2000)
# make sure this slot contains an SMDF share
assert data[
0:1] == b"\x00", "non-SDMF mutable shares not supported"
f.close()
(version, ig_seqnum, ig_roothash, ig_IV, ig_k, ig_N, ig_segsize,
ig_datalen, offsets) = unpack_header(data)
assert version == 0, "we only handle v0 SDMF files"
start = m.DATA_OFFSET + offsets["share_data"]
end = m.DATA_OFFSET + offsets["enc_privkey"]
flip_bit(start, end)
else:
# otherwise assume it's immutable
f = ShareFile(fn)
bp = ReadBucketProxy(None, None, '')
offsets = bp._parse_offsets(f.read_share_data(0, 0x24))
start = f._data_offset + offsets["data"]
end = f._data_offset + offsets["plaintext_hash_tree"]
flip_bit(start, end)
def corrupt_share(options):
import random
from allmydata.storage.mutable import MutableShareFile
from allmydata.storage.immutable import ShareFile
from allmydata.mutable.layout import unpack_header
from allmydata.immutable.layout import ReadBucketProxy
out = options.stdout
fn = options['filename']
assert options["offset"] == "block-random", "other offsets not implemented"
# first, what kind of share is it?
def flip_bit(start, end):
offset = random.randrange(start, end)
bit = random.randrange(0, 8)
print >>out, "[%d..%d): %d.b%d" % (start, end, offset, bit)
f = open(fn, "rb+")
f.seek(offset)
d = f.read(1)
d = chr(ord(d) ^ 0x01)
f.seek(offset)
f.write(d)
f.close()
f = open(fn, "rb")
prefix = f.read(32)
f.close()
if prefix == MutableShareFile.MAGIC:
# mutable
m = MutableShareFile(fn)
f = open(fn, "rb")
f.seek(m.DATA_OFFSET)
data = f.read(2000)
# make sure this slot contains an SMDF share
assert data[0] == "\x00", "non-SDMF mutable shares not supported"
f.close()
(version, ig_seqnum, ig_roothash, ig_IV, ig_k, ig_N, ig_segsize,
ig_datalen, offsets) = unpack_header(data)
assert version == 0, "we only handle v0 SDMF files"
start = m.DATA_OFFSET + offsets["share_data"]
end = m.DATA_OFFSET + offsets["enc_privkey"]
flip_bit(start, end)
else:
# otherwise assume it's immutable
f = ShareFile(fn)
bp = ReadBucketProxy(None, '', '')
offsets = bp._parse_offsets(f.read_share_data(0, 0x24))
start = f._data_offset + offsets["data"]
end = f._data_offset + offsets["plaintext_hash_tree"]
flip_bit(start, end)
def dump_immutable_chk_share(f, out, options):
from allmydata import uri
from allmydata.util import base32
from allmydata.immutable.layout import ReadBucketProxy
from allmydata.util.encodingutil import quote_output, to_bytes
# use a ReadBucketProxy to parse the bucket and find the uri extension
bp = ReadBucketProxy(None, None, '')
offsets = bp._parse_offsets(f.read_share_data(0, 0x44))
print("%20s: %d" % ("version", bp._version), file=out)
seek = offsets['uri_extension']
length = struct.unpack(bp._fieldstruct,
f.read_share_data(seek, bp._fieldsize))[0]
seek += bp._fieldsize
UEB_data = f.read_share_data(seek, length)
unpacked = uri.unpack_extension_readable(UEB_data)
keys1 = ("size", "num_segments", "segment_size", "needed_shares",
"total_shares")
keys2 = ("codec_name", "codec_params", "tail_codec_params")
keys3 = ("plaintext_hash", "plaintext_root_hash", "crypttext_hash",
"crypttext_root_hash", "share_root_hash", "UEB_hash")
display_keys = {"size": "file_size"}
def to_string(v):
if isinstance(v, bytes):
return unicode(v, "utf-8")
else:
return str(v)
for k in keys1:
if k in unpacked:
dk = display_keys.get(k, k)
print("%20s: %s" % (dk, to_string(unpacked[k])), file=out)
print(file=out)
for k in keys2:
if k in unpacked:
dk = display_keys.get(k, k)
print("%20s: %s" % (dk, to_string(unpacked[k])), file=out)
print(file=out)
for k in keys3:
if k in unpacked:
dk = display_keys.get(k, k)
print("%20s: %s" % (dk, to_string(unpacked[k])), file=out)
leftover = set(unpacked.keys()) - set(keys1 + keys2 + keys3)
if leftover:
print(file=out)
print("LEFTOVER:", file=out)
for k in sorted(leftover):
print("%20s: %s" % (k, to_string(unpacked[k])), file=out)
# the storage index isn't stored in the share itself, so we depend upon
# knowing the parent directory name to get it
pieces = options['filename'].split(os.sep)
if len(pieces) >= 2:
piece = to_bytes(pieces[-2])
if base32.could_be_base32_encoded(piece):
storage_index = base32.a2b(piece)
uri_extension_hash = base32.a2b(unpacked["UEB_hash"])
u = uri.CHKFileVerifierURI(storage_index, uri_extension_hash,
unpacked["needed_shares"],
unpacked["total_shares"],
unpacked["size"])
verify_cap = u.to_string()
print("%20s: %s" %
("verify-cap", quote_output(verify_cap, quotemarks=False)),
file=out)
sizes = {}
sizes['data'] = (offsets['plaintext_hash_tree'] - offsets['data'])
sizes['validation'] = (offsets['uri_extension'] -
offsets['plaintext_hash_tree'])
sizes['uri-extension'] = len(UEB_data)
print(file=out)
print(" Size of data within the share:", file=out)
for k in sorted(sizes):
print("%20s: %s" % (k, sizes[k]), file=out)
if options['offsets']:
print(file=out)
print(" Section Offsets:", file=out)
print("%20s: %s" % ("share data", f._data_offset), file=out)
for k in [
"data", "plaintext_hash_tree", "crypttext_hash_tree",
"block_hashes", "share_hashes", "uri_extension"
]:
name = {"data": "block data"}.get(k, k)
offset = f._data_offset + offsets[k]
print(" %20s: %s (0x%x)" % (name, offset, offset), file=out)
print("%20s: %s" % ("leases", f._lease_offset), file=out)
def dump_immutable_chk_share(f, out, options):
from allmydata import uri
from allmydata.util import base32
from allmydata.immutable.layout import ReadBucketProxy
from allmydata.util.encodingutil import quote_output, to_str
# use a ReadBucketProxy to parse the bucket and find the uri extension
bp = ReadBucketProxy(None, '', '')
offsets = bp._parse_offsets(f.read_share_data(0, 0x44))
print >>out, "%20s: %d" % ("version", bp._version)
seek = offsets['uri_extension']
length = struct.unpack(bp._fieldstruct,
f.read_share_data(seek, bp._fieldsize))[0]
seek += bp._fieldsize
UEB_data = f.read_share_data(seek, length)
unpacked = uri.unpack_extension_readable(UEB_data)
keys1 = ("size", "num_segments", "segment_size",
"needed_shares", "total_shares")
keys2 = ("codec_name", "codec_params", "tail_codec_params")
keys3 = ("plaintext_hash", "plaintext_root_hash",
"crypttext_hash", "crypttext_root_hash",
"share_root_hash", "UEB_hash")
display_keys = {"size": "file_size"}
for k in keys1:
if k in unpacked:
dk = display_keys.get(k, k)
print >>out, "%20s: %s" % (dk, unpacked[k])
print >>out
for k in keys2:
if k in unpacked:
dk = display_keys.get(k, k)
print >>out, "%20s: %s" % (dk, unpacked[k])
print >>out
for k in keys3:
if k in unpacked:
dk = display_keys.get(k, k)
print >>out, "%20s: %s" % (dk, unpacked[k])
leftover = set(unpacked.keys()) - set(keys1 + keys2 + keys3)
if leftover:
print >>out
print >>out, "LEFTOVER:"
for k in sorted(leftover):
print >>out, "%20s: %s" % (k, unpacked[k])
# the storage index isn't stored in the share itself, so we depend upon
# knowing the parent directory name to get it
pieces = options['filename'].split(os.sep)
if len(pieces) >= 2:
piece = to_str(pieces[-2])
if base32.could_be_base32_encoded(piece):
storage_index = base32.a2b(piece)
uri_extension_hash = base32.a2b(unpacked["UEB_hash"])
u = uri.CHKFileVerifierURI(storage_index, uri_extension_hash,
unpacked["needed_shares"],
unpacked["total_shares"], unpacked["size"])
verify_cap = u.to_string()
print >>out, "%20s: %s" % ("verify-cap", quote_output(verify_cap, quotemarks=False))
sizes = {}
sizes['data'] = (offsets['plaintext_hash_tree'] -
offsets['data'])
sizes['validation'] = (offsets['uri_extension'] -
offsets['plaintext_hash_tree'])
sizes['uri-extension'] = len(UEB_data)
print >>out
print >>out, " Size of data within the share:"
for k in sorted(sizes):
print >>out, "%20s: %s" % (k, sizes[k])
if options['offsets']:
print >>out
print >>out, " Section Offsets:"
print >>out, "%20s: %s" % ("share data", f._data_offset)
for k in ["data", "plaintext_hash_tree", "crypttext_hash_tree",
"block_hashes", "share_hashes", "uri_extension"]:
name = {"data": "block data"}.get(k,k)
offset = f._data_offset + offsets[k]
print >>out, " %20s: %s (0x%x)" % (name, offset, offset)
print >>out, "%20s: %s" % ("leases", f._lease_offset)