def extract_archive(cls, f):
logger.debug(f"Extracting {f.filename}")
content = f.blob
if f.password:
# Sflock expects byte string
pw = f.password.encode("utf-8")
else:
pw = None
if f.extension == "zip":
if "v5.1" in f.content_guess:
# Unzip is not capable to process this version, 7z is required (Zip7File)
archive_file = Zip7File(
SflockFile(contents=content, password=pw))
else:
archive_file = ZipFile(
SflockFile(contents=content, password=pw))
elif f.extension == "rar":
archive_file = RarFile(SflockFile(contents=content, password=pw))
elif f.extension == "tar":
archive_file = TarFile(SflockFile(contents=content, password=pw))
else: # Fallback to zip
archive_file = Zip7File(SflockFile(contents=content, password=pw))
files_in_zip = list(archive_file.unpack(password=pw, duplicates=[]))
extracted_files = []
for zf in files_in_zip:
h = HashFactory.get_hashstruct_from_bytes(zf.contents)
cg = zf.magic
fn = zf.filename.decode("utf-8")
ext = fn.rsplit(".", 1)[-1] if "." in fn else ""
f.extractions.append(
Extraction(content_guess=cg,
extension=ext,
description=fn,
hash=h))
file_struct = File(
content_guess=cg,
extension=ext,
encoding='application/octet-stream', # alternative: "hex"
filename=fn,
hash=h,
blob=zf.contents,
timestamp=f.timestamp)
extracted_files.append(file_struct)
logger.info(f"Extracted {zf.filename}")
f.is_enriched = True
return f, extracted_files
def test_udf_iso_noext(self):
upacker = Zip7File(f("iso_udf_noext"))
assert upacker.handles()
assert upacker.supported()
t = unpack("tests/files/iso_udf_noext")
assert t.unpacker == "7zfile"
assert len(t.children) == 1
assert t.children[0].filename == "ATTACHME.EXE"
def test_garbage(self):
t = Zip7File(f("garbage.bin"))
assert t.handles() is False
assert not t.f.selected
with pytest.raises(UnpackException) as e:
t.unpack()
assert e.value.state == Errors.NOTHING_EXTRACTED
def test_garbage2(self):
t = Zip7File(f("7z_garbage.7z"))
assert t.handles() is True
assert not t.f.selected
files = t.unpack()
assert len(files) == 1
assert not files[0].children
assert files[0].mode == "failed"
def test_garbage2(self):
t = Zip7File(f("7z_garbage.7z"))
assert t.handles() is True
assert not t.f.selected
files = t.unpack()
assert len(files) == 1
# The child file is garbage data. It should not be attempted
# to unpack.
assert not files[0].children
assert files[0].mode is None
def test_payment_iso(self):
t = Zip7File(f(b"payment.iso"))
assert t.handles() is True
assert not t.f.selected
files = t.unpack()
assert len(files) == 1
assert hashlib.md5(files[0].contents).hexdigest() == ("eccd7c33037181277ae23f3c3b5baf74")
assert not files[0].children
assert files[0].relaname == (b"payment slip and bank confirmation document.exe")
assert files[0].selected is True
assert files[0].duplicate is False
def test_7z_plain(self):
assert "7-zip archive" in f("7z_plain.7z").magic
t = Zip7File(f("7z_plain.7z"))
assert t.handles() is True
assert not t.f.selected
files = list(t.unpack())
assert len(files) == 1
assert files[0].relapath == "bar.txt"
assert files[0].contents == "hello world\n"
assert files[0].magic == "ASCII text"
assert files[0].parentdirs == []
assert not files[0].selected
def test_nested2_plain(self):
assert "7-zip archive" in f(b"7z_nested2.7z").magic
t = Zip7File(f(b"7z_nested2.7z"))
assert t.handles() is True
assert t.f.selected
files = list(t.unpack())
assert len(files) == 1
assert files[0].relapath == b"deepfoo/foo/bar.txt"
assert files[0].parentdirs == [b"deepfoo", b"foo"]
assert files[0].contents == b"hello world\n"
assert not files[0].password
assert files[0].magic == "ASCII text"
assert not files[0].selected
def test_nested2_plain(self):
assert "7-zip archive" in f("7z_nested2.7z").magic
t = Zip7File(f("7z_nested2.7z"))
assert t.handles() is True
files = list(t.unpack())
assert len(files) == 1
assert files[0].filepath == "deepfoo/foo/bar.txt"
assert files[0].parentdirs == ["deepfoo", "foo"]
assert files[0].contents == "hello world\n"
assert not files[0].password
assert files[0].magic == "ASCII text"
s = f("7z_nested2.7z").get_signature()
assert s is None
def test_7z_plain(self):
assert "7-zip archive" in f("7z_plain.7z").magic
t = Zip7File(f("7z_plain.7z"))
assert t.handles() is True
files = list(t.unpack())
assert len(files) == 1
assert files[0].filepath == "bar.txt"
assert files[0].contents == "hello world\n"
assert files[0].magic == "ASCII text"
assert files[0].parentdirs == []
# TODO A combination of file extension, file magic, and initial bytes
# signature should be used instead of just the bytes (as this call
# should not yield None).
assert f("7z_plain.7z").get_signature() is None
def test_count_supported():
count = 15
if AceFile(None).supported():
count += 1
if CabFile(None).supported():
count += 1
if RarFile(None).supported():
count += 1
if Zip7File(None).supported():
count += 7
assert count == len(supported())
def test_count_supported():
count = 10
if DaaFile(None).supported():
count += 1
if VHDFile(None).supported():
count += 2
if AceFile(None).supported():
count += 1
if CabFile(None).supported():
count += 1
if RarFile(None).supported():
count += 1
if Zip7File(None).supported():
count += 5
assert count == len(supported())
def test_no7z_plain():
assert "7-zip archive" in f("7z_plain.7z").magic
t = Zip7File(f("7z_plain.7z"))
assert t.handles() is True
def test_garbage(self):
t = Zip7File(f("garbage.bin"))
assert t.handles() is False
assert not t.f.selected
assert not t.unpack()
assert t.f.mode == "failed"
def test_suffix():
assert "7-zip archive" in f(b"7z_suffix.docx").magic
t = Zip7File(f(b"7z_suffix.docx"))
assert t.handles() is True
assert t.f.package == "7z"
