def test_fail_safe_write_file(self):
file_path = os.path.join(self.tmp_dir.name, "test_folder", "test_file")
write_binary_to_file(b'this is a test', file_path)
self.assertTrue(os.path.exists(file_path), "file not created")
read_binary = get_binary_from_file(file_path)
self.assertEqual(read_binary, b'this is a test',
"written data not correct")
# Test not overwrite flag
write_binary_to_file(b'do not overwrite', file_path, overwrite=False)
read_binary = get_binary_from_file(file_path)
self.assertEqual(read_binary, b'this is a test',
"written data not correct")
# Test overwrite flag
write_binary_to_file(b'overwrite', file_path, overwrite=True)
read_binary = get_binary_from_file(file_path)
self.assertEqual(read_binary, b'overwrite', "written data not correct")
# Test copy_file_flag
write_binary_to_file(b'second_overwrite', file_path, file_copy=True)
self.assertTrue(os.path.exists("{}-1".format(file_path)),
"new file copy does not exist")
read_binary_original = get_binary_from_file(file_path)
self.assertEqual(read_binary_original, b'overwrite',
"original file no longer correct")
read_binary_new = get_binary_from_file("{}-1".format(file_path))
self.assertEqual(read_binary_new, b'second_overwrite',
"binary of new file not correct")
def test_fail_safe_read_file(self):
test_file_path = os.path.join(self.get_directory_of_current_file(),
"data", "read_test")
file_binary = get_binary_from_file(test_file_path)
self.assertEqual(file_binary, b'this is a test', "content not correct")
# Test none existing file
none_existing_file_path = os.path.join(
self.get_directory_of_current_file(), "data", "none_existing_file")
file_binary = get_binary_from_file(none_existing_file_path)
self.assertEqual(file_binary, b'', "content not correct")
# Test link
link_path = os.path.join(self.get_directory_of_current_file(), "data",
"link_test")
file_binary = get_binary_from_file(link_path)
assert file_binary == 'symbolic link -> read_test'
def unpack_function(file_path, tmp_dir):
raw = get_binary_from_file(file_path)
meta_dict = _get_meta_data(raw)
meta_dict['encoding_overhead'] = ENCODING_OVERHEAD
payloads = _get_payloads(raw)
_store_files(payloads, tmp_dir)
return meta_dict
def test_set_binary():
binary = get_binary_from_file('{}/get_files_test/testfile1'.format(
get_test_data_dir()))
md5 = 'e802ca22f6cd2d9357cf3da1d191879e'
firmware = Firmware()
firmware.set_binary(binary)
assert firmware.md5 == md5
def _sync_view(self, plugin_path):
if plugin_path:
view_source = self._get_view_file_path(plugin_path)
if view_source is not None:
view = get_binary_from_file(view_source)
with ConnectTo(ViewUpdater, self.config) as connection:
connection.update_view(self.NAME, view)
def generate_uid(file_path):
file_data = get_binary_from_file(file_path)
if file_data == b'' or type(file_data) is not bytes:
return "0_0"
file_hash = sha256(file_data).hexdigest()
file_size = get_file_size(file_path)
return "{}_{}".format(file_hash, file_size)
def test_get_raw_payloads(self):
raw_content = get_binary_from_file(TEST_FILE)
payloads = _get_raw_payloads(raw_content)
self.assertEqual(len(payloads), 3, "number of payloads not correct")
self.assertEqual(payloads[0], b'<~<+oue+DGm>FD,5.Anc:,F<FCgH#.D-A0C~>', "simple payload not correct")
self.assertEqual(payloads[1], b'<~<+oue+DGm>@3BW&@rH6q+Dl72BHV,0DJ*O$+E1b7Ci<`m+EV:*F<GX<Dfol,+Cf>-FCAm$+\nEM+;ATD3q+Dbb0ATJu&DIal2D]it9/hSa~>', "multiline payload not correct")
self.assertEqual(payloads[2], b'<~@;^"*BOu3kAoD^,@<;~>', "other header format")
def unpack_function(file_path, tmp_dir):
raw_binary = get_binary_from_file(file_path)
meta_data = dict()
for extractor in EXTRACTOR_LIST:
data_sections = extractor.extract_function(raw_binary, *extractor.optional_parameters)
dump_files(data_sections, tmp_dir, suffix=extractor.file_suffix)
meta_data[extractor.name] = len(data_sections)
return meta_data
def test_store_blacklist():
tmp_dir = TemporaryDirectory()
tmp_file_path = os.path.join(tmp_dir.name, 'blacklist_test_file.txt')
test_data = ['abc', 'def']
_store_blacklist(test_data, tmp_file_path)
assert os.path.exists(tmp_file_path)
result = get_binary_from_file(tmp_file_path)
assert result == b'abc\ndef'
def get_template_as_string(view_name: str) -> str:
'''
Get the content of template ``view_name`` from the template directory as string.
:param view_name: The name of the template file.
:return: The contents of the template file as string.
'''
path = Path(get_template_dir()) / view_name
return get_binary_from_file(str(path)).decode('utf-8')
def _repack_extracted_files(extraction_dir, out_file_path):
with Popen('tar -C {} -cvzf {} .'.format(extraction_dir.name,
out_file_path),
shell=True,
stdout=PIPE) as process:
output = process.stdout.read().decode()
logging.debug('tar -cvzf:\n {}'.format(output))
return get_binary_from_file(out_file_path)
def __init__(self, file_path, raw=None):
self.errors = []
self.warnings = []
if raw is None:
self.raw = get_binary_from_file(file_path)
else:
self.raw = raw
self.parse_header()
self.extract_payload()
self.log_errors_and_warnings()
def unpack_function(file_path, tmp_dir):
"""
file_path specifies the input file.
tmp_dir should be used to store the extracted files.
Optional: Return a dict with meta information
"""
file_binary = get_binary_from_file(file_path)
pjl_commands = get_pjl_commands(file_binary)
extract_all_upgrades(file_binary, pjl_commands, tmp_dir)
extract_fingerprint(file_binary, tmp_dir)
return {'pjl_commands': pjl_commands}
def unpack_function(file_path, tmp_dir):
"""
file_path specifies the input file.
tmp_dir should be used to store the extracted files.
Optional: Return a dict with meta information
"""
raw_data = get_binary_from_file(file_path)
decompressed_data = zlib.decompress(raw_data)
output_file_path = os.path.join(tmp_dir, "zlib_decompressed")
write_binary_to_file(decompressed_data, output_file_path)
return {}
def test_extraction_new_container_format(self):
input_file = Path(TEST_DATA_DIR, 'hp_new_container.pjl')
_, meta_data = self.unpacker.extract_files_from_file(str(input_file), self.tmp_dir.name)
assert len(meta_data) > 1
assert Path(self.tmp_dir.name, 'fingerprint.txt').exists()
extracted_file_path = Path(self.tmp_dir.name, '812.bin')
assert extracted_file_path.exists()
binary_content = get_binary_from_file(str(extracted_file_path))
assert binary_content[0:4] == b'\x94\x1E\x12\x00'
assert len(binary_content) == 224
def unpack_function(file_path, tmp_dir):
raw_binary = get_binary_from_file(file_path)
ff_padded_sections = cut_at_padding(raw_binary,
padding_min_length=16,
padding_pattern=b'\xff')
lzma_streams = extract_lzma_streams(raw_binary)
decompressed_lzma_streams = get_decompressed_lzma_streams(lzma_streams)
dump_files(ff_padded_sections, tmp_dir)
dump_files(decompressed_lzma_streams, tmp_dir, suffix='_lzma_decompressed')
return _get_meta_data(ff_padded_sections, lzma_streams)
def test_extract_file_from_upgrade():
with TemporaryDirectory(prefix='fact_test_') as tmp_dir:
expected_path_of_dumped_file = Path(tmp_dir,
'HP_Color_LaserJet_CP4525.bin')
_extract_file_from_upgrade(TEST_DATA_UPGRADE_RAW, TEST_COMMAND,
tmp_dir)
assert expected_path_of_dumped_file.exists()
dumped_file_binary = get_binary_from_file(
str(expected_path_of_dumped_file))
assert dumped_file_binary == b'\x00Test File 1'
def tar_repack(self, file_path):
extraction_dir = TemporaryDirectory(prefix='FAF_tar_repack')
container_storage = TemporaryDirectory(prefix='FAF_tar_repack')
self.extract_files_from_file(file_path, extraction_dir.name)
out_file_path = os.path.join(container_storage.name, 'download.tar.gz')
output = Popen('tar -C {} -cvzf {} .'.format(extraction_dir.name,
out_file_path),
shell=True,
stdout=PIPE).stdout.read().decode()
logging.debug('tar -cvzf:\n {}'.format(output))
tar = get_binary_from_file(out_file_path)
extraction_dir.cleanup()
container_storage.cleanup()
return tar
def unpack_function(file_path: str, tmp_dir: str) -> dict:
"""
file_path specifies the input file.
tmp_dir should be used to store the extracted files.
Optional: Return a dict with meta information
"""
raw_binary = get_binary_from_file(file_path)
data_sections = cut_at_padding(raw_binary, padding_min_length=16)
lzma_streams = extract_lzma_streams(raw_binary)
decompressed_lzma_streams = get_decompressed_lzma_streams(lzma_streams)
dump_files(data_sections, tmp_dir)
dump_files(decompressed_lzma_streams, tmp_dir, suffix='_lzma_decompressed')
return _get_meta_data(data_sections, lzma_streams)
def process_object(self, file_object):
result = {}
tmp_dir = TemporaryDirectory(prefix='faf_analysis_binwalk_')
dir_path = tmp_dir.name
signature_analysis_result = execute_shell_command('(cd {} && xvfb-run -a binwalk -BEJ {})'.format(dir_path, file_object.file_path))
result['signature_analysis'] = make_unicode_string(signature_analysis_result)
result['summary'] = list(set(self._extract_summary(result['signature_analysis'])))
pic_path = os.path.join(dir_path, '{}.png'.format(os.path.basename(file_object.file_path)))
result['entropy_analysis_graph'] = get_binary_from_file(pic_path)
tmp_dir.cleanup()
file_object.processed_analysis[self.NAME] = result
return file_object
def test_extraction(self):
in_file = os.path.join(TEST_DATA_DIR, 'test.zlib')
files, meta_data = self.unpacker.extract_files_from_file(
in_file, self.tmp_dir.name)
self.assertEqual(len(files), 1,
'number of extracted files not correct')
self.assertEqual(files[0],
os.path.join(self.tmp_dir.name, 'zlib_decompressed'),
'file name not correct')
file_binary = get_binary_from_file(files[0])
file_hash = get_sha256(file_binary)
self.assertEqual(
file_hash,
'e429103649e24ca126077bfb38cce8c57cc913a966d7e36356e4fe0513ab02c4')
self.assertEqual(len(meta_data.keys()), 4,
'more or fewer than standard keys in meta dict')
def test_header_and_binary(self):
files, meta_data = self.unpacker.extract_files_from_file(
self.test_file.file_path, self.tmp_dir.name)
files = set(files)
self.assertEqual(len(files), 1, 'file number incorrect')
data_bin = get_binary_from_file(
os.path.join(self.tmp_dir.name, 'dlm_data.bin'))
self.assertEqual(
get_sha256(data_bin),
'701962b0d11f50d9129d5a1655ee054865e90cd1b547d40d590ea96f7dfb64eb')
self.assertEqual(meta_data['dlm_version'], 'NO_DLM_VERSION_CHECK',
'meta: dlm_version not correct')
self.assertEqual(
meta_data['dlm_signature'],
'90ec11f7b52468378362987a4ed9e56855070915887e6afe567e1c47875b29f9',
'meta: dlm_signature not correct')
self.assertEqual(meta_data['dlm_name'], '080415_08142013',
'meta: dlm_name not correct')
self.assertEqual(meta_data['dlm_extraction_criteria'],
'upgradeExtract.sh /tmp/080415_08142013.dnld',
'meta: dlm_criteria not correct')
def create_from_file(self, file_path):
self.set_binary(get_binary_from_file(file_path))
self.set_file_path(file_path)
def _get_uid(file_path, root_path: Path):
return create_uid(get_binary_from_file(str(root_path / file_path[1:])))
def _create_from_file(self, file_path: str):
self.set_binary(get_binary_from_file(file_path))
self.create_binary_from_path()
def get_template_as_string(view_name):
path = os.path.join(get_template_dir(), view_name)
return get_binary_from_file(path).decode('utf-8')
def _hash_compare(self, filename, hashsum):
binary_data = get_binary_from_file(
os.path.join(self.tmp_dir.name, filename))
self.assertEqual(get_sha256(binary_data), hashsum,
'Checksum incorrect for file {}'.format(filename))
def test_file_object_init_with_binary(self):
bin_data = get_binary_from_file('{}/test_data_file.bin'.format(get_test_data_dir()))
test_object = FileObject(bin_data)
self.assertEqual(test_object.sha256, '268d870ffa2b21784e4dc955d8e8b8eb5f3bcddd6720a1e6d31d2cf84bd1bff8', 'correct sha256')
self.assertEqual(test_object.file_name, None, 'correct file name')
def check_file_presence_and_content(self, file_path, file_binary):
self.assertTrue(os.path.exists(file_path), 'file exists')
self.assertEqual(get_binary_from_file(file_path), file_binary,
'correct content')
def get_analysis_view(view_name):
view_path = os.path.join(
get_src_dir(),
'web_interface/templates/analysis_plugins/{}.html'.format(view_name))
return get_binary_from_file(view_path).decode('utf-8')
