def test_that_a_file_can_be_fragmented_into_two_fragments(self, path_test_file_4k):
frags = File(path_test_file_4k).fragment((1,), block_size=512)
assert len(frags) == 2
assert _replace_uuids(frags[0].metadata) == _replace_uuids(
FileFragment(File(path_test_file_4k), 1, 0, 512).metadata)
assert _replace_uuids(frags[1].metadata) == _replace_uuids(
FileFragment(File(path_test_file_4k), 2, 512, 4096).metadata)
def test_that_a_file_can_be_fragmented_into_four_fragments(self, path_test_file_4k):
frags = File(path_test_file_4k).fragment((1, 3, 7), block_size=512)
assert len(frags) == 4
assert _replace_uuids(frags[0].metadata) == _replace_uuids(
FileFragment(File(path_test_file_4k), 1, 0, 512).metadata)
assert _replace_uuids(frags[1].metadata) == _replace_uuids(
FileFragment(File(path_test_file_4k), 2, 512, 1536).metadata)
assert _replace_uuids(frags[2].metadata) == _replace_uuids(
FileFragment(File(path_test_file_4k), 3, 1536, 3584).metadata)
assert _replace_uuids(frags[3].metadata) == _replace_uuids(
FileFragment(File(path_test_file_4k), 4, 3584, 4096).metadata)
def test_that_the_correct_hash_is_computed(self, path_test_file_4k):
assert FileFragment(
File(path_test_file_4k), 1, 0, 1024
).hash == '06aed7f43b72ab019f06f2cbf0a94237ad29cc36d2c91e27a9d3e734c90b665b'
assert FileFragment(
File(path_test_file_4k), 1, 1024, 2048
).hash == 'dbbed6c65649c043888d421b8a950374faa0f5f3af28a12f9a2224d3b7c3fd9a'
assert FileFragment(
File(path_test_file_4k), 1, 2048, 3072
).hash == '036c079fccd6a7527eb31f9dc7aaeb1cac70796c1a4a1627b81309ee018d11da'
assert FileFragment(
File(path_test_file_4k), 1, 3072, 4096
).hash == '57434187458631358bbf7241a53990c77be44fa37194ae149b32427c5bc5fcac'
def test_an_image_with_a_single_file_fragment(self, test_corpus_path):
woodblock.random.seed(13)
woodblock.file.corpus(test_corpus_path)
image_path = HERE / 'simple-file.dd'
metadata_path = pathlib.Path('.'.join((str(image_path), 'json')))
s = Scenario('simple file fragment')
s.add(File(test_corpus_path / '512').as_fragment())
image = Image(block_size=512)
image.add(s)
image.write(image_path)
assert image_path.is_file()
assert image_path.stat().st_size == 512
assert image_path.open('rb').read() == b'A' * 512
assert metadata_path.is_file()
assert _replace_uuids(json.load(metadata_path.open('r'))) == {
'block_size':
512,
'corpus':
str(test_corpus_path),
'seed':
woodblock.random.get_seed(),
'scenarios': [{
'name':
'simple file fragment',
'files': [{
'original': {
'type':
'file',
'path':
str((HERE.parent / 'data' / 'corpus' /
'512').relative_to(get_corpus())),
'size':
512,
'id':
'uuid',
'sha256':
'32beecb58a128af8248504600bd203dcc676adf41045300485655e6b8780a01d'
},
'fragments': [{
'number': 1,
'size': 512,
'sha256':
'32beecb58a128af8248504600bd203dcc676adf41045300485655e6b8780a01d',
'file_offsets': {
'start': 0,
'end': 512
},
'image_offsets': {
'start': 0,
'end': 512
}
}]
}]
}]
}
os.remove(image_path)
os.remove(metadata_path)
def test_that_fragment_is_created_correctly(self, path_test_file_512):
fragment = FileFragment(File(path_test_file_512), 1, 0, 512)
assert fragment.size == 512
call_count = 0
data = b''
for chunk in fragment:
call_count += 1
data = b''.join((data, chunk))
assert call_count == ceil(512 / 8192)
assert len(data) == 512
assert data == b'A' * 512
def test_that_the_metadata_is_correct(self, path_test_file_512):
fragment = FileFragment(File(path_test_file_512), 1, 0, 512)
meta = _replace_uuids(fragment.metadata)
assert meta == {
'file': {
'sha256':
'32beecb58a128af8248504600bd203dcc676adf41045300485655e6b8780a01d',
'id': 'uuid',
'type': 'file',
'size': 512,
'path': str(path_test_file_512.relative_to(get_corpus()))
},
'fragment': {
'sha256':
'32beecb58a128af8248504600bd203dcc676adf41045300485655e6b8780a01d',
'size': 512,
'number': 1,
'file_offsets': {
'start': 0,
'end': 512
}
}
}
def test_that_an_empty_list_of_fragmentation_points_return_a_single_fragment(self, path_test_file_4k):
frags = File(path_test_file_4k).fragment(tuple(), block_size=512)
assert len(frags) == 1
assert _replace_uuids(frags[0].metadata) == _replace_uuids(
FileFragment(File(path_test_file_4k), 1, 0, 4096).metadata)
def test_that_invalid_num_fragments_raises_an_error(self, num_fragments, path_test_file_4k):
with pytest.raises(InvalidFragmentationPointError):
File(path_test_file_4k).fragment_randomly(num_fragments, 512)
def test_an_image_with_two_reversed_file_fragments_and_three_filler_fragments(self, test_corpus_path):
woodblock.random.seed(13)
woodblock.file.corpus(test_corpus_path)
image_path = HERE / 'simple-fragmentation.dd'
metadata_path = pathlib.Path('.'.join((str(image_path), 'json')))
file_path = test_corpus_path / '4096'
frags = File(file_path).fragment_evenly(num_fragments=2)
s = Scenario('simple fragmentation with fillers')
s.add(RandomDataFragment(512))
s.add(frags[1])
s.add(ZeroesFragment(512))
s.add(frags[0])
s.add(RandomDataFragment(512))
image = Image(block_size=512)
image.add(s)
image.write(image_path)
assert image_path.is_file()
assert image_path.stat().st_size == 5632
assert metadata_path.is_file()
meta = _replace_uuids(json.load(metadata_path.open('r')))
assert meta['block_size'] == 512
assert meta['corpus'] == str(test_corpus_path)
assert meta['seed'] == 13
assert len(meta['scenarios']) == 1
sc_meta = meta['scenarios'][0]
assert sc_meta['name'] == 'simple fragmentation with fillers'
assert len(sc_meta['files']) == 4
assert sc_meta['files'][0]['original']['type'] == 'filler'
assert sc_meta['files'][0]['original']['path'] == 'random'
assert sc_meta['files'][0]['original']['size'] == 512
assert len(sc_meta['files'][0]['fragments']) == 1
assert sc_meta['files'][0]['fragments'][0]['number'] == 1
assert sc_meta['files'][0]['fragments'][0]['size'] == 512
assert sc_meta['files'][0]['fragments'][0]['file_offsets'] == {'start': 0, 'end': 512}
assert sc_meta['files'][0]['fragments'][0]['image_offsets'] == {'start': 0, 'end': 512}
assert sc_meta['files'][1] == {
'original': {'type': 'file', 'path': str(file_path.relative_to(get_corpus())), 'size': 4096, 'id': 'uuid',
'sha256': '0ec91e13ced59cfc1f297cfedd8c595a6200ac2b8c99bcc321e8c68cf1f166a0'},
'fragments': [{'number': 1, 'size': 2048,
'sha256': '291b808471ca4772e260dd50604e93082c22fbcf821fa3db7531e51343473717',
'file_offsets': {'start': 0, 'end': 2048}, 'image_offsets': {'start': 3072, 'end': 5120}},
{'number': 2, 'size': 2048,
'sha256': '570dc7f7ceea7fa7204588456fd00e53b0abf1cca9d35cc074383e8dcc418114',
'file_offsets': {'start': 2048, 'end': 4096}, 'image_offsets': {'start': 512, 'end': 2560}}
]}
assert sc_meta['files'][2] == {
'original': {'type': 'filler', 'path': 'zeroes', 'size': 512, 'id': 'uuid',
'sha256': '076a27c79e5ace2a3d47f9dd2e83e4ff6ea8872b3c2218f66c92b89b55f36560'},
'fragments': [{'number': 1, 'size': 512,
'sha256': '076a27c79e5ace2a3d47f9dd2e83e4ff6ea8872b3c2218f66c92b89b55f36560',
'file_offsets': {'start': 0, 'end': 512}, 'image_offsets': {'start': 2560, 'end': 3072}}]}
assert sc_meta['files'][3]['original']['type'] == 'filler'
assert sc_meta['files'][3]['original']['path'] == 'random'
assert sc_meta['files'][3]['original']['size'] == 512
assert len(sc_meta['files'][3]['fragments']) == 1
assert sc_meta['files'][3]['fragments'][0]['number'] == 1
assert sc_meta['files'][3]['fragments'][0]['size'] == 512
assert sc_meta['files'][3]['fragments'][0]['file_offsets'] == {'start': 0, 'end': 512}
assert sc_meta['files'][3]['fragments'][0]['image_offsets'] == {'start': 5120, 'end': 5632}
os.remove(image_path)
os.remove(metadata_path)
def test_that_invalid_fragmentation_points_raise_an_error(self, fragmentation_points, path_test_file_4k):
f = File(path_test_file_4k)
with pytest.raises(InvalidFragmentationPointError):
f.fragment(fragmentation_points)
def test_that_a_too_small_file_cannot_be_fragmented(self, path_test_file_4k):
with pytest.raises(InvalidFragmentationPointError):
File(path_test_file_4k).fragment_randomly(2, File(path_test_file_4k).size * 2)
def test_that_an_error_is_raised_when_no_corpus_is_set(self, path_test_file_4k):
woodblock.file.corpus(None)
with pytest.raises(WoodblockError):
File(path_test_file_4k)
def test_that_the_correct_number_of_fragments_is_generated(self, num_fragments, path_test_file_4k):
frags = File(path_test_file_4k).fragment_evenly(num_fragments=num_fragments, block_size=512)
assert len(frags) == num_fragments
def test_that_max_fragments_raises_for_invalid_block_sizes(self, block_size, path_test_file_4k):
with pytest.raises(WoodblockError):
File(path_test_file_4k).max_fragments(block_size)
def test_that_the_correct_number_of_fragments_is_generated_for_2k_file(self, num_fragments, path_test_file_2000):
frags = File(path_test_file_2000).fragment_randomly(num_fragments=num_fragments, block_size=512)
assert len(frags) == num_fragments
def test_that_max_fragments_returns_correct_number(self, block_size, expected_frags, path_test_file_4k):
assert File(path_test_file_4k).max_fragments(block_size) == expected_frags
def test_that_an_empty_file_raises_an_error(self):
with NamedTemporaryFile() as tmp:
with pytest.raises(WoodblockError):
File(pathlib.Path(tmp.name))
def test_that_a_non_existing_file_raises_an_error(self):
with pytest.raises(FileNotFoundError):
File(pathlib.Path('/nonexisting'))
def test_that_all_fragments_have_the_same_id(self, num_fragments, path_test_file_4k):
frags = File(path_test_file_4k).fragment_evenly(num_fragments=num_fragments, block_size=512)
for i in range(len(frags)):
assert frags[i - 1].metadata['file']['id'] == frags[i].metadata['file']['id']
def test_that_the_file_is_split_evenly(self, block_size, num_fragments, expected_frag_offsets, path_test_file_4k):
frags = File(path_test_file_4k).fragment_evenly(num_fragments=num_fragments, block_size=block_size)
frag_offsets = tuple(itemgetter('start', 'end')(x.metadata['fragment']['file_offsets']) for x in frags)
assert frag_offsets == expected_frag_offsets
