class ExpectedShaTests(TestCase):
def setUp(self):
super(ExpectedShaTests, self).setUp()
self.obj = Blob()
self.obj.data = b"foo"
def test_none(self):
_check_expected_sha(None, self.obj)
def test_hex(self):
_check_expected_sha(self.obj.sha().hexdigest().encode('ascii'),
self.obj)
self.assertRaises(AssertionError, _check_expected_sha, b"0" * 40,
self.obj)
def test_binary(self):
_check_expected_sha(self.obj.sha().digest(), self.obj)
self.assertRaises(AssertionError, _check_expected_sha, b"x" * 20,
self.obj)
def test_normalize_to_lf_no_op(self):
base_content = b"line1\nline2"
base_sha = "f8be7bb828880727816015d21abcbc37d033f233"
base_blob = Blob()
base_blob.set_raw_string(base_content)
self.assertEqual(base_blob.as_raw_chunks(), [base_content])
self.assertEqual(base_blob.sha().hexdigest(), base_sha)
filtered_blob = normalize_blob(base_blob,
convert_crlf_to_lf,
binary_detection=False)
self.assertEqual(filtered_blob.as_raw_chunks(), [base_content])
self.assertEqual(filtered_blob.sha().hexdigest(), base_sha)
def test_normalize_to_crlf_no_op(self):
base_content = b"line1\r\nline2"
base_sha = "3a1bd7a52799fe5cf6411f1d35f4c10bacb1db96"
base_blob = Blob()
base_blob.set_raw_string(base_content)
self.assertEqual(base_blob.as_raw_chunks(), [base_content])
self.assertEqual(base_blob.sha().hexdigest(), base_sha)
filtered_blob = normalize_blob(base_blob,
convert_lf_to_crlf,
binary_detection=False)
self.assertEqual(filtered_blob.as_raw_chunks(), [base_content])
self.assertEqual(filtered_blob.sha().hexdigest(), base_sha)
def test_normalize_to_crlf_binary(self):
base_content = b"line1\r\nline2\0"
base_sha = "b44504193b765f7cd79673812de8afb55b372ab2"
base_blob = Blob()
base_blob.set_raw_string(base_content)
self.assertEqual(base_blob.as_raw_chunks(), [base_content])
self.assertEqual(base_blob.sha().hexdigest(), base_sha)
filtered_blob = normalize_blob(base_blob,
convert_lf_to_crlf,
binary_detection=True)
self.assertEqual(filtered_blob.as_raw_chunks(), [base_content])
self.assertEqual(filtered_blob.sha().hexdigest(), base_sha)
def test_normalize_to_lf_no_op(self):
base_content = b"line1\nline2"
base_sha = "f8be7bb828880727816015d21abcbc37d033f233"
base_blob = Blob()
base_blob.set_raw_string(base_content)
self.assertEqual(base_blob.as_raw_chunks(), [base_content])
self.assertEqual(base_blob.sha().hexdigest(), base_sha)
filtered_blob = normalize_blob(
base_blob, convert_crlf_to_lf, binary_detection=False
)
self.assertEqual(filtered_blob.as_raw_chunks(), [base_content])
self.assertEqual(filtered_blob.sha().hexdigest(), base_sha)
def test_normalize_to_crlf_binary(self):
base_content = b"line1\r\nline2\0"
base_sha = "b44504193b765f7cd79673812de8afb55b372ab2"
base_blob = Blob()
base_blob.set_raw_string(base_content)
self.assertEqual(base_blob.as_raw_chunks(), [base_content])
self.assertEqual(base_blob.sha().hexdigest(), base_sha)
filtered_blob = normalize_blob(
base_blob, convert_lf_to_crlf, binary_detection=True
)
self.assertEqual(filtered_blob.as_raw_chunks(), [base_content])
self.assertEqual(filtered_blob.sha().hexdigest(), base_sha)
def test_normalize_to_crlf_no_op(self):
base_content = b"line1\r\nline2"
base_sha = "3a1bd7a52799fe5cf6411f1d35f4c10bacb1db96"
base_blob = Blob()
base_blob.set_raw_string(base_content)
self.assertEqual(base_blob.as_raw_chunks(), [base_content])
self.assertEqual(base_blob.sha().hexdigest(), base_sha)
filtered_blob = normalize_blob(
base_blob, convert_lf_to_crlf, binary_detection=False
)
self.assertEqual(filtered_blob.as_raw_chunks(), [base_content])
self.assertEqual(filtered_blob.sha().hexdigest(), base_sha)
def inventory_to_tree_and_blobs(repo, mapping, revision_id):
stack = []
cur = ""
tree = Tree()
inv = repo.get_inventory(revision_id)
for path, entry in inv.iter_entries():
while stack and not path.startswith(cur):
tree.serialize()
sha = tree.sha().hexdigest()
yield sha, tree
t = (stat.S_IFDIR, splitpath(cur)[-1:][0].encode('UTF-8'), sha)
cur, tree = stack.pop()
tree.add(*t)
if type(entry) == InventoryDirectory:
stack.append((cur, tree))
cur = path
tree = Tree()
if type(entry) == InventoryFile:
#FIXME: We can make potentially make this Lazy to avoid shaing lots of stuff
# and having all these objects in memory at once
blob = Blob()
_, blob._text = repo.iter_files_bytes([(entry.file_id, revision_id,
path)]).next()
sha = blob.sha().hexdigest()
yield sha, blob
name = splitpath(path)[-1:][0].encode('UTF-8')
mode = stat.S_IFREG | 0644
if entry.executable:
mode |= 0111
tree.add(mode, name, sha)
while len(stack) > 1:
tree.serialize()
sha = tree.sha().hexdigest()
yield sha, tree
t = (stat.S_IFDIR, splitpath(cur)[-1:][0].encode('UTF-8'), sha)
cur, tree = stack.pop()
tree.add(*t)
tree.serialize()
yield tree.sha().hexdigest(), tree
def inventory_to_tree_and_blobs(repo, mapping, revision_id):
stack = []
cur = ""
tree = Tree()
inv = repo.get_inventory(revision_id)
for path, entry in inv.iter_entries():
while stack and not path.startswith(cur):
tree.serialize()
sha = tree.sha().hexdigest()
yield sha, tree
t = (stat.S_IFDIR, splitpath(cur)[-1:][0].encode('UTF-8'), sha)
cur, tree = stack.pop()
tree.add(*t)
if type(entry) == InventoryDirectory:
stack.append((cur, tree))
cur = path
tree = Tree()
if type(entry) == InventoryFile:
#FIXME: We can make potentially make this Lazy to avoid shaing lots of stuff
# and having all these objects in memory at once
blob = Blob()
_, blob._text = repo.iter_files_bytes([(entry.file_id, revision_id, path)]).next()
sha = blob.sha().hexdigest()
yield sha, blob
name = splitpath(path)[-1:][0].encode('UTF-8')
mode = stat.S_IFREG | 0644
if entry.executable:
mode |= 0111
tree.add(mode, name, sha)
while len(stack) > 1:
tree.serialize()
sha = tree.sha().hexdigest()
yield sha, tree
t = (stat.S_IFDIR, splitpath(cur)[-1:][0].encode('UTF-8'), sha)
cur, tree = stack.pop()
tree.add(*t)
tree.serialize()
yield tree.sha().hexdigest(), tree
def test_normalize_to_crlf(self):
base_content = b"line1\nline2"
base_sha = "f8be7bb828880727816015d21abcbc37d033f233"
base_blob = Blob()
base_blob.set_raw_string(base_content)
self.assertEqual(base_blob.as_raw_chunks(), [base_content])
self.assertEqual(base_blob.sha().hexdigest(), base_sha)
filtered_blob = normalize_blob(base_blob,
convert_lf_to_crlf,
binary_detection=False)
normalized_content = b"line1\r\nline2"
normalized_sha = "3a1bd7a52799fe5cf6411f1d35f4c10bacb1db96"
self.assertEqual(filtered_blob.as_raw_chunks(), [normalized_content])
self.assertEqual(filtered_blob.sha().hexdigest(), normalized_sha)
def test_normalize_to_crlf(self):
base_content = b"line1\nline2"
base_sha = "f8be7bb828880727816015d21abcbc37d033f233"
base_blob = Blob()
base_blob.set_raw_string(base_content)
self.assertEqual(base_blob.as_raw_chunks(), [base_content])
self.assertEqual(base_blob.sha().hexdigest(), base_sha)
filtered_blob = normalize_blob(
base_blob, convert_lf_to_crlf, binary_detection=False
)
normalized_content = b"line1\r\nline2"
normalized_sha = "3a1bd7a52799fe5cf6411f1d35f4c10bacb1db96"
self.assertEqual(filtered_blob.as_raw_chunks(), [normalized_content])
self.assertEqual(filtered_blob.sha().hexdigest(), normalized_sha)
