def similarity(self, other):
if self.sha == other.sha:
return 1.0
if self._is_binary:
if self.binary == other.binary:
return 1.0
else:
return 0.0
return similarity(self.binary, other.binary)
def test_string_similarity(self):
base = '\n'.join([str(i) for i in range(0, 10)])
other = base
EPS = 0.0001
for i in range(0, 10):
other = other.replace(str(i), '*')
sim = similarity(base, other)
self.assertGreater((10 - i) / 10.0, sim)
self.assertLessEqual((9 - i) / 10.0, sim + EPS)
def similarity(self, other):
if self.sha == other.sha:
return 1.0
if self._is_binary:
if self.binary == other.binary:
return 1.0
else:
return 0.0
return similarity(self.binary, other.binary)
def test_string_similarity(self):
base = '\n'.join([str(i) for i in range(0, 10)])
other = base
EPS = 0.0001
for i in range(0, 10):
other = other.replace(str(i), '*')
sim = similarity(base, other)
self.assertGreater((10 - i) / 10.0, sim)
self.assertLessEqual((9 - i) / 10.0, sim + EPS)
def similarity(self, other):
""" compares similarity for text blobs
returns: if binary content return 1 if equal 0 otherwise
if text content return 0.0-1.0 of % of equal lines
"""
if self.sha == other.sha:
return 1.0
if self._is_binary:
if self.bytes == other.bytes:
return 1.0
else:
return 0.0
return similarity(self.bytes, other.bytes)
def similarity(self, other):
""" compares similarity for text blobs
returns: if binary content return 1 if equal 0 otherwise
if text content return 0.0-1.0 of % of equal lines
"""
if self.sha == other.sha:
return 1.0
if self._is_binary:
if self.bytes == other.bytes:
return 1.0
else:
return 0.0
return similarity(self.bytes, other.bytes)
