def test_set_operations(self):
"""Test advanced set operations"""
items1 = set(["abcde", "cdefg", "fghijk", "ijklm"])
items2 = set(["cdefg", "lmnop"])
idx1 = NGram(items1)
idx2 = NGram(items2)
results = lambda L: sorted(x[0] for x in L)
# Item removal
self.assertEqual(results(idx1.search('cde')), ["abcde","cdefg"])
idx1.remove('abcde')
self.assertEqual(results(idx1.search('cde')), ["cdefg"])
# Set intersection operation
items1.remove('abcde')
idx1.intersection_update(idx2)
self.assertEqual(idx1, items1.intersection(items2))
self.assertEqual(results(idx1.search('lmn')), [])
self.assertEqual(results(idx1.search('ijk')), [])
self.assertEqual(results(idx1.search('def')), ['cdefg'])
def test_set_operations(self):
"""Test advanced set operations"""
items1 = set(["abcde", "cdefg", "fghijk", "ijklm"])
items2 = set(["cdefg", "lmnop"])
idx1 = NGram(items1)
idx2 = NGram(items2)
results = lambda L: sorted(x[0] for x in L)
# Item removal
self.assertEqual(results(idx1.search('cde')), ["abcde", "cdefg"])
idx1.remove('abcde')
self.assertEqual(results(idx1.search('cde')), ["cdefg"])
# Set intersection operation
items1.remove('abcde')
idx1.intersection_update(idx2)
self.assertEqual(idx1, items1.intersection(items2))
self.assertEqual(results(idx1.search('lmn')), [])
self.assertEqual(results(idx1.search('ijk')), [])
self.assertEqual(results(idx1.search('def')), ['cdefg'])
def ngram(w1, w2, n):
"""
ngram distance
"""
pad = lambda x : "#{}#".format(x)
w1, w2 = pad(w1), pad(w2)
g1 = [w1[i:i+n] for i in range(len(w1)-n+1)]
g2 = [w2[i:i+n] for i in range(len(w2)-n+1)]
# compute ngram similarity
# d(a, b) = |a| + |b| + 2|a intersection b|
n = NGram(g1)
n.intersection_update(g2)
d = len(g1) + len(g2) - 2 * len(list(n))
return d