class TransitionMatchedWordConcordanceIndex(ConcordanceIndex):
def __init__(self, word_list):
self._offsets = HierarchicalIndex(3)
for index, word in enumerate(word_list):
if isinstance(word, UnparsableWordBinding):
continue
syntactic_category = word.root.syntactic_category
secondary_syntactic_category = word.root.secondary_syntactic_category
for suffix in word.suffixes:
syntactic_category = suffix.to_syntactic_category
if isinstance(suffix, DerivationalSuffixBinding):
secondary_syntactic_category = None
self._offsets.insert(index, suffix.matched_word,
syntactic_category,
secondary_syntactic_category)
def offsets(self,
word_str,
syntactic_category=None,
secondary_syntactic_category=None):
assert word_str is not None
if secondary_syntactic_category:
assert syntactic_category is not None
args = [word_str, syntactic_category, secondary_syntactic_category]
args = filter(lambda x: x is not None, args)
return self._offsets.get(*args)
class CompleteWordConcordanceIndex(ConcordanceIndex):
def __init__(self, word_list):
self._offsets = HierarchicalIndex(3)
for index, word in enumerate(word_list):
if isinstance(word, UnparsableWordBinding):
continue
self._offsets.insert(index, word.str, word.syntactic_category,
word.secondary_syntactic_category)
def offsets(self,
word_str,
syntactic_category=None,
secondary_syntactic_category=None):
assert word_str is not None
if secondary_syntactic_category:
assert syntactic_category is not None
args = [word_str, syntactic_category, secondary_syntactic_category]
args = filter(lambda x: x is not None, args)
return self._offsets.get(*args)
def test_index_should_validate_depth_in_operations(self):
# depth=2
idx = HierarchicalIndex(2)
assert_that(idx.get('A'), has_length(0))
assert_that(idx.get('A', 'X'), has_length(0))
self.assertRaises(AssertionError, lambda: idx.get('A', 'X', 'i'))
self.assertRaises(AssertionError, lambda: idx.insert(1))
self.assertRaises(AssertionError, lambda: idx.insert(1, 'A'))
idx.insert(1, 'A', 'X') # should not raise anything
self.assertRaises(AssertionError, lambda: idx.insert(1, 'A', 'X', 'i'))
assert_that(idx.get('A', 'X'), equal_to([1]))
# depth=3
idx = HierarchicalIndex(3)
assert_that(idx.get('A'), has_length(0))
assert_that(idx.get('A', 'X'), has_length(0))
assert_that(idx.get('A', 'X', 'i'), has_length(0))
self.assertRaises(AssertionError, lambda: idx.get('A', 'X', 'i', '1'))
self.assertRaises(AssertionError, lambda: idx.insert(1))
self.assertRaises(AssertionError, lambda: idx.insert(1, 'A'))
self.assertRaises(AssertionError, lambda: idx.insert(1, 'A', 'X'))
idx.insert(1, 'A', 'X', 'i') # should not raise anything
self.assertRaises(AssertionError,
lambda: idx.insert(1, 'A', 'X', 'i', 'a'))
assert_that(idx.get('A', 'X', 'i'), equal_to([1]))
# depth=N
N = 100
idx = HierarchicalIndex(N)
for i in range(1, N + 1):
assert_that(
idx.get(*range(0, i)), has_length(0)
) # try calling idx.get(0,0,0,0.....0) with N items at last iteration
self.assertRaises(AssertionError, lambda: idx.get(*range(0, N + 1)))
for i in range(1, N):
self.assertRaises(AssertionError,
lambda: idx.insert(1, *range(0, i)))
idx.insert(1, *range(0, N)) # should not raise anything
assert_that(idx.get(*range(0, N)), equal_to([1]))
def test_index_with_sample_case_for_depth_3(self):
idx = HierarchicalIndex(3)
# A
idx.insert(1, 'A', 'X', 'i')
idx.insert(2, 'A', 'X', 'ii')
idx.insert(3, 'A', 'X', 'ii')
idx.insert(4, 'A', 'Y', 'i')
idx.insert(5, 'A', 'Y', 'ii')
idx.insert(10, 'A', 'Z', 'ii')
idx.insert(11, 'A', 'Z', 'iii')
#B
idx.insert(6, 'B', 'X', 'ii')
idx.insert(7, 'B', 'X', 'iii')
idx.insert(8, 'B', 'Y', 'i')
#same queries with case for depth 2
assert_that(idx.get('A'), equal_to([1, 2, 3, 4, 5, 10, 11]))
assert_that(idx.get('A', 'Y'), equal_to([4, 5]))
assert_that(idx.get('B'), equal_to([6, 7, 8]))
assert_that(idx.get('B', 'X'), equal_to([6, 7]))
#new queries
assert_that(idx.get('B', 'X', 'ii'), equal_to([6]))
assert_that(idx.get('A', 'X', 'ii'), equal_to([2, 3]))
def test_index_with_sample_case_for_depth_2(self):
idx = HierarchicalIndex(2)
# A
idx.insert(1, 'A', 'X')
idx.insert(2, 'A', 'X')
idx.insert(3, 'A', 'X')
idx.insert(4, 'A', 'Y')
idx.insert(5, 'A', 'Y')
idx.insert(10, 'A', 'Z')
idx.insert(11, 'A', 'Z')
#B
idx.insert(6, 'B', 'X')
idx.insert(7, 'B', 'X')
idx.insert(8, 'B', 'Y')
assert_that(idx.get('A'), equal_to([1, 2, 3, 4, 5, 10, 11]))
assert_that(idx.get('A', 'Y'), equal_to([4, 5]))
assert_that(idx.get('B'), equal_to([6, 7, 8]))
assert_that(idx.get('B', 'X'), equal_to([6, 7]))
def test_index_should_validate_depth_in_operations(self):
# depth=2
idx = HierarchicalIndex(2)
assert_that(idx.get('A'), has_length(0))
assert_that(idx.get('A', 'X'), has_length(0))
self.assertRaises(AssertionError, lambda: idx.get('A', 'X', 'i'))
self.assertRaises(AssertionError, lambda: idx.insert(1))
self.assertRaises(AssertionError, lambda: idx.insert(1, 'A'))
idx.insert(1, 'A', 'X') # should not raise anything
self.assertRaises(AssertionError, lambda: idx.insert(1, 'A', 'X', 'i'))
assert_that(idx.get('A', 'X'), equal_to([1]))
# depth=3
idx = HierarchicalIndex(3)
assert_that(idx.get('A'), has_length(0))
assert_that(idx.get('A', 'X'), has_length(0))
assert_that(idx.get('A', 'X', 'i'), has_length(0))
self.assertRaises(AssertionError, lambda: idx.get('A', 'X', 'i', '1'))
self.assertRaises(AssertionError, lambda: idx.insert(1))
self.assertRaises(AssertionError, lambda: idx.insert(1, 'A'))
self.assertRaises(AssertionError, lambda: idx.insert(1, 'A', 'X'))
idx.insert(1, 'A', 'X', 'i') # should not raise anything
self.assertRaises(AssertionError, lambda: idx.insert(1, 'A', 'X', 'i', 'a'))
assert_that(idx.get('A', 'X', 'i'), equal_to([1]))
# depth=N
N = 100
idx = HierarchicalIndex(N)
for i in range(1, N + 1):
assert_that(idx.get(*range(0, i)), has_length(0)) # try calling idx.get(0,0,0,0.....0) with N items at last iteration
self.assertRaises(AssertionError, lambda: idx.get(*range(0, N + 1)))
for i in range(1, N):
self.assertRaises(AssertionError, lambda: idx.insert(1, *range(0, i)))
idx.insert(1, *range(0, N)) # should not raise anything
assert_that(idx.get(*range(0, N)), equal_to([1]))
def test_index_with_sample_case_for_depth_3(self):
idx = HierarchicalIndex(3)
# A
idx.insert(1, 'A', 'X', 'i')
idx.insert(2, 'A', 'X', 'ii')
idx.insert(3, 'A', 'X', 'ii')
idx.insert(4, 'A', 'Y', 'i')
idx.insert(5, 'A', 'Y', 'ii')
idx.insert(10, 'A', 'Z', 'ii')
idx.insert(11, 'A', 'Z', 'iii')
#B
idx.insert(6, 'B', 'X', 'ii')
idx.insert(7, 'B', 'X', 'iii')
idx.insert(8, 'B', 'Y', 'i')
#same queries with case for depth 2
assert_that(idx.get('A'), equal_to([1, 2, 3, 4, 5, 10, 11]))
assert_that(idx.get('A', 'Y'), equal_to([4, 5]))
assert_that(idx.get('B'), equal_to([6, 7, 8]))
assert_that(idx.get('B', 'X'), equal_to([6, 7]))
#new queries
assert_that(idx.get('B', 'X', 'ii'), equal_to([6]))
assert_that(idx.get('A', 'X', 'ii'), equal_to([2, 3]))
def test_index_with_sample_case_for_depth_2(self):
idx = HierarchicalIndex(2)
# A
idx.insert(1, 'A', 'X')
idx.insert(2, 'A', 'X')
idx.insert(3, 'A', 'X')
idx.insert(4, 'A', 'Y')
idx.insert(5, 'A', 'Y')
idx.insert(10, 'A', 'Z')
idx.insert(11, 'A', 'Z')
#B
idx.insert(6, 'B', 'X')
idx.insert(7, 'B', 'X')
idx.insert(8, 'B', 'Y')
assert_that(idx.get('A'), equal_to([1, 2, 3, 4, 5, 10, 11]))
assert_that(idx.get('A', 'Y'), equal_to([4, 5]))
assert_that(idx.get('B'), equal_to([6, 7, 8]))
assert_that(idx.get('B', 'X'), equal_to([6, 7]))