def test_with_fuzzy_string_transpose(self):
x1 = TokenSet.from_string("abr")
x2 = TokenSet.from_string("bra")
x3 = TokenSet.from_string("foo")
y = TokenSet.from_fuzzy_string("bar", 1)
assert x1.intersect(y).to_list() == ["abr"]
assert x2.intersect(y).to_list() == ["bra"]
assert x3.intersect(y).to_list() == []
def test_with_fuzzy_string_deletion(self):
x1 = TokenSet.from_string("ar")
x2 = TokenSet.from_string("br")
x3 = TokenSet.from_string("ba")
x4 = TokenSet.from_string("bar")
x5 = TokenSet.from_string("foo")
y = TokenSet.from_fuzzy_string("bar", 1)
assert x1.intersect(y).to_list() == ["ar"]
assert x2.intersect(y).to_list() == ["br"]
assert x3.intersect(y).to_list() == ["ba"]
assert x4.intersect(y).to_list() == ["bar"]
assert x5.intersect(y).to_list() == []
def test_with_fuzzy_string_substitution(self):
x1 = TokenSet.from_string("bar")
x2 = TokenSet.from_string("cur")
x3 = TokenSet.from_string("cat")
x4 = TokenSet.from_string("car")
x5 = TokenSet.from_string("foo")
y = TokenSet.from_fuzzy_string("car", 1)
assert x1.intersect(y).to_list() == ["bar"]
assert x2.intersect(y).to_list() == ["cur"]
assert x3.intersect(y).to_list() == ["cat"]
assert x4.intersect(y).to_list() == ["car"]
assert x5.intersect(y).to_list() == []
def test_with_fuzzy_string_insertion(self):
x1 = TokenSet.from_string("bbar")
x2 = TokenSet.from_string("baar")
x3 = TokenSet.from_string("barr")
x4 = TokenSet.from_string("bar")
x5 = TokenSet.from_string("ba")
x6 = TokenSet.from_string("foo")
x7 = TokenSet.from_string("bara")
y = TokenSet.from_fuzzy_string("bar", 1)
assert x1.intersect(y).to_list() == ["bbar"]
assert x2.intersect(y).to_list() == ["baar"]
assert x3.intersect(y).to_list() == ["barr"]
assert x4.intersect(y).to_list() == ["bar"]
assert x5.intersect(y).to_list() == ["ba"]
assert x6.intersect(y).to_list() == []
assert x7.intersect(y).to_list() == ["bara"]
def test_catastrophic_backtracking_with_leading_characters(self):
x = TokenSet.from_string("f" * 100)
y = TokenSet.from_string("*f")
assert len(x.intersect(y).to_list()) == 1
def test_contained_wildcard_backtracking_no_intersection(self):
x = TokenSet.from_string("ababc")
y = TokenSet.from_string("a*ac")
assert x.intersect(y).to_list() == []
def test_leading_wildcard_backtracking_no_intersection(self):
x = TokenSet.from_string("aaacbab")
y = TokenSet.from_string("*abc")
assert x.intersect(y).to_list() == []
def test_fuzzy_string_transpose(self):
x = TokenSet.from_string("bca")
y = TokenSet.from_fuzzy_string("abc", 2)
assert x.intersect(y).to_list() == ["bca"]
def test_leading_wildcard_intersection(self):
x = TokenSet.from_string("cat")
y = TokenSet.from_string("*t")
z = x.intersect(y)
assert {"cat"} == set(z.to_list())
def test_no_intersection(self):
x = TokenSet.from_string("cat")
y = TokenSet.from_string("bar")
z = x.intersect(y)
assert len(z.to_list()) == 0
def test_from_string_with_trailing_wildcard(self):
x = TokenSet.from_string("a*")
wild = x.edges["a"].edges["*"]
assert wild == wild.edges["*"]
assert wild.final
def test_wildcard_zero_or_more_characters(self):
x = TokenSet.from_string("foo")
y = TokenSet.from_string("foo*")
z = x.intersect(y)
assert {"foo"} == set(z.to_list())
def test_contained_wildcard_no_intersection(self):
x = TokenSet.from_string("foo")
y = TokenSet.from_string("b*r")
z = x.intersect(y)
assert len(z.to_list()) == 0
def test_contained_wildcard_intersection(self):
x = TokenSet.from_string("foo")
y = TokenSet.from_string("f*o")
z = x.intersect(y)
assert {"foo"} == set(z.to_list())
def test_leading_wildcard_no_intersection(self):
x = TokenSet.from_string("cat")
y = TokenSet.from_string("*r")
z = x.intersect(y)
assert len(z.to_list()) == 0
def test_leading_atrailing_wildcard_backtracking_intersection(self):
x = TokenSet.from_string("acbaabab")
y = TokenSet.from_string("a*ba*b")
assert x.intersect(y).to_list() == ["acbaabab"]
def test_from_string_without_wildcard(self):
TokenSet._next_id = 1
x = TokenSet.from_string("a")
assert str(x) == "0a2"
assert x.edges["a"].final
def test_fuzzy_string_substitution(self):
x = TokenSet.from_string("axx")
y = TokenSet.from_fuzzy_string("abc", 2)
assert x.intersect(y).to_list() == ["axx"]
def test_to_list_includes_single_words(self):
word = "bat"
token_set = TokenSet.from_string(word)
assert {word} == set(token_set.to_list())
def test_fuzzy_string_deletion(self):
x = TokenSet.from_string("a")
y = TokenSet.from_fuzzy_string("abc", 2)
assert x.intersect(y).to_list() == ["a"]
def test_builds_a_token_set_for_the_corpus(self):
needle = TokenSet.from_string("test")
assert "test" in self.builder.token_set.intersect(needle).to_list()
def test_simple_intersection(self):
x = TokenSet.from_string("cat")
y = TokenSet.from_string("cat")
z = x.intersect(y)
assert {"cat"} == set(z.to_list())