def check_formatter_output(self, expected_strings: Iterable[str], delimiter: str = ' '):
sample_input = delimiter.join(expected_strings)
regexp = PrefixTree(expected_strings).to_regexp(self._Formatter)
output_strings = sorted(set(re.compile(regexp).findall(sample_input)))
self.assertEqual(
sorted(set(expected_strings)),
output_strings,
msg="Regexp: {}\nInput: '{}'".format(regexp, sample_input)
)
class PrefixTreeTest(TestCase):
def setUp(self):
self._tree = PrefixTree()
def test_correctly_encodes_strings_with_special_characters(self):
for input_string, expected_regexp in SPECIAL_CHARACTER_STRINGS.items():
with self.subTest(input_string=input_string):
tree = PrefixTree()
tree.add(input_string)
self.assertEqual(expected_regexp, tree._root_node.to_regexp())
@given(NON_EMPTY_TEXT_ITERABLES)
def test_accepts_individual_strings(self, expected_strings):
for string in expected_strings:
self._tree.add(string)
assert_strings_can_be_matched(self,
self._tree.to_regexp(PythonFormatter),
expected_strings)
@given(NON_EMPTY_TEXT_ITERABLES)
def test_accepts_iterable_of_strings(self, expected_strings):
self._tree.extend(expected_strings)
assert_strings_can_be_matched(self,
self._tree.to_regexp(PythonFormatter),
expected_strings)
@given(NON_EMPTY_TEXT_ITERABLES)
def test_can_be_instantiated_with_initial_iterable_of_strings(
self, expected_strings):
self._tree = PrefixTree(expected_strings)
assert_strings_can_be_matched(self,
self._tree.to_regexp(PythonFormatter),
expected_strings)
def test_it_ignores_empty_strings(self):
tree = PrefixTree([''])
self.assertEqual(PythonFormatter._EMPTY_STRING_MATCH,
tree.to_regexp(PythonFormatter))
def check_formatter_output_matches_empty_string(self):
regexp = PrefixTree([]).to_regexp(self._Formatter)
output_word = re.compile(regexp).findall('')
self.assertListEqual([''], output_word)
def test_it_ignores_empty_strings(self):
tree = PrefixTree([''])
self.assertEqual(PythonFormatter._EMPTY_STRING_MATCH,
tree.to_regexp(PythonFormatter))
def test_can_be_instantiated_with_initial_iterable_of_strings(
self, expected_strings):
self._tree = PrefixTree(expected_strings)
assert_strings_can_be_matched(self,
self._tree.to_regexp(PythonFormatter),
expected_strings)
def test_correctly_encodes_strings_with_special_characters(self):
for input_string, expected_regexp in SPECIAL_CHARACTER_STRINGS.items():
with self.subTest(input_string=input_string):
tree = PrefixTree()
tree.add(input_string)
self.assertEqual(expected_regexp, tree._root_node.to_regexp())
def setUp(self):
self._tree = PrefixTree()
def iterable_to_regexp(
iterable: Iterable[str],
formatter: Type[BaseFormatter] = PythonFormatter) -> str:
return PrefixTree(iterable).to_regexp(formatter)
def stream_to_regexp(stream: TextIO,
formatter: Type[BaseFormatter] = PythonFormatter) -> str:
lines_generator = (line for line in stream.read().split(os.linesep)
if line)
prefix_tree = PrefixTree(lines_generator)
return prefix_tree.to_regexp(formatter)