def test_find_not_existing(self):
self.assertIsNone(find_slice_beg([1, 2, 3, 4, 5], slice_to_find=[]))
self.assertIsNone(find_slice_beg([1, 2, 3, 4, 5], slice_to_find=[5,
6]))
self.assertIsNone(find_slice_beg([1, 2, 3, 4, 5], slice_to_find=[7,
8]))
self.assertIsNone(find_slice_beg([1, 2, 3, 4, 5], slice_to_find=[1,
3]))
def test_find_all(self):
self.assertEqual([0],
find_slice_beg([1, 2, 3, 4, 5],
slice_to_find=[1],
find_all=True))
self.assertEqual([2],
find_slice_beg([1, 2, 3, 4, 5],
slice_to_find=[3],
find_all=True))
self.assertEqual([4],
find_slice_beg([1, 2, 3, 4, 5],
slice_to_find=[5],
find_all=True))
self.assertEqual([0, 2, 4],
find_slice_beg([1, 2, 1, 4, 1],
slice_to_find=[1],
find_all=True))
self.assertEqual([],
find_slice_beg([1, 2, 3, 4, 5],
slice_to_find=[],
find_all=True))
self.assertEqual([],
find_slice_beg([1, 2, 3, 4, 5],
slice_to_find=[6],
find_all=True))
self.assertEqual([],
find_slice_beg([1, 2, 3, 4, 5],
slice_to_find=[6, 7],
find_all=True))
def _find_all_introducers(self, source: List[str]):
found_introducers = []
for introducer in self.introducers:
introducer = split_on_special_characters(
introducer, preserve_special_characters=True)
found_indexes = find_slice_beg(source,
slice_to_find=introducer,
find_all=True,
case_insensitive=True)
found_introducers.extend([(idx, introducer)
for idx in found_indexes])
found_introducers.sort(key=lambda idx_introducer: idx_introducer[0])
return found_introducers
def test_find_single_elem(self):
self.assertEqual(0,
find_slice_beg([1, 2, 3, 4, 5], slice_to_find=[1, 2]))
self.assertEqual(1,
find_slice_beg([1, 2, 3, 4, 5], slice_to_find=[2, 3]))
self.assertEqual(2,
find_slice_beg([1, 2, 3, 4, 5], slice_to_find=[3, 4]))
self.assertEqual(3,
find_slice_beg([1, 2, 3, 4, 5], slice_to_find=[4, 5]))
self.assertEqual(0, find_slice_beg([1, 2, 3, 4, 5], slice_to_find=[1]))
self.assertEqual(4, find_slice_beg([1, 2, 3, 4, 5], slice_to_find=[5]))
self.assertEqual(
0, find_slice_beg([1, 2, 3, 4, 5], slice_to_find=[1, 2, 3, 4, 5]))
def _test_first_word_of_sentence_helper(self, sentence, analysis_subject,
expected_result):
source = split_on_special_characters(sentence,
preserve_special_characters=True)
analysis_subject = split_on_special_characters(
analysis_subject, preserve_special_characters=True)
slice_beg = find_slice_beg(source, slice_to_find=analysis_subject)
assert slice_beg is not None
slice_end = slice_beg + len(analysis_subject)
match = AddressMatch(
source=source,
match_slice_position=(slice_beg, slice_end),
location='' # doesn't matter
)
assert match.matched_phrase == ' '.join(analysis_subject)
ctx_analyser = FirstWordOfSentenceContext()
self.assertEqual(ctx_analyser(match), expected_result)
negated_ctx_analyser = FirstWordOfSentenceContext(negate=True)
self.assertEqual(negated_ctx_analyser(match), not expected_result)
def test_find_case_insensitive(self):
self.assertIsNotNone(
find_slice_beg(["Nieopodal"],
slice_to_find=["nieopodal"],
case_insensitive=True))