def test_slice_start_from_space(self):
offff = 20
txt = ' ' * offff + '''основании Устава, с одной стороны, и Фонд «Благо»'''
tm = TextMap(txt)
print(tm.map[0])
print(tm.tokens[11])
print(tm.map[11])
# print(f'[{doc.tokens_map.text}]')
print(f'[{tm.text}]')
print(len(tm))
tm_sliced = tm.slice(slice(0, len(tm)))
print('span-0')
print(tm.map[0])
print(tm_sliced.map[0])
self.assertEqual(len(tm), len(tm_sliced))
self.assertEqual(tm.map[0], tm_sliced.map[0])
for c in range(len(tm.tokens[0])):
print(c)
self.assertEqual(0, tm.token_index_by_char(c))
self.assertEqual(0, tm_sliced.token_index_by_char(c))
self.assertEqual(tm.text, tm_sliced.text)
self.assertEqual(0, tm.token_index_by_char(0))
def test_tokens_in_range(self):
text = 'мама'
tm = TextMap(text)
self.assertEqual(0, tm.token_index_by_char(0))
self.assertEqual(0, tm.token_index_by_char(1))
self.assertEqual(0, tm.token_index_by_char(2))
self.assertEqual(0, tm.token_index_by_char(3))
text = 'мама выла папу'
tm = TextMap(text)
self.assertEqual(1, tm.token_index_by_char(5))
self.assertEqual(1, tm.token_index_by_char(6))
self.assertEqual(1, tm.token_index_by_char(7))
self.assertEqual(1, tm.token_index_by_char(8))
self.assertEqual(2, tm.token_index_by_char(9))
self.assertEqual(1, tm.token_index_by_char(4))
def test_tokens_in_range_start_from_space(self):
text = ' мама'
tm = TextMap(text)
self.assertEqual(1, tm.map[0][0])
self.assertEqual(0, tm.token_index_by_char(0))
txt = ' ' * 20 + '''основании Устава, с одной стороны, и Фонд «Благо»'''
# tm = TextMap(txt)
doc = LegalDocument(txt).parse()
tm = doc.tokens_map
print(tm.map[0])
print(tm.tokens[11])
print(tm.map[11])
print(f'[{doc.tokens_map.text}]')
print(f'[{doc.text}]')
def test_slice(self):
text = 'этилен мама ಶ್ರೀರಾಮ'
tm = TextMap(text)
tm2: TextMap = tm.slice(slice(1, 2))
self.assertEqual(tm2[0], 'мама')
self.assertEqual(tm2.text, 'мама')
tm3 = tm2.slice(slice(0, 1))
self.assertEqual(tm3[0], 'мама')
self.assertEqual(0, tm.token_index_by_char(1))
self.assertEqual(0, tm2.token_index_by_char(1))
self.assertEqual(0, tm3.token_index_by_char(1))
self.assertEqual('мама', tm3.text)
self.assertEqual('мама', tm3.text_range([0, 1]))
self.assertEqual('мама', tm3.text_range([0, 2]))
