def test_add_codepoints(self):
self.lgr.add_codepoints([c for c in range(0x0061, 0x007A + 1)] +
[0x0107] + [0x0137, 0x0138])
expected_output = [
RangeChar(0x061, 0x0061, 0x007A),
Char(0x0107),
RangeChar(0x0137, 0x0137, 0x0138)
]
self.assertEqual(expected_output, list(self.lgr.repertoire))
def test_is_prefix_of(self):
c = Char(0x002A)
s = CharBase.from_cp_or_sequence([0x002A, 0x002B])
r = RangeChar(0x002A, 0x002A, 0x002B)
self.assertTrue(c.is_prefix_of([0x002A]))
self.assertTrue(r.is_prefix_of([0x002A]))
self.assertTrue(c.is_prefix_of([0x002A, 0x002B]))
self.assertTrue(r.is_prefix_of([0x002A, 0x002B]))
self.assertTrue(s.is_prefix_of([0x002A, 0x002B]))
self.assertTrue(s.is_prefix_of([0x002A, 0x002B, 0x002C]))
self.assertFalse(c.is_prefix_of([0x002B]))
self.assertFalse(r.is_prefix_of([0x002B]))
self.assertFalse(s.is_prefix_of([0x002B, 0x002A]))
self.assertFalse(s.is_prefix_of([0x002A]))
self.assertFalse(s.is_prefix_of([0x002B]))
def test_as_index(self):
self.assertEqual(Char(0x002A).as_index(), 0x002A)
self.assertEqual(CharSequence((0x002A, 0x002B)).as_index(), 0x002A)
self.assertEqual(RangeChar(0x002A, 0x002A, 0x02C).as_index(), 0x002A)
self.assertEqual(
CharBase.from_cp_or_sequence(0x002A).as_index(), 0x002A)
self.assertEqual(
CharBase.from_cp_or_sequence([0x002A]).as_index(), 0x002A)
self.assertEqual(
CharBase.from_cp_or_sequence([0x002A, 0x002B]).as_index(), 0x002A)
def test_lgr_ranges(self):
self.lgr.add_range(0x0061, 0x0065)
self.lgr.add_range(0x0066, 0x0068)
__, result = compute_stats(self.lgr, {})
stats = self.STATS.copy()
stats['codepoint_number'] = 8
stats['range_number'] = 2
stats['largest_range'] = RangeChar(0x0061, 0x0061, 0x0065)
stats['largest_range_len'] = 5
self.assertDictEqual(result, {'description': 'Generate stats',
'stats': stats})
def test_lgr_wrong_range_char(self):
self.lgr.add_range(0x0060, 0x0063, force=True)
r = RangeChar(0x0060, 0x0060, 0x0063)
unidb = IDNADatabase(self.DEFAULT_UNICODE_VERSION)
self.lgr.unicode_database = unidb
_, result = rebuild_lgr(self.lgr, {'unidb': unidb})
errors = result.get('repertoire', {}).get(r, {'errors': []})['errors']
self.assertEqual(len(errors), 1)
self.assertIsInstance(errors[0], CharInvalidIdnaProperty)
self.assertDictEqual(result, {'description': 'Rebuilding LGR with Unicode version {}'.format(
self.DEFAULT_UNICODE_VERSION),
'repertoire': {r: {'errors': errors}}})
def test_iter(self):
self.cd.add_char([0x0010])
self.cd.add_range(0x0001, 0x000A)
self.cd.add_char([0x0000])
self.cd.add_char([0x0011, 0x0012])
self.cd.add_char([0x0013])
expected_output = [
Char(0x0000),
RangeChar(0x0001, 0x0001, 0x000A),
Char(0x0010),
CharSequence([0x0011, 0x0012]),
Char(0x0013),
]
self.assertEqual(list(self.cd), expected_output)
def test_len(self):
self.assertEqual(len(Char(0x002A)), 1)
self.assertEqual(len(CharBase.from_cp_or_sequence([0x002A, 0x002B])),
2)
self.assertEqual(len(RangeChar(0x002A, 0x002A, 0x002B)), 1)
def test_char_range(self):
char = Char(0x002A)
range_char = RangeChar(0x002A, 0x002A, 0x002B)
self.assertEqual(char, range_char)
self.assertEqual(char.__hash__(), range_char.__hash__())