def setUp(self):
self.expr = '\w+'
self.prefix = r'\b'
self.suffix = r'\b'
self.rule_data = {'re': self.expr, 'flags': 'I'}
self.rule = RegularExpressionRule(None,
{ 'prefix': self.prefix,
'suffix': self.suffix },
self.rule_data, DEFAULT_FLAGS, {})
self.text = u'Some text\n with spaces\nи другими символами'
class TestRegularExpressionRule(unittest.TestCase):
def setUp(self):
self.expr = '\w+'
self.prefix = r'\b'
self.suffix = r'\b'
self.rule_data = {'re': self.expr, 'flags': 'I'}
self.rule = RegularExpressionRule(None,
{ 'prefix': self.prefix,
'suffix': self.suffix },
self.rule_data, DEFAULT_FLAGS, {})
self.text = u'Some text\n with spaces\nи другими символами'
def test_itermatches(self):
x = list(self.rule.itermatches(self.text))
self.assertEqual(len(x), 1)
pattern, matches = x[0]
flags = process_flags(self.rule_data['flags'], DEFAULT_FLAGS)
self.assertEqual(pattern['original'], self.expr)
self.assertEqual(pattern['compiled'],
re.compile(self.prefix + self.expr + self.suffix, flags))
matches_list = list(matches)
self.assertEqual(len(matches_list), 7)
self.assertEqual(matches_list[0], (0, 4))
self.assertEqual(matches_list[1], (5, 9))
self.assertEqual(matches_list[2], (14, 18))
self.assertEqual(matches_list[3], (19, 25))
self.assertEqual(matches_list[4], (26, 27))
self.assertEqual(matches_list[5], (28, 35))
self.assertEqual(matches_list[6], (36, 45))
def test_process(self):
result = self.rule.process(self.text)
self.assertEqual(result.lines,
dict(enumerate(self.text.splitlines(), 1)))
self.assertEqual(result.pattern_matches,
{
self.expr: {
1: [1, [(0, 4), (5, 9)]],
2: [1, [(4, 8), (9, 15)]],
3: [1, [(0, 1), (2, 9), (10, 19)]]
}
}
)
