def test_escape(self):
t1, t2 = self._tokenize(r'\[\n')
self.assertEqual(
(t1.type, t1.value),
(RegexTokenizer.TOK_CLASS, LitteralCharacterClass('[')))
self.assertEqual(
(t2.type, t2.value),
(RegexTokenizer.TOK_CLASS, LitteralCharacterClass('\n')))
def test_deadend(self):
rx = RegularExpression.concat(
RegularExpression.fromClass(LitteralCharacterClass(
self.t('<')[0])),
RegularExpression.fromClass(LitteralCharacterClass(
self.t('=')[0])))
rx.start()
rx.feed(self.t('<')[0]) # byte/char
self.assertFalse(rx.isDeadEnd())
def test_middle(self):
t1, t2, t3 = self._tokenize(
r's{symbol}e'.format(symbol=self.symbol[1]))
self.assertEqual(
(t1.type, t1.value),
(RegexTokenizer.TOK_CLASS, LitteralCharacterClass('s')))
self.assertEqual((t2.type, t2.value), self.symbol)
self.assertEqual(
(t3.type, t3.value),
(RegexTokenizer.TOK_CLASS, LitteralCharacterClass('e')))
def test_concat(self):
rx = RegularExpression.concat(
RegularExpression.fromClass(LitteralCharacterClass(
self.t('a')[0])),
RegularExpression.fromClass(LitteralCharacterClass(
self.t('b')[0])),
RegularExpression.fromClass(LitteralCharacterClass(
self.t('c')[0])))
self.assertTrue(rx.match(self.t('abc')))
self.assertFalse(rx.match(self.t('ab')))
def test_concat(self):
t1, t2, t3 = self._tokenize('abc')
self.assertEqual(
(t1.type, t1.value),
(RegexTokenizer.TOK_CLASS, LitteralCharacterClass('a')))
self.assertEqual(
(t2.type, t2.value),
(RegexTokenizer.TOK_CLASS, LitteralCharacterClass('b')))
self.assertEqual(
(t3.type, t3.value),
(RegexTokenizer.TOK_CLASS, LitteralCharacterClass('c')))
def test_closure(self):
t1, t2 = self._tokenize('a+')
self.assertEqual(
(t1.type, t1.value),
(RegexTokenizer.TOK_CLASS, LitteralCharacterClass('a')))
self.assertEqual((t2.type, t2.value),
(RegexTokenizer.TOK_EXPONENT, ExponentToken(1, None)))
def test_interval(self):
t1, t2 = self._tokenize('a{13-15}')
self.assertEqual(
(t1.type, t1.value),
(RegexTokenizer.TOK_CLASS, LitteralCharacterClass('a')))
self.assertEqual((t2.type, t2.value),
(RegexTokenizer.TOK_EXPONENT, ExponentToken(13, 15)))
def test_single_value(self):
t1, t2 = self._tokenize('a{42}')
self.assertEqual(
(t1.type, t1.value),
(RegexTokenizer.TOK_CLASS, LitteralCharacterClass('a')))
self.assertEqual((t2.type, t2.value),
(RegexTokenizer.TOK_EXPONENT, ExponentToken(42, 42)))
def test_any(self):
tok1, tok2 = self._tokenize('a.')
self.assertEqual(
(tok1.type, tok1.value),
(RegexTokenizer.TOK_CLASS, LitteralCharacterClass('a')))
self.assertEqual((tok2.type, tok2.value),
(RegexTokenizer.TOK_CLASS, AnyCharacterClass()))
def test_exponent_null(self):
rx = RegularExpression.exponent(
RegularExpression.fromClass(LitteralCharacterClass(
self.t('a')[0])), 0, 1)
self.assertTrue(rx.match(self.t('')))
self.assertTrue(rx.match(self.t('a')))
self.assertFalse(rx.match(self.t('aa')))
def test_kleene(self):
rx = RegularExpression.kleene(
RegularExpression.fromClass(LitteralCharacterClass(
self.t('a')[0])))
self.assertTrue(rx.match(self.t('')))
self.assertTrue(rx.match(self.t('a')))
self.assertTrue(rx.match(self.t('aa')))
self.assertFalse(rx.match(self.t('ab')))
def test_start(self):
t1, t2 = self._tokenize(r'{symbol}s'.format(symbol=self.symbol[1]))
self.assertEqual((t1.type, t1.value), self.symbol)
self.assertEqual(
(t2.type, t2.value),
(RegexTokenizer.TOK_CLASS, LitteralCharacterClass('s')))
def test_newline(self):
rx = RegularExpression.fromClass(
LitteralCharacterClass(self.t('\n')[0]))
self.assertTrue(rx.match(self.t('\n')))