我们从Python开源项目中，提取了以下18个代码示例，用于说明如何使用re.A。
def test_string_boundaries(self): # See http://bugs.python.org/issue10713 self.assertEqual(re.search(r"\b(abc)\b", "abc").group(1), "abc") # There's a word boundary at the start of a string. self.assertTrue(re.match(r"\b", "abc")) # A non-empty string includes a non-boundary zero-length match. self.assertTrue(re.search(r"\B", "abc")) # There is no non-boundary match at the start of a string. self.assertFalse(re.match(r"\B", "abc")) # However, an empty string contains no word boundaries, and also no # non-boundaries. self.assertIsNone(re.search(r"\B", "")) # This one is questionable and different from the perlre behaviour, # but describes current behavior. self.assertIsNone(re.search(r"\b", "")) # A single word-character string has two boundaries, but no # non-boundary gaps. self.assertEqual(len(re.findall(r"\b", "a")), 2) self.assertEqual(len(re.findall(r"\B", "a")), 0) # If there are no words, there are no boundaries self.assertEqual(len(re.findall(r"\b", " ")), 0) self.assertEqual(len(re.findall(r"\b", " ")), 0) # Can match around the whitespace. self.assertEqual(len(re.findall(r"\B", " ")), 2)
def test_basic_re_sub(self): self.assertTypedEqual(re.sub('y', 'a', 'xyz'), 'xaz') self.assertTypedEqual(re.sub('y', S('a'), S('xyz')), 'xaz') self.assertTypedEqual(re.sub(b'y', b'a', b'xyz'), b'xaz') self.assertTypedEqual(re.sub(b'y', B(b'a'), B(b'xyz')), b'xaz') self.assertTypedEqual(re.sub(b'y', bytearray(b'a'), bytearray(b'xyz')), b'xaz') self.assertTypedEqual(re.sub(b'y', memoryview(b'a'), memoryview(b'xyz')), b'xaz') for y in ("\xe0", "\u0430", "\U0001d49c"): self.assertEqual(re.sub(y, 'a', 'x%sz' % y), 'xaz') self.assertEqual(re.sub("(?i)b+", "x", "bbbb BBBB"), 'x x') self.assertEqual(re.sub(r'\d+', self.bump_num, '08.2 -2 23x99y'), '9.3 -3 24x100y') self.assertEqual(re.sub(r'\d+', self.bump_num, '08.2 -2 23x99y', 3), '9.3 -3 23x99y') self.assertEqual(re.sub('.', lambda m: r"\n", 'x'), '\\n') self.assertEqual(re.sub('.', r"\n", 'x'), '\n') s = r"\1\1" self.assertEqual(re.sub('(.)', s, 'x'), 'xx') self.assertEqual(re.sub('(.)', re.escape(s), 'x'), s) self.assertEqual(re.sub('(.)', lambda m: s, 'x'), s) self.assertEqual(re.sub('(?P<a>x)', '\g<a>\g<a>', 'xx'), 'xxxx') self.assertEqual(re.sub('(?P<a>x)', '\g<a>\g<1>', 'xx'), 'xxxx') self.assertEqual(re.sub('(?P<unk>x)', '\g<unk>\g<unk>', 'xx'), 'xxxx') self.assertEqual(re.sub('(?P<unk>x)', '\g<1>\g<1>', 'xx'), 'xxxx') self.assertEqual(re.sub('a',r'\t\n\v\r\f\a\b\B\Z\a\A\w\W\s\S\d\D','a'), '\t\n\v\r\f\a\b\\B\\Z\a\\A\\w\\W\\s\\S\\d\\D') self.assertEqual(re.sub('a', '\t\n\v\r\f\a', 'a'), '\t\n\v\r\f\a') self.assertEqual(re.sub('a', '\t\n\v\r\f\a', 'a'), (chr(9)+chr(10)+chr(11)+chr(13)+chr(12)+chr(7))) self.assertEqual(re.sub('^\s*', 'X', 'test'), 'Xtest')
def test_bug_1661(self): # Verify that flags do not get silently ignored with compiled patterns pattern = re.compile('.') self.assertRaises(ValueError, re.match, pattern, 'A', re.I) self.assertRaises(ValueError, re.search, pattern, 'A', re.I) self.assertRaises(ValueError, re.findall, pattern, 'A', re.I) self.assertRaises(ValueError, re.compile, pattern, re.I)
def test_bug_3629(self): # A regex that triggered a bug in the sre-code validator re.compile("(?P<quote>)(?(quote))")
def test_re_match(self): for string in 'a', S('a'): self.assertEqual(re.match('a', string).groups(), ()) self.assertEqual(re.match('(a)', string).groups(), ('a',)) self.assertEqual(re.match('(a)', string).group(0), 'a') self.assertEqual(re.match('(a)', string).group(1), 'a') self.assertEqual(re.match('(a)', string).group(1, 1), ('a', 'a')) for string in b'a', B(b'a'), bytearray(b'a'), memoryview(b'a'): self.assertEqual(re.match(b'a', string).groups(), ()) self.assertEqual(re.match(b'(a)', string).groups(), (b'a',)) self.assertEqual(re.match(b'(a)', string).group(0), b'a') self.assertEqual(re.match(b'(a)', string).group(1), b'a') self.assertEqual(re.match(b'(a)', string).group(1, 1), (b'a', b'a')) for a in ("\xe0", "\u0430", "\U0001d49c"): self.assertEqual(re.match(a, a).groups(), ()) self.assertEqual(re.match('(%s)' % a, a).groups(), (a,)) self.assertEqual(re.match('(%s)' % a, a).group(0), a) self.assertEqual(re.match('(%s)' % a, a).group(1), a) self.assertEqual(re.match('(%s)' % a, a).group(1, 1), (a, a)) pat = re.compile('((a)|(b))(c)?') self.assertEqual(pat.match('a').groups(), ('a', 'a', None, None)) self.assertEqual(pat.match('b').groups(), ('b', None, 'b', None)) self.assertEqual(pat.match('ac').groups(), ('a', 'a', None, 'c')) self.assertEqual(pat.match('bc').groups(), ('b', None, 'b', 'c')) self.assertEqual(pat.match('bc').groups(""), ('b', "", 'b', 'c')) # A single group m = re.match('(a)', 'a') self.assertEqual(m.group(0), 'a') self.assertEqual(m.group(0), 'a') self.assertEqual(m.group(1), 'a') self.assertEqual(m.group(1, 1), ('a', 'a')) pat = re.compile('(?:(?P<a1>a)|(?P<b2>b))(?P<c3>c)?') self.assertEqual(pat.match('a').group(1, 2, 3), ('a', None, None)) self.assertEqual(pat.match('b').group('a1', 'b2', 'c3'), (None, 'b', None)) self.assertEqual(pat.match('ac').group(1, 'b2', 3), ('a', None, 'c'))
def test_ignore_case_range(self): # Issues #3511, #17381. self.assertTrue(re.match(r'[9-a]', '_', re.I)) self.assertIsNone(re.match(r'[9-A]', '_', re.I)) self.assertTrue(re.match(br'[9-a]', b'_', re.I)) self.assertIsNone(re.match(br'[9-A]', b'_', re.I)) self.assertTrue(re.match(r'[\xc0-\xde]', '\xd7', re.I)) self.assertIsNone(re.match(r'[\xc0-\xde]', '\xf7', re.I)) self.assertTrue(re.match(r'[\xe0-\xfe]', '\xf7', re.I)) self.assertIsNone(re.match(r'[\xe0-\xfe]', '\xd7', re.I)) self.assertTrue(re.match(r'[\u0430-\u045f]', '\u0450', re.I)) self.assertTrue(re.match(r'[\u0430-\u045f]', '\u0400', re.I)) self.assertTrue(re.match(r'[\u0400-\u042f]', '\u0450', re.I)) self.assertTrue(re.match(r'[\u0400-\u042f]', '\u0400', re.I)) self.assertTrue(re.match(r'[\U00010428-\U0001044f]', '\U00010428', re.I)) self.assertTrue(re.match(r'[\U00010428-\U0001044f]', '\U00010400', re.I)) self.assertTrue(re.match(r'[\U00010400-\U00010427]', '\U00010428', re.I)) self.assertTrue(re.match(r'[\U00010400-\U00010427]', '\U00010400', re.I)) assert '\u212a'.lower() == 'k' # '?' self.assertTrue(re.match(r'[J-M]', '\u212a', re.I)) self.assertTrue(re.match(r'[j-m]', '\u212a', re.I)) self.assertTrue(re.match(r'[\u2129-\u212b]', 'K', re.I)) self.assertTrue(re.match(r'[\u2129-\u212b]', 'k', re.I)) assert '\u017f'.upper() == 'S' # '?' self.assertTrue(re.match(r'[R-T]', '\u017f', re.I)) self.assertTrue(re.match(r'[r-t]', '\u017f', re.I)) self.assertTrue(re.match(r'[\u017e-\u0180]', 'S', re.I)) self.assertTrue(re.match(r'[\u017e-\u0180]', 's', re.I)) assert '\ufb05'.upper() == '\ufb06'.upper() == 'ST' # '?', '?' self.assertTrue(re.match(r'[\ufb04-\ufb05]', '\ufb06', re.I)) self.assertTrue(re.match(r'[\ufb06-\ufb07]', '\ufb05', re.I))
def test_getlower(self): import _sre self.assertEqual(_sre.getlower(ord('A'), 0), ord('a')) self.assertEqual(_sre.getlower(ord('A'), re.LOCALE), ord('a')) self.assertEqual(_sre.getlower(ord('A'), re.UNICODE), ord('a')) self.assertEqual(re.match("abc", "ABC", re.I).group(0), "ABC") self.assertEqual(re.match(b"abc", b"ABC", re.I).group(0), b"ABC")
def test_inline_flags(self): # Bug #1700 upper_char = chr(0x1ea0) # Latin Capital Letter A with Dot Bellow lower_char = chr(0x1ea1) # Latin Small Letter A with Dot Bellow p = re.compile(upper_char, re.I | re.U) q = p.match(lower_char) self.assertTrue(q) p = re.compile(lower_char, re.I | re.U) q = p.match(upper_char) self.assertTrue(q) p = re.compile('(?i)' + upper_char, re.U) q = p.match(lower_char) self.assertTrue(q) p = re.compile('(?i)' + lower_char, re.U) q = p.match(upper_char) self.assertTrue(q) p = re.compile('(?iu)' + upper_char) q = p.match(lower_char) self.assertTrue(q) p = re.compile('(?iu)' + lower_char) q = p.match(upper_char) self.assertTrue(q)
def test_bug_13899(self): # Issue #13899: re pattern r"[\A]" should work like "A" but matches # nothing. Ditto B and Z. self.assertEqual(re.findall(r'[\A\B\b\C\Z]', 'AB\bCZ'), ['A', 'B', '\b', 'C', 'Z'])
def test_bytes(self): self.check(b'bytes pattern', "re.compile(b'bytes pattern')") self.check_flags(b'bytes pattern', re.A, "re.compile(b'bytes pattern', re.ASCII)")
