Python _sre.compile方法代码示例

# 需要导入模块: import _sre [as 别名]
# 或者: from _sre import compile [as 别名]
def test_re_groupref_exists(self):
        self.assertEqual(re.match('^(\()?([^()]+)(?(1)\))$', '(a)').groups(),
                         ('(', 'a'))
        self.assertEqual(re.match('^(\()?([^()]+)(?(1)\))$', 'a').groups(),
                         (None, 'a'))
        self.assertEqual(re.match('^(\()?([^()]+)(?(1)\))$', 'a)'), None)
        self.assertEqual(re.match('^(\()?([^()]+)(?(1)\))$', '(a'), None)
        self.assertEqual(re.match('^(?:(a)|c)((?(1)b|d))$', 'ab').groups(),
                         ('a', 'b'))
        self.assertEqual(re.match('^(?:(a)|c)((?(1)b|d))$', 'cd').groups(),
                         (None, 'd'))
        self.assertEqual(re.match('^(?:(a)|c)((?(1)|d))$', 'cd').groups(),
                         (None, 'd'))
        self.assertEqual(re.match('^(?:(a)|c)((?(1)|d))$', 'a').groups(),
                         ('a', ''))

        # Tests for bug #1177831: exercise groups other than the first group
        p = re.compile('(?P<g1>a)(?P<g2>b)?((?(g2)c|d))')
        self.assertEqual(p.match('abc').groups(),
                         ('a', 'b', 'c'))
        self.assertEqual(p.match('ad').groups(),
                         ('a', None, 'd'))
        self.assertEqual(p.match('abd'), None)
        self.assertEqual(p.match('ac'), None) 

# 需要导入模块: import _sre [as 别名]
# 或者: from _sre import compile [as 别名]
def test_finditer(self):
        iter = re.finditer(r":+", "a:b::c:::d")
        self.assertEqual([item.group(0) for item in iter],
                         [":", "::", ":::"])

        pat = re.compile(r":+")
        iter = pat.finditer("a:b::c:::d", 1, 10)
        self.assertEqual([item.group(0) for item in iter],
                         [":", "::", ":::"])

        pat = re.compile(r":+")
        iter = pat.finditer("a:b::c:::d", pos=1, endpos=10)
        self.assertEqual([item.group(0) for item in iter],
                         [":", "::", ":::"])

        pat = re.compile(r":+")
        iter = pat.finditer("a:b::c:::d", endpos=10, pos=1)
        self.assertEqual([item.group(0) for item in iter],
                         [":", "::", ":::"])

        pat = re.compile(r":+")
        iter = pat.finditer("a:b::c:::d", pos=3, endpos=8)
        self.assertEqual([item.group(0) for item in iter],
                         ["::", "::"]) 

# 需要导入模块: import _sre [as 别名]
# 或者: from _sre import compile [as 别名]
def test_bug_6509(self):
        # Replacement strings of both types must parse properly.
        # all strings
        pat = re.compile('a(\w)')
        self.assertEqual(pat.sub('b\\1', 'ac'), 'bc')
        pat = re.compile('a(.)')
        self.assertEqual(pat.sub('b\\1', 'a\u1234'), 'b\u1234')
        pat = re.compile('..')
        self.assertEqual(pat.sub(lambda m: 'str', 'a5'), 'str')

        # all bytes
        pat = re.compile(b'a(\w)')
        self.assertEqual(pat.sub(b'b\\1', b'ac'), b'bc')
        pat = re.compile(b'a(.)')
        self.assertEqual(pat.sub(b'b\\1', b'a\xCD'), b'b\xCD')
        pat = re.compile(b'..')
        self.assertEqual(pat.sub(lambda m: b'bytes', b'a5'), b'bytes') 

# 需要导入模块: import _sre [as 别名]
# 或者: from _sre import compile [as 别名]
def test_symbolic_groups(self):
        re.compile('(?P<a>x)(?P=a)(?(a)y)')
        re.compile('(?P<a1>x)(?P=a1)(?(a1)y)')
        self.assertRaises(re.error, re.compile, '(?P<a>)(?P<a>)')
        self.assertRaises(re.error, re.compile, '(?Px)')
        self.assertRaises(re.error, re.compile, '(?P=)')
        self.assertRaises(re.error, re.compile, '(?P=1)')
        self.assertRaises(re.error, re.compile, '(?P=a)')
        self.assertRaises(re.error, re.compile, '(?P=a1)')
        self.assertRaises(re.error, re.compile, '(?P=a.)')
        self.assertRaises(re.error, re.compile, '(?P<)')
        self.assertRaises(re.error, re.compile, '(?P<>)')
        self.assertRaises(re.error, re.compile, '(?P<1>)')
        self.assertRaises(re.error, re.compile, '(?P<a.>)')
        self.assertRaises(re.error, re.compile, '(?())')
        self.assertRaises(re.error, re.compile, '(?(a))')
        self.assertRaises(re.error, re.compile, '(?(1a))')
        self.assertRaises(re.error, re.compile, '(?(a.))') 

# 需要导入模块: import _sre [as 别名]
# 或者: from _sre import compile [as 别名]
def test_re_groupref_exists(self):
        self.assertEqual(re.match('^(\()?([^()]+)(?(1)\))$', '(a)').groups(),
                         ('(', 'a'))
        self.assertEqual(re.match('^(\()?([^()]+)(?(1)\))$', 'a').groups(),
                         (None, 'a'))
        self.assertIsNone(re.match('^(\()?([^()]+)(?(1)\))$', 'a)'))
        self.assertIsNone(re.match('^(\()?([^()]+)(?(1)\))$', '(a'))
        self.assertEqual(re.match('^(?:(a)|c)((?(1)b|d))$', 'ab').groups(),
                         ('a', 'b'))
        self.assertEqual(re.match('^(?:(a)|c)((?(1)b|d))$', 'cd').groups(),
                         (None, 'd'))
        self.assertEqual(re.match('^(?:(a)|c)((?(1)|d))$', 'cd').groups(),
                         (None, 'd'))
        self.assertEqual(re.match('^(?:(a)|c)((?(1)|d))$', 'a').groups(),
                         ('a', ''))

        # Tests for bug #1177831: exercise groups other than the first group
        p = re.compile('(?P<g1>a)(?P<g2>b)?((?(g2)c|d))')
        self.assertEqual(p.match('abc').groups(),
                         ('a', 'b', 'c'))
        self.assertEqual(p.match('ad').groups(),
                         ('a', None, 'd'))
        self.assertIsNone(p.match('abd'))
        self.assertIsNone(p.match('ac')) 

# 需要导入模块: import _sre [as 别名]
# 或者: from _sre import compile [as 别名]
def test_other_escapes(self):
        self.assertRaises(re.error, re.compile, "\\")
        self.assertEqual(re.match(r"\(", '(').group(), '(')
        self.assertIsNone(re.match(r"\(", ')'))
        self.assertEqual(re.match(r"\\", '\\').group(), '\\')
        self.assertEqual(re.match(r"[\]]", ']').group(), ']')
        self.assertIsNone(re.match(r"[\]]", '['))
        self.assertEqual(re.match(r"[a\-c]", '-').group(), '-')
        self.assertIsNone(re.match(r"[a\-c]", 'b'))
        self.assertEqual(re.match(r"[\^a]+", 'a^').group(), 'a^')
        self.assertIsNone(re.match(r"[\^a]+", 'b'))
        re.purge()  # for warnings
        for c in 'ceghijklmopquyzCEFGHIJKLMNOPQRTUVXY':
            warn = FutureWarning if c in 'Uu' else DeprecationWarning
            with check_py3k_warnings(('', warn)):
                self.assertEqual(re.match('\\%c$' % c, c).group(), c)
                self.assertIsNone(re.match('\\%c' % c, 'a'))
        for c in 'ceghijklmopquyzABCEFGHIJKLMNOPQRTUVXYZ':
            warn = FutureWarning if c in 'Uu' else DeprecationWarning
            with check_py3k_warnings(('', warn)):
                self.assertEqual(re.match('[\\%c]$' % c, c).group(), c)
                self.assertIsNone(re.match('[\\%c]' % c, 'a')) 

# 需要导入模块: import _sre [as 别名]
# 或者: from _sre import compile [as 别名]
def compile(p, flags=0):
    # internal: convert pattern list to internal format

    if isstring(p):
        pattern = p
        p = sre_parse.parse(p, flags)
    else:
        pattern = None

    code = _code(p, flags)

    # print(code)

    # map in either direction
    groupindex = p.pattern.groupdict
    indexgroup = [None] * p.pattern.groups
    for k, i in groupindex.items():
        indexgroup[i] = k

    return _sre.compile(
        pattern, flags | p.pattern.flags, code,
        p.pattern.groups-1,
        groupindex, indexgroup
        ) 

# 需要导入模块: import _sre [as 别名]
# 或者: from _sre import compile [as 别名]
def _compile_charset(charset, flags, code, fixup=None):
    # compile charset subprogram
    emit = code.append
    if fixup is None:
        fixup = _identityfunction
    for op, av in _optimize_charset(charset, fixup):
        emit(OPCODES[op])
        if op is NEGATE:
            pass
        elif op is LITERAL:
            emit(fixup(av))
        elif op is RANGE:
            emit(fixup(av[0]))
            emit(fixup(av[1]))
        elif op is CHARSET:
            code.extend(av)
        elif op is BIGCHARSET:
            code.extend(av)
        elif op is CATEGORY:
            if flags & SRE_FLAG_LOCALE:
                emit(CHCODES[CH_LOCALE[av]])
            elif flags & SRE_FLAG_UNICODE:
                emit(CHCODES[CH_UNICODE[av]])
            else:
                emit(CHCODES[av])
        else:
            raise error("internal: unsupported set operator")
    emit(OPCODES[FAILURE]) 

# 需要导入模块: import _sre [as 别名]
# 或者: from _sre import compile [as 别名]
def _code(p, flags):

    flags = p.pattern.flags | flags
    code = []

    # compile info block
    _compile_info(code, p, flags)

    # compile the pattern
    _compile(code, p.data, flags)

    code.append(OPCODES[SUCCESS])

    return code 

# 需要导入模块: import _sre [as 别名]
# 或者: from _sre import compile [as 别名]
def compile(p, flags=0):
    # internal: convert pattern list to internal format

    #print("sre_compile.py:compile:504:p", p)
    if isstring(p):
        pattern = p
        p = sre_parse.parse(p, flags)
    else:
        pattern = None

    #print('sre_compile.py:498:p', p)
    code = _code(p, flags)

    #print('sre_compile.py:501:code', code)
    # print code

    # XXX: <fl> get rid of this limitation!
    if p.pattern.groups > 100:
        raise AssertionError(
            "sorry, but this version only supports 100 named groups"
            )

    # map in either direction
    groupindex = p.pattern.groupdict
    indexgroup = [None] * p.pattern.groups
    for k, i in groupindex.items():
        indexgroup[i] = k

    return _sre.compile(
        pattern, flags | p.pattern.flags, code,
        p.pattern.groups-1,
        groupindex, indexgroup
        ) 

# 需要导入模块: import _sre [as 别名]
# 或者: from _sre import compile [as 别名]
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) 

# 需要导入模块: import _sre [as 别名]
# 或者: from _sre import compile [as 别名]
def test_bug_3629(self):
        # A regex that triggered a bug in the sre-code validator
        re.compile("(?P<quote>)(?(quote))") 

# 需要导入模块: import _sre [as 别名]
# 或者: from _sre import compile [as 别名]
def test_re_match(self):
        self.assertEqual(re.match('a', 'a').groups(), ())
        self.assertEqual(re.match('(a)', 'a').groups(), ('a',))
        self.assertEqual(re.match(r'(a)', 'a').group(0), 'a')
        self.assertEqual(re.match(r'(a)', 'a').group(1), 'a')
        self.assertEqual(re.match(r'(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')) 

# 需要导入模块: import _sre [as 别名]
# 或者: from _sre import compile [as 别名]
def test_getattr(self):
        self.assertEqual(re.compile("(?i)(a)(b)").pattern, "(?i)(a)(b)")
        self.assertEqual(re.compile("(?i)(a)(b)").flags, re.I | re.U)
        self.assertEqual(re.compile("(?i)(a)(b)").groups, 2)
        self.assertEqual(re.compile("(?i)(a)(b)").groupindex, {})
        self.assertEqual(re.compile("(?i)(?P<first>a)(?P<other>b)").groupindex,
                         {'first': 1, 'other': 2})

        self.assertEqual(re.match("(a)", "a").pos, 0)
        self.assertEqual(re.match("(a)", "a").endpos, 1)
        self.assertEqual(re.match("(a)", "a").string, "a")
        self.assertEqual(re.match("(a)", "a").regs, ((0, 1), (0, 1)))
        self.assertNotEqual(re.match("(a)", "a").re, None) 

# 需要导入模块: import _sre [as 别名]
# 或者: from _sre import compile [as 别名]
def test_big_codesize(self):
        # Issue #1160
        r = re.compile('|'.join(('%d'%x for x in range(10000))))
        self.assertIsNotNone(r.match('1000'))
        self.assertIsNotNone(r.match('9999'))