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
)
python类compile()的实例源码
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
)
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
)
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
)
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)
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')
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
)
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
)
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.))')
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'))
def test_lookbehind(self):
self.assertTrue(re.match(r'ab(?<=b)c', 'abc'))
self.assertIsNone(re.match(r'ab(?<=c)c', 'abc'))
self.assertIsNone(re.match(r'ab(?<!b)c', 'abc'))
self.assertTrue(re.match(r'ab(?<!c)c', 'abc'))
# Group reference.
with check_warnings(('', RuntimeWarning)):
re.compile(r'(a)a(?<=\1)c')
# Named group reference.
with check_warnings(('', RuntimeWarning)):
re.compile(r'(?P<g>a)a(?<=(?P=g))c')
# Conditional group reference.
with check_warnings(('', RuntimeWarning)):
re.compile(r'(a)b(?<=(?(1)b|x))c')
# Group used before defined.
with check_warnings(('', RuntimeWarning)):
re.compile(r'(a)b(?<=(?(2)b|x))(c)')
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.))')
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'))
def test_lookbehind(self):
self.assertTrue(re.match(r'ab(?<=b)c', 'abc'))
self.assertIsNone(re.match(r'ab(?<=c)c', 'abc'))
self.assertIsNone(re.match(r'ab(?<!b)c', 'abc'))
self.assertTrue(re.match(r'ab(?<!c)c', 'abc'))
# Group reference.
with check_warnings(('', RuntimeWarning)):
re.compile(r'(a)a(?<=\1)c')
# Named group reference.
with check_warnings(('', RuntimeWarning)):
re.compile(r'(?P<g>a)a(?<=(?P=g))c')
# Conditional group reference.
with check_warnings(('', RuntimeWarning)):
re.compile(r'(a)b(?<=(?(1)b|x))c')
# Group used before defined.
with check_warnings(('', RuntimeWarning)):
re.compile(r'(a)b(?<=(?(2)b|x))(c)')
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
)
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.))')
# New valid/invalid identifiers in Python 3
re.compile('(?P<µ>x)(?P=µ)(?(µ)y)')
re.compile('(?P<??????????????>x)(?P=??????????????)(?(??????????????)y)')
self.assertRaises(re.error, re.compile, '(?P<©>x)')
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)
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],
["::", "::"])
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')
def _compile_charset(charset, flags, code, fixup=None, fixes=None):
# compile charset subprogram
emit = code.append
for op, av in _optimize_charset(charset, fixup, fixes):
emit(op)
if op is NEGATE:
pass
elif op is LITERAL:
emit(av)
elif op is RANGE or op is RANGE_IGNORE:
emit(av[0])
emit(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(CH_LOCALE[av])
elif (flags & SRE_FLAG_UNICODE) and not (flags & SRE_FLAG_ASCII):
emit(CH_UNICODE[av])
else:
emit(av)
else:
raise error("internal: unsupported set operator %r" % (op,))
emit(FAILURE)
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(SUCCESS)
return code
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])
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
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
# 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
)
def _compile_charset(charset, flags, code, fixup=None, fixes=None):
# compile charset subprogram
emit = code.append
for op, av in _optimize_charset(charset, fixup, fixes,
flags & SRE_FLAG_UNICODE):
emit(OPCODES[op])
if op is NEGATE:
pass
elif op is LITERAL:
emit(av)
elif op is RANGE:
emit(av[0])
emit(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])
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
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
# 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
)
def _compile_charset(charset, flags, code, fixup=None, fixes=None):
# compile charset subprogram
emit = code.append
for op, av in _optimize_charset(charset, fixup, fixes):
emit(op)
if op is NEGATE:
pass
elif op is LITERAL:
emit(av)
elif op is RANGE or op is RANGE_IGNORE:
emit(av[0])
emit(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(CH_LOCALE[av])
elif flags & SRE_FLAG_UNICODE:
emit(CH_UNICODE[av])
else:
emit(av)
else:
raise error("internal: unsupported set operator %r" % (op,))
emit(FAILURE)
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(SUCCESS)
return code
def _compile_charset(charset, flags, code, fixup=None, fixes=None):
# compile charset subprogram
emit = code.append
for op, av in _optimize_charset(charset, fixup, fixes,
flags & SRE_FLAG_UNICODE):
emit(OPCODES[op])
if op is NEGATE:
pass
elif op is LITERAL:
emit(av)
elif op is RANGE:
emit(av[0])
emit(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])
