Mirrors
/
cpython
mirror of https://github.com/python/cpython
3
0
Fork 0
Code Releases Activity
Browse Source

Issue #27030: Unknown escapes consisting of ``'\'`` and ASCII letter in 

regular expressions now are errors.
pull/9921/head
Serhiy Storchaka 10 years ago
parent
d35bf03284
commit
9bd85b83f6
4 changed files with 32 additions and 84 deletions
Whitespace
Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL
Split View
Diff Options
Show Stats Download Patch File Download Diff File
  1. 23
      Doc/library/re.rst
  2. 49
      Lib/sre_parse.py
  3. 41
      Lib/test/test_re.py
  4. 3
      Misc/NEWS

23
Doc/library/re.rst
View File

@ -317,8 +317,9 @@ The special characters are:
The special sequences consist of ``'\'`` and a character from the list below.
If the ordinary character is not on the list, then the resulting RE will match
the second character. For example, ``\$`` matches the character ``'$'``.
If the ordinary character is not ASCII digit or ASCII letter, then the
resulting RE will match the second character. For example, ``\$`` matches the
character ``'$'``.
``\number``
Matches the contents of the group of the same number. Groups are numbered
@ -438,9 +439,8 @@ three digits in length.
.. versionchanged:: 3.3
The ``'\u'`` and ``'\U'`` escape sequences have been added.
.. deprecated-removed:: 3.5 3.6
Unknown escapes consist of ``'\'`` and ASCII letter now raise a
deprecation warning and will be forbidden in Python 3.6.
.. versionchanged:: 3.6
Unknown escapes consisting of ``'\'`` and ASCII letter now are errors.
.. seealso::
@ -528,11 +528,11 @@ form.
current locale. The use of this flag is discouraged as the locale mechanism
is very unreliable, and it only handles one "culture" at a time anyway;
you should use Unicode matching instead, which is the default in Python 3
for Unicode (str) patterns. This flag makes sense only with bytes patterns.
for Unicode (str) patterns. This flag can be used only with bytes patterns.
.. deprecated-removed:: 3.5 3.6
Deprecated the use of :const:`re.LOCALE` with string patterns or
:const:`re.ASCII`.
.. versionchanged:: 3.6
:const:`re.LOCALE` can be used only with bytes patterns and is
not compatible with :const:`re.ASCII`.
.. data:: M
@ -738,9 +738,8 @@ form.
.. versionchanged:: 3.5
Unmatched groups are replaced with an empty string.
.. deprecated-removed:: 3.5 3.6
Unknown escapes consist of ``'\'`` and ASCII letter now raise a
deprecation warning and will be forbidden in Python 3.6.
.. versionchanged:: 3.6
Unknown escapes consisting of ``'\'`` and ASCII letter now are errors.
.. function:: subn(pattern, repl, string, count=0, flags=0)

49
Lib/sre_parse.py
View File

@ -282,33 +282,6 @@ class Tokenizer:
def error(self, msg, offset=0):
return error(msg, self.string, self.tell() - offset)
# The following three functions are not used in this module anymore, but we keep
# them here (with DeprecationWarnings) for backwards compatibility.
def isident(char):
import warnings
warnings.warn('sre_parse.isident() will be removed in 3.5',
DeprecationWarning, stacklevel=2)
return "a" <= char <= "z" or "A" <= char <= "Z" or char == "_"
def isdigit(char):
import warnings
warnings.warn('sre_parse.isdigit() will be removed in 3.5',
DeprecationWarning, stacklevel=2)
return "0" <= char <= "9"
def isname(name):
import warnings
warnings.warn('sre_parse.isname() will be removed in 3.5',
DeprecationWarning, stacklevel=2)
# check that group name is a valid string
if not isident(name[0]):
return False
for char in name[1:]:
if not isident(char) and not isdigit(char):
return False
return True
def _class_escape(source, escape):
# handle escape code inside character class
code = ESCAPES.get(escape)
@ -351,9 +324,7 @@ def _class_escape(source, escape):
raise ValueError
if len(escape) == 2:
if c in ASCIILETTERS:
import warnings
warnings.warn('bad escape %s' % escape,
DeprecationWarning, stacklevel=8)
raise source.error('bad escape %s' % escape, len(escape))
return LITERAL, ord(escape[1])
except ValueError:
pass
@ -418,9 +389,7 @@ def _escape(source, escape, state):
raise source.error("invalid group reference", len(escape))
if len(escape) == 2:
if c in ASCIILETTERS:
import warnings
warnings.warn('bad escape %s' % escape,
DeprecationWarning, stacklevel=8)
raise source.error("bad escape %s" % escape, len(escape))
return LITERAL, ord(escape[1])
except ValueError:
pass
@ -798,10 +767,7 @@ def fix_flags(src, flags):
# Check and fix flags according to the type of pattern (str or bytes)
if isinstance(src, str):
if flags & SRE_FLAG_LOCALE:
import warnings
warnings.warn("LOCALE flag with a str pattern is deprecated. "
"Will be an error in 3.6",
DeprecationWarning, stacklevel=6)
raise ValueError("cannot use LOCALE flag with a str pattern")
if not flags & SRE_FLAG_ASCII:
flags |= SRE_FLAG_UNICODE
elif flags & SRE_FLAG_UNICODE:
@ -810,10 +776,7 @@ def fix_flags(src, flags):
if flags & SRE_FLAG_UNICODE:
raise ValueError("cannot use UNICODE flag with a bytes pattern")
if flags & SRE_FLAG_LOCALE and flags & SRE_FLAG_ASCII:
import warnings
warnings.warn("ASCII and LOCALE flags are incompatible. "
"Will be an error in 3.6",
DeprecationWarning, stacklevel=6)
raise ValueError("ASCII and LOCALE flags are incompatible")
return flags
def parse(str, flags=0, pattern=None):
@ -914,9 +877,7 @@ def parse_template(source, pattern):
this = chr(ESCAPES[this][1])
except KeyError:
if c in ASCIILETTERS:
import warnings
warnings.warn('bad escape %s' % this,
DeprecationWarning, stacklevel=4)
raise s.error('bad escape %s' % this, len(this))
lappend(this)
else:
lappend(this)

41
Lib/test/test_re.py
View File

@ -124,7 +124,7 @@ class ReTests(unittest.TestCase):
(chr(9)+chr(10)+chr(11)+chr(13)+chr(12)+chr(7)+chr(8)))
for c in 'cdehijklmopqsuwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ':
with self.subTest(c):
with self.assertWarns(DeprecationWarning):
with self.assertRaises(re.error):
self.assertEqual(re.sub('a', '\\' + c, 'a'), '\\' + c)
self.assertEqual(re.sub('^\s*', 'X', 'test'), 'Xtest')
@ -633,14 +633,10 @@ class ReTests(unittest.TestCase):
re.purge() # for warnings
for c in 'ceghijklmopqyzCEFGHIJKLMNOPQRTVXY':
with self.subTest(c):
with self.assertWarns(DeprecationWarning):
self.assertEqual(re.fullmatch('\\%c' % c, c).group(), c)
self.assertIsNone(re.match('\\%c' % c, 'a'))
self.assertRaises(re.error, re.compile, '\\%c' % c)
for c in 'ceghijklmopqyzABCEFGHIJKLMNOPQRTVXYZ':
with self.subTest(c):
with self.assertWarns(DeprecationWarning):
self.assertEqual(re.fullmatch('[\\%c]' % c, c).group(), c)
self.assertIsNone(re.match('[\\%c]' % c, 'a'))
self.assertRaises(re.error, re.compile, '[\\%c]' % c)
def test_string_boundaries(self):
# See http://bugs.python.org/issue10713
@ -993,10 +989,8 @@ class ReTests(unittest.TestCase):
self.assertTrue(re.match((r"\x%02x" % i).encode(), bytes([i])))
self.assertTrue(re.match((r"\x%02x0" % i).encode(), bytes([i])+b"0"))
self.assertTrue(re.match((r"\x%02xz" % i).encode(), bytes([i])+b"z"))
with self.assertWarns(DeprecationWarning):
self.assertTrue(re.match(br"\u1234", b'u1234'))
with self.assertWarns(DeprecationWarning):
self.assertTrue(re.match(br"\U00012345", b'U00012345'))
self.assertRaises(re.error, re.compile, br"\u1234")
self.assertRaises(re.error, re.compile, br"\U00012345")
self.assertTrue(re.match(br"\0", b"\000"))
self.assertTrue(re.match(br"\08", b"\0008"))
self.assertTrue(re.match(br"\01", b"\001"))
@ -1018,10 +1012,8 @@ class ReTests(unittest.TestCase):
self.assertTrue(re.match((r"[\x%02x]" % i).encode(), bytes([i])))
self.assertTrue(re.match((r"[\x%02x0]" % i).encode(), bytes([i])))
self.assertTrue(re.match((r"[\x%02xz]" % i).encode(), bytes([i])))
with self.assertWarns(DeprecationWarning):
self.assertTrue(re.match(br"[\u1234]", b'u'))
with self.assertWarns(DeprecationWarning):
self.assertTrue(re.match(br"[\U00012345]", b'U'))
self.assertRaises(re.error, re.compile, br"[\u1234]")
self.assertRaises(re.error, re.compile, br"[\U00012345]")
self.checkPatternError(br"[\567]",
r'octal escape value \567 outside of '
r'range 0-0o377', 1)
@ -1363,12 +1355,12 @@ class ReTests(unittest.TestCase):
if bletter:
self.assertIsNone(pat.match(bletter))
# Incompatibilities
self.assertWarns(DeprecationWarning, re.compile, '', re.LOCALE)
self.assertWarns(DeprecationWarning, re.compile, '(?L)')
self.assertWarns(DeprecationWarning, re.compile, b'', re.LOCALE | re.ASCII)
self.assertWarns(DeprecationWarning, re.compile, b'(?L)', re.ASCII)
self.assertWarns(DeprecationWarning, re.compile, b'(?a)', re.LOCALE)
self.assertWarns(DeprecationWarning, re.compile, b'(?aL)')
self.assertRaises(ValueError, re.compile, '', re.LOCALE)
self.assertRaises(ValueError, re.compile, '(?L)')
self.assertRaises(ValueError, re.compile, b'', re.LOCALE | re.ASCII)
self.assertRaises(ValueError, re.compile, b'(?L)', re.ASCII)
self.assertRaises(ValueError, re.compile, b'(?a)', re.LOCALE)
self.assertRaises(ValueError, re.compile, b'(?aL)')
def test_bug_6509(self):
# Replacement strings of both types must parse properly.
@ -1419,13 +1411,6 @@ class ReTests(unittest.TestCase):
# Test behaviour when not given a string or pattern as parameter
self.assertRaises(TypeError, re.compile, 0)
def test_bug_13899(self):
# Issue #13899: re pattern r"[\A]" should work like "A" but matches
# nothing. Ditto B and Z.
with self.assertWarns(DeprecationWarning):
self.assertEqual(re.findall(r'[\A\B\b\C\Z]', 'AB\bCZ'),
['A', 'B', '\b', 'C', 'Z'])
@bigmemtest(size=_2G, memuse=1)
def test_large_search(self, size):
# Issue #10182: indices were 32-bit-truncated.

3
Misc/NEWS
View File

@ -38,6 +38,9 @@ Core and Builtins
Library
-------
- Issue #27030: Unknown escapes consisting of ``'\'`` and ASCII letter in
regular expressions now are errors.
- Issue #27186: Add os.PathLike support to DirEntry (part of PEP 519).
Initial patch by Jelle Zijlstra.

Write Preview
Loading…
Cancel
Save