import sys
import sre_compile
import sre_parse
+import _locale
# public symbols
__all__ = [ "match", "search", "sub", "subn", "split", "findall",
bypass_cache = flags & DEBUG
if not bypass_cache:
cachekey = (type(key[0]),) + key
- p = _cache.get(cachekey)
- if p is not None:
- return p
+ try:
+ p, loc = _cache[cachekey]
+ if loc is None or loc == _locale.setlocale(_locale.LC_CTYPE):
+ return p
+ except KeyError:
+ pass
if isinstance(pattern, _pattern_type):
if flags:
raise ValueError('Cannot process flags argument with a compiled pattern')
if not bypass_cache:
if len(_cache) >= _MAXCACHE:
_cache.clear()
- _cache[cachekey] = p
+ if p.flags & LOCALE:
+ loc = _locale.setlocale(_locale.LC_CTYPE)
+ else:
+ loc = None
+ _cache[cachekey] = p, loc
return p
def _compile_repl(*key):
from test.test_support import verbose, run_unittest, import_module
from test.test_support import precisionbigmemtest, _2G, cpython_only
from test.test_support import captured_stdout, have_unicode, requires_unicode, u
+import locale
import re
from re import Scanner
import sre_constants
self.assertEqual(re.match("(foo)", "foo").group(1L), "foo")
self.assertRaises(IndexError, re.match("", "").group, sys.maxint + 1)
+ def test_locale_caching(self):
+ # Issue #22410
+ oldlocale = locale.setlocale(locale.LC_CTYPE)
+ self.addCleanup(locale.setlocale, locale.LC_CTYPE, oldlocale)
+ for loc in 'en_US.iso88591', 'en_US.utf8':
+ try:
+ locale.setlocale(locale.LC_CTYPE, loc)
+ except locale.Error:
+ # Unsupported locale on this system
+ self.skipTest('test needs %s locale' % loc)
+
+ re.purge()
+ self.check_en_US_iso88591()
+ self.check_en_US_utf8()
+ re.purge()
+ self.check_en_US_utf8()
+ self.check_en_US_iso88591()
+
+ def check_en_US_iso88591(self):
+ locale.setlocale(locale.LC_CTYPE, 'en_US.iso88591')
+ self.assertTrue(re.match(b'\xc5\xe5', b'\xc5\xe5', re.L|re.I))
+ self.assertTrue(re.match(b'\xc5', b'\xe5', re.L|re.I))
+ self.assertTrue(re.match(b'\xe5', b'\xc5', re.L|re.I))
+ self.assertTrue(re.match(b'(?Li)\xc5\xe5', b'\xc5\xe5'))
+ self.assertTrue(re.match(b'(?Li)\xc5', b'\xe5'))
+ self.assertTrue(re.match(b'(?Li)\xe5', b'\xc5'))
+
+ def check_en_US_utf8(self):
+ locale.setlocale(locale.LC_CTYPE, 'en_US.utf8')
+ self.assertTrue(re.match(b'\xc5\xe5', b'\xc5\xe5', re.L|re.I))
+ self.assertIsNone(re.match(b'\xc5', b'\xe5', re.L|re.I))
+ self.assertIsNone(re.match(b'\xe5', b'\xc5', re.L|re.I))
+ self.assertTrue(re.match(b'(?Li)\xc5\xe5', b'\xc5\xe5'))
+ self.assertIsNone(re.match(b'(?Li)\xc5', b'\xe5'))
+ self.assertIsNone(re.match(b'(?Li)\xe5', b'\xc5'))
+
def run_re_tests():
from test.re_tests import tests, SUCCEED, FAIL, SYNTAX_ERROR