Issue #22410: Module level functions in the re module now cache compiled
locale-dependent regular expressions taking into account the locale.
diff --git a/Lib/re.py b/Lib/re.py
index 8f5b399..e731a69 100644
--- a/Lib/re.py
+++ b/Lib/re.py
@@ -122,6 +122,7 @@
import sys
import sre_compile
import sre_parse
+import _locale
# public symbols
__all__ = [
@@ -274,7 +275,9 @@
def _compile(pattern, flags):
# internal: compile pattern
try:
- return _cache[type(pattern), pattern, flags]
+ p, loc = _cache[type(pattern), pattern, flags]
+ if loc is None or loc == _locale.setlocale(_locale.LC_CTYPE):
+ return p
except KeyError:
pass
if isinstance(pattern, _pattern_type):
@@ -288,7 +291,11 @@
if not (flags & DEBUG):
if len(_cache) >= _MAXCACHE:
_cache.clear()
- _cache[type(pattern), pattern, flags] = p
+ if p.flags & LOCALE:
+ loc = _locale.setlocale(_locale.LC_CTYPE)
+ else:
+ loc = None
+ _cache[type(pattern), pattern, flags] = p, loc
return p
def _compile_repl(repl, pattern):
diff --git a/Lib/test/test_re.py b/Lib/test/test_re.py
index dfc797c..4029561 100644
--- a/Lib/test/test_re.py
+++ b/Lib/test/test_re.py
@@ -1,6 +1,7 @@
from test.support import verbose, run_unittest, gc_collect, bigmemtest, _2G, \
cpython_only, captured_stdout
import io
+import locale
import re
from re import Scanner
import sre_compile
@@ -1276,6 +1277,42 @@
# with ignore case.
self.assertEqual(re.fullmatch('[a-c]+', 'ABC', re.I).span(), (0, 3))
+ 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'))
+
class PatternReprTests(unittest.TestCase):
def check(self, pattern, expected):
diff --git a/Misc/NEWS b/Misc/NEWS
index 76fdd8d..dd2aeb6 100644
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -180,6 +180,9 @@
Library
-------
+- Issue #22410: Module level functions in the re module now cache compiled
+ locale-dependent regular expressions taking into account the locale.
+
- Issue #22759: Query methods on pathlib.Path() (exists(), is_dir(), etc.)
now return False when the underlying stat call raises NotADirectoryError.