Add a workaround for a problem that UTF-8 strings can be corrupted

or broken by basic ctype functions in 4.4BSD descendants.  This
will be fixed in their future development branches but they'll keep
the POSIX-incompatibility for their backward-compatiblities in near
future.

1 files changed, 35 insertions, 0 deletions

diff --git a/Lib/test/test_locale.py b/Lib/test/test_locale.py
index 9187c9e..d8f7925 100644
--- a/Lib/test/test_locale.py
+++ b/Lib/test/test_locale.py
@@ -47,3 +47,38 @@ try:
     locale.getpreferredencoding()
 finally:
     locale.setlocale(locale.LC_NUMERIC, oldlocale)
+
+
+# Test BSD Rune locale's bug for isctype functions.
+def teststrop(s, method, output):
+    if verbose:
+        print "%s.%s() =? %s ..." % (repr(s), method, repr(output)),
+    result = getattr(s, method)()
+    if result != output:
+        if verbose:
+            print "no"
+        print "%s.%s() == %s != %s" % (repr(s), method, repr(result),
+                                       repr(output))
+    elif verbose:
+        print "yes"
+
+try:
+    oldlocale = locale.setlocale(locale.LC_CTYPE)
+    locale.setlocale(locale.LC_CTYPE, 'en_US.UTF-8')
+except locale.Error:
+    pass
+else:
+    try:
+        teststrop('\x20', 'isspace', True)
+        teststrop('\xa0', 'isspace', False)
+        teststrop('\xa1', 'isspace', False)
+        teststrop('\xc0', 'isalpha', False)
+        teststrop('\xc0', 'isalnum', False)
+        teststrop('\xc0', 'isupper', False)
+        teststrop('\xc0', 'islower', False)
+        teststrop('\xec\xa0\xbc', 'split', ['\xec\xa0\xbc'])
+        teststrop('\xed\x95\xa0', 'strip', '\xed\x95\xa0')
+        teststrop('\xcc\x85', 'lower', '\xcc\x85')
+        teststrop('\xed\x95\xa0', 'upper', '\xed\x95\xa0')
+    finally:
+        locale.setlocale(locale.LC_CTYPE, oldlocale)