#9200: backport tests but run them on wide builds only.

diff --git a/Lib/test/test_unicode.py b/Lib/test/test_unicode.py
index d5394e686468d58a607e0e946f1dd02e8f3264cb..399eed7e31f40656a15e5a0de0e9193bf3088f76 100644 (file)
--- a/Lib/test/test_unicode.py
+++ b/Lib/test/test_unicode.py
@@ -5,9 +5,16 @@ Written by Marc-Andre Lemburg (mal@lemburg.com).
 (c) Copyright CNRI, All Rights Reserved. NO WARRANTY.
 
 """#"
-import sys, struct, codecs
+import sys
+import struct
+import codecs
+import unittest
 from test import test_support, string_tests
 
+# decorator to skip tests on narrow builds
+requires_wide_build = unittest.skipIf(sys.maxunicode == 65535,
+                                      'requires wide build')
+
 # Error handling (bad decoder return)
 def search_function(encoding):
     def decode1(input, errors="strict"):
@@ -292,26 +299,83 @@ class UnicodeTest(
         string_tests.MixinStrUnicodeUserStringTest.test_islower(self)
         self.checkequalnofix(False, u'\u1FFc', 'islower')
 
+    @requires_wide_build
+    def test_islower_non_bmp(self):
+        # non-BMP, uppercase
+        self.assertFalse(u'\U00010401'.islower())
+        self.assertFalse(u'\U00010427'.islower())
+        # non-BMP, lowercase
+        self.assertTrue(u'\U00010429'.islower())
+        self.assertTrue(u'\U0001044E'.islower())
+        # non-BMP, non-cased
+        self.assertFalse(u'\U0001F40D'.islower())
+        self.assertFalse(u'\U0001F46F'.islower())
+
     def test_isupper(self):
         string_tests.MixinStrUnicodeUserStringTest.test_isupper(self)
         if not sys.platform.startswith('java'):
             self.checkequalnofix(False, u'\u1FFc', 'isupper')
 
+    @requires_wide_build
+    def test_isupper_non_bmp(self):
+        # non-BMP, uppercase
+        self.assertTrue(u'\U00010401'.isupper())
+        self.assertTrue(u'\U00010427'.isupper())
+        # non-BMP, lowercase
+        self.assertFalse(u'\U00010429'.isupper())
+        self.assertFalse(u'\U0001044E'.isupper())
+        # non-BMP, non-cased
+        self.assertFalse(u'\U0001F40D'.isupper())
+        self.assertFalse(u'\U0001F46F'.isupper())
+
     def test_istitle(self):
-        string_tests.MixinStrUnicodeUserStringTest.test_title(self)
+        string_tests.MixinStrUnicodeUserStringTest.test_istitle(self)
         self.checkequalnofix(True, u'\u1FFc', 'istitle')
         self.checkequalnofix(True, u'Greek \u1FFcitlecases ...', 'istitle')
 
+    @requires_wide_build
+    def test_istitle_non_bmp(self):
+        # non-BMP, uppercase + lowercase
+        self.assertTrue(u'\U00010401\U00010429'.istitle())
+        self.assertTrue(u'\U00010427\U0001044E'.istitle())
+        # apparently there are no titlecased (Lt) non-BMP chars in Unicode 6
+        for ch in [u'\U00010429', u'\U0001044E', u'\U0001F40D', u'\U0001F46F']:
+            self.assertFalse(ch.istitle(), '{!r} is not title'.format(ch))
+
     def test_isspace(self):
         string_tests.MixinStrUnicodeUserStringTest.test_isspace(self)
         self.checkequalnofix(True, u'\u2000', 'isspace')
         self.checkequalnofix(True, u'\u200a', 'isspace')
         self.checkequalnofix(False, u'\u2014', 'isspace')
 
+    @requires_wide_build
+    def test_isspace_non_bmp(self):
+        # apparently there are no non-BMP spaces chars in Unicode 6
+        for ch in [u'\U00010401', u'\U00010427', u'\U00010429', u'\U0001044E',
+                   u'\U0001F40D', u'\U0001F46F']:
+            self.assertFalse(ch.isspace(), '{!r} is not space.'.format(ch))
+
+    @requires_wide_build
+    def test_isalnum_non_bmp(self):
+        for ch in [u'\U00010401', u'\U00010427', u'\U00010429', u'\U0001044E',
+                   u'\U0001D7F6', u'\U000104A0', u'\U000104A0', u'\U0001F107']:
+            self.assertTrue(ch.isalnum(), '{!r} is alnum.'.format(ch))
+
     def test_isalpha(self):
         string_tests.MixinStrUnicodeUserStringTest.test_isalpha(self)
         self.checkequalnofix(True, u'\u1FFc', 'isalpha')
 
+    @requires_wide_build
+    def test_isalpha_non_bmp(self):
+        # non-BMP, cased
+        self.assertTrue(u'\U00010401'.isalpha())
+        self.assertTrue(u'\U00010427'.isalpha())
+        self.assertTrue(u'\U00010429'.isalpha())
+        self.assertTrue(u'\U0001044E'.isalpha())
+        # non-BMP, non-cased
+        self.assertFalse(u'\U0001F40D'.isalpha())
+        self.assertFalse(u'\U0001F46F'.isalpha())
+
     def test_isdecimal(self):
         self.checkequalnofix(False, u'', 'isdecimal')
         self.checkequalnofix(False, u'a', 'isdecimal')
@@ -324,12 +388,28 @@ class UnicodeTest(
 
         self.checkraises(TypeError, 'abc', 'isdecimal', 42)
 
+    @requires_wide_build
+    def test_isdecimal_non_bmp(self):
+        for ch in [u'\U00010401', u'\U00010427', u'\U00010429', u'\U0001044E',
+                   u'\U0001F40D', u'\U0001F46F', u'\U00011065', u'\U0001F107']:
+            self.assertFalse(ch.isdecimal(), '{!r} is not decimal.'.format(ch))
+        for ch in [u'\U0001D7F6', u'\U000104A0', u'\U000104A0']:
+            self.assertTrue(ch.isdecimal(), '{!r} is decimal.'.format(ch))
+
     def test_isdigit(self):
         string_tests.MixinStrUnicodeUserStringTest.test_isdigit(self)
         self.checkequalnofix(True, u'\u2460', 'isdigit')
         self.checkequalnofix(False, u'\xbc', 'isdigit')
         self.checkequalnofix(True, u'\u0660', 'isdigit')
 
+    @requires_wide_build
+    def test_isdigit_non_bmp(self):
+        for ch in [u'\U00010401', u'\U00010427', u'\U00010429', u'\U0001044E',
+                   u'\U0001F40D', u'\U0001F46F', u'\U00011065']:
+            self.assertFalse(ch.isdigit(), '{!r} is not a digit.'.format(ch))
+        for ch in [u'\U0001D7F6', u'\U000104A0', u'\U000104A0', u'\U0001F107']:
+            self.assertTrue(ch.isdigit(), '{!r} is a digit.'.format(ch))
+
     def test_isnumeric(self):
         self.checkequalnofix(False, u'', 'isnumeric')
         self.checkequalnofix(False, u'a', 'isnumeric')
@@ -342,6 +422,109 @@ class UnicodeTest(
 
         self.assertRaises(TypeError, u"abc".isnumeric, 42)
 
+    @requires_wide_build
+    def test_isnumeric_non_bmp(self):
+        for ch in [u'\U00010401', u'\U00010427', u'\U00010429', u'\U0001044E',
+                   u'\U0001F40D', u'\U0001F46F']:
+            self.assertFalse(ch.isnumeric(), '{!r} is not numeric.'.format(ch))
+        for ch in [u'\U00010107', u'\U0001D7F6', u'\U00023b1b',
+                   u'\U000104A0', u'\U0001F107']:
+            self.assertTrue(ch.isnumeric(), '{!r} is numeric.'.format(ch))
+
+    @requires_wide_build
+    def test_surrogates(self):
+        # this test actually passes on narrow too, but it's just by accident.
+        # Surrogates are seen as non-cased chars, so u'X\uD800X' is as
+        # uppercase as 'X X'
+        for s in (u'a\uD800b\uDFFF', u'a\uDFFFb\uD800',
+                  u'a\uD800b\uDFFFa', u'a\uDFFFb\uD800a'):
+            self.assertTrue(s.islower())
+            self.assertFalse(s.isupper())
+            self.assertFalse(s.istitle())
+        for s in (u'A\uD800B\uDFFF', u'A\uDFFFB\uD800',
+                  u'A\uD800B\uDFFFA', u'A\uDFFFB\uD800A'):
+            self.assertFalse(s.islower())
+            self.assertTrue(s.isupper())
+            self.assertTrue(s.istitle())
+
+        for meth_name in ('islower', 'isupper', 'istitle'):
+            meth = getattr(unicode, meth_name)
+            for s in (u'\uD800', u'\uDFFF', u'\uD800\uD800', u'\uDFFF\uDFFF'):
+                self.assertFalse(meth(s), '%r.%s() is False' % (s, meth_name))
+
+        for meth_name in ('isalpha', 'isalnum', 'isdigit', 'isspace',
+                          'isdecimal', 'isnumeric'):
+            meth = getattr(unicode, meth_name)
+            for s in (u'\uD800', u'\uDFFF', u'\uD800\uD800', u'\uDFFF\uDFFF',
+                      u'a\uD800b\uDFFF', u'a\uDFFFb\uD800',
+                      u'a\uD800b\uDFFFa', u'a\uDFFFb\uD800a'):
+                self.assertFalse(meth(s), '%r.%s() is False' % (s, meth_name))
+
+
+    @requires_wide_build
+    def test_lower(self):
+        string_tests.CommonTest.test_lower(self)
+        self.assertEqual(u'\U00010427'.lower(), u'\U0001044F')
+        self.assertEqual(u'\U00010427\U00010427'.lower(),
+                         u'\U0001044F\U0001044F')
+        self.assertEqual(u'\U00010427\U0001044F'.lower(),
+                         u'\U0001044F\U0001044F')
+        self.assertEqual(u'X\U00010427x\U0001044F'.lower(),
+                         u'x\U0001044Fx\U0001044F')
+
+    @requires_wide_build
+    def test_upper(self):
+        string_tests.CommonTest.test_upper(self)
+        self.assertEqual(u'\U0001044F'.upper(), u'\U00010427')
+        self.assertEqual(u'\U0001044F\U0001044F'.upper(),
+                         u'\U00010427\U00010427')
+        self.assertEqual(u'\U00010427\U0001044F'.upper(),
+                         u'\U00010427\U00010427')
+        self.assertEqual(u'X\U00010427x\U0001044F'.upper(),
+                         u'X\U00010427X\U00010427')
+
+    @requires_wide_build
+    def test_capitalize(self):
+        string_tests.CommonTest.test_capitalize(self)
+        self.assertEqual(u'\U0001044F'.capitalize(), u'\U00010427')
+        self.assertEqual(u'\U0001044F\U0001044F'.capitalize(),
+                         u'\U00010427\U0001044F')
+        self.assertEqual(u'\U00010427\U0001044F'.capitalize(),
+                         u'\U00010427\U0001044F')
+        self.assertEqual(u'\U0001044F\U00010427'.capitalize(),
+                         u'\U00010427\U0001044F')
+        self.assertEqual(u'X\U00010427x\U0001044F'.capitalize(),
+                         u'X\U0001044Fx\U0001044F')
+
+    @requires_wide_build
+    def test_title(self):
+        string_tests.MixinStrUnicodeUserStringTest.test_title(self)
+        self.assertEqual(u'\U0001044F'.title(), u'\U00010427')
+        self.assertEqual(u'\U0001044F\U0001044F'.title(),
+                         u'\U00010427\U0001044F')
+        self.assertEqual(u'\U0001044F\U0001044F \U0001044F\U0001044F'.title(),
+                         u'\U00010427\U0001044F \U00010427\U0001044F')
+        self.assertEqual(u'\U00010427\U0001044F \U00010427\U0001044F'.title(),
+                         u'\U00010427\U0001044F \U00010427\U0001044F')
+        self.assertEqual(u'\U0001044F\U00010427 \U0001044F\U00010427'.title(),
+                         u'\U00010427\U0001044F \U00010427\U0001044F')
+        self.assertEqual(u'X\U00010427x\U0001044F X\U00010427x\U0001044F'.title(),
+                         u'X\U0001044Fx\U0001044F X\U0001044Fx\U0001044F')
+
+    @requires_wide_build
+    def test_swapcase(self):
+        string_tests.CommonTest.test_swapcase(self)
+        self.assertEqual(u'\U0001044F'.swapcase(), u'\U00010427')
+        self.assertEqual(u'\U00010427'.swapcase(), u'\U0001044F')
+        self.assertEqual(u'\U0001044F\U0001044F'.swapcase(),
+                         u'\U00010427\U00010427')
+        self.assertEqual(u'\U00010427\U0001044F'.swapcase(),
+                         u'\U0001044F\U00010427')
+        self.assertEqual(u'\U0001044F\U00010427'.swapcase(),
+                         u'\U00010427\U0001044F')
+        self.assertEqual(u'X\U00010427x\U0001044F'.swapcase(),
+                         u'x\U0001044FX\U00010427')
+
     def test_contains(self):
         # Testing Unicode contains method
         self.assertIn('a', u'abdb')