Patch #445762: Support --disable-unicode

- Do not compile unicodeobject, unicodectype, and unicodedata if Unicode is disabled
- check for Py_USING_UNICODE in all places that use Unicode functions
- disables unicode literals, and the builtin functions
- add the types.StringTypes list
- remove Unicode literals from most tests.

Include/intobject.h

@@ -30,7 +30,9 @@ extern DL_IMPORT(PyTypeObject) PyInt_Type;
 #define PyInt_Check(op) ((op)->ob_type == &PyInt_Type)
 
 extern DL_IMPORT(PyObject *) PyInt_FromString(char*, char**, int);
+#ifdef Py_USING_UNICODE
 extern DL_IMPORT(PyObject *) PyInt_FromUnicode(Py_UNICODE*, int, int);
+#endif
 extern DL_IMPORT(PyObject *) PyInt_FromLong(long);
 extern DL_IMPORT(long) PyInt_AsLong(PyObject *);
 extern DL_IMPORT(long) PyInt_GetMax(void);

Include/longobject.h

@@ -42,7 +42,9 @@ extern DL_IMPORT(unsigned LONG_LONG) PyLong_AsUnsignedLongLong(PyObject *);
 #endif /* HAVE_LONG_LONG */
 
 DL_IMPORT(PyObject *) PyLong_FromString(char *, char **, int);
+#ifdef Py_USING_UNICODE
 DL_IMPORT(PyObject *) PyLong_FromUnicode(Py_UNICODE*, int, int);
+#endif
 
 /* _PyLong_FromByteArray:  View the n unsigned bytes as a binary integer in
    base 256, and return a Python long with the same numeric value.

Include/object.h

@@ -320,7 +320,9 @@ extern DL_IMPORT(int) PyObject_Print(PyObject *, FILE *, int);
 extern DL_IMPORT(void) _PyObject_Dump(PyObject *);
 extern DL_IMPORT(PyObject *) PyObject_Repr(PyObject *);
 extern DL_IMPORT(PyObject *) PyObject_Str(PyObject *);
+#ifdef Py_USING_UNICODE
 extern DL_IMPORT(PyObject *) PyObject_Unicode(PyObject *);
+#endif
 extern DL_IMPORT(int) PyObject_Compare(PyObject *, PyObject *);
 extern DL_IMPORT(PyObject *) PyObject_RichCompare(PyObject *, PyObject *, int);
 extern DL_IMPORT(int) PyObject_RichCompareBool(PyObject *, PyObject *, int);

Include/unicodeobject.h

@@ -58,6 +58,12 @@ Copyright (c) Corporation for National Research Initiatives.
 
 /* --- Internal Unicode Format -------------------------------------------- */
 
+#ifndef Py_USING_UNICODE
+
+#define PyUnicode_Check(op)                 0
+
+#else
+
 /* FIXME: MvL's new implementation assumes that Py_UNICODE_SIZE is
    properly set, but the default rules below doesn't set it.  I'll
    sort this out some other day -- fredrik@pythonware.com */
@@ -1087,4 +1093,5 @@ extern DL_IMPORT(int) _PyUnicode_IsAlpha(
 #ifdef __cplusplus
 }
 #endif
+#endif /* Py_USING_UNICODE */
 #endif /* !Py_UNICODEOBJECT_H */

Lib/ConfigParser.py

@@ -82,7 +82,7 @@ ConfigParser -- responsible for for parsing a list of
         write the configuration state in .ini format
 """
 
-import string
+import string, types
 import re
 
 __all__ = ["NoSectionError","DuplicateSectionError","NoOptionError",
@@ -222,7 +222,7 @@ class ConfigParser:
         configuration files in the list will be read.  A single
         filename may also be given.
         """
-        if type(filenames) in [type(''), type(u'')]:
+        if type(filenames) in types.StringTypes:
             filenames = [filenames]
         for filename in filenames:
             try:

Lib/copy.py

@@ -91,7 +91,10 @@ d[types.IntType] = _copy_atomic
 d[types.LongType] = _copy_atomic
 d[types.FloatType] = _copy_atomic
 d[types.StringType] = _copy_atomic
-d[types.UnicodeType] = _copy_atomic
+try:
+    d[types.UnicodeType] = _copy_atomic
+except AttributeError:
+    pass
 try:
     d[types.CodeType] = _copy_atomic
 except AttributeError:
@@ -170,7 +173,10 @@ d[types.IntType] = _deepcopy_atomic
 d[types.LongType] = _deepcopy_atomic
 d[types.FloatType] = _deepcopy_atomic
 d[types.StringType] = _deepcopy_atomic
-d[types.UnicodeType] = _deepcopy_atomic
+try:
+    d[types.UnicodeType] = _deepcopy_atomic
+except AttributeError:
+    pass
 d[types.CodeType] = _deepcopy_atomic
 d[types.TypeType] = _deepcopy_atomic
 d[types.XRangeType] = _deepcopy_atomic

Lib/site.py

@@ -305,7 +305,8 @@ if 0:
     encoding = "undefined"
 
 if encoding != "ascii":
-    sys.setdefaultencoding(encoding)
+    # On Non-Unicode builds this will raise an AttributeError...
+    sys.setdefaultencoding(encoding) # Needs Python Unicode build !
 
 #
 # Run custom site specific code, if available.

Lib/test/pickletester.py

@@ -1,6 +1,6 @@
 # test_pickle and test_cpickle both use this.
 
-from test_support import TestFailed
+from test_support import TestFailed, have_unicode
 import sys
 
 # break into multiple strings to please font-lock-mode
@@ -191,7 +191,11 @@ def dotest(pickle):
             print "accepted insecure string: %s" % repr(buf)
 
     # Test some Unicode end cases
-    endcases = [u'', u'<\\u>', u'<\\\u1234>', u'<\n>',  u'<\\>']
+    if have_unicode:
+        endcases = [unicode(''), unicode('<\\u>'), unicode('<\\\u1234>'),
+                    unicode('<\n>'),  unicode('<\\>')]
+    else:
+        endcases = []
     for u in endcases:
         try:
             u2 = pickle.loads(pickle.dumps(u))

Lib/test/string_tests.py

@@ -1,7 +1,7 @@
 """Common tests shared by test_string and test_userstring"""
 
 import string
-from test_support import verify, verbose, TestFailed
+from test_support import verify, verbose, TestFailed, have_unicode
 
 transtable = '\000\001\002\003\004\005\006\007\010\011\012\013\014\015\016\017\020\021\022\023\024\025\026\027\030\031\032\033\034\035\036\037 !"#$%&\'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`xyzdefghijklmnopqrstuvwxyz{|}~\177\200\201\202\203\204\205\206\207\210\211\212\213\214\215\216\217\220\221\222\223\224\225\226\227\230\231\232\233\234\235\236\237\240\241\242\243\244\245\246\247\250\251\252\253\254\255\256\257\260\261\262\263\264\265\266\267\270\271\272\273\274\275\276\277\300\301\302\303\304\305\306\307\310\311\312\313\314\315\316\317\320\321\322\323\324\325\326\327\330\331\332\333\334\335\336\337\340\341\342\343\344\345\346\347\350\351\352\353\354\355\356\357\360\361\362\363\364\365\366\367\370\371\372\373\374\375\376\377'
 
@@ -125,11 +125,12 @@ def run_method_tests(test):
     test('join', ' ', 'w x y z', Sequence())
     test('join', 'a', 'abc', ('abc',))
     test('join', 'a', 'z', UserList(['z']))
-    test('join', u'.', u'a.b.c', ['a', 'b', 'c'])
-    test('join', '.', u'a.b.c', [u'a', 'b', 'c'])
-    test('join', '.', u'a.b.c', ['a', u'b', 'c'])
-    test('join', '.', u'a.b.c', ['a', 'b', u'c'])
-    test('join', '.', TypeError, ['a', u'b', 3])
+    if have_unicode:
+        test('join', unicode('.'), unicode('a.b.c'), ['a', 'b', 'c'])
+        test('join', '.', unicode('a.b.c'), [unicode('a'), 'b', 'c'])
+        test('join', '.', unicode('a.b.c'), ['a', unicode('b'), 'c'])
+        test('join', '.', unicode('a.b.c'), ['a', 'b', unicode('c')])
+        test('join', '.', TypeError, ['a', unicode('b'), 3])
     for i in [5, 25, 125]:
         test('join', '-', ((('a' * i) + '-') * i)[:-1],
              ['a' * i] * i)

Lib/test/test_b1.py

@@ -119,7 +119,9 @@ if complex(0.0, 3.14j) != -3.14+0j: raise TestFailed, 'complex(0.0, 3.14j)'
 if complex(0j, 3.14) != 3.14j: raise TestFailed, 'complex(0j, 3.14)'
 if complex(0.0, 3.14) != 3.14j: raise TestFailed, 'complex(0.0, 3.14)'
 if complex("  3.14+J  ") != 3.14+1j:  raise TestFailed, 'complex("  3.14+J  )"'
-if complex(u"  3.14+J  ") != 3.14+1j:  raise TestFailed, 'complex(u"  3.14+J  )"'
+if have_unicode:
+    if complex(unicode("  3.14+J  ")) != 3.14+1j:
+        raise TestFailed, 'complex(u"  3.14+J  )"'
 class Z:
     def __complex__(self): return 3.14j
 z = Z()
@@ -174,18 +176,20 @@ if eval('b', globals, locals) != 200:
     raise TestFailed, "eval(3)"
 if eval('c', globals, locals) != 300:
     raise TestFailed, "eval(4)"
-if eval(u'1+1') != 2: raise TestFailed, 'eval(u\'1+1\')'
-if eval(u' 1+1\n') != 2: raise TestFailed, 'eval(u\' 1+1\\n\')'
+if have_unicode:
+    if eval(unicode('1+1')) != 2: raise TestFailed, 'eval(u\'1+1\')'
+    if eval(unicode(' 1+1\n')) != 2: raise TestFailed, 'eval(u\' 1+1\\n\')'
 globals = {'a': 1, 'b': 2}
 locals = {'b': 200, 'c': 300}
-if eval(u'a', globals) != 1:
-    raise TestFailed, "eval(1) == %s" % eval(u'a', globals)
-if eval(u'a', globals, locals) != 1:
-    raise TestFailed, "eval(2)"
-if eval(u'b', globals, locals) != 200:
-    raise TestFailed, "eval(3)"
-if eval(u'c', globals, locals) != 300:
-    raise TestFailed, "eval(4)"
+if have_unicode:
+    if eval(unicode('a'), globals) != 1:
+        raise TestFailed, "eval(1) == %s" % eval(unicode('a'), globals)
+    if eval(unicode('a'), globals, locals) != 1:
+        raise TestFailed, "eval(2)"
+    if eval(unicode('b'), globals, locals) != 200:
+        raise TestFailed, "eval(3)"
+    if eval(unicode('c'), globals, locals) != 300:
+        raise TestFailed, "eval(4)"
 
 print 'execfile'
 z = 0
@@ -249,9 +253,11 @@ if float(3.14) != 3.14: raise TestFailed, 'float(3.14)'
 if float(314) != 314.0: raise TestFailed, 'float(314)'
 if float(314L) != 314.0: raise TestFailed, 'float(314L)'
 if float("  3.14  ") != 3.14:  raise TestFailed, 'float("  3.14  ")'
-if float(u"  3.14  ") != 3.14:  raise TestFailed, 'float(u"  3.14  ")'
-if float(u"  \u0663.\u0661\u0664  ") != 3.14:
-    raise TestFailed, 'float(u"  \u0663.\u0661\u0664  ")'
+if have_unicode:
+    if float(unicode("  3.14  ")) != 3.14:
+        raise TestFailed, 'float(u"  3.14  ")'
+    if float(unicode("  \u0663.\u0661\u0664  ")) != 3.14:
+        raise TestFailed, 'float(u"  \u0663.\u0661\u0664  ")'
 
 print 'getattr'
 import sys
@@ -324,7 +330,9 @@ if int(3.5) != 3: raise TestFailed, 'int(3.5)'
 if int(-3.5) != -3: raise TestFailed, 'int(-3.5)'
 # Different base:
 if int("10",16) != 16L: raise TestFailed, 'int("10",16)'
-if int(u"10",16) != 16L: raise TestFailed, 'int(u"10",16)'
+if have_unicode:
+    if int(unicode("10"),16) != 16L:
+        raise TestFailed, 'int(u"10",16)'
 # Test conversion from strings and various anomalies
 L = [
         ('0', 0),
@@ -343,23 +351,26 @@ L = [
         ('  1\02  ', ValueError),
         ('', ValueError),
         (' ', ValueError),
-        ('  \t\t  ', ValueError),
-        (u'0', 0),
-        (u'1', 1),
-        (u'9', 9),
-        (u'10', 10),
-        (u'99', 99),
-        (u'100', 100),
-        (u'314', 314),
-        (u' 314', 314),
-        (u'\u0663\u0661\u0664 ', 314),
-        (u'  \t\t  314  \t\t  ', 314),
-        (u'  1x', ValueError),
-        (u'  1  ', 1),
-        (u'  1\02  ', ValueError),
-        (u'', ValueError),
-        (u' ', ValueError),
-        (u'  \t\t  ', ValueError),
+        ('  \t\t  ', ValueError)
+]
+if have_unicode:
+    L += [
+        (unicode('0'), 0),
+        (unicode('1'), 1),
+        (unicode('9'), 9),
+        (unicode('10'), 10),
+        (unicode('99'), 99),
+        (unicode('100'), 100),
+        (unicode('314'), 314),
+        (unicode(' 314'), 314),
+        (unicode('\u0663\u0661\u0664 '), 314),
+        (unicode('  \t\t  314  \t\t  '), 314),
+        (unicode('  1x'), ValueError),
+        (unicode('  1  '), 1),
+        (unicode('  1\02  '), ValueError),
+        (unicode(''), ValueError),
+        (unicode(' '), ValueError),
+        (unicode('  \t\t  '), ValueError),
 ]
 for s, v in L:
     for sign in "", "+", "-":
@@ -460,16 +471,23 @@ if long(-3.9) != -3L: raise TestFailed, 'long(-3.9)'
 if long(3.5) != 3L: raise TestFailed, 'long(3.5)'
 if long(-3.5) != -3L: raise TestFailed, 'long(-3.5)'
 if long("-3") != -3L: raise TestFailed, 'long("-3")'
-if long(u"-3") != -3L: raise TestFailed, 'long(u"-3")'
+if have_unicode:
+    if long(unicode("-3")) != -3L:
+        raise TestFailed, 'long(u"-3")'
 # Different base:
 if long("10",16) != 16L: raise TestFailed, 'long("10",16)'
-if long(u"10",16) != 16L: raise TestFailed, 'long(u"10",16)'
+if have_unicode:
+    if long(unicode("10"),16) != 16L:
+        raise TestFailed, 'long(u"10",16)'
 # Check conversions from string (same test set as for int(), and then some)
 LL = [
         ('1' + '0'*20, 10L**20),
-        ('1' + '0'*100, 10L**100),
-        (u'1' + u'0'*20, 10L**20),
-        (u'1' + u'0'*100, 10L**100),
+        ('1' + '0'*100, 10L**100)
+]
+if have_unicode:
+    L+=[
+        (unicode('1') + unicode('0')*20, 10L**20),
+        (unicode('1') + unicode('0')*100, 10L**100),
 ]
 for s, v in L + LL:
     for sign in "", "+", "-":

Lib/test/test_contains.py

@@ -1,4 +1,4 @@
-from test_support import TestFailed
+from test_support import TestFailed, have_unicode
 
 class base_set:
 
@@ -63,62 +63,65 @@ try:
 except TypeError:
     pass
 
-# Test char in Unicode
 
-check('c' in u'abc', "'c' not in u'abc'")
-check('d' not in u'abc', "'d' in u'abc'")
+if have_unicode:
 
-try:
-    '' in u'abc'
-    check(0, "'' in u'abc' did not raise error")
-except TypeError:
-    pass
+    # Test char in Unicode
 
-try:
-    'ab' in u'abc'
-    check(0, "'ab' in u'abc' did not raise error")
-except TypeError:
-    pass
+    check('c' in unicode('abc'), "'c' not in u'abc'")
+    check('d' not in unicode('abc'), "'d' in u'abc'")
 
-try:
-    None in u'abc'
-    check(0, "None in u'abc' did not raise error")
-except TypeError:
-    pass
+    try:
+        '' in unicode('abc')
+        check(0, "'' in u'abc' did not raise error")
+    except TypeError:
+        pass
 
-# Test Unicode char in Unicode
+    try:
+        'ab' in unicode('abc')
+        check(0, "'ab' in u'abc' did not raise error")
+    except TypeError:
+        pass
 
-check(u'c' in u'abc', "u'c' not in u'abc'")
-check(u'd' not in u'abc', "u'd' in u'abc'")
+    try:
+        None in unicode('abc')
+        check(0, "None in u'abc' did not raise error")
+    except TypeError:
+        pass
 
-try:
-    u'' in u'abc'
-    check(0, "u'' in u'abc' did not raise error")
-except TypeError:
-    pass
+    # Test Unicode char in Unicode
 
-try:
-    u'ab' in u'abc'
-    check(0, "u'ab' in u'abc' did not raise error")
-except TypeError:
-    pass
+    check(unicode('c') in unicode('abc'), "u'c' not in u'abc'")
+    check(unicode('d') not in unicode('abc'), "u'd' in u'abc'")
 
-# Test Unicode char in string
+    try:
+        unicode('') in unicode('abc')
+        check(0, "u'' in u'abc' did not raise error")
+    except TypeError:
+        pass
 
-check(u'c' in 'abc', "u'c' not in 'abc'")
-check(u'd' not in 'abc', "u'd' in 'abc'")
+    try:
+        unicode('ab') in unicode('abc')
+        check(0, "u'ab' in u'abc' did not raise error")
+    except TypeError:
+        pass
 
-try:
-    u'' in 'abc'
-    check(0, "u'' in 'abc' did not raise error")
-except TypeError:
-    pass
+    # Test Unicode char in string
 
-try:
-    u'ab' in 'abc'
-    check(0, "u'ab' in 'abc' did not raise error")
-except TypeError:
-    pass
+    check(unicode('c') in 'abc', "u'c' not in 'abc'")
+    check(unicode('d') not in 'abc', "u'd' in 'abc'")
+
+    try:
+        unicode('') in 'abc'
+        check(0, "u'' in 'abc' did not raise error")
+    except TypeError:
+        pass
+
+    try:
+        unicode('ab') in 'abc'
+        check(0, "u'ab' in 'abc' did not raise error")
+    except TypeError:
+        pass
 
 # A collection of tests on builtin sequence types
 a = range(10)

Lib/test/test_format.py

@@ -1,4 +1,4 @@
-from test_support import verbose
+from test_support import verbose, have_unicode
 import sys
 
 # test string formatting operator (I am not sure if this is being tested
@@ -34,7 +34,8 @@ def testformat(formatstr, args, output=None):
 
 def testboth(formatstr, *args):
     testformat(formatstr, *args)
-    testformat(unicode(formatstr), *args)
+    if have_unicode:
+        testformat(unicode(formatstr), *args)
 
 
 testboth("%.1d", (1,), "1")
@@ -212,5 +213,6 @@ def test_exc(formatstr, args, exception, excmsg):
 
 test_exc('abc %a', 1, ValueError,
          "unsupported format character 'a' (0x61) at index 5")
-test_exc(u'abc %\u3000', 1, ValueError,
-         "unsupported format character '?' (0x3000) at index 5")
+if have_unicode:
+    test_exc(unicode('abc %\u3000'), 1, ValueError,
+             "unsupported format character '?' (0x3000) at index 5")

Lib/test/test_iter.py

@@ -1,7 +1,7 @@
 # Test iterators.
 
 import unittest
-from test_support import run_unittest, TESTFN, unlink
+from test_support import run_unittest, TESTFN, unlink, have_unicode
 
 # Test result of triple loop (too big to inline)
 TRIPLETS = [(0, 0, 0), (0, 0, 1), (0, 0, 2),
@@ -214,8 +214,11 @@ class TestCase(unittest.TestCase):
         self.check_for_loop(iter("abcde"), ["a", "b", "c", "d", "e"])
 
     # Test a Unicode string
-    def test_iter_unicode(self):
-        self.check_for_loop(iter(u"abcde"), [u"a", u"b", u"c", u"d", u"e"])
+    if have_unicode:
+        def test_iter_unicode(self):
+            self.check_for_loop(iter(unicode("abcde")),
+                                [unicode("a"), unicode("b"), unicode("c"),
+                                 unicode("d"), unicode("e")])
 
     # Test a directory
     def test_iter_dict(self):
@@ -477,6 +480,7 @@ class TestCase(unittest.TestCase):
         d = {"one": 1, "two": 2, "three": 3}
         self.assertEqual(reduce(add, d), "".join(d.keys()))
 
+    # This test case will be removed if we don't have Unicode
     def test_unicode_join_endcase(self):
 
         # This class inserts a Unicode object into its argument's natural
@@ -493,7 +497,7 @@ class TestCase(unittest.TestCase):
                 i = self.i
                 self.i = i+1
                 if i == 2:
-                    return u"fooled you!"
+                    return unicode("fooled you!")
                 return self.it.next()
 
         f = open(TESTFN, "w")
@@ -510,13 +514,15 @@ class TestCase(unittest.TestCase):
         # and pass that on to unicode.join().
         try:
             got = " - ".join(OhPhooey(f))
-            self.assertEqual(got, u"a\n - b\n - fooled you! - c\n")
+            self.assertEqual(got, unicode("a\n - b\n - fooled you! - c\n"))
         finally:
             f.close()
             try:
                 unlink(TESTFN)
             except OSError:
                 pass
+    if not have_unicode:
+        def test_unicode_join_endcase(self): pass
 
     # Test iterators with 'x in y' and 'x not in y'.
     def test_in_and_not_in(self):

Lib/test/test_pprint.py

@@ -3,6 +3,11 @@ import unittest
 
 import test_support
 
+try:
+    uni = unicode
+except NameError:
+    def uni(x):return x
+
 
 class QueryTestCase(unittest.TestCase):
 
@@ -14,7 +19,7 @@ class QueryTestCase(unittest.TestCase):
     def test_basic(self):
         """Verify .isrecursive() and .isreadable() w/o recursion."""
         verify = self.assert_
-        for safe in (2, 2.0, 2j, "abc", [3], (2,2), {3: 3}, u"yaddayadda",
+        for safe in (2, 2.0, 2j, "abc", [3], (2,2), {3: 3}, uni("yaddayadda"),
                      self.a, self.b):
             verify(not pprint.isrecursive(safe),
                    "expected not isrecursive for " + `safe`)
@@ -58,8 +63,8 @@ class QueryTestCase(unittest.TestCase):
     def test_same_as_repr(self):
         "Simple objects and small containers that should be same as repr()."
         verify = self.assert_
-        for simple in (0, 0L, 0+0j, 0.0, "", u"", (), [], {}, verify, pprint,
-                       -6, -6L, -6-6j, -1.5, "x", u"x", (3,), [3], {3: 6},
+        for simple in (0, 0L, 0+0j, 0.0, "", uni(""), (), [], {}, verify, pprint,
+                       -6, -6L, -6-6j, -1.5, "x", uni("x"), (3,), [3], {3: 6},
                        (1,2), [3,4], {5: 6, 7: 8},
                        {"xy\tab\n": (3,), 5: [[]], (): {}},
                        range(10, -11, -1)

Lib/test/test_sre.py

@@ -6,7 +6,7 @@
 import sys
 sys.path=['.']+sys.path
 
-from test_support import verbose, TestFailed
+from test_support import verbose, TestFailed, have_unicode
 import sre
 import sys, os, string, traceback
 
@@ -378,7 +378,8 @@ for t in tests:
 
             # Try the match with UNICODE locale enabled, and check
             # that it still succeeds.
-            obj=sre.compile(pattern, sre.UNICODE)
-            result=obj.search(s)
-            if result==None:
-                print '=== Fails on unicode-sensitive match', t
+            if have_unicode:
+                obj=sre.compile(pattern, sre.UNICODE)
+                result=obj.search(s)
+                if result==None:
+                    print '=== Fails on unicode-sensitive match', t

Lib/test/test_support.py

@@ -56,6 +56,12 @@ def fcmp(x, y): # fuzzy comparison function
         return cmp(len(x), len(y))
     return cmp(x, y)
 
+try:
+    unicode
+    have_unicode = 1
+except NameError:
+    have_unicode = 0
+
 import os
 # Filename used for testing
 if os.name == 'java':
@@ -64,9 +70,10 @@ if os.name == 'java':
 elif os.name != 'riscos':
     TESTFN = '@test'
     # Unicode name only used if TEST_FN_ENCODING exists for the platform.
-    TESTFN_UNICODE=u"@test-\xe0\xf2" # 2 latin characters.
-    if os.name=="nt":
-        TESTFN_ENCODING="mbcs"
+    if have_unicode:
+        TESTFN_UNICODE=unicode("@test-\xe0\xf2", "latin-1") # 2 latin characters.
+        if os.name=="nt":
+            TESTFN_ENCODING="mbcs"
 else:
     TESTFN = 'test'
 del os

Lib/test/test_winreg.py

@@ -4,21 +4,24 @@
 from _winreg import *
 import os, sys
 
-from test_support import verify
+from test_support import verify, have_unicode
 
 test_key_name = "SOFTWARE\\Python Registry Test Key - Delete Me"
 
 test_data = [
     ("Int Value",     45,                                      REG_DWORD),
     ("String Val",    "A string value",                        REG_SZ,),
-    (u"Unicode Val",  u"A Unicode value",                      REG_SZ,),
     ("StringExpand",  "The path is %path%",                    REG_EXPAND_SZ),
-    ("UnicodeExpand", u"The path is %path%",                   REG_EXPAND_SZ),
     ("Multi-string",  ["Lots", "of", "string", "values"],      REG_MULTI_SZ),
-    ("Multi-unicode", [u"Lots", u"of", u"unicode", u"values"], REG_MULTI_SZ),
-    ("Multi-mixed",   [u"Unicode", u"and", "string", "values"],REG_MULTI_SZ),
     ("Raw Data",      ("binary"+chr(0)+"data"),                REG_BINARY),
 ]
+if have_unicode:
+    test_data+=[
+    (unicode("Unicode Val"),  unicode("A Unicode value"),                      REG_SZ,),
+    ("UnicodeExpand", unicode("The path is %path%"),                   REG_EXPAND_SZ),
+    ("Multi-unicode", [unicode("Lots"), unicode("of"), unicode("unicode"), unicode("values")], REG_MULTI_SZ),
+    ("Multi-mixed",   [unicode("Unicode"), unicode("and"), "string", "values"],REG_MULTI_SZ),
+    ]
 
 def WriteTestData(root_key):
     # Set the default value for this key.

Lib/types.py

@@ -19,7 +19,12 @@ except NameError:
     pass
 
 StringType = str
-UnicodeType = unicode
+try:
+    UnicodeType = unicode
+    StringTypes = [StringType, UnicodeType]
+except NameError:
+    StringTypes = [StringType]
+
 BufferType = type(buffer(''))
 
 TupleType = tuple

Makefile.pre.in

@@ -147,6 +147,7 @@ LIBOBJS=	@LIBOBJS@
 DLINCLDIR=	@DLINCLDIR@
 DYNLOADFILE=	@DYNLOADFILE@
 MACHDEP_OBJS=	@MACHDEP_OBJS@
+UNICODE_OBJS=   @UNICODE_OBJS@
 
 PYTHON=		python$(EXE)
 
@@ -263,8 +264,7 @@ OBJECT_OBJS=	\
 		Objects/stringobject.o \
 		Objects/tupleobject.o \
 		Objects/typeobject.o \
-		Objects/unicodeobject.o \
-		Objects/unicodectype.o
+		$(UNICODE_OBJS)
 
 
 ##########################################################################

Misc/NEWS

@@ -1,6 +1,12 @@
 What's New in Python 2.2a2?
 ===========================
 
+Build
+
+- configure supports a new option --enable-unicode, with the values
+  ucs2 and ucs4 (new in 2.2a1). With --disable-unicode, the Unicode
+  type and supporting code is completely removed from the interpreter.
+
 Tools
 
 - The new Tools/scripts/cleanfuture.py can be used to automatically
@@ -57,6 +63,12 @@ C API
   sure to check the Unicode width compatibility in their extensions by
   using at least one of the mangled Unicode APIs in the extension.
 
+- Two new flags METH_NOARGS and METH_O are available in method definition
+  tables to simplify implementation of methods with no arguments and a
+  single untyped argument. Calling such methods is more efficient than
+  calling corresponding METH_VARARGS methods. METH_OLDARGS is now
+  deprecated.
+
 Windows
 
 - "import module" now compiles module.pyw if it exists and nothing else
@@ -90,12 +102,6 @@ Core
   (These warnings currently don't conform to the warnings framework of
   PEP 230; we intend to fix this in 2.2a2.)
 
-- Two new flags METH_NOARGS and METH_O are available in method definition
-  tables to simplify implementation of methods with no arguments and a
-  single untyped argument. Calling such methods is more efficient than
-  calling corresponding METH_VARARGS methods. METH_OLDARGS is now
-  deprecated.
-
 - The UTF-16 codec was modified to be more RFC compliant. It will now
   only remove BOM characters at the start of the string and then
   only if running in native mode (UTF-16-LE and -BE won't remove a