Rip out all the u"..." literals and calls to unicode().

Lib/HTMLParser.py

@@ -376,7 +376,7 @@ class HTMLParser(markupbase.ParserBase):
                 # which is not part of HTML 4
                 import htmlentitydefs
                 if HTMLParser.entitydefs is None:
-                    entitydefs = HTMLParser.entitydefs = {'apos':u"'"}
+                    entitydefs = HTMLParser.entitydefs = {'apos':"'"}
                     for k, v in htmlentitydefs.name2codepoint.items():
                         entitydefs[k] = unichr(v)
                 try:

Lib/codecs.py

@@ -589,7 +589,7 @@ class StreamReader(Codec):
 
         """
         self.bytebuffer = ""
-        self.charbuffer = u""
+        self.charbuffer = ""
         self.linebuffer = None
 
     def seek(self, offset, whence=0):

Lib/compiler/transformer.py

@@ -740,7 +740,7 @@ class Transformer:
             # hack... changes in compile.c:parsestr and
             # tokenizer.c must be reflected here.
             if self.encoding not in ['utf-8', 'iso-8859-1']:
-                lit = unicode(lit, 'utf-8').encode(self.encoding)
+                lit = str(lit, 'utf-8').encode(self.encoding)
             return eval("# coding: %s\n%s" % (self.encoding, lit))
         else:
             return eval(lit)
@@ -750,7 +750,7 @@ class Transformer:
         for node in nodelist[1:]:
             k += self.decode_literal(node[1])
         if isinstance(k, bytes):
-          return Bytes(str(k), lineno=nodelist[0][2])
+            return Bytes(str(k), lineno=nodelist[0][2])
         return Const(k, lineno=nodelist[0][2])
 
     def atom_ellipsis(self, nodelist):
@@ -825,7 +825,7 @@ class Transformer:
         else:
             annotation = None
         return SimpleArg(name, annotation, lineno)
-        
+
     def com_arglist(self, nodelist):
         # varargslist:
         #     (fpdef ['=' test] ',')*

Lib/cookielib.py

@@ -644,7 +644,7 @@ def escape_path(path):
     # And here, kind of: draft-fielding-uri-rfc2396bis-03
     # (And in draft IRI specification: draft-duerst-iri-05)
     # (And here, for new URI schemes: RFC 2718)
-    if isinstance(path, unicode):
+    if isinstance(path, str):
         path = path.encode("utf-8")
     path = urllib.quote(path, HTTP_PATH_SAFE)
     path = ESCAPED_CHAR_RE.sub(uppercase_escaped_char, path)

Lib/copy.py

@@ -186,7 +186,7 @@ except NameError:
     pass
 d[str] = _deepcopy_atomic
 try:
-    d[unicode] = _deepcopy_atomic
+    d[str] = _deepcopy_atomic
 except NameError:
     pass
 try:

Lib/ctypes/__init__.py

@@ -59,7 +59,7 @@ def create_string_buffer(init, size=None):
     create_string_buffer(anInteger) -> character array
     create_string_buffer(aString, anInteger) -> character array
     """
-    if isinstance(init, (str, unicode)):
+    if isinstance(init, (str, str)):
         if size is None:
             size = len(init)+1
         buftype = c_char * size
@@ -281,7 +281,7 @@ else:
         create_unicode_buffer(anInteger) -> character array
         create_unicode_buffer(aString, anInteger) -> character array
         """
-        if isinstance(init, (str, unicode)):
+        if isinstance(init, (str, str)):
             if size is None:
                 size = len(init)+1
             buftype = c_wchar * size

Lib/ctypes/macholib/dyld.py

@@ -33,7 +33,7 @@ DEFAULT_LIBRARY_FALLBACK = [
 
 def ensure_utf8(s):
     """Not all of PyObjC and Python understand unicode paths very well yet"""
-    if isinstance(s, unicode):
+    if isinstance(s, str):
         return s.encode('utf8')
     return s
 

Lib/ctypes/test/test_as_parameter.py

@@ -24,7 +24,7 @@ class BasicWrapTestCase(unittest.TestCase):
             return
         f = dll._testfunc_i_bhilfd
         f.argtypes = [c_byte, c_wchar, c_int, c_long, c_float, c_double]
-        result = f(self.wrap(1), self.wrap(u"x"), self.wrap(3), self.wrap(4), self.wrap(5.0), self.wrap(6.0))
+        result = f(self.wrap(1), self.wrap("x"), self.wrap(3), self.wrap(4), self.wrap(5.0), self.wrap(6.0))
         self.failUnlessEqual(result, 139)
         self.failUnless(type(result), int)
 

Lib/ctypes/test/test_buffers.py

@@ -17,7 +17,7 @@ class StringBufferTestCase(unittest.TestCase):
         self.failUnlessEqual(b[:], "abc\0")
 
     def test_string_conversion(self):
-        b = create_string_buffer(u"abc")
+        b = create_string_buffer("abc")
         self.failUnlessEqual(len(b), 4) # trailing nul char
         self.failUnlessEqual(sizeof(b), 4 * sizeof(c_char))
         self.failUnless(type(b[0]) is str)
@@ -33,21 +33,21 @@ class StringBufferTestCase(unittest.TestCase):
             b = create_unicode_buffer(32)
             self.failUnlessEqual(len(b), 32)
             self.failUnlessEqual(sizeof(b), 32 * sizeof(c_wchar))
-            self.failUnless(type(b[0]) is unicode)
+            self.failUnless(type(b[0]) is str)
 
-            b = create_unicode_buffer(u"abc")
+            b = create_unicode_buffer("abc")
             self.failUnlessEqual(len(b), 4) # trailing nul char
             self.failUnlessEqual(sizeof(b), 4 * sizeof(c_wchar))
-            self.failUnless(type(b[0]) is unicode)
-            self.failUnlessEqual(b[0], u"a")
+            self.failUnless(type(b[0]) is str)
+            self.failUnlessEqual(b[0], "a")
             self.failUnlessEqual(b[:], "abc\0")
 
         def test_unicode_conversion(self):
             b = create_unicode_buffer("abc")
             self.failUnlessEqual(len(b), 4) # trailing nul char
             self.failUnlessEqual(sizeof(b), 4 * sizeof(c_wchar))
-            self.failUnless(type(b[0]) is unicode)
-            self.failUnlessEqual(b[0], u"a")
+            self.failUnless(type(b[0]) is str)
+            self.failUnlessEqual(b[0], "a")
             self.failUnlessEqual(b[:], "abc\0")
 
 if __name__ == "__main__":

Lib/ctypes/test/test_functions.py

@@ -70,7 +70,7 @@ class FunctionTestCase(unittest.TestCase):
             return
         f = dll._testfunc_i_bhilfd
         f.argtypes = [c_byte, c_wchar, c_int, c_long, c_float, c_double]
-        result = f(1, u"x", 3, 4, 5.0, 6.0)
+        result = f(1, "x", 3, 4, 5.0, 6.0)
         self.failUnlessEqual(result, 139)
         self.failUnlessEqual(type(result), int)
 
@@ -83,7 +83,7 @@ class FunctionTestCase(unittest.TestCase):
         f.argtypes = [c_byte, c_short, c_int, c_long, c_float, c_double]
         f.restype = c_wchar
         result = f(0, 0, 0, 0, 0, 0)
-        self.failUnlessEqual(result, u'\x00')
+        self.failUnlessEqual(result, '\x00')
 
     def test_voidresult(self):
         f = dll._testfunc_v

Lib/ctypes/test/test_parameters.py

@@ -58,8 +58,8 @@ class SimpleTypesTestCase(unittest.TestCase):
         self.failUnless(c_char_p.from_param(s)._obj is s)
 
         # new in 0.9.1: convert (encode) unicode to ascii
-        self.failUnlessEqual(c_char_p.from_param(u"123")._obj, "123")
-        self.assertRaises(UnicodeEncodeError, c_char_p.from_param, u"123\377")
+        self.failUnlessEqual(c_char_p.from_param("123")._obj, "123")
+        self.assertRaises(UnicodeEncodeError, c_char_p.from_param, "123\377")
 
         self.assertRaises(TypeError, c_char_p.from_param, 42)
 
@@ -75,16 +75,16 @@ class SimpleTypesTestCase(unittest.TestCase):
         except ImportError:
 ##            print "(No c_wchar_p)"
             return
-        s = u"123"
+        s = "123"
         if sys.platform == "win32":
             self.failUnless(c_wchar_p.from_param(s)._obj is s)
             self.assertRaises(TypeError, c_wchar_p.from_param, 42)
 
             # new in 0.9.1: convert (decode) ascii to unicode
-            self.failUnlessEqual(c_wchar_p.from_param("123")._obj, u"123")
+            self.failUnlessEqual(c_wchar_p.from_param("123")._obj, "123")
         self.assertRaises(UnicodeDecodeError, c_wchar_p.from_param, "123\377")
 
-        pa = c_wchar_p.from_param(c_wchar_p(u"123"))
+        pa = c_wchar_p.from_param(c_wchar_p("123"))
         self.failUnlessEqual(type(pa), c_wchar_p)
 
     def test_int_pointers(self):

Lib/ctypes/test/test_prototypes.py

@@ -123,7 +123,7 @@ class CharPointersTestCase(unittest.TestCase):
             pass
         else:
             self.failUnlessEqual(None, func(c_wchar_p(None)))
-            self.failUnlessEqual(u"123", func(c_wchar_p(u"123")))
+            self.failUnlessEqual("123", func(c_wchar_p("123")))
 
     def test_instance(self):
         func = testdll._testfunc_p_p
@@ -157,24 +157,24 @@ else:
             func.argtypes = POINTER(c_wchar),
 
             self.failUnlessEqual(None, func(None))
-            self.failUnlessEqual(u"123", func(u"123"))
+            self.failUnlessEqual("123", func("123"))
             self.failUnlessEqual(None, func(c_wchar_p(None)))
-            self.failUnlessEqual(u"123", func(c_wchar_p(u"123")))
+            self.failUnlessEqual("123", func(c_wchar_p("123")))
 
-            self.failUnlessEqual(u"123", func(c_wbuffer(u"123")))
+            self.failUnlessEqual("123", func(c_wbuffer("123")))
             ca = c_wchar("a")
-            self.failUnlessEqual(u"a", func(pointer(ca))[0])
-            self.failUnlessEqual(u"a", func(byref(ca))[0])
+            self.failUnlessEqual("a", func(pointer(ca))[0])
+            self.failUnlessEqual("a", func(byref(ca))[0])
 
         def test_c_wchar_p_arg(self):
             func = testdll._testfunc_p_p
             func.restype = c_wchar_p
             func.argtypes = c_wchar_p,
 
-            c_wchar_p.from_param(u"123")
+            c_wchar_p.from_param("123")
 
             self.failUnlessEqual(None, func(None))
-            self.failUnlessEqual("123", func(u"123"))
+            self.failUnlessEqual("123", func("123"))
             self.failUnlessEqual(None, func(c_wchar_p(None)))
             self.failUnlessEqual("123", func(c_wchar_p("123")))
 

Lib/ctypes/test/test_slicing.py

@@ -45,7 +45,7 @@ class SlicesTestCase(unittest.TestCase):
 
         import operator
         self.assertRaises(TypeError, operator.setslice,
-                          res, 0, 5, u"abcde")
+                          res, 0, 5, "abcde")
         dll.my_free(res)
 
         dll.my_strdup.restype = POINTER(c_byte)
@@ -88,7 +88,7 @@ class SlicesTestCase(unittest.TestCase):
         pass
     else:
         def test_wchar_ptr(self):
-            s = u"abcdefghijklmnopqrstuvwxyz\0"
+            s = "abcdefghijklmnopqrstuvwxyz\0"
 
             dll = CDLL(_ctypes_test.__file__)
             dll.my_wcsdup.restype = POINTER(c_wchar)
@@ -99,7 +99,7 @@ class SlicesTestCase(unittest.TestCase):
 
             import operator
             self.assertRaises(TypeError, operator.setslice,
-                              res, 0, 5, u"abcde")
+                              res, 0, 5, "abcde")
             dll.my_free(res)
 
             if sizeof(c_wchar) == sizeof(c_short):

Lib/ctypes/test/test_strings.py

@@ -62,17 +62,17 @@ else:
         def test(self):
             BUF = c_wchar * 4
 
-            buf = BUF(u"a", u"b", u"c")
-            self.failUnlessEqual(buf.value, u"abc")
+            buf = BUF("a", "b", "c")
+            self.failUnlessEqual(buf.value, "abc")
 
-            buf.value = u"ABCD"
-            self.failUnlessEqual(buf.value, u"ABCD")
+            buf.value = "ABCD"
+            self.failUnlessEqual(buf.value, "ABCD")
 
-            buf.value = u"x"
-            self.failUnlessEqual(buf.value, u"x")
+            buf.value = "x"
+            self.failUnlessEqual(buf.value, "x")
 
-            buf[1] = u"Z"
-            self.failUnlessEqual(buf.value, u"xZCD")
+            buf[1] = "Z"
+            self.failUnlessEqual(buf.value, "xZCD")
 
 class StringTestCase(unittest.TestCase):
     def XX_test_basic_strings(self):
@@ -99,7 +99,7 @@ class StringTestCase(unittest.TestCase):
         self.failUnlessEqual(cs.value, "XY")
         self.failUnlessEqual(cs.raw, "XY\000\000\000\000\000")
 
-        self.assertRaises(TypeError, c_string, u"123")
+        self.assertRaises(TypeError, c_string, "123")
 
     def XX_test_sized_strings(self):
 
@@ -142,13 +142,13 @@ except NameError:
 else:
     class WStringTestCase(unittest.TestCase):
         def test_wchar(self):
-            c_wchar(u"x")
-            repr(byref(c_wchar(u"x")))
+            c_wchar("x")
+            repr(byref(c_wchar("x")))
             c_wchar("x")
 
 
         def X_test_basic_wstrings(self):
-            cs = c_wstring(u"abcdef")
+            cs = c_wstring("abcdef")
 
             # XXX This behaviour is about to change:
             # len returns the size of the internal buffer in bytes.
@@ -156,30 +156,30 @@ else:
             self.failUnless(sizeof(cs) == 14)
 
             # The value property is the string up to the first terminating NUL.
-            self.failUnless(cs.value == u"abcdef")
-            self.failUnless(c_wstring(u"abc\000def").value == u"abc")
+            self.failUnless(cs.value == "abcdef")
+            self.failUnless(c_wstring("abc\000def").value == "abc")
 
-            self.failUnless(c_wstring(u"abc\000def").value == u"abc")
+            self.failUnless(c_wstring("abc\000def").value == "abc")
 
             # The raw property is the total buffer contents:
-            self.failUnless(cs.raw == u"abcdef\000")
-            self.failUnless(c_wstring(u"abc\000def").raw == u"abc\000def\000")
+            self.failUnless(cs.raw == "abcdef\000")
+            self.failUnless(c_wstring("abc\000def").raw == "abc\000def\000")
 
             # We can change the value:
-            cs.value = u"ab"
-            self.failUnless(cs.value == u"ab")
-            self.failUnless(cs.raw == u"ab\000\000\000\000\000")
+            cs.value = "ab"
+            self.failUnless(cs.value == "ab")
+            self.failUnless(cs.raw == "ab\000\000\000\000\000")
 
             self.assertRaises(TypeError, c_wstring, "123")
             self.assertRaises(ValueError, c_wstring, 0)
 
         def X_test_toolong(self):
-            cs = c_wstring(u"abcdef")
+            cs = c_wstring("abcdef")
             # Much too long string:
-            self.assertRaises(ValueError, setattr, cs, "value", u"123456789012345")
+            self.assertRaises(ValueError, setattr, cs, "value", "123456789012345")
 
             # One char too long values:
-            self.assertRaises(ValueError, setattr, cs, "value", u"1234567")
+            self.assertRaises(ValueError, setattr, cs, "value", "1234567")
 
 
 def run_test(rep, msg, func, arg):

Lib/ctypes/test/test_structures.py

@@ -269,15 +269,15 @@ class StructureTestCase(unittest.TestCase):
             _fields_ = [("name", c_wchar * 12),
                         ("age", c_int)]
 
-        p = PersonW(u"Someone")
+        p = PersonW("Someone")
         self.failUnlessEqual(p.name, "Someone")
 
-        self.failUnlessEqual(PersonW(u"1234567890").name, u"1234567890")
-        self.failUnlessEqual(PersonW(u"12345678901").name, u"12345678901")
+        self.failUnlessEqual(PersonW("1234567890").name, "1234567890")
+        self.failUnlessEqual(PersonW("12345678901").name, "12345678901")
         # exact fit
-        self.failUnlessEqual(PersonW(u"123456789012").name, u"123456789012")
+        self.failUnlessEqual(PersonW("123456789012").name, "123456789012")
         #too long
-        self.assertRaises(ValueError, PersonW, u"1234567890123")
+        self.assertRaises(ValueError, PersonW, "1234567890123")
 
     def test_init_errors(self):
         class Phone(Structure):

Lib/ctypes/test/test_unicode.py

@@ -23,31 +23,31 @@ else:
         def test_ascii_strict(self):
             ctypes.set_conversion_mode("ascii", "strict")
             # no conversions take place with unicode arguments
-            self.failUnlessEqual(wcslen(u"abc"), 3)
-            self.failUnlessEqual(wcslen(u"ab\u2070"), 3)
+            self.failUnlessEqual(wcslen("abc"), 3)
+            self.failUnlessEqual(wcslen("ab\u2070"), 3)
             # string args are converted
             self.failUnlessEqual(wcslen("abc"), 3)
             self.failUnlessRaises(ctypes.ArgumentError, wcslen, "ab")
 
         def test_ascii_replace(self):
             ctypes.set_conversion_mode("ascii", "replace")
-            self.failUnlessEqual(wcslen(u"abc"), 3)
-            self.failUnlessEqual(wcslen(u"ab\u2070"), 3)
+            self.failUnlessEqual(wcslen("abc"), 3)
+            self.failUnlessEqual(wcslen("ab\u2070"), 3)
             self.failUnlessEqual(wcslen("abc"), 3)
             self.failUnlessEqual(wcslen("ab"), 3)
 
         def test_ascii_ignore(self):
             ctypes.set_conversion_mode("ascii", "ignore")
-            self.failUnlessEqual(wcslen(u"abc"), 3)
-            self.failUnlessEqual(wcslen(u"ab\u2070"), 3)
+            self.failUnlessEqual(wcslen("abc"), 3)
+            self.failUnlessEqual(wcslen("ab\u2070"), 3)
             # ignore error mode skips non-ascii characters
             self.failUnlessEqual(wcslen("abc"), 3)
             self.failUnlessEqual(wcslen(""), 0)
 
         def test_latin1_strict(self):
             ctypes.set_conversion_mode("latin-1", "strict")
-            self.failUnlessEqual(wcslen(u"abc"), 3)
-            self.failUnlessEqual(wcslen(u"ab\u2070"), 3)
+            self.failUnlessEqual(wcslen("abc"), 3)
+            self.failUnlessEqual(wcslen("ab\u2070"), 3)
             self.failUnlessEqual(wcslen("abc"), 3)
             self.failUnlessEqual(wcslen(""), 4)
 
@@ -58,12 +58,12 @@ else:
 
             ctypes.set_conversion_mode("ascii", "replace")
             buf = ctypes.create_unicode_buffer("ab")
-            self.failUnlessEqual(buf[:], u"ab\uFFFD\uFFFD\uFFFD\0")
+            self.failUnlessEqual(buf[:], "ab\uFFFD\uFFFD\uFFFD\0")
 
             ctypes.set_conversion_mode("ascii", "ignore")
             buf = ctypes.create_unicode_buffer("ab")
             # is that correct? not sure.  But with 'ignore', you get what you pay for..
-            self.failUnlessEqual(buf[:], u"ab\0\0\0\0")
+            self.failUnlessEqual(buf[:], "ab\0\0\0\0")
 
     import _ctypes_test
     func = ctypes.CDLL(_ctypes_test.__file__)._testfunc_p_p
@@ -82,32 +82,32 @@ else:
         def test_ascii_replace(self):
             ctypes.set_conversion_mode("ascii", "strict")
             self.failUnlessEqual(func("abc"), "abc")
-            self.failUnlessEqual(func(u"abc"), "abc")
-            self.assertRaises(ctypes.ArgumentError, func, u"ab")
+            self.failUnlessEqual(func("abc"), "abc")
+            self.assertRaises(ctypes.ArgumentError, func, "ab")
 
         def test_ascii_ignore(self):
             ctypes.set_conversion_mode("ascii", "ignore")
             self.failUnlessEqual(func("abc"), "abc")
-            self.failUnlessEqual(func(u"abc"), "abc")
-            self.failUnlessEqual(func(u""), "")
+            self.failUnlessEqual(func("abc"), "abc")
+            self.failUnlessEqual(func(""), "")
 
         def test_ascii_replace(self):
             ctypes.set_conversion_mode("ascii", "replace")
             self.failUnlessEqual(func("abc"), "abc")
-            self.failUnlessEqual(func(u"abc"), "abc")
-            self.failUnlessEqual(func(u""), "????")
+            self.failUnlessEqual(func("abc"), "abc")
+            self.failUnlessEqual(func(""), "????")
 
         def test_buffers(self):
             ctypes.set_conversion_mode("ascii", "strict")
-            buf = ctypes.create_string_buffer(u"abc")
+            buf = ctypes.create_string_buffer("abc")
             self.failUnlessEqual(len(buf), 3+1)
 
             ctypes.set_conversion_mode("ascii", "replace")
-            buf = ctypes.create_string_buffer(u"ab")
+            buf = ctypes.create_string_buffer("ab")
             self.failUnlessEqual(buf[:], "ab???\0")
 
             ctypes.set_conversion_mode("ascii", "ignore")
-            buf = ctypes.create_string_buffer(u"ab")
+            buf = ctypes.create_string_buffer("ab")
             # is that correct? not sure.  But with 'ignore', you get what you pay for..
             self.failUnlessEqual(buf[:], "ab\0\0\0\0")
 

Lib/distutils/command/bdist_wininst.py

@@ -247,11 +247,11 @@ class bdist_wininst (Command):
 
         # Convert cfgdata from unicode to ascii, mbcs encoded
         try:
-            unicode
+            str
         except NameError:
             pass
         else:
-            if isinstance(cfgdata, unicode):
+            if isinstance(cfgdata, str):
                 cfgdata = cfgdata.encode("mbcs")
 
         # Append the pre-install script

Lib/distutils/command/build_clib.py

@@ -147,7 +147,7 @@ class build_clib (Command):
                 raise DistutilsSetupError, \
                       "each element of 'libraries' must a 2-tuple"
 
-            if isinstance(lib[0], basestring) StringType:
+            if isinstance(lib[0], basestring):
                 raise DistutilsSetupError, \
                       "first element of each tuple in 'libraries' " + \
                       "must be a string (the library name)"

Lib/distutils/command/register.py

@@ -259,7 +259,7 @@ Your selection [default 1]: ''', end=' ')
             if type(value) not in (type([]), type( () )):
                 value = [value]
             for value in value:
-                value = unicode(value).encode("utf-8")
+                value = str(value).encode("utf-8")
                 body.write(sep_boundary)
                 body.write('\nContent-Disposition: form-data; name="%s"'%key)
                 body.write("\n\n")

Lib/doctest.py

@@ -196,7 +196,7 @@ def _normalize_module(module, depth=2):
     """
     if inspect.ismodule(module):
         return module
-    elif isinstance(module, (str, unicode)):
+    elif isinstance(module, (str, str)):
         return __import__(module, globals(), locals(), ["*"])
     elif module is None:
         return sys.modules[sys._getframe(depth).f_globals['__name__']]

Lib/email/charset.py

@@ -202,10 +202,10 @@ class Charset:
         # is already a unicode, we leave it at that, but ensure that the
         # charset is ASCII, as the standard (RFC XXX) requires.
         try:
-            if isinstance(input_charset, unicode):
+            if isinstance(input_charset, str):
                 input_charset.encode('ascii')
             else:
-                input_charset = unicode(input_charset, 'ascii')
+                input_charset = str(input_charset, 'ascii')
         except UnicodeError:
             raise errors.CharsetError(input_charset)
         input_charset = input_charset.lower()
@@ -264,7 +264,7 @@ class Charset:
     def convert(self, s):
         """Convert a string from the input_codec to the output_codec."""
         if self.input_codec != self.output_codec:
-            return unicode(s, self.input_codec).encode(self.output_codec)
+            return str(s, self.input_codec).encode(self.output_codec)
         else:
             return s
 
@@ -281,10 +281,10 @@ class Charset:
         Characters that could not be converted to Unicode will be replaced
         with the Unicode replacement character U+FFFD.
         """
-        if isinstance(s, unicode) or self.input_codec is None:
+        if isinstance(s, str) or self.input_codec is None:
             return s
         try:
-            return unicode(s, self.input_codec, 'replace')
+            return str(s, self.input_codec, 'replace')
         except LookupError:
             # Input codec not installed on system, so return the original
             # string unchanged.
@@ -307,7 +307,7 @@ class Charset:
             codec = self.output_codec
         else:
             codec = self.input_codec
-        if not isinstance(ustr, unicode) or codec is None:
+        if not isinstance(ustr, str) or codec is None:
             return ustr
         try:
             return ustr.encode(codec, 'replace')

Lib/email/generator.py

@@ -23,7 +23,7 @@ fcre = re.compile(r'^From ', re.MULTILINE)
 def _is8bitstring(s):
     if isinstance(s, str):
         try:
-            unicode(s, 'us-ascii')
+            str(s, 'us-ascii')
         except UnicodeError:
             return True
     return False

Lib/email/header.py

@@ -21,9 +21,9 @@ from email.charset import Charset
 
 NL = '\n'
 SPACE = ' '
-USPACE = u' '
+USPACE = ' '
 SPACE8 = ' ' * 8
-UEMPTYSTRING = u''
+UEMPTYSTRING = ''
 
 MAXLINELEN = 76
 
@@ -210,7 +210,7 @@ class Header:
                 elif nextcs not in (None, 'us-ascii'):
                     uchunks.append(USPACE)
             lastcs = nextcs
-            uchunks.append(unicode(s, str(charset)))
+            uchunks.append(str(s, str(charset)))
         return UEMPTYSTRING.join(uchunks)
 
     # Rich comparison operators for equality only.  BAW: does it make sense to
@@ -257,13 +257,13 @@ class Header:
                 # Possibly raise UnicodeError if the byte string can't be
                 # converted to a unicode with the input codec of the charset.
                 incodec = charset.input_codec or 'us-ascii'
-                ustr = unicode(s, incodec, errors)
+                ustr = str(s, incodec, errors)
                 # Now make sure that the unicode could be converted back to a
                 # byte string with the output codec, which may be different
                 # than the iput coded.  Still, use the original byte string.
                 outcodec = charset.output_codec or 'us-ascii'
                 ustr.encode(outcodec, errors)
-            elif isinstance(s, unicode):
+            elif isinstance(s, str):
                 # Now we have to be sure the unicode string can be converted
                 # to a byte string with a reasonable output codec.  We want to
                 # use the byte string in the chunk.

Lib/email/message.py

@@ -751,13 +751,13 @@ class Message:
                 # LookupError will be raised if the charset isn't known to
                 # Python.  UnicodeError will be raised if the encoded text
                 # contains a character not in the charset.
-                charset = unicode(charset[2], pcharset).encode('us-ascii')
+                charset = str(charset[2], pcharset).encode('us-ascii')
             except (LookupError, UnicodeError):
                 charset = charset[2]
         # charset character must be in us-ascii range
         try:
             if isinstance(charset, str):
-                charset = unicode(charset, 'us-ascii')
+                charset = str(charset, 'us-ascii')
             charset = charset.encode('us-ascii')
         except UnicodeError:
             return failobj

Lib/email/test/test_email.py

@@ -505,7 +505,7 @@ class TestMessageAPI(TestEmailBase):
         msg = Message()
         msg.set_charset('us-ascii')
         self.assertEqual('us-ascii', msg.get_content_charset())
-        msg.set_charset(u'us-ascii')
+        msg.set_charset('us-ascii')
         self.assertEqual('us-ascii', msg.get_content_charset())
 
 
@@ -583,7 +583,7 @@ bug demonstration
         utf8 = Charset("utf-8")
         g_head = "Die Mieter treten hier ein werden mit einem Foerderband komfortabel den Korridor entlang, an s\xfcdl\xfcndischen Wandgem\xe4lden vorbei, gegen die rotierenden Klingen bef\xf6rdert. "
         cz_head = "Finan\xe8ni metropole se hroutily pod tlakem jejich d\xf9vtipu.. "
-        utf8_head = u"\u6b63\u78ba\u306b\u8a00\u3046\u3068\u7ffb\u8a33\u306f\u3055\u308c\u3066\u3044\u307e\u305b\u3093\u3002\u4e00\u90e8\u306f\u30c9\u30a4\u30c4\u8a9e\u3067\u3059\u304c\u3001\u3042\u3068\u306f\u3067\u305f\u3089\u3081\u3067\u3059\u3002\u5b9f\u969b\u306b\u306f\u300cWenn ist das Nunstuck git und Slotermeyer? Ja! Beiherhund das Oder die Flipperwaldt gersput.\u300d\u3068\u8a00\u3063\u3066\u3044\u307e\u3059\u3002".encode("utf-8")
+        utf8_head = "\u6b63\u78ba\u306b\u8a00\u3046\u3068\u7ffb\u8a33\u306f\u3055\u308c\u3066\u3044\u307e\u305b\u3093\u3002\u4e00\u90e8\u306f\u30c9\u30a4\u30c4\u8a9e\u3067\u3059\u304c\u3001\u3042\u3068\u306f\u3067\u305f\u3089\u3081\u3067\u3059\u3002\u5b9f\u969b\u306b\u306f\u300cWenn ist das Nunstuck git und Slotermeyer? Ja! Beiherhund das Oder die Flipperwaldt gersput.\u300d\u3068\u8a00\u3063\u3066\u3044\u307e\u3059\u3002".encode("utf-8")
         h = Header(g_head, g, header_name='Subject')
         h.append(cz_head, cz)
         h.append(utf8_head, utf8)
@@ -1514,7 +1514,7 @@ class TestRFC2047(unittest.TestCase):
         s = '=?ISO-8859-1?Q?Andr=E9?= Pirard <pirard@dom.ain>'
         dh = decode_header(s)
         eq(dh, [('Andr\xe9', 'iso-8859-1'), ('Pirard <pirard@dom.ain>', None)])
-        hu = unicode(make_header(dh)).encode('latin-1')
+        hu = str(make_header(dh)).encode('latin-1')
         eq(hu, 'Andr\xe9 Pirard <pirard@dom.ain>')
 
     def test_whitespace_eater_unicode_2(self):
@@ -1524,7 +1524,7 @@ class TestRFC2047(unittest.TestCase):
         eq(dh, [('The', None), ('quick brown fox', 'iso-8859-1'),
                 ('jumped over the', None), ('lazy dog', 'iso-8859-1')])
         hu = make_header(dh).__unicode__()
-        eq(hu, u'The quick brown fox jumped over the lazy dog')
+        eq(hu, 'The quick brown fox jumped over the lazy dog')
 
     def test_rfc2047_without_whitespace(self):
         s = 'Sm=?ISO-8859-1?B?9g==?=rg=?ISO-8859-1?B?5Q==?=sbord'
@@ -2770,7 +2770,7 @@ class TestCharset(unittest.TestCase):
         eq('hello w\xf6rld', c.body_encode('hello w\xf6rld'))
 
     def test_unicode_charset_name(self):
-        charset = Charset(u'us-ascii')
+        charset = Charset('us-ascii')
         self.assertEqual(str(charset), 'us-ascii')
         self.assertRaises(Errors.CharsetError, Charset, 'asc\xffii')
 
@@ -2809,7 +2809,7 @@ class TestHeader(TestEmailBase):
         utf8 = Charset("utf-8")
         g_head = "Die Mieter treten hier ein werden mit einem Foerderband komfortabel den Korridor entlang, an s\xfcdl\xfcndischen Wandgem\xe4lden vorbei, gegen die rotierenden Klingen bef\xf6rdert. "
         cz_head = "Finan\xe8ni metropole se hroutily pod tlakem jejich d\xf9vtipu.. "
-        utf8_head = u"\u6b63\u78ba\u306b\u8a00\u3046\u3068\u7ffb\u8a33\u306f\u3055\u308c\u3066\u3044\u307e\u305b\u3093\u3002\u4e00\u90e8\u306f\u30c9\u30a4\u30c4\u8a9e\u3067\u3059\u304c\u3001\u3042\u3068\u306f\u3067\u305f\u3089\u3081\u3067\u3059\u3002\u5b9f\u969b\u306b\u306f\u300cWenn ist das Nunstuck git und Slotermeyer? Ja! Beiherhund das Oder die Flipperwaldt gersput.\u300d\u3068\u8a00\u3063\u3066\u3044\u307e\u3059\u3002".encode("utf-8")
+        utf8_head = "\u6b63\u78ba\u306b\u8a00\u3046\u3068\u7ffb\u8a33\u306f\u3055\u308c\u3066\u3044\u307e\u305b\u3093\u3002\u4e00\u90e8\u306f\u30c9\u30a4\u30c4\u8a9e\u3067\u3059\u304c\u3001\u3042\u3068\u306f\u3067\u305f\u3089\u3081\u3067\u3059\u3002\u5b9f\u969b\u306b\u306f\u300cWenn ist das Nunstuck git und Slotermeyer? Ja! Beiherhund das Oder die Flipperwaldt gersput.\u300d\u3068\u8a00\u3063\u3066\u3044\u307e\u3059\u3002".encode("utf-8")
         h = Header(g_head, g)
         h.append(cz_head, cz)
         h.append(utf8_head, utf8)
@@ -2829,7 +2829,7 @@ class TestHeader(TestEmailBase):
         eq(decode_header(enc),
            [(g_head, "iso-8859-1"), (cz_head, "iso-8859-2"),
             (utf8_head, "utf-8")])
-        ustr = unicode(h)
+        ustr = str(h)
         eq(ustr.encode('utf-8'),
            'Die Mieter treten hier ein werden mit einem Foerderband '
            'komfortabel den Korridor entlang, an s\xc3\xbcdl\xc3\xbcndischen '
@@ -2897,9 +2897,9 @@ A very long line that must get split to something other than at the
 
     def test_utf8_shortest(self):
         eq = self.assertEqual
-        h = Header(u'p\xf6stal', 'utf-8')
+        h = Header('p\xf6stal', 'utf-8')
         eq(h.encode(), '=?utf-8?q?p=C3=B6stal?=')
-        h = Header(u'\u83ca\u5730\u6642\u592b', 'utf-8')
+        h = Header('\u83ca\u5730\u6642\u592b', 'utf-8')
         eq(h.encode(), '=?utf-8?b?6I+K5Zyw5pmC5aSr?=')
 
     def test_bad_8bit_header(self):
@@ -3152,7 +3152,7 @@ Content-Disposition: inline;
 '''
         msg = email.message_from_string(m)
         self.assertEqual(msg.get_filename(),
-                         u'This is even more ***fun*** is it not.pdf\ufffd')
+                         'This is even more ***fun*** is it not.pdf\ufffd')
 
     def test_rfc2231_unknown_encoding(self):
         m = """\

Lib/email/test/test_email_codecs.py

@@ -13,7 +13,7 @@ from email.Message import Message
 # We're compatible with Python 2.3, but it doesn't have the built-in Asian
 # codecs, so we have to skip all these tests.
 try:
-    unicode('foo', 'euc-jp')
+    str('foo', 'euc-jp')
 except LookupError:
     raise TestSkipped
 
@@ -57,7 +57,7 @@ Hello World! =?iso-2022-jp?b?GyRCJU8lbSE8JW8hPCVrJUkhKhsoQg==?=
         jcode  = 'euc-jp'
         msg = Message()
         msg.set_payload(jhello, jcode)
-        ustr = unicode(msg.get_payload(), msg.get_content_charset())
+        ustr = str(msg.get_payload(), msg.get_content_charset())
         self.assertEqual(jhello, ustr.encode(jcode))
 
 

Lib/email/test/test_email_codecs_renamed.py

@@ -13,7 +13,7 @@ from email.message import Message
 # We're compatible with Python 2.3, but it doesn't have the built-in Asian
 # codecs, so we have to skip all these tests.
 try:
-    unicode('foo', 'euc-jp')
+    str('foo', 'euc-jp')
 except LookupError:
     raise TestSkipped
 
@@ -57,7 +57,7 @@ Hello World! =?iso-2022-jp?b?GyRCJU8lbSE8JW8hPCVrJUkhKhsoQg==?=
         jcode  = 'euc-jp'
         msg = Message()
         msg.set_payload(jhello, jcode)
-        ustr = unicode(msg.get_payload(), msg.get_content_charset())
+        ustr = str(msg.get_payload(), msg.get_content_charset())
         self.assertEqual(jhello, ustr.encode(jcode))
 
 

Lib/email/test/test_email_renamed.py

@@ -564,7 +564,7 @@ bug demonstration
         utf8 = Charset("utf-8")
         g_head = "Die Mieter treten hier ein werden mit einem Foerderband komfortabel den Korridor entlang, an s\xfcdl\xfcndischen Wandgem\xe4lden vorbei, gegen die rotierenden Klingen bef\xf6rdert. "
         cz_head = "Finan\xe8ni metropole se hroutily pod tlakem jejich d\xf9vtipu.. "
-        utf8_head = u"\u6b63\u78ba\u306b\u8a00\u3046\u3068\u7ffb\u8a33\u306f\u3055\u308c\u3066\u3044\u307e\u305b\u3093\u3002\u4e00\u90e8\u306f\u30c9\u30a4\u30c4\u8a9e\u3067\u3059\u304c\u3001\u3042\u3068\u306f\u3067\u305f\u3089\u3081\u3067\u3059\u3002\u5b9f\u969b\u306b\u306f\u300cWenn ist das Nunstuck git und Slotermeyer? Ja! Beiherhund das Oder die Flipperwaldt gersput.\u300d\u3068\u8a00\u3063\u3066\u3044\u307e\u3059\u3002".encode("utf-8")
+        utf8_head = "\u6b63\u78ba\u306b\u8a00\u3046\u3068\u7ffb\u8a33\u306f\u3055\u308c\u3066\u3044\u307e\u305b\u3093\u3002\u4e00\u90e8\u306f\u30c9\u30a4\u30c4\u8a9e\u3067\u3059\u304c\u3001\u3042\u3068\u306f\u3067\u305f\u3089\u3081\u3067\u3059\u3002\u5b9f\u969b\u306b\u306f\u300cWenn ist das Nunstuck git und Slotermeyer? Ja! Beiherhund das Oder die Flipperwaldt gersput.\u300d\u3068\u8a00\u3063\u3066\u3044\u307e\u3059\u3002".encode("utf-8")
         h = Header(g_head, g, header_name='Subject')
         h.append(cz_head, cz)
         h.append(utf8_head, utf8)
@@ -1512,7 +1512,7 @@ class TestRFC2047(unittest.TestCase):
         s = '=?ISO-8859-1?Q?Andr=E9?= Pirard <pirard@dom.ain>'
         dh = decode_header(s)
         eq(dh, [('Andr\xe9', 'iso-8859-1'), ('Pirard <pirard@dom.ain>', None)])
-        hu = unicode(make_header(dh)).encode('latin-1')
+        hu = str(make_header(dh)).encode('latin-1')
         eq(hu, 'Andr\xe9 Pirard <pirard@dom.ain>')
 
     def test_whitespace_eater_unicode_2(self):
@@ -1522,7 +1522,7 @@ class TestRFC2047(unittest.TestCase):
         eq(dh, [('The', None), ('quick brown fox', 'iso-8859-1'),
                 ('jumped over the', None), ('lazy dog', 'iso-8859-1')])
         hu = make_header(dh).__unicode__()
-        eq(hu, u'The quick brown fox jumped over the lazy dog')
+        eq(hu, 'The quick brown fox jumped over the lazy dog')
 
     def test_rfc2047_missing_whitespace(self):
         s = 'Sm=?ISO-8859-1?B?9g==?=rg=?ISO-8859-1?B?5Q==?=sbord'
@@ -2769,7 +2769,7 @@ class TestCharset(unittest.TestCase):
         eq('hello w\xf6rld', c.body_encode('hello w\xf6rld'))
 
     def test_unicode_charset_name(self):
-        charset = Charset(u'us-ascii')
+        charset = Charset('us-ascii')
         self.assertEqual(str(charset), 'us-ascii')
         self.assertRaises(errors.CharsetError, Charset, 'asc\xffii')
 
@@ -2808,7 +2808,7 @@ class TestHeader(TestEmailBase):
         utf8 = Charset("utf-8")
         g_head = "Die Mieter treten hier ein werden mit einem Foerderband komfortabel den Korridor entlang, an s\xfcdl\xfcndischen Wandgem\xe4lden vorbei, gegen die rotierenden Klingen bef\xf6rdert. "
         cz_head = "Finan\xe8ni metropole se hroutily pod tlakem jejich d\xf9vtipu.. "
-        utf8_head = u"\u6b63\u78ba\u306b\u8a00\u3046\u3068\u7ffb\u8a33\u306f\u3055\u308c\u3066\u3044\u307e\u305b\u3093\u3002\u4e00\u90e8\u306f\u30c9\u30a4\u30c4\u8a9e\u3067\u3059\u304c\u3001\u3042\u3068\u306f\u3067\u305f\u3089\u3081\u3067\u3059\u3002\u5b9f\u969b\u306b\u306f\u300cWenn ist das Nunstuck git und Slotermeyer? Ja! Beiherhund das Oder die Flipperwaldt gersput.\u300d\u3068\u8a00\u3063\u3066\u3044\u307e\u3059\u3002".encode("utf-8")
+        utf8_head = "\u6b63\u78ba\u306b\u8a00\u3046\u3068\u7ffb\u8a33\u306f\u3055\u308c\u3066\u3044\u307e\u305b\u3093\u3002\u4e00\u90e8\u306f\u30c9\u30a4\u30c4\u8a9e\u3067\u3059\u304c\u3001\u3042\u3068\u306f\u3067\u305f\u3089\u3081\u3067\u3059\u3002\u5b9f\u969b\u306b\u306f\u300cWenn ist das Nunstuck git und Slotermeyer? Ja! Beiherhund das Oder die Flipperwaldt gersput.\u300d\u3068\u8a00\u3063\u3066\u3044\u307e\u3059\u3002".encode("utf-8")
         h = Header(g_head, g)
         h.append(cz_head, cz)
         h.append(utf8_head, utf8)
@@ -2828,7 +2828,7 @@ class TestHeader(TestEmailBase):
         eq(decode_header(enc),
            [(g_head, "iso-8859-1"), (cz_head, "iso-8859-2"),
             (utf8_head, "utf-8")])
-        ustr = unicode(h)
+        ustr = str(h)
         eq(ustr.encode('utf-8'),
            'Die Mieter treten hier ein werden mit einem Foerderband '
            'komfortabel den Korridor entlang, an s\xc3\xbcdl\xc3\xbcndischen '
@@ -2896,9 +2896,9 @@ A very long line that must get split to something other than at the
 
     def test_utf8_shortest(self):
         eq = self.assertEqual
-        h = Header(u'p\xf6stal', 'utf-8')
+        h = Header('p\xf6stal', 'utf-8')
         eq(h.encode(), '=?utf-8?q?p=C3=B6stal?=')
-        h = Header(u'\u83ca\u5730\u6642\u592b', 'utf-8')
+        h = Header('\u83ca\u5730\u6642\u592b', 'utf-8')
         eq(h.encode(), '=?utf-8?b?6I+K5Zyw5pmC5aSr?=')
 
     def test_bad_8bit_header(self):
@@ -3151,7 +3151,7 @@ Content-Disposition: inline;
 '''
         msg = email.message_from_string(m)
         self.assertEqual(msg.get_filename(),
-                         u'This is even more ***fun*** is it not.pdf\ufffd')
+                         'This is even more ***fun*** is it not.pdf\ufffd')
 
     def test_rfc2231_unknown_encoding(self):
         m = """\

Lib/email/utils.py

@@ -44,7 +44,7 @@ from email.encoders import _bencode, _qencode
 
 COMMASPACE = ', '
 EMPTYSTRING = ''
-UEMPTYSTRING = u''
+UEMPTYSTRING = ''
 CRLF = '\r\n'
 TICK = "'"
 
@@ -315,9 +315,9 @@ def collapse_rfc2231_value(value, errors='replace',
         rawval = unquote(value[2])
         charset = value[0] or 'us-ascii'
         try:
-            return unicode(rawval, charset, errors)
+            return str(rawval, charset, errors)
         except LookupError:
             # XXX charset is unknown to Python.
-            return unicode(rawval, fallback_charset, errors)
+            return str(rawval, fallback_charset, errors)
     else:
         return unquote(value)

Lib/encodings/__init__.py

@@ -60,7 +60,7 @@ def normalize_encoding(encoding):
     """
     # Make sure we have an 8-bit string, because .translate() works
     # differently for Unicode strings.
-    if isinstance(encoding, unicode):
+    if isinstance(encoding, str):
         # Note that .encode('latin-1') does *not* use the codec
         # registry, so this call doesn't recurse. (See unicodeobject.c
         # PyUnicode_AsEncodedString() for details)

Lib/encodings/punycode.py

@@ -189,7 +189,7 @@ def punycode_decode(text, errors):
     else:
         base = text[:pos]
         extended = text[pos+1:]
-    base = unicode(base, "ascii", errors)
+    base = str(base, "ascii", errors)
     extended = extended.upper()
     return insertion_sort(base, extended, errors)
 

Lib/encodings/utf_8_sig.py

@@ -57,7 +57,7 @@ class IncrementalDecoder(codecs.BufferedIncrementalDecoder):
                 if codecs.BOM_UTF8.startswith(input):
                     # not enough data to decide if this really is a BOM
                     # => try again on the next call
-                    return (u"", 0)
+                    return ("", 0)
                 else:
                     self.first = 0
             else:
@@ -106,7 +106,7 @@ class StreamReader(codecs.StreamReader):
         if len(input) < 3 and codecs.BOM_UTF8.startswith(input):
             # not enough data to decide if this is a BOM
             # => try again on the next call
-            return (u"", 0)
+            return ("", 0)
         self.decode = codecs.utf_8_decode
         return decode(input, errors)
 

Lib/glob.py

@@ -49,8 +49,8 @@ def iglob(pathname):
 def glob1(dirname, pattern):
     if not dirname:
         dirname = os.curdir
-    if isinstance(pattern, unicode) and not isinstance(dirname, unicode):
-        dirname = unicode(dirname, sys.getfilesystemencoding() or
+    if isinstance(pattern, str) and not isinstance(dirname, str):
+        dirname = str(dirname, sys.getfilesystemencoding() or
                                    sys.getdefaultencoding())
     try:
         names = os.listdir(dirname)

Lib/idlelib/EditorWindow.py

@@ -276,7 +276,7 @@ class EditorWindow(object):
 
     def _filename_to_unicode(self, filename):
         """convert filename to unicode in order to display it in Tk"""
-        if isinstance(filename, unicode) or not filename:
+        if isinstance(filename, str) or not filename:
             return filename
         else:
             try:

Lib/idlelib/OutputWindow.py

@@ -39,7 +39,7 @@ class OutputWindow(EditorWindow):
         # we assume that they are in the locale's encoding
         if isinstance(s, str):
             try:
-                s = unicode(s, IOBinding.encoding)
+                s = str(s, IOBinding.encoding)
             except UnicodeError:
                 # some other encoding; let Tcl deal with it
                 pass

Lib/idlelib/PyParse.py

@@ -105,7 +105,7 @@ _tran = ''.join(_tran)
 del ch
 
 try:
-    UnicodeType = type(unicode(""))
+    UnicodeType = type(str(""))
 except NameError:
     UnicodeType = None