Merging the py3k-pep3137 branch back into the py3k branch.

No detailed change log; just check out the change log for the py3k-pep3137
branch.  The most obvious changes:

  - str8 renamed to bytes (PyString at the C level);
  - bytes renamed to buffer (PyBytes at the C level);
  - PyString and PyUnicode are no longer compatible.

I.e. we now have an immutable bytes type and a mutable bytes type.

The behavior of PyString was modified quite a bit, to make it more
bytes-like.  Some changes are still on the to-do list.

3 files changed, 18 insertions, 7 deletions

diff --git a/Lib/plat-mac/aepack.py b/Lib/plat-mac/aepack.py
index 3caf2f5..e958b85 100644
--- a/Lib/plat-mac/aepack.py
+++ b/Lib/plat-mac/aepack.py
@@ -98,7 +98,7 @@ def pack(x, forcetype = None):
         return AE.AECreateDesc(b'long', struct.pack('l', x))
     if isinstance(x, float):
         return AE.AECreateDesc(b'doub', struct.pack('d', x))
-    if isinstance(x, (bytes, str8)):
+    if isinstance(x, (bytes, buffer)):
         return AE.AECreateDesc(b'TEXT', x)
     if isinstance(x, str):
         # See http://developer.apple.com/documentation/Carbon/Reference/Apple_Event_Manager/Reference/reference.html#//apple_ref/doc/constant_group/typeUnicodeText
diff --git a/Lib/plat-mac/aetypes.py b/Lib/plat-mac/aetypes.py
index cf6e3b9..d29ea97 100644
--- a/Lib/plat-mac/aetypes.py
+++ b/Lib/plat-mac/aetypes.py
@@ -22,7 +22,18 @@ def _four_char_code(four_chars):
     four_chars must contain only ASCII characters.
 
     """
-    return ("%-4.4s" % str(four_chars)).encode("latin-1")
+    if isinstance(four_chars, (bytes, buffer)):
+        b = bytes(four_chars[:4])
+        n = len(b)
+        if n < 4:
+            b += b' ' * (4 - n)
+        return b
+    else:
+        s = str(four_chars)[:4]
+        n = len(s)
+        if n < 4:
+            s += ' ' * (4 - n)
+        return bytes(s, "latin-1")  # MacRoman?
 
 class Unknown:
     """An uninterpreted AE object"""
@@ -47,7 +58,7 @@ class Enum:
         return "Enum(%r)" % (self.enum,)
 
     def __str__(self):
-        return self.enum.strip(b' ')
+        return self.enum.decode("latin-1").strip(" ")
 
     def __aepack__(self):
         return pack(self.enum, typeEnumeration)
@@ -559,7 +570,7 @@ class DelayedComponentItem:
         return "selector for element %s of %s"%(self.__class__.__name__, str(self.fr))
 
 template = """
-class %s(ComponentItem): want = '%s'
+class %s(ComponentItem): want = %r
 """
 
 exec(template % ("Text", b'text'))
diff --git a/Lib/plat-mac/plistlib.py b/Lib/plat-mac/plistlib.py
index e0e01ff..72dfa2e 100644
--- a/Lib/plat-mac/plistlib.py
+++ b/Lib/plat-mac/plistlib.py
@@ -164,7 +164,7 @@ class DumbXMLWriter:
 
     def simpleElement(self, element, value=None):
         if value is not None:
-            value = _escapeAndEncode(value)
+            value = _escape(value)
             self.writeln("<%s>%s</%s>" % (element, value, element))
         else:
             self.writeln("<%s/>" % element)
@@ -207,7 +207,7 @@ _controlCharPat = re.compile(
     r"[\x00\x01\x02\x03\x04\x05\x06\x07\x08\x0b\x0c\x0e\x0f"
     r"\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f]")
 
-def _escapeAndEncode(text):
+def _escape(text):
     m = _controlCharPat.search(text)
     if m is not None:
         raise ValueError("strings can't contains control characters; "
@@ -217,7 +217,7 @@ def _escapeAndEncode(text):
     text = text.replace("&", "&amp;")       # escape '&'
     text = text.replace("<", "&lt;")        # escape '<'
     text = text.replace(">", "&gt;")        # escape '>'
-    return text.encode("utf-8")             # encode as UTF-8
+    return text
 
 
 PLISTHEADER = b"""\