Unicode fixes, basic input/printing of unicode works.

IPython/core/interactiveshell.py

@@ -2265,13 +2265,17 b' class InteractiveShell(Configurable, Magic):'
         The return value can be used to decide whether to use sys.ps1 or
         sys.ps2 to prompt the next line."""
 
+        # We need to ensure that the source is unicode from here on.
+        if type(source)==str:
+            source = source.decode(self.stdin_encoding)
+        
         # if the source code has leading blanks, add 'if 1:\n' to it
         # this allows execution of indented pasted code. It is tempting
         # to add '\n' at the end of source to run commands like ' a=1'
         # directly, but this fails for more complicated scenarios
-        source=source.encode(self.stdin_encoding)
+
         if source[:1] in [' ', '\t']:
-            source = 'if 1:\n%s' % source
+            source = u'if 1:\n%s' % source
 
         try:
             code = self.compile(source,filename,symbol)

IPython/core/splitinput.py

@@ -21,6 +21,7 b' Authors:'
 #-----------------------------------------------------------------------------
 
 import re
+import sys
 
 #-----------------------------------------------------------------------------
 # Main function
@@ -55,7 +56,10 b' def split_user_input(line, pattern=None):'
     This is currently handles lines with '=' in them in a very inconsistent
     manner.
     """
-
+    # We need to ensure that the rest of this routine deals only with unicode
+    if type(line)==str:
+        line = line.decode(sys.stdin.encoding)
+        
     if pattern is None:
         pattern = line_split
     match = pattern.match(line)
@@ -65,15 +69,16 b' def split_user_input(line, pattern=None):'
             ifun, the_rest = line.split(None,1)
         except ValueError:
             # print "split failed for line '%s'" % line
-            ifun, the_rest = line,''
+            ifun, the_rest = line, u''
         pre = re.match('^(\s*)(.*)',line).groups()[0]
     else:
         pre,ifun,the_rest = match.groups()
 
-    # ifun has to be a valid python identifier, so it better be only pure
-    # ascii, no unicode:
+    # ifun has to be a valid python identifier, so it better encode into
+    # ascii.  We do still make it a unicode string so that we consistently
+    # return unicode, but it will be one that is guaranteed to be pure ascii
     try:
-        ifun = ifun.encode('ascii')
+        ifun = unicode(ifun.encode('ascii'))
     except UnicodeEncodeError:
         the_rest = ifun + u' ' + the_rest
         ifun = u''

IPython/zmq/iostream.py

@@ -61,6 +61,11 b' class OutStream(object):'
         if self.pub_socket is None:
             raise ValueError('I/O operation on closed file')
         else:
+            # We can only send raw bytes, not unicode objects, so we encode
+            # into utf-8 for all frontends if we get unicode inputs.
+            if type(string) == unicode:
+                string = string.encode('utf-8')
+                
             self._buffer.write(string)
             current_time = time.time()
             if self._start <= 0: