SPARK-1421. Make MLlib work on Python 2.6

docs/mllib-guide.md

@@ -38,6 +38,5 @@ depends on native Fortran routines. You may need to install the
 if it is not already present on your nodes. MLlib will throw a linking error if it cannot 
 detect these libraries automatically.
 
-To use MLlib in Python, you will need [NumPy](http://www.numpy.org) version 1.7 or newer
-and Python 2.7.
+To use MLlib in Python, you will need [NumPy](http://www.numpy.org) version 1.7 or newer.
 

docs/python-programming-guide.md

@@ -152,7 +152,7 @@ Many of the methods also contain [doctests](http://docs.python.org/2/library/doc
 # Libraries
 
 [MLlib](mllib-guide.html) is also available in PySpark. To use it, you'll need
-[NumPy](http://www.numpy.org) version 1.7 or newer, and Python 2.7. The [MLlib guide](mllib-guide.html) contains
+[NumPy](http://www.numpy.org) version 1.7 or newer. The [MLlib guide](mllib-guide.html) contains
 some example applications.
 
 # Where to Go from Here

python/pyspark/mllib/__init__.py

@@ -19,11 +19,7 @@
 Python bindings for MLlib.
 """
 
-# MLlib currently needs Python 2.7+ and NumPy 1.7+, so complain if lower
-
-import sys
-if sys.version_info[0:2] < (2, 7):
-    raise Exception("MLlib requires Python 2.7+")
+# MLlib currently needs and NumPy 1.7+, so complain if lower
 
 import numpy
 if numpy.version.version < '1.7':

python/pyspark/serializers.py

@@ -64,6 +64,7 @@
 from itertools import chain, izip, product
 import marshal
 import struct
+import sys
 from pyspark import cloudpickle
 
 
@@ -113,6 +114,11 @@ class FramedSerializer(Serializer):
     where C{length} is a 32-bit integer and data is C{length} bytes.
     """
 
+    def __init__(self):
+        # On Python 2.6, we can't write bytearrays to streams, so we need to convert them
+        # to strings first. Check if the version number is that old.
+        self._only_write_strings = sys.version_info[0:2] <= (2, 6)
+
     def dump_stream(self, iterator, stream):
         for obj in iterator:
             self._write_with_length(obj, stream)
@@ -127,7 +133,10 @@ def load_stream(self, stream):
     def _write_with_length(self, obj, stream):
         serialized = self.dumps(obj)
         write_int(len(serialized), stream)
-        stream.write(serialized)
+        if self._only_write_strings:
+            stream.write(str(serialized))
+        else:
+            stream.write(serialized)
 
     def _read_with_length(self, stream):
         length = read_int(stream)