Merge branch 'master' into gl-pickle-extensibility

Author: srikris

oss_src/fileio/union_fstream.cpp

@@ -68,6 +68,7 @@ union_fstream::union_fstream(std::string url,
       input_stream = (*cachestream)->get_underlying_stream();
       if (input_stream == nullptr) input_stream = cachestream;
       m_file_size = (*cachestream)->file_size();
+      original_input_stream_handle = std::static_pointer_cast<std::istream>(cachestream);
     }
   } else if (boost::starts_with(url, "s3://")) {
     // the S3 file type currently works by download/uploading a local file
@@ -80,6 +81,7 @@ union_fstream::union_fstream(std::string url,
       input_stream = (*s3stream)->get_underlying_stream();
       if (input_stream == nullptr) input_stream = s3stream;
       m_file_size = (*s3stream)->file_size();
+      original_input_stream_handle = std::static_pointer_cast<std::istream>(s3stream);
     }
   } else {
     // must be local file

oss_src/fileio/union_fstream.hpp

@@ -66,6 +66,9 @@ class union_fstream {
 
   std::shared_ptr<std::istream> input_stream;
   std::shared_ptr<std::ostream> output_stream;
+
+  // Hold the input stream from cache or s3 stream.
+  std::shared_ptr<std::istream> original_input_stream_handle;
 };
 
 } // namespace graphlab

oss_src/unity/python/sframe/test/test_sframe.py

@@ -1151,8 +1151,8 @@ def test_min_max_with_missing_values(self):
         self.assertEqual(sf2['Var of value'], [1, 0])
         self.assertEqual(sf2['Stdv of value'], [1, 0])
         self.assertEqual(sf2['Count Distinct of value'], [2, 1])
-        self.assertEqual(sorted(sf2['Distinct of value'][0]), sorted([1, None]))
-        self.assertEqual(sorted(sf2['Distinct of value'][1]), sorted([None]))
+        self.assertEqual(set(sf2['Distinct of value'][0]), set([1, None]))
+        self.assertEqual(set(sf2['Distinct of value'][1]), set([None]))
         self.assertEqual(sf2['Frequency Count of value'][0], {1:1, None:5})
         self.assertEqual(sf2['Frequency Count of value'][1], {None:4})