WIP

Author: giwa

examples/src/main/python/streaming/test_oprations.py

@@ -0,0 +1,24 @@
+import sys
+from operator import add
+
+from pyspark.conf import SparkConf
+from pyspark.streaming.context import StreamingContext
+from pyspark.streaming.duration import *
+
+if __name__ == "__main__":
+    if len(sys.argv) != 3:
+        print >> sys.stderr, "Usage: wordcount <hostname> <port>"
+        exit(-1)
+    conf = SparkConf()
+    conf.setAppName("PythonStreamingNetworkWordCount")
+    ssc = StreamingContext(conf=conf, duration=Seconds(1))
+
+    lines = ssc.socketTextStream(sys.argv[1], int(sys.argv[2]))
+    words = lines.flatMap(lambda line: line.split(" "))
+    mapped_words = words.map(lambda word: (word, 1))
+    count = mapped_words.reduceByKey(add)
+
+    count.pyprint()
+    ssc.start()
+#    ssc.awaitTermination()
+    ssc.stop()

python/pyspark/streaming/dstream.py

@@ -156,7 +156,6 @@ def _mergeCombiners(iterator):
                     combiners[k] = v
                 else:
                     combiners[k] = mergeCombiners(combiners[k], v)
-            return combiners.iteritems()
 
         return shuffled.mapPartitions(_mergeCombiners)