fied input of socketTextDStream

Author: Ken Takagiwa

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

@@ -10,7 +10,7 @@
         exit(-1)
     ssc = StreamingContext(appName="PythonStreamingNetworkWordCount", duration=Seconds(1))
 
-    lines = ssc.socketTextStream(sys.argv[1], sys.argv[2])
+    lines = ssc.socketTextStream(sys.argv[1], int(sys.argv[2]))
     fm_lines = lines.flatMap(lambda x: x.split(" "))
     filtered_lines = fm_lines.filter(lambda line: "Spark" in line)
     mapped_lines = fm_lines.map(lambda x: (x, 1))

python/pyspark/java_gateway.py

@@ -111,7 +111,7 @@ def run(self):
     java_import(gateway.jvm, "org.apache.spark.streaming.*")  # do we need this?
     java_import(gateway.jvm, "org.apache.spark.streaming.api.java.*")
     java_import(gateway.jvm, "org.apache.spark.streaming.api.python.*")
-    java_import(gateway.jvm, "org.apache.spark.streaming.dstream.*")  # do we need this?
+    java_import(gateway.jvm, "org.apache.spark.streaming.dstream.*")
     java_import(gateway.jvm, "org.apache.spark.mllib.api.python.*")
     java_import(gateway.jvm, "org.apache.spark.sql.SQLContext")
     java_import(gateway.jvm, "org.apache.spark.sql.hive.HiveContext")