Github user srowen commented on a diff in the pull request:
https://github.com/apache/spark/pull/4589#discussion_r24668926
--- Diff:
examples/src/main/java/org/apache/spark/examples/streaming/JavaStatefulNetworkWordCount.java
---
@@ -0,0 +1,111 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.examples.streaming;
+
+import java.util.List;
+import java.util.regex.Pattern;
+
+import scala.Tuple2;
+
+import com.google.common.base.Optional;
+import com.google.common.collect.Lists;
+
+import org.apache.spark.SparkConf;
+import org.apache.spark.api.java.StorageLevels;
+import org.apache.spark.api.java.function.FlatMapFunction;
+import org.apache.spark.api.java.function.Function2;
+import org.apache.spark.api.java.function.PairFunction;
+import org.apache.spark.streaming.Durations;
+import org.apache.spark.streaming.api.java.JavaDStream;
+import org.apache.spark.streaming.api.java.JavaPairDStream;
+import org.apache.spark.streaming.api.java.JavaReceiverInputDStream;
+import org.apache.spark.streaming.api.java.JavaStreamingContext;
+
+/**
+ * Counts words cumulatively in UTF8 encoded, '\n' delimited text received
from the network every
+ * second starting with initial value of word count.
+ * Usage: JavaStatefulNetworkWordCount <hostname> <port>
+ * <hostname> and <port> describe the TCP server that Spark Streaming
would connect to receive
+ * data.
+ * <p/>
+ * To run this on your local machine, you need to first run a Netcat server
+ * `$ nc -lk 9999`
+ * and then run the example
+ * `$ bin/run-example
+ * org.apache.spark.examples.streaming.JavaStatefulNetworkWordCount
localhost 9999`
+ */
+public class JavaStatefulNetworkWordCount {
+ private static final Pattern SPACE = Pattern.compile(" ");
+
+ public static void main(String[] args) {
+ if (args.length < 2) {
+ System.err.println("Usage: StatefulNetworkWordCount <hostname>
<port>");
--- End diff --
Update this class name too. Ideally, I think this example should be a
verbatim merge of `JavaNetworkWordCount` with the difference between Scala
`NetworkWordCount` and `StatefulNetworkWordCount`. It's not quite structured
like the latter, but it's close. I wonder if you could rearrange it a little
bit so that the symmetry is obvious.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
