Repository: spark Updated Branches: refs/heads/branch-1.3 ba91bf5f4 -> 1945fcfd9
[SPARK-5800] Streaming Docs. Change linked files according the selected language Currently, Spark Streaming Programming Guide after updateStateByKey explanation links to file stateful_network_wordcount.py and note "For the complete Scala code ..." for any language tab selected. This is an incoherence. I've changed the guide and link its pertinent example file. JavaStatefulNetworkWordCount.java example was not created so I added to the commit. Author: gasparms <gmu...@stratio.com> Closes #4589 from gasparms/feature/streaming-guide and squashes the following commits: 7f37f89 [gasparms] More style changes ec202b0 [gasparms] Follow spark style guide f527328 [gasparms] Improve example to look like scala example 4d8785c [gasparms] Remove throw exception e92e6b8 [gasparms] Fix incoherence 92db405 [gasparms] Fix Streaming Programming Guide. Change files according the selected language Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/e99e170c Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/e99e170c Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/e99e170c Branch: refs/heads/branch-1.3 Commit: e99e170c7bff95a102b3bf00cc31bfa81951d0cf Parents: ba91bf5 Author: gasparms <gmu...@stratio.com> Authored: Sat Feb 14 20:10:29 2015 +0000 Committer: Sean Owen <so...@cloudera.com> Committed: Sat Feb 14 20:20:14 2015 +0000 ---------------------------------------------------------------------- docs/streaming-programming-guide.md | 21 +++- .../streaming/JavaStatefulNetworkWordCount.java | 115 +++++++++++++++++++ 2 files changed, 132 insertions(+), 4 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/e99e170c/docs/streaming-programming-guide.md ---------------------------------------------------------------------- diff --git a/docs/streaming-programming-guide.md b/docs/streaming-programming-guide.md index 96fb12c..997de95 100644 --- a/docs/streaming-programming-guide.md +++ b/docs/streaming-programming-guide.md @@ -878,6 +878,12 @@ This is applied on a DStream containing words (say, the `pairs` DStream containi val runningCounts = pairs.updateStateByKey[Int](updateFunction _) {% endhighlight %} +The update function will be called for each word, with `newValues` having a sequence of 1's (from +the `(word, 1)` pairs) and the `runningCount` having the previous count. For the complete +Scala code, take a look at the example +[StatefulNetworkWordCount.scala]({{site.SPARK_GITHUB_URL}}/blob/master/examples/src/main/scala/org/apache +/spark/examples/streaming/StatefulNetworkWordCount.scala). + </div> <div data-lang="java" markdown="1"> @@ -899,6 +905,13 @@ This is applied on a DStream containing words (say, the `pairs` DStream containi JavaPairDStream<String, Integer> runningCounts = pairs.updateStateByKey(updateFunction); {% endhighlight %} +The update function will be called for each word, with `newValues` having a sequence of 1's (from +the `(word, 1)` pairs) and the `runningCount` having the previous count. For the complete +Java code, take a look at the example +[JavaStatefulNetworkWordCount.java]({{site +.SPARK_GITHUB_URL}}/blob/master/examples/src/main/java/org/apache/spark/examples/streaming +/JavaStatefulNetworkWordCount.java). + </div> <div data-lang="python" markdown="1"> @@ -916,14 +929,14 @@ This is applied on a DStream containing words (say, the `pairs` DStream containi runningCounts = pairs.updateStateByKey(updateFunction) {% endhighlight %} -</div> -</div> - The update function will be called for each word, with `newValues` having a sequence of 1's (from the `(word, 1)` pairs) and the `runningCount` having the previous count. For the complete -Scala code, take a look at the example +Python code, take a look at the example [stateful_network_wordcount.py]({{site.SPARK_GITHUB_URL}}/blob/master/examples/src/main/python/streaming/stateful_network_wordcount.py). +</div> +</div> + Note that using `updateStateByKey` requires the checkpoint directory to be configured, which is discussed in detail in the [checkpointing](#checkpointing) section. http://git-wip-us.apache.org/repos/asf/spark/blob/e99e170c/examples/src/main/java/org/apache/spark/examples/streaming/JavaStatefulNetworkWordCount.java ---------------------------------------------------------------------- diff --git a/examples/src/main/java/org/apache/spark/examples/streaming/JavaStatefulNetworkWordCount.java b/examples/src/main/java/org/apache/spark/examples/streaming/JavaStatefulNetworkWordCount.java new file mode 100644 index 0000000..09491fe --- /dev/null +++ b/examples/src/main/java/org/apache/spark/examples/streaming/JavaStatefulNetworkWordCount.java @@ -0,0 +1,115 @@ +/* + * 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.Arrays; +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.HashPartitioner; +import org.apache.spark.SparkConf; +import org.apache.spark.api.java.JavaPairRDD; +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: JavaStatefulNetworkWordCount <hostname> <port>"); + System.exit(1); + } + + StreamingExamples.setStreamingLogLevels(); + + // Update the cumulative count function + final Function2<List<Integer>, Optional<Integer>, Optional<Integer>> updateFunction = new + Function2<List<Integer>, Optional<Integer>, Optional<Integer>>() { + @Override + public Optional<Integer> call(List<Integer> values, Optional<Integer> state) { + Integer newSum = state.or(0); + for (Integer value : values) { + newSum += value; + } + return Optional.of(newSum); + } + }; + + // Create the context with a 1 second batch size + SparkConf sparkConf = new SparkConf().setAppName("JavaStatefulNetworkWordCount"); + JavaStreamingContext ssc = new JavaStreamingContext(sparkConf, Durations.seconds(1)); + ssc.checkpoint("."); + + // Initial RDD input to updateStateByKey + List<Tuple2<String, Integer>> tuples = Arrays.asList(new Tuple2<String, Integer>("hello", 1), + new Tuple2<String, Integer>("world", 1)); + JavaPairRDD<String, Integer> initialRDD = ssc.sc().parallelizePairs(tuples); + + JavaReceiverInputDStream<String> lines = ssc.socketTextStream( + args[0], Integer.parseInt(args[1]), StorageLevels.MEMORY_AND_DISK_SER_2); + + JavaDStream<String> words = lines.flatMap(new FlatMapFunction<String, String>() { + @Override + public Iterable<String> call(String x) { + return Lists.newArrayList(SPACE.split(x)); + } + }); + + JavaPairDStream<String, Integer> wordsDstream = words.mapToPair(new PairFunction<String, String, Integer>() { + @Override + public Tuple2<String, Integer> call(String s) { + return new Tuple2<String, Integer>(s, 1); + } + }); + + // This will give a Dstream made of state (which is the cumulative count of the words) + JavaPairDStream<String, Integer> stateDstream = wordsDstream.updateStateByKey(updateFunction, + new HashPartitioner(ssc.sc().defaultParallelism()), initialRDD); + + stateDstream.print(); + ssc.start(); + ssc.awaitTermination(); + } +} --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org
