diff options
author | James Thomas <jamesjoethomas@gmail.com> | 2016-06-28 16:12:48 -0700 |
---|---|---|
committer | Tathagata Das <tathagata.das1565@gmail.com> | 2016-06-28 16:12:48 -0700 |
commit | 3554713a163c58ca176ffde87d2c6e4a91bacb50 (patch) | |
tree | 3e8e18f14eb0f1c5d00a535b17360414b1cf4fb3 /examples/src/main/scala | |
parent | 8a977b065418f07d2bf4fe1607a5534c32d04c47 (diff) | |
download | spark-3554713a163c58ca176ffde87d2c6e4a91bacb50.tar.gz spark-3554713a163c58ca176ffde87d2c6e4a91bacb50.tar.bz2 spark-3554713a163c58ca176ffde87d2c6e4a91bacb50.zip |
[SPARK-16114][SQL] structured streaming network word count examples
## What changes were proposed in this pull request?
Network word count example for structured streaming
## How was this patch tested?
Run locally
Author: James Thomas <jamesjoethomas@gmail.com>
Author: James Thomas <jamesthomas@Jamess-MacBook-Pro.local>
Closes #13816 from jjthomas/master.
Diffstat (limited to 'examples/src/main/scala')
-rw-r--r-- | examples/src/main/scala/org/apache/spark/examples/sql/streaming/StructuredNetworkWordCount.scala | 76 |
1 files changed, 76 insertions, 0 deletions
diff --git a/examples/src/main/scala/org/apache/spark/examples/sql/streaming/StructuredNetworkWordCount.scala b/examples/src/main/scala/org/apache/spark/examples/sql/streaming/StructuredNetworkWordCount.scala new file mode 100644 index 0000000000..433f7a181b --- /dev/null +++ b/examples/src/main/scala/org/apache/spark/examples/sql/streaming/StructuredNetworkWordCount.scala @@ -0,0 +1,76 @@ +/* + * 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. + */ + +// scalastyle:off println +package org.apache.spark.examples.sql.streaming + +import org.apache.spark.sql.functions._ +import org.apache.spark.sql.SparkSession + +/** + * Counts words in UTF8 encoded, '\n' delimited text received from the network every second. + * + * Usage: StructuredNetworkWordCount <hostname> <port> + * <hostname> and <port> describe the TCP server that Structured Streaming + * would connect to receive data. + * + * 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 sql.streaming.StructuredNetworkWordCount + * localhost 9999` + */ +object StructuredNetworkWordCount { + def main(args: Array[String]) { + if (args.length < 2) { + System.err.println("Usage: StructuredNetworkWordCount <hostname> <port>") + System.exit(1) + } + + val host = args(0) + val port = args(1).toInt + + val spark = SparkSession + .builder + .appName("StructuredNetworkWordCount") + .getOrCreate() + + import spark.implicits._ + + // Create DataFrame representing the stream of input lines from connection to host:port + val lines = spark.readStream + .format("socket") + .option("host", host) + .option("port", port) + .load().as[String] + + // Split the lines into words + val words = lines.flatMap(_.split(" ")) + + // Generate running word count + val wordCounts = words.groupBy("value").count() + + // Start running the query that prints the running counts to the console + val query = wordCounts.writeStream + .outputMode("complete") + .format("console") + .start() + + query.awaitTermination() + } +} +// scalastyle:on println |