spark JavaStructuredNetworkWordCount 源码
spark JavaStructuredNetworkWordCount 代码
文件路径：/examples/src/main/java/org/apache/spark/examples/sql/streaming/JavaStructuredNetworkWordCount.java
/*
* 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.sql.streaming;
import org.apache.spark.api.java.function.FlatMapFunction;
import org.apache.spark.sql.*;
import org.apache.spark.sql.streaming.StreamingQuery;
import java.util.Arrays;
/**
* Counts words in UTF8 encoded, '\n' delimited text received from the network.
*
* Usage: JavaStructuredNetworkWordCount <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.JavaStructuredNetworkWordCount
* localhost 9999`
*/
public final class JavaStructuredNetworkWordCount {
public static void main(String[] args) throws Exception {
if (args.length < 2) {
System.err.println("Usage: JavaStructuredNetworkWordCount <hostname> <port>");
System.exit(1);
}
String host = args[0];
int port = Integer.parseInt(args[1]);
SparkSession spark = SparkSession
.builder()
.appName("JavaStructuredNetworkWordCount")
.getOrCreate();
// Create DataFrame representing the stream of input lines from connection to host:port
Dataset<Row> lines = spark
.readStream()
.format("socket")
.option("host", host)
.option("port", port)
.load();
// Split the lines into words
Dataset<String> words = lines.as(Encoders.STRING()).flatMap(
(FlatMapFunction<String, String>) x -> Arrays.asList(x.split(" ")).iterator(),
Encoders.STRING());
// Generate running word count
Dataset<Row> wordCounts = words.groupBy("value").count();
// Start running the query that prints the running counts to the console
StreamingQuery query = wordCounts.writeStream()
.outputMode("complete")
.format("console")
.start();
query.awaitTermination();
}
}
相关信息
相关文章
spark JavaStructuredComplexSessionization 源码
spark JavaStructuredKafkaWordCount 源码
spark JavaStructuredKerberizedKafkaWordCount 源码
0
赞
热门推荐
-
2、 - 优质文章
-
3、 gate.io
-
7、 golang
-
9、 openharmony
-
10、 Vue中input框自动聚焦