flink的wordCount

编写Flink代码要求

1、source -> transformations ->sink

创建环境有两种
批处理：ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
流处理：StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment()

2、在批处理中flink处理的数据对象是DataSet
在流处理中Flink处理的数据对象是DataStream

transformation 算子都是懒执行，需要最后使用env.execute()触发执行或者使用print（），count（），collect*() 触发执行

我使用的是maven
pom文件

<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
	xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
	<modelVersion>4.0.0</modelVersion>

	<groupId>com.myflink</groupId>
	<artifactId>MyFlinkCode</artifactId>
	<version>1.0-SNAPSHOT</version>
	<packaging>jar</packaging>

	<name>MyFlinkCode</name>


	<properties>
		<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
		<maven.compiler.source>1.8</maven.compiler.source>
		<maven.compiler.target>1.8</maven.compiler.target>
		<exec.mainClass>com.myflink.Launcher</exec.mainClass>
		<flink.version>1.7.1</flink.version>
	</properties>

	<dependencies>
		<dependency>
			<groupId>sk.upjs</groupId>
			<artifactId>jpaz2</artifactId>
			<version>1.1.1</version>
		</dependency>
		<!--flink依赖-->
		<dependency>
			<groupId>org.apache.flink</groupId>
			<artifactId>flink-java</artifactId>
			<version>${flink.version}</version>
		</dependency>
		<dependency>
			<groupId>org.apache.flink</groupId>
			<artifactId>flink-streaming-java_2.11</artifactId>
			<version>${flink.version}</version>
		</dependency>
		<dependency>
			<groupId>org.apache.flink</groupId>
			<artifactId>flink-clients_2.11</artifactId>
			<version>${flink.version}</version>
		</dependency>
		<dependency>
			<groupId>org.apache.flink</groupId>
			<artifactId>flink-connector-wikiedits_2.11</artifactId>
			<version>${flink.version}</version>
		</dependency>
		<!--flink kafka连接服务器的依赖-->
		<dependency>
			<groupId>org.apache.flink</groupId>
			<artifactId>flink-connector-kafka-0.11_2.11</artifactId>
			<version>${flink.version}</version>
		</dependency>
		<dependency>
			<groupId>junit</groupId>
			<artifactId>junit</artifactId>
			<version>4.11</version>
			<scope>test</scope>
		</dependency>
		<!--flink scala2.11 版本-->
		<dependency>
			<groupId>org.apache.flink</groupId>
			<artifactId>flink-scala_2.11</artifactId>
			<version>1.7.1</version>
		</dependency>
		<dependency>
			<groupId>org.scala-lang</groupId>
			<artifactId>scala-library</artifactId>
			<version>2.11.12</version>
		</dependency>

		<!--log4j he slf4j包 如果在控制台不想看到日志，可以将下面的包注释掉-->
		<dependency>
			<groupId>org.slf4j</groupId>
			<artifactId>slf4j-log4j12</artifactId>
			<version>1.7.25</version>
			<scope>test</scope>
		</dependency>

	</dependencies>

	<build>
		<plugins>
			<plugin>
				<groupId>org.apache.maven.plugins</groupId>
				<artifactId>maven-shade-plugin</artifactId>
				<version>3.0.0</version>
				<configuration>
					<filters>
						<filter>
							<artifact>*:*</artifact>
							<excludes>
								<exclude>META-INF/*.SF</exclude>
								<exclude>META-INF/*.DSA</exclude>
								<exclude>META-INF/*.RSA</exclude>
							</excludes>
						</filter>
					</filters>
				</configuration>
				<executions>
					<execution>
						<phase>package</phase>
						<goals>
							<goal>shade</goal>
						</goals>
						<configuration>
							<transformers>
								<transformer
									implementation="org.apache.maven.plugins.shade.resource.ManifestResourceTransformer">
									<mainClass>${exec.mainClass}</mainClass>
								</transformer>
							</transformers>
							<minimizeJar>true</minimizeJar>
							<finalName>MyFlinkCode</finalName>
						</configuration>
					</execution>
				</executions>
			</plugin>
		</plugins>
	</build>


</project>

public class wc {
    public static void main(String[] args) throws Exception {
        ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
        DataSource<String> dataSource = env.readTextFile("./data/words.txt");
        FlatMapOperator<String, String> words = dataSource.flatMap(new FlatMapFunction<String, String>() {
            @Override
            public void flatMap(String line, Collector<String> collector) throws Exception {
                String[] split = line.split(" ");
                for (String word : split) {
                    collector.collect(word);
                }
            }
        });
        MapOperator<String, Tuple2<String,Integer>> pairWords = words.map(new MapFunction<String, Tuple2<String,Integer>>() {
            @Override
            public Tuple2<String,Integer> map(String word) throws Exception {
                return new Tuple2<>(word, 1);
            }
        });
        UnsortedGrouping<Tuple2<String,Integer>> groupBy = pairWords.groupBy(0);
        AggregateOperator<Tuple2<String,Integer>> result= groupBy.sum(1);
        result.print();
    }
}