Flink的状态

 <properties>
        <flink.version>1.14.4</flink.version>
        <scala.version>2.12.10</scala.version>
        <scala.binary.version>2.12</scala.binary.version>
        <spark.version>3.0.0</spark.version>
        <hadoop.version>2.9.1</hadoop.version>
        <hudi.version>0.9.0</hudi.version>
    </properties>
    <repositories>
        <repository>
            <id>aliyun</id>
            <url>http://maven.aliyun.com/nexus/content/groups/public/</url>
        </repository>
        <repository>
            <id>cloudera</id>
            <url>https://repository.cloudera.com/artifactory/cloudera-repos/</url>
        </repository>
        <repository>
            <id>jboss</id>
            <url>http://repository.jboss.com/nexus/content/groups/public</url>
        </repository>
    </repositories>

    <dependencies>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-java</artifactId>
            <version>${flink.version}</version>
            <exclusions>
                <exclusion>
                    <groupId>org.apache.commons</groupId>
                    <artifactId>commons-lang3</artifactId>
                </exclusion>
            </exclusions>

        </dependency>
        <dependency>
            <groupId>org.apache.parquet</groupId>
            <artifactId>parquet-avro</artifactId>
            <version>1.10.1</version>
        </dependency>
        <dependency>
            <groupId>org.apache.avro</groupId>
            <artifactId>avro</artifactId>
            <version>1.9.0</version>
        </dependency>

        <dependency>
        <groupId>org.apache.hadoop</groupId>
        <artifactId>hadoop-mapreduce-client-core</artifactId>
        <version>2.9.1</version>
        </dependency>


        <dependency>
            <groupId>org.apache.logging.log4j</groupId>
            <artifactId>log4j-to-slf4j</artifactId>
            <version>2.14.1</version>
        </dependency>

        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-streaming-java_2.12</artifactId>
            <version>${flink.version}</version>

        </dependency>

        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-clients_2.12</artifactId>
            <version>${flink.version}</version>
        </dependency>
        <!-- 依赖Scala语言 -->
        <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-library</artifactId>
            <version>${scala.version}</version>
        </dependency>
        <!-- Spark Core 依赖 -->
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_${scala.binary.version}</artifactId>
            <version>${spark.version}</version>
        </dependency>
        <!-- Spark SQL 依赖 -->
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-sql_${scala.binary.version}</artifactId>
            <version>${spark.version}</version>
        </dependency>

        <!-- Hadoop Client 依赖 -->
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>${hadoop.version}</version>
        </dependency>

        <!-- hudi-spark3 -->
        <dependency>
            <groupId>org.apache.hudi</groupId>
            <artifactId>hudi-spark3-bundle_2.12</artifactId>
            <version>${hudi.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-avro_2.12</artifactId>
            <version>${spark.version}</version>
        </dependency>

    </dependencies>
    <build>
        <plugins>
            <plugin>
                <groupId>org.scala-tools</groupId>
                <artifactId>maven-scala-plugin</artifactId>
                <version>2.15.2</version>
                <executions>
                    <execution>
                        <id>scala-compile-first</id>
                        <goals>
                            <goal>compile</goal>
                        </goals>
                        <configuration>
                            <includes>
                                <include>**/*.scala</include>
                            </includes>
                        </configuration>
                    </execution>
                    <execution>
                        <id>scala-test-compile</id>
                        <goals>
                            <goal>testCompile</goal>
                        </goals>
                    </execution>
                </executions>
            </plugin>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <configuration>
                    <source>1.8</source>
                    <target>1.8</target>

                </configuration>
            </plugin>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-assembly-plugin</artifactId>
                <version>3.0.0</version>
                <configuration>
                    <descriptorRefs>
                        <descriptorRef>jar-with-dependencies</descriptorRef>
                    </descriptorRefs>
                </configuration>
                <executions>
                    <execution>
                        <id>make-assembly</id>
                        <phase>package</phase>

                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>

</project>

flink代码：

package com.xunfang;

import org.apache.flink.api.common.typeinfo.Types;
import org.apache.flink.api.java.ExecutionEnvironment;
import org.apache.flink.api.java.operators.AggregateOperator;
import org.apache.flink.api.java.operators.DataSource;
import org.apache.flink.api.java.operators.FlatMapOperator;
import org.apache.flink.api.java.operators.UnsortedGrouping;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.util.Collector;

public class BatchWordCount {
    public static void main(String[] args) throws Exception {
        //1.创建一个运行环境,现在已经不用了软
        ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
        //2.从文件中读取数据
        DataSource<String> stringDataSource =   env.readTextFile("Input/words.txt");
        //3.将每行数据进行分词,形成分词器，通过收集器
         FlatMapOperator<String, Tuple2<String, Long>> wordAndOneTuple = stringDataSource.flatMap((String line, Collector<Tuple2<String, Long>> out) -> {
            //分词切分
            String[] words = line.split("[\\s+|,]");
            //将每个分词，转换成二元组输出
            for (String word : words) {
                //收集器
                out.collect(Tuple2.of(word, 1L));
            }
            //防止泛型擦除
        }).returns(Types.TUPLE(Types.STRING, Types.LONG));
        //4.按照word进行分组,给定分组索引
        UnsortedGrouping<Tuple2<String, Long>> wordAndGroup = wordAndOneTuple.groupBy(0);
        //5。分组内进行聚合统计,以第二个值来进行分组
        AggregateOperator<Tuple2<String, Long>> sum = wordAndGroup.sum(1);
        //6结果的打印输出
        sum.print();

    }

}

flink第二个代码

package com.xunfang;

import org.apache.flink.api.common.typeinfo.Types;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.streaming.api.datastream.DataStreamSource;
import org.apache.flink.streaming.api.datastream.SingleOutputStreamOperator;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.util.Collector;

public class BoundStreamWordCount {
    public static void main(String[] args) throws Exception {
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        DataStreamSource<String> stringDataStreamSource = env.readTextFile("Input/words.txt");
       SingleOutputStreamOperator<Tuple2<String, Long>> sum = stringDataStreamSource.flatMap((String line, Collector<Tuple2<String, Long>> out) -> {
            String[] words = line.split("[\\s+|,]");
            for (String word : words) {
                out.collect(Tuple2.of(word, 1L));
            }
        }).returns(Types.TUPLE(Types.STRING, Types.LONG)).keyBy(data->data.f0).sum(1);
       sum.print();
       //启动执行
       env.execute();
    }
}

Flink的代码

package com.xunfang;


import org.apache.flink.api.common.typeinfo.Types;

import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.api.java.utils.ParameterTool;
import org.apache.flink.streaming.api.datastream.DataStreamSource;
import org.apache.flink.streaming.api.datastream.SingleOutputStreamOperator;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.util.Collector;

public class StreamWordCount {
    public static void main(String[] args) throws Exception {
         StreamExecutionEnvironment executionEnvironment = StreamExecutionEnvironment.getExecutionEnvironment();
         //读取socket文本流
        //从参数中提取主机名称端口号
        ParameterTool parameterTool = ParameterTool.fromArgs(args);
         String hostname = parameterTool.get("hostname");
        Integer port1 = parameterTool.getInt("port");

        DataStreamSource<String> stringDataStreamSource = executionEnvironment.socketTextStream("192.168.80.212",7777);
          SingleOutputStreamOperator<Tuple2<String, Long>> sum = stringDataStreamSource.flatMap((String line, Collector<Tuple2<String, Long>> out) -> {
            String[] words = line.split("[\\s+|,]");
            for (String word : words) {
                out.collect(Tuple2.of(word, 1L));
            }
        }).returns(Types.TUPLE(Types.STRING, Types.LONG)).keyBy(data -> data.f0).sum(1);
          sum.print();
        executionEnvironment.execute();

    }
}