东芃9394 2022-06-05 15:31 采纳率: 100%
浏览 105
已结题

Java-flink的sum方法输出

问题遇到的现象和发生背景

img

问题相关代码，请勿粘贴截图
package cn.itcast.hello.source;
import org.apache.flink.api.common.RuntimeExecutionMode;
import org.apache.flink.api.common.functions.FlatMapFunction;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.datastream.KeyedStream;
import org.apache.flink.streaming.api.datastream.SingleOutputStreamOperator;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.util.Collector;

public class DemoSource1 {

    public static void main(String[] args) throws Exception {
        // 1. 获取环境变量
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        env.setRuntimeMode(RuntimeExecutionMode.AUTOMATIC);

        DataStream<String> dataStream = env.fromElements("hello spark flink", "hello flink spark", "hadoop");
        // 2. transformation
        SingleOutputStreamOperator<Tuple2<String, Integer>> worldAndOne = dataStream.flatMap(new FlatMapFunction<String, Tuple2<String, Integer>>() {
            @Override
            public void flatMap(String value, Collector<Tuple2<String, Integer>> collector) throws Exception {
                String[] arr = value.split(" ");
                for (String str : arr) {
                    collector.collect(Tuple2.of(str, 1));
                }
            }
        });
        KeyedStream<Tuple2<String, Integer>, String> tuple2IntegerKeyedStream = worldAndOne.keyBy(t -> t.f0);
        SingleOutputStreamOperator<Tuple2<String, Integer>> sum = tuple2IntegerKeyedStream.sum(1);
        // 3. sink
        sum.print();
//        tuple2IntegerKeyedStream.print();
        env.execute();
    }
}

pom依赖：

<?xml version="1.0" encoding="UTF-8"?>
<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>cn.itcast</groupId>
    <artifactId>flink_study_47</artifactId>
    <version>1.0-SNAPSHOT</version>

    <!-- 指定仓库位置，依次为aliyun、apache和cloudera仓库 -->
    <repositories>
        <repository>
            <id>aliyun</id>
            <url>http://maven.aliyun.com/nexus/content/groups/public/</url>
        </repository>
        <repository>
            <id>apache</id>
            <url>https://repository.apache.org/content/repositories/snapshots/</url>
        </repository>
        <repository>
            <id>cloudera</id>
            <url>https://repository.cloudera.com/artifactory/cloudera-repos/</url>
        </repository>
    </repositories>

    <properties>
        <encoding>UTF-8</encoding>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
        <maven.compiler.source>1.8</maven.compiler.source>
        <maven.compiler.target>1.8</maven.compiler.target>
        <java.version>1.8</java.version>
        <scala.version>2.12</scala.version>
        <flink.version>1.12.0</flink.version>
    </properties>
    <dependencies>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-clients_2.12</artifactId>
            <version>${flink.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-scala_2.12</artifactId>
            <version>${flink.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-java</artifactId>
            <version>${flink.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-streaming-scala_2.12</artifactId>
            <version>${flink.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-streaming-java_2.12</artifactId>
            <version>${flink.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-table-api-scala-bridge_2.12</artifactId>
            <version>${flink.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-table-api-java-bridge_2.12</artifactId>
            <version>${flink.version}</version>
        </dependency>
        <!-- flink执行计划,这是1.9版本之前的-->
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-table-planner_2.12</artifactId>
            <version>${flink.version}</version>
        </dependency>
        <!-- blink执行计划,1.11+默认的-->
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-table-planner-blink_2.12</artifactId>
            <version>${flink.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-table-common</artifactId>
            <version>${flink.version}</version>
        </dependency>

        <!--<dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-cep_2.12</artifactId>
            <version>${flink.version}</version>
        </dependency>-->

        <!-- flink连接器-->
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-connector-kafka_2.12</artifactId>
            <version>${flink.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-sql-connector-kafka_2.12</artifactId>
            <version>${flink.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-connector-jdbc_2.12</artifactId>
            <version>${flink.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-csv</artifactId>
            <version>${flink.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-json</artifactId>
            <version>${flink.version}</version>
        </dependency>

        <!-- <dependency>
           <groupId>org.apache.flink</groupId>
           <artifactId>flink-connector-filesystem_2.12</artifactId>
           <version>${flink.version}</version>
       </dependency>-->
        <!--<dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-jdbc_2.12</artifactId>
            <version>${flink.version}</version>
        </dependency>-->
        <!--<dependency>
              <groupId>org.apache.flink</groupId>
              <artifactId>flink-parquet_2.12</artifactId>
              <version>${flink.version}</version>
         </dependency>-->
        <!--<dependency>
            <groupId>org.apache.avro</groupId>
            <artifactId>avro</artifactId>
            <version>1.9.2</version>
        </dependency>
        <dependency>
            <groupId>org.apache.parquet</groupId>
            <artifactId>parquet-avro</artifactId>
            <version>1.10.0</version>
        </dependency>-->


        <dependency>
            <groupId>org.apache.bahir</groupId>
            <artifactId>flink-connector-redis_2.11</artifactId>
            <version>1.0</version>
            <exclusions>
                <exclusion>
                    <artifactId>flink-streaming-java_2.11</artifactId>
                    <groupId>org.apache.flink</groupId>
                </exclusion>
                <exclusion>
                    <artifactId>flink-runtime_2.11</artifactId>
                    <groupId>org.apache.flink</groupId>
                </exclusion>
                <exclusion>
                    <artifactId>flink-core</artifactId>
                    <groupId>org.apache.flink</groupId>
                </exclusion>
                <exclusion>
                    <artifactId>flink-java</artifactId>
                    <groupId>org.apache.flink</groupId>
                </exclusion>
            </exclusions>
        </dependency>

        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-connector-hive_2.12</artifactId>
            <version>${flink.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hive</groupId>
            <artifactId>hive-metastore</artifactId>
            <version>2.1.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hive</groupId>
            <artifactId>hive-exec</artifactId>
            <version>2.1.0</version>
        </dependency>

        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-shaded-hadoop-2-uber</artifactId>
            <version>2.7.5-10.0</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hbase</groupId>
            <artifactId>hbase-client</artifactId>
            <version>2.1.0</version>
        </dependency>

        <dependency>
            <groupId>mysql</groupId>
            <artifactId>mysql-connector-java</artifactId>
            <version>5.1.38</version>
            <!--<version>8.0.20</version>-->
        </dependency>

        <!-- 高性能异步组件：Vertx-->
        <dependency>
            <groupId>io.vertx</groupId>
            <artifactId>vertx-core</artifactId>
            <version>3.9.0</version>
        </dependency>
        <dependency>
            <groupId>io.vertx</groupId>
            <artifactId>vertx-jdbc-client</artifactId>
            <version>3.9.0</version>
        </dependency>
        <dependency>
            <groupId>io.vertx</groupId>
            <artifactId>vertx-redis-client</artifactId>
            <version>3.9.0</version>
        </dependency>

        <!-- 日志 -->
        <dependency>
            <groupId>org.slf4j</groupId>
            <artifactId>slf4j-log4j12</artifactId>
            <version>1.7.7</version>
            <scope>runtime</scope>
        </dependency>
        <dependency>
            <groupId>log4j</groupId>
            <artifactId>log4j</artifactId>
            <version>1.2.17</version>
            <scope>runtime</scope>
        </dependency>

        <dependency>
            <groupId>com.alibaba</groupId>
            <artifactId>fastjson</artifactId>
            <version>1.2.44</version>
        </dependency>

        <dependency>
            <groupId>org.projectlombok</groupId>
            <artifactId>lombok</artifactId>
            <version>1.18.2</version>
            <scope>provided</scope>
        </dependency>

        <!-- 参考：https://blog.csdn.net/f641385712/article/details/84109098-->
        <!--<dependency>
            <groupId>org.apache.commons</groupId>
            <artifactId>commons-collections4</artifactId>
            <version>4.4</version>
        </dependency>-->
        <!--<dependency>
            <groupId>org.apache.thrift</groupId>
            <artifactId>libfb303</artifactId>
            <version>0.9.3</version>
            <type>pom</type>
            <scope>provided</scope>
         </dependency>-->
        <!--<dependency>
           <groupId>com.google.guava</groupId>
           <artifactId>guava</artifactId>
           <version>28.2-jre</version>
       </dependency>-->

    </dependencies>

    <build>
        <sourceDirectory>src/main/java</sourceDirectory>
        <plugins>
            <!-- 编译插件 -->
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <version>3.5.1</version>
                <configuration>
                    <source>1.8</source>
                    <target>1.8</target>
                    <!--<encoding>${project.build.sourceEncoding}</encoding>-->
                </configuration>
            </plugin>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-surefire-plugin</artifactId>
                <version>2.18.1</version>
                <configuration>
                    <useFile>false</useFile>
                    <disableXmlReport>true</disableXmlReport>
                    <includes>
                        <include>**/*Test.*</include>
                        <include>**/*Suite.*</include>
                    </includes>
                </configuration>
            </plugin>
            <!-- 打包插件(会包含所有依赖) -->
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-shade-plugin</artifactId>
                <version>2.3</version>
                <executions>
                    <execution>
                        <phase>package</phase>
                        <goals>
                            <goal>shade</goal>
                        </goals>
                        <configuration>
                            <filters>
                                <filter>
                                    <artifact>*:*</artifact>
                                    <excludes>
                                        <!--
                                        zip -d learn_spark.jar META-INF/*.RSA META-INF/*.DSA META-INF/*.SF -->
                                        <exclude>META-INF/*.SF</exclude>
                                        <exclude>META-INF/*.DSA</exclude>
                                        <exclude>META-INF/*.RSA</exclude>
                                    </excludes>
                                </filter>
                            </filters>
                            <transformers>
                                <transformer implementation="org.apache.maven.plugins.shade.resource.ManifestResourceTransformer">
                                    <!-- 设置jar包的入口类(可选) -->
                                    <mainClass></mainClass>
                                </transformer>
                            </transformers>
                        </configuration>
                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>

</project>
运行结果及报错内容

少显示一个(hadoop,1)

我的解答思路和尝试过的方法
我想要达到的结果

将(hadoop,1)也输出出来，着重解释为什么 “tuple2IntegerKeyedStream.sum(1);”后，就少了“(hadoop,1)”

  • 写回答

1条回答 默认 最新

  • sum墨 2022-06-05 19:28
    关注

    我的打印出来了，，，

    img


    我代码是这样的

    
import org.apache.flink.api.common.RuntimeExecutionMode;
import org.apache.flink.api.common.functions.FlatMapFunction;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.datastream.KeyedStream;
import org.apache.flink.streaming.api.datastream.SingleOutputStreamOperator;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.util.Collector;

public class WordCount {
    public static void main(String[] args) throws Exception {
        // 1. 获取环境变量
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        env.setRuntimeMode(RuntimeExecutionMode.AUTOMATIC);

        DataStream<String> dataStream = env.fromElements("hello spark flink", "hello flink spark", "hadoop");
        // 2. transformation
        SingleOutputStreamOperator<Tuple2<String, Integer>> worldAndOne = dataStream.flatMap(new FlatMapFunction<String, Tuple2<String, Integer>>() {
            @Override
            public void flatMap(String value, Collector<Tuple2<String, Integer>> collector) throws Exception {
                String[] arr = value.split(" ");
                for (String str : arr) {
                    collector.collect(Tuple2.of(str, 1));
                }
            }
        });
        KeyedStream<Tuple2<String, Integer>, String> tuple2IntegerKeyedStream = worldAndOne.keyBy(t -> t.f0);
        SingleOutputStreamOperator<Tuple2<String, Integer>> sum = tuple2IntegerKeyedStream.sum(1);
        // 3. sink
        sum.print();
     //   tuple2IntegerKeyedStream.print();
        env.execute();
    }
}
    本回答被题主选为最佳回答 , 对您是否有帮助呢?
    评论 编辑记录

报告相同问题？

问题事件

  • 系统已结题 6月14日
  • 已采纳回答 6月6日
  • 修改了问题 6月5日
  • 创建了问题 6月5日

悬赏问题

  • ¥50 永磁型步进电机PID算法
  • ¥15 sqlite 附加（attach database）加密数据库时，返回26是什么原因呢？
  • ¥88 找成都本地经验丰富懂小程序开发的技术大咖
  • ¥15 如何处理复杂数据表格的除法运算
  • ¥15 如何用stc8h1k08的片子做485数据透传的功能？(关键词-串口)
  • ¥15 有兄弟姐妹会用word插图功能制作类似citespace的图片吗？
  • ¥200 uniapp长期运行卡死问题解决
  • ¥15 latex怎么处理论文引理引用参考文献
  • ¥15 请教：如何用postman调用本地虚拟机区块链接上的合约？
  • ¥15 为什么使用javacv转封装rtsp为rtmp时出现如下问题：[h264 @ 000000004faf7500]no frame？