flink批处理_java

 <properties>
        <maven.compiler.source>8</maven.compiler.source>
        <maven.compiler.target>8</maven.compiler.target>
        <flink.version>1.10.0</flink.version>
        <scala.bin.version>2.11</scala.bin.version>
        <kafka.version>2.2.0</kafka.version>
        <jedis.version>2.9.0</jedis.version>
        <fastjson.version>1.2.53</fastjson.version>
        <hive.version>1.1.0</hive.version>
    </properties>

    <dependencies>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-streaming-scala_${scala.bin.version}</artifactId>
            <version>${flink.version}</version>
            <scope>provided</scope>
        </dependency>
        <dependency>
            <groupId>org.apache.kafka</groupId>
            <artifactId>kafka_${scala.bin.version}</artifactId>
            <version>${kafka.version}</version>
            <scope>provided</scope>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-connector-kafka_${scala.bin.version}</artifactId>
            <version>${flink.version}</version>
            <scope>provided</scope>
        </dependency>

        <dependency>
            <groupId>redis.clients</groupId>
            <artifactId>jedis</artifactId>
            <version>${jedis.version}</version>
            <scope>provided</scope>
        </dependency>
        <dependency>
            <groupId>com.alibaba</groupId>
            <artifactId>fastjson</artifactId>
            <version>${fastjson.version}</version>
        </dependency>
        <dependency>
            <groupId>mysql</groupId>
            <artifactId>mysql-connector-java</artifactId>
            <version>8.0.26</version>
        </dependency>
    </dependencies>

    <build>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-shade-plugin</artifactId>
                <version>3.1.1</version>
                <configuration>
                </configuration>
                <executions>
                    <execution>
                        <phase>package</phase>
                        <goals>
                            <goal>shade</goal>
                        </goals>
                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>

</project>

<dependencies>
    <!-- https://mvnrepository.com/artifact/org.apache.flink/flink-java -->
    <dependency>
        <groupId>org.apache.flink</groupId>
        <artifactId>flink-java</artifactId>
        <version>1.10.0</version>
    </dependency>
    <!-- https://mvnrepository.com/artifact/org.apache.flink/flink-streaming-java -->
    <dependency>
        <groupId>org.apache.flink</groupId>
        <artifactId>flink-streaming-java_2.11</artifactId>
        <version>1.10.0</version>
        <!-- <scope>provided</scope> -->
    </dependency>

</dependencies>

import org.apache.flink.api.common.functions.FlatMapFunction;
import org.apache.flink.api.java.DataSet;
import org.apache.flink.api.java.ExecutionEnvironment;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.util.Collector;

public class flink_example {

    public static void main(String[] args) throws Exception{
        // 创建执行环境
        ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();

        // 从文件中读取数据
        String inputPath = "D:\\test\\1.txt";
        //这里和spark很相似了
        DataSet<String> inputDataSet = env.readTextFile (inputPath);

        // 对数据集进行处理，按空格分词展开，转换成(word, 1)二元组进行统计
        DataSet<Tuple2<String, Integer>> resultSet = inputDataSet.flatMap(new MyFlatMapper())
                .groupBy(0)   // 按照第一个位置的word分组
                .sum(1);    // 将第二个位置上的数据求和
        resultSet.print();
    }

    // 自定义类，实现FlatMapFunction接口
    public static class MyFlatMapper implements FlatMapFunction<String, Tuple2<String, Integer>>
    {
        public void flatMap(String value, Collector<Tuple2<String, Integer>> out) throws Exception {
            // 按空格分词
            String[] words = value.split(" ");
            // 遍历所有word，包成二元组输出
            for (String word : words) {
                out.collect(new Tuple2<String,Integer>(word, 1));
            }
        }
    }
}