大数据hudi之集成flink:IDEA编码方式

除了用sql-client，还可以自己编写FlinkSQL程序，打包提交Flink作业。

环境准备

1）手动install依赖
mvn install:install-file -DgroupId=org.apache.hudi -DartifactId=hudi-flink_2.12 -Dversion=0.12.0 -Dpackaging=jar -Dfile=./hudi-flink1.13-bundle-0.12.0.jar
2）创建Maven工程

<?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>com.atguigu.hudi</groupId>
    <artifactId>flink-hudi-demo</artifactId>
    <version>1.0-SNAPSHOT</version>

    <properties>
        <maven.compiler.source>8</maven.compiler.source>
        <maven.compiler.target>8</maven.compiler.target>
        <flink.version>1.13.6</flink.version>
        <hudi.version>0.12.0</hudi.version>
        <java.version>1.8</java.version>
        <scala.binary.version>2.12</scala.binary.version>
        <slf4j.version>1.7.30</slf4j.version>
    </properties>

    <dependencies>

        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-java</artifactId>
            <version>${flink.version}</version>
            <scope>provided</scope>   <!--不会打包到依赖中，只参与编译，不参与运行 -->
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-streaming-java_${scala.binary.version}</artifactId>
            <version>${flink.version}</version>
            <scope>provided</scope>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-clients_${scala.binary.version}</artifactId>
            <version>${flink.version}</version>
            <scope>provided</scope>
        </dependency>

        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-table-planner-blink_${scala.binary.version}</artifactId>
            <version>${flink.version}</version>
            <scope>provided</scope>
        </dependency>

        <!--idea运行时也有webui-->
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-runtime-web_${scala.binary.version}</artifactId>
            <version>${flink.version}</version>
            <scope>provided</scope>
        </dependency>

        <dependency>
            <groupId>org.slf4j</groupId>
            <artifactId>slf4j-api</artifactId>
            <version>${slf4j.version}</version>
            <scope>provided</scope>
        </dependency>
        <dependency>
            <groupId>org.slf4j</groupId>
            <artifactId>slf4j-log4j12</artifactId>
            <version>${slf4j.version}</version>
            <scope>provided</scope>
        </dependency>
        <dependency>
            <groupId>org.apache.logging.log4j</groupId>
            <artifactId>log4j-to-slf4j</artifactId>
            <version>2.14.0</version>
            <scope>provided</scope>
        </dependency>


        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-statebackend-rocksdb_${scala.binary.version}</artifactId>
            <version>${flink.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>3.1.3</version>
            <scope>provided</scope>
        </dependency>

        <!--手动install到本地maven仓库-->
        <dependency>
            <groupId>org.apache.hudi</groupId>
            <artifactId>hudi-flink_2.12</artifactId>
            <version>${hudi.version}</version>
            <scope>provided</scope>
        </dependency>

    </dependencies>


    <build>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-shade-plugin</artifactId>
                <version>3.2.4</version>
                <executions>
                    <execution>
                        <phase>package</phase>
                        <goals>
                            <goal>shade</goal>
                        </goals>
                        <configuration>
                            <artifactSet>
                                <excludes>
                                    <exclude>com.google.code.findbugs:jsr305</exclude>
                                    <exclude>org.slf4j:*</exclude>
                                    <exclude>log4j:*</exclude>
                                    <exclude>org.apache.hadoop:*</exclude>
                                </excludes>
                            </artifactSet>
                            <filters>
                                <filter>
                                    <!-- Do not copy the signatures in the META-INF folder.
                                    Otherwise, this might cause SecurityExceptions when using the JAR. -->
                                    <artifact>*:*</artifact>
                                    <excludes>
                                        <exclude>META-INF/*.SF</exclude>
                                        <exclude>META-INF/*.DSA</exclude>
                                        <exclude>META-INF/*.RSA</exclude>
                                    </excludes>
                                </filter>
                            </filters>
                            <transformers combine.children="append">
                                <transformer implementation="org.apache.maven.plugins.shade.resource.ServicesResourceTransformer">
                                </transformer>
                            </transformers>
                        </configuration>
                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>

</project>

编写代码

package com.atguigu.hudi.flink;

import org.apache.flink.contrib.streaming.state.EmbeddedRocksDBStateBackend;
import org.apache.flink.contrib.streaming.state.PredefinedOptions;
import org.apache.flink.streaming.api.CheckpointingMode;
import org.apache.flink.streaming.api.environment.CheckpointConfig;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.table.api.bridge.java.StreamTableEnvironment;

import java.util.concurrent.TimeUnit;


public class HudiDemo {
    public static void main(String[] args) {
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();

        // 设置状态后端RocksDB
        EmbeddedRocksDBStateBackend embeddedRocksDBStateBackend = new EmbeddedRocksDBStateBackend(true);
        embeddedRocksDBStateBackend.setPredefinedOptions(PredefinedOptions.SPINNING_DISK_OPTIMIZED_HIGH_MEM);
        env.setStateBackend(embeddedRocksDBStateBackend);

        // checkpoint配置
        env.enableCheckpointing(TimeUnit.SECONDS.toMillis(30), CheckpointingMode.EXACTLY_ONCE);
        CheckpointConfig checkpointConfig = env.getCheckpointConfig();
        checkpointConfig.setCheckpointStorage("hdfs://hadoop1:8020/ckps");
        checkpointConfig.setMinPauseBetweenCheckpoints(TimeUnit.SECONDS.toMillis(20));
        checkpointConfig.setTolerableCheckpointFailureNumber(5);
        checkpointConfig.setCheckpointTimeout(TimeUnit.MINUTES.toMillis(1));
        checkpointConfig.enableExternalizedCheckpoints(CheckpointConfig.ExternalizedCheckpointCleanup.RETAIN_ON_CANCELLATION);

        StreamTableEnvironment sTableEnv = StreamTableEnvironment.create(env);

        sTableEnv.executeSql("CREATE TABLE sourceT (\n" +
                "  uuid varchar(20),\n" +
                "  name varchar(10),\n" +
                "  age int,\n" +
                "  ts timestamp(3),\n" +
                "  `partition` varchar(20)\n" +
                ") WITH (\n" +
                "  'connector' = 'datagen',\n" +
                "  'rows-per-second' = '1'\n" +
                ")");

        sTableEnv.executeSql("create table t2(\n" +
                "  uuid varchar(20),\n" +
                "  name varchar(10),\n" +
                "  age int,\n" +
                "  ts timestamp(3),\n" +
                "  `partition` varchar(20)\n" +
                ")\n" +
                "with (\n" +
                "  'connector' = 'hudi',\n" +
                "  'path' = '/tmp/hudi_flink/t2',\n" +
                "  'table.type' = 'MERGE_ON_READ'\n" +
                ")");

        sTableEnv.executeSql("insert into t2 select * from sourceT");

    }
}

提交运行

将代码打成jar包，上传到目录myjars，执行提交命令：

bin/flink run -t yarn-per-job \
-c com.atguigu.hudi.flink.HudiDemo \
./myjars/flink-hudi-demo-1.0-SNAPSHOT.jar