flink-sql 1.10 kafka 实时采集kafka中的数据写入到hbase

flink-sql从kafka读取数据写入mysql

1.导入依赖

<?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>com.lw</groupId>
    <artifactId>flin2k</artifactId>
    <version>1.0-SNAPSHOT</version>
    <dependencies>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-scala_2.11</artifactId>
            <version>1.10.0</version>
        </dependency>
        <!-- https://mvnrepository.com/artifact/org.apache.flink/flink-streaming-scala -->
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-streaming-scala_2.11</artifactId>
            <version>1.10.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-connector-kafka-0.11_2.11</artifactId>
            <version>1.10.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-table-common</artifactId>
            <version>1.10.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-table-api-scala-bridge_2.11</artifactId>
            <version>1.10.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-csv</artifactId>
            <version>1.10.0</version>
        </dependency>
        <!-- https://mvnrepository.com/artifact/org.apache.flink/flink-jdbc -->
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-jdbc_2.11</artifactId>
            <version>1.10.0</version>
        </dependency>
        <!-- https://mvnrepository.com/artifact/mysql/mysql-connector-java -->
        <dependency>
            <groupId>mysql</groupId>
            <artifactId>mysql-connector-java</artifactId>
            <version>5.1.47</version>
        </dependency>
        <!-- https://mvnrepository.com/artifact/org.apache.flink/flink-hbase -->
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-hbase_2.11</artifactId>
            <version>1.10.0</version>
        </dependency>
        <!-- https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-common -->
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>2.7.1</version>
        </dependency>



        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-table-planner_2.11</artifactId>
            <version>1.10.0</version>
        </dependency>

        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-table-planner_2.11</artifactId>
            <version>1.10.0</version>
        </dependency>

        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-table-planner-blink_2.11</artifactId>
            <version>1.10.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-table-api-scala-bridge_2.11</artifactId>
            <version>1.10.0</version>
        </dependency>

    </dependencies>

    <build>
        <plugins>
            <!-- 该插件用于将Scala代码编译成class文件 -->
            <plugin>
                <groupId>net.alchim31.maven</groupId>
                <artifactId>scala-maven-plugin</artifactId>
                <version>3.4.6</version>
                <executions>
                    <execution>
                        <!-- 声明绑定到maven的compile阶段 -->
                        <goals>
                            <goal>testCompile</goal>
                        </goals>
                    </execution>
                </executions>
            </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>
                        <goals>
                            <goal>single</goal>
                        </goals>
                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>

</project>

2.代码

package com.lw.table

import org.apache.flink.streaming.api.scala._
import org.apache.flink.table.api.{DataTypes, EnvironmentSettings, Table}
import org.apache.flink.table.api.scala._
import org.apache.flink.table.descriptors.{Csv, HBase, Kafka, Schema}
import org.apache.flink.types.Row
import org.apache.kafka.clients.consumer.ConsumerConfig


object printToHbase {
  def main(args: Array[String]): Unit = {
    val env: StreamExecutionEnvironment = StreamExecutionEnvironment.getExecutionEnvironment
    val settings: EnvironmentSettings = EnvironmentSettings.newInstance().useOldPlanner().inStreamingMode().build()
    val tableEnv: StreamTableEnvironment = StreamTableEnvironment.create(env,settings)

    tableEnv.connect(new Kafka().version("0.11").topic("test2").property(ConsumerConfig.BOOTSTRAP_SERVERS_CONFIG,"hadoop102:9092").property("zookeeper.connect","hadoop102:2181")
      .property(ConsumerConfig.GROUP_ID_CONFIG,"ae"))
      .withFormat(new Csv().fieldDelimiter(' '))
      .withSchema(new Schema().field("name",DataTypes.STRING())
        .field("age",DataTypes.INT()))
      .createTemporaryTable("kafkaInputTable")


    //创建hbasesink表时候  要求 第一列必须是rowkey。对应你查询的数据的第一列
    //字段对应 hbase 列族。
    //如果hbase列足 只有一个列足 那么hbasesink表就只有两列  rowkey 和 info列族。
    val hbaseDDL : String =
      """
        |Create table myHbaseTable(
        |rowkey string,   
        |info ROW(name varchar,age int)  -- info 要与hbase列族名字一样
        |) with(
        |    'connector.type' = 'hbase',
        |    'connector.version' = '1.4.3',                    -- hbase vesion 当前只支持1.4.3
        |    'connector.table-name' = 'user',                  -- hbase table name
        |    'connector.zookeeper.quorum' = 'hadoop102:2181',       -- zookeeper quorum 
        |    'connector.zookeeper.znode.parent' = '/hbase',    -- hbase znode in zookeeper
        |    'connector.write.buffer-flush.max-size' = '10mb', -- max flush size
        |    'connector.write.buffer-flush.max-rows' = '1000', -- max flush rows
        |    'connector.write.buffer-flush.interval' = '2s'    -- max flush interval
        |
        |)
      """.stripMargin

    tableEnv.sqlUpdate(hbaseDDL);

    //執行sql建表

    val resultTable: Table = tableEnv.sqlQuery("select name as rowkey,ROW(name,age) as info from kafkaInputTable ")

    resultTable.toAppendStream[Row].print()

    resultTable.insertInto("myHbaseTable")

    tableEnv.execute("kafka2mysql")

  }
}