flink1.7.2 tableapi批处理示例

最新推荐文章于 2025-07-14 17:08:13 发布

thinktothings

最新推荐文章于 2025-07-14 17:08:13 发布

阅读量1.5k

点赞数

CC 4.0 BY-SA版权

分类专栏： Flink 文章标签： flink1.7.2 tableapi批处理示例

本文链接：https://blog.youkuaiyun.com/thinktothings/article/details/88593691

flink1.7.2 tableapi批处理示例

源码

https://github.com/opensourceteams/flink-maven-scala

概述

本文为flink1.7.2 tableapi批处理示例
主要操作包括: print table,DataSet 转换成table,Scan,select,as,where / filter,groupBy,distinct,join,leftOuterJoin,rightOuterJoin
union,unionAll,intersect,intersectAll,minus,minusAll,in,orderBy,fetch,offset,Sink csv,insert

print table

功能描述: 打印输出表数据
scala 程序


package com.opensourceteams.module.bigdata.flink.example.tableapi.convert.dataset

import org.apache.flink.api.scala.{ExecutionEnvironment, _}
import org.apache.flink.table.api.TableEnvironment
import org.apache.flink.table.api.scala._

object Run2 {


  def main(args: Array[String]): Unit = {

    val env = ExecutionEnvironment.getExecutionEnvironment
    val tableEnv = TableEnvironment.getTableEnvironment(env)

    val dataSet = env.fromElements( (1,"a",10),(2,"b",20), (3,"c",30) )



    //从dataset转化为 table
    val table = tableEnv.fromDataSet(dataSet)

    table.first(1000).print()


    /**
      * 打印输出表数据
      *
      * 1,a,10
      * 2,b,20
      * 3,c,30
      */


  }

}

输出结果

1,a,10
2,b,20
3,c,30

DataSet 转换成table


package com.opensourceteams.module.bigdata.flink.example.tableapi.convert.dataset

import org.apache.flink.api.scala.{ExecutionEnvironment, _}
import org.apache.flink.table.api.TableEnvironment
import org.apache.flink.table.api.scala._

object Run1 {


  def main(args: Array[String]): Unit = {

    val env = ExecutionEnvironment.getExecutionEnvironment
    val tableEnv = TableEnvironment.getTableEnvironment(env)

    val dataSet = env.fromElements( (1,"a",10),(2,"b",20), (3,"c",30) )



    //从dataset转化为 table
    val table = tableEnv.fromDataSet(dataSet)

    //注册table
    tableEnv.registerTable("user1",table)


    //查询table 所有数据
    tableEnv.scan("user1").first(10)

      //print 输出 (相当于sink)
      .print()


    /**
      * 输出结果
      * 
      * 1,a,10
      * 2,b,20
      * 3,c,30
      */



  }

}

输出结果

1,a,10
2,b,20
3,c,30

Scan

功能描述: 查询表中所有数据
scala 程序


package com.opensourceteams.module.bigdata.flink.example.tableapi.operation.scan

import org.apache.flink.api.scala.{ExecutionEnvironment, _}
import org.apache.flink.table.api.TableEnvironment
import org.apache.flink.table.api.scala._

object Run {


  def main(args: Array[String]): Unit = {

    val env = ExecutionEnvironment.getExecutionEnvironment
    val tableEnv = TableEnvironment.getTableEnvironment(env)

    val dataSet = env.fromElements( (1,"a",10),(2,"b",20), (3,"c",30) )



    //从dataset转化为 table
    val table = tableEnv.fromDataSet(dataSet)

    //注册table
    tableEnv.registerTable("user1",table)


    //查询table 所有数据
    tableEnv.scan("user1").first(100)

      //print 输出 (相当于sink)
      .print()


    /**
      * 输出结果
      *
      * 1,a,10
      * 2,b,20
      * 3,c,30
      */



  }

}

输出结果


1,a,10
2,b,20
3,c,30

select

功能描述: 选择表中需要的字段
scala 程序


package com.opensourceteams.module.bigdata.flink.example.tableapi.operation.select

import org.apache.flink.api.scala.{ExecutionEnvironment, _}
import org.apache.flink.table.api.TableEnvironment
import org.apache.flink.table.api.scala._

object Run {


  def main(args: Array[String]): Unit = {

    val env = ExecutionEnvironment.getExecutionEnvironment
    val tableEnv = TableEnvironment.getTableEnvironment(env)

    val dataSet = env.fromElements( (1,"a",10),(2,"b",20), (3,"c",30) )



    //从dataset转化为 table
    val table = tableEnv.fromDataSet(dataSet)

    //注册table
    tableEnv.registerTable("user1",table)


    //查询table 所有数据
    tableEnv.scan("user1")
      //选择需要的字段
      .select('_1,'_2,'_3)
      .first(100)

      //print 输出 (相当于sink)
      .print()


    /**
      * 输出结果
      *
      * 1,a,10
      * 2,b,20
      * 3,c,30
      */



  }

}

输出结果

1,a,10
2,b,20
3,c,30

as

功能描述: 重命名字段名称
scala 程序


package com.opensourceteams.module.bigdata.flink.example.tableapi.operation.as

import org.apache.flink.api.scala.{ExecutionEnvironment, _}
import org.apache.flink.table.api.TableEnvironment
import org.apache.flink.table.api.scala._

object Run {


  def main(args: Array[String]): Unit = {

    val env = ExecutionEnvironment.getExecutionEnvironment
    val tableEnv = TableEnvironment.getTableEnvironment(env)

    val dataSet = env.fromElements( (1,"a",10),(2,"b",20), (3,"c",30) )



    //从dataset转化为 table
    val table = tableEnv.fromDataSet(dataSet)

    //注册table
    tableEnv.registerTable("user1",table)


    //查询table 所有数据
    tableEnv.scan("user1")

      //重命令字段名称
      .as('id,'name,'value)
      //选择需要的字段
      .select('id,'name,'value)
      .first(100)

      //print 输出 (相当于sink)
      .print()


    /**
      * 输出结果
      *
      * 1,a,10
      * 2,b,20
      * 3,c,30
      */



  }

}

输出结果

1,a,10
2,b,20
3,c,30

as

功能描述: 重命名字段名称
scala 程序


package com.opensourceteams.module.bigdata.flink.example.tableapi.operation.as

import org.apache.flink.api.scala.{ExecutionEnvironment, _}
import org.apache.flink.table.api.TableEnvironment
import org.apache.flink.table.api.scala._

object Run {


  def main(args: Array[String]): Unit = {

    val env = ExecutionEnvironment.getExecutionEnvironment
    val tableEnv = TableEnvironment.getTableEnvironment(env)

    val dataSet = env.fromElements( (1,"a",10),(2,"b",20), (3,"c",30) )



    //从dataset转化为 table
    val table