Flink读文件数据并且创建表然后用FlinkSql和TableAPI进行查询的Demo

sensor.txt

sensor_1,1547718199,35.8
sensor_6,1547718201,15.4
sensor_7,1547718202,6.7
sensor_10,1547718205,38.1
sensor_1,1547718207,37.2
sensor_1,1547718212,33.5
sensor_1,1547718215,38.1

TableAPI

import org.apache.flink.streaming.api.scala._
import org.apache.flink.table.api.scala._
import org.apache.flink.table.api.{DataTypes, Table}
import org.apache.flink.table.descriptors._

/**
 * 读取kafka的数据并且转成表
 */
object TableApiTest4 {
  def main(args: Array[String]): Unit = {
    val env = StreamExecutionEnvironment.getExecutionEnvironment
    env.setParallelism(1)
    val tableEnv = StreamTableEnvironment.create(env)

    val filePath = "D:\\20-Flink\\FlinkTutorial\\src\\main\\resources\\sensor.txt"
    tableEnv.connect(new FileSystem().path(filePath))

      .withFormat(new Csv()) // 指定csv格式,就是逗号分割的格式,因为kafka输入的数据就是这个格式的.
      //创建每个字段的名字和类型
      .withSchema(new Schema()
        .field("id", DataTypes.STRING())
        .field("timestamp", DataTypes.BIGINT())
        .field("temperature", DataTypes.DOUBLE())
      )
      // 创建表名
      .createTemporaryTable("inputTable")


    //    表的查询
    val sensorTable: Table = tableEnv.from("inputTable")
    val resultTable: Table = sensorTable
      .select('id, 'temperature)
      .filter('id === "sensor_1") //等于是 三个等号,

    resultTable.toAppendStream[(String, Double)].print("TableAPI")


    env.execute("table api test job")
  }
}

结果:

TableAPI> (sensor_1,35.8)
TableAPI> (sensor_1,37.2)
TableAPI> (sensor_1,33.5)
TableAPI> (sensor_1,38.1)

FlinkSql

import org.apache.flink.streaming.api.scala._
import org.apache.flink.table.api.scala._
import org.apache.flink.table.api.{DataTypes, Table}
import org.apache.flink.table.descriptors._

/**
 * 读取kafka的数据并且转成表
 */
object TableApiTest4 {
  def main(args: Array[String]): Unit = {
    val env = StreamExecutionEnvironment.getExecutionEnvironment
    env.setParallelism(1)
    val tableEnv = StreamTableEnvironment.create(env)

    val filePath = "D:\\20-Flink\\FlinkTutorial\\src\\main\\resources\\sensor.txt"
    tableEnv.connect(new FileSystem().path(filePath))

      .withFormat(new Csv()) // 指定csv格式,就是逗号分割的格式,因为kafka输入的数据就是这个格式的.
      //创建每个字段的名字和类型
      .withSchema(new Schema()
        .field("id", DataTypes.STRING())
        .field("timestamp", DataTypes.BIGINT())
        .field("temperature", DataTypes.DOUBLE())
      )
      // 创建表名
      .createTemporaryTable("inputTable")



    //    SQL简单查询
    val resultSqlTable: Table = tableEnv.sqlQuery(
      """
        |select id, temperature
        |from inputTable
        |where id = 'sensor_1'
          """.stripMargin)
    resultSqlTable.toAppendStream[(String, Double)].print("FlinkSql")


    env.execute("table api test job")
  }
}

结果:

FlinkSql> (sensor_1,35.8)
FlinkSql> (sensor_1,37.2)
FlinkSql> (sensor_1,33.5)
FlinkSql> (sensor_1,38.1)