Flink——表的创建，转换，输出

读取本地CSV文件流处理，按表处理

pom

<dependency>
    <groupId>org.apache.flink</groupId>
    <artifactId>flink-java</artifactId>
    <version>1.10.1</version>
</dependency>
<dependency>
    <groupId>org.apache.flink</groupId>
    <artifactId>flink-streaming-java_2.12</artifactId>
    <version>1.10.1</version>
</dependency>
<dependency>
    <groupId>org.apache.flink</groupId>
    <artifactId>flink-table-planner_2.12</artifactId>
    <version>1.10.1</version>
</dependency>
<dependency>
    <groupId>org.apache.flink</groupId>
    <artifactId>flink-table-planner-blink_2.12</artifactId>
    <version>1.10.1</version>
</dependency>
<dependency>
    <groupId>org.apache.flink</groupId>
    <artifactId>flink-csv</artifactId>
    <version>1.10.1</version>
</dependency>

package com.yrl.table;

import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.table.api.DataTypes;
import org.apache.flink.table.api.EnvironmentSettings;
import org.apache.flink.table.api.Table;
import org.apache.flink.table.api.java.StreamTableEnvironment;
import org.apache.flink.table.descriptors.Csv;
import org.apache.flink.table.descriptors.FileSystem;
import org.apache.flink.table.descriptors.Schema;
import org.apache.flink.types.Row;

public class Test03 {
    public static void main(String[] args) throws Exception {
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        env.setParallelism(1);


        //1.1基于老版本planner的流处理
        EnvironmentSettings oldEnvSettings = EnvironmentSettings.newInstance().useOldPlanner().inStreamingMode().build();
        StreamTableEnvironment tableEnv = StreamTableEnvironment.create(env,oldEnvSettings);


        //2.1创建表
        String path="D:\\大数据组件API\\Flink\\Flink01\\src\\main\\resources\\test.txt";
        tableEnv.connect(new FileSystem().path(path))   //创建连接
                .withFormat(new Csv())                 //数据格式
                .withSchema(new Schema()                //数据结构,顺序一致
                        .field("id", DataTypes.STRING())
                        .field("timestamp", DataTypes.BIGINT())
                        .field("temperature", DataTypes.DOUBLE())
                ).createTemporaryTable("inputTable");

        Table inputTable = tableEnv.from("inputTable");
        inputTable.printSchema();

        //3.1Table API
        Table res1 = inputTable.select("id,temperature").where("id='sensor_6'");
        Table res2 = inputTable.groupBy("id").select("id,id.count as count,temperature.avg as tempAvg");

        //3.2SQL
        String sql ="select id ,count(*) as `count` from inputTable group by id";
        Table res3 = tableEnv.sqlQuery(sql);


        tableEnv.toAppendStream(res1, Row.class).print("res1");
        tableEnv.toRetractStream(res2, Row.class).print("res2");
        tableEnv.toRetractStream(res3, Row.class).print("res3");

        //4.1表的输出
        String path2="D:\\大数据组件API\\Flink\\Flink01\\src\\main\\resources\\test2.csv";
        tableEnv.connect(new FileSystem().path(path2))   //创建连接
                .withFormat(new Csv())                 //数据格式
                .withSchema(new Schema()                //数据结构,顺序一致
                        .field("id", DataTypes.STRING())
                        .field("temp", DataTypes.DOUBLE())
                ).createTemporaryTable("outputTable");
        
        //res2,res3,聚合操作有更新，不支持直接写入文件
        res1.insertInto("outputTable");
        

        env.execute();


    }
}