Flink练习第二天：数据源获取方式（1）

目录

数据源类型：

代码如下：

注意：3.从已有定义对象获取数据，需要定义一个类：

运行结果

---

数据源类型：

1.从文件中读取数据

2.从集合中读取数据

3.从已有定义对象获取数据

4.从socket获取数据

5.从kafka获取数据

代码如下：

package com.atguigu.chapter05;

import org.apache.flink.api.common.serialization.SimpleStringSchema;
import org.apache.flink.streaming.api.datastream.DataStreamSource;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.streaming.connectors.kafka.FlinkKafkaConsumer;

import java.util.ArrayList;
import java.util.Properties;

/**
 * @author psl
 * @create 2022/5/2 17:48
 * @desc
 */
public class SourceTest {
    public static void main(String[] args) throws Exception {

        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        env.setParallelism(1);
        //从文件中读取数据
        DataStreamSource<String> stream1 = env.readTextFile("input/clicks.txt");

        //从集合中读取数据
        ArrayList<Integer> nums = new ArrayList<>();
        nums.add(1);
        nums.add(2);
        DataStreamSource<Integer> stream2 = env.fromCollection(nums);

        //从已有定义对象获取数据
        ArrayList<Event> events = new ArrayList<>();
        events.add(new Event("Mary","./home",1000L));
        events.add(new Event("Bob","./cart",2000L));
        events.add(new Event("Tom","./prod",3000L));
        DataStreamSource<Event> stream3 = env.fromCollection(events);

        //从socket获取数据
        DataStreamSource<String> stream4 = env.socketTextStream("10.22.82.120", 7777);

        stream1.print();
        stream2.print();
        stream3.print();
        stream4.print();

        //从kafka获取数据
        Properties properties = new Properties();
        properties.setProperty("bootstrap.servers","node04:9092");
        properties.setProperty("group.id","consumer-group");
        properties.setProperty("key.deserializer","oeg.apache.kafka.common.serialization.StringDeserializer");
        properties.setProperty("value.deserializer","oeg.apache.kafka.common.serialization.StringDeserializer");
        properties.setProperty("auto.offset.reset","latest");

        DataStreamSource<String> kafkastream = env.addSource(new FlinkKafkaConsumer<String>("clicks", new SimpleStringSchema(), properties));



        env.execute();

    }
}

注意：3.从已有定义对象获取数据，需要定义一个类：

package com.atguigu.chapter05;

import java.sql.Timestamp;

/**
 * @author psl
 * @create 2022/5/2 17:47
 * @desc
 */
public class Event {

    public String user;
    public String url;
    public Long timestamp;

    public Event() {
    }


    public Event(String user, String url, Long timestamp) {
        this.user = user;
        this.url = url;
        this.timestamp = timestamp;

    }


    @Override
    public String toString() {
        return "Event{" +
                "user='" + user + '\'' +
                ", url='" + url + '\'' +
                ", timestamp=" + new Timestamp(timestamp) +
                '}';
    }
}

运行结果