大数据-116 - Flink DataStream Sink 原理、概念、常见Sink类型 配置与使用 附带案例1：消费Kafka写到Redis

DataStream<String> dataStream = // 数据处理逻辑
dataStream.addSink(new FlinkKafkaProducer<>(
    "localhost:9092",         // Kafka broker 地址
    "output-topic",           // 输出的 Kafka 主题
    new SimpleStringSchema()   // 数据序列化格式
));

dataStream.addSink(JdbcSink.sink(
    "INSERT INTO my_table (column1, column2) VALUES (?, ?)",
    (statement, value) -> {
        statement.setString(1, value.f0);
        statement.setInt(2, value.f1);
    },
    JdbcExecutionOptions.builder()
        .withBatchSize(1000)
        .withBatchIntervalMs(200)
        .build(),
    new JdbcConnectionOptions.JdbcConnectionOptionsBuilder()
        .withUrl("jdbc:mysql://localhost:3306/mydb")
        .withDriverName("com.mysql.jdbc.Driver")
        .withUsername("user")
        .withPassword("password")
        .build()
));

public class PrintSinkFunction<T> extends RichSinkFunction<T> {
    @Override
    public void invoke(T value, Context context) {
        System.out.println(value);
    }
}

DataStream<String> dataStream = // 数据处理逻辑
StreamingFileSink<String> sink = StreamingFileSink
    .forRowFormat(new Path("/output/path"), new SimpleStringEncoder<String>("UTF-8"))
    .build();

dataStream.addSink(sink);

<dependency>
  <groupId>org.apache.flink</groupId>
  <artifactId>flink-connector-redis_2.11</artifactId>
  <version>1.1.5</version>
</dependency>

package icu.wzk;

import org.apache.flink.api.common.functions.FlatMapFunction;
import org.apache.flink.api.common.serialization.SimpleStringSchema;
import org.apache.flink.api.java.functions.KeySelector;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.streaming.api.datastream.DataStreamSource;
import org.apache.flink.streaming.api.datastream.SingleOutputStreamOperator;
import org.apache.flink.streaming.api.scala.StreamExecutionEnvironment;
import org.apache.flink.streaming.connectors.kafka.FlinkKafkaConsumer;
import org.apache.flink.util.Collector;

import java.util.Properties;

public class StreamFromKafka {

    public static void main(String[] args) {
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();

        // 配置信息
        Properties properties = new Properties();
        properties.setProperty("bootstrap.servers", "h121.wzk.icu:9092");

        // Kafka
        FlinkKafkaConsumer<String> consumer = new FlinkKafkaConsumer<>(
                "flink_test",
                new SimpleStringSchema(),
                properties
        );
        DataStreamSource<String> data = env.getJavaEnv().addSource(consumer);

        SingleOutputStreamOperator<Tuple2<String, Integer>> wordAndOne = data
                .flatMap(new FlatMapFunction<String, Tuple2<String, Integer>>() {
                    @Override
                    public void flatMap(String value, Collector<Tuple2<String, Integer>> out) throws Exception {
                        String[] words = value.split(" ");
                        for (String word: words) {
                            out.collect(new Tuple2<>(word, 1));
                        }
                    }
                });
        SingleOutputStreamOperator<Tuple2<String, Integer>> result = wordAndOne
                .keyBy(new KeySelector<Tuple2<String, Integer>, Object>() {
                    @Override
                    public Object getKey(Tuple2<String, Integer> value) throws Exception {
                        return value.f0;
                    }
                })
                .sum(1);
        result.print();
        env.execute("StreamFromKafka");
    }

}