2021年大数据Flink（四十七）：扩展阅读  File Sink

package cn.lanson.extend;

import org.apache.flink.api.common.serialization.SimpleStringEncoder;
import org.apache.flink.connector.file.sink.FileSink;
import org.apache.flink.core.fs.Path;
import org.apache.flink.runtime.state.filesystem.FsStateBackend;
import org.apache.flink.streaming.api.datastream.DataStreamSource;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.streaming.api.functions.sink.filesystem.OutputFileConfig;
import org.apache.flink.streaming.api.functions.sink.filesystem.bucketassigners.DateTimeBucketAssigner;
import org.apache.flink.streaming.api.functions.sink.filesystem.rollingpolicies.DefaultRollingPolicy;

import java.util.concurrent.TimeUnit;

/**
 * Author lanson
 * Desc
 */
public class FileSinkDemo {
    public static void main(String[] args) throws Exception {
        //1.env
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        env.enableCheckpointing(TimeUnit.SECONDS.toMillis(10));
        env.setStateBackend(new FsStateBackend("file:///D:/ckp"));

        //2.source
        DataStreamSource<String> lines = env.socketTextStream("node1", 9999);

        //3.sink
        //设置sink的前缀和后缀
        //文件的头和文件扩展名
        //prefix-xxx-.txt
        OutputFileConfig config = OutputFileConfig
                .builder()
                .withPartPrefix("prefix")
                .withPartSuffix(".txt")
                .build();

        //设置sink的路径
        String outputPath = "hdfs://node1:8020/FlinkFileSink/parquet";

        final FileSink<String> sink = FileSink
                .forRowFormat(new Path(outputPath), new SimpleStringEncoder<String>("UTF-8"))
                .withBucketAssigner(new DateTimeBucketAssigner<>())
                .withRollingPolicy(
                        DefaultRollingPolicy.builder()
                                .withRolloverInterval(TimeUnit.MINUTES.toMillis(15))
                                .withInactivityInterval(TimeUnit.MINUTES.toMillis(5))
                                .withMaxPartSize(1024 * 1024 * 1024)
                                .build())
                .withOutputFileConfig(config)
                .build();

        lines.sinkTo(sink).setParallelism(1);

        env.execute();
    }
}