ORC文件写入java代码实现汇总（开发笔记）

继上个博文：ORC文件读取java代码实现汇总（开发笔记）我们直接上代码：

package com.lu.Main;

import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
import io.airlift.compress.lzo.LzoCodec;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat;
import org.apache.hadoop.hive.ql.io.orc.OrcSerde;
import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspectorFactory;
import org.apache.hadoop.hive.serde2.objectinspector.StructObjectInspector;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Writable;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.OutputFormat;
import org.apache.hadoop.mapred.RecordWriter;
import org.apache.hadoop.mapred.Reporter;
import org.apache.log4j.BasicConfigurator;


public class TestOrcWriter {

    public static void main(String[] args) throws Exception {
        BasicConfigurator.configure(); //自动快速地使用缺省Log4j环境

        JobConf conf = new JobConf();
        FileSystem fs = FileSystem.get(conf);
        Path outputPath = new Path("/usr/local/orcoutput/112.orc");
        StructObjectInspector inspector =
                (StructObjectInspector) ObjectInspectorFactory
                        .getReflectionObjectInspector(MyRow.class,
                                ObjectInspectorFactory.ObjectInspectorOptions.JAVA);
        OrcSerde serde = new OrcSerde();
        OutputFormat outFormat = new OrcOutputFormat();
        RecordWriter writer = outFormat.getRecordWriter(fs, conf,
                outputPath.toString(), Reporter.NULL);
        writer.write(NullWritable.get(),
                serde.serialize(new MyRow("张三",20), inspector));
        writer.write(NullWritable.get(),
                serde.serialize(new MyRow("李四",22), inspector));
        writer.write(NullWritable.get(),
                serde.serialize(new MyRow("王五",30), inspector));
        writer.close(Reporter.NULL);
        fs.close();
        System.out.println("write success .");
//        LzoCodec lzoCodec = new LzoCodec();
//        ZlibCodec zlibCodec = new ZlibCodec();
//        SnappyCodec snappyCodec = new SnappyCodec();

    }

    static class MyRow implements Writable {
        String name;
        int age;

        MyRow(String name,int age){
            this.name = name;
            this.age = age;
        }
        @Override
        public void readFields(DataInput arg0) throws IOException {
            throw new UnsupportedOperationException("no write");
        }
        @Override
        public void write(DataOutput arg0) throws IOException {
            throw new UnsupportedOperationException("no read");
        }

    }

    

}

结果：

2022-03-19 10:51:36,195 INFO [org.apache.orc.impl.PhysicalFsWriter] - ORC writer created for path: /usr/local/orcoutput/112.orc with stripeSize: 67108864 blockSize: 268435456 compression: ZLIB bufferSize: 262144
0 [main] INFO org.apache.orc.impl.PhysicalFsWriter  - ORC writer created for path: /usr/local/orcoutput/112.orc with stripeSize: 67108864 blockSize: 268435456 compression: ZLIB bufferSize: 262144
2022-03-19 10:51:36,233 INFO [org.apache.orc.impl.WriterImpl] - ORC writer created for path: /usr/local/orcoutput/112.orc with stripeSize: 67108864 blockSize: 268435456 compression: ZLIB bufferSize: 262144
38 [main] INFO org.apache.orc.impl.WriterImpl  - ORC writer created for path: /usr/local/orcoutput/112.orc with stripeSize: 67108864 blockSize: 268435456 compression: ZLIB bufferSize: 262144
write success .

---

自己创建的两个群，一个是做3D及机器人方面的（包括算法图像处理，以及三维模型生成,机器人开发等），另一个是元宇宙：技术站群，两个群都是为了交流技术的，禁止乱发广告。