如何将.txt/.csv文件转换为orc格式

v64noz0r  于 2021-06-04  发布在  Hadoop
关注(0)|答案(2)|浏览(519)

对于某些要求，我想将文本文件（分隔）转换为orc（优化的行-列）格式。因为我必须定期运行它，所以我想编写一个java程序来实现这一点。我不想使用配置单元临时表解决方法。有人能帮我吗？下面是我试过的

/*ORCMapper.java*/
import java.io.IOException;
import java.util.*;
import org.apache.hadoop.mapred.*;
import org.apache.hadoop.hive.ql.io.orc.*;
import org.apache.hadoop.io.*;

public class ORCMapper  extends MapReduceBase implements
Mapper<LongWritable, Text, NullWritable, Writable>{

    OrcSerde serde;
    @Override
    public void configure(JobConf job) {
        serde = new OrcSerde();
    }

    @Override
    public void map(LongWritable key, Text value,
            OutputCollector<NullWritable, Writable> output, Reporter reporter)
            throws IOException {
        output.collect(NullWritable.get(),serde.serialize(value, null));
    }

}

/*ORCReducer.java*/
import java.io.IOException;
import java.util.Iterator;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Writable;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reducer;
import org.apache.hadoop.mapred.Reporter;

public class ORCReducer extends MapReduceBase implements Reducer<NullWritable, Writable, NullWritable, Writable>{

    @Override
    public void reduce(NullWritable key, Iterator<Writable> values,
            OutputCollector<NullWritable, Writable> output, Reporter reporter)
            throws IOException {
        Writable value = values.next();
         output.collect(key, value);
    }

}

/*ORCDriver.java*/
import java.io.*;
import org.apache.hadoop.fs.*;
import org.apache.hadoop.hive.ql.io.orc.*;
import org.apache.hadoop.io.*;
import org.apache.hadoop.mapred.*;
public class ORCDriver {
    public static void main(String[] args) throws IOException,
    InterruptedException, ClassNotFoundException {
        JobClient client = new JobClient();
        JobConf conf = new JobConf("ORC_Generator");
        conf.setInputFormat(TextInputFormat.class);
        conf.setOutputKeyClass(NullWritable.class);
        conf.setOutputValueClass(Writable.class);
        conf.setOutputFormat(OrcOutputFormat.class);
        FileInputFormat.addInputPath(conf, new Path("hdfs://localhost:9000/path/to/ipdir/textfile"));
        OrcOutputFormat.setOutputPath(conf, new Path("hdfs://localhost:9000/path/to/opdir/orcfile"));
        conf.setMapperClass(ORCMapper.class);
        System.out.println(OrcOutputFormat.getWorkOutputPath(conf));
        conf.setNumReduceTasks(0);

        client.setConf(conf);
        try {
          JobClient.runJob(conf);
        } catch (Exception e) {
          e.printStackTrace();
        }

    }

}

运行此命令将显示以下错误，并在本地文件中生成名为part-00000的文件

java.io.IOException: File already exists:part-00000
    at org.apache.hadoop.fs.RawLocalFileSystem.create(RawLocalFileSystem.java:249)
    at org.apache.hadoop.fs.RawLocalFileSystem.create(RawLocalFileSystem.java:241)
    at org.apache.hadoop.fs.ChecksumFileSystem$ChecksumFSOutputSummer.<init>(ChecksumFileSystem.java:335)
    at org.apache.hadoop.fs.ChecksumFileSystem.create(ChecksumFileSystem.java:381)
    at org.apache.hadoop.fs.ChecksumFileSystem.create(ChecksumFileSystem.java:364)
    at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:564)
    at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:545)
    at org.apache.hadoop.hive.ql.io.orc.WriterImpl.ensureWriter(WriterImpl.java:1672)
    at org.apache.hadoop.hive.ql.io.orc.WriterImpl.flushStripe(WriterImpl.java:1688)
    at org.apache.hadoop.hive.ql.io.orc.WriterImpl.close(WriterImpl.java:1868)
    at org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat$OrcRecordWriter.close(OrcOutputFormat.java:95)
    at org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat$OrcRecordWriter.close(OrcOutputFormat.java:80)
    at org.apache.hadoop.mapred.MapTask$DirectMapOutputCollector.close(MapTask.java:833)
    at org.apache.hadoop.mapred.MapTask.closeQuietly(MapTask.java:1763)
    at org.apache.hadoop.mapred.MapTask.runOldMapper(MapTask.java:439)
    at org.apache.hadoop.mapred.MapTask.run(MapTask.java:366)
    at org.apache.hadoop.mapred.LocalJobRunner$Job$MapTaskRunnable.run(LocalJobRunner.java:223)
    at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
    at java.util.concurrent.FutureTask.run(FutureTask.java:262)
    at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
    at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
    at java.lang.Thread.run(Thread.java:745)
14/09/02 11:23:26 INFO mapred.LocalJobRunner: Map task executor complete.
14/09/02 11:23:26 WARN mapred.LocalJobRunner: job_local688970064_0001
java.lang.Exception: java.lang.NullPointerException
    at org.apache.hadoop.mapred.LocalJobRunner$Job.run(LocalJobRunner.java:354)
Caused by: java.lang.NullPointerException
    at org.apache.hadoop.hive.ql.io.orc.WriterImpl.createTreeWriter(WriterImpl.java:1515)
    at org.apache.hadoop.hive.ql.io.orc.WriterImpl.<init>(WriterImpl.java:154)
    at org.apache.hadoop.hive.ql.io.orc.OrcFile.createWriter(OrcFile.java:258)
    at org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat$OrcRecordWriter.write(OrcOutputFormat.java:63)
    at org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat$OrcRecordWriter.write(OrcOutputFormat.java:46)
    at org.apache.hadoop.mapred.MapTask$DirectMapOutputCollector.collect(MapTask.java:847)
    at org.apache.hadoop.mapred.MapTask$OldOutputCollector.collect(MapTask.java:591)
    at ORCMapper.map(ORCMapper.java:42)
    at ORCMapper.map(ORCMapper.java:1)
    at org.apache.hadoop.mapred.MapRunner.run(MapRunner.java:50)
    at org.apache.hadoop.mapred.MapTask.runOldMapper(MapTask.java:430)
    at org.apache.hadoop.mapred.MapTask.run(MapTask.java:366)
    at org.apache.hadoop.mapred.LocalJobRunner$Job$MapTaskRunnable.run(LocalJobRunner.java:223)
    at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
    at java.util.concurrent.FutureTask.run(FutureTask.java:262)
    at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
    at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
    at java.lang.Thread.run(Thread.java:745)
14/09/02 11:23:26 INFO mapred.JobClient:  map 0% reduce 0%
14/09/02 11:23:26 INFO mapred.JobClient: Job complete: job_local688970064_0001
14/09/02 11:23:26 INFO mapred.JobClient: Counters: 0
14/09/02 11:23:26 INFO mapred.JobClient: Job Failed: NA
java.io.IOException: Job failed!
    at org.apache.hadoop.mapred.JobClient.runJob(JobClient.java:1357)
    at ORCDriver.main(ORCDriver.java:53)
Javahadoop

2条答案

按热度按时间
8tntrjer

8tntrjer1#

可以通过以下命令将文本数据插入orc表：

insert overwrite table orcTable select * from textTable;

第一个表由以下命令创建：

create table orcTable(name string, city string) stored as orc;

texttable的结构与orctable相同。

赞(0）分享  回复(0）举报  2021-06-04
wvt8vs2t

wvt8vs2t2#

您可以使用spark dataframes很容易地将分隔文件转换为orc格式。您还可以指定/强制架构并筛选特定的列。

public class OrcConvert {
   public static void main(String[] args) {
    SparkConf conf = new SparkConf().setAppName("OrcConvert");

    JavaSparkContext jsc = new JavaSparkContext(conf);
    HiveContext hiveContext = new HiveContext(jsc);

    String inputPath = args[0];
    String outputPath = args[1];

    DataFrame inputDf = hiveContext.read().format("com.databricks.spark.csv")
            .option("quote", "'").option("delimiter", "\001")
            .load(inputPath);

    inputDf.write().orc(outputPath);
  }
}

确保满足所有依赖项，配置单元也应运行以使用hivecontext，目前仅支持spark orc格式的hivecontext。

赞(0）分享  回复(0）举报  2021-06-04
我来回答

相关问题

    查看更多

    热门标签

    更多
    JavaquerypythonNode开发语言requestUtil数据库Table后端算法LoggerMessageElementParser

    最新问答

    更多
    • 蜀ICP备2022004421号-2 NULL123 https://www.null123.com © All rights reserved
    • 本站内容来源互联网,如果侵犯您的权益请联系我们删除, 联系方式：448109455@qq.com