使用地图缩减将文本文件转换为ORC格式

Question

我正在编写一个地图缩减代码，将文本文件转换为ORC格式。我使用了 ORCNewOutputFormat，它存在于 hive-exec-0.13.0 jar 中。我在 15 节点群集 （hdp 2.3） 中工作。问题是我无法加载要在我的地图缩减代码中访问的外部 jar（hive-exec-0.13.0.jar）。我也尝试了其他方法，例如 libjar 和分布式缓存，但代码无法访问 jar。还有其他方法可以做到这一点吗???

//Driver Code
import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.filecache.DistributedCache;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.hive.ql.io.orc.OrcNewOutputFormat;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.Writable;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
public class Driver {
    public static void main(String args[]) throws IOException, InterruptedException, ClassNotFoundException
    {
        Configuration conf =new Configuration();
        Job job =new Job(conf,"join");
        job.setJarByClass(Driver.class);
        job.setReducerClass(ReducerORC.class);
        job.setMapperClass(MapORC.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(Text.class);
        job.setOutputKeyClass(NullWritable.class);
        job.setOutputValueClass(Writable.class);
        conf.set("orc.create.index","true");
        OrcNewOutputFormat.setCompressOutput(job,true);
        OrcNewOutputFormat.setOutputPath(job,new Path(args[1]));
        FileInputFormat.addInputPath(job,new Path(args[0]));
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}

.

//Mapper Code
import java.io.IOException;
import java.util.StringTokenizer;
import org.apache.hadoop.filecache.DistributedCache;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer.Context;
public class MapORC extends Mapper<LongWritable, Text, Text, Text>
{
    @Override
    public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException
    {
        String [] split=value.toString().split(",",2);
        String id = split[0];
        String others= split[1];
            context.write(new Text(id),new Text(others) );
        }
    }

.

//Reducer Code
import java.util.ArrayList;
import java.io.IOException;
import java.util.List;
import org.apache.hadoop.filecache.DistributedCache;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.hive.ql.io.orc.OrcSerde;
import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspector;
import org.apache.hadoop.hive.serde2.typeinfo.TypeInfo;
import org.apache.hadoop.hive.serde2.typeinfo.TypeInfoUtils;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.Writable;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.Mapper.Context;
public class ReducerORC extends Reducer<Text,Text,NullWritable,Writable> {

    private final OrcSerde orcSerde = new OrcSerde();
    private Writable row;

    private final String Struct1 = "struct<name:string,age:String>";
    private final TypeInfo ReduceTypeInfo = TypeInfoUtils.getTypeInfoFromTypeString(Struct1);
    private final ObjectInspector ins = TypeInfoUtils.getStandardJavaObjectInspectorFromTypeInfo(ReduceTypeInfo);
    @Override
    protected void reduce(Text key,Iterable<Text> values, Context context) {
        List <Text> orcRecord = new ArrayList<Text>();
        orcRecord.add(key);
        for(Text value:values)
        {
        orcRecord.add(value);
        }
        this.row = orcSerde.serialize(orcRecord, ins);
        try {
            context.write(NullWritable.get(), this.row);
        } catch (IOException e) {
            e.printStackTrace();
        } catch (InterruptedException e) {
            e.printStackTrace();
        }
      }
   }

.

上述代码的错误

Exception in thread "main" java.lang.NoClassDefFoundError: org/apache/hadoop/hive/ql/io/orc/OrcNewOutputFormat
        at Driver.main(Driver.java:27)
        at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
        at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
        at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
        at java.lang.reflect.Method.invoke(Method.java:606)
        at org.apache.hadoop.util.RunJar.run(RunJar.java:221)
        at org.apache.hadoop.util.RunJar.main(RunJar.java:136)
Caused by: java.lang.ClassNotFoundException: org.apache.hadoop.hive.ql.io.orc.OrcNewOutputFormat
        at java.net.URLClassLoader$1.run(URLClassLoader.java:366)
        at java.net.URLClassLoader$1.run(URLClassLoader.java:355)
        at java.security.AccessController.doPrivileged(Native Method)
        at java.net.URLClassLoader.findClass(URLClassLoader.java:354)
        at java.lang.ClassLoader.loadClass(ClassLoader.java:425)
        at java.lang.ClassLoader.loadClass(ClassLoader.java:358)
        ... 7 more

Answer 1

您是否将HADOOP_CLASSPATH设置为包含所需的罐子？

如果这不起作用，您正在寻找的可能是HADOOP_USER_CLASSPATH_FIRST=true

这有助于您在HADOOP_CLASSPATH中使用 JAR 版本，而不是 Hadoop 发行版附带的版本。