Java 无法在hadoop上运行word count。谢谢
我尝试在eclipse中运行hadoop字数统计。但它有问题;它甚至无法调试Java 无法在hadoop上运行word count。谢谢,java,eclipse,hadoop,word-count,Java,Eclipse,Hadoop,Word Count,我尝试在eclipse中运行hadoop字数统计。但它有问题;它甚至无法调试 package test; import java.io.IOException; import java.util.ArrayList; import java.util.Collections; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.fs.Path; import org.apache.hadoop.io.In
package test;
import java.io.IOException;
import java.util.ArrayList;
import java.util.Collections;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import test.test.Map2.Combine;
public class test {
public static class Map2 extends Mapper<LongWritable, Text, Text, Text> {
public void map(LongWritable key, Text value, Context context)
throws IOException, InterruptedException {
String line = value.toString();
String values=line.split(" ")[0]+"\\|"+line.split(" ")[1];
context.write(new Text(" "),new Text(values));
}
//method reduce start
public static class Combine extends Reducer<Text, Text, Text, IntWritable> {
ArrayList<String> top5array= new ArrayList<String>();
public void reduce(Text key, Iterable<Text> values, Context context)
throws IOException, InterruptedException {
//arraylist
while(top5array.get(4)==null)
{
top5array.add(values.iterator().next().toString());
}
while(values.iterator().hasNext())
{
String currentValues=values.iterator().next().toString();
String currentkey=currentValues.split("\\|")[0];
Integer currentnum=Integer.parseInt(currentValues.split("\\|")[1]);
for(int i=0;i<5;i++)
{
Integer numofArray = Integer.parseInt(top5array.get(i).split("\\|")[1]);
if(top5array.get(i) != null && currentnum < numofArray)
{
break;
}
if(i == 4)
{
String currentKeyValuePair = currentkey + currentnum.toString();
top5array.add(5, currentKeyValuePair);
Collections.sort(top5array);
top5array.remove(0);
}
}// for end
}// while end
}//method reduce end
} // Combine end
}
// map end
public static class Reduce2 extends Reducer<Text, Text, Text, Text> {
ArrayList<String> top5array= new ArrayList<String>();
public void reduce(Text key, Iterable<Text> values, Context context)
throws IOException, InterruptedException {
while(top5array.get(4)==null)
{
top5array.add(values.iterator().next().toString());
}
while(values.iterator().hasNext())
{
String currentValues=values.iterator().next().toString();
String currentkey=currentValues.split("\\|")[0];
Integer currentnum=Integer.parseInt(currentValues.split("\\|")[1]);
for(int i=0;i<5;i++)
{
Integer numofArray = Integer.parseInt(top5array.get(i).split("\\|")[1]);
if(top5array.get(i) != null && currentnum < numofArray)
{
break;
}
if(i == 4)
{
String currentKeyValuePair = currentkey + currentnum.toString();
top5array.add(5, currentKeyValuePair);
Collections.sort(top5array);
top5array.remove(0);
}
}
}
String top5StringConca = "";
for(int i=0; i < 5; i++){
top5StringConca = top5StringConca + top5array.get(i);
}
context.write(new Text(" "), new Text(top5StringConca));
}
}
//the second of mapreduce end
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
Job job = Job.getInstance(conf);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
job.setMapperClass(Map2.class);
job.setReducerClass(Reduce2.class);
job.setCombinerClass(Combine.class);
job.setInputFormatClass(TextInputFormat.class);
job.setOutputFormatClass(TextOutputFormat.class);
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
job.waitForCompletion(true);
}
}
运行时出现的问题显示以下异常:
WARN [main] util.NativeCodeLoader (NativeCodeLoader.java:<clinit>(62))
- Unable to load native-hadoop library for your platform using builtin-java classes where applicable`
我怎样才能解决这个问题
在项目中添加hadoop jar。
如果您已经配置了hadoop,那么可以将您的HDF指向eclipse内部。为此,您必须包含依赖项。
如果在pom.xml中使用maven,请添加hadoop依赖项。还为eclipse添加第三方插件。这是向导。这些将在eclipse中启用MapReduce透视图。我在项目中添加了以下依赖项:
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-core</artifactId>
<version>1.2.1</version>
<scope>compile</scope>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-common</artifactId>
<version>2.6.0</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-client</artifactId>
<version>2.6.0</version>
</dependency>
您将看到依赖项本身包含hadoop jar。现在将取决于您是要使用jar提供的现有配置还是默认配置
现在尝试运行hadoop驱动程序类。您可以在eclipse中轻松调试代码。现在您的hadoop透视图也已启用。您可以在此处添加hdfs路径
您还可以检查远程调试。您是在windows上运行此程序吗?我是在ubuntui上运行的。我想知道如何在eclipse中调试mapreduce程序。请看一下。谢谢您的帮助,但是它不起作用谢谢你的回复。但是我找不到pom.xml?你能告诉我它在哪里吗?你当时没有使用基于maven的项目。使用工件Id名称搜索jar文件下载jar并包含到项目中。例如hadoop-client.jarHow?您是否会发布这些步骤,以便对将来有用!我的错误不在你提示的位置,它只是我的地图减少错误在我的地图。修改\t然后,我可以运行映射器,但现在,我也不能运行合并器和还原器!