Hadoop MapReduce旧API-将命令行参数传递到映射

Hadoop MapReduce旧API-将命令行参数传递到映射,hadoop,mapreduce,Hadoop,Mapreduce,我正在编写一个MapReduce作业,用于在使用旧API存储在HDFS中的输入文件中查找搜索字符串(通过命令行参数传递)的出现情况 下面是我的驾驶课- public class StringSearchDriver { public static void main(String[] args) throws IOException { JobConf jc = new JobConf(StringSearchDriver.class); jc.

我正在编写一个MapReduce作业,用于在使用旧API存储在HDFS中的输入文件中查找搜索字符串(通过命令行参数传递)的出现情况

下面是我的驾驶课-

public class StringSearchDriver
{

    public static void main(String[] args) throws IOException
    {
        JobConf jc = new JobConf(StringSearchDriver.class);
        jc.set("SearchWord", args[2]);
        jc.setJobName("String Search");
        FileInputFormat.addInputPath(jc, new Path(args[0]));
        FileOutputFormat.setOutputPath(jc, new Path(args[1]));
        jc.setMapperClass(StringSearchMap.class);
        jc.setReducerClass(StringSearchReduce.class);
        jc.setOutputKeyClass(Text.class);
        jc.setOutputValueClass(IntWritable.class);
        JobClient.runJob(jc);
    }
}
下面是我的Mapper类-

public class StringSearchMap extends MapReduceBase implements
        Mapper<LongWritable, Text, Text, IntWritable>
{
    String searchWord;

    public void configure(JobConf jc)
    {
        searchWord = jc.get("SearchWord");

    }



    @Override
    public void map(LongWritable key, Text value,  
            OutputCollector<Text, IntWritable> out, Reporter reporter)
            throws IOException
    {
        String[] input = value.toString().split("");

        for(String word:input)
        {
            if (word.equalsIgnoreCase(searchWord))
                out.collect(new Text(word), new IntWritable(1));
        }
    }

}
公共类StringSearchMap扩展了MapReduceBase实现
制图员
{
字符串搜索词;
公共void配置(JobConf jc)
{
searchWord=jc.get(“searchWord”);
}
@凌驾
公共无效映射(可长写键、文本值、,
输出收集器输出,报告器)
抛出IOException
{
字符串[]输入=value.toString().split(“”);
for(字符串字:输入)
{
if(word.equalsIgnoreCase(searchWord))
out.collect(新文本(word)、新可写(1));
}
}
}
在运行作业时(传递的命令行字符串为“hi”),我得到以下错误-

14/09/21 22:35:41 INFO mapred.JobClient: Task Id : attempt_201409212134_0005_m_000001_2, Status : FAILED
java.lang.ClassCastException: interface javax.xml.soap.Text
    at java.lang.Class.asSubclass(Class.java:3129)
    at org.apache.hadoop.mapred.JobConf.getOutputKeyComparator(JobConf.java:795)
    at org.apache.hadoop.mapred.MapTask$MapOutputBuffer.<init>(MapTask.java:964)
    at org.apache.hadoop.mapred.MapTask.runOldMapper(MapTask.java:422)
    at org.apache.hadoop.mapred.MapTask.run(MapTask.java:366)
    at org.apache.hadoop.mapred.Child$4.run(Child.java:255)
    at java.security.AccessController.doPrivileged(Native Method)
    at javax.security.auth.Subject.doAs(Subject.java:416)
    at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1190)
    at org.apache.hadoop.mapred.Child.main(Child.java:249)
14/09/21 22:35:41信息映射。作业客户端:任务Id:尝试\u 201409212134\u 0005\u m\u000001\u 2,状态:失败
java.lang.ClassCastException:接口javax.xml.soap.Text
在java.lang.Class.asSubclass(Class.java:3129)中
位于org.apache.hadoop.mapred.JobConf.getOutputKeyComparator(JobConf.java:795)
位于org.apache.hadoop.mapred.MapTask$MapOutputBuffer。(MapTask.java:964)
位于org.apache.hadoop.mapred.MapTask.runOldMapper(MapTask.java:422)
位于org.apache.hadoop.mapred.MapTask.run(MapTask.java:366)
位于org.apache.hadoop.mapred.Child$4.run(Child.java:255)
位于java.security.AccessController.doPrivileged(本机方法)
位于javax.security.auth.Subject.doAs(Subject.java:416)
位于org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1190)
位于org.apache.hadoop.mapred.Child.main(Child.java:249)

请建议。

文本;所需的hadoop包是org.apache.hadoop.io。。 检查您的包裹

import java.io.IOException;
import java.util.*;

import org.apache.hadoop.fs.Path;
import org.apache.hadoop.conf.*;
import org.apache.hadoop.io.*;
import org.apache.hadoop.mapred.*;
import org.apache.hadoop.util.*;

您自动导入了错误的导入。 而不是导入org.apache.hadoop.io.Text导入javax.xml.soap.Text

您可以在这个示例中找到错误的导入

有一点,最好采用新API

编辑

我使用了新的Api

import java.io.IOException;
import java.util.StringTokenizer;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.FileSystem;
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 org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

/**
 * @author Unmesha sreeveni
 * @Date 23 sep 2014
 */
public class StringSearchDriver extends Configured implements Tool {
    public static class Map extends
    Mapper<LongWritable, Text, Text, IntWritable> {

        private final static IntWritable one = new IntWritable(1);
        private Text word = new Text();

        public void map(LongWritable key, Text value, Context context)
                throws IOException, InterruptedException {
            Configuration conf = context.getConfiguration();
            String line = value.toString();
            String searchString = conf.get("word");
            StringTokenizer tokenizer = new StringTokenizer(line);
            while (tokenizer.hasMoreTokens()) {
                String token = tokenizer.nextToken();
                if(token.equals(searchString)){
                    word.set(token);
                    context.write(word, one);
                }

            }
        }
    }

    public static class Reduce extends
    Reducer<Text, IntWritable, Text, IntWritable> {

        public void reduce(Text key, Iterable<IntWritable> values,
                Context context) throws IOException, InterruptedException {

            int sum = 0;
            for (IntWritable val : values) {
                sum += val.get();
            }
            context.write(key, new IntWritable(sum));
        }
    }
    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        int res = ToolRunner.run(conf, new StringSearchDriver(), args);
        System.exit(res);

    }
    @Override
    public int run(String[] args) throws Exception {
        // TODO Auto-generated method stub
        if (args.length != 3) {
            System.out
            .printf("Usage: Search String <input dir> <output dir> <search word> \n");
            System.exit(-1);
        }

        String source = args[0];
        String dest = args[1];
        String searchword = args[2];
        Configuration conf = new Configuration();
        conf.set("word", searchword);
        Job job = new Job(conf, "Search String");
        job.setJarByClass(StringSearchDriver.class);
        FileSystem fs = FileSystem.get(conf);

        Path in =new Path(source);
        Path out =new Path(dest);
        if (fs.exists(out)) {
            fs.delete(out, true);
        }

        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        job.setMapperClass(Map.class);
        job.setReducerClass(Reduce.class);
        job.setInputFormatClass(TextInputFormat.class);
        job.setOutputFormatClass(TextOutputFormat.class);
        FileInputFormat.addInputPath(job, in);
        FileOutputFormat.setOutputPath(job, out);
        boolean sucess = job.waitForCompletion(true);
        return (sucess ? 0 : 1);
    }
}
import java.io.IOException;
导入java.util.StringTokenizer;
导入org.apache.hadoop.conf.Configuration;
导入org.apache.hadoop.conf.Configured;
导入org.apache.hadoop.fs.FileSystem;
导入org.apache.hadoop.fs.Path;
导入org.apache.hadoop.io.IntWritable;
导入org.apache.hadoop.io.LongWritable;
导入org.apache.hadoop.io.Text;
导入org.apache.hadoop.mapreduce.Job;
导入org.apache.hadoop.mapreduce.Mapper;
导入org.apache.hadoop.mapreduce.Reducer;
导入org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
导入org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
导入org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
导入org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
导入org.apache.hadoop.util.Tool;
导入org.apache.hadoop.util.ToolRunner;
/**
*@作者埃米沙·斯雷韦尼
*@日期2014年9月23日
*/
公共类StringSearchDriver扩展配置的实现工具{
公共静态类映射扩展
制图员{
私有最终静态IntWritable one=新的IntWritable(1);
私有文本字=新文本();
公共void映射(可长写键、文本值、上下文)
抛出IOException、InterruptedException{
conf=context.getConfiguration();
字符串行=value.toString();
String searchString=conf.get(“word”);
StringTokenizer标记器=新的StringTokenizer(行);
while(tokenizer.hasMoreTokens()){
String token=tokenizer.nextToken();
if(令牌等于(搜索字符串)){
word.set(令牌);
上下文。写(单词,一);
}
}
}
}
公共静态类Reduce扩展
减速器{
public void reduce(文本键、Iterable值、,
上下文)抛出IOException、InterruptedException{
整数和=0;
for(可写入值:值){
sum+=val.get();
}
write(key,newintwriteable(sum));
}
}
公共静态void main(字符串[]args)引发异常{
Configuration conf=新配置();
int res=ToolRunner.run(conf,new StringSearchDriver(),args);
系统退出(res);
}
@凌驾
公共int运行(字符串[]args)引发异常{
//TODO自动生成的方法存根
如果(参数长度!=3){
系统输出
.printf(“用法:搜索字符串\n”);
系统退出(-1);
}
字符串源=args[0];
字符串dest=args[1];
字符串searchword=args[2];
Configuration conf=新配置();
conf.set(“word”,searchword);
Job Job=新作业(conf,“搜索字符串”);
job.setJarByClass(StringSearchDriver.class);
FileSystem fs=FileSystem.get(conf);
路径输入=新路径(源);
路径输出=新路径(目的地);
如果(fs.exists(out)){
fs.删除(out,true);
}
job.setMapOutputKeyClass(Text.class);
setMapOutputValueClass(IntWritable.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
job.setMapperClass(Map.class);
job.setReducerClass(Reduce.class);
setInputFormatClass(TextInputFormat.class);
setOutputFormatClass(TextOutputFormat.class);
addInputPath(作业,在中);
setOutputPath(作业,输出);
布尔值suces=job.waitForCompletion(true);
返回(成功?0:1);
}
}

这是可行的。

ClassCastException:interface javax.xml