【发布时间】:2014-10-13 03:18:03
【问题描述】:
这是我加入 2 个数据集的示例程序。 该程序有 2 个映射器和 1 个化简器连接从 2 个不同映射器获得的值,这些映射器具有 2 个不同的文件作为输入。
我在 hadoop jar 命令中遇到错误。
命令:
hadoop jar /home/rahul/Downloads/testjars/datajoin.jar DataJoin /user/rahul/cust.txt /user/rahul/delivery.txt /user/rahul/output
错误:无效的参数个数 Datajoin
它实际上只需要 1 个输入路径和 1 个输出路径,而在我的命令中,我有 2 个输入用于 2 个不同的映射器和 1 个输出。
谁能帮帮我?
代码:
import java.io.IOException;
import java.util.StringTokenizer;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.MultipleInputs;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;
public class DataJoin {
public static class TokenizerMapper1 extends Mapper {
private Text word = new Text();
public void map(Object key, Text value, Context context)
throws IOException, InterruptedException {
String itr[] = value.toString().split("::");
word.set(itr[0].trim());
context.write(word, new Text("CD~" + itr[1]));
}
}
public static class TokenizerMapper2 extends Mapper {
private Text word = new Text();
public void map(Object key, Text value, Context context)
throws IOException, InterruptedException {
String itr[] = value.toString().split("::");
word.set(itr[0].trim());
context.write(word, new Text("DD~" + itr[1]));
}
}
public static class IntSumReducer extends Reducer {
private Text result = new Text();
public void reduce(Text key, Iterable values, Context context)
throws IOException, InterruptedException {
String sum = "";
for (Text val : values) {
sum += val.toString();
}
result.set(sum);
context.write(key, result);
}
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
String[] otherArgs = new GenericOptionsParser(conf, args)
.getRemainingArgs();
if (otherArgs.length != 2) {
System.err.println("Usage: DataJoin ");
System.exit(2);
}
Job job = new Job(conf, "Data Join");
job.setJarByClass(DataJoin.class);
job.setReducerClass(IntSumReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
MultipleInputs.addInputPath(job, new Path(otherArgs[0]),
TextInputFormat.class, TokenizerMapper1.class);
MultipleInputs.addInputPath(job, new Path(otherArgs[1]),
TextInputFormat.class, TokenizerMapper2.class);
FileOutputFormat.setOutputPath(job, new Path(otherArgs[2]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
【问题讨论】:
-
格式化您的代码并更好地提问