同时采取多个输入错误正在发生

Question

我得到这个错误:方法:

addInputPath(Job, Path, Class<? extends InputFormat>, Class<? extends Mapper>)

类型的MultipleInputs是不适用于参数(JobConf, Path, Class<TextInputFormat>, Class<App.MapClass>)

:

MultipleInputs.addInputPath(job, in, TextInputFormat.class, MapClass.class);
/* ------------------------ */
package hadoop.mi4;
/**
 * Hello world!
 *
 */
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.mapred.TextInputFormat;
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.MultipleInputs;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;

public class App {
    public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable>{
        private final static IntWritable one = new IntWritable(1);
        private Text word = new Text();
        public void map(Object key, Text value, Context context ) throws IOException, InterruptedException {
            StringTokenizer itr = new StringTokenizer(value.toString());
            while (itr.hasMoreTokens()) {
                word.set(itr.nextToken());
                context.write(word, one);
            }
        }
    }
    public static class TokenizerMapper1 extends Mapper<Object, Text, Text, IntWritable>{
        private final static IntWritable one = new IntWritable(1);
        private Text word = new Text();
        public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
            StringTokenizer itr = new StringTokenizer(value.toString());
            while (itr.hasMoreTokens()) {
                word.set(itr.nextToken());
                context.write(word, one);
            }
        }
    }
    public static class IntSumReducer extends Reducer<Text,IntWritable,Text,IntWritable> {
        private IntWritable result = new IntWritable();
        public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
            int sum = 0;
            for (IntWritable val : values) {
                sum += val.get();
            }
            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: App <in> <out>");
            System.exit(2);
         }
         Job job = new Job(conf, "word count");
         job.setJarByClass(App.class);
         job.setMapperClass(TokenizerMapper.class);
         job.setCombinerClass(IntSumReducer.class);
         job.setReducerClass(IntSumReducer.class);
         job.setOutputKeyClass(Text.class);
         job.setOutputValueClass(IntWritable.class);
         //FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
         MultipleInputs.addInputPath(job, new Path(otherArgs[0]), TextInputFormat.class, TokenizerMapper.class);
         MultipleInputs.addInputPath(job, new Path(otherArgs[1]), TextInputFormat.class, TokenizerMapper1.class);
         FileOutputFormat.setOutputPath(job, new Path(otherArgs[2]));
         System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}

Answer 1

它不工作，因为你已经从mapred与mapreduce混合类。替换下面的import

import org.apache.hadoop.mapred.TextInputFormat

import org.apache.hadoop.mapreduce.lib.input.TextInputFormat

Answer 2

看起来你的job变量的类型是JobConf，而它应该是Job。你应该试试

MultipleInputs.addInputPath(new Job(job), in, TextInputFormat.class, MapClass.class);

您还应该检查MapClass是否扩展了Mapper。