Question

一个文件包含这样的数据

robert 10,20,30
john 10,30,20

包含

等数据的另一个文件

surya 10|20|30
sumanth 30|40|10

像这10个文件我想得到输出数据是什么是昏迷分离和管道分离使用 Map Reduce

Answer 1

这里是用管道替换逗号分隔符的代码，并将同一姓氏的所有列表合并为一个

package my.reader;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
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 java.io.IOException;

public class ReadRows {
    public static class Map extends Mapper<LongWritable, Text, Text, Text> {
        public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            String[] res = value.toString().split("\t");
            if (res[1].contains(",")) {
                res[1] = res[1].replace(',','|');
            }
            context.write(new Text(res[0]), new Text(res[1]));
        }
    }

    public static class Reduce extends Reducer<Text,Text,Text,Text> {
        public void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException{
            String res = "";
            for(Text val : values) {
                res += "|" + val.toString();
            }
            context.write(key, new Text(res.substring(1)));
        }
    }

    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        if (args.length != 2) {
            System.err.println("Usage: my.reader.ReadRows <in> <out>");
            System.exit(2);
        }

        Job job = new Job(conf, "ReadRows");
        job.setJarByClass(ReadRows.class);
        job.setMapperClass(Map.class);
        job.setReducerClass(Reduce.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(Text.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(Text.class);
        job.setInputFormatClass(TextInputFormat.class);
        job.setOutputFormatClass(TextOutputFormat.class);

        FileInputFormat.addInputPath(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));

        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}

这里的代码只是解析它们并计算max：

public static class Map extends Mapper<LongWritable, Text, Text, IntWritable> {
    public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String[] res = value.toString().split("\t");
        String[] sal;
        if (res[1].contains(",")) {
            sal = res[1].split(",");
        } else {
            sal = res[1].split("\\|");
        }
        Integer maxSal = 0;
        for ( String s : sal ) {
            maxSal = max(Integer.valueOf(s), maxSal);
        }
        context.write(new Text(res[0]), new IntWritable(maxSal));
    }
}

public static class Reduce extends Reducer<Text,IntWritable,Text,IntWritable> {
    public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException{
        Integer maxSal = 0;
        for(IntWritable val : values) {
            maxSal = max(val.get(), maxSal);
        }
        context.write(key, new IntWritable(maxSal));
    }
}

我有10个CSV和TSV文件。我想在Apache Hadoop中使用MapReduce获取输出的CSV和TSV数据

1 个答案: