我们必须编写一个InputFormat和RecordReader,用于读取由' $'分隔的文本字符串。字符而不是换行符。
现在假设我们有一个像这样的数据集
$ <some data>
$ <some data>
我们希望使用第一个$作为分隔符,我们必须免除中期&#34;美元&#34;从使它成为分界符号。
您能否提出必要的功能或必要的步骤来实现这一目标?
提前谢谢
答案 0 :(得分:1)
输入文件
$Aniruddha Sinha$23$Hadoop$mapreduce$Kishore$30$Hadoop$mapreduce
输出文件
Aniruddha Sinha,23,Hadoop,mapreduce
Kishore,30,Hadoop,mapreduce
码
import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.SkipBadRecords;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
public class WordCount {
public static class TokenizerMapper
extends Mapper<Object, Text, Text, IntWritable>{
private final static IntWritable one = new IntWritable(1);
private Text word = new Text();
private int count = 0;
private StringBuilder sb = new StringBuilder();
public void map(Object key, Text value, Context context
) throws IOException, InterruptedException {
if(count < 4){
sb.append(value.toString());
sb.append(",");
count++;
if(count == 4){
System.out.println(sb.substring(0, sb.length()-1));
count = 0;
word.set(sb.substring(0, sb.length()-1));
context.write(word, one);
sb.delete(0, sb.length());
}
}
}
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
conf.set("textinputformat.record.delimiter", "$");
Job job = Job.getInstance(conf, "word count");
job.setJarByClass(WordCount.class);
job.setMapperClass(TokenizerMapper.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
SkipBadRecords.setMapperMaxSkipRecords(conf, 10);
FileInputFormat.setInputPaths(job, new Path("/home/kishore/input"));
FileOutputFormat.setOutputPath(job, new Path("/home/kishore/output"));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}