mapreduce 鍵值對怎麽定義的

壹般情況下Mapreduce輸出的鍵值對是以制表符\t為分隔符的，如下圖所示：

但有時候我們像將其設置為其它的分隔符輸出，比如","，如下圖所示：

此時可以在Mapreduce的主函數中添加如下的兩行代碼：

[java] view plain copy print?

conf.set("mapred.textoutputformat.ignoreseparator","true");

conf.set("mapred.textoutputformat.separator",",");

具體如下的WordCount程序：

[java] view plain copy print?

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.Mapper;

import org.apache.hadoop.mapreduce.Reducer;

import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;

import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import org.apache.hadoop.util.GenericOptionsParser;

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();

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();

//設置MapReduce的輸出的分隔符為逗號

conf.set("mapred.textoutputformat.ignoreseparator", "true");

conf.set("mapred.textoutputformat.separator", ",");

String[] otherArgs = new GenericOptionsParser(conf, args)

.getRemainingArgs();

if (otherArgs.length != 2) {

System.err.println("Usage: wordcount <in> <out>");

System.exit(2);

}

Job job = new Job(conf, "word count");

job.setJarByClass(WordCount.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]));

FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));

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

}

}

上一篇:porting advisor支持哪些軟件包掃描

下一篇:aix系統socket的tcp通訊超時時間怎麽查看和設置