package com.wc;
import java.io.BufferedReader;
import java.io.FileReader;
import java.io.IOException;
import java.net.URI;
import java.util.HashSet;
import java.util.Set;
import java.util.StringTokenizer;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
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;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
public class WordCount {
public static class TokenizerMapper extends
Mapper<Object, Text, Text, IntWritable> {
Logger logger=LoggerFactory.getLogger(TokenizerMapper.class);
private final static IntWritable one = new IntWritable(1);
private Text word = new Text();
private Set<String> set;
private FileSystem hdfs;
@Override
protected void setup(org.apache.hadoop.mapreduce.Mapper.Context context)
throws IOException, InterruptedException {
super.setup(context);
set=new HashSet<String>();
Configuration conf = context.getConfiguration();
logger.warn("welcome :"+conf.get("welcome"));
URI[] patternsURIs = Job.getInstance(conf).getCacheFiles();
Path patternsPath = new Path(patternsURIs[0].getPath());
String patternsFileName = patternsPath.getName().toString();
logger.warn("patternsFileName :"+patternsFileName);
BufferedReader br=new BufferedReader(new FileReader(patternsFileName));
String line=null;
while((line=br.readLine())!=null)
{
logger.warn("line :"+line);
line=line.trim();
set.add(line);
}
}
// value已经是文件内容的一行
public void map(Object key, Text value, Context context)
throws IOException, InterruptedException {
StringTokenizer itr = new StringTokenizer(value.toString());
while (itr.hasMoreTokens()) {
String token = itr.nextToken();
if(set.contains(word.toString()))
{
token+="ThisIsACachedWord";
}
word.set(token);
context.write(word, one);
logger.warn("the word is :"+word);
}
}
}
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);
Logger logger=LoggerFactory.getLogger(TokenizerMapper.class);
logger.warn("the sum is :" + sum);
context.write(key, result);
}
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
String[] otherArgs = new GenericOptionsParser(conf, args)
.getRemainingArgs();
// Job job = new Job(conf, "word count");
conf.set("welcome", "hello HI");
Job job = Job.getInstance(conf, WordCount.class.getName());
job.addCacheFile(new Path(args[2]).toUri());
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);
}
}
hadoop 2 cachefile 分布式缓存 和 Configuration set get 的用法
最新推荐文章于 2022-10-06 17:19:16 发布