import java.io.File;
import java.io.IOException;
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;
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 {
System.out.println("StringTokenizer:" + value.toString());
StringTokenizer itr = new StringTokenizer(value.toString());
while (itr.hasMoreTokens()) {
word.set(itr.nextToken());
context.write(word, one);
}
//hadoop 在eclipse中输出日志
org.apache.hadoop.mapreduce.Counter count = context.getCounter(
"map 中的值value", value.toString());
count.increment(1);
}
}
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);
//在eclipse中输出日志
org.apache.hadoop.mapreduce.Counter count= context.getCounter("reduce中的值key",
key.toString());
count.increment(1);
context.write(key, result);
}
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
//conf.set("mapred.job.tracker", "192.168.0.58:9001");
//conf.set("mapreduce.job.counters.limit", "1400");
//Error: Exceeded limits on number of counters 的解决方法
/**
./conf/mapred-site.xml 追加:如果是使用eclipse的话,修改hadoop-core-1.1.2.jar下的mapred-default.xml
<property>
<name>mapreduce.job.counters.limit</name>
<value>14000</value>
</property>
*/
System.out.println(new File(".").getAbsolutePath());
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]));
Path outputPath=new Path(otherArgs[1]);
FileSystem fs=outputPath.getFileSystem(conf);
if(fs.exists(outputPath))
{
fs.delete(outputPath);
}
FileOutputFormat.setOutputPath(job, outputPath);
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
hadoop 在eclipse中输出日志
最新推荐文章于 2019-06-13 22:07:45 发布