目录
一、需求
1.获取文本总行数
2.获取单词总数
二、具体代码
1.driver端程序编写
- 因为在mapper端即可完成计数任务,所以不需要reducer端 numreducetasks默认值是1,因此应在代码中设置为0
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import java.io.IOException;
public class MyCounterDemo {
/*
*定义枚举常量 LINE_COUNT :用于统计文件的总行数
* WORD_COUNT :用于统计单词总数
*/
public enum COUNTER_WORD_COUNT{
LINE_COUNT,WORD_COUNT
}
public static void main(String[] args)throws IOException,ClassNotFoundException,InterruptedException{
Configuration conf = new Configuration();
conf.set("fs.defaultFS","hdfs://192.168.230.13:9000");
Job job= Job.getInstance(conf);
job.setJarByClass(MyCounterDemo.class);
job.setMapperClass(MyCounterMapper.class);
//设置ReduceTask的个数,默认为1个
//当前的题目下,不需要reduce,直接在map端输出,所以设置为0
job.setNumReduceTasks(0);
job.setMapOutputKeyClass(NullWritable.class);
job.setMapOutputValueClass(NullWritable.class);
Path inPath = new Path("/mapreduce/9.1/counter/input");
Path outpath = new Path("/mapreduce/9.1/counter/output");
FileSystem fs = FileSystem.get(conf);
if (fs.exists(outpath)){
fs.delete(outpath,true);
}
FileInputFormat.setInputPaths(job,inPath);
FileOutputFormat.setOutputPath(job,outpath);
boolean waitForCompletion = job.waitForCompletion(true);
System.exit(waitForCompletion ? 0:1);
}
}
2.map端程序编写
有两种方法进行计算:①枚举计数器 ②自定义计数器(组名,计数器名字)
最后结果可以看到两种方法统计出的结果是一样的
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import java.io.IOException;
// 字节偏移量 --- 每一行的内容 --- 空值 --- 空值
public class MyCounterMapper extends Mapper<LongWritable,Text,NullWritable,NullWritable > {
@Override
protected void map(LongWritable key,Text value,
Mapper<LongWritable,Text,NullWritable,NullWritable>.Context context)throws IOException,InterruptedException{
//需求1:获取文件总行数
//因为是逐行读取,所以有多少行----代表调用多少次map()方法
//方法1:枚举计数器
context.getCounter(
MyCounterDemo.COUNTER_WORD_COUNT.LINE_COUNT).increment(1L);
//方法2:自定义计数器(组名,计数器名字)
context.getCounter("counter_word_count","line_count").increment(1L);
//需求2:获取单词个数
//获取一行文本内容,按照分隔符进行切分
String[] splits = value.toString().split(",");
//遍历数组
for(String word:splits){
//统计单词总数,遇见一个单词就加1
//方法1:枚举计数器
context.getCounter(MyCounterDemo.COUNTER_WORD_COUNT.WORD_COUNT
).increment(1L);
//方法2:自定义计数器(组名,计数器名字)
context.getCounter("counter_word_count",
"word_count").increment(1L);
}
}
}
结果:
方法1:
方法2: