一个最简单的WordCount解析:
import java.io.IOException;
import java.util.*;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.*;
import org.apache.hadoop.mapred
public class WordCount {
public static class Map extends MapReduceBase implements
Mapper<LongWritable, Text, Text, IntWritable> {
//这个Mapper中前两个参数对应map方法中的input key/value
//后两个参数对应于输出的OutputCollect类型
private final static IntWritable one = new IntWritable(1);
private Text word = new Text();
public void map(LongWritable key, Text value,
OutputCollector<Text, Writable> output, Reporter reporter)
throws IOException {
String line = value.toString();
StringTokenizer tokenizer = new StringTokenizer(line);
while (tokenizer.hasMoreTokens()) {
word.set(tokenizer.nextToken());
output.collect(word, one);
}
}
}
public static class Reduce extends MapReduceBase implements
Reducer<Text, IntWritable, Text, IntWritable> {
public void reduce(Text key, Iterator<IntWritable> values,
OutputCollector<Text, IntWritable> output, Reporter reporter)
throws IOException {
int sum = 0;
while (values.hasNext()) {
sum += values.next().get();
}
output.collect(key, new IntWritable(sum));
}
}
public static void main(String[] args) throws Exception {
//配置Job
JobConf conf = new JobConf(WordCount.class);
//设置Job名称
conf.setJobName("wordcount");
//设置输出键值类型
conf.setOutputKeyClass(Text.class);
conf.setOutputValueClass(IntWritable.class);
//指定Map/Reduce处理类
conf.setMapperClass(Map.class);
conf.setReducerClass(Reduce.class);
//指定TextInputFormat类为输入方式,该类将文件分解为行,并以换行或回车符作为行结尾
//并以文件中偏移量为键,以每行内容作为值
/*An InputFormat for plain text files.
Files are broken into lines.
Either linefeed or carriage-return are used to signal end of line.
Keys are the position in the file, and values are the line of text..
*/
conf.setInputFormat(TextInputFormat.class);
//指定该输出格式为TextOutputFormat,该类为写入一个文本文件
conf.setOutputFormat(TextOutputFormat.class);
//指定要解析的数据及输出文件路径
FileInputFormat.setInputPaths(conf, new Path(args[0]));
FileOutputFormat.setOutputPath(conf, new Path(args[1]));
//提交Job
JobClient.runJob(conf);
}
}
几个重要接口:
1.InputFormat(可以指定):指定输入源如何解析
将输入源分割为InputSplit(不可指定),使用RecordReader(不可指定)将每个InputSplit转化为输入记录
2.Mapper(用户定义)
3.Combiner(在map节点上,用户可以定义)将在Map之后进行,可以减少网络传输
4.Paritioner(在reduce节点,用户可以定义)将确定map后的结果谁来执行
5.Sort Map之后包括到partition后将有一次归并排序过程,Partition和Sort过程即是shuffle过程
6.reduce (用户定义)