分两部分:
<span style="font-size:18px;">/***
* @author YangXin
* @date 2016/2/21
* @ info 主要功能是mahout实现解析Wikipedia链接文件的Mapper接口
*/
package unitSix;
import java.io.IOException;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.mahout.math.VarLongWritable;
public class WikipediaToItemPrefsMapper extends Mapper<LongWritable, Text, VarLongWritable, VarLongWritable>{
private static final Pattern NUMBERS = Pattern.compile("(\\d+)");