向MapReduce转换：生成用户向量

分两部份：

<span>/***
 * @author YangXin
 * @date 2016/2/21
 * @ info 重要功效是mahout实现解析Wikipedia连接文件的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+)");
	public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException{
		String line = value.toString();
		Matcher m = NUMBERS.matcher(line);
		//定位用户ID
		m.find();                              
		VarLongWritable userID = new VarLongWritable(Long.parseLong(m.group()));
		VarLongWritable itemID = new VarLongWritable();
		while(m.find()){
			itemID.set(Long.parseLong(m.group()));
			//为每一个物品ID生成用户-物品对
			context.write(userID, itemID);
		}
	}
}</span><span>/***
 * @author YangXin
 * @date 2016