利用HDFS怎么實(shí)現(xiàn)多文件Join操作

import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
import java.util.HashMap;
import java.util.Map;


import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.contrib.utils.join.DataJoinMapperBase;
import org.apache.hadoop.contrib.utils.join.DataJoinReducerBase;
import org.apache.hadoop.contrib.utils.join.TaggedMapOutput;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.Writable;
import org.apache.hadoop.mapred.FileInputFormat;
import org.apache.hadoop.mapred.FileOutputFormat;
import org.apache.hadoop.mapred.JobClient;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.TextInputFormat;
import org.apache.hadoop.mapred.TextOutputFormat;
import org.apache.hadoop.util.ReflectionUtils;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;


import cn.eshore.traffic.hadoop.util.CommUtil;
import cn.eshore.traffic.hadoop.util.StringUtil;




/**
 * @ClassName: DataJoin
 * @Description: HDFS JOIN操作
 * @author hadoop
 * @date 2012-12-18 下午5:51:32
 */
public class InstallJoin extends Configured implements Tool {
private String static enSplitCode = "\\|";
private String static splitCode = "|";


// 自定義Reducer
public static class ReduceClass extends DataJoinReducerBase {


@Override
protected TaggedMapOutput combine(Object[] tags, Object[] values) {
String joinedStr = "";
//該段判斷用戶生成Left join限制【其中tags表示文件的路徑，install表示文件名稱(chēng)前綴】
//去掉則為All Join
if (tags.length == 1 && tags[0].toString().contains("install")) {
return null;
}

Map<String, String> map = new HashMap<String, String>();
for (int i = 0; i < values.length; i++) {
TaggedWritable tw = (TaggedWritable) values[i];
String line = ((Text) tw.getData()).toString();


String[] tokens = line.split(enSplitCode, 8);
String groupValue = tokens[6];

String type = tokens[7];

map.put(type, groupValue);
}

joinedStr += StringUtil.getCount(map.get("7"))+"|"+StringUtil.getCount(map.get("30"));
TaggedWritable retv = new TaggedWritable(new Text(joinedStr));
retv.setTag((Text) tags[0]);
return retv;
}
}


// 自定義Mapper
public static class MapClass extends DataJoinMapperBase {


//自定義Key【類(lèi)似數(shù)據(jù)庫(kù)中的主鍵/外鍵】
@Override
protected Text generateGroupKey(TaggedMapOutput aRecord) {
String line = ((Text) aRecord.getData()).toString();
String[] tokens = line.split(CommUtil.enSplitCode);


String key = "";
String type = tokens[7];
//由于不同文件中的Key所在列有可能不同，所以需要?jiǎng)討B(tài)生成Key，其中type為不同文件中的數(shù)據(jù)標(biāo)識(shí)；如：A文件最后一列為a用于表示此數(shù)據(jù)為A文件數(shù)據(jù)
if ("7".equals(type)) {
key = tokens[0]+"|"+tokens[1];
}else if ("30".equals(type)) {
key = tokens[0]+"|"+tokens[2];
}
return new Text(key);
}


@Override
protected Text generateInputTag(String inputFile) {
return new Text(inputFile);
}


@Override
protected TaggedMapOutput generateTaggedMapOutput(Object value) {
TaggedWritable retv = new TaggedWritable((Text) value);
retv.setTag(this.inputTag);
return retv;
}


}


public static class TaggedWritable extends TaggedMapOutput {


private Writable data;


// 自定義
public TaggedWritable() {
this.tag = new Text("");
}


public TaggedWritable(Writable data) {
this.tag = new Text("");
this.data = data;
}


@Override
public Writable getData() {
return data;
}


@Override
public void write(DataOutput out) throws IOException {
this.tag.write(out);
out.writeUTF(this.data.getClass().getName());
this.data.write(out);
}


@Override
public void readFields(DataInput in) throws IOException {
this.tag.readFields(in);
String dataClz = in.readUTF();
if (this.data == null
|| !this.data.getClass().getName().equals(dataClz)) {
try {
this.data = (Writable) ReflectionUtils.newInstance(
Class.forName(dataClz), null);
} catch (ClassNotFoundException e) {
e.printStackTrace();
}
}
this.data.readFields(in);
}


}


/**
* job運(yùn)行
*/
@Override
public int run(String[] paths) throws Exception {
int no = 0;
try {
Configuration conf = getConf();
JobConf job = new JobConf(conf, InstallJoin.class);
FileInputFormat.setInputPaths(job, new Path(paths[0]));
FileOutputFormat.setOutputPath(job, new Path(paths[1]));
job.setJobName("join_data_test");
job.setMapperClass(MapClass.class);
job.setReducerClass(ReduceClass.class);
job.setInputFormat(TextInputFormat.class);
job.setOutputFormat(TextOutputFormat.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(TaggedWritable.class);
job.set("mapred.textoutputformat.separator", CommUtil.splitCode);
JobClient.runJob(job);
no = 1;
} catch (Exception e) {
throw new Exception();
}
return no;
}


//測(cè)試
public static void main(String[] args) {
String[] paths = {
"hdfs://master...:9000/home/hadoop/traffic/join/newtype",
"hdfs://master...:9000/home/hadoop/traffic/join/newtype/output" }

int res = 0;
try {
res = ToolRunner.run(new Configuration(), new InstallJoin(), paths);
} catch (Exception e) {
e.printStackTrace();
}
System.exit(res);
}
}