我在hadoop（Java版）中尝试了mapreduce程序，从json文件中找到共同的朋友列表 . json文件内容具有以下模式：
{"name":"abc","id":123} [{"name":"xyz","id":124},{"name":"def","id":125},{"name":"cxf","id":155}]
{"name":"cxf","id":155} [{"name":"xyz","id":124},{"name":"abc","id":123},{"name":"yyy","id":129}]
模式解释如下：
朋友json tab由相关朋友json的数组分隔
因此abc有xyz，def和cxf作为朋友cxf有xyz abc和yyy为朋友 .
鉴于上述情况，abc和cxf之间的共同朋友是xyz .
试图通过创建自定义可写入来使用mapreduce实现相同的功能，映射器发出以下键值，键是一对朋友，值是键中第一个朋友的相关朋友（即朋友对）
K->V
(abc,xyz) -> [xyz,def,cxf]
(abc,def) -> [xyz,def,cxf]
(abc,cxf) -> [xyz,def,cxf]
(cxf,xyz) -> [xyz,abc,yyy]
(cxf,abc) -> [xyz,abc,yyy]
(cxf,yyy) -> [xyz,abc,yyy]
这里的关键实际上是一个自定义可写，创建了一个扩展WritableComparable的类，我已经重写了compareTo方法，这样这些对（a，b）和（b，a）是相同的 . 但我面临的问题是没有为所有对的组合调用compareTo方法，因此reducer逻辑失败 .
基于上面的例子，映射器发射了6个K，V对 . 但是compareTo只被调用了5次key1.compareTo（key2），key2.compareTo（key3），key3.compareTo（key4），key4.compareTo（key5），key5.compareTo（key6） .
知道为什么会这样吗？
下面是根据f11ler建议的逻辑的代码
Driver class :
package com.facebook.updated;
import java.io.IOException;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.SequenceFileOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
import org.apache.log4j.Logger;
public class FacebookMain extends Configured implements Tool
{
Logger logger = Logger.getLogger(FacebookMain.class);
public static void main(String[] args) throws Exception {
System.exit(ToolRunner.run(new FacebookMain(), args));
}
@Override
public int run(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
logger.info("Running======>");
Job job = Job.getInstance();
job.setJarByClass(FacebookMain.class);
job.setJobName("FBApp");
job.setMapOutputKeyClass(Friend.class);
job.setMapOutputValueClass(Friend.class);
job.setOutputKeyClass(FriendPair.class);
job.setOutputValueClass(Friend.class);
job.setMapperClass(FacebookMapper.class);
job.setReducerClass(FacebookReducer.class);
job.setInputFormatClass(org.apache.hadoop.mapreduce.lib.input.TextInputFormat.class);
job.setOutputFormatClass(SequenceFileOutputFormat.class);
FileInputFormat.setInputPaths(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
boolean val = job.waitForCompletion(true);
return val ? 0 : 1;
}
}
The customWritables (used to represent a friend and friendpair)
package com.facebook.updated;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
import lombok.Getter;
import lombok.Setter;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.WritableComparable;
import org.apache.log4j.Logger;
@Getter
@Setter
public class Friend implements WritableComparable<Friend> {
Logger logger = Logger.getLogger(Friend.class);
private IntWritable id;
private Text name;
public Friend() {
this.id = new IntWritable();
this.name = new Text();
}
@Override
public int compareTo(Friend arg0) {
int val = getId().compareTo(arg0.getId());
logger.info("compareTo Friend ======> " + arg0 + " and " + this + " compare is " + val);
return val;
}
@Override
public void readFields(DataInput in) throws IOException {
id.readFields(in);
name.readFields(in);
}
@Override
public void write(DataOutput out) throws IOException {
id.write(out);
name.write(out);
}
@Override
public boolean equals(Object obj) {
Friend f2 = (Friend) obj;
boolean val = this.getId().equals(f2.getId());
//logger.info("equals Friend ======> " + obj + " and " + this);
return val;
}
@Override
public String toString() {
return id + ":" + name + " ";
}
}
package com.facebook.updated;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
import lombok.Getter;
import lombok.Setter;
import org.apache.hadoop.io.WritableComparable;
import org.apache.log4j.Logger;
@Getter
@Setter
public class FriendPair implements WritableComparable<FriendPair> {
Logger logger = Logger.getLogger(FriendPair.class);
private Friend first;
private Friend second;
public FriendPair() {
this.first = new Friend();
this.second = new Friend();
}
public FriendPair(Friend f1, Friend f2) {
this.first = f1;
this.second = f2;
}
@Override
public int compareTo(FriendPair o) {
logger.info("compareTo FriendPair ======> " + o + " and " + this);
FriendPair pair2 = o;
int cmp = -1;
if (getFirst().compareTo(pair2.getFirst()) == 0 || getFirst().compareTo(pair2.getSecond()) == 0) {
cmp = 0;
}
if (cmp != 0) {
// logger.info("compareTo FriendPair ======> " + o + " and " + this
// + " comparison is " + cmp);
return cmp;
}
cmp = -1;
if (getSecond().compareTo(pair2.getFirst()) == 0 || getSecond().compareTo(pair2.getSecond()) == 0) {
cmp = 0;
}
// logger.info("compareTo FriendPair ======> " + o + " and " + this +
// " comparison is " + cmp);
// logger.info("getFirst() " + getFirst());
// logger.info("pair2.getFirst() " + pair2.getFirst());
// logger.info("getFirst().compareTo(pair2.getFirst()) " +
// getFirst().compareTo(pair2.getFirst()));
// logger.info("getFirst().compareTo(pair2.getSecond()) " +
// getFirst().compareTo(pair2.getSecond()));
// logger.info("getSecond().compareTo(pair2.getFirst()) " +
// getSecond().compareTo(pair2.getFirst()));
// logger.info("getSecond().compareTo(pair2.getSecond()) " +
// getSecond().compareTo(pair2.getSecond()));
// logger.info("pair2.getSecond() " + pair2.getSecond());
// logger.info("getSecond() " + getSecond());
// logger.info("pair2.getFirst() " + pair2.getFirst());
// logger.info("pair2.getSecond() " + pair2.getSecond());
return cmp;
}
@Override
public boolean equals(Object obj) {
FriendPair pair1 = this;
FriendPair pair2 = (FriendPair) obj;
boolean eq = false;
logger.info("equals FriendPair ======> " + obj + " and " + this);
if (pair1.getFirst().equals(pair2.getFirst()) || pair1.getFirst().equals(pair2.getSecond()))
eq = true;
if (!eq) {
// logger.info("equals FriendPair ======> " + obj + " and " + this +
// " equality is " + eq);
return false;
}
if (pair1.getSecond().equals(pair2.getFirst()) || pair1.getSecond().equals(pair2.getSecond()))
eq = true;
// logger.info("equals FriendPair ======> " + obj + " and " + this +
// " equality is " + eq);
return eq;
}
@Override
public void readFields(DataInput in) throws IOException {
first.readFields(in);
second.readFields(in);
}
@Override
public void write(DataOutput out) throws IOException {
first.write(out);
second.write(out);
}
@Override
public String toString() {
return "[" + first + ";" + second + "]";
}
@Override
public int hashCode() {
logger.info("hashCode FriendPair ======> " + this);
return first.getId().hashCode() + second.getId().hashCode();
}
}
Mapper and Reducer
package com.facebook.updated;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
import java.util.StringTokenizer;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.log4j.Logger;
import com.mongodb.BasicDBList;
import com.mongodb.BasicDBObject;
import com.mongodb.util.JSON;
public class FacebookMapper extends Mapper<LongWritable, Text, Friend, Friend> {
Logger log = Logger.getLogger(FacebookMapper.class);
@Override
protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Friend, Friend>.Context context)
throws IOException, InterruptedException {
String line = value.toString();
StringTokenizer st = new StringTokenizer(line, "\t");
String person = st.nextToken();
String friends = st.nextToken();
BasicDBObject personObj = (BasicDBObject) JSON.parse(person);
BasicDBList friendsList = (BasicDBList) JSON.parse(friends);
List<Friend> frndJavaList = new ArrayList<>();
for (Object frndObj : friendsList) {
frndJavaList.add(getFriend((BasicDBObject) frndObj));
}
Friend frnd = getFriend(personObj);
Friend[] array = frndJavaList.toArray(new Friend[frndJavaList.size()]);
for (Friend f : array) {
log.info("Map output is " + f + " and " + frnd);
context.write(f, frnd);
}
}
private static Friend getFriend(BasicDBObject personObj) {
Friend frnd = new Friend();
frnd.setId(new IntWritable(personObj.getInt("id")));
frnd.setName(new Text(personObj.getString("name")));
frnd.setHomeTown(new Text(personObj.getString("homeTown")));
return frnd;
}
}
package com.facebook.updated;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.log4j.Logger;
public class FacebookReducer extends Reducer<Friend, Friend, FriendPair, Friend> {
Logger log = Logger.getLogger(FacebookReducer.class);
@Override
protected void reduce(Friend friend, Iterable<Friend> vals,
Reducer<Friend, Friend, FriendPair, Friend>.Context context) throws IOException, InterruptedException {
List<Friend> friends = new ArrayList<>();
for (Friend frnd : vals) {
friends.add(frnd);
}
log.info("Reducer output is " + friend + " and values are " + friends);
if (friends.size() == 2) {
FriendPair key = new FriendPair(friends.get(0), friends.get(1));
context.write(key, friend);
} else {
//log.info("Size of friends is not 2 key is " + friend + " and values are " + friends);
}
}
}
Input json file containing 2 lines
{"name":"abc","id":123} [{"name":"xyz","id":124},{"name":"def","id":125},{"name":"cxf","id":155}]
{"name":"cxf","id":155} [{"name":"xyz","id":124},{"name":"abc","id":123},{"name":"yyy","id":129}]
Output of reducer （abc，abc） - > xyz
1 回答
排序需要
compareTo方法，这种关系应该是可传递的 . 这意味着如果a> b和b> c则a> c . 您的实施可能并非如此 .为什么在mapper中生成这种记录？如果“成为朋友”是对称关系，您只需使用此逻辑（伪代码）执行仅限映射器的作业：
Update: 如果这不是对称的（这意味着"xyz has friend abc"不是来自"abc has friend xyz"）那么我们需要反向记录：
制图员：
Reducer（与之前的mapper相同）：
Update2:
让我们看看这个算法如何与你的例子一起工作：
映射器的结果：
Mapreduce wiil将这个值按键组合，所以reducer的输入：
在reducer中，我们按值进行嵌套循环，但跳过与self的比较 . 结果：
这就是我们想要得到的 .