一、倒排索引案例(多job串联)
1、需求
有大量的文本(文档、网页),需要建立搜索索引,如图4-31所示。
(1)数据输入
(2)期望输出数据
atguigu c.txt–>2 b.txt–>2 a.txt–>3
pingping c.txt–>1 b.txt–>3 a.txt–>1
ss c.txt–>1 b.txt–>1 a.txt–>2
2、需求分析
3、第一次处理
(1)第一次处理,编写OneIndexMapper类
package com.atguigu.mapreduce.index;
import java.io.IOException;
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.hadoop.mapreduce.lib.input.FileSplit;
public class OneIndexMapper extends Mapper<LongWritable, Text, Text, IntWritable>{
String name;
Text k = new Text();
IntWritable v = new IntWritable();
@Override
protected void setup(Context context)throws IOException, InterruptedException {
// 获取文件名称
FileSplit split = (FileSplit) context.getInputSplit();
name = split.getPath().getName();
}
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
// 1 获取1行
String line = value.toString();
// 2 切割
String[] fields = line.split(" ");
for (String word : fields) {
// 3 拼接
k.set(word+"--"+name);
v.set(1);
// 4 写出
context.write(k, v);
}
}
}
(2)第一次处理,编写OneIndexReducer类
package com.atguigu.mapreduce.index;
import java.io.IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
public class OneIndexReducer extends Reducer<Text, IntWritable, Text, IntWritable>{
IntWritable v = new IntWritable();
@Override
protected void reduce(Text key, Iterable<IntWritable> values,Context context) throws IOException, InterruptedException {
int sum = 0;
// 1 累加求和
for(IntWritable value: values){
sum +=value.get();
}
v.set(sum);
// 2 写出
context.write(key, v);
}
}
(3)第一次处理,编写OneIndexDriver类
package com.atguigu.mapreduce.index;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
public class OneIndexDriver {
public static void main(String[] args) throws Exception {
// 输入输出路径需要根据自己电脑上实际的输入输出路径设置
args = new String[] { "e:/input/inputoneindex", "e:/output5" };
Configuration conf = new Configuration();
Job job = Job.getInstance(conf);
job.setJarByClass(OneIndexDriver.class);
job.setMapperClass(OneIndexMapper.class);
job.setReducerClass(OneIndexReducer.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(IntWritable.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
FileInputFormat.setInputPaths(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
job.waitForCompletion(true);
}
}
(4)查看第一次输出结果
atguigu--a.txt 3
atguigu--b.txt 2
atguigu--c.txt 2
pingping--a.txt 1
pingping--b.txt 3
pingping--c.txt 1
ss--a.txt 2
ss--b.txt 1
ss--c.txt 1
4、第二次处理
(1)第二次处理,编写TwoIndexMapper类
package com.atguigu.mapreduce.index;
import java.io.IOException;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
public class TwoIndexMapper extends Mapper<LongWritable, Text, Text, Text>{
Text k = new Text();
Text v = new Text();
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
// 1 获取1行数据
String line = value.toString();
// 2用“--”切割
String[] fields = line.split("--");
k.set(fields[0]);
v.set(fields[1]);
// 3 输出数据
context.write(k, v);
}
}
(2)第二次处理,编写TwoIndexReducer类
package com.atguigu.mapreduce.index;
import java.io.IOException;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
public class TwoIndexReducer extends Reducer<Text, Text, Text, Text> {
Text v = new Text();
@Override
protected void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
// atguigu a.txt 3
// atguigu b.txt 2
// atguigu c.txt 2
// atguigu c.txt-->2 b.txt-->2 a.txt-->3
StringBuilder sb = new StringBuilder();
// 1 拼接
for (Text value : values) {
sb.append(value.toString().replace("\t", "-->") + "\t");
}
v.set(sb.toString());
// 2 写出
context.write(key, v);
}
}
(3)第二次处理,编写TwoIndexDriver类
package com.atguigu.mapreduce.index;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
public class TwoIndexDriver {
public static void main(String[] args) throws Exception {
// 输入输出路径需要根据自己电脑上实际的输入输出路径设置
args = new String[] { "e:/input/inputtwoindex", "e:/output6" };
Configuration config = new Configuration();
Job job = Job.getInstance(config);
job.setJarByClass(TwoIndexDriver.class);
job.setMapperClass(TwoIndexMapper.class);
job.setReducerClass(TwoIndexReducer.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(Text.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
FileInputFormat.setInputPaths(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
boolean result = job.waitForCompletion(true);
System.exit(result?0:1);
}
}
(4)第二次查看最终结果
atguigu c.txt-->2 b.txt-->2 a.txt-->3
pingping c.txt-->1 b.txt-->3 a.txt-->1
ss c.txt-->1 b.txt-->1 a.txt-->2
二、TopN案例
1、需求
对需求2.3输出结果进行加工,输出流量使用量在前10的用户信息
(1)输入数据 (2)输出数据
2、需求分析
3、实现代码
(1)编写FlowBean类
package com.atguigu.mr.top;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
import org.apache.hadoop.io.WritableComparable;
public class FlowBean implements WritableComparable<FlowBean>{
private long upFlow;
private long downFlow;
private long sumFlow;
public FlowBean() {
super();
}
public FlowBean(long upFlow, long downFlow) {
super();
this.upFlow = upFlow;
this.downFlow = downFlow;
}
@Override
public void write(DataOutput out) throws IOException {
out.writeLong(upFlow);
out.writeLong(downFlow);
out.writeLong(sumFlow);
}
@Override
public void readFields(DataInput in) throws IOException {
upFlow = in.readLong();
downFlow = in.readLong();
sumFlow = in.readLong();
}
public long getUpFlow() {
return upFlow;
}
public void setUpFlow(long upFlow) {
this.upFlow = upFlow;
}
public long getDownFlow() {
return downFlow;
}
public void setDownFlow(long downFlow) {
this.downFlow = downFlow;
}
public long getSumFlow() {
return sumFlow;
}
public void setSumFlow(long sumFlow) {
this.sumFlow = sumFlow;
}
@Override
public String toString() {
return upFlow + "\t" + downFlow + "\t" + sumFlow;
}
public void set(long downFlow2, long upFlow2) {
downFlow = downFlow2;
upFlow = upFlow2;
sumFlow = downFlow2 + upFlow2;
}
@Override
public int compareTo(FlowBean bean) {
int result;
if (this.sumFlow > bean.getSumFlow()) {
result = -1;
}else if (this.sumFlow < bean.getSumFlow()) {
result = 1;
}else {
result = 0;
}
return result;
}
}
(2)编写TopNMapper类
package com.atguigu.mr.top;
import java.io.IOException;
import java.util.Iterator;
import java.util.TreeMap;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
public class TopNMapper extends Mapper<LongWritable, Text, FlowBean, Text>{
// 定义一个TreeMap作为存储数据的容器(天然按key排序)
private TreeMap<FlowBean, Text> flowMap = new TreeMap<FlowBean, Text>();
private FlowBean kBean;
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
kBean = new FlowBean();
Text v = new Text();
// 1 获取一行
String line = value.toString();
// 2 切割
String[] fields = line.split("\t");
// 3 封装数据
String phoneNum = fields[0];
long upFlow = Long.parseLong(fields[1]);
long downFlow = Long.parseLong(fields[2]);
long sumFlow = Long.parseLong(fields[3]);
kBean.setDownFlow(downFlow);
kBean.setUpFlow(upFlow);
kBean.setSumFlow(sumFlow);
v.set(phoneNum);
// 4 向TreeMap中添加数据
flowMap.put(kBean, v);
// 5 限制TreeMap的数据量,超过10条就删除掉流量最小的一条数据
if (flowMap.size() > 10) {
// flowMap.remove(flowMap.firstKey());
flowMap.remove(flowMap.lastKey());
}
}
@Override
protected void cleanup(Context context) throws IOException, InterruptedException {
// 6 遍历treeMap集合,输出数据
Iterator<FlowBean> bean = flowMap.keySet().iterator();
while (bean.hasNext()) {
FlowBean k = bean.next();
context.write(k, flowMap.get(k));
}
}
}
(3)编写TopNReducer类
package com.atguigu.mr.top;
import java.io.IOException;
import java.util.Iterator;
import java.util.TreeMap;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
public class TopNReducer extends Reducer<FlowBean, Text, Text, FlowBean> {
// 定义一个TreeMap作为存储数据的容器(天然按key排序)
TreeMap<FlowBean, Text> flowMap = new TreeMap<FlowBean, Text>();
@Override
protected void reduce(FlowBean key, Iterable<Text> values, Context context)throws IOException, InterruptedException {
for (Text value : values) {
FlowBean bean = new FlowBean();
bean.set(key.getDownFlow(), key.getUpFlow());
// 1 向treeMap集合中添加数据
flowMap.put(bean, new Text(value));
// 2 限制TreeMap数据量,超过10条就删除掉流量最小的一条数据
if (flowMap.size() > 10) {
// flowMap.remove(flowMap.firstKey());
flowMap.remove(flowMap.lastKey());
}
}
}
@Override
protected void cleanup(Reducer<FlowBean, Text, Text, FlowBean>.Context context) throws IOException, InterruptedException {
// 3 遍历集合,输出数据
Iterator<FlowBean> it = flowMap.keySet().iterator();
while (it.hasNext()) {
FlowBean v = it.next();
context.write(new Text(flowMap.get(v)), v);
}
}
}
(4)编写TopNDriver类
package com.atguigu.mr.top;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
public class TopNDriver {
public static void main(String[] args) throws Exception {
args = new String[]{"e:/output1","e:/output3"};
// 1 获取配置信息,或者job对象实例
Configuration configuration = new Configuration();
Job job = Job.getInstance(configuration);
// 6 指定本程序的jar包所在的本地路径
job.setJarByClass(TopNDriver.class);
// 2 指定本业务job要使用的mapper/Reducer业务类
job.setMapperClass(TopNMapper.class);
job.setReducerClass(TopNReducer.class);
// 3 指定mapper输出数据的kv类型
job.setMapOutputKeyClass(FlowBean.class);
job.setMapOutputValueClass(Text.class);
// 4 指定最终输出的数据的kv类型
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(FlowBean.class);
// 5 指定job的输入原始文件所在目录
FileInputFormat.setInputPaths(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
// 7 将job中配置的相关参数,以及job所用的java类所在的jar包, 提交给yarn去运行
boolean result = job.waitForCompletion(true);
System.exit(result ? 0 : 1);
}
}
三、找博客共同好友案例
1、需求
以下是博客的好友列表数据,冒号前是一个用户,冒号后是该用户的所有好友(数据中的好友关系是单向的)
求出哪些人两两之间有共同好友,及他俩的共同好友都有谁?
(1)数据输入
2、需求分析
先求出A、B、C、….等是谁的好友
第一次输出结果
A I,K,C,B,G,F,H,O,D,
B A,F,J,E,
C A,E,B,H,F,G,K,
D G,C,K,A,L,F,E,H,
E G,M,L,H,A,F,B,D,
F L,M,D,C,G,A,
G M,
H O,
I O,C,
J O,
K B,
L D,E,
M E,F,
O A,H,I,J,F,
第二次输出结果
A-B E C
A-C D F
A-D E F
A-E D B C
A-F O B C D E
A-G F E C D
A-H E C D O
A-I O
A-J O B
A-K D C
A-L F E D
A-M E F
B-C A
B-D A E
B-E C
B-F E A C
B-G C E A
B-H A E C
B-I A
B-K C A
B-L E
B-M E
B-O A
C-D A F
C-E D
C-F D A
C-G D F A
C-H D A
C-I A
C-K A D
C-L D F
C-M F
C-O I A
D-E L
D-F A E
D-G E A F
D-H A E
D-I A
D-K A
D-L E F
D-M F E
D-O A
E-F D M C B
E-G C D
E-H C D
E-J B
E-K C D
E-L D
F-G D C A E
F-H A D O E C
F-I O A
F-J B O
F-K D C A
F-L E D
F-M E
F-O A
G-H D C E A
G-I A
G-K D A C
G-L D F E
G-M E F
G-O A
H-I O A
H-J O
H-K A C D
H-L D E
H-M E
H-O A
I-J O
I-K A
I-O A
K-L D
K-O A
L-M E F
3、代码实现
(1)第一次Mapper类
package com.atguigu.mapreduce.friends;
import java.io.IOException;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
public class OneShareFriendsMapper extends Mapper<LongWritable, Text, Text, Text>{
@Override
protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, Text>.Context context)
throws IOException, InterruptedException {
// 1 获取一行 A:B,C,D,F,E,O
String line = value.toString();
// 2 切割
String[] fields = line.split(":");
// 3 获取person和好友
String person = fields[0];
String[] friends = fields[1].split(",");
// 4写出去
for(String friend: friends){
// 输出 <好友,人>
context.write(new Text(friend), new Text(person));
}
}
}
(2)第一次Reducer类
package com.atguigu.mapreduce.friends;
import java.io.IOException;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
public class OneShareFriendsReducer extends Reducer<Text, Text, Text, Text>{
@Override
protected void reduce(Text key, Iterable<Text> values, Context context)throws IOException, InterruptedException {
StringBuffer sb = new StringBuffer();
//1 拼接
for(Text person: values){
sb.append(person).append(",");
}
//2 写出
context.write(key, new Text(sb.toString()));
}
}
(3)第一次Driver类
package com.atguigu.mapreduce.friends;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
public class OneShareFriendsDriver {
public static void main(String[] args) throws Exception {
// 1 获取job对象
Configuration configuration = new Configuration();
Job job = Job.getInstance(configuration);
// 2 指定jar包运行的路径
job.setJarByClass(OneShareFriendsDriver.class);
// 3 指定map/reduce使用的类
job.setMapperClass(OneShareFriendsMapper.class);
job.setReducerClass(OneShareFriendsReducer.class);
// 4 指定map输出的数据类型
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(Text.class);
// 5 指定最终输出的数据类型
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
// 6 指定job的输入原始所在目录
FileInputFormat.setInputPaths(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
// 7 提交
boolean result = job.waitForCompletion(true);
System.exit(result?0:1);
}
}
(4)第二次Mapper类
package com.atguigu.mapreduce.friends;
import java.io.IOException;
import java.util.Arrays;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
public class TwoShareFriendsMapper extends Mapper<LongWritable, Text, Text, Text>{
@Override
protected void map(LongWritable key, Text value, Context context)
throws IOException, InterruptedException {
// A I,K,C,B,G,F,H,O,D,
// 友 人,人,人
String line = value.toString();
String[] friend_persons = line.split("\t");
String friend = friend_persons[0];
String[] persons = friend_persons[1].split(",");
Arrays.sort(persons);
for (int i = 0; i < persons.length - 1; i++) {
for (int j = i + 1; j < persons.length; j++) {
// 发出 <人-人,好友> ,这样,相同的“人-人”对的所有好友就会到同1个reduce中去
context.write(new Text(persons[i] + "-" + persons[j]), new Text(friend));
}
}
}
}
(5)第二次Reducer类
package com.atguigu.mapreduce.friends;
import java.io.IOException;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
public class TwoShareFriendsReducer extends Reducer<Text, Text, Text, Text>{
@Override
protected void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
StringBuffer sb = new StringBuffer();
for (Text friend : values) {
sb.append(friend).append(" ");
}
context.write(key, new Text(sb.toString()));
}
}
(6)第二次Driver类
package com.atguigu.mapreduce.friends;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
public class TwoShareFriendsDriver {
public static void main(String[] args) throws Exception {
// 1 获取job对象
Configuration configuration = new Configuration();
Job job = Job.getInstance(configuration);
// 2 指定jar包运行的路径
job.setJarByClass(TwoShareFriendsDriver.class);
// 3 指定map/reduce使用的类
job.setMapperClass(TwoShareFriendsMapper.class);
job.setReducerClass(TwoShareFriendsReducer.class);
// 4 指定map输出的数据类型
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(Text.class);
// 5 指定最终输出的数据类型
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
// 6 指定job的输入原始所在目录
FileInputFormat.setInputPaths(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
// 7 提交
boolean result = job.waitForCompletion(true);
System.exit(result?0:1);
}
}