hadoop實現單表和多表關聯
阿新 • • 發佈:2019-02-04
補充一個單錶鏈接的例子:
ublic class Single {
private static class SingleMapper extends
Mapper<LongWritable, Text, Text, Text> {
@Override
protected void map(LongWritable key, Text value,
Mapper<LongWritable, Text, Text, Text>.Context context)
throws IOException, InterruptedException {
String string = value.toString();
if (!string.contains("child")) {
String[] strings = string.split(" ");
context.write(new Text(strings[0]), new Text(strings[1] + ":1"));
context.write(new Text(strings[1 ]), new Text(strings[0] + ":2"));
}
}
}
// reduce是執行key的次數
private static class SingleReduce extends Reducer<Text, Text, Text, Text> {
@Override
protected void reduce(Text key, Iterable<Text> values,
Reducer<Text, Text, Text, Text>.Context context)
throws IOException, InterruptedException {
List<String> left = Lists.newArrayList();
List<String> right = Lists.newArrayList();
for (Text value : values) {
String[] strings = value.toString().split(":");
if (strings[1].equals("1")) {
right.add(strings[0]);
} else {
left.add(strings[0]);
}
}
for (String lef : left) {
for (String rig : right) {
context.write(new Text(lef), new Text(rig));
}
}
}
}
public static void main(String[] args) throws IOException,
ClassNotFoundException, InterruptedException {
Configuration configuration = HadoopConfig.getConfiguration();
Job job = Job.getInstance(configuration, "單表連線");
job.setJarByClass(Sort.class);
job.setMapperClass(SingleMapper.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(Text.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
job.setReducerClass(SingleReduce.class);
FileInputFormat.addInputPath(job, new Path("/data"));
FileOutputFormat.setOutputPath(job, new Path("/single"));
job.waitForCompletion(true);
}
補充一個多連結串列
import java.util.ArrayList;
import java.util.List;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.FileSplit;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;
public class MTjoin {
public static class Map extends Mapper<LongWritable, Text, Text, Text>{
private static Text k = new Text();
private static Text v = new Text();
protected void map(LongWritable key, Text value, Context context)
throws java.io.IOException ,InterruptedException {
String[] splits = value.toString().split("\t");
if(splits.length != 2){
return ;
}
//取得檔名 a.txt(工廠名字,序號) b.txt(序號,地址)
String fileName = ((FileSplit)context.getInputSplit()).getPath().getName();
if("a.txt".equals(fileName)){
k.set(splits[1]);
v.set("1"+splits[0]);
}else if("b.txt".equals(fileName)){
k.set(splits[0]);
v.set("2"+splits[1]);
}else{
return ;
}
context.write(k, v);
};
}
public static class Reduce extends Reducer<Text, Text, Text, Text>{
private static List<String> names = new ArrayList<String>();
private static List<String> addrs = new ArrayList<String>();
private static Text name = new Text();
private static Text addr = new Text();
protected void reduce(Text key, Iterable<Text> values, Context context)
throws java.io.IOException ,InterruptedException {
for (Text value : values) {
String temp = value.toString();
if(temp.startsWith("1")){
names.add(temp.substring(1));
}else{
addrs.add(temp.substring(1));
}
}
for (String n : names) {
for (String a : addrs) {
name.set(n);
addr.set(a);
context.write(name, addr);
}
}
names.clear();
addrs.clear();
};
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
String[] otherArgs = new GenericOptionsParser(conf,args).getRemainingArgs();
if(otherArgs.length != 2){
System.err.println("Usage:MTjoin");
System.exit(2);
}
Job job = new Job(conf, "MTjoin");
job.setJarByClass(MTjoin.class);
job.setMapperClass(Map.class);
job.setReducerClass(Reduce.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(Text.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
設計思路
分析這個事例,顯然需要進行單表連線,連線的是左表的parent列和又表的child列,且左表和右表示同一個表。
連線結果中除去連線的兩列就是所需要的結果,需要mapreduce解決這個事例,首先應該考慮如何實現表的自連線,其次就是連線的設定,最後是結果的整理
考慮到mapreduce的shuffle過程會將相同的key會連線在一起,所以可以將map結果的key設定成待連線的列,然後列中相同的值自然會連線在一起了,再與最開始的分析聯絡起來:
要連線的是左表parent列和右表的child列,且左表 和右表是用一個表,所以在map階段將讀入資料分割成child和parent之後,會將parent設定key,child設定成value進行是輸出,並作為左表,再將同一隊child和parent中的child設定成key,parent設定成value進行key,作為右表,為了區分輸出中的左右表,需要在輸出的value中再加上左表和右表,然後在shuffle過程中完成連線,reduce收到連線的結果,其中每個key的value-list就包含了“grandchild–grandparent”關係,取出每個key的value-list進行解析,將左表中的child放入一個數組,右表中的parent放入一個數組,然後對兩個陣列求#笛卡爾積#就是最後的結果了
import java.io.IOException;
import java.util.*;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Job;
import org.apche.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionParser;
public class STjoin{
public static int time=0;
public static class Map extends Mapper<Object,Text,Text,Text>{
//實現map函式
public void map(Object key,Text value,Context context)
throws IOException,InterruptedEXception{
String childname=new String();
String parentname=new String();
String relationtype=new String();//左右表標識
//輸入的一行預處理問題
StringTokenizer itr=new StringTokenizer(value.toString());
String[] values=new String[2];
int i=0;
while(itr.hasMoreTokens()){
values[i]=itr.nextToken();
i++;
}
if(values[0].compareTo("child")!=0){
childname=values[0];
parentname=values[1];
//輸出左表
relationtype="1";
context.write(new Text(values[1]),new Text(relationtype+"+"+childname+"+"+parentname));
//輸出右表
relationtype="2";
context.write(new Text(values[0],new Text(relationtype+"+"+childname+"+"+parentname));
}
}
}
public static class Reduce extends Reducer<Text,Text,Text,Text>{
public void reduce(Text key,Iterable<Text> values,Context context)
throws IOException,InterruptedException{
if(0==time){
context.write(new Text("grandchild"),new Text("grandparent"));
time++;
}
int grandchildnum=0;
String [] grandchild=new String [10];
int grandparentnum=0;
String [] grandparent =new String[10];
Iterator ite=values.iterator();
while(ite.hashNext()){
String record =ite.next().toString();
int len=record.length();
int i=2;
if(0==len){
continue;
}
// 取得左右表標識
char relationtype = record.charAt(0);
// 定義孩子和父母變數
String childname = new String();
String parentname = new String();
// 獲取value-list中value的child
while (record.charAt(i) != '+') {
childname += record.charAt(i);
i++;
}
i = i + 1;
// 獲取value-list中value的parent
while (i < len) {
parentname += record.charAt(i);
i++;
}
// 左表,取出child放入grandchildren
if ('1' == relationtype) {
grandchild[grandchildnum] = childname;
grandchildnum++;
}
// 右表,取出parent放入grandparent
if ('2' == relationtype) {
grandparent[grandparentnum] = parentname;
grandparentnum++;
}
}
// grandchild和grandparent陣列求笛卡爾兒積
if (0 != grandchildnum && 0 != grandparentnum) {
for (int m = 0; m < grandchildnum; m++) {
for (int n = 0; n < grandparentnum; n++) {
// 輸出結果
context.write(new Text(grandchild[m]), new Text(grandparent[n]));
}
}
}
}
}
public static void main(String[] args) throws Exception {
Configuration conf=new Configuration();
conf.set("mapred.job.tracker","192.168.224.100");
String[] ioArgs = new String[] { "STjoin_in", "STjoin_out" };
String[] otherArgs = new GenericOptionsParser(conf, ioArgs).getRemainingArgs();
if (otherArgs.length != 2) {
System.err.println("Usage: Single Table Join <in> <out>");
System.exit(2);
}
Job job = new Job(conf, "Single Table Join");
job.setJarByClass(STjoin.class);
// 設定Map和Reduce處理類
job.setMapperClass(Map.class);
job.setReducerClass(Reduce.class);
// 設定輸出型別
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
// 設定輸入和輸出目錄
FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
import java.io.IOException;
import java.util.*;
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.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;
public class MTjoin {
public static int time = 0;
/*
* 在map中先區分輸入行屬於左表還是右表,然後對兩列值進行分割,
* 儲存連線列在key值,剩餘列和左右表標誌在value中,最後輸出
*/
public static class Map extends Mapper<Object, Text, Text, Text> {
// 實現map函式
public void map(Object key, Text value, Context context)
throws IOException, InterruptedException {
String line = value.toString();// 每行檔案
String relationtype = new String();// 左右表標識
// 輸入檔案首行,不處理
if (line.contains("factoryname") == true
|| line.contains("addressed") == true) {
return;
}
// 輸入的一行預處理文字
StringTokenizer itr = new StringTokenizer(line);
String mapkey = new String();
String mapvalue = new String();
int i = 0;
while (itr.hasMoreTokens()) {
// 先讀取一個單詞
String token = itr.nextToken();
// 判斷該地址ID就把存到"values[0]"
if (token.charAt(0) >= '0' && token.charAt(0) <= '9') {
mapkey = token;
if (i > 0) {
relationtype = "1";
} else {
relationtype = "2";
}
continue;
}
// 存工廠名
mapvalue += token + " ";
i++;
}
// 輸出左右表
context.write(new Text(mapkey), new Text(relationtype + "+"+ mapvalue));
}
}
/*
* reduce解析map輸出,將value中資料按照左右表分別儲存,
* 然後求出笛卡爾積,並輸出。
*/
public static class Reduce extends Reducer<Text, Text, Text, Text> {
// 實現reduce函式
public void reduce(Text key, Iterable<Text> values, Context context)
throws IOException, InterruptedException {
// 輸出表頭
if (0 == time) {
context.write(new Text("factoryname"), new Text("addressname"));
time++;
}
int factorynum = 0;
String[] factory = new String[10];
int addressnum = 0;
String[] address = new String[10];
Iterator ite = values.iterator();
while (ite.hasNext()) {
String record = ite.next().toString();
int len = record.length();
int i = 2;
if (0 == len) {
continue;
}
// 取得左右表標識
char relationtype = record.charAt(0);
// 左表
if ('1' == relationtype) {
factory[factorynum] = record.substring(i);
factorynum++;
}
// 右表
if ('2' == relationtype) {
address[addressnum] = record.substring(i);
addressnum++;
}
}
// 求笛卡爾積
if (0 != factorynum && 0 != addressnum) {
for (int m = 0; m < factorynum; m++) {
for (int n = 0; n < addressnum; n++) {
// 輸出結果
context.write(new Text(factory[m]),
new Text(address[n]));
}
}
}
}
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
// 這句話很關鍵
conf.set("mapred.job.tracker", "192.168.1.2:9001");
String[] ioArgs = new String[] { "MTjoin_in", "MTjoin_out" };
String[] otherArgs = new GenericOptionsParser(conf, ioArgs).getRemainingArgs();
if (otherArgs.length != 2) {
System.err.println("Usage: Multiple Table Join <in> <out>");
System.exit(2);
}
Job job = new Job(conf, "Multiple Table Join");
job.setJarByClass(MTjoin.class);
// 設定Map和Reduce處理類
job.setMapperClass(Map.class);
job.setReducerClass(Reduce.class);
// 設定輸出型別
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
// 設定輸入和輸出目錄
FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}