大數據教程(10.1)倒排索引創建

        前面博主介紹了sql中join功能的大數據實現,本節將繼續爲小夥伴們分享倒排索引的創建。java

        1、需求sql

              在不少項目中,咱們須要對咱們的文檔創建索引(如:論壇帖子);咱們須要記錄某個詞在各個文檔中出現的次數而且記錄下來供咱們進行查詢搜素,這就是咱們作搜素引擎最基礎的功能;分詞框架有開源的CJK等,搜素框架有lucene等。可是當咱們須要創建索引的文件數量太多的時候,咱們使用lucene來作效率就會很低;此時咱們須要創建本身的索引,可使用hadoop來實現。apache

              圖一、待統計的文檔centos

              圖二、創建的索引文件效果服務器

        2、代碼實現app

               step1:map-reduce框架

package com.empire.hadoop.mr.inverindex;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
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;

public class InverIndexStepOne {

    static class InverIndexStepOneMapper extends Mapper<LongWritable, Text, Text, IntWritable> {

        Text        k = new Text();
        IntWritable v = new IntWritable(1);

        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {

            String line = value.toString();

            String[] words = line.split(" ");

            FileSplit inputSplit = (FileSplit) context.getInputSplit();
            String fileName = inputSplit.getPath().getName();
            for (String word : words) {
                k.set(word + "--" + fileName);
                context.write(k, v);

            }

        }

    }

    static class InverIndexStepOneReducer extends Reducer<Text, IntWritable, Text, IntWritable> {

        @Override
        protected void reduce(Text key, Iterable<IntWritable> values, Context context)
                throws IOException, InterruptedException {

            int count = 0;
            for (IntWritable value : values) {

                count += value.get();
            }

            context.write(key, new IntWritable(count));

        }

    }

    public static void main(String[] args) throws Exception {

        Configuration conf = new Configuration();

        Job job = Job.getInstance(conf);
        job.setJarByClass(InverIndexStepOne.class);

        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        FileInputFormat.setInputPaths(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        // FileInputFormat.setInputPaths(job, new Path(args[0]));
        // FileOutputFormat.setOutputPath(job, new Path(args[1]));

        job.setMapperClass(InverIndexStepOneMapper.class);
        job.setReducerClass(InverIndexStepOneReducer.class);

        job.waitForCompletion(true);

    }

}

               step2:map-reduceide

package com.empire.hadoop.mr.inverindex;

import java.io.IOException;

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.output.FileOutputFormat;

public class IndexStepTwo {
    public static class IndexStepTwoMapper extends Mapper<LongWritable, Text, Text, Text> {
        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            String line = value.toString();
            String[] files = line.split("--");
            context.write(new Text(files[0]), new Text(files[1]));
        }
    }

    public static class IndexStepTwoReducer 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 text : values) {
                sb.append(text.toString().replace("\t", "-->") + "\t");
            }
            context.write(key, new Text(sb.toString()));
        }
    }

    public static void main(String[] args) throws Exception {

        if (args.length < 1 || args == null) {
            args = new String[] { "D:/temp/out/part-r-00000", "D:/temp/out2" };
        }

        Configuration config = new Configuration();
        Job job = Job.getInstance(config);
        job.setJarByClass(IndexStepTwo.class);
        job.setMapperClass(IndexStepTwoMapper.class);
        job.setReducerClass(IndexStepTwoReducer.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]));

        System.exit(job.waitForCompletion(true) ? 1 : 0);
    }
}

        3、執行程序oop

#上傳jar

Alt+p
lcd d:/
put  IndexStepOne.jar  IndexStepTwo.jar
put a.txt b.txt c.txt

#準備hadoop處理的數據文件

cd /home/hadoop
hadoop fs  -mkdir -p /index/indexinput
hdfs dfs -put  a.txt b.txt c.txt  /index/indexinput


#運行程序

hadoop jar IndexStepOne.jar  com.empire.hadoop.mr.inverindex.InverIndexStepOne /index/indexinput /index/indexsteponeoutput   
 
hadoop jar IndexStepTwo.jar  com.empire.hadoop.mr.inverindex.IndexStepTwo /index/indexsteponeoutput    
 /index/indexsteptwooutput

        4、運行效果大數據

[hadoop@centos-aaron-h1 ~]$ hadoop jar IndexStepOne.jar  com.empire.hadoop.mr.inverindex.InverIndexStepOne /index/indexinput /index/indexsteponeoutput   
18/12/19 07:08:42 INFO client.RMProxy: Connecting to ResourceManager at centos-aaron-h1/192.168.29.144:8032
18/12/19 07:08:43 WARN mapreduce.JobResourceUploader: Hadoop command-line option parsing not performed. Implement the Tool interface and execute your application with ToolRunner to remedy this.
18/12/19 07:08:43 INFO input.FileInputFormat: Total input files to process : 3
18/12/19 07:08:43 INFO Configuration.deprecation: yarn.resourcemanager.system-metrics-publisher.enabled is deprecated. Instead, use yarn.system-metrics-publisher.enabled
18/12/19 07:08:44 INFO mapreduce.JobSubmitter: Submitting tokens for job: job_1545173547743_0001
18/12/19 07:08:45 INFO impl.YarnClientImpl: Submitted application application_1545173547743_0001
18/12/19 07:08:45 INFO mapreduce.Job: The url to track the job: http://centos-aaron-h1:8088/proxy/application_1545173547743_0001/
18/12/19 07:08:45 INFO mapreduce.Job: Running job: job_1545173547743_0001
18/12/19 07:08:56 INFO mapreduce.Job: Job job_1545173547743_0001 running in uber mode : false
18/12/19 07:08:56 INFO mapreduce.Job:  map 0% reduce 0%
18/12/19 07:09:05 INFO mapreduce.Job:  map 33% reduce 0%
18/12/19 07:09:20 INFO mapreduce.Job:  map 67% reduce 0%
18/12/19 07:09:21 INFO mapreduce.Job:  map 100% reduce 100%
18/12/19 07:09:23 INFO mapreduce.Job: Job job_1545173547743_0001 completed successfully
18/12/19 07:09:23 INFO mapreduce.Job: Counters: 50
        File System Counters
                FILE: Number of bytes read=1252
                FILE: Number of bytes written=791325
                FILE: Number of read operations=0
                FILE: Number of large read operations=0
                FILE: Number of write operations=0
                HDFS: Number of bytes read=689
                HDFS: Number of bytes written=297
                HDFS: Number of read operations=12
                HDFS: Number of large read operations=0
                HDFS: Number of write operations=2
        Job Counters 
                Killed map tasks=1
                Launched map tasks=4
                Launched reduce tasks=1
                Data-local map tasks=4
                Total time spent by all maps in occupied slots (ms)=53828
                Total time spent by all reduces in occupied slots (ms)=13635
                Total time spent by all map tasks (ms)=53828
                Total time spent by all reduce tasks (ms)=13635
                Total vcore-milliseconds taken by all map tasks=53828
                Total vcore-milliseconds taken by all reduce tasks=13635
                Total megabyte-milliseconds taken by all map tasks=55119872
                Total megabyte-milliseconds taken by all reduce tasks=13962240
        Map-Reduce Framework
                Map input records=14
                Map output records=70
                Map output bytes=1106
                Map output materialized bytes=1264
                Input split bytes=345
                Combine input records=0
                Combine output records=0
                Reduce input groups=21
                Reduce shuffle bytes=1264
                Reduce input records=70
                Reduce output records=21
                Spilled Records=140
                Shuffled Maps =3
                Failed Shuffles=0
                Merged Map outputs=3
                GC time elapsed (ms)=1589
                CPU time spent (ms)=5600
                Physical memory (bytes) snapshot=749715456
                Virtual memory (bytes) snapshot=3382075392
                Total committed heap usage (bytes)=380334080
        Shuffle Errors
                BAD_ID=0
                CONNECTION=0
                IO_ERROR=0
                WRONG_LENGTH=0
                WRONG_MAP=0
                WRONG_REDUCE=0
        File Input Format Counters 
                Bytes Read=344
        File Output Format Counters 
                Bytes Written=297
[hadoop@centos-aaron-h1 ~]$
[hadoop@centos-aaron-h1 ~]$  hadoop jar IndexStepTwo.jar  com.empire.hadoop.mr.inverindex.IndexStepTwo /index/indexsteponeoutput /index/indexsteptwooutput
18/12/19 07:11:27 INFO client.RMProxy: Connecting to ResourceManager at centos-aaron-h1/192.168.29.144:8032
18/12/19 07:11:27 WARN mapreduce.JobResourceUploader: Hadoop command-line option parsing not performed. Implement the Tool interface and execute your application with ToolRunner to remedy this.
18/12/19 07:11:27 INFO input.FileInputFormat: Total input files to process : 1
18/12/19 07:11:28 INFO mapreduce.JobSubmitter: number of splits:1
18/12/19 07:11:28 INFO Configuration.deprecation: yarn.resourcemanager.system-metrics-publisher.enabled is deprecated. Instead, use yarn.system-metrics-publisher.enabled
18/12/19 07:11:28 INFO mapreduce.JobSubmitter: Submitting tokens for job: job_1545173547743_0002
18/12/19 07:11:28 INFO impl.YarnClientImpl: Submitted application application_1545173547743_0002
18/12/19 07:11:29 INFO mapreduce.Job: The url to track the job: http://centos-aaron-h1:8088/proxy/application_1545173547743_0002/
18/12/19 07:11:29 INFO mapreduce.Job: Running job: job_1545173547743_0002
18/12/19 07:11:36 INFO mapreduce.Job: Job job_1545173547743_0002 running in uber mode : false
18/12/19 07:11:36 INFO mapreduce.Job:  map 0% reduce 0%
18/12/19 07:11:42 INFO mapreduce.Job:  map 100% reduce 0%
18/12/19 07:11:48 INFO mapreduce.Job:  map 100% reduce 100%
18/12/19 07:11:48 INFO mapreduce.Job: Job job_1545173547743_0002 completed successfully
18/12/19 07:11:48 INFO mapreduce.Job: Counters: 49
        File System Counters
                FILE: Number of bytes read=324
                FILE: Number of bytes written=394987
                FILE: Number of read operations=0
                FILE: Number of large read operations=0
                FILE: Number of write operations=0
                HDFS: Number of bytes read=427
                HDFS: Number of bytes written=253
                HDFS: Number of read operations=6
                HDFS: Number of large read operations=0
                HDFS: Number of write operations=2
        Job Counters 
                Launched map tasks=1
                Launched reduce tasks=1
                Data-local map tasks=1
                Total time spent by all maps in occupied slots (ms)=3234
                Total time spent by all reduces in occupied slots (ms)=3557
                Total time spent by all map tasks (ms)=3234
                Total time spent by all reduce tasks (ms)=3557
                Total vcore-milliseconds taken by all map tasks=3234
                Total vcore-milliseconds taken by all reduce tasks=3557
                Total megabyte-milliseconds taken by all map tasks=3311616
                Total megabyte-milliseconds taken by all reduce tasks=3642368
        Map-Reduce Framework
                Map input records=21
                Map output records=21
                Map output bytes=276
                Map output materialized bytes=324
                Input split bytes=130
                Combine input records=0
                Combine output records=0
                Reduce input groups=7
                Reduce shuffle bytes=324
                Reduce input records=21
                Reduce output records=7
                Spilled Records=42
                Shuffled Maps =1
                Failed Shuffles=0
                Merged Map outputs=1
                GC time elapsed (ms)=210
                CPU time spent (ms)=990
                Physical memory (bytes) snapshot=339693568
                Virtual memory (bytes) snapshot=1694265344
                Total committed heap usage (bytes)=137760768
        Shuffle Errors
                BAD_ID=0
                CONNECTION=0
                IO_ERROR=0
                WRONG_LENGTH=0
                WRONG_MAP=0
                WRONG_REDUCE=0
        File Input Format Counters 
                Bytes Read=297
        File Output Format Counters 
                Bytes Written=253
[hadoop@centos-aaron-h1 ~]$

        5、運行結果

[hadoop@centos-aaron-h1 ~]$  hdfs dfs -cat  /index/indexsteponeoutput/part-r-00000
boby--a.txt     1
boby--b.txt     2
boby--c.txt     4
fork--a.txt     2
fork--b.txt     4
fork--c.txt     8
hello--a.txt    2
hello--b.txt    4
hello--c.txt    8
integer--a.txt  1
integer--b.txt  2
integer--c.txt  4
source--a.txt   1
source--b.txt   2
source--c.txt   4
tom--a.txt      1
tom--b.txt      2
tom--c.txt      4
[hadoop@centos-aaron-h1 ~]$
[hadoop@centos-aaron-h1 ~]$  hdfs dfs -cat  /index/indexsteptwooutput/part-r-00000
boby    a.txt-->1       b.txt-->2       c.txt-->4
fork    a.txt-->2       b.txt-->4       c.txt-->8
hello   b.txt-->4       c.txt-->8       a.txt-->2
integer a.txt-->1       b.txt-->2       c.txt-->4
source  a.txt-->1       b.txt-->2       c.txt-->4
tom     a.txt-->1       b.txt-->2       c.txt-->4
[hadoop@centos-aaron-h1 ~]$

        最後寄語,以上是博主本次文章的所有內容,若是你們以爲博主的文章還不錯,請點贊;若是您對博主其它服務器大數據技術或者博主本人感興趣,請關注博主博客,而且歡迎隨時跟博主溝通交流。

相關文章
相關標籤/搜索