Hadoop项目练习

1 数据处理

2 统计网站不同浏览器访问次数

2.1 解析工具

https://github.com/LeeKemp/UserAgentParser
下载后用 maven 编译

安装

2.1.1 测试解析工具

修改 pom

<dependency>
            <groupId>com.kumkeegroupId>
            <artifactId>UserAgentParserartifactId>
            <version>0.0.1version>
dependency>

package com.bzt.cn.hdfs.useragent;

import com.kumkee.userAgent.UserAgent;
import com.kumkee.userAgent.UserAgentParser;

public class UserAgentTest {


    public static void main(String[] args) {
        String source = "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.101 Safari/537.36";

        UserAgentParser userAgentParser = new UserAgentParser();
        UserAgent agent = userAgentParser.parse(source);

        String browser = agent.getBrowser();
        String engine = agent.getEngine();
        String engineVersion = agent.getEngineVersion();
        String os = agent.getOs();
        String platform = agent.getPlatform();
        boolean isMobile = agent.isMobile();

        System.out.println(browser + ", " + engine + " , " + engineVersion + " ,"
                + os + " ," + platform + ", " + isMobile);
    }

}

2.2 抽取部分数据

[hadoop@node1 ~]$ ll
total 2752
-rw-r--r--.  1 hadoop hadoop 2769741 Oct 17  2017 10000_access.log
-rw-r--r--.  1 hadoop hadoop      58 Oct 30 10:13 animal.txt
drwxrwxr-x. 11 hadoop hadoop     236 Oct 29 10:49 apps
drwxrwxr-x.  4 hadoop hadoop      30 Oct 25 21:59 elasticsearchData
drwxrwxr-x.  4 hadoop hadoop      28 Sep 14 19:02 hbase
drwxrwxr-x.  4 hadoop hadoop      32 Sep 14 14:44 hdfsdir
drwxrwxr-x.  3 hadoop hadoop      17 Oct 29 11:00 hdp2.6-cdh5.7-data
-rw-r--r--.  1 hadoop hadoop      46 Oct 29 22:33 hello.txt
drwxrwxrwx.  3 hadoop hadoop      18 Oct 24 21:45 kafkaData
-rw-rw-r--.  1 hadoop hadoop       0 Oct 24 21:58 log-cleaner.log
drwxrwxr-x.  5 hadoop hadoop     133 Oct 23 14:40 metastore_db
-rw-r--r--.  1 hadoop hadoop    6709 Oct 30 10:30 part.jar
drwxrwxr-x.  3 hadoop hadoop      63 Oct 24 21:21 zookeeperData
-rw-rw-r--.  1 hadoop hadoop   26108 Oct 25 17:54 zookeeper.out
[hadoop@node1 ~]$ head -n 100 10000_access.log > 100_access.log
[hadoop@node1 ~]$ wc -l 100_access.log 
100 100_access.log
[hadoop@node1 ~]$ 

一条数据

183.162.52.7 - - [10/Nov/2016:00:01:02 +0800] "POST /api3/getadv HTTP/1.1" 200 813 "www.imooc.com" "-" cid=0×tamp=1478707261865&uid=2871142&marking=androidbanner&secrect=a6e8e14701ffe9f6063934780d9e2e6d&token=f51e97d1cb1a9caac669ea8acc162b96 "mukewang/5.0.0 (Android 5.1.1; Xiaomi Redmi 3 Build/LMY47V),Network 2G/3G" "-" 10.100.134.244:80 200 0.027 0.027

2.3 本地测试

package com.bzt.cn.hdfs.useragent;

import com.kumkee.userAgent.UserAgent;
import com.kumkee.userAgent.UserAgentParser;
import org.apache.commons.lang.StringUtils;
import org.junit.Test;

import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.InputStreamReader;
import java.util.HashMap;
import java.util.Map;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class UserAgentTest {


    @Test
    public void testReadFile() throws Exception {
        String path = "d://100_access.log";
        BufferedReader reader = new BufferedReader(
                new InputStreamReader(new FileInputStream(new File(path)))
        );

        String line = "";

        int i = 0;

        Map<String, Integer> browserMap = new HashMap<>();


        UserAgentParser userAgentParser = new UserAgentParser();

        while (line != null) {
            line = reader.readLine(); //一次读入一行数据

            i++;
            if (StringUtils.isNotBlank(line)) {
                String source = line.substring(getCharacterPosition(line, "\"", 7)) + 1;

                UserAgent agent = userAgentParser.parse(source);

                String browser = agent.getBrowser();
                String engine = agent.getEngine();
                String engineVersion = agent.getEngineVersion();
                String os = agent.getOs();
                String platform = agent.getPlatform();
                boolean isMobile = agent.isMobile();


                Integer browserValue = browserMap.get(browser);
                if (browserValue != null) {
                    browserMap.put(browser, (browserValue + 1));
                } else {
                    browserMap.put(browser, 1);
                }

                System.out.println(browser + ", " + engine + " , " + engineVersion + " ,"
                        + os + " ," + platform + ", " + isMobile);
            }

        }

        System.out.println("Records: " + (i - 1));
        System.out.println("===============================================");
        for (Map.Entry<String, Integer> entry : browserMap.entrySet()) {
            System.out.println(entry.getKey() + ", " + entry.getValue());
        }
    }

    /*
     * 测试自定义的方法
     * */
    @Test
    public void testGetCharacterPosition() {
        String value = "183.162.52.7 - - [10/Nov/2016:00:01:02 +0800] \"POST /api3/getadv HTTP/1.1\"";
        int index = getCharacterPosition(value, "\"", 2);
        System.out.println(index);

    }


    /*
     * 获取指定字符串中指定标识字符串出现索引的位置
     * */
    private int getCharacterPosition(String value, String operator, int index) {
        Matcher slashMatcher = Pattern.compile(operator).matcher(value);
        int mIdx = 0;
        while (slashMatcher.find()) {
            mIdx++;
            if (mIdx == index) {
                break;
            }
        }

        return slashMatcher.start();
    }


    /**
     * 单元测试
     */
    public void testUserAgentParser() {
        //public static void main(String[] args) {
        String source = "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.101 Safari/537.36";

        UserAgentParser userAgentParser = new UserAgentParser();
        UserAgent agent = userAgentParser.parse(source);

        String browser = agent.getBrowser();
        String engine = agent.getEngine();
        String engineVersion = agent.getEngineVersion();
        String os = agent.getOs();
        String platform = agent.getPlatform();
        boolean isMobile = agent.isMobile();

        System.out.println(browser + ", " + engine + " , " + engineVersion + " ,"
                + os + " ," + platform + ", " + isMobile);
    }

}

3 用 MapReduce 实现

3.1 pom 文件

<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0modelVersion>

    <groupId>com.bzt.cngroupId>
    <artifactId>test-hdfs-apiartifactId>
    <version>1.0version>

    <name>test-hdfs-apiname>
    
    <url>http://www.example.comurl>

    <properties>
        <project.build.sourceEncoding>UTF-8project.build.sourceEncoding>
        <maven.compiler.source>1.8maven.compiler.source>
        <maven.compiler.target>1.8maven.compiler.target>

        <hadoop.version>2.6.0-cdh5.7.0hadoop.version>
    properties>

    <repositories>
        <repository>
            <id>clouderaid>
            <url>https://repository.cloudera.com/artifactory/cloudera-repos/url>
        repository>

    repositories>

    <dependencies>

        <dependency>
            <groupId>org.apache.hadoopgroupId>
            <artifactId>hadoop-clientartifactId>
            <version>${hadoop.version}version>
            <scope>providedscope>
        dependency>

        <dependency>
            <groupId>com.kumkeegroupId>
            <artifactId>UserAgentParserartifactId>
            <version>0.0.1version>
        dependency>


        <dependency>
            <groupId>junitgroupId>
            <artifactId>junitartifactId>
            <version>4.11version>
            <scope>testscope>
        dependency>
    dependencies>

    <build>
        <plugins>

            <plugin>
                <artifactId>maven-assembly-pluginartifactId>
                <configuration>
                    <descriptorRefs>
                        <descriptorRef>jar-with-dependenciesdescriptorRef>
                    descriptorRefs>
                    <archive>
                        <manifest>
                            <mainClass>urlcount.BrowserCountmainClass>
                        manifest>
                    archive>
                configuration>
                <executions>
                    <execution>
                        <id>make-assemblyid>
                        <phase>packagephase>
                        <goals>
                            <goal>singlegoal>
                        goals>
                    execution>
                executions>
            plugin>


            <plugin>
                <groupId>org.apache.maven.pluginsgroupId>
                <artifactId>maven-compiler-pluginartifactId>
                <configuration>
                    <source>1.8source>
                    <target>1.8target>
                configuration>
            plugin>

            <plugin>
                <artifactId>maven-clean-pluginartifactId>
                <version>3.0.0version>
            plugin>
            
            <plugin>
                <artifactId>maven-resources-pluginartifactId>
                <version>3.0.2version>
            plugin>
            <plugin>
                <artifactId>maven-compiler-pluginartifactId>
                <version>3.7.0version>
            plugin>
            <plugin>
                <artifactId>maven-surefire-pluginartifactId>
                <version>2.20.1version>
            plugin>
            <plugin>
                <artifactId>maven-jar-pluginartifactId>
                <version>3.0.2version>
            plugin>
            <plugin>
                <artifactId>maven-install-pluginartifactId>
                <version>2.5.2version>
            plugin>
            <plugin>
                <artifactId>maven-deploy-pluginartifactId>
                <version>2.8.2version>
            plugin>
        plugins>
    build>
project>

3.2 源码

package urlcount;
import com.kumkee.userAgent.UserAgent;
import com.kumkee.userAgent.UserAgentParser;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
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.Partitioner;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import java.io.IOException;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class BrowserCount {
    public static class MyMapper extends Mapper<LongWritable, Text, Text, LongWritable> {

        LongWritable one = new LongWritable(1);
        private UserAgentParser userAgentParser;

        @Override
        protected void setup(Context context) throws IOException, InterruptedException {
            userAgentParser = new UserAgentParser();
        }

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

            //一行日志信息
            String line = value.toString();

            String source = line.substring(getCharacterPosition(line, "\"", 7)) + 1;

            UserAgent agent = userAgentParser.parse(source);

            String browser = agent.getBrowser();

            context.write(new Text(browser),one);
        }


        @Override
        protected void cleanup(Context context) throws IOException, InterruptedException {
            userAgentParser = null;
        }
    }


    /*
     * 获取指定字符串中指定标识字符串出现索引的位置
     * */
    private static int getCharacterPosition(String value, String operator, int index) {
        Matcher slashMatcher = Pattern.compile(operator).matcher(value);
        int mIdx = 0;
        while (slashMatcher.find()) {
            mIdx++;
            if (mIdx == index) {
                break;
            }
        }

        return slashMatcher.start();
    }

    /*
     * Reducer ; 归并操作
     * */
    public static class MyReducer extends Reducer<Text, LongWritable, Text, LongWritable> {

        long sum = 0;

        @Override
        protected void reduce(Text key, Iterable<LongWritable> values, Context context) throws IOException, InterruptedException {
            for (LongWritable value : values) {
                sum += value.get();
            }

            context.write(key, new LongWritable(sum));
        }
    }

    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration conf = new Configuration();

//        清理已经存在的输出目录
        Path outputPath = new Path(args[1]);
        FileSystem fileSystem = FileSystem.get(conf);
        if (fileSystem.exists(outputPath)) {
            fileSystem.delete(outputPath);
            System.out.println("output file deleted!");
        }

        // 创建 job
        Job job = Job.getInstance(conf, "BrowserCount");
        // 设置 job 处理类
        job.setJarByClass(BrowserCount.class);
        //设置作业处理的输入路径
        FileInputFormat.setInputPaths(job, new Path(args[0]));

        //设置 map 相关的参数
        job.setMapperClass(MyMapper.class);
        job.setOutputKeyClass(Text.class);
        job.setMapOutputValueClass(LongWritable.class);

        job.setReducerClass(MyReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(LongWritable.class);


        //设置作业处理的输出路径
        FileOutputFormat.setOutputPath(job, new Path(args[1]));

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

    }

}

3.3 maven 打包