mapreduce数据清洗-第一阶段
Result文件数据说明:
Ip:106.39.41.166,(城市)
Date:10/Nov/2016:00:01:02 +0800,(日期)
Day:10,(天数)
Traffic: 54 ,(流量)
Type: video,(类型:视频video或文章article)
Id: 8701(视频或者文章的id)
测试要求:
1、 数据清洗:按照进行数据清洗,并将清洗后的数据导入hive数据库中。
两阶段数据清洗:
(1)第一阶段:把需要的信息从原始日志中提取出来
ip: 199.30.25.88
time: 10/Nov/2016:00:01:03 +0800
traffic: 62
文章: article/11325
视频: video/3235
(2)第二阶段:根据提取出来的信息做精细化操作
ip--->城市 city(IP)
date--> time:2016-11-10 00:01:03
day: 10
traffic:62
type:article/video
id:11325
(3)hive数据库表结构:
create table data( ip string, time string , day string, traffic bigint,
type string, id string )
package test; import java.lang.String; import java.text.SimpleDateFormat; import java.util.Date; import java.util.Locale; 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 sjqx { static Dao dao=new Dao(); public static final SimpleDateFormat FORMAT = new SimpleDateFormat("d/MMM/yyyy:HH:mm:ss", Locale.ENGLISH); //原时间格式 public static final SimpleDateFormat dateformat1 = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss");//现时间格式 private static Date parseDateFormat(String string) { //转换时间格式 Date parse = null; try { parse = FORMAT.parse(string); } catch (Exception e) { e.printStackTrace(); } return parse; } public static class MyMapper extends Mapper<LongWritable, Text, Text/*map对应键类型*/, Text/*map对应值类型*/> { protected void map(LongWritable key, Text value,Context context)throws IOException, InterruptedException { String[] strNlist = value.toString().split(",");//如何分隔 //LongWritable,IntWritable,Text等 Date date = parseDateFormat(strNlist[1]); context.write(new Text(strNlist[0])/*map对应键类型*/,new Text(dateformat1.format(date)+","+strNlist[2]+","+strNlist[3]+","+strNlist[4]+","+strNlist[5])/*map对应值类型*/); } } public static class MyReducer extends Reducer<Text/*map对应键类型*/, Text/*map对应值类型*/, Text/*reduce对应键类型*/, Text/*reduce对应值类型*/> { // static No1Info info=new No1Info(); protected void reduce(Text key, Iterable<Text/*map对应值类型*/> values,Context context)throws IOException, InterruptedException { for (/*map对应值类型*/Text init : values) { // String[] strNlist = init.toString().split(","); // dao.add("data", strNlist); context.write( key/*reduce对应键类型*/, new Text(init)/*reduce对应值类型*/); } } } public static void main(String[] args) throws Exception { Configuration conf = new Configuration(); //将命令行中的参数自动设置到变量conf中 // String[] otherArgs = new GenericOptionsParser(conf,args).getRemainingArgs(); // if (otherArgs.length != 2) { // System.err.println("Usage: wordcount <in> <out>"); // System.exit(2); // } Job job = Job.getInstance(); //job.setJar("MapReduceDriver.jar"); job.setJarByClass(sjqx.class); // TODO: specify a mapper job.setMapperClass(MyMapper.class); job.setMapOutputKeyClass(/*map对应键类型*/Text.class); job.setMapOutputValueClass( /*map对应值类型*/Text.class); // TODO: specify a reducer job.setReducerClass(MyReducer.class); job.setOutputKeyClass(/*reduce对应键类型*/Text.class); job.setOutputValueClass(/*reduce对应值类型*/Text.class); // TODO: specify input and output DIRECTORIES (not files) FileInputFormat.setInputPaths(job, new Path("hdfs://localhost:9000/test/in/result")); FileOutputFormat.setOutputPath(job, new Path("hdfs://localhost:9000/test/out")); boolean flag = job.waitForCompletion(true); System.out.println("SUCCEED!"+flag); //任务完成提示 System.exit(flag ? 0 : 1); System.out.println(); } }
(清洗之前)(清洗之后)
在hive中创建表data
运行
load data inpath 'hdfs://localhost:9000/test/out/part-r-00000' overwrite into table data;
运行结果: