Hadoop实现电商商单分析(1)
一.Pro文件
1.ContentUtils (热点搜索统计)
package com.task.ds.pro;
import com.task.ds.utils.IPParser;
import com.task.ds.utils.LogParser;
import org.apache.commons.lang3.StringUtils;
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.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import java.io.IOException;
import java.util.Map;
public class ProvinceStatApp {
public static void main(String[] args) throws Exception {
Configuration configuration = new Configuration();
FileSystem fileSystem = FileSystem.get(configuration);
Path outputPath = new Path("E:\\IdeaProject\\hadoop\\project\\src\\main\\java\\com\\data\\省流量统计");
if (fileSystem.exists(outputPath)) {
fileSystem.delete(outputPath, true);
}
Job job = Job.getInstance(configuration);
job.setJarByClass(ProvinceStatApp.class);
job.setMapperClass(MyMapper.class);
job.setReducerClass(MyReducer.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(LongWritable.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(LongWritable.class);
FileInputFormat.setInputPaths(job, new Path("E:\\IdeaProject\\hadoop\\project\\src\\main\\java\\com\\data\\trackinfo_20130721.txt"));
FileOutputFormat.setOutputPath(job, new Path("E:\\IdeaProject\\hadoop\\project\\src\\main\\java\\com\\data\\省流量统计"));
job.waitForCompletion(true);
}
static class MyMapper extends Mapper<LongWritable, Text, Text, LongWritable> {
private LongWritable ONE = new LongWritable(1);
private LogParser logParser;
@Override
protected void setup(Context context) throws IOException, InterruptedException {
logParser = new LogParser();
}
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
String log = value.toString();
Map<String, String> info = logParser.parse(log);
String ip = info.get("ip");
if (StringUtils.isNotBlank(ip)) {
IPParser.RegionInfo regionInfo = IPParser.getInstance().analyseIp(ip);
if (regionInfo != null) {
String provine = regionInfo.getProvince();
if (StringUtils.isNotBlank(provine)) {
context.write(new Text(provine), ONE);
} else {
context.write(new Text("-"), ONE);
}
} else {
context.write(new Text("-"), ONE);
}
} else {
context.write(new Text("-"), ONE);
}
}
}
static class MyReducer extends Reducer<Text, LongWritable, Text, LongWritable> {
@Override
protected void reduce(Text key, Iterable<LongWritable> values, Context context) throws IOException, InterruptedException {
long count = 0;
System.out.println(context);
for (LongWritable value : values) {
count++;
}
context.write(key, new LongWritable(count));
}
}
}
2.etl (提取关键信息)
package com.task.ds.pro;
import com.task.ds.utils.IPParser;
import com.task.ds.utils.LogParser;
import org.apache.commons.lang3.StringUtils;
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.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import java.io.IOException;
import java.util.Map;
public class etl {
public static void main(String[] args) throws Exception {
Configuration configuration = new Configuration();
FileSystem fileSystem = FileSystem.get(configuration);
Path outputPath = new Path("E:\\IdeaProject\\hadoop\\project\\src\\main\\java\\com\\data\\提取关键信息");
if (fileSystem.exists(outputPath)) {
fileSystem.delete(outputPath, true);
}
Job job = Job.getInstance(configuration);
job.setJarByClass(ProvinceStatApp.class);
job.setMapperClass(MyMapper.class);
job.setReducerClass(MyReduce.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(Text.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
FileInputFormat.setInputPaths(job, new Path("E:\\IdeaProject\\hadoop\\project\\src\\main\\java\\com\\data\\trackinfo_20130721.txt"));
FileOutputFormat.setOutputPath(job, new Path("E:\\IdeaProject\\hadoop\\project\\src\\main\\java\\com\\data\\提取关键信息"));
job.waitForCompletion(true);
}
static class MyMapper extends Mapper<LongWritable, Text, Text, Text> {
private LongWritable ONE = new LongWritable(1);
private LogParser logParser;
@Override
protected void setup(Context context) throws IOException, InterruptedException {
logParser = new LogParser();
}
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
String log = value.toString();
ContentUtils contentUtils = new ContentUtils();
Map<String, String> info = logParser.parse(log);
String ip = info.get("ip");
String url = info.get("url");
String pageId = contentUtils.getPageId(url);
String country = info.get("country");
String province = info.get("province");
String city = info.get("city");
String time = info.get("time");
String out = "," + pageId + "," + ip + "," + country + "," + province + "," + city + "," + time;
context.write(new Text(url) , new Text(out));
}
}
static class MyReduce extends Reducer<Text, Text, Text, Text> {
@Override
protected void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
for (Text value : values) {
context.write(key,value);
}
}
}
}
3.ProvinceStatApp (省流量统计)
package com.task.ds.pro;
import com.task.ds.utils.IPParser;
import com.task.ds.utils.LogParser;
import org.apache.commons.lang3.StringUtils;
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.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import java.io.IOException;
import java.util.Map;
public class ProvinceStatApp {
public static void main(String[] args) throws Exception {
Configuration configuration = new Configuration();
FileSystem fileSystem = FileSystem.get(configuration);
Path outputPath = new Path("E:\\IdeaProject\\hadoop\\project\\src\\main\\java\\com\\data\\省流量统计");
if (fileSystem.exists(outputPath)) {
fileSystem.delete(outputPath, true);
}
Job job = Job.getInstance(configuration);
job.setJarByClass(ProvinceStatApp.class);
job.setMapperClass(MyMapper.class);
job.setReducerClass(MyReducer.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(LongWritable.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(LongWritable.class);
FileInputFormat.setInputPaths(job, new Path("E:\\IdeaProject\\hadoop\\project\\src\\main\\java\\com\\data\\trackinfo_20130721.txt"));
FileOutputFormat.setOutputPath(job, new Path("E:\\IdeaProject\\hadoop\\project\\src\\main\\java\\com\\data\\省流量统计"));
job.waitForCompletion(true);
}
static class MyMapper extends Mapper<LongWritable, Text, Text, LongWritable> {
private LongWritable ONE = new LongWritable(1);
private LogParser logParser;
@Override
protected void setup(Context context) throws IOException, InterruptedException {
logParser = new LogParser();
}
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
String log = value.toString();
Map<String, String> info = logParser.parse(log);
String ip = info.get("ip");
if (StringUtils.isNotBlank(ip)) {
IPParser.RegionInfo regionInfo = IPParser.getInstance().analyseIp(ip);
if (regionInfo != null) {
String provine = regionInfo.getProvince();
if (StringUtils.isNotBlank(provine)) {
context.write(new Text(provine), ONE);
} else {
context.write(new Text("-"), ONE);
}
} else {
context.write(new Text("-"), ONE);
}
} else {
context.write(new Text("-"), ONE);
}
}
}
static class MyReducer extends Reducer<Text, LongWritable, Text, LongWritable> {
@Override
protected void reduce(Text key, Iterable<LongWritable> values, Context context) throws IOException, InterruptedException {
long count = 0;
System.out.println(context);
for (LongWritable value : values) {
count++;
}
context.write(key, new LongWritable(count));
}
}
}