package?eb.cloud.mapreduce.MR.guoruonan;

import?org.apache.hadoop.conf.Configuration;
import?org.apache.hadoop.fs.FileStatus;
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.input.FileSplit;
import?org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import?org.apache.hadoop.util.GenericOptionsParser;

import?java.io.IOException;
import?java.util.ArrayList;
import?java.util.Collections;
import?java.util.Comparator;

public?class?Tfidf?{

????public?static?class?Mapper0?extends?Mapper?{
????????String?filename;

????????public?void?map（LongWritable?key?Text?value?Context?context）
????????????????throws?IOException?InterruptedException?{

????????????FileSplit?split?=?（FileSplit）?context.getInputSplit（）;
????????????filename?=?split.getPath（）.getName（）;
????????????String?newString?=?value.toString（）.toLowerCase（）;
????????????String?results[]?=?newString.split（“[^a-zA-Z]“）;
????????????int?flag?=?0;
????????????for?（String?val?:?results）?{
????????????????if?（val.equals（““））
????????????????????continue;
????????????????context.write（new?Text（filename）?new?Text（val））;
????????????}
????????}
????}

????public?static?class?Reducer0?extends?Reducer?{
????????public?void?reduce（Text?key?Iterable?values?Context?context）
????????????????throws?IOException?InterruptedException?{
????????????ArrayList?array?=?new?ArrayList（）;
????????????for?（Text?t?:?values）?{
????????????????array.add（t.toString（））;
????????????}
????????????for?（String?str?:?array）?{
????????????????context.write（new?Text（key.toString（）?+?“?“+str）?new?Text（““
????????????????????????+?array.size（）））;
????????????????//?
????????????}
????????}
????}

????public?static?class?Mapper1?extends?Mapper?{

????????public?void?map（LongWritable?key?Text?value?Context?context）
????????????????throws?IOException?InterruptedException?{
????????????String?line?=?value.toString（）;
????????????int?index?=?line.indexOf（“	“）;
????????????context.write（new?Text（line.substring（0?index））
????????????????????new?Text（line.substring（index?+?1）））;
????????}
????}

????public?static?class?Reducer1?extends?Reducer?{

????????public?void?reduce（Text?key?Iterable?values?Context?context）
????????????????throws?IOException?InterruptedException?{
????????????ArrayList?array?=?new?ArrayList（）;
????????????int?ciNum?=?1;
????????????for?（Text?val?:?values）?{
????????????????array.add（val.toString（））;
????????????????ciNum?=