package com.itcast;import java.io.IOException;
import java.util.Date;import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;/*** FileName:    WordMapper* Author:      Yuan-Programmer* Date:        2021/11/8 23:29* Description:*/
// 创建一个 WordMapper类 继承于 Mapper抽象类
public class WordMapper extends Mapper<Object, Text, Text, IntWritable> {private final static IntWritable one = new IntWritable(1);private Text word = new Text();// Mapper抽象类的核心方法，三个参数public void map(Object key, // 首字符偏移量Text value, // 文件的一行内容Context context) // Mapper端的上下文，与 OutputCollector 和 Reporter 的功能类似throws IOException, InterruptedException {String[] ars = value.toString().split("['.;,?| \t\n\r\f]");for (String tmp : ars) {if (tmp == null || tmp.length() <= 0) {continue;}word.set(tmp);System.out.println(new Date().toGMTString() + ":" + word + "出现一次，计数+1");context.write(word, one);}}
}

package com.itcast;import java.io.IOException;
import java.util.*;import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;/*** FileName:    WordReduce* Author:      Yuan-Programmer* Date:        2021/11/8 23:32* Description:*/
// 创建一个 WordReducer类 继承于 Reducer抽象类
public class WordReducer extends Reducer<Text, IntWritable, Text, IntWritable> {private IntWritable result = new IntWritable(); // 用于记录 key 的最终的词频数HashMap<String, Integer> map = new HashMap();// Reducer抽象类的核心方法，三个参数public void reduce(Text key, // Map端 输出的 key 值Iterable<IntWritable> values, // Map端 输出的 Value 集合（相同key的集合）Context context) // Reduce 端的上下文，与 OutputCollector 和 Reporter 的功能类似throws IOException, InterruptedException {int sum = 0;for (IntWritable val : values) // 遍历 values集合，并把值相加{sum += val.get();}map.put(key.toString(), sum);System.out.println(new Date().toGMTString() + ":" + key + "出现了" + result);}@Overrideprotected void cleanup(Context context) throws IOException, InterruptedException {//  根据map中的value进行排序Map<String, Integer> sortedMap = MapUtils.sortValue(map);Set<Map.Entry<String, Integer>> entries = sortedMap.entrySet();Iterator<Map.Entry<String, Integer>> it = entries.iterator();/*** 不设置count，对全部单词进行排序* 循环获取迭代器的Map对象，再获取对应K,V* 将K,V封装到上下文中*/while (it.hasNext()) {//  获取MapMap.Entry<String, Integer> entry = it.next();String key = entry.getKey();Integer value = entry.getValue();//  封装k3,v3Text k3 = new Text();k3.set(key);IntWritable v3 = new IntWritable();v3.set(value);//  写入上下文context.write(k3, v3);}}
}

package com.itcast;/*** FileName:    MapUtils* Author:      Yuan-Programmer* Date:        2021/11/9 0:05* Description:*/import java.util.*;/**•    Map工具类*/
public class MapUtils {/**– 根据Map的value值降序排序–   @param map–    @param–    @param–    @return*/public static <K, V extends Comparable<? super V>> Map<K, V> sortValue(Map<K, V> map) {List<Map.Entry<K, V>> list = new ArrayList(map.entrySet());Collections.sort(list, new Comparator<Map.Entry<K, V>>() {@Overridepublic int compare(Map.Entry<K, V> o1, Map.Entry<K, V> o2) {/*** o1-o2：升序* o2-o1：降序* 返回结果加上“-”表示取反操作（升序->降序，降序->升序）*/int compare = (o1.getValue()).compareTo(o2.getValue());return -compare;}});//将排序结果返回上一级Map<K, V> returnMap = new LinkedHashMap<K, V>();for (Map.Entry<K, V> entry : list) {returnMap.put(entry.getKey(), entry.getValue());}return returnMap;}
}