统计英文文本单词出现频率

要求：写一个程序，分析一个文本文件中各个词出现的频率，并且把频率最高的10个词打印出来。文本文件大约是30KB~300KB大小。

1.算法思想

       从english.txt按行读取英文文本，将每个string都封装成Word放入一个WordList中，使用HashMap来将String作为key,rate作为value，在update方法中，就可以直接使用map的get方法判断是否存在唯一的key（string）;计算出不同单词的出现频率rate后，对其进行排序打印出频率最高的10个单词（排序使用Collections工具类的sort()方法）。

注：单词String和频率rate封装在Word类中，以key(String)是否相同来衡量Word对象是否相同

2.程序

package Searchword;


import java.io.BufferedReader;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStreamReader;
import java.util.ArrayList;
import java.util.Collections;
import java.util.Comparator;
import java.util.HashMap;
import java.util.Map;
import java.util.regex.Matcher;
import java.util.regex.Pattern;


public class CountOfWordsTest {


	public static void main(String[] args) {


		test1();
	}


	public static void test1() {
		ArrayList<String> list = readFromFile1();
		ArrayList<Word<String, Integer>> WordList = countOfWords1(list);
		printList1(WordList);
	}


	/*
	 * @Description print the list
	 */
	private static void printList1(ArrayList<Word<String, Integer>> wordList) {


		for (int i = 0; i < 10; i++) {
			Word<String, Integer> word = wordList.get(i);
			String key = word.getKey();
			Integer value = word.getValue();
			System.out.println(key + ".." + value);
		}
	}


	public static ArrayList<Word<String, Integer>> countOfWords1(
			ArrayList<String> list) {
		ArrayList<Word<String, Integer>> WordList = new ArrayList<Word<String, Integer>>();


		for (int i = 0; i < list.size(); i++) {
			String temp = list.get(i);
			update1(WordList, temp);
		}


		Collections.sort(WordList, new Comparator<Word<String, Integer>>() {
			@Override
			public int compare(Word<String, Integer> o1,
					Word<String, Integer> o2) {
				Integer temp1 = o1.getValue();
				Integer temp2 = o2.getValue();
				return temp2.compareTo(temp1);
			}
		});


		return WordList;
	}


	public static void update1(ArrayList<Word<String, Integer>> WordList,
			String s) {


		Word<String, Integer> tempWord = new Word<String, Integer>(s, 1);
		int idx = WordList.indexOf(tempWord);


		if (idx == -1) {
			WordList.add(tempWord);
		} else {
			Word<String, Integer> word = WordList.get(idx);
			word.setValue(word.getValue() + 1);
		}
	}


	@SuppressWarnings("resource")
	public static ArrayList<String> readFromFile1() {
		ArrayList<String> list = new ArrayList<String>();
		BufferedReader br = null;
		StringBuilder sb = null;


		try {
			br = new BufferedReader(new InputStreamReader(new FileInputStream(
					"./src/dictionary.txt")));
			sb = new StringBuilder();


			String line;
			while ((line = br.readLine()) != null) {
				sb.append(line + " ");
			}
		} catch (IOException e) {
			e.printStackTrace();
		}
		String regEx = "[a-zA-Z]+";
		Pattern p = Pattern.compile(regEx);
		Matcher m = p.matcher(sb);
		while (m.find()) {
			String temp = m.group();
			list.add(temp);
		}
		return list;
	}


	/*
	 * @Description the inner class contains String and count
	 */
	private static class Word<KeyType, ValueType extends Comparable<? super ValueType>> {


		private KeyType key;
		private ValueType value;


		public Word(KeyType key, ValueType value) {
			this.key = key;
			this.value = value;
		}


		public KeyType getKey() {
			return key;
		}


		public void setKey(KeyType key) {
			this.key = key;
		}


		public ValueType getValue() {
			return value;
		}


		public void setValue(ValueType value) {
			this.value = value;
		}


		public boolean equals(Object obj) {
			if (this == obj) {
				return true;
			}


			if (obj != null && obj.getClass() == Word.class) {
				Word<KeyType, ValueType> tempWord = (Word<KeyType, ValueType>) obj;
				
				if (this.getKey().equals(tempWord.getKey())) {
					return true;
				}
			}
			return false;
		}
	}


}

4.运行结果

3.程序性能分析

由上图可见，计算300KB的文本用了280毫秒