文本统计器(Java)

1. 创建一个类,实现统计文本文件中各类字符和字符串的个数的功能,要求实现:

a) 按字符统计,输出各个字符的数量

b) 按单词统计,输出各个单词的数量

2. 在b)的基础上实现一个类keywordIdentifier,读入一个Java程序源文件,输出各个关键字的个数(注释中出现的关键字不计入关键字个数)

思考:统计1:如果文本文件只包含26个英文字母并且用空格分离,那么只需要使用数组就可以对字符计数,用空格分离得到字符串可以对字符串计数(是否区分大小写问题)。如果文本文件是英文,但是包含各种标点及其他符号,则使用集合key-value的形式来对字符计数,按字符依次读取,然后将26个字母以外的所有字符作为空格处理,再使用空格将其分离,最后对字符串统计计数。

关键字统计:需要所有关键字集合,对每行判断是否为注释,再对非注释进行空格分离,对关键字计数(采用key-value形式)

1.统计字符和单词 StringCounter.java

import java.util.Map;
import java.util.TreeMap;

public class StringCounter {
    
    private Map<String, Integer> charCount = new TreeMap<String, Integer>();
    
    private Map<String, Integer> wordCount = new TreeMap<String, Integer>();
    
    public void charCounter(String s) {
        Integer freq;
        for(int i = 0; i < s.length(); i++) {
            freq = charCount.get(s.substring(i, i+1));
            if(freq == null) {
                freq = new Integer(1);
            }
            else {
                freq = new Integer(freq.intValue() + 1);
            }
            charCount.put(s.substring(i, i+1), freq);
        }
    }
    
    public void wordCounter(String s) {
        //将除过a-zA-Z0-9的其他符号转为空格,再将多个空格转为一个空格
        String s1 = s.replaceAll("\W", " ");
        String s2 = s1.replaceAll(" +", " ");
        String[] s3 = s2.split(" ");
        Integer freq;
        for(String str : s3) {
            freq = wordCount.get(str);
            if(freq == null) {
                freq = new Integer(1);
            }
            else {
                freq = new Integer(freq.intValue() + 1);
            }
            wordCount.put(str, freq);
        }
    }
    
    public void output() {
        System.out.println(charCount);
        System.out.println(wordCount);
    }
}

2.测试 使用的文本文件为随意的英文文本

import java.io.IOException;
import java.io.RandomAccessFile;

public class CountTest {

    public static void main(String[] args) throws IOException {
        StringCounter sc = new StringCounter();
        
        long filePoint = 0;
        String s;
        RandomAccessFile file = new RandomAccessFile("string.txt", "r");
        long fileLength = file.length();
        while(filePoint < fileLength) {
            s = file.readLine();
            //处理及计数
            sc.charCounter(s);
            sc.wordCounter(s);
            filePoint = file.getFilePointer();
        }
        file.close();
        
        sc.output();
    }

}

3.关键词统计

  先将所有关键字放入map中,以关键字为键,次数0为值,再读文本统计个数

import java.io.IOException;
import java.io.RandomAccessFile;
import java.util.Map;
import java.util.TreeMap;

public class keywordIdentifier {

    private Map<String, Integer> keyWordCount = new TreeMap<String, Integer>();
    
    public void keyWord() throws IOException {
        long filePoint = 0;
        String s;
        RandomAccessFile file = new RandomAccessFile("keyword.txt", "r");
        long fileLength = file.length();
        while(filePoint < fileLength) {
            s = file.readLine();
            
            String[] s1 = s.split(" ");
            Integer freq = new Integer(0);
            for(String word : s1) {
                keyWordCount.put(word, freq);
            }
            
            filePoint = file.getFilePointer();
        }
        file.close();
    }
    
    public void keyWordCounter(String s){
        int pos = s.indexOf("//");
        if(pos == -1) {
            pos = s.length();
        }
        String sub = s.substring(0, pos);
     String sub1 = sub.replaceAll("\W", " "); String str
= sub1.replaceAll(" +", " "); String[] s1 = str.split(" "); Integer freq; for(String word : s1) { freq = keyWordCount.get(word); if(freq != null) { freq = new Integer(freq.intValue() + 1); keyWordCount.put(word, freq); } } } public void output() { System.out.println(keyWordCount); } }

4.测试关键词统计

import java.io.*;

public class CountTest {

    public static void main(String[] args) throws IOException {
        keywordIdentifier sc = new keywordIdentifier();
        sc.keyWord();
        long filePoint = 0;
        String s;
        RandomAccessFile file = new RandomAccessFile("CountTest.java", "r");
        long fileLength = file.length();
        while(filePoint < fileLength) {
            s = file.readLine();
            sc.keyWordCounter(s);
            filePoint = file.getFilePointer();
        }
        file.close();
        
        sc.output();
    }

}

输出:

{abstract=0, assert=0, boolean=0, break=0, byte=0, case=0, catch=0, char=0, class="1", const=0, continue=0, default=0, do=0, double=0, else=0, enum=0, extends=0, final=0, finally=0, float=0, for=0, goto=0, if=0, implements=0, import=1, instanceof=0, int=0, interface=0, long=2, native=0, new=2, package=1, private=0, protected=0, public=2, return=0, short=0, static=1, strictfp=0, super=0, switch=0, synchronized=0, this=0, throw=0, throws=1, transient=0, try=0, void=1, volatile=0, while=1}

原文地址:https://www.cnblogs.com/datamining-bio/p/9532925.html