How to Write a Spelling Corrector用java 寫拼字檢查器 Java實現 以備查驗

標籤：

import java.io.*;
import java.util.*;
import java.util.regex.*;

class Spelling {

private final HashMap<String, Integer> nWords = new HashMap<String, Integer>();

public Spelling(String file) throws IOException {
BufferedReader in = new BufferedReader(new FileReader(file));
Pattern p = Pattern.compile("\\w+");
for(String temp = ""; temp != null; temp = in.readLine()){
Matcher m = p.matcher(temp.toLowerCase());
while(m.find())
nWords.put((temp = m.group()), nWords.containsKey(temp) ? nWords.get(temp) + 1 : 1);
}
in.close();
//System.out.println(nWords.size());
}

private final ArrayList<String> edits(String word) {
ArrayList<String> result = new ArrayList<String>();
for(int i=0; i < word.length(); ++i) result.add(word.substring(0, i) + word.substring(i+1));
for(int i=0; i < word.length()-1; ++i) result.add(word.substring(0, i) + word.substring(i+1, i+2) + word.substring(i, i+1) + word.substring(i+2));
for(int i=0; i < word.length(); ++i) for(char c=‘a‘; c <= ‘z‘; ++c) result.add(word.substring(0, i) + String.valueOf(c) + word.substring(i+1));
for(int i=0; i <= word.length(); ++i) for(char c=‘a‘; c <= ‘z‘; ++c) result.add(word.substring(0, i) + String.valueOf(c) + word.substring(i));
return result;
}

public final String correct(String word) {
//如果詞袋子裡面含有這個詞直接返回
if(nWords.containsKey(word)) return word;
//沒有這個詞的話，那就認為這個詞拼字錯誤 找到所有的可能的基於這個詞的可能詞彙
ArrayList<String> list = edits(word);
HashMap<Integer, String> candidates = new HashMap<Integer, String>();
//在猜想的詞彙表中如果與字典中的詞重合，那就放進候選列表裡面
for(String s : list) if(nWords.containsKey(s)) candidates.put(nWords.get(s),s);
//如果在候選列表裡面有候選
if(candidates.size() > 0) return candidates.get(Collections.max(candidates.keySet()));
//沒有候選的時候怎麼辦？
for(String s : list)
for(String w : edits(s))
//進行第二次匹配，拿出猜想的可能詞彙，再進行一次猜想， 再不行的話，直接返回原來的word
if(nWords.containsKey(w))
candidates.put(nWords.get(w),w);
return candidates.size() > 0 ? candidates.get(Collections.max(candidates.keySet())) : word;
}

public static void main(String args[]) throws IOException {
if(args.length > 0) System.out.println((new Spelling("big.txt")).correct(args[0]));
}

}

 

 

http://raelcunha.com/spell-correct.php

How to Write a Spelling Corrector用java 寫拼字檢查器 Java實現 以備查驗