相似词查找器

Question

相似词查找器

我创造了一个类似的词查找器的乐趣。(word.txt是来自http://www.mieliestronk.com/corncob_lowercase.txt的单词)有什么方法可以让这个词更好或者更准确？

import java.util.*;
import java.io.*;
class Main {

    public static void print(String text, int times) {
        for (int i = 0; i < times; i++) {
            System.out.print(text);
        }

    }
    public static void println(String text, int times) {
        for (int i = 0; i < times; i++) {
            System.out.println(text);
        }

    }
    public static void main(String[] args) {
        ArrayList<String> arrayList = new ArrayList();
        try {
            BufferedReader reader = new BufferedReader(new FileReader("word.txt"));
            

            String line = null;
            while ((line = reader.readLine()) != null) {
                arrayList.add(line);
            }
            println("Welcome to similar word finder. This program searches ​58100 different words for words that are similar to the word that you entered",1);
            print("Enter a word: ", 1);

            Scanner scanner = new Scanner(System.in);
            String checkWord = scanner.nextLine();
                        for (int i = 0; i < checkWord.length(); i++) {
                                // checks whether the character is not a letter
                                // if it is not a letter ,it will return false
                                if ((Character.isLetter(checkWord.charAt(i)) == false)) {
                                    println("Your word contains a not-unicode letter!",1);
                                    System.exit(1);
                                }
                        }
                        ArrayList<String> similarwords = new ArrayList<>();
                        print("How strict do you want the search to be? (1) Very Strict (2) Normal strict (3) Not very strict: ",1);
                        String strict = scanner.nextLine();
            //println(arrayList.toString(),1);
            int minus = 0;
                        if (strict == "1") {
                            minus = 1;
                        } else {
                            if (strict=="2") {
                                minus = 2;
                            } else {
                                if (strict=="3") {
                                    minus = 3;
                                
                                } else {
                                    minus =2;
                                }
                            }
                        }
            int timesRight = 0;
            int timesRight2 = 0;
            if (checkWord.length() > 3) {
                  timesRight2 = checkWord.length()-minus;
                                        println("Similar Words:", 1);
            } else {
                            if (checkWord.length() > 2) {
                                timesRight2=checkWord.length();
                            }else {
                                timesRight=2;
                            }
                  
            }
            checkWord = checkWord.trim();                
            try {
                  String[] letters = checkWord.split("");
                                
                  for (String word3 : arrayList) {
                                    
                        timesRight=0;
                        String[] letters2 = word3.split("");
                        int under = 0;
                        if (letters.length<=letters2.length) {
                                under = letters.length;
                        } else {
                                under = letters2.length;
                        }
                        for(int i = 0; i < under;i++) {
                                    
                                    if (letters2[i].equals(letters[i])) {
                                timesRight++;
                                                
                          } else {
                              if(i<letters2.length-2 && i<letters.length-2){
                                  if (letters2[i+1].equals(letters[i])) {
                                        timesRight++;
                                                        
                                                    
                                  }
                              }
                                                
                            }
                        } 

                        if (timesRight>timesRight2) {
                                                    if 
                                                    if (word3 != checkWord) {
                                                            //System.out.println(checkWord);
                                                        similarwords.add(word3);
                              println(word3 +" #" + similarwords.size() , 1);
                                                    }else {
                                                        println(word3 + " (search word)",1);
                                                    }
                                            
                        } else {
                                                    //println("x",1);
                                                }
                  }
                                    
                                    
            } catch (Exception e) {
                    System.err.println("Error!: " + e);
                                
            }
                           
                        
                                                      
                            

                    
                
                

            
            
        } catch (Exception e) {
            e.printStackTrace();
       }
    }
}

Answer 1

如果你想要你的单词匹配更准确，查找Soundex匹配。

我致力于让你的代码更容易被普通人读懂。

我不知道你是怎么匹配单词的。我假设你是根据字母差异数来选择单词的。

通常，当您编写Java类时，它应该读起来像一篇文章。最重要的信息在开始时，随着代码的深入，您会看到越来越多的细节。我们称之为方法的一口大小的食物。

几乎所有的代码都在一个主要的方法中。您的代码对我来说很难理解，就像我说的，我放弃了试图理解您是如何比较单词的，而只是编写了我自己的代码。

下面是我写的查找类似单词的主要方法。

public void findSimilarWords() {
    List<String> wordList = readWordList();
    Scanner scanner = new Scanner(System.in);
    String checkword = readWord(scanner);
    int level = readStrictLevel(scanner);
    List<String> matchingWords = findMatchingWords(
            wordList, checkword, level);
    createOutput(checkword, matchingWords);
    scanner.close();
}

七行代码。现在，我们还不知道细节。我们知道有一个单词列表，我们从控制台得到一个单词和一个匹配级别，然后输出匹配的单词。在这一点上，这就是我们需要知道的。

我们将在进一步阅读类代码时获得详细信息。

我想我已经表达了自己的观点。这是修改后的代码。我希望您发现这段代码更容易理解，更重要的是，更容易修改。代码不仅仅是计算机的代码。人类也必须阅读和理解代码。包括时间过去之后的你。

import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.net.MalformedURLException;
import java.net.URL;
import java.util.ArrayList;
import java.util.List;
import java.util.Scanner;

public class SimilarWordFinder {
    
    public static void main(String[] args) {
        SimilarWordFinder swf = new SimilarWordFinder();
        swf.findSimilarWords();
    }

    public void findSimilarWords() {
        List<String> wordList = readWordList();
        Scanner scanner = new Scanner(System.in);
        String checkword = readWord(scanner);
        int level = readStrictLevel(scanner);
        List<String> matchingWords = findMatchingWords(
                wordList, checkword, level);
        createOutput(checkword, matchingWords);
        scanner.close();
    }
    
    private List<String> readWordList() {
        List<String> wordList = new ArrayList<>();
        try {
            URL url = new URL("http://www.mieliestronk.com/"
                    + "corncob_lowercase.txt");
            BufferedReader reader = new BufferedReader(
                    new InputStreamReader(url.openStream()));
            String line = reader.readLine();
            while (line != null) {
                wordList.add(line.trim());
                line = reader.readLine();
            }
            reader.close();
        } catch (MalformedURLException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        }
        return wordList;
    }
    
    private String readWord(Scanner scanner) {
        println("Welcome to similar word finder. This program "
                + "searches ​58,100 different words for words that "
                + "are similar to the word that you entered",
                1);
        boolean invalidWord = true;
        String checkWord  = "";
        
        while (invalidWord) {
            print("Enter a word: ", 1);
            checkWord = scanner.nextLine();
            invalidWord = false;
            for (int i = 0; i < checkWord.length(); i++) {
                // checks whether the character is not a letter
                // if it is not a letter ,it will return false
                if (!Character.isLetter(checkWord.charAt(i))) {
                    println("Your word contains a not-unicode letter!", 1);
                    invalidWord = true;
                    break;
                }
            }
        }
        
        return checkWord;
    }
    
    private int readStrictLevel(Scanner scanner) {
        print("How strict do you want the search to be? (1) Very "
                + "Strict (2) Normal strict (3) Not very strict: ",
                1);
        String strict = scanner.nextLine();
        return valueOf(strict);
    }
    
    private List<String> findMatchingWords(List<String> wordList,
            String word, int level) {
        List<String> similarWords = new ArrayList<>();
        
        for (String matchWord : wordList) {
            if (matchWord.length() == word.length()) {
                int difference = calculateWordDifference(word, matchWord);
                if (difference <= level) {
                    similarWords.add(matchWord);
                }
            }
        }
        
        return similarWords;
    }
    
    private int calculateWordDifference(String word, String matchWord) {
        int difference = 0;
        
        for (int i = 0; i < word.length(); i++) {
            if (word.charAt(i) != matchWord.charAt(i)) {
                difference++;
            }
        }
        
        return difference;
    }
    
    private void createOutput(String word, List<String> matchingWords) {
        println(" ", 1);
        println("The following words match \"" + word + "\"", 1);
        println(" ", 1);
        
        for (String matchingWord : matchingWords) {
            println("    " + matchingWord, 1);
        }
    }
    
    private void print(String text, int times) {
        for (int i = 0; i < times; i++) {
            System.out.print(text);
        }
    }

    private void println(String text, int times) {
        for (int i = 0; i < times; i++) {
            System.out.println(text);
        }
    }
    
    private int valueOf(String number) {
        try {
            return Integer.valueOf(number);
        } catch (NumberFormatException e) {
            return 2;
        }
    }
    
}