Return to Question

1. It only accepts English words
2. It will spell check the same word if it's used more than once
3. It prints out each suggestion in a new line, so large websites produce a messy output.

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

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.safety.Whitelist;

public class ParseCleanCheck {

    static Hashtable<String, String> dictionary;// To store all the words of the
    // dictionary
    static boolean suggestWord;// To indicate whether the word is spelled
                                // correctly or not.

    static Scanner urlInput = new Scanner(System.in);
    public static String cleanString = "";
    public static String url = "";
    public static boolean correct = true;

    /**
     * PARSER METHOD
     */
    public static void PageScanner() throws IOException {
        System.out.println("Pick an english website to scan.");

        // This do-while loop allows the user to try again after a mistake
        do {
            try {
                System.out.println("Enter a URL, starting with http://");
                url = urlInput.nextLine();
                // This creates a document out of the HTML on the web page
                Document doc = Jsoup.connect(url).get();
                // This converts the document into a string to be cleaned
                String htmlToClean = doc.toString();
                cleanString = Jsoup.clean(htmlToClean, Whitelist.none());
                correct = false;
            } catch (Exception e) {
                System.out.println("Incorrect format for a URL. Please try again.");
            }
        } while (correct);
    }

    /**
     * SPELL CHECKER METHOD
     */
    public static void SpellChecker() throws IOException {
        dictionary = new Hashtable<String, String>();
        System.out.println("Searching for spelling errors ... ");

        try {
            // Read and store the words of the dictionary
            BufferedReader dictReader = new BufferedReader(new FileReader("dictionary.txt"));

            while (dictReader.ready()) {
                String dictInput = dictReader.readLine();
                String[] dict = dictInput.split("\\s"); // create an array of
                                                        // dictionary words

                for (int i = 0; i < dict.length; i++) {
                    // key and value are identical
                    dictionary.put(dict[i], dict[i]);
                }
            }
            dictReader.close();
            String user_text = "";

            // Initializing a spelling suggestion object based on probability
            SuggestSpelling suggest = new SuggestSpelling("wordprobabilityDatabase.txt");

            // get user input for correction
             {
                
                user_text = cleanString;
                String[] words = user_text.split(" ");

                int error = 0;

                for (String word : words) {
                    suggestWord = true;
                    String outputWord = checkWord(word);

                    if (suggestWord) {
                        System.out.println("Suggestions for " + word + " are:  " + suggest.correct(outputWord) + "\n");
                        error++;
                    }
                }

                if (error == 0) {
                    System.out.println("No mistakes found");
                }
            }

        } catch (IOException e) {
            e.printStackTrace();
             System.exit(-1);
        }
    }

    /**
     * METHOD TO SPELL CHECK THE WORDS IN A STRING. IS USED IN SPELL CHECKER
     * METHOD THROUGH THE "WORD" STRING
     */

    public static String checkWord(String wordToCheck) {
        String wordCheck, unpunctWord;
        String word = wordToCheck.toLowerCase();

        // if word is found in dictionary then it is spelled correctly, so
        // return as it is.

        if ((wordCheck = (String) dictionary.get(word)) != null) {
            suggestWord = false; // no need to ask for suggestion for a correct
                                    // word.
            return wordCheck;
        }

        // Removing punctuation at end of word and giving it a shot ("." or "."
        // or "?!")
        int length = word.length();

        // Checking for the beginning of quotes(example: "she )
        if (length > 1 && word.substring(0, 1).equals("\"")) {
            unpunctWord = word.substring(1, length);

            if ((wordCheck = (String) dictionary.get(unpunctWord)) != null) {
                suggestWord = false; // no need to ask for suggestion for a
                                        // correct word.
                return wordCheck;
            } else // not found
                return unpunctWord; // removing the punctuations and returning
        }

        // Checking if "." or ",",etc.. at the end is the problem(example: book.
        // when book is present in the dictionary).
        if (word.substring(length - 1).equals(".") 
                || word.substring(length - 1).equals(",")
                || word.substring(length - 1).equals("!") 
                || word.substring(length - 1).equals(";")
                || word.substring(length - 1).equals(":")) {
            unpunctWord = word.substring(0, length - 1);

            if ((wordCheck = (String) dictionary.get(unpunctWord)) != null) {
                suggestWord = false; // no need to ask for suggestion for a
                                        // correct word.
                return wordCheck;
            } else {
                return unpunctWord; // removing the punctuation and returning it
                                    // clean
            }
        }

        // Checking for (!,\,",etc) ... in the problem (example: watch!" when
        // watch is present in the dictionary)
        
            if (length > 2 
                    && (word.substring(length - 2).equals(",\"") 
                    || word.substring(length - 2).equals(".\"")
                    || word.substring(length - 2).equals("?\"") 
                    || word.substring(length - 2).equals("!\""))) {
                    unpunctWord = word.substring(0, length - 2);
                    
            if ((wordCheck = (String) dictionary.get(unpunctWord)) != null) {
                suggestWord = false; // no need to ask for suggestion for a
                                        // correct word.
                return wordCheck;
            } else // not found
                return unpunctWord; // removing the inflections and returning
        }

        // If after all of these checks a word could not be corrected, return as
        // a misspelled word.
        return word;
    }}

1. It only accepts English words
2. It prints out each suggestion in a new line, so large websites produce a messy output.

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

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.safety.Whitelist;

public class ParseCleanCheck {

    static Hashtable<String, String> dictionary;// To store all the words of the
    // dictionary
    static boolean suggestWord;// To indicate whether the word is spelled
                                // correctly or not.

    static Scanner urlInput = new Scanner(System.in);
    public static String cleanString;
    public static String url = "";
    public static boolean correct = true;
    

    /**
     * PARSER METHOD
     */
    public static void PageScanner() throws IOException {
        System.out.println("Pick an english website to scan.");

        // This do-while loop allows the user to try again after a mistake
        do {
            try {
                System.out.println("Enter a URL, starting with http://");
                url = urlInput.nextLine();
                // This creates a document out of the HTML on the web page
                Document doc = Jsoup.connect(url).get();
                // This converts the document into a string to be cleaned
                String htmlToClean = doc.toString();
                cleanString = Jsoup.clean(htmlToClean, Whitelist.none());
            
                
                correct = false;
            } catch (Exception e) {
                System.out.println("Incorrect format for a URL. Please try again.");
            }
        } while (correct);
    }

    /**
     * SPELL CHECKER METHOD
     */
    public static void SpellChecker() throws IOException {
        dictionary = new Hashtable<String, String>();
        System.out.println("Searching for spelling errors ... ");

        try {
            // Read and store the words of the dictionary
            BufferedReader dictReader = new BufferedReader(new FileReader("dictionary.txt"));

            while (dictReader.ready()) {
                String dictInput = dictReader.readLine();
                String[] dict = dictInput.split("\\s"); // create an array of
                                                        // dictionary words

                for (int i = 0; i < dict.length; i++) {
                    // key and value are identical
                    dictionary.put(dict[i], dict[i]);
                }
            }
            dictReader.close();
            String user_text = "";

            // Initializing a spelling suggestion object based on probability
            SuggestSpelling suggest = new SuggestSpelling("wordprobabilityDatabase.txt");

            // get user input for correction
            {

                user_text = cleanString;
                String[] words = user_text.split(" ");
                 Set<String> wordSet = new HashSet<>();
                 
                int error = 0;

                for (String word : words) {
                    if(!wordSet.contains(word)) {
                        checkWord(word);

                        suggestWord = true;
                        String outputWord = checkWord(word);

                        if (suggestWord) {
                            System.out.println("Suggestions for " + word + " are:  " + suggest.correct(outputWord) + "\n");
                            error++;
                        }
                    }
                        
                        wordSet.add(word);
                    }

                if (error == 0) {
                    System.out.println("No mistakes found");
                }
            }

        } catch (IOException e) {
            e.printStackTrace();
            System.exit(-1);
        }
    }

    /**
     * METHOD TO SPELL CHECK THE WORDS IN A STRING. IS USED IN SPELL CHECKER
     * METHOD THROUGH THE "WORD" STRING
     */

    public static String checkWord(String wordToCheck) {
        String wordCheck, unpunctWord;
        String word = wordToCheck.toLowerCase();

        // if word is found in dictionary then it is spelled correctly, so
        // return as it is.

        if ((wordCheck = (String) dictionary.get(word)) != null) {
            suggestWord = false; // no need to ask for suggestion for a correct
                                    // word.
            return wordCheck;
        }

        // Removing punctuation at end of word and giving it a shot ("." or "."
        // or "?!")
        int length = word.length();

        // Checking for the beginning of quotes(example: "she )
        if (length > 1 && word.substring(0, 1).equals("\"")) {
            unpunctWord = word.substring(1, length);

            if ((wordCheck = (String) dictionary.get(unpunctWord)) != null) {
                suggestWord = false; // no need to ask for suggestion for a
                                        // correct word.
                return wordCheck;
            } else // not found
                return unpunctWord; // removing the punctuations and returning
        }

        // Checking if "." or ",",etc.. at the end is the problem(example: book.
        // when book is present in the dictionary).
        if (word.substring(length - 1).equals(".") 
                || word.substring(length - 1).equals(",")
                || word.substring(length - 1).equals("!") 
                || word.substring(length - 1).equals(";")
                || word.substring(length - 1).equals(":")) {
            unpunctWord = word.substring(0, length - 1);

            if ((wordCheck = (String) dictionary.get(unpunctWord)) != null) {
                suggestWord = false; // no need to ask for suggestion for a
                                        // correct word.
                return wordCheck;
            } else {
                return unpunctWord; // removing the punctuation and returning it
                                    // clean
            }
        }

        // Checking for (!,\,",etc) ... in the problem (example: watch!" when
        // watch is present in the dictionary)

        if (length > 2 && (word.substring(length - 2).equals(",\"") 
                || word.substring(length - 2).equals(".\"")
                || word.substring(length - 2).equals("?\"") 
                || word.substring(length - 2).equals("!\""))) {
            unpunctWord = word.substring(0, length - 2);

            if ((wordCheck = (String) dictionary.get(unpunctWord)) != null) {
                suggestWord = false; // no need to ask for suggestion for a
                                        // correct word.
                return wordCheck;
            } else // not found
                return unpunctWord; // removing the inflections and returning
        }

        // If after all of these checks a word could not be corrected, return as
        // a misspelled word.
        return word;
    } 
}

I've created a program that spell checks a website. Here is the idea that I have in mind:

• Using a parser (jsoup), scan the text off of a website into a string
• Try to spell check the string and offer suggestions
• Use a spell checking algorithm that reads from a dictionary.txt file and uses probability theory.

I've implemented a program that spell checks a website. Here is the idea that I have in mind:

• Scan all of the words in a web page into a string (using jsoup)
• Filter out all of the HTML markup and code
• Use a spell checking algorithm that reads from a dictionary.txt file and uses probability theory to offer suggestions

• Using a parser (jsoup), scan the text off of a website
• Try to spell check the text and offer suggestions
• Use a spell checking algorithm that reads from a dictionary.txt file and uses probability theory.

1. It only accepts English words
2. It will spell check the same word over and over if it's used more than once
3. It prints out each suggestion in a new line, so large websites produce a messy output.

• Using a parser (jsoup), scan the text off of a website into a string
• Try to spell check the string and offer suggestions
• Use a spell checking algorithm that reads from a dictionary.txt file and uses probability theory.

1. It only accepts English words
2. It will spell check the same word if it's used more than once
3. It prints out each suggestion in a new line, so large websites produce a messy output.