CS1103 Programming Assignment Unit 5 - Use HashSet and TreeSet to implement a spell checker

Questions

Use HashSet and TreeSet to implement a spell checker. Specifically, please read the file words.txt, which contains a list of English words, and store them in a set. Then, check the words in a file provided by the user, and provide a list of possible correct spellings.

1. Codes and Files

Codes

import javax.swing.*;
import java.io.File;
import java.util.*;

public class CheckingWords {
    public static void main(String[] args) {
        Scanner filein = null;
        Scanner inputFile = null;
        // Use a LinkedHashSet to store corrections, the same misspelled word is only saved once
        LinkedHashSet<String> outputs = new LinkedHashSet<>();

        try {
            // use a HashSet to store the words in the dictionary
            HashSet<String> hashSet = new HashSet<>();

            // read the words, change them to lowercase, and store them in the HashSet
            filein = new Scanner(new File("F:\\words.txt"));
            while (filein.hasNext()) {
                String lowercaseWord = filein.next().toLowerCase();
                hashSet.add(lowercaseWord);
            }

            // read the file from the user and skip over any non-letter characters
            inputFile = new Scanner(getInputFileNameFromUser()).useDelimiter("[^a-zA-Z]+");

            // process the file from the user
            while (inputFile.hasNext()) {
                String originalWord = inputFile.next();

                // convert the word to lowercase for comparison with lowercase words in the hashSet
                String lowerCaseWord = originalWord.toLowerCase();

                // process the bad word and and add the corrections to the outputs set
                if ((!hashSet.contains(lowerCaseWord))) {
                    var treeSet = corrections(lowerCaseWord, hashSet);
                    if (treeSet.isEmpty()) {
                        outputs.add(lowerCaseWord + ":" + " (no suggestions)");
                    } else {
                        outputs.add(lowerCaseWord + ": " + iterateSet(treeSet));
                    }
                }
            }

            // print the outputs, and the same misspelled word is output only once
            for (String s : outputs) {
                System.out.println(s);
            }
        } catch (Exception e) {
            System.out.println(e.getMessage());
        } finally {
            Objects.requireNonNull(filein).close();
            Objects.requireNonNull(inputFile).close();
        }
    }

    /**
     * Iterate the set in the required manner.
     * For example: txt: tat, tet, text, tit, tot, tut
     */
    static String iterateSet(TreeSet<String> treeSet) {
        int count = 0;
        StringBuilder stringBuilder = new StringBuilder();

        for (String s : treeSet) {
            stringBuilder.append(s);
            if (count < treeSet.size() - 1) {
                stringBuilder.append(", ");
            }
            count++;
        }

        return stringBuilder.toString();
    }


    /***
     * Lets the user select an input file using a standard file
     * selection dialog box. If the user cancels the dialog
     * without selecting a file, the return value is null.
     */
    static File getInputFileNameFromUser() {
        JFileChooser fileDialog = new JFileChooser();
        fileDialog.setDialogTitle("Select File for Input");
        int option = fileDialog.showOpenDialog(null);
        if (option != JFileChooser.APPROVE_OPTION)
            return null;
        else
            return fileDialog.getSelectedFile();
    }

    /**
     * Providing a list of possible correct spellings.
     * The possible corrections that the program considers are as follows:
     * • Delete any one of the letters from the misspelled word.
     * • Change any letter in the misspelled word to any other letter.
     * • Insert any letter at any point in the misspelled word.
     * • Swap any two neighboring characters in the misspelled word.
     * • Insert a space at any point in the misspelled word (and check that both of the words that are produced are in the dictionary)
     *
     * @param badWord
     * @param dictionary
     * @return
     */
    static TreeSet corrections(String badWord, HashSet dictionary) {
        TreeSet<String> treeSet = new TreeSet<String>();

        // Delete any one of the letters from the misspelled word
        for (int i = 0; i < badWord.length(); i++) {
            String newWord = badWord.substring(0, i) + badWord.substring(i + 1);
            if ((dictionary.contains(newWord))) {
                treeSet.add(newWord);
            }
        }

        // Change any letter in the misspelled word to any other letter
        for (int i = 0; i < badWord.length(); i++) {
            for (char ch = 'a'; ch <= 'z'; ch++) {
                String newWord = badWord.substring(0, i) + ch + badWord.substring(i + 1);
                if (dictionary.contains(newWord)) {
                    treeSet.add(newWord);
                }
            }
        }

        // Insert any letter at any point in the misspelled word
        for (int i = 0; i <= badWord.length(); i++) {
            for (char ch = 'a'; ch <= 'z'; ch++) {
                String newWord = badWord.substring(0, i) + ch + badWord.substring(i);
                if (dictionary.contains(newWord)) {
                    treeSet.add(newWord);
                }
            }
        }

        // Swap any two neighboring characters in the misspelled word
        for (int i = 0; i < badWord.length() - 1; i++) {
            String newWord = badWord.substring(0, i) + badWord.substring(i + 1, i + 2) + badWord.substring(i, i + 1) + badWord.substring(i + 2);
            if (dictionary.contains(newWord)) {
                treeSet.add(newWord);
            }

        }

        // Insert a space at any point in the misspelled word,
        // and check that both of the words that are produced are in the dictionary
        for (int i = 1; i < badWord.length(); i++) {
            String twoNewWords = badWord.substring(0, i) + " " + badWord.substring(i);
            StringTokenizer stringTokenizer = new StringTokenizer(twoNewWords, " ");
            while (stringTokenizer.hasMoreTokens()) {
                String newWord1 = stringTokenizer.nextToken();
                String newWord2 = stringTokenizer.nextToken();
                // check that both of the words that are produced are in the dictionary
                if (dictionary.contains(newWord1) && dictionary.contains(newWord2)) {
                    treeSet.add(twoNewWords);
                }
            }
        }

        return treeSet;
    }
}

Files
Please click here to download the dictionary: words.txt

Please click here to download the test file: testPage.txt

2. Outputs

s: a, as, cs, es, gs, is, ks, ls, ms, os, rs, sb, sc, se, sh, si, sm, sn, so, sq, sr, st, ts, us, vs
hashset: hash set
treeset: tree set
isempty: is empty
txt: tat, tet, text, tit, tot, tut
filein: file in
hasnext: has next
tk: bk, ok, ta, tb, tc, th, ti, tl, tm, to, ts, ty
wordlist: word list
ve: ave, be, eve, fe, ge, he, le, me, ne, re, se, va, vet, vex, vie, vs, we, xe, ye
getinputfilenamefromuser: (no suggestions)
jfilechooser: (no suggestions)
filedialog: file dialog
setdialogtitle: (no suggestions)
int: ant, dint, hint, in, ina, inc, ind, ink, inn, ins, inti, into, it, lint, mint, nit, pint, tint
showopendialog: (no suggestions)
getselectedfile: (no suggestions)
usedelimiter: use delimiter
za: a, ba, ca, fa, ga, ha, la, ma, na, pa, ra, ta, va, ya, zap, zn, zr
z: a, hz, oz, zn, zr
shouldn: should
t: a, at, it, lt, mt, pt, st, ta, tb, tc, th, ti, tl, tm, to, ts, ty
badword: bad word
html: (no suggestions)
cpsc: (no suggestions)
cvs: cs, vs
href: ref
pre: are, ere, ire, ore, pare, pee, per, pie, poe, pore, prep, pres, prey, pro, pry, pure, pyre, re
hav: av, ha, had, hag, hah, hal, ham, han, has, hat, have, haw, hay

Process finished with exit code 0

​

---

This is the ending, thanks for reading.

---