Commit 8ace970f authored by Manuel Segimon's avatar Manuel Segimon
Browse files

Merge branch '32-add-spelling-corrections' into 'master' 

Resolve "Add spelling corrections"

Closes #32

See merge request ec504/ec504_projects/group7!17
parents 3328321e 9640d115

src/main/java/edu/bu/LanguageCorrection/Corrector.java

+10 −0
Original line number Diff line number Diff line
@@ -63,6 +63,16 @@ public class Corrector { 
        // Divide sentence into words

        String[] words = inputSentence.split(" ");



        // Check if all words are in the trie

        for (int i = 0; i < words.length; i++) {

            if (!detector.containsWord(words[i])) {

                String closestWord = detector.findClosestWord(words[i]);

                if (closestWord != null) {

                    words[i] = closestWord;

                }

            }

        }



        List<String> sentences = generateSentences(words);



        // Use a priority queue to store sentences along with their scores

src/main/java/edu/bu/LanguageCorrection/TrieNode.java

+36 −0
Original line number Diff line number Diff line
@@ -24,6 +24,42 @@ public class TrieNode implements Serializable, Cloneable { 
        past.childCounts += 1;

    }



    public boolean containsWord(String word) {

        return this.children.containsKey(word);

    }



    public String findClosestWord(String inputWord) {

        int minDistance = Integer.MAX_VALUE;

        String closestWord = null;



        for (String word : this.children.keySet()) {

            int distance = levenshteinDistance(inputWord, word);

            if (distance < minDistance) {

                minDistance = distance;

                closestWord = word;

            }

        }

        return closestWord;

    }



    private int levenshteinDistance(String s1, String s2) {

        int[][] dp = new int[s1.length() + 1][s2.length() + 1];



        for (int i = 0; i <= s1.length(); i++) {

            for (int j = 0; j <= s2.length(); j++) {

                if (i == 0) {

                    dp[i][j] = j;

                } else if (j == 0) {

                    dp[i][j] = i;

                } else {

                    dp[i][j] = Math.min(Math.min(dp[i - 1][j] + 1, dp[i][j - 1] + 1),

                            dp[i - 1][j - 1] + (s1.charAt(i - 1) == s2.charAt(j - 1) ? 0 : 1));

                }

            }

        }

        return dp[s1.length()][s2.length()];

    }



    public float probability(String phrase) {

        String[] words = phrase.split(" ");

        if (words.length <= 1) { // If word does not exist in trie