Merge pull request #7 from Seen-Arabic:@Feature/Remove-Arabic-Affixes

Remove Arabic Affixes Fixes #3
Seen-Arabic · Nov 30, 2023 · 4e7d8d1 · 4e7d8d1
2 parents 7fde65c + 959685c
commit 4e7d8d1
Show file tree

Hide file tree

Showing 3 changed files with 173 additions and 0 deletions.
diff --git a/src/main/java/io/github/seen_arabic/arabic_services/ArabicServices.java b/src/main/java/io/github/seen_arabic/arabic_services/ArabicServices.java
@@ -88,6 +88,17 @@ public static String tashfeer(String text) {
         return newSentence.toString().trim();
     }
 
+    /**
+     * Word to letters.
+     *
+     * For example
+     * text: "هذه جملة"
+     * to
+     * resulting string: "هاء ذال هاء جيم ميم لام تاء_مربوطة"
+     *
+     * @param word The input string {@link String}
+     * @return The resulting string {@link String}
+     */
     public static String wordToLetters(String word) {
         StringBuilder newWord = new StringBuilder();
 
@@ -113,6 +124,37 @@ public static String wordToLetters(String word) {
         return newWord.toString().trim();
     }
 
+    /**
+     * RemoveArabicAffixes
+     * 
+     * Removes predefined affixes (prefixes and suffixes) from an Arabic word if it
+     * starts or ends with those affixes.
+     * This function is designed specifically for processing Arabic text, where
+     * certain affixes might need to be removed
+     * for linguistic, stylistic, or morphological reasons.
+     *
+     * @param word - The Arabic word from which the affixes are to be
+     *             removed. {@link String}
+     * @return The word after removing any matching affixes. Returns the
+     *         original word if no affix matches are found. {@link String}
+     */
+    public static String removeArabicAffixes(String word) {
+        if (Data.ARABIC_PREFIXES.contains(word.substring(0, 2))) {
+            // For: ALEF & LAM
+            word = word.substring(2);
+        } else if (Data.ARABIC_PREFIXES.contains(word.substring(0, 1))) {
+            word = word.substring(1);
+        }
+
+        if (Data.ARABIC_SUFFIXES.contains(word.substring(word.length() - 2))) {
+            word = word.substring(0, word.length() - 2);
+        } else if (Data.ARABIC_SUFFIXES.contains(word.substring(word.length() - 1))) {
+            word = word.substring(0, word.length() - 1);
+        }
+
+        return word.trim();
+    }
+
     private static String handleNoonIssue(String text) {
         String arabicLetters = String.join("", Data.LETTERS_DICT.keySet()) + "ـ";
         String regex = Data.NOON + "(" + "?=[^" + arabicLetters + "]" + ")|" + Data.NOON + "\\z";

diff --git a/src/main/java/io/github/seen_arabic/arabic_services/Data.java b/src/main/java/io/github/seen_arabic/arabic_services/Data.java
@@ -11,6 +11,20 @@ class Data {
     static final List<Character> YAA = Arrays.asList('ى', 'ئ');
     static final List<Character> WAW = Arrays.asList('ؤ');
 
+    /**
+     * List of common Arabic prefixes. These prefixes are used in the
+     * removeArabicPrefix method
+     * to identify and remove them from the beginning of Arabic words.
+     */
+    public static final List<String> ARABIC_PREFIXES = Arrays.asList("أ", "ا", "إ", "ال", "ي", "ت", "ن", "ب");
+
+    /**
+     * List of common Arabic suffixes. These suffixes might be used in other
+     * functions
+     * to identify and manipulate them at the end of Arabic words.
+     */
+    public static final List<String> ARABIC_SUFFIXES = Arrays.asList("ة", "ه", "ي", "ى", "ية", "ين", "ون", "هم");
+
     static final String TEXT_NULL_MESSAGE = "text must be not null";
 
     static final Map<String, String> LETTERS_DICT;

diff --git a/src/test/java/io/github/seen_arabic/arabic_services/ArabicServicesTest.java b/src/test/java/io/github/seen_arabic/arabic_services/ArabicServicesTest.java
@@ -124,4 +124,121 @@ private void itShouldHandleInputWithSpaces() {
         String result = ArabicServices.wordToLetters(input);
         assertEquals("هاء ذال هاء  جيم ميم لام تاء_مربوطة  ألف خاء راء ألف_لينة", result);
     }
+
+    @Test
+    public void testRemoveArabicAffixes() {
+        itShouldRemoveAlfPrefixFromAWord();
+        itShouldRemoveAlefPrefixAndTaaSuffixFromAWord();
+        itShouldRemoveAlefHamzaBelowPrefixFromAWord();
+        itShouldRemoveAlPrefixFromAWord();
+        itShouldRemoveYaPrefixFromAWord();
+        itShouldRemoveTaPrefixFromAWord();
+        itShouldRemoveNunPrefixFromAWord();
+        itShouldRemoveBaPrefixFromAWord();
+        itShouldRemoveTaSuffixFromAWord();
+        itShouldRemoveHaSuffixFromAWord();
+        itShouldRemoveYaSuffixFromAWord();
+        itShouldRemoveAlefMaksuraSuffixFromAWord();
+        itShouldRemoveYaAlefSuffixFromAWord();
+        itShouldRemoveYaNunSuffixFromAWord();
+        itShouldRemoveWawNunSuffixFromAWord();
+        itShouldRemoveHumSuffixFromAWord();
+    }
+
+    private void itShouldRemoveAlfPrefixFromAWord() {
+        String word = "أمل";
+        String result = ArabicServices.removeArabicAffixes(word);
+        assertEquals("مل", result);
+    }
+
+    private void itShouldRemoveAlefPrefixAndTaaSuffixFromAWord() {
+        String word = "امرأة";
+        String result = ArabicServices.removeArabicAffixes(word);
+        assertEquals("مرأ", result);
+    }
+
+    private void itShouldRemoveAlefHamzaBelowPrefixFromAWord() {
+        String word = "إنسان";
+        String result = ArabicServices.removeArabicAffixes(word);
+        assertEquals("نسان", result);
+    }
+
+    private void itShouldRemoveAlPrefixFromAWord() {
+        String word = "الكتاب";
+        String result = ArabicServices.removeArabicAffixes(word);
+        assertEquals("كتاب", result);
+    }
+
+    private void itShouldRemoveYaPrefixFromAWord() {
+        String word = "يوم";
+        String result = ArabicServices.removeArabicAffixes(word);
+        assertEquals("وم", result);
+    }
+
+    private void itShouldRemoveTaPrefixFromAWord() {
+        String word = "تفاح";
+        String result = ArabicServices.removeArabicAffixes(word);
+        assertEquals("فاح", result);
+    }
+
+    private void itShouldRemoveNunPrefixFromAWord() {
+        String word = "نجم";
+        String result = ArabicServices.removeArabicAffixes(word);
+        assertEquals("جم", result);
+    }
+
+    private void itShouldRemoveBaPrefixFromAWord() {
+        String word = "بيت";
+        String result = ArabicServices.removeArabicAffixes(word);
+        assertEquals("يت", result);
+    }
+
+    private void itShouldRemoveTaSuffixFromAWord() {
+        String word = "كتابة";
+        String result = ArabicServices.removeArabicAffixes(word);
+        assertEquals("كتاب", result);
+    }
+
+    private void itShouldRemoveHaSuffixFromAWord() {
+        String word = "جديه";
+        String result = ArabicServices.removeArabicAffixes(word);
+        assertEquals("جدي", result);
+    }
+
+    private void itShouldRemoveYaSuffixFromAWord() {
+        String word = "ذهبي";
+        String result = ArabicServices.removeArabicAffixes(word);
+        assertEquals("ذهب", result);
+    }
+
+    private void itShouldRemoveAlefMaksuraSuffixFromAWord() {
+        String word = "منزلي";
+        String result = ArabicServices.removeArabicAffixes(word);
+        assertEquals("منزل", result);
+    }
+
+    private void itShouldRemoveYaAlefSuffixFromAWord() {
+        String word = "علمية";
+        String result = ArabicServices.removeArabicAffixes(word);
+        assertEquals("علم", result);
+    }
+
+    private void itShouldRemoveYaNunSuffixFromAWord() {
+        String word = "موظفين";
+        String result = ArabicServices.removeArabicAffixes(word);
+        assertEquals("موظف", result);
+    }
+
+    private void itShouldRemoveWawNunSuffixFromAWord() {
+        String word = "موظفون";
+        String result = ArabicServices.removeArabicAffixes(word);
+        assertEquals("موظف", result);
+    }
+
+    private void itShouldRemoveHumSuffixFromAWord() {
+        String word = "طلابهم";
+        String result = ArabicServices.removeArabicAffixes(word);
+        assertEquals("طلاب", result);
+    }
+
 }