Merge pull request #23 from Seen-Arabic/22-trim-text-before-converting

resolve #22 Trim text before converting

Author: AbdelrahmanBayoumi

CHANGELOG.md

@@ -1,38 +1,55 @@
 <h1 align=center>📜 Changelog - سجل التغيير</h1>
 <p align=center>All notable changes to this project will be documented in this file.</p>
 
+## [Unreleased](https://github.com/Seen-Arabic/Arabic-Services-JavaScript/compare/v1.0.5...HEAD)
 
-## [Unreleased](https://github.com/Seen-Arabic/Arabic-Services-JavaScript/compare/v1.0.4...HEAD)
+## [1.0.5](https://github.com/Seen-Arabic/Arabic-Services-JavaScript/releases/tag/v1.0.5) - 2023-12-03 (19 Jumada al-awwal 1445)
+
+### Updated
+
+-   Trim text before converting ([#22](https://github.com/Seen-Arabic/Arabic-Services-JavaScript/issues/22))
+
+[Full Changelog](https://github.com/Seen-Arabic/Arabic-Services-JavaScript/compare/v1.0.3...v1.0.4)
 
 ## [1.0.4](https://github.com/Seen-Arabic/Arabic-Services-JavaScript/releases/tag/v1.0.4) - 2023-11-30 (16 Jumada al-awwal 1445)
+
 ### Updated
--  rename `Panned` to `Banned`: which is the correct translation of `محظور` ([PR #19](https://github.com/Seen-Arabic/Arabic-Services-JavaScript/pull/19))
+
+-   rename `Panned` to `Banned`: which is the correct translation of `محظور` ([PR #19](https://github.com/Seen-Arabic/Arabic-Services-JavaScript/pull/19))
 
 [Full Changelog](https://github.com/Seen-Arabic/Arabic-Services-JavaScript/compare/v1.0.3...v1.0.4)
 
 ## [1.0.3](https://github.com/Seen-Arabic/Arabic-Services-JavaScript/releases/tag/v1.0.3) - 2023-11-18 (04 Jumada al-awwal 1445)
+
 ### Added
-- Convert To Old Arabic And Tashfeer Banned Words: Transform Arabic text into old script and replace Banned Arabic text with visually similar characters for encoding purposes. (Banned words are words that considered as hate speech in social media) ([#18](https://github.com/Seen-Arabic/Arabic-Services-JavaScript/issues/18))
+
+-   Convert To Old Arabic And Tashfeer Banned Words: Transform Arabic text into old script and replace Banned Arabic text with visually similar characters for encoding purposes. (Banned words are words that considered as hate speech in social media) ([#18](https://github.com/Seen-Arabic/Arabic-Services-JavaScript/issues/18))
 
 [Full Changelog](https://github.com/Seen-Arabic/Arabic-Services-JavaScript/compare/v1.0.2...v1.0.3)
 
 ## [1.0.2](https://github.com/Seen-Arabic/Arabic-Services-JavaScript/releases/tag/v1.0.2) - 2023-11-18 (04 Jumada al-awwal 1445)
+
 ### Added
-- Tashfeer Banned Words: Replaces Banned Arabic text with visually similar characters for encoding purposes. (Banned words are words that considered as hate speech in social media) ([#16](https://github.com/Seen-Arabic/Arabic-Services-JavaScript/issues/16))
-- Remove Arabic Affixes: Removes predefined affixes (prefixes and suffixes) from an Arabic word if it starts or ends with those affixes. ([#17](https://github.com/Seen-Arabic/Arabic-Services-JavaScript/issues/17))
+
+-   Tashfeer Banned Words: Replaces Banned Arabic text with visually similar characters for encoding purposes. (Banned words are words that considered as hate speech in social media) ([#16](https://github.com/Seen-Arabic/Arabic-Services-JavaScript/issues/16))
+-   Remove Arabic Affixes: Removes predefined affixes (prefixes and suffixes) from an Arabic word if it starts or ends with those affixes. ([#17](https://github.com/Seen-Arabic/Arabic-Services-JavaScript/issues/17))
 
 [Full Changelog](https://github.com/Seen-Arabic/Arabic-Services-JavaScript/compare/v1.0.1...v1.0.2)
 
 ## [1.0.1](https://github.com/Seen-Arabic/Arabic-Services-JavaScript/releases/tag/v1.0.1) - 2023-11-15 (Jumada al-awwal 1445)
+
 ### Added
-- Word To Letters: Convert Arabic word to its pronounced letters.  ([#2](https://github.com/Seen-Arabic/Arabic-Services-JavaScript/issues/2))
+
+-   Word To Letters: Convert Arabic word to its pronounced letters. ([#2](https://github.com/Seen-Arabic/Arabic-Services-JavaScript/issues/2))
 
 [Full Changelog](https://github.com/Seen-Arabic/Arabic-Services-JavaScript/compare/1.0.0...v1.0.1)
 
 ## [1.0.0](https://github.com/Seen-Arabic/Arabic-Services-JavaScript/releases/tag/1.0.0) - 2023-11-07 (23 Rabi` al Thani 1445)
+
 ### Added
-- Initial release of the library with the following functionalities:
-    - Tashkeel Removal: Easily remove Tashkeel from Arabic text.  ([#12](https://github.com/Seen-Arabic/Arabic-Services-JavaScript/issues/12))
-    - Tatweel Removal: Remove Tatweel character from Arabic phrases.  ([#8](https://github.com/Seen-Arabic/Arabic-Services-JavaScript/issues/8))
-    - Convert To Old Arabic: Transform Arabic text into old script.  ([#9](https://github.com/Seen-Arabic/Arabic-Services-JavaScript/issues/9))
-    - Tashfeer: Replaces Arabic text with visually similar characters for encoding purposes.  ([#13](https://github.com/Seen-Arabic/Arabic-Services-JavaScript/issues/13))
+
+-   Initial release of the library with the following functionalities:
+    -   Tashkeel Removal: Easily remove Tashkeel from Arabic text. ([#12](https://github.com/Seen-Arabic/Arabic-Services-JavaScript/issues/12))
+    -   Tatweel Removal: Remove Tatweel character from Arabic phrases. ([#8](https://github.com/Seen-Arabic/Arabic-Services-JavaScript/issues/8))
+    -   Convert To Old Arabic: Transform Arabic text into old script. ([#9](https://github.com/Seen-Arabic/Arabic-Services-JavaScript/issues/9))
+    -   Tashfeer: Replaces Arabic text with visually similar characters for encoding purposes. ([#13](https://github.com/Seen-Arabic/Arabic-Services-JavaScript/issues/13))

package.json

@@ -1,6 +1,6 @@
 {
 	"name": "arabic-services",
-	"version": "1.0.4",
+	"version": "1.0.5",
 	"description": "Utility functions on Arabic text",
 	"main": "./dist/index.js",
 	"types": "./dist/index.d.ts",

src/scripts/scripts.ts

@@ -21,7 +21,10 @@ import { setCharAt, similarityScore } from '../utils';
  *   Output: "الخيل والليل والبيداء تعرفني"
  */
 export function removeTashkeel(text: string): string {
-	return text.replace(new RegExp('[' + TASHKEEL.join('') + ']', 'g'), '').replace(/ٱ/g, 'ا');
+	return text
+		.trim()
+		.replace(new RegExp('[' + TASHKEEL.join('') + ']', 'g'), '')
+		.replace(/ٱ/g, 'ا');
 }
 
 /**
@@ -33,7 +36,7 @@ export function removeTashkeel(text: string): string {
  *   Output: "الحىل واللىل والٮىدا ٮعرڡٮى"
  */
 export function toOldArabic(sentence: string): string {
-	sentence = removeTashkeel(sentence);
+	sentence = removeTashkeel(sentence.trim());
 	let newSentence = '';
 	for (let letter = 0; letter < sentence.length; letter++) {
 		// if letter is not Arabic letter => append to newSentence
@@ -61,7 +64,8 @@ export function toOldArabic(sentence: string): string {
 
 export function toOldArabicAndTashfeerBannedWords(sentence: string, levelOfTashfeer: number = 2): string {
 	let new_sentence = '';
-	for (const word of sentence.split(' ')) {
+	const words = sentence.trim().split(' ');
+	for (const word of words) {
 		if (checkIfBannedWord(word)) {
 			new_sentence += tashfeerHandler(word, levelOfTashfeer) + ' ';
 		} else {
@@ -80,7 +84,7 @@ export function toOldArabicAndTashfeerBannedWords(sentence: string, levelOfTashf
  *   Output: "رائع"
  */
 export function removeTatweel(text: string): string {
-	return text.replace(/ـ/g, '');
+	return text.trim().replace(/ـ/g, '');
 }
 
 /**
@@ -89,18 +93,19 @@ export function removeTatweel(text: string): string {
  * @returns {string} The word with pronounced letters separated by spaces.
  */
 export function wordToLetters(word: string): string {
+	const trimmedWord = word.trim();
 	let newWord = '';
 
 	// Loop through each character in the input word
-	for (let i = 0; i < word.length; i++) {
-		const letter = word[i];
+	for (let i = 0; i < trimmedWord.length; i++) {
+		const letter = trimmedWord[i];
 
 		// Check if the current letter has a pronunciation in PRONOUNCED_LETTERS
 		if (PRONOUNCED_LETTERS.hasOwnProperty(letter)) {
 			newWord += PRONOUNCED_LETTERS[letter];
 
 			// Add a space after the pronounced letter unless it's the last letter in the word
-			if (i !== word.length - 1) {
+			if (i !== trimmedWord.length - 1) {
 				newWord += ' ';
 			}
 		} else {
@@ -121,6 +126,7 @@ export function wordToLetters(word: string): string {
  * @returns {string} The word after removing any matching affixes. Returns the original word if no affix matches are found.
  */
 export function removeArabicAffixes(word: string): string {
+	word = word.trim();
 	if (ARABIC_PREFIXES.includes(word.substring(0, 2))) {
 		// For: ALEF & LAM
 		word = setCharAt(word, 0, '');
@@ -263,6 +269,7 @@ function tashfeerHandler(word: string, level: number = 0): string {
  * @returns {string} The encrypted sentence.
  */
 export function tashfeer(sentence: string, levelOfTashfeer: number = 1): string {
+	sentence = sentence.trim();
 	let new_sentence = '';
 	for (const word of sentence.split(' ')) {
 		new_sentence += tashfeerHandler(word, levelOfTashfeer) + ' ';
@@ -308,6 +315,7 @@ function checkIfBannedWord(string: string): boolean {
  */
 export function tashfeerBannedWords(sentence: string, levelOfTashfeer: number = 2): string {
 	let new_sentence = '';
+	sentence = sentence.trim();
 	for (const word of sentence.split(' ')) {
 		if (checkIfBannedWord(word)) {
 			new_sentence += tashfeerHandler(word, levelOfTashfeer) + ' ';