From e9355cd058eb289a3f0d2ab0df5785638db4fcf7 Mon Sep 17 00:00:00 2001
From: Niskala Airaha <34799053+niskala5570@users.noreply.github.com>
Date: Wed, 24 May 2023 08:07:48 +0800
Subject: [PATCH 1/2] Tukar regex

---
 alih-kata.py | 25 +++++++++++++++++--------
 1 file changed, 17 insertions(+), 8 deletions(-)

diff --git a/alih-kata.py b/alih-kata.py
index 367f8ac..d9a8711 100644
--- a/alih-kata.py
+++ b/alih-kata.py
@@ -52,7 +52,7 @@ def gantikan_tanda(padanan):
 
     ayat_diterjemah = re.sub(r'(?<!\\)(\\[Nnh])', r' {\1} ', ayat)
 
-    ayat_diterjemah = re.sub(r'(?<!{){[^}]+}|[A-Za-z]+', lambda padanan: alih_kata(padanan, translations, chosen_translations, ayat), ayat_diterjemah)
+    ayat_diterjemah = re.sub(r'(?<!{){[^}]+}|[A-Za-z-]+', lambda padanan: alih_kata(padanan, translations, chosen_translations, ayat), ayat_diterjemah)
     ayat_diterjemah = re.sub(r'[?,;,.]', gantikan_tanda, ayat_diterjemah)
 
     ayat_diterjemah = ayat_diterjemah.replace('{\\N}', '\\N').replace('{\\n}', '\\n').replace('{\\h}', '\\h')
@@ -92,7 +92,7 @@ def alih_kata_sarikata(file_path, translations, padanan_tanda, padanan_tanggaman
 
         dialog.text = dialog_terjemah
 
-        katan_rumi_jawi = re.findall(r'(?<!{)(?<!\\)(?:\\\\)*(?<!\\[Nnh])\b[A-Za-z]+(?<!\\)(?!})(?<!\\[Nnh])', teks_dialog)
+        katan_rumi_jawi = re.findall(r'(?<!{)(?<!\\)(?:\\\\)*(?<!\\[Nnh])\b[A-Za-z-]+(?<!\\)(?!})(?<!\\[Nnh])', teks_dialog)
         for katan in katan_rumi_jawi:
             if katan.lower() not in translations and not re.search(r'(?<!\\){[^}]+}', teks_dialog):
                 katan_terjemah = alih_kata(re.search(katan, teks_dialog), translations, chosen_translations, teks_dialog)
@@ -101,15 +101,23 @@ def alih_kata_sarikata(file_path, translations, padanan_tanda, padanan_tanggaman
                         if katan.lower().endswith(tanggaman_akhiran):
                             katan_terjemah = alih_kata(re.search(katan[:-len(tanggaman_akhiran)], teks_dialog), translations, chosen_translations, teks_dialog) + padanan_tanggaman_akhiran[tanggaman_akhiran]
                             break
-                if katan_terjemah == katan:
-                    for tanggaman_awalan in padanan_tanggaman_awalan:
-                        if katan.lower().startswith(tanggaman_awalan):
-                            katan_terjemah = padanan_tanggaman_awalan[tanggaman_awalan] + alih_kata(re.search(katan[len(tanggaman_awalan):], teks_dialog), translations, chosen_translations, teks_dialog)
-                            break
+                    if katan_terjemah == katan:
+                        for tanggaman_awalan in padanan_tanggaman_awalan:
+                            if katan.lower().startswith(tanggaman_awalan):
+                                katan_terjemah = padanan_tanggaman_awalan[tanggaman_awalan] + alih_kata(re.search(katan[len(tanggaman_awalan):], teks_dialog), translations, chosen_translations, teks_dialog)
+                                break
                 if katan_terjemah != katan:
                     dialog_terjemah = dialog_terjemah.replace(katan, katan_terjemah)
                 else:
-                    tidak_teralih.append((i, katan))  # Store the index and untranslated word
+                    # Check for compound words with hyphens
+                    if '-' in katan:
+                        compound_words = katan.split('-')
+                        compound_translations = [translations.get(word.lower(), word) for word in compound_words]
+                        if all(word in translations for word in compound_words):
+                            katan_terjemah = '-'.join(compound_translations)
+                            dialog_terjemah = dialog_terjemah.replace(katan, katan_terjemah)
+                    else:
+                        tidak_teralih.append((i, katan))  # Store the index and untranslated word
 
         sarikata.events[i].text = dialog_terjemah
 
@@ -118,6 +126,7 @@ def alih_kata_sarikata(file_path, translations, padanan_tanda, padanan_tanggaman
 
     return len(tidak_teralih), tidak_teralih
 
+
 katan_kamus = {}
 
 for file in os.listdir(folder_kamus):

From 61fdd877a87a860ec3eafd31310eca48b54c822c Mon Sep 17 00:00:00 2001
From: Niskala Airaha <34799053+niskala5570@users.noreply.github.com>
Date: Wed, 24 May 2023 09:56:49 +0800
Subject: [PATCH 2/2] Update alih-kata.py

---
 alih-kata.py | 54 +++++++++++++++++++++++-----------------------------
 1 file changed, 24 insertions(+), 30 deletions(-)

diff --git a/alih-kata.py b/alih-kata.py
index d9a8711..339db4f 100644
--- a/alih-kata.py
+++ b/alih-kata.py
@@ -1,5 +1,8 @@
-# The code mostly generated by ChatGPT (I can't code and just stitch it together part by part)
-# Even I don't understand much but I will explain what the code will do inside README.md
+# Kod ni kebanyakkannya ditulis dengan ChatGPT sebab aku malas dan tak reti.
+# Jadi aku camtum2 macam lego, kalau nampak cacat dan rajin nak tolong kemaskan, dipersilakan.
+# Aku buat kod ni sebab nak percepatkan kerja sahaja, takdelah aku perlu tulis balik Jawi dari awal.
+# Untuk perkataan bersengkang, kena buat masukan kamus baru sebab kod tak akan pisahkan(tokenize) Contohnya "Kazuki-kun"
+# Ini supaya perkataan berganda seperti "apa-apa, اڤ٢" dapat dialih dengan sempurna
 
 import pysubs2
 import os
@@ -9,7 +12,7 @@
 folder_keluar = "Keluar"
 folder_kamus = "Kamus"
 
-def muat_katan(file_path):
+def muatKamus(file_path):
     data = {}
     with open(file_path) as file:
         lines = file.readlines()
@@ -22,7 +25,7 @@ def muat_katan(file_path):
                 data[rumi] = [jawi]
     return data
 
-def alih_kata(padanan, translations, chosen_translations, context):
+def alihKata(padanan, translations, chosen_translations, context):
     katan = padanan.group(0)
     if katan.lower() in translations:
         translations_list = translations[katan.lower()]
@@ -43,7 +46,7 @@ def alih_kata(padanan, translations, chosen_translations, context):
             return translations_list[0]
     return katan
 
-def alih_ayat(ayat, translations, padanan_tanda, chosen_translations):
+def alihAyat(ayat, translations, padanan_tanda, chosen_translations):
     def gantikan_tanda(padanan):
         tanda = padanan.group(0)
         if tanda in padanan_tanda:
@@ -52,21 +55,21 @@ def gantikan_tanda(padanan):
 
     ayat_diterjemah = re.sub(r'(?<!\\)(\\[Nnh])', r' {\1} ', ayat)
 
-    ayat_diterjemah = re.sub(r'(?<!{){[^}]+}|[A-Za-z-]+', lambda padanan: alih_kata(padanan, translations, chosen_translations, ayat), ayat_diterjemah)
+    ayat_diterjemah = re.sub(r'(?<!{){[^}]+}|[A-Za-z\-]+', lambda padanan: alihKata(padanan, translations, chosen_translations, ayat), ayat_diterjemah)
     ayat_diterjemah = re.sub(r'[?,;,.]', gantikan_tanda, ayat_diterjemah)
 
     ayat_diterjemah = ayat_diterjemah.replace('{\\N}', '\\N').replace('{\\n}', '\\n').replace('{\\h}', '\\h')
 
     return ayat_diterjemah
 
-def baiki_ejaan(teks):
+def baikiEjaan(teks):
     # Cari dan ganti 'د ' dan 'ک ' yang berjarak untuk membetulkan perkataan cthnya 'د سکوله'
     teks = re.sub(r'\bد\s', 'د', teks)
     teks = re.sub(r'\bک\s', 'ک', teks)
 
     return teks
 
-def alih_kata_sarikata(file_path, translations, padanan_tanda, padanan_tanggaman_akhiran, padanan_tanggaman_awalan):
+def alihKata_Sarikata(file_path, translations, padanan_tanda, padanan_tanggaman_akhiran, padanan_tanggaman_awalan):
     sarikata = pysubs2.load(file_path)
     tidak_teralih = []
     chosen_translations = {}  # Dictionary to store chosen translations
@@ -84,7 +87,7 @@ def alih_kata_sarikata(file_path, translations, padanan_tanda, padanan_tanggaman
             extracted_content[placeholder] = '{' + extract + '}'
             teks_dialog = teks_dialog.replace('{' + extract + '}', placeholder)
 
-        dialog_terjemah = baiki_ejaan(alih_ayat(teks_dialog, translations, padanan_tanda, chosen_translations))
+        dialog_terjemah = baikiEjaan(alihAyat(teks_dialog, translations, padanan_tanda, chosen_translations))
         dialog_terjemah = "{\\fe-1}" + dialog_terjemah
 
         for placeholder, content in extracted_content.items():
@@ -92,32 +95,24 @@ def alih_kata_sarikata(file_path, translations, padanan_tanda, padanan_tanggaman
 
         dialog.text = dialog_terjemah
 
-        katan_rumi_jawi = re.findall(r'(?<!{)(?<!\\)(?:\\\\)*(?<!\\[Nnh])\b[A-Za-z-]+(?<!\\)(?!})(?<!\\[Nnh])', teks_dialog)
+        katan_rumi_jawi = re.findall(r'(?<!{)(?<!\\)(?:\\\\)*(?<!\\[Nnh])\b[A-Za-z\-]+(?<!\\)(?!})(?<!\\[Nnh])', teks_dialog)
         for katan in katan_rumi_jawi:
             if katan.lower() not in translations and not re.search(r'(?<!\\){[^}]+}', teks_dialog):
-                katan_terjemah = alih_kata(re.search(katan, teks_dialog), translations, chosen_translations, teks_dialog)
+                katan_terjemah = alihKata(re.search(katan, teks_dialog), translations, chosen_translations, teks_dialog)
                 if katan_terjemah == katan:
                     for tanggaman_akhiran in padanan_tanggaman_akhiran:
                         if katan.lower().endswith(tanggaman_akhiran):
-                            katan_terjemah = alih_kata(re.search(katan[:-len(tanggaman_akhiran)], teks_dialog), translations, chosen_translations, teks_dialog) + padanan_tanggaman_akhiran[tanggaman_akhiran]
+                            katan_terjemah = alihKata(re.search(katan[:-len(tanggaman_akhiran)], teks_dialog), translations, chosen_translations, teks_dialog) + padanan_tanggaman_akhiran[tanggaman_akhiran]
+                            break
+                if katan_terjemah == katan:
+                    for tanggaman_awalan in padanan_tanggaman_awalan:
+                        if katan.lower().startswith(tanggaman_awalan):
+                            katan_terjemah = padanan_tanggaman_awalan[tanggaman_awalan] + alihKata(re.search(katan[len(tanggaman_awalan):], teks_dialog), translations, chosen_translations, teks_dialog)
                             break
-                    if katan_terjemah == katan:
-                        for tanggaman_awalan in padanan_tanggaman_awalan:
-                            if katan.lower().startswith(tanggaman_awalan):
-                                katan_terjemah = padanan_tanggaman_awalan[tanggaman_awalan] + alih_kata(re.search(katan[len(tanggaman_awalan):], teks_dialog), translations, chosen_translations, teks_dialog)
-                                break
                 if katan_terjemah != katan:
                     dialog_terjemah = dialog_terjemah.replace(katan, katan_terjemah)
                 else:
-                    # Check for compound words with hyphens
-                    if '-' in katan:
-                        compound_words = katan.split('-')
-                        compound_translations = [translations.get(word.lower(), word) for word in compound_words]
-                        if all(word in translations for word in compound_words):
-                            katan_terjemah = '-'.join(compound_translations)
-                            dialog_terjemah = dialog_terjemah.replace(katan, katan_terjemah)
-                    else:
-                        tidak_teralih.append((i, katan))  # Store the index and untranslated word
+                    tidak_teralih.append((i, katan))  # Store the index and untranslated word
 
         sarikata.events[i].text = dialog_terjemah
 
@@ -126,16 +121,15 @@ def alih_kata_sarikata(file_path, translations, padanan_tanda, padanan_tanggaman
 
     return len(tidak_teralih), tidak_teralih
 
-
 katan_kamus = {}
 
 for file in os.listdir(folder_kamus):
     if file.endswith(".tsv"):
         file_path = os.path.join(folder_kamus, file)
-        katan_kamus = {**katan_kamus, **muat_katan(file_path)}
+        katan_kamus = {**katan_kamus, **muatKamus(file_path)}
 
 padanan_tanda = {"?": "؟", ";": "⁏", ",": "⹁", ".": "."}
-padanan_tanggaman_akhiran = {"lah": "له", "kah": "که", "nya": "ڽ", "kan": "کن", "i": "ي", "ku": "کو", "mu": "مو"}
+padanan_tanggaman_akhiran = {"lah": "له", "kah": "که", "kan": "کن", "i": "ي", "ku": "کو", "mu": "مو", "nya": "ڽ"}
 padanan_tanggaman_awalan = {"ber": "بر", "mem": "مم", "meng": "مڠ", "se": "س", "tak": "تق", "per": "ڤر"}
 
 select_translation = True
@@ -147,7 +141,7 @@ def alih_kata_sarikata(file_path, translations, padanan_tanda, padanan_tanggaman
         print(f"Mengalih kata: {fail}\n---")
         laluan_fail = os.path.join(folder_masuk, fail)
         if select_translation:
-            tidak_teralih_count, tidak_teralih = alih_kata_sarikata(laluan_fail, katan_kamus, padanan_tanda, padanan_tanggaman_akhiran, padanan_tanggaman_awalan)
+            tidak_teralih_count, tidak_teralih = alihKata_Sarikata(laluan_fail, katan_kamus, padanan_tanda, padanan_tanggaman_akhiran, padanan_tanggaman_awalan)
         else:
             tidak_teralih_count, tidak_teralih = 0, []
         if tidak_teralih_count > 0: