Transliterates Turkish names/words to Bulgarian Cyrillic

transliterate_tr_to_bg.py

import re
def transliterate_tr_to_bg(names, silent_g=False):
    """Transliterates Turkish names/words to Bulgarian Cyrillic.

    Transliteration follows standard Turkish-to-Bulgarian mapping conventions:
    - Turkish-specific letters: ı→ъ, İ→И, I→Ъ, ş→ш, ç→ч, ğ→г (optional)
    - Digraphs: Ya/ya → Я/я, Yu/yu → Ю/ю
    - Multi-character mappings: ö→йо, ü→ю, c→ддж

    Args:
        names: A string, list, tuple, or set of strings to transliterate.
        silent_g: If True, ğ/Ğ is treated as silent (omitted). 
                  If False (default), ğ/Ğ maps to г/Г.

    Returns:
        Transliterated string, or list of strings if input is a collection.

    Note:
        This is a character-by-character transliteration and does not handle
        palatalization of k, g, l before front vowels.
    """
    def _convert(text):
        if not text:
            return ""

        def apply_case(original, cyrillic_lower):
            """Dynamically match output case to input case."""
            if original.isupper():
                return cyrillic_lower.upper()
            if original[0].isupper():
                return cyrillic_lower.capitalize()
            return cyrillic_lower

        result = []
        i, n = 0, len(text)
        
        # Base mapping (lowercase Turkish -> lowercase Cyrillic)
        base_map = {
            'a':'а','b':'б','c':'дж','ç':'ч','d':'д','e':'е','f':'ф','g':'г',
            'h':'х','ı':'ъ','i':'и','j':'ж','k':'к','l':'л','m':'м','n':'н','o':'о',
            'p':'п','r':'р','s':'с','ş':'ш','t':'т','u':'у','v':'в','y':'й','z':'з',
            'ö':'йо','ü':'ю'
        }

        while i < n:
            # 1. Check 2-character digraphs first
            if i + 1 < n:
                two = text[i:i+2]
                two_lower = two.lower()
                
                if two_lower == 'ya':
                    # Start of word -> я/ю, else -> йа/йу
                    cyr = 'я' if i == 0 else 'йа'
                    result.append(apply_case(two, cyr))
                    i += 2
                    continue
                elif two_lower == 'yu':
                    cyr = 'ю' if i == 0 else 'йу'
                    result.append(apply_case(two, cyr))
                    i += 2
                    continue

            # 2. Single character processing
            ch = text[i]
            ch_lower = ch.lower()

            # Handle ğ/Ğ
            if ch_lower == 'ğ':
                if not silent_g:
                    result.append(apply_case(ch, 'г'))
                i += 1
                continue

            # Base mapping
            if ch_lower in base_map:
                result.append(apply_case(ch, base_map[ch_lower]))
            else:
                result.append(ch)  # Keep punctuation, numbers, etc.

            i += 1

        out = "".join(result)
        
        # Exception: final -ЪТ → -ИТ (case-aware)
        if out.upper().endswith("ЪТ"):
            suffix = "ИТ" if out[-2:].isupper() else "Ит" if out[-2].isupper() else "ит"
            out = out[:-2] + suffix
            
        return out

    if isinstance(names, str):
        return _convert(names)
    elif isinstance(names, (list, tuple, set)):
        return [_convert(str(n)) for n in names]
    else:
        raise TypeError("Input must be a string or iterable of strings.")


# ==========================================
# TEST BENCH
# ==========================================
test_cases = [
    "Özdemir", "İLYAS", "Feyzullah Yardımcı", "Yaşar Dinç", 
    "CEVİZ", "Kaya", "Ünal", "Cem", "Işık", "Dağ"
]

print("=== CASE PRESERVATION TEST ===")
for name in test_cases:
    print(f"{name:<20} -> {transliterate_tr_to_bg(name)}")

print("\n=== BATCH TEST (Your Examples) ===")
test_batch = [
    "Adem", "Bıçak", "Cem", "Çelik", "Demir", "Enver", "Fatih", 
    "Güneş", "Dağ", "Hasan", "Işık", "İsmail", "Jale", "Kaya", 
    "Leyla", "Mehmet", "Nevzat", "Osman", "Özdemir", "Polat", 
    "Ramazan", "Selim", "Şahin", "Tarık", "Uğur", "Ünal", "Veli", 
    "Yaşar", "Ziya"
]

results = transliterate_tr_to_bg(test_batch)
for original, cyrillic in zip(test_batch, results):
    print(f"{original:<10} -> {cyrillic}")

with open("names.txt", "r", encoding="utf-8") as file:
    for line in file:
        print(transliterate_tr_to_bg(line.strip()))