from typing import Dict, List, FrozenSet


KASHMIRI_CHARACTER_MAPPING: Dict[str, List[str]] = {'آ': ['ﺁ', 'ﺂ'],
                                                          'أ': ['ﺃ'],
                                                          'ا': ['ﺍ', 'ﺎ'],
                                                          'ب': ['ﺏ', 'ﺐ', 'ﺑ', 'ﺒ'],
                                                          'پ': ['ﭖ', 'ﭘ', 'ﭙ', ],
                                                          'ت': ['ﺕ', 'ﺖ', 'ﺗ', 'ﺘ'],
                                                          'ٹ': ['ﭦ', 'ﭧ', 'ﭨ', 'ﭩ'],
                                                          'ث': ['ﺛ', 'ﺜ', 'ﺚ'],
                                                          'ج': ['ﺝ', 'ﺞ', 'ﺟ', 'ﺠ'],
                                                          'ح': ['ﺡ', 'ﺣ', 'ﺤ', 'ﺢ'],
                                                          'خ': ['ﺧ', 'ﺨ', 'ﺦ'],
                                                          'د': ['ﺩ', 'ﺪ'],
                                                          'ذ': ['ﺬ', 'ﺫ'],
                                                          'ر': ['ﺭ', 'ﺮ'],
                                                          'ز': ['ﺯ', 'ﺰ', ],
                                                          'س': ['ﺱ', 'ﺲ', 'ﺳ', 'ﺴ', ],
                                                          'ش': ['ﺵ', 'ﺶ', 'ﺷ', 'ﺸ'],
                                                          'ص': ['ﺹ', 'ﺺ', 'ﺻ', 'ﺼ', ],
                                                          'ض': ['ﺽ', 'ﺾ', 'ﺿ', 'ﻀ'],
                                                          'ط': ['ﻃ', 'ﻄ'],
                                                          'ظ': ['ﻅ', 'ﻇ', 'ﻈ'],
                                                          'ع': ['ﻉ', 'ﻊ', 'ﻋ', 'ﻌ', ],
                                                          'غ': ['ﻍ', 'ﻏ', 'ﻐ', ],
                                                          'ف': ['ﻑ', 'ﻒ', 'ﻓ', 'ﻔ', ],
                                                          'ق': ['ﻕ', 'ﻖ', 'ﻗ', 'ﻘ', ],
                                                          'ل': ['ﻝ', 'ﻞ', 'ﻟ', 'ﻠ', ],
                                                          'م': ['ﻡ', 'ﻢ', 'ﻣ', 'ﻤ', ],
                                                          'ن': ['ﻥ', 'ﻦ', 'ﻧ', 'ﻨ', ],
                                                          'چ': ['ﭺ', 'ﭻ', 'ﭼ', 'ﭽ'],
                                                          'ڈ': ['ﮈ', 'ﮉ'],
                                                          'ڑ': ['ﮍ', 'ﮌ'],
                                                          'ژ': ['ﮋ', ],
                                                          'ک': ['ﮎ', 'ﮏ', 'ﮐ', 'ﮑ', 'ﻛ', 'ك'],
                                                          'گ': ['ﮒ', 'ﮓ', 'ﮔ', 'ﮕ'],
                                                          'ں': ['ﮞ', 'ﮟ'],
                                                          'و': ['ﻮ', 'ﻭ', 'ﻮ', ],
                                                          'ؤ': ['ﺅ'],
                                                          'ھ': ['ﮪ', 'ﮬ', 'ﮭ', 'ﻬ', 'ﻫ', 'ﮫ'],
                                                          'ہ': ['ﻩ', 'ﮦ', 'ﻪ', 'ﮧ', 'ﮩ', 'ﮨ', 'ه', ],
                                                          'ۂ': [],
                                                          'ۃ': ['ة'],
                                                          'ء': ['ﺀ'],
                                                          'ی': ['ﯼ', 'ى', 'ﯽ', 'ﻰ', 'ﻱ', 'ﻲ', 'ﯾ', 'ﯿ', 'ي'],
                                                          'ئ': ['ﺋ', 'ﺌ', ],
                                                          'ے': ['ﮮ', 'ﮯ', 'ﻳ', 'ﻴ', ],
                                                          'ۓ': [],
                                                          '۰': ['٠'],
                                                          '۱': ['١'],
                                                          '۲': ['٢'],
                                                          '۳': ['٣'],
                                                          '۴': ['٤'],
                                                          '۵': ['٥'],
                                                          '۶': ['٦'],
                                                          '۷': ['٧'],
                                                          '۸': ['٨'],
                                                          '۹': ['٩'],
                                                          '۔': [],
                                                          '؟': [],
                                                          '٫': [],
                                                          '،': [],
                                                          'لا': ['ﻻ', 'ﻼ'],
                                                          '': ['ـ'],
                                                          'ژ':['ـژ', 'ـژ'],
                                                          'ؠ':['ـؠ','\u06ea', '\u066e\u06ea', 'ؠـ', 'ـؠـ', ],
                                                          'ۄ':['\u06c5'],
                                                          ' ' : ['\u200C'], # NOT A CHARACTER, HANDLING ZWNJ by Replacing with space
                                                          'ۍ' : []
                                                          
                                                          }

PUNCTUATION_MAP: Dict[str, List[str]] = {
    '"': ['„', '“', '”', "''", '´´'],
    '-': ['–'],
    ' - ': ['—'],
    "'": ['´', '‘', '‚', '’'],
    '...': ['…'],
    
}

ENG_KASHMIRI_DIGITS_MAP: Dict = {
    '0': ['۰'],
    '1': ['۱'],
    '2': ['۲'],
    '3': ['۳'],
    '4': ['۴'],
    '5': ['۵'],
    '6': ['۶'],
    '7': ['۷'],
    '8': ['۸'],
    '9': ['۹']
}

KASHMIRI_ENG_DIGITS_MAP: Dict = {
    '۰': ['0'],
    '۱': ['1'],
    '۲': ['2'],
    '۳': ['3'],
    '۴': ['4'],
    '۵': ['5'],
    '۶': ['6'],
    '۷': ['7'],
    '۸': ['8'],
    '۹': ['9']
}
KASHMIRI_DIACRITICS: FrozenSet[str] = frozenset("\u064e \u0670 \u0654 \u0650 \u0656 \u0655 \u065f \u064f \u0657 \u065A \u065b".split())

KASHMIRI_PUNCTUATIONS: FrozenSet[str] = frozenset("؛ ، ٫  ؟ ۔ ٪".split())

# Characters, Diacritics, Digits (Both sets), and Punctuations suitable for TTS vocabulary
ALL_CHARACTERS: FrozenSet[str] = frozenset(
    list(KASHMIRI_CHARACTER_MAPPING.keys()) + 
    list(KASHMIRI_DIACRITICS) + 
    list(KASHMIRI_PUNCTUATIONS) +
    list(ENG_KASHMIRI_DIGITS_MAP.keys()) +
    list(PUNCTUATION_MAP.keys())
)

WORD_TO_DIGIT_MAP: Dict[str, List[str]] = {
    'صفرٕ': ['0'],
    'اکھ': ['1'],
    'زٕ': ['2'],
    'ترٛےٚ': ['3'],
    'ژور': ['4'],
    'پانژھ': ['5'],
    'شیٚیہ': ['6'],
    'ستھ': ['7'],
    'ٲٹھ': ['8'],
    'نو': ['9']
}