Python3 version of KrutidevToUnicode.py

KrutidevToUnicode3.py

# KrutidevToUnicode
# coding=utf-8

class KrutidevToUnicode:
    
    CHARS_KD = [
    "ñ", "Q+Z", "sas", "aa", ")Z", "ZZ", "‘", "’", "“", "”",

    "å", "ƒ", "„", "…", "†", "‡", "ˆ", "‰", "Š", "‹",

    "¶+", "d+", "[+k", "[+", "x+", "T+", "t+", "M+", "<+", "Q+", ";+", "j+", "u+",
    "Ùk", "Ù", "ä", "–", "—", "é", "™", "=kk", "f=k",

    "à", "á", "â", "ã", "ºz", "º", "í", "{k", "{", "=", "«",
    "Nî", "Vî", "Bî", "Mî", "<î", "|", "K", "}",
    "J", "Vª", "Mª", "<ªª", "Nª", "Ø", "Ý", "nzZ", "æ", "ç", "Á", "xz", "#", ":",

    "v‚", "vks", "vkS", "vk", "v", "b±", "Ã", "bZ", "b", "m", "Å", ",s", ",", "_",

    "ô", "d", "Dk", "D", "[k", "[", "x", "Xk", "X", "Ä", "?k", "?", "³",
    "pkS", "p", "Pk", "P", "N", "t", "Tk", "T", ">", "÷", "¥",

    "ê", "ë", "V", "B", "ì", "ï", "M+", "<+", "M", "<", ".k", ".",
    "r", "Rk", "R", "Fk", "F", ")", "n", "/k", "èk", "/", "Ë", "è", "u", "Uk", "U",

    "i", "Ik", "I", "Q", "¶", "c", "Ck", "C", "Hk", "H", "e", "Ek", "E",
    ";", "¸", "j", "y", "Yk", "Y", "G", "o", "Ok", "O",
    "'k", "'", "\"k", "\"", "l", "Lk", "L", "g",

    "È", "z",
    "Ì", "Í", "Î", "Ï", "Ñ", "Ò", "Ó", "Ô", "Ö", "Ø", "Ù", "Ük", "Ü",

    "‚", "ks", "kS", "k", "h", "q", "w", "`", "s", "S",
    "a", "¡", "%", "W", "•", "·", "∙", "·", "~j", "~", "\\", "+", " ः",
    "^", "*", "Þ", "ß", "(", "¼", "½", "¿", "À", "¾", "A", "-", "&", "&", "Œ", "]", "~ ", "@"
    ]

    CHARS_UNICODE = [
    "॰", "QZ+", "sa", "a", "र्द्ध", "Z", "\"", "\"", "'", "'",

    "०", "१", "२", "३", "४", "५", "६", "७", "८", "९",

    "फ़्", "क़", "ख़", "ख़्", "ग़", "ज़्", "ज़", "ड़", "ढ़", "फ़", "य़", "ऱ", "ऩ",
    "त्त", "त्त्", "क्त", "दृ", "कृ", "न्न", "न्न्", "=k", "f=",

    "ह्न", "ह्य", "हृ", "ह्म", "ह्र", "ह्", "द्द", "क्ष", "क्ष्", "त्र", "त्र्",
    "छ्य", "ट्य", "ठ्य", "ड्य", "ढ्य", "द्य", "ज्ञ", "द्व",
    "श्र", "ट्र", "ड्र", "ढ्र", "छ्र", "क्र", "फ्र", "र्द्र", "द्र", "प्र", "प्र", "ग्र", "रु", "रू",

    "ऑ", "ओ", "औ", "आ", "अ", "ईं", "ई", "ई", "इ", "उ", "ऊ", "ऐ", "ए", "ऋ",

    "क्क", "क", "क", "क्", "ख", "ख्", "ग", "ग", "ग्", "घ", "घ", "घ्", "ङ",
    "चै", "च", "च", "च्", "छ", "ज", "ज", "ज्", "झ", "झ्", "ञ",

    "ट्ट", "ट्ठ", "ट", "ठ", "ड्ड", "ड्ढ", "ड़", "ढ़", "ड", "ढ", "ण", "ण्",
    "त", "त", "त्", "थ", "थ्", "द्ध", "द", "ध", "ध", "ध्", "ध्", "ध्", "न", "न", "न्",

    "प", "प", "प्", "फ", "फ्", "ब", "ब", "ब्", "भ", "भ्", "म", "म", "म्",
    "य", "य्", "र", "ल", "ल", "ल्", "ळ", "व", "व", "व्",
    "श", "श्", "ष", "ष्", "स", "स", "स्", "ह",

    "ीं", "्र",
    "द्द", "ट्ट", "ट्ठ", "ड्ड", "कृ", "भ", "्य", "ड्ढ", "झ्", "क्र", "त्त्", "श", "श्",

    "ॉ", "ो", "ौ", "ा", "ी", "ु", "ू", "ृ", "े", "ै",
    "ं", "ँ", "ः", "ॅ", "ऽ", "ऽ", "ऽ", "ऽ", "्र", "्", "?", "़", ":",
    "‘", "’", "“", "”", ";", "(", ")", "{", "}", "=", "।", ".", "-", "µ", "॰", ",", "् ", "/"
    ]
    
    @staticmethod
    def do_convert(krutidevPart):
        processPart = krutidevPart
        if processPart != "":
            for input_symbol_idx in range(0, len(KrutidevToUnicode.CHARS_KD)):
                idx = 0
                while idx > -1:
                    processPart = processPart.replace(KrutidevToUnicode.CHARS_KD[input_symbol_idx], KrutidevToUnicode.CHARS_UNICODE[input_symbol_idx])
                    idx = processPart.find(KrutidevToUnicode.CHARS_KD[input_symbol_idx])
            
            # Code for Replacing five Special glyphs
            
            # Code for Glyph1 : ± (reph+anusvAr)
            
            processPart = processPart.replace('±', "Zं")
            
            # Glyp2: Æ
            # code for replacing "f" with "ि" and correcting its position too. (moving it one position forward)
            
            processPart = processPart.replace('Æ', "र्f")
            
            position_of_i = processPart.find('f')
            while position_of_i > -1:
                charecter_next_to_i = processPart[position_of_i + 1]
                charecter_to_be_replaced = "f" + charecter_next_to_i
                processPart = processPart.replace(charecter_to_be_replaced, charecter_next_to_i + "ि")
                position_of_i = processPart.find('f', position_of_i + 1)
            
            # Glyph3 & Glyph4: Ç  É
            # code for replacing "fa" with "िं"  and correcting its position too.(moving it two positions forward)
            
            processPart = processPart.replace('Ç', "fa")
            processPart = processPart.replace('É', "र्fa")
            
            position_of_i = processPart.find('fa')
            while position_of_i > -1:
                charecter_next_to_ip2 = processPart[position_of_i + 2]
                charecter_to_be_replaced = "fa" + charecter_next_to_ip2
                processPart = processPart.replace(charecter_to_be_replaced, charecter_next_to_ip2 + "िं")
                position_of_i = processPart.find('fa', position_of_i + 1)
            
            # Glyph5: Ê
            # code for replacing "h" with "ी"  and correcting its position too.(moving it one positions forward)
            
            processPart = processPart.replace('Ê', "ीZ")
            
            # End of Code for Replacing four Special glyphs
            
            # following loop to eliminate 'chhotee ee kee maatraa' on half-letters as a result of above transformation.
            position_of_wrong_ee = processPart.find("ि्")
            while position_of_wrong_ee > -1:
                consonent_next_to_wrong_ee = processPart[position_of_wrong_ee + 2]
                charecter_to_be_replaced = "ि्" + consonent_next_to_wrong_ee
                processPart = processPart.replace(charecter_to_be_replaced, "्" + consonent_next_to_wrong_ee + "ि")
                position_of_wrong_ee = processPart.find("ि्", position_of_wrong_ee + 2)
            
            # Eliminating reph "Z" and putting 'half - r' at proper position for this.
            set_of_matras = "अ आ इ ई उ ऊ ए ऐ ओ औ ा ि ी ु ू ृ े ै ो ौ ं : ँ ॅ"
            position_of_R = processPart.find("Z")
            while position_of_R > -1:
                probable_position_of_half_r = position_of_R - 1
                charecter_at_probable_position_of_half_r = processPart[probable_position_of_half_r]
                
                # trying to find non-maatra position left to current O (ie, half -r).
                while set_of_matras.find(charecter_at_probable_position_of_half_r) > -1:
                    probable_position_of_half_r = probable_position_of_half_r - 1
                    charecter_at_probable_position_of_half_r = processPart[probable_position_of_half_r]
                
                charecter_to_be_replaced = processPart[probable_position_of_half_r, (position_of_R - probable_position_of_half_r)]
                new_replacement_string = "र्" + charecter_to_be_replaced
                charecter_to_be_replaced = charecter_to_be_replaced + "Z"
                processPart = processPart.replace(charecter_to_be_replaced, new_replacement_string)
                position_of_R = processPart.find("Z")
        
        return processPart
        
    @staticmethod
    def convert_to_unicode(krutidevString):
        unicodeString = ''
        
        text_size = len(krutidevString)
        sthiti1 = 0
        sthiti2 = 0
        chale_chalo = 1
        max_text_size = 6000
        
        while chale_chalo == 1:
            sthiti1 = sthiti2
            
            if sthiti2 < (text_size - max_text_size):
                sthiti2 += max_text_size
                while krutidevString[sthiti2] != ' ':
                    sthiti2 -= 1
            else:
                sthiti2 = text_size
                chale_chalo = 0
            
            modifiedSubstring = krutidevString[sthiti1:sthiti2]
            unicodeString += KrutidevToUnicode.do_convert(modifiedSubstring)
        
        return unicodeString

Fork of https://gist.github.com/trinopoty/b83b136ff25cdfda0cbe774dc17e43ca with minor and hopefully obvious fixes for Python 3.

Test with an input string I got from https://www.unicodetokrutidev.com/:

Python 3.8.2 (default, May 18 2021, 11:47:11) 
[Clang 12.0.5 (clang-1205.0.22.9)] on darwin
Type "help", "copyright", "credits" or "license" for more information.
>>> from KrutidevToUnicode import KrutidevToUnicode
>>> KrutidevToUnicode.convert_to_unicode(';gk\u00a1 is vkidk ;wfudksM')
'यहाँ पे आपका यूनिकोड'

For background, see also https://stackoverflow.com/questions/68204953/unicode-to-kruti-dev-010

See also https://github.com/jmcmanu2/python_practice/blob/master/Unicode%20KrutiDev%20converter.py which converts both ways. I have a Python 3 fork of that at https://gist.github.com/tripleee/b82a79f5b3e57dc6a487ae45077cdbd3 now.

I am not able to convert a string 'ikVhZd' probably because it conatins Z. There is an error in line 138 due to TypeError: string indices must be integers.

@agupta54 The linked other code (see my previous comment) seems to be able to convert your string without errors; I get पार्टीक (I have no idea whether this is correct; I'm afraid I don't read devanagari, let alone speak whichever language this is; but it seems to agree with what I get from https://www.unicodetokrutidev.com/)

I was getting a problem in that code as well in line 168 since there is a comma to slice a string. After changing line 168 to
charecter_to_be_replaced = processPart[ probable_position_of_half_r: (position_of_R - probable_position_of_half_r)+2]
I was able to get the same output पार्टीक