scriptshifter/scriptshifter/tables/data/asian_cyrillic.yml

general:
  name: Asian Cyrillic
  inherits: _cyrillic_base

roman_to_script:
  map:
    # COMMON COMBINING CHARACTERS (always follow a base letter): 
    # combining grave U+0300
    # combining acute U+0301
    # combining circumflex U+0302
    # combining macron U+0304
    # combining breve U+0306
    # combining dot above U+0307
    # combining diaeresis U+0308
    # combining ring above U+030A
    # combining double acute U+030B
    # combining caron (hachek) U+030C
    # combining candrabindu U+0310
    # combining dot below U+0323
    # combining comma below U+0326 (Romanian, Latvian, Livonian)
    # combining cedilla U+0327 (French, Turkish, Azeri)
    # combining ogonek (hook) U+0328 (Polish, Lithuanian)
    # combining left ligature U+FE20 (Cyrillic transliteration)
    # combining right ligature U+FE21 (Cyrillic transliteration)
    # soft sign/prime (spacing) U+02B9(Cyrillic transliteration)
    # hard sign/double prime (spacing) U+02BA (Cyrillic transliteration)
    # ayn(spacing) U+02BB (Semitic and Caucasian languages)
    # alif (spacing) U+02BC (Semitic languages)
    # middle dot (space) U+00B7) (Catalan)

    # REGULAR LATIN ALPHABETIC CHARACTERS TO BE CONVERTED

    # CONVERSION OF "I/i" LIGATED TO "A/a" (all capitalization patterns)
    "I\uFE20A\uFE21": "\u042F"
    "I\uFE20a\uFE21": "\u042F"
    "i\uFE20a\uFE21": "\u044F"
    "i\uFE20A\uFE21": "\u044F"

    # CONVERSION OF "A/a" WITH BREVE (0306)
    "A\u0306": "\u04D8"
    "a\u0306": "\u04D9"

    # DE-ACTIVATED CONVERSION OF GAGAUZ AND MARI LETTER "A/a" WITH BREVE DUE TO CONFLICTING ROMANIZATION
    #"A\u0306": "\u04D2"
    # DE-ACTIVATED CONVERSION OF GAGAUZ AND MARC LETTER "A/a" WITH BREVE DUE TO CONFLICTING ROMANIZATION
    #"a\u0306": "\u04D3"

    # REMAINING LONE "A/a"


    "V\u0307": "\u0474"
    "v\u0307": "\u0475"

    "Gh": "\u0492"
    "GH": "\u0492"
    "gH": "\u0493"
    "gh": "\u0493"

    # DE-ACTIVATED CONVERSION OF YAKUT "A" WITH DIAERSIS DUE TO CONFLICTING ROMANIZATION
    #"Gh": "\u0494"
    # DE-ACTIVATED CONVERSION OF YAKUT "A" WITH DIAERSIS DUE TO CONFLICTING ROMANIZATION
    #"GH": "\u0494"
    # DE-ACTIVATED CONVERSION OF YAKUT "a" WITH DIAERSIS DUE TO CONFLICTING ROMANIZATION
    #"gH": "\u0495"
    # DE-ACTIVATED CONVERSION OF YAKUT "a" WITH DIAERSIS DUE TO CONFLICTING ROMANIZATION
    #"gh": "\u0495"

    "G\u0301": "\u0494"
    "g\u0301": "\u0495"
    "G\u0307": "\u049C"
    "g\u0307": "\u049D"
    "G": "\u0413"
    "g": "\u0433"


    # CONVERION OF "I/i" LIGATED TO "E/e", SOME WITH MACRON (0304) AND OGONEK (0328)
    "I\uFE20E\uFE21\u0304": "\u0464"
    "I\uFE20E\u0304\uFE21": "\u0464"
    "I\uFE20e\uFE21\u0304": "\u0464"
    "I\uFE20e\u0304\uFE21": "\u0464"
    "I\uFE20E\uFE21\u0328": "\u0468"
    "I\uFE20E\u0328\uFE21": "\u0468"
    "I\uFE20e\uFE21\u0328": "\u0468"
    "I\uFE20e\u0328\uFE21": "\u0468"
    "i\uFE20e\uFE21\u0304": "\u0465"
    "i\uFE20e\u0304\uFE21": "\u0465"
    "i\uFE20E\uFE21\u0304": "\u0465"
    "i\uFE20E\u0304\uFE21": "\u0465"
    "i\uFE20e\uFE21\u0328": "\u0469"
    "i\uFE20e\u0328\uFE21": "\u0469"
    "i\uFE20E\uFE21\u0328": "\u0469"
    "i\uFE20E\u0328\uFE21": "\u0469"
    "I\uFE20E\uFE21": "\u0462"
    "I\uFE20e\uFE21": "\u0462"
    "i\uFE20e\uFE21": "\u0463"
    "i\uFE20E\uFE21": "\u0463"

    # CONVERSION OF "E/e" WITH MACRON (0304), DOT ABOVE (0307), DIAERESIS (0308), OGONEK (0328), & CARON (030C)
    "E\u030C": "\u0462"
    "E\u0304": "\u0404"
    "E\u0307": "\u042D"
    "E\u0308": "\u0401"
    "E\u0328": "\u0466"
    "e\u030C": "\u0463"
    "e\u0304": "\u0454"
    "e\u0307": "\u044D"
    "e\u0308": "\u0451"
    "e\u0328": "\u0467"

    # CONVERSION OF REMAINING LONE "E/e"

    "ZH": "\u0416"
    "Zh": "\u0416"
    "zH": "\u0436"
    "zh": "\u0436"


    # CONVERSION OF "T/t" LIGATED OR BLENDED WITH "H/h" (all capitalization patterns)
    "T\uFE20H\uFE21": "\u0498"
    "T\uFE20h\uFE21": "\u0498"
    "t\uFE20H\uFE21": "\u0499"
    "t\uFE20h\uFE21": "\u0499"
    "Th": "\u04AA"
    "TH": "\u04AA"
    "tH": "\u04AB"
    "th": "\u04AB"

    # CONVERION OF "I/i" LIGATED TO "O/o" WITH MACRON (0304) AND OGONEK (0328)
    "I\uFE20O\uFE21\u0328": "\u046C"
    "I\uFE20O\u0328\uFE21": "\u046C"
    "I\uFE20o\uFE21\u0328": "\u046C"
    "I\uFE20o\u0328\uFE21": "\u046C"
    "i\uFE20o\uFE21\u0328": "\u046D"
    "i\uFE20o\u0328\uFE21": "\u046D"
    "i\uFE20O\uFE21\u0328": "\u046D"
    "i\uFE20O\u0328\uFE21": "\u046D"


    # CONVERION OF "I/i" LIGATED TO "U/u"
    "I\uFE20U\uFE21": "\u042E"
    "I\uFE20u\uFE21": "\u042E"
    "i\uFE20u\uFE21": "\u044E"
    "i\uFE20U\uFE21": "\u044E"


    # CONVERSION OF "I/i" WITH MACRON (0304), BREVE (0306), AND CANDRABINDU (0310)
    "I\u0304": "\u0406"
    "I\u0306": "\u0419"
    "I\u0310": "\u0408"
    "i\u0304": "\u0456"
    "i\u0306": "\u0439"
    "i\u0310": "\u0458"

    # CONVERSION OF REMAINING LONE "I/i"
    "I": "\u0418"
    "i": "\u0438"

    "J": "\u0496"
    "j": "\u0497"

    # DE-ACTIVATED CONVERSION OF AZERI "J" DUE TO CONFLICTING ROMANIZATION
    #"J": "\u04B8"
    # DE-ACTIVATED CONVERSION OF AZERI "j" DUE TO CONFLICTING ROMANIZATION
    #"J": "\u04B9"
    # DE-ACTIVATED CONVERSION OF TAJIK "J" DUE TO CONFLICTING ROMANIZATION
    #"J": "\u04B6"
    # DE-ACTIVATED CONVERSION OF TAJIK "j" DUE TO CONFLICTING ROMANIZATION
    #"J": "\u04B7"


    "K\uFE20S\uFE21": "\u046E"
    "K\uFE20s\uFE21": "\u046E"
    "k\uFE20s\uFE21": "\u046F"
    "k\uFE20S\uFE21": "\u046F"
    "Q": "\u04A0"
    "q": "\u04A1"

    # DE-ACTIVATED CONVERSION OF KHANTY "Q" DUE TO CONFLICTING ROMANIZATION
    #"Q": "\u04C3"
    # DE-ACTIVATED CONVERSION OF KHANTY "q" DUE TO CONFLICTING ROMANIZATION
    #"q": "\u04C4"



    "N\uFE20G\uFE21": "\u04A2"
    "N\uFE20g\uFE21": "\u04A2"
    "n\uFE20G\uFE21": "\u04A3"
    "n\uFE20g\uFE21": "\u04A3"

    # DE-ACTIVATED CONVERSION OF YAKUT "NG/ng" DUE TO CONFLICTING ROMANIZATION
    #"N\uFE20G\uFE21": "\u04A4"
    #"N\uFE20g\uFE21": "\u04A4"
    #"n\uFE20G\uFE21": "\u04A5"
    #"n\uFE20g\uFE21": "\u04A5"

    # DE-ACTIVATED CONVERSION OF CHUKCHI AND EVENKI "NG/ng" DUE TO CONFLICTING ROMANIZATION
    #"N\uFE20G\uFE21": "\u04C7"
    #"N\uFE20g\uFE21": "\u04C7"
    #"n\uFE20G\uFE21": "\u04C8"
    #"n\uFE20g\uFE21": "\u04C8"


    # CONVERION OF "O/o" WITH OR WITHOUT MACRON (0304), LIGATED TO "T/t"
    "O\u0304\uFE20T\uFE21": "\u047E"
    "O\u0304\uFE20t\uFE21": "\u047E"
    "O\uFE20\u0304T\uFE21": "\u047E"
    "O\uFE20\u0304t\uFE21": "\u047E"
    "O\uFE20T\uFE21": "\u047E"
    "O\uFE20t\uFE21": "\u047E"
    "o\u0304\uFE20t\uFE21": "\u047F"
    "o\u0304\uFE20T\uFE21": "\u047F"
    "o\uFE20\u0304t\uFE21": "\u047F"
    "o\uFE20\u0304T\uFE21": "\u047F"
    "o\uFE20t\uFE21": "\u047F"
    "o\uFE20T\uFE21": "\u047F"


    # CONVERSION OF "O/o" WITH MACRON(0304)
    "O\u0304": "\u04EA"
    "o\u0304": "\u04EB"
    # CONVERSION OF "O/o" WITH DOT ABOVE (0307) USED IN MOST CENTRAL ASIAN LANGUAGES
    "O\u0307": "\u04E8"
    "o\u0307": "\u04E9"

    # DE-ACTIVATED CONVERSION OF GAGAUZ, KOMI, AND MARI "O" WITH DOT ABOVE (0307)DUE TO CONFLICTING ROMANIZATION
    #"O\u0307": "\u04E6"
    #"o\u0307": "\u04E7"

    # CONVERSION OF REMAINING LONE "O/o"

    "P\uFE20S\uFE21": "\u0470"
    "P\uFE20s\uFE21": "\u0470"
    "p\uFE20s\uFE21": "\u0471"
    "p\uFE20S\uFE21": "\u0471"


    "SHCH": "\u0429"
    "SHCh": "\u0429"
    "SHch": "\u0429"
    "Shch": "\u0429"
    "sHCH": "\u0449"
    "shCH": "\u0449"
    "shcH": "\u0449"
    "shch": "\u0449"

    "sH": "\u0448"

    "T\uFE20S\uFE21\u0307": "\u04B4"
    "T\uFE20S\u0307\uFE21": "\u04B4"
    "T\uFE20s\uFE21\u0307": "\u04B4"
    "T\uFE20s\u0307\uFE21": "\u04B4"
    "t\uFE20S\uFE21\u0307": "\u04B5"
    "t\uFE20S\u0307\uFE21": "\u04B5"
    "t\uFE20s\uFE21\u0307": "\u04B5"
    "t\uFE20s\u0307\uFE21": "\u04B5"

    "T\uFE20S\uFE21": "\u0426"
    "T\uFE20s\uFE21": "\u0426"
    "t\uFE20s\uFE21": "\u0446"
    "t\uFE20S\uFE21": "\u0446"

    # CONVERSION OF "U/u" WITH MACRON(0304), BREVE (0306), AND DOT ABOVE (0307)
    "U\u0304": "\u04B0"
    "u\u0304": "\u04B1"

    # DE-ACTIVATED CONVERSION OF TAJIK LETTER DUE TO CONFLICTING ROMANIZATION
    #"U\u0304": "\u04EE"
    # DE-ACTIVATED CONVERSION OF TAJIK LETTER DUE TO CONFLICTING ROMANIZATION
    #"U\u0304": "\u04EF"

    "U\u0306": "\u040E"
    "u\u0306": "\u0454"
    "U\u0307": "\u04AE"
    "u\u0307": "\u04AF"

    # DE-ACTIVATED CONVERSION OF GAGAUZ AND MARI LETTER "O/o" WITH DOT ABOVE DUE TO CONFLICTING ROMANIZATION
    #"U\u0307": "\u04E6"
    #"u\u0307": "\u04E7"

    # CONVERSION OF ESKIMO AND KARAKALPAK "W/w" THAT MAPS TO THE SAME CHARACTERS AS "U/u" WITH BREVE
    "W": "\u040E"
    "w": "\u0454"


    "F\u0307": "\u0472"
    "f\u0307": "\u0473"

    "cH": "\u0447"

    # CONVERSION OF CYRILLIC PALOCHKA (ASPIRATION SIGN) USED IN MANY CENTRAL ASIAN LANGUAGES (NOT NORMALLY INITIALLY)
    "H\u0307": "\u04BA"
    "h\u0307": "\u04BB"

    # DE-ACTIVATED CONVERSION OF TAJIK AND UZBEK LETTER "H/h" WITH DOT ABOVE (0307) DUE TO CONFLICTING ROMANIZATION
    #"H\u0307": "\u04B2"
    #"h\u0307": "\u04B3"
    # DE-ACTIVATED CONVERSION OF ARCHAIC LETTER "H/h" WITH DOT ABOVE (0307) DUE TO CONFLICTING ROMANIZATION
    #"H\u0307": "\u04FC"
    #"h\u0307": "\u04FD"

    "Y\u0307": "\u04F8"
    "y\u0307": "\u04F9"

    "Y": "\u042B"
    "y": "\u044B"

    "\u0027": "\u044C"
    # this conversion is ambiguous - \u044C is also theoretically possible
    "\u02BA": "\u044A"

script_to_roman:
  map:
    "\u044F": "i\uFE20a\uFE21"
    "\u04D8": "A\u0306"
    "\u04D9": "a\u0306"
    # DE-ACTIVATED CONVERSION OF GAGAUZ AND MARI LETTER "A/a" WITH BREVE DUE TO CONFLICTING ROMANIZATION
    "\u04D2": "A\u0306"
    # DE-ACTIVATED CONVERSION OF GAGAUZ AND MARC LETTER "A/a" WITH BREVE DUE TO CONFLICTING ROMANIZATION
    "\u04D3": "a\u0306"
    "\u0474": "V\u0307"
    "\u0475": "v\u0307"
    "\u0492": "Gh"
    "\u0493": "gh"
    # DE-ACTIVATED CONVERSION OF YAKUT "A" WITH DIAERSIS DUE TO CONFLICTING ROMANIZATION
    "\u0494": "Gh"
    # DE-ACTIVATED CONVERSION OF YAKUT "a" WITH DIAERSIS DUE TO CONFLICTING ROMANIZATION
    "\u0495": "gh"
    "\u0494": "G\u0301"
    "\u0495": "g\u0301"
    "\u049C": "G\u0307"
    "\u049D": "g\u0307"
    "\u0413": "G"
    "\u0433": "g"
    # CONVERION OF "I/i" LIGATED TO "E/e", SOME WITH MACRON (0304) AND OGONEK (0328)
    "\u0464": "I\uFE20E\uFE21\u0304"
    "\u0468": "I\uFE20E\uFE21\u0328"
    "\u0465": "i\uFE20e\uFE21\u0304"
    "\u0469": "i\uFE20e\uFE21\u0328"
    "\u0462": "I\uFE20E\uFE21"
    "\u0463": "i\uFE20e\uFE21"
    # CONVERSION OF "E/e" WITH MACRON (0304), DOT ABOVE (0307), DIAERESIS (0308), OGONEK (0328), & CARON (030C)
    "\u0404": "E\u0304"
    "\u042D": "E\u0307"
    "\u0401": "E\u0308"
    "\u0466": "E\u0328"
    "\u0454": "e\u0304"
    "\u044D": "e\u0307"
    "\u0451": "e\u0308"
    "\u0467": "e\u0328"
    "\u0416": "Zh"
    "\u0436": "zh"
    # CONVERSION OF "T/t" LIGATED OR BLENDED WITH "H/h" (all capitalization patterns)
    "\u0498": "T\uFE20H\uFE21"
    "\u0499": "t\uFE20h\uFE21"
    "\u04AA": "Th"
    "\u04AB": "th"
    # CONVERION OF "I/i" LIGATED TO "O/o" WITH MACRON (0304) AND OGONEK (0328)
    "\u046C": "I\uFE20O\uFE21\u0328"
    "\u046D": "i\uFE20o\uFE21\u0328"
    # CONVERION OF "I/i" LIGATED TO "U/u"
    "\u044E": "i\uFE20u\uFE21"
    # CONVERSION OF "I/i" WITH MACRON (0304), BREVE (0306), AND CANDRABINDU (0310)
    "\u0406": "I\u0304"
    "\u0408": "I\u0310"
    "\u0456": "i\u0304"
    "\u0458": "i\u0310"
    # CONVERSION OF REMAINING LONE "I/i"
    "\u0418": "I"
    "\u0438": "i"
    "\u0496": "J"
    "\u0497": "j"
    # DE-ACTIVATED CONVERSION OF AZERI "J" DUE TO CONFLICTING ROMANIZATION
    "\u04B8": #"J"
    # DE-ACTIVATED CONVERSION OF AZERI "j" DUE TO CONFLICTING ROMANIZATION
    "\u04B9": #"J"
    # DE-ACTIVATED CONVERSION OF TAJIK "J" DUE TO CONFLICTING ROMANIZATION
    "\u04B6": #"J"
    # DE-ACTIVATED CONVERSION OF TAJIK "j" DUE TO CONFLICTING ROMANIZATION
    "\u04B7": #"J"
    "\u0445": "kh"
    "\u046E": "K\uFE20S\uFE21"
    "\u046F": "k\uFE20s\uFE21"
    "\u04A0": "Q"
    "\u04A1": "q"
    # DE-ACTIVATED CONVERSION OF KHANTY "Q" DUE TO CONFLICTING ROMANIZATION
    "\u04C3": "Q"
    # DE-ACTIVATED CONVERSION OF KHANTY "q" DUE TO CONFLICTING ROMANIZATION
    "\u04C4": "q"
    "\u04A2": "N\uFE20G\uFE21"
    "\u04A3": "n\uFE20g\uFE21"
    # DE-ACTIVATED CONVERSION OF YAKUT "NG/ng" DUE TO CONFLICTING ROMANIZATION
    "\u04A4": #"N\uFE20G\uFE21"
    "\u04A5": #"n\uFE20g\uFE21"
    # DE-ACTIVATED CONVERSION OF CHUKCHI AND EVENKI "NG/ng" DUE TO CONFLICTING ROMANIZATION
    "\u04C7": #"N\uFE20G\uFE21"
    "\u04C8": #"n\uFE20g\uFE21"
    # CONVERION OF "O/o" WITH OR WITHOUT MACRON (0304), LIGATED TO "T/t"
    "\u047E": "O\u0304\uFE20T\uFE21"
    "\u047F": "o\u0304\uFE20t\uFE21"
    # CONVERSION OF "O/o" WITH MACRON(0304)
    "\u04EA": "O\u0304"
    "\u04EB": "o\u0304"
    # CONVERSION OF "O/o" WITH DOT ABOVE (0307) USED IN MOST CENTRAL ASIAN LANGUAGES
    "\u04E8": "O\u0307"
    "\u04E9": "o\u0307"
    # DE-ACTIVATED CONVERSION OF GAGAUZ, KOMI, AND MARI "O" WITH DOT ABOVE (0307)DUE TO CONFLICTING ROMANIZATION
    "\u04E6": #"O\u0307"
    "\u04E7": #"o\u0307"
    # CONVERSION OF REMAINING LONE "O/o"
    "\u0470": "P\uFE20S\uFE21"
    "\u0471": "p\uFE20s\uFE21"
    "\u04B4": "T\uFE20S\uFE21\u0307"
    "\u04B5": "t\uFE20s\uFE21\u0307"
    "\u0426": "T\uFE20S\uFE21"
    "\u0446": "t\uFE20s\uFE21"
    # CONVERSION OF "U/u" WITH MACRON(0304), BREVE (0306), AND DOT ABOVE (0307)
    "\u04B0": "U\u0304"
    "\u04B1": "u\u0304"
    # DE-ACTIVATED CONVERSION OF TAJIK LETTER DUE TO CONFLICTING ROMANIZATION
    "\u04EE": #"U\u0304"
    # DE-ACTIVATED CONVERSION OF TAJIK LETTER DUE TO CONFLICTING ROMANIZATION
    "\u04EF": #"U\u0304"
    "\u040E": "U\u0306"
    "\u0454": "u\u0306"
    "\u04AE": "U\u0307"
    "\u04AF": "u\u0307"
    # DE-ACTIVATED CONVERSION OF GAGAUZ AND MARI LETTER "O/o" WITH DOT ABOVE DUE TO CONFLICTING ROMANIZATION
    "\u04E6": #"U\u0307"
    "\u04E7": #"u\u0307"
    # CONVERSION OF ESKIMO AND KARAKALPAK "W/w" THAT MAPS TO THE SAME CHARACTERS AS "U/u" WITH BREVE
    "\u040E": "W"
    "\u0454": "w"
    "\u0472": "F\u0307"
    "\u0473": "f\u0307"
    "\u0444": "f"
    "\u0427": "Ch"
    # CONVERSION OF CYRILLIC PALOCHKA (ASPIRATION SIGN) USED IN MANY CENTRAL ASIAN LANGUAGES (NOT NORMALLY INITIALLY)
    "\u04BA": "H\u0307"
    "\u04BB": "h\u0307"
    # DE-ACTIVATED CONVERSION OF TAJIK AND UZBEK LETTER "H/h" WITH DOT ABOVE (0307) DUE TO CONFLICTING ROMANIZATION
    "\u04B2": "H\u0307"
    "\u04B3": "h\u0307"
    # DE-ACTIVATED CONVERSION OF ARCHAIC LETTER "H/h" WITH DOT ABOVE (0307) DUE TO CONFLICTING ROMANIZATION
    "\u04FC": "H\u0307"
    "\u04FD": "h\u0307"
    "\u04F8": "Y\u0307"
    "\u04F9": "y\u0307"
    "\u042B": "Y"
    "\u044B": "y"
    # this conversion is ambiguous - \u044C is also theoretically possible
    "\u044A": "\u02BA"