|
@@ -1,452 +1,700 @@
|
|
|
-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"
|
|
|
-
|
|
|
+general:
|
|
|
+ name: Asian (Cyrillic)
|
|
|
+ parents:
|
|
|
+ - _cyrillic_base
|
|
|
+
|
|
|
+# COMMON COMBINING CHARACTERS (always follow a base letter):
|
|
|
+# combining grave \u0300
|
|
|
+# combining acute \u0301
|
|
|
+# combining circumflex \u0302
|
|
|
+# combining tilde \u0303
|
|
|
+# combining macron \u0304
|
|
|
+# combining breve \u0306
|
|
|
+# combining dot above \u0307
|
|
|
+# combining diaeresis \u0308
|
|
|
+# combining ring above \u030A
|
|
|
+# combining double acute \u030B
|
|
|
+# combining caron (hachek) \u030C
|
|
|
+# combining candrabindu \u0310
|
|
|
+# combining dot below \u0323
|
|
|
+# combining dieresis below \u0324
|
|
|
+# combining comma below \u0326 (Romanian, Latvian, Livonian)
|
|
|
+# combining cedilla \u0327 (French, Turkish, Azeri)
|
|
|
+# combining ogonek (hook) \u0328 (Polish, Lithuanian)
|
|
|
+# combining low line \u0332
|
|
|
+# combining double low line \u0333
|
|
|
+# combining left ligature \uFE20 (Cyrillic transliteration)
|
|
|
+# combining right ligature \uFE21 (Cyrillic transliteration)
|
|
|
+# soft sign/prime (spacing) \u02B9(Cyrillic transliteration)
|
|
|
+# hard sign/double prime (spacing) \u02BA (Cyrillic transliteration)
|
|
|
+# ayn(spacing) \u02BB (Semitic and Caucasian languages)
|
|
|
+# alif (spacing) \u02BC (Semitic languages)
|
|
|
+# middle dot (space) \u00B7) (Catalan)
|
|
|
+
|
|
|
+roman_to_script:
|
|
|
+ map:
|
|
|
+ "A\uFE20E\uFE21": "\u04D4"
|
|
|
+ "A\uFE20e\uFE21": "\u04D4"
|
|
|
+ "a\uFE20e\uFE21": "\u04D5"
|
|
|
+ "A\u0306\u0323": "\u04D0"
|
|
|
+ "a\u0306\u0323": "\u04D1"
|
|
|
+ "\u00C6": "\u04D4"
|
|
|
+ "\u00E6": "\u04D5"
|
|
|
+ "A\u0306": "\u04D8"
|
|
|
+ "a\u0306": "\u04D9"
|
|
|
+ "A\u030B": "\u04DA"
|
|
|
+ "a\u030B": "\u04DB"
|
|
|
+ "A\u0308": "\u04D2"
|
|
|
+ "a\u0308": "\u04D3"
|
|
|
+ "A\u0310": "\u0518"
|
|
|
+ "a\u0310": "\u0519"
|
|
|
+
|
|
|
+ "B": "\u0411"
|
|
|
+ "b": "\u0431"
|
|
|
+
|
|
|
+ "C\u0301h\u0301": "\u04BE"
|
|
|
+ "c\u0301h\u0301": "\u04BF"
|
|
|
+ "C\u0301h": "\u04BC"
|
|
|
+ "c\u0301h": "\u04BD"
|
|
|
+ "C\u0301": "\u040B"
|
|
|
+ "c\u0301": "\u045B"
|
|
|
+ "C\u0308h": "\u04F4"
|
|
|
+ "c\u0308h": "\u04F5"
|
|
|
+ "C\u0323h": "\u04CB"
|
|
|
+ "c\u0323h": "\u04CC"
|
|
|
+
|
|
|
+ "D\u0301": "\u0502"
|
|
|
+ "d\u0301": "\u0503"
|
|
|
+ "D\u0307": "\u0500"
|
|
|
+ "d\u0307": "\u0501"
|
|
|
+ "D\uFE20c\uFE21h": "\u052C"
|
|
|
+ "d\uFE20c\uFE21h": "\u052D"
|
|
|
+ "D\uFE20z\uFE21h": "\u052A"
|
|
|
+ "d\uFE20z\uFE21h": "\u052B"
|
|
|
+ "D\uFE20Z\uFE21": "\u04E0"
|
|
|
+ "d\uFE20z\uFE21": "\u04E1"
|
|
|
+ "Dz\u030C": "\u040F"
|
|
|
+ "dz\u030C": "\u045F"
|
|
|
+ "D": "\u0414"
|
|
|
+ "d": "\u0434"
|
|
|
+
|
|
|
+ "E\u0300": "\u0400"
|
|
|
+ "e\u0300": "\u0450"
|
|
|
+ "E\u0304": "\u0404"
|
|
|
+ "e\u0304": "\u0454"
|
|
|
+ "E\u0306": "\u04D6"
|
|
|
+ "e\u0306": "\u04D7"
|
|
|
+ "E\u0306\u0323": "\u048C"
|
|
|
+ "e\u0306\u0323": "\u048D"
|
|
|
+ "E\u0307": "\u042D"
|
|
|
+ "e\u0307": "\u044D"
|
|
|
+ "E\u0308\u0323": "\u04EC"
|
|
|
+ "e\u0308\u0323": "\u04ED"
|
|
|
+ "E\u0308": "\u0401"
|
|
|
+ "e\u0308": "\u0451"
|
|
|
+ "E\u0328": "\u0466"
|
|
|
+ "e\u0328": "\u0467"
|
|
|
+
|
|
|
+ "F\u0307": "\u0472"
|
|
|
+ "f\u0307": "\u0473"
|
|
|
+ "F": "\u0424"
|
|
|
+ "f": "\u0444"
|
|
|
+
|
|
|
+ "Gh\u0327": "\u04FA"
|
|
|
+ "gh\u0327": "\u04FB"
|
|
|
+ "Gh": "\u0492"
|
|
|
+ "gh": "\u0493"
|
|
|
+ "G\u0301": "\u0403"
|
|
|
+ "g\u0301": "\u0453"
|
|
|
+ "G\u0306": "\u0490"
|
|
|
+ "g\u0306": "\u0491"
|
|
|
+ "G\u0307": "\u049C"
|
|
|
+ "g\u0307": "\u049D"
|
|
|
+ "G\u0323": "\u04F6"
|
|
|
+ "g\u0323": "\u04F7"
|
|
|
+ "G\u0327": "\u0494"
|
|
|
+ "g\u0327": "\u0495"
|
|
|
+
|
|
|
+ "H\u0304": "\u04FE"
|
|
|
+ "h\u0304": "\u04FF"
|
|
|
+ "H\u0327": "\u04FC"
|
|
|
+ "h\u0327": "\u04FD"
|
|
|
+ "H\u0307": "\u04BA"
|
|
|
+ "h\u0307": "\u04BB"
|
|
|
+ "H\u0308": "\u04C0"
|
|
|
+ "h\u0308": "\u04CF"
|
|
|
+
|
|
|
+ "I\u0300": "\u040D"
|
|
|
+ "i\u0300": "\u045D"
|
|
|
+ "I\u0304\u0323": "\u04E2"
|
|
|
+ "i\u0304\u0323": "\u04E3"
|
|
|
+ "I\u0304": "\u0406"
|
|
|
+ "i\u0304": "\u0456"
|
|
|
+ "I\u0306\u0323": "\u048A"
|
|
|
+ "i\u0306\u0323": "\u048B"
|
|
|
+ "I\u0306": "\u0419"
|
|
|
+ "i\u0306": "\u0439"
|
|
|
+ "I\u0308\u0323": "\u04E4"
|
|
|
+ "i\u0308\u0323": "\u04E5"
|
|
|
+ "I\u0308": "\u0407"
|
|
|
+ "i\u0308": "\u0457"
|
|
|
+ "I\u0310": "\u0408"
|
|
|
+ "i\u0310": "\u0458"
|
|
|
+
|
|
|
+ "I\uFE20A\uFE21": "\u042F"
|
|
|
+ "i\uFE20a\uFE21": "\u044F"
|
|
|
+ "A": "\u0410"
|
|
|
+ "a": "\u0430"
|
|
|
+
|
|
|
+ "I\uFE20E\uFE21\u0304": "\u0464"
|
|
|
+ "i\uFE20e\uFE21\u0304": "\u0465"
|
|
|
+ "I\uFE20E\uFE21\u0328": "\u0468"
|
|
|
+ "i\uFE20e\uFE21\u0328": "\u0469"
|
|
|
+ "I\uFE20E\uFE21": "\u0462"
|
|
|
+ "i\uFE20e\uFE21": "\u0463"
|
|
|
+ "E": "\u0415"
|
|
|
+ "e": "\u0435"
|
|
|
+
|
|
|
+ "I\uFE20O\uFE21\u0328": "\u046C"
|
|
|
+ "i\uFE20o\uFE21\u0328": "\u046D"
|
|
|
+ "I\uFE20U\uFE21": "\u042E"
|
|
|
+ "i\uFE20u\uFE21": "\u044E"
|
|
|
+ "I": "\u0418"
|
|
|
+ "i": "\u0438"
|
|
|
+
|
|
|
+ "J\u0304": "\u04B8"
|
|
|
+ "j\u0304": "\u04B9"
|
|
|
+ "J\u0306": "\u04C1"
|
|
|
+ "j\u0306": "\u04C2"
|
|
|
+ "J\u0302": "\u04B6"
|
|
|
+ "j\u0302": "\u04B7"
|
|
|
+ "J\u0308": "\u04DC"
|
|
|
+ "j\u0308": "\u04DD"
|
|
|
+
|
|
|
+ "K\u0300": "\u051E"
|
|
|
+ "k\u0300": "\u051F"
|
|
|
+ "K\u0301": "\u040C"
|
|
|
+ "k\u0301": "\u045C"
|
|
|
+ "K\uFE20H\uFE21": "\u04B2"
|
|
|
+ "k\uFE20h\uFE21": "\u04B3"
|
|
|
+ "Kh": "\u0425"
|
|
|
+ "kh": "\u0445"
|
|
|
+ "K\uFE20S\uFE21": "\u046E"
|
|
|
+ "k\uFE20s\uFE21": "\u046F"
|
|
|
+ "K": "\u041A"
|
|
|
+ "k": "\u043A"
|
|
|
+
|
|
|
+ "Lj": "\u0409"
|
|
|
+ "lj": "\u0459"
|
|
|
+ "Lkh\u0307": "\u0514"
|
|
|
+ "lkh\u0307": "\u0515"
|
|
|
+ "L\u0301": "\u0508"
|
|
|
+ "l\u0301": "\u0509"
|
|
|
+ "L\u0321": "\u04C5"
|
|
|
+ "l\u0326": "\u04C6"
|
|
|
+ "L\u0323": "\u052E"
|
|
|
+ "l\u0323": "\u052F"
|
|
|
+ "L\u0327": "\u0512"
|
|
|
+ "l\u0327": "\u0513"
|
|
|
+ "L\u0324": "\u0520"
|
|
|
+ "l\u0324": "\u0521"
|
|
|
+ "L": "\u041B"
|
|
|
+ "l": "\u043B"
|
|
|
+
|
|
|
+ "M\u0323": "\u04CD"
|
|
|
+ "m\u0323": "\u04CE"
|
|
|
+ "M": "\u041C"
|
|
|
+ "m": "\u043C"
|
|
|
+
|
|
|
+ "Nj": "\u040A"
|
|
|
+ "nj": "\u045A"
|
|
|
+ "N\u0301G\u0300": "\u04A4"
|
|
|
+ "n\u0301g\u0300": "\u04A5"
|
|
|
+ "N\u0301": "\u050A"
|
|
|
+ "n\u0301": "\u050B"
|
|
|
+ "N\u0326": "\u0528"
|
|
|
+ "n\u0326": "\u0529"
|
|
|
+ "N\u0327": "\u0522"
|
|
|
+ "n\u0327": "\u0523"
|
|
|
+ "N\uFE20\u0323G\uFE21": "\u04C9"
|
|
|
+ "n\uFE20\u0323g\uFE21": "\u04CA"
|
|
|
+ "N\uFE20\u0327G\uFE21": "\u04C7"
|
|
|
+ "n\uFE20\u0327g\uFE21": "\u04C8"
|
|
|
+ "N\uFE20G\uFE21": "\u04A2"
|
|
|
+ "n\uFE20g\uFE21": "\u04A3"
|
|
|
+ "No\u0332": "\u2116"
|
|
|
+ "N": "\u041D"
|
|
|
+ "n": "\u043D"
|
|
|
+
|
|
|
+ "G": "\u0413"
|
|
|
+ "g": "\u0433"
|
|
|
+
|
|
|
+ "J": "\u0496"
|
|
|
+ "j": "\u0497"
|
|
|
+
|
|
|
+ "O\u0303": "\u047C"
|
|
|
+ "o\u0303": "\u047D"
|
|
|
+ "O\u0304\u0323": "\u047A"
|
|
|
+ "o\u0304\u0323": "\u047B"
|
|
|
+ "O\u0304\uFE20T\uFE21": "\u047E"
|
|
|
+ "o\u0304\uFE20t\uFE21": "\u047F"
|
|
|
+ "O\u0304\u0324": "\u0460"
|
|
|
+ "o\u0304\u0324": "\u0461"
|
|
|
+ "O\u0304": "\u04EA"
|
|
|
+ "o\u0304": "\u04EB"
|
|
|
+ "O\u0307": "\u04E8"
|
|
|
+ "o\u0307": "\u04E9"
|
|
|
+ "O\u0308": "\u04E6"
|
|
|
+ "o\u0308": "\u04E7"
|
|
|
+ "O\u0328": "\u046A"
|
|
|
+ "o\u0328": "\u046B"
|
|
|
+ "O\uFE20u\uFE21": "\u0478"
|
|
|
+ "o\uFE20u\uFE21": "\u0479"
|
|
|
+ "O": "\u041E"
|
|
|
+ "o": "\u043E"
|
|
|
+
|
|
|
+ "Ph": "\u04A6"
|
|
|
+ "ph": "\u04A7"
|
|
|
+ "P\u0323": "\u0524"
|
|
|
+ "p\u0323": "\u0525"
|
|
|
+ "P\uFE20S\uFE21": "\u0470"
|
|
|
+ "p\uFE20s\uFE21": "\u0471"
|
|
|
+ "P": "\u041F"
|
|
|
+ "p": "\u043F"
|
|
|
+
|
|
|
+ "Q\u0300": "\u04A0"
|
|
|
+ "q\u0300": "\u04A1"
|
|
|
+ "Q\u0302": "\u0480"
|
|
|
+ "q\u0302": "\u0481"
|
|
|
+ "Q\u0304": "\u049E"
|
|
|
+ "q\u0304": "\u049F"
|
|
|
+ "Q\u0307": "\u04C3"
|
|
|
+ "q\u0307": "\u04C4"
|
|
|
+ "Q\u0308": "\u051A"
|
|
|
+ "q\u0308": "\u051B"
|
|
|
+ "Q": "\u049A"
|
|
|
+ "q": "\u049B"
|
|
|
+
|
|
|
+ "Rkh\u0307": "\u0516"
|
|
|
+ "rkh\u0307": "\u0517"
|
|
|
+ "R\u0306": "\u048E"
|
|
|
+ "r\u0306": "\u048F"
|
|
|
+ "R": "\u0420"
|
|
|
+ "r": "\u0440"
|
|
|
+
|
|
|
+ "Shch": "\u0429"
|
|
|
+ "shch": "\u0449"
|
|
|
+ "Sh\u0323": "\u0526"
|
|
|
+ "sh\u0323": "\u0527"
|
|
|
+ "Sh": "\u0428"
|
|
|
+ "sh": "\u0448"
|
|
|
+ "S\u0301": "\u050C"
|
|
|
+ "s\u0301": "\u050D"
|
|
|
+ "S\u0307": "\u0405"
|
|
|
+ "s\u0307": "\u0455"
|
|
|
+
|
|
|
+ "Ch": "\u0427"
|
|
|
+ "ch": "\u0447"
|
|
|
+ "C": "\u0426"
|
|
|
+ "c": "\u0446"
|
|
|
+
|
|
|
+ "Th": "\u04AA"
|
|
|
+ "th": "\u04AB"
|
|
|
+ "T\u0301": "\u050E"
|
|
|
+ "t\u0301": "\u050F"
|
|
|
+ "T\u0327": "\u04AC"
|
|
|
+ "t\u0327": "\u04AD"
|
|
|
+ "T\uFE20H\uFE21": "\u0498"
|
|
|
+ "t\uFE20h\uFE21": "\u0499"
|
|
|
+ "T\uFE20S\uFE21": "\u0426"
|
|
|
+ "t\uFE20s\uFE21": "\u0446"
|
|
|
+ "T\uFE20S\uFE21\u0307": "\u04B4"
|
|
|
+ "t\uFE20s\uFE21\u0307": "\u04B5"
|
|
|
+
|
|
|
+ "S": "\u0421"
|
|
|
+ "s": "\u0441"
|
|
|
+
|
|
|
+ "T": "\u0422"
|
|
|
+ "t": "\u0442"
|
|
|
+
|
|
|
+ "U\u0302": "\u04B0"
|
|
|
+ "u\u0302": "\u04B1"
|
|
|
+ "U\u0304": "\u04EE"
|
|
|
+ "u\u0304": "\u04EF"
|
|
|
+ "U\u0306": "\u040E"
|
|
|
+ "u\u0306": "\u045E"
|
|
|
+ "U\u0307": "\u04AE"
|
|
|
+ "u\u0307": "\u04AF"
|
|
|
+ "U\u0308": "\u04F0"
|
|
|
+ "u\u0308": "\u04F1"
|
|
|
+ "U\u030B": "\u04F2"
|
|
|
+ "u\u030B": "\u04F3"
|
|
|
+ "U": "\u0423"
|
|
|
+ "u": "\u0443"
|
|
|
+
|
|
|
+ "V\u0307": "\u0474"
|
|
|
+ "v\u0307": "\u0475"
|
|
|
+ "V\u0308": "\u0476"
|
|
|
+ "v\u0308": "\u0477"
|
|
|
+ "V": "\u0412"
|
|
|
+ "v": "\u0432"
|
|
|
+
|
|
|
+ "W\u0308": "\u051C"
|
|
|
+ "w\u0308": "\u051D"
|
|
|
+ "W": "\u04A8"
|
|
|
+ "w": "\u04A9"
|
|
|
+
|
|
|
+ "X": "\u0058"
|
|
|
+ "x": "\u0078"
|
|
|
+
|
|
|
+ "Y\u0307": "\u0474"
|
|
|
+ "y\u0307": "\u0475"
|
|
|
+ "Y\u0308": "\u04F8"
|
|
|
+ "y\u0308": "\u04F9"
|
|
|
+ "Y": "\u042B"
|
|
|
+ "y": "\u044B"
|
|
|
+
|
|
|
+ "Zh": "\u0416"
|
|
|
+ "zh": "\u0436"
|
|
|
+ "Z\u0301": "\u0504"
|
|
|
+ "z\u0301": "\u0505"
|
|
|
+ "Z\u0307": "\u0510"
|
|
|
+ "z\u0307": "\u0511"
|
|
|
+ "Z\u0308": "\u04DE"
|
|
|
+ "z\u0308": "\u04DF"
|
|
|
+ "Z\u0327": "\u0506"
|
|
|
+ "z\u0327": "\u0507"
|
|
|
+ "Z": "\u0417"
|
|
|
+ "z": "\u0437"
|
|
|
+
|
|
|
+ "H": "\u0413"
|
|
|
+ "h": "\u0433"
|
|
|
+
|
|
|
+ "\u0110": "\u0402"
|
|
|
+ "\u0111": "\u0452"
|
|
|
+ "\u02B9\u0333": "\u042C"
|
|
|
+ "\u02B9": "\u044C"
|
|
|
+ "\u02BA\u0333": "\u042A"
|
|
|
+ "\u02BA": "\u044A"
|
|
|
+ "\u0303": "\u0487"
|
|
|
+ "\u0311": "\u0484"
|
|
|
+ "\u0313": "\u0486"
|
|
|
+ "\u0314": "\u0485"
|
|
|
+ "\u007E": "\u0483"
|
|
|
+ "(|)": "\u0482"
|
|
|
+ "(^)": "\u0488"
|
|
|
+ "(')": "\u0489"
|
|
|
+
|
|
|
+ "\u003C\u003C": "\u00AB"
|
|
|
+ "\u003E\u003E": "\u00BB"
|
|
|
+
|
|
|
+script_to_roman:
|
|
|
+ map:
|
|
|
+
|
|
|
+ "\u00AB": """
|
|
|
+ "\u00BB": """
|
|
|
+ "\u2116": "No\u0332"
|
|
|
+ "\u0400": "E\u0300"
|
|
|
+ "\u0401": "E\u0308"
|
|
|
+ "\u0402": "\u0110"
|
|
|
+ "\u0403": "G\u0301"
|
|
|
+ "\u0404": "E\u0304"
|
|
|
+ "\u0405": "S\u0307"
|
|
|
+ "\u0406": "I\u0304"
|
|
|
+ "\u0407": "I\u0308"
|
|
|
+ "\u0408": "I\u0310"
|
|
|
+ "\u0409": "Lj"
|
|
|
+ "\u040A": "Nj"
|
|
|
+ "\u040B": "C\u0301"
|
|
|
+ "\u040C": "K\u0301"
|
|
|
+ "\u040D": "I\u0300"
|
|
|
+ "\u040E": "U\u0306"
|
|
|
+ "\u040F": "Dz\u030C"
|
|
|
+ "\u0410": "A"
|
|
|
+ "\u0411": "B"
|
|
|
+ "\u0412": "V"
|
|
|
+ "\u0413": "G"
|
|
|
+ "\u0414": "D"
|
|
|
+ "\u0415": "E"
|
|
|
+ "\u0416": "Zh"
|
|
|
+ "\u0417": "Z"
|
|
|
+ "\u0418": "I"
|
|
|
+ "\u0419": "I\u0306"
|
|
|
+ "\u041A": "K"
|
|
|
+ "\u041B": "L"
|
|
|
+ "\u041C": "M"
|
|
|
+ "\u041D": "N"
|
|
|
+ "\u041E": "O"
|
|
|
+ "\u041F": "P"
|
|
|
+ "\u0420": "R"
|
|
|
+ "\u0421": "S"
|
|
|
+ "\u0422": "T"
|
|
|
+ "\u0423": "U"
|
|
|
+ "\u0424": "F"
|
|
|
+ "\u0425": "Kh"
|
|
|
+ "\u0426": "T\uFE20S\uFE21"
|
|
|
+ "\u0427": "Ch"
|
|
|
+ "\u0428": "Sh"
|
|
|
+ "\u0429": "Shch"
|
|
|
+ "\u042A": "\u02BA\u0333"
|
|
|
+ "\u042B": "Y"
|
|
|
+ "\u042C": "\u02B9\u0333"
|
|
|
+ "\u042D": "E\u0307"
|
|
|
+ "\u042E": "I\uFE20U\uFE21"
|
|
|
+ "\u042F": "I\uFE20A\uFE21"
|
|
|
+ "\u0430": "a"
|
|
|
+ "\u0431": "b"
|
|
|
+ "\u0432": "v"
|
|
|
+ "\u0433": "g"
|
|
|
+ "\u0434": "d"
|
|
|
+ "\u0435": "e"
|
|
|
+ "\u0436": "zh"
|
|
|
+ "\u0437": "z"
|
|
|
+ "\u0438": "i"
|
|
|
+ "\u0439": "i\u0306"
|
|
|
+ "\u043A": "k"
|
|
|
+ "\u043B": "l"
|
|
|
+ "\u043C": "m"
|
|
|
+ "\u043D": "n"
|
|
|
+ "\u043E": "o"
|
|
|
+ "\u043F": "p"
|
|
|
+ "\u0440": "r"
|
|
|
+ "\u0441": "s"
|
|
|
+ "\u0442": "t"
|
|
|
+ "\u0443": "u"
|
|
|
+ "\u0444": "f"
|
|
|
+ "\u0445": "kh"
|
|
|
+ "\u0446": "t\uFE20s\uFE21"
|
|
|
+ "\u0447": "ch"
|
|
|
+ "\u0448": "sh"
|
|
|
+ "\u0449": "shch"
|
|
|
+ "\u044A": "\u02BA"
|
|
|
+ "\u044B": "y"
|
|
|
+ "\u044C": "\u02B9"
|
|
|
+ "\u044D": "e\u0307"
|
|
|
+ "\u044E": "i\uFE20u\uFE21"
|
|
|
+ "\u044F": "i\uFE20a\uFE21"
|
|
|
+ "\u0450": "e\u0300"
|
|
|
+ "\u0451": "e\u0308"
|
|
|
+ "\u0452": "\u0111"
|
|
|
+ "\u0453": "g\u0301"
|
|
|
+ "\u0454": "e\u0304"
|
|
|
+ "\u0455": "s\u0307"
|
|
|
+ "\u0456": "i\u0304"
|
|
|
+ "\u0457": "i\u0308"
|
|
|
+ "\u0458": "i\u0310"
|
|
|
+ "\u0459": "lj"
|
|
|
+ "\u045A": "nj"
|
|
|
+ "\u045B": "c\u0301"
|
|
|
+ "\u045C": "k\u0301"
|
|
|
+ "\u045D": "i\u0300"
|
|
|
+ "\u045E": "u\u0306"
|
|
|
+ "\u045F": "dz\u030C"
|
|
|
+ "\u0460": "O\u0304\u0324"
|
|
|
+ "\u0461": "o\u0304\u0324"
|
|
|
+ "\u0462": "I\uFE20E\uFE21"
|
|
|
+ "\u0463": "i\uFE20e\uFE21"
|
|
|
+ "\u0464": "I\uFE20E\uFE21\u0304"
|
|
|
+ "\u0465": "i\uFE20e\uFE21\u0304"
|
|
|
+ "\u0466": "E\u0328"
|
|
|
+ "\u0467": "e\u0328"
|
|
|
+ "\u0468": "I\uFE20E\uFE21\u0328"
|
|
|
+ "\u0469": "i\uFE20e\uFE21\u0328"
|
|
|
+ "\u046A": "O\u0328"
|
|
|
+ "\u046B": "o\u0328"
|
|
|
+ "\u046C": "I\uFE20O\uFE21\u0328"
|
|
|
+ "\u046D": "i\uFE20o\uFE21\u0328"
|
|
|
+ "\u046E": "K\uFE20S\uFE21"
|
|
|
+ "\u046F": "k\uFE20s\uFE21"
|
|
|
+ "\u0470": "P\uFE20S\uFE21"
|
|
|
+ "\u0471": "p\uFE20s\uFE21"
|
|
|
+ "\u0472": "F\u0307"
|
|
|
+ "\u0473": "f\u0307"
|
|
|
+ "\u0474": "V\u0307"
|
|
|
+ "\u0475": "v\u0307"
|
|
|
+ "\u0476": "V\u0308"
|
|
|
+ "\u0477": "v\u0308"
|
|
|
+ "\u0478": "O\uFE20u\uFE21"
|
|
|
+ "\u0479": "o\uFE20u\uFE21"
|
|
|
+ "\u047A": "O\u0304\u0323"
|
|
|
+ "\u047B": "o\u0304\u0323"
|
|
|
+ "\u047C": "O\u0303"
|
|
|
+ "\u047D": "o\u0303"
|
|
|
+ "\u047E": "O\u0304\uFE20T\uFE21"
|
|
|
+ "\u047F": "o\u0304\uFE20t\uFE21"
|
|
|
+ "\u0480": "Q\u0302"
|
|
|
+ "\u0481": "q\u0302"
|
|
|
+ "\u0482": "(|)"
|
|
|
+ "\u0483": "\u007E"
|
|
|
+ "\u0484": "\u0311"
|
|
|
+ "\u0485": "\u0314"
|
|
|
+ "\u0486": "\u0313"
|
|
|
+ "\u0487": "\u0303"
|
|
|
+ "\u0488": "(^)"
|
|
|
+ "\u0489": "(')"
|
|
|
+ "\u048A": "I\u0306\u0323"
|
|
|
+ "\u048B": "i\u0306\u0323"
|
|
|
+ "\u048C": "E\u0306\u0323"
|
|
|
+ "\u048D": "e\u0306\u0323"
|
|
|
+ "\u048E": "R\u0306"
|
|
|
+ "\u048F": "r\u0306"
|
|
|
+ "\u0490": "G\u0306"
|
|
|
+ "\u0491": "g\u0306"
|
|
|
+ "\u0492": "Gh"
|
|
|
+ "\u0493": "gh"
|
|
|
+ "\u0494": "G\u0327"
|
|
|
+ "\u0495": "g\u0327"
|
|
|
+ "\u0496": "J"
|
|
|
+ "\u0497": "j"
|
|
|
+ "\u0498": "T\uFE20H\uFE21"
|
|
|
+ "\u0499": "t\uFE20h\uFE21"
|
|
|
+ "\u049A": "Q"
|
|
|
+ "\u049B": "q"
|
|
|
+ "\u049C": "G\u0307"
|
|
|
+ "\u049D": "g\u0307"
|
|
|
+ "\u049E": "Q\u0304"
|
|
|
+ "\u049F": "q\u0304"
|
|
|
+ "\u04A0": "Q\u0300"
|
|
|
+ "\u04A1": "q\u0300"
|
|
|
+ "\u04A2": "N\uFE20G\uFE21"
|
|
|
+ "\u04A3": "n\uFE20g\uFE21"
|
|
|
+ "\u04A4": "N\u0301G\u0300"
|
|
|
+ "\u04A5": "n\u0301g\u0300"
|
|
|
+ "\u04A6": "Ph"
|
|
|
+ "\u04A7": "ph"
|
|
|
+ "\u04A8": "W"
|
|
|
+ "\u04A9": "w"
|
|
|
+ "\u04AA": "Th"
|
|
|
+ "\u04AB": "th"
|
|
|
+ "\u04AC": "T\u0327"
|
|
|
+ "\u04AD": "t\u0327"
|
|
|
+ "\u04AE": "U\u0307"
|
|
|
+ "\u04AF": "u\u0307"
|
|
|
+ "\u04B0": "U\u0302"
|
|
|
+ "\u04B1": "u\u0302"
|
|
|
+ "\u04B2": "K\uFE20H\uFE21"
|
|
|
+ "\u04B3": "k\uFE20h\uFE21"
|
|
|
+ "\u04B4": "T\uFE20S\uFE21\u0307"
|
|
|
+ "\u04B5": "t\uFE20s\uFE21\u0307"
|
|
|
+ "\u04B6": "J\u0302"
|
|
|
+ "\u04B7": "j\u0302"
|
|
|
+ "\u04B8": "J\u0304"
|
|
|
+ "\u04B9": "j\u0304"
|
|
|
+ "\u04BA": "H\u0307"
|
|
|
+ "\u04BB": "h\u0307"
|
|
|
+ "\u04BC": "C\u0301h"
|
|
|
+ "\u04BD": "c\u0301h"
|
|
|
+ "\u04BE": "C\u0301h\u0301"
|
|
|
+ "\u04BF": "c\u0301h\u0301"
|
|
|
+ "\u04C0": "H\u0308"
|
|
|
+ "\u04C1": "J\u0306"
|
|
|
+ "\u04C2": "j\u0306"
|
|
|
+ "\u04C3": "Q\u0307"
|
|
|
+ "\u04C4": "q\u0307"
|
|
|
+ "\u04C5": "L\u0326"
|
|
|
+ "\u04C6": "l\u0326"
|
|
|
+ "\u04C7": "N\uFE20\u0327G\uFE21"
|
|
|
+ "\u04C8": "n\uFE20\u0327g\uFE21"
|
|
|
+ "\u04C9": "N\uFE20\u0323G\uFE21"
|
|
|
+ "\u04CA": "n\uFE20\u0323g\uFE21"
|
|
|
+ "\u04CB": "C\u0323h"
|
|
|
+ "\u04CC": "c\u0323h"
|
|
|
+ "\u04CD": "M\u0323"
|
|
|
+ "\u04CE": "m\u0323"
|
|
|
+ "\u04CF": "h\u0308"
|
|
|
+ "\u04D0": "A\u0306\u0323"
|
|
|
+ "\u04D1": "a\u0306\u0323"
|
|
|
+ "\u04D2": "A\u0308"
|
|
|
+ "\u04D3": "a\u0308"
|
|
|
+ "\u04D4": "\u00C6"
|
|
|
+ "\u04D5": "\u00E6"
|
|
|
+ "\u04D6": "E\u0306"
|
|
|
+ "\u04D7": "e\u0306"
|
|
|
+ "\u04D8": "A\u0306"
|
|
|
+ "\u04D9": "a\u0306"
|
|
|
+ "\u04DA": "A\u030B"
|
|
|
+ "\u04DB": "a\u030B"
|
|
|
+ "\u04DC": "J\u0308"
|
|
|
+ "\u04DD": "j\u0308"
|
|
|
+ "\u04DE": "Z\u0308"
|
|
|
+ "\u04DF": "z\u0308"
|
|
|
+ "\u04E0": "D\uFE20Z\uFE21"
|
|
|
+ "\u04E1": "d\uFE20z\uFE21"
|
|
|
+ "\u04E2": "I\u0304\u0323"
|
|
|
+ "\u04E3": "i\u0304\u0323"
|
|
|
+ "\u04E4": "I\u0308\u0323"
|
|
|
+ "\u04E5": "i\u0308\u0323"
|
|
|
+ "\u04E6": "O\u0308"
|
|
|
+ "\u04E7": "o\u0308"
|
|
|
+ "\u04E8": "O\u0307"
|
|
|
+ "\u04E9": "o\u0307"
|
|
|
+ "\u04EA": "O\u0304"
|
|
|
+ "\u04EB": "o\u0304"
|
|
|
+ "\u04EC": "E\u0308\u0323"
|
|
|
+ "\u04ED": "e\u0308\u0323"
|
|
|
+ "\u04EE": "U\u0304"
|
|
|
+ "\u04EF": "u\u0304"
|
|
|
+ "\u04F0": "U\u0308"
|
|
|
+ "\u04F1": "u\u0308"
|
|
|
+ "\u04F2": "U\u030B"
|
|
|
+ "\u04F3": "u\u030B"
|
|
|
+ "\u04F4": "C\u0308h"
|
|
|
+ "\u04F5": "c\u0308h"
|
|
|
+ "\u04F6": "G\u0323"
|
|
|
+ "\u04F7": "g\u0323"
|
|
|
+ "\u04F8": "Y\u0308"
|
|
|
+ "\u04F9": "y\u0308"
|
|
|
+ "\u04FA": "Gh\u0327"
|
|
|
+ "\u04FB": "gh\u0327"
|
|
|
+ "\u04FC": "H\u0327"
|
|
|
+ "\u04FD": "h\u0327"
|
|
|
+ "\u04FE": "H\u0304"
|
|
|
+ "\u04FF": "h\u0304"
|
|
|
+ "\u0500": "D\u0307"
|
|
|
+ "\u0501": "d\u0307"
|
|
|
+ "\u0502": "D\u0301"
|
|
|
+ "\u0503": "d\u0301"
|
|
|
+ "\u0504": "Z\u0301"
|
|
|
+ "\u0505": "z\u0301"
|
|
|
+ "\u0506": "Z\u0327"
|
|
|
+ "\u0507": "z\u0327"
|
|
|
+ "\u0508": "L\u0301"
|
|
|
+ "\u0509": "l\u0301"
|
|
|
+ "\u050A": "N\u0301"
|
|
|
+ "\u050B": "n\u0301"
|
|
|
+ "\u050C": "S\u0301"
|
|
|
+ "\u050D": "s\u0301"
|
|
|
+ "\u050E": "T\u0301"
|
|
|
+ "\u050F": "t\u0301"
|
|
|
+ "\u0510": "Z\u0307"
|
|
|
+ "\u0511": "z\u0307"
|
|
|
+ "\u0512": "L\u0327"
|
|
|
+ "\u0513": "l\u0327"
|
|
|
+ "\u0514": "Lkh\u0307"
|
|
|
+ "\u0515": "lkh\u0307"
|
|
|
+ "\u0516": "Rkh\u0307"
|
|
|
+ "\u0517": "rkh\u0307"
|
|
|
+ "\u0518": "A\u0310"
|
|
|
+ "\u0519": "a\u0310"
|
|
|
+ "\u051A": "Q\u0308"
|
|
|
+ "\u051B": "q\u0308"
|
|
|
+ "\u051C": "W\u0308"
|
|
|
+ "\u051D": "w\u0308"
|
|
|
+ "\u051E": "K\u0300"
|
|
|
+ "\u051F": "k\u0300"
|
|
|
+ "\u0520": "L\u0324"
|
|
|
+ "\u0521": "l\u0324"
|
|
|
+ "\u0522": "N\u0327"
|
|
|
+ "\u0523": "n\u0327"
|
|
|
+ "\u0524": "P\u0323"
|
|
|
+ "\u0525": "p\u0323"
|
|
|
+ "\u0526": "Sh\u0323"
|
|
|
+ "\u0527": "sh\u0323"
|
|
|
+ "\u0528": "N\u0326"
|
|
|
+ "\u0529": "n\u0326"
|
|
|
+ "\u052A": "D\uFE20z\uFE21h"
|
|
|
+ "\u052B": "d\uFE20z\uFE21h"
|
|
|
+ "\u052C": "D\uFE20c\uFE21h"
|
|
|
+ "\u052D": "d\uFE20c\uFE21h"
|
|
|
+ "\u052E": "L\u0323"
|
|
|
+ "\u052F": "l\u0323"
|