X-Git-Url: https://git.saurik.com/apple/icu.git/blobdiff_plain/9d88c94317aeac5dd26c1dbe8c2112dbe855d2b5..73c04bcfe1096173b00431f0cdc742894b15eef0:/icuSources/data/translit/InterIndic_Devanagari.txt diff --git a/icuSources/data/translit/InterIndic_Devanagari.txt b/icuSources/data/translit/InterIndic_Devanagari.txt index 5b921c4f..d04e7ec8 100644 --- a/icuSources/data/translit/InterIndic_Devanagari.txt +++ b/icuSources/data/translit/InterIndic_Devanagari.txt @@ -1,158 +1,150 @@ -#-------------------------------------------------------------------- -# Copyright (c) 1999-2004, International Business Machines -# Corporation and others. All Rights Reserved. -#-------------------------------------------------------------------- - -# InterIndic-Devanagari -#:: NFD (NFC) ; -#Rules for Decomposed characters - \ue028\ue03c > \u0929; #\ue029 - \ue030\ue03c > \u0931; #\ue031 - \ue033\ue03c > \u0934; #\ue034 - \ue015\ue03c > \u0958; #\ue058 LETTER QA (For Urdu) - \ue016\ue03c > \u0959; #\ue059 LETTER KHHA (For Urdu) - \ue017\ue03c > \u095a; #\ue05a LETTER GHHA (For Urdu) - \ue01c\ue03c > \u095b; #\ue05b LETTER ZA (For Urdu) - \ue021\ue03c > \u095c; #\ue05c LETTER DDDHA (pronounced RRA) - \ue022\ue03c > \u095d; #\ue05d LETTER RHA (pronounced RRHA) - \ue02b\ue03c > \u095e; #\ue05e LETTER FA - \ue02f\ue03c > \u095f; #\ue05f LETTER YYA - - #Decomposed compatibility transliterations - \ue012\ue057>\u0914; # FALLBACK FOR TAMIL AU - 0 > \u0966; # FALLBACK FOR TAMIL - 1 > \u0967; - - \ue055>; # FALLBACK BLOW AWAY KANNADA AND TELUGU LENGTH MARK - \ue056>; # FALLBACK BLOW AWAY KANNADA AND TELUGU AI LENGTH MARK - \ue057>; # FALLBACK BLOW AWAY TAMIL AU LENGTH MARK - - \ue001 > \u0901; # SIGN CANDRABINDU - \ue002 > \u0902; # SIGN ANUSVARA - \ue003 > \u0903; # SIGN VISARGA - \ue004 > \u0904; # SIGN SHORT A - \ue005 > \u0905; # LETTER A - \ue006 > \u0906; # LETTER AA - \ue007 > \u0907; # LETTER I - \ue008 > \u0908; # LETTER II - \ue009 > \u0909; # LETTER U - \ue00a > \u090a; # LETTER UU - \ue00b > \u090b; # LETTER VOCALIC R - \ue00c > \u090c; # LETTER VOCALIC L - \ue00d > \u090d; # LETTER CANDRA E (For representing English sounds) - \ue00e > \u090e; # LETTER SHORT E(For Southern Scripts) - \ue00f > \u090f; # LETTER E - \ue010 > \u0910; # LETTER AI - \ue011 > \u0911; # LETTER CANDRA O (For representing English sounds) - \ue012 > \u0912; # LETTER SHORT O (For Southern Scripts) - \ue013 > \u0913; # LETTER O - \ue014 > \u0914; # LETTER AU - \ue015 > \u0915; # LETTER KA - \ue016 > \u0916; # LETTER KHA - \ue017 > \u0917; # LETTER GA - \ue018 > \u0918; # LETTER GHA - \ue019 > \u0919; # LETTER NGA - \ue01a > \u091a; # LETTER CA - \ue01b > \u091b; # LETTER CHA - \ue01c > \u091c; # LETTER JA - \ue01d > \u091d; # LETTER JHA - \ue01e > \u091e; # LETTER NYA - \ue01f > \u091f; # LETTER TTA - \ue020 > \u0920; # LETTER TTHA - \ue021 > \u0921; # LETTER DDA - \ue022 > \u0922; # LETTER DDHA - \ue023 > \u0923; # LETTER NNA - \ue024 > \u0924; # LETTER TA - \ue025 > \u0925; # LETTER THA - \ue026 > \u0926; # LETTER DA - \ue027 > \u0927; # LETTER DHA - \ue028 > \u0928; # LETTER NA - \ue029 > \u0929; # LETTER NNNA - \ue02a > \u092a; # LETTER PA - \ue02b > \u092b; # LETTER PHA - \ue02c > \u092c; # LETTER BA - \ue02d > \u092d; # LETTER BHA - \ue02e > \u092e; # LETTER MA - \ue02f > \u092f; # LETTER YA - \ue030 > \u0930; # LETTER RA - \ue031 > \u0931; # LETTER RRA (Eyelash RA for Southern scripts) - #\ue031 > \u0930; - \ue032 > \u0932; # LETTER LA - \ue033 > \u0933; # LETTER LLA - \ue034 > \u0934; # LETTER LLLA (LLLA for Southern scripts) - #\ue034 > \u0933; - \ue035 > \u0935; # LETTER VA - \ue036 > \u0936; # LETTER SHA - \ue037 > \u0937; # LETTER SSA - \ue038 > \u0938; # LETTER SA - \ue039 > \u0939; # LETTER HA - \ue03c > \u093c; # SIGN NUKTA - \ue03d > \u093d; # SIGN AVAGRAHA - \ue03e > \u093e; # VOWEL SIGN AA - \ue03f > \u093f; # VOWEL SIGN I - \ue040 > \u0940; # VOWEL SIGN II - \ue041 > \u0941; # VOWEL SIGN U - \ue042 > \u0942; # VOWEL SIGN UU - \ue043 > \u0943; # VOWEL SIGN VOCALIC R - \ue044 > \u0944; # VOWEL SIGN VOCALIC RR - \ue045 > \u0945; # VOWEL SIGN CANDRA E - \ue046 > \u0946; # VOWEL SIGN SHORT E - \ue047 > \u0947; # VOWEL SIGN E - \ue048 > \u0948; # VOWEL SIGN AI - \ue049 > \u0949; # VOWEL SIGN CANDRA O - \ue04a > \u094a; # VOWEL SIGN SHORT O - \ue04b > \u094b; # VOWEL SIGN O - \ue04c > \u094c; # VOWEL SIGN AU - \ue04d > \u094d; # SIGN VIRAMA - \ue050 > \u0950; # OM - \ue051 > \u0951; # STRESS SIGN UDATTA - \ue052 > \u0952; # STRESS SIGN ANUDATTA - \ue053 > \u0953; # GRAVE ACCENT - \ue054 > \u0954; # ACUTE ACCENT - \ue058 > \u0958; # LETTER QA (For Urdu) - \ue059 > \u0959; # LETTER KHHA (For Urdu) - \ue05a > \u095a; # LETTER GHHA (For Urdu) - \ue05b > \u095b; # LETTER ZA (For Urdu) - \ue05c > \u095c; # LETTER DDDHA (pronounced RRA) - \ue05d > \u095d; # LETTER RHA (pronounced RRHA) - \ue05e > \u095e; # LETTER FA - \ue05f > \u095f; # LETTER YYA - \ue060 > \u0960; # LETTER VOCALIC RR - \ue061 > \u0961; # LETTER VOCALIC LL - \ue062 > \u0962; # VOWEL SIGN VOCALIC L - \ue063 > \u0963; # VOWEL SIGN VOCALIC LL - \ue064 > \u0964; # DANDA - \ue065 > \u0965; # DOUBLE DANDA - \ue066 > \u0966; # DIGIT ZERO - \ue067 > \u0967; # DIGIT ONE - \ue068 > \u0968; # DIGIT TWO - \ue069 > \u0969; # DIGIT THREE - \ue06a > \u096a; # DIGIT FOUR - \ue06b > \u096b; # DIGIT FIVE - \ue06c > \u096c; # DIGIT SIX - \ue06d > \u096d; # DIGIT SEVEN - \ue06e > \u096e; # DIGIT EIGHT - \ue06f > \u096f; # DIGIT NINE - - \ue070>\u0970; # ABBREVIATION SIGN - \ue071>\u0930; # LETTER RA WITH MIDDLE DIAGONAL - \ue072>\u0930; # LETTER RA WITH LOWER DIAGONAL - \ue073>; # RUPEE MARK - \ue074>\u0930\u0942; # RUPEE SIGN - \ue075>; # CURRENCY NUMERATOR ONE - \ue076>; # CURRENCY NUMERATOR TWO - \ue077>; # CURRENCY NUMERATOR THREE - \ue078>; # CURRENCY NUMERATOR FOUR - \ue079>; # CURRENCY NUMERATOR ONE LESS THAN THE DENOMINATOR - \ue07A>; # CURRENCY DENOMINATOR SIXTEEN - \ue07B>; # ISSHAR - \uE07C>; # TIPPI - \uE07D>; # ADDAK - \uE07E>; # IRI - \uE07F>; # URA - \uE080>; # EK ONKAR - \uE081>\u0935; # FALLBACK FOR ORIYA LETTER WA - -# \u0970 # UNMAPPED Devanagari-InterIndic: ABBREVIATION SIGN -# :: NFC; -# eof +# *************************************************************************** +# * +# * Copyright (C) 2004-2006, International Business Machines +# * Corporation; Unicode, Inc.; and others. All Rights Reserved. +# * +# *************************************************************************** +# File: InterIndic_Devanagari.txt +# Generated from CLDR: Thu Jul 20 16:27:15 PDT 2006 +# +\uE028\uE03C > ऩ; #\uE029 +\uE030\uE03C > ऱ; #\uE031 +\uE033\uE03C > ऴ; #\uE034 +\uE015\uE03C > क़; #\uE058 LETTER QA (For Urdu) +\uE016\uE03C > ख़; #\uE059 LETTER KHHA (For Urdu) +\uE017\uE03C > ग़; #\uE05A LETTER GHHA (For Urdu) +\uE01C\uE03C > ज़; #\uE05B LETTER ZA (For Urdu) +\uE021\uE03C > ड़; #\uE05C LETTER DDDHA (pronounced RRA) +\uE022\uE03C > ढ़; #\uE05D LETTER RHA (pronounced RRHA) +\uE02B\uE03C > फ़; #\uE05E LETTER FA +\uE02F\uE03C > य़; #\uE05F LETTER YYA +\uE012\uE057>औ; # FALLBACK FOR TAMIL AU +0 > ०; # FALLBACK FOR TAMIL +1 > १; +\uE055>; # FALLBACK BLOW AWAY KANNADA AND TELUGU LENGTH MARK +\uE056>; # FALLBACK BLOW AWAY KANNADA AND TELUGU AI LENGTH MARK +\uE057>; # FALLBACK BLOW AWAY TAMIL AU LENGTH MARK +\uE001 > \u0901; # SIGN CANDRABINDU +\uE002 > \u0902; # SIGN ANUSVARA +\uE003 > ः; # SIGN VISARGA +\uE004 > ऄ; # SIGN SHORT A +\uE005 > अ; # LETTER A +\uE006 > आ; # LETTER AA +\uE007 > इ; # LETTER I +\uE008 > ई; # LETTER II +\uE009 > उ; # LETTER U +\uE00A > ऊ; # LETTER UU +\uE00B > ऋ; # LETTER VOCALIC R +\uE00C > ऌ; # LETTER VOCALIC L +\uE00D > ऍ; # LETTER CANDRA E (For representing English sounds) +\uE00E > ऎ; # LETTER SHORT E(For Southern Scripts) +\uE00F > ए; # LETTER E +\uE010 > ऐ; # LETTER AI +\uE011 > ऑ; # LETTER CANDRA O (For representing English sounds) +\uE012 > ऒ; # LETTER SHORT O (For Southern Scripts) +\uE013 > ओ; # LETTER O +\uE014 > औ; # LETTER AU +\uE015 > क; # LETTER KA +\uE016 > ख; # LETTER KHA +\uE017 > ग; # LETTER GA +\uE018 > घ; # LETTER GHA +\uE019 > ङ; # LETTER NGA +\uE01A > च; # LETTER CA +\uE01B > छ; # LETTER CHA +\uE01C > ज; # LETTER JA +\uE01D > झ; # LETTER JHA +\uE01E > ञ; # LETTER NYA +\uE01F > ट; # LETTER TTA +\uE020 > ठ; # LETTER TTHA +\uE021 > ड; # LETTER DDA +\uE022 > ढ; # LETTER DDHA +\uE023 > ण; # LETTER NNA +\uE024 > त; # LETTER TA +\uE025 > थ; # LETTER THA +\uE026 > द; # LETTER DA +\uE027 > ध; # LETTER DHA +\uE028 > न; # LETTER NA +\uE029 > ऩ; # LETTER NNNA +\uE02A > प; # LETTER PA +\uE02B > फ; # LETTER PHA +\uE02C > ब; # LETTER BA +\uE02D > भ; # LETTER BHA +\uE02E > म; # LETTER MA +\uE02F > य; # LETTER YA +\uE030 > र; # LETTER RA +\uE031 > ऱ; # LETTER RRA (Eyelash RA for Southern scripts) +\uE032 > ल; # LETTER LA +\uE033 > ळ; # LETTER LLA +\uE034 > ऴ; # LETTER LLLA (LLLA for Southern scripts) +\uE035 > व; # LETTER VA +\uE036 > श; # LETTER SHA +\uE037 > ष; # LETTER SSA +\uE038 > स; # LETTER SA +\uE039 > ह; # LETTER HA +\uE03C > \u093C; # SIGN NUKTA +\uE03D > ऽ; # SIGN AVAGRAHA +\uE03E > ा; # VOWEL SIGN AA +\uE03F > ि; # VOWEL SIGN I +\uE040 > ी; # VOWEL SIGN II +\uE041 > \u0941; # VOWEL SIGN U +\uE042 > \u0942; # VOWEL SIGN UU +\uE043 > \u0943; # VOWEL SIGN VOCALIC R +\uE044 > \u0944; # VOWEL SIGN VOCALIC RR +\uE045 > \u0945; # VOWEL SIGN CANDRA E +\uE046 > \u0946; # VOWEL SIGN SHORT E +\uE047 > \u0947; # VOWEL SIGN E +\uE048 > \u0948; # VOWEL SIGN AI +\uE049 > ॉ; # VOWEL SIGN CANDRA O +\uE04A > ॊ; # VOWEL SIGN SHORT O +\uE04B > ो; # VOWEL SIGN O +\uE04C > ौ; # VOWEL SIGN AU +\uE04D > \u094D; # SIGN VIRAMA +\uE050 > ॐ; # OM +\uE051 > \u0951; # STRESS SIGN UDATTA +\uE052 > \u0952; # STRESS SIGN ANUDATTA +\uE053 > \u0953; # GRAVE ACCENT +\uE054 > \u0954; # ACUTE ACCENT +\uE058 > क़; # LETTER QA (For Urdu) +\uE059 > ख़; # LETTER KHHA (For Urdu) +\uE05A > ग़; # LETTER GHHA (For Urdu) +\uE05B > ज़; # LETTER ZA (For Urdu) +\uE05C > ड़; # LETTER DDDHA (pronounced RRA) +\uE05D > ढ़; # LETTER RHA (pronounced RRHA) +\uE05E > फ़; # LETTER FA +\uE05F > य़; # LETTER YYA +\uE060 > ॠ; # LETTER VOCALIC RR +\uE061 > ॡ; # LETTER VOCALIC LL +\uE062 > \u0962; # VOWEL SIGN VOCALIC L +\uE063 > \u0963; # VOWEL SIGN VOCALIC LL +\uE064 > ।; # DANDA +\uE065 > ॥; # DOUBLE DANDA +\uE066 > ०; # DIGIT ZERO +\uE067 > १; # DIGIT ONE +\uE068 > २; # DIGIT TWO +\uE069 > ३; # DIGIT THREE +\uE06A > ४; # DIGIT FOUR +\uE06B > ५; # DIGIT FIVE +\uE06C > ६; # DIGIT SIX +\uE06D > ७; # DIGIT SEVEN +\uE06E > ८; # DIGIT EIGHT +\uE06F > ९; # DIGIT NINE +\uE070>॰; # ABBREVIATION SIGN +\uE071>र; # LETTER RA WITH MIDDLE DIAGONAL +\uE072>र; # LETTER RA WITH LOWER DIAGONAL +\uE073>; # RUPEE MARK +\uE074>र\u0942; # RUPEE SIGN +\uE075>; # CURRENCY NUMERATOR ONE +\uE076>; # CURRENCY NUMERATOR TWO +\uE077>; # CURRENCY NUMERATOR THREE +\uE078>; # CURRENCY NUMERATOR FOUR +\uE079>; # CURRENCY NUMERATOR ONE LESS THAN THE DENOMINATOR +\uE07A>; # CURRENCY DENOMINATOR SIXTEEN +\uE07B>; # ISSHAR +\uE07C>; # TIPPI +\uE07D>; # ADDAK +\uE07E>; # IRI +\uE07F>; # URA +\uE080>; # EK ONKAR +\uE081>व; # FALLBACK FOR ORIYA LETTER WA +\uE082>ॽ; # Devanagari Glottal Sign +\uE083>त\u094D; # Bengali Khanda-ta