src/com/ibm/icu/dev/tool/translit/indicExceptions.txt

/**
 *******************************************************************************
 * Copyright (C) 2002-2004, International Business Machines Corporation and    *
 * others. All Rights Reserved.                                                *
 *******************************************************************************
 */

/* Reserved in all 9 scripts */

/*
   These codepoints are marked RESERVED in all 9 indic scripts.
   There should not be any transliteration work on these codepoints, 
   if they are ever encountered.  Ignore these codepoints.

   Common reserved codepoints in ALL 9 scripts : (offset)
   00, 04, 
   3A, 3B, 
   4E, 4F, 
   7B, 7C, 7D, 7E, 7F
*/

/* Script-specific */
/*
   These codepoints are specific to their respective script.
   Transliteration of these codepoints from one script to another is meaningless.

   For example,
      \u0B70 (Oriya) and \u0BF0 (Tamil) are non-reserved codepoints within each script.
      On transliterating \u0B70 from Oriya to Tamil, we will get \u0BF0.
      But \u0B70 in Oriya represents ISSHAR, whereas \u0BF0 in Tamil represents NUMBER TEN.

   \u0970 Devanagari abbreviation sign

   \u09F0 Bengali letter RA with middle diagonal (Assamese)
   \u09F1 Bengali letter RA with lower diagonal 
          (=Bengali letter VA with lower diagonal, Assamese)
   \u09F2 Bengali rupee mark
   \u09F3 Bengali rupee sign
   \u09F4 Bengali currency numerator one
   \u09F5 Bengali currency numerator two
   \u09F6 Bengali currency numerator three
   \u09F7 Bengali currency numerator four
   \u09F8 Bengali currency numerator one less than the denominator
   \u09F9 Bengali currency denominator sixteen
   \u09FA Bengali isshar

   \u0A70 Gurmukhi tippi (nasalization)
   \u0A71 Gurmukhi addak (doubles following consonant)
   \u0A72 Gurmukhi iri (base for vowels)
   \u0A73 Gurmukhi ura (base for vowels)
   \u0A74 Gurmukhi ek onkar (God is One)

   \u0B70 Oriya isshar

   \u0BF0 Tamil number ten
   \u0BF1 Tamil number one hundred
   \u0BF2 Tamil number one thousand
*/



/*****************************************************************************/
/*  NOTE : <unknown> code will map back to itself                            */
/*         till we find a good match                                         */
/*****************************************************************************/



/*****************************************************************************/
/* Devanagari                                                                */
/*****************************************************************************/

"\u0955>\u0955;"  // <unknown> Length Mark - Kannada (\u0CD5), Telugu (\u0C55)
"\u0956>\u0948;"  // AI Length Mark -> Devanagari Vowel Sign AI
"\u0957>\u094C;"  // AU Length Mark -> Devanagari Vowel Sign AU



/*****************************************************************************/
/* Bengali                                                                   */
/*****************************************************************************/

"\u098D>\u098D;"  // <unknown> independent vowel Candra E
"\u098E>\u098F;"  // Letter Short E -> Letter E
"\u0991>\u0993;"  // Letter Candra O -> Letter O
"\u0992>\u0993;"  // Letter Short O -> Letter O
"\u09A9>\u09A8;"  // Letter NNNA -> Letter NA
"\u09B1>\u09B0;"  // Letter RRA -> Letter RA
"\u09B3>\u09B2;"  // Letter LLA -> Letter LA
"\u09B4>\u09B2;"  // Letter LLLA -> Letter LA
"\u09B5>\u09AC;"  // Letter VA -> Letter BA
"\u09BD>\u09BD;"  // <unknown> Sign Avagraha - Devanagari (\u093D)
"\u09C5>\u09C7;"  // Vowel Candra E -> Vowel E
"\u09C6>\u09C7;"  // Vowel Short E -> Vowel E
"\u09C9>\u09CB;"  // Vowel Candra O -> Vowel O
"\u09CA>\u09CB;"  // Vowel Short O -> Vowel O
"\u09D0>\u09D0;"  // <unknown> OM - Devanagari (\u0950), Gujarati (\u0AD0)
"\u09D1>\u09D1;"  // <unknown> Stress - Devanagari (\u0951)
"\u09D2>\u09D2;"  // <unknown> Stress - Devanagari (\u0952)
"\u09D3>\u09D3;"  // <unknown> Accent - Devanagari (\u0953)
"\u09D4>\u09D4;"  // <unknown> Accent - Devanagari (\u0954)
"\u09D5>\u09D5;"  // <unknown> Length Mark - Kannada (\u0CD5), Telugu (\u0C55)
"\u09D6>\u09C8;"  // AI Length Mark -> Bengali Vowel Sign AI
"\u09D8>\u0995;"  // Letter QA -> Letter KA
"\u09D9>\u0996;"  // Letter KHHA -> Letter KHA
"\u09DA>\u0997;"  // Letter GHHA -> Letter GA
"\u09DB>\u099C;"  // Letter ZA -> Letter JA
"\u09DE>\u09AB;"  // Letter FA -> Letter PHA
"\u09E4>\u09E4;"  // <unknown> Danda - Devanagari (\u0964)
"\u09E5>\u09E5;"  // <unknown> Double Danda - Devanagari (\u0965)



/*****************************************************************************/
/* Gurmukhi                                                                  */
/*****************************************************************************/

"\u0A01>\u0A02;"
"\u0A03>\u0A03;"  // <unknown> Sign Visarga - Devanagari (\u0903) & the rest
"\u0A0B>\u0A30\u0A3F;"
"\u0A0C>\u0A07;"
"\u0A0D>\u0A10;"
"\u0A0E>\u0A0F;"
"\u0A11>\u0A14;"
"\u0A12>\u0A13;"
"\u0A29>\u0A28;"
"\u0A31>\u0A30;"
"\u0A34>\u0A33;"
"\u0A37>\u0A36;"
"\u0A3D>\u0A3D;"  // <unknown> Sign Avagraha - Devanagari (\u093D)
"\u0A43>\u0A43;"  // <unknown> Vocalic R - Devanagari (\u0943)
"\u0A44>\u0A44;"  // <unknown> Vocalic RR - Devanagari (\u0944)
"\u0A45>\u0A48;"
"\u0A46>\u0A47;"
"\u0A49>\u0A4C;"
"\u0A4A>\u0A4B;"
"\u0A50>\u0A50;"  // <unknown> OM - Devanagari (\u0950), Gujarati (\u0AD0)
"\u0A51>\u0A51;"  // <unknown> Stress - Devanagari (\u0951)
"\u0A52>\u0A52;"  // <unknown> Stress - Devanagari (\u0952)
"\u0A53>\u0A53;"  // <unknown> Accent - Devanagari (\u0953)
"\u0A54>\u0A54;"  // <unknown> Accent - Devanagari (\u0954)
"\u0A55>\u0A55;"  // <unknown> Length Mark - Kannada (\u0CD5), Telugu (\u0C55)
"\u0A56>\u0A48;"  // AI Length Mark -> Gurmukhi Vowel Sign AI
"\u0A57>\u0A4C;"  // AU Length Mark -> Gurmukhi Vowel Sign AU
"\u0A58>\u0A15\u0A3C;"
"\u0A5D>\u0A22\u0A3C;"  // Letter RHA -> Gurmukhi letter ddha (\u0A22) + nukta (\u0A3C)
"\u0A5F>\u0A2F;"
"\u0A60>\u0A30\u0A3F;"
"\u0A61>\u0A08\u0A3C;"
"\u0A62>\u0A3F\u0A3C;"
"\u0A63>\u0A40\u0A3C;"
"\u0A64>\u0A64;"  // <unknown> Danda - Devanagari (\u0964)
"\u0A65>\u0A65;"  // <unknown> Double Danda - Devanagari (\u0965)



/*****************************************************************************/
/* Gujarati                                                                  */
/*****************************************************************************/
"\u0A8C>\u0AB2\u0AC3;"
"\u0A8E>\u0A8D;"
"\u0A92>\u0A91;"
"\u0AA9>\u0AA8;"
"\u0AB1>\u0AB0;"
"\u0AB4>\u0AB3;"
"\u0AC6>\u0AC5;"
"\u0ACA>\u0AC9;"
"\u0AD1>\u0AD1;"  // <unknown> Stress - Devanagari (\u0951)
"\u0AD2>\u0AD2;"  // <unknown> Stress - Devanagari (\u0952)
"\u0AD3>\u0AD3;"  // <unknown> Accent - Devanagari (\u0953)
"\u0AD4>\u0AD4;"  // <unknown> Accent - Devanagari (\u0954)
"\u0AD5>\u0AD5;"  // <unknown> Length Mark - Kannada (\u0CD5), Telugu (\u0C55)
"\u0AD6>\u0AC8;"  // AI Length Mark -> Gujarati Vowel Sign AI
"\u0AD7>\u0ACC;"  // AU Length Mark -> Gujarati Vowel Sign AU
"\u0AD8>\u0A95\u0ABC;"
"\u0AD9>\u0A96\u0ABC;"
"\u0ADA>\u0A97\u0ABC;"
"\u0ADB>\u0A9C\u0ABC;"
"\u0ADC>\u0AA1\u0ABC;"
"\u0ADD>\u0AA2\u0ABC;"
"\u0ADE>\u0AAB\u0ABC;"
"\u0ADF>\u0AAF\u0ABC;"
"\u0AE1>\u0AB2\u0AC3;"
"\u0AE2>\u0ABF\u0ABC;"
"\u0AE3>\u0AC0\u0ABC;"
"\u0AE4>\u0AE4;"  // <unknown> Danda - Devanagari (\u0964)
"\u0AE5>\u0AE5;"  // <unknown> Double Danda - Devanagari (\u0965)



/*****************************************************************************/
/* Oriya                                                                     */
/*****************************************************************************/
"\u0B0D>\u0B0F;"
"\u0B0E>\u0B0F;"
"\u0B11>\u0B13;"
"\u0B12>\u0B13;"
"\u0B29>\u0B28;"
"\u0B31>\u0B30;"
"\u0B34>\u0B33;"
"\u0B35>\u0B2C;"  // Letter VA -> Oriya Letter BA
"\u0B44>\u0B43\u0B3C;"
"\u0B45>\u0B47;"
"\u0B46>\u0B47;"
"\u0B49>\u0B4B;"
"\u0B4A>\u0B4B;"
"\u0B50>\u0B13\u0B01;"
"\u0B51>\u0B51;"  // <unknown> Stress - Devanagari (\u0951)
"\u0B52>\u0B52;"  // <unknown> Stress - Devanagari (\u0952)
"\u0B53>\u0B53;"  // <unknown> Accent - Devanagari (\u0953)
"\u0B54>\u0B54;"  // <unknown> Accent - Devanagari (\u0954)
"\u0B55>\u0B55;"  // <unknown> Length Mark - Kannada (\u0CD5), Telugu (\u0C55)
"\u0B58>\u0B15\u0B3C;"
"\u0B59>\u0B16\u0B3C;"
"\u0B5A>\u0B17\u0B3C;"
"\u0B5B>\u0B1C\u0B3C;"
"\u0B5E>\u0B2B\u0B3C;"
"\u0B62>\u0B56\u0B3C;"
"\u0B63>\u0B57\u0B3C;"
"\u0B64>\u0B64;"  // <unknown> Danda - Devanagari (\u0964)
"\u0B65>\u0B65;"  // <unknown> Double Danda - Devanagari (\u0965)



/*****************************************************************************/
/* Tamil                                                                     */
/*****************************************************************************/

"\u0B81>\u0B81;"  // <unknown> Candrabindu - Devanagari (\u0901) ,etc
"\u0B8B>\u0BB0\u0BBF;"
"\u0B8C>\u0B87;"
"\u0B8D>\u0B86;"
"\u0B91>\u0B86;"
"\u0B96>\u0B95;"
"\u0B97>\u0B95;"
"\u0B98>\u0B95;"
"\u0B9B>\u0B9A;"
"\u0B9D>\u0B9A;"
"\u0BA0>\u0B9F;"
"\u0BA1>\u0B9F;"
"\u0BA2>\u0B9F;"
"\u0BA5>\u0BA4;"
"\u0BA6>\u0BA4;"
"\u0BA7>\u0BA4;"
"\u0BAB>\u0BAA;"
"\u0BAC>\u0BAA;"
"\u0BAD>\u0BAA;"
"\u0BB6>\u0BB7;"
"\u0BBC>\u0BBC;"  // <unknown> Nukta
"\u0BBD>\u0BBD;"  // <unknown> Sign Avagraha - Devanagari (\u093D)
"\u0BC3>\u0BCD\u0BB0\u0BBF;"
"\u0BC4>\u0BCD\u0BB0\u0BBF;"
"\u0BC5>\u0BBE;"
"\u0BC9>\u0BBE;"
"\u0BD0>\u0B93\u0BAE\u0BCD;"
"\u0BD1>\u0BD1;"  // <unknown> Stress - Devanagari (\u0951)
"\u0BD2>\u0BD2;"  // <unknown> Stress - Devanagari (\u0952)
"\u0BD3>\u0BD3;"  // <unknown> Accent - Devanagari (\u0953)
"\u0BD4>\u0BD4;"  // <unknown> Accent - Devanagari (\u0954)
"\u0BD5>\u0BD5;"  // <unknown> Length Mark - Kannada (\u0CD5), Telugu (\u0C55)
"\u0BD6>\u0BC8;"  // AI Length Mark -> Tamil Vowel Sign AI
"\u0BD8>\u0B95;"
"\u0BD9>\u0B95;"
"\u0BDA>\u0B95;"
"\u0BDB>\u0B9C;"
"\u0BDC>\u0B9F;"
"\u0BDD>\u0B9F;"
"\u0BDE>\u0BAA;"
"\u0BDF>\u0BAF;"
"\u0BE0>\u0BB0\u0BBF;"
"\u0BE1>\u0B88;"
"\u0BE2>\u0BE2;"  // <unknown> Vocalic L - Devanagari (\u0962)
"\u0BE3>\u0BE3;"  // <unknown> Vocalic LL - Devanagari (\u0963)
"\u0BE4>\u0BE4;"  // <unknown> Danda - Devanagari (\u0964)
"\u0BE5>\u0BE5;"  // <unknown> Double Danda - Devanagari (\u0965)
"\u0BE6>\u0030;"  // ZERO - Digit ZERO



/*****************************************************************************/
/* Telugu                                                                    */
/*****************************************************************************/

"\u0C0D>\u0C0E;"
"\u0C11>\u0C12;"
"\u0C29>\u0C28;"
"\u0C34>\u0C33;"
"\u0C3C>\u0C3C;"  // <unknown> Nukta
"\u0C3D>\u0C3D;"  // <unknown> Sign Avagraha - Devanagari (\u093D)
"\u0C45>\u0C46;"
"\u0C49>\u0C4A;"
"\u0C50>\u0C13\u0C02;"
"\u0C51>\u0C51;"  // <unknown> Stress - Devanagari (\u0951)
"\u0C52>\u0C52;"  // <unknown> Stress - Devanagari (\u0952)
"\u0C53>\u0C53;"  // <unknown> Accent - Devanagari (\u0953)
"\u0C54>\u0C54;"  // <unknown> Accent - Devanagari (\u0954)
"\u0C57>\u0C4C;"
"\u0C58>\u0C15;"
"\u0C59>\u0C16;"
"\u0C5A>\u0C17;"
"\u0C5B>\u0C1C;"
"\u0C5C>\u0C21;"
"\u0C5D>\u0C22;"
"\u0C5E>\u0C2B;"
"\u0C5F>\u0C2F;"
"\u0C62>\u0C3F;"
"\u0C63>\u0C40;"
"\u0C64>\u0C64;"  // <unknown> Danda - Devanagari (\u0964)
"\u0C65>\u0C65;"  // <unknown> Double Danda - Devanagari (\u0965)



/*****************************************************************************/
/* Kannada                                                                   */
/*****************************************************************************/

"\u0C81>\u0C82;"
"\u0C8D>\u0C8E;"
"\u0C91>\u0C92;"
"\u0CA9>\u0CA8;"
"\u0CB4>\u0CB3;"
"\u0CBC>\u0CBC;"  // <unknown> Nukta
"\u0CBD>\u0CBD;"  // <unknown> Sign Avagraha - Devanagari (\u093D)
"\u0CC5>\u0CC6;"
"\u0CC9>\u0CCA;"
"\u0CD0>\u0C93\u0C82;"
"\u0CD1>\u0CD1;"  // <unknown> Stress - Devanagari (\u0951)
"\u0CD2>\u0CD2;"  // <unknown> Stress - Devanagari (\u0952)
"\u0CD3>\u0CD3;"  // <unknown> Accent - Devanagari (\u0953)
"\u0CD4>\u0CD4;"  // <unknown> Accent - Devanagari (\u0954)
"\u0CD7>\u0CCC;"
"\u0CD8>\u0C95;"
"\u0CD9>\u0C96;"
"\u0CDA>\u0C97;"
"\u0CDB>\u0C9C;"
"\u0CDC>\u0CA1;"
"\u0CDD>\u0CA2;"
"\u0CDF>\u0CAF;"
"\u0CE2>\u0CBF;"
"\u0CE3>\u0CC0;"
"\u0CE4>\u0CE4;"  // <unknown> Danda - Devanagari (\u0964)
"\u0CE5>\u0CE5;"  // <unknown> Double Danda - Devanagari (\u0965)



/*****************************************************************************/
/* Malayalam                                                                 */
/*****************************************************************************/

"\u0D01>\u0D02;"
"\u0D0D>\u0D06;"
"\u0D11>\u0D13;"
"\u0D29>\u0D28;"
"\u0D3C>\u0D3C;"  // <unknown> Nukta
"\u0D3D>\u0D3D;"  // <unknown> Sign Avagraha - Devanagari (\u093D)
"\u0D44>\u0D44;"  // <unknown> Vocalic RR - Devanagari (\u0944)
"\u0D45>\u0D3E;"
"\u0D49>\u0D4B;"
"\u0D50>\u0D50;"  // <unknown> OM - Devanagari (\u0950), Gujarati (\u0AD0)
"\u0D51>\u0D51;"  // <unknown> Stress - Devanagari (\u0951)
"\u0D52>\u0D52;"  // <unknown> Stress - Devanagari (\u0952)
"\u0D53>\u0D53;"  // <unknown> Accent - Devanagari (\u0953)
"\u0D54>\u0D54;"  // <unknown> Accent - Devanagari (\u0954)
"\u0D55>\u0D55;"  // <unknown> Length Mark - Kannada (\u0CD5), Telugu (\u0C55)
"\u0D56>\u0D48;"  // AI Length Mark -> Malayalam Vowel Sign AI
"\u0D58>\u0D15;"
"\u0D59>\u0D16;"
"\u0D5A>\u0D17;"
"\u0D5B>\u0D1C;"
"\u0D5C>\u0D21;"
"\u0D5D>\u0D22;"
"\u0D5E>\u0D2B;"
"\u0D5F>\u0D2F;"
"\u0D62>\u0D62;"  // <unknown> Vocalic L - Devanagari (\u0962)
"\u0D63>\u0D63;"  // <unknown> Vocalic LL - Devanagari (\u0963)
"\u0D64>\u0D64;"  // <unknown> Danda - Devanagari (\u0964)
"\u0D65>\u0D65;"  // <unknown> Double Danda - Devanagari (\u0965)