Skip to content

Instantly share code, notes, and snippets.

Created January 7, 2012 19:48
Show Gist options
  • Save anonymous/1575793 to your computer and use it in GitHub Desktop.
Save anonymous/1575793 to your computer and use it in GitHub Desktop.
TECkit mapping for DN to Unicode romanised Skt. conversion
; TECkit mapping for DN to Unicode romanised Skt. conversion
;Updated March 23, 2010 9:53:03 PM EDT
LHSName "UNICODE"
RHSName "UNICODE"
Define NUL U+007F
pass(Unicode)
UniClass [LTR] = ( U+0100 U+0101 'i' 'I' U+012A U+012B 'u' 'U' U+016A U+016B U+1E5A U+1E5B U+1E5C U+1E5D 'E' 'e' 'Ai' 'ai' 'O' 'o' 'Au' 'au' U+1E36 U+1E37 U+1E38 U+1E39 U+1E42 U+1E43 U+1E24 U+1E25 'K' 'k' 'Kh' 'kh' 'G' 'g' 'Gh' 'gh' U+1E44 U+1E45 'C' 'c' 'Ch' 'ch' 'J' 'j' 'Jh' 'jh' 'Ñ' 'ñ' U+1E6C U+1E6D 'U+1E6C h' 'U+1E6D h' U+1E0C U+1E0D 'U+1E0C h' 'U+1E0D h' U+1E46 U+1E47 'T' 't' 'Th' 'th' 'D' 'd' 'Dh' 'dh' 'N' 'n' 'P' 'p' 'Ph' 'ph' 'B' 'b' 'Bh' 'bh' 'M' 'm' 'Y' 'y' 'R' 'r' 'L' 'l' 'V' 'v' U+015A U+015B U+1E62 U+1E63 'S' 's' 'H' 'h' )
UniClass [rMedVow] = ( U+0100 U+0101 'I' 'i' U+012A U+012B 'U' 'u' U+016A U+016B U+1E5A U+1E5B U+1E5C U+1E5D 'E' 'e' U+0114 U+0115 'Ai' 'ai' 'O' 'o' U+014E U+014F 'Au' 'au' U+1E36 U+1E37 U+1E38 U+1E39 U+1E42 U+1E43 U+1E24 U+1E25 )
;UniClass [dMedVow] = ( U+093E U+093F U+0940 U+0941 U+0942 U+0943 U+0944 U+0947 U+0948 U+094B U+094C U+0962 U+0963 U+0902 U+0903 )
UniClass [rCons] = ( 'k' 'K' 'kh' 'Kh' 'G' 'g' 'Gh' 'gh' U+1E44 U+1E45 'C' 'c' 'Ch' 'ch' 'J' 'j' 'Jh' 'jh' 'Ñ' 'ñ' U+1E6C U+1E6D 'U+1E6C h' 'U+1E6D h' U+1E0C U+1E0D 'U+1E0C h' 'U+1E0D h' U+1E46 U+1E47 'T' 't' 'Th' 'th' 'D' 'd' 'Dh' 'dh' 'N' 'n' 'P' 'p' 'Ph' 'ph' 'B' 'b' 'Bh' 'bh' 'M' 'm' 'Y' 'y' 'R' 'r' 'L' 'l' 'V' 'v' U+015A U+015B U+1E62 U+1E63 'S' 's' 'H' 'h' )
;UniClass [dCons] = ( U+0915 U+0916 U+0917 U+0918 U+0919 U+091A U+091B U+091C U+091D U+091E U+091F U+0920 U+0921 U+0922 U+0923 U+0924 U+0925 U+0926 U+0927 U+0928 U+092A U+092B U+092C U+092D U+092E U+092F U+0930 U+0932 U+0935 U+0936 U+0937 U+0938 U+0939 )
;initial vowels
U+0905 <> 'a' / ^[rCons] _
U+0905 <> 'a' / 'a'_
U+0905 <> 'A' / ^[rCons] _
U+0905<> U+00E4 ; ä
U+0905<> U+00E4 ; Ä
U+0906 <> U+0100 / ^[rCons] _
U+0906 <> U+0101 / ^[rCons] _
U+0907 <> 'i' / ^[rCons] _
U+0907 <> 'I' / ^[rCons] _
U+0907<> U+00EF ; ï
U+0907<> U+00CF ; Ï
U+0907 U+0901<> U+0129 / ^[rCons] _ ; i + candrabindu
U+0908 <> U+012A / ^[rCons] _
U+0908 <> U+012B / ^[rCons] _
U+0909 <> 'u' / ^[rCons] _
U+0909 <> 'U' / ^[rCons] _
U+0909<> U+00FC ; ü
U+0909<> U+00DC ; Ü
U+090A <> U+016A / ^[rCons] _
U+090A <> U+016B / ^[rCons] _
U+090B<> U+1E5A / ^[rCons] _ ;initial Ṛ
U+090B <> U+1E5B / ^[rCons] _
U+0960<> U+1E5C / ^[rCons] _ ;initial Ṝ
U+0960 <> U+1E5D / ^[rCons] _
U+090C<> U+1E36 / ^[rCons] _ ;initial Ḷ
U+090C <> U+1E37 / ^[rCons] _
U+0961<> U+1E38 / ^[rCons] _ ;initial Ḹ
U+0961 <> U+1E39 / ^[rCons] _
U+090F <> 'e' / ^[rCons] _
U+090F <> 'E' / ^[rCons] _
U+090D <> U+0114 / ^[rCons] _
U+090D <> U+0115 / ^[rCons] _
U+0910 <> 'ai' / ^[rCons] _
U+0910 <> 'Ai' / ^[rCons] _
U+0913 <> 'o' / ^[rCons] _
U+0913 <> 'O' / ^[rCons] _
U+0913 U+0901<> U+00F5 / ^[rCons] _ ; o + candrabindu
U+0911 <> U+014E / ^[rCons] _
U+0911 <> U+014F / ^[rCons] _
U+0914 <> 'au' / ^[rCons] _
U+0914 <> 'Au' / ^[rCons] _
;non-final consonants
U+0915 <> 'k' / _ [rMedVow]
U+0915 <> 'K' / _ [rMedVow]
U+0916 <> 'kh' / _ [rMedVow]
U+0916 <> 'Kh' / _ [rMedVow]
U+0917 <> 'g' / _ [rMedVow]
U+0917 <> 'G' / _ [rMedVow]
U+0918 <> 'gh' / _ [rMedVow]
U+0918 <> 'Gh' / _ [rMedVow]
U+0919 <> U+1E44 / _ [rMedVow]
U+0919 <> U+1E45 / _ [rMedVow]
U+091A <> 'C' / _ [rMedVow]
U+091A <> 'c' / _ [rMedVow]
U+091B <> 'ch' / _ [rMedVow]
U+091B <> 'Ch' / _ [rMedVow]
U+091C <> 'J' / _ [rMedVow]
U+091C <> 'j' / _ [rMedVow]
U+091D <> 'Jh' / _ [rMedVow]
U+091D <> 'jh' / _ [rMedVow]
U+091E <> 'ñ' / _ [rMedVow]
U+091E <> 'Ñ' / _ [rMedVow]
U+091F <> U+1E6C / _ [rMedVow]
U+091F <> U+1E6D / _ [rMedVow]
U+0920 <> U+1E6C 'h' / _ [rMedVow]
U+0920 <> U+1E6D 'h' / _ [rMedVow]
U+0921 <> U+1E0C / _ [rMedVow]
U+0921 <> U+1E0D / _ [rMedVow]
U+0922 <> U+1E0C 'h' / _ [rMedVow]
U+0922 <> U+1E0D 'h' / _ [rMedVow]
U+0923 <> U+1E46 / _ [rMedVow]
U+0923 <> U+1E47 / _ [rMedVow]
U+0924 <> 't' / _ [rMedVow]
U+0924 <> 'T' / _ [rMedVow]
U+0925 <> 'th' / _ [rMedVow]
U+0925 <> 'Th' / _ [rMedVow]
U+0926 <> 'D' / _ [rMedVow]
U+0926 <> 'd' / _ [rMedVow]
U+0927 <> 'Dh' / _ [rMedVow]
U+0927 <> 'dh' / _ [rMedVow]
U+0928 <> 'N' / _ [rMedVow]
U+0928 <> 'n' / _ [rMedVow]
U+092A <> 'P' / _ [rMedVow]
U+092A <> 'p' / _ [rMedVow]
U+092B <> 'Ph' / _ [rMedVow]
U+092B <> 'ph' / _ [rMedVow]
U+092C <> 'B' / _ [rMedVow]
U+092C <> 'b' / _ [rMedVow]
U+092D <> 'Bh' / _ [rMedVow]
U+092D <> 'bh' / _ [rMedVow]
U+092E <> 'M' / _ [rMedVow]
U+092E <> 'm' / _ [rMedVow]
U+092F <> 'Y' / _ [rMedVow]
U+092F <> 'y' / _ [rMedVow]
U+0930 <> 'R' / _ [rMedVow]
U+0930 <> 'r' / _ [rMedVow]
U+0932 <> 'L' / _ [rMedVow]
U+0932 <> 'l' / _ [rMedVow]
U+0935 <> 'V' / _ [rMedVow]
U+0935 <> 'v' / _ [rMedVow]
U+0936 <> U+015A / _ [rMedVow]
U+0936 <> U+015B / _ [rMedVow]
U+0937 <> U+1E62 / _ [rMedVow]
U+0937 <> U+1E63 / _ [rMedVow]
U+0938 <> 'S' / _ [rMedVow]
U+0938 <> 's' / _ [rMedVow]
U+0939 <> 'H' / _ [rMedVow]
U+0939 <> 'h' / _ [rMedVow]
;medial vowels
U+093E <> U+0101 ;ā
U+093F <> 'i' ;i
U+093F U+0901<> U+0129 ; i + candrabindu
U+0940 <> U+012B ;ī
U+0941 <> 'u' ;u
U+0942 <> U+016B ;ū
U+0943 <> U+1E5B ;ṛ
U+0944 <> U+1E5D ;ṝ
U+0947 <> 'e' ;e
U+0948 <> 'ai' ;ai
U+094B <> 'o' ;o
U+094B U+0901<> U+00F5 ; o + candrabindu
U+094C <> 'au' ;au
U+0962 <> U+1E37 ;ḷ
U+0963 <> U+1E39 ;ḹ
U+0902 <> U+1E43 ;ṃ
U+0903 <> U+1E25 ;ḥ
U+0905 U+0902 <> U+0061 U+1E43 / [rMedVow] _ ;Vaṃ
U+0905 U+0902 <> U+0061 U+1E43 / U+0061 _ ;aaṃ
U+0905 U+0903 <> U+0061 U+1E25 / [rMedVow] _ ;Vaḥ
U+0905 U+0903 <> U+0061 U+1E25 / U+0061 _ ;aaḥ
U+0902 <> U+0061 U+1E43 / ^[rMedVow] _ ;aṃ
U+0902 <> U+0061 U+1E43 / ^U+0061 _ ;aṃ
U+0903 <> U+0061 U+1E25 ;aḥ
;final cons
U+0915 U+094D <> 'k'
U+0916 U+094D <> 'kh'
U+0917 U+094D <> 'g'
U+0918 U+094D <> 'gh'
U+0919 U+094D <> U+1E45
U+091A U+094D <> 'c'
U+091B U+094D <> 'ch'
U+091C U+094D <> 'j'
U+091D U+094D <> 'jh'
U+091E U+094D <> 'ñ'
U+091F U+094D <> U+1E6D
U+0920 U+094D <> U+1E6D 'h'
U+0921 U+094D <> U+1E0D
U+0922 U+094D <> U+1E0D 'h'
U+0923 U+094D <> U+1E47
U+0924 U+094D <> 't'
U+0925 U+094D <> 'th'
U+0926 U+094D <> 'd'
U+0927 U+094D <> 'dh'
U+0928 U+094D <> 'n'
U+092A U+094D <> 'p'
U+092B U+094D <> 'ph'
U+092C U+094D <> 'b'
U+092D U+094D <> 'bh'
U+092E U+094D <> 'm'
U+092F U+094D <> 'y'
U+0930 U+094D <> 'r'
U+0932 U+094D <> 'l'
U+0935 U+094D <> 'v'
U+0936 U+094D <> U+015B
U+0937 U+094D <> U+1E63
U+0938 U+094D <> 's'
U+0939 U+094D <> 'h'
;avagraha and daṇḍa
U+093D <> U+02BC ;styled apostrophe
U+093D <> U+2019 ;styled apostrophe
U+093D <> U+0027 ;unstyled apostrophe
U+0965 <> U+002F U+002F ;double daṇḍa
U+0964 <> U+002F ;single daṇḍa
;numerals
U+0966 <> U+0030 ; 0
U+0967 <> U+0031 ; 1
U+0968 <> U+0032 ; 2
U+0969 <> U+0033 ; 3
U+096A <> U+0034 ; 4
U+096B <> U+0035 ; 5
U+096C <> U+0036 ; 6
U+096D <> U+0037 ; 7
U+096E <> U+0038 ; 8
U+096F <> U+0039 ; 9
pass(Unicode)
UniClass [dCons] = ( U+0915 .. U+0939 )
@D <> [dCons]=D 'a' ;strips the -a off consonants
@D <> [dCons]=D 'A' ;strips the -A off consonants
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment