m17n-contrib 1.1.14-1 / usr / share / m17n / te-rts.mim

;; te-rts.mim -- Telugu input method with RTS method

;; Copyright (C) 2003, 2004, 2005, 2006
;;   National Institute of Advanced Industrial Science and Technology (AIST)
;;   Registration Number H15PRO112
;; Copyright 2005, 2006, 2010 Suraj N. Kurapati <sunaku@gmail.com>
;; Copyright 2006 Chaitanya Kamisetty <chaitanya@atc.tcs.co.in>


;; This file is part of the m17n contrib; a sub-part of the m17n
;; library.

;; The m17n library is free software; you can redistribute it and/or
;; modify it under the terms of the GNU Lesser General Public License
;; as published by the Free Software Foundation; either version 2.1 of
;; the License, or (at your option) any later version.

;; The m17n library is distributed in the hope that it will be useful,
;; but WITHOUT ANY WARRANTY; without even the implied warranty of
;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
;; Lesser General Public License for more details.

;; You should have received a copy of the GNU Lesser General Public
;; License along with the m17n library; if not, write to the Free
;; Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
;; Boston, MA 02110-1301, USA.


(input-method te rts)

(description "Input method for Telugu script with RTS method.
For the detail of RTS, see the page:
  <http://groups.google.com/groups?selm=Bv0A9M.27B@rice.edu>.

This input method is based on the Telugu Rice Transliteration Standard (RTS)
specification[1] and its Rice Inverse Transliterator (RIT) supplement[2].

The original RTS specification was written by Ananda Kishore and Rama Rao
Kanneganti in 1992 and can presently be accessed in the archives[1] of the
'soc.culture.indian.telugu' USENET newsgroup.

The RIT supplement[2] enriches RTS with alternative combinations.  However,
in cases where RIT and RTS define conflicting mappings for the same
combination, such as 'ea', only the RTS mapping is honored.

Finally, this input method deviates from the RTS in the following ways:

* The combination '\@n' yields '�' because its corresponding glyph does not
  yet exist in the Telugu unicode chart.

* The combination 'm' yields 'ం' if it appears at the end of a word.  The
  user can type 'm&' to bypass this behavior and force 'm' to yield 'మ్'.

* The sunna prevention operator '&' can be used to force a more literal
  transliteration of consonant compounds such as 'jn' by writing 'j&n'.

[1]: http://groups.google.com/groups?selm=Bv0A9M.27B@rice.edu
[2]: http://www.teluguworld.org/RIT/rit3.0/manual.html
")

(title "క")

(map
 (starter
  ((S-\ )) ((C-@))

  ("a") ("b") ("c") ("d") ("e") ("f") ("g") ("h") ("i") ("j")
  ("k") ("l") ("m") ("n") ("o") ("p") ("r") ("s") ("t") ("u")
  ("v") ("w") ("x") ("y") ("z")

  ("A") ("B") ("C") ("D") ("E") ("G") ("H") ("I") ("J") ("K")
  ("L") ("M") ("N") ("O") ("P") ("R") ("S") ("T") ("U") ("V")
  ("W")

  ("0") ("1") ("2") ("3") ("4") ("5") ("6") ("7") ("8") ("9")

  ("@") ("|") ("~") ("#")
 )

 (consonant

  ;-------------------------------------------------------------------------
  ; row 1 - క ఖ గ ఘ ఙ
  ;-------------------------------------------------------------------------

  ("k" "క్")

  ("kh" "ఖ్")
  ("kH" "ఖ్")
  ("K" "ఖ్")
  ("Kh" "ఖ్")
  ("KH" "ఖ్")

  ("g" "గ్")

  ("gh" "ఘ్")
  ("gH" "ఘ్")
  ("G" "ఘ్")
  ("Gh" "ఘ్")
  ("GH" "ఘ్")

  ("~m" "ఙ్")

  ;-------------------------------------------------------------------------
  ; row 2 - చ ఛ జ ఝ ఞ
  ;-------------------------------------------------------------------------

  ("c" "చ్")
  ("ch" "చ్")
  ("cH" "చ్")

  ("~c" "ౘ")

  ("C" "ఛ్")
  ("Ch" "ఛ్")
  ("CH" "ఛ్")
  ("c'" "ఛ్") ; from RIT 2.0, 3.0

  ("j" "జ్")
  ("z" "జ్") ; from RIT 3.0

  ("~j" "ౙ")

  ("jh" "ఝ్")
  ("jH" "ఝ్")
  ("J" "ఝ్")
  ("Jh" "ఝ్")
  ("JH" "ఝ్")

  ("~n" "ఞ్")

  ;-------------------------------------------------------------------------
  ; row 3 - ట ఠ డ ఢ ణ
  ;-------------------------------------------------------------------------

  ("T" "ట్")
  ("t'" "ట్")

  ("Th" "ఠ్")
  ("TH" "ఠ్")
  ("th'" "ఠ్")
  ("tH'" "ఠ్")

  ("D" "డ్")
  ("d'" "డ్")

  ("Dh" "ఢ్")
  ("DH" "ఢ్")
  ("dh'" "ఢ్")
  ("dH'" "ఢ్")

  ("N" "ణ్")
  ("nh" "ణ్")
  ("nH" "ణ్")
  ("n'" "ణ్") ; from RIT 2.0, 3.0

  ;-------------------------------------------------------------------------
  ; row 4 - త థ ద ధ న
  ;-------------------------------------------------------------------------

  ("t" "త్")

  ("th" "థ్")
  ("tH" "థ్")

  ("d" "ద్")

  ("dh" "ధ్")
  ("dH" "ధ్")

  ;-------------------------------------------------------------------------
  ; row 5 - ప ఫ బ భ మ
  ;-------------------------------------------------------------------------

  ("p" "ప్")

  ("f" "ఫ్")
  ("P" "ఫ్")
  ("ph" "ఫ్")
  ("pH" "ఫ్")
  ("Ph" "ఫ్")
  ("PH" "ఫ్")

  ("b" "బ్")

  ("bh" "భ్")
  ("bH" "భ్")
  ("B" "భ్")
  ("Bh" "భ్")
  ("BH" "భ్")

  ;-------------------------------------------------------------------------
  ; row 6 - య ర ల వ శ ష స హ ళ క్ష ఱ
  ;-------------------------------------------------------------------------

  ; ("y" "య్") is defined below in consonant-without-sunna

  ; ("r" "ర్") is defined below in consonant-without-sunna

  ("l" "ల్")

  ("v" "వ్")
  ("V" "వ్") ; from RIT 3.0
  ("w" "వ్")
  ("W" "వ్") ; from RIT 3.0

  ("S" "శ్")
  ("s'" "శ్") ; from RIT 2.0, 3.0

  ("sh" "ష్")
  ("sH" "ష్")
  ("Sh" "ష్") ; from RIT 3.0
  ("SH" "ష్") ; from RIT 3.0

  ("s" "స్")

  ("h" "హ్")
  ("H" "హ్")

  ("L" "ళ్")
  ("lh" "ళ్")
  ("lH" "ళ్")
  ("Lh" "ళ్")
  ("LH" "ళ్")
  ("l'" "ళ్") ; from RIT 2.0, 3.0

  ("x" "క్ష్")
  ("ksh" "క్ష్")
  ("ksH" "క్ష్")
  ("ks" "క్స్") ; disambiguation for this input method's 1-character lookahead

  ("~r" "ఱ్")
  ("r''" "ఱ్") ; from RIT 2.0, 3.0

  ;---------------------------------------------------------------------------
  ; compounds
  ;---------------------------------------------------------------------------

  ("jn" "జ్ఞ్")
  ("j&n" "జ్న్") ; apply sunna prevention operator to produce literal compound

  ("dd'" "డ్డ్") ; from RIT 3.0
  ("dd" "ద్ద్") ; disambiguation for this input method's 1-character lookahead

  ("tt'" "ట్ట్") ; from RIT 3.0
  ("tt" "త్త్") ; disambiguation for this input method's 1-character lookahead
 )

 (consonant-without-sunna

  ; Quotation from "sunna generation" section of RIT 3.0 specification:
  ;
  ;   when 'n' or 'm' is followed by a consonant except 'r' or 'y' RIT
  ;   assumes it to be a sunna
  ;
  ("r" "ర్")
  ("y" "య్")

  ; Quotation from "sunna generation" section of RIT 3.0 specification:
  ;
  ;   You can prevent a sunna generation by writing 'n&' or 'm&'.
  ;
  ("n&" "న్")
  ("m&" "మ్")
 )

 (sunna-inside-word
  ("n" "న్")
  ("m" "మ్")
 )

 (sunna-endof-word

  ;-------------------------------------------------------------------------
  ; whitespace
  ;-------------------------------------------------------------------------

  ("m " "ం ")
  ((m Tab) "ం\t")
  ((m Return) "ం\n")

  ;-------------------------------------------------------------------------
  ; punctuation
  ;-------------------------------------------------------------------------
  ;
  ; The sequences below are generated by this Bourne shell script:
  ;
  ;     for ch in '!' '\"' '#' '$' '%' "'" '(' ')' '*' '+' ',' '-' '.' \
  ;               '/' '\\' ':' ';' '<' '=' '>' '?' '[' ']' '_' '`' '{' '}'
  ;     do echo "  (\"m${ch}\" \"ం${ch}\")"; done
  ;
  ; Sequences ending with '^' '&' '|' '@' '~' are omitted from the above
  ; loop because those punctuation marks already serve a purpose in this
  ; input method.
  ;
  ("m!" "ం!")
  ("m\"" "ం\"")
  ("m#" "ం#")
  ("m$" "ం$")
  ("m%" "ం%")
  ("m'" "ం'")
  ("m(" "ం(")
  ("m)" "ం)")
  ("m*" "ం*")
  ("m+" "ం+")
  ("m," "ం,")
  ("m-" "ం-")
  ("m." "ం.")
  ("m/" "ం/")
  ("m\\" "ం\\")
  ("m:" "ం:")
  ("m;" "ం;")
  ("m<" "ం<")
  ("m=" "ం=")
  ("m>" "ం>")
  ("m?" "ం?")
  ("m[" "ం[")
  ("m]" "ం]")
  ("m_" "ం_")
  ("m`" "ం`")
  ("m{" "ం{")
  ("m}" "ం}")
 )

 (independent
  ((S-\ ) "‌")
  ((C-@) "‍")

  ;-------------------------------------------------------------------------
  ; vowels
  ;-------------------------------------------------------------------------

  ("a" "అ")

  ("aa" "ఆ")
  ("a'" "ఆ")
  ("A" "ఆ") ; from RIT 2.0, 3.0

  ("i" "ఇ")

  ("ee" "ఈ")
  ("ii" "ఈ")
  ("ia" "ఈ")
  ("i'" "ఈ")
  ("I" "ఈ") ; from RIT 2.0, 3.0

  ("u" "ఉ")

  ("oo" "ఊ")
  ("uu" "ఊ")
  ("U" "ఊ")
  ("ua" "ఊ")
  ("u'" "ఊ")

  ("R" "ఋ")
  ("r'" "ఋ") ; from RIT 2.0

  ("Ru" "ౠ")
  ("r'u" "ౠ") ; from RIT 2.0

  ("~l" "ౢ")

  ("~L" "ౣ")

  ("e" "ఎ")

  ("ea" "ఏ")
  ("ae" "ఏ")
  ("E" "ఏ")
  ("e'" "ఏ")

  ("ai" "ఐ")
  ("ei" "ఐ") ; from RIT 3.0

  ("o" "ఒ")

  ("oe" "ఓ")
  ("O" "ఓ")
  ("oa" "ఓ")
  ("o'" "ఓ")

  ("au" "ఔ")
  ("ou" "ఔ")
  ("ow" "ఔ") ; from RIT 3.0

  ; This combination is defined in the "internal representation" section of
  ; RTS.  It was widely used in early RTS implementations which lacked the
  ; automatic sunna generation capability and has thus became the defacto
  ; way of producing a sunna manually.
  ("M" "ం")

  ("@M" "ఁ")
  ("@m" "ఁ") ; from RIT 3.0

  ("@h" "ః")

  ("@n" "�")
  ("@N" "�") ; from RIT 3.0

  ("@2" "ఽ")

  ;-------------------------------------------------------------------------
  ; digits
  ;-------------------------------------------------------------------------

  ("0" "౦")
  ("1" "౧")
  ("2" "౨")
  ("3" "౩")
  ("4" "౪")
  ("5" "౫")
  ("6" "౬")
  ("7" "౭")
  ("8" "౮")
  ("9" "౯")

  ;-------------------------------------------------------------------------
  ; punctuation
  ;-------------------------------------------------------------------------

  ; The characters at the right-hand-side of these mappings are borrowed
  ; from the Devanagiri unicode chart because they do not yet exist in the
  ; Telugu unicode chart.
  ("|" "।") ; from RIT 3.0
  ("||" "॥") ; from Yudit
 )

 (dependent
  ("^" (delete @-) "్‌")

  ;-------------------------------------------------------------------------
  ; vowels
  ;-------------------------------------------------------------------------

  ("a" (delete @-) "")

  ("aa" (delete @-) "ా")
  ("a'" (delete @-) "ా")
  ("A" (delete @-) "ా") ; from RIT 3.0

  ("i" (delete @-) "ి")

  ("ee" (delete @-) "ీ")
  ("ii" (delete @-) "ీ")
  ("ia" (delete @-) "ీ")
  ("i'" (delete @-) "ీ")
  ("I" (delete @-) "ీ") ; from RIT 3.0

  ("u" (delete @-) "ు")

  ("oo" (delete @-) "ూ")
  ("uu" (delete @-) "ూ")
  ("U" (delete @-) "ూ")
  ("ua" (delete @-) "ూ")
  ("u'" (delete @-) "ూ")

  ("R" (delete @-) "ృ")
  ("r'" (delete @-) "ృ") ; from RIT 2.0

  ("Ru" (delete @-) "ౄ")
  ("r'u" (delete @-) "ౄ") ; from RIT 2.0

  ("~l" (delete @-) "ౢ")

  ("~L" (delete @-) "ౣ")

  ("e" (delete @-) "ె")

  ("ea" (delete @-) "ే")
  ("ae" (delete @-) "ే")
  ("E" (delete @-) "ే")
  ("e'" (delete @-) "ే")

  ("ai" (delete @-) "ై")
  ("ei" (delete @-) "ై") ; from RIT 3.0

  ("o" (delete @-) "ొ")

  ("oe" (delete @-) "ో")
  ("O" (delete @-) "ో")
  ("oa" (delete @-) "ో")
  ("o'" (delete @-) "ో")

  ("au" (delete @-) "ౌ")
  ("ou" (delete @-) "ౌ")
  ("ow" (delete @-) "ౌ") ; from RIT 3.0
 )

 (single_hash
  ("#" "")
 )

 (triple_hash
  ("###" "#")
 )

 (invariant
  ("a" "a") ("b" "b") ("c" "c") ("d" "d") ("e" "e") ("f" "f") ("g" "g")
  ("h" "h") ("i" "i") ("j" "j") ("k" "k") ("l" "l") ("m" "m") ("n" "n")
  ("o" "o") ("p" "p") ("q" "q") ("r" "r") ("s" "s") ("t" "t") ("u" "u")
  ("v" "v") ("w" "w") ("x" "x") ("y" "y") ("z" "z")

  ("A" "A") ("B" "B") ("C" "C") ("D" "D") ("E" "E") ("F" "F") ("G" "G")
  ("H" "H") ("I" "I") ("J" "J") ("K" "K") ("L" "L") ("M" "M") ("N" "N")
  ("O" "O") ("P" "P") ("Q" "Q") ("R" "R") ("S" "S") ("T" "T") ("U" "U")
  ("V" "V") ("W" "W") ("X" "X") ("Y" "Y") ("Z" "Z")

  ("0" "0") ("1" "1") ("2" "2") ("3" "3") ("4" "4") ("5" "5") ("6" "6")
  ("7" "7") ("8" "8") ("9" "9")

  ("~" "~") ("`" "`") ("!" "!") ("@" "@") ("$" "$") ("%" "%") ("^" "^")
  ("&" "&") ("*" "*") ("(" "(") (")" ")") ("_" "_") ("-" "-") ("+" "+")
  ("=" "=") ("{" "{") ("[" "[") ("}" "}") ("]" "]") ("|" "|" ) ("\\" "\\")
  (":" ":") (";" ";") ("\"" "\"") ("\'" "\'") ("<" "<") ("," ",") (">" ">")
  ("." ".") ("?" "?") ("/" "/")

  (" " " ") ((Tab) ("\t")) ((BackSpace) (undo)) ((Return) ("\n"))
 )

 (return
  ((Return)))

 (backspace
  ((BackSpace) (undo)))
)

(state
 (init
  (starter (pushback 1) (shift intermediate))
 )

 (intermediate
  (consonant (shift second))
  (consonant-without-sunna (shift second))
  (sunna-inside-word (shift second-sunna-inside-word))
  (sunna-endof-word (shift init))
  (independent (shift init))
  (single_hash (shift no_transliteration))
  (triple_hash (shift init))
  (backspace)
  (return (shift init))
 )

 (second
  (consonant)
  (consonant-without-sunna)
  (sunna-inside-word (shift second-sunna-inside-word))
  (sunna-endof-word (shift init))
  (dependent (shift init))
  (backspace)
  (return (shift init))
 )

 (second-sunna-inside-word
  (t (mark p))
  (consonant (move p) (delete @-) (delete @-) "ం" (move @>) (shift second))
  (consonant-without-sunna (shift second))
  (sunna-inside-word)
  (sunna-endof-word (shift init))
  (dependent (shift init))
  (backspace)
 )

 (no_transliteration
  (single_hash (shift init))
  (invariant)
 )
)

;; Local Variables:
;; coding: utf-8
;; mode: emacs-lisp
;; End: