;; -*- emacs-lisp -*- ;; UTIL - Unified Transliteration of Indic Languages, a transliteration method ;; based on IAST, ISO-15919, GRETIL and ALA-LC. ;; ;; Copyright (C) 2020 Satish B. Setty ;; ;; Distributed under the open source Fair License: https://opensource.org/licenses/Fair ;; ;; Instructions: ;; (1) Copy this file to some dir in your 'load-path ;; (2) Add this line in your init file: (require 'indic-roman-postfix) ;; (provide 'indic-roman-postfix) (quail-define-package "indic-roman-postfix" "UTF-8" "InR<" t "Input method for Indic transliteration with postfix modifiers. Covers the Gretil standard character set [1] and NLK [2]. Long vowels are dealt with by doubling. | | postfix | examples | |------------------+---------+-----------------------| | macron above | ~ | aa -> ā n~ -> n̄ | | macron below | _ | n_ -> ṉ r_ -> ṟ | | dot above | ; | n; -> ṅ s; -> ṡ | | dot below | . | d. -> ḍ rr. -> ṝ | | combination | | ll. -> ḹ ll; -> ḻ̇ | [1]: http://gretil.sub.uni-goettingen.de/gretil/gretdias.pdf [2]: Appendix F: http://varamozhi.sourceforge.net/iscii91.pdf " nil t nil nil nil nil nil nil nil nil t) (quail-define-rules ;; macron above ("aa" ["ā"]) ("ee" ["ē"]) ("ii" ["ī"]) ("oo" ["ō"]) ("uu" ["ū"]) ("n~" ["n̄"]) ("s~" ["s̄"]) ("z~" ["z̄"]) ;; alternative for ذ so that /ẕ/ can be for Tamil /ḻ̇/ ("r~" ["r̄"]) ;; alternative for Tamil /ḻ̇/ or /ẕ/ since Das Gupta uses /r̤/. IPA also uses /ɻ/ ;; macron below ("b_" ["ḇ"]) ("c_" ["c̱"]) ;; alternative for /ċ/ so that alveolars have _ below ("d_" ["ḏ"]) ("g_" ["g̱"]) ("h_" ["ẖ"]) ("j_" ["j̱"]) ("k_" ["ḵ"]) ("l_" ["ḻ"]) ("n_" ["ṉ"]) ("r_" ["ṟ"]) ("s_" ["s̱"]) ("t_" ["ṯ"]) ("z_" ["ẕ"]) ;; dot below ("a." ["ạ"]) ("d." ["ḍ"]) ("e." ["ẹ"]) ("h." ["ḥ"]) ("l." ["ḷ"]) ("m." ["ṃ"]) ("n." ["ṇ"]) ("o." ["ọ"]) ("r." ["ṛ"]) ("s." ["ṣ"]) ("t." ["ṭ"]) ("u." ["ụ"]) ("x." ["x̣"]) ("z." ["ẓ"]) ;; dot above ("c;" ["ċ"]) ("g;" ["ġ"]) ("m;" ["ṁ"]) ("n;" ["ṅ"]) ("r;" ["ṙ"]) ("s;" ["ṡ"]) ;; श so that "tick above" can be eliminated completely ("x;" ["ẋ"]) ("y;" ["ẏ"]) ("z;" ["ż"]) ;; macron above, dot below ("aa." ["ạ̄"]) ("ee." ["ẹ̄"]) ("ll." ["ḹ"]) ("mm." ["ṃ̄"]) ("nn." ["ṇ̄"]) ("oo." ["ọ̄"]) ("rr." ["ṝ"]) ("uu." ["ụ̄"]) ;; macron below, dot above ("ll;" ["ḻ̇"]) ;; diacritics ("&" ["’"]) ;; avagraha ("~" ["̐"]) ;; anunasika (combining candrabindu) ("%" ["̃"]) ;; combining tilde above (alternative anunasika) ("'" ["́"]) ;; vedic accent udātta (acute accent) ("`" ["̀"]) ;; vedic accent independent svarita (grave accent) ("\\" ["ʽ"]) ;; single backslash (arabic ain) ("/" ["ʼ"]) ;; single forward slash (arabic hamza) (";;" ["ˊ"]) ;; maithili rising tone ("--" ["ˋ"]) ;; maithili falling tone (";-" ["˙"]) ;; maithili neutral tone ;; obsolete ("n~~" ["ñ"]); ("s'" ["ś"]) ;; IAST alternative to ṡ ("l'" ["ĺ"]) ;; precom. candrabindu ) ;; ;; Dravidian ;; ("l:" "l̤") ;; tamil/kannada LLA ळ ಳ ள ള "retroflex lateral approximant" (≠ NLK = ALA-LC use ḷ) ;; ("r_" "ṟ") ;; tamil/kannada RRA ऱ ಱ ற റ "alveolar r" (= NLK = ALA-LC) ;; ("l_" "ḻ") ;; tamil/kannada LLLA ऴ ೞ ழ ഴ "retroflex approximant" = zha (= NLK ≅ ALA-LC ழ = ḻ but ೞ = l̤) ;; ("n_" "ṉ") ;; tamil/malaylm NNNA ऩ ನ಼ ன ഩ "alveolar n" (= NLK = ALA-LC) ;; ("k_" "ḵ") ;; tamil aytham (= ISO15919) ;; ("t_" "ṯ") ;; bengali ৎ (maybe) ;; ;; ;; ;; Indo-Aryan ;; ("r:" "r̤") ;; ड़ (Devanagari DDDHA), ড়, ੜ, ଡ଼ (Bengali, Gurmukhi, Oriya RRA) "retroflex flap" (missing in NLK, ALA-LC uses ṛ) ;; ("r:h" "r̤h") ;; ढ़, ঢ়, ଢ଼ (Devanagari, Bengali, Oriya RHA) "aspirated retroflex flap" (missing in NLK, ALA-LC uses ṛh) ;; ("r;" "ṙ") ;; better alternative because pre-composed + reuse "dot above" ;; ("h_" "ẖ") ;; jihvamuliya (= ALA-LC) ;; ("h;" "ḣ") ;; upadhmaniya (≠ ALA-LC = GRETIL = ḫ) ;; ("e." "ẹ") ;; ऍ ઍ candra E (≠ ALA-LC = NLK = ê). Note ALA uses ॲ for ऍ ;; ("o." "ọ") ;; ऑ ઑ candra O (≠ ALC-LC = NLK = ô) ;; ;; ;; ;; Urdu loanwords (all follow ALA-LC Hindi & Punjabi) ;; ;; q k_h_ g; g;h z f t: s: h: