From fea0bcccf81692ab4e7bcb2a2e60793a2247daff Mon Sep 17 00:00:00 2001 From: Philipp Gesang Date: Sat, 27 Feb 2010 22:37:27 +0100 Subject: Initial commit. --- tex/context/interface/third/t-transliterator.xml | 46 + .../third/transliterator/t-transliterator.mkiv | 2057 ++++++++++++++++++++ .../third/transliterator/t-transliterator.tex | 1 + 3 files changed, 2104 insertions(+) create mode 100644 tex/context/interface/third/t-transliterator.xml create mode 100644 tex/context/third/transliterator/t-transliterator.mkiv create mode 100644 tex/context/third/transliterator/t-transliterator.tex (limited to 'tex/context') diff --git a/tex/context/interface/third/t-transliterator.xml b/tex/context/interface/third/t-transliterator.xml new file mode 100644 index 0000000..2ffb449 --- /dev/null +++ b/tex/context/interface/third/t-transliterator.xml @@ -0,0 +1,46 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/tex/context/third/transliterator/t-transliterator.mkiv b/tex/context/third/transliterator/t-transliterator.mkiv new file mode 100644 index 0000000..fc07c1d --- /dev/null +++ b/tex/context/third/transliterator/t-transliterator.mkiv @@ -0,0 +1,2057 @@ +%D \enableregime[utf] +%D \module +%D [ file=t-degrade, +%D version=2010.02.26, +%D title=\CONTEXT\ User Module, +%D subtitle=The Transliterator, +%D author=Philipp Gesang, +%D date=\currentdate, +%D copyright=Philipp Gesang, +%D license=2-clause BSD, +%D email={pgesang at ix dot urz dot uni-heidelberg dot de}] +%D This module is licensed under the conditions of the BSD license with +%D two clauses: http://www.freebsd.org/copyright/freebsd-license.html. +%D Substitute /OWNER/Philipp Gesang/; /YEAR/2010/.\newpage + +\writestatus{loading}{Transliteration from non-Latin scripts} + +\startmodule[transliterator] + +\unprotect + +%D Use the Transliterator by adding \type{\usemodule[transliterator]} somewhere +%D before \type{\starttext}. Adjust the Transliterator through the +%D \type{\setupTranslit} command. As a first argument it accepts a set of +%D key-value options; at present you may configure \type{mode} and +%D \type{hyphenate}. +\def\setupTranslit[#1]{\getparameters[TRL][#1]} + +%D At first we'll set some defaults: +\setupTranslit[mode=ru_old,hyphenate=cz,debug=false] +%D Possible values for \type{mode} are by the time of this writing: +%D \type{ru}, \type{ru_transcript_de}, \type{ru_transcript_en}, \type{ru_old}, +%D \type{all}, \type{iso9_ocs}, \type{ocs}, \type{ocs_gla}, \type{ru_cz}, +%D \type{ocs_cz}, \type{gr} and \type{gr_n}. +%D Possible values for \type{hyphenate} are all valid \CONTEXT\ language code, for an +%D overview see \type{http://wiki.contextgarden.net/Language_Codes}. +%D In praxi you may want to choose either Czech (the default) or Slovak +%D (\type{sk}) for most transliterations from cyrillic scripts. I've not yet +%D made up my mind concerning Greek transliteration, any suggestions are +%D welcome. + +%D For clarity's sake we'll stuff everything Lua into one table. +\startluacode +translit = translit or {} +translit.debug_count = 0 +\stopluacode + +%D We want to keep track of all the tables we'll create so we put them into +%D a separate dictionary accompanied by a description string. +\startluacode +translit.tables = {} +\stopluacode + + +%D Next we define respective lists of vowels and consonants as used in the +%D russian alphabet. They are needed later when substitution tables for some +%D idiosyncratic transcriptions are generated. +\startluacode +-- If you haven't heard of cyrillic scripts until now you might want to read +-- at least the first 15 pages of +-- http://www.uni-giessen.de/partosch/eurotex99/berdnikov2.pdf +-- before you continue reading this file. + +translit.ru_vowels = {"а", "е", "ё", "и", "й", "о", "у", "ы", "э", "ю", "я", + "А", "Е", "Ё", "И", "Й", "О", "У", "Ы", "Э", "Ю", "Я"} +translit.ru_consonants = {"б", "в", "г", "д", "ж", "з", "к", "л", "м", "н", + "п", "р", "с", "т", "ф", "х", "ц", "ч", "ш", "щ", + "Б", "В", "Г", "Д", "Ж", "З", "К", "Л", "М", "Н", + "П", "Р", "С", "Т", "Ф", "Х", "Ц", "Ч", "Ш", "Щ"} +\stopluacode + +%D Substitution tables are the very heart of the Transliterator. Due to the +%D nature of languages and scripts exhaustive substitution is the simplest +%D method for transliterations and transcriptions unless they are one-to-one +%D mappings like those defined in ISO~9. +%D +%D To achieve better reusability we split the tables into segments, the most +%D obvious being the \type{*_low} and \type{*_upp} variants for sets of lowercase +%D and uppercase characters. Another set is constituted by e.~g. the +%D \type{ru_old*} tables that allow adding transcription of historical +%D characters if needed; by the way those are included in the default +%D transliteration mode \type{ru_old}. + +%-===========================================================================-- +%- ISO 9.1995(E) standardized transliteration for cyrillic -- +%-===========================================================================-- + +\startluacode +----------------------------------------- +-- Lowercase russian cyrillic alphabet -- +----------------------------------------- +translit.ru_low = { + ["а"] = "a", -- U+0430 -> U+0061 + ["б"] = "b", -- U+0431 -> U+0062 + ["в"] = "v", -- U+0432 -> U+0076 + ["г"] = "g", -- U+0433 -> U+0067 + ["д"] = "d", -- U+0434 -> U+0064 + ["е"] = "e", -- U+0435 -> U+0065 + ["ё"] = "ë", -- U+0451 -> U+00eb + ["ж"] = "ž", -- U+0436 -> U+017e + ["з"] = "z", -- U+0437 -> U+007a + ["и"] = "i", -- U+0438 -> U+0069 + ["й"] = "j", -- U+0439 -> U+006a + ["к"] = "k", -- U+043a -> U+006b + ["л"] = "l", -- U+043b -> U+006c + ["м"] = "m", -- U+043c -> U+006d + ["н"] = "n", -- U+043d -> U+006e + ["о"] = "o", -- U+043e -> U+006f + ["п"] = "p", -- U+043f -> U+0070 + ["р"] = "r", -- U+0440 -> U+0072 + ["с"] = "s", -- U+0441 -> U+0073 + ["т"] = "t", -- U+0442 -> U+0074 + ["у"] = "u", -- U+0443 -> U+0075 + ["ф"] = "f", -- U+0444 -> U+0066 + ["х"] = "h", -- U+0445 -> U+0068 + ["ц"] = "c", -- U+0446 -> U+0063 + ["ч"] = "č", -- U+0447 -> U+010d + ["ш"] = "š", -- U+0448 -> U+0161 + ["щ"] = "ŝ", -- U+0449 -> U+015d + ["ъ"] = "ʺ", -- U+044a -> U+02ba <- That's somewhat ambiguous as 0x2ba is + ["ы"] = "y", -- U+044b -> U+0079 used for uppercase, too. + ["ь"] = "ʹ", -- U+044c -> U+02b9 <- Same here with 0x2b9. + ["э"] = "è", -- U+044d -> U+00e8 + ["ю"] = "û", -- U+044e -> U+00fb + ["я"] = "â" -- U+044f -> U+00e2 +} + +translit.tables["russian lowercase ISO~9"] = translit.ru_low + +----------------------------------------- +-- Uppercase russian cyrillic alphabet -- +----------------------------------------- + +translit.ru_upp = { + ["А"] = "A", -- U+0410 -> U+0041 + ["Б"] = "B", -- U+0411 -> U+0042 + ["В"] = "V", -- U+0412 -> U+0056 + ["Г"] = "G", -- U+0413 -> U+0047 + ["Д"] = "D", -- U+0414 -> U+0044 + ["Е"] = "E", -- U+0415 -> U+0045 + ["Ё"] = "Ë", -- U+0401 -> U+00cb + ["Ж"] = "Ž", -- U+0416 -> U+017d + ["З"] = "Z", -- U+0417 -> U+005a + ["И"] = "I", -- U+0418 -> U+0049 + ["Й"] = "J", -- U+0419 -> U+004a + ["К"] = "K", -- U+041a -> U+004b + ["Л"] = "L", -- U+041b -> U+004c + ["М"] = "M", -- U+041c -> U+004d + ["Н"] = "N", -- U+041d -> U+004e + ["О"] = "O", -- U+041e -> U+004f + ["П"] = "P", -- U+041f -> U+0050 + ["Р"] = "R", -- U+0420 -> U+0052 + ["С"] = "S", -- U+0421 -> U+0053 + ["Т"] = "T", -- U+0422 -> U+0054 + ["У"] = "U", -- U+0423 -> U+0055 + ["Ф"] = "F", -- U+0424 -> U+0046 + ["Х"] = "H", -- U+0425 -> U+0048 + ["Ц"] = "C", -- U+0426 -> U+0043 + ["Ч"] = "Č", -- U+0427 -> U+010c + ["Ш"] = "Š", -- U+0428 -> U+0160 + ["Щ"] = "Ŝ", -- U+0429 -> U+015c + ["Ъ"] = "ʺ", -- U+042a -> U+02ba + ["Ы"] = "Y", -- U+042b -> U+0059 + ["Ь"] = "ʹ", -- U+042c -> U+02b9 + ["Э"] = "È", -- U+042d -> U+00c8 + ["Ю"] = "Û", -- U+042e -> U+00db + ["Я"] = "Â" -- U+042f -> U+00c2 +} + +translit.tables["russian uppercase ISO~9"] = translit.ru_upp + +---------------------------------------------------------- +-- Lowercase pre-1918 russian cyrillic additional chars -- +---------------------------------------------------------- +-- cf. http://www.russportal.ru/index.php?id=oldorth.decret1917 + +translit.ru_old_low = { + ["ѣ"] = "ě", -- U+048d -> U+011b + ["і"] = "ì", -- U+0456 -> U+00ec + ["ѳ"] = "f", -- U+0473 -> U+0066 + ["ѵ"] = "ỳ", -- U+0475 -> U+1ef3 +} + +translit.tables["russian pre-1918 lowercase ISO~9"] = translit.ru_low + +translit.ru_old_upp = { + ["Ѣ"] = "Ě", -- U+048c -> U+011a + ["І"] = "Ì", -- U+0406 -> U+00cc + ["Ѳ"] = "F", -- U+0424 -> U+0046 + ["Ѵ"] = "Ỳ", -- U+0474 -> U+1ef2 +} + +translit.tables["russian pre-1918 uppercase ISO~9"] = translit.ru_upp + +--------------------------------------------------------- +-- Lowercase characters from other cyrillic alphabets -- +--------------------------------------------------------- + +translit.non_ru_low = { + ["ӑ"] = "ă", -- U+04d1 -> U+0103 + ["ӓ"] = "ä", -- U+04d3 -> U+00e4 + ["ә"] = "a̋", -- u+04d9 -> U+0061+030b + ["ґ"] = "g̀", -- u+0491 -> U+0067+0300 + ["ҕ"] = "ğ", -- U+0495 -> U+011f + ["ғ"] = "ġ", -- U+0493 -> U+0121 + ["ђ"] = "đ", -- U+0452 -> U+0111 + ["ѓ"] = "ǵ", -- U+0453 -> U+01f5 + ["ӗ"] = "ĕ", -- U+04d7 -> U+0115 + ["є"] = "ê", -- U+0454 -> U+00ea + ["ҽ"] = "c̆", -- U+04bd -> U+0063+0306 + ["ҿ"] = "ç̆", -- U+04bf -> U+00e7+0306 + ["ӂ"] = "z̆", -- U+04c2 -> U+007a+0306 + ["ӝ"] = "z̄", -- U+04dd -> U+007a+0304 + ["җ"] = "ž̧", -- U+0497 -> U+017e+0327 + ["ӟ"] = "z̈", -- U+04df -> U+007a+0308 + ["ѕ"] = "ẑ", -- U+0455 -> U+1e91 -- Mapped to dz in old cyrillic non-ISO. + ["ӡ"] = "ź", -- U+04e1 -> U+017a + ["ӥ"] = "î", -- U+04e5 -> U+00ee + ["і"] = "ì", -- U+0456 -> U+00ec + ["ї"] = "ï", -- U+0457 -> U+00ef + ["ј"] = "ǰ", -- U+0458 -> U+01f0 + ["қ"] = "ķ", -- U+049b -> U+0137 + ["ҟ"] = "k̄", -- U+049f -> U+006b+0304 + ["љ"] = "l̂", -- U+0459 -> U+006c+0302 + ["њ"] = "n̂", -- U+045a -> U+006e+0302 + ["ҥ"] = "ṅ", -- U+04a5 -> U+1e45 + ["ң"] = "ṇ", -- U+04a3 -> U+1e47 + ["ӧ"] = "ö", -- U+04e7 -> U+00f6 + ["ө"] = "ô", -- U+04e9 -> U+00f4 + ["ҧ"] = "ṕ", -- U+04a7 -> U+1e55 + ["ҫ"] = "ç", -- U+04ab -> U+00e7 + ["ҭ"] = "ţ", -- U+04ad -> U+0163 + ["ћ"] = "ć", -- U+045b -> U+0107 + ["ќ"] = "ḱ", -- U+045c -> U+1e31 + ["у́"] = "ú", -- U+0443+ -> U+00fA + ["ў"] = "ŭ", -- U+045e -> U+016d + ["ӱ"] = "ü", -- U+04f1 -> U+00fc + ["ӳ"] = "ű", -- U+04f3 -> U+0171 + ["ү"] = "ù", -- U+04af -> U+00f9 + ["ҳ"] = "ḩ", -- U+04b3 -> U+1e29 + ["һ"] = "ḥ", -- U+04bb -> U+1e25 + ["ҵ"] = "c̄", -- U+04b5 -> U+0063+0304 + ["ӵ"] = "c̈", -- U+04f5 -> U+0063+0308 + ["ҷ"] = "ç", -- U+04cc -> U+00e7 + ["џ"] = "d̂", -- U+045f -> U+0064+0302 + ["ӹ"] = "ÿ", -- U+04f9 -> U+00ff + ["ѣ"] = "ě", -- U+048d -> U+011b + ["ѫ"] = "ǎ", -- U+046b -> U+01ce -- Mapped to ǫ in non-ISO old cyrillic. + ["ѳ"] = "f̀", -- U+0473 -> U+0066+0300 -- This is mapped to ‘f’ in ru_old. + ["ѵ"] = "ỳ", -- U+0475 -> U+1ef3 + ["ҩ"] = "ò", -- U+04a9 -> U+00f2 + ["Ӏ"] = "‡" -- U+04cf -> U+2021 +} + +translit.tables["cyrillic other lowercase ISO~9"] = translit.non_ru_low + +--------------------------------------------------------- +-- Uppercase characters from other cyrillic alphabets -- +--------------------------------------------------------- + +translit.non_ru_upp = { + ["Ӑ"] = "Ă", -- U+04d0 -> U+0102 + ["Ӓ"] = "Ä", -- U+04d2 -> U+00c4 + ["Ә"] = "A̋", -- U+04d8 -> U+0041+030b + ["Ґ"] = "G̀", -- U+0490 -> U+0047+0300 + ["Ҕ"] = "Ğ", -- U+0494 -> U+011e + ["Ғ"] = "Ġ", -- U+0492 -> U+0120 + ["Ђ"] = "Đ", -- U+0402 -> U+0110 + ["Ѓ"] = "Ǵ", -- U+0403 -> U+01f4 + ["Ӗ"] = "Ĕ", -- U+04d6 -> U+0114 + ["Є"] = "Ê", -- U+0404 -> U+00ca + ["Ҽ"] = "C̆", -- U+04bc -> U+0043+0306 + ["Ҿ"] = "Ç̆", -- U+04be -> U+00c7+0306 + ["Ӂ"] = "Z̆", -- U+04c1 -> U+005a+0306 + ["Ӝ"] = "Z̄", -- U+04dc -> U+005a+0304 + ["Җ"] = "Ž̦", -- U+0496 -> U+017d+0326 + ["Ӟ"] = "Z̈", -- U+04de -> U+005a+0308 + ["Ѕ"] = "Ẑ", -- U+0405 -> U+1e90 + ["Ӡ"] = "Ź", -- U+04e0 -> U+0179 + ["Ӥ"] = "Î", -- U+04e4 -> U+00ce + ["І"] = "Ì", -- U+0406 -> U+00cc + ["Ї"] = "Ï", -- U+0407 -> U+00cf + ["Ј"] = "J̌", -- U+0408 -> U+004a+030c + ["Қ"] = "Ķ", -- U+049a -> U+0136 + ["Ҟ"] = "K̄", -- U+049e -> U+004b+0304 + ["Љ"] = "L̂", -- U+0409 -> U+004c+0302 + ["Њ"] = "N̂", -- U+040a -> U+004e+0302 + ["Ҥ"] = "Ṅ", -- U+04a4 -> U+1e44 + ["Ң"] = "Ṇ", -- U+04a2 -> U+1e46 + ["Ӧ"] = "Ö", -- U+04e6 -> U+00d6 + ["Ө"] = "Ô", -- U+04e8 -> U+00d4 + ["Ҧ"] = "Ṕ", -- U+04a6 -> U+1e54 + ["Ҫ"] = "Ç", -- U+04aa -> U+00c7 + ["Ҭ"] = "Ţ", -- U+04ac -> U+0162 + ["Ћ"] = "Ć", -- U+040b -> U+0106 + ["Ќ"] = "Ḱ", -- U+040c -> U+1e30 + ["У́"] = "Ú", -- U+0423 -> U+00da + ["Ў"] = "Ŭ", -- U+040e -> U+016c + ["Ӱ"] = "Ü", -- U+04f0 -> U+00dc + ["Ӳ"] = "Ű", -- U+04f2 -> U+0170 + ["Ү"] = "Ù", -- U+04ae -> U+00d9 + ["Ҳ"] = "Ḩ", -- U+04b2 -> U+1e28 + ["Һ"] = "Ḥ", -- U+04ba -> U+1e24 + ["Ҵ"] = "C̄", -- U+04b4 -> U+0043+0304 + ["Ӵ"] = "C̈", -- U+04f4 -> U+0043+0308 + ["Ҷ"] = "Ç", -- U+04cb -> U+00c7 + ["Џ"] = "D̂", -- U+040f -> U+0044+0302 + ["Ӹ"] = "Ÿ", -- U+04f8 -> U+0178 + ["Ѣ"] = "Ě", -- U+048c -> U+011a + ["Ѫ"] = "Ǎ", -- U+046a -> U+01cd + ["Ѳ"] = "F̀", -- U+0472 -> U+0046+0300 + ["Ѵ"] = "Ỳ", -- U+0474 -> U+1ef2 + ["Ҩ"] = "Ò", -- U+04a8 -> U+00d2 + ["’"] = "‵", -- U+2035 -> U+2019 + ["Ӏ"] = "‡" -- U+04c0 -> U+2021 +} + +translit.tables["cyrillic other uppercase ISO~9"] = translit.non_ru_upp + +\stopluacode + +\startluacode + +--===========================================================================-- +-- Legacy national transliterations -- +--===========================================================================-- +-- Note: +-- Use these only as a last resort. ‘Vulgar’ transcription is ugly and +-- chauvinistic. + +--------------------------------- +-- German simple transcription -- +--------------------------------- +-- Reference: „DUDEN. Rechtschreibung der deutschen Sprache“; 20. Aufl., +-- Mannheim et. al. 1991. + +-------------------------------------------------------- +-- Lowercase German simple transcription---first pass -- +-------------------------------------------------------- + +translit.ru_trsc_low_first = { + [" е"] = " je", + ["ъе"] = "je", + ["ье"] = "je", + [" ё"] = " jo", + ["ъё"] = "jo", + ["ьё"] = "jo", + ["жё"] = "scho", + ["чё"] = "tscho", + ["шё"] = "scho", + ["щё"] = "schtscho", + ["ье"] = "je", + ["ьи"] = "ji", + ["ьо"] = "jo", + ["ий"] = "i", + ["ый"] = "y", + ["кс"] = "x" -- Extraordinarily stupid one. +} + +translit.tables["German transcription first pass lowercase"] = translit.ru_trsc_low_first + +-------------------------------------------------------- +-- Uppercase German simple transcription---first pass -- +-------------------------------------------------------- + +translit.ru_trsc_upp_first = { + [" Е"] = " Je", + ["Ъe"] = "Je", -- Pedantic, isn't it? + ["Ье"] = "Je", + [" Ё"] = "Jo", + ["Ъё"] = "Jo", + ["Ьё"] = "Jo", + ["Жё"] = "Scho", + ["Чё"] = "Tscho", + ["Шё"] = "Scho", + ["Щё"] = "Schtscho", + ["Кс"] = "ks" +} + +translit.tables["German transcription first pass uppercase"] = translit.ru_trsc_upp_first + +------------------------------------------- +-- Lowercase German simple transcription -- +------------------------------------------- + +translit.ru_trsc_low = { + ["а"] = "a", + ["б"] = "b", + ["в"] = "w", + ["г"] = "g", + ["д"] = "d", + ["е"] = "e", + ["ё"] = "jo", + ["ж"] = "sch", + ["з"] = "s", + ["и"] = "i", + ["й"] = "i", + ["к"] = "k", + ["л"] = "l", + ["м"] = "m", + ["н"] = "n", + ["о"] = "o", + ["п"] = "p", + ["р"] = "r", + ["с"] = "s", + ["т"] = "t", + ["у"] = "u", + ["ф"] = "f", + ["х"] = "ch", + ["ц"] = "z", + ["ч"] = "tsch", + ["ш"] = "sch", + ["щ"] = "schtsch", + ["ъ"] = "", + ["ы"] = "y", + ["ь"] = "", + ["э"] = "e", + ["ю"] = "ju", + ["я"] = "ja" +} + +translit.tables["German transcription second pass lowercase"] = translit.ru_trsc_low + +------------------------------------------- +-- Uppercase German simple transcription -- +------------------------------------------- + +translit.ru_trsc_upp = { + ["А"] = "A", + ["Б"] = "B", + ["В"] = "W", + ["Г"] = "G", + ["Д"] = "D", + ["Е"] = "E", + ["Ё"] = "Jo", + ["Ж"] = "Sch", + ["З"] = "S", + ["И"] = "I", + ["Й"] = "J", + ["К"] = "K", + ["Л"] = "L", + ["М"] = "M", + ["Н"] = "N", + ["О"] = "O", + ["П"] = "P", + ["Р"] = "R", + ["С"] = "S", + ["Т"] = "T", + ["У"] = "U", + ["Ф"] = "F", + ["Х"] = "Ch", + ["Ц"] = "Z", + ["Ч"] = "Tsch", + ["Ш"] = "Sch", + ["Щ"] = "Schtsch", + ["Ъ"] = "", + ["Ы"] = "Y", + ["Ь"] = "", + ["Э"] = "E", + ["Ю"] = "Ju", + ["Я"] = "Ja" +} + +translit.tables["German transcription second pass uppercase"] = translit.ru_trsc_upp + +\stopluacode + +%D The following are more interesting than the previous tables because they +%D implement various rules. For instance the table +%D \type{translit.ru_trsc_irule} holds a substitution dictionary for all +%D possible combinations (including nonsense galore) of a vowel preceding an +%D “й” (Russian short i) preceding a consonant; here we access the sets of +%D Russian vowels as well consonants that were defined earlier. + +\startluacode +-- The й-rule, VйC -> ViC +translit.ru_trsc_irule = {} +for i, vow in ipairs(translit.ru_vowels) do + for j, cons in ipairs(translit.ru_consonants) do + local new_ante = vow .. "й" .. cons + local new_post = vow .. "i" .. cons + translit.ru_trsc_irule[new_ante] = new_post + end +end + +translit.tables["German transcription i-rule"] = translit.ru_trsc_irule + +-- The second й-rule, йV -> jV && [иы]йC -> [иы]jC +translit.ru_trsc_jrule = {} +for i, vow in ipairs(translit.ru_vowels) do + local new_ante = "й" .. vow + local new_post = "j" .. vow + translit.ru_trsc_jrule[new_ante] = new_post +end + +translit.ru_trsc_iy = {"и", "ы", "И", "Ы"} +for i, cons in ipairs(translit.ru_consonants) do + for j, iy in ipairs(translit.ru_trsc_iy) do + local new_ante = iy .. "й" .. cons + local new_post = iy .. "j" .. cons + translit.ru_trsc_jrule[new_ante] = new_post + end +end + +translit.tables["German transcription j-rule"] = translit.ru_trsc_jrule + +-- The с-rule, VсV -> VssV +translit.ru_trsc_srule = {} +for i, vow_1 in ipairs(translit.ru_vowels) do +for j, vow_2 in ipairs(translit.ru_vowels) do + local new_ante = vow_1 .. "с" .. vow_2 + local new_post = vow_1 .. "ss" .. vow_2 + translit.ru_trsc_srule[new_ante] = new_post + end +end + +translit.tables["German transcription s-rule"] = translit.ru_trsc_srule + +-- The sharp-s-rule, Vсх -> Vßх +translit.ru_trsc_sharpsrule = {} +for i, vow in ipairs(translit.ru_vowels) do + local new_ante = vow .. "сх" + local new_post = vow .. "ßх" + translit.ru_trsc_sharpsrule[new_ante] = new_post +end + +translit.tables["German transcription sharp-s-rule"] = translit.ru_trsc_sharpsrule + +-- The е-rule, Vе -> Vje +translit.ru_trsc_jerule = {} +for i, vow in ipairs(translit.ru_vowels) do + local new_ante = vow .. "е" + local new_post = vow .. "je" + translit.ru_trsc_jerule[new_ante] = new_post +end + +translit.tables["German transcription je-rule"] = translit.ru_trsc_jerule + +-- The ё-rule, Vё -> Vjo +-- This should be redundant as [жцчшщ]ё -> o, else ё -> jo . +-- Somebody should teach those DUDEN-guys parsimony. +translit.ru_trsc_jorule = {} +for i, vow in ipairs(translit.ru_vowels) do + local new_ante = vow .. "ё" + local new_post = vow .. "jo" + translit.ru_trsc_jorule[new_ante] = new_post +end + +translit.tables["German transcription (redundant) jo-rule"] = translit.ru_trsc_jorule + +\stopluacode + +\startluacode + +--------------------------------------------------------- +-- Lowercase English simple transcription---first pass -- +--------------------------------------------------------- + +translit.ru_trsc_en_low_first = { + [" е"] = " ye", + ["ъе"] = "ye", + ["ье"] = "ye", + ["ье"] = "ye", + ["ьи"] = "yi", +} + +translit.tables["English transcription lowercase first pass"] = translit.ru_trsc_en_low_first + +--------------------------------------------------------- +-- Uppercase English simple transcription---first pass -- +--------------------------------------------------------- + +translit.ru_trsc_en_upp_first = { + [" Е"] = " Ye", + ["Ъe"] = "Ye", + ["Ье"] = "Ye", +} + +translit.tables["English transcription uppercase first pass"] = translit.ru_trsc_en_upp_first + +-------------------------------------------- +-- Lowercase English simple transcription -- +-------------------------------------------- + +translit.ru_trsc_en_low = { + ["а"] = "a", + ["б"] = "b", + ["в"] = "v", + ["г"] = "g", + ["д"] = "d", + ["е"] = "e", + ["ё"] = "e", + ["ж"] = "zh", + ["з"] = "z", + ["и"] = "i", + ["й"] = "y", + ["к"] = "k", + ["л"] = "l", + ["м"] = "m", + ["н"] = "n", + ["о"] = "o", + ["п"] = "p", + ["р"] = "r", + ["с"] = "s", + ["т"] = "t", + ["у"] = "u", + ["ф"] = "f", + ["х"] = "kh", + ["ц"] = "ts", + ["ч"] = "ch", + ["ш"] = "sh", + ["щ"] = "shsh", + ["ъ"] = "", + ["ы"] = "y", + ["ь"] = "", + ["э"] = "e", + ["ю"] = "yu", + ["я"] = "ya" +} + +translit.tables["English transcription lowercase second pass"] = translit.ru_trsc_en_low + +-------------------------------------------- +-- Uppercase English simple transcription -- +-------------------------------------------- + +translit.ru_trsc_en_upp = { + ["А"] = "A", + ["Б"] = "B", + ["В"] = "V", + ["Г"] = "G", + ["Д"] = "D", + ["Е"] = "E", + ["Ё"] = "E", + ["Ж"] = "Zh", + ["З"] = "Z", + ["И"] = "I", + ["Й"] = "Y", + ["К"] = "K", + ["Л"] = "L", + ["М"] = "M", + ["Н"] = "N", + ["О"] = "O", + ["П"] = "P", + ["Р"] = "R", + ["С"] = "S", + ["Т"] = "T", + ["У"] = "U", + ["Ф"] = "F", + ["Х"] = "Kh", + ["Ц"] = "Ts", + ["Ч"] = "Ch", + ["Ш"] = "Sh", + ["Щ"] = "Shsh", + ["Ъ"] = "", + ["Ы"] = "Y", + ["Ь"] = "", + ["Э"] = "E", + ["Ю"] = "Yu", + ["Я"] = "Ya" +} + +translit.tables["English transcription uppercase second pass"] = translit.ru_trsc_en_upp + +-- The english е-rule, Vе -> Vye +translit.ru_trsc_en_jerule = {} +for i, vow in ipairs(translit.ru_vowels) do + local new_ante = vow .. "е" + local new_post = vow .. "ye" + translit.ru_trsc_en_jerule[new_ante] = new_post +end + +translit.tables["English transcription ye-rule"] = translit.ru_trsc_en_jerule + +\stopluacode + +\startluacode + +----------------------------------- +-- Lowercase Czech transcription -- +----------------------------------- + +translit.ru_trsc_cz_low = { + ["а"] = "a", + ["б"] = "b", + ["в"] = "v", + ["г"] = "g", + ["д"] = "d", + ["е"] = "e", + ["ё"] = "ë", + ["ж"] = "ž", + ["з"] = "z", + ["и"] = "i", + ["й"] = "j", + ["к"] = "k", + ["л"] = "l", + ["м"] = "m", + ["н"] = "n", + ["о"] = "o", + ["п"] = "p", + ["р"] = "r", + ["с"] = "s", + ["т"] = "t", + ["у"] = "u", + ["ф"] = "f", + ["х"] = "ch", + ["ц"] = "c", + ["ч"] = "č", + ["ш"] = "š", + ["щ"] = "šč", + ["ъ"] = "ъ", + ["ы"] = "y", + ["ь"] = "ь", + ["э"] = "è", + ["ю"] = "ju", -- Maybe we should do things like ню -> ňu and тя -> ťa, but + ["я"] = "ja" -- that would complicate things a bit and linguists might not +} -- agree. + +translit.tables["Czech transcription lowercase"] = translit.ru_trsc_cz_low + +----------------------------------- +-- Uppercase Czech transcription -- +----------------------------------- + +translit.ru_trsc_cz_upp = { + ["А"] = "A", + ["Б"] = "B", + ["В"] = "V", + ["Г"] = "G", + ["Д"] = "D", + ["Е"] = "E", + ["Ё"] = "Ë", + ["Ж"] = "Ž", + ["З"] = "Z", + ["И"] = "I", + ["Й"] = "J", + ["К"] = "K", + ["Л"] = "L", + ["М"] = "M", + ["Н"] = "N", + ["О"] = "O", + ["П"] = "P", + ["Р"] = "R", + ["С"] = "S", + ["Т"] = "T", + ["У"] = "U", + ["Ф"] = "F", + ["Х"] = "Ch", + ["Ц"] = "C", + ["Ч"] = "Č", + ["Ш"] = "Š", + ["Щ"] = "Šč", + ["Ъ"] = "Ъ", + ["Ы"] = "Y", + ["Ь"] = "Ь", + ["Э"] = "È", + ["Ю"] = "Ju", + ["Я"] = "Ja" +} + +translit.tables["Czech transcription uppercase"] = translit.ru_trsc_cz_upp + +---------------------------------------------- +-- Lowercase Additional Czech Transcription -- +---------------------------------------------- + +translit.ru_trsc_cz_add_low = { + ["ѕ"] = "dz", + ["і"] = "ï", + ["ѹ"] = "u", + ["ѡ"] = "ō", + ["ѣ"] = "ě", + ["ѥ"] = "je", + ["ѧ"] = "ę", + ["ѩ"] = "ję", + ["ѫ"] = "ǫ", + ["ѭ"] = "jǫ", + ["ѯ"] = "ks", + ["ѱ"] = "ps", + ["ѳ"] = "th", + ["ѵ"] = "ÿ", +} + +translit.tables["Czech transcription for OCS and pre-1918 lowercase"] = translit.ru_trsc_cz_add_low + + +---------------------------------------------- +-- Uppercase Additional Czech Transcription -- +---------------------------------------------- + +translit.ru_trsc_cz_add_upp = { + ["Ѕ"] = "Dz", + ["І"] = "Ï", + ["Ѹ"] = "U", + ["Ѡ"] = "Ō", + ["Ѣ"] = "Ě", + ["Ѥ"] = "Je", + ["Ѧ"] = "Ę", + ["Ѩ"] = "Ję", + ["Ѫ"] = "Ǫ", + ["Ѭ"] = "Jǫ", + ["Ѯ"] = "Ks", + ["Ѱ"] = "Ps", + ["Ѳ"] = "Th", + ["Ѵ"] = "Ÿ", +} + +translit.tables["Czech transcription for OCS and pre-1918 uppercase"] = translit.ru_trsc_cz_add_upp + +\stopluacode + +%-===========================================================================-- +%- Other transliterations -- +%-===========================================================================-- + +\startluacode + +-- The following are needed because ISO 9 does not cover old Slavonic +-- characters that became obsolete before the advent of гражданский шрифт. + +-- Please note that these mappings are not bijective so don't expect the result +-- to be easily revertible (by machines). + +-- Source p. 77 of +-- http://www.schaeken.nl/lu/research/online/publications/akslstud/as2_03_kapitel_c.pdf + +----------------------------------------------------------------------------- +-- Lowercase pre-Peter cyrillic characters -- “scientific transliteration” -- +----------------------------------------------------------------------------- + +translit.ocs_low = { + ["а"] = "a", + ["б"] = "b", + ["в"] = "v", + ["г"] = "g", + ["д"] = "d", + ["є"] = "e", + ["ж"] = "ž", + ["ꙃ"] = "ʒ", -- U+0292, alternative: dz U+01f3 + ["ѕ"] = "ʒ", + ["ꙁ"] = "z", + ["з"] = "z", + ["и"] = "i", + ["і"] = "i", + ["ї"] = "i", + ["ћ"] = "g’", + ["к"] = "k", + ["л"] = "l", + ["м"] = "m", + ["н"] = "n", + ["о"] = "o", + ["п"] = "p", + ["р"] = "r", + ["с"] = "s", + ["т"] = "t", + ["оу"] = "u", + ["ѹ"] = "u", + ["ꙋ"] = "u", + ["ф"] = "f", + ["х"] = "x", + ["ѡ"] = "o", --"ō", + ["ѿ"] = "ot", -- U+047f + ["ѽ"] = "o!", -- U+047d + ["ꙍ"] = "o!", -- U+064D + ["ц"] = "c", + ["ч"] = "č", + ["ш"] = "š", + ["щ"] = "št", + ["ъ"] = "ъ", + ["ы"] = "y", + ["ꙑ"] = "y", -- Old jery (U+a651) as used e.g. by the OCS Wikipedia. + ["ь"] = "ь", + ["ѣ"] = "ě", + ["ю"] = "ju", + ["ꙗ"] = "ja", + ["ѥ"] = "je", + ["ѧ"] = "ę", + ["ѩ"] = "ję", + ["ѫ"] = "ǫ", + ["ѭ"] = "jǫ", + ["ѯ"] = "ks", + ["ѱ"] = "ps", + ["ѳ"] = "th", + ["ѵ"] = "ü", +} + +translit.tables["OCS \\quotation{scientific} transliteration lowercase"] = translit.ocs_low + +----------------------------------------------------------------------------- +-- Uppercase pre-Peter cyrillic characters -- “scientific transliteration” -- +----------------------------------------------------------------------------- + +translit.ocs_upp = { + ["А"] = "A", + ["Б"] = "B", + ["В"] = "V", + ["Г"] = "G", + ["Д"] = "D", + ["Є"] = "E", + ["Ж"] = "Ž", + ["Ꙃ"] = "Ʒ", -- U+01b7, alternative: Dz U+01f2 + ["Ѕ"] = "Ʒ", + ["Ꙁ"] = "Z", + ["З"] = "Z", + ["И"] = "I", + ["І"] = "I", + ["Ї"] = "I", + ["Ћ"] = "G’", + ["К"] = "K", + ["Л"] = "L", + ["М"] = "M", + ["Н"] = "N", + ["О"] = "O", + ["П"] = "P", + ["Р"] = "R", + ["С"] = "S", + ["Т"] = "T", + ["Оу"] = "U", + ["Ѹ"] = "U", + ["ꙋ"] = "U", + ["Ф"] = "F", + ["Х"] = "X", + ["Ѡ"] = "Ō", + ["Ѿ"] = "Ot", -- U+047c + ["Ѽ"] = "O!", -- U+047e + ["Ꙍ"] = "O!", -- U+064C + ["Ц"] = "C", + ["Ч"] = "Č", + ["Ш"] = "Š", + ["Щ"] = "Št", + ["Ъ"] = "Ŭ", + ["Ы"] = "Y", + ["Ꙑ"] = "Y", -- U+a650 + ["Ь"] = "Ĭ", + ["Ѣ"] = "Ě", + ["Ю"] = "Ju", + ["Ꙗ"] = "Ja", + ["Ѥ"] = "Je", + ["Ѧ"] = "Ę", + ["Ѩ"] = "Ję", + ["Ѫ"] = "Ǫ", + ["Ѭ"] = "Jǫ", + ["Ѯ"] = "Ks", + ["Ѱ"] = "Ps", + ["Ѳ"] = "Th", + ["Ѵ"] = "Ü", +} + +translit.tables["OCS \\quotation{scientific} transliteration uppercase"] = translit.ocs_upp + +-- Note on the additional tables: these cover characters that are not defined +-- in ISO 9 but have a “scientific” transliteration. You may use them as +-- complementary mapping to ISO 9, trading off homogenity for completeness. + +---------------------------------------------------------------------------------------- +-- Lowercase additional pre-Peter cyrillic characters -- “scientific transliteration” -- +---------------------------------------------------------------------------------------- + +translit.ocs_add_low = { + ["ѕ"] = "dz", -- Mapped to ẑ in ISO 9 (Macedonian …) + ["ѯ"] = "ks", + ["ѱ"] = "ps", + ["ѡ"] = "ô", + ["ѫ"] = "ǫ", -- Mapped to ǎ in ISO 9. + ["ѧ"] = "ę", + ["ѭ"] = "jǫ", + ["ѩ"] = "ję", + ["ѥ"] = "je", + ["ѹ"] = "u", -- Digraph uk. + ["ꙋ"] = "u", -- Monograph uk, U+a64b. (No glyph yet in the "fixed" font in February 2010 …) + ["ꙑ"] = "y", -- U+a651 +} + +translit.tables["OCS \\quotation{scientific} transliteration additional lowercase"] = translit.ocs_add_low + +---------------------------------------------------------------------------------------- +-- Uppercase additional pre-Peter cyrillic characters -- “scientific transliteration” -- +---------------------------------------------------------------------------------------- + +translit.ocs_add_upp = { + ["Ѕ"] = "Dz", + ["Ѯ"] = "Ks", + ["Ѱ"] = "Ps", + ["Ѡ"] = "Ô", + ["Ѫ"] = "Ǫ", + ["Ѧ"] = "Ę", + ["Ѭ"] = "Jǫ", + ["Ѩ"] = "Ję", + ["Ѥ"] = "Je", + ["Ѹ"] = "U", -- Digraph uk. + ["Ꙋ"] = "U", -- Monograph Uk, U+a64a. + ["Ꙑ"] = "Y", -- U+a650 +} + +translit.tables["OCS \\quotation{scientific} transliteration additional uppercase"] = translit.ocs_add_upp + + +\stopluacode + +%-===========================================================================-- +%- Glagolica -- +%-===========================================================================-- + +\startluacode + +------------------------------------------- +-- Lowercase Glagolitic Transliteration -- +------------------------------------------- + +translit.ocs_gla_low = { + ["ⰰ"] = "a", -- GLAGOLITIC SMALL LETTER AZU + ["ⰱ"] = "b", -- GLAGOLITIC SMALL LETTER BUKY + ["ⰲ"] = "v", -- GLAGOLITIC SMALL LETTER VEDE + ["ⰳ"] = "g", -- GLAGOLITIC SMALL LETTER GLAGOLI + ["ⰴ"] = "d", -- GLAGOLITIC SMALL LETTER DOBRO + ["ⰵ"] = "e", -- GLAGOLITIC SMALL LETTER YESTU + ["ⰶ"] = "ž", -- GLAGOLITIC SMALL LETTER ZHIVETE + ["ⰷ"] = "ʒ", -- GLAGOLITIC SMALL LETTER DZELO + ["ⰸ"] = "z", -- GLAGOLITIC SMALL LETTER ZEMLJA + ["ⰹ"] = "i", -- GLAGOLITIC SMALL LETTER IZHE + ["ⰺ"] = "i", -- GLAGOLITIC SMALL LETTER INITIAL IZHE + ["ⰻ"] = "i", -- GLAGOLITIC SMALL LETTER I + ["ⰼ"] = "g’", -- GLAGOLITIC SMALL LETTER DJERVI + ["ⰽ"] = "k", -- GLAGOLITIC SMALL LETTER KAKO + ["ⰾ"] = "l", -- GLAGOLITIC SMALL LETTER LJUDIJE + ["ⰿ"] = "m", -- GLAGOLITIC SMALL LETTER MYSLITE + ["ⱀ"] = "n", -- GLAGOLITIC SMALL LETTER NASHI + ["ⱁ"] = "o", -- GLAGOLITIC SMALL LETTER ONU + ["ⱂ"] = "p", -- GLAGOLITIC SMALL LETTER POKOJI + ["ⱃ"] = "r", -- GLAGOLITIC SMALL LETTER RITSI + ["ⱄ"] = "s", -- GLAGOLITIC SMALL LETTER SLOVO + ["ⱅ"] = "t", -- GLAGOLITIC SMALL LETTER TVRIDO + ["ⱆ"] = "u", -- GLAGOLITIC SMALL LETTER UKU + ["ⱇ"] = "f", -- GLAGOLITIC SMALL LETTER FRITU + ["ⱈ"] = "x", -- GLAGOLITIC SMALL LETTER HERU + ["ⱉ"] = "o", -- GLAGOLITIC SMALL LETTER OTU + ["ⱊ"] = "?", -- GLAGOLITIC SMALL LETTER PE + ["ⱋ"] = "št", -- GLAGOLITIC SMALL LETTER SHTA + ["ⱌ"] = "c", -- GLAGOLITIC SMALL LETTER TSI + ["ⱍ"] = "č", -- GLAGOLITIC SMALL LETTER CHRIVI + ["ⱎ"] = "š", -- GLAGOLITIC SMALL LETTER SHA + ["ⱏ"] = "ъ", -- GLAGOLITIC SMALL LETTER YERU + ["ⱐ"] = "ь", -- GLAGOLITIC SMALL LETTER YERI + ["ⱑ"] = "ě", -- GLAGOLITIC SMALL LETTER YATI + ["ⱒ"] = "x", -- GLAGOLITIC SMALL LETTER SPIDERY HA + ["ⱓ"] = "ju", -- GLAGOLITIC SMALL LETTER YU + ["ⱔ"] = "ę", -- GLAGOLITIC SMALL LETTER SMALL YUS + ["ⱕ"] = "y̨", -- GLAGOLITIC SMALL LETTER SMALL YUS WITH TAIL + ["ⱖ"] = "??", -- GLAGOLITIC SMALL LETTER YO + ["ⱗ"] = "ję", -- GLAGOLITIC SMALL LETTER IOTATED SMALL YU + ["ⱘ"] = "ǫ", -- GLAGOLITIC SMALL LETTER BIG YUS + ["ⱙ"] = "jǫ", -- GLAGOLITIC SMALL LETTER IOTATED BIG YUS + ["ⱚ"] = "th", -- GLAGOLITIC SMALL LETTER FITA + ["ⱛ"] = "ü", -- GLAGOLITIC SMALL LETTER IZHITSA + ["ⱜ"] = "??", -- GLAGOLITIC SMALL LETTER SHTAPIC + ["ⱝ"] = "??", -- GLAGOLITIC SMALL LETTER TROKUTASTI A + ["ⱞ"] = "m", -- GLAGOLITIC SMALL LETTER LATINATE MYSLITE +} + +translit.tables["Glagolica transliteration for OCS lowercase"] = translit.ocs_gla_low + +------------------------------------------------ +-- Uppercase (?!) Glagolitic Transliteration -- +------------------------------------------------ + +translit.ocs_gla_upp = { + ["Ⰰ"] = "A", -- GLAGOLITIC CAPITAL LETTER AZU + ["Ⰱ"] = "B", -- GLAGOLITIC CAPITAL LETTER BUKY + ["Ⰲ"] = "V", -- GLAGOLITIC CAPITAL LETTER VEDE + ["Ⰳ"] = "G", -- GLAGOLITIC CAPITAL LETTER GLAGOLI + ["Ⰴ"] = "D", -- GLAGOLITIC CAPITAL LETTER DOBRO + ["Ⰵ"] = "E", -- GLAGOLITIC CAPITAL LETTER YESTU + ["Ⰶ"] = "Ž", -- GLAGOLITIC CAPITAL LETTER ZHIVETE + ["Ⰷ"] = "Ʒ", -- GLAGOLITIC CAPITAL LETTER DZELO + ["Ⰸ"] = "Z", -- GLAGOLITIC CAPITAL LETTER ZEMLJA + ["Ⰹ"] = "I", -- GLAGOLITIC CAPITAL LETTER IZHE + ["Ⰺ"] = "I", -- GLAGOLITIC CAPITAL LETTER INITIAL IZHE + ["Ⰻ"] = "I", -- GLAGOLITIC CAPITAL LETTER I + ["Ⰼ"] = "G’", -- GLAGOLITIC CAPITAL LETTER DJERVI + ["Ⰽ"] = "K", -- GLAGOLITIC CAPITAL LETTER KAKO + ["Ⰾ"] = "L", -- GLAGOLITIC CAPITAL LETTER LJUDIJE + ["Ⰿ"] = "M", -- GLAGOLITIC CAPITAL LETTER MYSLITE + ["Ⱀ"] = "N", -- GLAGOLITIC CAPITAL LETTER NASHI + ["Ⱁ"] = "O", -- GLAGOLITIC CAPITAL LETTER ONU + ["Ⱂ"] = "P", -- GLAGOLITIC CAPITAL LETTER POKOJI + ["Ⱃ"] = "R", -- GLAGOLITIC CAPITAL LETTER RITSI + ["Ⱄ"] = "S", -- GLAGOLITIC CAPITAL LETTER SLOVO + ["Ⱅ"] = "T", -- GLAGOLITIC CAPITAL LETTER TVRIDO + ["Ⱆ"] = "U", -- GLAGOLITIC CAPITAL LETTER UKU + ["Ⱇ"] = "F", -- GLAGOLITIC CAPITAL LETTER FRITU + ["Ⱈ"] = "X", -- GLAGOLITIC CAPITAL LETTER HERU + ["Ⱉ"] = "O", -- GLAGOLITIC CAPITAL LETTER OTU + ["Ⱊ"] = "?", -- GLAGOLITIC CAPITAL LETTER PE + ["Ⱋ"] = "Št", -- GLAGOLITIC CAPITAL LETTER SHTA + ["Ⱌ"] = "C", -- GLAGOLITIC CAPITAL LETTER TSI + ["Ⱍ"] = "Č", -- GLAGOLITIC CAPITAL LETTER CHRIVI + ["Ⱎ"] = "Š", -- GLAGOLITIC CAPITAL LETTER SHA + ["Ⱏ"] = "Ъ", -- GLAGOLITIC CAPITAL LETTER YERU + ["Ⱐ"] = "Ь", -- GLAGOLITIC CAPITAL LETTER YERI + ["Ⱑ"] = "Ě", -- GLAGOLITIC CAPITAL LETTER YATI + ["Ⱒ"] = "X", -- GLAGOLITIC CAPITAL LETTER SPIDERY HA + ["Ⱓ"] = "Ju", -- GLAGOLITIC CAPITAL LETTER YU + ["Ⱔ"] = "Ę", -- GLAGOLITIC CAPITAL LETTER SMALL YUS + ["Ⱕ"] = "Y̨", -- GLAGOLITIC CAPITAL LETTER SMALL YUS WITH TAIL + ["Ⱖ"] = "??", -- GLAGOLITIC CAPITAL LETTER YO + ["Ⱗ"] = "Ję", -- GLAGOLITIC CAPITAL LETTER IOTATED SMALL YUS + ["Ⱘ"] = "Ǫ", -- GLAGOLITIC CAPITAL LETTER BIG YUS + ["Ⱙ"] = "Jǫ", -- GLAGOLITIC CAPITAL LETTER IOTATED BIG YUS + ["Ⱚ"] = "Th", -- GLAGOLITIC CAPITAL LETTER FITA + ["Ⱛ"] = "Ü", -- GLAGOLITIC CAPITAL LETTER IZHITSA + ["Ⱜ"] = "??", -- GLAGOLITIC CAPITAL LETTER SHTAPIC + ["Ⱝ"] = "??", -- GLAGOLITIC CAPITAL LETTER TROKUTASTI A + ["Ⱞ"] = "M", -- GLAGOLITIC CAPITAL LETTER LATINATE MYSLIT +} + +translit.tables["Glagolica transliteration for OCS uppercase"] = translit.ocs_gla_upp + +\stopluacode + +%-===========================================================================-- +%- Greek -- +%-===========================================================================-- + +\startluacode + +-- Note that the Greek transliteration mapping isn't bijective so transliterated +-- texts won't be reversible. (Shouldn't be impossible to make one up using +-- diacritics on latin characters to represent all possible combinations of +-- Greek breathings + accents.) + +-- Good reading on composed / precombined unicode: +-- http://www.tlg.uci.edu/~opoudjis/unicode/unicode_gaps.html#precomposed + +------------------------------------------------- +-- Lowercase Greek Initial Position Diphthongs -- +------------------------------------------------- + +translit.gr_di_in_low = { + [" αὑ"] = " hau", + [" αὕ"] = " hau", + [" αὓ"] = " hau", + [" αὗ"] = " hau", + [" εὑ"] = " heu", + [" εὕ"] = " heu", + [" εὓ"] = " heu", + [" εὗ"] = " heu", + [" ηὑ"] = " hēu", + [" ηὕ"] = " hēu", + [" ηὓ"] = " hēu", + [" ηὗ"] = " hēu", + [" οὑ"] = " hu", + [" οὕ"] = " hu", + [" οὓ"] = " hu", + [" οὗ"] = " hu", + [" ωὑ"] = " hōu", + [" ωὕ"] = " hōu", + [" ωὓ"] = " hōu", + [" ωὗ"] = " hōu" +} + +translit.tables["Greek transliteration initial breathing diphthongs lowercase"] = translit.gr_di_in_low + +------------------------------------------------- +-- Uppercase Greek Initial Position Diphthongs -- +------------------------------------------------- + +translit.gr_di_in_upp = { + [" Αὑ"] = " Hau", + [" Αὕ"] = " Hau", + [" Αὓ"] = " Hau", + [" Αὗ"] = " Hau", + [" Εὑ"] = " Heu", + [" Εὕ"] = " Heu", + [" Εὓ"] = " Heu", + [" Εὗ"] = " Heu", + [" Ηὑ"] = " Hēu", + [" Ηὕ"] = " Hēu", + [" Ηὓ"] = " Hēu", + [" Ηὗ"] = " Hēu", + [" Οὑ"] = " Hu", + [" Οὕ"] = " Hu", + [" Οὓ"] = " Hu", + [" Οὗ"] = " Hu", + [" Ωὑ"] = " Hōu", + [" Ωὕ"] = " Hōu", + [" Ωὓ"] = " Hōu", + [" Ωὗ"] = " Hōu" +} + +translit.tables["Greek transliteration initial breathing diphthongs uppercase"] = translit.gr_di_in_upp + +--------------------------------------- +-- Lowercase Greek Initial Position -- +--------------------------------------- + +translit.gr_in_low = { + [" ἁ"] = " ha", + [" ἅ"] = " ha", + [" ἃ"] = " ha", + [" ἇ"] = " ha", + [" ᾁ"] = " ha", + [" ᾅ"] = " ha", + [" ᾃ"] = " ha", + [" ᾇ"] = " ha", + [" ἑ"] = " he", + [" ἕ"] = " he", + [" ἓ"] = " he", + [" ἡ"] = " hē", + [" ἥ"] = " hē", + [" ἣ"] = " hē", + [" ἧ"] = " hē", + [" ᾑ"] = " hē", + [" ᾕ"] = " hē", + [" ᾓ"] = " hē", + [" ᾗ"] = " hē", + [" ἱ"] = " hi", + [" ἵ"] = " hi", + [" ἳ"] = " hi", + [" ἷ"] = " hi", + [" ὁ"] = " ho", + [" ὅ"] = " ho", + [" ὃ"] = " ho", + [" ὑ"] = " hy", + [" ὕ"] = " hy", + [" ὓ"] = " hy", + [" ὗ"] = " hy", + [" ὡ"] = " hō", + [" ὥ"] = " hō", + [" ὣ"] = " hō", + [" ὧ"] = " hō", + [" ᾡ"] = " hō", + [" ᾥ"] = " hō", + [" ᾣ"] = " hō", + [" ᾧ"] = " hō", +} + +translit.tables["Greek transliteration initial breathing lowercase"] = translit.gr_in_low + +--------------------------------------- +-- Uppercase Greek Initial Position -- +--------------------------------------- + +translit.gr_in_upp = { + [" Ἁ"] = " Ha", + [" Ἅ"] = " Ha", + [" Ἃ"] = " Ha", + [" Ἇ"] = " Ha", + [" ᾉ"] = " Ha", + [" ᾍ"] = " Ha", + [" ᾋ"] = " Ha", + [" ᾏ"] = " Ha", + [" Ἑ"] = " He", + [" Ἕ"] = " He", + [" Ἓ"] = " He", + [" Ἡ"] = " Hē", + [" Ἥ"] = " Hē", + [" Ἣ"] = " Hē", + [" Ἧ"] = " Hē", + [" ᾙ"] = " Hē", + [" ᾝ"] = " Hē", + [" ᾛ"] = " Hē", + [" ᾟ"] = " Hē", + [" Ἱ"] = " Hi", + [" Ἵ"] = " Hi", + [" Ἳ"] = " Hi", + [" Ἷ"] = " Hi", + [" Ὁ"] = " Ho", + [" Ὅ"] = " Ho", + [" Ὃ"] = " Ho", + [" Ὑ"] = " Hy", + [" Ὕ"] = " Hy", + [" Ὓ"] = " Hy", + [" Ὗ"] = " Hy", + [" Ὡ"] = " Hō", + [" Ὥ"] = " Hō", + [" Ὣ"] = " Hō", + [" Ὧ"] = " Hō", + [" ᾩ"] = " Hō", + [" ᾭ"] = " Hō", + [" ᾫ"] = " Hō", + [" ᾯ"] = " Hō", +} + +translit.tables["Greek transliteration initial breathing uppercase"] = translit.gr_in_upp + +--------------------------------- +-- Lowercase Greek Diphthongs -- +--------------------------------- + +translit.gr_di_low = { + ["αυ"] = "au", + ["αύ"] = "au", + ["αὺ"] = "au", + ["αῦ"] = "au", + ["αὐ"] = "au", + ["αὔ"] = "au", + ["αὒ"] = "au", + ["αὖ"] = "au", + ["αὑ"] = "au", + ["αὕ"] = "au", + ["αὓ"] = "au", + ["αὗ"] = "au", + ["ευ"] = "eu", + ["εύ"] = "eu", + ["εὺ"] = "eu", + ["εῦ"] = "eu", + ["εὐ"] = "eu", + ["εὔ"] = "eu", + ["εὒ"] = "eu", + ["εὖ"] = "eu", + ["εὑ"] = "eu", + ["εὕ"] = "eu", + ["εὓ"] = "eu", + ["εὗ"] = "eu", + ["ηυ"] = "ēu", + ["ηύ"] = "ēu", + ["ηὺ"] = "ēu", + ["ηῦ"] = "ēu", + ["ηὐ"] = "ēu", + ["ηὔ"] = "ēu", + ["ηὒ"] = "ēu", + ["ηὖ"] = "ēu", + ["ηὑ"] = "ēu", + ["ηὕ"] = "ēu", + ["ηὓ"] = "ēu", + ["ηὗ"] = "ēu", + ["ου"] = "u", + ["ου"] = "u", + ["ου"] = "u", + ["ού"] = "u", + ["οὺ"] = "u", + ["οῦ"] = "u", + ["οὐ"] = "u", + ["οὔ"] = "u", + ["οὒ"] = "u", + ["οὖ"] = "u", + ["οὑ"] = "u", + ["οὕ"] = "u", + ["οὓ"] = "u", + ["οὗ"] = "u", + ["ωυ"] = "ōu", + ["ωύ"] = "ōu", + ["ωὺ"] = "ōu", + ["ωῦ"] = "ōu", + ["ωὐ"] = "ōu", + ["ωὔ"] = "ōu", + ["ωὒ"] = "ōu", + ["ωὖ"] = "ōu", + ["ωὑ"] = "ōu", + ["ωὕ"] = "ōu", + ["ωὓ"] = "ōu", + ["ωὗ"] = "ōu", + ["ῤῥ"] = "rrh", +} + +translit.tables["Greek transliteration diphthongs lowercase"] = translit.gr_in_low + +--------------------------------- +-- Uppercase Greek Diphthongs -- +--------------------------------- + +translit.gr_di_upp = { + ["Αυ"] = "Au", + ["Αύ"] = "Au", + ["Αὺ"] = "Au", + ["Αῦ"] = "Au", + ["Αὐ"] = "Au", + ["Αὔ"] = "Au", + ["Αὒ"] = "Au", + ["Αὖ"] = "Au", + ["Αὑ"] = "Au", + ["Αὕ"] = "Au", + ["Αὓ"] = "Au", + ["Αὗ"] = "Au", + ["Ευ"] = "Eu", + ["Εύ"] = "Eu", + ["Εὺ"] = "Eu", + ["Εῦ"] = "Eu", + ["Εὐ"] = "Eu", + ["Εὔ"] = "Eu", + ["Εὒ"] = "Eu", + ["Εὖ"] = "Eu", + ["Εὑ"] = "Eu", + ["Εὕ"] = "Eu", + ["Εὓ"] = "Eu", + ["Εὗ"] = "Eu", + ["Ηυ"] = "Ēu", + ["Ηύ"] = "Ēu", + ["Ηὺ"] = "Ēu", + ["Ηῦ"] = "Ēu", + ["Ηὐ"] = "Ēu", + ["Ηὔ"] = "Ēu", + ["Ηὒ"] = "Ēu", + ["Ηὖ"] = "Ēu", + ["Ηὑ"] = "Ēu", + ["Ηὕ"] = "Ēu", + ["Ηὓ"] = "Ēu", + ["Ηὗ"] = "Ēu", + ["Ου"] = "U", + ["Ου"] = "U", + ["Ου"] = "U", + ["Ού"] = "U", + ["Οὺ"] = "U", + ["Οῦ"] = "U", + ["Οὐ"] = "U", + ["Οὔ"] = "U", + ["Οὒ"] = "U", + ["Οὖ"] = "U", + ["Οὑ"] = "U", + ["Οὕ"] = "U", + ["Οὓ"] = "U", + ["Οὗ"] = "U", + ["Ωυ"] = "Ōu", + ["Ωύ"] = "Ōu", + ["Ωὺ"] = "Ōu", + ["Ωῦ"] = "Ōu", + ["Ωὐ"] = "Ōu", + ["Ωὔ"] = "Ōu", + ["Ωὒ"] = "Ōu", + ["Ωὖ"] = "Ōu", + ["Ωὑ"] = "Ōu", + ["Ωὕ"] = "Ōu", + ["Ωὓ"] = "Ōu", + ["Ωὗ"] = "Ōu", +} + +translit.tables["Greek transliteration diphthongs uppercase"] = translit.gr_in_upp + +-- The following will be used in an option that ensures transcription of +-- nasalization, e.g. Ἁγχίσης -> “Anchises” (instead of “Agchises”) +translit.gr_nrule = { + ["γγ"] = "ng", + ["γκ"] = "nk", + ["γξ"] = "nx", + ["γχ"] = "nch", +} + +translit.tables["Greek transliteration optional nasalization"] = translit.gr_nrule + +\stopluacode + +\startluacode + +-------------------------------------- +-- Lowercase Greek Transliteration -- +-------------------------------------- + +translit.gr_low = { + ["α"] = "a", + ["ά"] = "a", + ["ὰ"] = "a", + ["ᾶ"] = "a", + ["ᾳ"] = "a", + ["ἀ"] = "a", + ["ἁ"] = "a", + ["ἄ"] = "a", + ["ἂ"] = "a", + ["ἆ"] = "a", + ["ἁ"] = "a", + ["ἅ"] = "a", + ["ἃ"] = "a", + ["ἇ"] = "a", + ["ᾁ"] = "a", + ["ᾴ"] = "a", + ["ᾲ"] = "a", + ["ᾷ"] = "a", + ["ᾄ"] = "a", + ["ᾂ"] = "a", + ["ᾅ"] = "a", + ["ᾃ"] = "a", + ["ᾆ"] = "a", + ["ᾇ"] = "a", + ["β"] = "b", + ["γ"] = "g", + ["δ"] = "d", + ["ε"] = "e", + ["έ"] = "e", + ["ὲ"] = "e", + ["ἐ"] = "e", + ["ἔ"] = "e", + ["ἒ"] = "e", + ["ἑ"] = "e", + ["ἕ"] = "e", + ["ἓ"] = "e", + ["ζ"] = "z", + ["η"] = "ē", + ["η"] = "ē", + ["ή"] = "ē", + ["ὴ"] = "ē", + ["ῆ"] = "ē", + ["ῃ"] = "ē", + ["ἠ"] = "ē", + ["ἤ"] = "ē", + ["ἢ"] = "ē", + ["ἦ"] = "ē", + ["ᾐ"] = "ē", + ["ἡ"] = "ē", + ["ἥ"] = "ē", + ["ἣ"] = "ē", + ["ἧ"] = "ē", + ["ᾑ"] = "ē", + ["ῄ"] = "ē", + ["ῂ"] = "ē", + ["ῇ"] = "ē", + ["ᾔ"] = "ē", + ["ᾒ"] = "ē", + ["ᾕ"] = "ē", + ["ᾓ"] = "ē", + ["ᾖ"] = "ē", + ["ᾗ"] = "ē", + ["θ"] = "th", + ["ι"] = "i", + ["ί"] = "i", + ["ὶ"] = "i", + ["ῖ"] = "i", + ["ἰ"] = "i", + ["ἴ"] = "i", + ["ἲ"] = "i", + ["ἶ"] = "i", + ["ἱ"] = "i", + ["ἵ"] = "i", + ["ἳ"] = "i", + ["ἷ"] = "i", + ["ϊ"] = "i", + ["ΐ"] = "i", + ["ῒ"] = "i", + ["ῗ"] = "i", + ["κ"] = "k", + ["λ"] = "l", + ["μ"] = "m", + ["ν"] = "n", + ["ξ"] = "x", + ["ο"] = "o", + ["ό"] = "o", + ["ὸ"] = "o", + ["ὀ"] = "o", + ["ὄ"] = "o", + ["ὂ"] = "o", + ["ὁ"] = "o", + ["ὅ"] = "o", + ["ὃ"] = "o", + ["π"] = "p", + ["ρ"] = "r", + ["ῤ"] = "r", + ["ῥ"] = "rh", + ["σ"] = "s", + ["ς"] = "s", + ["τ"] = "t", + ["υ"] = "y", + ["ύ"] = "y", + ["ὺ"] = "y", + ["ῦ"] = "y", + ["ὐ"] = "y", + ["ὔ"] = "y", + ["ὒ"] = "y", + ["ὖ"] = "y", + ["ὑ"] = "y", + ["ὕ"] = "y", + ["ὓ"] = "y", + ["ὗ"] = "y", + ["ϋ"] = "y", + ["ΰ"] = "y", + ["ῢ"] = "y", + ["ῧ"] = "y", + ["φ"] = "ph", + ["χ"] = "ch", + ["ψ"] = "ps", + ["ω"] = "ō", + ["ώ"] = "ō", + ["ὼ"] = "ō", + ["ῶ"] = "ō", + ["ῳ"] = "ō", + ["ὠ"] = "ō", + ["ὤ"] = "ō", + ["ὢ"] = "ō", + ["ὦ"] = "ō", + ["ᾠ"] = "ō", + ["ὡ"] = "ō", + ["ὥ"] = "ō", + ["ὣ"] = "ō", + ["ὧ"] = "ō", + ["ᾡ"] = "ō", + ["ῴ"] = "ō", + ["ῲ"] = "ō", + ["ῷ"] = "ō", + ["ᾤ"] = "ō", + ["ᾢ"] = "ō", + ["ᾥ"] = "ō", + ["ᾣ"] = "ō", + ["ᾦ"] = "ō", + ["ᾧ"] = "ō", +} + +translit.tables["Greek transliteration lowercase"] = translit.gr_low + +-------------------------------------- +-- Uppercase Greek Transliteration -- +-------------------------------------- + +translit.gr_upp = { + ["Α"] = "A", + ["Ά"] = "A", + ["Ὰ"] = "A", +--["ᾶ"] = "A", + ["ᾼ"] = "A", + ["Ἀ"] = "A", + ["Ἁ"] = "A", + ["Ἄ"] = "A", + ["Ἂ"] = "A", + ["Ἆ"] = "A", + ["Ἁ"] = "A", + ["Ἅ"] = "A", + ["Ἃ"] = "A", + ["Ἇ"] = "A", + ["ᾉ"] = "A", +--["ᾴ"] = "A", -- I’d be very happy if anybody could explain to me +--["ᾲ"] = "A", -- why there's Ά, ᾌ and ᾼ but no “A + iota subscript +--["ᾷ"] = "A", -- + acute” …, same for Η, Υ and Ω + diacritica. + ["ᾌ"] = "A", + ["ᾊ"] = "A", + ["ᾍ"] = "A", + ["ᾋ"] = "A", + ["ᾎ"] = "A", + ["ᾏ"] = "A", + ["Β"] = "B", + ["Γ"] = "G", + ["Δ"] = "D", + ["Ε"] = "E", + ["Έ"] = "E", + ["Ὲ"] = "E", + ["Ἐ"] = "E", + ["Ἔ"] = "E", + ["Ἒ"] = "E", + ["Ἑ"] = "E", + ["Ἕ"] = "E", + ["Ἓ"] = "E", + ["Ζ"] = "Z", + ["Η"] = "Ē", + ["Η"] = "Ē", + ["Ή"] = "Ē", + ["Ὴ"] = "Ē", +--["ῆ"] = "Ē", + ["ῌ"] = "Ē", + ["Ἠ"] = "Ē", + ["Ἤ"] = "Ē", + ["Ἢ"] = "Ē", + ["Ἦ"] = "Ē", + ["ᾘ"] = "Ē", + ["Ἡ"] = "Ē", + ["Ἥ"] = "Ē", + ["Ἣ"] = "Ē", + ["Ἧ"] = "Ē", + ["ᾙ"] = "Ē", +--["ῄ"] = "Ē", +--["ῂ"] = "Ē", +--["ῇ"] = "Ē", + ["ᾜ"] = "Ē", + ["ᾚ"] = "Ē", + ["ᾝ"] = "Ē", + ["ᾛ"] = "Ē", + ["ᾞ"] = "Ē", + ["ᾟ"] = "Ē", + ["Θ"] = "Th", + ["Ι"] = "I", + ["Ί"] = "I", + ["Ὶ"] = "I", +--["ῖ"] = "I", + ["Ἰ"] = "I", + ["Ἴ"] = "I", + ["Ἲ"] = "I", + ["Ἶ"] = "I", + ["Ἱ"] = "I", + ["Ἵ"] = "I", + ["Ἳ"] = "I", + ["Ἷ"] = "I", + ["Ϊ"] = "I", +--["ΐ"] = "I", +--["ῒ"] = "I", +--["ῗ"] = "I", + ["Κ"] = "K", + ["Λ"] = "L", + ["Μ"] = "M", + ["Ν"] = "N", + ["Ξ"] = "X", + ["Ο"] = "O", + ["Ό"] = "O", + ["Ὸ"] = "O", + ["Ὀ"] = "O", + ["Ὄ"] = "O", + ["Ὂ"] = "O", + ["Ὁ"] = "O", + ["Ὅ"] = "O", + ["Ὃ"] = "O", + ["Π"] = "P", + ["Ρ"] = "R", +--["ῤ"] = "R", + ["Ῥ"] = "Rh", + ["Σ"] = "S", + ["Σ"] = "S", + ["Τ"] = "T", + ["Υ"] = "Y", + ["Ύ"] = "Y", + ["Ὺ"] = "Y", +--["ῦ"] = "Y", +--["ὐ"] = "Y", +--["ὔ"] = "Y", +--["ὒ"] = "Y", +--["ὖ"] = "Y", + ["Ὑ"] = "Y", + ["Ὕ"] = "Y", + ["Ὓ"] = "Y", + ["Ὗ"] = "Y", + ["Ϋ"] = "Y", +--["ΰ"] = "Y", +--["ῢ"] = "Y", +--["ῧ"] = "Y", + ["Φ"] = "Ph", + ["Χ"] = "Ch", + ["Ψ"] = "Ps", + ["Ω"] = "Ō", + ["Ώ"] = "Ō", + ["Ὼ"] = "Ō", +--["ῶ"] = "Ō", + ["ῼ"] = "Ō", + ["Ὠ"] = "Ō", + ["Ὤ"] = "Ō", + ["Ὢ"] = "Ō", + ["Ὦ"] = "Ō", + ["ᾨ"] = "Ō", + ["Ὡ"] = "Ō", + ["Ὥ"] = "Ō", + ["Ὣ"] = "Ō", + ["Ὧ"] = "Ō", + ["ᾩ"] = "Ō", +--["ῴ"] = "Ō", +--["ῲ"] = "Ō", +--["ῷ"] = "Ō", + ["ᾬ"] = "Ō", + ["ᾪ"] = "Ō", + ["ᾭ"] = "Ō", + ["ᾫ"] = "Ō", + ["ᾮ"] = "Ō", + ["ᾯ"] = "Ō", +} + +translit.tables["Greek transliteration uppercase"] = translit.gr_upp + +------------ +-- Varia -- +------------ + +translit.gr_other = { + ["ϝ"] = "w", + ["Ϝ"] = "W", + ["ϙ"] = "q", + ["Ϙ"] = "Q", + ["ϡ"] = "ss", + ["Ϡ"] = "Ss", +} + +translit.tables["Greek transliteration archaic characters"] = translit.gr_other + +\stopluacode + +%-===========================================================================-- +%- End Of Tables -- +%-===========================================================================-- + +%D The function \type{translit.subst(s, t)} is used to replace any key of +%D \type{t} that occurs in \type{s} with the according value of \type{t}. + +\startluacode + +function translit.subst (text, tab) + for symbol, replacement in pairs(tab) do + text = utf.gsub(text, symbol, replacement) + end + return text +end + +\stopluacode +%D \type{translit.add_table(t, ta)} is used to build the final substitution tables +%D from those we defined earlier; any keys in the previous table \type{t} are +%D overwritten if they exist in the added table \type{ta}, too. +\startluacode + +function translit.add_table (t, t_add) + for key, value in pairs (t_add) do + t[key] = value + end + return t +end + +\stopluacode +%D We might want to have all the table data nicely formatted by \CONTEXT\ +%D itself, here's how we'll do it. \type{translit.show_tab(t)} handles a +%D single table \type{t}, builds a Natural TABLE out of its content and +%D hands it down to the machine for typesetting. For debugging purposes it +%D does not only print the replacement pairs but shows their code points as +%D well. +\startluacode + +function translit.show_tab (tab) + -- Output a transliteration table, nicely formatted with natural tables. + local cnt = 0 + context ("\\setupTABLE[r][each] [style=\\tfx,align=center] ") + context ("\\setupTABLE[c][each] [frame=off]") + context ("\\setupTABLE[r][each] [frame=off]") + context ("\\setupTABLE[c][first] [style=italic]") + context ("\\setupTABLE[r][first] [style=bold,topframe=on,bottomframe=on]") + context ("\\setupTABLE[r][last] [style=bold,topframe=on,bottomframe=on]") + context ("\\bTABLE [split=yes,option=stretch]") + context ("\\bTABLEhead\\bTR".. + "\\bTH Number\\eTH" .. + "\\bTH letters\\eTH" .. + "\\bTH n\\eTH" .. + "\\bTH replacement\\eTH".. + "\\bTH n\\eTH" .. + "\\bTH bytes\\eTH".. + "\\bTH repl. bytes".. + "\\eTH\\eTR\\eTABLEhead ") + context("\\bTABLEbody") + for key, val in pairs(tab) do + local strempty = function (s) + -- Some characters might not be replaced but removed, others might be + -- multi-char sequences. + if #s == 0 then return "nil" + else + local i = 0 + local r = "" + -- The following loop could be replaced by checking the string length with utf.len(s) … + repeat + i = i + 1 + if utf.byte(s,i) == nil then break else r = r .. utf.byte(s,i) .. " " end + until (false) + return r + end + end + cnt = cnt + 1 + context ("\\bTR\\bTC " .. cnt .. "\\eTC") + context ("\\bTC " .. + key .. "\\eTC\\bTC " .. + utf.len(key) .. "\\eTC\\bTC " .. + val .. "\\eTC\\bTC " .. + utf.len(val) .. "\\eTC\\bTC " .. + strempty(key) .. "\\eTC\\bTC " .. + strempty(val) .. "\\eTC") + context ("\\eTR ") + end + context("\\eTABLEbody") + context ("\\bTABLEfoot\\bTR".. + "\\bTC Number\\eTC" .. + "\\bTC letters\\eTC" .. + "\\bTC n\\eTC" .. + "\\bTC replacement\\eTC".. + "\\bTC n\\eTC" .. + "\\bTC bytes\\eTC".. + "\\bTC repl. bytes".. + "\\eTC\\eTR\\eTABLEfoot ") + context ("\\eTABLE ") +end + +\stopluacode +%D Having to pick out single tables for printing can be tedious, therefore we +%D let Lua do the job in our stead. \type{translit.show_all_tabs()} calls +%D \type{translit.show_tab} on every table that is registered with +%D \type{translit.table} -- and uses its registered key as table heading. +\startluacode + +function translit.show_all_tabs () + -- Output all translation tables that are registered within translit.tables. + -- This will be quite unordered. + context ("\\chapter{Transliterator Showing All Tables}") + for key, val in pairs(translit.tables) do + context ("\\section{" .. key .. "}") + translit.show_tab (val) + end +end + +\stopluacode +%D Now to the function \type{translit.transliterate(m, t)}: it constitutes the +%D metafunction that is called by the \type{\transliterate} command and itself +%D chooses the substitution tables according to the \type{m} parameter and +%D applies them in a given order on the string \type{m}. +%D (The correct order in multi-pass substitution has to be enforced because the +%D tables are in fact unordered dictionaries.) +\startluacode + +function translit.transliterate (method, text) + local repl_tab = {} + if method == "ru" then + translit.add_table(repl_tab, translit.ru_upp) + translit.add_table(repl_tab, translit.ru_low) + elseif method == "ru_transcript_de" then + text = translit.subst (text, translit.ru_trsc_jrule) + text = translit.subst (text, translit.ru_trsc_irule) + text = translit.subst (text, translit.ru_trsc_srule) + text = translit.subst (text, translit.ru_trsc_sharpsrule) + text = translit.subst (text, translit.ru_trsc_jerule) +-- text = translit.subst (text, translit.ru_trsc_jorule) + translit.add_table(repl_tab, translit.ru_trsc_upp_first) + translit.add_table(repl_tab, translit.ru_trsc_low_first) + text = translit.subst (text, repl_tab) + repl_tab = {} + translit.add_table(repl_tab, translit.ru_trsc_upp) + translit.add_table(repl_tab, translit.ru_trsc_low) + elseif method == "ru_transcript_en" then + text = translit.subst (text, translit.ru_trsc_en_jerule) + translit.add_table(repl_tab, translit.ru_trsc_en_upp_first) + translit.add_table(repl_tab, translit.ru_trsc_en_low_first) + translit.add_table(repl_tab, translit.ru_trsc_en_upp) + translit.add_table(repl_tab, translit.ru_trsc_en_low) + elseif method == "ru_old" then + translit.add_table(repl_tab, translit.ru_upp) + translit.add_table(repl_tab, translit.ru_low) + translit.add_table(repl_tab, translit.ru_old_upp) + translit.add_table(repl_tab, translit.ru_old_low) + elseif method == "all" then + translit.add_table(repl_tab, translit.ru_upp) + translit.add_table(repl_tab, translit.ru_low) + translit.add_table(repl_tab, translit.ru_old_upp) + translit.add_table(repl_tab, translit.ru_old_low) + translit.add_table(repl_tab, translit.non_ru_upp) + translit.add_table(repl_tab, translit.non_ru_low) + elseif method == "iso9_ocs" then + translit.add_table(repl_tab, translit.ru_upp) + translit.add_table(repl_tab, translit.ru_low) + translit.add_table(repl_tab, translit.non_ru_upp) + translit.add_table(repl_tab, translit.non_ru_low) + translit.add_table(repl_tab, translit.ocs_add_upp) + translit.add_table(repl_tab, translit.ocs_add_low) + elseif method == "ocs" then + translit.add_table(repl_tab, translit.ocs_low) + translit.add_table(repl_tab, translit.ocs_upp) + elseif method == "ocs_gla" then + translit.add_table(repl_tab, translit.ocs_gla_low) + translit.add_table(repl_tab, translit.ocs_gla_upp) + elseif method == "ru_cz" then + translit.add_table(repl_tab, translit.ru_trsc_cz_low) + translit.add_table(repl_tab, translit.ru_trsc_cz_upp) + elseif method == "ocs_cz" then + translit.add_table(repl_tab, translit.ru_trsc_cz_low) + translit.add_table(repl_tab, translit.ru_trsc_cz_upp) + translit.add_table(repl_tab, translit.ru_trsc_cz_add_low) + translit.add_table(repl_tab, translit.ru_trsc_cz_add_upp) + elseif method == "gr" then + translit.add_table(repl_tab, translit.gr_di_in_low) + translit.add_table(repl_tab, translit.gr_di_in_upp) + translit.add_table(repl_tab, translit.gr_in_low) + translit.add_table(repl_tab, translit.gr_in_upp) + text = translit.subst (text, repl_tab) + repl_tab = {} + translit.add_table(repl_tab, translit.gr_di_low) + translit.add_table(repl_tab, translit.gr_di_upp) + text = translit.subst (text, repl_tab) + repl_tab = {} + translit.add_table(repl_tab, translit.gr_low) + translit.add_table(repl_tab, translit.gr_upp) + translit.add_table(repl_tab, translit.gr_other) + elseif method == "gr_n" then + translit.add_table(repl_tab, translit.gr_di_in_low) + translit.add_table(repl_tab, translit.gr_di_in_upp) + translit.add_table(repl_tab, translit.gr_in_low) + translit.add_table(repl_tab, translit.gr_in_upp) + text = translit.subst (text, repl_tab) + repl_tab = {} + translit.add_table(repl_tab, translit.gr_di_low) + translit.add_table(repl_tab, translit.gr_di_upp) + translit.add_table(repl_tab, translit.gr_nrule) + text = translit.subst (text, repl_tab) + repl_tab = {} + translit.add_table(repl_tab, translit.gr_low) + translit.add_table(repl_tab, translit.gr_upp) + translit.add_table(repl_tab, translit.gr_other) + end + text = translit.subst (text, repl_tab) + tex.print (text) +end +\stopluacode + +%D The following will help debugging and reviewing tables. Make sure your +%D typescript can handle the characters, in general it's no use with Latin +%D Modern which unfortunately provides only a restricted set of the unicode +%D range. +%D +%D The user-level command to output a single substitution table is +%D \type{\showOneTranslitTab{#1}}. +\define[1]\showOneTranslitTab{% + \ctxlua{translit.show_tab(#1)}% +} + +%D The user-level command to output all defined tables is +%D \type{\showTranslitTabs{#1}}. +\define\showTranslitTabs{% + \ctxlua{translit.show_all_tabs()}% +} + +\startluacode +function translit.debug_next () + translit.debug_count = translit.debug_count + 1 + tex.print("\\tfxx{\\bf translit debug msg. nr.~" .. translit.debug_count .. "}") +end +\stopluacode + +\def\translitDebug#1{% + \doif{\TRLdebug}{true}{% + %\inmargin{\ctxlua{translit.debug_next()} #1}% Unreadable with too many debug messages. + {\ss\inmargin{\ctxlua{translit.debug_next()}} #1}% + }% +} + + +%D The user-level command \type{\transliterate[#1]{#2}} does the job of +%D switching to a given language (for hyphenation) and adjusting the +%D substitution method locally. It takes an optional list \type{[#1]} of +%D key-value arguments to allow ad-hoc specification of either two that deviate +%D from the defaults set initially by means of \type{\setupTranslit}. +%D +%D Internally, \type{\dotransliterate} is called according to the \CONTEXT\ +%D coding style and in case the user provides \type{hyphenate=} or +%D \type{mode=} those will be used instead of the globals. Note that this +%D leaves the latter unchanged. Thus, in order to permanently switch to +%D another transliteration style the user would have to set it by calling +%D \type{\setupTranslit} again. + +\def\dotransliterate[#1]#2{% + \iffirstargument% + \let\TRLlocalhyphenate\undefined% + \let\TRLlocalmode\undefined% + \getparameters[TRLlocal][#1]% + \ifcsname TRLlocalhyphenate\endcsname% + \translitDebug{\type{\TRLlocalhyphenate} expands to \TRLlocalhyphenate\ (global: \TRLhyphenate). }% + \language[\TRLlocalhyphenate]% + \else% + \translitDebug{\type{\TRLlocalhyphenate} is undefined. Using \TRLhyphenate instead. }% + \language[\TRLhyphenate]% + \fi% + \ifcsname TRLlocalmode\endcsname% + %\translitDebug{{\type{\TRLlocalmode} expands to \TRLlocalmode. }}% + \translitDebug{\type{\TRLlocalmode} is defined. }% + \ctxlua{translit.transliterate ("\TRLlocalmode", "#2")}% + \else% + \translitDebug{\type{\TRLlocalmode} is undefined. Using global \type{\TRLmode}. }% + \ctxlua{translit.transliterate ("\TRLmode", "#2")}% + \fi% + \else% + \language[\TRLhyphenate]% + \translitDebug{No translit options given. Using defaults. }% + \ctxlua{translit.transliterate ("\TRLmode", "#2")}% + \fi% +} + +\def\transliterate{\dosingleempty\dotransliterate} + +\protect + +% vim:ft=context diff --git a/tex/context/third/transliterator/t-transliterator.tex b/tex/context/third/transliterator/t-transliterator.tex new file mode 100644 index 0000000..c08e822 --- /dev/null +++ b/tex/context/third/transliterator/t-transliterator.tex @@ -0,0 +1 @@ +\loadmarkfile[t-transliterator] -- cgit v1.2.3