From 814b93d12bc9a0792b150527495ece0847a343fc Mon Sep 17 00:00:00 2001 From: Philipp Gesang Date: Sun, 21 Nov 2021 19:22:18 +0100 Subject: reorganize source tree --- src/t-transliterator.mkii | 3 + src/t-transliterator.mkiv | 188 ++++++++++ src/t-transliterator.tex | 1 + src/t-transliterator.xml | 63 ++++ src/trans_tables_bg.lua | 114 ++++++ src/trans_tables_glag.lua | 128 +++++++ src/trans_tables_gr.lua | 709 ++++++++++++++++++++++++++++++++++++ src/trans_tables_iso9.lua | 310 ++++++++++++++++ src/trans_tables_scntfc.lua | 287 +++++++++++++++ src/trans_tables_sr.lua | 241 ++++++++++++ src/trans_tables_trsc.lua | 867 ++++++++++++++++++++++++++++++++++++++++++++ src/transliterator.lua | 283 +++++++++++++++ 12 files changed, 3194 insertions(+) create mode 100644 src/t-transliterator.mkii create mode 100644 src/t-transliterator.mkiv create mode 100644 src/t-transliterator.tex create mode 100644 src/t-transliterator.xml create mode 100644 src/trans_tables_bg.lua create mode 100644 src/trans_tables_glag.lua create mode 100644 src/trans_tables_gr.lua create mode 100644 src/trans_tables_iso9.lua create mode 100644 src/trans_tables_scntfc.lua create mode 100644 src/trans_tables_sr.lua create mode 100644 src/trans_tables_trsc.lua create mode 100644 src/transliterator.lua (limited to 'src') diff --git a/src/t-transliterator.mkii b/src/t-transliterator.mkii new file mode 100644 index 0000000..2fcfb0b --- /dev/null +++ b/src/t-transliterator.mkii @@ -0,0 +1,3 @@ +% Suggested by Taco +\message{Module is unsupported under mkii} +\endinput diff --git a/src/t-transliterator.mkiv b/src/t-transliterator.mkiv new file mode 100644 index 0000000..ae08278 --- /dev/null +++ b/src/t-transliterator.mkiv @@ -0,0 +1,188 @@ +%D \module +%D [ file=t-transliterator, +%D version=2021-11-21 18:19:24+0100, +%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, there is a copy it in a file named "COPYING" in the +%D transliterator source tree. + +\writestatus{loading}{Transliteration from non-Latin scripts} + +\unprotect + +\definenamespace [TRL] [ + name=transliterate, + type=module, + setup=list, + parent=TRL, + style=no, + version=2021, + comment=Transliteration from non-Latin scripts., +] + +\ctxlua{environment.loadluafile ("transliterator")} + +%D Use the Transliterator by adding \type{\usemodule[transliterator]} somewhere +%D before \type{\starttext}. Adjust the Transliterator through the +%D \type{\setuptransliterate} 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\set_serbian_exceptions{% + \doifelse{\transliterateparameter{sr_exceptions}}\v!yes + {\ctxlua{thirddata.translit.sr_except = true}} + {\ctxlua{thirddata.translit.sr_except = false}}% +} + +\def\set_hinting{% + \doifelse{\transliterateparameter{hinting}}\v!yes + {\ctxlua{thirddata.translit.hinting = true}} + {\ctxlua{thirddata.translit.hinting = false}}% +} + +\appendtoks \set_serbian_exceptions \to \everysetuptransliterate +\appendtoks \set_hinting \to \everysetuptransliterate + +%D At first we'll set some defaults: + +\setuptransliterate[% + debug=\v!false, + hinting=\v!yes, + hyphenate=cz, + mode=ru_old, + sr_exceptions=\v!yes, + deficient_font=\v!no, +] + +%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 As not all fonts, even the expensive ones, support some of the most frequent +%D unicode signs used in ISO~9, there are fallbacks for the transliterations of +%D the weak and hard sign. +%D They work with the modes \type{iso9_ocs}, \type{all} and +%D \type{ru_old} only and can be triggered by setting the +%D variable \type{deficient_font} to the value {\em yes}. +%D This will transliterate {\em ь} and {\em ъ} (both upper and +%D lower case) to the more common, but non-ISO characters {\em ’} and {\em ”} +%D respectively. +%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 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{% + \startluacode + environment.loadluafile ("trans_tables_iso9") + environment.loadluafile ("trans_tables_trsc") + environment.loadluafile ("trans_tables_scntfc") + environment.loadluafile ("trans_tables_trsc") + environment.loadluafile ("trans_tables_glag") + environment.loadluafile ("trans_tables_gr") + thirddata.translit.gen_rules_en() + thirddata.translit.gen_rules_de() + thirddata.translit.show_tab(translit["\luaescapestring{#1}"]) + \stopluacode +} + +%D The user-level command to output all defined tables is +%D \type{\showTranslitTabs}. + +\define\showTranslitTabs{% + \ctxlua{thirddata.translit.show_all_tabs()}% +} + +\def\translitDebug#1{% + \doif{\transliterateparameter{debug}}{yes}{% + {\ss\inmargin{\ctxlua{thirddata.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{\setuptransliterate}. +%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{\setuptransliterate} again. +%D +% All credits for rewriting the TeX code go to Wolfgang as well. +% http://www.ntg.nl/pipermail/ntg-context/2010/047816.html + +\def\dotransliterate[#1]#2{% + \bgroup\iffirstargument + \setuptransliterate[#1]% + \fi + \language[\transliterateparameter{hyphenate}]% + \ctxlua{ + thirddata.translit.deficient_font = "\transliterateparameter{deficient_font}" + thirddata.translit.transliterate("\transliterateparameter{mode}","\luaescapestring{#2}") + }% + \egroup% +} + +\unexpanded\def\transliterate{\dosingleempty\dotransliterate} + +\def\expandabletransliterate#1{% + %\bgroup + %\setuptransliterate[#1]% + %\language[\transliterateparameter{hyphenate}]% + \ctxlua{ + thirddata.translit.deficient_font = "\transliterateparameter{deficient_font}" + thirddata.translit.transliterate("\transliterateparameter{mode}","#1") + }% + %\egroup% +} + +\unexpanded\def\starttransliterate{% + \bgroup% + \dosingleempty\dostarttransliterate% +} + +\let\stoptransliterate\relax + +\def\dostarttransliterate[#1]#2\stoptransliterate{% + \iffirstargument + \setuptransliterate[#1]% + \fi + \language[\transliterateparameter{hyphenate}]% + \ctxlua{thirddata.translit.transliterate("\transliterateparameter{mode}","\luaescapestring{#2}")}% + \egroup% +} + +\newconditional\transliterate_useexpanded \setfalse\transliterate_useexpanded + +\def\transliterate_conditional[#1]#2{% + \ifconditional\transliterate_useexpanded + \transliterate[#1]{#2}% + \else + \expandabletransliterate{#2}% + \fi% +} + +\protect \endinput + +% vim:ft=context diff --git a/src/t-transliterator.tex b/src/t-transliterator.tex new file mode 100644 index 0000000..9d4e9f0 --- /dev/null +++ b/src/t-transliterator.tex @@ -0,0 +1 @@ +\loadmarkfile{t-transliterator} diff --git a/src/t-transliterator.xml b/src/t-transliterator.xml new file mode 100644 index 0000000..d45f9cf --- /dev/null +++ b/src/t-transliterator.xml @@ -0,0 +1,63 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/src/trans_tables_bg.lua b/src/trans_tables_bg.lua new file mode 100644 index 0000000..b319666 --- /dev/null +++ b/src/trans_tables_bg.lua @@ -0,0 +1,114 @@ +--===========================================================================-- +-- Bulgarian -- +--===========================================================================-- + +local translit = thirddata.translit +local pcache = translit.parser_cache +local lpegmatch = lpeg.match + +if not translit.done_bg then + --------------------------------------------------------------------------- + -- Uppercase Bulgarian -> „scientific“ transliteration -- + --------------------------------------------------------------------------- + + translit.bg_upp = translit.make_add_dict{ + ["А"] = "A", + ["Б"] = "B", + ["В"] = "V", + ["Г"] = "G", + ["Д"] = "D", + ["Е"] = "E", + ["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"] = "Št", + ["Ъ"] = "Ă", + ["Ь"] = "′", + ["Ю"] = "Ju", + ["Я"] = "Ja", + } + translit.tables["Bulgarian \\quotation{scientific} transliteration uppercase"] = translit.bg_upp + + --------------------------------------------------------------------------- + -- Lowercase Bulgarian -> „scientific“ transliteration -- + --------------------------------------------------------------------------- + translit.bg_low = translit.make_add_dict{ + ["а"] = "a", + ["б"] = "b", + ["в"] = "v", + ["г"] = "g", + ["д"] = "d", + ["е"] = "e", + ["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"] = "št", + ["ъ"] = "ă", + ["ь"] = "′", + ["ю"] = "ju", + ["я"] = "ja", + } + + translit.tables["Bulgarian \\quotation{scientific} transliteration lowercase"] = translit.bg_low + + translit.done_bg = true +end + +local P, Cs = lpeg.P, lpeg.Cs +local addrules = translit.addrules +local utfchar = translit.utfchar + +local function bulgarian (mode) + local bulgarian_parser + if mode == "de" then + local bg = translit.bg_upp + translit.bg_low + local p_bg = addrules(bg) + bulgarian_parser = Cs((p_bg / bg + utfchar)^0) + else + return nil + end + return bulgarian_parser +end + +translit.methods["bg_de"] = function (text) + local p = pcache["bg_de"] + if not p then + p = bulgarian("de") + pcache["bg_de"] = p + end + return p and lpegmatch(p, text) or "" +end + +-- vim:ft=lua:sw=4:ts=4 diff --git a/src/trans_tables_glag.lua b/src/trans_tables_glag.lua new file mode 100644 index 0000000..41974fd --- /dev/null +++ b/src/trans_tables_glag.lua @@ -0,0 +1,128 @@ + +--===========================================================================-- +-- Glagolica -- +--===========================================================================-- + +local translit = thirddata.translit + +------------------------------------------- +-- Lowercase Glagolitic Transliteration -- +------------------------------------------- + +if not translit.done_glagolica then + translit.ocs_gla_low = translit.make_add_dict{ + ["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 = translit.make_add_dict{ + ["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 + + translit.done_glagolica = true +end + +--===========================================================================-- +-- End Of Tables -- +--===========================================================================-- + + diff --git a/src/trans_tables_gr.lua b/src/trans_tables_gr.lua new file mode 100644 index 0000000..b4c77e7 --- /dev/null +++ b/src/trans_tables_gr.lua @@ -0,0 +1,709 @@ +--===========================================================================-- +-- Greek -- +--===========================================================================-- + +local translit = thirddata.translit +local pcache = translit.parser_cache +local lpegmatch = lpeg.match + +-- 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 -- +------------------------------------------------- + +if not translit.done_greek then + translit.gr_di_in_low = translit.make_add_dict{ + [" 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 = translit.make_add_dict{ + [" 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 = translit.make_add_dict{ + [" 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 = translit.make_add_dict{ + [" 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 = translit.make_add_dict{ + ["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 = translit.make_add_dict{ + ["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 = translit.make_add_dict{ + ["γγ"] = "ng", + ["γκ"] = "nk", + ["γξ"] = "nx", + ["γχ"] = "nch", + } + + translit.tables["Greek transliteration optional nasalization"] = translit.gr_nrule + + + -------------------------------------- + -- Lowercase Greek Transliteration -- + -------------------------------------- + + translit.gr_low = translit.make_add_dict{ + ["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 = translit.make_add_dict{ + ["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 = translit.make_add_dict{ + ["ϝ"] = "w", + ["Ϝ"] = "W", + ["ϙ"] = "q", + ["Ϙ"] = "Q", + ["ϡ"] = "ss", + ["Ϡ"] = "Ss", + } + + translit.tables["Greek transliteration archaic characters"] = translit.gr_other + + translit.done_greek = true +end + +--===========================================================================-- +-- End Of Tables -- +--===========================================================================-- + +local function greek (mode, text) + local P, V, Cs = lpeg.P, lpeg.V, lpeg.Cs + local addrules = translit.addrules + local utfchar = translit.utfchar + + if mode == "gr" or mode == "gr_n" then + + local gr_di_in, gr_in, gr_di, gr = translit.make_add_dict{}, translit.make_add_dict{}, translit.make_add_dict{}, translit.make_add_dict{} + gr_di_in = gr_di_in + translit.gr_di_in_low + translit.gr_di_in_upp + gr_in = gr_in + translit.gr_in_low + translit.gr_in_upp + gr_di = gr_di + translit.gr_di_low + translit.gr_di_upp + gr = gr + translit.gr_low + translit.gr_upp + translit.gr_other + + if mode == "gr_n" then gr_di = gr_di + translit.gr_nrule end + + local p_di_in, p_in, p_di, p + + p_di_in = addrules( gr_di_in, p_di_in ) + p_in = addrules( gr_in, p_in ) + p_di = addrules( gr_di, p_di ) + p = addrules( gr, p ) + + local g = P{ -- 2959 rules + Cs((V"init_diph" + + V"init" + + V"diph" + + V"other" + + utfchar + )^0), + + init_diph = Cs(p_di_in / gr_di_in ), + init = Cs(p_in / gr_in ), + diph = Cs(p_di / gr_di ), + other = Cs(p / gr ), + } + + return g + end +end + +translit.methods["gr"] = function (text) + p = pcache["gr"] + if not p then + p = greek("gr") + pcache["gr"] = p + end + return lpegmatch(p, text) +end + +translit.methods["gr_n"] = function (text) + p = pcache["gr_n"] + if not p then + p = greek("gr_n") + pcache["gr_n"] = p + end + return lpegmatch(p, text) +end + +-- vim:ft=lua:sw=4:ts=4 diff --git a/src/trans_tables_iso9.lua b/src/trans_tables_iso9.lua new file mode 100644 index 0000000..256d994 --- /dev/null +++ b/src/trans_tables_iso9.lua @@ -0,0 +1,310 @@ +--===========================================================================-- +-- ISO 9.1995(E) standardized transliteration for cyrillic -- +--===========================================================================-- + +local translit = thirddata.translit +local pcache = translit.parser_cache +local lpegmatch = lpeg.match + +if not translit.done_iso9 then + ----------------------------------------- + -- Lowercase russian cyrillic alphabet -- + ----------------------------------------- + translit.ru_low = translit.make_add_dict({ + ["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 = translit.make_add_dict({ + ["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 = translit.make_add_dict{ + ["ѣ"] = "ě", -- U+048d -> U+011b -- 2-byte + ["і"] = "ì", -- U+0456 -> U+00ec -- 2-byte + ["ѳ"] = "f", -- U+0473 -> U+0066 -- 2-byte + ["ѵ"] = "ỳ", -- U+0475 -> U+1ef3 -- 3-byte + } + + translit.tables["russian pre-1918 lowercase ISO~9 2 byte"] = translit.ru_old_low + + translit.ru_old_upp = translit.make_add_dict{ + ["Ѣ"] = "Ě", -- U+048c -> U+011a -- 2-byte + ["І"] = "Ì", -- U+0406 -> U+00cc -- 2-byte + ["Ѳ"] = "F", -- U+0424 -> U+0046 -- 2-byte + ["Ѵ"] = "Ỳ", -- U+0474 -> U+1ef2 -- 3-byte + } + + translit.ru_jer_hack = translit.make_add_dict{ + ["ь"] = "’", + ["Ь"] = "’", + ["ъ"] = "”", + ["Ъ"] = "”", + } + + translit.tables["russian magkij / tverdyj znak hack"] = translit.ru_jer_hack + + translit.tables["russian pre-1918 uppercase ISO~9 2 byte"] = translit.ru_old_upp + + --------------------------------------------------------- + -- Lowercase characters from other cyrillic alphabets -- + --------------------------------------------------------- + + translit.non_ru_low = translit.make_add_dict{ + ["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 = translit.make_add_dict{ + ["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 + + translit.done_iso9 = true +end + +--===========================================================================-- +-- End Of Tables -- +--===========================================================================-- + +local function iso9 (mode) + local P, R, S, V, Cs = lpeg.P, lpeg.R, lpeg.S, lpeg.V, lpeg.Cs + local addrules = translit.addrules + local utfchar = translit.utfchar + + local iso9 = translit.make_add_dict{} + iso9 = translit.ru_upp + translit.ru_low + + if mode == "ru_old" or mode == "all" then + + iso9 = iso9 + translit.ru_old_upp + translit.ru_old_low + + if mode == "all" then + iso9 = iso9 + + translit.non_ru_upp + + translit.non_ru_low + end + if translit.deficient_font == "yes" then + iso9 = iso9 + + translit.ru_old_upp + + translit.ru_old_low + + translit.ru_jer_hack + end + end + + local p_iso9 = addrules (iso9, p_iso9) + local iso9_parser = Cs((p_iso9 / iso9 + utfchar)^0) + + return iso9_parser +end + +translit.methods["all"] = function (text) + local pname = "all" .. translit.deficient_font + local p = pcache[pname] + if not p then + p = iso9("all") + pcache[pname] = p + end + return lpegmatch(p, text) +end + +translit.methods["ru"] = translit.methods["all"] + +translit.methods["ru_old"] = function (text) + local pname = "ru_old" .. translit.deficient_font + local p = pcache[pname] + if not p then + p = iso9("all") + pcache[pname] = p + end + return lpegmatch(p, text) +end + +-- vim:ft=lua:sw=4:ts=4 diff --git a/src/trans_tables_scntfc.lua b/src/trans_tables_scntfc.lua new file mode 100644 index 0000000..96002c4 --- /dev/null +++ b/src/trans_tables_scntfc.lua @@ -0,0 +1,287 @@ +--===========================================================================-- +-- Other transliterations -- +--===========================================================================-- + +local translit = thirddata.translit +local pcache = translit.parser_cache +local lpegmatch = lpeg.match + +-- 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 + +if not translit.done_ocs then + ----------------------------------------------------------------------- + -- Lowercase and uppercase letter Uk -- “scientific transliteration” -- + ----------------------------------------------------------------------- + + translit.ocs_uk = translit.make_add_dict{ + ["oу"] = "u", + ["оу"] = "u", + ["Оу"] = "U", + } + ----------------------------------------------------------------------------- + -- Lowercase pre-Peter cyrillic characters -- “scientific transliteration” -- + ----------------------------------------------------------------------------- + + translit.ocs_low = translit.make_add_dict{ + ["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", + ["у"] = "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 = translit.make_add_dict{ + ["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", + ["У"] = "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 = translit.make_add_dict{ + ["ѕ"] = "dz", -- Mapped to ẑ in ISO 9 (Macedonian …) + ["ѯ"] = "ks", + ["ѱ"] = "ps", + ["ѡ"] = "ô", + ["ѿ"] = "ot", -- U+047f + ["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 = translit.make_add_dict{ + ["Ѕ"] = "Dz", + ["Ѯ"] = "Ks", + ["Ѱ"] = "Ps", + ["Ѡ"] = "Ô", + ["Ѿ"] = "ot", + ["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 + translit.done_ocs = true +end + +--===========================================================================-- +-- End Of Tables -- +--===========================================================================-- + +local function scientific (mode) + local P, Cs = lpeg.P, lpeg.Cs + local utfchar = translit.utfchar + local addrules = translit.addrules + + local cyr = translit.make_add_dict{} + local cyruk, p_cyruk, p_cyr, scientific_parser + + if mode == "iso9_ocs" or mode == "iso9_ocs_hack" then + + environment.loadluafile("trans_tables_iso9") + cyr = translit.ocs_add_low + + translit.ocs_add_upp + + translit.ocs_low + + translit.ru_upp + + translit.ru_low + + translit.ru_old_upp + + translit.ru_old_low + + translit.non_ru_upp + + translit.non_ru_low + + translit.ocs_upp + + if translit.deficient_font == "yes" then + cyr = cyr + translit.ru_jer_hack + end + + p_cyr = addrules(cyr, p_cyr) + + scientific_parser = Cs((p_cyr / cyr + utfchar)^0) + + elseif mode == ("ocs") then + + cyr = translit.ocs_low + translit.ocs_upp + + p_cyruk = addrules(translit.ocs_uk, cyruk) + p_cyr = addrules(cyr, p_cyr) + + scientific_parser = Cs((p_cyruk / translit.ocs_uk + + p_cyr / cyr + + utfchar)^0) + + elseif mode == ("ocs_gla") then + environment.loadluafile( "trans_tables_glag") + cyr = translit.ocs_gla_low + translit.ocs_gla_upp + + p_cyr = addrules(cyr, p_cyr) + scientific_parser = Cs((p_cyr / cyr + utfchar)^0) + end + + return scientific_parser +end + + +translit.methods["iso9_ocs"] = function (text) + local pname = "iso9_ocs" .. translit.deficient_font + local p = pcache[pname] + if not p then + p = scientific("iso9_ocs") + pcache[pname] = p + end + return lpegmatch(p, text) +end + +translit.methods["ocs"] = function (text) + local p = pcache["ocs"] + if not p then + p = scientific("ocs") + pcache["ocs"] = p + end + return lpegmatch(p, text) +end + +translit.methods["ocs_gla"] = function (text) + local p = pcache["ocs_gla"] + if not p then + p = scientific("ocs_gla") + pcache["ocs_gla"] = p + end + return lpegmatch(p, text) +end + +-- vim:ft=lua:ts=4:sw=4 diff --git a/src/trans_tables_sr.lua b/src/trans_tables_sr.lua new file mode 100644 index 0000000..4f549c5 --- /dev/null +++ b/src/trans_tables_sr.lua @@ -0,0 +1,241 @@ + +--===========================================================================-- +-- Serbian -- +--===========================================================================-- + +local translit = thirddata.translit +local pcache = translit.parser_cache +local lpegmatch = lpeg.match + + +-- Special thanks to Mojca Miklavec and Arthur Reutenauer for their +-- assistance in creating these transliteration routines. + +if not translit.done_serbian then + -------------------------------------------- + -- Lowercase Serbian (Cyrillic -> Latin) -- + -------------------------------------------- + translit.sr_tolt_lower = translit.make_add_dict{ + ["а"] = "a", + ["б"] = "b", + ["в"] = "v", + ["г"] = "g", + ["д"] = "d", + ["ђ"] = "đ", + ["е"] = "e", + ["ж"] = "ž", + ["з"] = "z", + ["и"] = "i", + ["ј"] = "j", + ["к"] = "k", + ["л"] = "l", + ["љ"] = "lj", + ["м"] = "m", + ["н"] = "n", + ["њ"] = "nj", + ["о"] = "o", + ["п"] = "p", + ["р"] = "r", + ["с"] = "s", + ["т"] = "t", + ["ћ"] = "ć", + ["у"] = "u", + ["ф"] = "f", + ["х"] = "h", + ["ц"] = "c", + ["ч"] = "č", + ["џ"] = "dž", + ["ш"] = "š", + } + + translit.tables["Serbian Cyr->Lat Transliteration lowercase"] = translit.sr_tolt_lower + + -------------------------------------------- + -- Uppercase Serbian (Cyrillic -> Latin) -- + -------------------------------------------- + + translit.sr_tolt_upper = translit.make_add_dict{ + ["А"] = "A", + ["Б"] = "B", + ["В"] = "V", + ["Г"] = "G", + ["Д"] = "D", + ["Ђ"] = "Đ", + ["Е"] = "E", + ["Ж"] = "Ž", + ["З"] = "Z", + ["И"] = "I", + ["Ј"] = "J", + ["К"] = "K", + ["Л"] = "L", + ["Љ"] = "Lj", + ["М"] = "M", + ["Н"] = "N", + ["Њ"] = "Nj", + ["О"] = "O", + ["П"] = "P", + ["Р"] = "R", + ["С"] = "S", + ["Т"] = "T", + ["Ћ"] = "Ć", + ["У"] = "U", + ["Ф"] = "F", + ["Х"] = "H", + ["Ц"] = "C", + ["Ч"] = "Č", + ["Џ"] = "Dž", + ["Ш"] = "Š", + } + + translit.tables["Serbian Cyr->Lat Transliteration uppercase"] = translit.sr_tolt_upper + + local function __inverse_tab (t) + local result = { } + for k,v in next,t do result[v] = k end + return result + end + + translit.sr_tocy_lower = translit.make_add_dict(__inverse_tab(translit.sr_tolt_lower)) + translit.sr_tocy_upper = translit.make_add_dict(__inverse_tab(translit.sr_tolt_upper)) + + + --- Good reading up front: + --- + --- + + local except = { + ["konjug"] = "конјуг", + ["konjunk"] = "конјунк", + ["injekc"] = "инјекц", + ["injunkt"] = "инјункт", + ["panjelin"] = "панјелин", + ["tanjug"] = "танјуг", + ["vanjezič"] = "ванјезич", + ["vanjadransk"] = "ванјадранск", + + ["nadžanj"] = "наджањ", + ["nadždrel"] = "надждрел", + ["nadžet"] = "наджет", + ["nadživ"] = "наджив", + ["nadžnj"] = "наджњ", + ["nadžup"] = "наджуп", + ["odžal"] = "оджал", + ["odžar"] = "оджар", + ["odživ"] = "оджив", + ["odžubor"] = "оджубор", + ["odžur"] = "оджур", + ["odžvak"] = "оджвак", + ["podžanr"] = "поджанр", + ["podže"] = "подже", -- “поджећи” + } + + local P = lpeg.P + local sub, upper = unicode.utf8.sub, unicode.utf8.upper + + local p_tocy, p_i_tocy, p_tolt, p_i_tolt + + for left, right in next, except do -- generating exception patterns for both sides + local Left = upper(sub(left, 1, 1)) .. sub(left, 2) + local Right = upper(sub(right, 1, 1)) .. sub(right, 2) + local LEFT, RIGHT = upper(left), upper(right) + + local p_i_left = P(left) / right + P(Left) / Right + P(LEFT) / RIGHT + local p_i_right = P(right) / left + P(Right) / Left + P(RIGHT) / LEFT + + local p_left = P" " * p_i_left + local p_right = P" " * p_i_right + + if not p_tocy then + p_tocy = p_left + p_i_tocy = p_i_left + p_tolt = p_right + p_i_tolt = p_i_right + else + p_tocy = p_tocy + p_left + p_i_tocy = p_i_tocy + p_i_left + p_tolt = p_tolt + p_right + p_i_tolt = p_i_tolt + p_i_right + end + end + + local _p_hintchar = P"*" / "" + local hintme = "dln" + local _p_tocy_hint, _p_tolt_hint + + for left in hintme:utfcharacters() do + local right = translit.sr_tocy_lower[left] + local LEFT, RIGHT = upper(left), upper(right) + if not _p_tocy_hint then + _p_tocy_hint = P(left) / right + P(LEFT) / RIGHT + _p_tolt_hint = P(right) / left + P(RIGHT) / LEFT + else + _p_tocy_hint = _p_tocy_hint + P(left) / right + P(LEFT) / RIGHT + _p_tolt_hint = _p_tolt_hint + P(right) / left + P(RIGHT) / LEFT + end + end + + translit.serbian_exceptions = { } + translit.serbian_exceptions.p_tocy = p_tocy + translit.serbian_exceptions.p_tolt = p_tolt + translit.serbian_exceptions.p_tocy_init = p_i_tocy + translit.serbian_exceptions.p_tolt_init = p_i_tolt + translit.serbian_exceptions.p_tocy_hint = _p_tocy_hint * _p_hintchar + translit.serbian_exceptions.p_tolt_hint = _p_tolt_hint * _p_hintchar + + translit.done_serbian = true +end + +--===========================================================================-- +-- End Of Tables -- +--===========================================================================-- + + +local t = translit +local function sr (mode) + local P, R, Cs = lpeg.P, lpeg.R, lpeg.Cs + local utfchar = translit.utfchar + local modestr = "p_" .. mode:match("to..$") + local _p_sre = t.serbian_exceptions[modestr] + local _p_sre_i = t.serbian_exceptions[modestr .. "_init"] + + local trl_sr = translit.make_add_dict{} + trl_sr = t[mode.."_upper"] + t[mode.."_lower"] + + -- transliteration from latin script requires macro handling … + local _p_macro = P[[\]] * R("az", "AZ")^1 -- assuming standard catcodes + local _p_sr = translit.addrules (trl_sr, _p_sr) / trl_sr + if translit.hinting then + _p_sr = t.serbian_exceptions[modestr .. "_hint"] + _p_sr + end + + local p_sr + if translit.sr_except then + p_sr = Cs(_p_sre_i^-1 * (_p_macro + _p_sre + _p_sr + utfchar)^0) + else + p_sr = Cs((_p_macro + _p_sr + utfchar)^0) + end + + return p_sr +end + +translit.methods["sr_tolt"] = function (text) + local pname = "sr_tolt" .. tostring(translit.hinting) .. tostring(translit.sr_except) + local p = pcache[pname] + if not p then + p = sr("sr_tolt") + pcache[pname] = p + end + return lpegmatch(p, text) +end + +translit.methods["sr_tocy"] = function (text) + local pname = "sr_tocy" .. tostring(translit.hinting) .. tostring(translit.sr_except) + local p = pcache[pname] + if not p then + p = sr("sr_tocy") + pcache[pname] = p + end + return lpegmatch(p, text) +end + +-- vim:ft=lua:sw=4:ts=4 diff --git a/src/trans_tables_trsc.lua b/src/trans_tables_trsc.lua new file mode 100644 index 0000000..fbc35d1 --- /dev/null +++ b/src/trans_tables_trsc.lua @@ -0,0 +1,867 @@ +--===================================================================-- +-- Legacy national transliterations -- +--===================================================================-- + +local translit = thirddata.translit +local addrules = translit.addrules +local utfchar = translit.utfchar + +local lpegmatch = lpeg.match +local tablepack = table.pack -- lua 5.2 precaution + +--------------------------------- +-- German simple transcription -- +--------------------------------- +-- Reference: „DUDEN. Rechtschreibung der deutschen Sprache“; +-- 20. Aufl., +-- Mannheim et. al. 1991. + +if lpeg.version() == "0.9" and not translit.done_ru_trsc_de then + + -------------------------------------------------------- + -- Lowercase German simple transcription---first pass -- + -------------------------------------------------------- + + translit.ru_trsc_low_first = translit.make_add_dict{ + [" 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" + } + + translit.tables["German transcription first pass lowercase"] + = translit.ru_trsc_low_first + + -------------------------------------------------------- + -- Uppercase German simple transcription---first pass -- + -------------------------------------------------------- + + translit.ru_trsc_upp_first = translit.make_add_dict{ + [" 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 = translit.make_add_dict{ + ["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 = translit.make_add_dict{ + ["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 + + translit.ru_trsc_iy = {"и", "ы", "И", "Ы"} + + function translit.gen_rules_de() + -- The following are more interesting than the previous tables + -- because they implement various rules. For instance the + -- table \type{translit.ru_trsc_irule} holds a substitution + -- dictionary for all possible combinations (including nonsense + -- galore) of a vowel preceding an “й” (Russian short i) + -- preceding a consonant; here we access the sets of Russian + -- vowels as well consonants that were defined earlier. + + -- The й-rule, VйC -> ViC + translit.ru_trsc_irule = translit.make_add_dict{} + for _, vow in ipairs(translit.ru_vowels) do + for _, 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 _, 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 + + for _, cons in ipairs(translit.ru_consonants) do + for _, 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 = translit.make_add_dict{} + 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 = translit.make_add_dict{} + 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 = translit.make_add_dict{} + 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 = translit.make_add_dict{} + 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 + + end + + translit.gen_rules_de() + translit.done_ru_trsc_de = true +end + +if lpeg.version() == "0.10" and not translit.done_ru_trsc_de then + + -- This is about *eight* times as fast as the old pattern. Just + -- waiting for v0.10 to make it into luatex. + + local de_tables = { } + + -------------------------------------------------------- + -- Lowercase German simple transcription---first pass -- + -------------------------------------------------------- + + de_tables[1] = { -- lowercase initial + [" е"] = " je", ["ъе"] = "je", ["ье"] = "je", + [" ё"] = " jo", ["ъё"] = "jo", ["ьё"] = "jo", + ["жё"] = "scho", ["цё"] = "scho", ["чё"] = "zo", + ["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"] + = de_tables[1] + + -------------------------------------------------------- + -- Uppercase German simple transcription---first pass -- + -------------------------------------------------------- + + de_tables[2] = { -- uppercase initial + [" Е"] = " Je", ["Ъe"] = "Je", ["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"] + = de_tables[2] + + ------------------------------------------- + -- Lowercase German simple transcription -- + ------------------------------------------- + + de_tables[3] = { -- lowercase + ["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"] + = de_tables[3] + + ------------------------------------------- + -- Uppercase German simple transcription -- + ------------------------------------------- + + de_tables[4] = { -- uppercase + ["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"] + = de_tables[4] + + local B, P, Cs = lpeg.B, lpeg.P, lpeg.Cs + + -- All chars are 2-byte. + local Co = P{ + P"б" + "в" + "г" + "д" + "ж" + "з" + "к" + "л" + "м" + "н" + + "п" + "р" + "с" + "т" + "ф" + "х" + "ц" + "ч" + "ш" + "щ" + + "ъ" + "ь" + + "Б" + "В" + "Г" + "Д" + "Ж" + "З" + "К" + "Л" + "М" + "Н" + + "П" + "Р" + "С" + "Т" + "Ф" + "Х" + "Ц" + "Ч" + "Ш" + "Щ" + + "Ъ" + "Ь" + } + + local Vo = P{ + P"а" + "е" + "ё" + "и" + "й" + "о" + "у" + "ы" + "э" + "я" + + "ю" + "А" + "Е" + "Ё" + "И" + "Й" + "О" + "У" + "Ы" + "Э" + + "Я" + "Ю" + } + + local iy = P"и" + P"ы" + P"И" + P"Ы" + + ------------------------------------------- + -- Pattern generation. + ------------------------------------------- + + local p_transcript + + for _, set in next, de_tables do + for str, rep in next, set do + if not p_transcript then -- it’ll be empty initially + p_transcript = P(str) / rep + else + p_transcript = p_transcript + (P(str) / rep) + end + end + end + + local irule = B(Vo,2) * Cs(P"й") * #Co / "i" + local iyrule = B(iy,2) * Cs(P"й") * #Co / "j" + local jrule = Cs(P"й") * #Vo / "j" + local srule = B(Vo,2) * Cs(P"с") * #Vo / "ss" + local ssrule = B(Vo,2) * Cs(P"с") * #P"х" / "ß" + local jerule = B(Vo,2) * Cs(P"е") / "je" + local jorule = B(Vo,2) * Cs(P"ё") / "jo" + + translit.future_ru_transcript_de + = Cs((iyrule + jrule + irule + + jerule + srule + ssrule + + jorule + p_transcript + 1)^0 + ) +end + +if not translit.done_ru_trsc_en then + + --------------------------------------------------------- + -- Lowercase English simple transcription---first pass -- + --------------------------------------------------------- + + translit.ru_trsc_en_low_first = translit.make_add_dict{ + [" 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 = translit.make_add_dict{ + [" 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 = translit.make_add_dict{ + ["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 = translit.make_add_dict{ + ["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 + + function translit.gen_rules_en () + -- The english е-rule, Vе -> Vye + translit.ru_trsc_en_jerule = translit.make_add_dict{} + 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 + end + + translit.gen_rules_en() + translit.done_ru_trsc_en = true +end + + +if not translit.done_ru_trsc_cz then + ----------------------------------- + -- Lowercase Czech transcription -- + ----------------------------------- + + translit.ru_trsc_cz_low = translit.make_add_dict{ + ["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 + ["я"] = "ja", -- тя -> ťa, but 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 = translit.make_add_dict{ + ["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 = translit.make_add_dict{ + ["ѕ"] = "dz", + ["з"] = "z", + ["ꙁ"] = "z", + ["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 = translit.make_add_dict{ + ["Ѕ"] = "Dz", + ["З"] = "Z", + ["Ꙁ"] = "Z", + ["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 + translit.done_ru_trsc_cz = true +end + +--===================================================================-- +-- End Of Tables -- +--===================================================================-- + +local function transcript (mode, text) + local P, R, S, V, Cs = lpeg.P, lpeg.R, lpeg.S, lpeg.V, lpeg.Cs + + local trsc_parser, p_rules, capt, p_de + + local function tab_subst (s, ...) + local sets = { ... } + local p_tmp, tmp = nil, translit.make_add_dict{} + for n=1, #sets do + local set = sets[n] + tmp = tmp + set + end + p_tmp = addrules(tmp, p_tmp) + local fp = Cs((Cs(P(p_tmp) / tmp) + utfchar)^0) + return lpegmatch(fp, s) + end + + if mode == "ru_transcript_en" then + + text = tab_subst(text, translit.ru_trsc_en_jerule) + text = tab_subst(text, + translit.ru_trsc_en_low_first, + translit.ru_trsc_en_upp_first) + text = tab_subst(text, + translit.ru_trsc_en_low, + translit.ru_trsc_en_upp) + + return text + + elseif mode == "ru_transcript_en_exp" then + + local en_low_upp = translit.make_add_dict{} + en_low_upp = translit.ru_trsc_en_low + translit.ru_trsc_en_upp + + local twochar + local tworepl = translit.make_add_dict{} + + twochar = addrules( translit.ru_trsc_en_low_first, twochar) + twochar = addrules( translit.ru_trsc_en_upp_first, twochar) + + tworepl = translit.ru_trsc_en_low_first + + translit.ru_trsc_en_upp_first + + -- The е-rule, Vе -> Vye + local function V_je (s) + local ante = utf.sub(s, 1, 1) + return en_low_upp[ante] .. "ye" + end + + local jerule = Cs((vow * "е") / V_je) + + local dvoje = Cs(twochar / tworepl) + local other = Cs((utfchar) / en_low_upp) + + local g = Cs((dvoje + jerule + other + utfchar)^0) + + text = g:match(text) + + return text + + elseif mode == "ru_cz" or mode == "ocs_cz" then + text = tab_subst(text, + translit.ru_trsc_cz_low, + translit.ru_trsc_cz_upp) + if mode == "ocs_cz" then + text = tab_subst(text, + translit.ru_trsc_cz_add_low, + translit.ru_trsc_cz_add_upp) + end + return text + end + + if mode == "ru_transcript_de_exp" then + + local vow, con, iy + vow = addrules(translit.ru_vowels, vow) + con = addrules(translit.ru_consonants, con) + iy = addrules(translit.ru_trsc_iy, iy ) + + local de_low_upp = translit.make_add_dict{} + de_low_upp = translit.ru_trsc_upp + translit.ru_trsc_low + + local twochar + local tworepl = translit.make_add_dict{} + + twochar = addrules( translit.ru_trsc_low_first, twochar ) + twochar = addrules( translit.ru_trsc_upp_first, twochar ) + + tworepl = translit.ru_trsc_low_first + + translit.ru_trsc_upp_first + + -- The й-rule, VйC -> ViC + local function V_i_C (s) + local ante = utf.sub(s, 1, 1) + local post = utf.sub(s, 3, 3) + return de_low_upp[ante] .. "i" .. de_low_upp[post] + end + + -- The second й-rule, йV -> jV && [иы]йC -> [иы]jC + local function iy_j_C (s) + local ante = utf.sub(s, 1, 1) + local post = utf.sub(s, 3, 3) + return de_low_upp[ante] .. "j" .. de_low_upp[post] + end + + local function j_V (s) + local post = utf.sub(s, 2, 2) + return "j" .. de_low_upp[post] + end + + -- The с-rule, VсV -> VssV + local function V_ss_V (s) + local ante = utf.sub(s, 1, 1) + local post = utf.sub(s, 3, 3) + return de_low_upp[ante] .. "ss" .. de_low_upp[post] + end + + -- The sharp-s-rule, Vсх -> Vßх + local function V_sz_ch (s) + local ante = utf.sub(s, 1, 1) + return de_low_upp[ante] .. "ßch" + end + + -- The е-rule, Vе -> Vje + local function V_je (s) + local ante = utf.sub(s, 1, 1) + return de_low_upp[ante] .. "je" + end + + -- Reapplying V_je on its result + next char would make the + -- following two rules obsolete. + local function V_jeje (s) + local ante = utf.sub(s, 1, 1) + return de_low_upp[ante] .. "jeje" + end + + local function V___je (s) + local ante = utf.sub(s, 1, 1) + return de_low_upp[ante] .. "jeje" + end + + -- The ё-rule, Vё -> Vjo + -- This should be redundant as [жцчшщ]ё -> o, else ё -> jo . + -- Somebody should teach those DUDEN guys parsimony. + local function V_jo (s) + local ante = utf.sub(s, 1, 1) + return de_low_upp[ante] .. "jo" + end + + local iyrule = Cs((iy * "й" * con) / iy_j_C) + local jrule = Cs(("й" * vow) / j_V) + local irule = Cs((vow * "й" * con) / V_i_C) + + local ssrule = Cs((vow * "с" * vow) / V_ss_V) + local szrule = Cs((vow * "сх") / V_sz_ch) + + --local _jrule = Cs((vow * "ее") / V___je) + local jjrule = Cs((vow * "ее") / V_jeje) + local jerule = Cs((vow * "е") / V_je) + local jorule = Cs((vow * "ё") / V_jo) + + local dvoje = Cs(twochar / tworepl) + local other = Cs((utfchar) / de_low_upp) + + local izhe = iyrule + jrule + irule + local slovo = ssrule + szrule + local jest = jjrule + jerule + jorule + + local g = Cs((izhe + slovo + jest + dvoje + other + utfchar)^0) + + text = g:match(text) + return text + + elseif mode == "ru_transcript_de" then + + if lpeg.version() == "0.9" then + + text = tab_subst(text, translit.ru_trsc_jrule) + text = tab_subst(text, translit.ru_trsc_irule) + text = tab_subst(text, translit.ru_trsc_jerule) + text = tab_subst(text, translit.ru_trsc_srule) + text = tab_subst(text, translit.ru_trsc_sharpsrule) + text = tab_subst(text, translit.ru_trsc_jorule) + text = tab_subst(text, + translit.ru_trsc_upp_first, + translit.ru_trsc_low_first) + text = tab_subst(text, + translit.ru_trsc_upp, + translit.ru_trsc_low) + + return text + elseif lpeg.version() == "0.10" then + return translit.future_ru_transcript_de:match(text) + end + + end + +end + +translit.methods ["ru_transcript_de"] + = function (text) return transcript("ru_transcript_de" , text) end +translit.methods ["ru_transcript_de_exp"] + = function (text) return transcript("ru_transcript_de_exp", text) end +translit.methods ["ru_transcript_en"] + = function (text) return transcript("ru_transcript_en" , text) end +translit.methods ["ru_transcript_en_exp"] + = function (text) return transcript("ru_transcript_en_exp", text) end +translit.methods ["ru_cz"] + = function (text) return transcript("ru_cz" , text) end +translit.methods ["ocs_cz"] + = function (text) return transcript("ocs_cz" , text) end + +-- vim:sw=4:ts=4:expandtab:ft=lua diff --git a/src/transliterator.lua b/src/transliterator.lua new file mode 100644 index 0000000..c101ec5 --- /dev/null +++ b/src/transliterator.lua @@ -0,0 +1,283 @@ +#!/usr/bin/env texlua +-------------------------------------------------------------------------------- +-- FILE: transliterator.lua +-- USAGE: to be called by t-transliterator.mkiv +-- DESCRIPTION: basic lua environment for the Transliterator module +-- REQUIREMENTS: latest ConTeXt MkIV +-- AUTHOR: Philipp Gesang (Phg), +-- CREATED: 2010-12-23 22:12:31+0100 +-------------------------------------------------------------------------------- +-- + +thirddata = thirddata or { } +thirddata.translit = thirddata.translit or { } +local translit = thirddata.translit +translit.tables = translit.tables or { } +translit.methods = translit.methods or { } +translit.deficient_font = "no" +translit.parser_cache = { } + +local utf8 = unicode and unicode.utf8 or utf8 +local utf8byte = utf8.byte +local utf8len = utf8.len + +-------------------------------------------------------------------------------- +-- Predefining vowel lists +-------------------------------------------------------------------------------- +-- 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"} + +-- Substitution tables are the very heart of the Transliterator. Due to the +-- nature of languages and scripts exhaustive substitution is the simplest +-- method for transliterations and transcriptions unless they are one-to-one +-- mappings like those defined in ISO~9. +-- +-- To achieve better reusability we split the tables into segments, the most +-- obvious being the \type{*_low} and \type{*_upp} variants for sets of lowercase +-- and uppercase characters. Another set is constituted by e.~g. the +-- \type{ru_old*} tables that allow adding transcription of historical +-- characters if needed; by the way those are included in the default +-- transliteration mode \type{ru_old}. + +-- Tables can be found in separate Lua files. +-- See {\tt +-- trans_tables_glag.lua +-- trans_tables_gr.lua +-- trans_tables_iso9.lua +-- trans_tables_scntfc.lua +-- and +-- trans_tables_trsc.lua.} + +-------------------------------------------------------------------------------- +-- Metatables allow for lazy concatenation. +-------------------------------------------------------------------------------- + +do + -- This returns the Union of both key sets for the “+” operator. + -- The values of the first table will be updated (read: overridden) by + -- those given in the second. + local Dict_add = { + __add = function (dict_a, dict_b) + assert (type(dict_a) == "table" and type(dict_b) == "table") + local dict_result = setmetatable({}, Dict_add) + + for key, val in pairs(dict_a) do + dict_result[key] = val + end + + for key, val in pairs(dict_b) do + dict_result[key] = val + end + return dict_result + end + } + + translit.make_add_dict = function (dict) + return setmetatable(dict, Dict_add) + end +end + +-------------------------------------------------------------------------------- +-- Auxiliary Functions +-------------------------------------------------------------------------------- + +-- Generate a rule pattern from hash table. +do + local P, R, V = lpeg.P, lpeg.R, lpeg.V + + -- multi-char rules first + translit.addrules = function (dict, rules) + local by_length, occurring_lengths = { }, { } + for chr, _ in next, dict do + local l = utf8len(chr) + if not by_length[l] then + by_length[l] = { } + occurring_lengths[#occurring_lengths+1] = l + end + by_length[l][#by_length[l]+1] = chr + end + table.sort(occurring_lengths) + for i=#occurring_lengths, 1, -1 do + local l = occurring_lengths[i] + for _, chr in next, by_length[l] do + rules = rules and rules + P(chr) or P(chr) + end + end + return rules + end + +-- Modified version of Hans’s utf pattern (l-lpeg.lua). + + + translit.utfchar = P{ + V"utf8one" + V"utf8two" + V"utf8three" + V"utf8four", + + utf8next = R("\128\191"), + utf8one = R("\000\127"), + utf8two = R("\194\223") * V"utf8next", + utf8three = R("\224\239") * V"utf8next" * V"utf8next", + utf8four = R("\240\244") * V"utf8next" * V"utf8next" * V"utf8next", + } +end + +-- We might want to have all the table data nicely formatted by \CONTEXT\ +-- itself, here's how we'll do it. \type{translit.show_tab(t)} handles a +-- single table \type{t}, builds a Natural TABLE out of its content and +-- hands it down to the machine for typesetting. For debugging purposes it +-- does not only print the replacement pairs but shows their code points as +-- well. + +-- handle the input chars and replacement values +local strempty = function (s) + if s == "" then return "nil" + else + -- add the unicode positions of the replacements (can be more + -- than one with composed diacritics + local i = 1 + local r = "" + repeat + r = r .. utf8byte(s,i) .. " " + i = i + 1 + until utf8byte(s,i) == nil + return r + end +end + +function translit.show_tab (tab) + -- Output a transliteration table, nicely formatted with natural tables. + -- Lots of calls to context() but as it’s only a goodie this doesn’t + -- really matter. + 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() + context.bTR() + context.bTH() context("number") context.eTH() + context.bTH() context("letters") context.eTH() + context.bTH() context("n") context.eTH() + context.bTH() context("replacement") context.eTH() + context.bTH() context("n") context.eTH() + context.bTH() context("bytes") context.eTH() + context.bTH() context("repl. bytes") context.eTH() + context.eTR() + context.eTABLEhead() + context.bTABLEbody() + + for key, val in next,tab do + cnt = cnt + 1 + context.bTR() + context.bTC() context(cnt) context.eTC() + context.bTC() context(key) context.eTC() + context.bTC() context(string.len(key)) context.eTC() + context.bTC() context(val) context.eTC() + context.bTC() context(string.len(val)) context.eTC() + context.bTC() context(strempty(key)) context.eTC() + context.bTC() context(strempty(val)) context.eTC() + context.eTR() + end + + context.eTABLEbody() + context.bTABLEfoot() context.bTR() + context.bTC() context("number") context.eTC() + context.bTC() context("letters") context.eTC() + context.bTC() context("n") context.eTC() + context.bTC() context("replacement") context.eTC() + context.bTC() context("n") context.eTC() + context.bTC() context("bytes") context.eTC() + context.bTC() context("repl. bytes") context.eTC() + context.eTR() + context.eTABLEfoot() + context.eTABLE() +end + +-- Having to pick out single tables for printing can be tedious, therefore we +-- let Lua do the job in our stead. \type{translit.show_all_tabs()} calls +-- \type{translit.show_tab} on every table that is registered with +-- \type{translit.table} -- and uses its registered key as table heading. + +function translit.show_all_tabs () + environment.loadluafile ("trans_tables_iso9") + environment.loadluafile ("trans_tables_trsc") + environment.loadluafile ("trans_tables_scntfc") + environment.loadluafile ("trans_tables_sr") + environment.loadluafile ("trans_tables_trsc") + environment.loadluafile ("trans_tables_glag") + environment.loadluafile ("trans_tables_gr") + translit.gen_rules_en() + translit.gen_rules_de() + -- 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 + +-- for internal use only + +translit.debug_count = 0 + +function translit.debug_next () + translit.debug_count = translit.debug_count + 1 + context("\\tfxx{\\bf translit debug msg. nr.~" .. translit.debug_count .. "}") +end + +-------------------------------------------------------------------------------- +-- User-level Function +-------------------------------------------------------------------------------- + +-- \type{translit.transliterate(m, t)} constitutes the +-- metafunction that is called by the \type{\transliterate} command. +-- It loads the transliteration tables according to \type{method} and calls the +-- corresponding function. + +-- Those supposedly are the most frequently used so it won’t hurt to preload +-- them. The rest will be loaded on request. +environment.loadluafile ("trans_tables_iso9") + +function translit.transliterate (method, text) + local methods = translit.methods + if not methods[method] then -- register tables and method + if method == "ru_transcript_de" or + method == "ru_transcript_de_exp" or -- experimental lpeg + method == "ru_transcript_en" or + method == "ru_transcript_en_exp" or + method == "ru_cz" or + method == "ocs_cz" then + environment.loadluafile ("trans_tables_trsc") + elseif method == "iso9_ocs" or + method == "iso9_ocs_hack" or + method == "ocs" or + method == "ocs_gla" then + environment.loadluafile ("trans_tables_scntfc") + elseif method:match("^sr_") then + environment.loadluafile ("trans_tables_sr") + elseif method:match("^bg_") then -- only bg_de for now + environment.loadluafile ("trans_tables_bg") + elseif method == "gr" or + method == "gr_n" then + environment.loadluafile ("trans_tables_gr") + end + end + + if translit.__script then + return methods[method](text) + end + context ( methods[method](text) ) +end + +-- vim:sw=4:ts=4:expandtab:ft=lua -- cgit v1.2.3