diff options
author | Philipp Gesang <pgesang@ix.urz.uni-heidelberg.de> | 2010-03-19 22:10:06 +0100 |
---|---|---|
committer | Philipp Gesang <pgesang@ix.urz.uni-heidelberg.de> | 2010-03-19 22:10:06 +0100 |
commit | e6e1e893c0bb13e4cdb9d2e58afc981257a73b81 (patch) | |
tree | 0cb913011d4e18f91becc1c8abeeba9d4012694b | |
parent | de7913532bd56d8d7d88ac1ef522e18157eaac17 (diff) | |
download | transliterator-e6e1e893c0bb13e4cdb9d2e58afc981257a73b81.tar.gz |
dirty hack to be used with limited fonts
3 files changed, 37 insertions, 5 deletions
diff --git a/tex/context/third/transliterator/t-transliterator.mkiv b/tex/context/third/transliterator/t-transliterator.mkiv index 16c197b..ef8c15e 100644 --- a/tex/context/third/transliterator/t-transliterator.mkiv +++ b/tex/context/third/transliterator/t-transliterator.mkiv @@ -31,6 +31,13 @@ %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: \type{iso9_ocs_hack}, which is essentially +%D \type{iso9_ocs}, and \type{ru_old_jer_hack}, which is essentially +%D \type{ru_old}. These two 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 @@ -223,8 +230,9 @@ end \startluacode function translit.transliterate (method, text) - if method == "ru" or - method == "ru_old" or + if method == "ru" or + method == "ru_old" or + method == "ru_old_jer_hack" or method == "all" then environment.loadluafile ("trans_tables_iso9") @@ -238,8 +246,9 @@ function translit.transliterate (method, text) then environment.loadluafile ("trans_tables_trsc") text = translit.transcript (method, text) - elseif method == "iso9_ocs" or - method == "ocs" or + elseif method == "iso9_ocs" or + method == "iso9_ocs_hack" or + method == "ocs" or method == "ocs_gla" then environment.loadluafile ("trans_tables_scntfc") diff --git a/tex/context/third/transliterator/trans_tables_iso9.lua b/tex/context/third/transliterator/trans_tables_iso9.lua index f85ed35..4518466 100644 --- a/tex/context/third/transliterator/trans_tables_iso9.lua +++ b/tex/context/third/transliterator/trans_tables_iso9.lua @@ -107,6 +107,15 @@ translit.ru_old_upp = { ["Ѵ"] = "Ỳ", -- U+0474 -> U+1ef2 -- 3-byte } +translit.ru_jer_hack = { + ["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 --------------------------------------------------------- @@ -276,6 +285,14 @@ function translit.iso9 (mode, text) end end + if mode == "ru_old_jer_hack" then + iso9 = translit.add_table(iso9, + translit.ru_old_upp, + translit.ru_old_low, + translit.ru_jer_hack + ) + end + local p_iso9 p_iso9 = addrules (iso9, p_iso9) diff --git a/tex/context/third/transliterator/trans_tables_scntfc.lua b/tex/context/third/transliterator/trans_tables_scntfc.lua index d42a970..93bdbb4 100644 --- a/tex/context/third/transliterator/trans_tables_scntfc.lua +++ b/tex/context/third/transliterator/trans_tables_scntfc.lua @@ -211,7 +211,7 @@ function translit.scientific (mode, text) local cyr = {} local cyruk, p_cyruk, p_cyr local scientific_parser - if mode == ("iso9_ocs") then + if mode == "iso9_ocs" or mode == "iso9_ocs_hack" then environment.loadluafile("trans_tables_iso9.lua") translit.add_table( cyr, @@ -225,6 +225,12 @@ function translit.scientific (mode, text) translit.ocs_add_upp ) + if mode == "iso9_ocs_hack" then + translit.add_table( cyr, + translit.ru_jer_hack + ) + end + p_cyr = Cs(utfchar) / cyr scientific_parser = Cs((p_cyr + utfchar)^0) |