Tissevert/pandoc
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1

Moved babelLangToBCP, polyglossiaLangToBCP to new module...

Browse source 
Text.Pandoc.Readers.LaTeX.Lang (unexported).
This commit is contained in:
John MacFarlane 2018-10-01 21:27:20 -07:00
parent 9abdbb2783
commit 799cd5db7a
3 changed files with 176 additions and 134 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
pandoc.cabal
View file

@ -510,6 +510,7 @@ library
Text.Pandoc.Readers.Docx.StyleMap,
Text.Pandoc.Readers.Docx.Fields,
Text.Pandoc.Readers.LaTeX.Parsing,
Text.Pandoc.Readers.LaTeX.Lang,
Text.Pandoc.Readers.Odt.Base,
Text.Pandoc.Readers.Odt.Namespaces,
Text.Pandoc.Readers.Odt.StyleReader,

136
src/Text/Pandoc/Readers/LaTeX.hs
View file

@ -72,6 +72,8 @@ import Text.Pandoc.Parsing hiding (blankline, many, mathDisplay, mathInline,
import Text.Pandoc.Readers.LaTeX.Types (ExpansionPoint (..), Macro (..),
ArgSpec (..), Tok (..), TokType (..))
import Text.Pandoc.Readers.LaTeX.Parsing
import Text.Pandoc.Readers.LaTeX.Lang (polyglossiaLangToBCP47,
babelLangToBCP47)
import Text.Pandoc.Shared
import qualified Text.Pandoc.Translations as Translations
import Text.Pandoc.Walk
@ -2265,137 +2267,3 @@ setDefaultLanguage = do
setTranslations l
updateState $ setMeta "lang" $ str (renderLang l)
return mempty
polyglossiaLangToBCP47 :: M.Map String (String -> Lang)
polyglossiaLangToBCP47 = M.fromList
[ ("arabic", \o -> case filter (/=' ') o of
"locale=algeria" -> Lang "ar" "" "DZ" []
"locale=mashriq" -> Lang "ar" "" "SY" []
"locale=libya" -> Lang "ar" "" "LY" []
"locale=morocco" -> Lang "ar" "" "MA" []
"locale=mauritania" -> Lang "ar" "" "MR" []
"locale=tunisia" -> Lang "ar" "" "TN" []
_ -> Lang "ar" "" "" [])
, ("german", \o -> case filter (/=' ') o of
"spelling=old" -> Lang "de" "" "DE" ["1901"]
"variant=austrian,spelling=old"
-> Lang "de" "" "AT" ["1901"]
"variant=austrian" -> Lang "de" "" "AT" []
"variant=swiss,spelling=old"
-> Lang "de" "" "CH" ["1901"]
"variant=swiss" -> Lang "de" "" "CH" []
_ -> Lang "de" "" "" [])
, ("lsorbian", \_ -> Lang "dsb" "" "" [])
, ("greek", \o -> case filter (/=' ') o of
"variant=poly" -> Lang "el" "" "polyton" []
"variant=ancient" -> Lang "grc" "" "" []
_ -> Lang "el" "" "" [])
, ("english", \o -> case filter (/=' ') o of
"variant=australian" -> Lang "en" "" "AU" []
"variant=canadian" -> Lang "en" "" "CA" []
"variant=british" -> Lang "en" "" "GB" []
"variant=newzealand" -> Lang "en" "" "NZ" []
"variant=american" -> Lang "en" "" "US" []
_ -> Lang "en" "" "" [])
, ("usorbian", \_ -> Lang "hsb" "" "" [])
, ("latin", \o -> case filter (/=' ') o of
"variant=classic" -> Lang "la" "" "" ["x-classic"]
_ -> Lang "la" "" "" [])
, ("slovenian", \_ -> Lang "sl" "" "" [])
, ("serbianc", \_ -> Lang "sr" "cyrl" "" [])
, ("pinyin", \_ -> Lang "zh" "Latn" "" ["pinyin"])
, ("afrikaans", \_ -> Lang "af" "" "" [])
, ("amharic", \_ -> Lang "am" "" "" [])
, ("assamese", \_ -> Lang "as" "" "" [])
, ("asturian", \_ -> Lang "ast" "" "" [])
, ("bulgarian", \_ -> Lang "bg" "" "" [])
, ("bengali", \_ -> Lang "bn" "" "" [])
, ("tibetan", \_ -> Lang "bo" "" "" [])
, ("breton", \_ -> Lang "br" "" "" [])
, ("catalan", \_ -> Lang "ca" "" "" [])
, ("welsh", \_ -> Lang "cy" "" "" [])
, ("czech", \_ -> Lang "cs" "" "" [])
, ("coptic", \_ -> Lang "cop" "" "" [])
, ("danish", \_ -> Lang "da" "" "" [])
, ("divehi", \_ -> Lang "dv" "" "" [])
, ("esperanto", \_ -> Lang "eo" "" "" [])
, ("spanish", \_ -> Lang "es" "" "" [])
, ("estonian", \_ -> Lang "et" "" "" [])
, ("basque", \_ -> Lang "eu" "" "" [])
, ("farsi", \_ -> Lang "fa" "" "" [])
, ("finnish", \_ -> Lang "fi" "" "" [])
, ("french", \_ -> Lang "fr" "" "" [])
, ("friulan", \_ -> Lang "fur" "" "" [])
, ("irish", \_ -> Lang "ga" "" "" [])
, ("scottish", \_ -> Lang "gd" "" "" [])
, ("ethiopic", \_ -> Lang "gez" "" "" [])
, ("galician", \_ -> Lang "gl" "" "" [])
, ("hebrew", \_ -> Lang "he" "" "" [])
, ("hindi", \_ -> Lang "hi" "" "" [])
, ("croatian", \_ -> Lang "hr" "" "" [])
, ("magyar", \_ -> Lang "hu" "" "" [])
, ("armenian", \_ -> Lang "hy" "" "" [])
, ("interlingua", \_ -> Lang "ia" "" "" [])
, ("indonesian", \_ -> Lang "id" "" "" [])
, ("icelandic", \_ -> Lang "is" "" "" [])
, ("italian", \_ -> Lang "it" "" "" [])
, ("japanese", \_ -> Lang "jp" "" "" [])
, ("khmer", \_ -> Lang "km" "" "" [])
, ("kurmanji", \_ -> Lang "kmr" "" "" [])
, ("kannada", \_ -> Lang "kn" "" "" [])
, ("korean", \_ -> Lang "ko" "" "" [])
, ("lao", \_ -> Lang "lo" "" "" [])
, ("lithuanian", \_ -> Lang "lt" "" "" [])
, ("latvian", \_ -> Lang "lv" "" "" [])
, ("malayalam", \_ -> Lang "ml" "" "" [])
, ("mongolian", \_ -> Lang "mn" "" "" [])
, ("marathi", \_ -> Lang "mr" "" "" [])
, ("dutch", \_ -> Lang "nl" "" "" [])
, ("nynorsk", \_ -> Lang "nn" "" "" [])
, ("norsk", \_ -> Lang "no" "" "" [])
, ("nko", \_ -> Lang "nqo" "" "" [])
, ("occitan", \_ -> Lang "oc" "" "" [])
, ("panjabi", \_ -> Lang "pa" "" "" [])
, ("polish", \_ -> Lang "pl" "" "" [])
, ("piedmontese", \_ -> Lang "pms" "" "" [])
, ("portuguese", \_ -> Lang "pt" "" "" [])
, ("romansh", \_ -> Lang "rm" "" "" [])
, ("romanian", \_ -> Lang "ro" "" "" [])
, ("russian", \_ -> Lang "ru" "" "" [])
, ("sanskrit", \_ -> Lang "sa" "" "" [])
, ("samin", \_ -> Lang "se" "" "" [])
, ("slovak", \_ -> Lang "sk" "" "" [])
, ("albanian", \_ -> Lang "sq" "" "" [])
, ("serbian", \_ -> Lang "sr" "" "" [])
, ("swedish", \_ -> Lang "sv" "" "" [])
, ("syriac", \_ -> Lang "syr" "" "" [])
, ("tamil", \_ -> Lang "ta" "" "" [])
, ("telugu", \_ -> Lang "te" "" "" [])
, ("thai", \_ -> Lang "th" "" "" [])
, ("turkmen", \_ -> Lang "tk" "" "" [])
, ("turkish", \_ -> Lang "tr" "" "" [])
, ("ukrainian", \_ -> Lang "uk" "" "" [])
, ("urdu", \_ -> Lang "ur" "" "" [])
, ("vietnamese", \_ -> Lang "vi" "" "" [])
]
babelLangToBCP47 :: String -> Maybe Lang
babelLangToBCP47 s =
case s of
"austrian" -> Just $ Lang "de" "" "AT" ["1901"]
"naustrian" -> Just $ Lang "de" "" "AT" []
"swissgerman" -> Just $ Lang "de" "" "CH" ["1901"]
"nswissgerman" -> Just $ Lang "de" "" "CH" []
"german" -> Just $ Lang "de" "" "DE" ["1901"]
"ngerman" -> Just $ Lang "de" "" "DE" []
"lowersorbian" -> Just $ Lang "dsb" "" "" []
"uppersorbian" -> Just $ Lang "hsb" "" "" []
"polutonikogreek" -> Just $ Lang "el" "" "" ["polyton"]
"slovene" -> Just $ Lang "sl" "" "" []
"australian" -> Just $ Lang "en" "" "AU" []
"canadian" -> Just $ Lang "en" "" "CA" []
"british" -> Just $ Lang "en" "" "GB" []
"newzealand" -> Just $ Lang "en" "" "NZ" []
"american" -> Just $ Lang "en" "" "US" []
"classiclatin" -> Just $ Lang "la" "" "" ["x-classic"]
_ -> fmap ($ "") $ M.lookup s polyglossiaLangToBCP47

173
src/Text/Pandoc/Readers/LaTeX/Lang.hs Normal file
View file

@ -0,0 +1,173 @@
{-# LANGUAGE NoImplicitPrelude #-}
{-
Copyright (C) 2018 John MacFarlane <jgm@berkeley.edu>
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program; if not, write to the Free Software
Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
-}
{- |
Module : Text.Pandoc.Readers.LaTeX.Lang
Copyright : Copyright (C) 2018 John MacFarlane
License : GNU GPL, version 2 or above
Maintainer : John MacFarlane <jgm@berkeley.edu>
Stability : alpha
Portability : portable
Functions for parsing polyglossia and babel language specifiers to
BCP47 'Lang'.
-}
module Text.Pandoc.Readers.LaTeX.Lang
( polyglossiaLangToBCP47
, babelLangToBCP47
)
where
import Prelude
import qualified Data.Map as M
import Text.Pandoc.BCP47 (Lang(..))
polyglossiaLangToBCP47 :: M.Map String (String -> Lang)
polyglossiaLangToBCP47 = M.fromList
[ ("arabic", \o -> case filter (/=' ') o of
"locale=algeria" -> Lang "ar" "" "DZ" []
"locale=mashriq" -> Lang "ar" "" "SY" []
"locale=libya" -> Lang "ar" "" "LY" []
"locale=morocco" -> Lang "ar" "" "MA" []
"locale=mauritania" -> Lang "ar" "" "MR" []
"locale=tunisia" -> Lang "ar" "" "TN" []
_ -> Lang "ar" "" "" [])
, ("german", \o -> case filter (/=' ') o of
"spelling=old" -> Lang "de" "" "DE" ["1901"]
"variant=austrian,spelling=old"
-> Lang "de" "" "AT" ["1901"]
"variant=austrian" -> Lang "de" "" "AT" []
"variant=swiss,spelling=old"
-> Lang "de" "" "CH" ["1901"]
"variant=swiss" -> Lang "de" "" "CH" []
_ -> Lang "de" "" "" [])
, ("lsorbian", \_ -> Lang "dsb" "" "" [])
, ("greek", \o -> case filter (/=' ') o of
"variant=poly" -> Lang "el" "" "polyton" []
"variant=ancient" -> Lang "grc" "" "" []
_ -> Lang "el" "" "" [])
, ("english", \o -> case filter (/=' ') o of
"variant=australian" -> Lang "en" "" "AU" []
"variant=canadian" -> Lang "en" "" "CA" []
"variant=british" -> Lang "en" "" "GB" []
"variant=newzealand" -> Lang "en" "" "NZ" []
"variant=american" -> Lang "en" "" "US" []
_ -> Lang "en" "" "" [])
, ("usorbian", \_ -> Lang "hsb" "" "" [])
, ("latin", \o -> case filter (/=' ') o of
"variant=classic" -> Lang "la" "" "" ["x-classic"]
_ -> Lang "la" "" "" [])
, ("slovenian", \_ -> Lang "sl" "" "" [])
, ("serbianc", \_ -> Lang "sr" "cyrl" "" [])
, ("pinyin", \_ -> Lang "zh" "Latn" "" ["pinyin"])
, ("afrikaans", \_ -> Lang "af" "" "" [])
, ("amharic", \_ -> Lang "am" "" "" [])
, ("assamese", \_ -> Lang "as" "" "" [])
, ("asturian", \_ -> Lang "ast" "" "" [])
, ("bulgarian", \_ -> Lang "bg" "" "" [])
, ("bengali", \_ -> Lang "bn" "" "" [])
, ("tibetan", \_ -> Lang "bo" "" "" [])
, ("breton", \_ -> Lang "br" "" "" [])
, ("catalan", \_ -> Lang "ca" "" "" [])
, ("welsh", \_ -> Lang "cy" "" "" [])
, ("czech", \_ -> Lang "cs" "" "" [])
, ("coptic", \_ -> Lang "cop" "" "" [])
, ("danish", \_ -> Lang "da" "" "" [])
, ("divehi", \_ -> Lang "dv" "" "" [])
, ("esperanto", \_ -> Lang "eo" "" "" [])
, ("spanish", \_ -> Lang "es" "" "" [])
, ("estonian", \_ -> Lang "et" "" "" [])
, ("basque", \_ -> Lang "eu" "" "" [])
, ("farsi", \_ -> Lang "fa" "" "" [])
, ("finnish", \_ -> Lang "fi" "" "" [])
, ("french", \_ -> Lang "fr" "" "" [])
, ("friulan", \_ -> Lang "fur" "" "" [])
, ("irish", \_ -> Lang "ga" "" "" [])
, ("scottish", \_ -> Lang "gd" "" "" [])
, ("ethiopic", \_ -> Lang "gez" "" "" [])
, ("galician", \_ -> Lang "gl" "" "" [])
, ("hebrew", \_ -> Lang "he" "" "" [])
, ("hindi", \_ -> Lang "hi" "" "" [])
, ("croatian", \_ -> Lang "hr" "" "" [])
, ("magyar", \_ -> Lang "hu" "" "" [])
, ("armenian", \_ -> Lang "hy" "" "" [])
, ("interlingua", \_ -> Lang "ia" "" "" [])
, ("indonesian", \_ -> Lang "id" "" "" [])
, ("icelandic", \_ -> Lang "is" "" "" [])
, ("italian", \_ -> Lang "it" "" "" [])
, ("japanese", \_ -> Lang "jp" "" "" [])
, ("khmer", \_ -> Lang "km" "" "" [])
, ("kurmanji", \_ -> Lang "kmr" "" "" [])
, ("kannada", \_ -> Lang "kn" "" "" [])
, ("korean", \_ -> Lang "ko" "" "" [])
, ("lao", \_ -> Lang "lo" "" "" [])
, ("lithuanian", \_ -> Lang "lt" "" "" [])
, ("latvian", \_ -> Lang "lv" "" "" [])
, ("malayalam", \_ -> Lang "ml" "" "" [])
, ("mongolian", \_ -> Lang "mn" "" "" [])
, ("marathi", \_ -> Lang "mr" "" "" [])
, ("dutch", \_ -> Lang "nl" "" "" [])
, ("nynorsk", \_ -> Lang "nn" "" "" [])
, ("norsk", \_ -> Lang "no" "" "" [])
, ("nko", \_ -> Lang "nqo" "" "" [])
, ("occitan", \_ -> Lang "oc" "" "" [])
, ("panjabi", \_ -> Lang "pa" "" "" [])
, ("polish", \_ -> Lang "pl" "" "" [])
, ("piedmontese", \_ -> Lang "pms" "" "" [])
, ("portuguese", \_ -> Lang "pt" "" "" [])
, ("romansh", \_ -> Lang "rm" "" "" [])
, ("romanian", \_ -> Lang "ro" "" "" [])
, ("russian", \_ -> Lang "ru" "" "" [])
, ("sanskrit", \_ -> Lang "sa" "" "" [])
, ("samin", \_ -> Lang "se" "" "" [])
, ("slovak", \_ -> Lang "sk" "" "" [])
, ("albanian", \_ -> Lang "sq" "" "" [])
, ("serbian", \_ -> Lang "sr" "" "" [])
, ("swedish", \_ -> Lang "sv" "" "" [])
, ("syriac", \_ -> Lang "syr" "" "" [])
, ("tamil", \_ -> Lang "ta" "" "" [])
, ("telugu", \_ -> Lang "te" "" "" [])
, ("thai", \_ -> Lang "th" "" "" [])
, ("turkmen", \_ -> Lang "tk" "" "" [])
, ("turkish", \_ -> Lang "tr" "" "" [])
, ("ukrainian", \_ -> Lang "uk" "" "" [])
, ("urdu", \_ -> Lang "ur" "" "" [])
, ("vietnamese", \_ -> Lang "vi" "" "" [])
]
babelLangToBCP47 :: String -> Maybe Lang
babelLangToBCP47 s =
case s of
"austrian" -> Just $ Lang "de" "" "AT" ["1901"]
"naustrian" -> Just $ Lang "de" "" "AT" []
"swissgerman" -> Just $ Lang "de" "" "CH" ["1901"]
"nswissgerman" -> Just $ Lang "de" "" "CH" []
"german" -> Just $ Lang "de" "" "DE" ["1901"]
"ngerman" -> Just $ Lang "de" "" "DE" []
"lowersorbian" -> Just $ Lang "dsb" "" "" []
"uppersorbian" -> Just $ Lang "hsb" "" "" []
"polutonikogreek" -> Just $ Lang "el" "" "" ["polyton"]
"slovene" -> Just $ Lang "sl" "" "" []
"australian" -> Just $ Lang "en" "" "AU" []
"canadian" -> Just $ Lang "en" "" "CA" []
"british" -> Just $ Lang "en" "" "GB" []
"newzealand" -> Just $ Lang "en" "" "NZ" []
"american" -> Just $ Lang "en" "" "US" []
"classiclatin" -> Just $ Lang "la" "" "" ["x-classic"]
_ -> fmap ($ "") $ M.lookup s polyglossiaLangToBCP47