diff options
| author | John MacFarlane <jgm@berkeley.edu> | 2021-04-11 21:28:48 -0700 |
|---|---|---|
| committer | John MacFarlane <jgm@berkeley.edu> | 2021-04-17 16:15:14 -0700 |
| commit | aecbf8156eb7c36c4b41de27797e262c23728db5 (patch) | |
| tree | 2c9fe9de41a0f7037485dacee444b36cc2ccc110 /src/Text/Pandoc/Readers | |
| parent | 7ba8c0d2a5e2b89ae1547759510b2ee21de88cb1 (diff) | |
| download | pandoc-aecbf8156eb7c36c4b41de27797e262c23728db5.tar.gz | |
Remove Text.Pandoc.BCP47 module.
[API change]
Use Lang from UnicodeCollation.Lang instead.
This is a richer implementation of BCP 47.
Diffstat (limited to 'src/Text/Pandoc/Readers')
| -rw-r--r-- | src/Text/Pandoc/Readers/BibTeX.hs | 9 | ||||
| -rw-r--r-- | src/Text/Pandoc/Readers/LaTeX.hs | 2 | ||||
| -rw-r--r-- | src/Text/Pandoc/Readers/LaTeX/Lang.hs | 241 |
3 files changed, 129 insertions, 123 deletions
diff --git a/src/Text/Pandoc/Readers/BibTeX.hs b/src/Text/Pandoc/Readers/BibTeX.hs index 956b9f1f7..b82a81350 100644 --- a/src/Text/Pandoc/Readers/BibTeX.hs +++ b/src/Text/Pandoc/Readers/BibTeX.hs @@ -48,11 +48,14 @@ readBibLaTeX = readBibTeX' BibTeX.Biblatex readBibTeX' :: PandocMonad m => Variant -> ReaderOptions -> Text -> m Pandoc readBibTeX' variant _opts t = do - lang <- maybe (Lang "en" (Just "US")) parseLang - <$> lookupEnv "LANG" + mblangEnv <- lookupEnv "LANG" + let defaultLang = Lang "en" Nothing (Just "US") [] [] [] + let lang = case mblangEnv of + Nothing -> defaultLang + Just l -> either (const defaultLang) id $ parseLang l locale <- case getLocale lang of Left e -> - case getLocale (Lang "en" (Just "US")) of + case getLocale (Lang "en" Nothing (Just "US") [] [] []) of Right l -> return l Left _ -> throwError $ PandocCiteprocError e Right l -> return l diff --git a/src/Text/Pandoc/Readers/LaTeX.hs b/src/Text/Pandoc/Readers/LaTeX.hs index 851756065..83caf742a 100644 --- a/src/Text/Pandoc/Readers/LaTeX.hs +++ b/src/Text/Pandoc/Readers/LaTeX.hs @@ -33,7 +33,7 @@ import qualified Data.Set as Set import Data.Text (Text) import qualified Data.Text as T import System.FilePath (addExtension, replaceExtension, takeExtension) -import Text.Pandoc.BCP47 (renderLang) +import UnicodeCollation.Lang (renderLang) import Text.Pandoc.Builder as B import Text.Pandoc.Class.PandocPure (PandocPure) import Text.Pandoc.Class.PandocMonad (PandocMonad (..), getResourcePath, diff --git a/src/Text/Pandoc/Readers/LaTeX/Lang.hs b/src/Text/Pandoc/Readers/LaTeX/Lang.hs index 08e217bdb..b92e6ab57 100644 --- a/src/Text/Pandoc/Readers/LaTeX/Lang.hs +++ b/src/Text/Pandoc/Readers/LaTeX/Lang.hs @@ -23,7 +23,7 @@ import qualified Data.Map as M import Data.Text (Text) import qualified Data.Text as T import Text.Pandoc.Shared (extractSpaces) -import Text.Pandoc.BCP47 (Lang(..), renderLang) +import UnicodeCollation.Lang (Lang(..), renderLang) import Text.Pandoc.Class (PandocMonad(..), setTranslations) import Text.Pandoc.Readers.LaTeX.Parsing import Text.Pandoc.Parsing (updateState, option, getState, QuoteContext(..), @@ -99,133 +99,136 @@ setDefaultLanguage = do polyglossiaLangToBCP47 :: M.Map T.Text (T.Text -> Lang) polyglossiaLangToBCP47 = M.fromList [ ("arabic", \o -> case T.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" "" "" []) + "locale=algeria" -> Lang "ar" Nothing (Just "DZ") [] [] [] + "locale=mashriq" -> Lang "ar" Nothing (Just "SY") [] [] [] + "locale=libya" -> Lang "ar" Nothing (Just "LY") [] [] [] + "locale=morocco" -> Lang "ar" Nothing (Just "MA") [] [] [] + "locale=mauritania" -> Lang "ar" Nothing (Just "MR") [] [] [] + "locale=tunisia" -> Lang "ar" Nothing (Just "TN") [] [] [] + _ -> Lang "ar" Nothing (Just "") [] [] []) , ("german", \o -> case T.filter (/=' ') o of - "spelling=old" -> Lang "de" "" "DE" ["1901"] + "spelling=old" -> Lang "de" Nothing (Just "DE") ["1901"] [] [] "variant=austrian,spelling=old" - -> Lang "de" "" "AT" ["1901"] - "variant=austrian" -> Lang "de" "" "AT" [] + -> Lang "de" Nothing (Just "AT") ["1901"] [] [] + "variant=austrian" -> Lang "de" Nothing (Just "AT") [] [] [] "variant=swiss,spelling=old" - -> Lang "de" "" "CH" ["1901"] - "variant=swiss" -> Lang "de" "" "CH" [] - _ -> Lang "de" "" "" []) - , ("lsorbian", \_ -> Lang "dsb" "" "" []) + -> Lang "de" Nothing (Just "CH") ["1901"] [] [] + "variant=swiss" -> Lang "de" Nothing (Just "CH") [] [] [] + _ -> Lang "de" Nothing Nothing [] [] []) + , ("lsorbian", \_ -> Lang "dsb" Nothing Nothing [] [] []) , ("greek", \o -> case T.filter (/=' ') o of - "variant=poly" -> Lang "el" "" "polyton" [] - "variant=ancient" -> Lang "grc" "" "" [] - _ -> Lang "el" "" "" []) + "variant=poly" -> Lang "el" Nothing (Just "polyton") [] [] [] + "variant=ancient" -> Lang "grc" Nothing Nothing [] [] [] + _ -> Lang "el" Nothing Nothing [] [] []) , ("english", \o -> case T.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" "" "" []) + "variant=australian" -> Lang "en" Nothing (Just "AU") [] [] [] + "variant=canadian" -> Lang "en" Nothing (Just "CA") [] [] [] + "variant=british" -> Lang "en" Nothing (Just "GB") [] [] [] + "variant=newzealand" -> Lang "en" Nothing (Just "NZ") [] [] [] + "variant=american" -> Lang "en" Nothing (Just "US") [] [] [] + _ -> Lang "en" Nothing (Just "") [] [] []) + , ("usorbian", \_ -> Lang "hsb" Nothing Nothing [] [] []) , ("latin", \o -> case T.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" "" "" []) + "variant=classic" -> Lang "la" Nothing Nothing ["x-classic"] [] [] + _ -> Lang "la" Nothing Nothing [] [] []) + , ("slovenian", \_ -> Lang "sl" Nothing Nothing [] [] []) + , ("serbianc", \_ -> Lang "sr" (Just "Cyrl") Nothing [] [] []) + , ("pinyin", \_ -> Lang "zh" (Just "Latn") Nothing ["pinyin"] [] []) + , ("afrikaans", \_ -> simpleLang "af") + , ("amharic", \_ -> simpleLang "am") + , ("assamese", \_ -> simpleLang "as") + , ("asturian", \_ -> simpleLang "ast") + , ("bulgarian", \_ -> simpleLang "bg") + , ("bengali", \_ -> simpleLang "bn") + , ("tibetan", \_ -> simpleLang "bo") + , ("breton", \_ -> simpleLang "br") + , ("catalan", \_ -> simpleLang "ca") + , ("welsh", \_ -> simpleLang "cy") + , ("czech", \_ -> simpleLang "cs") + , ("coptic", \_ -> simpleLang "cop") + , ("danish", \_ -> simpleLang "da") + , ("divehi", \_ -> simpleLang "dv") + , ("esperanto", \_ -> simpleLang "eo") + , ("spanish", \_ -> simpleLang "es") + , ("estonian", \_ -> simpleLang "et") + , ("basque", \_ -> simpleLang "eu") + , ("farsi", \_ -> simpleLang "fa") + , ("finnish", \_ -> simpleLang "fi") + , ("french", \_ -> simpleLang "fr") + , ("friulan", \_ -> simpleLang "fur") + , ("irish", \_ -> simpleLang "ga") + , ("scottish", \_ -> simpleLang "gd") + , ("ethiopic", \_ -> simpleLang "gez") + , ("galician", \_ -> simpleLang "gl") + , ("hebrew", \_ -> simpleLang "he") + , ("hindi", \_ -> simpleLang "hi") + , ("croatian", \_ -> simpleLang "hr") + , ("magyar", \_ -> simpleLang "hu") + , ("armenian", \_ -> simpleLang "hy") + , ("interlingua", \_ -> simpleLang "ia") + , ("indonesian", \_ -> simpleLang "id") + , ("icelandic", \_ -> simpleLang "is") + , ("italian", \_ -> simpleLang "it") + , ("japanese", \_ -> simpleLang "jp") + , ("khmer", \_ -> simpleLang "km") + , ("kurmanji", \_ -> simpleLang "kmr") + , ("kannada", \_ -> simpleLang "kn") + , ("korean", \_ -> simpleLang "ko") + , ("lao", \_ -> simpleLang "lo") + , ("lithuanian", \_ -> simpleLang "lt") + , ("latvian", \_ -> simpleLang "lv") + , ("malayalam", \_ -> simpleLang "ml") + , ("mongolian", \_ -> simpleLang "mn") + , ("marathi", \_ -> simpleLang "mr") + , ("dutch", \_ -> simpleLang "nl") + , ("nynorsk", \_ -> simpleLang "nn") + , ("norsk", \_ -> simpleLang "no") + , ("nko", \_ -> simpleLang "nqo") + , ("occitan", \_ -> simpleLang "oc") + , ("panjabi", \_ -> simpleLang "pa") + , ("polish", \_ -> simpleLang "pl") + , ("piedmontese", \_ -> simpleLang "pms") + , ("portuguese", \_ -> simpleLang "pt") + , ("romansh", \_ -> simpleLang "rm") + , ("romanian", \_ -> simpleLang "ro") + , ("russian", \_ -> simpleLang "ru") + , ("sanskrit", \_ -> simpleLang "sa") + , ("samin", \_ -> simpleLang "se") + , ("slovak", \_ -> simpleLang "sk") + , ("albanian", \_ -> simpleLang "sq") + , ("serbian", \_ -> simpleLang "sr") + , ("swedish", \_ -> simpleLang "sv") + , ("syriac", \_ -> simpleLang "syr") + , ("tamil", \_ -> simpleLang "ta") + , ("telugu", \_ -> simpleLang "te") + , ("thai", \_ -> simpleLang "th") + , ("turkmen", \_ -> simpleLang "tk") + , ("turkish", \_ -> simpleLang "tr") + , ("ukrainian", \_ -> simpleLang "uk") + , ("urdu", \_ -> simpleLang "ur") + , ("vietnamese", \_ -> simpleLang "vi") ] +simpleLang :: Text -> Lang +simpleLang l = Lang l Nothing Nothing [] [] [] + babelLangToBCP47 :: T.Text -> 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"] + "austrian" -> Just $ Lang "de" Nothing (Just "AT") ["1901"] [] [] + "naustrian" -> Just $ Lang "de" Nothing (Just "AT") [] [] [] + "swissgerman" -> Just $ Lang "de" Nothing (Just "CH") ["1901"] [] [] + "nswissgerman" -> Just $ Lang "de" Nothing (Just "CH") [] [] [] + "german" -> Just $ Lang "de" Nothing (Just "DE") ["1901"] [] [] + "ngerman" -> Just $ Lang "de" Nothing (Just "DE") [] [] [] + "lowersorbian" -> Just $ Lang "dsb" Nothing Nothing [] [] [] + "uppersorbian" -> Just $ Lang "hsb" Nothing Nothing [] [] [] + "polutonikogreek" -> Just $ Lang "el" Nothing Nothing ["polyton"] [] [] + "slovene" -> Just $ simpleLang "sl" + "australian" -> Just $ Lang "en" Nothing (Just "AU") [] [] [] + "canadian" -> Just $ Lang "en" Nothing (Just "CA") [] [] [] + "british" -> Just $ Lang "en" Nothing (Just "GB") [] [] [] + "newzealand" -> Just $ Lang "en" Nothing (Just "NZ") [] [] [] + "american" -> Just $ Lang "en" Nothing (Just "US") [] [] [] + "classiclatin" -> Just $ Lang "la" Nothing Nothing ["x-classic"] [] [] _ -> ($ "") <$> M.lookup s polyglossiaLangToBCP47 |