blob: 3fdbdc5af717cdb31f26e3510c9d7a3e63539942 (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
|
{-# LANGUAGE OverloadedStrings #-}
{-# LANGUAGE ScopedTypeVariables #-}
{- |
Module : Text.Pandoc.Writers.LaTeX.Lang
Copyright : Copyright (C) 2006-2021 John MacFarlane
License : GNU GPL, version 2 or above
Maintainer : John MacFarlane <jgm@berkeley.edu>
Stability : alpha
Portability : portable
-}
module Text.Pandoc.Writers.LaTeX.Lang
( toBabel
) where
import Data.Text (Text)
import Text.Collate.Lang (Lang(..))
-- Takes a list of the constituents of a BCP47 language code and
-- converts it to a Babel language string.
-- http://mirrors.ctan.org/macros/latex/required/babel/base/babel.pdf
-- List of supported languages (slightly outdated):
-- http://tug.ctan.org/language/hyph-utf8/doc/generic/hyph-utf8/hyphenation.pdf
toBabel :: Lang -> Text
toBabel (Lang "de" _ (Just "AT") vars _ _)
| "1901" `elem` vars = "austrian"
| otherwise = "naustrian"
toBabel (Lang "de" _ (Just "CH") vars _ _)
| "1901" `elem` vars = "swissgerman"
| otherwise = "nswissgerman"
toBabel (Lang "de" _ _ vars _ _)
| "1901" `elem` vars = "german"
| otherwise = "ngerman"
toBabel (Lang "dsb" _ _ _ _ _) = "lowersorbian"
toBabel (Lang "el" _ _ vars _ _)
| "polyton" `elem` vars = "polutonikogreek"
toBabel (Lang "en" _ (Just "AU") _ _ _) = "australian"
toBabel (Lang "en" _ (Just "CA") _ _ _) = "canadian"
toBabel (Lang "en" _ (Just "GB") _ _ _) = "british"
toBabel (Lang "en" _ (Just "NZ") _ _ _) = "newzealand"
toBabel (Lang "en" _ (Just "UK") _ _ _) = "british"
toBabel (Lang "en" _ (Just "US") _ _ _) = "american"
toBabel (Lang "fr" _ (Just "CA") _ _ _) = "canadien"
toBabel (Lang "fra" _ _ vars _ _)
| "aca" `elem` vars = "acadian"
toBabel (Lang "grc" _ _ _ _ _) = "ancientgreek"
toBabel (Lang "hsb" _ _ _ _ _) = "uppersorbian"
toBabel (Lang "la" _ _ vars _ _)
| "x-classic" `elem` vars = "classiclatin"
toBabel (Lang "pt" _ (Just "BR") _ _ _) = "brazilian"
toBabel (Lang "sl" _ _ _ _ _) = "slovene"
toBabel x = commonFromBcp47 x
-- Takes a list of the constituents of a BCP47 language code
-- and converts it to a string shared by Babel and Polyglossia.
-- https://tools.ietf.org/html/bcp47#section-2.1
commonFromBcp47 :: Lang -> Text
commonFromBcp47 (Lang "sr" (Just "Cyrl") _ _ _ _) = "serbianc"
commonFromBcp47 (Lang "zh" (Just "Latn") _ vars _ _)
| "pinyin" `elem` vars = "pinyin"
commonFromBcp47 (Lang l _ _ _ _ _) = fromIso l
where
fromIso "af" = "afrikaans"
fromIso "am" = "amharic"
fromIso "ar" = "arabic"
fromIso "as" = "assamese"
fromIso "ast" = "asturian"
fromIso "bg" = "bulgarian"
fromIso "bn" = "bengali"
fromIso "bo" = "tibetan"
fromIso "br" = "breton"
fromIso "ca" = "catalan"
fromIso "cy" = "welsh"
fromIso "cs" = "czech"
fromIso "cop" = "coptic"
fromIso "da" = "danish"
fromIso "dv" = "divehi"
fromIso "el" = "greek"
fromIso "en" = "english"
fromIso "eo" = "esperanto"
fromIso "es" = "spanish"
fromIso "et" = "estonian"
fromIso "eu" = "basque"
fromIso "fa" = "farsi"
fromIso "fi" = "finnish"
fromIso "fr" = "french"
fromIso "fur" = "friulan"
fromIso "ga" = "irish"
fromIso "gd" = "scottish"
fromIso "gez" = "ethiopic"
fromIso "gl" = "galician"
fromIso "he" = "hebrew"
fromIso "hi" = "hindi"
fromIso "hr" = "croatian"
fromIso "hu" = "magyar"
fromIso "hy" = "armenian"
fromIso "ia" = "interlingua"
fromIso "id" = "indonesian"
fromIso "ie" = "interlingua"
fromIso "is" = "icelandic"
fromIso "it" = "italian"
fromIso "ja" = "japanese"
fromIso "km" = "khmer"
fromIso "kmr" = "kurmanji"
fromIso "kn" = "kannada"
fromIso "ko" = "korean"
fromIso "la" = "latin"
fromIso "lo" = "lao"
fromIso "lt" = "lithuanian"
fromIso "lv" = "latvian"
fromIso "ml" = "malayalam"
fromIso "mn" = "mongolian"
fromIso "mr" = "marathi"
fromIso "nb" = "norsk"
fromIso "nl" = "dutch"
fromIso "nn" = "nynorsk"
fromIso "no" = "norsk"
fromIso "nqo" = "nko"
fromIso "oc" = "occitan"
fromIso "pa" = "panjabi"
fromIso "pl" = "polish"
fromIso "pms" = "piedmontese"
fromIso "pt" = "portuguese"
fromIso "rm" = "romansh"
fromIso "ro" = "romanian"
fromIso "ru" = "russian"
fromIso "sa" = "sanskrit"
fromIso "se" = "samin"
fromIso "sk" = "slovak"
fromIso "sq" = "albanian"
fromIso "sr" = "serbian"
fromIso "sv" = "swedish"
fromIso "syr" = "syriac"
fromIso "ta" = "tamil"
fromIso "te" = "telugu"
fromIso "th" = "thai"
fromIso "ti" = "ethiopic"
fromIso "tk" = "turkmen"
fromIso "tr" = "turkish"
fromIso "uk" = "ukrainian"
fromIso "ur" = "urdu"
fromIso "vi" = "vietnamese"
fromIso _ = ""
|
