sisu 7.0.0

data/lib/sisu/i18n.rb

@@ -0,0 +1,702 @@
+# encoding: utf-8
+=begin
+
+* Name: SiSU
+
+** Description: documents, structuring, processing, publishing, search
+*** internationalisation
+
+** Author: Ralph Amissah
+  <ralph@amissah.com>
+  <ralph.amissah@gmail.com>
+
+** Copyright: (C) 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006,
+  2007, 2008, 2009, 2010, 2011, 2012, 2013, 2014, 2015 Ralph Amissah,
+  All Rights Reserved.
+
+** License: GPL 3 or later:
+
+  SiSU, a framework for document structuring, publishing and search
+
+  Copyright (C) Ralph Amissah
+
+  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 3 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, see <http://www.gnu.org/licenses/>.
+
+  If you have Internet connection, the latest version of the GPL should be
+  available at these locations:
+  <http://www.fsf.org/licensing/licenses/gpl.html>
+  <http://www.gnu.org/licenses/gpl.html>
+
+  <http://www.sisudoc.org/sisu/en/manifest/gpl.fsf.html>
+
+** SiSU uses:
+  * Standard SiSU markup syntax,
+  * Standard SiSU meta-markup syntax, and the
+  * Standard SiSU object citation numbering and system
+
+** Hompages:
+  <http://www.jus.uio.no/sisu>
+  <http://www.sisudoc.org>
+
+** Git
+  <http://git.sisudoc.org/gitweb/?p=code/sisu.git;a=summary>
+  <http://git.sisudoc.org/gitweb/?p=code/sisu.git;a=blob;f=lib/sisu/i18n.rb;hb=HEAD>
+
+=end
+module SiSU_i18n
+  @@language_table,@@language_list=nil,nil
+  class Languages
+    def language
+      def table
+        @@language_table ||= {
+          am:    { c: 'am',    n: 'Amharic',           t: 'Amharic',                     xlp: 'amharic'          },
+          bg:    { c: 'bg',    n: 'Bulgarian',         t: 'Български (Bəlgarski)',       xlp: 'bulgarian'        },
+          bn:    { c: 'bn',    n: 'Bengali',           t: 'Bengali',                     xlp: 'bengali'          },
+          br:    { c: 'br',    n: 'Breton',            t: 'Breton',                      xlp: 'breton'           },
+          ca:    { c: 'ca',    n: 'Catalan',           t: 'catalan',                     xlp: 'catalan'          },
+          cs:    { c: 'cs',    n: 'Czech',             t: 'česky',                       xlp: 'czech'            },
+          cy:    { c: 'cy',    n: 'Welsh',             t: 'Welsh',                       xlp: 'welsh'            },
+          da:    { c: 'da',    n: 'Danish',            t: 'dansk',                       xlp: 'danish'           },
+          de:    { c: 'de',    n: 'German',            t: 'Deutsch',                     xlp: 'german'           },
+          el:    { c: 'el',    n: 'Greek',             t: 'Ελληνικά (Ellinika)',         xlp: 'greek'            },
+          en:    { c: 'en',    n: 'English',           t: 'English',                     xlp: 'english'          },
+          eo:    { c: 'eo',    n: 'Esperanto',         t: 'Esperanto',                   xlp: 'esperanto'        },
+          es:    { c: 'es',    n: 'Spanish',           t: 'español',                     xlp: 'spanish'          },
+          et:    { c: 'et',    n: 'Estonian',          t: 'Estonian',                    xlp: 'estonian'         },
+          eu:    { c: 'eu',    n: 'Basque',            t: 'basque',                      xlp: 'basque'           },
+          fi:    { c: 'fi',    n: 'Finnish',           t: 'suomi',                       xlp: 'finnish'          },
+          fr:    { c: 'fr',    n: 'French',            t: 'français',                    xlp: 'french'           },
+          ga:    { c: 'ga',    n: 'Irish',             t: 'Irish',                       xlp: 'irish'            },
+          gl:    { c: 'gl',    n: 'Galician',          t: 'Galician',                    xlp: 'galician'         },
+          he:    { c: 'he',    n: 'Hebrew',            t: 'Hebrew',                      xlp: 'hebrew'           },
+          hi:    { c: 'hi',    n: 'Hindi',             t: 'Hindi',                       xlp: 'hindi'            },
+          hr:    { c: 'hr',    n: 'Croatian',          t: 'Croatian',                    xlp: 'croatian'         },
+          hy:    { c: 'hy',    n: 'Armenian',          t: 'Armenian',                    xlp: 'armenian'         },
+          ia:    { c: 'ia',    n: 'Interlingua',       t: 'Interlingua',                 xlp: 'interlingua'      },
+          is:    { c: 'is',    n: 'Icelandic',         t: 'Icelandic',                   xlp: 'icelandic'        },
+          it:    { c: 'it',    n: 'Italian',           t: 'Italiano',                    xlp: 'italian'          },
+          ja:    { c: 'ja',    n: 'Japanese',          t: '日本語 (Nihongo)',            xlp: 'japanese'         },
+          ko:    { c: 'ko',    n: 'Korean',            t: 'Korean',                      xlp: 'korean'           },
+          la:    { c: 'la',    n: 'Latin',             t: 'Latin',                       xlp: 'latin'            },
+          lo:    { c: 'lo',    n: 'Lao',               t: 'Lao',                         xlp: 'lao'              },
+          lt:    { c: 'lt',    n: 'Lithuanian',        t: 'Lithuanian',                  xlp: 'lithuanian'       },
+          lv:    { c: 'lv',    n: 'Latvian',           t: 'Latvian',                     xlp: 'latvian'          },
+          ml:    { c: 'ml',    n: 'Malayalam',         t: 'Malayalam',                   xlp: 'malayalam'        },
+          mr:    { c: 'mr',    n: 'Marathi',           t: 'Marathi',                     xlp: 'marathi'          },
+          nl:    { c: 'nl',    n: 'Dutch',             t: 'Nederlands',                  xlp: 'dutch'            },
+          no:    { c: 'no',    n: 'Norwegian',         t: 'norsk',                       xlp: 'norsk'            },
+          nn:    { c: 'nn',    n: 'Norwegian Nynorsk', t: 'nynorsk',                     xlp: 'nynorsk'          },
+          oc:    { c: 'oc',    n: 'Occitan',           t: 'Occitan',                     xlp: 'occitan'          },
+          pl:    { c: 'pl',    n: 'Polish',            t: 'polski',                      xlp: 'polish'           },
+          pt:    { c: 'pt',    n: 'Portuguese',        t: 'Português',                   xlp: 'portuges'         },
+          pt_BR: { c: 'pt_BR', n: 'Portuguese Brazil', t: 'Brazilian Português',         xlp: 'brazilian'        },
+          ro:    { c: 'ro',    n: 'Romanian',          t: 'română',                      xlp: 'romanian'         },
+          ru:    { c: 'ru',    n: 'Russian',           t: 'Русский (Russkij)',           xlp: 'russian'          },
+          sa:    { c: 'sa',    n: 'Sanskrit',          t: 'Sanskrit',                    xlp: 'sanskrit'         },
+          se:    { c: 'se',    n: 'Sami',              t: 'Samin',                       xlp: 'samin'            },
+          sk:    { c: 'sk',    n: 'Slovak',            t: 'slovensky',                   xlp: 'slovak'           },
+          sl:    { c: 'sl',    n: 'Slovenian',         t: 'Slovenian',                   xlp: 'slovenian'        },
+          sq:    { c: 'sq',    n: 'Albanian',          t: 'Albanian',                    xlp: 'albanian'         },
+          sr:    { c: 'sr',    n: 'Serbian',           t: 'Serbian',                     xlp: 'serbian'          },
+          sv:    { c: 'sv',    n: 'Swedish',           t: 'svenska',                     xlp: 'swedish'          },
+          ta:    { c: 'ta',    n: 'Tamil',             t: 'Tamil',                       xlp: 'tamil'            },
+          te:    { c: 'te',    n: 'Telugu',            t: 'Telugu',                      xlp: 'telugu'           },
+          th:    { c: 'th',    n: 'Thai',              t: 'Thai',                        xlp: 'thai'             },
+          tk:    { c: 'tk',    n: 'Turkmen',           t: 'Turkmen',                     xlp: 'turkmen'          },
+          tr:    { c: 'tr',    n: 'Turkish',           t: 'Türkçe',                      xlp: 'turkish'          },
+          uk:    { c: 'uk',    n: 'Ukranian',          t: 'українська (ukrajins\'ka)',   xlp: 'ukrainian'        },
+          ur:    { c: 'ur',    n: 'Urdu',              t: 'Urdu',                        xlp: 'urdu'             },
+          us:    { c: 'en',    n: 'English (American)',t: 'English',                     xlp: 'english'          },
+          vi:    { c: 'vi',    n: 'Vietnamese',        t: 'Vietnamese',                  xlp: 'vietnamese'       },
+          zh:    { c: 'zh',    n: 'Chinese',           t: '中文',                        xlp: 'chinese'          },
+          en:    { c: 'en',    n: 'English',           t: 'English',                     xlp: 'english'          },
+          xx:    { c: 'xx',    n: 'Default',           t: 'English',                     xlp: 'english'          },
+        }
+      end
+      def list
+        @@language_list ||= {
+          'am'    => table[:am],
+          'bg'    => table[:bg],
+          'bn'    => table[:bn],
+          'br'    => table[:br],
+          'ca'    => table[:ca],
+          'cs'    => table[:cs],
+          'cy'    => table[:cy],
+          'da'    => table[:da],
+          'de'    => table[:de],
+          'el'    => table[:el],
+          'en'    => table[:en],
+          'eo'    => table[:eo],
+          'es'    => table[:es],
+          'et'    => table[:et],
+          'eu'    => table[:eu],
+          'fi'    => table[:fi],
+          'fr'    => table[:fr],
+          'ga'    => table[:ga],
+          'gl'    => table[:gl],
+          'he'    => table[:he],
+          'hi'    => table[:hi],
+          'hr'    => table[:hr],
+          'hy'    => table[:hy],
+          'ia'    => table[:ia],
+          'is'    => table[:is],
+          'it'    => table[:it],
+          'ja'    => table[:ja],
+          'ko'    => table[:ko],
+          'la'    => table[:la],
+          'lo'    => table[:lo],
+          'lt'    => table[:lt],
+          'lv'    => table[:lv],
+          'ml'    => table[:ml],
+          'mr'    => table[:mr],
+          'nl'    => table[:nl],
+          'no'    => table[:no],
+          'nn'    => table[:nn],
+          'oc'    => table[:oc],
+          'pl'    => table[:pl],
+          'pt'    => table[:pt],
+          'pt_BR' => table[:pt_BR],
+          'ro'    => table[:ro],
+          'ru'    => table[:ru],
+          'sa'    => table[:sa],
+          'se'    => table[:se],
+          'sk'    => table[:sk],
+          'sl'    => table[:sl],
+          'sq'    => table[:sq],
+          'sr'    => table[:sr],
+          'sv'    => table[:sv],
+          'ta'    => table[:ta],
+          'te'    => table[:te],
+          'th'    => table[:th],
+          'tk'    => table[:tk],
+          'tr'    => table[:tr],
+          'uk'    => table[:uk],
+          'ur'    => table[:ur],
+          'us'    => table[:en],
+          'vi'    => table[:vi],
+          'zh'    => table[:zh],
+          'en'    => table[:en],
+          'xx'    => table[:en]
+        }
+      end
+      self
+    end
+  end
+  class Alphabet
+    def initialize(lng_code)
+      @lng_code=lng_code
+    end
+    def hash_arrays
+      @alph=case @lng_code
+      when /en/                                                              #english
+        {
+          u: %w[A B C D E F G H I J K L M N O P Q R S T U V W X Y Z],
+          l: %w[a b c d e f g h i j k l m n o p q r s t u v w x y z]
+        }
+      when /da|no|nn/                                                        #danish, norwegian
+        {
+          u: %w[A B C D E F G H I J K L M N O P Q R S T U V W X Y Z Å Æ Ø],
+          l: %w[a b c d e f g h i j k l m n o p q r s t u v w x y z å æ ø]
+          #u: %W[A B C D E F G H I J K L M N O P Q R S T U V W X Y Z Æ Ø Å],
+          #l: %w[a b c d e f g h i j k l m n o p q r s t u v w x y z æ ø å]
+        }
+      when /sv/                                                              #swedish
+        {
+          u: %w[A B C D E F G H I J K L M N O P Q R S T U V W X Y Z Å Ä Ö],
+          l: %w[a b c d e f g h i j k l m n o p q r s t u v w x y z å ä ö]
+        }
+      else                                                                   #english default
+        {
+          u: %w[A B C D E F G H I J K L M N O P Q R S T U V W X Y Z],
+          l: %w[a b c d e f g h i j k l m n o p q r s t u v w x y z]
+        }
+      end
+    end
+    def hash_strings
+      { u: hash_arrays[:u].join, l: hash_arrays[:l].join }
+    end
+  end
+end
+__END__
+Language Lists
+* po4a c:
+  <http://www.debian.org/international/l10n/po/>
+  Px[:lng_lst] see constants.rb
+* polyglossia xlp:
+  <http://mirrors.ctan.org/macros/xetex/latex/polyglossia/polyglossia.pdf>
+  missing from (:c) list:
+    arabic asturian bahasai bahasam coptic divehi farsi lsorbian magyar scottish syriac usorbian
+note ISO_639-1
+  <http://en.wikipedia.org/wiki/ISO_639-1>
+  <http://en.wikipedia.org/wiki/List_of_ISO_639-1_codes>
+also note ISO_639-2
+  <http://en.wikipedia.org/wiki/ISO_639-2>
+  <http://en.wikipedia.org/wiki/List_of_ISO_639-2_codes>
+
+Px[:lng_lst] # constants.rb
+
+module SiSU_TextTranslation
+  class Language
+    def initialize(md)
+      @md=md
+    end
+    def tex_name(char)
+      @lang=if char
+        case char
+        when 'sq'    then 'albanian'
+        when 'am'    then 'amharic'
+       #when 'ar'    then 'arabic'         # see polyglossia
+        when 'hy'    then 'armenian'
+       #when ''      then 'asturian'       # polyglossia
+       #when ''      then 'bahasai'        # polyglossia
+       #when ''      then 'bahasam'        # polyglossia
+        when 'eu'    then 'basque'
+        when 'bn'    then 'bengali'
+        when 'pt_BR' then 'brazilian'
+        when 'br'    then 'breton'
+        when 'bg'    then 'bulgarian'
+        when 'ca'    then 'catalan'        # see polyglossia
+       #when ''      then 'coptic'         # polyglossia
+        when 'hr'    then 'croatian'
+        when 'cs'    then 'czech'
+        when 'da'    then 'danish'
+       #when ''      then 'divehi'         # polyglossia
+        when 'nl'    then 'dutch'          # see polyglossia
+        when 'en'    then 'english'        # see polyglossia
+        when 'eo'    then 'esperanto'      # see polyglossia
+        when 'et'    then 'estonian'
+        when 'gl'    then 'galician'
+        when 'de'    then 'german'
+        when 'el'    then 'greek'          #gl ?
+        when 'he'    then 'hebrew'
+        when 'hi'    then 'hindi'
+        when 'is'    then 'icelandic'
+        when 'ia'    then 'interlingua'
+        when 'ga'    then 'irish'
+        when 'it'    then 'italian'
+       #when ''      then 'farsi'          # polyglossia
+        when 'fi'    then 'finnish'
+        when 'fr'    then 'french'
+        when 'lo'    then 'lao'
+        when 'la'    then 'latin'
+        when 'lv'    then 'latvian'
+        when 'lt'    then 'lithuanian'
+       #when ''      then 'lsorbian'       # polyglossia
+       #when ''      then 'magyar'         # polyglossia
+        when 'ml'    then 'malayalam'
+        when 'mr'    then 'marathi'
+       #when 'hu'    then 'magyar'
+        when 'no'    then 'norske'
+        when 'nn'    then 'nynorsk'
+        when 'oc'    then 'occitan'
+        when 'pl'    then 'polish'
+        when 'pt'    then 'portuges'
+        when 'ro'    then 'romanian'
+        when 'ru'    then 'russian'
+        when 'se'    then 'samin'          #(check sami?)
+        when 'sa'    then 'sanskrit'
+        when 'sr'    then 'serbian'
+       #when ''      then 'scottish'       # polyglossia  (gd (Gaelic (Scots)))
+        when 'sk'    then 'slovak'
+        when 'sl'    then 'slovenian'
+        when 'es'    then 'spanish'
+        when 'sv'    then 'swedish'
+        when 'ta'    then 'tamil'
+        when 'te'    then 'telugu'
+        when 'th'    then 'thai'
+        when 'tr'    then 'turkish'
+        when 'tk'    then 'turkmen'
+        when 'uk'    then 'ukrainian'
+        when 'ur'    then 'urdu'
+       #when ''      then 'usorbian'       # polyglossia
+        when 'vi'    then 'vietnamese'
+        when 'cy'    then 'welsh'
+        when 'us'    then 'USenglish'      # depreciated, see iso-639-2
+        else         then 'english'
+        end
+      else            'english'
+      end
+    end
+  end
+end
+#% Language List po4a
+http://www.debian.org/international/l10n/po/
+see polyglossia for subset
+* CSB (Unknown language)
+* KAB (Unknown language)
+* TLH (Unknown language)
+* aa (Afar)
+* ab (Abkhazian)
+* af (Afrikaans)
+* af_ZA (Afrikaans, as spoken in South Africa)
+* am (Amharic)
+* an (Unknown language)
+* ang (Unknown language)
+* ar (Arabic)
+* ar_AR (Arabic, as spoken in Argentina)
+* ar_EG (Arabic, as spoken in Egypt)
+* ar_OM (Arabic, as spoken in Oman)
+* ar_PS (Arabic, as spoken in Palestinian Territory, Occupied)
+* ar_SA (Arabic, as spoken in Saudi Arabia)
+* ar_SY (Arabic, as spoken in Syrian Arab Republic)
+* as (Assamese)
+* ast (Unknown language)
+* ay (Aymara)
+* az (Azerbaijani)
+* az_IR (Azerbaijani, as spoken in Iran)
+* be (Belarusian)
+* be@latin (Unknown language)
+* be@tarask (Unknown language)
+* bem (Unknown language)
+* bg (Bulgarian)
+* bg_BG (Bulgarian, as spoken in Bulgaria)
+* bi (Bislama)
+* bn (Bengali)
+* bn_BD (Bengali, as spoken in Bangladesh)
+* bn_IN (Bengali, as spoken in India)
+* bo (Tibetan)
+* br (Breton)
+* bs (Bosnian)
+* bs_BA (Bosnian, as spoken in Bosnia and Herzegovina)
+* bs_BS (Bosnian, as spoken in Bahamas)
+* byn (Unknown language)
+* ca (Catalan)
+* ca@valencia (Unknown language)
+* ca_AD (Catalan, as spoken in Andorra)
+* ca_ES (Catalan, as spoken in Spain)
+* ca_ES@valencia (Unknown language)
+* ca_FR (Catalan, as spoken in France)
+* ca_IT (Catalan, as spoken in Italy)
+* co (Corsican)
+* crh (Unknown language)
+* cs (Czech)
+* cs_CZ (Czech, as spoken in Czech Republic)
+* csb (Unknown language)
+* cy (Welsh)
+* cy_GB (Welsh, as spoken in Great Britain)
+* cz (Unknown language)
+* da (Danish)
+* da_DK (Danish, as spoken in Denmark)
+* de (German)
+* de_AT (German, as spoken in Austria)
+* de_CH (German, as spoken in Switzerland)
+* de_DE (German, as spoken in Germany)
+* dk (Unknown language)
+* dz (Dzongkha)
+* el (Greek)
+* el_GR (Greek, as spoken in Greece)
+* en (English)
+* en@boldquot (Unknown language)
+* en@quot (Unknown language)
+* en@shaw (Unknown language)
+* en_AU (English, as spoken in Australia)
+* en_CA (English, as spoken in Canada)
+* en_GB (English, as spoken in Great Britain)
+* en_NZ (English, as spoken in New Zealand)
+* en_US (English, as spoken in United States)
+* en_US@piglatin (Unknown language)
+* en_ZA (English, as spoken in South Africa)
+* eo (Esperanto)
+* es (Spanish)
+* es_AR (Spanish, as spoken in Argentina)
+* es_CL (Spanish, as spoken in Chile)
+* es_CO (Spanish, as spoken in Colombia)
+* es_CR (Spanish, as spoken in Costa Rica)
+* es_DO (Spanish, as spoken in Dominican Republic)
+* es_EC (Spanish, as spoken in Ecuador)
+* es_ES (Spanish, as spoken in Spain)
+* es_GA (Spanish, as spoken in Gabon)
+* es_GT (Spanish, as spoken in Guatemala)
+* es_HN (Spanish, as spoken in Honduras)
+* es_LA (Spanish, as spoken in Lao People''s Democratic Republic)
+* es_MX (Spanish, as spoken in Mexico)
+* es_NI (Spanish, as spoken in Nicaragua)
+* es_PA (Spanish, as spoken in Panama)
+* es_PE (Spanish, as spoken in Peru)
+* es_PR (Spanish, as spoken in Puerto Rico)
+* es_SV (Spanish, as spoken in El Salvador)
+* es_UY (Spanish, as spoken in Uruguay)
+* es_VE (Spanish, as spoken in Venezuela)
+* et (Estonian)
+* et_EE (Estonian, as spoken in Estonia)
+* eu (Basque)
+* eu_ES (Basque, as spoken in Spain)
+* fa (Persian)
+* fa_AF (Persian, as spoken in Afghanistan)
+* fa_IR (Persian, as spoken in Iran)
+* fi (Finnish)
+* fi_FI (Finnish, as spoken in Finland)
+* fil (Unknown language)
+* fo (Faeroese)
+* fo_FO (Faeroese, as spoken in Faroe Islands)
+* fr (French)
+* fr_BE (French, as spoken in Belgium)
+* fr_CA (French, as spoken in Canada)
+* fr_CH (French, as spoken in Switzerland)
+* fr_FR (French, as spoken in France)
+* fr_FX (French, as spoken in France, Metropolitan)
+* fr_LU (French, as spoken in Luxembourg)
+* frp (Unknown language)
+* fur (Unknown language)
+* fy (Frisian)
+* fy_NL (Frisian, as spoken in Netherlands)
+* ga (Irish)
+* gd (Gaelic (Scots))
+* gez (Unknown language)
+* gl (Galician)
+* gl_ES (Galician, as spoken in Spain)
+* gn (Guarani)
+* gu (Gujarati)
+* gv (Manx)
+* ha (Hausa)
+* he (Hebrew)
+* he_IL (Hebrew, as spoken in Israel)
+* hi (Hindi)
+* hne (Unknown language)
+* hr (Croatian)
+* hr_HR (Croatian, as spoken in Croatia)
+* ht (Unknown language)
+* hu (Hungarian)
+* hu_HU (Hungarian, as spoken in Hungary)
+* hy (Armenian)
+* ia (Interlingua)
+* id (Indonesian)
+* id_ID (Indonesian, as spoken in Indonesia)
+* ig (Unknown language)
+* io (Unknown language)
+* is (Icelandic)
+* is_IS (Icelandic, as spoken in Iceland)
+* it (Italian)
+* it_CH (Italian, as spoken in Switzerland)
+* it_IT (Italian, as spoken in Italy)
+* iu (Inuktitut)
+* ja (Japanese)
+* ja_JP (Japanese, as spoken in Japan)
+* jv (Unknown language)
+* jv_ID (Unknown language)
+* ka (Georgian)
+* kab (Unknown language)
+* kk (Kazakh)
+* kl (Kalaallisut)
+* km (Khmer)
+* km_KH (Khmer, as spoken in Cambodia)
+* kn (Kannada)
+* ko (Korean)
+* ko_KR (Korean, as spoken in Korea)
+* ks (Kashmiri)
+* ku (Kurdish)
+* kw (Cornish)
+* ky (Kirghiz)
+* la (Latin)
+* lb (Letzeburgesch)
+* lg (Unknown language)
+* li (Unknown language)
+* ln (Lingala)
+* lo (Lao)
+* lt (Lithuanian)
+* lt_LT (Lithuanian, as spoken in Lithuania)
+* lv (Latvian)
+* lv_LV (Latvian, as spoken in Latvia)
+* mai (Unknown language)
+* mal (Unknown language)
+* mg (Malagasy)
+* mi (Maori)
+* mk (Macedonian)
+* mk_MK (Macedonian, as spoken in Macedonia, the Former Yugoslav Republic of)
+* ml (Malayalam)
+* ml_IN (Malayalam, as spoken in India)
+* ml_ML (Malayalam, as spoken in Mali)
+* mn (Mongolian)
+* mr (Marathi)
+* ms (Malay)
+* ms_MY (Malay, as spoken in Malaysia)
+* mt (Maltese)
+* my (Burmese)
+* my_MM (Burmese, as spoken in Myanmar)
+* na (Nauru)
+* nb (Norwegian Bokmål)
+* nb_NO (Norwegian Bokmål, as spoken in Norway)
+* nds (Unknown language)
+* ne (Nepali)
+* new (Unknown language)
+* nl (Dutch)
+* nl_BE (Dutch, as spoken in Belgium)
+* nl_NL (Dutch, as spoken in Netherlands)
+* nn (Norwegian Nynorsk)
+* nn_NO (Norwegian Nynorsk, as spoken in Norway)
+* no (Norwegian)
+* no_NO (Norwegian, as spoken in Norway)
+* nr (Ndebele, South)
+* nso (Unknown language)
+* oc (Occitan (post 1500))
+* oc_FR (Occitan (post 1500), as spoken in France)
+* om (Oromo)
+* or (Oriya)
+* pa (Panjabi)
+* pl (Polish)
+* pl_PL (Polish, as spoken in Poland)
+* pms (Unknown language)
+* ps (Pushto)
+* pt (Portuguese)
+* pt_BR (Portuguese, as spoken in Brazil)
+* pt_PT (Portuguese, as spoken in Portugal)
+* qu (Quechua)
+* rm (Rhaeto-Romance)
+* ro (Romanian)
+* ro_RO (Romanian, as spoken in Romania)
+* ru (Russian)
+* ru_RU (Russian, as spoken in Russia)
+* rw (Kinyarwanda)
+* sa (Sanskrit)
+* sc (Sardinian)
+* sd (Sindhi)
+* se (Sami)
+* se_NO (Sami, as spoken in Norway)
+* si (Sinhalese)
+* si_LK (Sinhalese, as spoken in Sri Lanka)
+* si_SI (Sinhalese, as spoken in Slovenia)
+* sk (Slovak)
+* sk_SK (Slovak, as spoken in Slovakia)
+* sl (Slovenian)
+* sl_SI (Slovenian, as spoken in Slovenia)
+* sl_SL (Slovenian, as spoken in Sierra Leone)
+* so (Somali)
+* sp (Unknown language)
+* sq (Albanian)
+* sq_AL (Albanian, as spoken in Albania)
+* sr (Serbian)
+* sr@Latn (Unknown language)
+* sr@ije (Unknown language)
+* sr@ijekavian (Unknown language)
+* sr@ijekavianlatin (Unknown language)
+* sr@latin (Unknown language)
+* sr_SR (Serbian, as spoken in Suriname)
+* sr_YU (Serbian, as spoken in Yugoslavia)
+* st (Sotho)
+* su (Sundanese)
+* su_ID (Sundanese, as spoken in Indonesia)
+* sv (Swedish)
+* sv_SE (Swedish, as spoken in Sweden)
+* sw (Swahili)
+* ta (Tamil)
+* ta_LK (Tamil, as spoken in Sri Lanka)
+* te (Telugu)
+* tg (Tajik)
+* th (Thai)
+* th_TH (Thai, as spoken in Thailand)
+* ti (Tigrinya)
+* tig (Unknown language)
+* tk (Turkmen)
+* tl (Tagalog)
+* tlh (Unknown language)
+* to (Tonga)
+* tr (Turkish)
+* tr_TR (Turkish, as spoken in Turkey)
+* tt (Tatar)
+* ug (Uighur)
+* ug_CN (Uighur, as spoken in China)
+* uk (Ukrainian)
+* uk_UA (Ukrainian, as spoken in Ukraine)
+* ur (Urdu)
+* ur_PK (Urdu, as spoken in Pakistan)
+* uz (Uzbek)
+* uz@cyrillic (Unknown language)
+* ve (Unknown language)
+* vi (Vietnamese)
+* vi_AR (Vietnamese, as spoken in Argentina)
+* vi_DE (Vietnamese, as spoken in Germany)
+* vi_PL (Vietnamese, as spoken in Poland)
+* vi_TR (Vietnamese, as spoken in Turkey)
+* vi_VN (Vietnamese, as spoken in Vietnam)
+* wa (Unknown language)
+* wal (Unknown language)
+* wo (Wolof)
+* xh (Xhosa)
+* yi (Yiddish)
+* yo (Yoruba)
+* zh (Chinese)
+* zh_CN (Chinese, as spoken in China)
+* zh_HK (Chinese, as spoken in Hong Kong)
+* zh_TW (Chinese, as spoken in Taiwan)
+* zu (Zulu)
+
+ 'sq';    'albanian'
+ 'am';    'amharic'
+#'ar';    'arabic'         # see polyglossia
+ 'hy';    'armenian'
+#'';      'asturian'       # polyglossia
+#'';      'bahasai'        # polyglossia
+#'';      'bahasam'        # polyglossia
+ 'eu';    'basque'
+ 'bn';    'bengali'
+ 'pt_BR'; 'brazilian'
+ 'br';    'breton'
+ 'bg';    'bulgarian'
+ 'ca';    'catalan'        # see polyglossia
+#'';      'coptic'         # polyglossia
+ 'hr';    'croatian'
+ 'cs';    'czech'
+ 'da';    'danish'
+#'';      'divehi'         # polyglossia
+ 'nl';    'dutch'          # see polyglossia
+ 'en';    'english'        # see polyglossia
+ 'eo';    'esperanto'      # see polyglossia
+ 'et';    'estonian'
+ 'gl';    'galician'
+ 'de';    'german'
+ 'el';    'greek'          #gl ?
+ 'he';    'hebrew'
+ 'hi';    'hindi'
+ 'is';    'icelandic'
+ 'ia';    'interlingua'
+ 'ga';    'irish'
+ 'it';    'italian'
+#'';      'farsi'          # polyglossia
+ 'fi';    'finnish'
+ 'fr';    'french'
+ 'lo';    'lao'
+ 'la';    'latin'
+ 'lv';    'latvian'
+ 'lt';    'lithuanian'
+#'';      'lsorbian'       # polyglossia
+#'';      'magyar'         # polyglossia
+ 'ml';    'malayalam'
+ 'mr';    'marathi'
+#'hu';    'magyar'
+ 'no';    'norske'
+ 'nn';    'nynorsk'
+ 'oc';    'occitan'
+ 'pl';    'polish'
+ 'pt';    'portuges'
+ 'ro';    'romanian'
+ 'ru';    'russian'
+ 'se';    'samin'          #(check sami?)
+ 'sa';    'sanskrit'
+ 'sr';    'serbian'
+#'';      'scottish'       # polyglossia  (gd (Gaelic (Scots)))
+ 'sk';    'slovak'
+ 'sl';    'slovenian'
+ 'es';    'spanish'
+ 'sv';    'swedish'
+ 'ta';    'tamil'
+ 'te';    'telugu'
+ 'th';    'thai'
+ 'tr';    'turkish'
+ 'tk';    'turkmen'
+ 'uk';    'ukrainian'
+ 'ur';    'urdu'
+#'';      'usorbian'       # polyglossia
+ 'vi';    'vietnamese'
+ 'cy';    'welsh'
+ 'us';    'USenglish'      # depreciated, see iso-639-2