perl-install

package lang; # $Id$

use diagnostics;
use strict;
use common;
use log;

#- key: lang name (locale name for some (~5) special cases needing
#-      extra distinctions)
#- [0]: lang name in english
#- [1]: transliterated locale name in the locale name (used for sorting)
#- [2]: default locale name to use for that language if there isn't
#-      an existing locale for the combination language+country choosen
#- [3]: geographic groups that this language belongs to (for displaying
#-      in the menu grouped in smaller lists), 1=Europe, 2=Asia, 3=Africa,
#-      4=Oceania&Pacific, 5=America (if you wonder, it's the order
#-      used in the olympic flag)
#- [4]: special value for LANGUAGE variable (if different of the default
#-      of 'll_CC:ll_DD:ll' (ll_CC: locale (if exist) resulting of the
#-      combination of chosen lang (ll) and country (CC), ll_DD: the
#-      default locale shown here (field [2]) and ll: the language (the key))
our %langs = (
'af' =>    [ 'Afrikaans',           'Afrikaans',         'af_ZA', '  3  ', 'iso-8859-1' ],
'am' =>    [ 'Amharic',             'ZZ emarNa',         'am_ET', '  3  ', 'utf_am' ],
'ar' =>    [ 'Arabic',              'AA Arabic',         'ar_EG', ' 23  ', 'utf_ar' ],
'as' =>    [ 'Assamese',            'ZZ Assamese',       'as_IN', ' 2   ', 'utf_bn' ],
'az' =>    [ 'Azeri (Latin)',       'Azerbaycanca',      'az_AZ', ' 2   ', 'utf_az' ],
'be' =>    [ 'Belarussian',         'Belaruskaya',       'be_BY', '1    ', 'cp1251' ],
'bg' =>    [ 'Bulgarian',           'Blgarski',          'bg_BG', '1    ', 'cp1251' ],
'bn' =>    [ 'Bengali',             'ZZ Bengali',        'bn_BD', ' 2   ', 'utf_bn' ],
'br' =>    [ 'Britton',             'Brezhoneg',         'br_FR', '1    ', 'iso-8859-15', 'br:fr_FR:fr' ],
'bs' =>    [ 'Bosnian',             'Bosanski',          'bs_BA', '1    ', 'iso-8859-2' ],
'ca' =>    [ 'Catalan',             'Catala',            'ca_ES', '1    ', 'iso-8859-15', 'ca:es_ES:es' ],
'cs' =>    [ 'Czech',               'Cestina',           'cs_CZ', '1    ', 'iso-8859-2' ],
'cy' =>    [ 'Welsh',               'Cymraeg',           'cy_GB', '1    ', 'utf_lat8',    'cy:en_GB:en' ],
'da' =>    [ 'Danish',              'Dansk',             'da_DK', '1    ', 'iso-8859-15' ],
'de' =>    [ 'German',              'Deutsch',           'de_DE', '1    ', 'iso-8859-15' ],
#-'dz' =>  [ 'Buthanese',           'ZZ Dzhonka',        'dz_BT', ' 2   ', 'unicode' ],
'el' =>    [ 'Greek',               'Ellynika',          'el_GR', '1    ', 'iso-8859-7' ],
'en_GB' => [ 'English',             'English',           'en_GB', '12345', 'iso-8859-15' ],
'en_US' => [ 'English (American)', 'English (American)', 'en_US', '    5', 'C' ],
'en_IE' => [ 'English (Ireland)',   'English (Ireland)', 'en_IE', '1    ', 'iso-8859-15', 'en_IE:en_GB:en' ],
'eo' =>    [ 'Esperanto',           'Esperanto',         'eo_XX', '12345', 'unicode' ],
'es' =>    [ 'Spanish',             'Espanol',           'es_ES', '1 3 5', 'iso-8859-15' ],
'et' =>    [ 'Estonian',            'Eesti',             'et_EE', '1    ', 'iso-8859-15' ],
'eu' =>    [ 'Euskara (Basque)',    'Euskara',           'eu_ES', '1    ', 'iso-8859-15' ],
'fa' =>    [ 'Farsi (Iranian)',     'AA Farsi',          'fa_IR', ' 2   ', 'utf_ar' ],
'fi' =>    [ 'Finnish (Suomi)',     'Suomi',             'fi_FI', '1    ', 'iso-8859-15' ],
'fo' =>    [ 'Faroese',             'Foroyskt',          'fo_FO', '1    ', 'iso-8859-1' ],
'fr' =>    [ 'French',              'Francais',          'fr_FR', '1 345', 'iso-8859-15' ],
'ga' =>    [ 'Gaelic (Irish)',      'Gaeilge',           'ga_IE', '1    ', 'iso-8859-15', 'ga:en_IE:en_GB:en' ],
#'gd' =>   [ 'Gaelic (Scottish)',   'Gaidhlig',          'gd_GB', '1    ', 'utf_lat8',    'gd:en_GB:en' ],
'gl' =>    [ 'Galician',            'Galego',            'gl_ES', '1    ', 'iso-8859-15', 'gl:es_ES:es:pt:pt_BR' ],
#'gn' =>   [ 'Guarani',             'Avane-e',           'gn_PY', '    5', 'utf8',    'gn:es_PY:es' ],
'gu' =>    [ 'Gujarati',            'ZZ Gujarati',       'gu_IN', ' 2   ', 'unicode' ],
#'gv' =>   [ 'Gaelic (Manx)',       'Gaelg',             'gv_GB', '1    ', 'utf_lat8',    'gv:en_GB:en' ],
'he' =>    [ 'Hebrew',              'AA Ivrit',          'he_IL', ' 2   ', 'utf_he' ],
'hi' =>    [ 'Hindi',               'ZZ Hindi',          'hi_IN', ' 2   ', 'unicode' ],
'hr' =>    [ 'Croatian',            'Hrvatski',          'hr_HR', '1    ', 'iso-8859-2' ],
'hu' =>    [ 'Hungarian',           'Magyar',            'hu_HU', '1    ', 'iso-8859-2' ],
'hy' =>    [ 'Armenian',            'ZZ Armenian',       'hy_AM', ' 2   ', 'utf_hy' ],
# locale not done yet
#'ia' =>   [ 'Interlingua',         'Interlingua',       'ia_XX', '1   5', 'utf8' ],
'id' =>    [ 'Indonesian',          'Bahasa Indonesia',  'id_ID', ' 2   ', 'iso-8859-1' ],
'is' =>    [ 'Icelandic',           'Islenska',          'is_IS', '1    ', 'iso-8859-1' ],
'it' =>    [ 'Italian',             'Italiano',          'it_IT', '1    ', 'iso-8859-15' ],
#-'iu' =>  [ 'Inuktitut',           'ZZ Inuktitut',      'iu_CA', '    5', 'utf_iu' ],
'ja' =>    [ 'Japanese',            'ZZ Nihongo',        'ja_JP', ' 2   ', 'jisx0208' ],
'ka' =>    [ 'Georgian',            'ZZ Georgian',       'ka_GE', ' 2   ', 'utf_ka' ],
#-'kl' =>  [ 'Greenlandic (inuit)', 'ZZ Inuit',          'kl_GL', '    5', 'iso-8859-1' ],
'kn' =>    [ 'Kannada',             'ZZ Kannada',        'kn_IN', ' 2   ', 'utf_kn' ],
'ko' =>    [ 'Korean',              'ZZ Korea',          'ko_KR', ' 2   ', 'ksc5601' ],
'ku' =>    [ 'Kurdish',             'Kurdi',             'ku_TR', ' 2   ', 'iso-8859-9' ],
#-'kw' =>  [ 'Cornish',             'Kernewek',          'kw_GB', '1    ', 'utf_lat8',    'kw:en_GB:en' ],
'ky' =>    [ 'Kyrgyz',              'Kyrgyz',            'ky_KG', ' 2   ', 'utf_cyr2' ],
'li' =>    [ 'Limbourgish',         'Limburgs',          'li_NL', '1    ', 'iso-8859-15' ],
'lo' =>    [ 'Laotian',             'Laotian',           'lo_LA', ' 2   ', 'utf_lo' ],
'lt' =>    [ 'Lithuanian',          'Lietuviskai',       'lt_LT', '1    ', 'iso-8859-13' ],
'lv' =>    [ 'Latvian',             'Latviesu',          'lv_LV', '1    ', 'iso-8859-13' ],
'mi' =>    [ 'Maori',               'Maori',             'mi_NZ', '   4 ', 'unicode' ],
'mk' =>    [ 'Macedonian',          'Makedonski',        'mk_MK', '1    ', 'utf_cyr1' ],
'ml' =>    [ 'Malayalam',           'ZZ Malayalam',      'ml_IN', ' 2   ', 'unicode' ],
'mn' =>    [ 'Mongolian',           'Mongol',            'mn_MN', ' 2   ', 'utf_cyr2' ],
'mr' =>    [ 'Marathi',             'ZZ Marathi',        'mr_IN', ' 2   ', 'unicode' ],
'ms' =>    [ 'Malay',               'Bahasa Melayu',     'ms_MY', ' 2   ', 'iso-8859-1' ],
'mt' =>    [ 'Maltese',             'Maltin',            'mt_MT', '1 3  ', 'unicode' ],
'nb' =>    [ 'Norwegian Bokmaal',   'Norsk, Bokmal',     'nb_NO', '1    ', 'iso-8859-1',  'nb:no' ],
'nds' =>   [ 'Low Saxon',           'Platduutsch',      'nds_DE', '1    ', 'iso-8859-1', 'nds_DE:nds' ],
'ne' =>    [ 'Nepali',              'ZZ Nepali',         'ne_NP', ' 2   ', 'unicode' ],
'nl' =>    [ 'Dutch',               'Nederlands',        'nl_NL', '1    ', 'iso-8859-15' ],
'nn' =>    [ 'Norwegian Nynorsk',   'Norsk, Nynorsk',    'nn_NO', '1    ', 'iso-8859-1',  'nn:no@nynorsk:no_NY:no:nb' ],
'oc' =>    [ 'Occitan',             'Occitan',           'oc_FR', '1    ', 'iso-8859-1',  'oc:fr_FR:fr' ],
# 'tl' in priority position for now, as 'ph' is not yet official and 'tl'
# is used instead. Monolingual window managers won't see the menus otherwise
'ph' =>    [ 'Filipino',            'Filipino',          'ph_PH', ' 2   ', 'iso-8859-1',  'tl:ph' ],
'pl' =>    [ 'Polish',              'Polski',            'pl_PL', '1    ', 'iso-8859-2' ],
'pt' =>    [ 'Portuguese',          'Portugues',         'pt_PT', '1 3  ', 'iso-8859-15', 'pt_PT:pt:pt_BR' ],
'pt_BR' => [ 'Portuguese Brazil', 'Portugues do Brasil', 'pt_BR', '    5', 'iso-8859-1',  'pt_BR:pt_PT:pt' ],
'ro' =>    [ 'Romanian',            'Romana',            'ro_RO', '1    ', 'iso-8859-2' ],
'ru' =>    [ 'Russian',             'Russkij',           'ru_RU', '12   ', 'koi8-u' ],
'se' =>    [ 'Saami',               'Samegiella',        'se_NO', '1    ', 'unicode' ], 
'sk' =>    [ 'Slovak',              'Slovencina',        'sk_SK', '1    ', 'iso-8859-2' ],
'sl' =>    [ 'Slovenian',           'Slovenscina',       'sl_SI', '1    ', 'iso-8859-2' ],
'sq' =>    [ 'Albanian',            'Shqip',             'sq_AL', '1    ', 'iso-8859-1' ], 
'sr' =>    [ 'Serbian Cyrillic',    'Srpska',            'sr_CS', '1    ', 'utf_cyr1', 'sp:sr' ],
'sr@Latn' => [ 'Serbian Latin',     'Srpska',            'sr_CS', '1    ', 'unicode',  'sh:sr@Latn' ], 
#- ss_ZA not yet done, using en_ZA locale instead
'ss' =>    [ 'Swati',               'SiSwati',           'en_ZA', '  3  ', 'iso-8859-1', 'ss:en_ZA' ],
'st' =>    [ 'Sotho',               'Sesotho',           'st_ZA', '  3  ', 'iso-8859-1', 'st:nso:en_ZA' ],
'sv' =>    [ 'Swedish',             'Svenska',           'sv_SE', '1    ', 'iso-8859-1' ],
'ta' =>    [ 'Tamil',               'ZZ Tamil',          'ta_IN', ' 2   ', 'utf_ta' ],
'te' =>    [ 'Telugu',              'ZZ Telugu',         'te_IN', ' 2   ', 'unicode' ],
'tg' =>    [ 'Tajik',               'Tojiki',            'tg_TJ', ' 2   ', 'utf_cyr2' ],
'th' =>    [ 'Thai',                'ZZ Thai',           'th_TH', ' 2   ', 'tis620' ],
#-'tk' =>  [ 'Turkmen',             'Turkmence',         'tk_TM', ' 2   ', 'utf8' ],
'tr' =>    [ 'Turkish',             'Turkce',            'tr_TR', ' 2   ', 'iso-8859-9' ],
#-'tt' =>  [ 'Tatar',               'Tatarca',           'tt_RU', ' 2   ', 'utf8' ],
'uk' =>    [ 'Ukrainian',           'Ukrayinska',        'uk_UA', '1    ', 'koi8-u' ],
#-'ur' =>  [ 'Urdu',                'AA Urdu',           'ur_PK', ' 2   ', 'utf_ar' ],  
'uz@Latn' => [ 'Uzbek (latin)',     'Ozbekcha',          'uz_UZ', ' 2   ', 'utf_cyr2', 'uz@Latn:uz' ],
'uz' =>    [ 'Uzbek (cyrillic)',    'Ozbekcha',          'uz_UZ', ' 2   ', 'utf_cyr2', 'uz@Cyrl:uz' ],
#- ve_ZA not yet done, using en_ZA locale instead
've' =>    [ 'Venda',               'Venda',             'en_ZA', '  3  ', 'iso-8859-1', 've:ven:en_ZA' ],
'vi' =>    [ 'Vietnamese',          'Tieng Viet',        'vi_VN', ' 2   ', 'utf_vi' ],
'wa' =>    [ 'Walon',               'Walon',             'wa_BE', '1    ', 'iso-8859-15', 'wa:fr_BE:fr' ],
#- locale not done yet
#'wen' =>   [ 'Sorbian',             'XX Sorbian',       'wen_XX', '1    ', 'iso-8859-1' ],
'xh' =>    [ 'Xhosa',               'IsiXhosa',          'xh_ZA', '  3  ', 'iso-8859-1', 'xh:en_ZA' ],
'yi' =>    [ 'Yiddish',             'AA Yidish',         'yi_US', '1   5', 'utf_he' ],
'zh_CN' => [ 'Chinese Simplified',  'ZZ ZhongWen',       'zh_CN', ' 2   ', 'gb2312',      'zh_CN.GB2312:zh_CN:zh' ],
'zh_TW' => [ 'Chinese Traditional', 'ZZ ZhongWen',       'zh_TW', ' 2   ', 'Big5',        'zh_TW.Big5:zh_TW:zh_HK:zh' ],
'zu' =>    [ 'Zulu',                 'IsiZulu',          'zu_ZA', '  3  ', 'iso-8859-1', 'xh:en_ZA' ],
);
sub l2name           { exists $langs{$_[0]} && $langs{$_[0]}[0] }
sub l2transliterated { exists $langs{$_[0]} && $langs{$_[0]}[1] }
sub l2locale         { exists $langs{$_[0]} && $langs{$_[0]}[2] }
sub l2location {
    my %geo = (1 => 'Europe', 2 => 'Asia', 3 => 'Africa', 4 => 'Oceania/Pacific', 5 => 'America');
    map { if_($langs{$_[0]}[3] =~ $_, $geo{$_}) } 1..5;
}
sub l2charset        { exists $langs{$_[0]} && $langs{$_[0]}[4] }
sub l2language       { exists $langs{$_[0]} && $langs{$_[0]}[5] }
sub list_langs {
    my (%options) = @_;
    my @l = keys %langs;
    $options{exclude_non_installed} ? grep { -e "/usr/share/locale/".l2locale($_)."/LC_CTYPE" } @l : @l;
}

sub text_direction_rtl() { N("default:LTR") eq "default:RTL" }


#- key: country name (that should be YY in xx_YY locale)
#- [0]: country name in natural language
#- [1]: default locale for that country 
#- [2]: geographic groups that this country belongs to (for displaying
#-      in the menu grouped in smaller lists), 1=Europe, 2=Asia, 3=Africa,
#-      4=Oceania&Pacific, 5=America (if you wonder, it's the order
#-      used in the olympic flag)
#-
#- Note: for countries for which a glibc locale don't exist (yet) I tried to
#- put a locale that makes sense; and a '#' at the end of the line to show
#- the locale is not the "correct" one. 'en_US' is used when no good choice
#- is available.
my %countries = (
'AF' => [ N_("Afghanistan"),    'en_US', '2' ], #
'AD' => [ N_("Andorra"),        'ca_ES', '1' ], #
'AE' => [ N_("United Arab Emirates"), 'ar_AE', '2' ],
'AG' => [ N_("Antigua and Barbuda"), 'en_US', '5' ], #
'AI' => [ N_("Anguilla"),       'en_US', '5' ], #
'AL' => [ N_("Albania"),        'sq_AL', '1' ],
'AM' => [ N_("Armenia"),        'hy_AM', '2' ],
'AN' => [ N_("Netherlands Antilles"), 'en_US', '5' ], #
'AO' => [ N_("Angola"),         'pt_PT', '3' ], #
'AQ' => [ N_("Antarctica"),     'en_US', '4' ], #
'AR' => [ N_("Argentina"),      'es_AR', '5' ],
'AS' => [ N_("American Samoa"), 'en_US', '4' ], #
'AT' => [ N_("Austria"),        'de_AT', '1' ],
'AU' => [ N_("Australia"),      'en_AU', '4' ],
'AW' => [ N_("Aruba"),          'en_US', '5' ], #
'AZ' => [ N_("Azerbaijan"),     'az_AZ', '1' ],
'BA' => [ N_("Bosnia and Herzegovina"), 'bs_BA', '1' ],
'BB' => [ N_("Barbados"),       'en_US', '5' ], #
'BD' => [ N_("Bangladesh"),     'bn_BD', '2' ],
'BE' => [ N_("Belgium"),        'fr_BE', '1' ],
'BF' => [ N_("Burkina Faso"),   'en_US', '3' ], #
'BG' => [ N_("Bulgaria"),       'bg_BG', '1' ],
'BH' => [ N_("Bahrain"),        'ar_BH', '2' ],
'BI' => [ N_("Burundi"),        'en_US', '3' ], #
'BJ' => [ N_("Benin"),          'fr_FR', '3' ], #
'BM' => [ N_("Bermuda"),        'en_US', '5' ], #
'BN' => [ N_("Brunei Darussalam"), 'ar_EG', '2' ], #
'BO' => [ N_("Bolivia"),        'es_BO', '5' ],
'BR' => [ N_("Brazil"),         'pt_BR', '5' ],
'BS' => [ N_("Bahamas"),        'en_US', '5' ], #
'BT' => [ N_("Bhutan"),         'en_IN', '2' ], #
'BV' => [ N_("Bouvet Island"),  'en_US', '3' ], #
'BW' => [ N_("Botswana"),       'en_BW', '3' ],
'BY' => [ N_("Belarus"),        'be_BY', '1' ],
'BZ' => [ N_("Belize"),         'en_US', '5' ], #
'CA' => [ N_("Canada"),         'en_CA', '5' ],
'CC' => [ N_("Cocos (Keeling) Islands"), 'en_US', '4' ], #
'CD' => [ N_("Congo (Kinshasa)"), 'fr_FR', '3' ], #
'CF' => [ N_("Central African Republic"), 'fr_FR', '3' ], #
'CG' => [ N_("Congo (Brazzaville)"), 'fr_FR', '3' ], #
'CH' => [ N_("Switzerland"),    'de_CH', '1' ],
'CI' => [ N_("Cote d'Ivoire"),  'fr_FR', '3' ], #
'CK' => [ N_("Cook Islands"),   'en_US', '4' ], #
'CL' => [ N_("Chile"),          'es_CL', '5' ],
'CM' => [ N_("Cameroon"),       'fr_FR', '3' ], #
'CN' => [ N_("China"),          'zh_CN', '2' ],
'CO' => [ N_("Colombia"),       'es_CO', '5' ],
'CR' => [ N_("Costa Rica"),     'es_CR', '5' ],
'CU' => [ N_("Cuba"),           'es_DO', '5' ], #
'CV' => [ N_("Cape Verde"),     'pt_PT', '3' ], #
'CX' => [ N_("Christmas Island"), 'en_US', '4' ], #
'CY' => [ N_("Cyprus"),         'en_US', '1' ], #
'CZ' => [ N_("Czech Republic"), 'cs_CZ', '2' ],
'DE' => [ N_("Germany"),        'de_DE', '1' ],
'DJ' => [ N_("Djibouti"),       'en_US', '3' ], #
'DK' => [ N_("Denmark"),        'da_DK', '1' ],
'DM' => [ N_("Dominica"),       'en_US', '5' ], #
'DO' => [ N_("Dominican Republic"), 'es_DO', '5' ],
'DZ' => [ N_("Algeria"),        'ar_DZ', '3' ],
'EC' => [ N_("Ecuador"),        'es_EC', '5' ],
'EE' => [ N_("Estonia"),        'et_EE', '1' ],
'EG' => [ N_("Egypt"),          'ar_EG', '3' ],
'EH' => [ N_("Western Sahara"), 'ar_MA', '3' ], #
'ER' => [ N_("Eritrea"),        'ti_ER', '3' ],
'ES' => [ N_("Spain"),          'es_ES', '1' ],
'ET' => [ N_("Ethiopia"),       'am_ET', '3' ],
'FI' => [ N_("Finland"),        'fi_FI', '1' ],
'FJ' => [ N_("Fiji"),           'en_US', '4' ], #
'FK' => [ N_("Falkland Islands (Malvinas)"), 'en_GB', '5' ], #
'FM' => [ N_("Micronesia"),     'en_US', '4' ], #
'FO' => [ N_("Faroe Islands"),  'fo_FO', '1' ],
'FR' => [ N_("France"),         'fr_FR', '1' ],
'GA' => [ N_("Gabon"),          'fr_FR', '3' ], #
'GB' => [ N_("United Kingdom"), 'en_GB', '1' ],
'GD' => [ N_("Grenada"),        'en_US', '5' ], #
'GE' => [ N_("Georgia"),        'ka_GE', '2' ],
'GF' => [ N_("French Guiana"),  'fr_FR', '5' ], #
'GH' => [ N_("Ghana"),          'en_GB', '3' ], #
'GI' => [ N_("Gibraltar"),      'en_GB', '1' ], #
'GL' => [ N_("Greenland"),      'kl_GL', '5' ],
'GM' => [ N_("Gambia"),         'en_US', '3' ], #
'GN' => [ N_("Guinea"),         'en_US', '3' ], #
'GP' => [ N_("Guadeloupe"),     'fr_FR', '5' ], #
'GQ' => [ N_("Equatorial Guinea"), 'en_US', '3' ], #
'GR' => [ N_("Greece"),         'el_GR', '1' ],
'GS' => [ N_("South Georgia and the South Sandwich Islands"), 'en_US', '4' ], #
'GT' => [ N_("Guatemala"),      'es_GT', '5' ],
'GU' => [ N_("Guam"),           'en_US', '4' ], #
'GW' => [ N_("Guinea-Bissau"),  'pt_PT', '3' ], #
'GY' => [ N_("Guyana"),         'en_US', '5' ], #
'HK' => [ N_("China (Hong Kong)"),      'zh_HK', '2' ],
'HM' => [ N_("Heard and McDonald Islands"), 'en_US', '4' ], #
'HN' => [ N_("Honduras"),       'es_HN', '5' ],
'HR' => [ N_("Croatia"),        'hr_HR', '1' ],
'HT' => [ N_("Haiti"),          'fr_FR', '5' ], #
'HU' => [ N_("Hungary"),        'hu_HU', '1' ],
'ID' => [ N_("Indonesia"),      'id_ID', '2' ],
'IE' => [ N_("Ireland"),        'en_IE', '1' ],
'IL' => [ N_("Israel"),         'he_IL', '2' ],
'IN' => [ N_("India"),          'hi_IN', '2' ],
'IO' => [ N_("British Indian Ocean Territory"), 'en_GB', '2' ], #
'IQ' => [ N_("Iraq"),           'ar_IQ', '2' ],
'IR' => [ N_("Iran"),           'fa_IR', '2' ],
'IS' => [ N_("Iceland"),        'is_IS', '1' ],
'IT' => [ N_("Italy"),          'it_IT', '1' ],
'JM' => [ N_("Jamaica"),        'en_US', '5' ], #
'JO' => [ N_("Jordan"),         'ar_JO', '2' ],
'JP' => [ N_("Japan"),          'ja_JP', '2' ],
'KE' => [ N_("Kenya"),          'en_ZW', '3' ], #
'KG' => [ N_("Kyrgyzstan"),     'ky_KG', '2' ], #
'KH' => [ N_("Cambodia"),       'en_US', '2' ], # km_KH not released yet
'KI' => [ N_("Kiribati"),       'en_US', '3' ], #
'KM' => [ N_("Comoros"),        'en_US', '2' ], #
'KN' => [ N_("Saint Kitts and Nevis"), 'en_US', '5' ], #
'KP' => [ N_("Korea (North)"),  'ko_KR', '2' ], #
'KR' => [ N_("Korea"),          'ko_KR', '2' ],
'KW' => [ N_("Kuwait"),         'ar_KW', '2' ],
'KY' => [ N_("Cayman Islands"), 'en_US', '5' ], #
'KZ' => [ N_("Kazakhstan"),     'ru_RU', '2' ], #
'LA' => [ N_("Laos"),           'lo_LA', '2' ],
'LB' => [ N_("Lebanon"),        'ar_LB', '2' ],
'LC' => [ N_("Saint Lucia"),    'en_US', '5' ], #
'LI' => [ N_("Liechtenstein"),  'de_CH', '1' ], #
'LK' => [ N_("Sri Lanka"),      'en_IN', '2' ], #
'LR' => [ N_("Liberia"),        'en_US', '3' ], #
'LS' => [ N_("Lesotho"),        'en_BW', '3' ], #
'LT' => [ N_("Lithuania"),      'lt_LT', '1' ],
'LU' => [ N_("Luxembourg"),     'de_LU', '1' ],
'LV' => [ N_("Latvia"),         'lv_LV', '1' ],
'LY' => [ N_("Libya"),          'ar_LY', '3' ],
'MA' => [ N_("Morocco"),        'ar_MA', '3' ],
'MC' => [ N_("Monaco"),         'fr_FR', '1' ], #
'MD' => [ N_("Moldova"),        'ro_RO', '1' ], #
'MG' => [ N_("Madagascar"),     'fr_FR', '3' ], #
'MH' => [ N_("Marshall Islands"), 'en_US', '4' ], #
'MK' => [ N_("Macedonia"),      'mk_MK', '1' ],
'ML' => [ N_("Mali"),           'en_US', '3' ], #
'MM' => [ N_("Myanmar"),        'en_US', '2' ], #
'MN' => [ N_("Mongolia"),       'mn_MN', '2' ],
'MP' => [ N_("Northern Mariana Islands"), 'en_US', '2' ], #
'MQ' => [ N_("Martinique"),     'fr_FR', '5' ], #
'MR' => [ N_("Mauritania"),     'en_US', '3' ], #
'MS' => [ N_("Montserrat"),     'en_US', '5' ], #
'MT' => [ N_("Malta"),          'mt_MT', '1' ],
'MU' => [ N_("Mauritius"),      'en_US', '3' ], #
'MV' => [ N_("Maldives"),       'en_US', '4' ], #
'MW' => [ N_("Malawi"),         'en_US', '3' ], #
'MX' => [ N_("Mexico"),         'es_MX', '5' ],
'MY' => [ N_("Malaysia"),       'ms_MY', '2' ],
'MZ' => [ N_("Mozambique"),     'pt_PT', '3' ], #
'NA' => [ N_("Namibia"),        'en_US', '3' ], #
'NC' => [ N_("New Caledonia"),  'fr_FR', '4' ], #
'NE' => [ N_("Niger"),          'en_US', '3' ], #
'NF' => [ N_("Norfolk Island"), 'en_GB', '4' ], #
'NG' => [ N_("Nigeria"),        'en_US', '3' ], #
'NI' => [ N_("Nicaragua"),      'es_NI', '5' ],
'NL' => [ N_("Netherlands"),    'nl_NL', '1' ],
'NO' => [ N_("Norway"),         'nb_NO', '1' ],
'NP' => [ N_("Nepal"),          'ne_NP', '2' ],
'NR' => [ N_("Nauru"),          'en_US', '4' ], #
'NU' => [ N_("Niue"),           'en_US', '4' ], #
'NZ' => [ N_("New Zealand"),    'en_NZ', '4' ],
'OM' => [ N_("Oman"),           'ar_OM', '2' ],
'PA' => [ N_("Panama"),         'es_PA', '5' ],
'PE' => [ N_("Peru"),           'es_PE', '5' ],
'PF' => [ N_("French Polynesia"), 'fr_FR', '4' ], #
'PG' => [ N_("Papua New Guinea"), 'en_NZ', '4' ], #
'PH' => [ N_("Philippines"),    'ph_PH', '2' ],
'PK' => [ N_("Pakistan"),       'ur_PK', '2' ],
'PL' => [ N_("Poland"),         'pl_PL', '1' ],
'PM' => [ N_("Saint Pierre and Miquelon"), 'fr_CA', '5' ], #
'PN' => [ N_("Pitcairn"),      'en_US', '4' ], #
'PR' => [ N_("Puerto Rico"),    'es_PR', '5' ],
'PS' => [ N_("Palestine"),      'ar_JO', '2' ], #
'PT' => [ N_("Portugal"),       'pt_PT', '1' ],
'PY' => [ N_("Paraguay"),       'es_PY', '5' ],
'PW' => [ N_("Palau"),          'en_US', '2' ], #
'QA' => [ N_("Qatar"),          'ar_QA', '2' ],
'RE' => [ N_("Reunion"),        'fr_FR', '2' ], #
'RO' => [ N_("Romania"),        'ro_RO', '1' ],
'RU' => [ N_("Russia"),         'ru_RU', '1' ],
'RW' => [ N_("Rwanda"),         'fr_FR', '3' ], #
'SA' => [ N_("Saudi Arabia"),   'ar_SA', '2' ],
'SB' => [ N_("Solomon Islands"), 'en_US', '4' ], #
'SC' => [ N_("Seychelles"),     'en_US', '4' ], #
'SD' => [ N_("Sudan"),          'ar_SD', '5' ],
'SE' => [ N_("Sweden"),         'sv_SE', '1' ],
'SG' => [ N_("Singapore"),      'en_SG', '2' ],
'SH' => [ N_("Saint Helena"),   'en_GB', '5' ], #
'SI' => [ N_("Slovenia"),       'sl_SI', '1' ],
'SJ' => [ N_("Svalbard and Jan Mayen Islands"), 'en_US', '1' ], #
'SK' => [ N_("Slovakia"),       'sk_SK', '1' ],
'SL' => [ N_("Sierra Leone"),   'en_US', '3' ], #
'SM' => [ N_("San Marino"),     'it_IT', '1' ], #
'SN' => [ N_("Senegal"),        'fr_FR', '3' ], #
'SO' => [ N_("Somalia"),        'en_US', '3' ], # so_SO
'SR' => [ N_("Suriname"),       'nl_NL', '5' ], #
'ST' => [ N_("Sao Tome and Principe"), 'en_US', '5' ], #
'SV' => [ N_("El Salvador"),    'es_SV', '5' ],
'SY' => [ N_("Syria"),          'ar_SY', '2' ],
'SZ' => [ N_("Swaziland"),      'en_BW', '3' ], #
'TC' => [ N_("Turks and Caicos Islands"), 'en_US', '5' ], #
'TD' => [ N_("Chad"),           'en_US', '3' ], #
'TF' => [ N_("French Southern Territories"), 'fr_FR', '4' ], #
'TG' => [ N_("Togo"),           'fr_FR', '3' ], #
'TH' => [ N_("Thailand"),       'th_TH', '2' ],
'TJ' => [ N_("Tajikistan"),     'tg_TJ', '2' ],
'TK' => [ N_("Tokelau"),        'en_US', '4' ], #
'TL' => [ N_("East Timor"),     'pt_PT', '4' ], #
'TM' => [ N_("Turkmenistan"),   'en_US', '2' ], #
'TN' => [ N_("Tunisia"),        'ar_TN', '5' ],
'TO' => [ N_("Tonga"),          'en_US', '3' ], #
'TR' => [ N_("Turkey"),         'tr_TR', '2' ],
'TT' => [ N_("Trinidad and Tobago"), 'en_US', '5' ], #
'TV' => [ N_("Tuvalu"),         'en_US', '4' ], #
'TW' => [ N_("Taiwan"),         'zh_TW', '2' ],
'TZ' => [ N_("Tanzania"),       'en_US', '3' ], #
'UA' => [ N_("Ukraine"),        'uk_UA', '1' ],
'UG' => [ N_("Uganda"),         'en_US', '3' ], # lug_UG
'UM' => [ N_("United States Minor Outlying Islands"), 'en_US', '5' ], #
'US' => [ N_("United States"),  'en_US', '5' ],
'UY' => [ N_("Uruguay"),        'es_UY', '5' ],
'UZ' => [ N_("Uzbekistan"),     'uz_UZ', '2' ],
'VA' => [ N_("Vatican"),        'it_IT', '1' ], #
'VC' => [ N_("Saint Vincent and the Grenadines"), 'en_US', '5' ], 
'VE' => [ N_("Venezuela"),      'es_VE', '5' ],
'VG' => [ N_("Virgin Islands (British)"), 'en_GB', '5' ], #
'VI' => [ N_("Virgin Islands (U.S.)"), 'en_US', '5' ], #
'VN' => [ N_("Vietnam"),        'vi_VN', '2' ],
'VU' => [ N_("Vanuatu"),        'en_US', '4' ], #
'WF' => [ N_("Wallis and Futuna"), 'fr_FR', '4' ], #
'WS' => [ N_("Samoa"),          'en_US', '4' ], #
'YE' => [ N_("Yemen"),          'ar_YE', '2' ],
'YT' => [ N_("Mayotte"),        'fr_FR', '3' ], #
'CS' => [ N_("Serbia & Montenegro"), 'sr_CS', '1' ],
'ZA' => [ N_("South Africa"),   'en_ZA', '5' ],
'ZM' => [ N_("Zambia"),         'en_US', '3' ], #
'ZW' => [ N_("Zimbabwe"),       'en_ZW', '5' ],
);
sub c2name   { exists $countries{$_[0]} && translate($countries{$_[0]}[0]) }
sub c2locale { exists $countries{$_[0]} && $countries{$_[0]}[1] }
sub list_countries {
    my (%options) = @_;
    my @l = keys %countries;
    $options{exclude_non_installed} ? grep { -e "/usr/share/locale/".c2locale($_)."/LC_CTYPE" } @l : @l;
}

#- this list is built with the following command on the compile cluster:
#- rpm -qpl /cooker/RPMS/locales-* | grep LC_CTYPE | cut -d'/' -f5 | grep '_' | grep -v '\.' | sort | tr '\n' ' ' ; echo
our @locales = qw(ad_ET af_ZA am_ET an_ES ar_AE ar_BH ar_DZ ar_EG ar_IN ar_IQ ar_JO ar_KW ar_LB ar_LY ar_MA ar_OM ar_QA ar_SA ar_SD ar_SY ar_TN ar_YE as_IN az_AZ be_BY bg_BG bn_BD bn_IN br_FR bs_BA ca_ES cs_CZ cy_GB da_DK de_AT de_BE de_CH de_DE de_LU el_GR en_AU en_BE en_BW en_CA en_DK en_GB en_HK en_IE en_IN en_NZ en_PH en_SG en_US en_ZA en_ZW eo_XX es_AR es_BO es_CL es_CO es_CR es_DO es_EC es_ES es_GT es_HN es_MX es_NI es_PA es_PE es_PR es_PY es_SV es_US es_UY es_VE et_EE eu_ES fa_IR fi_FI fo_FO fr_BE fr_CA fr_CH fr_FR fr_LU ga_IE gd_GB gez_ER gez_ER@abegede gez_ET gez_ET@abegede gl_ES gu_IN gv_GB he_IL hi_IN hr_HR hu_HU hy_AM id_ID is_IS it_CH it_IT iu_CA ja_JP ka_GE kl_GL kn_IN ko_KR ku_TR kw_GB li_BE li_NL lo_LA lt_LT lv_LV mi_NZ mk_MK ml_IN mn_MN mr_IN ms_MY mt_MT nb_NO nds_DE nds_DE@traditional nds_NL ne_NP nl_BE nl_NL nn_NO oc_FR om_ET om_KE pa_IN ph_PH pl_PL pt_BR pt_PT qo_ET ro_RO ru_RU ru_UA se_NO sh_YU sid_ET sk_SK sl_SI sq_AL sr_CS sr_CS@Latn sr_YU sr_YU@Latn st_ZA sv_FI sv_SE sx_ET sz_ET ta_IN te_IN tg_TJ th_TH ti_ER ti_ET tig_ER tl_PH tr_TR tt_RU uk_UA ur_PK uz_UZ uz_UZ@Cyrl uz_UZ@Latn vi_VN wa_BE xh_ZA yi_US zh_CN zh_HK zh_SG zh_TW zu_ZA);
	
sub standard_locale {
    my ($lang, $country, $prefer_lang) = @_;
  retry:
    member("${lang}_${country}", @locales) and return "${lang}_${country}";
    $prefer_lang && member($lang, @locales) and return $lang;
    length($lang) > 2 and $lang =~ s/^(..).*/$1/, goto retry;
}

sub fix_variant {
    my ($locale) = @_;
    #- uz@Cyrl_UZ -> uz_UZ@Cyrl
    $locale =~ s/(.*)(\@\w+)(_.*)/$1$3$2/;
    $locale;
}

sub getlocale_for_lang {
    my ($lang, $country, $o_utf8) = @_;
    fix_variant((standard_locale($lang, $country, 'prefer_lang') || l2locale($lang)) . ($o_utf8 ? '.UTF-8' : ''));
}

sub getlocale_for_country {
    my ($lang, $country, $o_utf8) = @_;
    fix_variant((standard_locale($lang, $country, '') || c2locale($country)) . ($o_utf8 ? '.UTF-8' : ''));
}

sub getLANGUAGE {
    my ($lang, $o_country, $o_utf8) = @_;
    l2language($lang) || join(':', uniq(getlocale_for_lang($lang, $o_country, $o_utf8), $lang, if_($lang =~ /^(..)_/, $1)));
}

my %xim = (
#- xcin only works with 'zh_TW', 'zh_TW.Big5', 'zh_CN', 'zh_CN.GB2312'
#- all other locale names, in particular 'zh_HK' or 'zh_TW.UTF-8'
#- are unknown to it. So chinput is used for all but 'zh_TW'
  'zh_TW' => { 
 	ENC => 'big5',
 	XIM => 'xcin',
 	XIM_PROGRAM => 'xcin',
 	XMODIFIERS => '"@im=xcin-zh_TW"',
	GTK_IM_MODULE => 'xim',
 	CONSOLE_NOT_LOCALIZED => 'yes',
  },
  'zh_TW.UTF-8' => {
	ENC => 'utf8',
	XIM => 'Chinput',
	XIM_PROGRAM => '"chinput -big5"',
	XMODIFIERS => '"@im=Chinput"',
	GTK_IM_MODULE => 'xim',
	CONSOLE_NOT_LOCALIZED => 'yes',
  },
  'zh_CN' => {
	ENC => 'gb',
	XIM => 'Chinput',
	XIM_PROGRAM => '"chinput -gb"',
	XMODIFIERS => '"@im=Chinput"',
	GTK_IM_MODULE => 'xim',
	CONSOLE_NOT_LOCALIZED => 'yes',
  },
  'zh_CN.UTF-8' => {
	ENC => 'utf8',
	XIM => 'Chinput',
	XIM_PROGRAM => '"chinput -gb"',
	XMODIFIERS => '"@im=Chinput"',
	GTK_IM_MODULE => 'xim',
	CONSOLE_NOT_LOCALIZED => 'yes',
  },
  'zh_SG' => {
	ENC => 'gb',
	XIM => 'Chinput',
	XIM_PROGRAM => '"chinput -gb"',
	XMODIFIERS => '"@im=Chinput"',
	GTK_IM_MODULE => 'xim',
	CONSOLE_NOT_LOCALIZED => 'yes',
  },
  'zh_SG.UTF-8' => {
	ENC => 'utf8',
	XIM => 'Chinput',
	XIM_PROGRAM => '"chinput -gb"',
	XMODIFIERS => '"@im=Chinput"',
	GTK_IM_MODULE => 'xim',
	CONSOLE_NOT_LOCALIZED => 'yes',
  },
  'zh_HK' => {
	ENC => 'big5',
	XIM => 'Chinput',
	XIM_PROGRAM => '"chinput -big5"',
	XMODIFIERS => '"@im=Chinput"',
	GTK_IM_MODULE => 'xim',
	CONSOLE_NOT_LOCALIZED => 'yes',
  },
  'zh_HK.UTF-8' => {
	ENC => 'utf8',
	XIM => 'Chinput',
	XIM_PROGRAM => '"chinput -big5"',
	XMODIFIERS => '"@im=Chinput"',
	GTK_IM_MODULE => 'xim',
	CONSOLE_NOT_LOCALIZED => 'yes',
  },
  'ko_KR' => {
	ENC => 'kr',
	XIM => 'Ami',
	#- NOTE: there are several possible versions of ami, for the different
	#- desktops (kde, gnome, etc). So XIM_PROGRAM isn't defined; it will
	#- be the xinitrc script, XIM section, that will choose the right one 
	#- XIM_PROGRAM => 'ami',
	XMODIFIERS => '"@im=Ami"',
	GTK_IM_MODULE => 'xim',
	CONSOLE_NOT_LOCALIZED => 'yes',
  },
  'ko_KR.UTF-8' => {
	ENC => 'utf8',
	XIM => 'Ami',
	#- NOTE: there are several possible versions of ami, for the different
	#- desktops (kde, gnome, etc). So XIM_PROGRAM isn't defined; it will
	#- be the xinitrc script, XIM section, that will choose the right one 
	#- XIM_PROGRAM => 'ami',
	XMODIFIERS => '"@im=Ami"',
	GTK_IM_MODULE => 'xim',
	CONSOLE_NOT_LOCALIZED => 'yes',
  },
  'ja_JP' => {
	ENC => 'eucj',
	XIM => 'uim-anthy',
	XIM_PROGRAM => 'uim-xim',
	XMODIFIERS => '"@im=uim-anthy"',
	GTK_IM_MODULE => 'uim-anthy',
  },
  'ja_JP.UTF-8' => {
	ENC => 'utf8',
	XIM => 'uim-anthy',
	XIM_PROGRAM => 'uim-xim',
	XMODIFIERS => '"@im=uim-anthy"',
	GTK_IM_MODULE => 'uim-anthy',
  },
  #-�XFree86 has an internal XIM for Thai that enables syntax checking etc.
  #-�'Passthroug' is no check at all, 'BasicCheck' accepts bad sequences
  #-�and convert them to right ones, 'Strict' refuses bad sequences
  'th_TH' => {
	XIM_PROGRAM => '/bin/true', #- it's an internal module
	XMODIFIERS => '"@im=BasicCheck"',
  },
  #-�xvnkb is not an XIM input method; but an input method of another
  #-�kind, only XIM_PROGRAM needs to be defined
  #- ! xvnkb doesn't work in UTF-8 !
#-  'vi_VN.VISCII' => {
#-	XIM_PROGRAM => 'xvnkb',
#-  },
);

#- [0]: console font name
#- [1]: sfm map for console font (if needed)
#- [2]: acm file for console font (none if utf8)
#- [3]: iocharset param for mount (utf8 if utf8)
#- [4]: codepage parameter for mount (none if utf8)
my %charsets = (
#- chinese needs special console driver for text mode
"Big5"        => [ undef,         undef,   undef,           "big5",       "950" ],
"gb2312"      => [ undef,         undef,   undef,           "gb2312",     "936" ],
"C"           => [ "lat0-16",     undef,   "iso15",         "iso8859-1",  "850" ],
"iso-8859-1"  => [ "lat1-16",     undef,   "iso01",         "iso8859-1",  "850" ],
"iso-8859-2"  => [ "lat2-sun16",  undef,   "iso02",         "iso8859-2",  "852" ],
"iso-8859-5"  => [ "UniCyr_8x16", undef,   "iso05",         "iso8859-5",  "866" ],
"iso-8859-7"  => [ "iso07.f16",   undef,   "iso07",         "iso8859-7",  "869" ],
"iso-8859-9"  => [ "lat5u-16",    undef,   "iso09",         "iso8859-9",  "857" ],
"iso-8859-13" => [ "tlat7",       undef,   "iso13",         "iso8859-13", "775" ],
"iso-8859-15" => [ "lat0-16",     undef,   "iso15",         "iso8859-15", "850" ],
#- japanese needs special console driver for text mode [kon2]
"jisx0208"    => [ undef,         undef,   "trivial.trans", "euc-jp",     "932" ],
"koi8-r"      => [ "UniCyr_8x16", undef,   "koi8-r",        "koi8-r",     "866" ],
"koi8-u"      => [ "UniCyr_8x16", undef,   "koi8-u",        "koi8-u",     "866" ],
"cp1251"      => [ "UniCyr_8x16", undef,   "cp1251",        "cp1251",     "866" ],
#- korean needs special console driver for text mode
"ksc5601"     => [ undef,         undef,   undef,           "euc-kr",     "949" ],
#- I have no console font for Thai...
"tis620"      => [ undef,         undef,   "trivial.trans", "tis-620",    "874" ],
# UTF-8 encodings here; they differ in the console font mainly.
"utf_am"      => [ "Agafari-16",     undef,   undef,      "utf8",    undef ],
"utf_ar"      => [ "iso06.f16",      undef,   undef,      "utf8",    undef ],
"utf_az"      => [ "tiso09e",        undef,   undef,      "utf8",    undef ],
"utf_bn"      => [ undef,            undef,   undef,      "utf8",    undef ],
"utf_cyr1"    => [ "UniCyr_8x16",    undef,   undef,      "utf8",    undef ],
"utf_cyr2"    => [ "koi8-k",         undef,   undef,      "utf8",    undef ],
"utf_he"      => [ "iso08.f16",      undef,   undef,      "utf8",    undef ],
"utf_hy"      => [ "arm8",           undef,   undef,      "utf8",    undef ],
"utf_ka"      => [ "t_geors",        undef,   undef,      "utf8",    undef ],
"utf_kn"      => [ undef,            undef,   undef,      "utf8",    undef ],
"utf_lo"      => [ undef,            undef,   undef,      "utf8",    undef ],
"utf_ta"      => [ "tamil",          undef,   undef,      "utf8",    undef ],
"utf_vi"      => [ "tcvn8x16",       undef,   undef,      "utf8",    undef ],
"utf_lat8"    => [ "iso14.f16",      undef,   undef,      "utf8",    undef ],
# default for utf-8 encodings
"unicode"     => [ "LatArCyrHeb-16", undef,   undef,      "utf8",    undef ],
);

#- for special cases not handled magically
my %charset2kde_charset = (
    gb2312 => 'gb2312.1980-0',
    jisx0208 => 'jisx0208.1983-0',
    ksc5601 => 'ksc5601.1987-0',
    Big5 => 'big5-0',
    cp1251 => 'microsoft-cp1251',
    utf8 => 'iso10646-1',
    tis620 => 'tis620-0',
    #- Tamil KDE translations still use TSCII, and KDE know it as iso-8859-1
    utf_ta => 'iso8859-1',
);

my @during_install__lang_having_their_LC_CTYPE = qw(ja ko ta);


#- -------------------

sub list { 
    my (%options) = @_;
    my @l = list_langs();
    if ($options{exclude_non_installed_langs}) {
	@l = grep { -e "/usr/share/locale/$_/LC_CTYPE" } @l;
    }
    @l;
}

sub l2console_font {
    my ($locale, $during_install) = @_;
    my $c = $charsets{l2charset($locale->{lang}) || return} or return;
    my ($name, $sfm, $acm) = @$c;
    undef $acm if $locale->{utf8} && !$during_install;
    ($name, $sfm, $acm);
}

sub get_kde_lang {
    my ($locale, $o_default) = @_;

    #- get it using 
    #- echo C $(rpm -qp --qf "%{name}\n" /RPMS/kde-i18n-*  | sed 's/kde-i18n-//')
    my @valid_kde_langs = qw(C af ar az be bg br bs ca cs cy da de el en_GB eo es et eu fa fi fo fr ga gl he hr hu id is it ja ko ku lo lt lv mi mk mn mt nb nl nn nso oc pl pt pt_BR ro ru se sk sl sr ss sv ta th tr uk uz ven vi wa wen xh zh_CN zh_TW zu);
    my %valid_kde_langs; @valid_kde_langs{@valid_kde_langs} = ();

    my $valid_lang = sub {
	my ($lang) = @_;
	#- fast & dirty solution to ensure bad entries do not happen
        my %fixlangs = (en => 'C', en_US => 'C',
                        'sr@Latn' => 'sr',
                        st => 'nso', ve => 'ven',
                        zh_CN => 'zh_CN', zh_SG => 'zh_CN', zh_TW => 'zh_TW', zh_HK => 'zh_TW');
        exists $fixlangs{$lang} ? $fixlangs{$lang} :
	  exists $valid_kde_langs{$lang} ? $lang :
	  exists $valid_kde_langs{substr($lang, 0, 2)} ? substr($lang, 0, 2) : '';
    };

    my $r;
    $r ||= $valid_lang->($locale->{lang});
    $r ||= find { $valid_lang->($_) } split(':', getlocale_for_lang($locale->{lang}, $locale->{country}));
    $r || $o_default || 'C';
}

sub charset2kde_charset {
    my ($charset, $o_default) = @_;
    my $iocharset = ($charsets{$charset} || [])->[3];

    my @valid_kde_charsets = qw(big5-0 gb2312.1980-0 iso10646-1 iso8859-1 iso8859-4 iso8859-6 iso8859-8 iso8859-13 iso8859-14 iso8859-15 iso8859-2 iso8859-3 iso8859-5 iso8859-7 iso8859-9 koi8-r koi8-u ksc5601.1987-0 jisx0208.1983-0 microsoft-cp1251 tis620-0);
    my %valid_kde_charsets; @valid_kde_charsets{@valid_kde_charsets} = ();

    my $valid_charset = sub {
	my ($charset) = @_;
	#- fast & dirty solution to ensure bad entries do not happen
	exists $valid_kde_charsets{$charset} && $charset;
    };

    my $r;
    $r ||= $valid_charset->($charset2kde_charset{$charset});
    $r ||= $valid_charset->($charset2kde_charset{$iocharset});
    $r ||= $valid_charset->($iocharset);
    $r || $o_default || 'iso10646-1';
}

#- font+size for different charsets; the field [0] is the default,
#- others are overrridens for fixed(1), toolbar(2), menu(3) and taskbar(4)
my %charset2kde_font = (
  'C' => [ "Sans,10", "Monospace,10" ],
  'iso-8859-1'  => [ "Sans,10", "Monospace,10" ],
  'iso-8859-2'  => [ "Sans,10", "Monospace,10" ],
  'iso-8859-7'  => [ "Helvetica,12", "courier,10", "Helvetica,11" ],
  'iso-8859-9'  => [ "Sans,10", "Monospace,10" ],
  'iso-8859-15' => [ "Sans,10", "Monospace,10" ],
  'iso-8859-13' => [ "Sans,10", "Monospace,10" ],
  'jisx0208' => [ "Kochi Mincho,13", "Kochi Gothic,13" ],
  'ksc5601' => [ "Baekmuk Gulim,16" ],
  'gb2312' => [ "AR PL SungtiL GB,13" ],
  'Big5' => [ "AR PL Mingti2L Big5,13" ],
  'tis620' => [ "Norasi,16", "Norasi,15" ],
  'utf_ar' => [ "Kacs_qr,14", "Courier New,13", "Kacs_qr,13" ], 
  'utf_am' => [ "GF Zemen Unicode,15" ],
  'utf_az' => [ "Nimbus Sans,12", "Nimbus Mono,10", "Nimbus Sans,11" ],
  'utf_bn' => [ "Mukti,14", ],
  'utf_he' => [ "Nachlieli,13", , "Miriam Mono,10", "Nachlieli,11" ],
  'utf_hy' => [ "Artsounk,12", "Monospace,10", "Artsounk,11" ],
  'utf_kn' => [ "Sampige,14", ],
  'utf_ta' => [ "TSCu_Paranar,14", "Tsc_avarangalfxd,10", "TSCu_Paranar,12", ],
  #- the following should be changed to better defaults when better fonts
  #- get available
Mode	Name	Size
-rw-r--r--	.gitattributes	21	log stats plain
-rw-r--r--	.perl_checker	1054	log stats plain
-rw-r--r--	Makefile	3127	log stats plain
-rw-r--r--	Makefile.config	1119	log stats plain
-rw-r--r--	Makefile.drakxtools	3772	log stats plain
-rw-r--r--	NEWS	90143	log stats plain
-rw-r--r--	PORTING	188	log stats plain
-rw-r--r--	any.pm	59875	log stats plain
-rw-r--r--	authentication.pm	33191	log stats plain
-rw-r--r--	bootloader.pm	68464	log stats plain
-rw-r--r--	bootsplash.pm	2503	log stats plain
-rw-r--r--	c.pm	428	log stats plain
d---------	c	184	log stats plain
-rw-r--r--	common.pm	13552	log stats plain
-rw-r--r--	cpufreq.pm	4907	log stats plain
-rw-r--r--	dbus_object.pm	1702	log stats plain
-rw-r--r--	detect_devices.pm	45820	log stats plain
-rw-r--r--	devices.pm	7388	log stats plain
d---------	diskdrake	278	log stats plain
-rw-r--r--	do_pkgs.pm	7727	log stats plain
-rw-r--r--	fs.pm	11641	log stats plain
d---------	fs	627	log stats plain
-rw-r--r--	fsedit.pm	22177	log stats plain
-rw-r--r--	handle_configs.pm	4249	log stats plain
d---------	harddrake	184	log stats plain
d---------	install	864	log stats plain
-rw-r--r--	interactive.pm	21844	log stats plain
d---------	interactive	142	log stats plain
-rw-r--r--	lang.pm	64551	log stats plain
l---------	list_modules.pm	25	log stats plain
-rw-r--r--	log.pm	1024	log stats plain
-rw-r--r--	lvm.pm	6887	log stats plain
-rw-r--r--	messages.pm	5665	log stats plain
-rw-r--r--	mirror.pm	4803	log stats plain
-rw-r--r--	modalias.pm	2958	log stats plain
-rw-r--r--	modules.pm	10740	log stats plain
d---------	modules	209	log stats plain
-rw-r--r--	mygtk2.pm	53396	log stats plain
-rw-r--r--	partition_table.pm	20617	log stats plain
d---------	partition_table	351	log stats plain
d---------	pixmaps	1481	log stats plain
-rw-r--r--	pkgs.pm	10490	log stats plain
-rw-r--r--	raid.pm	8218	log stats plain
d---------	resize_fat	493	log stats plain
-rw-r--r--	run_program.pm	6024	log stats plain
-rw-r--r--	scanner.pm	21060	log stats plain
d---------	security	179	log stats plain
-rw-r--r--	services.pm	26293	log stats plain
d---------	share	391	log stats plain
-rw-r--r--	standalone.pm	11833	log stats plain
d---------	standalone	1730	log stats plain
-rw-r--r--	timezone.pm	8251	log stats plain
-rw-r--r--	ugtk2.pm	56373	log stats plain
d---------	unused	358	log stats plain
-rw-r--r--	wizards.pm	8194	log stats plain