source: gsdl/trunk/perllib/lang.pm@ 15894

###########################################################################
#
# lang.pm --
# A component of the Greenstone digital library software
# from the New Zealand Digital Library Project at the 
# University of Waikato, New Zealand.
#
# Copyright (C) 1999 New Zealand Digital Library Project
#
# 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., 675 Mass Ave, Cambridge, MA 02139, USA.
#
###########################################################################

# this module translates language descriptions to and from
# the ISO 639 standard

package lang;

use strict;

@lang::trans = (["ab", "Abkhazian"],      ["om", "Afan Oromo"],
      ["om", "Oromo"],          ["aa", "Afar"],
      ["af", "Afrikaans"],      ["sq", "Albanian"],
      ["am", "Amharic"],        ["ar", "Arabic"],
      ["hy", "Armenian"],       ["as", "Assamese"],
      ["ay", "Aymara"],         ["az", "Azerbaijani"],

      ["ba", "Bashkir"],        ["eu", "Basque"],
      ["bn", "Bengali"],        ["bn", "Bangla"],
      ["dz", "Bhutani"],        ["bh", "Bihari"],
      ["bi", "Bislama"],        ["br", "Breton"],
      ["bg", "Bulgarian"],      ["my", "Burmese"],
      ["be", "Byelorussian"],

      ["km", "Cambodian"],      ["ca", "Catalan"],
      ["zh", "Chinese"],        ["co", "Corsican"],
      ["hr", "Croatian"],       ["cs", "Czech"],

      ["da", "Danish"],         ["nl", "Dutch"],

      ["en", "English"],        ["eo", "Esperanto"],
      ["et", "Estonian"],       ["fo", "Faroese"],
      ["fj", "Fijian"],         ["fi", "Finnish"],
      ["fr", "French"],         ["fy", "Frisian"],

      ["gl", "Galician"],       ["ka", "Georgian"],
      ["de", "German"],         ["el", "Greek"],
      ["kl", "Greenlandic"],    ["gn", "Guarani"],
      ["gu", "Gujarati"],

      ["ha", "Hausa"],          ["iw", "Hebrew"],
      ["hi", "Hindi"],          ["hu", "Hungarian"],

      ["is", "Icelandic"],      ["in", "Indonesian"],
      ["ia", "Interlingua"],    ["ie", "Interlingue"],
      ["ik", "Inupiak"],        ["ga", "Irish"],
      ["it", "Italian"],

      ["ja", "Japanese"],       ["jv", "Javanese"],

      ["kn", "Kannada"],        ["ks", "Kashmiri"],
      ["kk", "Kazakh"],         ["rw", "Kinyarwanda"],
      ["ky", "Kirghiz"],        ["rn", "Kirundi"],
      ["ko", "Korean"],         ["ku", "Kurdish"],

      ["lo", "Laothian"],       ["la", "Latin"],
      ["lv", "Latvian"],        ["lv", "Lettish"],
      ["ln", "Lingala"],        ["lt", "Lithuanian"],

      ["mk", "Macedonian"],     ["mg", "Malagasy"],
      ["ms", "Malay"],          ["ml", "Malayalam"],
      ["mt", "Maltese"],        ["mi", "Maori"],
      ["mr", "Marathi"],        ["mo", "Moldavian"],
      ["mn", "Mongolian"],

      ["na", "Nauru"],          ["ne", "Nepali"],
      ["no", "Norwegian"],

      ["oc", "Occitan"],        ["or", "Oriya"],

      ["ps", "Pashto"],         ["ps", "Pushto"],
      ["fa", "Persian"],        ["pl", "Polish"],
      ["pt", "Portuguese"],     ["pa", "Punjabi"],

      ["qu", "Quechua"],

      ["rm", "Rhaeto-Romance"], ["ro", "Romanian"],
      ["ru", "Russian"],

      ["sm", "Samoan"],         ["sg", "Sangho"],
      ["sa", "Sanskrit"],       ["gd", "Scots Gaelic"],
      ["sr", "Serbian"],        ["sh", "Serbo-Croatian"],
      ["st", "Sesotho"],        ["tn", "Setswana"],
      ["sn", "Shona"],          ["sd", "Sindhi"],
      ["si", "Singhalese"],     ["ss", "Siswati"],
      ["sk", "Slovak"],         ["sl", "Slovenian"],
      ["so", "Somali"],         ["es", "Spanish"],
      ["su", "Sundanese"],      ["sw", "Swahili"],
      ["sv", "Swedish"],

      ["tl", "Tagalog"],        ["tg", "Tajik"],
      ["ta", "Tamil"],          ["tt", "Tatar"],
      ["te", "Telugu"],         ["th", "Thai"],
      ["bo", "Tibetan"],        ["ti", "Tigrinya"],
      ["to", "Tonga"],          ["ts", "Tsonga"],
      ["tr", "Turkish"],        ["tk", "Turkmen"],
      ["tw", "Twi"],

      ["uk", "Ukrainian"],      ["ur", "Urdu"],
      ["uz", "Uzbek"],

      ["vi", "Vietnamese"],     ["vo", "Volapuk"],

      ["cy", "Welsh"],          ["wo", "Wolof"],

      ["xh", "Xhosa"],

      ["ji", "Yiddish"],        ["yo", "Yoruba"],

      ["zu", "Zulu"]);


sub one_english_to_iso639 {
    my ($english) = @_;
    my $iso639 = "";

    foreach my $lang (@lang::trans) {
    my $code = $lang->[0];
    my $enname = $lang->[1];
    if ($english =~ /^\s*($code|$enname)\s*$/i) {
        # found the language
        $iso639 = $code;
        last;

    }
    }

    return $iso639;
}


sub english_to_iso639 {
    my ($englishlist) = @_;
    my ($english);

    my @englishlist = split (",", $englishlist);
    my @iso639list = ();

    foreach my $english (@englishlist) {
    push (@iso639list, &one_english_to_iso639($english));
    }

    return join (",", @iso639list);
}


sub one_iso639_to_english {
    my ($iso639) = @_;
    my $english = "";

    foreach my $lang (@lang::trans) {
    my $code = $lang->[0];
    my $enname = $lang->[1];
    if ($iso639 =~ /\s*($code|$enname)\s*$/i) {
        # found the language
        $english = $enname;
        last;

    }
    }

    return $english;
}


sub iso639_to_english {
    my ($iso639list) = @_;
    my ($iso639);

    my @iso639list = split (",", $iso639list);
    my @englishlist = ();

    foreach $iso639 (@iso639list) {
    push (@englishlist, &one_iso639_to_english($iso639));
    }

    return join (",", @englishlist);
}


1;