isoCodeToEnWikiName.put("BE", "Belarusian");
isoCodeToEnWikiName.put("BN", "Bengali");
isoCodeToEnWikiName.put("BG", "Bulgarian");
- isoCodeToEnWikiName.put("MY", "Burmese");
isoCodeToEnWikiName.put("CA", "Catalan");
isoCodeToEnWikiName.put("SH", "Serbo-Croatian");
isoCodeToEnWikiName.put("HR", "Croatian");
isoCodeToEnWikiName.put("ID", "Indonesian");
isoCodeToEnWikiName.put("GA", "Irish");
isoCodeToEnWikiName.put("GD", "Gaelic");
+ isoCodeToEnWikiName.put("GV", "Manx");
isoCodeToEnWikiName.put("IT", "Italian");
isoCodeToEnWikiName.put("LA", "Latin");
isoCodeToEnWikiName.put("LV", "Latvian");
isoCodeToEnWikiName.put("KO", "Korean");
isoCodeToEnWikiName.put("KU", "Kurdish");
isoCodeToEnWikiName.put("LO", "Lao");
- isoCodeToEnWikiName.put("MS", "Malay");
+ isoCodeToEnWikiName.put("MS", "Malay$");
isoCodeToEnWikiName.put("ML", "Malayalam");
isoCodeToEnWikiName.put("MI", "Maori");
isoCodeToEnWikiName.put("MN", "Mongolian");
isoCodeToEnWikiName.put("AZ", "Azeri");
isoCodeToEnWikiName.put("EU", "Basque");
isoCodeToEnWikiName.put("BR", "Breton");
- isoCodeToEnWikiName.put("MR", "Burmese");
+ isoCodeToEnWikiName.put("MR", "Marathi");
isoCodeToEnWikiName.put("FO", "Faroese");
isoCodeToEnWikiName.put("GL", "Galician");
isoCodeToEnWikiName.put("KA", "Georgian");
isoCodeToEnWikiName.put("HT", "Haitian Creole");
isoCodeToEnWikiName.put("LB", "Luxembourgish");
isoCodeToEnWikiName.put("MK", "Macedonian");
+ isoCodeToEnWikiName.put("GV", "Manx");
// No longer exists in EN:
// isoCodeToEnWikiName.put("BS", "Bosnian");
// isoCodeToEnWikiName.put("SR", "Serbian");
+
+ // Font doesn't work:
+ //isoCodeToEnWikiName.put("MY", "Burmese");
+
{
- Set<String> missing = new LinkedHashSet<String>(isoCodeToEnWikiName.keySet());
- missing.removeAll(Language.isoCodeToResources.keySet());
+ //Set<String> missing = new LinkedHashSet<String>(isoCodeToEnWikiName.keySet());
+ //missing.removeAll(Language.isoCodeToResources.keySet());
//System.out.println(missing);
}
- assert Language.isoCodeToResources.keySet().containsAll(isoCodeToEnWikiName.keySet());
+ //assert Language.isoCodeToResources.keySet().containsAll(isoCodeToEnWikiName.keySet());
}
public static final Map<String,Map<String,String>> wikiCodeToIsoCodeToWikiName = new LinkedHashMap<String, Map<String,String>>();
isoCodeToWikiName.put("SV", "Schwedisch");
isoCodeToWikiName.put("ES", "Spanisch");
- // egrep -o '\{\{=[a-zA-Z]+=\}\}' frwiktionary-pages-articles.xml | sort | uniq -c | sort -nr
+ // egrep -o '== *\{\{langue\|[a-zA-Z]+\}\} *==' frwiktionary-pages-articles.xml | sort | uniq -c | sort -nr
isoCodeToWikiName = new LinkedHashMap<String, String>();
wikiCodeToIsoCodeToWikiName.put("fr", isoCodeToWikiName);
isoCodeToWikiName.put("FR", Pattern.quote("{{langue|fr}}"));
isoCodeToWikiName.put("EL", Pattern.quote("{{-grc-}}"));
isoCodeToWikiName.put("SV", Pattern.quote("{{-sv-}}"));
+ // There seems to be no consistent pattern and few foreign language entries anyway
+ isoCodeToWikiName = new LinkedHashMap<String, String>();
+ wikiCodeToIsoCodeToWikiName.put("es", isoCodeToWikiName);
+ isoCodeToWikiName.put("ES", Pattern.quote("{{ES"));
}
public static String getEnglishName(String langCode) {
String name = isoCodeToEnWikiName.get(langCode);
return null;
}
if (name.indexOf('|') != -1) {
- return name.substring(name.indexOf('|'));
+ return name.substring(0, name.indexOf('|'));
+ }
+ if (name.indexOf('$') != -1) {
+ return name.substring(0, name.indexOf('$'));
}
return name; // can be null.
}