Refactor code to generate dictionaries to make it all one loop!

diff --git a/src/com/hughes/android/dictionary/engine/CheckDictionariesMain.java b/src/com/hughes/android/dictionary/engine/CheckDictionariesMain.java
index e4d5c0c9616e1942ef21553bd03c11780223ffad..3beb2ba5ca78791ef39ff1ecbcc9b00e7c35ea18 100644 (file)
--- a/src/com/hughes/android/dictionary/engine/CheckDictionariesMain.java
+++ b/src/com/hughes/android/dictionary/engine/CheckDictionariesMain.java
@@ -56,8 +56,8 @@ public class CheckDictionariesMain {
       
       // Find the stats.
       System.out.println("Stats...");
-      final String lang1 = WiktionaryLangs.isoCodeToWikiName.get(dictionaryInfo.indexInfos.get(0).shortName);
-      final String lang2 = WiktionaryLangs.isoCodeToWikiName.get(dictionaryInfo.indexInfos.get(1).shortName);
+      final String lang1 = WiktionaryLangs.isoCodeToEnWikiName.get(dictionaryInfo.indexInfos.get(0).shortName);
+      final String lang2 = WiktionaryLangs.isoCodeToEnWikiName.get(dictionaryInfo.indexInfos.get(1).shortName);
       dictNames.add(String.format("%s-%s\n", lang1, lang2));
       final String row = dictionaryInfo.append(new StringBuilder()).toString();
       if (!zipFile.canRead()) {

diff --git a/src/com/hughes/android/dictionary/engine/DictionaryBuilderMain.java b/src/com/hughes/android/dictionary/engine/DictionaryBuilderMain.java
index db5c757fe83a391848174eba0047e9d44a97c43c..c17ebec6717e5bff24da762eb7bf493797520195 100644 (file)
--- a/src/com/hughes/android/dictionary/engine/DictionaryBuilderMain.java
+++ b/src/com/hughes/android/dictionary/engine/DictionaryBuilderMain.java
@@ -14,6 +14,7 @@
 
 package com.hughes.android.dictionary.engine;
 
+import java.util.ArrayList;
 import java.util.Arrays;
 import java.util.LinkedHashMap;
 import java.util.LinkedHashSet;
@@ -31,47 +32,128 @@ public class DictionaryBuilderMain extends TestCase {
   static final String INPUTS = "data/inputs/";
   static final String STOPLISTS = "data/inputs/stoplists/";
   static final String OUTPUTS = "data/outputs/";  
+
+  
+  static final Map<String,String>  isoToDedication = new LinkedHashMap<String, String>();
+  static {
+  isoToDedication.put("AF", "Afrikaans dictionary dedicated to Heiko and Mariëtte Horn.");
+  isoToDedication.put("HR", "Croatian dictionary dedicated to Ines Viskic and Miro Kresonja.");
+  isoToDedication.put("NL", "Dutch dictionary dedicated to Mike LeBeau.");
+  // German handled in file.
+  isoToDedication.put("EL", "Greek dictionary dedicated to Noah Egge.");
+  isoToDedication.put("IT", "Italian dictionary dedicated to Carolina Tropini, my favorite stardust in the whole universe!  Ti amo!");
+  isoToDedication.put("KO", "Korean dictionary dedicated to Ande Elwood--fall fashion und Fernsehturms!");
+  isoToDedication.put("PT", "Portuguese dictionary dedicated to Carlos Melo, one Tough Mudder.");
+  isoToDedication.put("RO", "Romanian dictionary dedicated to Radu Teodorescu.");
+  isoToDedication.put("RU", "Russian dictionary dedicated to Maxim Aronin--best friend always!.");
+  isoToDedication.put("SR", "Serbian dictionary dedicated to Filip Crnogorac--thanks for the honey.");
+  isoToDedication.put("ES", "Spanish dictionary made especially for Carolina Tropini! <3 XoXoXXXXX!");
+  isoToDedication.put("SV", "Swedish dictionary dedicated to Kajsa Palmblad--björn kramar!");
+  }
+  private static String getDedication(String iso) {
+    return isoToDedication.containsKey(iso) ? "\n\n" + isoToDedication.get(iso) : "";
+  }
+  
+  static final Map<String,String>  isoToStoplist = new LinkedHashMap<String, String>();
+  static {
+  isoToStoplist.put("DE", "de.txt");
+  isoToStoplist.put("EN", "en.txt");
+  isoToStoplist.put("ES", "es.txt");
+  isoToStoplist.put("IT", "it.txt");
+  isoToStoplist.put("FR", "fr.txt");
+  }
+  private static String getStoplist(String iso) {
+    return isoToStoplist.containsKey(iso) ? isoToStoplist.get(iso) : "empty.txt";
+  }
+  
+  static List<String> getMainArgs(final String[] pair) {
+    final List<String> result = new ArrayList<String>();
     
-  public static void main(final String[] args) throws Exception {
+    final String lang1 = pair[0];
+    final String lang2 = pair[1];
     
-    // Builds all the dictionaries it can, outputs list to a text file.
+    final String dictFile = String.format("%s/%s-%s.quickdic", 
+        OUTPUTS, lang1, lang2);
     
-    final Map<String,String> isoToWikiName = new LinkedHashMap<String, String>(WiktionaryLangs.isoCodeToWikiName);
-    isoToWikiName.remove("EN");
-    isoToWikiName.remove("DE");
+    result.add(String.format("--dictOut=%s", dictFile));
+    result.add(String.format("--lang1Stoplist=%s", STOPLISTS + getStoplist(lang1)));
+    result.add(String.format("--lang2Stoplist=%s", STOPLISTS + getStoplist(lang2)));
 
-    final Map<String,String>  isoToDedication = new LinkedHashMap<String, String>();
-    isoToDedication.put("AF", "Afrikaans dictionary dedicated to Heiko and Mariëtte Horn.");
-    isoToDedication.put("HR", "Croatian dictionary dedicated to Ines Viskic and Miro Kresonja.");
-    isoToDedication.put("NL", "Dutch dictionary dedicated to Mike LeBeau.");
-    // German handled in file.
-    isoToDedication.put("EL", "Greek dictionary dedicated to Noah Egge.");
-    isoToDedication.put("IT", "Italian dictionary dedicated to Carolina Tropini, my favorite stardust in the whole universe!  Ti amo!");
-    isoToDedication.put("KO", "Korean dictionary dedicated to Ande Elwood--fall fashion und Fernsehturms!");
-    isoToDedication.put("PT", "Portuguese dictionary dedicated to Carlos Melo, one Tough Mudder.");
-    isoToDedication.put("RO", "Romanian dictionary dedicated to Radu Teodorescu.");
-    isoToDedication.put("RU", "Russian dictionary dedicated to Maxim Aronin--best friend always!.");
-    isoToDedication.put("SR", "Serbian dictionary dedicated to Filip Crnogorac--thanks for the honey.");
-    isoToDedication.put("ES", "Spanish dictionary made especially for Carolina Tropini! <3 XoXoXXXXX!");
-    isoToDedication.put("SV", "Swedish dictionary dedicated to Kajsa Palmblad--björn kramar!");
+    int i = 2;
+    
+    // Deal with the pairs where one is English.
+    if (Arrays.asList(pair).contains("EN")) {
+      final String foreignIso = pair[0].equals("EN") ? pair[1] : pair[0];
+      
+      
+      String foreignRegex = WiktionaryLangs.isoCodeToEnWikiName.get(foreignIso);
+      if (foreignIso.equals("ZH")) {
+        // HACK: The missing "e" prevents a full match, causing "Cantonese" to be appended to the entries.
+        foreignRegex = "Chinese|Mandarin|Cantones";
+      }
+      
+      final int enIndex;
+      if (foreignIso.equals("DE")) {
+        // German-English is a special case since it was the first ever QuickDic!
+        result.add(String.format("--lang1=%s", "DE"));
+        result.add(String.format("--lang2=%s", "EN"));
+        result.add("--dictInfo=@" + INPUTS + "de-en_chemnitz_enwiktionary.info");
 
-    final Map<String,String>  isoToStoplist = new LinkedHashMap<String, String>();
-    isoToStoplist.put("DE", "de.txt");
-    isoToStoplist.put("EN", "en.txt");
-    isoToStoplist.put("ES", "es.txt");
-    isoToStoplist.put("IT", "it.txt");
-    isoToStoplist.put("FR", "fr.txt");
+        enIndex = 2;
+      } else {
+        result.add(String.format("--lang1=%s", "EN"));
+        result.add(String.format("--lang2=%s",  foreignIso));
+        result.add(String.format("--dictInfo=(EN)Wikitionary-based EN-%s dictionary.%s", foreignIso, getDedication(foreignIso)));
+        enIndex = 1;
+      }
+      
+      result.add(String.format("--input%d=%s/wikiSplit/en/%s.data", i, INPUTS, foreignIso));
+      result.add(String.format("--input%dName=enwiktionary.%s", i, foreignIso)) ;
+      result.add(String.format("--input%dFormat=enwiktionary", i));
+      result.add(String.format("--input%dWiktionaryType=EnForeign", i));
+      result.add(String.format("--input%dLangPattern=%s", i, foreignRegex));
+      result.add(String.format("--input%dLangCodePattern=%s", i, foreignIso.toLowerCase()));
+      result.add(String.format("--input%dEnIndex=%d", i, enIndex));
+      ++i;
+
+      result.add(String.format("--input%d=%swikiSplit/en/EN.data", i, INPUTS));
+      result.add(String.format("--input%dName=enwiktionary.english", i));
+      result.add(String.format("--input%dFormat=enwiktionary", i));
+      result.add(String.format("--input%dWiktionaryType=EnToTranslation", i));
+      result.add(String.format("--input%dLangPattern=%s", i, foreignRegex));
+      result.add(String.format("--input%dLangCodePattern=%s", i, foreignIso.toLowerCase()));
+      result.add(String.format("--input%dEnIndex=%d", i, enIndex));
+      ++i;
+      
+      if (foreignIso.equals("DE")) {
+        result.add(String.format("--input%d=%sde-en_chemnitz.txt", i, INPUTS));
+        result.add(String.format("--input%dName=chemnitz", i));
+        result.add(String.format("--input%dCharset=UTF8", i));
+        result.add(String.format("--input%dFormat=chemnitz", i));
+        ++i;
+      }
+    } else {
+      // Pairs without English.
+      result.add(String.format("--lang1=%s", lang1));
+      result.add(String.format("--lang2=%s", lang2));
+      
+      result.add(String.format("--input%d=%swikiSplit/en/EN.data", i, INPUTS));
+      result.add(String.format("--input%dName=BETA!enwiktionary.%s-%s", i, lang1, lang2));
+      result.add(String.format("--input%dFormat=%s", i, EnTranslationToTranslationParser.NAME));
+      result.add(String.format("--input%dLangPattern1=%s", i, lang1));
+      result.add(String.format("--input%dLangPattern2=%s", i, lang2));
+      ++i;
+    }
+    return result;
+  }
 
-    final Map<String,String>  isoToRegex = new LinkedHashMap<String, String>();
-    // HACK: The missing "e" prevents a full match, causing "Cantonese" to be appended to the entries.
-    isoToRegex.put("ZH", "Chinese|Mandarin|Cantones");
+  public static void main(final String[] args) throws Exception {
     
+    final List<String[]> allPairs = new ArrayList<String[]>();
     
     // Build the non EN ones.
-    
     final String[][] nonEnPairs = new String[][] {
         
-        /*
         {"AR", "DE" },
         {"AR", "ES" },
         {"AR", "FR" },
@@ -148,14 +230,24 @@ public class DictionaryBuilderMain extends TestCase {
         {"PL", "RU" },  // Polish
         {"PL", "HU" },  // Polish
         {"PL", "ES" },  // Polish
-
-        */
         
+        //{"TR", "EL" },  // Turkish, Greek
 
     };
+    allPairs.addAll(Arrays.asList(nonEnPairs));
+    
+    // Add all the EN-XX pairs.
+    for (final String isoCode : WiktionaryLangs.isoCodeToEnWikiName.keySet()) {
+      if (isoCode.equals("EN") || isoCode.equals("DE")) {
+        continue;
+      }
+      allPairs.add(new String[] {"EN", isoCode});
+    }
+    allPairs.add(new String[] {"EN", "DE"});
     
+        
     final Set<List<String>> done = new LinkedHashSet<List<String>>();
-    for (final String[] pair : nonEnPairs) {
+    for (final String[] pair : allPairs) {
       Arrays.sort(pair);
       final List<String> pairList = Arrays.asList(pair);
       if (done.contains(pairList)) {
@@ -163,127 +255,8 @@ public class DictionaryBuilderMain extends TestCase {
       }
       done.add(pairList);
       
-      final String lang1 = pair[0];
-      final String lang2 = pair[1];
-      
-      final String dictFile = String.format("%s/%s-%s_enwiktionary_BETA.quickdic", 
-          OUTPUTS, lang1, lang2);
-      System.out.println("building dictFile: " + dictFile);
-
-      if (!isoToStoplist.containsKey(lang1)) {
-        isoToStoplist.put(lang1, "empty.txt");
-      }
-      if (!isoToStoplist.containsKey(lang2)) {
-        isoToStoplist.put(lang2, "empty.txt");
-      }
-      
-      DictionaryBuilder.main(new String[] {
-          String.format("--dictOut=%s", dictFile),
-          String.format("--lang1=%s", lang1),
-          String.format("--lang2=%s", lang2),
-          String.format("--lang1Stoplist=%s", STOPLISTS + isoToStoplist.get(lang1)),
-          String.format("--lang2Stoplist=%s", STOPLISTS + isoToStoplist.get(lang2)),
-          String.format("--dictInfo=(EN)Wikitionary-based %s-%s dictionary.", lang1, lang2),
-
-          String.format("--input2=%swikiSplit/en/EN.data", INPUTS),
-          String.format("--input2Name=BETA!enwiktionary.%s-%s", lang1, lang2),
-          String.format("--input2Format=%s", EnTranslationToTranslationParser.NAME),
-          String.format("--input2LangPattern1=%s", lang1),
-          String.format("--input2LangPattern2=%s", lang2),
-      });
+      DictionaryBuilder.main(getMainArgs(pair).toArray(new String[0]));
     }
-    if (1==1) {
-      //return;
-    }
-
-
-    // Now build the EN ones.
-    
-//    isoToWikiName.keySet().retainAll(Arrays.asList("UK", "HR", "FI"));
-    //isoToWikiName.clear();
-    boolean go = false;
-    for (final String foreignIso : isoToWikiName.keySet()) {
-      if (foreignIso.equals("SL")) {
-        go = true;
-      }
-      if (!go) {
-        continue;
-      }
-
-        final String dictFile = String.format("%s/EN-%s_enwiktionary.quickdic", OUTPUTS, foreignIso);
-        System.out.println("building dictFile: " + dictFile);
-        
-        if (!isoToStoplist.containsKey(foreignIso)) {
-          isoToStoplist.put(foreignIso, "empty.txt");
-        }
-        if (!isoToDedication.containsKey(foreignIso)) {
-          isoToDedication.put(foreignIso, "");
-        }
-        if (!isoToRegex.containsKey(foreignIso)) {
-          isoToRegex.put(foreignIso, isoToWikiName.get(foreignIso));
-        }
-  
-        DictionaryBuilder.main(new String[] {
-            String.format("--dictOut=%s", dictFile),
-            String.format("--lang1=EN"),
-            String.format("--lang2=%s", foreignIso),
-            String.format("--lang1Stoplist=%s", STOPLISTS + isoToStoplist.get("EN")),
-            String.format("--lang2Stoplist=%s", STOPLISTS + isoToStoplist.get(foreignIso)),
-            String.format("--dictInfo=(EN)Wikitionary-based EN-%s dictionary.\n\n%s", foreignIso, isoToDedication.get(foreignIso)),
-
-            "--input2=" + INPUTS + "wikiSplit/en/" + foreignIso + ".data",
-            "--input2Name=enwiktionary." + foreignIso,
-            "--input2Format=enwiktionary",
-            "--input2WiktionaryType=EnForeign",
-            "--input2LangPattern=" + isoToRegex.get(foreignIso),
-            "--input2LangCodePattern=" + foreignIso.toLowerCase(),
-            "--input2EnIndex=1",
-
-            "--input3=" + INPUTS + "wikiSplit/en/EN.data",
-            "--input3Name=enwiktionary.english",
-            "--input3Format=enwiktionary",
-            "--input3WiktionaryType=EnToTranslation",
-            "--input3LangPattern=" + isoToRegex.get(foreignIso),
-            "--input3LangCodePattern=" + foreignIso.toLowerCase(),
-            "--input3EnIndex=1",
-
-        });
-        
-    }  // foreignIso
-
-    // Now special case German-English.
-
-    final String dictFile = String.format("%s/DE-EN_chemnitz_enwiktionary.quickdic", OUTPUTS);
-    DictionaryBuilder.main(new String[] {
-        "--dictOut=" + dictFile,
-        "--lang1=DE",
-        "--lang2=EN",
-        String.format("--lang1Stoplist=%s", STOPLISTS + "de.txt"),
-        String.format("--lang2Stoplist=%s", STOPLISTS + "en.txt"),
-        "--dictInfo=@" + INPUTS + "de-en_chemnitz_enwiktionary.info",
-
-        "--input4=" + INPUTS + "de-en_chemnitz.txt",
-        "--input4Name=chemnitz",
-        "--input4Charset=UTF8",
-        "--input4Format=chemnitz",
-        
-        "--input2=" + INPUTS + "wikiSplit/en/DE.data",
-        "--input2Name=enwiktionary.DE",
-        "--input2Format=enwiktionary",
-        "--input2WiktionaryType=EnForeign",
-        "--input2LangPattern=German",
-        "--input2LangCodePattern=de",
-        "--input2EnIndex=2",
-
-        "--input3=" + INPUTS + "wikiSplit/en/EN.data",
-        "--input3Name=enwiktionary.english",
-        "--input3Format=enwiktionary",
-        "--input3WiktionaryType=EnToTranslation",
-        "--input3LangPattern=German",
-        "--input3LangCodePattern=de",
-        "--input3EnIndex=2",
-    });
-    
-  }
     
+  }    
 }

diff --git a/src/com/hughes/android/dictionary/engine/LanguageTest.java b/src/com/hughes/android/dictionary/engine/LanguageTest.java
index 7b84dd644845682305cab6e6f7482f70ceb55b21..4f909623678e5498512d834a253911dc10a99599 100644 (file)
--- a/src/com/hughes/android/dictionary/engine/LanguageTest.java
+++ b/src/com/hughes/android/dictionary/engine/LanguageTest.java
@@ -183,8 +183,8 @@ public class LanguageTest extends TestCase {
 
   
   public void testEnWiktionaryNames() {
-    final Set<String> enLangs = new LinkedHashSet<String>(WiktionaryLangs.isoCodeToWikiName.keySet());
-    for (final String code : WiktionaryLangs.isoCodeToWikiName.keySet()) {
+    final Set<String> enLangs = new LinkedHashSet<String>(WiktionaryLangs.isoCodeToEnWikiName.keySet());
+    for (final String code : WiktionaryLangs.isoCodeToEnWikiName.keySet()) {
       enLangs.add(code.toLowerCase());
     }
     assertEquals(enLangs.toString(), Language.isoCodeToResources.keySet().toString());

diff --git a/src/com/hughes/android/dictionary/parser/wiktionary/WiktionaryLangs.java b/src/com/hughes/android/dictionary/parser/wiktionary/WiktionaryLangs.java
index e2caa412cd46217dc0fad6e1027bfb7e5d432f58..bf855b38da14561acaab2d5c503b8ae628c8d9b9 100644 (file)
--- a/src/com/hughes/android/dictionary/parser/wiktionary/WiktionaryLangs.java
+++ b/src/com/hughes/android/dictionary/parser/wiktionary/WiktionaryLangs.java
@@ -20,94 +20,94 @@ import java.util.regex.Pattern;
 
 public class WiktionaryLangs {
   
-  public static final Map<String,String> isoCodeToWikiName = new LinkedHashMap<String,String>();
+  public static final Map<String,String> isoCodeToEnWikiName = new LinkedHashMap<String,String>();
   static {
-    isoCodeToWikiName.put("AF", "Afrikaans");
-    isoCodeToWikiName.put("SQ", "Albanian");
-    isoCodeToWikiName.put("AR", "Arabic");
-    isoCodeToWikiName.put("HY", "Armenian");
-    isoCodeToWikiName.put("BE", "Belarusian");
-    isoCodeToWikiName.put("BN", "Bengali");
-    isoCodeToWikiName.put("BS", "Bosnian");
-    isoCodeToWikiName.put("BG", "Bulgarian");
-    isoCodeToWikiName.put("CA", "Catalan");
-    isoCodeToWikiName.put("HR", "Croatian");
-    isoCodeToWikiName.put("CS", "Czech");
-    isoCodeToWikiName.put("ZH", "Chinese|Mandarin|Cantonese");
-    isoCodeToWikiName.put("DA", "Danish");
-    isoCodeToWikiName.put("NL", "Dutch");
-    isoCodeToWikiName.put("EN", "English");
-    isoCodeToWikiName.put("EO", "Esperanto");
-    isoCodeToWikiName.put("ET", "Estonian");
-    isoCodeToWikiName.put("FI", "Finnish");
-    isoCodeToWikiName.put("FR", "French");
-    isoCodeToWikiName.put("DE", "German");
-    isoCodeToWikiName.put("EL", "Greek");
-    isoCodeToWikiName.put("haw", "Hawaiian");
-    isoCodeToWikiName.put("HE", "Hebrew");
-    isoCodeToWikiName.put("HI", "Hindi");
-    isoCodeToWikiName.put("HU", "Hungarian");
-    isoCodeToWikiName.put("IS", "Icelandic");
-    isoCodeToWikiName.put("ID", "Indonesian");
-    isoCodeToWikiName.put("GA", "Irish");
-    isoCodeToWikiName.put("GD", "Gaelic");
-    isoCodeToWikiName.put("IT", "Italian");
-    isoCodeToWikiName.put("LA", "Latin");
-    isoCodeToWikiName.put("LV", "Latvian");
-    isoCodeToWikiName.put("LT", "Lithuanian");
-    isoCodeToWikiName.put("JA", "Japanese");
-    isoCodeToWikiName.put("KO", "Korean");
-    isoCodeToWikiName.put("KU", "Kurdish");
-    isoCodeToWikiName.put("LO", "Lao");
-    isoCodeToWikiName.put("MS", "Malay");
-    isoCodeToWikiName.put("ML", "Malayalam");
-    isoCodeToWikiName.put("MI", "Maori");
-    isoCodeToWikiName.put("MN", "Mongolian");
-    isoCodeToWikiName.put("NE", "Nepali");
-    isoCodeToWikiName.put("NO", "Norwegian");
-    isoCodeToWikiName.put("FA", "Persian");
-    isoCodeToWikiName.put("PL", "Polish");
-    isoCodeToWikiName.put("PT", "Portuguese");
-    isoCodeToWikiName.put("PA", "Punjabi");
-    isoCodeToWikiName.put("RO", "Romanian");
-    isoCodeToWikiName.put("RU", "Russian");
-    isoCodeToWikiName.put("SA", "Sanskrit");
-    isoCodeToWikiName.put("SR", "Serbian");
-    isoCodeToWikiName.put("SK", "Slovak");
-    isoCodeToWikiName.put("SL", "Slovene|Slovenian");
-    isoCodeToWikiName.put("SO", "Somali");
-    isoCodeToWikiName.put("ES", "Spanish");
-    isoCodeToWikiName.put("SW", "Swahili");
-    isoCodeToWikiName.put("SV", "Swedish");
-    isoCodeToWikiName.put("TL", "Tagalog");
-    isoCodeToWikiName.put("TG", "Tajik");
-    isoCodeToWikiName.put("TH", "Thai");
-    isoCodeToWikiName.put("BO", "Tibetan");
-    isoCodeToWikiName.put("TR", "Turkish");
-    isoCodeToWikiName.put("UK", "Ukrainian");
-    isoCodeToWikiName.put("UR", "Urdu");
-    isoCodeToWikiName.put("VI", "Vietnamese");
-    isoCodeToWikiName.put("CI", "Welsh");
-    isoCodeToWikiName.put("YI", "Yiddish");
-    isoCodeToWikiName.put("ZU", "Zulu");
+    isoCodeToEnWikiName.put("AF", "Afrikaans");
+    isoCodeToEnWikiName.put("SQ", "Albanian");
+    isoCodeToEnWikiName.put("AR", "Arabic");
+    isoCodeToEnWikiName.put("HY", "Armenian");
+    isoCodeToEnWikiName.put("BE", "Belarusian");
+    isoCodeToEnWikiName.put("BN", "Bengali");
+    isoCodeToEnWikiName.put("BS", "Bosnian");
+    isoCodeToEnWikiName.put("BG", "Bulgarian");
+    isoCodeToEnWikiName.put("CA", "Catalan");
+    isoCodeToEnWikiName.put("HR", "Croatian");
+    isoCodeToEnWikiName.put("CS", "Czech");
+    isoCodeToEnWikiName.put("ZH", "Chinese|Mandarin|Cantonese");
+    isoCodeToEnWikiName.put("DA", "Danish");
+    isoCodeToEnWikiName.put("NL", "Dutch");
+    isoCodeToEnWikiName.put("EN", "English");
+    isoCodeToEnWikiName.put("EO", "Esperanto");
+    isoCodeToEnWikiName.put("ET", "Estonian");
+    isoCodeToEnWikiName.put("FI", "Finnish");
+    isoCodeToEnWikiName.put("FR", "French");
+    isoCodeToEnWikiName.put("DE", "German");
+    isoCodeToEnWikiName.put("EL", "Greek");
+    isoCodeToEnWikiName.put("haw", "Hawaiian");
+    isoCodeToEnWikiName.put("HE", "Hebrew");
+    isoCodeToEnWikiName.put("HI", "Hindi");
+    isoCodeToEnWikiName.put("HU", "Hungarian");
+    isoCodeToEnWikiName.put("IS", "Icelandic");
+    isoCodeToEnWikiName.put("ID", "Indonesian");
+    isoCodeToEnWikiName.put("GA", "Irish");
+    isoCodeToEnWikiName.put("GD", "Gaelic");
+    isoCodeToEnWikiName.put("IT", "Italian");
+    isoCodeToEnWikiName.put("LA", "Latin");
+    isoCodeToEnWikiName.put("LV", "Latvian");
+    isoCodeToEnWikiName.put("LT", "Lithuanian");
+    isoCodeToEnWikiName.put("JA", "Japanese");
+    isoCodeToEnWikiName.put("KO", "Korean");
+    isoCodeToEnWikiName.put("KU", "Kurdish");
+    isoCodeToEnWikiName.put("LO", "Lao");
+    isoCodeToEnWikiName.put("MS", "Malay");
+    isoCodeToEnWikiName.put("ML", "Malayalam");
+    isoCodeToEnWikiName.put("MI", "Maori");
+    isoCodeToEnWikiName.put("MN", "Mongolian");
+    isoCodeToEnWikiName.put("NE", "Nepali");
+    isoCodeToEnWikiName.put("NO", "Norwegian");
+    isoCodeToEnWikiName.put("FA", "Persian");
+    isoCodeToEnWikiName.put("PL", "Polish");
+    isoCodeToEnWikiName.put("PT", "Portuguese");
+    isoCodeToEnWikiName.put("PA", "Punjabi");
+    isoCodeToEnWikiName.put("RO", "Romanian");
+    isoCodeToEnWikiName.put("RU", "Russian");
+    isoCodeToEnWikiName.put("SA", "Sanskrit");
+    isoCodeToEnWikiName.put("SR", "Serbian");
+    isoCodeToEnWikiName.put("SK", "Slovak");
+    isoCodeToEnWikiName.put("SL", "Slovene|Slovenian");
+    isoCodeToEnWikiName.put("SO", "Somali");
+    isoCodeToEnWikiName.put("ES", "Spanish");
+    isoCodeToEnWikiName.put("SW", "Swahili");
+    isoCodeToEnWikiName.put("SV", "Swedish");
+    isoCodeToEnWikiName.put("TL", "Tagalog");
+    isoCodeToEnWikiName.put("TG", "Tajik");
+    isoCodeToEnWikiName.put("TH", "Thai");
+    isoCodeToEnWikiName.put("BO", "Tibetan");
+    isoCodeToEnWikiName.put("TR", "Turkish");
+    isoCodeToEnWikiName.put("UK", "Ukrainian");
+    isoCodeToEnWikiName.put("UR", "Urdu");
+    isoCodeToEnWikiName.put("VI", "Vietnamese");
+    isoCodeToEnWikiName.put("CI", "Welsh");
+    isoCodeToEnWikiName.put("YI", "Yiddish");
+    isoCodeToEnWikiName.put("ZU", "Zulu");
     
-    isoCodeToWikiName.put("AZ", "Azeri");
-    isoCodeToWikiName.put("EU", "Basque");
-    isoCodeToWikiName.put("BR", "Breton");
-    isoCodeToWikiName.put("MR", "Burmese");
-    isoCodeToWikiName.put("FO", "Faroese");
-    isoCodeToWikiName.put("GL", "Galician");
-    isoCodeToWikiName.put("KA", "Georgian");
-    isoCodeToWikiName.put("HT", "Haitian Creole");
-    isoCodeToWikiName.put("LB", "Luxembourgish");
-    isoCodeToWikiName.put("MK", "Macedonian");
+    isoCodeToEnWikiName.put("AZ", "Azeri");
+    isoCodeToEnWikiName.put("EU", "Basque");
+    isoCodeToEnWikiName.put("BR", "Breton");
+    isoCodeToEnWikiName.put("MR", "Burmese");
+    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");
     
   }
 
   public static final Map<String,Map<String,String>> wikiCodeToIsoCodeToWikiName = new LinkedHashMap<String, Map<String,String>>();
   static {
     // en
-    wikiCodeToIsoCodeToWikiName.put("en", isoCodeToWikiName);
+    wikiCodeToIsoCodeToWikiName.put("en", isoCodeToEnWikiName);
     
     Map<String,String> isoCodeToWikiName;