Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/.DS_Store has changed

--- a/software/mpdl-services/mpiwg-mpdl-lt/build/classes/constants.properties	Wed Nov 09 15:32:05 2011 +0100
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,1 +0,0 @@
-dataDir=/Users/jwillenborg/mpdl/data/lt
\ No newline at end of file

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/exception/ApplicationException.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/dict/app/Lexica.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/dict/app/Lexicon.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/dict/app/LexiconEntry.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/dict/db/DBLexWriter.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/dict/db/DbEnvLex.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/dict/db/LexEntryContentHandler.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/dict/db/LexEntryErrorHandler.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/dict/db/LexHandler.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/general/Betacode2UnicodeLex.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/general/Buckwalter2UnicodeLex.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/general/Constants.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/general/Language.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/general/Transcoder.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/general/Unicode2BetacodeLex.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/general/Unicode2BuckwalterLex.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/morph/app/Form.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/morph/app/Lemma.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/morph/app/MorphFileReaderContentHandler$Element.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/morph/app/MorphFileReaderContentHandler.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/morph/app/MorphologyCache.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/morph/app/SimpleMorphContentHandler$Element.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/morph/app/SimpleMorphContentHandler.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/morph/db/DBMorphHandler.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/morph/db/DBMorphSupWriter.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/morph/db/DBMorphWriter.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/morph/db/DBMorphWriterContentHandler$Element.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/morph/db/DBMorphWriterContentHandler.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/morph/db/DbEnvMorph.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/morph/db/DbEnvMorphSup.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/text/norm/MpdlNormalizer.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/text/norm/Normalizer.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/text/norm/lang/MpdlNormalizerLexAR.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/text/norm/lang/MpdlNormalizerLexDE.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/text/norm/lang/MpdlNormalizerLexEL.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/text/norm/lang/MpdlNormalizerLexEN.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/text/norm/lang/MpdlNormalizerLexFR.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/text/norm/lang/MpdlNormalizerLexIT.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/text/norm/lang/MpdlNormalizerLexLA.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/text/norm/lang/MpdlNormalizerLexNL.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/text/norm/lang/MpdlNormalizerLexZH.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/text/reg/DBRegularizationHandler.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/text/reg/DbEnvRegularization.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/text/reg/Regularization.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/text/reg/RegularizationManager.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/text/tokenize/ChineseTokenizer.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/text/tokenize/Token.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/text/tokenize/Tokenizer.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/text/tokenize/XmlTokenizer.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/text/tokenize/XmlTokenizerContentHandler$1.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/text/tokenize/XmlTokenizerContentHandler$Element.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/text/tokenize/XmlTokenizerContentHandler.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/text/transcode/Betacode2UnicodeLex.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/text/transcode/Buckwalter2UnicodeLex.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/text/transcode/Transcoder.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/text/transcode/Unicode2BetacodeLex.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lt/text/transcode/Unicode2BuckwalterLex.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/lucene/util/LuceneUtil.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/test/TestLocal.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/util/FileUtil.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/util/LuceneUtil.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/util/StringUtilEscapeChars.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/util/StringUtils.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/util/Util.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/util/XmlUtil$1.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/build/classes/de/mpg/mpiwg/berlin/mpdl/util/XmlUtil.class has changed

Binary file software/mpdl-services/mpiwg-mpdl-lt/dist/mpiwg-mpdl-lt.jar has changed

--- a/software/mpdl-services/mpiwg-mpdl-lt/src/de/mpg/mpiwg/berlin/mpdl/lt/dict/app/Lexicon.java	Wed Nov 09 15:32:05 2011 +0100
+++ b/software/mpdl-services/mpiwg-mpdl-lt/src/de/mpg/mpiwg/berlin/mpdl/lt/dict/app/Lexicon.java	Wed Dec 14 12:48:43 2011 +0100
@@ -140,6 +140,14 @@
     }
   }
 
+  public LexiconEntry getEntry(String lexEntryName) {
+    LexiconEntry retEntry = null;
+    if (entries == null) {
+      entries.get(lexEntryName);  
+    }
+    return retEntry;
+  }
+
   /*
    * without lexicon entries (non-Javadoc)
    * @see java.lang.Object#clone()
@@ -157,6 +165,7 @@
     String result = "";
     result = result + "<dictionary>";
     result = result + "<name>" + name + "</name>";
+    result = result + "<language>" + sourceLang + "</language>";
     result = result + "<description>" + description + "</description>";
     result = result + "<entries>";
     for (int i=0; i<entries.size(); i++) {
@@ -195,4 +204,21 @@
     return result;
   }
 
+  public String toXmlStringCompact() {
+    String result = "";
+    result = result + "<dictionary>";
+    result = result + "<name>" + name + "</name>";
+    result = result + "<language>" + sourceLang + "</language>";
+    result = result + "<description>" + description + "</description>";
+    result = result + "<entries>";
+    for (int i=0; i<entries.size(); i++) {
+      result = result + "<entry>";
+      LexiconEntry entry = getEntries().get(i);
+      result = result + "<form>" + entry.getFormName() + "</form>";
+      result = result + "</entry>";
+    }
+    result = result + "</entries>";
+    result = result + "</dictionary>";
+    return result;
+  }
 }

--- a/software/mpdl-services/mpiwg-mpdl-lt/src/de/mpg/mpiwg/berlin/mpdl/lt/dict/db/LexHandler.java	Wed Nov 09 15:32:05 2011 +0100
+++ b/software/mpdl-services/mpiwg-mpdl-lt/src/de/mpg/mpiwg/berlin/mpdl/lt/dict/db/LexHandler.java	Wed Dec 14 12:48:43 2011 +0100
@@ -60,7 +60,7 @@
    * @return lemmas
    * @throws ApplicationException
    */
-  public ArrayList<Lemma> getLemmas(String query, String type, String language, String normalization) throws ApplicationException {
+  public ArrayList<Lemma> getLemmas(String query, String type, String language, int normMode) throws ApplicationException {
     ArrayList<Lemma> lexLemmas = new ArrayList<Lemma>();
     // get lemmas of all forms in query
     MorphologyCache morphologyCache = MorphologyCache.getInstance();
@@ -69,21 +69,10 @@
       String queryForm = queryForms[k];
       ArrayList<Lemma> lemmas = null;
       if (type.equals("form")) {
-        if (normalization.equals("norm"))
-          lemmas = morphologyCache.getLemmasByFormName(language, queryForm, true);
-        else if (normalization.equals("none"))
-          lemmas = morphologyCache.getLemmasByFormName(language, queryForm, false);
-        else 
-          lemmas = morphologyCache.getLemmasByFormName(language, queryForm, true);  // TODO reg and reg+norm
+        lemmas = morphologyCache.getLemmasByFormName(language, queryForm, normMode);
       } else if (type.equals("lemma")) {
         lemmas = new ArrayList<Lemma>();
-        Lemma l = null;
-        if (normalization.equals("norm"))
-          l = morphologyCache.getLemma(language, queryForm, true);
-        else if (normalization.equals("none"))
-          l = morphologyCache.getLemma(language, queryForm, false);
-        else 
-          l = morphologyCache.getLemma(language, queryForm, true);
+        Lemma l = morphologyCache.getLemma(language, queryForm, normMode);
         if (l != null)
           lemmas.add(l);
       }
@@ -101,7 +90,7 @@
       return lexLemmas;
   }
 
-  public ArrayList<Lexicon> getLexEntries(ArrayList<Lemma> lexLemmas, String language, String lexiconName) throws ApplicationException {
+  public ArrayList<Lexicon> getLexEntries(ArrayList<Lemma> lexLemmas, String language, String lexiconName, String query) throws ApplicationException {
     ArrayList<Lexicon> retLexicons = new ArrayList<Lexicon>();
     ArrayList<Lexicon> lexicons = Lexica.getInstance().getLexicons(language);
     if (lexiconName != null) {
@@ -115,19 +104,25 @@
         Lexicon lexicon = lexicons.get(i).clone(); // clone without lexicon entries
         for (int j=0; j<lexLemmas.size(); j++) {
           String lemmaName = lexLemmas.get(j).getLemmaName();
-          if (Language.getInstance().isGerman(language) && lemmaName.contains("ae"))
-            lemmaName = lemmaName.replaceAll("ae", "Š");
-          if (Language.getInstance().isGerman(language) && lemmaName.contains("oe"))
-            lemmaName = lemmaName.replaceAll("oe", "š");
-          if (Language.getInstance().isGerman(language) && lemmaName.contains("ue"))
-            lemmaName = lemmaName.replaceAll("ue", "Ÿ");
-          if (Language.getInstance().isGerman(language) && lemmaName.contains("ss"))
-            lemmaName = lemmaName.replaceAll("ss", "§");
           LexiconEntry lexEntry = getEntry(lexicon, lemmaName);
           if (lexEntry != null) {
             lexicon.addEntry(lexEntry); // add entries to the cloned lexicon
           }
         }
+        if (Language.getInstance().isGerman(language) && query != null) {
+          String[] lexFormNames = query.split(" ");
+          for (int j=0; j<lexFormNames.length; j++) {
+            String lexFormName = lexFormNames[j];          
+            LexiconEntry lexEntry = lexicon.getEntry(lexFormName);
+            if (lexEntry == null) {
+              LexiconEntry newLexEntry = new LexiconEntry(lexiconName, lexFormName, null);
+              String lexiconQueryUrl = lexicon.getQueryUrl();
+              String remoteUrl = lexiconQueryUrl + lexFormName;
+              newLexEntry.setRemoteUrl(remoteUrl);
+              lexicon.addEntry(newLexEntry);
+            }
+          }
+        }
         if (! lexicon.isEmpty())
           retLexicons.add(lexicon);
       }
@@ -143,10 +138,10 @@
    * @return delivers lexical entries by the help of the morphology component (lexical entry of the stem of the normalized word form)
    * @throws ApplicationException
    */
-  public ArrayList<String> getLexEntryKeys(String formName, String language, boolean normalize) throws ApplicationException {
+  public ArrayList<String> getLexEntryKeys(String formName, String language, int normMode) throws ApplicationException {
     ArrayList<String> lexEntryKeys = new ArrayList<String>();
     MorphologyCache morphologyCache = MorphologyCache.getInstance();
-    ArrayList<Lemma> formLemmas = morphologyCache.getLemmasByFormName(language, formName, normalize);
+    ArrayList<Lemma> formLemmas = morphologyCache.getLemmasByFormName(language, formName, normMode);
     boolean hasLexEntry = false;
     hasLexEntry = hasLexEntryKey(formName, language);
     if (hasLexEntry)
@@ -158,7 +153,7 @@
         if (! hasLexEntry) {
           hasLexEntry = hasLexEntryKey(lName, language);
         }
-        if (language.equals("de") || language.equals("fr") || language.equals("nl"))   // TODO Lexika fŸr diese Sprachen in BerkeleyDB einbringen (fŸr nl auch eine bessere Morph.)
+        if (language.equals("de") || language.equals("fr") || language.equals("nl"))   // TODO Lexika für diese Sprachen in BerkeleyDB einbringen (für nl auch eine bessere Morph.)
           lexEntryKeys.add(lName);
         if (! lName.equals(formName) && hasLexEntry) {
           lexEntryKeys.add(lName);
@@ -188,8 +183,7 @@
     return hasLexEntry;
   }
   
-  public ArrayList<Lexicon> getLexEntriesBeginningWith(String language, String formPrefix, int pageNumber) throws ApplicationException {
-    int pageSize = 50;
+  public ArrayList<Lexicon> getLexEntriesBeginningWith(String language, String formPrefix, int pageNumber, int pageSize) throws ApplicationException {
     int from = (pageNumber * pageSize) - pageSize + 1;
     int to = pageNumber * pageSize;
     ArrayList<Lexicon> statLexicons = Lexica.getInstance().getLocalLexicons(language);
@@ -211,8 +205,7 @@
     return retLexicons;
   }
   
-  public ArrayList<Lexicon> getLexEntriesByLexiconBeginningWith(String lexiconName, String formPrefix, int pageNumber) throws ApplicationException {
-    int pageSize = 50;
+  public ArrayList<Lexicon> getLexEntriesByLexiconBeginningWith(String lexiconName, String formPrefix, int pageNumber, int pageSize) throws ApplicationException {
     int from = (pageNumber * pageSize) - pageSize + 1;
     int to = pageNumber * pageSize;
     Lexicon lexicon = Lexica.getInstance().getLexicon(lexiconName).clone();
@@ -265,6 +258,7 @@
       cursor.close();
       if (dbFoundValueStr != null) {
         retLexEntry = new LexiconEntry(lexiconName, formName, dbFoundValueStr);
+        retLexEntry = correct(retLexEntry);  // correct errors: e.g. in lsj some html entities are not correct
       }
     } catch (DatabaseException e) {
       throw new ApplicationException(e);
@@ -292,6 +286,7 @@
           byte[] foundKeyBytes = dbEntryKey.getData();
           String dbFoundKeyStr = new String(foundKeyBytes, "utf-8");
           LexiconEntry lexEntry = new LexiconEntry(lexiconName, dbFoundKeyStr, dbFoundValueStr);
+          lexEntry = correct(lexEntry);  // correct errors: e.g. in lsj some html entities are not correct
           retLexEntries.add(lexEntry);
         }
         operationStatus = cursor.getNext(dbEntryKey, foundValue, LockMode.DEFAULT);
@@ -309,6 +304,17 @@
     return retLexEntries;
   }
 
+  private LexiconEntry correct(LexiconEntry lexEntry) {
+    String lexiconName = lexEntry.getLexiconName();
+    String content = lexEntry.getContent();
+    if (content != null && content.contains("&#") && lexiconName.equals("lsj")) {  // errors in greek lexicon lsj
+      content = content.replaceAll("&#\u03C7", "&#x"); // html entity: replace greek Minuskel Chi by "x"
+      content = content.replaceAll("&#x[^0-9]{4};", ""); // html entity: remove entity if special greek not hex characters appear
+      lexEntry.setContent(content);
+    }
+    return lexEntry;
+  }
+
   public static void main(String[] args) throws ApplicationException {
     getInstance();
     instance.beginOperation();

--- a/software/mpdl-services/mpiwg-mpdl-lt/src/de/mpg/mpiwg/berlin/mpdl/lt/general/Language.java	Wed Nov 09 15:32:05 2011 +0100
+++ b/software/mpdl-services/mpiwg-mpdl-lt/src/de/mpg/mpiwg/berlin/mpdl/lt/general/Language.java	Wed Dec 14 12:48:43 2011 +0100
@@ -169,4 +169,46 @@
     else 
       return false;
   }
+  
+  public String getHtmlSelectBox(String language) {
+    String result = "<select name=\"language\">";
+    if (isArabic(language))
+      result = result + "<option value =\"ara\" selected=\"true\">Arabic</option>";
+    else
+      result = result + "<option value =\"ara\">Arabic</option>";
+    if (isChinese(language))
+      result = result + "<option value =\"zho\" selected=\"true\">Chinese</option>";
+    else
+      result = result + "<option value =\"zho\">Chinese</option>";
+    if (isDutch(language))
+      result = result + "<option value =\"nld\" selected=\"true\">Dutch</option>";
+    else
+      result = result + "<option value =\"nld\">Dutch</option>";
+    if (isEnglish(language))
+      result = result + "<option value =\"eng\" selected=\"true\">English</option>";
+    else
+      result = result + "<option value =\"eng\">English</option>";
+    if (isFrench(language))
+      result = result + "<option value =\"fra\" selected=\"true\">French</option>";
+    else
+      result = result + "<option value =\"fra\">French</option>";
+    if (isGerman(language))
+      result = result + "<option value =\"ger\" selected=\"true\">German</option>";
+    else
+      result = result + "<option value =\"ger\">German</option>";
+    if (isGreek(language))
+      result = result + "<option value =\"grc\" selected=\"true\">Greek</option>";
+    else
+      result = result + "<option value =\"grc\">Greek</option>";
+    if (isItalian(language))
+      result = result + "<option value =\"ita\" selected=\"true\">Italian</option>";
+    else
+      result = result + "<option value =\"ita\">Italian</option>";
+    if (isLatin(language))
+      result = result + "<option value =\"lat\" selected=\"true\">Latin</option>";
+    else
+      result = result + "<option value =\"lat\">Latin</option>";
+    result = result + "</select>";
+    return result;
+  }
 }
\ No newline at end of file

--- a/software/mpdl-services/mpiwg-mpdl-lt/src/de/mpg/mpiwg/berlin/mpdl/lt/morph/app/MorphologyCache.java	Wed Nov 09 15:32:05 2011 +0100
+++ b/software/mpdl-services/mpiwg-mpdl-lt/src/de/mpg/mpiwg/berlin/mpdl/lt/morph/app/MorphologyCache.java	Wed Dec 14 12:48:43 2011 +0100
@@ -64,14 +64,19 @@
     LOGGER.info("Morphology db cache: closed");
   }
 
-  public ArrayList<Lemma> getLemmasByFormName(String lang, String formNameArg, boolean normalize) throws ApplicationException {
+  /*
+  public ArrayList<Lemma> getLemmasByFormName(String lang, String formName, boolean normalize) throws ApplicationException {
+    return getLemmasByFormName(lang, formName, normalize, Normalizer.DISPLAY);
+  }
+  */
+  
+  public ArrayList<Lemma> getLemmasByFormName(String lang, String formNameArg, int normMode) throws ApplicationException {
     String language = Language.getInstance().getLanguageId(lang);
     ArrayList<Lemma> retFormLemmas = null;
     String formName = formNameArg;
-    if (normalize) {
-      Normalizer normalizer = new Normalizer(language);
-      formName = normalizer.normalize(formNameArg);
-    }
+    Normalizer normalizer = new Normalizer(language);
+    normalizer.setNormMode(normMode);
+    formName = normalizer.normalize(formNameArg);
     // first look in local cache
     String key = language + "###" + formName;
     Hashtable<String, Lemma> formLemmasHashtable = forms.get(key);
@@ -114,13 +119,12 @@
     return retFormLemmas;
   }
   
-  public Lemma getLemma(String lang, String lemmaNameArg, boolean normalize) throws ApplicationException {
+  public Lemma getLemma(String lang, String lemmaNameArg, int normMode) throws ApplicationException {
     String language = Language.getInstance().getLanguageId(lang);
     String lemmaName = lemmaNameArg;
-    if (normalize) {
-      Normalizer normalizer = new Normalizer(language);
-      lemmaName = normalizer.normalize(lemmaNameArg);
-    }
+    Normalizer normalizer = new Normalizer(language);
+    normalizer.setNormMode(normMode);
+    lemmaName = normalizer.normalize(lemmaNameArg);
     // first look in local cache
     String key = language + "###" + lemmaName;
     Lemma lemma = lemmas.get(key);
@@ -138,7 +142,7 @@
     return lemma;
   }
   
-  public ArrayList<Form> getFormsByLuceneQuery(String lang, String luceneQueryString, boolean normalize) throws ApplicationException {
+  public ArrayList<Form> getFormsByLuceneQuery(String lang, String luceneQueryString, int normMode) throws ApplicationException {
     String language = Language.getInstance().getLanguageId(lang);
     ArrayList<Form> result = new ArrayList<Form>();
     luceneQueryString = luceneQueryString.toLowerCase();
@@ -146,19 +150,18 @@
     if (! (formsFromQuery == null || formsFromQuery.isEmpty())) {
       for (int i=0; i<formsFromQuery.size(); i++) {
         String formStr = formsFromQuery.get(i);
-        if (normalize) {
-          Normalizer normalizer = new Normalizer(language);
-          formStr = normalizer.normalize(formStr);
-        }
+        Normalizer normalizer = new Normalizer(language);
+        normalizer.setNormMode(normMode);
+        formStr = normalizer.normalize(formStr);
         ArrayList<Lemma> formLemmas = null;
         // lemma mode: if formName contains "lemmalemma" then the lemma itself is fetched
         if (formStr.startsWith("lemmalemma")) {
           formLemmas = new ArrayList<Lemma>();
           String lemmaName = formStr.substring(10);
-          Lemma lemma = getLemma(language, lemmaName, false);
+          Lemma lemma = getLemma(language, lemmaName, Normalizer.NONE);
           formLemmas.add(lemma);
         } else {
-          formLemmas = getLemmasByFormName(language, formStr, false);
+          formLemmas = getLemmasByFormName(language, formStr, normMode);
         }
         if (formLemmas != null && ! formLemmas.isEmpty()) {
           for (int j=0; j<formLemmas.size(); j++) {
@@ -172,7 +175,7 @@
     return result;
   }
 
-  public ArrayList<Lemma> getLemmasByLuceneQuery(String lang, String luceneQueryString, boolean normalize) throws ApplicationException {
+  public ArrayList<Lemma> getLemmasByLuceneQuery(String lang, String luceneQueryString, int normMode) throws ApplicationException {
     String language = Language.getInstance().getLanguageId(lang);
     Hashtable<String, Lemma> lemmas = new Hashtable<String, Lemma>();
     luceneQueryString = luceneQueryString.toLowerCase();
@@ -180,19 +183,18 @@
     if (! (formsFromQuery == null || formsFromQuery.isEmpty())) {
       for (int i=0; i<formsFromQuery.size(); i++) {
         String formStr = formsFromQuery.get(i);
-        if (normalize) {
-          Normalizer normalizer = new Normalizer(language);
-          formStr = normalizer.normalize(formStr);
-        }
+        Normalizer normalizer = new Normalizer(language);
+        normalizer.setNormMode(normMode);
+        formStr = normalizer.normalize(formStr);
         ArrayList<Lemma> formLemmas = null;
         // lemma mode: if formName starts with "lemmalemma" then the lemma itself is fetched
         if (formStr.startsWith("lemmalemma")) {
           formLemmas = new ArrayList<Lemma>();
           String lemmaName = formStr.substring(10);
-          Lemma lemma = getLemma(language, lemmaName, false);
+          Lemma lemma = getLemma(language, lemmaName, Normalizer.NONE);
           formLemmas.add(lemma);
         } else {
-          formLemmas = getLemmasByFormName(language, formStr, false);
+          formLemmas = getLemmasByFormName(language, formStr, normMode);
         }
         if (formLemmas != null) {
           for (int j=0; j<formLemmas.size(); j++) {
@@ -223,13 +225,13 @@
     Hashtable<String, String> indexKeys = new Hashtable<String, String>();
     for (int j=0; j<lemmaNames.size(); j++) {
       String lemmaName = lemmaNames.get(j);
-      Lemma lemma = getLemma(language, lemmaName, false);
+      Lemma lemma = getLemma(language, lemmaName, Normalizer.NONE);
       indexKeys.put(lemmaName, lemmaName);
       if (lemma != null) {
         ArrayList<Form> lemmaForms = lemma.getFormsList();
         for (int k=0; k<lemmaForms.size(); k++) {
           Form form = lemmaForms.get(k);
-          ArrayList<Lemma> fLemmas = getLemmasByFormName(language, form.getFormName(), false);
+          ArrayList<Lemma> fLemmas = getLemmasByFormName(language, form.getFormName(), Normalizer.NONE);
           if (fLemmas != null) {
             String indexKey = "";
             if (fLemmas.size() == 1) {

--- a/software/mpdl-services/mpiwg-mpdl-lt/src/de/mpg/mpiwg/berlin/mpdl/lt/text/norm/Normalizer.java	Wed Nov 09 15:32:05 2011 +0100
+++ b/software/mpdl-services/mpiwg-mpdl-lt/src/de/mpg/mpiwg/berlin/mpdl/lt/text/norm/Normalizer.java	Wed Dec 14 12:48:43 2011 +0100
@@ -19,6 +19,7 @@
 import de.mpg.mpiwg.berlin.mpdl.lt.text.reg.RegularizationManager;
 
 public class Normalizer {
+  public static int NONE = -1;  // no normalization
   public static int DISPLAY = 1;  // normalization in DISPLAY mode
   public static int DICTIONARY = 2;  // normalization in DICTIONARY mode
   public static int SEARCH = 3;  // normalization in SEARCH mode; never used so far in indexing because it does not support the morph. lexicons such as CELEX (e.g. eingeschränkt would not be stemmed to eingeschraenkt) 

--- a/software/mpdl-services/mpiwg-mpdl-lt/src/de/mpg/mpiwg/berlin/mpdl/lt/text/tokenize/XmlTokenizerContentHandler.java	Wed Nov 09 15:32:05 2011 +0100
+++ b/software/mpdl-services/mpiwg-mpdl-lt/src/de/mpg/mpiwg/berlin/mpdl/lt/text/tokenize/XmlTokenizerContentHandler.java	Wed Dec 14 12:48:43 2011 +0100
@@ -12,6 +12,7 @@
 import de.mpg.mpiwg.berlin.mpdl.lt.general.Language;
 import de.mpg.mpiwg.berlin.mpdl.lt.morph.app.Form;
 import de.mpg.mpiwg.berlin.mpdl.lt.morph.app.Lemma;
+import de.mpg.mpiwg.berlin.mpdl.lt.text.norm.Normalizer;
 import de.mpg.mpiwg.berlin.mpdl.util.StringUtils;
 
 public class XmlTokenizerContentHandler implements ContentHandler {
@@ -329,7 +330,7 @@
       ArrayList<Lemma> lemmas = null;
       if (withForms() || withLemmas()) {
         LexHandler lexHandler = LexHandler.getInstance();
-        lemmas = lexHandler.getLemmas(wordForm, "form", language, "none");
+        lemmas = lexHandler.getLemmas(wordForm, "form", language, Normalizer.NONE);
       }
       wordTag = insertWordTags(origWordFormDeresolved, wordForm, language, null, lemmas);
       return wordTag;

--- a/software/mpdl-services/mpiwg-mpdl-lt/src/de/mpg/mpiwg/berlin/mpdl/test/TestLocal.java	Wed Nov 09 15:32:05 2011 +0100
+++ b/software/mpdl-services/mpiwg-mpdl-lt/src/de/mpg/mpiwg/berlin/mpdl/test/TestLocal.java	Wed Dec 14 12:48:43 2011 +0100
@@ -16,6 +16,7 @@
 import de.mpg.mpiwg.berlin.mpdl.lt.dict.app.LexiconEntry;
 import de.mpg.mpiwg.berlin.mpdl.lt.dict.db.LexHandler;
 import de.mpg.mpiwg.berlin.mpdl.lt.morph.app.Lemma;
+import de.mpg.mpiwg.berlin.mpdl.lt.text.norm.Normalizer;
 import de.mpg.mpiwg.berlin.mpdl.lt.text.tokenize.Token;
 import de.mpg.mpiwg.berlin.mpdl.lt.text.tokenize.Tokenizer;
 import de.mpg.mpiwg.berlin.mpdl.lt.text.tokenize.XmlTokenizer;
@@ -27,10 +28,10 @@
     try {
       TestLocal test = new TestLocal();
       test.init();
-      // test.testCalls();
+      test.testCalls();
       // test.tokenizeString();
       // test.tokenizeXmlFragment();
-      test.getLexEntriesByLexiconBeginningWith("ls", "a");
+      // test.getLexEntriesByLexiconBeginningWith("ls", "a");
       // test.end();
     } catch (Exception e) {
       e.printStackTrace();
@@ -93,21 +94,21 @@
   }
   
   private void testCalls() throws ApplicationException {
-    String query = "sum quibus";
-    String language = "lat";
+    String query = "vergewissernd";
+    String language = "deu";
     // String query = "ἱκανῶσ";
     // String language = "el";
     String inputType = "form";
     String outputType = null;
     String outputFormat = "html";
     String dictionaryName = null;
-    String normalization = "norm";
-    getLexEntries(query, language, inputType, outputType, outputFormat, dictionaryName, normalization);
+    int normMode = Normalizer.DICTIONARY;
+    getLexEntries(query, language, inputType, outputType, outputFormat, dictionaryName, normMode);
   }
 
-  private void getLexEntries(String query, String language, String inputType , String outputType, String outputFormat, String dictionaryName, String normalization) throws ApplicationException {
-    ArrayList<Lemma> lemmas = lexHandler.getLemmas(query, inputType, language, normalization);
-    ArrayList<Lexicon> dictionaries = lexHandler.getLexEntries(lemmas, language, dictionaryName);
+  private void getLexEntries(String query, String language, String inputType , String outputType, String outputFormat, String dictionaryName, int normMode) throws ApplicationException {
+    ArrayList<Lemma> lemmas = lexHandler.getLemmas(query, inputType, language, normMode);
+    ArrayList<Lexicon> dictionaries = lexHandler.getLexEntries(lemmas, language, dictionaryName, query);
     // String result = lexHandler.getLexEntries(query, language, inputType, outputType, outputFormat, dictionaryName, normalization);
     String result = "";
     result = result + "<dictionaries>";
@@ -120,12 +121,12 @@
   }
   
   private void getLexEntriesByLexiconBeginningWith(String lexiconName, String prefix) throws ApplicationException {
-    ArrayList<Lexicon> lexEntries = lexHandler.getLexEntriesByLexiconBeginningWith(lexiconName, prefix, 1);
+    ArrayList<Lexicon> lexEntries = lexHandler.getLexEntriesByLexiconBeginningWith(lexiconName, prefix, 1, 50);
     System.out.println(lexEntries);
   }
 
   private void getLexEntriesBeginningWith(String language, String prefix) throws ApplicationException {
-    ArrayList<Lexicon> lexEntries = lexHandler.getLexEntriesBeginningWith(language, prefix, 1);
+    ArrayList<Lexicon> lexEntries = lexHandler.getLexEntriesBeginningWith(language, prefix, 1, 50);
     System.out.println(lexEntries);
   }
 }