Revision: 7425
          
http://languagetool.svn.sourceforge.net/languagetool/?rev=7425&view=rev
Author:   milek_pl
Date:     2012-06-20 17:09:11 +0000 (Wed, 20 Jun 2012)
Log Message:
-----------
dictionary shrinking: using cfsa2 encoding to make distribution smaller

Modified Paths:
--------------
    trunk/JLanguageTool/src/resource/br/breton.dict
    trunk/JLanguageTool/src/resource/ca/catalan.dict
    trunk/JLanguageTool/src/resource/ca/catalan_synth.dict
    trunk/JLanguageTool/src/resource/de/german.dict
    trunk/JLanguageTool/src/resource/en/english.dict
    trunk/JLanguageTool/src/resource/en/english_synth.dict
    trunk/JLanguageTool/src/resource/gl/galician.dict
    trunk/JLanguageTool/src/resource/gl/galician_synth.dict
    trunk/JLanguageTool/src/resource/nl/dutch.dict
    trunk/JLanguageTool/src/resource/nl/dutch_synth.dict
    trunk/JLanguageTool/src/resource/ru/russian.dict
    trunk/JLanguageTool/src/resource/ru/russian_synth.dict
    trunk/JLanguageTool/src/resource/sk/slovak.dict
    trunk/JLanguageTool/src/resource/sk/slovak_synth.dict
    
trunk/JLanguageTool/src/test/org/languagetool/dev/index/LanguageToolFilterTest.java
    
trunk/JLanguageTool/src/test/org/languagetool/synthesis/en/EnglishSynthesizerTest.java
    
trunk/JLanguageTool/src/test/org/languagetool/tagging/de/GermanTaggerTest.java

Modified: trunk/JLanguageTool/src/resource/br/breton.dict
===================================================================
(Binary files differ)

Modified: trunk/JLanguageTool/src/resource/ca/catalan.dict
===================================================================
(Binary files differ)

Modified: trunk/JLanguageTool/src/resource/ca/catalan_synth.dict
===================================================================
(Binary files differ)

Modified: trunk/JLanguageTool/src/resource/de/german.dict
===================================================================
(Binary files differ)

Modified: trunk/JLanguageTool/src/resource/en/english.dict
===================================================================
(Binary files differ)

Modified: trunk/JLanguageTool/src/resource/en/english_synth.dict
===================================================================
(Binary files differ)

Modified: trunk/JLanguageTool/src/resource/gl/galician.dict
===================================================================
(Binary files differ)

Modified: trunk/JLanguageTool/src/resource/gl/galician_synth.dict
===================================================================
(Binary files differ)

Modified: trunk/JLanguageTool/src/resource/nl/dutch.dict
===================================================================
(Binary files differ)

Modified: trunk/JLanguageTool/src/resource/nl/dutch_synth.dict
===================================================================
(Binary files differ)

Modified: trunk/JLanguageTool/src/resource/ru/russian.dict
===================================================================
(Binary files differ)

Modified: trunk/JLanguageTool/src/resource/ru/russian_synth.dict
===================================================================
(Binary files differ)

Modified: trunk/JLanguageTool/src/resource/sk/slovak.dict
===================================================================
(Binary files differ)

Modified: trunk/JLanguageTool/src/resource/sk/slovak_synth.dict
===================================================================
(Binary files differ)

Modified: 
trunk/JLanguageTool/src/test/org/languagetool/dev/index/LanguageToolFilterTest.java
===================================================================
--- 
trunk/JLanguageTool/src/test/org/languagetool/dev/index/LanguageToolFilterTest.java
 2012-06-20 15:33:49 UTC (rev 7424)
+++ 
trunk/JLanguageTool/src/test/org/languagetool/dev/index/LanguageToolFilterTest.java
 2012-06-20 17:09:11 UTC (rev 7425)
@@ -44,7 +44,7 @@
     filter = new LanguageToolFilter(stream, new 
JLanguageTool(Language.ENGLISH));
 
     assertTokenStreamContents(filter, new String[] { "_POS_SENT_START", "How", 
"_POS_WRB", "do",
-        "_POS_VBP", "_POS_VB", "you", "_POS_PRP", "thin", "_POS_JJ", 
"_POS_VBP", "_POS_VB", "?",
+        "_POS_VBP", "_POS_VB", "you", "_POS_PRP", "thin", "_POS_VBP", 
"_POS_VB", "_POS_JJ", "?",
         "_POS_SENT_END" }, new int[] { 0, 0, 0, 4, 4, 4, 7, 7, 11, 11, 11, 11, 
15, 15 }, new int[] {
         0, 3, 3, 6, 6, 6, 10, 10, 15, 15, 15, 15, 16, 16 }, new String[] { 
"pos", "word", "pos",
         "word", "pos", "pos", "word", "pos", "word", "pos", "pos", "pos", 
"word", "pos" },

Modified: 
trunk/JLanguageTool/src/test/org/languagetool/synthesis/en/EnglishSynthesizerTest.java
===================================================================
--- 
trunk/JLanguageTool/src/test/org/languagetool/synthesis/en/EnglishSynthesizerTest.java
      2012-06-20 15:33:49 UTC (rev 7424)
+++ 
trunk/JLanguageTool/src/test/org/languagetool/synthesis/en/EnglishSynthesizerTest.java
      2012-06-20 17:09:11 UTC (rev 7425)
@@ -34,8 +34,8 @@
     EnglishSynthesizer synth = new EnglishSynthesizer();
     assertEquals(synth.synthesize(dummyToken("blablabla"), 
         "blablabla").length, 0);
-    
-    assertEquals("[were, was]", 
Arrays.toString(synth.synthesize(dummyToken("be"), "VBD")));
+        
+    assertEquals("[was, were]", 
Arrays.toString(synth.synthesize(dummyToken("be"), "VBD")));
     assertEquals("[presidents]", 
Arrays.toString(synth.synthesize(dummyToken("president"), "NNS")));
     assertEquals("[tested]", 
Arrays.toString(synth.synthesize(dummyToken("test"), "VBD")));
     assertEquals("[tested]", 
Arrays.toString(synth.synthesize(dummyToken("test"), "VBD", false)));

Modified: 
trunk/JLanguageTool/src/test/org/languagetool/tagging/de/GermanTaggerTest.java
===================================================================
--- 
trunk/JLanguageTool/src/test/org/languagetool/tagging/de/GermanTaggerTest.java  
    2012-06-20 15:33:49 UTC (rev 7424)
+++ 
trunk/JLanguageTool/src/test/org/languagetool/tagging/de/GermanTaggerTest.java  
    2012-06-20 17:09:11 UTC (rev 7425)
@@ -149,8 +149,8 @@
     upperCaseWord.add("Das");
 
     List<AnalyzedTokenReadings> readings = tagger.tag(upperCaseWord);
-    assertEquals("[Das[der/PRO:PER:NOM:SIN:NEU, der/PRO:PER:AKK:SIN:NEU, 
der/PRO:DEM:NOM:SIN:NEU, " +
-            "der/PRO:DEM:AKK:SIN:NEU, der/ART:DEF:NOM:SIN:NEU, 
der/ART:DEF:AKK:SIN:NEU]]", readings.toString());
+    assertEquals("[Das[der/ART:DEF:AKK:SIN:NEU, der/ART:DEF:NOM:SIN:NEU, " +
+               "der/PRO:DEM:AKK:SIN:NEU, der/PRO:DEM:NOM:SIN:NEU, 
der/PRO:PER:AKK:SIN:NEU, der/PRO:PER:NOM:SIN:NEU]]", readings.toString());
     
     readings = tagger.tag(upperCaseWord, false);
     assertEquals("[Das[null/null]]", readings.toString());
@@ -160,8 +160,8 @@
     // words not originally in Morphy but added in LT 1.8 (moved from 
added.txt to german.dict)
     final GermanTagger tagger = new GermanTagger();
     final List<AnalyzedTokenReadings> readings = 
tagger.tag(Collections.singletonList("Wichtigtuerinnen"));
-    assertEquals("[Wichtigtuerinnen[Wichtigtuerin/SUB:NOM:PLU:FEM, 
Wichtigtuerin/SUB:GEN:PLU:FEM, " +
-            "Wichtigtuerin/SUB:DAT:PLU:FEM, Wichtigtuerin/SUB:AKK:PLU:FEM]]", 
readings.toString());
+    assertEquals("[Wichtigtuerinnen[Wichtigtuerin/SUB:AKK:PLU:FEM, " +
+               "Wichtigtuerin/SUB:DAT:PLU:FEM, Wichtigtuerin/SUB:GEN:PLU:FEM, 
Wichtigtuerin/SUB:NOM:PLU:FEM]]", readings.toString());
   }
 
   public void testDictionary() throws IOException {

This was sent by the SourceForge.net collaborative development platform, the 
world's largest Open Source development site.


------------------------------------------------------------------------------
Live Security Virtual Conference
Exclusive live event will cover all the ways today's security and 
threat landscape has changed and how IT managers can respond. Discussions 
will include endpoint security, mobile security and the latest in malware 
threats. http://www.accelacomm.com/jaw/sfrnl04242012/114/50122263/
_______________________________________________
Languagetool-cvs mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/languagetool-cvs

Reply via email to