Revision: 7957
          
http://languagetool.svn.sourceforge.net/languagetool/?rev=7957&view=rev
Author:   dnaber
Date:     2012-09-01 23:56:53 +0000 (Sat, 01 Sep 2012)
Log Message:
-----------
wikipedia indexing: print page title during indexing

Modified Paths:
--------------
    
trunk/JLanguageTool/src/dev/org/languagetool/dev/wikipedia/WikipediaIndexHandler.java

Modified: 
trunk/JLanguageTool/src/dev/org/languagetool/dev/wikipedia/WikipediaIndexHandler.java
===================================================================
--- 
trunk/JLanguageTool/src/dev/org/languagetool/dev/wikipedia/WikipediaIndexHandler.java
       2012-09-01 23:43:42 UTC (rev 7956)
+++ 
trunk/JLanguageTool/src/dev/org/languagetool/dev/wikipedia/WikipediaIndexHandler.java
       2012-09-01 23:56:53 UTC (rev 7957)
@@ -59,7 +59,9 @@
   private int end = 0;
 
   private boolean inText = false;
+  private boolean inTitle = false;
   private StringBuilder text = new StringBuilder();
+  private StringBuilder title = new StringBuilder();
   private TextFilter textFilter = new BlikiWikipediaTextFilter();
 
   // ===========================================================
@@ -81,7 +83,7 @@
   public void startElement(String namespaceURI, String lName, String qName, 
Attributes attrs)
       throws SAXException {
     if (qName.equals("title")) {
-      inText = true;
+      inTitle = true;
     } else if (qName.equals("text")) {
       inText = true;
     }
@@ -91,9 +93,10 @@
   @SuppressWarnings("unused")
   public void endElement(String namespaceURI, String sName, String qName) {
     if (qName.equals("title")) {
-      text = new StringBuilder();
+      inTitle = false;
     } else if (qName.equals("text")) {
-      System.out.println(++articleCount);
+      System.out.println(++articleCount + ": " + title);
+      title = new StringBuilder();
       if (articleCount < start) {
         return;
       } else if (articleCount >= end && end != 0) {
@@ -117,6 +120,8 @@
     final String s = new String(buf, offset, len);
     if (inText) {
       text.append(s);
+    } else if (inTitle) {
+      title.append(s);
     }
   }
 

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
Languagetool-cvs@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/languagetool-cvs

Reply via email to