/[Apache-SVN]/lucene/nutch/trunk/src/plugin/parse-pdf/src/java/org/apache/nutch/parse/pdf/PdfParser.java
ViewVC logotype

Diff of /lucene/nutch/trunk/src/plugin/parse-pdf/src/java/org/apache/nutch/parse/pdf/PdfParser.java

Parent Directory Parent Directory | Revision Log Revision Log | View Patch Patch

--- lucene/nutch/trunk/src/plugin/parse-pdf/src/java/org/apache/nutch/parse/pdf/PdfParser.java	2005/08/19 21:12:51	233558
+++ lucene/nutch/trunk/src/plugin/parse-pdf/src/java/org/apache/nutch/parse/pdf/PdfParser.java	2005/08/19 21:15:02	233559
@@ -33,6 +33,7 @@ import org.apache.nutch.parse.Parse;
 import org.apache.nutch.parse.ParseData;
 import org.apache.nutch.parse.ParseImpl;
 import org.apache.nutch.parse.Outlink;
+import org.apache.nutch.parse.OutlinkExtractor;
 import org.apache.nutch.parse.ParseException;
 
 import java.text.SimpleDateFormat;
@@ -161,7 +162,7 @@ public class PdfParser implements Parser
       title = "";
 
     // collect outlink
-    Outlink[] outlinks = new Outlink[0];
+    Outlink[] outlinks = OutlinkExtractor.getOutlinks(text);
 
     // collect meta data
     Properties metadata = new Properties();

 

infrastructure at apache.org
ViewVC Help
Powered by ViewVC 1.1.26