Author: kwright
Date: Thu Sep 18 21:27:52 2014
New Revision: 1626090

URL: http://svn.apache.org/r1626090
Log:
Fix for CONNECTORS-1039.

Modified:
    manifoldcf/trunk/CHANGES.txt
    
manifoldcf/trunk/connectors/documentfilter/connector/src/main/java/org/apache/manifoldcf/agents/transformation/documentfilter/DocumentFilter.java

Modified: manifoldcf/trunk/CHANGES.txt
URL: 
http://svn.apache.org/viewvc/manifoldcf/trunk/CHANGES.txt?rev=1626090&r1=1626089&r2=1626090&view=diff
==============================================================================
--- manifoldcf/trunk/CHANGES.txt (original)
+++ manifoldcf/trunk/CHANGES.txt Thu Sep 18 21:27:52 2014
@@ -3,6 +3,10 @@ $Id$
 
 ======================= 2.0-dev =====================
 
+CONNECTORS-1039: Use a URL-centric way of getting the extension
+for document filtering.
+(David Morana, Karl Wright)
+
 CONNECTORS-1038: Handle multiple pool closes properly.
 (Karl Wright)
 

Modified: 
manifoldcf/trunk/connectors/documentfilter/connector/src/main/java/org/apache/manifoldcf/agents/transformation/documentfilter/DocumentFilter.java
URL: 
http://svn.apache.org/viewvc/manifoldcf/trunk/connectors/documentfilter/connector/src/main/java/org/apache/manifoldcf/agents/transformation/documentfilter/DocumentFilter.java?rev=1626090&r1=1626089&r2=1626090&view=diff
==============================================================================
--- 
manifoldcf/trunk/connectors/documentfilter/connector/src/main/java/org/apache/manifoldcf/agents/transformation/documentfilter/DocumentFilter.java
 (original)
+++ 
manifoldcf/trunk/connectors/documentfilter/connector/src/main/java/org/apache/manifoldcf/agents/transformation/documentfilter/DocumentFilter.java
 Thu Sep 18 21:27:52 2014
@@ -28,6 +28,7 @@ import org.apache.commons.io.FilenameUti
 
 import java.io.*;
 import java.util.*;
+import java.net.*;
 
 public class DocumentFilter extends 
org.apache.manifoldcf.agents.transformation.BaseTransformationConnector {
 
@@ -481,7 +482,17 @@ public class DocumentFilter extends org.
     }
     
     public boolean checkURLIndexable(String url) {
-      String extension = FilenameUtils.getExtension(url);
+      String extension = null;
+      try
+      {
+        String path = new URI(url).getPath();
+        if (path != null)
+          extension = FilenameUtils.getExtension(path);
+      }
+      catch (URISyntaxException e)
+      {
+        extension = FilenameUtils.getExtension(url);
+      }
       if (extension == null || extension.length() == 0)
         extension = ".";
       return extensions.contains(extension.toLowerCase(Locale.ROOT));


Reply via email to