svn commit: r999181 - in /nutch/trunk: CHANGES.txt conf/nutch-default.xml src/plugin/index-more/src/java/org/apache/nutch/indexer/more/MoreIndexingFilter.java

[ma...@apache.org]

Author: mattmann
Date: Tue Sep 21 01:53:51 2010
New Revision: 999181

URL: http://svn.apache.org/viewvc?rev=999181&view=rev
Log:
- fix for NUTCH-901 Make index-more plug-in configurable

Modified:
    nutch/trunk/CHANGES.txt
    nutch/trunk/conf/nutch-default.xml
    nutch/trunk/src/plugin/index-more/src/java/org/apache/nutch/indexer/more/MoreIndexingFilter.java

Modified: nutch/trunk/CHANGES.txt
URL: http://svn.apache.org/viewvc/nutch/trunk/CHANGES.txt?rev=999181&r1=999180&r2=999181&view=diff
==============================================================================
--- nutch/trunk/CHANGES.txt (original)
+++ nutch/trunk/CHANGES.txt Tue Sep 21 01:53:51 2010
@@ -2,6 +2,8 @@ Nutch Change Log
 
 Release 2.0 - Current Development
 
+* NUTCH-901 Make index-more plug-in configurable (Markus Jelsma via mattmann)
+
 * NUTCH-862 HttpClient null pointer exception (Sebastian Nagel via ab)
 
 * NUTCH-904 "-resume" option is always processed as "false" in FetcherJob

Modified: nutch/trunk/conf/nutch-default.xml
URL: http://svn.apache.org/viewvc/nutch/trunk/conf/nutch-default.xml?rev=999181&r1=999180&r2=999181&view=diff
==============================================================================
--- nutch/trunk/conf/nutch-default.xml (original)
+++ nutch/trunk/conf/nutch-default.xml Tue Sep 21 01:53:51 2010
@@ -713,6 +713,19 @@
   </description>
 </property>
 
+
+<!-- moreindexingfilter plugin properties -->
+
+<property>
+  <name>moreIndexingFilter.indexMimeTypeParts</name>
+  <value>true</value>
+  <description>Determines whether the index-more plugin will split the mime-type
+  in sub parts, this requires the type field to be multi valued. Set to true for backward
+  compatibility. False will not split the mime-type.
+  </description>
+</property>
+
+
 <!-- URL normalizer properties -->
 
 <property>

Modified: nutch/trunk/src/plugin/index-more/src/java/org/apache/nutch/indexer/more/MoreIndexingFilter.java
URL: http://svn.apache.org/viewvc/nutch/trunk/src/plugin/index-more/src/java/org/apache/nutch/indexer/more/MoreIndexingFilter.java?rev=999181&r1=999180&r2=999181&view=diff
==============================================================================
--- nutch/trunk/src/plugin/index-more/src/java/org/apache/nutch/indexer/more/MoreIndexingFilter.java (original)
+++ nutch/trunk/src/plugin/index-more/src/java/org/apache/nutch/indexer/more/MoreIndexingFilter.java Tue Sep 21 01:53:51 2010
@@ -199,10 +199,13 @@ public class MoreIndexingFilter implemen
 
     doc.add("type", scontentType);
 
-    String[] parts = getParts(scontentType);
+    // Check if we need to split the content type in sub parts
+    if (conf.getBoolean("moreIndexingFilter.indexMimeTypeParts", true)) {
+      String[] parts = getParts(contentType);
 
-    for (String part : parts) {
-      doc.add("type", part);
+      for(String part: parts) {
+        doc.add("type", part);
+      }
     }
 
     // leave this for future improvement