[Archive-access-cvs] SF.net SVN: archive-access: [2343] trunk/archive-access/projects/nutchwax/ archive/conf/nutch-site.xml

[<bi...@us...>]

Revision: 2343
          http://archive-access.svn.sourceforge.net/archive-access/?rev=2343&view=rev
Author:   binzino
Date:     2008-06-28 17:20:16 -0700 (Sat, 28 Jun 2008)

Log Message:
-----------
Changed "archive-digest" to "digest" to match changes in NutchWax
code.  Added "exclusive" property to ConfigurableIndexingFilter
config.  Added explicit ordering of index filters so that ours is
called last so it can over-write metadata values: url, orig, digest.

Modified Paths:
--------------
    trunk/archive-access/projects/nutchwax/archive/conf/nutch-site.xml

Modified: trunk/archive-access/projects/nutchwax/archive/conf/nutch-site.xml
===================================================================
--- trunk/archive-access/projects/nutchwax/archive/conf/nutch-site.xml	2008-06-29 00:17:48 UTC (rev 2342)
+++ trunk/archive-access/projects/nutchwax/archive/conf/nutch-site.xml	2008-06-29 00:20:16 UTC (rev 2343)
@@ -10,21 +10,32 @@
   <!-- Add 'index-nutchwax' and 'query-nutchwax' to plugin list. -->
   <!-- Also, add 'parse-pdf' -->
   <!-- Remove 'urlfilter-regex' and 'normalizer-(pass|regex|basic)' -->
-  <value>protocol-http|parse-(text|html|js|pdf)|index-(basic|anchor|nutchwax)|query-(basic|site|url|nutchwax)|summary-basic|scoring-opic|urlfilter-nutchwax</value>
+  <value>protocol-http|parse-(text|html|js|pdf)|index-(basic|nutchwax)|query-(basic|site|url|nutchwax)|summary-basic|scoring-opic|urlfilter-nutchwax</value>
 </property>
 
 <property>
+  <name>indexingfilter.order</name>
+  <value>
+    org.apache.nutch.indexer.basic.BasicIndexingFilter
+    org.archive.nutchwax.index.ConfigurableIndexingFilter
+  </value>
+</property>
+
+<property>
   <!-- Configure the 'index-nutchwax' plugin.  Specify how the metadata fields added by the ArcsToSegment are mapped to the Lucene documents during indexing.
        The specifications here are of the form "src-key:lowercase:store:tokenize:dest-key"
        Where the only required part is the "src-key", the rest will assume the following defaults:
           lowercase = true
           store     = true
           tokenize  = false
+          exclusive = true
           dest-key  = src-key
     -->
   <name>nutchwax.filter.index</name>
   <value>
-    archive-digest:false
+    url:false:true:true
+    orig:false
+    digest:false
     arcname:false
     collection
     date
@@ -46,7 +57,7 @@
   <!-- We do *not* use this filter for handling "date" queries, there is a specific filter for that: DateQueryFilter -->
   <name>nutchwax.filter.query</name>
   <value>
-    raw:archive-digest:false
+    raw:digest:false
     raw:arcname:false
     group:collection
     group:type


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