[Archive-access-cvs] SF.net SVN: archive-access:[2835] trunk/archive-access/projects/nutchwax/ archive/src/plugin/index-nutchwax/src/java/org/archive/nutchwax/index/ FieldSetter.java

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

Revision: 2835
          http://archive-access.svn.sourceforge.net/archive-access/?rev=2835&view=rev
Author:   binzino
Date:     2009-10-27 21:14:24 +0000 (Tue, 27 Oct 2009)

Log Message:
-----------
Updated to Nutch 1.0 API.

Modified Paths:
--------------
    trunk/archive-access/projects/nutchwax/archive/src/plugin/index-nutchwax/src/java/org/archive/nutchwax/index/FieldSetter.java

Modified: trunk/archive-access/projects/nutchwax/archive/src/plugin/index-nutchwax/src/java/org/archive/nutchwax/index/FieldSetter.java
===================================================================
--- trunk/archive-access/projects/nutchwax/archive/src/plugin/index-nutchwax/src/java/org/archive/nutchwax/index/FieldSetter.java	2009-10-26 23:02:50 UTC (rev 2834)
+++ trunk/archive-access/projects/nutchwax/archive/src/plugin/index-nutchwax/src/java/org/archive/nutchwax/index/FieldSetter.java	2009-10-27 21:14:24 UTC (rev 2835)
@@ -26,14 +26,14 @@
 
 import org.apache.commons.logging.Log;
 import org.apache.commons.logging.LogFactory;
-import org.apache.lucene.document.Document;
-import org.apache.lucene.document.Field;
 import org.apache.hadoop.conf.Configuration;
 import org.apache.hadoop.io.Text;
 import org.apache.nutch.crawl.CrawlDatum;
 import org.apache.nutch.crawl.Inlinks;
 import org.apache.nutch.indexer.IndexingException;
 import org.apache.nutch.indexer.IndexingFilter;
+import org.apache.nutch.indexer.NutchDocument;
+import org.apache.nutch.indexer.lucene.LuceneWriter;
 import org.apache.nutch.metadata.Metadata;
 import org.apache.nutch.parse.Parse;
 
@@ -152,7 +152,7 @@
    *   Remove field if specified value is <code>null</code>.
    * </p>
    */
-  public Document filter( Document doc, Parse parse, Text url, CrawlDatum datum, Inlinks inlinks )
+  public NutchDocument filter( NutchDocument doc, Parse parse, Text url, CrawlDatum datum, Inlinks inlinks )
     throws IndexingException
   {
     Metadata meta = parse.getData().getContentMeta();
@@ -160,20 +160,29 @@
     for ( FieldSetting setting : this.settings )
       {
         // First, remove the existing field.
-        doc.removeFields( setting.key );
+        doc.removeField( setting.key );
 
         // Add the value if it is given.
         if ( setting.value != null )
           {
-            doc.add( new Field( setting.key,
-                                setting.value,
-                                setting.store    ? Field.Store.YES : Field.Store.NO, 
-                                setting.tokenize ? Field.Index.TOKENIZED : Field.Index.UN_TOKENIZED ) );
+            doc.add( setting.key, setting.value );
           }
       }
 
     return doc;
   }
 
+  public void addIndexBackendOptions( Configuration conf ) 
+  {
+
+    for ( FieldSetting setting : this.settings )
+      {
+        LuceneWriter.addFieldOptions( setting.key,
+                                      setting.store ?    LuceneWriter.STORE.YES : LuceneWriter.STORE.NO,
+                                      setting.tokenize ? LuceneWriter.INDEX.TOKENIZED : LuceneWriter.INDEX.UNTOKENIZED, 
+                                      conf );
+      }
+
+  }
  
 }


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