You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@nutch.apache.org by jn...@apache.org on 2014/05/29 12:20:43 UTC

svn commit: r1598241 - in /nutch/trunk: CHANGES.txt src/java/org/apache/nutch/indexer/IndexingFiltersChecker.java

Author: jnioche
Date: Thu May 29 10:20:42 2014
New Revision: 1598241

URL: http://svn.apache.org/r1598241
Log:
 NUTCH-1758 IndexChecker to send document to IndexWriters (jnioche)

Modified:
    nutch/trunk/CHANGES.txt
    nutch/trunk/src/java/org/apache/nutch/indexer/IndexingFiltersChecker.java

Modified: nutch/trunk/CHANGES.txt
URL: http://svn.apache.org/viewvc/nutch/trunk/CHANGES.txt?rev=1598241&r1=1598240&r2=1598241&view=diff
==============================================================================
--- nutch/trunk/CHANGES.txt (original)
+++ nutch/trunk/CHANGES.txt Thu May 29 10:20:42 2014
@@ -2,6 +2,8 @@ Nutch Change Log
 
 Nutch Current Development
 
+* NUTCH-1758 IndexChecker to send document to IndexWriters (jnioche)
+
 * NUTCH-1786 CrawlDb should follow db.url.normalizers and db.url.filters (Diaa via markus)
 
 * NUTCH-1757 ParserChecker to take custom metadata as input (jnioche)

Modified: nutch/trunk/src/java/org/apache/nutch/indexer/IndexingFiltersChecker.java
URL: http://svn.apache.org/viewvc/nutch/trunk/src/java/org/apache/nutch/indexer/IndexingFiltersChecker.java?rev=1598241&r1=1598240&r2=1598241&view=diff
==============================================================================
--- nutch/trunk/src/java/org/apache/nutch/indexer/IndexingFiltersChecker.java (original)
+++ nutch/trunk/src/java/org/apache/nutch/indexer/IndexingFiltersChecker.java Thu May 29 10:20:42 2014
@@ -22,6 +22,7 @@ import java.util.List;
 import org.apache.hadoop.conf.Configuration;
 import org.apache.hadoop.conf.Configured;
 import org.apache.hadoop.io.Text;
+import org.apache.hadoop.mapred.JobConf;
 import org.apache.hadoop.util.Tool;
 import org.apache.hadoop.util.ToolRunner;
 import org.apache.nutch.crawl.CrawlDatum;
@@ -84,6 +85,8 @@ public class IndexingFiltersChecker exte
 
     ProtocolOutput output = protocol.getProtocolOutput(new Text(url), datum);
     
+    IndexWriters writers = new IndexWriters(getConf());
+    
     if (!output.getStatus().isSuccess()) {
       System.out.println("Fetch failed with protocol status: " + output.getStatus());
       return 0;
@@ -150,6 +153,13 @@ public class IndexingFiltersChecker exte
         }
       }
     }
+    
+    if (conf.getBoolean("doIndex", false) && doc!=null){
+    	writers.open(new JobConf(getConf()), "IndexingFilterChecker");
+    	writers.write(doc);
+    	writers.close();
+    }
+    
     return 0;
   }