Author: snagel
Date: Mon Mar 17 21:56:32 2014
New Revision: 1578620
URL: http://svn.apache.org/r1578620
Log:
NUTCH-1671 indexchecker to add digest field
Modified:
nutch/branches/2.x/CHANGES.txt
nutch/branches/2.x/src/java/org/apache/nutch/indexer/IndexingFiltersChecker.java
Modified: nutch/branches/2.x/CHANGES.txt
URL:
http://svn.apache.org/viewvc/nutch/branches/2.x/CHANGES.txt?rev=1578620&r1=1578619&r2=1578620&view=diff
==============================================================================
--- nutch/branches/2.x/CHANGES.txt (original)
+++ nutch/branches/2.x/CHANGES.txt Mon Mar 17 21:56:32 2014
@@ -2,6 +2,8 @@ Nutch Change Log
Current Development
+* NUTCH-1671 indexchecker to add digest field (snagel, lufeng)
+
* NUTCH-1645 Junit Test Case for Adaptive Fetch Schedule class (Yasin
Kılınç, lufeng, Sertac TURKEL via snagel)
* NUTCH-1478 Parse-metatags and index-metadata plugin for Nutch 2.x series
(kiran, Nguyen Manh Tien, Talat UYARER, Vangelis Karvounis via lewismc)
Modified:
nutch/branches/2.x/src/java/org/apache/nutch/indexer/IndexingFiltersChecker.java
URL:
http://svn.apache.org/viewvc/nutch/branches/2.x/src/java/org/apache/nutch/indexer/IndexingFiltersChecker.java?rev=1578620&r1=1578619&r2=1578620&view=diff
==============================================================================
---
nutch/branches/2.x/src/java/org/apache/nutch/indexer/IndexingFiltersChecker.java
(original)
+++
nutch/branches/2.x/src/java/org/apache/nutch/indexer/IndexingFiltersChecker.java
Mon Mar 17 21:56:32 2014
@@ -37,6 +37,7 @@ import org.apache.nutch.protocol.Protoco
import org.apache.nutch.protocol.ProtocolStatusUtils;
import org.apache.nutch.storage.WebPage;
import org.apache.nutch.util.NutchConfiguration;
+import org.apache.nutch.util.StringUtil;
import org.apache.nutch.util.URLUtil;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
@@ -122,6 +123,7 @@ public class IndexingFiltersChecker exte
}
NutchDocument doc = new NutchDocument();
+ doc.add("digest", StringUtil.toHexString(page.getSignature()));
try {
doc = indexers.filter(doc, url, page);