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 2010/07/12 18:09:32 UTC
svn commit: r963328 - in /nutch/branches/branch-1.2: CHANGES.txt
src/java/org/apache/nutch/indexer/solr/SolrDeleteDuplicates.java
Author: jnioche
Date: Mon Jul 12 16:09:32 2010
New Revision: 963328
URL: http://svn.apache.org/viewvc?rev=963328&view=rev
Log:
https://issues.apache.org/jira/browse/NUTCH-850
Modified:
nutch/branches/branch-1.2/CHANGES.txt
nutch/branches/branch-1.2/src/java/org/apache/nutch/indexer/solr/SolrDeleteDuplicates.java
Modified: nutch/branches/branch-1.2/CHANGES.txt
URL: http://svn.apache.org/viewvc/nutch/branches/branch-1.2/CHANGES.txt?rev=963328&r1=963327&r2=963328&view=diff
==============================================================================
--- nutch/branches/branch-1.2/CHANGES.txt (original)
+++ nutch/branches/branch-1.2/CHANGES.txt Mon Jul 12 16:09:32 2010
@@ -2,6 +2,8 @@ Nutch Change Log
Release 1.2 - Current Development
+* NUTCH-850 SolrDeleteDuplicates needs to clone the SolrRecord objects (jnioche)
+
* NUTCH-838 Add timing information to all Tool classes (Jeroen van Vianen, mattmann)
* NUTCH-835 Document deduplication failed using MD5Signature (Sebastian Nagel via ab)
Modified: nutch/branches/branch-1.2/src/java/org/apache/nutch/indexer/solr/SolrDeleteDuplicates.java
URL: http://svn.apache.org/viewvc/nutch/branches/branch-1.2/src/java/org/apache/nutch/indexer/solr/SolrDeleteDuplicates.java?rev=963328&r1=963327&r2=963328&view=diff
==============================================================================
--- nutch/branches/branch-1.2/src/java/org/apache/nutch/indexer/solr/SolrDeleteDuplicates.java (original)
+++ nutch/branches/branch-1.2/src/java/org/apache/nutch/indexer/solr/SolrDeleteDuplicates.java Mon Jul 12 16:09:32 2010
@@ -99,6 +99,12 @@ Tool {
private String id;
public SolrRecord() { }
+
+ public SolrRecord(SolrRecord old) {
+ this.id = old.id;
+ this.boost = old.boost;
+ this.tstamp = old.tstamp;
+ }
public SolrRecord(String id, float boost, long tstamp) {
this.id = id;
@@ -309,14 +315,14 @@ Tool {
public void reduce(Text key, Iterator<SolrRecord> values,
OutputCollector<Text, SolrRecord> output, Reporter reporter)
throws IOException {
- SolrRecord recordToKeep = values.next();
+ SolrRecord recordToKeep = new SolrRecord(values.next());
while (values.hasNext()) {
SolrRecord solrRecord = values.next();
if (solrRecord.getBoost() > recordToKeep.getBoost() ||
(solrRecord.getBoost() == recordToKeep.getBoost() &&
solrRecord.getTstamp() > recordToKeep.getTstamp())) {
updateRequest.deleteById(recordToKeep.id);
- recordToKeep = solrRecord;
+ recordToKeep = new SolrRecord(solrRecord);
} else {
updateRequest.deleteById(solrRecord.id);
}