You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@nutch.apache.org by ma...@apache.org on 2011/03/18 16:05:35 UTC
svn commit: r1082943 - in /nutch/branches/branch-1.3: CHANGES.txt
conf/log4j.properties src/bin/nutch
Author: markus
Date: Fri Mar 18 15:05:34 2011
New Revision: 1082943
URL: http://svn.apache.org/viewvc?rev=1082943&view=rev
Log:
NUTCH-963 Add support for deleting Solr documents with STATUS_DB_GONE in CrawlDB (Claudio Martella, markus)
Modified:
nutch/branches/branch-1.3/CHANGES.txt
nutch/branches/branch-1.3/conf/log4j.properties
nutch/branches/branch-1.3/src/bin/nutch
Modified: nutch/branches/branch-1.3/CHANGES.txt
URL: http://svn.apache.org/viewvc/nutch/branches/branch-1.3/CHANGES.txt?rev=1082943&r1=1082942&r2=1082943&view=diff
==============================================================================
--- nutch/branches/branch-1.3/CHANGES.txt (original)
+++ nutch/branches/branch-1.3/CHANGES.txt Fri Mar 18 15:05:34 2011
@@ -2,6 +2,8 @@ Nutch Change Log
Release 1.3 - Current Development
+* NUTCH-963 Add support for deleting Solr documents with STATUS_DB_GONE in CrawlDB (Claudio Martella, markus)
+
* NUTCH-825 Publish nutch artifacts to central maven repository (mattmann, jnioche)
* NUTCH-962 max. redirects not handled correctly: fetcher stops at max-1 redirects (Sebastian Nagel via ab)
Modified: nutch/branches/branch-1.3/conf/log4j.properties
URL: http://svn.apache.org/viewvc/nutch/branches/branch-1.3/conf/log4j.properties?rev=1082943&r1=1082942&r2=1082943&view=diff
==============================================================================
--- nutch/branches/branch-1.3/conf/log4j.properties (original)
+++ nutch/branches/branch-1.3/conf/log4j.properties Fri Mar 18 15:05:34 2011
@@ -24,6 +24,7 @@ log4j.logger.org.apache.nutch.crawl.Link
log4j.logger.org.apache.nutch.crawl.LinkDbMerger=INFO,cmdstdout
log4j.logger.org.apache.nutch.indexer.solr.SolrIndexer=INFO,cmdstdout
log4j.logger.org.apache.nutch.indexer.solr.SolrDeleteDuplicates=INFO,cmdstdout
+log4j.logger.org.apache.nutch.indexer.solr.SolrClean=INFO,cmdstdout
log4j.logger.org.apache.nutch=INFO
log4j.logger.org.apache.hadoop=WARN
Modified: nutch/branches/branch-1.3/src/bin/nutch
URL: http://svn.apache.org/viewvc/nutch/branches/branch-1.3/src/bin/nutch?rev=1082943&r1=1082942&r2=1082943&view=diff
==============================================================================
--- nutch/branches/branch-1.3/src/bin/nutch (original)
+++ nutch/branches/branch-1.3/src/bin/nutch Fri Mar 18 15:05:34 2011
@@ -49,6 +49,7 @@ if [ $# = 0 ]; then
echo " mergelinkdb merge linkdb-s, with optional filtering"
echo " solrindex run the solr indexer on parsed segments and linkdb"
echo " solrdedup remove duplicates from solr"
+ echo " solrclean remove HTTP 301 and 404 documents from solr"
echo " plugin load a plugin and run one of its classes main()"
echo " or"
echo " CLASSNAME run the class named CLASSNAME"
@@ -210,6 +211,8 @@ elif [ "$COMMAND" = "solrindex" ] ; then
CLASS=org.apache.nutch.indexer.solr.SolrIndexer
elif [ "$COMMAND" = "solrdedup" ] ; then
CLASS=org.apache.nutch.indexer.solr.SolrDeleteDuplicates
+elif [ "$COMMAND" = "solrclean" ] ; then
+ CLASS=org.apache.nutch.indexer.solr.SolrClean
elif [ "$COMMAND" = "plugin" ] ; then
CLASS=org.apache.nutch.plugin.PluginRepository
else