Author: jnioche
Date: Fri Jul 16 15:02:45 2010
New Revision: 964817
URL: http://svn.apache.org/viewvc?rev=964817&view=rev
Log:
re-adapted nutch script to the class names used NutchBase
Modified:
nutch/branches/nutchbase/src/bin/nutch
Modified: nutch/branches/nutchbase/src/bin/nutch
URL:
http://svn.apache.org/viewvc/nutch/branches/nutchbase/src/bin/nutch?rev=964817&r1=964816&r2=964817&view=diff
==============================================================================
--- nutch/branches/nutchbase/src/bin/nutch (original)
+++ nutch/branches/nutchbase/src/bin/nutch Fri Jul 16 15:02:45 2010
@@ -32,31 +32,22 @@ done
if [ $# = 0 ]; then
echo "Usage: nutch [-core] COMMAND"
echo "where COMMAND is one of:"
- echo " crawl one-step crawler for intranets"
- echo " readdb read / dump crawl db"
- echo " convdb convert crawl db from pre-0.9 format"
- echo " mergedb merge crawldb-s, with optional filtering"
- echo " readlinkdb read / dump link db"
- echo " inject inject new urls into the database"
- echo " generate generate new segments to fetch from crawl db"
- echo " freegen generate new segments to fetch from text files"
- echo " fetch fetch a segment's pages"
- echo " parse parse a segment's pages"
- echo " readseg read / dump segment data"
- echo " mergesegs merge several segments, with optional filtering
and slicing"
- echo " updatedb update crawl db from segments after fetching"
- echo " invertlinks create a linkdb from parsed segments"
- 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 " plugin load a plugin and run one of its classes main()"
+# echo " crawl one-step crawler for intranets"
+ echo " inject inject new urls into the database"
+ echo " generate generate new segments to fetch from crawl db"
+ echo " fetch fetch URLs marked during generate"
+ echo " parse parse URLs marked during fetch"
+ echo " updatedb update web table after parsing"
+ echo " solrindex run the solr indexer on parsed segments and linkdb"
+ echo " solrdedup remove duplicates from solr"
+ echo " plugin load a plugin and run one of its classes main()"
echo " or"
- echo " CLASSNAME run the class named CLASSNAME"
+ echo " CLASSNAME run the class named CLASSNAME"
echo "Most commands print help when invoked w/o parameters."
echo ""
echo "Expert: -core option is for developers only. It avoids building the
job jar, "
- echo " instead it simply includes classes compiled with ant
compile-core. "
- echo " NOTE: this works only for jobs executed in 'local' mode"
+ echo " instead it simply includes classes compiled with ant compile-core. "
+ echo " NOTE: this works only for jobs executed in 'local' mode"
exit 1
fi
@@ -177,43 +168,25 @@ fi
# figure out which class to run
if [ "$COMMAND" = "crawl" ] ; then
- CLASS=org.apache.nutch.crawl.Crawl
+CLASS=org.apache.nutch.crawl.Crawl
elif [ "$COMMAND" = "inject" ] ; then
- CLASS=org.apache.nutch.crawl.Injector
+CLASS=org.apache.nutch.crawl.InjectorJob
elif [ "$COMMAND" = "generate" ] ; then
- CLASS=org.apache.nutch.crawl.Generator
-elif [ "$COMMAND" = "freegen" ] ; then
- CLASS=org.apache.nutch.tools.FreeGenerator
+CLASS=org.apache.nutch.crawl.GeneratorJob
elif [ "$COMMAND" = "fetch" ] ; then
- CLASS=org.apache.nutch.fetcher.Fetcher
+CLASS=org.apache.nutch.fetcher.FetcherJob
elif [ "$COMMAND" = "parse" ] ; then
- CLASS=org.apache.nutch.parse.ParseSegment
-elif [ "$COMMAND" = "readdb" ] ; then
- CLASS=org.apache.nutch.crawl.CrawlDbReader
-elif [ "$COMMAND" = "convdb" ] ; then
- CLASS=org.apache.nutch.tools.compat.CrawlDbConverter
-elif [ "$COMMAND" = "mergedb" ] ; then
- CLASS=org.apache.nutch.crawl.CrawlDbMerger
-elif [ "$COMMAND" = "readlinkdb" ] ; then
- CLASS=org.apache.nutch.crawl.LinkDbReader
-elif [ "$COMMAND" = "readseg" ] ; then
- CLASS=org.apache.nutch.segment.SegmentReader
-elif [ "$COMMAND" = "mergesegs" ] ; then
- CLASS=org.apache.nutch.segment.SegmentMerger
+CLASS=org.apache.nutch.parse.ParserJob
elif [ "$COMMAND" = "updatedb" ] ; then
- CLASS=org.apache.nutch.crawl.CrawlDb
-elif [ "$COMMAND" = "invertlinks" ] ; then
- CLASS=org.apache.nutch.crawl.LinkDb
-elif [ "$COMMAND" = "mergelinkdb" ] ; then
- CLASS=org.apache.nutch.crawl.LinkDbMerger
+CLASS=org.apache.nutch.crawl.DbUpdaterJob
elif [ "$COMMAND" = "solrindex" ] ; then
- CLASS=org.apache.nutch.indexer.solr.SolrIndexer
+CLASS=org.apache.nutch.indexer.solr.SolrIndexerJob
elif [ "$COMMAND" = "solrdedup" ] ; then
- CLASS=org.apache.nutch.indexer.solr.SolrDeleteDuplicates
+CLASS=org.apache.nutch.indexer.solr.SolrDeleteDuplicates
elif [ "$COMMAND" = "plugin" ] ; then
- CLASS=org.apache.nutch.plugin.PluginRepository
+CLASS=org.apache.nutch.plugin.PluginRepository
else
- CLASS=$COMMAND
+CLASS=$COMMAND
fi
# distributed mode
