You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@nutch.apache.org by Apache Wiki <wi...@apache.org> on 2006/08/02 23:16:05 UTC
[Nutch Wiki] Update of "IntranetRecrawl" by MatthewHolt
Dear Wiki user,
You have subscribed to a wiki page or wiki category on "Nutch Wiki" for change notification.
The following page has been changed by MatthewHolt:
http://wiki.apache.org/nutch/IntranetRecrawl
------------------------------------------------------------------------------
linkdb_dir=$crawl_dir/linkdb
index_dir=$crawl_dir/index
+ # Sets the number of current segments for later clean up
+ seg_num=`ls $segments_dir | wc -l`
+
# The generate/fetch/update cycle
for ((i=1; i <= depth ; i++))
do
@@ -147, +150 @@
# Update segments
$nutch_dir/nutch invertlinks $linkdb_dir -dir $segments_dir
+ # Merge segments
+ mergesegs_dir=$crawl_dir/mergesegs_dir
+ $nutch_dir/nutch mergesegs $mergesegs_dir -dir $segments_dir
+ cp -R $mergesegs_dir/* $segments_dir
+ rm -rf $mergesegs_dir
+
# Index segments
new_indexes=$crawl_dir/newindexes
+ segment=`ls -d $segments_dir/* | tail -1`
- $nutch_dir/nutch index $new_indexes $webdb_dir $linkdb_dir $segments_dir/*
+ $nutch_dir/nutch index $new_indexes $webdb_dir $linkdb_dir $segment
# De-duplicate indexes
$nutch_dir/nutch dedup $new_indexes
@@ -163, +173 @@
# Clean up
rm -rf $new_indexes
+ # sleeps for 1 minute to make sure tomcat has released its lock on dir's
+ # before removing them
+ sleep 1m
+
+ echo "***Removing old segment directories that are no longer in use. If any of these error out it is not a problem, just used for clean up."
+
+ seg_num=`expr $seg_num + $depth`
+ for segment in `ls -dr $segments_dir/* | tail -$seg_num`
+ do
+ echo "Removing Segment: $segment"
+ rm -rf $segment
+ done
}}}