Author: ogrisel
Date: Wed Sep 21 10:11:44 2011
New Revision: 1173555
URL: http://svn.apache.org/viewvc?rev=1173555&view=rev
Log:
STANBOL-323: clean images_en.nt and labels_de.nt file manually before importing
Modified:
incubator/stanbol/trunk/entityhub/indexing/dbpedia/fetch_prepare.sh
Modified: incubator/stanbol/trunk/entityhub/indexing/dbpedia/fetch_prepare.sh
URL:
http://svn.apache.org/viewvc/incubator/stanbol/trunk/entityhub/indexing/dbpedia/fetch_prepare.sh?rev=1173555&r1=1173554&r2=1173555&view=diff
==============================================================================
--- incubator/stanbol/trunk/entityhub/indexing/dbpedia/fetch_prepare.sh
(original)
+++ incubator/stanbol/trunk/entityhub/indexing/dbpedia/fetch_prepare.sh Wed Sep
21 10:11:44 2011
@@ -34,7 +34,6 @@ cd $WORKSPACE/indexing/resources/rdfdata
wget -c $DBPEDIA/dbpedia_3.7.owl.bz2
wget -c $DBPEDIA/en/instance_types_en.nt.bz2
wget -c $DBPEDIA/ar/labels_ar.nt.bz2
-wget -c $DBPEDIA/de/labels_de.nt.bz2
wget -c $DBPEDIA/en/labels_en.nt.bz2
wget -c $DBPEDIA/es/labels_es.nt.bz2
wget -c $DBPEDIA/fr/labels_fr.nt.bz2
@@ -51,10 +50,18 @@ wget -c $DBPEDIA/en/short_abstracts_en.n
if [ ! -f images_en.nt ]
then
wget -c $DBPEDIA/en/images_en.nt.bz2
- bzcat images_en.nt.bz2 | grep -v '\\' > images_en.nt
+ bzcat images_en.nt.bz2 | grep -v '\\\\' > images_en.nt
rm -f images_en.nt.bz2
fi
+# same problem for german labels
+if [ ! -f labels_de.nt ]
+then
+ wget -c $DBPEDIA/de/labels_de.nt.bz2
+ bzcat labels_de.nt.bz2 | grep -v '\\\\' > labels_de.nt
+ rm -f labels_de.nt.bz2
+fi
+
# Type specific attributes
wget -c $DBPEDIA/en/geo_coordinates_en.nt.bz2
wget -c $DBPEDIA/en/persondata_en.nt.bz2